Compare commits
@@ -13,6 +13,7 @@ from hashlib import sha256
|
||||
from pathlib import Path
|
||||
import json
|
||||
from typing import Any
|
||||
from message_handoff import stable_event_id
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
@@ -55,13 +56,19 @@ class AgentEventBus:
|
||||
payload: dict[str, Any],
|
||||
correlation_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
event_id = "evt_" + sha256(
|
||||
json.dumps(
|
||||
{"kind": kind, "source": source, "summary": summary, "payload": payload},
|
||||
sort_keys=True,
|
||||
ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
).hexdigest()[:16]
|
||||
event_id = stable_event_id(
|
||||
source=source, target=target, message_type=kind, payload=payload,
|
||||
tenant_id=(payload.get('tenant_id') if isinstance(payload, dict) else None),
|
||||
user_id=(payload.get('user_id') if isinstance(payload, dict) else None),
|
||||
project_id=(payload.get('project_id') if isinstance(payload, dict) else None),
|
||||
conversation_id=(payload.get('conversation_id') if isinstance(payload, dict) else None),
|
||||
task_id=(payload.get('task_id') if isinstance(payload, dict) else None),
|
||||
run_id=(payload.get('run_id') if isinstance(payload, dict) else None),
|
||||
correlation_id=(payload.get('correlation_id') if isinstance(payload, dict) else None),
|
||||
causation_id=(payload.get('causation_id') if isinstance(payload, dict) else None),
|
||||
sequence=(payload.get('sequence') if isinstance(payload, dict) else None),
|
||||
idempotency_key=(payload.get('idempotency_key') if isinstance(payload, dict) else None),
|
||||
)
|
||||
event = AgentEvent(event_id, kind, source, target, summary, payload, correlation_id=correlation_id)
|
||||
self._write("pending", event.to_dict())
|
||||
self._audit("created", event.to_dict())
|
||||
|
||||
@@ -7,7 +7,7 @@ class AgentEventObservabilityBridge:
|
||||
def __init__(self, hooks: AgentObservabilityHooks | None = None):
|
||||
self.hooks = hooks or AgentObservabilityHooks()
|
||||
|
||||
def consume(self, event: dict):
|
||||
def consume(self, event: dict, *, actor=None, trace=None):
|
||||
kind = event.get("kind")
|
||||
payload = event.get("payload", {})
|
||||
if kind == "agent_started":
|
||||
@@ -16,6 +16,8 @@ class AgentEventObservabilityBridge:
|
||||
visible_scope=payload.get("scope", "self"),
|
||||
entry_agent=payload.get("agent", "unknown"),
|
||||
execution_id=event.get("id"),
|
||||
actor=actor,
|
||||
trace=trace,
|
||||
)
|
||||
if kind == "agent_delegated":
|
||||
return self.hooks.delegate(event["execution_id"], payload.get("agent", "unknown"))
|
||||
|
||||
@@ -31,6 +31,18 @@ class AgentExecutionRecord:
|
||||
status: str = "completed"
|
||||
started_at: str = field(default_factory=utc_now)
|
||||
ended_at: str = field(default_factory=utc_now)
|
||||
trace_id: str | None = None
|
||||
span_id: str | None = None
|
||||
parent_span_id: str | None = None
|
||||
correlation_id: str | None = None
|
||||
causation_id: str | None = None
|
||||
tenant_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
task_id: str | None = None
|
||||
claim_id: str | None = None
|
||||
run_id: str | None = None
|
||||
message_id: str | None = None
|
||||
|
||||
def to_dict(self):
|
||||
return asdict(self)
|
||||
|
||||
@@ -9,25 +9,49 @@ try:
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .agent_observability import AgentExecutionRecord
|
||||
from .agent_observability import AgentExecutionRecord, AgentObservability
|
||||
from .agent_observability_dashboard import AgentObservabilityDashboard
|
||||
from .agent_observability_store import AgentObservabilityStore
|
||||
from .trace_tool_credential_governance import GovernanceActor, TraceContext, authorize_scope
|
||||
|
||||
store = AgentObservabilityStore()
|
||||
dashboard = AgentObservabilityDashboard(store.load())
|
||||
|
||||
|
||||
def record_agent_execution(payload: dict[str, Any]):
|
||||
record = AgentExecutionRecord(**payload)
|
||||
def record_agent_execution(payload: dict[str, Any], *, actor: GovernanceActor | dict[str, Any] | None = None, trace: TraceContext | None = None):
|
||||
scoped = any(payload.get(name) is not None for name in (
|
||||
"trace_id", "span_id", "tenant_id", "project_id", "conversation_id", "task_id", "run_id"
|
||||
))
|
||||
values = dict(payload)
|
||||
if scoped:
|
||||
if actor is None or trace is None:
|
||||
raise RuntimeError("TRACE_ACTOR_CONTEXT_REQUIRED")
|
||||
trusted = GovernanceActor.from_value(actor)
|
||||
authorize_scope(trusted, trace.scope)
|
||||
bound = {
|
||||
"trace_id": trace.trace_id, "span_id": trace.span_id,
|
||||
"parent_span_id": trace.parent_span_id, "correlation_id": trace.correlation_id,
|
||||
"causation_id": trace.causation_id, "tenant_id": trace.scope.tenant_id,
|
||||
"user_id": trace.scope.user_id, "project_id": trace.scope.project_id,
|
||||
"conversation_id": trace.scope.conversation_id, "task_id": trace.task_id,
|
||||
"claim_id": trace.claim_id, "run_id": trace.scope.run_id, "message_id": trace.message_id,
|
||||
}
|
||||
for name, authoritative in bound.items():
|
||||
if values.get(name) not in (None, authoritative):
|
||||
raise RuntimeError("TRACE_SCOPE_MISMATCH_DENY:" + name)
|
||||
values[name] = authoritative
|
||||
record = AgentExecutionRecord(**values)
|
||||
return {"status": "ok", "record": store.append(record)}
|
||||
|
||||
|
||||
def get_agent_observability(user_id: str | None = None, group_id: str | None = None, role: str = "user"):
|
||||
records = store.query(user_id, group_id, role)
|
||||
def get_agent_observability(user_id: str | None = None, group_id: str | None = None, role: str = "user", *, actor: GovernanceActor | dict[str, Any] | None = None):
|
||||
records = store.query(user_id, group_id, role, actor=actor)
|
||||
visible = AgentObservability()
|
||||
visible.records = [AgentExecutionRecord(**record) for record in records]
|
||||
return {
|
||||
"status": "ok",
|
||||
"records": records,
|
||||
"summary": store.load().summary(user_id if role != "owner" else None),
|
||||
"summary": visible.summary(None),
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -14,6 +14,11 @@ from uuid import uuid4
|
||||
|
||||
from .agent_observability import AgentExecutionRecord
|
||||
from .agent_observability_store import AgentObservabilityStore
|
||||
from .trace_tool_credential_governance import (
|
||||
GovernanceActor,
|
||||
TraceContext,
|
||||
authorize_scope,
|
||||
)
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
@@ -36,6 +41,7 @@ class AgentRunContext:
|
||||
input_tokens: int = 0
|
||||
output_tokens: int = 0
|
||||
status: str = "running"
|
||||
trace: TraceContext | None = None
|
||||
|
||||
def delegate(self, agent_name: str) -> None:
|
||||
if agent_name not in self.path:
|
||||
@@ -59,7 +65,19 @@ class AgentObservabilityHooks:
|
||||
visible_scope: str,
|
||||
entry_agent: str,
|
||||
execution_id: str | None = None,
|
||||
*,
|
||||
actor: GovernanceActor | dict[str, Any] | None = None,
|
||||
trace: TraceContext | None = None,
|
||||
) -> dict[str, Any]:
|
||||
if execution_id is not None and execution_id in self.active:
|
||||
raise RuntimeError("OBSERVABILITY_EXECUTION_CONFLICT")
|
||||
if trace is not None:
|
||||
if actor is None:
|
||||
raise RuntimeError("TRACE_ACTOR_CONTEXT_REQUIRED")
|
||||
trusted_actor = GovernanceActor.from_value(actor)
|
||||
authorize_scope(trusted_actor, trace.scope)
|
||||
if trace.scope.user_id is not None and trace.scope.user_id != user_id:
|
||||
raise RuntimeError("TRACE_SCOPE_MISMATCH_DENY:user_id")
|
||||
run = AgentRunContext(
|
||||
execution_id=execution_id or f"exec_{uuid4().hex[:12]}",
|
||||
user_id=user_id,
|
||||
@@ -67,6 +85,7 @@ class AgentObservabilityHooks:
|
||||
entry_agent=entry_agent,
|
||||
path=[entry_agent],
|
||||
used_hermes=entry_agent.lower() == "hermes",
|
||||
trace=trace,
|
||||
)
|
||||
self.active[run.execution_id] = run
|
||||
return {"status": "started", "execution_id": run.execution_id, "run": run.__dict__}
|
||||
@@ -106,6 +125,18 @@ class AgentObservabilityHooks:
|
||||
status=status,
|
||||
started_at=run.started_at,
|
||||
ended_at=ended_at,
|
||||
trace_id=run.trace.trace_id if run.trace else None,
|
||||
span_id=run.trace.span_id if run.trace else None,
|
||||
parent_span_id=run.trace.parent_span_id if run.trace else None,
|
||||
correlation_id=run.trace.correlation_id if run.trace else None,
|
||||
causation_id=run.trace.causation_id if run.trace else None,
|
||||
tenant_id=run.trace.scope.tenant_id if run.trace else None,
|
||||
project_id=run.trace.scope.project_id if run.trace else None,
|
||||
conversation_id=run.trace.scope.conversation_id if run.trace else None,
|
||||
task_id=run.trace.task_id if run.trace else None,
|
||||
claim_id=run.trace.claim_id if run.trace else None,
|
||||
run_id=run.trace.scope.run_id if run.trace else None,
|
||||
message_id=run.trace.message_id if run.trace else None,
|
||||
)
|
||||
return {"status": "stored", "record": self.store.append(record)}
|
||||
|
||||
|
||||
@@ -12,6 +12,12 @@ from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from .agent_observability import AgentExecutionRecord, AgentObservability
|
||||
from .trace_tool_credential_governance import (
|
||||
GovernanceActor,
|
||||
GovernanceError,
|
||||
GovernanceScope,
|
||||
authorize_scope,
|
||||
)
|
||||
|
||||
|
||||
class AgentObservabilityStore:
|
||||
@@ -23,6 +29,11 @@ class AgentObservabilityStore:
|
||||
def append(self, record: AgentExecutionRecord) -> dict[str, Any]:
|
||||
path = self.records_dir / f"{record.execution_id}.json"
|
||||
data = record.to_dict()
|
||||
if path.exists():
|
||||
existing = json.loads(path.read_text(encoding="utf-8"))
|
||||
if existing == data:
|
||||
return existing
|
||||
raise RuntimeError("OBSERVABILITY_EXECUTION_CONFLICT")
|
||||
path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
return data
|
||||
|
||||
@@ -33,8 +44,36 @@ class AgentObservabilityStore:
|
||||
observability.records.append(AgentExecutionRecord(**raw))
|
||||
return observability
|
||||
|
||||
def query(self, user_id: str | None = None, group_id: str | None = None, role: str = "user") -> list[dict[str, Any]]:
|
||||
def query(self, user_id: str | None = None, group_id: str | None = None, role: str = "user", *, actor: GovernanceActor | dict[str, Any] | None = None) -> list[dict[str, Any]]:
|
||||
records = [record.to_dict() for record in self.load().records]
|
||||
scoped = [record for record in records if record.get("tenant_id") is not None]
|
||||
legacy = [record for record in records if record.get("tenant_id") is None]
|
||||
if actor is not None:
|
||||
trusted = GovernanceActor.from_value(actor)
|
||||
visible: list[dict[str, Any]] = []
|
||||
for record in scoped:
|
||||
try:
|
||||
authorize_scope(
|
||||
trusted,
|
||||
GovernanceScope(
|
||||
"tenant",
|
||||
tenant_id=record.get("tenant_id"),
|
||||
user_id=record.get("user_id"),
|
||||
project_id=record.get("project_id"),
|
||||
conversation_id=record.get("conversation_id"),
|
||||
run_id=record.get("run_id"),
|
||||
),
|
||||
)
|
||||
except GovernanceError:
|
||||
continue
|
||||
visible.append(record)
|
||||
if trusted.privileged:
|
||||
visible.extend(legacy)
|
||||
else:
|
||||
visible.extend(record for record in legacy if record.get("user_id") == trusted.scope.user_id)
|
||||
return visible
|
||||
# Caller-supplied role remains a legacy compatibility path only.
|
||||
records = legacy
|
||||
if role == "owner":
|
||||
return records
|
||||
if role == "group_admin" and group_id:
|
||||
|
||||
@@ -0,0 +1,315 @@
|
||||
#!/usr/bin/env python3
|
||||
"""HTTP API for AIOS external-agent online task distribution.
|
||||
|
||||
The service is intended to bind to loopback and be published through the
|
||||
existing TLS reverse proxy. Control operations use a server-managed control
|
||||
Bearer token. Agents receive individual Bearer tokens at registration; only
|
||||
token hashes are persisted.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import hmac
|
||||
import json
|
||||
import os
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
import re
|
||||
from typing import Any, Mapping
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from aios_agent_task_protocol import TaskProtocolError, TaskStore
|
||||
|
||||
|
||||
MAX_BODY = 1024 * 1024
|
||||
TASK_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class APIConfig:
|
||||
db_path: Path
|
||||
control_token_path: Path
|
||||
host: str = "127.0.0.1"
|
||||
port: int = 18940
|
||||
token_pepper: str = ""
|
||||
|
||||
@classmethod
|
||||
def from_env(cls) -> "APIConfig":
|
||||
return cls(
|
||||
db_path=Path(os.getenv(
|
||||
"AIOS_AGENT_TASK_DB",
|
||||
"/var/lib/aios-agent-task/state.sqlite3",
|
||||
)),
|
||||
control_token_path=Path(os.getenv(
|
||||
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
|
||||
"/run/credentials/aios-agent-task-api.service/control_token",
|
||||
)),
|
||||
host=os.getenv("AIOS_AGENT_TASK_HOST", "127.0.0.1"),
|
||||
port=int(os.getenv("AIOS_AGENT_TASK_PORT", "18940")),
|
||||
token_pepper=os.getenv("AIOS_AGENT_TASK_TOKEN_PEPPER", ""),
|
||||
)
|
||||
|
||||
|
||||
class AgentTaskApplication:
|
||||
def __init__(self, config: APIConfig) -> None:
|
||||
self.config = config
|
||||
self.store = TaskStore(
|
||||
config.db_path,
|
||||
token_pepper=config.token_pepper,
|
||||
)
|
||||
|
||||
def _control_token(self) -> str:
|
||||
path = self.config.control_token_path
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise TaskProtocolError("CONTROL_CREDENTIAL_UNAVAILABLE", 503)
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 32:
|
||||
raise TaskProtocolError("CONTROL_CREDENTIAL_INVALID", 503)
|
||||
return value
|
||||
|
||||
@staticmethod
|
||||
def _bearer(headers: Mapping[str, str]) -> str:
|
||||
value = str(headers.get("Authorization") or "")
|
||||
if not value.startswith("Bearer "):
|
||||
return ""
|
||||
return value[7:].strip()
|
||||
|
||||
def authenticate_control(self, headers: Mapping[str, str]) -> None:
|
||||
supplied = self._bearer(headers)
|
||||
expected = self._control_token()
|
||||
if not supplied or not hmac.compare_digest(supplied, expected):
|
||||
raise TaskProtocolError("UNAUTHORIZED", 401)
|
||||
|
||||
def authenticate_agent(self, headers: Mapping[str, str]) -> dict[str, Any]:
|
||||
return self.store.authenticate_agent(self._bearer(headers))
|
||||
|
||||
def principal(self, headers: Mapping[str, str]) -> tuple[str, dict[str, Any] | None]:
|
||||
supplied = self._bearer(headers)
|
||||
if not supplied:
|
||||
raise TaskProtocolError("UNAUTHORIZED", 401)
|
||||
try:
|
||||
expected = self._control_token()
|
||||
except TaskProtocolError:
|
||||
expected = ""
|
||||
if expected and hmac.compare_digest(supplied, expected):
|
||||
return "control", None
|
||||
return "agent", self.store.authenticate_agent(supplied)
|
||||
|
||||
def health(self) -> dict[str, Any]:
|
||||
return {
|
||||
"status": "ok",
|
||||
"schema": "aios.agent-task.v1",
|
||||
"task_states": [
|
||||
"QUEUED", "CLAIMED", "RUNNING", "VERIFYING",
|
||||
"SUCCEEDED", "FAILED", "EXPIRED", "CANCELLED",
|
||||
],
|
||||
"lease_recovery": True,
|
||||
"atomic_claim": True,
|
||||
"idempotent_result_submission": True,
|
||||
"server_side_verification_required": True,
|
||||
"plaintext_credentials_persisted": False,
|
||||
}
|
||||
|
||||
def register_agent(self, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
self.authenticate_control(headers)
|
||||
return self.store.register_agent(
|
||||
agent_id=str(body.get("agent_id") or ""),
|
||||
agent_type=str(body.get("agent_type") or ""),
|
||||
agent_version=str(body.get("agent_version") or ""),
|
||||
capabilities=body.get("capabilities") or [],
|
||||
metadata=body.get("metadata") if isinstance(body.get("metadata"), Mapping) else {},
|
||||
)
|
||||
|
||||
def create_task(self, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
self.authenticate_control(headers)
|
||||
return self.store.create_task(
|
||||
task_id=str(body.get("task_id") or "") or None,
|
||||
goal=str(body.get("goal") or ""),
|
||||
instructions=str(body.get("instructions") or ""),
|
||||
success_criteria=body.get("success_criteria"),
|
||||
required_capabilities=body.get("required_capabilities") or [],
|
||||
constraints=body.get("constraints") if isinstance(body.get("constraints"), Mapping) else {},
|
||||
metadata=body.get("metadata") if isinstance(body.get("metadata"), Mapping) else {},
|
||||
deadline=str(body.get("deadline") or "") or None,
|
||||
priority=body.get("priority", 0),
|
||||
max_attempts=body.get("max_attempts", 3),
|
||||
idempotency_key=str(body.get("idempotency_key") or ""),
|
||||
)
|
||||
|
||||
def poll(self, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
agent = self.authenticate_agent(headers)
|
||||
tasks = self.store.poll_tasks(
|
||||
agent_id=agent["agent_id"],
|
||||
limit=int(body.get("limit", 20)),
|
||||
)
|
||||
return {"agent_id": agent["agent_id"], "tasks": tasks}
|
||||
|
||||
def claim(self, task_id: str, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
agent = self.authenticate_agent(headers)
|
||||
return self.store.claim_task(
|
||||
task_id=task_id,
|
||||
agent_id=agent["agent_id"],
|
||||
lease_seconds=int(body.get("lease_seconds", 300)),
|
||||
)
|
||||
|
||||
def heartbeat(self, task_id: str, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
agent = self.authenticate_agent(headers)
|
||||
return self.store.heartbeat(
|
||||
task_id=task_id,
|
||||
agent_id=agent["agent_id"],
|
||||
lease_token=str(body.get("lease_token") or ""),
|
||||
progress=body.get("progress") if isinstance(body.get("progress"), Mapping) else {},
|
||||
lease_seconds=int(body.get("lease_seconds", 300)),
|
||||
)
|
||||
|
||||
def result(self, task_id: str, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
agent = self.authenticate_agent(headers)
|
||||
result = body.get("result")
|
||||
if not isinstance(result, Mapping):
|
||||
raise TaskProtocolError("RESULT_INVALID", 400)
|
||||
return self.store.submit_result(
|
||||
task_id=task_id,
|
||||
agent_id=agent["agent_id"],
|
||||
lease_token=str(body.get("lease_token") or ""),
|
||||
idempotency_key=str(body.get("idempotency_key") or ""),
|
||||
result=result,
|
||||
)
|
||||
|
||||
def verify(self, task_id: str, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
self.authenticate_control(headers)
|
||||
return self.store.verify_task(
|
||||
task_id=task_id,
|
||||
decision=str(body.get("decision") or ""),
|
||||
verification=body.get("verification") if isinstance(body.get("verification"), Mapping) else {},
|
||||
)
|
||||
|
||||
def cancel(self, task_id: str, headers: Mapping[str, str], body: Mapping[str, Any]) -> dict[str, Any]:
|
||||
self.authenticate_control(headers)
|
||||
return self.store.cancel_task(task_id=task_id, reason=str(body.get("reason") or ""))
|
||||
|
||||
def get_task(self, task_id: str, headers: Mapping[str, str]) -> dict[str, Any]:
|
||||
kind, agent = self.principal(headers)
|
||||
task = self.store.get_task(task_id)
|
||||
if kind == "agent" and task.get("claimed_by") != agent["agent_id"]:
|
||||
raise TaskProtocolError("FORBIDDEN", 403)
|
||||
return task
|
||||
|
||||
def events(self, task_id: str, headers: Mapping[str, str]) -> dict[str, Any]:
|
||||
self.authenticate_control(headers)
|
||||
return {"task_id": task_id, "events": self.store.get_events(task_id)}
|
||||
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
app: AgentTaskApplication | None = None
|
||||
server_version = "AIOSAgentTaskAPI/1"
|
||||
|
||||
def log_message(self, _format: str, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def _headers(self) -> dict[str, str]:
|
||||
return {key: value for key, value in self.headers.items()}
|
||||
|
||||
def _json(self, value: Any, status: int = 200) -> None:
|
||||
payload = json.dumps(value, ensure_ascii=False, sort_keys=True).encode("utf-8")
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("Content-Length", str(len(payload)))
|
||||
self.end_headers()
|
||||
self.wfile.write(payload)
|
||||
|
||||
def _body(self) -> dict[str, Any]:
|
||||
try:
|
||||
size = int(self.headers.get("Content-Length", "0"))
|
||||
except ValueError as exc:
|
||||
raise TaskProtocolError("CONTENT_LENGTH_INVALID", 400) from exc
|
||||
if size < 0 or size > MAX_BODY:
|
||||
raise TaskProtocolError("REQUEST_TOO_LARGE", 413)
|
||||
raw = self.rfile.read(size) if size else b"{}"
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
raise TaskProtocolError("JSON_INVALID", 400) from exc
|
||||
if not isinstance(value, dict):
|
||||
raise TaskProtocolError("JSON_OBJECT_REQUIRED", 400)
|
||||
return value
|
||||
|
||||
@staticmethod
|
||||
def _task_route(path: str) -> tuple[str, str | None]:
|
||||
match = re.fullmatch(
|
||||
r"/v1/tasks/([A-Za-z0-9][A-Za-z0-9._:-]{2,179})(?:/(claim|heartbeat|result|verify|cancel|events))?",
|
||||
path,
|
||||
)
|
||||
if match:
|
||||
return match.group(1), match.group(2)
|
||||
return "", None
|
||||
|
||||
def _run(self, callback) -> None:
|
||||
try:
|
||||
callback()
|
||||
except TaskProtocolError as exc:
|
||||
self._json({"error": exc.code}, exc.http_status)
|
||||
except Exception as exc:
|
||||
self._json({"error": "INTERNAL_ERROR", "detail": type(exc).__name__}, 500)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
def action() -> None:
|
||||
if self.app is None:
|
||||
raise TaskProtocolError("SERVICE_UNAVAILABLE", 503)
|
||||
path = urlparse(self.path).path.rstrip("/") or "/"
|
||||
if path == "/health":
|
||||
self._json(self.app.health())
|
||||
return
|
||||
task_id, suffix = self._task_route(path)
|
||||
if task_id and suffix is None:
|
||||
self._json(self.app.get_task(task_id, self._headers()))
|
||||
return
|
||||
if task_id and suffix == "events":
|
||||
self._json(self.app.events(task_id, self._headers()))
|
||||
return
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
self._run(action)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
def action() -> None:
|
||||
if self.app is None:
|
||||
raise TaskProtocolError("SERVICE_UNAVAILABLE", 503)
|
||||
path = urlparse(self.path).path.rstrip("/") or "/"
|
||||
body = self._body()
|
||||
if path == "/v1/agents/register":
|
||||
self._json(self.app.register_agent(self._headers(), body), 201)
|
||||
return
|
||||
if path == "/v1/tasks":
|
||||
self._json(self.app.create_task(self._headers(), body), 201)
|
||||
return
|
||||
if path == "/v1/tasks/poll":
|
||||
self._json(self.app.poll(self._headers(), body))
|
||||
return
|
||||
task_id, suffix = self._task_route(path)
|
||||
if not task_id:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
if suffix == "claim":
|
||||
self._json(self.app.claim(task_id, self._headers(), body))
|
||||
elif suffix == "heartbeat":
|
||||
self._json(self.app.heartbeat(task_id, self._headers(), body))
|
||||
elif suffix == "result":
|
||||
self._json(self.app.result(task_id, self._headers(), body))
|
||||
elif suffix == "verify":
|
||||
self._json(self.app.verify(task_id, self._headers(), body))
|
||||
elif suffix == "cancel":
|
||||
self._json(self.app.cancel(task_id, self._headers(), body))
|
||||
else:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
self._run(action)
|
||||
|
||||
|
||||
def serve(config: APIConfig | None = None) -> None:
|
||||
config = config or APIConfig.from_env()
|
||||
application = AgentTaskApplication(config)
|
||||
Handler.app = application
|
||||
ThreadingHTTPServer((config.host, config.port), Handler).serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
@@ -0,0 +1,722 @@
|
||||
"""Owner-controlled CAS-bound execution-envelope rebind for Online Agent Tasks.
|
||||
|
||||
This service exists for a narrow recovery case: a Task was projected/claimed with a read-only
|
||||
source_capture envelope before its already-registered deterministic plan became authoritative.
|
||||
|
||||
It never creates Tasks/Jobs/branches and never accepts arbitrary metadata patches. It only replaces
|
||||
metadata.execution + the derived execution_projection for the same governed binding, after an
|
||||
official NEEDS_REWORK transition has returned the Task to QUEUED with no active lease.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sqlite3
|
||||
from typing import Any, Callable, Mapping, Sequence
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
from aios_online_agent_execution import (
|
||||
GovernedExecutionBinding,
|
||||
validate_execution_envelope,
|
||||
)
|
||||
|
||||
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
|
||||
SHA_RE = re.compile(r"^[0-9a-f]{64}$")
|
||||
MAX_BODY = 64 * 1024
|
||||
AUTHORIZATION_ID_ENV = "AIOS_AGENT_TASK_EXECUTION_REBIND_AUTHORIZATION_ID"
|
||||
|
||||
|
||||
class ExecutionRebindError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 409) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
def _canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value, sort_keys=True, separators=(",", ":"), ensure_ascii=False
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def _sha(value: object) -> str:
|
||||
return hashlib.sha256(_canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def _now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def _require_string(
|
||||
value: object,
|
||||
code: str,
|
||||
pattern: re.Pattern[str] | None = None,
|
||||
) -> str:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
raise ExecutionRebindError(code, 400)
|
||||
value = value.strip()
|
||||
if pattern is not None and pattern.fullmatch(value) is None:
|
||||
raise ExecutionRebindError(code, 400)
|
||||
return value
|
||||
|
||||
|
||||
def _required_authorization_id() -> str:
|
||||
value = os.environ.get(AUTHORIZATION_ID_ENV, "").strip()
|
||||
if not value:
|
||||
raise RuntimeError("TASK_EXECUTION_REBIND_AUTHORIZATION_ID_MISSING")
|
||||
if KEY_RE.fullmatch(value) is None:
|
||||
raise RuntimeError("TASK_EXECUTION_REBIND_AUTHORIZATION_ID_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecutionRebindRequest:
|
||||
expected_status: str
|
||||
expected_revision: int
|
||||
expected_attempt: int
|
||||
previous_verification_sha256: str
|
||||
expected_old_execution_digest: str
|
||||
expected_new_execution_digest: str
|
||||
authorization_id: str
|
||||
idempotency_key: str
|
||||
reason: str
|
||||
|
||||
@classmethod
|
||||
def from_mapping(cls, value: Mapping[str, Any]) -> "ExecutionRebindRequest":
|
||||
allowed = {
|
||||
"expected_status",
|
||||
"expected_revision",
|
||||
"expected_attempt",
|
||||
"previous_verification_sha256",
|
||||
"expected_old_execution_digest",
|
||||
"expected_new_execution_digest",
|
||||
"authorization_id",
|
||||
"idempotency_key",
|
||||
"reason",
|
||||
}
|
||||
if set(value) != allowed:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_FIELDS_INVALID", 400)
|
||||
|
||||
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
|
||||
if status != "QUEUED":
|
||||
raise ExecutionRebindError("EXPECTED_STATUS_INVALID", 400)
|
||||
|
||||
revision = value["expected_revision"]
|
||||
attempt = value["expected_attempt"]
|
||||
if (
|
||||
not isinstance(revision, int)
|
||||
or isinstance(revision, bool)
|
||||
or revision < 0
|
||||
or not isinstance(attempt, int)
|
||||
or isinstance(attempt, bool)
|
||||
or attempt < 1
|
||||
):
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_INTEGER_INVALID", 400)
|
||||
|
||||
verification = _require_string(
|
||||
value["previous_verification_sha256"], "VERIFICATION_SHA256_INVALID"
|
||||
)
|
||||
old_digest = _require_string(
|
||||
value["expected_old_execution_digest"], "OLD_EXECUTION_DIGEST_INVALID"
|
||||
)
|
||||
new_digest = _require_string(
|
||||
value["expected_new_execution_digest"], "NEW_EXECUTION_DIGEST_INVALID"
|
||||
)
|
||||
for digest, code in (
|
||||
(verification, "VERIFICATION_SHA256_INVALID"),
|
||||
(old_digest, "OLD_EXECUTION_DIGEST_INVALID"),
|
||||
(new_digest, "NEW_EXECUTION_DIGEST_INVALID"),
|
||||
):
|
||||
if SHA_RE.fullmatch(digest) is None:
|
||||
raise ExecutionRebindError(code, 400)
|
||||
if old_digest == new_digest:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_DIGEST_UNCHANGED", 400)
|
||||
|
||||
authorization = _require_string(
|
||||
value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE
|
||||
)
|
||||
key = _require_string(value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE)
|
||||
reason = _require_string(value["reason"], "EXECUTION_REBIND_REASON_INVALID")
|
||||
if len(reason) > 512:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_REASON_INVALID", 400)
|
||||
|
||||
return cls(
|
||||
status,
|
||||
revision,
|
||||
attempt,
|
||||
verification,
|
||||
old_digest,
|
||||
new_digest,
|
||||
authorization,
|
||||
key,
|
||||
reason,
|
||||
)
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return {
|
||||
"expected_status": self.expected_status,
|
||||
"expected_revision": self.expected_revision,
|
||||
"expected_attempt": self.expected_attempt,
|
||||
"previous_verification_sha256": self.previous_verification_sha256,
|
||||
"expected_old_execution_digest": self.expected_old_execution_digest,
|
||||
"expected_new_execution_digest": self.expected_new_execution_digest,
|
||||
"authorization_id": self.authorization_id,
|
||||
"idempotency_key": self.idempotency_key,
|
||||
"reason": self.reason,
|
||||
}
|
||||
|
||||
|
||||
class CanonicalBridgeExecutionResolver:
|
||||
"""Resolve the already-registered plan from the canonical governed Bridge."""
|
||||
|
||||
def __init__(self, base_url: str, control_token: str) -> None:
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.control_token = control_token
|
||||
|
||||
def __call__(
|
||||
self,
|
||||
task_id: str,
|
||||
required_capabilities: Sequence[str],
|
||||
) -> dict[str, Any]:
|
||||
body = json.dumps(
|
||||
{
|
||||
"task_id": task_id,
|
||||
"required_capabilities": list(required_capabilities),
|
||||
},
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
request = urllib.request.Request(
|
||||
self.base_url + "/v2/execution-envelope",
|
||||
method="POST",
|
||||
data=body,
|
||||
headers={
|
||||
"Authorization": "Bearer " + self.control_token,
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "application/json",
|
||||
},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=15) as response:
|
||||
raw = response.read()
|
||||
status = response.status
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw = exc.read()
|
||||
status = exc.code
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
raise ExecutionRebindError("CANONICAL_EXECUTION_RESPONSE_INVALID", 502) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise ExecutionRebindError("CANONICAL_EXECUTION_RESPONSE_INVALID", 502)
|
||||
if status != 200:
|
||||
raise ExecutionRebindError(
|
||||
str(value.get("error") or "CANONICAL_EXECUTION_RESOLUTION_FAILED"),
|
||||
502 if status >= 500 else 409,
|
||||
)
|
||||
return dict(value)
|
||||
|
||||
|
||||
class ExecutionRebindStore:
|
||||
"""Official owner-controlled mutation with CAS, plan resolution and durable audit."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
db_path: Path,
|
||||
resolver: Callable[[str, Sequence[str]], Mapping[str, Any]],
|
||||
) -> None:
|
||||
self.db_path = Path(db_path)
|
||||
self.resolver = resolver
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.db_path, timeout=30.0)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA busy_timeout=30000")
|
||||
return connection
|
||||
|
||||
@staticmethod
|
||||
def _columns(
|
||||
connection: sqlite3.Connection,
|
||||
table: str,
|
||||
) -> dict[str, sqlite3.Row]:
|
||||
return {
|
||||
str(row["name"]): row
|
||||
for row in connection.execute(f'PRAGMA table_info("{table}")')
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _json_value(raw: object, code: str) -> dict[str, Any]:
|
||||
if isinstance(raw, Mapping):
|
||||
return dict(raw)
|
||||
if not isinstance(raw, str):
|
||||
raise ExecutionRebindError(code, 409)
|
||||
try:
|
||||
value = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise ExecutionRebindError(code, 409) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise ExecutionRebindError(code, 409)
|
||||
return dict(value)
|
||||
|
||||
@staticmethod
|
||||
def _verification_hash(raw: object) -> str:
|
||||
if raw in (None, ""):
|
||||
value: object = {}
|
||||
elif isinstance(raw, str):
|
||||
try:
|
||||
value = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise ExecutionRebindError("TASK_VERIFICATION_INVALID", 409) from exc
|
||||
else:
|
||||
value = raw
|
||||
return _sha(value)
|
||||
|
||||
@staticmethod
|
||||
def _metadata_column(columns: Mapping[str, sqlite3.Row]) -> str:
|
||||
for name in ("metadata_json", "metadata"):
|
||||
if name in columns:
|
||||
return name
|
||||
raise ExecutionRebindError("TASK_METADATA_SCHEMA_UNSUPPORTED", 503)
|
||||
|
||||
@staticmethod
|
||||
def _required_capabilities(
|
||||
task: sqlite3.Row,
|
||||
columns: Mapping[str, sqlite3.Row],
|
||||
old_execution: Mapping[str, Any],
|
||||
) -> list[str]:
|
||||
for field in ("required_capabilities_json", "required_capabilities"):
|
||||
if field not in columns:
|
||||
continue
|
||||
raw = task[field]
|
||||
if raw in (None, ""):
|
||||
continue
|
||||
if isinstance(raw, str):
|
||||
try:
|
||||
value = json.loads(raw)
|
||||
except json.JSONDecodeError:
|
||||
value = [item for item in raw.split(",") if item.strip()]
|
||||
else:
|
||||
value = raw
|
||||
if isinstance(value, list) and all(isinstance(item, str) for item in value):
|
||||
return [item.strip() for item in value if item.strip()]
|
||||
value = old_execution.get("capability_scope")
|
||||
if isinstance(value, list) and all(isinstance(item, str) for item in value):
|
||||
return [item for item in value if item]
|
||||
raise ExecutionRebindError("TASK_CAPABILITIES_UNAVAILABLE", 503)
|
||||
|
||||
@staticmethod
|
||||
def _event_table(
|
||||
connection: sqlite3.Connection,
|
||||
) -> tuple[str, dict[str, sqlite3.Row]]:
|
||||
tables = {
|
||||
row["name"]
|
||||
for row in connection.execute(
|
||||
"SELECT name FROM sqlite_master WHERE type='table'"
|
||||
)
|
||||
}
|
||||
for name in ("task_events", "events"):
|
||||
if name not in tables:
|
||||
continue
|
||||
columns = ExecutionRebindStore._columns(connection, name)
|
||||
if "task_id" in columns and ("event_type" in columns or "type" in columns):
|
||||
return name, columns
|
||||
raise ExecutionRebindError("TASK_EVENT_TABLE_UNSUPPORTED", 503)
|
||||
|
||||
@staticmethod
|
||||
def _insert_event(
|
||||
connection: sqlite3.Connection,
|
||||
task_id: str,
|
||||
payload: Mapping[str, Any],
|
||||
) -> None:
|
||||
table, columns = ExecutionRebindStore._event_table(connection)
|
||||
values: dict[str, Any] = {"task_id": task_id}
|
||||
if "event_type" in columns:
|
||||
values["event_type"] = "TASK_EXECUTION_REBIND_AUTHORIZED"
|
||||
else:
|
||||
values["type"] = "TASK_EXECUTION_REBIND_AUTHORIZED"
|
||||
payload_text = json.dumps(payload, sort_keys=True, separators=(",", ":"))
|
||||
if "payload_json" in columns:
|
||||
values["payload_json"] = payload_text
|
||||
elif "payload" in columns:
|
||||
values["payload"] = payload_text
|
||||
else:
|
||||
raise ExecutionRebindError("TASK_EVENT_PAYLOAD_UNSUPPORTED", 503)
|
||||
if "created_at" in columns:
|
||||
values["created_at"] = _now()
|
||||
if "agent_id" in columns:
|
||||
values["agent_id"] = "owner-control"
|
||||
if "actor_id" in columns:
|
||||
values["actor_id"] = "owner-control"
|
||||
names = list(values)
|
||||
quoted = ",".join('"' + name + '"' for name in names)
|
||||
placeholders = ",".join("?" for _ in names)
|
||||
connection.execute(
|
||||
f'INSERT INTO "{table}" ({quoted}) VALUES ({placeholders})',
|
||||
tuple(values[name] for name in names),
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _ensure_rebind_table(connection: sqlite3.Connection) -> None:
|
||||
connection.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS task_execution_rebinds (
|
||||
task_id TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL,
|
||||
request_sha256 TEXT NOT NULL,
|
||||
authorization_id TEXT NOT NULL,
|
||||
previous_verification_sha256 TEXT NOT NULL,
|
||||
old_execution_digest TEXT NOT NULL,
|
||||
new_execution_digest TEXT NOT NULL,
|
||||
expected_revision INTEGER NOT NULL,
|
||||
applied_revision INTEGER NOT NULL,
|
||||
attempt INTEGER NOT NULL,
|
||||
reason TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(task_id,idempotency_key)
|
||||
)
|
||||
"""
|
||||
)
|
||||
|
||||
def _load_and_validate(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
task_id: str,
|
||||
request: ExecutionRebindRequest,
|
||||
) -> tuple[sqlite3.Row, dict[str, sqlite3.Row], str, dict[str, Any], dict[str, Any]]:
|
||||
columns = self._columns(connection, "tasks")
|
||||
required = {
|
||||
"task_id",
|
||||
"status",
|
||||
"attempt",
|
||||
"revision",
|
||||
"claimed_by",
|
||||
"lease_token_hash",
|
||||
"lease_expires_at",
|
||||
"verification_json",
|
||||
}
|
||||
if not required.issubset(columns):
|
||||
raise ExecutionRebindError("TASK_SCHEMA_EXECUTION_REBIND_UNSUPPORTED", 503)
|
||||
metadata_column = self._metadata_column(columns)
|
||||
task = connection.execute(
|
||||
"SELECT * FROM tasks WHERE task_id=?",
|
||||
(task_id,),
|
||||
).fetchone()
|
||||
if task is None:
|
||||
raise ExecutionRebindError("TASK_NOT_FOUND", 404)
|
||||
|
||||
if (
|
||||
str(task["status"]) != request.expected_status
|
||||
or int(task["revision"]) != request.expected_revision
|
||||
or int(task["attempt"]) != request.expected_attempt
|
||||
):
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_CAS_MISMATCH", 409)
|
||||
if task["lease_token_hash"] not in (None, "") or task["lease_expires_at"] not in (None, ""):
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_ACTIVE_LEASE_DENY", 409)
|
||||
|
||||
verification_sha = self._verification_hash(task["verification_json"])
|
||||
if verification_sha != request.previous_verification_sha256:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_VERIFICATION_DRIFT", 409)
|
||||
|
||||
metadata = self._json_value(
|
||||
task[metadata_column],
|
||||
"TASK_METADATA_INVALID",
|
||||
)
|
||||
execution = metadata.get("execution")
|
||||
if not isinstance(execution, Mapping):
|
||||
raise ExecutionRebindError("TASK_EXECUTION_METADATA_MISSING", 409)
|
||||
old_execution = validate_execution_envelope(dict(execution))
|
||||
if old_execution["execution_digest"] != request.expected_old_execution_digest:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_OLD_DIGEST_DRIFT", 409)
|
||||
if old_execution.get("action") != "source_capture":
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_SOURCE_CAPTURE_REQUIRED", 409)
|
||||
|
||||
projection = metadata.get("execution_projection")
|
||||
if isinstance(projection, Mapping):
|
||||
projected_digest = str(projection.get("execution_digest") or "")
|
||||
if projected_digest and projected_digest != request.expected_old_execution_digest:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_PROJECTION_DRIFT", 409)
|
||||
return task, columns, metadata_column, metadata, old_execution
|
||||
|
||||
def rebind(
|
||||
self,
|
||||
task_id: str,
|
||||
request: ExecutionRebindRequest,
|
||||
) -> dict[str, Any]:
|
||||
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
|
||||
required_authorization = _required_authorization_id()
|
||||
if request.authorization_id != required_authorization:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_AUTHORIZATION_ID_MISMATCH", 403)
|
||||
|
||||
request_sha = _sha(request.public())
|
||||
|
||||
# Idempotent replay must win before CAS validation because a successful
|
||||
# rebind necessarily increments the Task revision and changes the persisted envelope.
|
||||
with self._connect() as connection:
|
||||
self._ensure_rebind_table(connection)
|
||||
replay = connection.execute(
|
||||
"SELECT * FROM task_execution_rebinds WHERE task_id=? AND idempotency_key=?",
|
||||
(task_id, request.idempotency_key),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
if replay["request_sha256"] != request_sha:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_IDEMPOTENCY_CONFLICT", 409)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": int(replay["attempt"]),
|
||||
"revision": int(replay["applied_revision"]),
|
||||
"old_execution_digest": replay["old_execution_digest"],
|
||||
"new_execution_digest": replay["new_execution_digest"],
|
||||
"authorization_id": replay["authorization_id"],
|
||||
"idempotent": True,
|
||||
}
|
||||
|
||||
# Read/CAS snapshot first. Canonical Bridge resolution happens outside the DB write lock.
|
||||
with self._connect() as connection:
|
||||
task, columns, _, _, old_execution = self._load_and_validate(
|
||||
connection, task_id, request
|
||||
)
|
||||
capabilities = self._required_capabilities(task, columns, old_execution)
|
||||
|
||||
binding = GovernedExecutionBinding.from_mapping(old_execution)
|
||||
resolved = dict(self.resolver(task_id, capabilities))
|
||||
new_execution = validate_execution_envelope(resolved, binding=binding)
|
||||
if new_execution.get("action") != "deterministic":
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_DETERMINISTIC_PLAN_REQUIRED", 409)
|
||||
if new_execution["execution_digest"] != request.expected_new_execution_digest:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_NEW_DIGEST_DRIFT", 409)
|
||||
if new_execution["execution_digest"] == old_execution["execution_digest"]:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_DIGEST_UNCHANGED", 409)
|
||||
|
||||
# Re-read under BEGIN IMMEDIATE and apply only if the exact snapshot is unchanged.
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._ensure_rebind_table(connection)
|
||||
|
||||
replay = connection.execute(
|
||||
"SELECT * FROM task_execution_rebinds WHERE task_id=? AND idempotency_key=?",
|
||||
(task_id, request.idempotency_key),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
if replay["request_sha256"] != request_sha:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_IDEMPOTENCY_CONFLICT", 409)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": int(replay["attempt"]),
|
||||
"revision": int(replay["applied_revision"]),
|
||||
"old_execution_digest": replay["old_execution_digest"],
|
||||
"new_execution_digest": replay["new_execution_digest"],
|
||||
"authorization_id": replay["authorization_id"],
|
||||
"idempotent": True,
|
||||
}
|
||||
|
||||
task, columns, metadata_column, metadata, current_old = self._load_and_validate(
|
||||
connection, task_id, request
|
||||
)
|
||||
if current_old["execution_digest"] != old_execution["execution_digest"]:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_OLD_DIGEST_DRIFT", 409)
|
||||
|
||||
new_metadata = dict(metadata)
|
||||
new_metadata["execution"] = new_execution
|
||||
new_metadata["execution_projection"] = {
|
||||
"schema": "aios.online-agent.task-projection.v1",
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"execution_digest": new_execution["execution_digest"],
|
||||
}
|
||||
applied_revision = request.expected_revision + 1
|
||||
previous_claimed_by = task["claimed_by"]
|
||||
|
||||
cursor = connection.execute(
|
||||
f"""
|
||||
UPDATE tasks
|
||||
SET "{metadata_column}"=?, revision=?, claimed_by=NULL,
|
||||
lease_token_hash=NULL, lease_expires_at=NULL
|
||||
WHERE task_id=? AND status=? AND revision=? AND attempt=?
|
||||
AND claimed_by IS ? AND lease_token_hash IS NULL AND lease_expires_at IS NULL
|
||||
""",
|
||||
(
|
||||
json.dumps(new_metadata, sort_keys=True, separators=(",", ":")),
|
||||
applied_revision,
|
||||
task_id,
|
||||
request.expected_status,
|
||||
request.expected_revision,
|
||||
request.expected_attempt,
|
||||
previous_claimed_by,
|
||||
),
|
||||
)
|
||||
if cursor.rowcount != 1:
|
||||
raise ExecutionRebindError("EXECUTION_REBIND_CAS_MISMATCH", 409)
|
||||
|
||||
event_payload = {
|
||||
"schema": "aios.task-execution-rebind.event.v1",
|
||||
"task_id": task_id,
|
||||
"job_id": binding.job_id,
|
||||
"authorization_id": request.authorization_id,
|
||||
"idempotency_key": request.idempotency_key,
|
||||
"reason": request.reason,
|
||||
"previous_verification_sha256": request.previous_verification_sha256,
|
||||
"old_execution_digest": old_execution["execution_digest"],
|
||||
"new_execution_digest": new_execution["execution_digest"],
|
||||
"old_action": old_execution.get("action"),
|
||||
"new_action": new_execution.get("action"),
|
||||
"previous_revision": request.expected_revision,
|
||||
"applied_revision": applied_revision,
|
||||
"attempt": request.expected_attempt,
|
||||
"request_sha256": request_sha,
|
||||
"previous_claimed_by": previous_claimed_by,
|
||||
"stale_claim_normalized": previous_claimed_by not in (None, ""),
|
||||
}
|
||||
self._insert_event(connection, task_id, event_payload)
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO task_execution_rebinds(
|
||||
task_id,idempotency_key,request_sha256,authorization_id,
|
||||
previous_verification_sha256,old_execution_digest,new_execution_digest,
|
||||
expected_revision,applied_revision,attempt,reason,created_at
|
||||
) VALUES (?,?,?,?,?,?,?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
task_id,
|
||||
request.idempotency_key,
|
||||
request_sha,
|
||||
request.authorization_id,
|
||||
request.previous_verification_sha256,
|
||||
old_execution["execution_digest"],
|
||||
new_execution["execution_digest"],
|
||||
request.expected_revision,
|
||||
applied_revision,
|
||||
request.expected_attempt,
|
||||
request.reason,
|
||||
_now(),
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": request.expected_attempt,
|
||||
"revision": applied_revision,
|
||||
"old_execution_digest": old_execution["execution_digest"],
|
||||
"new_execution_digest": new_execution["execution_digest"],
|
||||
"authorization_id": request.authorization_id,
|
||||
"idempotent": False,
|
||||
}
|
||||
|
||||
|
||||
class ExecutionRebindHandler(BaseHTTPRequestHandler):
|
||||
store: ExecutionRebindStore | None = None
|
||||
control_token: str = ""
|
||||
|
||||
def log_message(self, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def _json(self, value: Mapping[str, Any], status: int) -> None:
|
||||
data = json.dumps(
|
||||
dict(value), sort_keys=True, separators=(",", ":")
|
||||
).encode("utf-8")
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(data)))
|
||||
self.end_headers()
|
||||
self.wfile.write(data)
|
||||
|
||||
def _authorized(self) -> bool:
|
||||
header = self.headers.get("Authorization", "")
|
||||
return (
|
||||
header.startswith("Bearer ")
|
||||
and bool(self.control_token)
|
||||
and hmac.compare_digest(header[7:], self.control_token)
|
||||
)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/health":
|
||||
self._json(
|
||||
{"status": "ok", "service": "aios-agent-task-execution-rebind"},
|
||||
200,
|
||||
)
|
||||
else:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
match = re.fullmatch(r"/v1/tasks/([^/]+)/execution-rebind", self.path)
|
||||
if match is None:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
if not self._authorized():
|
||||
self._json({"error": "UNAUTHORIZED"}, 401)
|
||||
return
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
except ValueError:
|
||||
self._json({"error": "CONTENT_LENGTH_INVALID"}, 400)
|
||||
return
|
||||
if length < 1 or length > MAX_BODY:
|
||||
self._json({"error": "REQUEST_SIZE_INVALID"}, 413)
|
||||
return
|
||||
try:
|
||||
value = json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
if not isinstance(value, Mapping):
|
||||
raise ValueError
|
||||
request = ExecutionRebindRequest.from_mapping(value)
|
||||
if self.store is None:
|
||||
raise ExecutionRebindError("RUNTIME_UNAVAILABLE", 503)
|
||||
result = self.store.rebind(match.group(1), request)
|
||||
self._json(result, 200 if result["idempotent"] else 201)
|
||||
except ExecutionRebindError as exc:
|
||||
self._json({"error": exc.code}, exc.status)
|
||||
except (UnicodeDecodeError, json.JSONDecodeError, ValueError):
|
||||
self._json({"error": "REQUEST_INVALID"}, 400)
|
||||
|
||||
|
||||
def load_control_token(path: Path) -> str:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise RuntimeError("TASK_EXECUTION_REBIND_CONTROL_CREDENTIAL_UNAVAILABLE")
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 32:
|
||||
raise RuntimeError("TASK_EXECUTION_REBIND_CONTROL_CREDENTIAL_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def serve() -> None:
|
||||
db = Path(os.environ.get("AIOS_AGENT_TASK_DB", "/var/lib/aios-agent-task/state.sqlite3"))
|
||||
_required_authorization_id()
|
||||
token_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
|
||||
str(
|
||||
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
/ "agent_task_control_token"
|
||||
),
|
||||
)
|
||||
)
|
||||
token = load_control_token(token_path)
|
||||
bridge = os.environ.get(
|
||||
"AIOS_GOVERNED_WRITE_API_URL",
|
||||
"http://127.0.0.1:18892",
|
||||
)
|
||||
host = os.environ.get("AIOS_TASK_EXECUTION_REBIND_HOST", "127.0.0.1")
|
||||
port = int(os.environ.get("AIOS_TASK_EXECUTION_REBIND_PORT", "18942"))
|
||||
ExecutionRebindHandler.store = ExecutionRebindStore(
|
||||
db,
|
||||
CanonicalBridgeExecutionResolver(bridge, token),
|
||||
)
|
||||
ExecutionRebindHandler.control_token = token
|
||||
ThreadingHTTPServer((host, port), ExecutionRebindHandler).serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,870 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Durable online task protocol for external AIOS agents.
|
||||
|
||||
The store is deliberately independent from Git/Gitea mutation. It provides a
|
||||
small durable state machine for publishing work, atomic claim/lease ownership,
|
||||
heartbeat, idempotent result submission, explicit server-side verification,
|
||||
lease recovery, and audit events.
|
||||
|
||||
No plaintext agent credential or task lease token is persisted.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timedelta, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
from pathlib import Path
|
||||
import secrets
|
||||
import sqlite3
|
||||
from typing import Any, Callable, Iterable, Mapping
|
||||
import uuid
|
||||
|
||||
from aios_capability_contract import has_capabilities
|
||||
from aios_online_agent_execution import (
|
||||
ExecutionProjectionError,
|
||||
validate_execution_envelope,
|
||||
)
|
||||
|
||||
|
||||
TERMINAL_STATES = frozenset({"SUCCEEDED", "FAILED", "EXPIRED", "CANCELLED"})
|
||||
ACTIVE_LEASE_STATES = frozenset({"CLAIMED", "RUNNING"})
|
||||
TASK_STATES = frozenset({
|
||||
"QUEUED", "CLAIMED", "RUNNING", "VERIFYING",
|
||||
"SUCCEEDED", "FAILED", "EXPIRED", "CANCELLED",
|
||||
})
|
||||
VERIFY_DECISIONS = frozenset({"SUCCEEDED", "NEEDS_REWORK", "FAILED"})
|
||||
|
||||
|
||||
GOVERNED_WRITE_CAPABILITIES = frozenset({
|
||||
"governed.write.branch",
|
||||
"governed.write.file",
|
||||
})
|
||||
EXECUTION_PROJECTION_SCHEMA = "aios.online-agent.task-projection.v1"
|
||||
|
||||
|
||||
def _validate_write_execution_binding(
|
||||
task_id: str,
|
||||
required_capabilities: list[str],
|
||||
metadata: Mapping[str, Any],
|
||||
) -> None:
|
||||
required = set(required_capabilities)
|
||||
if not required.intersection(GOVERNED_WRITE_CAPABILITIES):
|
||||
return
|
||||
execution = metadata.get("execution")
|
||||
projection = metadata.get("execution_projection")
|
||||
if not isinstance(execution, Mapping) or not isinstance(projection, Mapping):
|
||||
raise TaskProtocolError("GOVERNED_EXECUTION_BINDING_REQUIRED", 409)
|
||||
try:
|
||||
canonical = validate_execution_envelope(dict(execution))
|
||||
except (ExecutionProjectionError, TypeError, ValueError, KeyError) as exc:
|
||||
raise TaskProtocolError("EXECUTION_ENVELOPE_INVALID", 409) from exc
|
||||
if canonical.get("task_id") != task_id:
|
||||
raise TaskProtocolError("TASK_BINDING_CONFLICT", 409)
|
||||
if set(canonical.get("capability_scope") or ()) != required:
|
||||
raise TaskProtocolError("EXECUTION_CAPABILITY_SCOPE_CONFLICT", 409)
|
||||
if (
|
||||
projection.get("schema") != EXECUTION_PROJECTION_SCHEMA
|
||||
or projection.get("task_id") != task_id
|
||||
or projection.get("job_id") != canonical.get("job_id")
|
||||
or projection.get("execution_digest") != canonical.get("execution_digest")
|
||||
):
|
||||
raise TaskProtocolError("EXECUTION_PROJECTION_INVALID", 409)
|
||||
|
||||
|
||||
class TaskProtocolError(RuntimeError):
|
||||
def __init__(self, code: str, http_status: int = 409) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.http_status = http_status
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class Principal:
|
||||
kind: str
|
||||
identifier: str
|
||||
|
||||
|
||||
def utcnow() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def iso(value: datetime) -> str:
|
||||
return value.astimezone(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def parse_time(value: str | None) -> datetime | None:
|
||||
if not value:
|
||||
return None
|
||||
parsed = datetime.fromisoformat(value)
|
||||
if parsed.tzinfo is None:
|
||||
parsed = parsed.replace(tzinfo=timezone.utc)
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def canonical_json(value: Any) -> str:
|
||||
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
|
||||
|
||||
def digest_json(value: Any) -> str:
|
||||
return hashlib.sha256(canonical_json(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _string_list(value: Iterable[object] | None, field: str, *, max_items: int = 128) -> list[str]:
|
||||
if value is None:
|
||||
return []
|
||||
if isinstance(value, (str, bytes)) or not isinstance(value, Iterable):
|
||||
raise TaskProtocolError(field.upper() + "_INVALID", 400)
|
||||
result: list[str] = []
|
||||
for item in value:
|
||||
text = str(item).strip()
|
||||
if not text or len(text) > 160:
|
||||
raise TaskProtocolError(field.upper() + "_INVALID", 400)
|
||||
result.append(text)
|
||||
if len(result) > max_items:
|
||||
raise TaskProtocolError(field.upper() + "_TOO_LARGE", 400)
|
||||
return sorted(set(result))
|
||||
|
||||
|
||||
def _json_object(value: object | None, field: str, *, max_bytes: int = 128 * 1024) -> dict[str, Any]:
|
||||
if value is None:
|
||||
return {}
|
||||
if not isinstance(value, Mapping):
|
||||
raise TaskProtocolError(field.upper() + "_INVALID", 400)
|
||||
result = dict(value)
|
||||
if len(canonical_json(result).encode("utf-8")) > max_bytes:
|
||||
raise TaskProtocolError(field.upper() + "_TOO_LARGE", 413)
|
||||
return result
|
||||
|
||||
|
||||
def _criteria(value: object | None) -> list[Any]:
|
||||
if value is None:
|
||||
return []
|
||||
if isinstance(value, (str, bytes)) or not isinstance(value, list):
|
||||
raise TaskProtocolError("SUCCESS_CRITERIA_INVALID", 400)
|
||||
if len(value) > 128:
|
||||
raise TaskProtocolError("SUCCESS_CRITERIA_TOO_LARGE", 413)
|
||||
if len(canonical_json(value).encode("utf-8")) > 128 * 1024:
|
||||
raise TaskProtocolError("SUCCESS_CRITERIA_TOO_LARGE", 413)
|
||||
return list(value)
|
||||
|
||||
|
||||
class TaskStore:
|
||||
"""SQLite-backed durable task store.
|
||||
|
||||
SQLite BEGIN IMMEDIATE serializes claims so two agents cannot successfully
|
||||
claim the same queued task. WAL mode allows concurrent readers.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
path: str | Path,
|
||||
*,
|
||||
now: Callable[[], datetime] = utcnow,
|
||||
token_pepper: str = "",
|
||||
) -> None:
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
self.now = now
|
||||
self.token_pepper = token_pepper
|
||||
self._initialize()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.path, timeout=10, isolation_level=None)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA journal_mode=WAL")
|
||||
connection.execute("PRAGMA synchronous=FULL")
|
||||
connection.execute("PRAGMA busy_timeout=10000")
|
||||
return connection
|
||||
|
||||
def _initialize(self) -> None:
|
||||
with self._connect() as connection:
|
||||
connection.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS agents (
|
||||
agent_id TEXT PRIMARY KEY,
|
||||
agent_type TEXT NOT NULL,
|
||||
agent_version TEXT NOT NULL,
|
||||
capabilities_json TEXT NOT NULL,
|
||||
metadata_json TEXT NOT NULL,
|
||||
token_hash TEXT NOT NULL UNIQUE,
|
||||
status TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
last_seen_at TEXT NOT NULL
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS tasks (
|
||||
task_id TEXT PRIMARY KEY,
|
||||
goal TEXT NOT NULL,
|
||||
instructions TEXT NOT NULL,
|
||||
success_criteria_json TEXT NOT NULL,
|
||||
required_capabilities_json TEXT NOT NULL,
|
||||
constraints_json TEXT NOT NULL,
|
||||
metadata_json TEXT NOT NULL,
|
||||
deadline TEXT,
|
||||
priority INTEGER NOT NULL,
|
||||
max_attempts INTEGER NOT NULL,
|
||||
attempt INTEGER NOT NULL DEFAULT 0,
|
||||
status TEXT NOT NULL,
|
||||
claimed_by TEXT,
|
||||
lease_token_hash TEXT,
|
||||
lease_expires_at TEXT,
|
||||
result_json TEXT,
|
||||
result_digest TEXT,
|
||||
result_idempotency_key TEXT,
|
||||
verification_json TEXT,
|
||||
revision INTEGER NOT NULL DEFAULT 1,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL,
|
||||
FOREIGN KEY(claimed_by) REFERENCES agents(agent_id)
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS idempotency (
|
||||
scope TEXT NOT NULL,
|
||||
key TEXT NOT NULL,
|
||||
payload_digest TEXT NOT NULL,
|
||||
response_json TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(scope, key)
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS events (
|
||||
event_id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
task_id TEXT,
|
||||
agent_id TEXT,
|
||||
event_type TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_tasks_queue
|
||||
ON tasks(status, priority DESC, created_at);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_tasks_lease
|
||||
ON tasks(status, lease_expires_at);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_events_task
|
||||
ON events(task_id, event_id);
|
||||
"""
|
||||
)
|
||||
|
||||
def _token_hash(self, token: str) -> str:
|
||||
return hashlib.sha256((self.token_pepper + "\0" + token).encode("utf-8")).hexdigest()
|
||||
|
||||
@staticmethod
|
||||
def _row_task(row: sqlite3.Row, *, include_result: bool = True) -> dict[str, Any]:
|
||||
value: dict[str, Any] = {
|
||||
"task_id": row["task_id"],
|
||||
"goal": row["goal"],
|
||||
"instructions": row["instructions"],
|
||||
"success_criteria": json.loads(row["success_criteria_json"]),
|
||||
"required_capabilities": json.loads(row["required_capabilities_json"]),
|
||||
"constraints": json.loads(row["constraints_json"]),
|
||||
"metadata": json.loads(row["metadata_json"]),
|
||||
"deadline": row["deadline"],
|
||||
"priority": row["priority"],
|
||||
"max_attempts": row["max_attempts"],
|
||||
"attempt": row["attempt"],
|
||||
"status": row["status"],
|
||||
"claimed_by": row["claimed_by"],
|
||||
"lease_expires_at": row["lease_expires_at"],
|
||||
"revision": row["revision"],
|
||||
"created_at": row["created_at"],
|
||||
"updated_at": row["updated_at"],
|
||||
}
|
||||
if include_result:
|
||||
value["result"] = json.loads(row["result_json"]) if row["result_json"] else None
|
||||
value["verification"] = (
|
||||
json.loads(row["verification_json"]) if row["verification_json"] else None
|
||||
)
|
||||
return value
|
||||
|
||||
def _event(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
event_type: str,
|
||||
*,
|
||||
task_id: str | None = None,
|
||||
agent_id: str | None = None,
|
||||
payload: Mapping[str, Any] | None = None,
|
||||
) -> None:
|
||||
connection.execute(
|
||||
"INSERT INTO events(task_id,agent_id,event_type,payload_json,created_at)"
|
||||
" VALUES(?,?,?,?,?)",
|
||||
(task_id, agent_id, event_type, canonical_json(dict(payload or {})), iso(self.now())),
|
||||
)
|
||||
|
||||
def register_agent(
|
||||
self,
|
||||
*,
|
||||
agent_id: str,
|
||||
agent_type: str,
|
||||
agent_version: str,
|
||||
capabilities: Iterable[object],
|
||||
metadata: Mapping[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
agent_id = agent_id.strip()
|
||||
agent_type = agent_type.strip()
|
||||
agent_version = agent_version.strip()
|
||||
if not agent_id or len(agent_id) > 160 or not agent_type or not agent_version:
|
||||
raise TaskProtocolError("AGENT_IDENTITY_INVALID", 400)
|
||||
caps = _string_list(capabilities, "capabilities")
|
||||
meta = _json_object(metadata, "metadata")
|
||||
token = "agt_" + secrets.token_urlsafe(32)
|
||||
now = iso(self.now())
|
||||
try:
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
connection.execute(
|
||||
"INSERT INTO agents(agent_id,agent_type,agent_version,capabilities_json,"
|
||||
"metadata_json,token_hash,status,created_at,last_seen_at)"
|
||||
" VALUES(?,?,?,?,?,?,?,?,?)",
|
||||
(
|
||||
agent_id,
|
||||
agent_type,
|
||||
agent_version,
|
||||
canonical_json(caps),
|
||||
canonical_json(meta),
|
||||
self._token_hash(token),
|
||||
"ACTIVE",
|
||||
now,
|
||||
now,
|
||||
),
|
||||
)
|
||||
self._event(
|
||||
connection,
|
||||
"AGENT_REGISTERED",
|
||||
agent_id=agent_id,
|
||||
payload={"agent_type": agent_type, "agent_version": agent_version},
|
||||
)
|
||||
connection.commit()
|
||||
except sqlite3.IntegrityError as exc:
|
||||
raise TaskProtocolError("AGENT_ALREADY_EXISTS", 409) from exc
|
||||
return {
|
||||
"agent_id": agent_id,
|
||||
"agent_type": agent_type,
|
||||
"agent_version": agent_version,
|
||||
"capabilities": caps,
|
||||
"agent_token": token,
|
||||
"credential_returned_once": True,
|
||||
}
|
||||
|
||||
def authenticate_agent(self, token: str) -> dict[str, Any]:
|
||||
if not token:
|
||||
raise TaskProtocolError("UNAUTHORIZED", 401)
|
||||
token_hash = self._token_hash(token)
|
||||
with self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT * FROM agents WHERE token_hash=? AND status='ACTIVE'",
|
||||
(token_hash,),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("UNAUTHORIZED", 401)
|
||||
connection.execute(
|
||||
"UPDATE agents SET last_seen_at=? WHERE agent_id=?",
|
||||
(iso(self.now()), row["agent_id"]),
|
||||
)
|
||||
return {
|
||||
"agent_id": row["agent_id"],
|
||||
"agent_type": row["agent_type"],
|
||||
"agent_version": row["agent_version"],
|
||||
"capabilities": json.loads(row["capabilities_json"]),
|
||||
"metadata": json.loads(row["metadata_json"]),
|
||||
}
|
||||
|
||||
def _idempotent_lookup(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
*,
|
||||
scope: str,
|
||||
key: str,
|
||||
payload_digest: str,
|
||||
) -> dict[str, Any] | None:
|
||||
row = connection.execute(
|
||||
"SELECT payload_digest,response_json FROM idempotency WHERE scope=? AND key=?",
|
||||
(scope, key),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return None
|
||||
if not hmac.compare_digest(row["payload_digest"], payload_digest):
|
||||
raise TaskProtocolError("IDEMPOTENCY_CONFLICT", 409)
|
||||
return json.loads(row["response_json"])
|
||||
|
||||
def _idempotent_store(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
*,
|
||||
scope: str,
|
||||
key: str,
|
||||
payload_digest: str,
|
||||
response: Mapping[str, Any],
|
||||
) -> None:
|
||||
connection.execute(
|
||||
"INSERT INTO idempotency(scope,key,payload_digest,response_json,created_at)"
|
||||
" VALUES(?,?,?,?,?)",
|
||||
(scope, key, payload_digest, canonical_json(dict(response)), iso(self.now())),
|
||||
)
|
||||
|
||||
def create_task(
|
||||
self,
|
||||
*,
|
||||
task_id: str | None,
|
||||
goal: str,
|
||||
instructions: str,
|
||||
success_criteria: object | None,
|
||||
required_capabilities: Iterable[object] | None = None,
|
||||
constraints: Mapping[str, Any] | None = None,
|
||||
metadata: Mapping[str, Any] | None = None,
|
||||
deadline: str | None = None,
|
||||
priority: int = 0,
|
||||
max_attempts: int = 3,
|
||||
idempotency_key: str,
|
||||
) -> dict[str, Any]:
|
||||
task_id = (task_id or ("task-" + uuid.uuid4().hex)).strip()
|
||||
goal = goal.strip()
|
||||
instructions = instructions.strip()
|
||||
idempotency_key = idempotency_key.strip()
|
||||
if not task_id or len(task_id) > 180 or not goal or not instructions:
|
||||
raise TaskProtocolError("TASK_BINDING_INVALID", 400)
|
||||
if not idempotency_key or len(idempotency_key) > 160:
|
||||
raise TaskProtocolError("IDEMPOTENCY_KEY_INVALID", 400)
|
||||
if not isinstance(priority, int) or isinstance(priority, bool) or not -100 <= priority <= 100:
|
||||
raise TaskProtocolError("PRIORITY_INVALID", 400)
|
||||
if not isinstance(max_attempts, int) or isinstance(max_attempts, bool) or not 1 <= max_attempts <= 20:
|
||||
raise TaskProtocolError("MAX_ATTEMPTS_INVALID", 400)
|
||||
parsed_deadline = parse_time(deadline)
|
||||
if parsed_deadline and parsed_deadline <= self.now():
|
||||
raise TaskProtocolError("DEADLINE_INVALID", 400)
|
||||
criteria = _criteria(success_criteria)
|
||||
required = _string_list(required_capabilities, "required_capabilities")
|
||||
constraints_value = _json_object(constraints, "constraints")
|
||||
metadata_value = _json_object(metadata, "metadata")
|
||||
_validate_write_execution_binding(task_id, required, metadata_value)
|
||||
payload = {
|
||||
"task_id": task_id,
|
||||
"goal": goal,
|
||||
"instructions": instructions,
|
||||
"success_criteria": criteria,
|
||||
"required_capabilities": required,
|
||||
"constraints": constraints_value,
|
||||
"metadata": metadata_value,
|
||||
"deadline": iso(parsed_deadline) if parsed_deadline else None,
|
||||
"priority": priority,
|
||||
"max_attempts": max_attempts,
|
||||
}
|
||||
payload_digest = digest_json(payload)
|
||||
now = iso(self.now())
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
replay = self._idempotent_lookup(
|
||||
connection,
|
||||
scope="create_task",
|
||||
key=idempotency_key,
|
||||
payload_digest=payload_digest,
|
||||
)
|
||||
if replay is not None:
|
||||
connection.commit()
|
||||
return {**replay, "idempotent": True}
|
||||
try:
|
||||
connection.execute(
|
||||
"INSERT INTO tasks(task_id,goal,instructions,success_criteria_json,"
|
||||
"required_capabilities_json,constraints_json,metadata_json,deadline,priority,"
|
||||
"max_attempts,attempt,status,revision,created_at,updated_at)"
|
||||
" VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)",
|
||||
(
|
||||
task_id,
|
||||
goal,
|
||||
instructions,
|
||||
canonical_json(criteria),
|
||||
canonical_json(required),
|
||||
canonical_json(constraints_value),
|
||||
canonical_json(metadata_value),
|
||||
payload["deadline"],
|
||||
priority,
|
||||
max_attempts,
|
||||
0,
|
||||
"QUEUED",
|
||||
1,
|
||||
now,
|
||||
now,
|
||||
),
|
||||
)
|
||||
except sqlite3.IntegrityError as exc:
|
||||
raise TaskProtocolError("TASK_ID_CONFLICT", 409) from exc
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
result = self._row_task(row)
|
||||
self._idempotent_store(
|
||||
connection,
|
||||
scope="create_task",
|
||||
key=idempotency_key,
|
||||
payload_digest=payload_digest,
|
||||
response=result,
|
||||
)
|
||||
self._event(connection, "TASK_CREATED", task_id=task_id, payload={"priority": priority})
|
||||
connection.commit()
|
||||
return result
|
||||
|
||||
def _expire_locked(self, connection: sqlite3.Connection) -> None:
|
||||
now_dt = self.now()
|
||||
now = iso(now_dt)
|
||||
rows = connection.execute(
|
||||
"SELECT * FROM tasks WHERE status IN ('QUEUED','CLAIMED','RUNNING')"
|
||||
).fetchall()
|
||||
for row in rows:
|
||||
deadline = parse_time(row["deadline"])
|
||||
if deadline is not None and deadline <= now_dt:
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status='EXPIRED',lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,revision=revision+1,updated_at=? WHERE task_id=?",
|
||||
(now, row["task_id"]),
|
||||
)
|
||||
self._event(connection, "TASK_EXPIRED", task_id=row["task_id"])
|
||||
continue
|
||||
if row["status"] in ACTIVE_LEASE_STATES:
|
||||
lease_expires = parse_time(row["lease_expires_at"])
|
||||
if lease_expires is not None and lease_expires <= now_dt:
|
||||
if row["attempt"] >= row["max_attempts"]:
|
||||
next_state = "FAILED"
|
||||
else:
|
||||
next_state = "QUEUED"
|
||||
if next_state == "FAILED":
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status=?,lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,revision=revision+1,updated_at=? WHERE task_id=?",
|
||||
(next_state, now, row["task_id"]),
|
||||
)
|
||||
else:
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status=?,claimed_by=NULL,lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,revision=revision+1,updated_at=? WHERE task_id=?",
|
||||
(next_state, now, row["task_id"]),
|
||||
)
|
||||
self._event(
|
||||
connection,
|
||||
"LEASE_EXPIRED",
|
||||
task_id=row["task_id"],
|
||||
agent_id=row["claimed_by"],
|
||||
payload={"next_state": next_state, "attempt": row["attempt"]},
|
||||
)
|
||||
|
||||
def expire_leases(self) -> int:
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
before = connection.total_changes
|
||||
self._expire_locked(connection)
|
||||
changed = connection.total_changes - before
|
||||
connection.commit()
|
||||
return changed
|
||||
|
||||
def poll_tasks(self, *, agent_id: str, limit: int = 20) -> list[dict[str, Any]]:
|
||||
if not 1 <= int(limit) <= 100:
|
||||
raise TaskProtocolError("LIMIT_INVALID", 400)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._expire_locked(connection)
|
||||
agent = connection.execute(
|
||||
"SELECT capabilities_json FROM agents WHERE agent_id=? AND status='ACTIVE'",
|
||||
(agent_id,),
|
||||
).fetchone()
|
||||
if agent is None:
|
||||
raise TaskProtocolError("AGENT_NOT_FOUND", 404)
|
||||
capabilities = json.loads(agent["capabilities_json"])
|
||||
rows = connection.execute(
|
||||
"SELECT * FROM tasks WHERE status='QUEUED' ORDER BY priority DESC,created_at ASC"
|
||||
).fetchall()
|
||||
result = []
|
||||
for row in rows:
|
||||
required = json.loads(row["required_capabilities_json"])
|
||||
if has_capabilities(capabilities, required):
|
||||
result.append(self._row_task(row, include_result=False))
|
||||
if len(result) >= int(limit):
|
||||
break
|
||||
connection.commit()
|
||||
return result
|
||||
|
||||
def _agent_capabilities(self, connection: sqlite3.Connection, agent_id: str) -> set[str]:
|
||||
row = connection.execute(
|
||||
"SELECT capabilities_json FROM agents WHERE agent_id=? AND status='ACTIVE'",
|
||||
(agent_id,),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("AGENT_NOT_FOUND", 404)
|
||||
return set(json.loads(row["capabilities_json"]))
|
||||
|
||||
def claim_task(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
lease_seconds: int = 300,
|
||||
) -> dict[str, Any]:
|
||||
if not isinstance(lease_seconds, int) or isinstance(lease_seconds, bool) or not 30 <= lease_seconds <= 3600:
|
||||
raise TaskProtocolError("LEASE_SECONDS_INVALID", 400)
|
||||
lease_token = "lease_" + secrets.token_urlsafe(32)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._expire_locked(connection)
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
if row["status"] != "QUEUED":
|
||||
raise TaskProtocolError("TASK_NOT_CLAIMABLE", 409)
|
||||
capabilities = self._agent_capabilities(connection, agent_id)
|
||||
required = json.loads(row["required_capabilities_json"])
|
||||
if not has_capabilities(capabilities, required):
|
||||
raise TaskProtocolError("AGENT_CAPABILITY_MISMATCH", 403)
|
||||
attempt = int(row["attempt"]) + 1
|
||||
if attempt > int(row["max_attempts"]):
|
||||
raise TaskProtocolError("TASK_ATTEMPTS_EXHAUSTED", 409)
|
||||
expires = self.now() + timedelta(seconds=lease_seconds)
|
||||
now = iso(self.now())
|
||||
updated = connection.execute(
|
||||
"UPDATE tasks SET status='CLAIMED',claimed_by=?,lease_token_hash=?,"
|
||||
"lease_expires_at=?,attempt=?,revision=revision+1,updated_at=? "
|
||||
"WHERE task_id=? AND status='QUEUED'",
|
||||
(
|
||||
agent_id,
|
||||
self._token_hash(lease_token),
|
||||
iso(expires),
|
||||
attempt,
|
||||
now,
|
||||
task_id,
|
||||
),
|
||||
)
|
||||
if updated.rowcount != 1:
|
||||
raise TaskProtocolError("TASK_CLAIM_CONFLICT", 409)
|
||||
self._event(
|
||||
connection,
|
||||
"TASK_CLAIMED",
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
payload={"attempt": attempt, "lease_expires_at": iso(expires)},
|
||||
)
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
connection.commit()
|
||||
return {
|
||||
**self._row_task(row, include_result=False),
|
||||
"lease_token": lease_token,
|
||||
"lease_token_returned_once": True,
|
||||
}
|
||||
|
||||
def _validate_lease(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
*,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
lease_token: str,
|
||||
allowed_states: frozenset[str] = ACTIVE_LEASE_STATES,
|
||||
) -> sqlite3.Row:
|
||||
self._expire_locked(connection)
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
if row["status"] not in allowed_states:
|
||||
raise TaskProtocolError("TASK_LEASE_NOT_ACTIVE", 409)
|
||||
if row["claimed_by"] != agent_id:
|
||||
raise TaskProtocolError("TASK_LEASE_OWNER_MISMATCH", 403)
|
||||
if not row["lease_token_hash"] or not hmac.compare_digest(
|
||||
row["lease_token_hash"], self._token_hash(lease_token)
|
||||
):
|
||||
raise TaskProtocolError("TASK_LEASE_TOKEN_INVALID", 403)
|
||||
expires = parse_time(row["lease_expires_at"])
|
||||
if expires is None or expires <= self.now():
|
||||
raise TaskProtocolError("TASK_LEASE_EXPIRED", 409)
|
||||
return row
|
||||
|
||||
def heartbeat(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
lease_token: str,
|
||||
progress: Mapping[str, Any] | None = None,
|
||||
lease_seconds: int = 300,
|
||||
) -> dict[str, Any]:
|
||||
if not 30 <= int(lease_seconds) <= 3600:
|
||||
raise TaskProtocolError("LEASE_SECONDS_INVALID", 400)
|
||||
progress_value = _json_object(progress, "progress", max_bytes=64 * 1024)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._validate_lease(
|
||||
connection,
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
lease_token=lease_token,
|
||||
)
|
||||
expires = self.now() + timedelta(seconds=int(lease_seconds))
|
||||
now = iso(self.now())
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status='RUNNING',lease_expires_at=?,revision=revision+1,"
|
||||
"updated_at=? WHERE task_id=?",
|
||||
(iso(expires), now, task_id),
|
||||
)
|
||||
self._event(
|
||||
connection,
|
||||
"TASK_HEARTBEAT",
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
payload={"progress": progress_value, "lease_expires_at": iso(expires)},
|
||||
)
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
connection.commit()
|
||||
return self._row_task(row, include_result=False)
|
||||
|
||||
def submit_result(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
agent_id: str,
|
||||
lease_token: str,
|
||||
idempotency_key: str,
|
||||
result: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
idempotency_key = idempotency_key.strip()
|
||||
if not idempotency_key or len(idempotency_key) > 160:
|
||||
raise TaskProtocolError("IDEMPOTENCY_KEY_INVALID", 400)
|
||||
result_value = _json_object(result, "result", max_bytes=1024 * 1024)
|
||||
result_digest = digest_json(result_value)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
if row["result_idempotency_key"] == idempotency_key:
|
||||
if not row["result_digest"] or not hmac.compare_digest(row["result_digest"], result_digest):
|
||||
raise TaskProtocolError("IDEMPOTENCY_CONFLICT", 409)
|
||||
connection.commit()
|
||||
return {**self._row_task(row), "idempotent": True}
|
||||
self._validate_lease(
|
||||
connection,
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
lease_token=lease_token,
|
||||
)
|
||||
now = iso(self.now())
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status='VERIFYING',result_json=?,result_digest=?,"
|
||||
"result_idempotency_key=?,lease_token_hash=NULL,lease_expires_at=NULL,"
|
||||
"revision=revision+1,updated_at=? WHERE task_id=?",
|
||||
(
|
||||
canonical_json(result_value),
|
||||
result_digest,
|
||||
idempotency_key,
|
||||
now,
|
||||
task_id,
|
||||
),
|
||||
)
|
||||
self._event(
|
||||
connection,
|
||||
"RESULT_SUBMITTED",
|
||||
task_id=task_id,
|
||||
agent_id=agent_id,
|
||||
payload={"result_digest": result_digest, "idempotency_key": idempotency_key},
|
||||
)
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
connection.commit()
|
||||
return self._row_task(row)
|
||||
|
||||
def verify_task(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
decision: str,
|
||||
verification: Mapping[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
decision = decision.strip().upper()
|
||||
if decision not in VERIFY_DECISIONS:
|
||||
raise TaskProtocolError("VERIFICATION_DECISION_INVALID", 400)
|
||||
verification_value = _json_object(verification, "verification")
|
||||
verification_value = {"decision": decision, **verification_value}
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
if row["status"] != "VERIFYING":
|
||||
raise TaskProtocolError("TASK_NOT_VERIFYING", 409)
|
||||
if decision == "SUCCEEDED":
|
||||
next_state = "SUCCEEDED"
|
||||
elif decision == "FAILED":
|
||||
next_state = "FAILED"
|
||||
elif int(row["attempt"]) >= int(row["max_attempts"]):
|
||||
next_state = "FAILED"
|
||||
verification_value["reason"] = verification_value.get(
|
||||
"reason", "MAX_ATTEMPTS_EXHAUSTED"
|
||||
)
|
||||
else:
|
||||
next_state = "QUEUED"
|
||||
now = iso(self.now())
|
||||
if next_state in {"SUCCEEDED", "FAILED"}:
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status=?,lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,verification_json=?,revision=revision+1,updated_at=? "
|
||||
"WHERE task_id=?",
|
||||
(next_state, canonical_json(verification_value), now, task_id),
|
||||
)
|
||||
else:
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status=?,claimed_by=NULL,lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,verification_json=?,revision=revision+1,updated_at=? "
|
||||
"WHERE task_id=?",
|
||||
(next_state, canonical_json(verification_value), now, task_id),
|
||||
)
|
||||
self._event(
|
||||
connection,
|
||||
"TASK_VERIFIED",
|
||||
task_id=task_id,
|
||||
agent_id=row["claimed_by"],
|
||||
payload={"decision": decision, "next_state": next_state},
|
||||
)
|
||||
updated = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
connection.commit()
|
||||
return self._row_task(updated)
|
||||
|
||||
def cancel_task(self, *, task_id: str, reason: str = "") -> dict[str, Any]:
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
if row["status"] in TERMINAL_STATES:
|
||||
connection.commit()
|
||||
return self._row_task(row)
|
||||
connection.execute(
|
||||
"UPDATE tasks SET status='CANCELLED',lease_token_hash=NULL,"
|
||||
"lease_expires_at=NULL,revision=revision+1,updated_at=? WHERE task_id=?",
|
||||
(iso(self.now()), task_id),
|
||||
)
|
||||
self._event(connection, "TASK_CANCELLED", task_id=task_id, payload={"reason": reason})
|
||||
updated = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
connection.commit()
|
||||
return self._row_task(updated)
|
||||
|
||||
def get_task(self, task_id: str) -> dict[str, Any]:
|
||||
self.expire_leases()
|
||||
with self._connect() as connection:
|
||||
row = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if row is None:
|
||||
raise TaskProtocolError("TASK_NOT_FOUND", 404)
|
||||
return self._row_task(row)
|
||||
|
||||
def get_events(self, task_id: str, *, limit: int = 200) -> list[dict[str, Any]]:
|
||||
with self._connect() as connection:
|
||||
rows = connection.execute(
|
||||
"SELECT * FROM events WHERE task_id=? ORDER BY event_id DESC LIMIT ?",
|
||||
(task_id, max(1, min(int(limit), 1000))),
|
||||
).fetchall()
|
||||
return [
|
||||
{
|
||||
"event_id": row["event_id"],
|
||||
"task_id": row["task_id"],
|
||||
"agent_id": row["agent_id"],
|
||||
"event_type": row["event_type"],
|
||||
"payload": json.loads(row["payload_json"]),
|
||||
"created_at": row["created_at"],
|
||||
}
|
||||
for row in reversed(rows)
|
||||
]
|
||||
@@ -0,0 +1,427 @@
|
||||
"""Owner-controlled, CAS-bound retry extension for exhausted Online Agent Tasks."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sqlite3
|
||||
from typing import Any, Mapping
|
||||
|
||||
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
|
||||
MAX_BODY = 64 * 1024
|
||||
AUTHORIZE_EXTENSION_ID_ENV = "AIOS_AGENT_TASK_AUTHORIZATION_ID"
|
||||
|
||||
|
||||
class RetryExtensionError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 409) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
def _canonical(value: object) -> bytes:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
|
||||
|
||||
|
||||
def _sha(value: object) -> str:
|
||||
return hashlib.sha256(_canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def _required_authorization_id() -> str:
|
||||
value = os.environ.get(AUTHORIZE_EXTENSION_ID_ENV, "").strip()
|
||||
if not value:
|
||||
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_MISSING")
|
||||
if KEY_RE.fullmatch(value) is None:
|
||||
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def _now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def _require_string(value: object, code: str, pattern: re.Pattern[str] | None = None) -> str:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
raise RetryExtensionError(code, 400)
|
||||
value = value.strip()
|
||||
if pattern is not None and pattern.fullmatch(value) is None:
|
||||
raise RetryExtensionError(code, 400)
|
||||
return value
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RetryExtensionRequest:
|
||||
expected_status: str
|
||||
expected_revision: int
|
||||
expected_attempt: int
|
||||
expected_max_attempts: int
|
||||
next_max_attempts: int
|
||||
previous_verification_sha256: str
|
||||
authorization_id: str
|
||||
idempotency_key: str
|
||||
|
||||
@classmethod
|
||||
def from_mapping(cls, value: Mapping[str, Any]) -> "RetryExtensionRequest":
|
||||
allowed = {
|
||||
"expected_status", "expected_revision", "expected_attempt", "expected_max_attempts",
|
||||
"next_max_attempts", "previous_verification_sha256", "authorization_id", "idempotency_key",
|
||||
}
|
||||
if set(value) != allowed:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_FIELDS_INVALID", 400)
|
||||
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
|
||||
if status != "FAILED":
|
||||
raise RetryExtensionError("EXPECTED_STATUS_INVALID", 400)
|
||||
ints: dict[str, int] = {}
|
||||
for field in ("expected_revision", "expected_attempt", "expected_max_attempts", "next_max_attempts"):
|
||||
item = value[field]
|
||||
if not isinstance(item, int) or isinstance(item, bool) or item < 0:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_INTEGER_INVALID", 400)
|
||||
ints[field] = item
|
||||
if ints["expected_attempt"] != ints["expected_max_attempts"]:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_NOT_EXHAUSTED", 409)
|
||||
if ints["next_max_attempts"] != ints["expected_max_attempts"] + 1:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_MUST_BE_BOUNDED_ONE_STEP", 400)
|
||||
if ints["next_max_attempts"] > 50:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_LIMIT_EXCEEDED", 400)
|
||||
verification = _require_string(value["previous_verification_sha256"], "VERIFICATION_SHA256_INVALID")
|
||||
if re.fullmatch(r"[0-9a-f]{64}", verification) is None:
|
||||
raise RetryExtensionError("VERIFICATION_SHA256_INVALID", 400)
|
||||
authorization = _require_string(value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE)
|
||||
key = _require_string(value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE)
|
||||
return cls(
|
||||
status,
|
||||
ints["expected_revision"],
|
||||
ints["expected_attempt"],
|
||||
ints["expected_max_attempts"],
|
||||
ints["next_max_attempts"],
|
||||
verification,
|
||||
authorization,
|
||||
key,
|
||||
)
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return {
|
||||
"expected_status": self.expected_status,
|
||||
"expected_revision": self.expected_revision,
|
||||
"expected_attempt": self.expected_attempt,
|
||||
"expected_max_attempts": self.expected_max_attempts,
|
||||
"next_max_attempts": self.next_max_attempts,
|
||||
"previous_verification_sha256": self.previous_verification_sha256,
|
||||
"authorization_id": self.authorization_id,
|
||||
"idempotency_key": self.idempotency_key,
|
||||
}
|
||||
|
||||
|
||||
class RetryExtensionStore:
|
||||
"""Owns the official mutation. Direct/manual DB edits remain forbidden."""
|
||||
|
||||
def __init__(self, db_path: Path) -> None:
|
||||
self.db_path = Path(db_path)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.db_path, timeout=30.0)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA busy_timeout=30000")
|
||||
return connection
|
||||
|
||||
@staticmethod
|
||||
def _columns(connection: sqlite3.Connection, table: str) -> dict[str, sqlite3.Row]:
|
||||
return {str(row["name"]): row for row in connection.execute(f'PRAGMA table_info("{table}")')}
|
||||
|
||||
@staticmethod
|
||||
def _event_table(connection: sqlite3.Connection) -> tuple[str, dict[str, sqlite3.Row]]:
|
||||
tables = {
|
||||
row["name"]
|
||||
for row in connection.execute("SELECT name FROM sqlite_master WHERE type='table'")
|
||||
}
|
||||
for name in ("task_events", "events"):
|
||||
if name not in tables:
|
||||
continue
|
||||
columns = RetryExtensionStore._columns(connection, name)
|
||||
if "task_id" in columns and ("event_type" in columns or "type" in columns):
|
||||
return name, columns
|
||||
raise RetryExtensionError("TASK_EVENT_TABLE_UNSUPPORTED", 503)
|
||||
|
||||
@staticmethod
|
||||
def _verification_hash(raw: object) -> str:
|
||||
if raw in (None, ""):
|
||||
value: object = {}
|
||||
elif isinstance(raw, str):
|
||||
try:
|
||||
value = json.loads(raw)
|
||||
except json.JSONDecodeError as exc:
|
||||
raise RetryExtensionError("TASK_VERIFICATION_INVALID", 409) from exc
|
||||
else:
|
||||
value = raw
|
||||
return _sha(value)
|
||||
|
||||
@staticmethod
|
||||
def _ensure_extension_table(connection: sqlite3.Connection) -> None:
|
||||
connection.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS task_retry_extensions (
|
||||
task_id TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL,
|
||||
request_sha256 TEXT NOT NULL,
|
||||
authorization_id TEXT NOT NULL,
|
||||
previous_verification_sha256 TEXT NOT NULL,
|
||||
previous_max_attempts INTEGER NOT NULL,
|
||||
next_max_attempts INTEGER NOT NULL,
|
||||
expected_revision INTEGER NOT NULL,
|
||||
applied_revision INTEGER NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(task_id, idempotency_key)
|
||||
)
|
||||
"""
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _insert_event(
|
||||
connection: sqlite3.Connection,
|
||||
task_id: str,
|
||||
payload: Mapping[str, Any],
|
||||
) -> None:
|
||||
table, columns = RetryExtensionStore._event_table(connection)
|
||||
values: dict[str, Any] = {"task_id": task_id}
|
||||
if "event_type" in columns:
|
||||
values["event_type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
|
||||
else:
|
||||
values["type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
|
||||
payload_text = json.dumps(payload, sort_keys=True, separators=(",", ":"))
|
||||
if "payload_json" in columns:
|
||||
values["payload_json"] = payload_text
|
||||
elif "payload" in columns:
|
||||
values["payload"] = payload_text
|
||||
else:
|
||||
raise RetryExtensionError("TASK_EVENT_PAYLOAD_UNSUPPORTED", 503)
|
||||
if "created_at" in columns:
|
||||
values["created_at"] = _now()
|
||||
if "agent_id" in columns:
|
||||
values["agent_id"] = "owner-control"
|
||||
if "actor_id" in columns:
|
||||
values["actor_id"] = "owner-control"
|
||||
names = list(values)
|
||||
sql = f'INSERT INTO "{table}" ({",".join(f"""\"{name}\"""" for name in names)}) VALUES ({",".join("?" for _ in names)})'
|
||||
connection.execute(sql, tuple(values[name] for name in names))
|
||||
|
||||
def extend(self, task_id: str, request: RetryExtensionRequest) -> dict[str, Any]:
|
||||
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
|
||||
required_authorization_id = _required_authorization_id()
|
||||
if request.authorization_id != required_authorization_id:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_AUTHORIZATION_ID_MISMATCH", 403)
|
||||
request_payload = request.public()
|
||||
request_sha = _sha(request_payload)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._ensure_extension_table(connection)
|
||||
replay = connection.execute(
|
||||
"SELECT * FROM task_retry_extensions WHERE task_id=? AND idempotency_key=?",
|
||||
(task_id, request.idempotency_key),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
if replay["request_sha256"] != request_sha:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_IDEMPOTENCY_CONFLICT", 409)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": request.expected_attempt,
|
||||
"max_attempts": int(replay["next_max_attempts"]),
|
||||
"revision": int(replay["applied_revision"]),
|
||||
"idempotent": True,
|
||||
"authorization_id": replay["authorization_id"],
|
||||
"previous_verification_sha256": replay["previous_verification_sha256"],
|
||||
}
|
||||
|
||||
columns = self._columns(connection, "tasks")
|
||||
required = {
|
||||
"task_id", "status", "attempt", "max_attempts", "revision", "claimed_by",
|
||||
"lease_token_hash", "lease_expires_at", "verification_json",
|
||||
}
|
||||
if not required.issubset(columns):
|
||||
raise RetryExtensionError("TASK_SCHEMA_RETRY_EXTENSION_UNSUPPORTED", 503)
|
||||
task = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
|
||||
if task is None:
|
||||
raise RetryExtensionError("TASK_NOT_FOUND", 404)
|
||||
actual_verification_sha = self._verification_hash(task["verification_json"])
|
||||
if actual_verification_sha != request.previous_verification_sha256:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_VERIFICATION_DRIFT", 409)
|
||||
if (
|
||||
task["status"] != request.expected_status
|
||||
or int(task["revision"]) != request.expected_revision
|
||||
or int(task["attempt"]) != request.expected_attempt
|
||||
or int(task["max_attempts"]) != request.expected_max_attempts
|
||||
):
|
||||
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
|
||||
for lease_field in ("lease_token_hash", "lease_expires_at"):
|
||||
if lease_field in columns and task[lease_field] not in (None, ""):
|
||||
raise RetryExtensionError("RETRY_EXTENSION_ACTIVE_LEASE_DENY", 409)
|
||||
|
||||
previous_claimed_by = task["claimed_by"]
|
||||
applied_revision = request.expected_revision + 1
|
||||
cursor = connection.execute(
|
||||
"""
|
||||
UPDATE tasks
|
||||
SET status='QUEUED', max_attempts=?, revision=?, claimed_by=NULL,
|
||||
lease_token_hash=NULL, lease_expires_at=NULL
|
||||
WHERE task_id=? AND status=? AND revision=? AND attempt=? AND max_attempts=?
|
||||
AND claimed_by IS ?
|
||||
AND lease_token_hash IS NULL AND lease_expires_at IS NULL
|
||||
""",
|
||||
(
|
||||
request.next_max_attempts,
|
||||
applied_revision,
|
||||
task_id,
|
||||
request.expected_status,
|
||||
request.expected_revision,
|
||||
request.expected_attempt,
|
||||
request.expected_max_attempts,
|
||||
previous_claimed_by,
|
||||
),
|
||||
)
|
||||
if cursor.rowcount != 1:
|
||||
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
|
||||
|
||||
event_payload = {
|
||||
"schema": "aios.task-retry-extension.event.v1",
|
||||
"task_id": task_id,
|
||||
"authorization_id": request.authorization_id,
|
||||
"idempotency_key": request.idempotency_key,
|
||||
"previous_verification_sha256": request.previous_verification_sha256,
|
||||
"previous_max_attempts": request.expected_max_attempts,
|
||||
"next_max_attempts": request.next_max_attempts,
|
||||
"previous_revision": request.expected_revision,
|
||||
"applied_revision": applied_revision,
|
||||
"request_sha256": request_sha,
|
||||
"previous_claimed_by": previous_claimed_by,
|
||||
"stale_terminal_claim_normalized": previous_claimed_by not in (None, ""),
|
||||
}
|
||||
self._insert_event(connection, task_id, event_payload)
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO task_retry_extensions(
|
||||
task_id,idempotency_key,request_sha256,authorization_id,previous_verification_sha256,
|
||||
previous_max_attempts,next_max_attempts,expected_revision,applied_revision,created_at
|
||||
) VALUES (?,?,?,?,?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
task_id,
|
||||
request.idempotency_key,
|
||||
request_sha,
|
||||
request.authorization_id,
|
||||
request.previous_verification_sha256,
|
||||
request.expected_max_attempts,
|
||||
request.next_max_attempts,
|
||||
request.expected_revision,
|
||||
applied_revision,
|
||||
_now(),
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": request.expected_attempt,
|
||||
"max_attempts": request.next_max_attempts,
|
||||
"revision": applied_revision,
|
||||
"idempotent": False,
|
||||
"authorization_id": request.authorization_id,
|
||||
"previous_verification_sha256": request.previous_verification_sha256,
|
||||
}
|
||||
|
||||
|
||||
class RetryExtensionHandler(BaseHTTPRequestHandler):
|
||||
store: RetryExtensionStore | None = None
|
||||
control_token: str = ""
|
||||
|
||||
def log_message(self, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def _json(self, value: Mapping[str, Any], status: int) -> None:
|
||||
data = json.dumps(dict(value), sort_keys=True, separators=(",", ":")).encode("utf-8")
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(data)))
|
||||
self.end_headers()
|
||||
self.wfile.write(data)
|
||||
|
||||
def _authorized(self) -> bool:
|
||||
header = self.headers.get("Authorization", "")
|
||||
return (
|
||||
header.startswith("Bearer ")
|
||||
and bool(self.control_token)
|
||||
and hmac.compare_digest(header[7:], self.control_token)
|
||||
)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/health":
|
||||
self._json({"status": "ok", "service": "aios-agent-task-retry-extension"}, 200)
|
||||
else:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
match = re.fullmatch(r"/v1/tasks/([^/]+)/retry-extension", self.path)
|
||||
if match is None:
|
||||
self._json({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
if not self._authorized():
|
||||
self._json({"error": "UNAUTHORIZED"}, 401)
|
||||
return
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
except ValueError:
|
||||
self._json({"error": "CONTENT_LENGTH_INVALID"}, 400)
|
||||
return
|
||||
if length < 1 or length > MAX_BODY:
|
||||
self._json({"error": "REQUEST_SIZE_INVALID"}, 413)
|
||||
return
|
||||
try:
|
||||
value = json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
if not isinstance(value, Mapping):
|
||||
raise ValueError
|
||||
request = RetryExtensionRequest.from_mapping(value)
|
||||
if self.store is None:
|
||||
raise RetryExtensionError("RUNTIME_UNAVAILABLE", 503)
|
||||
result = self.store.extend(match.group(1), request)
|
||||
self._json(result, 200 if result["idempotent"] else 201)
|
||||
except RetryExtensionError as exc:
|
||||
self._json({"error": exc.code}, exc.status)
|
||||
except (UnicodeDecodeError, json.JSONDecodeError, ValueError):
|
||||
self._json({"error": "REQUEST_INVALID"}, 400)
|
||||
|
||||
|
||||
def load_control_token(path: Path) -> str:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_UNAVAILABLE")
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 32:
|
||||
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def serve() -> None:
|
||||
db = Path(os.environ.get("AIOS_AGENT_TASK_DB", "/var/lib/aios-agent-task/state.sqlite3"))
|
||||
_required_authorization_id()
|
||||
token_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
|
||||
str(Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials")) / "agent_task_control_token"),
|
||||
)
|
||||
)
|
||||
host = os.environ.get("AIOS_TASK_RETRY_HOST", "127.0.0.1")
|
||||
port = int(os.environ.get("AIOS_TASK_RETRY_PORT", "18941"))
|
||||
RetryExtensionHandler.store = RetryExtensionStore(db)
|
||||
RetryExtensionHandler.control_token = load_control_token(token_path)
|
||||
ThreadingHTTPServer((host, port), RetryExtensionHandler).serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
@@ -0,0 +1,655 @@
|
||||
"""CAS-bound projection from an unprivileged planner to a host coordinator."""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import hmac
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sqlite3
|
||||
from typing import Any, Callable, Mapping, Sequence
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
from aios_agent_task_initial_execution_projection import (
|
||||
InitialExecutionProjectionError,
|
||||
InitialExecutionProjectionStore,
|
||||
JOB_RE,
|
||||
KEY_RE,
|
||||
MAX_BODY,
|
||||
SHA_RE,
|
||||
TASK_RE,
|
||||
_canonical,
|
||||
_now,
|
||||
_required_authorization_id,
|
||||
_require_string,
|
||||
_sha,
|
||||
load_control_token,
|
||||
)
|
||||
from aios_online_agent_execution import (
|
||||
GovernedExecutionBinding,
|
||||
validate_execution_envelope,
|
||||
)
|
||||
|
||||
|
||||
RUNTIME_CAPABILITY = "agent.runtime.openclaw"
|
||||
COORDINATOR_CAPABILITY = "engineering.autonomous"
|
||||
COORDINATOR_CAPABILITIES = [RUNTIME_CAPABILITY, COORDINATOR_CAPABILITY]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SupervisorCoordinatorProjectionRequest:
|
||||
expected_status: str
|
||||
expected_revision: int
|
||||
expected_attempt: int
|
||||
expected_metadata_sha256: str
|
||||
expected_required_capabilities_sha256: str
|
||||
previous_verification_sha256: str
|
||||
expected_planner_result_sha256: str
|
||||
expected_old_execution_digest: str
|
||||
expected_new_execution_digest: str
|
||||
expected_job_id: str
|
||||
authorization_id: str
|
||||
idempotency_key: str
|
||||
reason: str
|
||||
|
||||
@classmethod
|
||||
def from_mapping(
|
||||
cls, value: Mapping[str, Any]
|
||||
) -> "SupervisorCoordinatorProjectionRequest":
|
||||
allowed = {
|
||||
"expected_status",
|
||||
"expected_revision",
|
||||
"expected_attempt",
|
||||
"expected_metadata_sha256",
|
||||
"expected_required_capabilities_sha256",
|
||||
"previous_verification_sha256",
|
||||
"expected_planner_result_sha256",
|
||||
"expected_old_execution_digest",
|
||||
"expected_new_execution_digest",
|
||||
"expected_job_id",
|
||||
"authorization_id",
|
||||
"idempotency_key",
|
||||
"reason",
|
||||
}
|
||||
if set(value) != allowed:
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_PROJECTION_FIELDS_INVALID", 400
|
||||
)
|
||||
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
|
||||
revision = value["expected_revision"]
|
||||
attempt = value["expected_attempt"]
|
||||
if (
|
||||
status != "QUEUED"
|
||||
or not isinstance(revision, int)
|
||||
or isinstance(revision, bool)
|
||||
or revision < 2
|
||||
or not isinstance(attempt, int)
|
||||
or isinstance(attempt, bool)
|
||||
or attempt < 1
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_PROJECTION_STATE_INVALID", 400
|
||||
)
|
||||
names = (
|
||||
"expected_metadata_sha256",
|
||||
"expected_required_capabilities_sha256",
|
||||
"previous_verification_sha256",
|
||||
"expected_planner_result_sha256",
|
||||
"expected_old_execution_digest",
|
||||
"expected_new_execution_digest",
|
||||
)
|
||||
digests = {
|
||||
name: _require_string(value[name], name.upper() + "_INVALID", SHA_RE)
|
||||
for name in names
|
||||
}
|
||||
job_id = _require_string(value["expected_job_id"], "JOB_ID_INVALID", JOB_RE)
|
||||
authorization_id = _require_string(
|
||||
value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE
|
||||
)
|
||||
idempotency_key = _require_string(
|
||||
value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE
|
||||
)
|
||||
reason = _require_string(value["reason"], "PROJECTION_REASON_INVALID")
|
||||
if len(reason) > 512:
|
||||
raise InitialExecutionProjectionError("PROJECTION_REASON_INVALID", 400)
|
||||
return cls(
|
||||
status,
|
||||
revision,
|
||||
attempt,
|
||||
digests["expected_metadata_sha256"],
|
||||
digests["expected_required_capabilities_sha256"],
|
||||
digests["previous_verification_sha256"],
|
||||
digests["expected_planner_result_sha256"],
|
||||
digests["expected_old_execution_digest"],
|
||||
digests["expected_new_execution_digest"],
|
||||
job_id,
|
||||
authorization_id,
|
||||
idempotency_key,
|
||||
reason,
|
||||
)
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return {
|
||||
"expected_status": self.expected_status,
|
||||
"expected_revision": self.expected_revision,
|
||||
"expected_attempt": self.expected_attempt,
|
||||
"expected_metadata_sha256": self.expected_metadata_sha256,
|
||||
"expected_required_capabilities_sha256": self.expected_required_capabilities_sha256,
|
||||
"previous_verification_sha256": self.previous_verification_sha256,
|
||||
"expected_planner_result_sha256": self.expected_planner_result_sha256,
|
||||
"expected_old_execution_digest": self.expected_old_execution_digest,
|
||||
"expected_new_execution_digest": self.expected_new_execution_digest,
|
||||
"expected_job_id": self.expected_job_id,
|
||||
"authorization_id": self.authorization_id,
|
||||
"idempotency_key": self.idempotency_key,
|
||||
"reason": self.reason,
|
||||
}
|
||||
|
||||
|
||||
class CanonicalCoordinatorExecutionResolver:
|
||||
def __init__(self, base_url: str, control_token: str) -> None:
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.control_token = control_token
|
||||
|
||||
def __call__(
|
||||
self,
|
||||
task_id: str,
|
||||
expected_job_id: str,
|
||||
runtime_input: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
body = {
|
||||
"task_id": task_id,
|
||||
"job_id": expected_job_id,
|
||||
"required_capabilities": COORDINATOR_CAPABILITIES,
|
||||
"execution": {
|
||||
"action": "agent_runtime",
|
||||
"adapter": "openclaw",
|
||||
"capability_scope": COORDINATOR_CAPABILITIES,
|
||||
"runtime_input": dict(runtime_input),
|
||||
},
|
||||
}
|
||||
request = urllib.request.Request(
|
||||
self.base_url + "/v2/execution-envelope",
|
||||
method="POST",
|
||||
data=_canonical(body),
|
||||
headers={
|
||||
"Authorization": "Bearer " + self.control_token,
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "application/json",
|
||||
},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=15) as response:
|
||||
raw, status = response.read(), response.status
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw, status = exc.read(), exc.code
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
raise InitialExecutionProjectionError(
|
||||
"CANONICAL_COORDINATOR_EXECUTION_RESPONSE_INVALID", 502
|
||||
) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise InitialExecutionProjectionError(
|
||||
"CANONICAL_COORDINATOR_EXECUTION_RESPONSE_INVALID", 502
|
||||
)
|
||||
if status != 200:
|
||||
raise InitialExecutionProjectionError(
|
||||
str(value.get("error") or "CANONICAL_COORDINATOR_EXECUTION_FAILED"),
|
||||
502 if status >= 500 else 409,
|
||||
)
|
||||
return dict(value)
|
||||
|
||||
|
||||
class SupervisorCoordinatorProjectionStore(InitialExecutionProjectionStore):
|
||||
def __init__(
|
||||
self,
|
||||
db_path: Path,
|
||||
resolver: Callable[[str, str, Mapping[str, Any]], Mapping[str, Any]],
|
||||
) -> None:
|
||||
super().__init__(db_path, resolver) # type: ignore[arg-type]
|
||||
self.coordinator_resolver = resolver
|
||||
|
||||
@staticmethod
|
||||
def _ensure_table(connection: sqlite3.Connection) -> None:
|
||||
connection.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS task_supervisor_coordinator_projections (
|
||||
task_id TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL,
|
||||
request_sha256 TEXT NOT NULL,
|
||||
authorization_id TEXT NOT NULL,
|
||||
expected_job_id TEXT NOT NULL,
|
||||
planner_result_sha256 TEXT NOT NULL,
|
||||
old_execution_digest TEXT NOT NULL,
|
||||
new_execution_digest TEXT NOT NULL,
|
||||
expected_revision INTEGER NOT NULL,
|
||||
applied_revision INTEGER NOT NULL,
|
||||
attempt INTEGER NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(task_id,idempotency_key)
|
||||
)
|
||||
"""
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def _planner_event_chain(
|
||||
cls, connection: sqlite3.Connection, task_id: str
|
||||
) -> None:
|
||||
table, columns = cls._event_table(connection)
|
||||
ordering = "event_id" if "event_id" in columns else "rowid"
|
||||
rows = connection.execute(
|
||||
f'SELECT event_type,payload_json FROM "{table}" '
|
||||
f'WHERE task_id=? ORDER BY {ordering}',
|
||||
(task_id,),
|
||||
).fetchall()
|
||||
events = [str(row[0]) for row in rows]
|
||||
try:
|
||||
projection = len(events) - 1 - events[::-1].index(
|
||||
"TASK_INITIAL_EXECUTION_PROJECTION_AUTHORIZED"
|
||||
)
|
||||
except ValueError as exc:
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_PROJECTION_EVENT_MISSING", 409
|
||||
) from exc
|
||||
tail = events[projection + 1 :]
|
||||
if (
|
||||
len(tail) < 4
|
||||
or tail[0] != "TASK_CLAIMED"
|
||||
or tail.count("TASK_CLAIMED") != 1
|
||||
or tail.count("RESULT_SUBMITTED") != 1
|
||||
or tail.count("TASK_VERIFIED") != 1
|
||||
or tail[-1] != "TASK_VERIFIED"
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_EVENT_CHAIN_INVALID", 409
|
||||
)
|
||||
result = tail.index("RESULT_SUBMITTED")
|
||||
if (
|
||||
not any(event == "TASK_HEARTBEAT" for event in tail[1:result])
|
||||
or any(
|
||||
event not in {
|
||||
"TASK_CLAIMED",
|
||||
"TASK_HEARTBEAT",
|
||||
"RESULT_SUBMITTED",
|
||||
"TASK_VERIFIED",
|
||||
}
|
||||
for event in tail
|
||||
)
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_EVENT_CHAIN_INVALID", 409
|
||||
)
|
||||
verification_event = json.loads(rows[-1][1])
|
||||
if (
|
||||
verification_event.get("decision") != "NEEDS_REWORK"
|
||||
or verification_event.get("next_state") != "QUEUED"
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_NEEDS_REWORK_EVENT_REQUIRED", 409
|
||||
)
|
||||
|
||||
def _load(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
task_id: str,
|
||||
request: SupervisorCoordinatorProjectionRequest,
|
||||
) -> tuple[sqlite3.Row, dict[str, Any], dict[str, Any]]:
|
||||
task = connection.execute(
|
||||
"SELECT * FROM tasks WHERE task_id=?", (task_id,)
|
||||
).fetchone()
|
||||
if task is None:
|
||||
raise InitialExecutionProjectionError("TASK_NOT_FOUND", 404)
|
||||
if (
|
||||
task["status"] != request.expected_status
|
||||
or int(task["revision"]) != request.expected_revision
|
||||
or int(task["attempt"]) != request.expected_attempt
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_PROJECTION_CAS_MISMATCH", 409
|
||||
)
|
||||
if (
|
||||
task["claimed_by"] not in (None, "")
|
||||
or task["lease_token_hash"] not in (None, "")
|
||||
or task["lease_expires_at"] not in (None, "")
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_ACTIVE_LEASE_DENY", 409
|
||||
)
|
||||
metadata = self._json_value(task["metadata_json"], "TASK_METADATA_INVALID")
|
||||
capabilities = self._json_value(
|
||||
task["required_capabilities_json"], "TASK_CAPABILITIES_INVALID"
|
||||
)
|
||||
result = self._json_value(task["result_json"], "PLANNER_RESULT_INVALID")
|
||||
verification = self._json_value(
|
||||
task["verification_json"], "PLANNER_VERIFICATION_INVALID"
|
||||
)
|
||||
if (
|
||||
not isinstance(metadata, Mapping)
|
||||
or not isinstance(capabilities, list)
|
||||
or not isinstance(result, Mapping)
|
||||
or not isinstance(verification, Mapping)
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_STATE_INVALID", 409
|
||||
)
|
||||
metadata, result, verification = dict(metadata), dict(result), dict(verification)
|
||||
if _sha(metadata) != request.expected_metadata_sha256:
|
||||
raise InitialExecutionProjectionError("TASK_METADATA_DRIFT", 409)
|
||||
if _sha(capabilities) != request.expected_required_capabilities_sha256:
|
||||
raise InitialExecutionProjectionError("TASK_CAPABILITIES_DRIFT", 409)
|
||||
if _sha(result) != request.expected_planner_result_sha256:
|
||||
raise InitialExecutionProjectionError("PLANNER_RESULT_DRIFT", 409)
|
||||
if _sha(verification) != request.previous_verification_sha256:
|
||||
raise InitialExecutionProjectionError("PLANNER_VERIFICATION_DRIFT", 409)
|
||||
old = metadata.get("execution")
|
||||
if not isinstance(old, Mapping):
|
||||
raise InitialExecutionProjectionError("TASK_EXECUTION_METADATA_MISSING", 409)
|
||||
old_execution = validate_execution_envelope(dict(old))
|
||||
if (
|
||||
old_execution.get("action") != "agent_runtime"
|
||||
or old_execution.get("adapter") != "openclaw"
|
||||
or old_execution.get("capability_scope") != [RUNTIME_CAPABILITY]
|
||||
or old_execution.get("execution_digest")
|
||||
!= request.expected_old_execution_digest
|
||||
or capabilities != [RUNTIME_CAPABILITY]
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_EXECUTION_CONTRACT_INVALID", 409
|
||||
)
|
||||
expected_result = {
|
||||
"task_id": task_id,
|
||||
"job_id": request.expected_job_id,
|
||||
"status": "SUCCEEDED",
|
||||
"execution_mode": "agent_runtime",
|
||||
"agent_runtime": "openclaw",
|
||||
"execution_digest": request.expected_old_execution_digest,
|
||||
"control_plane_access_granted_to_runtime": False,
|
||||
"credential_material_exposed": False,
|
||||
"secret_material_exposed": False,
|
||||
"changed_files": [],
|
||||
"writer_lease": "NONE",
|
||||
"direct_main_write": False,
|
||||
"production_write": False,
|
||||
"force_push": False,
|
||||
"protected_ref_bypass": False,
|
||||
}
|
||||
if any(result.get(name) != expected for name, expected in expected_result.items()):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_RESULT_CONTRACT_INVALID", 409
|
||||
)
|
||||
if verification.get("decision") != "NEEDS_REWORK":
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_NEEDS_REWORK_REQUIRED", 409
|
||||
)
|
||||
self._planner_event_chain(connection, task_id)
|
||||
return task, metadata, result
|
||||
|
||||
def project(
|
||||
self,
|
||||
task_id: str,
|
||||
request: SupervisorCoordinatorProjectionRequest,
|
||||
) -> dict[str, Any]:
|
||||
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
|
||||
if request.authorization_id != _required_authorization_id():
|
||||
raise InitialExecutionProjectionError("AUTHORIZATION_ID_MISMATCH", 403)
|
||||
request_sha = _sha(request.public())
|
||||
with self._connect() as connection:
|
||||
self._ensure_table(connection)
|
||||
replay = connection.execute(
|
||||
"SELECT * FROM task_supervisor_coordinator_projections "
|
||||
"WHERE task_id=? AND idempotency_key=?",
|
||||
(task_id, request.idempotency_key),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
if replay["request_sha256"] != request_sha:
|
||||
raise InitialExecutionProjectionError("IDEMPOTENCY_CONFLICT", 409)
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": replay["attempt"],
|
||||
"revision": replay["applied_revision"],
|
||||
"execution_digest": replay["new_execution_digest"],
|
||||
"required_capabilities": COORDINATOR_CAPABILITIES,
|
||||
"idempotent": True,
|
||||
}
|
||||
with self._connect() as connection:
|
||||
task, _, result = self._load(connection, task_id, request)
|
||||
runtime_input = self._runtime_input(task)
|
||||
resolved = dict(
|
||||
self.coordinator_resolver(task_id, request.expected_job_id, runtime_input)
|
||||
)
|
||||
binding = GovernedExecutionBinding.from_mapping(resolved)
|
||||
if binding.task_id != task_id or binding.job_id != request.expected_job_id:
|
||||
raise InitialExecutionProjectionError("GOVERNED_BINDING_CONFLICT", 409)
|
||||
result_binding = {
|
||||
name: result.get(name)
|
||||
for name in (
|
||||
"task_id",
|
||||
"job_id",
|
||||
"repository",
|
||||
"base_oid",
|
||||
"expected_branch_oid",
|
||||
"target_branch",
|
||||
"generation",
|
||||
)
|
||||
}
|
||||
expected_binding = {
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"repository": binding.repository,
|
||||
"base_oid": binding.base_oid,
|
||||
"expected_branch_oid": binding.expected_branch_oid,
|
||||
"target_branch": binding.target_branch,
|
||||
"generation": binding.generation,
|
||||
}
|
||||
if result_binding != expected_binding:
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_PLANNER_BINDING_CONFLICT", 409
|
||||
)
|
||||
execution = validate_execution_envelope(resolved, binding=binding)
|
||||
if (
|
||||
execution.get("action") != "agent_runtime"
|
||||
or execution.get("adapter") != "openclaw"
|
||||
or execution.get("capability_scope") != COORDINATOR_CAPABILITIES
|
||||
or execution.get("change_set") != []
|
||||
or execution.get("verification") != []
|
||||
or execution.get("governance", {}).get("writer_lease") is not False
|
||||
or execution.get("execution_digest") != request.expected_new_execution_digest
|
||||
):
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_ENVELOPE_INVALID", 409
|
||||
)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
self._ensure_table(connection)
|
||||
task, metadata, _ = self._load(connection, task_id, request)
|
||||
new_metadata = dict(metadata)
|
||||
new_metadata["execution"] = execution
|
||||
new_metadata["execution_projection"] = {
|
||||
"schema": "aios.online-agent.task-projection.v1",
|
||||
"task_id": task_id,
|
||||
"job_id": request.expected_job_id,
|
||||
"execution_digest": execution["execution_digest"],
|
||||
}
|
||||
applied_revision = request.expected_revision + 1
|
||||
cursor = connection.execute(
|
||||
"""
|
||||
UPDATE tasks SET metadata_json=?,required_capabilities_json=?,
|
||||
revision=?,updated_at=?
|
||||
WHERE task_id=? AND status=? AND revision=? AND attempt=?
|
||||
AND claimed_by IS NULL AND lease_token_hash IS NULL
|
||||
AND lease_expires_at IS NULL AND metadata_json=?
|
||||
AND required_capabilities_json=? AND result_json=?
|
||||
AND verification_json=?
|
||||
""",
|
||||
(
|
||||
json.dumps(new_metadata, sort_keys=True, separators=(",", ":")),
|
||||
json.dumps(COORDINATOR_CAPABILITIES, separators=(",", ":")),
|
||||
applied_revision,
|
||||
_now(),
|
||||
task_id,
|
||||
request.expected_status,
|
||||
request.expected_revision,
|
||||
request.expected_attempt,
|
||||
task["metadata_json"],
|
||||
task["required_capabilities_json"],
|
||||
task["result_json"],
|
||||
task["verification_json"],
|
||||
),
|
||||
)
|
||||
if cursor.rowcount != 1:
|
||||
raise InitialExecutionProjectionError(
|
||||
"SUPERVISOR_COORDINATOR_PROJECTION_CAS_MISMATCH", 409
|
||||
)
|
||||
event = {
|
||||
"schema": "aios.supervisor-coordinator-projection.event.v1",
|
||||
"task_id": task_id,
|
||||
"job_id": request.expected_job_id,
|
||||
"authorization_id": request.authorization_id,
|
||||
"idempotency_key": request.idempotency_key,
|
||||
"reason": request.reason,
|
||||
"old_execution_digest": request.expected_old_execution_digest,
|
||||
"new_execution_digest": execution["execution_digest"],
|
||||
"required_capabilities": COORDINATOR_CAPABILITIES,
|
||||
"previous_revision": request.expected_revision,
|
||||
"applied_revision": applied_revision,
|
||||
"attempt": request.expected_attempt,
|
||||
"request_sha256": request_sha,
|
||||
"credential_forwarded_to_planner": False,
|
||||
"writer_lease": False,
|
||||
"main_write": False,
|
||||
"production_write": False,
|
||||
}
|
||||
table, columns = self._event_table(connection)
|
||||
values = {
|
||||
"task_id": task_id,
|
||||
"event_type": "TASK_SUPERVISOR_COORDINATOR_PROJECTION_AUTHORIZED",
|
||||
"payload_json": json.dumps(event, sort_keys=True, separators=(",", ":")),
|
||||
"created_at": _now(),
|
||||
"agent_id": "owner-control",
|
||||
}
|
||||
names = [name for name in values if name in columns]
|
||||
connection.execute(
|
||||
f'INSERT INTO "{table}" ({",".join(chr(34)+name+chr(34) for name in names)}) '
|
||||
f'VALUES ({",".join("?" for _ in names)})',
|
||||
tuple(values[name] for name in names),
|
||||
)
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO task_supervisor_coordinator_projections(
|
||||
task_id,idempotency_key,request_sha256,authorization_id,
|
||||
expected_job_id,planner_result_sha256,old_execution_digest,
|
||||
new_execution_digest,expected_revision,applied_revision,
|
||||
attempt,created_at
|
||||
) VALUES (?,?,?,?,?,?,?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
task_id,
|
||||
request.idempotency_key,
|
||||
request_sha,
|
||||
request.authorization_id,
|
||||
request.expected_job_id,
|
||||
request.expected_planner_result_sha256,
|
||||
request.expected_old_execution_digest,
|
||||
execution["execution_digest"],
|
||||
request.expected_revision,
|
||||
applied_revision,
|
||||
request.expected_attempt,
|
||||
_now(),
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"status": "QUEUED",
|
||||
"attempt": request.expected_attempt,
|
||||
"revision": applied_revision,
|
||||
"execution_digest": execution["execution_digest"],
|
||||
"required_capabilities": COORDINATOR_CAPABILITIES,
|
||||
"credential_forwarded_to_planner": False,
|
||||
"idempotent": False,
|
||||
}
|
||||
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
store: SupervisorCoordinatorProjectionStore | None = None
|
||||
control_token: str = ""
|
||||
|
||||
def log_message(self, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def send_json(self, value: Mapping[str, Any], status: int) -> None:
|
||||
raw = _canonical(dict(value))
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(raw)))
|
||||
self.end_headers()
|
||||
self.wfile.write(raw)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/health":
|
||||
self.send_json(
|
||||
{"status": "ok", "service": "aios-supervisor-coordinator-projection"},
|
||||
200,
|
||||
)
|
||||
else:
|
||||
self.send_json({"error": "NOT_FOUND"}, 404)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
match = re.fullmatch(
|
||||
r"/v1/tasks/([^/]+)/supervisor-coordinator-projection", self.path
|
||||
)
|
||||
header = self.headers.get("Authorization", "")
|
||||
if match is None:
|
||||
self.send_json({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
if (
|
||||
not header.startswith("Bearer ")
|
||||
or not hmac.compare_digest(header[7:], self.control_token)
|
||||
):
|
||||
self.send_json({"error": "UNAUTHORIZED"}, 401)
|
||||
return
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
if length < 1 or length > MAX_BODY:
|
||||
raise InitialExecutionProjectionError("REQUEST_SIZE_INVALID", 413)
|
||||
value = json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
if not isinstance(value, Mapping) or self.store is None:
|
||||
raise InitialExecutionProjectionError("REQUEST_INVALID", 400)
|
||||
request = SupervisorCoordinatorProjectionRequest.from_mapping(value)
|
||||
result = self.store.project(match.group(1), request)
|
||||
self.send_json(result, 200 if result["idempotent"] else 201)
|
||||
except InitialExecutionProjectionError as exc:
|
||||
self.send_json({"error": exc.code}, exc.status)
|
||||
except (ValueError, UnicodeDecodeError, json.JSONDecodeError):
|
||||
self.send_json({"error": "REQUEST_INVALID"}, 400)
|
||||
|
||||
|
||||
def serve() -> None:
|
||||
credential = Path(
|
||||
os.environ.get(
|
||||
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
|
||||
str(
|
||||
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
/ "agent_task_control_token"
|
||||
),
|
||||
)
|
||||
)
|
||||
token = load_control_token(credential)
|
||||
bridge = os.environ.get("AIOS_GOVERNED_WRITE_API_URL", "http://127.0.0.1:18892")
|
||||
db = Path(os.environ.get("AIOS_AGENT_TASK_DB", "/var/lib/aios-agent-task/state.sqlite3"))
|
||||
Handler.control_token = token
|
||||
Handler.store = SupervisorCoordinatorProjectionStore(
|
||||
db, CanonicalCoordinatorExecutionResolver(bridge, token)
|
||||
)
|
||||
host = os.environ.get("AIOS_SUPERVISOR_COORDINATOR_PROJECTION_HOST", "127.0.0.1")
|
||||
port = int(os.environ.get("AIOS_SUPERVISOR_COORDINATOR_PROJECTION_PORT", "18944"))
|
||||
ThreadingHTTPServer((host, port), Handler).serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
@@ -0,0 +1,470 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Canonical AIOS all-modified-files evidence packager.
|
||||
|
||||
The bundle contract is intentionally compatible with the historical
|
||||
aios_package_all_modified_files_v1.sh output while keeping secret scanning in
|
||||
version-controlled, tested code.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timezone
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import subprocess
|
||||
import tempfile
|
||||
import zipfile
|
||||
from typing import Iterable
|
||||
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
|
||||
# A PEM private-key finding requires the complete PEM header. Source code,
|
||||
# tests, docs, or error text containing only "BEGIN PRIVATE KEY" are not
|
||||
# credentials and must not be rejected.
|
||||
PEM_PRIVATE_KEY_RE = re.compile(
|
||||
rb"-----BEGIN (?:RSA |EC |DSA |OPENSSH )?PRIVATE KEY-----",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
BEARER_RE = re.compile(
|
||||
rb"authorization\s*:\s*bearer\s+[A-Za-z0-9._~+/=-]{20,}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
KEY_VALUE_SECRET_RE = re.compile(
|
||||
rb"(?:password|passwd|secret|api[_-]?key)\s*[:=]\s*[^\s,;]{12,}",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
DOCUMENT_SUFFIXES = {".md", ".rst", ".adoc", ".txt"}
|
||||
DOCUMENT_PREFIXES = (
|
||||
"README",
|
||||
"CHANGELOG",
|
||||
"RUNBOOK",
|
||||
"ADR",
|
||||
"ARCHITECTURE",
|
||||
"DEPLOYMENT",
|
||||
"TROUBLESHOOTING",
|
||||
)
|
||||
|
||||
|
||||
class PackagerError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def sha256(data: bytes) -> str:
|
||||
return hashlib.sha256(data).hexdigest()
|
||||
|
||||
|
||||
def secret_finding(data: bytes) -> str | None:
|
||||
if PEM_PRIVATE_KEY_RE.search(data):
|
||||
return "PEM_PRIVATE_KEY"
|
||||
if BEARER_RE.search(data):
|
||||
return "AUTHORIZATION_BEARER"
|
||||
if KEY_VALUE_SECRET_RE.search(data):
|
||||
return "KEY_VALUE_SECRET"
|
||||
return None
|
||||
|
||||
|
||||
def scan_secret(data: bytes, label: str) -> None:
|
||||
finding = secret_finding(data)
|
||||
if finding is not None:
|
||||
raise PackagerError(
|
||||
f"MODIFIED_FILES_SECRET_SCAN_MATCH:{finding}:{label}"
|
||||
)
|
||||
|
||||
|
||||
def git_bytes(git_dir: Path, oid: str, path: str) -> bytes:
|
||||
try:
|
||||
return subprocess.check_output(
|
||||
[
|
||||
"/usr/bin/git",
|
||||
f"--git-dir={git_dir}",
|
||||
"show",
|
||||
f"{oid}:{path}",
|
||||
],
|
||||
timeout=30,
|
||||
)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
raise PackagerError(
|
||||
"MODIFIED_FILES_GIT_SHOW_FAILED:" + path
|
||||
) from exc
|
||||
|
||||
|
||||
def git_text(git_dir: Path, *args: str) -> str:
|
||||
try:
|
||||
return subprocess.check_output(
|
||||
["/usr/bin/git", f"--git-dir={git_dir}", *args],
|
||||
text=True,
|
||||
timeout=30,
|
||||
)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
raise PackagerError(
|
||||
"MODIFIED_FILES_GIT_COMMAND_FAILED:" + " ".join(args)
|
||||
) from exc
|
||||
|
||||
|
||||
def validate_lineage(git_dir: Path, base: str, candidate: str) -> None:
|
||||
if OID_RE.fullmatch(base) is None or OID_RE.fullmatch(candidate) is None:
|
||||
raise PackagerError("MODIFIED_FILES_OID_INVALID")
|
||||
for oid in (base, candidate):
|
||||
try:
|
||||
subprocess.run(
|
||||
[
|
||||
"/usr/bin/git",
|
||||
f"--git-dir={git_dir}",
|
||||
"cat-file",
|
||||
"-e",
|
||||
f"{oid}^{{commit}}",
|
||||
],
|
||||
check=True,
|
||||
timeout=30,
|
||||
)
|
||||
except subprocess.CalledProcessError as exc:
|
||||
raise PackagerError("MODIFIED_FILES_COMMIT_MISSING:" + oid) from exc
|
||||
if subprocess.run(
|
||||
[
|
||||
"/usr/bin/git",
|
||||
f"--git-dir={git_dir}",
|
||||
"merge-base",
|
||||
"--is-ancestor",
|
||||
base,
|
||||
candidate,
|
||||
],
|
||||
check=False,
|
||||
timeout=30,
|
||||
).returncode != 0:
|
||||
raise PackagerError("MODIFIED_FILES_LINEAGE_INVALID")
|
||||
|
||||
|
||||
def safe_destination(root: Path, relative: str) -> Path:
|
||||
path = Path(relative)
|
||||
if path.is_absolute() or ".." in path.parts:
|
||||
raise PackagerError("MODIFIED_FILE_PATH_INVALID:" + relative)
|
||||
destination = root / path
|
||||
destination.parent.mkdir(parents=True, exist_ok=True)
|
||||
return destination
|
||||
|
||||
|
||||
def is_document_path(path: str) -> bool:
|
||||
value = Path(path)
|
||||
if path.startswith("docs/"):
|
||||
return True
|
||||
if value.suffix.lower() in DOCUMENT_SUFFIXES:
|
||||
return True
|
||||
upper = value.name.upper()
|
||||
return any(upper.startswith(prefix) for prefix in DOCUMENT_PREFIXES)
|
||||
|
||||
|
||||
def diff_entries(
|
||||
git_dir: Path,
|
||||
base: str,
|
||||
candidate: str,
|
||||
before_root: Path,
|
||||
after_root: Path,
|
||||
) -> list[dict[str, object]]:
|
||||
raw = git_text(
|
||||
git_dir,
|
||||
"diff",
|
||||
"--name-status",
|
||||
"-M",
|
||||
"-C",
|
||||
base,
|
||||
candidate,
|
||||
)
|
||||
entries: list[dict[str, object]] = []
|
||||
for line in raw.splitlines():
|
||||
if not line.strip():
|
||||
continue
|
||||
parts = line.split("\t")
|
||||
status = parts[0]
|
||||
code = status[0]
|
||||
old_path: str | None = None
|
||||
new_path: str | None = None
|
||||
if code in {"R", "C"}:
|
||||
if len(parts) != 3:
|
||||
raise PackagerError(
|
||||
"MODIFIED_FILES_DIFF_PARSE_INVALID:" + line
|
||||
)
|
||||
old_path, new_path = parts[1], parts[2]
|
||||
else:
|
||||
if len(parts) != 2:
|
||||
raise PackagerError(
|
||||
"MODIFIED_FILES_DIFF_PARSE_INVALID:" + line
|
||||
)
|
||||
new_path = parts[1] if code != "D" else None
|
||||
old_path = parts[1] if code != "A" else None
|
||||
|
||||
entry: dict[str, object] = {"status": status}
|
||||
if old_path is not None:
|
||||
entry["previous_path"] = old_path
|
||||
before = git_bytes(git_dir, base, old_path)
|
||||
scan_secret(before, "before:" + old_path)
|
||||
safe_destination(before_root, old_path).write_bytes(before)
|
||||
entry["before_sha256"] = sha256(before)
|
||||
entry["before_bytes"] = len(before)
|
||||
if new_path is not None:
|
||||
entry["path"] = new_path
|
||||
after = git_bytes(git_dir, candidate, new_path)
|
||||
scan_secret(after, "after:" + new_path)
|
||||
safe_destination(after_root, new_path).write_bytes(after)
|
||||
entry["after_sha256"] = sha256(after)
|
||||
entry["after_bytes"] = len(after)
|
||||
entry["deleted"] = code == "D"
|
||||
entry["added"] = code == "A"
|
||||
entry["renamed"] = code == "R"
|
||||
entry["copied"] = code == "C"
|
||||
entries.append(entry)
|
||||
return entries
|
||||
|
||||
|
||||
def execution_entries(
|
||||
extra_root: Path | None,
|
||||
execution_root: Path,
|
||||
) -> list[dict[str, object]]:
|
||||
if extra_root is None or not extra_root.exists():
|
||||
return []
|
||||
if extra_root.is_symlink() or not extra_root.is_dir():
|
||||
raise PackagerError("EXTRA_FILES_DIR_INVALID")
|
||||
|
||||
entries: list[dict[str, object]] = []
|
||||
for path in sorted(extra_root.rglob("*")):
|
||||
if path.is_symlink():
|
||||
raise PackagerError(
|
||||
"EXTRA_FILE_SYMLINK_REJECTED:" + str(path)
|
||||
)
|
||||
if not path.is_file():
|
||||
continue
|
||||
relative = path.relative_to(extra_root).as_posix()
|
||||
data = path.read_bytes()
|
||||
scan_secret(data, "execution:" + relative)
|
||||
safe_destination(execution_root, relative).write_bytes(data)
|
||||
entries.append(
|
||||
{
|
||||
"path": relative,
|
||||
"sha256": sha256(data),
|
||||
"bytes": len(data),
|
||||
}
|
||||
)
|
||||
return entries
|
||||
|
||||
|
||||
def write_checksums(bundle: Path) -> None:
|
||||
checks: list[tuple[str, str]] = []
|
||||
for path in sorted(bundle.rglob("*")):
|
||||
if path.is_file() and path.name != "checksums.sha256":
|
||||
checks.append(
|
||||
(
|
||||
sha256(path.read_bytes()),
|
||||
path.relative_to(bundle).as_posix(),
|
||||
)
|
||||
)
|
||||
(bundle / "checksums.sha256").write_text(
|
||||
"".join(f"{digest} {name}\n" for digest, name in checks),
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
|
||||
def verify_checksums(bundle: Path) -> None:
|
||||
checksum_path = bundle / "checksums.sha256"
|
||||
for line in checksum_path.read_text(encoding="utf-8").splitlines():
|
||||
digest, relative = line.split(" ", 1)
|
||||
path = bundle / relative
|
||||
if not path.is_file() or sha256(path.read_bytes()) != digest:
|
||||
raise PackagerError(
|
||||
"MODIFIED_FILES_CHECKSUM_CLOSURE_INVALID:" + relative
|
||||
)
|
||||
|
||||
|
||||
def build_bundle(
|
||||
*,
|
||||
git_dir: Path,
|
||||
base: str,
|
||||
candidate: str,
|
||||
task_id: str,
|
||||
extra_dir: Path | None = None,
|
||||
output_root: Path | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> dict[str, object]:
|
||||
if TASK_RE.fullmatch(task_id) is None:
|
||||
raise PackagerError("TASK_ID_INVALID")
|
||||
validate_lineage(git_dir, base, candidate)
|
||||
|
||||
timestamp = (now or datetime.now(timezone.utc)).strftime(
|
||||
"%Y%m%dT%H%M%SZ"
|
||||
)
|
||||
safe_task = re.sub(r"[^A-Za-z0-9._-]+", "-", task_id).strip("-")
|
||||
if output_root is None:
|
||||
output_root = Path(
|
||||
tempfile.mkdtemp(
|
||||
prefix=f"aios-modified-files-bundle-{safe_task}-{timestamp}-",
|
||||
dir="/var/tmp",
|
||||
)
|
||||
)
|
||||
else:
|
||||
output_root.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
bundle = output_root / "bundle"
|
||||
before_root = bundle / "repo" / "before"
|
||||
after_root = bundle / "repo" / "after"
|
||||
execution_root = bundle / "execution"
|
||||
before_root.mkdir(parents=True)
|
||||
after_root.mkdir(parents=True)
|
||||
execution_root.mkdir(parents=True)
|
||||
|
||||
changes = diff_entries(
|
||||
git_dir,
|
||||
base,
|
||||
candidate,
|
||||
before_root,
|
||||
after_root,
|
||||
)
|
||||
execution_files = execution_entries(extra_dir, execution_root)
|
||||
|
||||
document_changes = [
|
||||
entry
|
||||
for entry in changes
|
||||
if is_document_path(
|
||||
str(entry.get("path") or entry.get("previous_path") or "")
|
||||
)
|
||||
]
|
||||
execution_documents = [
|
||||
entry
|
||||
for entry in execution_files
|
||||
if is_document_path(str(entry["path"]))
|
||||
]
|
||||
|
||||
documents_index = {
|
||||
"schema": "aios.modified-documents.index.v1",
|
||||
"task_id": task_id,
|
||||
"base_oid": base,
|
||||
"candidate_oid": candidate,
|
||||
"repository_documents": document_changes,
|
||||
"execution_documents": execution_documents,
|
||||
"repository_document_count": len(document_changes),
|
||||
"execution_document_count": len(execution_documents),
|
||||
}
|
||||
(bundle / "documents-index.json").write_text(
|
||||
json.dumps(documents_index, indent=2, sort_keys=True) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
|
||||
manifest = {
|
||||
"schema": "aios.all-modified-files.bundle.v1",
|
||||
"task_id": task_id,
|
||||
"base_oid": base,
|
||||
"candidate_oid": candidate,
|
||||
"generated_at": (
|
||||
now or datetime.now(timezone.utc)
|
||||
).isoformat(),
|
||||
"changed_file_count": len(changes),
|
||||
"execution_file_count": len(execution_files),
|
||||
"repository_document_count": len(document_changes),
|
||||
"execution_document_count": len(execution_documents),
|
||||
"changes": changes,
|
||||
"execution_files": execution_files,
|
||||
}
|
||||
(bundle / "all-modified-files-manifest.json").write_text(
|
||||
json.dumps(manifest, indent=2, sort_keys=True) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
write_checksums(bundle)
|
||||
verify_checksums(bundle)
|
||||
|
||||
zip_name = (
|
||||
f"AIOS_{task_id}_ALL_MODIFIED_FILES_{candidate[:12]}.zip"
|
||||
.replace("/", "-")
|
||||
)
|
||||
zip_path = output_root / zip_name
|
||||
with zipfile.ZipFile(
|
||||
zip_path,
|
||||
"w",
|
||||
compression=zipfile.ZIP_DEFLATED,
|
||||
) as archive:
|
||||
for path in sorted(bundle.rglob("*")):
|
||||
if path.is_symlink():
|
||||
raise PackagerError(
|
||||
"BUNDLE_SYMLINK_REJECTED:" + str(path)
|
||||
)
|
||||
if path.is_file():
|
||||
archive.write(
|
||||
path,
|
||||
arcname=path.relative_to(bundle).as_posix(),
|
||||
)
|
||||
|
||||
zip_sha = sha256(zip_path.read_bytes())
|
||||
summary = {
|
||||
"schema": "aios.all-modified-files.bundle-summary.v1",
|
||||
"task_id": task_id,
|
||||
"base_oid": base,
|
||||
"candidate_oid": candidate,
|
||||
"bundle_path": str(zip_path),
|
||||
"bundle_sha256": zip_sha,
|
||||
"changed_file_count": len(changes),
|
||||
"execution_file_count": len(execution_files),
|
||||
"repository_document_count": len(document_changes),
|
||||
"execution_document_count": len(execution_documents),
|
||||
}
|
||||
(output_root / "ALL_MODIFIED_FILES_BUNDLE.json").write_text(
|
||||
json.dumps(summary, indent=2, sort_keys=True) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
return summary
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("base")
|
||||
parser.add_argument("candidate")
|
||||
parser.add_argument("task_id")
|
||||
parser.add_argument("extra_dir", nargs="?")
|
||||
parser.add_argument(
|
||||
"--authority-git-dir",
|
||||
default=os.environ.get(
|
||||
"AIOS_AUTHORITY_GIT_DIR",
|
||||
"/data/aios-gitops/repo.git",
|
||||
),
|
||||
)
|
||||
parser.add_argument("--output-root")
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
summary = build_bundle(
|
||||
git_dir=Path(args.authority_git_dir),
|
||||
base=args.base,
|
||||
candidate=args.candidate,
|
||||
task_id=args.task_id,
|
||||
extra_dir=Path(args.extra_dir) if args.extra_dir else None,
|
||||
output_root=(
|
||||
Path(args.output_root) if args.output_root else None
|
||||
),
|
||||
)
|
||||
except PackagerError as exc:
|
||||
print("FATAL:" + str(exc))
|
||||
return 20
|
||||
|
||||
print("ALL_MODIFIED_FILES_BUNDLE=PASS")
|
||||
print("ALL_MODIFIED_FILES_BUNDLE_PATH=" + str(summary["bundle_path"]))
|
||||
print("ALL_MODIFIED_FILES_BUNDLE_SHA256=" + str(summary["bundle_sha256"]))
|
||||
print("CHANGED_FILE_COUNT=" + str(summary["changed_file_count"]))
|
||||
print("EXECUTION_FILE_COUNT=" + str(summary["execution_file_count"]))
|
||||
print(
|
||||
"REPOSITORY_DOCUMENT_COUNT="
|
||||
+ str(summary["repository_document_count"])
|
||||
)
|
||||
print(
|
||||
"EXECUTION_DOCUMENT_COUNT="
|
||||
+ str(summary["execution_document_count"])
|
||||
)
|
||||
print(
|
||||
"ALL_MODIFIED_FILES_EVIDENCE="
|
||||
+ str(Path(str(summary["bundle_path"])).parent)
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -94,6 +94,91 @@ class AuthorityGitExecutor:
|
||||
self._git(["worktree", "add", "--detach", str(path), base_oid])
|
||||
return path
|
||||
|
||||
def recover_failed_detached_worktree_exact(
|
||||
self,
|
||||
*,
|
||||
path: Path,
|
||||
expected_oid: str,
|
||||
stale_oid: str,
|
||||
target_ref: str,
|
||||
) -> str:
|
||||
"""Recreate one exact clean, detached, single-attempt worktree at its durable head."""
|
||||
_oid(expected_oid, "expected_oid")
|
||||
_oid(stale_oid, "stale_oid")
|
||||
if not TASK_BRANCH_RE.fullmatch(target_ref):
|
||||
raise AuthorityGitError("TASK_BRANCH_SCOPE_DENIED")
|
||||
if self.read_ref(target_ref) is not None:
|
||||
raise AuthorityGitError("AUTHORITY_TARGET_BRANCH_ALREADY_EXISTS")
|
||||
if (
|
||||
not path.is_absolute()
|
||||
or path.parent != self.worktree_root
|
||||
or path.name in {"", ".", ".."}
|
||||
or path.is_symlink()
|
||||
or not path.is_dir()
|
||||
):
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_PATH_INVALID")
|
||||
head = subprocess.run(
|
||||
["git", "-C", str(path), "rev-parse", "HEAD"],
|
||||
text=True, capture_output=True, check=False,
|
||||
)
|
||||
if head.returncode != 0 or head.stdout.strip() != stale_oid or stale_oid == expected_oid:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_HEAD_INVALID")
|
||||
symbolic = subprocess.run(
|
||||
["git", "-C", str(path), "symbolic-ref", "-q", "HEAD"],
|
||||
text=True, capture_output=True, check=False,
|
||||
)
|
||||
if symbolic.returncode != 1:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_NOT_DETACHED")
|
||||
status = subprocess.run(
|
||||
["git", "-C", str(path), "status", "--porcelain=v1", "--untracked-files=all"],
|
||||
text=True, capture_output=True, check=False,
|
||||
)
|
||||
if status.returncode != 0 or status.stdout:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_NOT_CLEAN")
|
||||
parents = self._git(["rev-list", "--parents", "-n", "1", stale_oid]).split()
|
||||
if parents != [stale_oid, expected_oid]:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_LINEAGE_INVALID")
|
||||
registered = [
|
||||
line.removeprefix("worktree ")
|
||||
for line in self._git(["worktree", "list", "--porcelain"]).splitlines()
|
||||
if line.startswith("worktree ")
|
||||
]
|
||||
if registered.count(str(path)) != 1:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_REGISTRATION_INVALID")
|
||||
self._git(["worktree", "remove", "--force", str(path)])
|
||||
if path.exists() or path.is_symlink():
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_REMOVE_FAILED")
|
||||
recreated = self.create_detached_worktree(expected_oid, path.name, path.parent)
|
||||
readback = subprocess.run(
|
||||
["git", "-C", str(recreated), "rev-parse", "HEAD"],
|
||||
text=True, capture_output=True, check=False,
|
||||
)
|
||||
detached = subprocess.run(
|
||||
["git", "-C", str(recreated), "symbolic-ref", "-q", "HEAD"],
|
||||
text=True, capture_output=True, check=False,
|
||||
)
|
||||
if readback.returncode != 0 or readback.stdout.strip() != expected_oid or detached.returncode != 1:
|
||||
raise AuthorityGitError("WORKTREE_RECOVERY_READBACK_MISMATCH")
|
||||
return stale_oid
|
||||
|
||||
def create_task_branch_CAS(self, branch: str, expected_base_oid: str, new_oid: str) -> str:
|
||||
if not TASK_BRANCH_RE.fullmatch(branch):
|
||||
raise AuthorityGitError("TASK_BRANCH_SCOPE_DENIED")
|
||||
_oid(expected_base_oid, "expected_base_oid")
|
||||
_oid(new_oid, "new_oid")
|
||||
current = self.read_ref(branch)
|
||||
if current is not None:
|
||||
if current == new_oid:
|
||||
return new_oid
|
||||
raise AuthorityGitError("AUTHORITY_TARGET_BRANCH_ALREADY_EXISTS")
|
||||
if not self.ancestry_check(expected_base_oid, new_oid):
|
||||
raise AuthorityGitError("NEW_OID_NOT_DESCENDANT")
|
||||
self._git(["update-ref", branch, new_oid, "0" * 40])
|
||||
readback = self.read_ref(branch)
|
||||
if readback != new_oid:
|
||||
raise AuthorityGitError("AUTHORITY_CREATE_READBACK_MISMATCH")
|
||||
return readback
|
||||
|
||||
def advance_task_branch_CAS(self, branch: str, expected_oid: str, new_oid: str) -> str:
|
||||
if not TASK_BRANCH_RE.fullmatch(branch):
|
||||
raise AuthorityGitError("TASK_BRANCH_SCOPE_DENIED")
|
||||
|
||||
@@ -0,0 +1,288 @@
|
||||
"""Unified autonomous control-plane primitives.
|
||||
|
||||
This is deliberately a library, not another daemon. Task API, workers and host
|
||||
recovery code consume the same Admission -> Invariant -> Repair semantics.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass
|
||||
from enum import Enum
|
||||
import re
|
||||
from typing import Callable, Iterable, Mapping, Sequence
|
||||
|
||||
from aios_capability_contract import (
|
||||
capability_contract,
|
||||
has_capabilities,
|
||||
normalize_required_capabilities,
|
||||
normalize_worker_capabilities,
|
||||
registered_capability,
|
||||
validate_capability_contract_registry,
|
||||
)
|
||||
|
||||
|
||||
class FailureClass(str, Enum):
|
||||
CAPABILITY_CONTRACT_ERROR = "CAPABILITY_CONTRACT_ERROR"
|
||||
CREDENTIAL_PROJECTION_ERROR = "CREDENTIAL_PROJECTION_ERROR"
|
||||
DEPENDENCY_UNAVAILABLE = "DEPENDENCY_UNAVAILABLE"
|
||||
POLICY_DENIED = "POLICY_DENIED"
|
||||
RESOURCE_UNAVAILABLE = "RESOURCE_UNAVAILABLE"
|
||||
WORKER_CRASH = "WORKER_CRASH"
|
||||
LEASE_LOST = "LEASE_LOST"
|
||||
BUSINESS_PERMANENT = "BUSINESS_PERMANENT"
|
||||
UNKNOWN = "UNKNOWN"
|
||||
|
||||
|
||||
class RepairLevel(int, Enum):
|
||||
AUTO_LOCAL = 0
|
||||
AUTO_REPAIR_TASK = 1
|
||||
OWNER_APPROVAL = 2
|
||||
MANUAL = 3
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class InvariantResult:
|
||||
name: str
|
||||
passed: bool
|
||||
detail: str = ""
|
||||
|
||||
def as_dict(self) -> dict[str, object]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class AdmissionDecision:
|
||||
admitted: bool
|
||||
state: str
|
||||
invariants: tuple[InvariantResult, ...]
|
||||
failure_class: FailureClass | None = None
|
||||
repair_level: RepairLevel | None = None
|
||||
repair_action: str | None = None
|
||||
|
||||
def as_dict(self) -> dict[str, object]:
|
||||
return {
|
||||
"schema": "aios.runtime-admission.decision.v1",
|
||||
"admitted": self.admitted,
|
||||
"state": self.state,
|
||||
"invariants": [item.as_dict() for item in self.invariants],
|
||||
"failure_class": None if self.failure_class is None else self.failure_class.value,
|
||||
"repair_level": None if self.repair_level is None else int(self.repair_level),
|
||||
"repair_action": self.repair_action,
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RepairDecision:
|
||||
failure_class: FailureClass
|
||||
level: RepairLevel
|
||||
action: str
|
||||
consumes_business_attempt: bool
|
||||
|
||||
def as_dict(self) -> dict[str, object]:
|
||||
return {
|
||||
"failure_class": self.failure_class.value,
|
||||
"level": int(self.level),
|
||||
"action": self.action,
|
||||
"consumes_business_attempt": self.consumes_business_attempt,
|
||||
}
|
||||
|
||||
|
||||
def classify_failure(error: object, *, phase: str = "") -> FailureClass:
|
||||
text = (str(error) + " " + str(phase)).lower()
|
||||
if any(token in text for token in (
|
||||
"credential", "permission denied", "token registry", "secret", "unauthorized"
|
||||
)):
|
||||
return FailureClass.CREDENTIAL_PROJECTION_ERROR
|
||||
if any(token in text for token in (
|
||||
"transport", "unavailable", "timeout", "connection", "bad gateway", "http_5"
|
||||
)):
|
||||
return FailureClass.DEPENDENCY_UNAVAILABLE
|
||||
if any(token in text for token in (
|
||||
"capability", "eligible", "matcher", "contract"
|
||||
)):
|
||||
return FailureClass.CAPABILITY_CONTRACT_ERROR
|
||||
if any(token in text for token in (
|
||||
"policy", "forbidden", "approval required", "not authorized"
|
||||
)):
|
||||
return FailureClass.POLICY_DENIED
|
||||
if any(token in text for token in ("lease lost", "lease_expired", "heartbeat_failed")):
|
||||
return FailureClass.LEASE_LOST
|
||||
if any(token in text for token in ("out of memory", "disk full", "resource")):
|
||||
return FailureClass.RESOURCE_UNAVAILABLE
|
||||
if any(token in text for token in ("worker crash", "process exited", "signal")):
|
||||
return FailureClass.WORKER_CRASH
|
||||
if any(token in text for token in ("invalid release", "business permanent")):
|
||||
return FailureClass.BUSINESS_PERMANENT
|
||||
return FailureClass.UNKNOWN
|
||||
|
||||
|
||||
def repair_for_failure(failure: FailureClass) -> RepairDecision:
|
||||
table = {
|
||||
FailureClass.CAPABILITY_CONTRACT_ERROR: RepairDecision(
|
||||
failure, RepairLevel.AUTO_REPAIR_TASK,
|
||||
"create_same_lineage_capability_contract_repair", False,
|
||||
),
|
||||
FailureClass.CREDENTIAL_PROJECTION_ERROR: RepairDecision(
|
||||
failure, RepairLevel.AUTO_REPAIR_TASK,
|
||||
"restore_service_private_credential_projection", False,
|
||||
),
|
||||
FailureClass.DEPENDENCY_UNAVAILABLE: RepairDecision(
|
||||
failure, RepairLevel.AUTO_LOCAL,
|
||||
"retry_dependency_health_and_resume", False,
|
||||
),
|
||||
FailureClass.RESOURCE_UNAVAILABLE: RepairDecision(
|
||||
failure, RepairLevel.AUTO_LOCAL,
|
||||
"heal_runtime_resource_and_resume", False,
|
||||
),
|
||||
FailureClass.WORKER_CRASH: RepairDecision(
|
||||
failure, RepairLevel.AUTO_LOCAL,
|
||||
"restart_worker_and_resume_same_lineage", False,
|
||||
),
|
||||
FailureClass.LEASE_LOST: RepairDecision(
|
||||
failure, RepairLevel.AUTO_LOCAL,
|
||||
"recover_lease_and_resume_same_lineage", False,
|
||||
),
|
||||
FailureClass.POLICY_DENIED: RepairDecision(
|
||||
failure, RepairLevel.OWNER_APPROVAL,
|
||||
"request_bound_owner_authorization", False,
|
||||
),
|
||||
FailureClass.BUSINESS_PERMANENT: RepairDecision(
|
||||
failure, RepairLevel.MANUAL,
|
||||
"terminal_business_failure", True,
|
||||
),
|
||||
FailureClass.UNKNOWN: RepairDecision(
|
||||
failure, RepairLevel.AUTO_REPAIR_TASK,
|
||||
"create_diagnostic_repair_task", False,
|
||||
),
|
||||
}
|
||||
return table[failure]
|
||||
|
||||
|
||||
def _probe(
|
||||
name: str,
|
||||
probes: Mapping[str, Callable[[], bool]],
|
||||
) -> InvariantResult:
|
||||
fn = probes.get(name)
|
||||
if fn is None:
|
||||
return InvariantResult(name, False, "PROBE_MISSING")
|
||||
try:
|
||||
passed = bool(fn())
|
||||
except Exception as exc:
|
||||
return InvariantResult(name, False, "PROBE_ERROR:" + type(exc).__name__)
|
||||
return InvariantResult(name, passed, "PASS" if passed else "NOT_READY")
|
||||
|
||||
|
||||
def runtime_admission(
|
||||
*,
|
||||
worker_capabilities: Iterable[object],
|
||||
required_capabilities: Iterable[object],
|
||||
requested_operations: Sequence[str] = (),
|
||||
probes: Mapping[str, Callable[[], bool]] | None = None,
|
||||
) -> AdmissionDecision:
|
||||
"""Admission is evaluated before claim; failures do not consume attempts."""
|
||||
|
||||
worker_values = tuple(worker_capabilities)
|
||||
required_values = tuple(required_capabilities)
|
||||
probe_map = probes or {}
|
||||
invariants: list[InvariantResult] = []
|
||||
|
||||
registry = validate_capability_contract_registry()
|
||||
invariants.append(InvariantResult(
|
||||
"capability_contract_registry",
|
||||
bool(registry.get("valid")),
|
||||
"PASS" if registry.get("valid") else "REGISTRY_INVALID",
|
||||
))
|
||||
|
||||
task_known = all(registered_capability(item) for item in required_values)
|
||||
worker_known = all(registered_capability(item, worker=True) for item in worker_values)
|
||||
invariants.extend((
|
||||
InvariantResult("task_capabilities_registered", task_known, "PASS" if task_known else "UNKNOWN_TASK_CAPABILITY"),
|
||||
InvariantResult("worker_capabilities_registered", worker_known, "PASS" if worker_known else "UNKNOWN_WORKER_CAPABILITY"),
|
||||
))
|
||||
|
||||
capability_match = (
|
||||
task_known
|
||||
and worker_known
|
||||
and has_capabilities(worker_values, required_values)
|
||||
)
|
||||
invariants.append(InvariantResult(
|
||||
"capability_match",
|
||||
capability_match,
|
||||
"PASS" if capability_match else "WORKER_NOT_ELIGIBLE",
|
||||
))
|
||||
|
||||
normalized = normalize_required_capabilities(required_values)
|
||||
contracts = [
|
||||
capability_contract(item)
|
||||
for item in normalized
|
||||
if not str(item).startswith("exact:")
|
||||
]
|
||||
contracts = [item for item in contracts if item is not None]
|
||||
|
||||
forbidden: set[str] = set()
|
||||
dependencies: set[str] = set()
|
||||
health: set[str] = set()
|
||||
for contract in contracts:
|
||||
forbidden.update(contract.forbidden)
|
||||
dependencies.update(contract.dependencies)
|
||||
health.update(contract.health_requirements)
|
||||
|
||||
requested = {str(item).strip().lower() for item in requested_operations if str(item).strip()}
|
||||
forbidden_hit = sorted(requested & {item.lower() for item in forbidden})
|
||||
invariants.append(InvariantResult(
|
||||
"forbidden_operations_absent",
|
||||
not forbidden_hit,
|
||||
"PASS" if not forbidden_hit else "FORBIDDEN:" + ",".join(forbidden_hit),
|
||||
))
|
||||
|
||||
for name in sorted(dependencies | health):
|
||||
invariants.append(_probe(name, probe_map))
|
||||
|
||||
failed = [item for item in invariants if not item.passed]
|
||||
if not failed:
|
||||
return AdmissionDecision(
|
||||
True,
|
||||
"EXECUTION_READY",
|
||||
tuple(invariants),
|
||||
)
|
||||
|
||||
details = " ".join(item.name + ":" + item.detail for item in failed)
|
||||
failure = classify_failure(details, phase="admission")
|
||||
if any(item.name == "forbidden_operations_absent" and not item.passed for item in failed):
|
||||
failure = FailureClass.POLICY_DENIED
|
||||
elif any("credential" in item.name for item in failed):
|
||||
failure = FailureClass.CREDENTIAL_PROJECTION_ERROR
|
||||
elif any(item.name in {"capability_contract_registry", "task_capabilities_registered", "worker_capabilities_registered", "capability_match"} for item in failed):
|
||||
failure = FailureClass.CAPABILITY_CONTRACT_ERROR
|
||||
elif any(item.name in dependencies or item.name in health for item in failed):
|
||||
failure = FailureClass.DEPENDENCY_UNAVAILABLE
|
||||
|
||||
repair = repair_for_failure(failure)
|
||||
return AdmissionDecision(
|
||||
False,
|
||||
"EXECUTION_READY_FAILED",
|
||||
tuple(invariants),
|
||||
failure,
|
||||
repair.level,
|
||||
repair.action,
|
||||
)
|
||||
|
||||
|
||||
def system_invariant_snapshot(
|
||||
*,
|
||||
worker_capabilities: Iterable[object],
|
||||
required_capabilities: Iterable[object],
|
||||
requested_operations: Sequence[str] = (),
|
||||
probes: Mapping[str, Callable[[], bool]] | None = None,
|
||||
) -> dict[str, object]:
|
||||
decision = runtime_admission(
|
||||
worker_capabilities=worker_capabilities,
|
||||
required_capabilities=required_capabilities,
|
||||
requested_operations=requested_operations,
|
||||
probes=probes,
|
||||
)
|
||||
return {
|
||||
"schema": "aios.system-invariants.v1",
|
||||
"status": "HEALTHY" if decision.admitted else "DEGRADED",
|
||||
"execution_ready": decision.admitted,
|
||||
"admission": decision.as_dict(),
|
||||
}
|
||||
@@ -0,0 +1,142 @@
|
||||
"""Private Unix-socket caller projection and rehydration client.
|
||||
|
||||
The broker response body is deliberately public metadata only. The short-lived
|
||||
credential projection is delivered in a private response header, consumed
|
||||
inside the model API process, and never returned by an HTTP API or persisted.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
import hashlib
|
||||
import http.client
|
||||
import json
|
||||
from pathlib import Path
|
||||
import socket
|
||||
from typing import Any, Mapping
|
||||
|
||||
CALLER = "chatgpt-governed-implementer-singlehost"
|
||||
SCOPE = "release:candidate"
|
||||
GOVERNED_TASK_SCOPE = "governed-task:project"
|
||||
PROJECTED_SCOPES = frozenset({GOVERNED_TASK_SCOPE, SCOPE})
|
||||
CREDENTIAL_HEADER = "X-AIOS-Caller-Projection-Credential"
|
||||
|
||||
|
||||
class CallerProjectionError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 503) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProjectionResult:
|
||||
public: dict[str, Any]
|
||||
credential_loaded: bool
|
||||
|
||||
|
||||
class _UnixHTTPConnection(http.client.HTTPConnection):
|
||||
def __init__(self, socket_path: Path, timeout: float) -> None:
|
||||
super().__init__("localhost", timeout=timeout)
|
||||
self.socket_path = socket_path
|
||||
|
||||
def connect(self) -> None:
|
||||
sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
|
||||
sock.settimeout(self.timeout)
|
||||
try:
|
||||
sock.connect(str(self.socket_path))
|
||||
except Exception:
|
||||
sock.close()
|
||||
raise
|
||||
self.sock = sock
|
||||
|
||||
|
||||
class CallerProjectionClient:
|
||||
def __init__(self, socket_path: Path, *, timeout: float = 2.0) -> None:
|
||||
self.socket_path = Path(socket_path)
|
||||
self.timeout = timeout
|
||||
|
||||
@staticmethod
|
||||
def _idempotency_key(caller: str, scope: str) -> str:
|
||||
digest = hashlib.sha256((caller + "\0" + scope).encode()).hexdigest()
|
||||
return "caller-projection-" + digest[:32] + "-v1"
|
||||
|
||||
def rehydrate(
|
||||
self,
|
||||
caller: str,
|
||||
scope: str,
|
||||
request: Mapping[str, Any] | None = None,
|
||||
) -> ProjectionResult:
|
||||
if caller != CALLER:
|
||||
raise CallerProjectionError("CALLER_MISMATCH", 403)
|
||||
if scope not in PROJECTED_SCOPES:
|
||||
raise CallerProjectionError("SCOPE_MISMATCH", 403)
|
||||
body = {
|
||||
"caller": caller,
|
||||
"scope": scope,
|
||||
"idempotency_key": self._idempotency_key(caller, scope),
|
||||
"request": dict(request or {}),
|
||||
}
|
||||
connection = _UnixHTTPConnection(self.socket_path, self.timeout)
|
||||
try:
|
||||
connection.request(
|
||||
"POST",
|
||||
"/v1/project-caller",
|
||||
body=json.dumps(body, sort_keys=True, separators=(",", ":")).encode(),
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "application/json",
|
||||
"X-AIOS-Account": caller,
|
||||
},
|
||||
)
|
||||
response = connection.getresponse()
|
||||
status = response.status
|
||||
raw = response.read()
|
||||
credential = response.getheader(CREDENTIAL_HEADER, "")
|
||||
except (OSError, TimeoutError, http.client.HTTPException) as exc:
|
||||
raise CallerProjectionError("PROJECTION_BROKER_UNAVAILABLE", 503) from exc
|
||||
finally:
|
||||
connection.close()
|
||||
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except Exception as exc:
|
||||
raise CallerProjectionError("PROJECTION_RESPONSE_INVALID", 503) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise CallerProjectionError("PROJECTION_RESPONSE_INVALID", 503)
|
||||
if status != 200:
|
||||
code = str(value.get("error") or "PROJECTION_DENIED")
|
||||
raise CallerProjectionError(code, 403 if status < 500 else 503)
|
||||
if any(
|
||||
str(key).lower() in {
|
||||
"credential",
|
||||
"credential_material",
|
||||
"token",
|
||||
"bearer",
|
||||
"secret",
|
||||
"password",
|
||||
}
|
||||
for key in value
|
||||
):
|
||||
raise CallerProjectionError("PROJECTION_SECRET_FIELD_REJECTED", 503)
|
||||
if value.get("caller") != CALLER or value.get("scope") != scope:
|
||||
raise CallerProjectionError("PROJECTION_BINDING_INVALID", 503)
|
||||
if value.get("projection_state") != "ACKED":
|
||||
raise CallerProjectionError("PROJECTION_STATE_INVALID", 503)
|
||||
if value.get("credential_state") != "REHYDRATED":
|
||||
raise CallerProjectionError("CREDENTIAL_REHYDRATION_INVALID", 503)
|
||||
if value.get("rehydration_state") not in {"GENERATED", "RECOVERED"}:
|
||||
raise CallerProjectionError("REHYDRATION_STATE_INVALID", 503)
|
||||
effective_scopes = value.get("effective_scopes")
|
||||
if (
|
||||
not isinstance(effective_scopes, list)
|
||||
or len(effective_scopes) != len(set(effective_scopes))
|
||||
or not all(isinstance(item, str) for item in effective_scopes)
|
||||
or scope not in effective_scopes
|
||||
or not set(effective_scopes).issubset(PROJECTED_SCOPES)
|
||||
):
|
||||
raise CallerProjectionError("PROJECTION_SCOPE_INVALID", 503)
|
||||
if value.get("secret_exposed") is not False:
|
||||
raise CallerProjectionError("PROJECTION_SECRET_EXPOSURE", 503)
|
||||
if not isinstance(credential, str) or len(credential) < 32:
|
||||
raise CallerProjectionError("CREDENTIAL_REHYDRATION_MISSING", 503)
|
||||
return ProjectionResult(public=dict(value), credential_loaded=True)
|
||||
@@ -0,0 +1,341 @@
|
||||
"""Canonical fail-closed capability semantics for task eligibility."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Iterable
|
||||
from dataclasses import asdict, dataclass
|
||||
from typing import Any
|
||||
|
||||
|
||||
_TASK_ALIASES: dict[str, frozenset[str]] = {
|
||||
"repository_read": frozenset({"repo.read"}),
|
||||
"git.read": frozenset({"repo.read"}),
|
||||
"repo.read": frozenset({"repo.read"}),
|
||||
"test_execution": frozenset({"test.execute"}),
|
||||
"git.test": frozenset({"test.execute"}),
|
||||
"test.execute": frozenset({"test.execute"}),
|
||||
"governed_git_write": frozenset({"governed.git.write.branch", "governed.git.write.file"}),
|
||||
"governed.git.write": frozenset({"governed.git.write.branch", "governed.git.write.file"}),
|
||||
"governed.write.branch": frozenset({"governed.git.write.branch"}),
|
||||
"governed.write.file": frozenset({"governed.git.write.file"}),
|
||||
"shell": frozenset({"runtime.shell"}),
|
||||
"git": frozenset({"runtime.git"}),
|
||||
"python": frozenset({"runtime.python"}),
|
||||
"code.read": frozenset({"legacy.code.read"}),
|
||||
"code.review": frozenset({"legacy.code.review"}),
|
||||
"code.write": frozenset({"legacy.code.write"}),
|
||||
"code.write.patch": frozenset({"legacy.code.write.patch"}),
|
||||
"test.python": frozenset({"legacy.test.python"}),
|
||||
"test.shell.allowlisted": frozenset({"legacy.test.shell.allowlisted"}),
|
||||
"git.commit": frozenset({"legacy.git.commit"}),
|
||||
"git.diff.read": frozenset({"legacy.git.diff.read"}),
|
||||
"git.force_push": frozenset({"legacy.git.force_push"}),
|
||||
"deploy.production": frozenset({"legacy.deploy.production"}),
|
||||
"secret.transform": frozenset({"legacy.secret.transform"}),
|
||||
"secure_file_transformer": frozenset({"legacy.secure_file_transformer"}),
|
||||
"runtime.shadow": frozenset({"legacy.runtime.shadow"}),
|
||||
"review.security": frozenset({"legacy.review.security"}),
|
||||
"review.api-contract": frozenset({"legacy.review.api-contract"}),
|
||||
"gpu.train": frozenset({"legacy.gpu.train"}),
|
||||
"agent.runtime.hermes": frozenset({"agent.runtime.hermes"}),
|
||||
"agent.runtime.openclaw": frozenset({"agent.runtime.openclaw"}),
|
||||
"engineering.autonomous": frozenset({"engineering.autonomous"}),
|
||||
"release:candidate": frozenset({"release:candidate"}),
|
||||
}
|
||||
|
||||
_WORKER_ALIASES: dict[str, frozenset[str]] = {
|
||||
"git.read": frozenset({"repo.read"}),
|
||||
"repo.read": frozenset({"repo.read"}),
|
||||
"repository_read": frozenset({"repo.read"}),
|
||||
"git.test": frozenset({"test.execute"}),
|
||||
"test.execute": frozenset({"test.execute"}),
|
||||
"test_execution": frozenset({"test.execute"}),
|
||||
"governed.write.branch": frozenset({"governed.git.write.branch"}),
|
||||
"governed.git.write.branch": frozenset({"governed.git.write.branch"}),
|
||||
"governed.write.file": frozenset({"governed.git.write.file"}),
|
||||
"governed.git.write.file": frozenset({"governed.git.write.file"}),
|
||||
"shell": frozenset({"runtime.shell"}),
|
||||
"git": frozenset({"runtime.git"}),
|
||||
"python": frozenset({"runtime.python"}),
|
||||
"code.read": frozenset({"legacy.code.read"}),
|
||||
"code.review": frozenset({"legacy.code.review"}),
|
||||
"code.write": frozenset({"legacy.code.write"}),
|
||||
"code.write.patch": frozenset({"legacy.code.write.patch"}),
|
||||
"test.python": frozenset({"legacy.test.python"}),
|
||||
"test.shell.allowlisted": frozenset({"legacy.test.shell.allowlisted"}),
|
||||
"git.commit": frozenset({"legacy.git.commit"}),
|
||||
"git.diff.read": frozenset({"legacy.git.diff.read"}),
|
||||
"git.force_push": frozenset({"legacy.git.force_push"}),
|
||||
"deploy.production": frozenset({"legacy.deploy.production"}),
|
||||
"secret.transform": frozenset({"legacy.secret.transform"}),
|
||||
"secure_file_transformer": frozenset({"legacy.secure_file_transformer"}),
|
||||
"runtime.shadow": frozenset({"legacy.runtime.shadow"}),
|
||||
"review.security": frozenset({"legacy.review.security"}),
|
||||
"review.api-contract": frozenset({"legacy.review.api-contract"}),
|
||||
"gpu.train": frozenset({"legacy.gpu.train"}),
|
||||
"agent.runtime.hermes": frozenset({"agent.runtime.hermes"}),
|
||||
"agent.runtime.openclaw": frozenset({"agent.runtime.openclaw"}),
|
||||
"engineering.autonomous": frozenset({"engineering.autonomous"}),
|
||||
"release:candidate": frozenset({"release:candidate"}),
|
||||
}
|
||||
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CapabilityContract:
|
||||
"""Versioned runtime contract attached to one canonical semantic capability."""
|
||||
|
||||
name: str
|
||||
min_version: int = 1
|
||||
max_version: int = 1
|
||||
permissions: tuple[str, ...] = ()
|
||||
forbidden: tuple[str, ...] = ()
|
||||
dependencies: tuple[str, ...] = ()
|
||||
health_requirements: tuple[str, ...] = ()
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
# This registry is the semantic source of truth. Alias tables below are retained
|
||||
# as compatibility adapters; startup/tests validate every alias target against
|
||||
# this registry so a name cannot be accepted in one layer and be unknown in
|
||||
# another.
|
||||
_CAPABILITY_CONTRACTS: dict[str, CapabilityContract] = {
|
||||
"repo.read": CapabilityContract("repo.read", permissions=("repository_read",)),
|
||||
"test.execute": CapabilityContract("test.execute", permissions=("test_execution",)),
|
||||
"governed.git.write.branch": CapabilityContract(
|
||||
"governed.git.write.branch",
|
||||
permissions=("governed_branch_write",),
|
||||
dependencies=("writer_lease", "governed_gitops"),
|
||||
),
|
||||
"governed.git.write.file": CapabilityContract(
|
||||
"governed.git.write.file",
|
||||
permissions=("governed_file_write",),
|
||||
dependencies=("writer_lease", "governed_gitops"),
|
||||
),
|
||||
"governed.git.write": CapabilityContract(
|
||||
"governed.git.write",
|
||||
permissions=("governed_git_write",),
|
||||
dependencies=("writer_lease", "governed_gitops"),
|
||||
),
|
||||
"runtime.shell": CapabilityContract("runtime.shell", permissions=("runtime_shell",)),
|
||||
"runtime.git": CapabilityContract("runtime.git", permissions=("runtime_git",)),
|
||||
"runtime.python": CapabilityContract("runtime.python", permissions=("runtime_python",)),
|
||||
"legacy.code.read": CapabilityContract("legacy.code.read"),
|
||||
"legacy.code.review": CapabilityContract("legacy.code.review"),
|
||||
"legacy.code.write": CapabilityContract("legacy.code.write"),
|
||||
"legacy.code.write.patch": CapabilityContract("legacy.code.write.patch"),
|
||||
"legacy.test.python": CapabilityContract("legacy.test.python"),
|
||||
"legacy.test.shell.allowlisted": CapabilityContract("legacy.test.shell.allowlisted"),
|
||||
"legacy.git.commit": CapabilityContract("legacy.git.commit"),
|
||||
"legacy.git.diff.read": CapabilityContract("legacy.git.diff.read"),
|
||||
"legacy.git.force_push": CapabilityContract(
|
||||
"legacy.git.force_push",
|
||||
forbidden=("protected_ref_bypass",),
|
||||
),
|
||||
"legacy.deploy.production": CapabilityContract(
|
||||
"legacy.deploy.production",
|
||||
permissions=("production_deploy",),
|
||||
dependencies=("owner_approval", "deployment_controller"),
|
||||
health_requirements=("approval_envelope_verified", "runtime_acceptance_available"),
|
||||
),
|
||||
"legacy.secret.transform": CapabilityContract("legacy.secret.transform"),
|
||||
"legacy.secure_file_transformer": CapabilityContract("legacy.secure_file_transformer"),
|
||||
"legacy.runtime.shadow": CapabilityContract("legacy.runtime.shadow"),
|
||||
"legacy.review.security": CapabilityContract("legacy.review.security"),
|
||||
"legacy.review.api-contract": CapabilityContract("legacy.review.api-contract"),
|
||||
"legacy.gpu.train": CapabilityContract("legacy.gpu.train"),
|
||||
"agent.runtime.hermes": CapabilityContract(
|
||||
"agent.runtime.hermes",
|
||||
dependencies=("hermes_runtime",),
|
||||
health_requirements=("worker_liveness",),
|
||||
),
|
||||
"agent.runtime.openclaw": CapabilityContract(
|
||||
"agent.runtime.openclaw",
|
||||
dependencies=("openclaw_runtime",),
|
||||
health_requirements=("worker_liveness",),
|
||||
),
|
||||
"engineering.autonomous": CapabilityContract(
|
||||
"engineering.autonomous",
|
||||
dependencies=("agent_task_control_plane",),
|
||||
health_requirements=("worker_liveness",),
|
||||
),
|
||||
"release:candidate": CapabilityContract(
|
||||
"release:candidate",
|
||||
min_version=1,
|
||||
max_version=1,
|
||||
permissions=("prepare_release",),
|
||||
forbidden=(
|
||||
"production_deploy",
|
||||
"submit_owner_approval",
|
||||
"tag_publish",
|
||||
"baseline_registry_finalize",
|
||||
"runtime_switch",
|
||||
),
|
||||
dependencies=(
|
||||
"credential_projection",
|
||||
"trusted_builder",
|
||||
),
|
||||
health_requirements=(
|
||||
"authenticated_probe",
|
||||
"release_api_health",
|
||||
"worker_liveness",
|
||||
),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def capability_contract(name: object) -> CapabilityContract | None:
|
||||
"""Return the contract for one canonical or registered capability name."""
|
||||
|
||||
text = _clean(name)
|
||||
direct = _CAPABILITY_CONTRACTS.get(text)
|
||||
if direct is not None:
|
||||
return direct
|
||||
mapped = _TASK_ALIASES.get(text) or _WORKER_ALIASES.get(text)
|
||||
if mapped is None or len(mapped) != 1:
|
||||
return None
|
||||
return _CAPABILITY_CONTRACTS.get(next(iter(mapped)))
|
||||
|
||||
|
||||
def registered_capability(name: object, *, worker: bool = False) -> bool:
|
||||
"""Fail-closed validation used by registration/task admission."""
|
||||
|
||||
text = _clean(name)
|
||||
if "*" in text:
|
||||
return False
|
||||
aliases = _WORKER_ALIASES if worker else _TASK_ALIASES
|
||||
mapped = aliases.get(text)
|
||||
if mapped is None:
|
||||
return text in _CAPABILITY_CONTRACTS
|
||||
return all(item in _CAPABILITY_CONTRACTS for item in mapped)
|
||||
|
||||
|
||||
def validate_capability_contract_registry() -> dict[str, object]:
|
||||
"""Prove alias/contract closure and contract safety invariants."""
|
||||
|
||||
alias_targets: set[str] = set()
|
||||
for mapping in (_TASK_ALIASES, _WORKER_ALIASES):
|
||||
for values in mapping.values():
|
||||
alias_targets.update(values)
|
||||
missing = sorted(alias_targets - set(_CAPABILITY_CONTRACTS))
|
||||
invalid_versions = sorted(
|
||||
name
|
||||
for name, contract in _CAPABILITY_CONTRACTS.items()
|
||||
if contract.min_version < 1 or contract.max_version < contract.min_version
|
||||
)
|
||||
permission_forbidden_overlap = sorted(
|
||||
name
|
||||
for name, contract in _CAPABILITY_CONTRACTS.items()
|
||||
if set(contract.permissions) & set(contract.forbidden)
|
||||
)
|
||||
return {
|
||||
"schema": "aios.capability-contract-registry.v1",
|
||||
"contract_count": len(_CAPABILITY_CONTRACTS),
|
||||
"missing_alias_targets": missing,
|
||||
"invalid_versions": invalid_versions,
|
||||
"permission_forbidden_overlap": permission_forbidden_overlap,
|
||||
"valid": not missing and not invalid_versions and not permission_forbidden_overlap,
|
||||
}
|
||||
|
||||
|
||||
def capability_contract_snapshot() -> dict[str, dict[str, Any]]:
|
||||
return {
|
||||
name: contract.as_dict()
|
||||
for name, contract in sorted(_CAPABILITY_CONTRACTS.items())
|
||||
}
|
||||
|
||||
|
||||
_UNKNOWN_PREFIX = "exact:"
|
||||
|
||||
|
||||
def _clean(value: object) -> str:
|
||||
if not isinstance(value, str):
|
||||
raise ValueError("capability must be a string")
|
||||
text = value.strip().lower()
|
||||
if not text:
|
||||
raise ValueError("capability must not be empty")
|
||||
return text
|
||||
|
||||
|
||||
def normalize_required_capabilities(values: Iterable[object]) -> frozenset[str]:
|
||||
"""Map task-facing names to one semantic vocabulary.
|
||||
|
||||
Unknown names remain explicit exact requirements. They are never treated
|
||||
as wildcards or granted by a failed normalization.
|
||||
"""
|
||||
|
||||
result: set[str] = set()
|
||||
for value in values:
|
||||
text = _clean(value)
|
||||
if "*" in text:
|
||||
result.add(_UNKNOWN_PREFIX + text)
|
||||
else:
|
||||
mapped = _TASK_ALIASES.get(text)
|
||||
if mapped is None or any(item not in _CAPABILITY_CONTRACTS for item in mapped):
|
||||
result.add(_UNKNOWN_PREFIX + text)
|
||||
else:
|
||||
result.update(mapped)
|
||||
return frozenset(result)
|
||||
|
||||
|
||||
def normalize_worker_capabilities(values: Iterable[object]) -> frozenset[str]:
|
||||
"""Map registered worker names to effective semantic capabilities."""
|
||||
|
||||
result: set[str] = set()
|
||||
for value in values:
|
||||
text = _clean(value)
|
||||
if "*" in text:
|
||||
continue
|
||||
mapped = _WORKER_ALIASES.get(text)
|
||||
if mapped is not None and all(item in _CAPABILITY_CONTRACTS for item in mapped):
|
||||
result.update(mapped)
|
||||
if {
|
||||
"governed.git.write.branch",
|
||||
"governed.git.write.file",
|
||||
}.issubset(result):
|
||||
result.add("governed.git.write")
|
||||
return frozenset(result)
|
||||
|
||||
|
||||
def has_capabilities(
|
||||
worker_capabilities: Iterable[object],
|
||||
required_capabilities: Iterable[object],
|
||||
) -> bool:
|
||||
"""Return the single eligibility decision used by poll and claim."""
|
||||
|
||||
required = normalize_required_capabilities(required_capabilities)
|
||||
effective = normalize_worker_capabilities(worker_capabilities)
|
||||
if any(value.startswith(_UNKNOWN_PREFIX) for value in required):
|
||||
return False
|
||||
return required.issubset(effective)
|
||||
|
||||
|
||||
def required_capabilities_subset(
|
||||
granted_requirements: Iterable[object],
|
||||
required_requirements: Iterable[object],
|
||||
) -> bool:
|
||||
"""Check semantic capability containment for delegation constraints."""
|
||||
granted = normalize_required_capabilities(granted_requirements)
|
||||
required = normalize_required_capabilities(required_requirements)
|
||||
if any(value.startswith(_UNKNOWN_PREFIX) for value in granted | required):
|
||||
return False
|
||||
return required.issubset(granted)
|
||||
|
||||
|
||||
def normalized_capability_matrix(
|
||||
worker_capabilities: Iterable[object],
|
||||
required_capabilities: Iterable[object],
|
||||
) -> dict[str, object]:
|
||||
"""Expose non-secret decision evidence for tests and diagnostics."""
|
||||
|
||||
worker_values = tuple(worker_capabilities)
|
||||
required_values = tuple(required_capabilities)
|
||||
worker = normalize_worker_capabilities(worker_values)
|
||||
required = normalize_required_capabilities(required_values)
|
||||
return {
|
||||
"worker_effective": sorted(worker),
|
||||
"task_required": sorted(required),
|
||||
"eligible": has_capabilities(worker_values, required_values),
|
||||
}
|
||||
@@ -13,6 +13,8 @@ BRIDGE_OPERATIONS = (
|
||||
"getGovernedWriteCapabilities",
|
||||
"createGovernedTask",
|
||||
"acquireWriterLease",
|
||||
"bootstrapWriterLease",
|
||||
"renewWriterLease",
|
||||
"commitFileGoverned",
|
||||
"commitFilesGoverned",
|
||||
"getGitOpsJob",
|
||||
@@ -31,6 +33,8 @@ BRIDGE_OPERATIONS = (
|
||||
OPERATION_REQUIRED_FIELDS = {
|
||||
"createGovernedTask": ("task_id", "repository", "base_oid", "target_branch", "risk", "description", "idempotency_key"),
|
||||
"acquireWriterLease": ("schema", "task_id", "repository", "branch_mode", "base_oid", "expected_branch_oid", "target_branch", "generation", "lease_seconds"),
|
||||
"bootstrapWriterLease": ("schema", "task_id", "repository", "branch_mode", "base_oid", "expected_branch_oid", "target_branch", "generation", "lease_seconds"),
|
||||
"renewWriterLease": ("schema", "task_id", "repository", "branch_mode", "base_oid", "expected_branch_oid", "target_branch", "generation", "lease_seconds"),
|
||||
"commitFileGoverned": ("task_id", "repository", "expected_branch_oid", "target_branch", "generation", "idempotency_key", "path", "content_base64", "message"),
|
||||
"commitFilesGoverned": ("task_id", "repository", "expected_branch_oid", "target_branch", "generation", "idempotency_key", "files", "message"),
|
||||
"getGitOpsJob": ("job_id",),
|
||||
@@ -46,6 +50,49 @@ OPERATION_REQUIRED_FIELDS = {
|
||||
"getControlPlaneSnapshot": (),
|
||||
}
|
||||
|
||||
BRIDGE_OPERATION_CONTRACTS = {
|
||||
"acquireWriterLease": {
|
||||
"method": "POST",
|
||||
"path": "/v2/writer-lease",
|
||||
"required_fields": OPERATION_REQUIRED_FIELDS["acquireWriterLease"],
|
||||
"response_fields": (
|
||||
"task_id", "job_id", "generation", "lease_seconds", "lease_expires_at",
|
||||
"create_target_branch", "worktree_mode", "cas_ref_update_required",
|
||||
),
|
||||
},
|
||||
"bootstrapWriterLease": {
|
||||
"method": "POST",
|
||||
"path": "/v2/writer-lease/bootstrap",
|
||||
"required_fields": OPERATION_REQUIRED_FIELDS["bootstrapWriterLease"],
|
||||
"response_fields": (
|
||||
"task_id", "job_id", "generation", "lease_seconds", "lease_expires_at",
|
||||
"create_target_branch", "worktree_mode", "cas_ref_update_required",
|
||||
"recovered", "bootstrapped", "runtime_rehydrated",
|
||||
"durable_branch_lease_present", "idempotent",
|
||||
),
|
||||
},
|
||||
"renewWriterLease": {
|
||||
"method": "POST",
|
||||
"path": "/v2/writer-lease/renew",
|
||||
"required_fields": OPERATION_REQUIRED_FIELDS["renewWriterLease"],
|
||||
"response_fields": (
|
||||
"task_id", "job_id", "generation", "lease_seconds", "lease_expires_at",
|
||||
"recovered", "bootstrapped", "runtime_rehydrated",
|
||||
"durable_branch_lease_present", "idempotent",
|
||||
),
|
||||
},
|
||||
"commitFileGoverned": {
|
||||
"method": "POST", "path": "/v2/commit-file",
|
||||
"required_fields": OPERATION_REQUIRED_FIELDS["commitFileGoverned"],
|
||||
"response_fields": ("job_id", "commit_oid", "commit_visible", "branch_mode", "target_branch", "generation"),
|
||||
},
|
||||
"commitFilesGoverned": {
|
||||
"method": "POST", "path": "/v2/commit-files",
|
||||
"required_fields": OPERATION_REQUIRED_FIELDS["commitFilesGoverned"],
|
||||
"response_fields": ("job_id", "commit_oid", "commit_visible", "branch_mode", "target_branch", "generation"),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class RuntimeDriftError(RuntimeError):
|
||||
pass
|
||||
@@ -122,6 +169,14 @@ class BridgeV2Adapter:
|
||||
"legacy_writes_enabled": False,
|
||||
"governed_writes_enabled": True,
|
||||
"operations": list(BRIDGE_OPERATIONS),
|
||||
"operation_contracts": {
|
||||
operation: {
|
||||
**contract,
|
||||
"required_fields": list(contract["required_fields"]),
|
||||
"response_fields": list(contract["response_fields"]),
|
||||
}
|
||||
for operation, contract in BRIDGE_OPERATION_CONTRACTS.items()
|
||||
},
|
||||
"force_push": False,
|
||||
"main_write": False,
|
||||
"tag_write": False,
|
||||
@@ -151,6 +206,8 @@ class BridgeV2Adapter:
|
||||
|
||||
def createGovernedTask(self, request: Mapping[str, Any]) -> Any: return self._call("createGovernedTask", request)
|
||||
def acquireWriterLease(self, request: Mapping[str, Any]) -> Any: return self._call("acquireWriterLease", request)
|
||||
def bootstrapWriterLease(self, request: Mapping[str, Any]) -> Any: return self._call("bootstrapWriterLease", request)
|
||||
def renewWriterLease(self, request: Mapping[str, Any]) -> Any: return self._call("renewWriterLease", request)
|
||||
def commitFileGoverned(self, request: Mapping[str, Any]) -> Any: return self._call("commitFileGoverned", request)
|
||||
def commitFilesGoverned(self, request: Mapping[str, Any]) -> Any: return self._call("commitFilesGoverned", request)
|
||||
def getGitOpsJob(self, request: Mapping[str, Any]) -> Any: return self._call("getGitOpsJob", request)
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -51,11 +51,13 @@ class AuthorityPort(Protocol):
|
||||
def branch_exists(self, branch: str) -> bool: ...
|
||||
def branch_head(self, branch: str) -> str: ...
|
||||
def is_ancestor(self, older: str, newer: str) -> bool: ...
|
||||
def create_task_branch_cas(self, branch: str, expected_base: str, new: str) -> str: ...
|
||||
def compare_and_swap_branch(self, branch: str, expected: str, new: str) -> str: ...
|
||||
|
||||
|
||||
class RemotePort(Protocol):
|
||||
def repository_identity(self) -> str: ...
|
||||
def push_new_exact(self, branch: str, new: str) -> None: ...
|
||||
def push_exact(self, branch: str, expected: str, new: str) -> None: ...
|
||||
def read_git_ref(self, branch: str) -> str | None: ...
|
||||
def read_api_branch(self, branch: str) -> str | None: ...
|
||||
@@ -103,6 +105,9 @@ class AuthorityGitAdapter:
|
||||
def is_ancestor(self, older: str, newer: str) -> bool:
|
||||
return self.executor.ancestry_check(older, newer)
|
||||
|
||||
def create_task_branch_cas(self, branch: str, expected_base: str, new: str) -> str:
|
||||
return self.executor.create_task_branch_CAS(self._ref(branch), expected_base, new)
|
||||
|
||||
def compare_and_swap_branch(self, branch: str, expected: str, new: str) -> str:
|
||||
return self.executor.advance_task_branch_CAS(self._ref(branch), expected, new)
|
||||
|
||||
@@ -152,7 +157,7 @@ class DetachedGitWorkspace:
|
||||
def materialize_files(self, files: Mapping[str, bytes]) -> None:
|
||||
dirty = self._dirty_paths()
|
||||
expected_paths = set(files)
|
||||
if dirty and dirty != expected_paths:
|
||||
if dirty and not dirty.issubset(expected_paths):
|
||||
raise ContinuationExecutionError("WORKTREE_DIRTY_SCOPE_MISMATCH")
|
||||
for relative, content in files.items():
|
||||
target = (self.path / relative).resolve()
|
||||
@@ -258,6 +263,15 @@ class GiteaContinuationRemote:
|
||||
raise ContinuationExecutionError("GITEA_GIT_READBACK_INVALID")
|
||||
return oid
|
||||
|
||||
def push_new_exact(self, branch: str, new: str) -> None:
|
||||
self._require_projected()
|
||||
self.repository_identity()
|
||||
if self.read_git_ref(branch) is not None:
|
||||
raise ContinuationExecutionError("GITEA_TARGET_BRANCH_ALREADY_EXISTS")
|
||||
_run(["git", "push", self.remote_name, f"{new}:refs/heads/{branch}"], cwd=self.workspace)
|
||||
if self.read_git_ref(branch) != new:
|
||||
raise ContinuationExecutionError("GITEA_CREATE_READBACK_MISMATCH")
|
||||
|
||||
def push_exact(self, branch: str, expected: str, new: str) -> None:
|
||||
self._require_projected()
|
||||
self.repository_identity()
|
||||
@@ -329,6 +343,7 @@ class ContinuationPermissions:
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class ContinuationRuntimeBinding:
|
||||
request: WriterLeaseRequestV2
|
||||
job_id: str
|
||||
workspace_path: Path
|
||||
lease_not_before: datetime
|
||||
lease_expires_at: datetime
|
||||
@@ -389,13 +404,20 @@ class ContinuationExecutor:
|
||||
def observe_generation(self, branch: str, generation: int) -> None:
|
||||
self._observed_generations[branch] = max(generation, self._observed_generations.get(branch, 0))
|
||||
|
||||
def _max_generation(self, branch: str) -> int:
|
||||
def _max_generation(self, branch: str, *, exclude_job_id: str | None = None) -> int:
|
||||
observed = self._observed_generations.get(branch, 0)
|
||||
with self.controller.store._connect() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT MAX(generation) AS generation FROM branch_leases WHERE branch=?",
|
||||
(branch,),
|
||||
).fetchone()
|
||||
if exclude_job_id is None:
|
||||
row = connection.execute(
|
||||
"SELECT MAX(generation) AS generation FROM branch_leases WHERE branch=?",
|
||||
(branch,),
|
||||
).fetchone()
|
||||
else:
|
||||
row = connection.execute(
|
||||
"SELECT MAX(generation) AS generation FROM branch_leases "
|
||||
"WHERE branch=? AND job_id!=?",
|
||||
(branch, exclude_job_id),
|
||||
).fetchone()
|
||||
durable = int(row["generation"] or 0)
|
||||
return max(observed, durable)
|
||||
|
||||
@@ -404,6 +426,7 @@ class ContinuationExecutor:
|
||||
return {
|
||||
"schema": WriterLeaseRequestV2.schema,
|
||||
"task_id": request.task_id,
|
||||
"job_id": request.job_id,
|
||||
"repository": request.repository,
|
||||
"branch_mode": request.branch_mode,
|
||||
"base_oid": request.base_oid,
|
||||
@@ -413,10 +436,21 @@ class ContinuationExecutor:
|
||||
"lease_seconds": request.lease_seconds,
|
||||
}
|
||||
|
||||
def _validate_preflight(self, binding: ContinuationRuntimeBinding) -> None:
|
||||
def _validate_preflight(self, binding: ContinuationRuntimeBinding, *, job_id: str | None = None) -> None:
|
||||
request = binding.request
|
||||
normalized = validate_writer_lease_request_v2(self._request_mapping(request), self.authority)
|
||||
if normalized != {**self._request_mapping(request), "create_target_branch": False, "worktree_mode": "detached_at_expected_head", "cas_ref_update_required": True}:
|
||||
request_mapping = self._request_mapping(request)
|
||||
normalized = validate_writer_lease_request_v2(request_mapping, self.authority)
|
||||
expected_normalized = {
|
||||
**request_mapping,
|
||||
"create_target_branch": request.branch_mode == "CREATE_NEW",
|
||||
"worktree_mode": (
|
||||
"detached_at_base_oid"
|
||||
if request.branch_mode == "CREATE_NEW"
|
||||
else "detached_at_expected_head"
|
||||
),
|
||||
"cas_ref_update_required": True,
|
||||
}
|
||||
if normalized != expected_normalized:
|
||||
raise ContinuationExecutionError("CONTINUATION_NORMALIZATION_INVALID")
|
||||
if not binding.original_receipt_valid or not binding.original_grant_consumed:
|
||||
raise ContinuationExecutionError("ORIGINAL_GRANT_LINEAGE_INVALID")
|
||||
@@ -426,7 +460,7 @@ class ContinuationExecutor:
|
||||
raise ContinuationExecutionError("LEASE_NOT_ACTIVE")
|
||||
if now >= binding.lease_expires_at:
|
||||
raise ContinuationExecutionError("LEASE_EXPIRED")
|
||||
if request.generation <= self._max_generation(request.target_branch):
|
||||
if request.generation <= self._max_generation(request.target_branch, exclude_job_id=job_id):
|
||||
raise ContinuationExecutionError("GENERATION_NOT_MONOTONIC")
|
||||
if not self.workspace.is_detached():
|
||||
raise ContinuationExecutionError("WORKTREE_NOT_DETACHED")
|
||||
@@ -452,57 +486,102 @@ class ContinuationExecutor:
|
||||
"generation": request.generation,
|
||||
}
|
||||
|
||||
def execute(self, binding: ContinuationRuntimeBinding, commit: ContinuationCommit) -> dict[str, object]:
|
||||
payload = commit.payload()
|
||||
submitted = self.controller.submit(self._job_request(binding, commit, payload), payload=payload)
|
||||
current = self.controller.store.read(submitted.job_id)
|
||||
if JobState(current["state"]) == JobState.COMPLETED:
|
||||
def execute(
|
||||
self,
|
||||
binding: ContinuationRuntimeBinding,
|
||||
commit: ContinuationCommit,
|
||||
*,
|
||||
before_complete: Callable[[str], None] | None = None,
|
||||
) -> dict[str, object]:
|
||||
commit.payload()
|
||||
if not binding.job_id or binding.request.job_id != binding.job_id:
|
||||
raise ContinuationExecutionError("RUNTIME_LINEAGE_MISSING_JOB_ID")
|
||||
current = self.controller.store.read(binding.job_id)
|
||||
current_state = JobState(current["state"])
|
||||
if current_state == JobState.COMPLETED:
|
||||
return self.controller.store._receipt(current, duplicate=True).as_dict()
|
||||
self._validate_preflight(binding)
|
||||
if current_state == JobState.REMOTE_VERIFIED:
|
||||
receipt = json.loads(str(current["receipt_json"] or "{}"))
|
||||
commit_oid = str(receipt.get("authority_oid") or "")
|
||||
if not OID_RE.fullmatch(commit_oid):
|
||||
raise ContinuationExecutionError("GOVERNED_COMMIT_OID_INVALID")
|
||||
if before_complete is not None:
|
||||
before_complete(commit_oid)
|
||||
return self.controller.advance(
|
||||
binding.job_id,
|
||||
JobState.COMPLETED,
|
||||
side_effect_state="REMOTE_VERIFIED",
|
||||
receipt=receipt,
|
||||
).as_dict()
|
||||
self._validate_preflight(binding, job_id=binding.job_id)
|
||||
request = binding.request
|
||||
projected = False
|
||||
try:
|
||||
self.credential.project()
|
||||
projected = True
|
||||
row = self.controller.store.read(submitted.job_id)
|
||||
if JobState(row["state"]) == JobState.REQUESTED:
|
||||
row = self.controller.store.read(binding.job_id)
|
||||
state = JobState(row["state"])
|
||||
if state == JobState.REQUESTED:
|
||||
self.controller.advance(
|
||||
submitted.job_id,
|
||||
binding.job_id,
|
||||
JobState.AUTHORIZED,
|
||||
side_effect_state="AUTHORIZED",
|
||||
receipt={"task_id": request.task_id, "original_grant_consumed": True},
|
||||
expected_revision=int(row["revision"]),
|
||||
)
|
||||
row = self.controller.store.read(submitted.job_id)
|
||||
if JobState(row["state"]) == JobState.AUTHORIZED:
|
||||
row = self.controller.store.read(binding.job_id)
|
||||
state = JobState(row["state"])
|
||||
if state == JobState.AUTHORIZED:
|
||||
self.controller.lease_job(
|
||||
submitted.job_id,
|
||||
lease_id=f"lease-{submitted.job_id}",
|
||||
binding.job_id,
|
||||
lease_id=f"lease-{binding.job_id}",
|
||||
lineage_anchor_oid=request.base_oid,
|
||||
current_head_oid=request.expected_branch_oid,
|
||||
generation=request.generation,
|
||||
lease_expires_at=binding.lease_expires_at.astimezone(timezone.utc).isoformat(),
|
||||
expected_revision=int(row["revision"]),
|
||||
)
|
||||
self.controller.advance(submitted.job_id, JobState.WORKTREE_READY, side_effect_state="WORKTREE_READY")
|
||||
self.controller.advance(submitted.job_id, JobState.EXECUTING, side_effect_state="IN_PROGRESS")
|
||||
row = self.controller.store.read(binding.job_id)
|
||||
state = JobState(row["state"])
|
||||
if state == JobState.LEASED:
|
||||
self.controller.advance(binding.job_id, JobState.WORKTREE_READY,
|
||||
side_effect_state="WORKTREE_READY", expected_revision=int(row["revision"]))
|
||||
row = self.controller.store.read(binding.job_id)
|
||||
state = JobState(row["state"])
|
||||
if state == JobState.WORKTREE_READY:
|
||||
self.controller.advance(binding.job_id, JobState.EXECUTING,
|
||||
side_effect_state="IN_PROGRESS", expected_revision=int(row["revision"]))
|
||||
elif state != JobState.EXECUTING:
|
||||
raise ContinuationExecutionError("JOB_EXECUTION_STATE_INVALID")
|
||||
new_oid = self.workspace.commit_files(commit.files, commit.message)
|
||||
if not OID_RE.fullmatch(new_oid) or not self.authority.is_ancestor(request.expected_branch_oid, new_oid):
|
||||
raise ContinuationExecutionError("NON_FAST_FORWARD_COMMIT")
|
||||
authority_oid = self.authority.compare_and_swap_branch(request.target_branch, request.expected_branch_oid, new_oid)
|
||||
if request.branch_mode == "CREATE_NEW":
|
||||
authority_oid = self.authority.create_task_branch_cas(request.target_branch, request.base_oid, new_oid)
|
||||
else:
|
||||
authority_oid = self.authority.compare_and_swap_branch(request.target_branch, request.expected_branch_oid, new_oid)
|
||||
if authority_oid != new_oid:
|
||||
raise ContinuationExecutionError("AUTHORITY_CAS_READBACK_MISMATCH")
|
||||
self.controller.advance(
|
||||
submitted.job_id,
|
||||
binding.job_id,
|
||||
JobState.LOCAL_VERIFIED,
|
||||
side_effect_state="LOCAL_VERIFIED",
|
||||
receipt={"authority_oid": authority_oid, "force_push": False},
|
||||
)
|
||||
try:
|
||||
self.controller.advance(submitted.job_id, JobState.REMOTE_SYNCING, side_effect_state="IN_PROGRESS")
|
||||
self.remote.push_exact(request.target_branch, request.expected_branch_oid, new_oid)
|
||||
self.controller.advance(binding.job_id, JobState.REMOTE_SYNCING, side_effect_state="IN_PROGRESS")
|
||||
if request.branch_mode == "CREATE_NEW":
|
||||
self.remote.push_new_exact(request.target_branch, new_oid)
|
||||
else:
|
||||
self.remote.push_exact(request.target_branch, request.expected_branch_oid, new_oid)
|
||||
except Exception:
|
||||
return self._remote_pending(submitted.job_id, authority_oid, new_oid)
|
||||
return self._finish_remote_verification(submitted.job_id, authority_oid, new_oid)
|
||||
return self._remote_pending(binding.job_id, authority_oid, new_oid)
|
||||
return self._finish_remote_verification(
|
||||
binding.job_id,
|
||||
authority_oid,
|
||||
new_oid,
|
||||
before_complete=before_complete,
|
||||
)
|
||||
finally:
|
||||
if projected:
|
||||
self.credential.revoke()
|
||||
@@ -525,7 +604,14 @@ class ContinuationExecutor:
|
||||
)
|
||||
return result.as_dict()
|
||||
|
||||
def _finish_remote_verification(self, job_id: str, authority_oid: str, new_oid: str) -> dict[str, object]:
|
||||
def _finish_remote_verification(
|
||||
self,
|
||||
job_id: str,
|
||||
authority_oid: str,
|
||||
new_oid: str,
|
||||
*,
|
||||
before_complete: Callable[[str], None] | None = None,
|
||||
) -> dict[str, object]:
|
||||
row = self.controller.store.read(job_id)
|
||||
branch = row["branch"]
|
||||
request = json.loads(row["request_json"])["binding"]
|
||||
@@ -542,8 +628,20 @@ class ContinuationExecutor:
|
||||
"reconciliation_decision": decision.action.value,
|
||||
"force_push": False,
|
||||
}
|
||||
self.controller.advance(job_id, JobState.REMOTE_VERIFIED, side_effect_state="REMOTE_VERIFIED", receipt=receipt)
|
||||
return self.controller.advance(job_id, JobState.COMPLETED, side_effect_state="REMOTE_VERIFIED", receipt=receipt).as_dict()
|
||||
self.controller.advance(
|
||||
job_id,
|
||||
JobState.REMOTE_VERIFIED,
|
||||
side_effect_state="REMOTE_VERIFIED",
|
||||
receipt=receipt,
|
||||
)
|
||||
if before_complete is not None:
|
||||
before_complete(new_oid)
|
||||
return self.controller.advance(
|
||||
job_id,
|
||||
JobState.COMPLETED,
|
||||
side_effect_state="REMOTE_VERIFIED",
|
||||
receipt=receipt,
|
||||
).as_dict()
|
||||
|
||||
def reconcile(self, job_id: str) -> dict[str, object]:
|
||||
row = self.controller.store.read(job_id)
|
||||
|
||||
@@ -49,6 +49,7 @@ class WriterLeaseRequestV2:
|
||||
target_branch: str
|
||||
generation: int
|
||||
lease_seconds: int = 900
|
||||
job_id: str = ""
|
||||
|
||||
schema = "aios.task-writer-lease.v2"
|
||||
accepted_schemas = frozenset({"aios.task-writer-lease.v2", "aios.task-writer-lease-request.v2"})
|
||||
@@ -56,6 +57,8 @@ class WriterLeaseRequestV2:
|
||||
def validate(self, probe: BranchProbe) -> None:
|
||||
if not self.task_id or self.repository != "aios/aios":
|
||||
raise ContinuationError("request_identity_invalid")
|
||||
if not self.job_id or not self.job_id.startswith("job-"):
|
||||
raise ContinuationError("job_id_invalid")
|
||||
if self.branch_mode not in {"CREATE_NEW", "CONTINUE_EXISTING"}:
|
||||
raise ContinuationError("branch_mode_invalid")
|
||||
_oid(self.base_oid, "base_oid")
|
||||
|
||||
@@ -6,6 +6,7 @@ from datetime import datetime, timedelta, timezone
|
||||
import os
|
||||
from pathlib import Path
|
||||
import secrets
|
||||
import re
|
||||
from typing import Any, Callable, Mapping
|
||||
|
||||
|
||||
@@ -21,9 +22,14 @@ class CredentialLease:
|
||||
scopes: tuple[str, ...]
|
||||
provider: str
|
||||
state: str = "ACTIVE"
|
||||
scope_type: str = "system"
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
run_id: str | None = None
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return {"lease_id": self.lease_id, "task_id": self.task_id, "repository": self.repository, "target_branch": self.target_branch, "generation": self.generation, "issued_at": self.issued_at, "expires_at": self.expires_at, "scopes": list(self.scopes), "provider": self.provider, "state": self.state}
|
||||
return {"lease_id": self.lease_id, "task_id": self.task_id, "repository": self.repository, "target_branch": self.target_branch, "generation": self.generation, "issued_at": self.issued_at, "expires_at": self.expires_at, "scopes": list(self.scopes), "provider": self.provider, "state": self.state, "scope_type": self.scope_type, "tenant_id": self.tenant_id, "user_id": self.user_id, "project_id": self.project_id, "run_id": self.run_id}
|
||||
|
||||
|
||||
class FileCredentialProvider:
|
||||
@@ -43,11 +49,19 @@ class CredentialBroker:
|
||||
self.now = now or (lambda: datetime.now(timezone.utc))
|
||||
self._leases: dict[str, CredentialLease] = {}
|
||||
|
||||
def issue(self, *, task_id: str, repository: str, target_branch: str, generation: int, scopes: tuple[str, ...] = ("git:push", "gitea:read"), lease_seconds: int = 900) -> dict[str, Any]:
|
||||
def issue(self, *, task_id: str, repository: str, target_branch: str, generation: int, scopes: tuple[str, ...] = ("git:push", "gitea:read"), lease_seconds: int = 900, scope_type: str = "system", tenant_id: str | None = None, user_id: str | None = None, project_id: str | None = None, run_id: str | None = None) -> dict[str, Any]:
|
||||
if repository != "aios/aios" or not target_branch.startswith("agent/") or generation < 1 or not 1 <= lease_seconds <= 86400:
|
||||
raise ValueError("CREDENTIAL_LEASE_BINDING_INVALID")
|
||||
if scope_type == "tenant":
|
||||
if not tenant_id:
|
||||
raise ValueError("CREDENTIAL_SCOPE_DENY")
|
||||
elif scope_type in {"system", "global"}:
|
||||
if any((tenant_id, user_id, project_id, run_id)):
|
||||
raise ValueError("CREDENTIAL_SCOPE_DENY")
|
||||
else:
|
||||
raise ValueError("CREDENTIAL_SCOPE_DENY")
|
||||
now = self.now().astimezone(timezone.utc)
|
||||
lease = CredentialLease("lease-" + secrets.token_hex(16), task_id, repository, target_branch, generation, now.isoformat(), (now + timedelta(seconds=lease_seconds)).isoformat(), tuple(scopes), type(self.provider).__name__)
|
||||
lease = CredentialLease("lease-" + secrets.token_hex(16), task_id, repository, target_branch, generation, now.isoformat(), (now + timedelta(seconds=lease_seconds)).isoformat(), tuple(scopes), type(self.provider).__name__, "ACTIVE", scope_type, tenant_id, user_id, project_id, run_id)
|
||||
self._leases[lease.lease_id] = lease
|
||||
return lease.as_dict()
|
||||
|
||||
@@ -64,7 +78,39 @@ class CredentialBroker:
|
||||
lease = self._get(lease_id)
|
||||
if lease.state != "ACTIVE":
|
||||
raise RuntimeError("CREDENTIAL_LEASE_NOT_ACTIVE")
|
||||
return self.provider.environment(lease)
|
||||
environment = self.provider.environment(lease)
|
||||
for key, value in environment.items():
|
||||
upper = str(key).upper()
|
||||
if not isinstance(value, str):
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
sensitive = any(marker in upper for marker in ("CREDENTIAL", "TOKEN", "SECRET", "PASSWORD", "PRIVATE_KEY", "API_KEY"))
|
||||
if re.search(r"(?i)bearer\s+\S+|(?:token|secret|password|api[_-]?key)\s*[:=]", value):
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
if sensitive and upper.endswith("_FILE"):
|
||||
candidate = Path(value)
|
||||
credential_root = Path("/run/credentials")
|
||||
try:
|
||||
resolved = candidate.resolve(strict=False)
|
||||
except OSError as exc:
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY") from exc
|
||||
if not candidate.is_absolute() or not (resolved == credential_root or credential_root in resolved.parents):
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
elif sensitive and upper.endswith("_REFERENCE"):
|
||||
if re.fullmatch(r"(?:systemd-credential|vault|secret-manager):[A-Za-z0-9][A-Za-z0-9._:/#-]{0,255}", value) is None:
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
elif sensitive:
|
||||
raise RuntimeError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
return environment
|
||||
|
||||
def authorize(self, lease_id: str, *, task_id: str, operation: str, scope_type: str = "system", tenant_id: str | None = None, user_id: str | None = None, project_id: str | None = None, run_id: str | None = None) -> Mapping[str, str]:
|
||||
lease = self._get(lease_id)
|
||||
if lease.state != "ACTIVE" or lease.task_id != task_id or operation not in lease.scopes:
|
||||
raise RuntimeError("CREDENTIAL_SCOPE_DENY")
|
||||
requested = (scope_type, tenant_id, user_id, project_id, run_id)
|
||||
actual = (lease.scope_type, lease.tenant_id, lease.user_id, lease.project_id, lease.run_id)
|
||||
if requested != actual:
|
||||
raise RuntimeError("CREDENTIAL_SCOPE_DENY")
|
||||
return self.environment(lease_id)
|
||||
|
||||
def status(self, lease_id: str) -> dict[str, Any]:
|
||||
return self._get(lease_id).as_dict()
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -27,6 +27,19 @@ class ServiceUnavailable(JobError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class LeaseRenewalResult:
|
||||
"""Durable outcome of one writer-lease recovery attempt."""
|
||||
|
||||
renewed: bool
|
||||
idempotent: bool
|
||||
durable: bool
|
||||
lease_expires_at: str | None
|
||||
|
||||
def __bool__(self) -> bool:
|
||||
return self.renewed or self.idempotent
|
||||
|
||||
|
||||
class BindingConflict(JobError):
|
||||
pass
|
||||
|
||||
@@ -66,6 +79,14 @@ def utc_now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
|
||||
def parse_utc(value: str) -> datetime:
|
||||
normalized = value[:-1] + "+00:00" if value.endswith("Z") else value
|
||||
parsed = datetime.fromisoformat(normalized)
|
||||
if parsed.tzinfo is None:
|
||||
raise ValueError("LEASE_EXPIRY_INVALID")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def canonical_json(value: Any) -> bytes:
|
||||
return (
|
||||
json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False) + "\n"
|
||||
@@ -404,13 +425,16 @@ class GitOpsJobController:
|
||||
self.store._mirror(result)
|
||||
return self.store._receipt(result, duplicate=True)
|
||||
|
||||
def update_lease(self, lease_id: str, *, expected_revision: int, current_head_oid: str, generation: int, state: str = "ACTIVE") -> None:
|
||||
def update_lease(self, lease_id: str, *, expected_revision: int, current_head_oid: str, generation: int, state: str = "ACTIVE", lease_expires_at: str | None = None) -> None:
|
||||
if len(current_head_oid) != 40 or generation < 1:
|
||||
raise JobError("LEASE_BINDING_INVALID")
|
||||
try:
|
||||
with self.store._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
updated = connection.execute("UPDATE branch_leases SET current_head_oid=?,generation=?,state=?,revision=revision+1 WHERE lease_id=? AND revision=?", (current_head_oid, generation, state, lease_id, expected_revision))
|
||||
if lease_expires_at is None:
|
||||
updated = connection.execute("UPDATE branch_leases SET current_head_oid=?,generation=?,state=?,revision=revision+1 WHERE lease_id=? AND revision=?", (current_head_oid, generation, state, lease_id, expected_revision))
|
||||
else:
|
||||
updated = connection.execute("UPDATE branch_leases SET current_head_oid=?,generation=?,lease_expires_at=?,state=?,revision=revision+1 WHERE lease_id=? AND revision=?", (current_head_oid, generation, lease_expires_at, state, lease_id, expected_revision))
|
||||
if updated.rowcount != 1:
|
||||
raise JobError("LEASE_REVISION_CAS_CONFLICT")
|
||||
connection.commit()
|
||||
@@ -419,6 +443,94 @@ class GitOpsJobController:
|
||||
except sqlite3.Error as exc:
|
||||
raise ServiceUnavailable("JOB_DB_UNAVAILABLE") from exc
|
||||
|
||||
def renew_lease(
|
||||
self,
|
||||
*,
|
||||
branch: str,
|
||||
lineage_anchor_oid: str,
|
||||
current_head_oid: str,
|
||||
generation: int,
|
||||
lease_expires_at: str,
|
||||
) -> LeaseRenewalResult:
|
||||
if (
|
||||
not branch
|
||||
or len(lineage_anchor_oid) != 40
|
||||
or len(current_head_oid) != 40
|
||||
or generation < 1
|
||||
or not lease_expires_at.strip()
|
||||
):
|
||||
raise JobError("LEASE_BINDING_INVALID")
|
||||
try:
|
||||
with self.store._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
rows = connection.execute(
|
||||
"SELECT lease_id, revision, generation, state, lease_expires_at "
|
||||
"FROM branch_leases "
|
||||
"WHERE branch=? AND lineage_anchor_oid=? AND current_head_oid=? "
|
||||
"AND generation=? AND state='ACTIVE' ORDER BY revision DESC",
|
||||
(branch, lineage_anchor_oid, current_head_oid, generation),
|
||||
).fetchall()
|
||||
if not rows:
|
||||
connection.commit()
|
||||
return LeaseRenewalResult(False, False, False, None)
|
||||
if len(rows) != 1:
|
||||
raise JobError("LEASE_BINDING_CONFLICT")
|
||||
row = rows[0]
|
||||
try:
|
||||
current_expires_at = parse_utc(str(row["lease_expires_at"]))
|
||||
requested_expires_at = parse_utc(lease_expires_at)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise JobError("LEASE_EXPIRY_INVALID") from exc
|
||||
now = datetime.now(timezone.utc)
|
||||
if requested_expires_at <= now:
|
||||
raise JobError("LEASE_EXPIRY_INVALID")
|
||||
if current_expires_at > now:
|
||||
connection.commit()
|
||||
return LeaseRenewalResult(
|
||||
False,
|
||||
True,
|
||||
True,
|
||||
str(row["lease_expires_at"]),
|
||||
)
|
||||
updated = connection.execute(
|
||||
"UPDATE branch_leases SET lease_expires_at=?,revision=revision+1 "
|
||||
"WHERE lease_id=? AND revision=? AND generation=? "
|
||||
"AND state='ACTIVE' AND lease_expires_at=?",
|
||||
(
|
||||
lease_expires_at,
|
||||
row["lease_id"],
|
||||
int(row["revision"]),
|
||||
generation,
|
||||
row["lease_expires_at"],
|
||||
),
|
||||
)
|
||||
if updated.rowcount != 1:
|
||||
current = connection.execute(
|
||||
"SELECT lease_expires_at, generation, state FROM branch_leases "
|
||||
"WHERE lease_id=?",
|
||||
(row["lease_id"],),
|
||||
).fetchone()
|
||||
if (
|
||||
current is not None
|
||||
and int(current["generation"]) == generation
|
||||
and current["state"] == "ACTIVE"
|
||||
and parse_utc(str(current["lease_expires_at"])) > now
|
||||
):
|
||||
connection.commit()
|
||||
return LeaseRenewalResult(
|
||||
False,
|
||||
True,
|
||||
True,
|
||||
str(current["lease_expires_at"]),
|
||||
)
|
||||
raise JobError("LEASE_REVISION_CAS_CONFLICT")
|
||||
connection.commit()
|
||||
return LeaseRenewalResult(True, False, True, lease_expires_at)
|
||||
except JobError:
|
||||
raise
|
||||
except sqlite3.Error as exc:
|
||||
raise ServiceUnavailable("JOB_DB_UNAVAILABLE") from exc
|
||||
|
||||
def advance(self, job_id: str, state: JobState, *, side_effect_state: str, receipt: Mapping[str, Any] | None = None, expected_revision: int | None = None) -> JobReceipt:
|
||||
return self._advance(
|
||||
job_id,
|
||||
|
||||
@@ -2,13 +2,20 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, asdict
|
||||
from contextlib import contextmanager
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
from typing import Any, Mapping
|
||||
|
||||
from aios_gitops_job_controller import GitOpsJobController, JobStore
|
||||
from aios_gitops_job_controller import GitOpsJobController, JobStore, sha256_json
|
||||
from aios_online_agent_execution import (
|
||||
GovernedExecutionBinding,
|
||||
project_execution_envelope,
|
||||
project_online_task,
|
||||
)
|
||||
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
BRANCH_RE = re.compile(r"^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$")
|
||||
@@ -36,35 +43,161 @@ class GovernedTaskBinding:
|
||||
return {"task_id": self.task_id, "repository": self.repository, "base_oid": self.base_oid, "target_branch": self.target_branch, "expected_branch_oid": self.expected_branch_oid, "generation": self.generation, "branch_mode": self.branch_mode, "create_target_branch": self.branch_mode == "CREATE_NEW", "worktree_mode": "detached_at_base_oid" if self.branch_mode == "CREATE_NEW" else "detached_at_expected_head", "cas_ref_update_required": True, "idempotent": idempotent, "state": "BOUND", "job_id": self.job_id}
|
||||
|
||||
|
||||
def _safe(value: str) -> str:
|
||||
def _legacy_safe(value: str) -> str:
|
||||
return re.sub(r"[^A-Za-z0-9_.-]+", "-", value).strip("-")[:120] or "task"
|
||||
|
||||
|
||||
def _task_key(value: str) -> str:
|
||||
readable = _legacy_safe(value)[:72]
|
||||
return f"{readable}-{hashlib.sha256(value.encode('utf-8')).hexdigest()[:24]}"
|
||||
|
||||
|
||||
class GovernedTaskBootstrap:
|
||||
def __init__(self, authority: Any, root: Path, *, remote_name: str, token_path: Path, ssh_key_path: Path, api_base: str = "https://g.cnnetmkt.top/git/api/v1") -> None:
|
||||
self.authority = authority; self.root = Path(root); self.remote_name = remote_name; self.token_path = Path(token_path); self.ssh_key_path = Path(ssh_key_path); self.api_base = api_base; self.task_meta_root = self.root / "task-bindings"; self.job_root = self.root / "jobs"; self.task_meta_root.mkdir(parents=True, exist_ok=True); self.job_root.mkdir(parents=True, exist_ok=True)
|
||||
self.authority = authority; self.root = Path(root); self.remote_name = remote_name; self.token_path = Path(token_path); self.ssh_key_path = Path(ssh_key_path); self.api_base = api_base; self.task_meta_root = self.root / "task-bindings"; self.job_root = self.root / "jobs"; self.lock_root = self.root / "task-locks"; self.task_meta_root.mkdir(parents=True, exist_ok=True); self.job_root.mkdir(parents=True, exist_ok=True); self.lock_root.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def _store(self, task_id: str) -> tuple[JobStore, GitOpsJobController]:
|
||||
root = self.job_root / _safe(task_id); store = JobStore(root, payload_root=root / "payloads"); return store, GitOpsJobController(store)
|
||||
legacy = self.job_root / _legacy_safe(task_id)
|
||||
keyed = self.job_root / _task_key(task_id)
|
||||
root = legacy if legacy.is_dir() and not keyed.exists() else keyed
|
||||
store = JobStore(root, payload_root=root / "payloads"); return store, GitOpsJobController(store)
|
||||
|
||||
def _metadata(self, task_id: str) -> Path:
|
||||
return self.task_meta_root / (_safe(task_id) + ".json")
|
||||
return self.task_meta_root / (_task_key(task_id) + ".json")
|
||||
|
||||
def _legacy_metadata(self, task_id: str) -> Path:
|
||||
return self.task_meta_root / (_legacy_safe(task_id) + ".json")
|
||||
|
||||
@contextmanager
|
||||
def _task_lock(self, task_id: str):
|
||||
path = self.lock_root / (_task_key(task_id) + ".lock")
|
||||
with path.open("a+b") as handle:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
|
||||
|
||||
@contextmanager
|
||||
def _branch_lock(self, repository: str, target_branch: str):
|
||||
key = hashlib.sha256((repository + "\0" + target_branch).encode("utf-8")).hexdigest()
|
||||
path = self.lock_root / ("branch-" + key + ".lock")
|
||||
with path.open("a+b") as handle:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
|
||||
|
||||
def _read_existing(self, task_id: str) -> GovernedTaskBinding | None:
|
||||
path = self._metadata(task_id)
|
||||
if not path.exists():
|
||||
path = self._legacy_metadata(task_id)
|
||||
if not path.is_file() or path.is_symlink(): return None
|
||||
return GovernedTaskBinding(**json.loads(path.read_text(encoding="utf-8")))
|
||||
binding = GovernedTaskBinding(**json.loads(path.read_text(encoding="utf-8")))
|
||||
if binding.task_id != task_id:
|
||||
raise BootstrapError("TASK_BINDING_KEY_COLLISION")
|
||||
return binding
|
||||
|
||||
def get_binding(self, task_id: str) -> GovernedTaskBinding:
|
||||
"""Return the exact durable binding; never synthesize missing lineage."""
|
||||
existing = self._read_existing(str(task_id))
|
||||
if existing is None or not existing.job_id:
|
||||
raise BootstrapError("TASK_EXECUTION_PROJECTION_MISSING")
|
||||
return existing
|
||||
|
||||
def execution_binding(self, binding: GovernedTaskBinding) -> GovernedExecutionBinding:
|
||||
expected = binding.expected_branch_oid
|
||||
mode = binding.branch_mode
|
||||
if mode == "CREATE_NEW":
|
||||
current = self.authority.read_ref("refs/heads/" + binding.target_branch)
|
||||
if current is not None:
|
||||
store, _ = self._store(binding.task_id)
|
||||
with store._connect() as connection:
|
||||
rows = connection.execute(
|
||||
"SELECT current_head_oid,generation,state,lineage_anchor_oid "
|
||||
"FROM branch_leases WHERE job_id=? AND branch=? AND state='ACTIVE' "
|
||||
"ORDER BY revision DESC",
|
||||
(binding.job_id, binding.target_branch),
|
||||
).fetchall()
|
||||
if len(rows) != 1:
|
||||
raise BootstrapError("SAME_JOB_CONTINUATION_LEASE_INVALID")
|
||||
row = rows[0]
|
||||
if (
|
||||
str(row["current_head_oid"] or "") != current
|
||||
or int(row["generation"] or 0) != binding.generation
|
||||
or str(row["lineage_anchor_oid"] or "") != binding.base_oid
|
||||
):
|
||||
raise BootstrapError("SAME_JOB_CONTINUATION_BINDING_INVALID")
|
||||
expected = current
|
||||
mode = "CONTINUE_EXISTING"
|
||||
return GovernedExecutionBinding.from_mapping(
|
||||
{
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"repository": binding.repository,
|
||||
"base_oid": binding.base_oid,
|
||||
"expected_branch_oid": expected,
|
||||
"target_branch": binding.target_branch,
|
||||
"branch_mode": mode,
|
||||
"generation": binding.generation,
|
||||
"idempotency_key": binding.idempotency_key,
|
||||
}
|
||||
)
|
||||
|
||||
def execution_envelope(
|
||||
self,
|
||||
task_id: str,
|
||||
execution_request: Mapping[str, Any] | None = None,
|
||||
*,
|
||||
required_capabilities: tuple[str, ...] = (),
|
||||
expected_job_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
binding = self.get_binding(task_id)
|
||||
if expected_job_id and binding.job_id != expected_job_id:
|
||||
raise BootstrapError("JOB_BINDING_CONFLICT")
|
||||
return project_execution_envelope(
|
||||
self.execution_binding(binding),
|
||||
execution_request,
|
||||
required_capabilities=required_capabilities,
|
||||
)
|
||||
|
||||
def online_task_projection(
|
||||
self,
|
||||
task_id: str,
|
||||
task_request: Mapping[str, Any],
|
||||
execution_request: Mapping[str, Any] | None = None,
|
||||
*,
|
||||
expected_job_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
binding = self.get_binding(task_id)
|
||||
if expected_job_id and binding.job_id != expected_job_id:
|
||||
raise BootstrapError("JOB_BINDING_CONFLICT")
|
||||
return project_online_task(self.execution_binding(binding), task_request, execution_request)
|
||||
|
||||
def _write(self, binding: GovernedTaskBinding) -> None:
|
||||
path = self._metadata(binding.task_id); temporary = path.with_suffix(".tmp"); temporary.write_text(json.dumps(asdict(binding), sort_keys=True), encoding="utf-8"); temporary.replace(path)
|
||||
|
||||
def create(self, request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
task_id = str(request.get("task_id") or "")
|
||||
if not task_id:
|
||||
raise BootstrapError("TASK_BINDING_INVALID")
|
||||
repository = str(request.get("repository") or "")
|
||||
target_branch = str(request.get("target_branch") or "")
|
||||
with self._task_lock(task_id):
|
||||
with self._branch_lock(repository, target_branch):
|
||||
return self._create_locked(request)
|
||||
|
||||
def _create_locked(self, request: Mapping[str, Any]) -> dict[str, Any]:
|
||||
values = {key: str(request[key]) for key in ("task_id", "repository", "base_oid", "target_branch", "risk", "description", "idempotency_key")}
|
||||
if values["repository"] != "aios/aios" or not OID_RE.fullmatch(values["base_oid"]): raise BootstrapError("TASK_BINDING_INVALID")
|
||||
if not BRANCH_RE.fullmatch(values["target_branch"]): raise BootstrapError("TARGET_BRANCH_INVALID")
|
||||
existing = self._read_existing(values["task_id"])
|
||||
if existing is not None:
|
||||
if any(getattr(existing, key) != values[key] for key in ("repository", "base_oid", "target_branch", "risk", "description")): raise BootstrapError("TASK_BINDING_CONFLICT")
|
||||
if any(getattr(existing, key) != values[key] for key in ("repository", "base_oid", "target_branch", "risk", "description", "idempotency_key")): raise BootstrapError("TASK_BINDING_CONFLICT")
|
||||
optional = {"expected_branch_oid": existing.expected_branch_oid, "branch_mode": existing.branch_mode, "generation": existing.generation}
|
||||
for key, durable in optional.items():
|
||||
if key in request and str(request[key]) != str(durable): raise BootstrapError("TASK_BINDING_CONFLICT")
|
||||
return existing.response(idempotent=True)
|
||||
if not self.authority.commit_exists(values["base_oid"]): raise BootstrapError("BASE_COMMIT_NOT_FOUND")
|
||||
current = self.authority.read_ref("refs/heads/" + values["target_branch"])
|
||||
@@ -74,8 +207,61 @@ class GovernedTaskBootstrap:
|
||||
if expected != values["base_oid"]: raise BootstrapError("EXPECTED_BASE_CONFLICT")
|
||||
else:
|
||||
if expected != current: raise BootstrapError("EXISTING_BRANCH_OID_CONFLICT")
|
||||
mode, generation = "CONTINUE_EXISTING", int(request.get("generation", 2))
|
||||
if generation < 1: raise BootstrapError("GENERATION_INVALID")
|
||||
parent_task_id = str(request.get("parent_task_id") or "")
|
||||
parent_job_id = str(request.get("parent_job_id") or "")
|
||||
if not parent_task_id or not parent_job_id:
|
||||
raise BootstrapError("EXISTING_BRANCH_OWNERSHIP_REQUIRED")
|
||||
parent = self._read_existing(parent_task_id)
|
||||
if parent is None or parent.job_id != parent_job_id or parent.repository != values["repository"] or parent.target_branch != values["target_branch"]:
|
||||
raise BootstrapError("EXISTING_BRANCH_OWNERSHIP_CONFLICT")
|
||||
store, _ = self._store(parent_task_id)
|
||||
with store._connect() as connection:
|
||||
rows = connection.execute(
|
||||
"SELECT current_head_oid,generation,state FROM branch_leases WHERE job_id=? AND branch=? AND state='ACTIVE' ORDER BY revision DESC",
|
||||
(parent_job_id, values["target_branch"]),
|
||||
).fetchall()
|
||||
if len(rows) != 1 or str(rows[0]["current_head_oid"] or "") != current:
|
||||
raise BootstrapError("EXISTING_BRANCH_OWNERSHIP_CONFLICT")
|
||||
mode, generation = "CONTINUE_EXISTING", int(rows[0]["generation"]) + 1
|
||||
if "generation" in request and int(request["generation"]) != generation:
|
||||
raise BootstrapError("GENERATION_BINDING_CONFLICT")
|
||||
online_request = request.get("online_task")
|
||||
execution_request = request.get("execution")
|
||||
projection_required = (
|
||||
online_request is not None
|
||||
or execution_request is not None
|
||||
or request.get("require_online_task_projection") is True
|
||||
)
|
||||
if projection_required:
|
||||
if not isinstance(online_request, Mapping):
|
||||
raise BootstrapError("ONLINE_TASK_REQUEST_INVALID")
|
||||
if execution_request is not None and not isinstance(execution_request, Mapping):
|
||||
raise BootstrapError("EXECUTION_REQUEST_INVALID")
|
||||
provisional_job_id = "job-" + sha256_json(
|
||||
{"client_idempotency_key": values["idempotency_key"]}
|
||||
)[:32]
|
||||
try:
|
||||
provisional_binding = GovernedExecutionBinding.from_mapping(
|
||||
{
|
||||
"task_id": values["task_id"],
|
||||
"job_id": provisional_job_id,
|
||||
"repository": values["repository"],
|
||||
"base_oid": values["base_oid"],
|
||||
"expected_branch_oid": expected,
|
||||
"target_branch": values["target_branch"],
|
||||
"branch_mode": mode,
|
||||
"generation": generation,
|
||||
"idempotency_key": values["idempotency_key"],
|
||||
}
|
||||
)
|
||||
project_online_task(
|
||||
provisional_binding,
|
||||
dict(online_request),
|
||||
dict(execution_request or {}),
|
||||
)
|
||||
except Exception as exc:
|
||||
raise BootstrapError("EXECUTION_BINDING_INVALID") from exc
|
||||
|
||||
payload = json.dumps(values, sort_keys=True, separators=(",", ":")).encode()
|
||||
_, controller = self._store(values["task_id"])
|
||||
receipt = controller.submit({"idempotency_key": values["idempotency_key"], "campaign_id": values["task_id"], "task_id": values["task_id"], "repository": values["repository"], "operation": "GOVERNED_TASK_CREATE", "branch": values["target_branch"], "expected_branch_oid": expected, "payload_digest": hashlib.sha256(payload).hexdigest(), "lineage_anchor_oid": values["base_oid"]}, payload=payload)
|
||||
|
||||
@@ -0,0 +1,456 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Disabled-by-default TLS edge for the read-only GPT Online Task ingress.
|
||||
|
||||
The internal AIOS ingress remains loopback-only. This service is a separate edge
|
||||
that may bind non-loopback only when the owner explicitly approves it. It
|
||||
forwards only the tiny read-only ingress API and never proxies the canonical
|
||||
Bridge or Task API.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections import defaultdict, deque
|
||||
from dataclasses import dataclass
|
||||
import hashlib
|
||||
import hmac
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import secrets
|
||||
import ssl
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from typing import Any, Mapping
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
UPSTREAM = "http://127.0.0.1:18945"
|
||||
MAX_BODY = 64 * 1024
|
||||
MAX_RESPONSE = 256 * 1024
|
||||
MAX_CONCURRENT_REQUESTS = 32
|
||||
REQUEST_TIMEOUT_SECONDS = 20
|
||||
RATE_WINDOW_SECONDS = 60
|
||||
RATE_LIMIT_REQUESTS = 60
|
||||
RATE_BURST_REQUESTS = 15
|
||||
RATE_MAX_CLIENTS = 4096
|
||||
_AUDIT_SALT = secrets.token_bytes(32)
|
||||
PUBLIC_APPROVAL_ENV = "AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED"
|
||||
PUBLIC_DOMAIN_ENV = "AIOS_GPT_EDGE_PUBLIC_DOMAIN"
|
||||
TASK_PATH_RE = re.compile(r"^/v1/read-only-tasks(?:/[A-Za-z0-9][A-Za-z0-9._:-]{7,127})?$")
|
||||
|
||||
|
||||
def _client_pseudonym(value: str) -> str:
|
||||
return hashlib.sha256(_AUDIT_SALT + value.encode("utf-8", "replace")).hexdigest()[:16]
|
||||
|
||||
|
||||
def audit(event: str, **fields: object) -> None:
|
||||
safe = {
|
||||
"event": event,
|
||||
"ts_unix_ms": int(time.time() * 1000),
|
||||
}
|
||||
for key, value in fields.items():
|
||||
if key in {"authorization", "body", "token", "cookie", "client_ip"}:
|
||||
continue
|
||||
safe[key] = value
|
||||
print(
|
||||
json.dumps(safe, sort_keys=True, separators=(",", ":")),
|
||||
file=sys.stderr,
|
||||
flush=True,
|
||||
)
|
||||
|
||||
|
||||
class EdgeError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 400) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def public_bind_allowed(host: str, approval: str) -> str:
|
||||
value = host.strip()
|
||||
if value in {"127.0.0.1", "::1", "localhost"}:
|
||||
return value
|
||||
if approval != "1":
|
||||
raise RuntimeError("GPT_EDGE_PUBLIC_BIND_OWNER_APPROVAL_REQUIRED")
|
||||
if value not in {"0.0.0.0", "::"}:
|
||||
raise RuntimeError("GPT_EDGE_BIND_ADDRESS_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def validated_public_domain(value: str) -> str:
|
||||
domain = value.strip().lower()
|
||||
if not domain:
|
||||
return ""
|
||||
if len(domain) > 253 or re.fullmatch(
|
||||
r"(?=.{1,253}\Z)(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?",
|
||||
domain,
|
||||
) is None:
|
||||
raise RuntimeError("GPT_EDGE_PUBLIC_DOMAIN_INVALID")
|
||||
return domain
|
||||
|
||||
|
||||
def validated_edge_identity(host: str, approval: str, domain: str) -> tuple[str, str]:
|
||||
bind_host = public_bind_allowed(host, approval)
|
||||
public_domain = validated_public_domain(domain)
|
||||
if bind_host not in {"127.0.0.1", "::1", "localhost"} and not public_domain:
|
||||
raise RuntimeError("GPT_EDGE_PUBLIC_DOMAIN_REQUIRED")
|
||||
return bind_host, public_domain
|
||||
|
||||
|
||||
def validate_tls_file(path: Path, *, key: bool) -> Path:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise RuntimeError("GPT_EDGE_TLS_FILE_INVALID")
|
||||
size = path.stat().st_size
|
||||
if size < 16 or size > 256 * 1024:
|
||||
raise RuntimeError("GPT_EDGE_TLS_FILE_INVALID")
|
||||
if key and (path.stat().st_mode & 0o077):
|
||||
raise RuntimeError("GPT_EDGE_TLS_KEY_MODE_INVALID")
|
||||
return path
|
||||
|
||||
|
||||
def build_tls_context(cert_path: Path, key_path: Path) -> ssl.SSLContext:
|
||||
cert = validate_tls_file(cert_path, key=False)
|
||||
key = validate_tls_file(key_path, key=True)
|
||||
context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
|
||||
context.minimum_version = ssl.TLSVersion.TLSv1_2
|
||||
context.options |= ssl.OP_NO_COMPRESSION
|
||||
context.load_cert_chain(certfile=str(cert), keyfile=str(key))
|
||||
return context
|
||||
|
||||
|
||||
def allowed_route(method: str, raw_path: str) -> str:
|
||||
parsed = urlsplit(raw_path)
|
||||
if parsed.query or parsed.fragment:
|
||||
raise EdgeError("QUERY_OR_FRAGMENT_DENY", 400)
|
||||
path = parsed.path
|
||||
if method == "GET" and path in {"/health", "/openapi.json"}:
|
||||
return path
|
||||
if method == "POST" and path == "/v1/read-only-tasks":
|
||||
return path
|
||||
if method == "GET" and TASK_PATH_RE.fullmatch(path):
|
||||
return path
|
||||
raise EdgeError("ROUTE_DENY", 404)
|
||||
|
||||
|
||||
def route_label(method: str, path: str) -> str:
|
||||
if method == "GET" and path == "/health":
|
||||
return "health"
|
||||
if method == "GET" and path == "/openapi.json":
|
||||
return "openapi"
|
||||
if method == "POST" and path == "/v1/read-only-tasks":
|
||||
return "task_create"
|
||||
if method == "GET" and path.startswith("/v1/read-only-tasks/"):
|
||||
return "task_status"
|
||||
return "unknown"
|
||||
|
||||
|
||||
def forwarded_headers(headers: Mapping[str, str], *, body: bool) -> dict[str, str]:
|
||||
result = {"Accept": "application/json"}
|
||||
authorization = headers.get("Authorization")
|
||||
if not isinstance(authorization, str) or not authorization.startswith("Bearer "):
|
||||
raise EdgeError("AUTHORIZATION_REQUIRED", 401)
|
||||
token = authorization[7:]
|
||||
if len(token) < 32 or len(token) > 4096 or any(ch.isspace() for ch in token):
|
||||
raise EdgeError("AUTHORIZATION_INVALID", 401)
|
||||
result["Authorization"] = authorization
|
||||
if body:
|
||||
content_type = headers.get("Content-Type", "")
|
||||
if content_type.split(";", 1)[0].strip().lower() != "application/json":
|
||||
raise EdgeError("CONTENT_TYPE_INVALID", 415)
|
||||
result["Content-Type"] = "application/json"
|
||||
return result
|
||||
|
||||
|
||||
class RateLimiter:
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
window_seconds: int = RATE_WINDOW_SECONDS,
|
||||
limit: int = RATE_LIMIT_REQUESTS,
|
||||
burst: int = RATE_BURST_REQUESTS,
|
||||
max_clients: int = RATE_MAX_CLIENTS,
|
||||
now_fn=time.monotonic,
|
||||
) -> None:
|
||||
self.window_seconds = window_seconds
|
||||
self.limit = limit
|
||||
self.burst = burst
|
||||
self.max_clients = max_clients
|
||||
self.now_fn = now_fn
|
||||
self._lock = threading.Lock()
|
||||
self._events: dict[str, deque[float]] = defaultdict(deque)
|
||||
|
||||
def _prune_stale(self, cutoff: float) -> None:
|
||||
stale = [
|
||||
key
|
||||
for key, events in self._events.items()
|
||||
if not events or events[-1] <= cutoff
|
||||
]
|
||||
for key in stale:
|
||||
self._events.pop(key, None)
|
||||
|
||||
def allowed(self, key: str) -> bool:
|
||||
now = self.now_fn()
|
||||
cutoff = now - self.window_seconds
|
||||
with self._lock:
|
||||
if key not in self._events and len(self._events) >= self.max_clients:
|
||||
self._prune_stale(cutoff)
|
||||
if len(self._events) >= self.max_clients:
|
||||
return False
|
||||
events = self._events[key]
|
||||
while events and events[0] <= cutoff:
|
||||
events.popleft()
|
||||
if len(events) >= self.limit + self.burst:
|
||||
return False
|
||||
events.append(now)
|
||||
return True
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Proxy:
|
||||
upstream: str = UPSTREAM
|
||||
timeout: int = REQUEST_TIMEOUT_SECONDS
|
||||
|
||||
def request(
|
||||
self,
|
||||
method: str,
|
||||
path: str,
|
||||
headers: Mapping[str, str],
|
||||
body: bytes | None,
|
||||
) -> tuple[int, bytes, str]:
|
||||
if self.upstream != UPSTREAM:
|
||||
raise EdgeError("UPSTREAM_DRIFT_DENY", 503)
|
||||
req = urllib.request.Request(
|
||||
self.upstream + path,
|
||||
method=method,
|
||||
data=body,
|
||||
headers=dict(headers),
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self.timeout) as response:
|
||||
raw = response.read(MAX_RESPONSE + 1)
|
||||
status = response.status
|
||||
content_type = response.headers.get("Content-Type", "application/json")
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw = exc.read(MAX_RESPONSE + 1)
|
||||
status = exc.code
|
||||
content_type = exc.headers.get("Content-Type", "application/json")
|
||||
except Exception as exc:
|
||||
raise EdgeError("UPSTREAM_UNAVAILABLE", 502) from exc
|
||||
if len(raw) > MAX_RESPONSE:
|
||||
raise EdgeError("UPSTREAM_RESPONSE_TOO_LARGE", 502)
|
||||
if content_type.split(";", 1)[0].strip().lower() != "application/json":
|
||||
raise EdgeError("UPSTREAM_CONTENT_TYPE_INVALID", 502)
|
||||
return status, raw, "application/json"
|
||||
|
||||
|
||||
class EdgeServer(ThreadingHTTPServer):
|
||||
daemon_threads = True
|
||||
request_queue_size = 64
|
||||
allow_reuse_address = True
|
||||
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
proxy = Proxy()
|
||||
limiter = RateLimiter()
|
||||
concurrency = threading.BoundedSemaphore(MAX_CONCURRENT_REQUESTS)
|
||||
expected_domain = ""
|
||||
|
||||
server_version = "AIOSGPTIngressEdge/1.0"
|
||||
sys_version = ""
|
||||
|
||||
def log_message(self, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def respond_json(self, value: Mapping[str, Any], status: int) -> None:
|
||||
raw = canonical(value)
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("X-Content-Type-Options", "nosniff")
|
||||
self.send_header("Referrer-Policy", "no-referrer")
|
||||
self.send_header("Content-Security-Policy", "default-src 'none'")
|
||||
self.send_header("Strict-Transport-Security", "max-age=31536000")
|
||||
self.send_header("Content-Length", str(len(raw)))
|
||||
self.end_headers()
|
||||
self.wfile.write(raw)
|
||||
|
||||
def send_proxy_response(self, status: int, raw: bytes, content_type: str) -> None:
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", content_type)
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("X-Content-Type-Options", "nosniff")
|
||||
self.send_header("Referrer-Policy", "no-referrer")
|
||||
self.send_header("Content-Security-Policy", "default-src 'none'")
|
||||
self.send_header("Strict-Transport-Security", "max-age=31536000")
|
||||
self.send_header("Content-Length", str(len(raw)))
|
||||
self.end_headers()
|
||||
self.wfile.write(raw)
|
||||
|
||||
def client_key(self) -> str:
|
||||
return str(self.client_address[0])
|
||||
|
||||
def validate_host(self) -> None:
|
||||
if not self.expected_domain:
|
||||
return
|
||||
host = self.headers.get("Host", "").split(":", 1)[0].lower()
|
||||
if not hmac.compare_digest(host, self.expected_domain):
|
||||
raise EdgeError("HOST_HEADER_DENY", 421)
|
||||
|
||||
def body(self) -> bytes:
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "-1"))
|
||||
except ValueError as exc:
|
||||
raise EdgeError("CONTENT_LENGTH_INVALID") from exc
|
||||
if length < 1 or length > MAX_BODY:
|
||||
raise EdgeError("REQUEST_SIZE_INVALID", 413)
|
||||
raw = self.rfile.read(length)
|
||||
if len(raw) != length:
|
||||
raise EdgeError("REQUEST_BODY_TRUNCATED", 400)
|
||||
# Validate JSON at the edge so malformed bodies do not consume upstream work.
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except Exception as exc:
|
||||
raise EdgeError("REQUEST_JSON_INVALID", 400) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise EdgeError("REQUEST_JSON_OBJECT_REQUIRED", 400)
|
||||
return canonical(value)
|
||||
|
||||
def handle_proxy(self, method: str) -> None:
|
||||
client_id = _client_pseudonym(self.client_key())
|
||||
started = time.monotonic()
|
||||
acquired = self.concurrency.acquire(blocking=False)
|
||||
if not acquired:
|
||||
audit("EDGE_BUSY", client_id=client_id, method=method)
|
||||
self.respond_json({"error": "EDGE_BUSY"}, 503)
|
||||
return
|
||||
label = "unknown"
|
||||
try:
|
||||
self.validate_host()
|
||||
path = allowed_route(method, self.path)
|
||||
label = route_label(method, path)
|
||||
if path == "/health" and method == "GET":
|
||||
self.respond_json(
|
||||
{
|
||||
"status": "ok",
|
||||
"service": "aios-gpt-https-edge",
|
||||
"upstream": "loopback-readonly-ingress",
|
||||
},
|
||||
200,
|
||||
)
|
||||
audit(
|
||||
"EDGE_REQUEST",
|
||||
client_id=client_id,
|
||||
method=method,
|
||||
route=label,
|
||||
status=200,
|
||||
duration_ms=int((time.monotonic() - started) * 1000),
|
||||
)
|
||||
return
|
||||
if not self.limiter.allowed(self.client_key()):
|
||||
audit(
|
||||
"EDGE_RATE_LIMIT",
|
||||
client_id=client_id,
|
||||
method=method,
|
||||
route=label,
|
||||
)
|
||||
self.respond_json({"error": "RATE_LIMITED"}, 429)
|
||||
return
|
||||
has_body = method == "POST"
|
||||
headers = forwarded_headers(self.headers, body=has_body)
|
||||
body = self.body() if has_body else None
|
||||
status, raw, content_type = self.proxy.request(
|
||||
method,
|
||||
path,
|
||||
headers,
|
||||
body,
|
||||
)
|
||||
self.send_proxy_response(status, raw, content_type)
|
||||
audit(
|
||||
"EDGE_REQUEST",
|
||||
client_id=client_id,
|
||||
method=method,
|
||||
route=label,
|
||||
status=status,
|
||||
duration_ms=int((time.monotonic() - started) * 1000),
|
||||
)
|
||||
except EdgeError as exc:
|
||||
audit(
|
||||
"EDGE_REJECT",
|
||||
client_id=client_id,
|
||||
method=method,
|
||||
route=label,
|
||||
status=exc.status,
|
||||
error=exc.code,
|
||||
)
|
||||
self.respond_json({"error": exc.code}, exc.status)
|
||||
finally:
|
||||
self.concurrency.release()
|
||||
|
||||
def do_GET(self) -> None:
|
||||
self.handle_proxy("GET")
|
||||
|
||||
def do_POST(self) -> None:
|
||||
self.handle_proxy("POST")
|
||||
|
||||
def do_PUT(self) -> None:
|
||||
self.respond_json({"error": "METHOD_DENY"}, 405)
|
||||
|
||||
def do_PATCH(self) -> None:
|
||||
self.respond_json({"error": "METHOD_DENY"}, 405)
|
||||
|
||||
def do_DELETE(self) -> None:
|
||||
self.respond_json({"error": "METHOD_DENY"}, 405)
|
||||
|
||||
def do_CONNECT(self) -> None:
|
||||
self.respond_json({"error": "METHOD_DENY"}, 405)
|
||||
|
||||
def do_OPTIONS(self) -> None:
|
||||
self.respond_json({"error": "METHOD_DENY"}, 405)
|
||||
|
||||
|
||||
def serve() -> None:
|
||||
host, public_domain = validated_edge_identity(
|
||||
os.environ.get("AIOS_GPT_EDGE_HOST", "127.0.0.1"),
|
||||
os.environ.get(PUBLIC_APPROVAL_ENV, "0"),
|
||||
os.environ.get(PUBLIC_DOMAIN_ENV, ""),
|
||||
)
|
||||
port = int(os.environ.get("AIOS_GPT_EDGE_PORT", "18443"))
|
||||
if not 1024 <= port <= 65535:
|
||||
raise RuntimeError("GPT_EDGE_PORT_INVALID")
|
||||
Handler.expected_domain = public_domain
|
||||
|
||||
credentials = Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
cert_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_GPT_EDGE_TLS_CERT_FILE",
|
||||
str(credentials / "tls_cert"),
|
||||
)
|
||||
)
|
||||
key_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_GPT_EDGE_TLS_KEY_FILE",
|
||||
str(credentials / "tls_key"),
|
||||
)
|
||||
)
|
||||
context = build_tls_context(cert_path, key_path)
|
||||
|
||||
server = EdgeServer((host, port), Handler)
|
||||
server.socket = context.wrap_socket(server.socket, server_side=True)
|
||||
server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
@@ -0,0 +1,561 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Owner-approved activation/rollback controller for the AIOS GPT HTTPS edge.
|
||||
|
||||
This controller never creates approval, TLS, or ingress credentials. It consumes
|
||||
owner-managed inputs, applies one exact public-bind overlay, verifies the live
|
||||
edge, and provides an idempotent rollback path.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import socket
|
||||
import ssl
|
||||
import stat
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
import urllib.request
|
||||
from typing import Any, Mapping
|
||||
|
||||
APPROVAL_SCHEMA = "aios.gpt-https-edge.public-approval.v1"
|
||||
STATE_SCHEMA = "aios.gpt-https-edge.activation-state.v1"
|
||||
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
SHA_RE = re.compile(r"^[0-9a-f]{64}$")
|
||||
APPROVAL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$")
|
||||
DOMAIN_RE = re.compile(
|
||||
r"(?=.{1,253}\Z)"
|
||||
r"(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+"
|
||||
r"[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?"
|
||||
)
|
||||
|
||||
EDGE_UNIT = "aios-gpt-https-edge.service"
|
||||
INGRESS_UNIT = "aios-gpt-online-task-ingress.service"
|
||||
PUBLIC_HOST = "0.0.0.0"
|
||||
PUBLIC_PORT = 18443
|
||||
INGRESS_HEALTH = "http://127.0.0.1:18945/health"
|
||||
DROPIN_NAME = "zzzzzzzzzz-owner-approved-public.conf"
|
||||
|
||||
|
||||
class ActivationError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def sha256_bytes(data: bytes) -> str:
|
||||
return hashlib.sha256(data).hexdigest()
|
||||
|
||||
|
||||
def sha256_file(path: Path) -> str:
|
||||
return sha256_bytes(path.read_bytes())
|
||||
|
||||
|
||||
def parse_time(value: object, *, field: str) -> datetime:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
raise ActivationError("APPROVAL_" + field.upper() + "_INVALID")
|
||||
text = value.strip()
|
||||
if text.endswith("Z"):
|
||||
text = text[:-1] + "+00:00"
|
||||
try:
|
||||
parsed = datetime.fromisoformat(text)
|
||||
except ValueError as exc:
|
||||
raise ActivationError("APPROVAL_" + field.upper() + "_INVALID") from exc
|
||||
if parsed.tzinfo is None:
|
||||
raise ActivationError("APPROVAL_" + field.upper() + "_INVALID")
|
||||
return parsed.astimezone(timezone.utc)
|
||||
|
||||
|
||||
def validate_domain(value: object) -> str:
|
||||
if not isinstance(value, str):
|
||||
raise ActivationError("APPROVAL_DOMAIN_INVALID")
|
||||
domain = value.strip().lower()
|
||||
if DOMAIN_RE.fullmatch(domain) is None:
|
||||
raise ActivationError("APPROVAL_DOMAIN_INVALID")
|
||||
return domain
|
||||
|
||||
|
||||
def validate_root_file(
|
||||
path: Path,
|
||||
*,
|
||||
exact_mode: int | None = None,
|
||||
max_size: int = 256 * 1024,
|
||||
) -> Path:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise ActivationError("OWNER_FILE_INVALID")
|
||||
info = path.stat()
|
||||
if info.st_uid != 0 or info.st_gid != 0:
|
||||
raise ActivationError("OWNER_FILE_OWNERSHIP_INVALID")
|
||||
mode = stat.S_IMODE(info.st_mode)
|
||||
if exact_mode is not None and mode != exact_mode:
|
||||
raise ActivationError("OWNER_FILE_MODE_INVALID")
|
||||
if info.st_size < 16 or info.st_size > max_size:
|
||||
raise ActivationError("OWNER_FILE_SIZE_INVALID")
|
||||
return path
|
||||
|
||||
|
||||
def certificate_dns_names(cert_path: Path) -> tuple[str, ...]:
|
||||
try:
|
||||
decoded = ssl._ssl._test_decode_cert(str(cert_path))
|
||||
except Exception as exc:
|
||||
raise ActivationError("TLS_CERT_DECODE_INVALID") from exc
|
||||
names = [
|
||||
value
|
||||
for kind, value in decoded.get("subjectAltName", ())
|
||||
if kind == "DNS"
|
||||
]
|
||||
if not names:
|
||||
for rdn in decoded.get("subject", ()):
|
||||
for key, value in rdn:
|
||||
if key == "commonName":
|
||||
names.append(value)
|
||||
return tuple(names)
|
||||
|
||||
|
||||
def cert_matches_domain(cert_path: Path, domain: str) -> bool:
|
||||
names = certificate_dns_names(cert_path)
|
||||
try:
|
||||
return bool(names) and any(ssl._dnsname_match(name, domain) for name in names)
|
||||
except ssl.CertificateError:
|
||||
return False
|
||||
|
||||
|
||||
def validate_tls_pair(
|
||||
cert_path: Path,
|
||||
key_path: Path,
|
||||
domain: str,
|
||||
*,
|
||||
now_fn=time.time,
|
||||
) -> dict[str, Any]:
|
||||
validate_root_file(cert_path)
|
||||
validate_root_file(key_path, exact_mode=0o600)
|
||||
context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
|
||||
context.minimum_version = ssl.TLSVersion.TLSv1_2
|
||||
context.options |= ssl.OP_NO_COMPRESSION
|
||||
try:
|
||||
context.load_cert_chain(str(cert_path), str(key_path))
|
||||
except Exception as exc:
|
||||
raise ActivationError("TLS_CERT_KEY_PAIR_INVALID") from exc
|
||||
if not cert_matches_domain(cert_path, domain):
|
||||
raise ActivationError("TLS_CERT_DOMAIN_MISMATCH")
|
||||
decoded = ssl._ssl._test_decode_cert(str(cert_path))
|
||||
not_after = decoded.get("notAfter")
|
||||
if not not_after:
|
||||
raise ActivationError("TLS_CERT_EXPIRY_MISSING")
|
||||
remaining = ssl.cert_time_to_seconds(not_after) - now_fn()
|
||||
if remaining < 7 * 86400:
|
||||
raise ActivationError("TLS_CERT_EXPIRY_TOO_CLOSE")
|
||||
return {
|
||||
"cert_sha256": sha256_file(cert_path),
|
||||
"remaining_days": int(remaining // 86400),
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Approval:
|
||||
approval_id: str
|
||||
candidate_oid: str
|
||||
domain: str
|
||||
bind_host: str
|
||||
port: int
|
||||
tls_cert_sha256: str
|
||||
owner: str
|
||||
issued_at: datetime
|
||||
not_before: datetime
|
||||
expires_at: datetime
|
||||
raw_sha256: str
|
||||
|
||||
@classmethod
|
||||
def load(
|
||||
cls,
|
||||
path: Path,
|
||||
*,
|
||||
candidate_oid: str,
|
||||
cert_path: Path,
|
||||
now: datetime | None = None,
|
||||
) -> "Approval":
|
||||
validate_root_file(path, exact_mode=0o600, max_size=64 * 1024)
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except Exception as exc:
|
||||
raise ActivationError("APPROVAL_JSON_INVALID") from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise ActivationError("APPROVAL_JSON_INVALID")
|
||||
allowed = {
|
||||
"schema",
|
||||
"approval_id",
|
||||
"candidate_oid",
|
||||
"domain",
|
||||
"public_bind",
|
||||
"bind_host",
|
||||
"port",
|
||||
"tls_cert_sha256",
|
||||
"issued_at",
|
||||
"not_before",
|
||||
"expires_at",
|
||||
"owner",
|
||||
}
|
||||
if set(value) != allowed or value.get("schema") != APPROVAL_SCHEMA:
|
||||
raise ActivationError("APPROVAL_FIELDS_INVALID")
|
||||
|
||||
approval_id = value.get("approval_id")
|
||||
if not isinstance(approval_id, str) or APPROVAL_ID_RE.fullmatch(approval_id) is None:
|
||||
raise ActivationError("APPROVAL_ID_INVALID")
|
||||
if not OID_RE.fullmatch(str(value.get("candidate_oid") or "")):
|
||||
raise ActivationError("APPROVAL_CANDIDATE_INVALID")
|
||||
if value["candidate_oid"] != candidate_oid:
|
||||
raise ActivationError("APPROVAL_CANDIDATE_MISMATCH")
|
||||
if value.get("public_bind") is not True:
|
||||
raise ActivationError("APPROVAL_PUBLIC_BIND_REQUIRED")
|
||||
if value.get("bind_host") != PUBLIC_HOST or value.get("port") != PUBLIC_PORT:
|
||||
raise ActivationError("APPROVAL_BINDING_INVALID")
|
||||
|
||||
cert_sha = str(value.get("tls_cert_sha256") or "")
|
||||
if SHA_RE.fullmatch(cert_sha) is None:
|
||||
raise ActivationError("APPROVAL_CERT_SHA_INVALID")
|
||||
if not cert_path.is_file() or sha256_file(cert_path) != cert_sha:
|
||||
raise ActivationError("APPROVAL_CERT_SHA_MISMATCH")
|
||||
|
||||
domain = validate_domain(value.get("domain"))
|
||||
owner = value.get("owner")
|
||||
if not isinstance(owner, str) or not owner.strip() or len(owner) > 255:
|
||||
raise ActivationError("APPROVAL_OWNER_INVALID")
|
||||
|
||||
issued_at = parse_time(value.get("issued_at"), field="issued_at")
|
||||
not_before = parse_time(value.get("not_before"), field="not_before")
|
||||
expires_at = parse_time(value.get("expires_at"), field="expires_at")
|
||||
current = now or datetime.now(timezone.utc)
|
||||
if not (issued_at <= not_before <= expires_at):
|
||||
raise ActivationError("APPROVAL_TIME_ORDER_INVALID")
|
||||
if current < not_before:
|
||||
raise ActivationError("APPROVAL_NOT_YET_VALID")
|
||||
if current >= expires_at:
|
||||
raise ActivationError("APPROVAL_EXPIRED")
|
||||
if expires_at - issued_at > __import__("datetime").timedelta(days=7):
|
||||
raise ActivationError("APPROVAL_VALIDITY_TOO_LONG")
|
||||
|
||||
return cls(
|
||||
approval_id=approval_id,
|
||||
candidate_oid=candidate_oid,
|
||||
domain=domain,
|
||||
bind_host=PUBLIC_HOST,
|
||||
port=PUBLIC_PORT,
|
||||
tls_cert_sha256=cert_sha,
|
||||
owner=owner.strip(),
|
||||
issued_at=issued_at,
|
||||
not_before=not_before,
|
||||
expires_at=expires_at,
|
||||
raw_sha256=sha256_file(path),
|
||||
)
|
||||
|
||||
|
||||
def validate_release(release_root: Path) -> dict[str, Path]:
|
||||
if release_root.is_symlink() or not release_root.is_dir():
|
||||
raise ActivationError("IMMUTABLE_RELEASE_INVALID")
|
||||
edge = release_root / "active-runtime/app/aios_gpt_https_edge.py"
|
||||
controller = release_root / "active-runtime/app/aios_gpt_https_edge_activation.py"
|
||||
for path in (edge, controller):
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise ActivationError("IMMUTABLE_RELEASE_INVALID")
|
||||
return {"edge": edge, "controller": controller}
|
||||
|
||||
|
||||
def render_dropin(approval: Approval, release_root: Path) -> str:
|
||||
app = release_root / "active-runtime/app/aios_gpt_https_edge.py"
|
||||
return (
|
||||
"[Service]\n"
|
||||
f"Environment=AIOS_GPT_EDGE_HOST={approval.bind_host}\n"
|
||||
f"Environment=AIOS_GPT_EDGE_PORT={approval.port}\n"
|
||||
"Environment=AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=1\n"
|
||||
f"Environment=AIOS_GPT_EDGE_PUBLIC_DOMAIN={approval.domain}\n"
|
||||
"ExecStart=\n"
|
||||
f"ExecStart=/usr/bin/python3 -B {app}\n"
|
||||
f"ReadOnlyPaths={release_root}\n"
|
||||
)
|
||||
|
||||
|
||||
def atomic_write(path: Path, data: str, mode: int = 0o600) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
fd, name = tempfile.mkstemp(prefix="." + path.name + ".", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, mode)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
handle.write(data)
|
||||
handle.flush()
|
||||
os.fsync(handle.fileno())
|
||||
os.replace(name, path)
|
||||
finally:
|
||||
if os.path.exists(name):
|
||||
os.unlink(name)
|
||||
|
||||
|
||||
class Systemd:
|
||||
def run(self, *args: str, check: bool = True) -> subprocess.CompletedProcess[str]:
|
||||
return subprocess.run(
|
||||
["/usr/bin/systemctl", *args],
|
||||
check=check,
|
||||
text=True,
|
||||
capture_output=True,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
def active(self, unit: str) -> bool:
|
||||
return self.run("is-active", "--quiet", unit, check=False).returncode == 0
|
||||
|
||||
def enabled(self, unit: str) -> bool:
|
||||
return self.run("is-enabled", "--quiet", unit, check=False).returncode == 0
|
||||
|
||||
def show(self, unit: str, prop: str) -> str:
|
||||
return self.run("show", unit, f"--property={prop}", "--value").stdout.strip()
|
||||
|
||||
|
||||
def require_ingress_ready(systemd: Systemd) -> None:
|
||||
if not systemd.active(INGRESS_UNIT):
|
||||
raise ActivationError("INGRESS_SERVICE_NOT_ACTIVE")
|
||||
try:
|
||||
with urllib.request.urlopen(INGRESS_HEALTH, timeout=5) as response:
|
||||
if response.status != 200:
|
||||
raise ActivationError("INGRESS_HEALTH_FAILED")
|
||||
value = json.loads(response.read().decode())
|
||||
except ActivationError:
|
||||
raise
|
||||
except Exception as exc:
|
||||
raise ActivationError("INGRESS_HEALTH_FAILED") from exc
|
||||
if value.get("status") != "ok":
|
||||
raise ActivationError("INGRESS_HEALTH_FAILED")
|
||||
|
||||
|
||||
def tls_probe(domain: str, cert_path: Path, *, port: int = PUBLIC_PORT) -> None:
|
||||
context = ssl.create_default_context(cafile=str(cert_path))
|
||||
context.check_hostname = True
|
||||
context.verify_mode = ssl.CERT_REQUIRED
|
||||
try:
|
||||
with socket.create_connection(("127.0.0.1", port), timeout=5) as sock:
|
||||
with context.wrap_socket(sock, server_hostname=domain) as tls_sock:
|
||||
if tls_sock.version() not in {"TLSv1.2", "TLSv1.3"}:
|
||||
raise ActivationError("EDGE_TLS_VERSION_INVALID")
|
||||
except ActivationError:
|
||||
raise
|
||||
except Exception as exc:
|
||||
raise ActivationError("EDGE_TLS_PROBE_FAILED") from exc
|
||||
|
||||
|
||||
def receipt_for(
|
||||
approval: Approval,
|
||||
release_root: Path,
|
||||
*,
|
||||
state: str,
|
||||
) -> dict[str, Any]:
|
||||
return {
|
||||
"schema": STATE_SCHEMA,
|
||||
"state": state,
|
||||
"approval_id": approval.approval_id,
|
||||
"approval_sha256": approval.raw_sha256,
|
||||
"candidate_oid": approval.candidate_oid,
|
||||
"domain": approval.domain,
|
||||
"bind_host": approval.bind_host,
|
||||
"port": approval.port,
|
||||
"tls_cert_sha256": approval.tls_cert_sha256,
|
||||
"release_root": str(release_root),
|
||||
"updated_at": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
|
||||
|
||||
def activate(
|
||||
*,
|
||||
approval: Approval,
|
||||
release_root: Path,
|
||||
cert_path: Path,
|
||||
key_path: Path,
|
||||
dropin_path: Path,
|
||||
state_path: Path,
|
||||
systemd: Systemd,
|
||||
) -> dict[str, Any]:
|
||||
if os.geteuid() != 0:
|
||||
raise ActivationError("ROOT_REQUIRED")
|
||||
release = validate_release(release_root)
|
||||
app = release["edge"]
|
||||
require_ingress_ready(systemd)
|
||||
validate_tls_pair(cert_path, key_path, approval.domain)
|
||||
|
||||
if state_path.is_file():
|
||||
try:
|
||||
existing = json.loads(state_path.read_text(encoding="utf-8"))
|
||||
except Exception:
|
||||
existing = {}
|
||||
if (
|
||||
existing.get("schema") == STATE_SCHEMA
|
||||
and existing.get("state") == "ACTIVE"
|
||||
and existing.get("approval_sha256") == approval.raw_sha256
|
||||
and existing.get("candidate_oid") == approval.candidate_oid
|
||||
and systemd.active(EDGE_UNIT)
|
||||
):
|
||||
return existing
|
||||
|
||||
dropin = render_dropin(approval, release_root)
|
||||
modified = False
|
||||
try:
|
||||
atomic_write(dropin_path, dropin, mode=0o644)
|
||||
modified = True
|
||||
systemd.run("daemon-reload")
|
||||
systemd.run("enable", EDGE_UNIT)
|
||||
systemd.run("restart", EDGE_UNIT)
|
||||
if not systemd.active(EDGE_UNIT):
|
||||
raise ActivationError("EDGE_SERVICE_NOT_ACTIVE")
|
||||
exec_start = systemd.show(EDGE_UNIT, "ExecStart")
|
||||
environment = systemd.show(EDGE_UNIT, "Environment")
|
||||
if str(app) not in exec_start:
|
||||
raise ActivationError("EDGE_EFFECTIVE_EXECSTART_INVALID")
|
||||
for expected in (
|
||||
f"AIOS_GPT_EDGE_HOST={approval.bind_host}",
|
||||
f"AIOS_GPT_EDGE_PORT={approval.port}",
|
||||
"AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=1",
|
||||
f"AIOS_GPT_EDGE_PUBLIC_DOMAIN={approval.domain}",
|
||||
):
|
||||
if expected not in environment:
|
||||
raise ActivationError("EDGE_EFFECTIVE_ENVIRONMENT_INVALID")
|
||||
tls_probe(approval.domain, cert_path, port=approval.port)
|
||||
receipt = receipt_for(approval, release_root, state="ACTIVE")
|
||||
atomic_write(state_path, json.dumps(receipt, indent=2, sort_keys=True) + "\n")
|
||||
return receipt
|
||||
except Exception:
|
||||
if modified:
|
||||
rollback(
|
||||
dropin_path=dropin_path,
|
||||
state_path=state_path,
|
||||
systemd=systemd,
|
||||
reason="activation_failed",
|
||||
)
|
||||
raise
|
||||
|
||||
|
||||
def rollback(
|
||||
*,
|
||||
dropin_path: Path,
|
||||
state_path: Path,
|
||||
systemd: Systemd,
|
||||
reason: str,
|
||||
) -> dict[str, Any]:
|
||||
if os.geteuid() != 0:
|
||||
raise ActivationError("ROOT_REQUIRED")
|
||||
systemd.run("stop", EDGE_UNIT, check=False)
|
||||
systemd.run("disable", EDGE_UNIT, check=False)
|
||||
dropin_path.unlink(missing_ok=True)
|
||||
systemd.run("daemon-reload")
|
||||
if systemd.active(EDGE_UNIT):
|
||||
raise ActivationError("EDGE_ROLLBACK_SERVICE_STILL_ACTIVE")
|
||||
previous: dict[str, Any] = {}
|
||||
if state_path.is_file():
|
||||
try:
|
||||
previous = json.loads(state_path.read_text(encoding="utf-8"))
|
||||
except Exception:
|
||||
previous = {}
|
||||
receipt = {
|
||||
"schema": STATE_SCHEMA,
|
||||
"state": "ROLLED_BACK",
|
||||
"reason": reason[:255],
|
||||
"candidate_oid": previous.get("candidate_oid"),
|
||||
"approval_id": previous.get("approval_id"),
|
||||
"domain": previous.get("domain"),
|
||||
"updated_at": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
atomic_write(state_path, json.dumps(receipt, indent=2, sort_keys=True) + "\n")
|
||||
return receipt
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("command", choices=("check", "activate", "rollback"))
|
||||
parser.add_argument("--candidate")
|
||||
parser.add_argument("--approval", default="/etc/aios-gitops/gpt-https-edge.approved")
|
||||
parser.add_argument("--tls-cert", default="/etc/aios-gitops/gpt-https-edge-tls.crt")
|
||||
parser.add_argument("--tls-key", default="/etc/aios-gitops/gpt-https-edge-tls.key")
|
||||
parser.add_argument("--release-root")
|
||||
parser.add_argument(
|
||||
"--dropin",
|
||||
default=f"/etc/systemd/system/{EDGE_UNIT}.d/{DROPIN_NAME}",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--state",
|
||||
default="/var/lib/aios-gpt-https-edge-activation/state.json",
|
||||
)
|
||||
parser.add_argument("--reason", default="owner_requested")
|
||||
args = parser.parse_args()
|
||||
|
||||
systemd = Systemd()
|
||||
if args.command == "rollback":
|
||||
value = rollback(
|
||||
dropin_path=Path(args.dropin),
|
||||
state_path=Path(args.state),
|
||||
systemd=systemd,
|
||||
reason=args.reason,
|
||||
)
|
||||
print(json.dumps(value, indent=2, sort_keys=True))
|
||||
return 0
|
||||
|
||||
candidate = str(args.candidate or "")
|
||||
if OID_RE.fullmatch(candidate) is None:
|
||||
raise SystemExit("CANDIDATE_REQUIRED")
|
||||
release_root = (
|
||||
Path(args.release_root)
|
||||
if args.release_root
|
||||
else Path(f"/opt/aios/releases/{candidate}-gpt-https-edge-public")
|
||||
)
|
||||
cert_path = Path(args.tls_cert)
|
||||
key_path = Path(args.tls_key)
|
||||
approval = Approval.load(
|
||||
Path(args.approval),
|
||||
candidate_oid=candidate,
|
||||
cert_path=cert_path,
|
||||
)
|
||||
tls = validate_tls_pair(cert_path, key_path, approval.domain)
|
||||
release = validate_release(release_root)
|
||||
require_ingress_ready(systemd)
|
||||
|
||||
if args.command == "check":
|
||||
value = {
|
||||
"status": "READY",
|
||||
"candidate_oid": candidate,
|
||||
"approval_id": approval.approval_id,
|
||||
"approval_sha256": approval.raw_sha256,
|
||||
"domain": approval.domain,
|
||||
"bind_host": approval.bind_host,
|
||||
"port": approval.port,
|
||||
"edge_sha256": sha256_file(release["edge"]),
|
||||
"controller_sha256": sha256_file(release["controller"]),
|
||||
**tls,
|
||||
"public_network_mutation": False,
|
||||
}
|
||||
print(json.dumps(value, indent=2, sort_keys=True))
|
||||
return 0
|
||||
|
||||
value = activate(
|
||||
approval=approval,
|
||||
release_root=release_root,
|
||||
cert_path=cert_path,
|
||||
key_path=key_path,
|
||||
dropin_path=Path(args.dropin),
|
||||
state_path=Path(args.state),
|
||||
systemd=systemd,
|
||||
)
|
||||
print(json.dumps(value, indent=2, sort_keys=True))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,816 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Credential-isolated host-side ingress for externally scheduled read-only Online Tasks.
|
||||
|
||||
This service is intentionally not a public AIOS control plane. It accepts a tiny,
|
||||
authenticated external intent and translates it to the canonical loopback Bridge.
|
||||
Callers cannot select repository coordinates, capabilities, execution action,
|
||||
worker, branch policy, credentials, verification decisions, or write permissions.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import hmac
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sqlite3
|
||||
import threading
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from typing import Any, Mapping
|
||||
|
||||
SCHEMA = "aios.gpt-online-task-ingress.request.v1"
|
||||
RESPONSE_SCHEMA = "aios.gpt-online-task-ingress.response.v1"
|
||||
OPENAPI_VERSION = "3.1.0"
|
||||
|
||||
REQUEST_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$")
|
||||
TASK_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
JOB_ID_RE = re.compile(r"^job-[0-9a-f]{32}$")
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
MAX_BODY = 64 * 1024
|
||||
MAX_GOAL = 12_000
|
||||
MAX_INSTRUCTIONS = 24_000
|
||||
MAX_CRITERIA = 16
|
||||
MAX_CRITERION_TEXT = 1_000
|
||||
|
||||
READONLY_CAPABILITIES = ("git.read", "git.test")
|
||||
REPOSITORY = "aios/aios"
|
||||
|
||||
|
||||
class IngressError(RuntimeError):
|
||||
def __init__(self, code: str, status: int = 400) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.status = status
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def digest(value: object) -> str:
|
||||
return hashlib.sha256(canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def load_secret(path: Path, *, code: str) -> str:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise RuntimeError(code + "_UNAVAILABLE")
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 32 or "\n" in value or "\r" in value:
|
||||
raise RuntimeError(code + "_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def normalized_request(value: Mapping[str, Any]) -> dict[str, Any]:
|
||||
allowed = {
|
||||
"schema",
|
||||
"request_id",
|
||||
"goal",
|
||||
"instructions",
|
||||
"success_criteria",
|
||||
"constraints",
|
||||
}
|
||||
if set(value) - allowed:
|
||||
raise IngressError("UNKNOWN_FIELDS")
|
||||
if value.get("schema") != SCHEMA:
|
||||
raise IngressError("SCHEMA_INVALID")
|
||||
|
||||
request_id = value.get("request_id")
|
||||
if not isinstance(request_id, str) or REQUEST_ID_RE.fullmatch(request_id) is None:
|
||||
raise IngressError("REQUEST_ID_INVALID")
|
||||
|
||||
goal = value.get("goal")
|
||||
if not isinstance(goal, str) or not goal.strip() or len(goal) > MAX_GOAL:
|
||||
raise IngressError("GOAL_INVALID")
|
||||
instructions = value.get("instructions", "")
|
||||
if not isinstance(instructions, str) or len(instructions) > MAX_INSTRUCTIONS:
|
||||
raise IngressError("INSTRUCTIONS_INVALID")
|
||||
|
||||
criteria = value.get("success_criteria") or []
|
||||
if not isinstance(criteria, list) or len(criteria) > MAX_CRITERIA:
|
||||
raise IngressError("SUCCESS_CRITERIA_INVALID")
|
||||
normalized_criteria = []
|
||||
for item in criteria:
|
||||
if not isinstance(item, Mapping) or set(item) != {"id", "description"}:
|
||||
raise IngressError("SUCCESS_CRITERIA_INVALID")
|
||||
criterion_id = item.get("id")
|
||||
description = item.get("description")
|
||||
if (
|
||||
not isinstance(criterion_id, str)
|
||||
or not criterion_id.strip()
|
||||
or len(criterion_id) > 120
|
||||
or not isinstance(description, str)
|
||||
or not description.strip()
|
||||
or len(description) > MAX_CRITERION_TEXT
|
||||
):
|
||||
raise IngressError("SUCCESS_CRITERIA_INVALID")
|
||||
normalized_criteria.append(
|
||||
{"id": criterion_id.strip(), "description": description.strip()}
|
||||
)
|
||||
|
||||
constraints = value.get("constraints") or {}
|
||||
if not isinstance(constraints, Mapping):
|
||||
raise IngressError("CONSTRAINTS_INVALID")
|
||||
allowed_constraints = {
|
||||
"max_files",
|
||||
"focus_paths",
|
||||
"notes",
|
||||
}
|
||||
if set(constraints) - allowed_constraints:
|
||||
raise IngressError("CONSTRAINTS_FIELDS_INVALID")
|
||||
normalized_constraints: dict[str, Any] = {}
|
||||
if "max_files" in constraints:
|
||||
max_files = constraints["max_files"]
|
||||
if (
|
||||
not isinstance(max_files, int)
|
||||
or isinstance(max_files, bool)
|
||||
or not 1 <= max_files <= 500
|
||||
):
|
||||
raise IngressError("MAX_FILES_INVALID")
|
||||
normalized_constraints["max_files"] = max_files
|
||||
if "focus_paths" in constraints:
|
||||
paths = constraints["focus_paths"]
|
||||
if (
|
||||
not isinstance(paths, list)
|
||||
or len(paths) > 32
|
||||
or not all(
|
||||
isinstance(path, str)
|
||||
and path
|
||||
and len(path) <= 512
|
||||
and not path.startswith("/")
|
||||
and ".." not in Path(path).parts
|
||||
for path in paths
|
||||
)
|
||||
):
|
||||
raise IngressError("FOCUS_PATHS_INVALID")
|
||||
normalized_constraints["focus_paths"] = paths
|
||||
if "notes" in constraints:
|
||||
notes = constraints["notes"]
|
||||
if not isinstance(notes, str) or len(notes) > 4_000:
|
||||
raise IngressError("CONSTRAINT_NOTES_INVALID")
|
||||
normalized_constraints["notes"] = notes
|
||||
|
||||
return {
|
||||
"schema": SCHEMA,
|
||||
"request_id": request_id,
|
||||
"goal": goal.strip(),
|
||||
"instructions": instructions,
|
||||
"success_criteria": normalized_criteria,
|
||||
"constraints": normalized_constraints,
|
||||
}
|
||||
|
||||
|
||||
def validated_bind_host(value: str) -> str:
|
||||
host = value.strip()
|
||||
if host not in {"127.0.0.1", "::1", "localhost"}:
|
||||
raise RuntimeError("GPT_INGRESS_NON_LOOPBACK_BIND_DENY")
|
||||
return host
|
||||
|
||||
|
||||
def task_id_for(request_id: str) -> str:
|
||||
suffix = hashlib.sha256(request_id.encode("utf-8")).hexdigest()[:24]
|
||||
return "gpt-readonly-" + suffix
|
||||
|
||||
|
||||
def branch_for(task_id: str) -> str:
|
||||
return "agent/external-gpt-readonly/" + task_id[-24:]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class Upstream:
|
||||
bridge_base: str
|
||||
task_base: str
|
||||
control_token: str
|
||||
timeout: int = 20
|
||||
|
||||
def _request(
|
||||
self,
|
||||
base: str,
|
||||
method: str,
|
||||
path: str,
|
||||
body: Mapping[str, Any] | None = None,
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
raw_body = None if body is None else canonical(body)
|
||||
headers = {
|
||||
"Authorization": "Bearer " + self.control_token,
|
||||
"Accept": "application/json",
|
||||
}
|
||||
if raw_body is not None:
|
||||
headers["Content-Type"] = "application/json"
|
||||
req = urllib.request.Request(
|
||||
base.rstrip("/") + path,
|
||||
method=method,
|
||||
data=raw_body,
|
||||
headers=headers,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self.timeout) as response:
|
||||
raw = response.read()
|
||||
status = response.status
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw = exc.read()
|
||||
status = exc.code
|
||||
except Exception as exc:
|
||||
raise IngressError("UPSTREAM_TRANSPORT_FAILED", 503) from exc
|
||||
try:
|
||||
value = json.loads(raw.decode("utf-8"))
|
||||
except Exception as exc:
|
||||
raise IngressError("UPSTREAM_RESPONSE_INVALID", 502) from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise IngressError("UPSTREAM_RESPONSE_INVALID", 502)
|
||||
return status, dict(value)
|
||||
|
||||
def control_snapshot(self) -> dict[str, Any]:
|
||||
status, value = self._request(
|
||||
self.bridge_base,
|
||||
"GET",
|
||||
"/v2/control-plane-snapshot",
|
||||
)
|
||||
if status != 200:
|
||||
raise IngressError("CONTROL_SNAPSHOT_UNAVAILABLE", 503)
|
||||
return value
|
||||
|
||||
def create_governed_task(
|
||||
self,
|
||||
body: Mapping[str, Any],
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
return self._request(
|
||||
self.bridge_base,
|
||||
"POST",
|
||||
"/v2/governed-task",
|
||||
body,
|
||||
)
|
||||
|
||||
def execution_envelope(
|
||||
self,
|
||||
body: Mapping[str, Any],
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
return self._request(
|
||||
self.bridge_base,
|
||||
"POST",
|
||||
"/v2/execution-envelope",
|
||||
body,
|
||||
)
|
||||
|
||||
def get_task(self, task_id: str) -> tuple[int, dict[str, Any]]:
|
||||
return self._request(
|
||||
self.task_base,
|
||||
"GET",
|
||||
"/v1/tasks/" + task_id,
|
||||
)
|
||||
|
||||
|
||||
class Store:
|
||||
def __init__(self, path: Path) -> None:
|
||||
self.path = Path(path)
|
||||
self._lock = threading.RLock()
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with self._connect() as con:
|
||||
con.execute(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS external_task_requests(
|
||||
request_id TEXT PRIMARY KEY,
|
||||
request_sha256 TEXT NOT NULL,
|
||||
task_id TEXT NOT NULL UNIQUE,
|
||||
job_id TEXT,
|
||||
base_oid TEXT,
|
||||
state TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL,
|
||||
response_json TEXT
|
||||
)
|
||||
"""
|
||||
)
|
||||
con.commit()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
con = sqlite3.connect(self.path, timeout=30)
|
||||
con.row_factory = sqlite3.Row
|
||||
con.execute("PRAGMA busy_timeout=30000")
|
||||
return con
|
||||
|
||||
def get(self, request_id: str) -> sqlite3.Row | None:
|
||||
with self._connect() as con:
|
||||
return con.execute(
|
||||
"SELECT * FROM external_task_requests WHERE request_id=?",
|
||||
(request_id,),
|
||||
).fetchone()
|
||||
|
||||
def reserve(self, request: Mapping[str, Any], task_id: str) -> sqlite3.Row:
|
||||
request_sha = digest(request)
|
||||
timestamp = now()
|
||||
with self._lock, self._connect() as con:
|
||||
con.execute("BEGIN IMMEDIATE")
|
||||
row = con.execute(
|
||||
"SELECT * FROM external_task_requests WHERE request_id=?",
|
||||
(request["request_id"],),
|
||||
).fetchone()
|
||||
if row is not None:
|
||||
if row["request_sha256"] != request_sha:
|
||||
raise IngressError("IDEMPOTENCY_CONFLICT", 409)
|
||||
con.commit()
|
||||
return row
|
||||
con.execute(
|
||||
"""
|
||||
INSERT INTO external_task_requests(
|
||||
request_id,request_sha256,task_id,state,created_at,updated_at
|
||||
) VALUES(?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
request["request_id"],
|
||||
request_sha,
|
||||
task_id,
|
||||
"PENDING",
|
||||
timestamp,
|
||||
timestamp,
|
||||
),
|
||||
)
|
||||
con.commit()
|
||||
row = self.get(request["request_id"])
|
||||
assert row is not None
|
||||
return row
|
||||
|
||||
def bound(
|
||||
self,
|
||||
request_id: str,
|
||||
*,
|
||||
job_id: str,
|
||||
base_oid: str,
|
||||
response: Mapping[str, Any],
|
||||
) -> None:
|
||||
with self._lock, self._connect() as con:
|
||||
con.execute(
|
||||
"""
|
||||
UPDATE external_task_requests
|
||||
SET job_id=?,base_oid=?,state='BOUND',response_json=?,updated_at=?
|
||||
WHERE request_id=?
|
||||
""",
|
||||
(
|
||||
job_id,
|
||||
base_oid,
|
||||
json.dumps(response, sort_keys=True, separators=(",", ":")),
|
||||
now(),
|
||||
request_id,
|
||||
),
|
||||
)
|
||||
con.commit()
|
||||
|
||||
|
||||
class IngressService:
|
||||
def __init__(self, upstream: Upstream, store: Store) -> None:
|
||||
self.upstream = upstream
|
||||
self.store = store
|
||||
|
||||
@staticmethod
|
||||
def _main_oid(snapshot: Mapping[str, Any]) -> str:
|
||||
candidates = [
|
||||
snapshot.get("authoritative_head_oid"),
|
||||
snapshot.get("head"),
|
||||
(snapshot.get("aggregate") or {}).get("authoritative_head_oid")
|
||||
if isinstance(snapshot.get("aggregate"), Mapping)
|
||||
else None,
|
||||
]
|
||||
for candidate in candidates:
|
||||
if isinstance(candidate, str) and OID_RE.fullmatch(candidate):
|
||||
return candidate
|
||||
raise IngressError("AUTHORITATIVE_HEAD_UNAVAILABLE", 503)
|
||||
|
||||
@staticmethod
|
||||
def _public_response(
|
||||
request_id: str,
|
||||
task_id: str,
|
||||
job_id: str,
|
||||
state: str,
|
||||
) -> dict[str, Any]:
|
||||
return {
|
||||
"schema": RESPONSE_SCHEMA,
|
||||
"request_id": request_id,
|
||||
"task_id": task_id,
|
||||
"job_id": job_id,
|
||||
"state": state,
|
||||
"execution_mode": "source_capture",
|
||||
"capabilities": list(READONLY_CAPABILITIES),
|
||||
"write_access": False,
|
||||
"official_verification_required": True,
|
||||
}
|
||||
|
||||
def _recover_existing(
|
||||
self,
|
||||
request: Mapping[str, Any],
|
||||
row: sqlite3.Row,
|
||||
) -> dict[str, Any] | None:
|
||||
task_id = str(row["task_id"])
|
||||
status, task = self.upstream.get_task(task_id)
|
||||
if status == 404:
|
||||
return None
|
||||
if status != 200:
|
||||
raise IngressError("TASK_RECOVERY_FAILED", 503)
|
||||
metadata = task.get("metadata")
|
||||
execution = (
|
||||
metadata.get("execution")
|
||||
if isinstance(metadata, Mapping)
|
||||
and isinstance(metadata.get("execution"), Mapping)
|
||||
else {}
|
||||
)
|
||||
job_id = str(execution.get("job_id") or row["job_id"] or "")
|
||||
base_oid = str(execution.get("base_oid") or row["base_oid"] or "")
|
||||
if (
|
||||
task.get("task_id") != task_id
|
||||
or not JOB_ID_RE.fullmatch(job_id)
|
||||
or not OID_RE.fullmatch(base_oid)
|
||||
or execution.get("action") != "source_capture"
|
||||
or sorted(execution.get("capability_scope") or [])
|
||||
!= sorted(READONLY_CAPABILITIES)
|
||||
or (execution.get("governance") or {}).get("writer_lease") is not False
|
||||
):
|
||||
raise IngressError("TASK_RECOVERY_BINDING_INVALID", 409)
|
||||
response = self._public_response(
|
||||
request["request_id"],
|
||||
task_id,
|
||||
job_id,
|
||||
str(task.get("status") or "BOUND"),
|
||||
)
|
||||
self.store.bound(
|
||||
request["request_id"],
|
||||
job_id=job_id,
|
||||
base_oid=base_oid,
|
||||
response=response,
|
||||
)
|
||||
return response
|
||||
|
||||
def create(self, raw: Mapping[str, Any]) -> dict[str, Any]:
|
||||
request = normalized_request(raw)
|
||||
task_id = task_id_for(request["request_id"])
|
||||
row = self.store.reserve(request, task_id)
|
||||
if row["state"] == "BOUND" and row["response_json"]:
|
||||
return json.loads(row["response_json"])
|
||||
|
||||
recovered = self._recover_existing(request, row)
|
||||
if recovered is not None:
|
||||
return recovered
|
||||
|
||||
snapshot = self.upstream.control_snapshot()
|
||||
base_oid = self._main_oid(snapshot)
|
||||
target_branch = branch_for(task_id)
|
||||
binding_key = "gpt-readonly-binding-" + digest(
|
||||
{"request_id": request["request_id"], "base_oid": base_oid}
|
||||
)[:24]
|
||||
constraints = {
|
||||
**request["constraints"],
|
||||
"repository_mutation": "forbidden",
|
||||
"control_plane_side_effects": "forbidden",
|
||||
"credential_access": "forbidden",
|
||||
}
|
||||
body = {
|
||||
"task_id": task_id,
|
||||
"repository": REPOSITORY,
|
||||
"base_oid": base_oid,
|
||||
"expected_branch_oid": base_oid,
|
||||
"target_branch": target_branch,
|
||||
"branch_mode": "CREATE_NEW",
|
||||
"generation": 1,
|
||||
"risk": "low",
|
||||
"description": "Externally requested read-only governed Online Task.",
|
||||
"idempotency_key": binding_key,
|
||||
"priority": 0,
|
||||
"max_attempts": 3,
|
||||
"require_online_task_projection": True,
|
||||
"online_task": {
|
||||
"goal": request["goal"],
|
||||
"instructions": request["instructions"],
|
||||
"success_criteria": request["success_criteria"],
|
||||
"constraints": constraints,
|
||||
"required_capabilities": list(READONLY_CAPABILITIES),
|
||||
"priority": 0,
|
||||
"max_attempts": 3,
|
||||
},
|
||||
"execution": {
|
||||
"action": "source_capture",
|
||||
"adapter": "source_capture",
|
||||
"capability_scope": list(READONLY_CAPABILITIES),
|
||||
"source_signals": [
|
||||
"external read-only source analysis request",
|
||||
"no repository mutation no credential access no control-plane side effects",
|
||||
],
|
||||
},
|
||||
}
|
||||
status, value = self.upstream.create_governed_task(body)
|
||||
if status not in {200, 201, 202}:
|
||||
if status == 409:
|
||||
recovered = self._recover_existing(request, row)
|
||||
if recovered is not None:
|
||||
return recovered
|
||||
raise IngressError(
|
||||
"GOVERNED_TASK_CREATE_FAILED",
|
||||
409 if status == 409 else 503,
|
||||
)
|
||||
job_id = str(value.get("job_id") or "")
|
||||
if value.get("task_id") != task_id or JOB_ID_RE.fullmatch(job_id) is None:
|
||||
raise IngressError("GOVERNED_TASK_RESPONSE_INVALID", 502)
|
||||
|
||||
envelope_status, envelope = self.upstream.execution_envelope(
|
||||
{
|
||||
"task_id": task_id,
|
||||
"job_id": job_id,
|
||||
"required_capabilities": list(READONLY_CAPABILITIES),
|
||||
"execution": body["execution"],
|
||||
}
|
||||
)
|
||||
if envelope_status != 200:
|
||||
raise IngressError("EXECUTION_PROJECTION_FAILED", 503)
|
||||
if (
|
||||
envelope.get("task_id") != task_id
|
||||
or envelope.get("job_id") != job_id
|
||||
or envelope.get("base_oid") != base_oid
|
||||
or envelope.get("action") != "source_capture"
|
||||
or sorted(envelope.get("capability_scope") or [])
|
||||
!= sorted(READONLY_CAPABILITIES)
|
||||
or (envelope.get("governance") or {}).get("writer_lease") is not False
|
||||
):
|
||||
raise IngressError("EXECUTION_PROJECTION_INVALID", 502)
|
||||
|
||||
response = self._public_response(
|
||||
request["request_id"],
|
||||
task_id,
|
||||
job_id,
|
||||
"BOUND",
|
||||
)
|
||||
self.store.bound(
|
||||
request["request_id"],
|
||||
job_id=job_id,
|
||||
base_oid=base_oid,
|
||||
response=response,
|
||||
)
|
||||
return response
|
||||
|
||||
def status(self, request_id: str) -> dict[str, Any]:
|
||||
if REQUEST_ID_RE.fullmatch(request_id) is None:
|
||||
raise IngressError("REQUEST_ID_INVALID")
|
||||
row = self.store.get(request_id)
|
||||
if row is None:
|
||||
raise IngressError("REQUEST_NOT_FOUND", 404)
|
||||
task_id = str(row["task_id"])
|
||||
status, task = self.upstream.get_task(task_id)
|
||||
if status == 200 and not row["job_id"]:
|
||||
metadata = task.get("metadata")
|
||||
execution = (
|
||||
metadata.get("execution")
|
||||
if isinstance(metadata, Mapping)
|
||||
and isinstance(metadata.get("execution"), Mapping)
|
||||
else {}
|
||||
)
|
||||
job_id = str(execution.get("job_id") or "")
|
||||
base_oid = str(execution.get("base_oid") or "")
|
||||
if (
|
||||
JOB_ID_RE.fullmatch(job_id)
|
||||
and OID_RE.fullmatch(base_oid)
|
||||
and execution.get("action") == "source_capture"
|
||||
and sorted(execution.get("capability_scope") or [])
|
||||
== sorted(READONLY_CAPABILITIES)
|
||||
and (execution.get("governance") or {}).get("writer_lease") is False
|
||||
):
|
||||
recovered = self._public_response(
|
||||
request_id,
|
||||
task_id,
|
||||
job_id,
|
||||
str(task.get("status") or "BOUND"),
|
||||
)
|
||||
self.store.bound(
|
||||
request_id,
|
||||
job_id=job_id,
|
||||
base_oid=base_oid,
|
||||
response=recovered,
|
||||
)
|
||||
row = self.store.get(request_id) or row
|
||||
if status == 404:
|
||||
return {
|
||||
"schema": RESPONSE_SCHEMA,
|
||||
"request_id": request_id,
|
||||
"task_id": task_id,
|
||||
"state": "PENDING",
|
||||
"official_verification_required": True,
|
||||
}
|
||||
if status != 200:
|
||||
raise IngressError("TASK_STATUS_UNAVAILABLE", 503)
|
||||
|
||||
result = task.get("result") if isinstance(task.get("result"), Mapping) else {}
|
||||
verification = (
|
||||
task.get("verification")
|
||||
if isinstance(task.get("verification"), Mapping)
|
||||
else {}
|
||||
)
|
||||
safe = {
|
||||
"schema": RESPONSE_SCHEMA,
|
||||
"request_id": request_id,
|
||||
"task_id": task_id,
|
||||
"job_id": str(row["job_id"] or ""),
|
||||
"state": str(task.get("status") or "UNKNOWN"),
|
||||
"attempt": int(task.get("attempt") or 0),
|
||||
"claimed": bool(task.get("claimed_by")),
|
||||
"result_status": result.get("status"),
|
||||
"result_classification": result.get("classification"),
|
||||
"official_verification": verification.get("decision"),
|
||||
"official_classification": verification.get("classification"),
|
||||
"write_access": False,
|
||||
}
|
||||
if result.get("execution_mode") == "source_capture":
|
||||
snapshot = result.get("source_snapshot")
|
||||
if isinstance(snapshot, Mapping):
|
||||
safe["source_snapshot_sha256"] = snapshot.get("payload_sha256")
|
||||
safe["source_snapshot_file_count"] = snapshot.get("file_count")
|
||||
return safe
|
||||
|
||||
|
||||
def openapi_document() -> dict[str, Any]:
|
||||
return {
|
||||
"openapi": OPENAPI_VERSION,
|
||||
"info": {
|
||||
"title": "AIOS Read-Only Online Task Ingress",
|
||||
"version": "1.0.0",
|
||||
},
|
||||
"paths": {
|
||||
"/v1/read-only-tasks": {
|
||||
"post": {
|
||||
"operationId": "createReadOnlyOnlineTask",
|
||||
"security": [{"bearerAuth": []}],
|
||||
"requestBody": {"required": True},
|
||||
"responses": {"200": {"description": "Task accepted"}},
|
||||
}
|
||||
},
|
||||
"/v1/read-only-tasks/{request_id}": {
|
||||
"get": {
|
||||
"operationId": "getReadOnlyOnlineTaskStatus",
|
||||
"security": [{"bearerAuth": []}],
|
||||
"responses": {"200": {"description": "Sanitized task status"}},
|
||||
}
|
||||
},
|
||||
},
|
||||
"components": {
|
||||
"securitySchemes": {
|
||||
"bearerAuth": {
|
||||
"type": "http",
|
||||
"scheme": "bearer",
|
||||
}
|
||||
}
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
service: IngressService | None = None
|
||||
ingress_token: str = ""
|
||||
|
||||
def log_message(self, *_args: Any) -> None:
|
||||
return
|
||||
|
||||
def respond(self, value: Mapping[str, Any], status: int) -> None:
|
||||
raw = canonical(value)
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.send_header("Content-Length", str(len(raw)))
|
||||
self.end_headers()
|
||||
self.wfile.write(raw)
|
||||
|
||||
def authorized(self) -> bool:
|
||||
header = self.headers.get("Authorization", "")
|
||||
return (
|
||||
header.startswith("Bearer ")
|
||||
and bool(self.ingress_token)
|
||||
and hmac.compare_digest(header[7:], self.ingress_token)
|
||||
)
|
||||
|
||||
def body(self) -> dict[str, Any]:
|
||||
try:
|
||||
length = int(self.headers.get("Content-Length", "-1"))
|
||||
except ValueError as exc:
|
||||
raise IngressError("CONTENT_LENGTH_INVALID") from exc
|
||||
if length < 1 or length > MAX_BODY:
|
||||
raise IngressError("REQUEST_SIZE_INVALID", 413)
|
||||
try:
|
||||
value = json.loads(self.rfile.read(length).decode("utf-8"))
|
||||
except Exception as exc:
|
||||
raise IngressError("REQUEST_JSON_INVALID") from exc
|
||||
if not isinstance(value, Mapping):
|
||||
raise IngressError("REQUEST_OBJECT_REQUIRED")
|
||||
return dict(value)
|
||||
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/health":
|
||||
self.respond(
|
||||
{
|
||||
"status": "ok",
|
||||
"service": "aios-gpt-online-task-ingress",
|
||||
"mode": "read-only",
|
||||
},
|
||||
200,
|
||||
)
|
||||
return
|
||||
if self.path == "/openapi.json":
|
||||
self.respond(openapi_document(), 200)
|
||||
return
|
||||
if not self.authorized():
|
||||
self.respond({"error": "UNAUTHORIZED"}, 401)
|
||||
return
|
||||
match = re.fullmatch(r"/v1/read-only-tasks/([^/?#]+)", self.path)
|
||||
if match is None:
|
||||
self.respond({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
try:
|
||||
if self.service is None:
|
||||
raise IngressError("RUNTIME_UNAVAILABLE", 503)
|
||||
self.respond(self.service.status(match.group(1)), 200)
|
||||
except IngressError as exc:
|
||||
self.respond({"error": exc.code}, exc.status)
|
||||
|
||||
def do_POST(self) -> None:
|
||||
if self.path != "/v1/read-only-tasks":
|
||||
self.respond({"error": "NOT_FOUND"}, 404)
|
||||
return
|
||||
if not self.authorized():
|
||||
self.respond({"error": "UNAUTHORIZED"}, 401)
|
||||
return
|
||||
try:
|
||||
if self.service is None:
|
||||
raise IngressError("RUNTIME_UNAVAILABLE", 503)
|
||||
value = self.service.create(self.body())
|
||||
self.respond(value, 200)
|
||||
except IngressError as exc:
|
||||
self.respond({"error": exc.code}, exc.status)
|
||||
|
||||
|
||||
def serve() -> None:
|
||||
ingress_token_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_GPT_INGRESS_TOKEN_FILE",
|
||||
str(
|
||||
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
/ "gpt_ingress_token"
|
||||
),
|
||||
)
|
||||
)
|
||||
control_token_path = Path(
|
||||
os.environ.get(
|
||||
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
|
||||
str(
|
||||
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
/ "agent_task_control_token"
|
||||
),
|
||||
)
|
||||
)
|
||||
ingress_token = load_secret(
|
||||
ingress_token_path,
|
||||
code="GPT_INGRESS_CREDENTIAL",
|
||||
)
|
||||
control_token = load_secret(
|
||||
control_token_path,
|
||||
code="CONTROL_PLANE_CREDENTIAL",
|
||||
)
|
||||
|
||||
state_root = Path(
|
||||
os.environ.get(
|
||||
"AIOS_GPT_INGRESS_STATE_ROOT",
|
||||
"/var/lib/aios-gpt-online-task-ingress",
|
||||
)
|
||||
)
|
||||
host = validated_bind_host(
|
||||
os.environ.get("AIOS_GPT_INGRESS_HOST", "127.0.0.1")
|
||||
)
|
||||
port = int(os.environ.get("AIOS_GPT_INGRESS_PORT", "18945"))
|
||||
if not 1024 <= port <= 65535:
|
||||
raise RuntimeError("GPT_INGRESS_PORT_INVALID")
|
||||
|
||||
Handler.service = IngressService(
|
||||
Upstream(
|
||||
bridge_base=os.environ.get(
|
||||
"AIOS_GOVERNED_WRITE_API_URL",
|
||||
"http://127.0.0.1:18892",
|
||||
),
|
||||
task_base=os.environ.get(
|
||||
"AIOS_AGENT_TASK_API_URL",
|
||||
"http://127.0.0.1:18940",
|
||||
),
|
||||
control_token=control_token,
|
||||
),
|
||||
Store(state_root / "state.sqlite3"),
|
||||
)
|
||||
Handler.ingress_token = ingress_token
|
||||
ThreadingHTTPServer((host, port), Handler).serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
serve()
|
||||
@@ -0,0 +1,306 @@
|
||||
"""Uncredentialed deterministic executor for governed Online Agent changes.
|
||||
|
||||
This process never receives Agent/Owner/Bridge credentials and never writes Git refs.
|
||||
It operates only on an exchange bundle and returns hash-bound changed files + test evidence.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
from dataclasses import dataclass
|
||||
import errno
|
||||
import hashlib
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import shutil
|
||||
import socket
|
||||
import subprocess
|
||||
import tarfile
|
||||
import tempfile
|
||||
import time
|
||||
from typing import Any, Mapping, Sequence
|
||||
|
||||
ALLOWED_PROGRAMS = {"/usr/bin/python3", "/usr/bin/git", "/bin/true", "/usr/bin/true"}
|
||||
MAX_ARCHIVE_BYTES = 64 * 1024 * 1024
|
||||
MAX_FILE_BYTES = 4 * 1024 * 1024
|
||||
SECRET_ENV_TOKENS = ("TOKEN", "SECRET", "PASSWORD", "CREDENTIAL", "AUTHORIZATION", "PRIVATE_KEY")
|
||||
REQUEST_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{15,254}$")
|
||||
SENSITIVE_VALUE_RE = re.compile(
|
||||
r"(?i)(authorization\s*[:=]\s*bearer\s+\S+|authorization\s+bearer\s+\S+|"
|
||||
r"(?:password|passwd|secret|token|api[_-]?key)\s*[:=]\s*\S+)"
|
||||
)
|
||||
|
||||
|
||||
class IsolatedExecutorError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def sha256(data: bytes) -> str:
|
||||
return hashlib.sha256(data).hexdigest()
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
|
||||
|
||||
|
||||
def safe_relative(value: object) -> str:
|
||||
if not isinstance(value, str) or not value or value.startswith("/"):
|
||||
raise IsolatedExecutorError("PATH_INVALID")
|
||||
path = Path(value)
|
||||
if ".." in path.parts or "." in path.parts or any(part in {"", ".git"} for part in path.parts):
|
||||
raise IsolatedExecutorError("PATH_INVALID")
|
||||
return path.as_posix()
|
||||
|
||||
|
||||
def resolve_under(root: Path, relative: str) -> Path:
|
||||
root = root.resolve()
|
||||
path = (root / safe_relative(relative)).resolve(strict=False)
|
||||
if path == root or root not in path.parents:
|
||||
raise IsolatedExecutorError("PATH_ESCAPE")
|
||||
return path
|
||||
|
||||
|
||||
def _credential_exposure(directory: Path) -> str | None:
|
||||
"""Return an exposure code; EACCES is the intended credential isolation proof."""
|
||||
try:
|
||||
if not directory.exists():
|
||||
return None
|
||||
if directory.is_symlink():
|
||||
return "CREDENTIAL_MOUNT_SYMLINK"
|
||||
if os.access(directory, os.R_OK):
|
||||
return "CREDENTIAL_MOUNT_ACCESSIBLE"
|
||||
if directory.is_dir():
|
||||
for child in directory.iterdir():
|
||||
if child.is_file() and os.access(child, os.R_OK):
|
||||
return "CREDENTIAL_FILE_ACCESSIBLE"
|
||||
except PermissionError:
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def assert_uncredentialed() -> None:
|
||||
credentials = Path("/run/credentials")
|
||||
candidates = {credentials}
|
||||
credentials_directory = Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
|
||||
candidates.add(credentials_directory)
|
||||
leaked = sorted(
|
||||
key for key, value in os.environ.items()
|
||||
if value
|
||||
and (any(token in key.upper() for token in SECRET_ENV_TOKENS) or SENSITIVE_VALUE_RE.search(str(value)))
|
||||
)
|
||||
if leaked:
|
||||
raise IsolatedExecutorError("CREDENTIAL_ENV_EXPOSED:" + ",".join(leaked))
|
||||
for directory in candidates:
|
||||
exposure = _credential_exposure(directory)
|
||||
if exposure is not None:
|
||||
raise IsolatedExecutorError(exposure)
|
||||
# In the intended PrivateNetwork namespace host loopback services are unreachable.
|
||||
try:
|
||||
probe = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
|
||||
except OSError as exc:
|
||||
if exc.errno in {errno.EACCES, errno.EPERM, errno.EAFNOSUPPORT}:
|
||||
return
|
||||
raise IsolatedExecutorError("NETWORK_ISOLATION_PROBE_FAILED") from exc
|
||||
probe.settimeout(0.15)
|
||||
try:
|
||||
if probe.connect_ex(("127.0.0.1", 18892)) == 0:
|
||||
raise IsolatedExecutorError("GOVERNED_BRIDGE_REACHABLE")
|
||||
finally:
|
||||
probe.close()
|
||||
|
||||
|
||||
def extract_source(archive: Path, root: Path) -> None:
|
||||
if archive.is_symlink() or not archive.is_file() or archive.stat().st_size > MAX_ARCHIVE_BYTES:
|
||||
raise IsolatedExecutorError("SOURCE_ARCHIVE_INVALID")
|
||||
with tarfile.open(archive, "r:gz") as tf:
|
||||
for member in tf.getmembers():
|
||||
path = Path(member.name)
|
||||
if path.is_absolute() or ".." in path.parts or ".git" in path.parts:
|
||||
raise IsolatedExecutorError("SOURCE_ARCHIVE_PATH_INVALID")
|
||||
if member.issym() or member.islnk():
|
||||
raise IsolatedExecutorError("SOURCE_ARCHIVE_LINK_DENY")
|
||||
tf.extractall(root, filter="data")
|
||||
|
||||
|
||||
def run_command(item: Mapping[str, Any], root: Path) -> dict[str, Any]:
|
||||
argv = item.get("argv")
|
||||
if not isinstance(argv, Sequence) or isinstance(argv, (str, bytes)) or not argv:
|
||||
raise IsolatedExecutorError("COMMAND_INVALID")
|
||||
argv = [str(part) for part in argv]
|
||||
if argv[0] not in ALLOWED_PROGRAMS:
|
||||
raise IsolatedExecutorError("COMMAND_PROGRAM_DENY")
|
||||
if argv[0] == "/usr/bin/python3" and "-m" in argv:
|
||||
index = argv.index("-m")
|
||||
if index + 1 >= len(argv) or argv[index + 1] not in {"pytest", "py_compile"}:
|
||||
raise IsolatedExecutorError("PYTHON_MODULE_DENY")
|
||||
if argv[0] == "/usr/bin/git" and any(
|
||||
token in {"push", "update-ref", "commit", "merge", "rebase", "reset", "clean", "branch"}
|
||||
for token in argv[1:]
|
||||
):
|
||||
raise IsolatedExecutorError("GIT_MUTATION_DENY")
|
||||
timeout = int(item.get("timeout_seconds") or 300)
|
||||
if not 1 <= timeout <= 1800:
|
||||
raise IsolatedExecutorError("COMMAND_TIMEOUT_INVALID")
|
||||
cwd = root if item.get("cwd", ".") == "." else resolve_under(root, str(item.get("cwd")))
|
||||
started = time.monotonic()
|
||||
completed = subprocess.run(
|
||||
argv,
|
||||
cwd=cwd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=False,
|
||||
timeout=timeout,
|
||||
env={"PATH": "/usr/bin:/bin", "LC_ALL": "C.UTF-8"},
|
||||
)
|
||||
result = {
|
||||
"label": str(item.get("label") or "command"),
|
||||
"exit_code": completed.returncode,
|
||||
"stdout_sha256": sha256(completed.stdout.encode("utf-8", "replace")),
|
||||
"stderr_sha256": sha256(completed.stderr.encode("utf-8", "replace")),
|
||||
"duration_ms": int((time.monotonic() - started) * 1000),
|
||||
}
|
||||
if completed.returncode != 0:
|
||||
raise IsolatedExecutorError(
|
||||
"COMMAND_FAILED:" + result["label"] + ":" + str(completed.returncode)
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
def apply_changes(request: Mapping[str, Any], root: Path) -> list[str]:
|
||||
changes = request.get("change_set")
|
||||
if not isinstance(changes, list) or not changes:
|
||||
raise IsolatedExecutorError("CHANGE_SET_INVALID")
|
||||
changed: list[str] = []
|
||||
for change in changes:
|
||||
if not isinstance(change, Mapping):
|
||||
raise IsolatedExecutorError("CHANGE_INVALID")
|
||||
relative = safe_relative(change.get("path"))
|
||||
path = resolve_under(root, relative)
|
||||
current = path.read_bytes() if path.is_file() else None
|
||||
expected = change.get("expected_sha256")
|
||||
if expected is not None and (current is None or sha256(current) != expected):
|
||||
raise IsolatedExecutorError("SOURCE_DRIFT:" + relative)
|
||||
operation = change.get("operation")
|
||||
if operation == "write_file":
|
||||
content = change.get("content")
|
||||
if not isinstance(content, str):
|
||||
raise IsolatedExecutorError("WRITE_CONTENT_INVALID")
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(content, encoding="utf-8")
|
||||
elif operation == "replace_text":
|
||||
if current is None:
|
||||
raise IsolatedExecutorError("REPLACE_SOURCE_MISSING")
|
||||
old = str(change.get("old"))
|
||||
new = str(change.get("new"))
|
||||
count = int(change.get("count", 1))
|
||||
text = current.decode("utf-8")
|
||||
if text.count(old) != count:
|
||||
raise IsolatedExecutorError("REPLACE_COUNT_INVALID:" + relative)
|
||||
path.write_text(text.replace(old, new), encoding="utf-8")
|
||||
elif operation == "delete_file":
|
||||
if path.exists():
|
||||
path.unlink()
|
||||
else:
|
||||
raise IsolatedExecutorError("CHANGE_OPERATION_INVALID")
|
||||
changed.append(relative)
|
||||
return sorted(set(changed))
|
||||
|
||||
|
||||
def changed_bundle(root: Path, changed: list[str]) -> list[dict[str, Any]]:
|
||||
files = []
|
||||
for relative in changed:
|
||||
path = resolve_under(root, relative)
|
||||
if path.exists():
|
||||
data = path.read_bytes()
|
||||
if len(data) > MAX_FILE_BYTES:
|
||||
raise IsolatedExecutorError("CHANGED_FILE_TOO_LARGE:" + relative)
|
||||
files.append({
|
||||
"path": relative,
|
||||
"deleted": False,
|
||||
"sha256": sha256(data),
|
||||
"content_b64": base64.b64encode(data).decode("ascii"),
|
||||
})
|
||||
else:
|
||||
files.append({"path": relative, "deleted": True, "sha256": None, "content_b64": None})
|
||||
return files
|
||||
|
||||
|
||||
def execute_request(request_path: Path, result_path: Path) -> None:
|
||||
assert_uncredentialed()
|
||||
request = json.loads(request_path.read_text(encoding="utf-8"))
|
||||
if request.get("schema") != "aios.isolated-execution.request.v1":
|
||||
raise IsolatedExecutorError("REQUEST_SCHEMA_INVALID")
|
||||
request_id = request.get("request_id")
|
||||
if not isinstance(request_id, str) or not REQUEST_ID_RE.fullmatch(request_id):
|
||||
raise IsolatedExecutorError("REQUEST_ID_INVALID")
|
||||
source_archive = Path(str(request.get("source_archive") or ""))
|
||||
if not source_archive.is_absolute():
|
||||
raise IsolatedExecutorError("SOURCE_ARCHIVE_PATH_INVALID")
|
||||
expected_archive_sha = str(request.get("source_archive_sha256") or "")
|
||||
if sha256(source_archive.read_bytes()) != expected_archive_sha:
|
||||
raise IsolatedExecutorError("SOURCE_ARCHIVE_SHA_MISMATCH")
|
||||
with tempfile.TemporaryDirectory(prefix="aios-isolated-executor-") as temporary:
|
||||
root = Path(temporary) / "workspace"
|
||||
root.mkdir()
|
||||
extract_source(source_archive, root)
|
||||
changed = apply_changes(request, root)
|
||||
commands = [
|
||||
run_command(item, root)
|
||||
for item in request.get("verification", [])
|
||||
if isinstance(item, Mapping)
|
||||
]
|
||||
result = {
|
||||
"schema": "aios.isolated-execution.result.v1",
|
||||
"request_id": request_id,
|
||||
"request_sha256": sha256(canonical(request)),
|
||||
"changed_files": changed_bundle(root, changed),
|
||||
"verification": commands,
|
||||
"credential_isolation": {
|
||||
"credential_env_absent": True,
|
||||
"credential_mount_inaccessible": True,
|
||||
"governed_bridge_unreachable": True,
|
||||
},
|
||||
}
|
||||
result["result_sha256"] = sha256(canonical(result))
|
||||
temporary_result = result_path.with_suffix(".tmp")
|
||||
temporary_result.write_text(json.dumps(result, sort_keys=True, separators=(",", ":")), encoding="utf-8")
|
||||
os.replace(temporary_result, result_path)
|
||||
|
||||
|
||||
def serve(root: Path) -> None:
|
||||
assert_uncredentialed()
|
||||
requests = root / "requests"
|
||||
results = root / "results"
|
||||
failed = root / "failed"
|
||||
for path in (requests, results, failed):
|
||||
path.mkdir(parents=True, exist_ok=True)
|
||||
while True:
|
||||
for request in sorted(requests.glob("*.json")):
|
||||
if request.is_symlink():
|
||||
continue
|
||||
result = results / request.name
|
||||
try:
|
||||
execute_request(request, result)
|
||||
request.unlink()
|
||||
except Exception as exc:
|
||||
(failed / request.name).write_text(
|
||||
json.dumps({"error": str(exc) or type(exc).__name__}, sort_keys=True),
|
||||
encoding="utf-8",
|
||||
)
|
||||
request.unlink(missing_ok=True)
|
||||
time.sleep(0.5)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--root", default="/var/lib/aios-online-agent-executor")
|
||||
parser.add_argument("--request")
|
||||
parser.add_argument("--result")
|
||||
args = parser.parse_args()
|
||||
if args.request and args.result:
|
||||
execute_request(Path(args.request), Path(args.result))
|
||||
else:
|
||||
serve(Path(args.root))
|
||||
@@ -3,6 +3,15 @@ from __future__ import annotations
|
||||
import hashlib, hmac, json, os, re, subprocess, sys, time, urllib.parse, urllib.request, uuid
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from pathlib import Path
|
||||
|
||||
from aios_caller_admission_projection import (
|
||||
CALLER,
|
||||
SCOPE,
|
||||
GOVERNED_TASK_SCOPE,
|
||||
PROJECTED_SCOPES,
|
||||
CallerProjectionClient,
|
||||
CallerProjectionError,
|
||||
)
|
||||
from baseline_authority import BaselineAuthority, BaselineAuthorityError
|
||||
from typing import Any
|
||||
|
||||
@@ -89,6 +98,11 @@ SILENT_RELEASE_PUBLIC_KEYS = Path(os.getenv(
|
||||
'AIOS_SILENT_RELEASE_PUBLIC_KEYS',
|
||||
'/etc/aios-gitops/silent-release-owner-public-keys.json',
|
||||
))
|
||||
CALLER_PROJECTION_SOCKET = Path(os.getenv(
|
||||
'AIOS_OWNER_AUTH_BROKER_SOCKET',
|
||||
'/run/aios-owner-authorization-broker/broker.sock',
|
||||
))
|
||||
CALLER_PROJECTION_CLIENT = CallerProjectionClient(CALLER_PROJECTION_SOCKET)
|
||||
monitor = ActionMonitor()
|
||||
|
||||
BASE_MODELS = [
|
||||
@@ -112,6 +126,9 @@ READ_ONLY_GET_PATHS = frozenset({
|
||||
'/admin/ai-evolution/api/data',
|
||||
'/api/release-consistency', '/api/tag-publication-status',
|
||||
'/api/release-acceptance',
|
||||
'/api/governed-write-capabilities', '/api/control-plane-snapshot',
|
||||
'/api/caller-capabilities',
|
||||
'/api/online-agent-task', '/api/online-agent-task-events',
|
||||
'/getReleaseCandidate', '/getReleasePlan', '/getReleaseAcceptance',
|
||||
'/getApprovalEnvelope', '/getReleaseSaga', '/getCapabilityStatus',
|
||||
'/getRecoveryStatus',
|
||||
@@ -124,6 +141,25 @@ SILENT_RELEASE_POST_PATHS = frozenset({
|
||||
'/startDeployment',
|
||||
})
|
||||
|
||||
GOVERNED_EXECUTION_CAPABILITIES = frozenset({
|
||||
"governed.write.branch",
|
||||
"governed.write.file",
|
||||
})
|
||||
|
||||
|
||||
def requires_governed_execution(value: Mapping[str, Any]) -> bool:
|
||||
capabilities = value.get("required_capabilities")
|
||||
if capabilities is None:
|
||||
return False
|
||||
if not isinstance(capabilities, list):
|
||||
return True
|
||||
return bool(
|
||||
GOVERNED_EXECUTION_CAPABILITIES.intersection(
|
||||
{str(item) for item in capabilities}
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def reject_non_read_http(handler, method: str, path: str) -> bool:
|
||||
if method == 'GET':
|
||||
return False
|
||||
@@ -407,14 +443,113 @@ class H(BaseHTTPRequestHandler):
|
||||
except Exception: return {'_raw':raw}
|
||||
def actor(self):
|
||||
auth=self.headers.get('Authorization',''); tok=auth[7:].strip() if auth.startswith('Bearer ') else self.headers.get('X-AIOS-Token','')
|
||||
rec=authenticate(tok)
|
||||
if rec: return {'ok':True,'account':safe(rec.get('account') or rec.get('name') or 'token-user'),'role':rec.get('role','user'),'scopes':set(rec.get('scopes') or [])}
|
||||
return {'ok':False,'account':'anonymous','role':'anonymous','scopes':set()}
|
||||
def need(self, scope):
|
||||
a=self.actor()
|
||||
if not a['ok']: self.sendj({'error':'unauthorized','hint':'Bearer token required'},401); return None
|
||||
if '*' not in a['scopes'] and scope not in a['scopes']: self.sendj({'error':'forbidden','required_scope':scope,'account':a['account']},403); return None
|
||||
try:
|
||||
rec=authenticate(tok)
|
||||
except Exception:
|
||||
rec=None
|
||||
if not isinstance(rec, dict) or not rec:
|
||||
return {
|
||||
'ok': False,
|
||||
'account': 'anonymous',
|
||||
'role': 'anonymous',
|
||||
'scopes': set(),
|
||||
'static_scopes': set(),
|
||||
'projection': None,
|
||||
'credential_loaded': False,
|
||||
}
|
||||
scopes = set(rec.get('scopes') or [])
|
||||
return {
|
||||
'ok': True,
|
||||
'account': safe(rec.get('account') or rec.get('name') or 'token-user'),
|
||||
'role': rec.get('role', 'user'),
|
||||
'scopes': scopes,
|
||||
'static_scopes': set(scopes),
|
||||
'projection': None,
|
||||
'credential_loaded': False,
|
||||
}
|
||||
def need(self, scope, *, projection_request=None):
|
||||
a = self.actor()
|
||||
if not a['ok']:
|
||||
self.sendj({'error': 'unauthorized', 'hint': 'Bearer token required'}, 401)
|
||||
return None
|
||||
if a['account'] == CALLER and scope in PROJECTED_SCOPES:
|
||||
try:
|
||||
result = CALLER_PROJECTION_CLIENT.rehydrate(
|
||||
a['account'],
|
||||
scope,
|
||||
projection_request,
|
||||
)
|
||||
except CallerProjectionError as exc:
|
||||
self.sendj(
|
||||
{
|
||||
'error': 'caller_projection_denied',
|
||||
'projection_state': 'DENIED',
|
||||
'detail': exc.code,
|
||||
'account': a['account'],
|
||||
},
|
||||
exc.status,
|
||||
)
|
||||
return None
|
||||
projection = result.public
|
||||
a['scopes'].update(projection.get('effective_scopes') or [])
|
||||
a['projection'] = projection
|
||||
a['credential_loaded'] = result.credential_loaded
|
||||
if '*' not in a['scopes'] and scope not in a['scopes']:
|
||||
self.sendj(
|
||||
{
|
||||
'error': 'forbidden',
|
||||
'required_scope': scope,
|
||||
'account': a['account'],
|
||||
},
|
||||
403,
|
||||
)
|
||||
return None
|
||||
return a
|
||||
def caller_capabilities(self):
|
||||
actor = self.actor()
|
||||
if not actor['ok']:
|
||||
return self.sendj(
|
||||
{'error': 'unauthorized', 'hint': 'Bearer token required'},
|
||||
401,
|
||||
)
|
||||
effective = set(actor['static_scopes'])
|
||||
projection_state = 'NOT_REQUIRED'
|
||||
credential_state = 'NOT_REQUIRED'
|
||||
rehydration_state = 'NOT_APPLICABLE'
|
||||
admitted = True
|
||||
projection_error = None
|
||||
if actor['account'] == CALLER:
|
||||
try:
|
||||
result = CALLER_PROJECTION_CLIENT.rehydrate(
|
||||
actor['account'],
|
||||
GOVERNED_TASK_SCOPE,
|
||||
{},
|
||||
)
|
||||
except CallerProjectionError as exc:
|
||||
admitted = False
|
||||
projection_state = 'DENIED'
|
||||
credential_state = 'NOT_REHYDRATED'
|
||||
rehydration_state = 'FAILED'
|
||||
projection_error = exc.code
|
||||
else:
|
||||
effective.update(result.public.get('effective_scopes') or [])
|
||||
projection_state = result.public['projection_state']
|
||||
credential_state = result.public['credential_state']
|
||||
rehydration_state = result.public['rehydration_state']
|
||||
return self.sendj(
|
||||
{
|
||||
'schema': 'aios.caller-capability-introspection.v1',
|
||||
'caller_identity': actor['account'],
|
||||
'admitted': admitted,
|
||||
'effective_scopes': sorted(effective),
|
||||
'projection_state': projection_state,
|
||||
'credential_state': credential_state,
|
||||
'rehydration_state': rehydration_state,
|
||||
'projection_error': projection_error,
|
||||
'secret_exposed': False,
|
||||
}
|
||||
)
|
||||
|
||||
def bridge_release(self, path, data):
|
||||
route = {
|
||||
'/createTagApprovalRequest': '/v2/tag/approval-request',
|
||||
@@ -446,24 +581,183 @@ class H(BaseHTTPRequestHandler):
|
||||
return self.sendj(body, exc.code)
|
||||
except (urllib.error.URLError, TimeoutError) as exc:
|
||||
return self.sendj({'error': 'GOVERNED_BRIDGE_UNAVAILABLE', 'detail': type(exc).__name__}, 503)
|
||||
def do_POST(self):
|
||||
path = urllib.parse.urlparse(self.path).path
|
||||
if path in {
|
||||
'/createTagApprovalRequest', '/requestOrCreateTag', '/getTagPublicationStatus',
|
||||
'/buildProductionArtifact', '/executeApprovedProductionRelease',
|
||||
'/getReleaseConsistency', '/runReleaseAcceptance',
|
||||
}:
|
||||
actor = self.need('tag:create')
|
||||
if not actor:
|
||||
return
|
||||
return self.bridge_release(path, self.body())
|
||||
if reject_non_read_http(self, 'POST', path):
|
||||
return
|
||||
return self.sendj({'error': 'not_found', 'path': path}, 404)
|
||||
def bridge_v2_json(self, route, data=None, method='POST'):
|
||||
base = os.getenv('AIOS_BRIDGE_V2_URL', 'http://127.0.0.1:18892').rstrip('/')
|
||||
payload = None if data is None else json.dumps(
|
||||
data, sort_keys=True, separators=(',', ':')
|
||||
).encode('utf-8')
|
||||
request = urllib.request.Request(
|
||||
base + route,
|
||||
data=payload,
|
||||
headers={'Content-Type': 'application/json'} if payload is not None else {},
|
||||
method=method,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
result = json.loads(response.read().decode('utf-8'))
|
||||
return self.sendj(result, response.status)
|
||||
except urllib.error.HTTPError as exc:
|
||||
try:
|
||||
body = json.loads(exc.read().decode('utf-8'))
|
||||
except Exception:
|
||||
body = {'error': 'bridge_http_error'}
|
||||
return self.sendj(body, exc.code)
|
||||
except (urllib.error.URLError, TimeoutError) as exc:
|
||||
return self.sendj(
|
||||
{'error': 'GOVERNED_BRIDGE_UNAVAILABLE', 'detail': type(exc).__name__},
|
||||
503,
|
||||
)
|
||||
|
||||
def control_plane_snapshot(self):
|
||||
"""Build a non-sensitive snapshot locally when Bridge v2 has no snapshot HTTP route."""
|
||||
base = os.getenv('AIOS_BRIDGE_V2_URL', 'http://127.0.0.1:18892').rstrip('/')
|
||||
|
||||
def bridge_get(route):
|
||||
request = urllib.request.Request(
|
||||
base + route,
|
||||
headers={'Accept': 'application/json'},
|
||||
method='GET',
|
||||
)
|
||||
with urllib.request.urlopen(request, timeout=15) as response:
|
||||
if response.status != 200:
|
||||
raise RuntimeError('bridge_read_http_' + str(response.status))
|
||||
value = json.loads(response.read().decode('utf-8'))
|
||||
if not isinstance(value, dict):
|
||||
raise RuntimeError('bridge_read_not_object')
|
||||
return value
|
||||
|
||||
try:
|
||||
runtime = bridge_get('/v2/runtime')
|
||||
capabilities = bridge_get('/v2/capabilities')
|
||||
repository = repository_snapshot(
|
||||
git_dir=AUTHORITATIVE_GIT_DIR,
|
||||
repository_identity=REPOSITORY_IDENTITY,
|
||||
)
|
||||
if not repository.get('repository_available'):
|
||||
return self.sendj({
|
||||
'error': 'AUTHORITATIVE_REPOSITORY_UNAVAILABLE',
|
||||
'query_error': repository.get('query_error'),
|
||||
}, 503)
|
||||
baseline = dict(BASELINE_AUTHORITY.read())
|
||||
except BaselineAuthorityError as exc:
|
||||
return self.sendj({
|
||||
'error': 'RECONCILIATION_REQUIRED',
|
||||
'detail': str(exc),
|
||||
}, 503)
|
||||
except urllib.error.HTTPError as exc:
|
||||
return self.sendj({
|
||||
'error': 'GOVERNED_BRIDGE_UNAVAILABLE',
|
||||
'detail': 'HTTP_' + str(exc.code),
|
||||
}, 503)
|
||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError, RuntimeError, json.JSONDecodeError) as exc:
|
||||
return self.sendj({
|
||||
'error': 'GOVERNED_BRIDGE_UNAVAILABLE',
|
||||
'detail': type(exc).__name__,
|
||||
}, 503)
|
||||
|
||||
legacy = capabilities.get('legacy_writes_enabled')
|
||||
if legacy is None:
|
||||
legacy = capabilities.get('legacy_global_writes_enabled')
|
||||
payload = {
|
||||
'schema': 'aios.control-plane-snapshot.aggregate.v1',
|
||||
'snapshot_source': 'model-api-local-aggregate',
|
||||
'version': {
|
||||
'target_release': runtime.get('control_plane_release_version'),
|
||||
},
|
||||
'runtime': {
|
||||
'bridge_schema_version': runtime.get('bridge_schema_version'),
|
||||
'control_plane_release_version': runtime.get('control_plane_release_version'),
|
||||
'runtime_release_commit': runtime.get('runtime_release_commit'),
|
||||
'runtime_path': runtime.get('runtime_path'),
|
||||
'artifact_sha256': runtime.get('artifact_sha256'),
|
||||
'drift_status': runtime.get('drift_status'),
|
||||
'deployment_state': runtime.get('deployment_state'),
|
||||
},
|
||||
'repository': {
|
||||
'identity': runtime.get('repository_identity') or runtime.get('repository') or REPOSITORY_IDENTITY,
|
||||
'authority_git_dir': runtime.get('authoritative_git_dir') or repository.get('authoritative_git_dir'),
|
||||
'authority_main_oid': repository.get('authoritative_head_oid'),
|
||||
},
|
||||
'production': {
|
||||
'baseline_version': baseline.get('current_baseline'),
|
||||
'target_oid': baseline.get('target_oid'),
|
||||
'deployment_state': baseline.get('status'),
|
||||
'baseline_generation': baseline.get('generation'),
|
||||
'baseline_sha256': baseline.get('authority_sha256'),
|
||||
},
|
||||
'task': {},
|
||||
'capabilities': {
|
||||
'legacy_writes_enabled': legacy,
|
||||
'governed_writes_enabled': capabilities.get('governed_writes_enabled'),
|
||||
'force_push': capabilities.get('force_push'),
|
||||
'main_write': capabilities.get('main_write'),
|
||||
'tag_write': capabilities.get('tag_write'),
|
||||
'baseline_write': capabilities.get('baseline_write'),
|
||||
'production_write': capabilities.get('production_write'),
|
||||
},
|
||||
'credential_broker': {
|
||||
'status': 'SERVER_SIDE_ONLY',
|
||||
'provider': 'BridgeV2RuntimeCredentialProjection',
|
||||
},
|
||||
'secret_material_exposed': False,
|
||||
}
|
||||
return self.sendj(payload)
|
||||
|
||||
def agent_task_control(self, method, route, data=None):
|
||||
token_path = Path(os.getenv(
|
||||
'AIOS_AGENT_TASK_CONTROL_TOKEN_FILE',
|
||||
'/run/credentials/aios-gitops-model-api-v2r2c1-staging.service/agent_task_control_token',
|
||||
))
|
||||
if token_path.is_symlink() or not token_path.is_file():
|
||||
return self.sendj({'error': 'AGENT_TASK_CONTROL_CREDENTIAL_UNAVAILABLE'}, 503)
|
||||
token = token_path.read_text(encoding='utf-8').strip()
|
||||
if len(token) < 32:
|
||||
return self.sendj({'error': 'AGENT_TASK_CONTROL_CREDENTIAL_INVALID'}, 503)
|
||||
base = os.getenv('AIOS_AGENT_TASK_API_URL', 'http://127.0.0.1:18940').rstrip('/')
|
||||
payload = None if data is None else json.dumps(
|
||||
data, sort_keys=True, separators=(',', ':')
|
||||
).encode('utf-8')
|
||||
headers = {'Authorization': 'Bearer ' + token, 'Accept': 'application/json'}
|
||||
if payload is not None:
|
||||
headers['Content-Type'] = 'application/json'
|
||||
request = urllib.request.Request(
|
||||
base + route, data=payload, headers=headers, method=method
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
result = json.loads(response.read().decode('utf-8'))
|
||||
return self.sendj(result, response.status)
|
||||
except urllib.error.HTTPError as exc:
|
||||
try:
|
||||
body = json.loads(exc.read().decode('utf-8'))
|
||||
except Exception:
|
||||
body = {'error': 'agent_task_http_error'}
|
||||
return self.sendj(body, exc.code)
|
||||
except (urllib.error.URLError, TimeoutError) as exc:
|
||||
return self.sendj(
|
||||
{'error': 'AGENT_TASK_API_UNAVAILABLE', 'detail': type(exc).__name__},
|
||||
503,
|
||||
)
|
||||
|
||||
def do_GET(self):
|
||||
u=urllib.parse.urlparse(self.path); path=u.path.rstrip('/') if u.path != '/' else u.path
|
||||
if path not in READ_ONLY_GET_PATHS: return self.sendj({'error':'not_found','path':path},404)
|
||||
q=urllib.parse.parse_qs(u.query)
|
||||
if path == '/api/governed-write-capabilities':
|
||||
return self.bridge_v2_json('/v2/capabilities', method='GET')
|
||||
if path == '/api/control-plane-snapshot':
|
||||
return self.control_plane_snapshot()
|
||||
if path == '/api/caller-capabilities':
|
||||
return self.caller_capabilities()
|
||||
if path in ('/api/online-agent-task', '/api/online-agent-task-events'):
|
||||
actor = self.need('agent-task:control')
|
||||
if not actor:
|
||||
return
|
||||
task_id = (q.get('task_id') or [''])[0]
|
||||
if not re.fullmatch(r'[A-Za-z0-9][A-Za-z0-9._:-]{2,179}', task_id):
|
||||
return self.sendj({'error': 'task_id_invalid'}, 400)
|
||||
suffix = '/events' if path.endswith('-events') else ''
|
||||
return self.agent_task_control('GET', '/v1/tasks/' + task_id + suffix)
|
||||
try:
|
||||
if path in ('/health','/api/health'):
|
||||
return self.sendj({
|
||||
@@ -700,12 +994,68 @@ class H(BaseHTTPRequestHandler):
|
||||
return self.sendj({'error':'not_found','path':path},404)
|
||||
def do_POST(self):
|
||||
path=urllib.parse.urlparse(self.path).path.rstrip('/')
|
||||
governed_routes = {
|
||||
'/createGovernedTask': ('/v2/governed-task', 'branch:create'),
|
||||
'/acquireWriterLease': ('/v2/writer-lease', 'file:write'),
|
||||
'/commitFileGoverned': ('/v2/commit-file', 'file:write'),
|
||||
'/commitFilesGoverned': ('/v2/commit-files', 'file:write'),
|
||||
'/getGitOpsJob': ('/v2/job', 'file:write'),
|
||||
'/resumeGitOpsJob': ('/v2/job/resume', 'file:write'),
|
||||
'/reconcileGitOpsJob': ('/v2/job/reconcile', 'file:write'),
|
||||
'/createTagApprovalRequest': ('/v2/tag/approval-request', 'tag:create'),
|
||||
'/requestOrCreateTag': ('/v2/tag/publish', 'tag:create'),
|
||||
'/getTagPublicationStatus': ('/v2/tag/status', 'tag:create'),
|
||||
'/buildProductionArtifact': ('/v2/release/artifact', 'tag:create'),
|
||||
'/executeApprovedProductionRelease': ('/v2/release/execute', 'tag:create'),
|
||||
'/getReleaseConsistency': ('/v2/release/consistency', 'tag:create'),
|
||||
'/runReleaseAcceptance': ('/v2/release/acceptance', 'tag:create'),
|
||||
}
|
||||
if path in governed_routes:
|
||||
route, scope = governed_routes[path]
|
||||
if path == '/createGovernedTask' and self.actor()['account'] == CALLER:
|
||||
scope = GOVERNED_TASK_SCOPE
|
||||
actor = self.need(scope)
|
||||
if not actor:
|
||||
return
|
||||
return self.bridge_v2_json(route, self.body(), method='POST')
|
||||
if path in {
|
||||
'/createOnlineAgentTask', '/registerOnlineAgent',
|
||||
'/verifyOnlineAgentTask', '/cancelOnlineAgentTask',
|
||||
}:
|
||||
actor = self.need('agent-task:control')
|
||||
if not actor:
|
||||
return
|
||||
data = self.body()
|
||||
if path == '/createOnlineAgentTask':
|
||||
if requires_governed_execution(data):
|
||||
return self.sendj(
|
||||
{
|
||||
'error': 'governed_execution_binding_required',
|
||||
'hint': 'use createGovernedTask',
|
||||
},
|
||||
409,
|
||||
)
|
||||
return self.agent_task_control('POST', '/v1/tasks', data)
|
||||
if path == '/registerOnlineAgent':
|
||||
return self.agent_task_control('POST', '/v1/agents/register', data)
|
||||
task_id = str(data.pop('task_id', '') or '')
|
||||
if not re.fullmatch(r'[A-Za-z0-9][A-Za-z0-9._:-]{2,179}', task_id):
|
||||
return self.sendj({'error': 'task_id_invalid'}, 400)
|
||||
suffix = '/verify' if path == '/verifyOnlineAgentTask' else '/cancel'
|
||||
return self.agent_task_control('POST', '/v1/tasks/' + task_id + suffix, data)
|
||||
if reject_non_read_http(self, 'POST', path): return
|
||||
data=self.body()
|
||||
try:
|
||||
if path == '/createReleaseCandidate':
|
||||
a=self.need('release:candidate')
|
||||
if not a: return
|
||||
a = self.need(
|
||||
'release:candidate',
|
||||
projection_request={
|
||||
'source_commit': str(data.get('source_commit') or ''),
|
||||
'version': str(data.get('version') or ''),
|
||||
},
|
||||
)
|
||||
if not a:
|
||||
return
|
||||
return self.sendj(
|
||||
silent_release_service().create_release_candidate(data)
|
||||
)
|
||||
@@ -996,7 +1346,7 @@ def api_spec():
|
||||
return {
|
||||
'version': 'V2R2C1-IMMUTABLE-STAGING',
|
||||
'openapi': '/api/openapi.yaml',
|
||||
'read': ['GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /getReleaseCandidate','GET /getApprovalEnvelope','GET /getReleaseSaga','GET /admin/ai-evolution'],
|
||||
'read': ['GET /api/caller-capabilities','GET /api/base','GET /api/ver','GET /api/diff','GET /api/patch','GET /api/model','GET /api/run','GET /getReleaseCandidate','GET /getApprovalEnvelope','GET /getReleaseSaga','GET /admin/ai-evolution'],
|
||||
'write': ['POST /api/branch','POST /api/file','POST /api/commit','POST /api/patch','POST /api/tag','POST /api/rollback','POST /api/model','PUT /api/model-priority','POST /api/nl','POST /createReleaseCandidate','POST /submitOwnerApproval','POST /startDeployment'],
|
||||
'policy': {
|
||||
'bearer_required_for_write': True,
|
||||
@@ -1011,6 +1361,9 @@ def api_spec():
|
||||
'silent_release_shadow_default': True,
|
||||
'runtime_mode': 'IMMUTABLE_STAGING',
|
||||
'governed_release_routing': 'bridge-v2',
|
||||
'caller_admission_projection': 'durable-owner-policy-server-side-ack',
|
||||
'caller_projection_scope': SCOPE,
|
||||
'caller_projection_caller': CALLER,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,232 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Root-owned Model Governance configuration reconciler.
|
||||
|
||||
The config contains provider/model/policy metadata only. Raw credentials are rejected by
|
||||
aios_model_governance and never stored in the governance database.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
|
||||
from aios_model_governance import (
|
||||
ModelGovernanceError,
|
||||
ModelGovernanceStore,
|
||||
ModelRecord,
|
||||
ProviderRecord,
|
||||
ScopePolicy,
|
||||
)
|
||||
|
||||
SCHEMA = "aios.model-governance.bootstrap.v1"
|
||||
MAX_CONFIG_BYTES = 512 * 1024
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value, ensure_ascii=False, sort_keys=True, separators=(",", ":")
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def fail(code: str) -> None:
|
||||
raise SystemExit(code)
|
||||
|
||||
|
||||
def _load(path: Path) -> dict[str, Any]:
|
||||
if path.is_symlink() or not path.is_file() or path.stat().st_size > MAX_CONFIG_BYTES:
|
||||
fail("MODEL_GOVERNANCE_CONFIG_INVALID")
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError:
|
||||
fail("MODEL_GOVERNANCE_CONFIG_INVALID")
|
||||
if not isinstance(value, Mapping) or value.get("schema") != SCHEMA:
|
||||
fail("MODEL_GOVERNANCE_CONFIG_SCHEMA_INVALID")
|
||||
return dict(value)
|
||||
|
||||
|
||||
def _provider_desired(value: Mapping[str, Any]) -> ProviderRecord:
|
||||
return ProviderRecord(
|
||||
provider_id=str(value.get("provider_id") or ""),
|
||||
credential_ref=value.get("credential_ref"),
|
||||
enabled=bool(value.get("enabled", True)),
|
||||
failure_domain=str(value.get("failure_domain") or "default"),
|
||||
max_failures=int(value.get("max_failures") or 3),
|
||||
cooldown_seconds=int(value.get("cooldown_seconds") or 60),
|
||||
)
|
||||
|
||||
|
||||
def _model_desired(value: Mapping[str, Any]) -> ModelRecord:
|
||||
return ModelRecord(
|
||||
model_id=str(value.get("model_id") or ""),
|
||||
provider_id=str(value.get("provider_id") or ""),
|
||||
version=str(value.get("version") or ""),
|
||||
capabilities=tuple(value.get("capabilities") or ()),
|
||||
input_cost_micros_per_1k=int(value.get("input_cost_micros_per_1k") or 0),
|
||||
output_cost_micros_per_1k=int(value.get("output_cost_micros_per_1k") or 0),
|
||||
max_input_tokens=int(value.get("max_input_tokens") or 0),
|
||||
max_output_tokens=int(value.get("max_output_tokens") or 0),
|
||||
evaluation_state=str(value.get("evaluation_state") or "APPROVED"),
|
||||
evaluation_sha256=str(value.get("evaluation_sha256") or ""),
|
||||
enabled=bool(value.get("enabled", True)),
|
||||
priority=int(value.get("priority") or 100),
|
||||
)
|
||||
|
||||
|
||||
def _policy_desired(value: Mapping[str, Any]) -> ScopePolicy:
|
||||
return ScopePolicy(
|
||||
scope_type=str(value.get("scope_type") or ""),
|
||||
tenant_id=value.get("tenant_id"),
|
||||
project_id=value.get("project_id"),
|
||||
allowed_models=tuple(value.get("allowed_models") or ()),
|
||||
denied_providers=tuple(value.get("denied_providers") or ()),
|
||||
required_capabilities=tuple(value.get("required_capabilities") or ()),
|
||||
pinned_model_id=value.get("pinned_model_id"),
|
||||
pinned_model_version=value.get("pinned_model_version"),
|
||||
max_input_tokens_per_request=int(value.get("max_input_tokens_per_request") or 0),
|
||||
max_output_tokens_per_request=int(value.get("max_output_tokens_per_request") or 0),
|
||||
daily_token_budget=int(value.get("daily_token_budget") or 0),
|
||||
daily_cost_budget_micros=int(value.get("daily_cost_budget_micros") or 0),
|
||||
fallback_limit=int(value.get("fallback_limit") or 0),
|
||||
)
|
||||
|
||||
|
||||
def _row_dict(row: object) -> dict[str, Any] | None:
|
||||
return dict(row) if row is not None else None
|
||||
|
||||
|
||||
def _provider_matches(row: Mapping[str, Any], desired: ProviderRecord) -> bool:
|
||||
return (
|
||||
row["credential_ref"] == desired.credential_ref
|
||||
and bool(row["enabled"]) == desired.enabled
|
||||
and row["failure_domain"] == desired.failure_domain
|
||||
and int(row["max_failures"]) == desired.max_failures
|
||||
and int(row["cooldown_seconds"]) == desired.cooldown_seconds
|
||||
)
|
||||
|
||||
|
||||
def _model_matches(row: Mapping[str, Any], desired: ModelRecord) -> bool:
|
||||
return (
|
||||
row["provider_id"] == desired.provider_id
|
||||
and row["version"] == desired.version
|
||||
and tuple(json.loads(row["capabilities_json"])) == tuple(sorted(set(desired.capabilities)))
|
||||
and int(row["input_cost_micros_per_1k"]) == desired.input_cost_micros_per_1k
|
||||
and int(row["output_cost_micros_per_1k"]) == desired.output_cost_micros_per_1k
|
||||
and int(row["max_input_tokens"]) == desired.max_input_tokens
|
||||
and int(row["max_output_tokens"]) == desired.max_output_tokens
|
||||
and row["evaluation_state"] == desired.evaluation_state
|
||||
and row["evaluation_sha256"] == desired.evaluation_sha256
|
||||
and bool(row["enabled"]) == desired.enabled
|
||||
and int(row["priority"]) == desired.priority
|
||||
)
|
||||
|
||||
|
||||
def _policy_matches(row: Mapping[str, Any], desired: ScopePolicy) -> bool:
|
||||
return (
|
||||
row["scope_type"] == desired.scope_type
|
||||
and row["tenant_id"] == desired.tenant_id
|
||||
and row["project_id"] == desired.project_id
|
||||
and tuple(json.loads(row["allowed_models_json"])) == tuple(sorted(set(desired.allowed_models)))
|
||||
and tuple(json.loads(row["denied_providers_json"])) == tuple(sorted(set(desired.denied_providers)))
|
||||
and tuple(json.loads(row["required_capabilities_json"])) == tuple(sorted(set(desired.required_capabilities)))
|
||||
and row["pinned_model_id"] == desired.pinned_model_id
|
||||
and row["pinned_model_version"] == desired.pinned_model_version
|
||||
and int(row["max_input_tokens_per_request"]) == desired.max_input_tokens_per_request
|
||||
and int(row["max_output_tokens_per_request"]) == desired.max_output_tokens_per_request
|
||||
and int(row["daily_token_budget"]) == desired.daily_token_budget
|
||||
and int(row["daily_cost_budget_micros"]) == desired.daily_cost_budget_micros
|
||||
and int(row["fallback_limit"]) == desired.fallback_limit
|
||||
)
|
||||
|
||||
|
||||
def apply_config(db_path: Path, config_path: Path) -> dict[str, Any]:
|
||||
config = _load(config_path)
|
||||
config_sha = hashlib.sha256(canonical(config)).hexdigest()
|
||||
providers = config.get("providers") or []
|
||||
models = config.get("models") or []
|
||||
policies = config.get("policies") or []
|
||||
if not all(isinstance(value, list) for value in (providers, models, policies)):
|
||||
fail("MODEL_GOVERNANCE_CONFIG_COLLECTION_INVALID")
|
||||
|
||||
store = ModelGovernanceStore(db_path)
|
||||
changes = {"providers": 0, "models": 0, "policies": 0, "unchanged": 0}
|
||||
try:
|
||||
for item in providers:
|
||||
if not isinstance(item, Mapping):
|
||||
fail("MODEL_GOVERNANCE_PROVIDER_CONFIG_INVALID")
|
||||
desired = _provider_desired(item)
|
||||
row = store.conn.execute(
|
||||
"SELECT * FROM model_governance_providers WHERE provider_id=?",
|
||||
(desired.provider_id,),
|
||||
).fetchone()
|
||||
if row is not None and _provider_matches(row, desired):
|
||||
changes["unchanged"] += 1
|
||||
continue
|
||||
expected = int(row["revision"]) if row is not None else 0
|
||||
store.register_provider(desired, expected_revision=expected)
|
||||
changes["providers"] += 1
|
||||
|
||||
for item in models:
|
||||
if not isinstance(item, Mapping):
|
||||
fail("MODEL_GOVERNANCE_MODEL_CONFIG_INVALID")
|
||||
desired = _model_desired(item)
|
||||
row = store.conn.execute(
|
||||
"SELECT * FROM model_governance_models WHERE model_id=?",
|
||||
(desired.model_id,),
|
||||
).fetchone()
|
||||
if row is not None and _model_matches(row, desired):
|
||||
changes["unchanged"] += 1
|
||||
continue
|
||||
expected = int(row["revision"]) if row is not None else 0
|
||||
store.register_model(desired, expected_revision=expected)
|
||||
changes["models"] += 1
|
||||
|
||||
for item in policies:
|
||||
if not isinstance(item, Mapping):
|
||||
fail("MODEL_GOVERNANCE_POLICY_CONFIG_INVALID")
|
||||
desired = _policy_desired(item)
|
||||
row = store.conn.execute(
|
||||
"SELECT * FROM model_governance_scope_policies WHERE scope_key=?",
|
||||
(desired.scope_key,),
|
||||
).fetchone()
|
||||
if row is not None and _policy_matches(row, desired):
|
||||
changes["unchanged"] += 1
|
||||
continue
|
||||
expected = int(row["revision"]) if row is not None else 0
|
||||
store.set_scope_policy(desired, expected_revision=expected)
|
||||
changes["policies"] += 1
|
||||
|
||||
if not store.verify_audit_chain():
|
||||
fail("MODEL_GOVERNANCE_AUDIT_CHAIN_INVALID")
|
||||
return {
|
||||
"schema": "aios.model-governance.bootstrap-result.v1",
|
||||
"database": str(db_path),
|
||||
"config_sha256": config_sha,
|
||||
"changes": changes,
|
||||
"audit_chain_valid": True,
|
||||
}
|
||||
finally:
|
||||
store.close()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--db", required=True)
|
||||
parser.add_argument("--config", required=True)
|
||||
parser.add_argument("--output")
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
result = apply_config(Path(args.db), Path(args.config))
|
||||
except ModelGovernanceError as exc:
|
||||
print(json.dumps({"status": "FAILED", "error": exc.code}, sort_keys=True))
|
||||
return 20
|
||||
data = json.dumps(result, indent=2, sort_keys=True) + "\n"
|
||||
if args.output:
|
||||
Path(args.output).write_text(data, encoding="utf-8")
|
||||
print(data, end="")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,302 @@
|
||||
"""Durable checkpoint journal for the generic Online Agent worker.
|
||||
|
||||
The JSON task state remains a fast cache. This SQLite journal is the durable,
|
||||
append-only evidence used for restart/resume/replay decisions.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
from typing import Any, Mapping
|
||||
|
||||
PHASE_ORDER = {
|
||||
"claimed": 10,
|
||||
"workspace_prepared": 20,
|
||||
"verification_passed": 30,
|
||||
"agent_runtime_done": 40,
|
||||
"source_capture_done": 40,
|
||||
"commit_done": 40,
|
||||
"reconciliation_required": 45,
|
||||
"result_pending": 50,
|
||||
"result_submitted": 60,
|
||||
}
|
||||
|
||||
|
||||
class CheckpointError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False, default=str).encode("utf-8")
|
||||
|
||||
|
||||
def sha256_json(value: object) -> str:
|
||||
return hashlib.sha256(canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CheckpointBinding:
|
||||
task_id: str
|
||||
attempt: int
|
||||
execution_digest: str
|
||||
job_id: str
|
||||
repository: str
|
||||
base_oid: str
|
||||
expected_branch_oid: str
|
||||
target_branch: str
|
||||
generation: int
|
||||
|
||||
def material(self) -> dict[str, Any]:
|
||||
return {
|
||||
"task_id": self.task_id,
|
||||
"attempt": self.attempt,
|
||||
"execution_digest": self.execution_digest,
|
||||
"job_id": self.job_id,
|
||||
"repository": self.repository,
|
||||
"base_oid": self.base_oid,
|
||||
"expected_branch_oid": self.expected_branch_oid,
|
||||
"target_branch": self.target_branch,
|
||||
"generation": self.generation,
|
||||
}
|
||||
|
||||
@property
|
||||
def binding_sha256(self) -> str:
|
||||
return sha256_json(self.material())
|
||||
|
||||
|
||||
class CheckpointStore:
|
||||
def __init__(self, path: Path) -> None:
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with self._connect() as connection:
|
||||
connection.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS checkpoints(
|
||||
task_id TEXT NOT NULL,
|
||||
attempt INTEGER NOT NULL,
|
||||
sequence INTEGER NOT NULL,
|
||||
phase TEXT NOT NULL,
|
||||
phase_order INTEGER NOT NULL,
|
||||
execution_digest TEXT NOT NULL,
|
||||
job_id TEXT NOT NULL,
|
||||
repository TEXT NOT NULL,
|
||||
base_oid TEXT NOT NULL,
|
||||
expected_branch_oid TEXT NOT NULL,
|
||||
target_branch TEXT NOT NULL,
|
||||
generation INTEGER NOT NULL,
|
||||
binding_sha256 TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
payload_sha256 TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(task_id, attempt, sequence)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_checkpoints_task_latest
|
||||
ON checkpoints(task_id, attempt DESC, sequence DESC);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS idx_checkpoints_exact_replay
|
||||
ON checkpoints(task_id, attempt, phase, payload_sha256);
|
||||
CREATE TABLE IF NOT EXISTS checkpoint_heads(
|
||||
task_id TEXT PRIMARY KEY,
|
||||
attempt INTEGER NOT NULL,
|
||||
sequence INTEGER NOT NULL,
|
||||
phase TEXT NOT NULL,
|
||||
phase_order INTEGER NOT NULL,
|
||||
execution_digest TEXT NOT NULL,
|
||||
binding_sha256 TEXT NOT NULL,
|
||||
payload_sha256 TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
);
|
||||
"""
|
||||
)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.path, timeout=30.0)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA journal_mode=WAL")
|
||||
connection.execute("PRAGMA synchronous=FULL")
|
||||
connection.execute("PRAGMA busy_timeout=30000")
|
||||
return connection
|
||||
|
||||
@staticmethod
|
||||
def _phase_order(phase: str) -> int:
|
||||
try:
|
||||
return PHASE_ORDER[phase]
|
||||
except KeyError as exc:
|
||||
raise CheckpointError("CHECKPOINT_PHASE_INVALID") from exc
|
||||
|
||||
def append(
|
||||
self,
|
||||
binding: CheckpointBinding,
|
||||
phase: str,
|
||||
payload: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
order = self._phase_order(phase)
|
||||
payload_value = dict(payload)
|
||||
payload_sha = sha256_json(payload_value)
|
||||
with self._connect() as connection:
|
||||
connection.execute("BEGIN IMMEDIATE")
|
||||
replay = connection.execute(
|
||||
"""
|
||||
SELECT * FROM checkpoints
|
||||
WHERE task_id=? AND attempt=? AND phase=? AND payload_sha256=?
|
||||
""",
|
||||
(binding.task_id, binding.attempt, phase, payload_sha),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
connection.commit()
|
||||
return dict(replay)
|
||||
|
||||
head = connection.execute(
|
||||
"SELECT * FROM checkpoint_heads WHERE task_id=?",
|
||||
(binding.task_id,),
|
||||
).fetchone()
|
||||
if head is not None:
|
||||
head_attempt = int(head["attempt"])
|
||||
head_order = int(head["phase_order"])
|
||||
if binding.attempt < head_attempt:
|
||||
raise CheckpointError("CHECKPOINT_ATTEMPT_REGRESSION")
|
||||
if binding.attempt == head_attempt:
|
||||
if head["execution_digest"] != binding.execution_digest:
|
||||
raise CheckpointError("CHECKPOINT_EXECUTION_DIGEST_CONFLICT")
|
||||
if head["binding_sha256"] != binding.binding_sha256:
|
||||
raise CheckpointError("CHECKPOINT_SCOPE_MISMATCH_DENY")
|
||||
if order < head_order and phase != "reconciliation_required":
|
||||
raise CheckpointError("CHECKPOINT_PHASE_REGRESSION")
|
||||
sequence = int(head["sequence"]) + 1
|
||||
else:
|
||||
sequence = 1
|
||||
else:
|
||||
sequence = 1
|
||||
|
||||
created_at = now()
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO checkpoints(
|
||||
task_id,attempt,sequence,phase,phase_order,execution_digest,job_id,
|
||||
repository,base_oid,expected_branch_oid,target_branch,generation,
|
||||
binding_sha256,payload_json,payload_sha256,created_at
|
||||
) VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)
|
||||
""",
|
||||
(
|
||||
binding.task_id,
|
||||
binding.attempt,
|
||||
sequence,
|
||||
phase,
|
||||
order,
|
||||
binding.execution_digest,
|
||||
binding.job_id,
|
||||
binding.repository,
|
||||
binding.base_oid,
|
||||
binding.expected_branch_oid,
|
||||
binding.target_branch,
|
||||
binding.generation,
|
||||
binding.binding_sha256,
|
||||
canonical(payload_value).decode("utf-8"),
|
||||
payload_sha,
|
||||
created_at,
|
||||
),
|
||||
)
|
||||
connection.execute(
|
||||
"""
|
||||
INSERT INTO checkpoint_heads(
|
||||
task_id,attempt,sequence,phase,phase_order,execution_digest,
|
||||
binding_sha256,payload_sha256,updated_at
|
||||
) VALUES (?,?,?,?,?,?,?,?,?)
|
||||
ON CONFLICT(task_id) DO UPDATE SET
|
||||
attempt=excluded.attempt,
|
||||
sequence=excluded.sequence,
|
||||
phase=excluded.phase,
|
||||
phase_order=excluded.phase_order,
|
||||
execution_digest=excluded.execution_digest,
|
||||
binding_sha256=excluded.binding_sha256,
|
||||
payload_sha256=excluded.payload_sha256,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(
|
||||
binding.task_id,
|
||||
binding.attempt,
|
||||
sequence,
|
||||
phase,
|
||||
order,
|
||||
binding.execution_digest,
|
||||
binding.binding_sha256,
|
||||
payload_sha,
|
||||
created_at,
|
||||
),
|
||||
)
|
||||
connection.commit()
|
||||
row = connection.execute(
|
||||
"SELECT * FROM checkpoints WHERE task_id=? AND attempt=? AND sequence=?",
|
||||
(binding.task_id, binding.attempt, sequence),
|
||||
).fetchone()
|
||||
return dict(row)
|
||||
|
||||
def latest(self, task_id: str) -> dict[str, Any] | None:
|
||||
with self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"""
|
||||
SELECT * FROM checkpoints
|
||||
WHERE task_id=?
|
||||
ORDER BY attempt DESC, sequence DESC
|
||||
LIMIT 1
|
||||
""",
|
||||
(task_id,),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return None
|
||||
value = dict(row)
|
||||
value["payload"] = json.loads(value.pop("payload_json"))
|
||||
return value
|
||||
|
||||
def latest_for_attempt(self, task_id: str, attempt: int) -> dict[str, Any] | None:
|
||||
with self._connect() as connection:
|
||||
row = connection.execute(
|
||||
"""
|
||||
SELECT * FROM checkpoints
|
||||
WHERE task_id=? AND attempt=?
|
||||
ORDER BY sequence DESC
|
||||
LIMIT 1
|
||||
""",
|
||||
(task_id, attempt),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return None
|
||||
value = dict(row)
|
||||
value["payload"] = json.loads(value.pop("payload_json"))
|
||||
return value
|
||||
|
||||
def verify_latest_binding(self, binding: CheckpointBinding) -> dict[str, Any] | None:
|
||||
value = self.latest(binding.task_id)
|
||||
if value is None:
|
||||
return None
|
||||
if int(value["attempt"]) > binding.attempt:
|
||||
raise CheckpointError("CHECKPOINT_FUTURE_ATTEMPT")
|
||||
# A previous attempt may be reused only when the immutable execution/scope binding matches.
|
||||
if value["execution_digest"] != binding.execution_digest:
|
||||
return None
|
||||
expected = CheckpointBinding(
|
||||
task_id=value["task_id"],
|
||||
attempt=int(value["attempt"]),
|
||||
execution_digest=value["execution_digest"],
|
||||
job_id=value["job_id"],
|
||||
repository=value["repository"],
|
||||
base_oid=value["base_oid"],
|
||||
expected_branch_oid=value["expected_branch_oid"],
|
||||
target_branch=value["target_branch"],
|
||||
generation=int(value["generation"]),
|
||||
)
|
||||
current_scope = binding.material()
|
||||
historical_scope = expected.material()
|
||||
current_scope.pop("attempt", None)
|
||||
historical_scope.pop("attempt", None)
|
||||
if sha256_json(current_scope) != sha256_json(historical_scope):
|
||||
raise CheckpointError("CHECKPOINT_SCOPE_MISMATCH_DENY")
|
||||
return value
|
||||
@@ -0,0 +1,463 @@
|
||||
"""Bounded read-only repository interface map for governed Online Agent analysis.
|
||||
|
||||
The compact map intentionally returns symbols and short source excerpts rather than a
|
||||
source archive. It is designed for control-plane consumers that cannot safely ingest a
|
||||
multi-megabyte repository snapshot.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import ast
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
from typing import Any, Iterable, Mapping, Sequence
|
||||
|
||||
|
||||
SCHEMA = "aios.engineering.interface-map.v1"
|
||||
MAX_RESULT_BYTES = 120 * 1024
|
||||
TARGET_RESULT_BYTES = 108 * 1024
|
||||
MAX_MODULES = 40
|
||||
MAX_SYMBOLS = 80
|
||||
MAX_TESTS = 40
|
||||
MAX_EXCERPTS = 25
|
||||
MAX_EXCERPT_CHARS = 1200
|
||||
MAX_FILE_BYTES = 2 * 1024 * 1024
|
||||
|
||||
ROOTS = (
|
||||
"active-runtime/app",
|
||||
"runtime/agent-os",
|
||||
"tests",
|
||||
"db/migrations",
|
||||
"migrations",
|
||||
"deploy/systemd",
|
||||
"docs/task-plane",
|
||||
"docs/superpowers/specs",
|
||||
)
|
||||
SUFFIXES = {".py", ".sql", ".service", ".md", ".json", ".yaml", ".yml"}
|
||||
|
||||
DEFAULT_TERMS = {
|
||||
"agent", "worker", "fleet", "scheduler", "scheduling", "task", "claim", "lease",
|
||||
"heartbeat", "capacity", "concurrency", "priority", "fairness", "queue", "retry",
|
||||
"backoff", "circuit", "health", "liveness", "scope", "tenant", "project", "trace",
|
||||
"message", "checkpoint", "recovery", "idempotency", "dispatch", "assignment",
|
||||
}
|
||||
FLEET_CONTRACT_TERMS: dict[str, tuple[str, ...]] = {
|
||||
"FLEET_AGENT_REGISTRATION": ("agent", "register", "worker", "capability", "version"),
|
||||
"FLEET_CAPACITY_SCHEDULING": ("capacity", "slot", "concurrency", "scheduler", "queue"),
|
||||
"FLEET_FAIRNESS": ("fair", "priority", "queue", "tenant", "project", "starvation"),
|
||||
"FLEET_FAULT_ISOLATION": ("failure", "health", "liveness", "timeout", "circuit", "poison"),
|
||||
"FLEET_WORKER_REASSIGNMENT": ("reassign", "assignment", "claim", "lease", "retry", "worker"),
|
||||
"FLEET_SCOPE_ISOLATION": ("tenant", "project", "scope", "conversation", "task", "run"),
|
||||
"FLEET_IDEMPOTENT_DISPATCH": ("idempot", "dispatch", "claim", "lease", "result", "attempt"),
|
||||
"FLEET_FAILURE_RECOVERY": ("checkpoint", "resume", "recover", "retry", "cleanup", "receipt"),
|
||||
}
|
||||
|
||||
MODEL_GOVERNANCE_CONTRACT_TERMS: dict[str, tuple[str, ...]] = {
|
||||
"MODEL_PROVIDER_REGISTRY": ("model", "provider", "registry", "endpoint", "capability"),
|
||||
"MODEL_SELECTION_POLICY": ("model", "select", "route", "policy", "capability"),
|
||||
"MODEL_VERSION_PINNING": ("model", "version", "pin", "revision", "snapshot"),
|
||||
"MODEL_BUDGET_ACCOUNTING": ("budget", "token", "cost", "quota", "usage"),
|
||||
"MODEL_FALLBACK_POLICY": ("fallback", "retry", "route", "provider", "model"),
|
||||
"MODEL_SCOPE_ISOLATION": ("tenant", "project", "scope", "policy", "model"),
|
||||
"MODEL_CREDENTIAL_BOUNDARY": ("credential", "secret", "provider", "tool", "token"),
|
||||
"MODEL_TRACE_AUDIT": ("trace", "audit", "model", "provider", "request"),
|
||||
"MODEL_EVALUATION_GATE": ("eval", "evaluation", "approval", "quality", "gate"),
|
||||
"MODEL_ROUTING_RESILIENCE": ("route", "retry", "fallback", "timeout", "health"),
|
||||
}
|
||||
|
||||
PROFILE_CLASSIFICATION = {
|
||||
"fleet": "P2_INTERFACE_MAP_CAPTURED",
|
||||
"model_governance": "MODEL_GOVERNANCE_INTERFACE_MAP_CAPTURED",
|
||||
}
|
||||
|
||||
MODEL_PROFILE_MARKERS = {
|
||||
"model", "provider", "llm", "inference", "routing", "router", "budget",
|
||||
"token", "cost", "quota", "fallback", "evaluation", "eval", "approval",
|
||||
"version", "pinning",
|
||||
}
|
||||
SENSITIVE_RE = re.compile(
|
||||
r"(?i)(authorization\s*:\s*bearer\s+\S+|"
|
||||
r"(?:password|passwd|secret|token|api[_-]?key)\s*[:=]\s*['\"]?[^'\"\s,;]+)"
|
||||
)
|
||||
SQL_TABLE_RE = re.compile(
|
||||
r"(?is)\bcreate\s+table\s+(?:if\s+not\s+exists\s+)?[\"`[]?([A-Za-z_][A-Za-z0-9_.-]*)"
|
||||
)
|
||||
|
||||
|
||||
class CompactInterfaceMapError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def _sha(data: bytes) -> str:
|
||||
return hashlib.sha256(data).hexdigest()
|
||||
|
||||
|
||||
def _bounded_excerpt(text: str, start_line: int, end_line: int) -> str:
|
||||
lines = text.splitlines()
|
||||
start = max(0, start_line - 2)
|
||||
end = min(len(lines), max(end_line + 1, start + 1))
|
||||
excerpt = "\n".join(lines[start:end])
|
||||
excerpt = SENSITIVE_RE.sub("<redacted-sensitive-source-pattern>", excerpt)
|
||||
if len(excerpt) > MAX_EXCERPT_CHARS:
|
||||
excerpt = excerpt[: MAX_EXCERPT_CHARS - 1] + "…"
|
||||
return excerpt
|
||||
|
||||
|
||||
def _signal_terms(signals: Sequence[str]) -> set[str]:
|
||||
terms = set(DEFAULT_TERMS)
|
||||
for signal in signals:
|
||||
if not isinstance(signal, str):
|
||||
continue
|
||||
terms.update(
|
||||
token.lower()
|
||||
for token in re.findall(r"[A-Za-z][A-Za-z0-9_.-]{2,63}", signal)
|
||||
)
|
||||
return set(sorted(terms)[:96])
|
||||
|
||||
|
||||
def _profile(source_signals: Sequence[str]) -> str:
|
||||
tokens: set[str] = set()
|
||||
for signal in source_signals:
|
||||
if not isinstance(signal, str):
|
||||
continue
|
||||
tokens.update(
|
||||
token.lower()
|
||||
for token in re.findall(r"[A-Za-z][A-Za-z0-9_.-]{2,63}", signal)
|
||||
)
|
||||
model_score = len(tokens & MODEL_PROFILE_MARKERS)
|
||||
return "model_governance" if model_score >= 2 else "fleet"
|
||||
|
||||
|
||||
def _contract_terms(profile: str) -> Mapping[str, tuple[str, ...]]:
|
||||
if profile == "model_governance":
|
||||
return MODEL_GOVERNANCE_CONTRACT_TERMS
|
||||
if profile == "fleet":
|
||||
return FLEET_CONTRACT_TERMS
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_PROFILE_INVALID")
|
||||
|
||||
|
||||
def _candidate_files(root: Path, terms: set[str]) -> list[dict[str, Any]]:
|
||||
root = root.resolve()
|
||||
candidates: list[dict[str, Any]] = []
|
||||
for relative_root in ROOTS:
|
||||
directory = (root / relative_root).resolve(strict=False)
|
||||
if directory == root or root not in directory.parents:
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_SCOPE_INVALID")
|
||||
if not directory.is_dir() or directory.is_symlink():
|
||||
continue
|
||||
for path in sorted(directory.rglob("*")):
|
||||
if path.is_symlink() or not path.is_file() or path.suffix.lower() not in SUFFIXES:
|
||||
continue
|
||||
resolved = path.resolve(strict=True)
|
||||
if root not in resolved.parents:
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_PATH_ESCAPE")
|
||||
data = path.read_bytes()
|
||||
if len(data) > MAX_FILE_BYTES:
|
||||
continue
|
||||
relative = path.relative_to(root).as_posix()
|
||||
text = data.decode("utf-8", "ignore")
|
||||
searchable = (relative + "\n" + text[:384000]).lower()
|
||||
matched = sorted(term for term in terms if term in searchable)
|
||||
if not matched:
|
||||
continue
|
||||
path_bonus = sum(3 for term in terms if term in relative.lower())
|
||||
test_bonus = 3 if relative.startswith("tests/") else 0
|
||||
score = min(250, len(matched) + path_bonus + test_bonus)
|
||||
candidates.append(
|
||||
{
|
||||
"path": relative,
|
||||
"sha256": _sha(data),
|
||||
"bytes": len(data),
|
||||
"score": score,
|
||||
"text": text,
|
||||
"suffix": path.suffix.lower(),
|
||||
}
|
||||
)
|
||||
candidates.sort(key=lambda item: (-item["score"], item["path"]))
|
||||
return candidates
|
||||
|
||||
|
||||
def _python_symbols(item: Mapping[str, Any], terms: set[str]) -> list[dict[str, Any]]:
|
||||
try:
|
||||
tree = ast.parse(str(item["text"]), filename=str(item["path"]))
|
||||
except SyntaxError:
|
||||
return []
|
||||
result: list[dict[str, Any]] = []
|
||||
|
||||
class Visitor(ast.NodeVisitor):
|
||||
def __init__(self) -> None:
|
||||
self.stack: list[str] = []
|
||||
|
||||
def _record(self, node: ast.AST, kind: str, name: str) -> None:
|
||||
qualified = ".".join([*self.stack, name]) if self.stack else name
|
||||
haystack = f"{item['path']} {qualified}".lower()
|
||||
score = sum(3 if term in haystack else 0 for term in terms)
|
||||
if name.startswith("test_"):
|
||||
score += 12
|
||||
result.append(
|
||||
{
|
||||
"path": item["path"],
|
||||
"symbol": qualified,
|
||||
"kind": kind,
|
||||
"line": int(getattr(node, "lineno", 1)),
|
||||
"end_line": int(getattr(node, "end_lineno", getattr(node, "lineno", 1))),
|
||||
"score": score + int(item["score"]),
|
||||
}
|
||||
)
|
||||
|
||||
def visit_ClassDef(self, node: ast.ClassDef) -> Any:
|
||||
self._record(node, "class", node.name)
|
||||
self.stack.append(node.name)
|
||||
self.generic_visit(node)
|
||||
self.stack.pop()
|
||||
|
||||
def visit_FunctionDef(self, node: ast.FunctionDef) -> Any:
|
||||
self._record(node, "function", node.name)
|
||||
self.stack.append(node.name)
|
||||
self.generic_visit(node)
|
||||
self.stack.pop()
|
||||
|
||||
def visit_AsyncFunctionDef(self, node: ast.AsyncFunctionDef) -> Any:
|
||||
self._record(node, "async_function", node.name)
|
||||
self.stack.append(node.name)
|
||||
self.generic_visit(node)
|
||||
self.stack.pop()
|
||||
|
||||
Visitor().visit(tree)
|
||||
return result
|
||||
|
||||
|
||||
def _surface_ref(symbol: Mapping[str, Any]) -> str:
|
||||
return f"{symbol['path']}::{symbol['symbol']}"
|
||||
|
||||
|
||||
def _contract_map(
|
||||
symbols: Sequence[Mapping[str, Any]],
|
||||
modules: Sequence[Mapping[str, Any]],
|
||||
contract_terms: Mapping[str, tuple[str, ...]],
|
||||
) -> dict[str, Any]:
|
||||
result: dict[str, Any] = {}
|
||||
module_paths = [str(item["path"]) for item in modules]
|
||||
for contract, terms in contract_terms.items():
|
||||
scored: list[tuple[int, str]] = []
|
||||
for symbol in symbols:
|
||||
haystack = _surface_ref(symbol).lower()
|
||||
score = sum(1 for term in terms if term in haystack)
|
||||
if score:
|
||||
scored.append((score, _surface_ref(symbol)))
|
||||
scored.sort(key=lambda item: (-item[0], item[1]))
|
||||
surfaces = [value for _, value in scored[:6]]
|
||||
if not surfaces:
|
||||
for path in module_paths:
|
||||
score = sum(1 for term in terms if term in path.lower())
|
||||
if score:
|
||||
surfaces.append(path)
|
||||
if len(surfaces) == 6:
|
||||
break
|
||||
result[contract] = {
|
||||
"status": "PARTIAL" if surfaces else "GAP",
|
||||
"surfaces": surfaces,
|
||||
}
|
||||
return result
|
||||
|
||||
|
||||
def _gap_evidence(
|
||||
symbols: Sequence[Mapping[str, Any]],
|
||||
profile: str,
|
||||
) -> tuple[list[str], list[str], list[str]]:
|
||||
haystack = "\n".join(_surface_ref(item).lower() for item in symbols)
|
||||
|
||||
if profile == "model_governance":
|
||||
invariants = [
|
||||
"Online Task claim/heartbeat remains the authoritative worker ownership boundary.",
|
||||
"Provider/model credentials remain outside uncredentialed planner/executor processes.",
|
||||
"P0-A tenant/project scope and P0-C trace/audit lineage must constrain model routing.",
|
||||
"P1 retry/checkpoint semantics remain authoritative for model-call execution recovery.",
|
||||
]
|
||||
failure_windows: list[str] = []
|
||||
if "provider" not in haystack and "model" not in haystack:
|
||||
failure_windows.append("No first-class model/provider registry surface detected.")
|
||||
if "budget" not in haystack and "cost" not in haystack and "quota" not in haystack:
|
||||
failure_windows.append("No explicit durable model budget/cost/quota accounting surface detected.")
|
||||
if "fallback" not in haystack and "route" not in haystack:
|
||||
failure_windows.append("No explicit model fallback/routing policy surface detected.")
|
||||
if "eval" not in haystack and "approval" not in haystack:
|
||||
failure_windows.append("No explicit evaluation/approval gate surface detected for model changes.")
|
||||
if "version" not in haystack and "pin" not in haystack:
|
||||
failure_windows.append("No explicit model-version pinning surface detected.")
|
||||
desired = (
|
||||
("trace", "P0-C trace/audit lineage"),
|
||||
("scope", "P0-A tenant/project scope isolation"),
|
||||
("credential", "P0-C credential governance"),
|
||||
("checkpoint", "P1 durable execution recovery"),
|
||||
("message", "P0-B MessageEnvelope/handoff"),
|
||||
("retry", "P1 retry/idempotency"),
|
||||
)
|
||||
else:
|
||||
invariants = [
|
||||
"Online Task claim/heartbeat remains the authoritative worker ownership boundary.",
|
||||
"Governed mutation remains separated from read-only analysis and requires WriterLease.",
|
||||
"P1 attempt-aware result idempotency and durable checkpoint recovery are reusable fleet primitives.",
|
||||
"Scope/trace/message lineage must remain attached when work is scheduled or reassigned.",
|
||||
]
|
||||
failure_windows = []
|
||||
if "scheduler" not in haystack:
|
||||
failure_windows.append("No first-class durable fleet scheduler symbol detected; worker-local polling may still be the scheduling mechanism.")
|
||||
if "capacity" not in haystack and "slot" not in haystack:
|
||||
failure_windows.append("No explicit durable worker-capacity/slot primitive detected.")
|
||||
if "fair" not in haystack and "starvation" not in haystack:
|
||||
failure_windows.append("No explicit fairness/starvation policy symbol detected.")
|
||||
if "circuit" not in haystack:
|
||||
failure_windows.append("No explicit circuit-breaker primitive detected for repeated worker/task failures.")
|
||||
if "reassign" not in haystack:
|
||||
failure_windows.append("No explicit worker-reassignment primitive detected beyond lease expiry/retry semantics.")
|
||||
desired = (
|
||||
("checkpoint", "P1 durable checkpoint/resume"),
|
||||
("message", "P0-B MessageEnvelope/handoff"),
|
||||
("trace", "P0-C trace correlation"),
|
||||
("scope", "P0-A scope isolation"),
|
||||
("lease", "claim/WriterLease ownership"),
|
||||
("heartbeat", "worker liveness"),
|
||||
("idempot", "retry-safe dispatch/result"),
|
||||
)
|
||||
|
||||
reuse_points: list[str] = []
|
||||
for token, label in desired:
|
||||
match = next((item for item in symbols if token in _surface_ref(item).lower()), None)
|
||||
if match is not None:
|
||||
reuse_points.append(f"{label}: {_surface_ref(match)}")
|
||||
return invariants, failure_windows, reuse_points
|
||||
|
||||
|
||||
def _trim_to_budget(value: dict[str, Any]) -> dict[str, Any]:
|
||||
def size() -> int:
|
||||
return len(json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":")).encode("utf-8"))
|
||||
|
||||
while size() > TARGET_RESULT_BYTES and value["bounded_excerpts"]:
|
||||
value["bounded_excerpts"].pop()
|
||||
while size() > TARGET_RESULT_BYTES and len(value["implementation_map"]["functions"]) > 20:
|
||||
value["implementation_map"]["functions"].pop()
|
||||
while size() > TARGET_RESULT_BYTES and len(value["implementation_map"]["classes"]) > 15:
|
||||
value["implementation_map"]["classes"].pop()
|
||||
while size() > TARGET_RESULT_BYTES and len(value["implementation_map"]["tests"]) > 15:
|
||||
value["implementation_map"]["tests"].pop()
|
||||
while size() > TARGET_RESULT_BYTES and len(value["implementation_map"]["modules"]) > 20:
|
||||
value["implementation_map"]["modules"].pop()
|
||||
final_size = size()
|
||||
if final_size > MAX_RESULT_BYTES:
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_RESULT_TOO_LARGE")
|
||||
value["result_bytes"] = final_size
|
||||
return value
|
||||
|
||||
|
||||
def build_compact_interface_map(
|
||||
worktree: Path,
|
||||
source_signals: Sequence[str],
|
||||
*,
|
||||
source_commit: str,
|
||||
) -> dict[str, Any]:
|
||||
root = Path(worktree)
|
||||
if not root.is_dir() or root.is_symlink():
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_WORKTREE_INVALID")
|
||||
if re.fullmatch(r"[0-9a-f]{40}", source_commit) is None:
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_SOURCE_COMMIT_INVALID")
|
||||
|
||||
profile = _profile(source_signals)
|
||||
terms = _signal_terms(source_signals)
|
||||
candidates = _candidate_files(root, terms)
|
||||
if not candidates:
|
||||
raise CompactInterfaceMapError("INTERFACE_MAP_EMPTY")
|
||||
|
||||
module_candidates = candidates[:MAX_MODULES]
|
||||
modules = [
|
||||
{
|
||||
"path": item["path"],
|
||||
"sha256": item["sha256"],
|
||||
"bytes": item["bytes"],
|
||||
"score": item["score"],
|
||||
}
|
||||
for item in module_candidates
|
||||
]
|
||||
|
||||
symbols: list[dict[str, Any]] = []
|
||||
tables: list[dict[str, Any]] = []
|
||||
systemd_units: list[dict[str, Any]] = []
|
||||
for item in candidates:
|
||||
if item["suffix"] == ".py":
|
||||
symbols.extend(_python_symbols(item, terms))
|
||||
elif item["suffix"] == ".sql":
|
||||
for table in SQL_TABLE_RE.findall(str(item["text"])):
|
||||
tables.append({"path": item["path"], "table": table, "sha256": item["sha256"]})
|
||||
elif item["suffix"] == ".service":
|
||||
systemd_units.append({"path": item["path"], "unit": Path(str(item["path"])).name, "sha256": item["sha256"]})
|
||||
|
||||
symbols.sort(key=lambda item: (-int(item["score"]), str(item["path"]), str(item["symbol"])))
|
||||
all_symbols = list(symbols)
|
||||
test_symbols = [
|
||||
item for item in all_symbols
|
||||
if str(item["path"]).startswith("tests/") or str(item["symbol"]).split(".")[-1].startswith("test_")
|
||||
][: min(MAX_TESTS, 24)]
|
||||
non_test_symbols = [
|
||||
item for item in all_symbols
|
||||
if item not in test_symbols
|
||||
][: max(0, MAX_SYMBOLS - len(test_symbols))]
|
||||
symbols = [*test_symbols, *non_test_symbols]
|
||||
symbols.sort(key=lambda item: (-int(item["score"]), str(item["path"]), str(item["symbol"])))
|
||||
classes = [
|
||||
{k: item[k] for k in ("path", "symbol", "line", "end_line")}
|
||||
for item in symbols
|
||||
if item["kind"] == "class"
|
||||
]
|
||||
functions = [
|
||||
{k: item[k] for k in ("path", "symbol", "line", "end_line")}
|
||||
for item in symbols
|
||||
if item["kind"] in {"function", "async_function"} and not str(item["symbol"]).split(".")[-1].startswith("test_")
|
||||
]
|
||||
tests = [
|
||||
{k: item[k] for k in ("path", "symbol", "line", "end_line")}
|
||||
for item in symbols
|
||||
if str(item["path"]).startswith("tests/") or str(item["symbol"]).split(".")[-1].startswith("test_")
|
||||
][:MAX_TESTS]
|
||||
|
||||
excerpts: list[dict[str, Any]] = []
|
||||
by_path = {str(item["path"]): item for item in candidates}
|
||||
for symbol in symbols:
|
||||
if len(excerpts) == MAX_EXCERPTS:
|
||||
break
|
||||
item = by_path.get(str(symbol["path"]))
|
||||
if item is None:
|
||||
continue
|
||||
excerpt = _bounded_excerpt(str(item["text"]), int(symbol["line"]), int(symbol["end_line"]))
|
||||
if not excerpt.strip():
|
||||
continue
|
||||
excerpts.append(
|
||||
{
|
||||
"path": symbol["path"],
|
||||
"symbol": symbol["symbol"],
|
||||
"sha256": item["sha256"],
|
||||
"excerpt": excerpt,
|
||||
}
|
||||
)
|
||||
|
||||
invariants, failure_windows, reuse_points = _gap_evidence(all_symbols, profile)
|
||||
result = {
|
||||
"schema": SCHEMA,
|
||||
"profile": profile,
|
||||
"classification": PROFILE_CLASSIFICATION[profile],
|
||||
"source_commit": source_commit,
|
||||
"implementation_map": {
|
||||
"modules": modules,
|
||||
"classes": classes[:MAX_SYMBOLS],
|
||||
"functions": functions[:MAX_SYMBOLS],
|
||||
"tables": tables[:40],
|
||||
"systemd_units": systemd_units[:20],
|
||||
"tests": tests,
|
||||
"current_invariants": invariants,
|
||||
"failure_windows": failure_windows,
|
||||
"reuse_points": reuse_points,
|
||||
},
|
||||
"bounded_excerpts": excerpts,
|
||||
"contracts": _contract_map(all_symbols, modules, _contract_terms(profile)),
|
||||
}
|
||||
return _trim_to_budget(result)
|
||||
@@ -0,0 +1,482 @@
|
||||
"""Canonical governed execution projection for Online Agent Tasks.
|
||||
|
||||
The durable governed binding is authoritative. Natural-language task fields and
|
||||
worker configuration are never allowed to invent repository, ref, generation, or
|
||||
idempotency coordinates.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping, Sequence
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
|
||||
EXECUTION_SCHEMA = "aios.online-agent.execution.v2"
|
||||
PROJECTION_SCHEMA = "aios.online-agent.task-projection.v1"
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
BRANCH_RE = re.compile(r"^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$")
|
||||
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
|
||||
PROTECTED_PREFIXES = ("main", "master", "refs/", "tags/", "tag/", "release/", "baseline/", "production/")
|
||||
MUTATION_ACTIONS = frozenset({"deterministic"})
|
||||
READ_ONLY_ACTIONS = frozenset({"source_capture", "agent_runtime"})
|
||||
SUPPORTED_ACTIONS = frozenset({"deterministic", "source_capture", "agent_runtime"})
|
||||
AGENT_RUNTIME_ADAPTERS = frozenset({"hermes", "openclaw"})
|
||||
MAX_AGENT_RUNTIME_INPUT_BYTES = 64 * 1024
|
||||
|
||||
|
||||
class ExecutionProjectionError(RuntimeError):
|
||||
"""A canonical fail-closed projection or validation error."""
|
||||
|
||||
|
||||
class OnlineTaskProjectionClient:
|
||||
"""Official HTTP projection client using only a control credential reference."""
|
||||
|
||||
def __init__(self, api_base: str, control_token_path: Path) -> None:
|
||||
self.api_base = api_base.rstrip("/")
|
||||
self.control_token_path = Path(control_token_path)
|
||||
|
||||
def _token(self) -> str:
|
||||
path = self.control_token_path
|
||||
if path.is_symlink() or not path.is_file():
|
||||
_error("ONLINE_TASK_PROJECTION_CONTROL_UNAVAILABLE")
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 32:
|
||||
_error("ONLINE_TASK_PROJECTION_CONTROL_INVALID")
|
||||
return value
|
||||
|
||||
def create(
|
||||
self,
|
||||
projected_task: Mapping[str, Any],
|
||||
*,
|
||||
binding: "GovernedExecutionBinding",
|
||||
) -> dict[str, Any]:
|
||||
body = dict(projected_task)
|
||||
payload = _canonical(body).encode("utf-8")
|
||||
request = urllib.request.Request(
|
||||
self.api_base + "/v1/tasks",
|
||||
method="POST",
|
||||
data=payload,
|
||||
headers={
|
||||
"Authorization": "Bearer " + self._token(),
|
||||
"Content-Type": "application/json",
|
||||
"Accept": "application/json",
|
||||
},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=15) as response:
|
||||
result = json.loads(response.read().decode("utf-8"))
|
||||
status = response.status
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw = exc.read(8192).decode("utf-8", "replace")
|
||||
try:
|
||||
error = json.loads(raw).get("error")
|
||||
except (AttributeError, json.JSONDecodeError):
|
||||
error = "HTTP_ERROR"
|
||||
raise ExecutionProjectionError(f"ONLINE_TASK_PROJECTION_FAILED:{exc.code}:{error}") from exc
|
||||
except (OSError, urllib.error.URLError, TimeoutError) as exc:
|
||||
raise ExecutionProjectionError("ONLINE_TASK_PROJECTION_UNAVAILABLE") from exc
|
||||
if status not in {200, 201} or not isinstance(result, dict):
|
||||
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
|
||||
if result.get("task_id") != binding.task_id or result.get("status") not in {"QUEUED", "VERIFYING", "SUCCEEDED"}:
|
||||
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
|
||||
metadata = result.get("metadata")
|
||||
if not isinstance(metadata, Mapping):
|
||||
_error("ONLINE_TASK_PROJECTION_RESPONSE_INVALID")
|
||||
returned_execution = validate_execution_envelope(
|
||||
_object(metadata.get("execution"), "ONLINE_TASK_PROJECTION_RESPONSE_INVALID"),
|
||||
binding=binding,
|
||||
)
|
||||
submitted_metadata = _object(body.get("metadata"), "ONLINE_TASK_PROJECTION_REQUEST_INVALID")
|
||||
submitted_execution = validate_execution_envelope(
|
||||
_object(submitted_metadata.get("execution"), "ONLINE_TASK_PROJECTION_REQUEST_INVALID"),
|
||||
binding=binding,
|
||||
)
|
||||
if _canonical(returned_execution) != _canonical(submitted_execution):
|
||||
_error("ONLINE_TASK_PROJECTION_RESPONSE_BINDING_INVALID")
|
||||
return result
|
||||
|
||||
|
||||
def _error(code: str) -> None:
|
||||
raise ExecutionProjectionError(code)
|
||||
|
||||
|
||||
def _object(value: object, code: str) -> dict[str, Any]:
|
||||
if not isinstance(value, Mapping):
|
||||
_error(code)
|
||||
return dict(value)
|
||||
|
||||
|
||||
def _string(value: object, code: str) -> str:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
_error(code)
|
||||
return value.strip()
|
||||
|
||||
|
||||
def _task_id(value: object) -> str:
|
||||
value = _string(value, "TASK_ID_INVALID")
|
||||
if TASK_RE.fullmatch(value) is None:
|
||||
_error("TASK_ID_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def _oid(value: object, code: str) -> str:
|
||||
value = _string(value, code)
|
||||
if OID_RE.fullmatch(value) is None:
|
||||
_error(code)
|
||||
return value
|
||||
|
||||
|
||||
def _branch(value: object) -> str:
|
||||
value = _string(value, "TARGET_BRANCH_INVALID")
|
||||
if BRANCH_RE.fullmatch(value) is None or value.startswith(PROTECTED_PREFIXES):
|
||||
_error("TARGET_BRANCH_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def _generation(value: object) -> int:
|
||||
if not isinstance(value, int) or isinstance(value, bool) or value < 1:
|
||||
_error("GENERATION_INVALID")
|
||||
return value
|
||||
|
||||
|
||||
def _canonical(value: object) -> str:
|
||||
return json.dumps(value, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
||||
|
||||
|
||||
def _digest(value: object) -> str:
|
||||
return hashlib.sha256(_canonical(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _source_signals(value: object) -> tuple[str, ...]:
|
||||
"""Normalize untrusted natural-language hints before they enter a signed envelope."""
|
||||
if value is None:
|
||||
return ()
|
||||
if not isinstance(value, Sequence) or isinstance(value, (str, bytes)):
|
||||
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
|
||||
result: list[str] = []
|
||||
for item in value:
|
||||
if not isinstance(item, str):
|
||||
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
|
||||
text = " ".join(item.split()).strip()
|
||||
if not text:
|
||||
continue
|
||||
# Projection may accept long task prose, but execution envelopes stay bounded.
|
||||
text = text[:512].rstrip()
|
||||
if text not in result:
|
||||
result.append(text)
|
||||
if len(result) == 16:
|
||||
break
|
||||
return tuple(result)
|
||||
|
||||
|
||||
def _agent_runtime_input(value: object) -> dict[str, Any]:
|
||||
if not isinstance(value, Mapping):
|
||||
_error("AGENT_RUNTIME_INPUT_REQUIRED")
|
||||
raw = dict(value)
|
||||
allowed = {"goal", "instructions", "success_criteria", "constraints"}
|
||||
if set(raw) - allowed:
|
||||
_error("AGENT_RUNTIME_INPUT_FIELDS_INVALID")
|
||||
goal = _string(raw.get("goal"), "AGENT_RUNTIME_GOAL_REQUIRED")
|
||||
instructions = raw.get("instructions", "")
|
||||
if not isinstance(instructions, str):
|
||||
_error("AGENT_RUNTIME_INSTRUCTIONS_INVALID")
|
||||
criteria = raw.get("success_criteria", [])
|
||||
if not isinstance(criteria, list) or len(criteria) > 32:
|
||||
_error("AGENT_RUNTIME_SUCCESS_CRITERIA_INVALID")
|
||||
normalized_criteria: list[dict[str, str]] = []
|
||||
for item in criteria:
|
||||
if not isinstance(item, Mapping):
|
||||
_error("AGENT_RUNTIME_SUCCESS_CRITERIA_INVALID")
|
||||
criterion_id = _string(item.get("id"), "AGENT_RUNTIME_SUCCESS_CRITERIA_INVALID")
|
||||
description = _string(
|
||||
item.get("description"), "AGENT_RUNTIME_SUCCESS_CRITERIA_INVALID"
|
||||
)
|
||||
normalized_criteria.append(
|
||||
{"id": criterion_id[:120], "description": description[:1000]}
|
||||
)
|
||||
constraints = raw.get("constraints", {})
|
||||
if not isinstance(constraints, Mapping):
|
||||
_error("AGENT_RUNTIME_CONSTRAINTS_INVALID")
|
||||
sensitive_markers = ("token", "secret", "password", "credential", "authorization", "api_key", "apikey")
|
||||
for key in constraints:
|
||||
lowered = str(key).lower()
|
||||
if any(marker in lowered for marker in sensitive_markers):
|
||||
_error("AGENT_RUNTIME_SECRET_FIELD_DENY")
|
||||
normalized = {
|
||||
"goal": goal[:12000],
|
||||
"instructions": instructions[:32000],
|
||||
"success_criteria": normalized_criteria,
|
||||
"constraints": dict(constraints),
|
||||
}
|
||||
if len(_canonical(normalized).encode("utf-8")) > MAX_AGENT_RUNTIME_INPUT_BYTES:
|
||||
_error("AGENT_RUNTIME_INPUT_TOO_LARGE")
|
||||
return normalized
|
||||
|
||||
|
||||
def _capabilities(value: object) -> tuple[str, ...]:
|
||||
if value is None:
|
||||
return ()
|
||||
if not isinstance(value, Sequence) or isinstance(value, (str, bytes)):
|
||||
_error("CAPABILITY_SCOPE_INVALID")
|
||||
result = tuple(sorted({_string(item, "CAPABILITY_SCOPE_INVALID") for item in value}))
|
||||
if any(len(item) > 120 for item in result):
|
||||
_error("CAPABILITY_SCOPE_INVALID")
|
||||
return result
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class GovernedExecutionBinding:
|
||||
task_id: str
|
||||
job_id: str
|
||||
repository: str
|
||||
base_oid: str
|
||||
expected_branch_oid: str
|
||||
target_branch: str
|
||||
branch_mode: str
|
||||
generation: int
|
||||
idempotency_key: str
|
||||
|
||||
@classmethod
|
||||
def from_mapping(cls, value: Mapping[str, Any]) -> "GovernedExecutionBinding":
|
||||
data = dict(value)
|
||||
task_id = _task_id(data.get("task_id"))
|
||||
job_id = _string(data.get("job_id"), "JOB_ID_REQUIRED")
|
||||
if TASK_RE.fullmatch(job_id) is None:
|
||||
_error("JOB_ID_INVALID")
|
||||
repository = _string(data.get("repository"), "REPOSITORY_INVALID")
|
||||
if repository != "aios/aios":
|
||||
_error("WRONG_REPOSITORY_ENVELOPE_DENY")
|
||||
base_oid = _oid(data.get("base_oid"), "BASE_OID_INVALID")
|
||||
expected = _oid(data.get("expected_branch_oid"), "EXPECTED_BRANCH_OID_INVALID")
|
||||
target = _branch(data.get("target_branch"))
|
||||
mode = _string(data.get("branch_mode"), "BRANCH_MODE_MISSING")
|
||||
if mode not in {"CREATE_NEW", "CONTINUE_EXISTING"}:
|
||||
_error("BRANCH_MODE_INVALID")
|
||||
generation = _generation(data.get("generation"))
|
||||
if mode == "CREATE_NEW" and expected != base_oid:
|
||||
_error("EXPECTED_BASE_CONFLICT")
|
||||
key = _string(data.get("idempotency_key"), "IDEMPOTENCY_KEY_INVALID")
|
||||
if KEY_RE.fullmatch(key) is None:
|
||||
_error("IDEMPOTENCY_KEY_INVALID")
|
||||
return cls(task_id, job_id, repository, base_oid, expected, target, mode, generation, key)
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
def binding_from_bootstrap(value: Mapping[str, Any]) -> GovernedExecutionBinding:
|
||||
return GovernedExecutionBinding.from_mapping(value)
|
||||
|
||||
|
||||
def validate_execution_envelope(
|
||||
value: Mapping[str, Any],
|
||||
*,
|
||||
binding: GovernedExecutionBinding | None = None,
|
||||
worker_capabilities: Sequence[str] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
envelope = dict(value)
|
||||
if envelope.get("schema") != EXECUTION_SCHEMA:
|
||||
_error("EXECUTION_ENVELOPE_SCHEMA_VALIDATION")
|
||||
candidate = GovernedExecutionBinding.from_mapping(envelope)
|
||||
if binding is not None and candidate != binding:
|
||||
comparisons = (
|
||||
(candidate.task_id, binding.task_id, "TASK_BINDING_CONFLICT"),
|
||||
(candidate.job_id, binding.job_id, "JOB_BINDING_CONFLICT"),
|
||||
(candidate.repository, binding.repository, "WRONG_REPOSITORY_ENVELOPE_DENY"),
|
||||
(candidate.base_oid, binding.base_oid, "WRONG_BASE_ENVELOPE_DENY"),
|
||||
(candidate.expected_branch_oid, binding.expected_branch_oid, "WRONG_EXPECTED_HEAD_ENVELOPE_DENY"),
|
||||
(candidate.target_branch, binding.target_branch, "WRONG_BRANCH_ENVELOPE_DENY"),
|
||||
(candidate.generation, binding.generation, "WRONG_GENERATION_ENVELOPE_DENY"),
|
||||
(candidate.branch_mode, binding.branch_mode, "BRANCH_MODE_BINDING_CONFLICT"),
|
||||
(candidate.idempotency_key, binding.idempotency_key, "IDEMPOTENCY_BINDING_CONFLICT"),
|
||||
)
|
||||
for actual, expected, code in comparisons:
|
||||
if actual != expected:
|
||||
_error(code)
|
||||
action = _string(envelope.get("action"), "EXECUTION_ACTION_MISSING")
|
||||
if action not in SUPPORTED_ACTIONS:
|
||||
_error("EXECUTION_ACTION_UNSUPPORTED")
|
||||
capability_scope = _capabilities(envelope.get("capability_scope"))
|
||||
if worker_capabilities is not None and not set(capability_scope).issubset(set(worker_capabilities)):
|
||||
_error("CAPABILITY_MISMATCH_DENY")
|
||||
workspace = _object(envelope.get("workspace"), "WORKSPACE_POLICY_REQUIRED")
|
||||
if workspace.get("authority_git_dir") != "/data/aios-gitops/repo.git" or workspace.get("read_only_repository") is not True:
|
||||
_error("WORKSPACE_POLICY_DENY")
|
||||
governance = _object(envelope.get("governance"), "GOVERNANCE_POLICY_REQUIRED")
|
||||
governed_coordinates = (
|
||||
(governance.get("task_id"), candidate.task_id, "TASK_BINDING_CONFLICT"),
|
||||
(governance.get("job_id"), candidate.job_id, "JOB_BINDING_CONFLICT"),
|
||||
(governance.get("idempotency_key"), candidate.idempotency_key, "IDEMPOTENCY_BINDING_CONFLICT"),
|
||||
)
|
||||
for actual_coordinate, expected_coordinate, code in governed_coordinates:
|
||||
if actual_coordinate != expected_coordinate:
|
||||
_error(code)
|
||||
commit_key = _string(governance.get("commit_idempotency_key"), "COMMIT_IDEMPOTENCY_KEY_INVALID")
|
||||
if KEY_RE.fullmatch(commit_key) is None:
|
||||
_error("COMMIT_IDEMPOTENCY_KEY_INVALID")
|
||||
if governance.get("writer_lease") is not (action in MUTATION_ACTIONS):
|
||||
_error("WRITER_LEASE_POLICY_DENY")
|
||||
for field in ("main_write", "production_write", "tag_write", "baseline_write", "force_push", "protected_ref_bypass"):
|
||||
if governance.get(field, False) is not False:
|
||||
_error("POLICY_DENY")
|
||||
changes = envelope.get("change_set")
|
||||
verification = envelope.get("verification")
|
||||
if not isinstance(changes, list) or not isinstance(verification, list):
|
||||
_error("EXECUTION_OPERATIONS_INVALID")
|
||||
if action == "source_capture":
|
||||
if changes or verification:
|
||||
_error("SOURCE_CAPTURE_MUTATION_DENY")
|
||||
signals = list(_source_signals(envelope.get("source_signals") or []))
|
||||
if envelope.get("source_signals") != signals:
|
||||
_error("SOURCE_CAPTURE_SIGNALS_INVALID")
|
||||
if envelope.get("runtime_input") not in (None, {}):
|
||||
_error("SOURCE_CAPTURE_RUNTIME_INPUT_DENY")
|
||||
elif action == "agent_runtime":
|
||||
if changes or verification:
|
||||
_error("AGENT_RUNTIME_MUTATION_DENY")
|
||||
adapter = str(envelope.get("adapter") or "")
|
||||
if adapter not in AGENT_RUNTIME_ADAPTERS:
|
||||
_error("AGENT_RUNTIME_ADAPTER_INVALID")
|
||||
runtime_input = _agent_runtime_input(envelope.get("runtime_input"))
|
||||
if envelope.get("runtime_input") != runtime_input:
|
||||
_error("AGENT_RUNTIME_INPUT_NOT_CANONICAL")
|
||||
required_runtime_capability = f"agent.runtime.{adapter}"
|
||||
if required_runtime_capability not in capability_scope:
|
||||
_error("AGENT_RUNTIME_CAPABILITY_REQUIRED")
|
||||
if envelope.get("source_signals") not in (None, []):
|
||||
_error("AGENT_RUNTIME_SOURCE_SIGNALS_DENY")
|
||||
elif not changes:
|
||||
_error("CHANGE_SET_INVALID")
|
||||
declared = str(envelope.get("execution_digest") or "")
|
||||
material = {key: item for key, item in envelope.items() if key != "execution_digest"}
|
||||
actual = _digest(material)
|
||||
if declared != actual:
|
||||
_error("EXECUTION_DIGEST_INVALID")
|
||||
return {**material, "execution_digest": actual}
|
||||
|
||||
|
||||
def project_execution_envelope(
|
||||
binding: GovernedExecutionBinding,
|
||||
execution_request: Mapping[str, Any] | None = None,
|
||||
*,
|
||||
required_capabilities: Sequence[str] = (),
|
||||
) -> dict[str, Any]:
|
||||
request = dict(execution_request or {})
|
||||
action = str(request.get("action") or "source_capture")
|
||||
if action not in SUPPORTED_ACTIONS:
|
||||
_error("EXECUTION_ACTION_UNSUPPORTED")
|
||||
capabilities = _capabilities(request.get("capability_scope", required_capabilities))
|
||||
governance = {
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"idempotency_key": binding.idempotency_key,
|
||||
"commit_idempotency_key": str(request.get("commit_idempotency_key") or f"{binding.task_id}-commit-g{binding.generation}"),
|
||||
"writer_lease": action in MUTATION_ACTIONS,
|
||||
"main_write": False,
|
||||
"production_write": False,
|
||||
"tag_write": False,
|
||||
"baseline_write": False,
|
||||
"force_push": False,
|
||||
"protected_ref_bypass": False,
|
||||
}
|
||||
supplied_governance = request.get("governance")
|
||||
if supplied_governance is not None:
|
||||
governance.update(_object(supplied_governance, "GOVERNANCE_POLICY_REQUIRED"))
|
||||
material: dict[str, Any] = {
|
||||
"schema": EXECUTION_SCHEMA,
|
||||
**binding.public(),
|
||||
"action": action,
|
||||
"adapter": str(
|
||||
request.get("adapter")
|
||||
or ("deterministic" if action == "deterministic" else "source_capture")
|
||||
),
|
||||
"capability_scope": list(capabilities),
|
||||
"change_set": list(request.get("change_set") or []),
|
||||
"verification": list(request.get("verification") or []),
|
||||
"source_signals": list(_source_signals(request.get("source_signals") or [])) if action == "source_capture" else [],
|
||||
"runtime_input": _agent_runtime_input(request.get("runtime_input")) if action == "agent_runtime" else {},
|
||||
"governance": governance,
|
||||
"workspace": {
|
||||
"authority_git_dir": "/data/aios-gitops/repo.git",
|
||||
"read_only_repository": True,
|
||||
"cleanup_policy": "always",
|
||||
},
|
||||
}
|
||||
envelope = {**material, "execution_digest": _digest(material)}
|
||||
return validate_execution_envelope(envelope, binding=binding)
|
||||
|
||||
|
||||
def project_online_task(
|
||||
binding: GovernedExecutionBinding,
|
||||
task_request: Mapping[str, Any],
|
||||
execution_request: Mapping[str, Any] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
request = dict(task_request)
|
||||
required = _capabilities(request.get("required_capabilities"))
|
||||
execution_value = dict(execution_request or {})
|
||||
if str(execution_value.get("action") or "source_capture") == "agent_runtime":
|
||||
adapter = str(execution_value.get("adapter") or "")
|
||||
if adapter not in AGENT_RUNTIME_ADAPTERS:
|
||||
_error("AGENT_RUNTIME_ADAPTER_INVALID")
|
||||
runtime_input = execution_value.get("runtime_input")
|
||||
if runtime_input is None:
|
||||
runtime_input = {
|
||||
"goal": request.get("goal"),
|
||||
"instructions": request.get("instructions") or "",
|
||||
"success_criteria": request.get("success_criteria") or [],
|
||||
"constraints": request.get("constraints") or {},
|
||||
}
|
||||
execution_value["runtime_input"] = runtime_input
|
||||
execution = project_execution_envelope(
|
||||
binding,
|
||||
execution_value,
|
||||
required_capabilities=required,
|
||||
)
|
||||
metadata = dict(request.get("metadata") or {})
|
||||
if "execution" in metadata:
|
||||
validate_execution_envelope(_object(metadata["execution"], "EXECUTION_ENVELOPE_INVALID"), binding=binding)
|
||||
if metadata["execution"] != execution:
|
||||
_error("EXECUTION_PROJECTION_CONFLICT")
|
||||
metadata["execution"] = execution
|
||||
metadata["execution_projection"] = {
|
||||
"schema": PROJECTION_SCHEMA,
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"execution_digest": execution["execution_digest"],
|
||||
}
|
||||
return {
|
||||
**request,
|
||||
"task_id": binding.task_id,
|
||||
"metadata": metadata,
|
||||
"required_capabilities": list(required),
|
||||
"idempotency_key": str(request.get("idempotency_key") or f"online-task:{binding.idempotency_key}"),
|
||||
}
|
||||
|
||||
|
||||
def resolve_task_execution(
|
||||
task: Mapping[str, Any],
|
||||
binding: GovernedExecutionBinding,
|
||||
*,
|
||||
worker_capabilities: Sequence[str] | None = None,
|
||||
) -> tuple[dict[str, Any], str]:
|
||||
metadata = task.get("metadata")
|
||||
if isinstance(metadata, Mapping) and "execution" in metadata:
|
||||
value = validate_execution_envelope(
|
||||
_object(metadata["execution"], "EXECUTION_ENVELOPE_INVALID"),
|
||||
binding=binding,
|
||||
worker_capabilities=worker_capabilities,
|
||||
)
|
||||
return value, "persisted"
|
||||
projected = project_execution_envelope(
|
||||
binding,
|
||||
{"action": "source_capture", "capability_scope": task.get("required_capabilities") or []},
|
||||
required_capabilities=task.get("required_capabilities") or [],
|
||||
)
|
||||
validate_execution_envelope(projected, binding=binding, worker_capabilities=worker_capabilities)
|
||||
return projected, "recovered_projection"
|
||||
@@ -0,0 +1,187 @@
|
||||
"""Durable, authority-bound deterministic execution plans for Online Agent Tasks."""
|
||||
from __future__ import annotations
|
||||
|
||||
from contextlib import contextmanager
|
||||
from dataclasses import dataclass
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any, Mapping
|
||||
|
||||
from aios_online_agent_execution import (
|
||||
GovernedExecutionBinding,
|
||||
project_execution_envelope,
|
||||
)
|
||||
|
||||
|
||||
class ExecutionPlanError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def _canonical(value: object) -> bytes:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
|
||||
|
||||
|
||||
def _digest(value: object) -> str:
|
||||
return hashlib.sha256(_canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def _task_key(task_id: str) -> str:
|
||||
readable = "".join(ch if ch.isalnum() or ch in "._-" else "-" for ch in task_id).strip("-")[:72] or "task"
|
||||
return readable + "-" + hashlib.sha256(task_id.encode("utf-8")).hexdigest()[:24]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExecutionPlanRecord:
|
||||
task_id: str
|
||||
job_id: str
|
||||
source_head_oid: str
|
||||
generation: int
|
||||
idempotency_key: str
|
||||
plan_digest: str
|
||||
execution: dict[str, Any]
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return {
|
||||
"schema": "aios.online-agent.plan-record.v1",
|
||||
"task_id": self.task_id,
|
||||
"job_id": self.job_id,
|
||||
"source_head_oid": self.source_head_oid,
|
||||
"generation": self.generation,
|
||||
"idempotency_key": self.idempotency_key,
|
||||
"plan_digest": self.plan_digest,
|
||||
"execution": dict(self.execution),
|
||||
}
|
||||
|
||||
|
||||
class ExecutionPlanStore:
|
||||
def __init__(self, root: Path) -> None:
|
||||
self.root = Path(root)
|
||||
self.root.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def _path(self, task_id: str) -> Path:
|
||||
return self.root / (_task_key(task_id) + ".json")
|
||||
|
||||
@contextmanager
|
||||
def _lock(self, task_id: str):
|
||||
path = self.root / (_task_key(task_id) + ".lock")
|
||||
with path.open("a+b") as handle:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
|
||||
|
||||
@staticmethod
|
||||
def _source_head(binding: GovernedExecutionBinding) -> str:
|
||||
return binding.expected_branch_oid if binding.branch_mode == "CONTINUE_EXISTING" else binding.base_oid
|
||||
|
||||
def _read(self, task_id: str) -> ExecutionPlanRecord | None:
|
||||
path = self._path(task_id)
|
||||
if not path.is_file() or path.is_symlink():
|
||||
return None
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
if not isinstance(value, Mapping) or value.get("schema") != "aios.online-agent.plan-record.v1":
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_RECORD_INVALID")
|
||||
execution = value.get("execution")
|
||||
if not isinstance(execution, Mapping):
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_RECORD_INVALID")
|
||||
return ExecutionPlanRecord(
|
||||
task_id=str(value.get("task_id") or ""),
|
||||
job_id=str(value.get("job_id") or ""),
|
||||
source_head_oid=str(value.get("source_head_oid") or ""),
|
||||
generation=int(value.get("generation") or 0),
|
||||
idempotency_key=str(value.get("idempotency_key") or ""),
|
||||
plan_digest=str(value.get("plan_digest") or ""),
|
||||
execution=dict(execution),
|
||||
)
|
||||
|
||||
def register(
|
||||
self,
|
||||
binding: GovernedExecutionBinding,
|
||||
request: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
with self._lock(binding.task_id):
|
||||
return self._register_locked(binding, request)
|
||||
|
||||
def _register_locked(
|
||||
self,
|
||||
binding: GovernedExecutionBinding,
|
||||
request: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
if request.get("schema") != "aios.online-agent.plan.v1":
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_SCHEMA_INVALID")
|
||||
if request.get("task_id") != binding.task_id or request.get("job_id") != binding.job_id:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_BINDING_CONFLICT")
|
||||
if int(request.get("generation") or 0) != binding.generation:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_GENERATION_CONFLICT")
|
||||
source_head = str(request.get("source_head_oid") or "")
|
||||
if source_head != self._source_head(binding):
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_SOURCE_HEAD_CONFLICT")
|
||||
key = str(request.get("idempotency_key") or "")
|
||||
if len(key) < 8:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_IDEMPOTENCY_INVALID")
|
||||
execution_request = request.get("execution")
|
||||
if not isinstance(execution_request, Mapping) or execution_request.get("action") != "deterministic":
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_DETERMINISTIC_REQUIRED")
|
||||
envelope = project_execution_envelope(binding, execution_request)
|
||||
material = {
|
||||
"task_id": binding.task_id,
|
||||
"job_id": binding.job_id,
|
||||
"source_head_oid": source_head,
|
||||
"generation": binding.generation,
|
||||
"idempotency_key": key,
|
||||
"execution": dict(execution_request),
|
||||
}
|
||||
plan_digest = _digest(material)
|
||||
existing = self._read(binding.task_id)
|
||||
expected_previous = request.get("expected_previous_plan_digest")
|
||||
if existing is not None:
|
||||
if existing.idempotency_key == key:
|
||||
if existing.plan_digest != plan_digest:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_IDEMPOTENCY_CONFLICT")
|
||||
return {**existing.public(), "idempotent": True, "execution_digest": envelope["execution_digest"]}
|
||||
if expected_previous != existing.plan_digest:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_REPLACEMENT_CAS_MISMATCH")
|
||||
if existing.source_head_oid != source_head:
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_STALE_REPLACEMENT_DENY")
|
||||
elif expected_previous not in (None, ""):
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_REPLACEMENT_CAS_MISMATCH")
|
||||
|
||||
record = ExecutionPlanRecord(
|
||||
task_id=binding.task_id,
|
||||
job_id=binding.job_id,
|
||||
source_head_oid=source_head,
|
||||
generation=binding.generation,
|
||||
idempotency_key=key,
|
||||
plan_digest=plan_digest,
|
||||
execution=dict(execution_request),
|
||||
)
|
||||
path = self._path(binding.task_id)
|
||||
temporary = path.with_suffix(".tmp")
|
||||
temporary.write_text(
|
||||
json.dumps(record.public(), sort_keys=True, separators=(",", ":")),
|
||||
encoding="utf-8",
|
||||
)
|
||||
temporary.replace(path)
|
||||
return {**record.public(), "idempotent": False, "execution_digest": envelope["execution_digest"]}
|
||||
|
||||
def resolve(self, binding: GovernedExecutionBinding) -> dict[str, Any] | None:
|
||||
record = self._read(binding.task_id)
|
||||
if record is None:
|
||||
return None
|
||||
if (
|
||||
record.task_id != binding.task_id
|
||||
or record.job_id != binding.job_id
|
||||
or record.generation != binding.generation
|
||||
):
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_BINDING_CONFLICT")
|
||||
if record.source_head_oid != self._source_head(binding):
|
||||
raise ExecutionPlanError("EXECUTION_PLAN_SOURCE_HEAD_DRIFT")
|
||||
envelope = project_execution_envelope(binding, record.execution)
|
||||
return {
|
||||
"execution": dict(record.execution),
|
||||
"plan_digest": record.plan_digest,
|
||||
"execution_digest": envelope["execution_digest"],
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,82 @@
|
||||
"""Immutable release-lineage contracts used by activation and recovery."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass
|
||||
from typing import Any, Mapping
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ReleaseLineage:
|
||||
task_id: str
|
||||
candidate_id: str
|
||||
source_commit: str
|
||||
version: str
|
||||
required_capabilities: tuple[str, ...]
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
FIXED_V2R2C2 = ReleaseLineage(
|
||||
task_id="r42-release-candidate-v2r2c2-live-20260819",
|
||||
candidate_id="r42-release-candidate-v2r2c2-20260819",
|
||||
source_commit="71e736b05fab13efc06af7a4fe2dc022c1cf9a85",
|
||||
version="V2R2C2",
|
||||
required_capabilities=("release:candidate",),
|
||||
)
|
||||
|
||||
|
||||
class ReleaseLineageError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def validate_fixed_v2r2c2_task(task: Mapping[str, Any]) -> dict[str, Any]:
|
||||
"""Validate identity/source/version without mutating Task state.
|
||||
|
||||
This contract intentionally does not bind status/attempt/revision, because
|
||||
those are lifecycle state and may change through governed retry/recovery.
|
||||
"""
|
||||
|
||||
if str(task.get("task_id") or "") != FIXED_V2R2C2.task_id:
|
||||
raise ReleaseLineageError("FIXED_TASK_ID_DRIFT")
|
||||
|
||||
capabilities = task.get("required_capabilities")
|
||||
if (
|
||||
not isinstance(capabilities, list)
|
||||
or tuple(capabilities) != FIXED_V2R2C2.required_capabilities
|
||||
):
|
||||
raise ReleaseLineageError("FIXED_TASK_CAPABILITY_DRIFT")
|
||||
|
||||
constraints = task.get("constraints")
|
||||
if not isinstance(constraints, Mapping):
|
||||
raise ReleaseLineageError("FIXED_TASK_CONSTRAINTS_MISSING")
|
||||
release = constraints.get("release_candidate")
|
||||
if not isinstance(release, Mapping):
|
||||
raise ReleaseLineageError("FIXED_RELEASE_BINDING_MISSING")
|
||||
|
||||
actual = {
|
||||
"candidate_id": str(release.get("candidate_id") or ""),
|
||||
"source_commit": str(release.get("source_commit") or ""),
|
||||
"version": str(release.get("version") or ""),
|
||||
}
|
||||
expected = {
|
||||
"candidate_id": FIXED_V2R2C2.candidate_id,
|
||||
"source_commit": FIXED_V2R2C2.source_commit,
|
||||
"version": FIXED_V2R2C2.version,
|
||||
}
|
||||
if actual != expected:
|
||||
raise ReleaseLineageError(
|
||||
"FIXED_RELEASE_LINEAGE_DRIFT:"
|
||||
+ repr({"expected": expected, "actual": actual})
|
||||
)
|
||||
|
||||
return {
|
||||
"schema": "aios.release-lineage.validation.v1",
|
||||
"status": "VERIFIED",
|
||||
"lineage": FIXED_V2R2C2.as_dict(),
|
||||
"task_status": task.get("status"),
|
||||
"attempt": task.get("attempt"),
|
||||
"max_attempts": task.get("max_attempts"),
|
||||
"revision": task.get("revision"),
|
||||
}
|
||||
@@ -0,0 +1,714 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Persistent release-preparation Online Agent worker.
|
||||
|
||||
The worker is intentionally narrower than the generic engineering worker:
|
||||
it can only consume tasks whose required capability set is exactly
|
||||
{"release:candidate"} and whose payload asks for immutable release-candidate
|
||||
creation. It never receives Owner signing, deployment, tag, baseline or Git
|
||||
write credentials.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import socket
|
||||
import threading
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from typing import Any, Mapping
|
||||
from aios_autonomous_control_plane import (
|
||||
classify_failure,
|
||||
repair_for_failure,
|
||||
runtime_admission,
|
||||
)
|
||||
|
||||
AGENT_ID = os.environ.get(
|
||||
"AIOS_RELEASE_WORKER_AGENT_ID",
|
||||
"online-release-worker-cn-network-mkt-20260819",
|
||||
).strip()
|
||||
AGENT_VERSION = os.environ.get(
|
||||
"AIOS_RELEASE_WORKER_AGENT_VERSION",
|
||||
"2026-08-19.1-release-candidate",
|
||||
).strip()
|
||||
TASK_API = os.environ.get(
|
||||
"AIOS_AGENT_TASK_API_URL",
|
||||
"http://127.0.0.1:18940",
|
||||
).rstrip("/")
|
||||
RELEASE_API = os.environ.get("AIOS_RELEASE_API_URL", "").rstrip("/")
|
||||
POLL_SECONDS = int(os.environ.get("AIOS_RELEASE_WORKER_POLL_SECONDS", "3"))
|
||||
LEASE_SECONDS = int(os.environ.get("AIOS_RELEASE_WORKER_LEASE_SECONDS", "60"))
|
||||
HEARTBEAT_SECONDS = int(
|
||||
os.environ.get("AIOS_RELEASE_WORKER_HEARTBEAT_SECONDS", "15")
|
||||
)
|
||||
STATE_ROOT = Path(
|
||||
os.environ.get(
|
||||
"AIOS_RELEASE_WORKER_STATE_ROOT",
|
||||
"/var/lib/aios-online-agent-release",
|
||||
)
|
||||
)
|
||||
EXPECTED_CAPABILITIES = frozenset({"release:candidate"})
|
||||
LIVENESS_PATH = Path(
|
||||
os.environ.get(
|
||||
"AIOS_WORKER_LIVENESS_PATH",
|
||||
str(STATE_ROOT / "worker-liveness.json"),
|
||||
)
|
||||
)
|
||||
CANDIDATE_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,255}$")
|
||||
OID_RE = re.compile(r"^[0-9a-f]{40}$")
|
||||
VERSION_RE = re.compile(r"^V[0-9]+R[0-9]+C[0-9]+$")
|
||||
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
|
||||
SECRET_MARKERS = (
|
||||
"authorization",
|
||||
"token",
|
||||
"secret",
|
||||
"credential",
|
||||
"password",
|
||||
"private_key",
|
||||
"signature",
|
||||
)
|
||||
|
||||
|
||||
class ReleaseWorkerError(RuntimeError):
|
||||
def __init__(self, code: str, *, phase: str) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
self.phase = phase
|
||||
|
||||
|
||||
def now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value,
|
||||
ensure_ascii=False,
|
||||
sort_keys=True,
|
||||
separators=(",", ":"),
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def sha256(value: bytes) -> str:
|
||||
return hashlib.sha256(value).hexdigest()
|
||||
|
||||
|
||||
def sanitized(value: Any) -> Any:
|
||||
if isinstance(value, Mapping):
|
||||
result: dict[str, Any] = {}
|
||||
for key, inner in value.items():
|
||||
lowered = str(key).lower()
|
||||
if any(marker in lowered for marker in SECRET_MARKERS):
|
||||
result[str(key)] = "[REDACTED]"
|
||||
else:
|
||||
result[str(key)] = sanitized(inner)
|
||||
return result
|
||||
if isinstance(value, list):
|
||||
return [sanitized(item) for item in value]
|
||||
return value
|
||||
|
||||
|
||||
def audit(event: str, **fields: Any) -> None:
|
||||
STATE_ROOT.mkdir(parents=True, exist_ok=True, mode=0o750)
|
||||
path = STATE_ROOT / "events.jsonl"
|
||||
record = {
|
||||
"schema": "aios.release-worker.event.v1",
|
||||
"event": event,
|
||||
"created_at": now(),
|
||||
"agent_id": AGENT_ID,
|
||||
**sanitized(fields),
|
||||
}
|
||||
with path.open("a", encoding="utf-8") as handle:
|
||||
handle.write(json.dumps(record, sort_keys=True) + "\n")
|
||||
os.chmod(path, 0o640)
|
||||
|
||||
|
||||
def sd_notify(message: str) -> None:
|
||||
target = os.environ.get("NOTIFY_SOCKET", "")
|
||||
if not target:
|
||||
return
|
||||
if target.startswith("@"):
|
||||
address = "\0" + target[1:]
|
||||
else:
|
||||
address = target
|
||||
sock = socket.socket(socket.AF_UNIX, socket.SOCK_DGRAM)
|
||||
try:
|
||||
sock.connect(address)
|
||||
sock.sendall(message.encode("utf-8"))
|
||||
except OSError:
|
||||
# Liveness JSON remains the diagnostic source; systemd will enforce
|
||||
# WatchdogSec if notify transport is persistently broken.
|
||||
pass
|
||||
finally:
|
||||
sock.close()
|
||||
|
||||
|
||||
def write_liveness(
|
||||
state: str,
|
||||
*,
|
||||
task_id: str | None = None,
|
||||
stage: str | None = None,
|
||||
error: str | None = None,
|
||||
visible_count: int | None = None,
|
||||
) -> None:
|
||||
STATE_ROOT.mkdir(parents=True, exist_ok=True, mode=0o750)
|
||||
value = {
|
||||
"schema": "aios.online-agent.worker-liveness.v1",
|
||||
"agent_id": AGENT_ID,
|
||||
"agent_type": "release-preparation-worker",
|
||||
"agent_version": AGENT_VERSION,
|
||||
"pid": os.getpid(),
|
||||
"state": state,
|
||||
"last_seen_epoch": time.time(),
|
||||
"last_seen_at": now(),
|
||||
"poll_seconds": POLL_SECONDS,
|
||||
"heartbeat_seconds": HEARTBEAT_SECONDS,
|
||||
"api_base": TASK_API,
|
||||
"capabilities": sorted(EXPECTED_CAPABILITIES),
|
||||
"task_id": task_id,
|
||||
"stage": stage,
|
||||
"error": error,
|
||||
"visible_count": visible_count,
|
||||
}
|
||||
LIVENESS_PATH.parent.mkdir(parents=True, exist_ok=True, mode=0o750)
|
||||
temporary = LIVENESS_PATH.with_name(
|
||||
"." + LIVENESS_PATH.name + f".{os.getpid()}.tmp"
|
||||
)
|
||||
temporary.write_text(
|
||||
json.dumps(value, ensure_ascii=False, sort_keys=True) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
os.chmod(temporary, 0o640)
|
||||
os.replace(temporary, LIVENESS_PATH)
|
||||
|
||||
|
||||
def load_credential(name: str) -> str:
|
||||
directory = Path(os.environ.get("CREDENTIALS_DIRECTORY", ""))
|
||||
path = directory / name
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise ReleaseWorkerError(
|
||||
"CREDENTIAL_UNAVAILABLE:" + name,
|
||||
phase="startup",
|
||||
)
|
||||
value = path.read_text(encoding="utf-8").strip()
|
||||
if len(value) < 24 or any(ch.isspace() for ch in value):
|
||||
raise ReleaseWorkerError(
|
||||
"CREDENTIAL_INVALID:" + name,
|
||||
phase="startup",
|
||||
)
|
||||
return value
|
||||
|
||||
|
||||
def http_json(
|
||||
base: str,
|
||||
method: str,
|
||||
route: str,
|
||||
token: str,
|
||||
body: Mapping[str, Any] | None = None,
|
||||
*,
|
||||
timeout: int = 30,
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
data = None if body is None else canonical(body)
|
||||
headers = {"Accept": "application/json"}
|
||||
if token:
|
||||
headers["Authorization"] = "Bearer " + token
|
||||
if data is not None:
|
||||
headers["Content-Type"] = "application/json"
|
||||
request = urllib.request.Request(
|
||||
base + route,
|
||||
method=method,
|
||||
data=data,
|
||||
headers=headers,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response:
|
||||
raw, status = response.read(), response.status
|
||||
except urllib.error.HTTPError as exc:
|
||||
raw, status = exc.read(), exc.code
|
||||
except (urllib.error.URLError, TimeoutError) as exc:
|
||||
raise ReleaseWorkerError(
|
||||
"HTTP_TRANSPORT_UNAVAILABLE",
|
||||
phase="network",
|
||||
) from exc
|
||||
try:
|
||||
value = json.loads(raw.decode())
|
||||
except Exception as exc:
|
||||
raise ReleaseWorkerError(
|
||||
"HTTP_RESPONSE_INVALID",
|
||||
phase="network",
|
||||
) from exc
|
||||
return status, value if isinstance(value, dict) else {}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ReleaseRequest:
|
||||
candidate_id: str
|
||||
source_commit: str
|
||||
version: str
|
||||
projection_id: str | None
|
||||
|
||||
@classmethod
|
||||
def from_task(cls, task: Mapping[str, Any]) -> "ReleaseRequest":
|
||||
if not TASK_RE.fullmatch(str(task.get("task_id") or "")):
|
||||
raise ReleaseWorkerError("TASK_ID_INVALID", phase="validation")
|
||||
caps = task.get("required_capabilities")
|
||||
if (
|
||||
not isinstance(caps, list)
|
||||
or frozenset(caps) != EXPECTED_CAPABILITIES
|
||||
or len(caps) != 1
|
||||
):
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_CAPABILITY_SCOPE_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
metadata = task.get("metadata")
|
||||
if not isinstance(metadata, Mapping):
|
||||
metadata = {}
|
||||
constraints = task.get("constraints")
|
||||
if not isinstance(constraints, Mapping):
|
||||
constraints = {}
|
||||
release = constraints.get("release_candidate")
|
||||
if not isinstance(release, Mapping):
|
||||
release = metadata.get("release_candidate")
|
||||
if not isinstance(release, Mapping):
|
||||
release = task.get("release_candidate")
|
||||
if not isinstance(release, Mapping):
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_CANDIDATE_PAYLOAD_MISSING",
|
||||
phase="validation",
|
||||
)
|
||||
allowed = {
|
||||
"candidate_id",
|
||||
"source_commit",
|
||||
"version",
|
||||
"projection_id",
|
||||
}
|
||||
if set(release) - allowed:
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_CANDIDATE_PAYLOAD_FIELDS_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
candidate_id = str(release.get("candidate_id") or "")
|
||||
source_commit = str(release.get("source_commit") or "")
|
||||
version = str(release.get("version") or "")
|
||||
projection_id = release.get("projection_id")
|
||||
if CANDIDATE_RE.fullmatch(candidate_id) is None:
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_CANDIDATE_ID_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
if OID_RE.fullmatch(source_commit) is None:
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_SOURCE_COMMIT_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
if VERSION_RE.fullmatch(version) is None:
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_VERSION_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
if projection_id is not None:
|
||||
projection_id = str(projection_id)
|
||||
if not re.fullmatch(r"projection-[0-9a-f]{32}", projection_id):
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_PROJECTION_ID_INVALID",
|
||||
phase="validation",
|
||||
)
|
||||
return cls(
|
||||
candidate_id=candidate_id,
|
||||
source_commit=source_commit,
|
||||
version=version,
|
||||
projection_id=projection_id,
|
||||
)
|
||||
|
||||
def body(self) -> dict[str, str]:
|
||||
return {
|
||||
"candidate_id": self.candidate_id,
|
||||
"source_commit": self.source_commit,
|
||||
"version": self.version,
|
||||
}
|
||||
|
||||
|
||||
class Heartbeat:
|
||||
def __init__(
|
||||
self,
|
||||
agent_token: str,
|
||||
task_id: str,
|
||||
lease_token: str,
|
||||
) -> None:
|
||||
self.agent_token = agent_token
|
||||
self.task_id = task_id
|
||||
self.lease_token = lease_token
|
||||
self.stage = "claimed"
|
||||
self.failure: str | None = None
|
||||
self.stop = threading.Event()
|
||||
self.thread = threading.Thread(
|
||||
target=self._run,
|
||||
name="release-worker-heartbeat",
|
||||
daemon=True,
|
||||
)
|
||||
|
||||
def first(self) -> None:
|
||||
status, value = http_json(
|
||||
TASK_API,
|
||||
"POST",
|
||||
f"/v1/tasks/{self.task_id}/heartbeat",
|
||||
self.agent_token,
|
||||
{
|
||||
"lease_token": self.lease_token,
|
||||
"lease_seconds": LEASE_SECONDS,
|
||||
"progress": {
|
||||
"stage": self.stage,
|
||||
"worker_version": AGENT_VERSION,
|
||||
},
|
||||
},
|
||||
)
|
||||
if status != 200:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_HEARTBEAT_FAILED",
|
||||
phase="heartbeat",
|
||||
)
|
||||
audit(
|
||||
"TASK_HEARTBEAT",
|
||||
task_id=self.task_id,
|
||||
stage=self.stage,
|
||||
api_status=status,
|
||||
)
|
||||
write_liveness(
|
||||
"BUSY",
|
||||
task_id=self.task_id,
|
||||
stage=self.stage,
|
||||
)
|
||||
sd_notify("WATCHDOG=1")
|
||||
|
||||
def _run(self) -> None:
|
||||
while not self.stop.wait(HEARTBEAT_SECONDS):
|
||||
try:
|
||||
status, value = http_json(
|
||||
TASK_API,
|
||||
"POST",
|
||||
f"/v1/tasks/{self.task_id}/heartbeat",
|
||||
self.agent_token,
|
||||
{
|
||||
"lease_token": self.lease_token,
|
||||
"lease_seconds": LEASE_SECONDS,
|
||||
"progress": {
|
||||
"stage": self.stage,
|
||||
"worker_version": AGENT_VERSION,
|
||||
},
|
||||
},
|
||||
)
|
||||
if status != 200:
|
||||
self.failure = str(value.get("error") or status)
|
||||
return
|
||||
audit(
|
||||
"TASK_HEARTBEAT",
|
||||
task_id=self.task_id,
|
||||
stage=self.stage,
|
||||
api_status=status,
|
||||
)
|
||||
write_liveness(
|
||||
"BUSY",
|
||||
task_id=self.task_id,
|
||||
stage=self.stage,
|
||||
)
|
||||
sd_notify("WATCHDOG=1")
|
||||
except Exception as exc:
|
||||
self.failure = type(exc).__name__
|
||||
return
|
||||
|
||||
def ensure(self) -> None:
|
||||
if self.failure:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_LEASE_LOST",
|
||||
phase="heartbeat",
|
||||
)
|
||||
|
||||
def close(self) -> None:
|
||||
self.stop.set()
|
||||
if self.thread.ident is not None:
|
||||
self.thread.join(timeout=2)
|
||||
|
||||
|
||||
def release_admission(
|
||||
task: Mapping[str, Any],
|
||||
*,
|
||||
release_token: str,
|
||||
):
|
||||
required = task.get("required_capabilities")
|
||||
if not isinstance(required, list):
|
||||
required = []
|
||||
|
||||
def release_api_health() -> bool:
|
||||
status, value = http_json(
|
||||
RELEASE_API,
|
||||
"GET",
|
||||
"/health",
|
||||
"",
|
||||
timeout=10,
|
||||
)
|
||||
return status == 200 and str(value.get("status") or "").lower() in {"ok", "healthy"}
|
||||
|
||||
def authenticated_probe() -> bool:
|
||||
status, _ = http_json(
|
||||
RELEASE_API,
|
||||
"POST",
|
||||
"/createReleaseCandidate",
|
||||
release_token,
|
||||
{},
|
||||
timeout=10,
|
||||
)
|
||||
# Authentication + credential projection succeeded; the empty release
|
||||
# request is intentionally rejected by request validation.
|
||||
return status == 400
|
||||
|
||||
probes = {
|
||||
"credential_projection": authenticated_probe,
|
||||
"trusted_builder": release_api_health,
|
||||
"authenticated_probe": authenticated_probe,
|
||||
"release_api_health": release_api_health,
|
||||
"worker_liveness": lambda: True,
|
||||
}
|
||||
return runtime_admission(
|
||||
worker_capabilities=EXPECTED_CAPABILITIES,
|
||||
required_capabilities=required,
|
||||
requested_operations=("prepare_release",),
|
||||
probes=probes,
|
||||
)
|
||||
|
||||
|
||||
def result_payload(
|
||||
task_id: str,
|
||||
release: ReleaseRequest,
|
||||
builder: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
builder_candidate = builder.get("candidate_id")
|
||||
if builder_candidate not in {None, release.candidate_id}:
|
||||
raise ReleaseWorkerError(
|
||||
"BUILDER_CANDIDATE_BINDING_INVALID",
|
||||
phase="release",
|
||||
)
|
||||
immutable = {
|
||||
"candidate_id": release.candidate_id,
|
||||
"source_commit": release.source_commit,
|
||||
"version": release.version,
|
||||
}
|
||||
return {
|
||||
"status": "SUCCEEDED",
|
||||
"classification": "RELEASE_CANDIDATE_CREATED",
|
||||
"execution_mode": "release_candidate",
|
||||
"adapter": "release_candidate",
|
||||
"task_id": task_id,
|
||||
"agent_id": AGENT_ID,
|
||||
"release_candidate": immutable,
|
||||
"release_candidate_request_sha256": sha256(canonical(immutable)),
|
||||
"builder_response": sanitized(dict(builder)),
|
||||
"projection_id": release.projection_id,
|
||||
"writer_lease": "NONE",
|
||||
"changed_files": [],
|
||||
"direct_main_write": False,
|
||||
"production_write": False,
|
||||
"tag_write": False,
|
||||
"baseline_write": False,
|
||||
"runtime_switch": False,
|
||||
"owner_approval_submitted": False,
|
||||
"credential_material_exposed": False,
|
||||
}
|
||||
|
||||
|
||||
def execute_task(
|
||||
task: Mapping[str, Any],
|
||||
*,
|
||||
agent_token: str,
|
||||
release_token: str,
|
||||
) -> bool:
|
||||
task_id = str(task.get("task_id") or "")
|
||||
release = ReleaseRequest.from_task(task)
|
||||
admission = release_admission(
|
||||
task,
|
||||
release_token=release_token,
|
||||
)
|
||||
if not admission.admitted:
|
||||
audit(
|
||||
"TASK_ADMISSION_BLOCKED",
|
||||
task_id=task_id,
|
||||
admission=admission.as_dict(),
|
||||
)
|
||||
write_liveness(
|
||||
"BLOCKED",
|
||||
task_id=task_id,
|
||||
stage="execution_ready",
|
||||
error=admission.failure_class.value if admission.failure_class else "ADMISSION_FAILED",
|
||||
)
|
||||
return False
|
||||
audit(
|
||||
"TASK_ADMISSION_PASSED",
|
||||
task_id=task_id,
|
||||
admission=admission.as_dict(),
|
||||
)
|
||||
status, claimed = http_json(
|
||||
TASK_API,
|
||||
"POST",
|
||||
f"/v1/tasks/{task_id}/claim",
|
||||
agent_token,
|
||||
{"lease_seconds": LEASE_SECONDS},
|
||||
)
|
||||
if status in {409, 423}:
|
||||
return False
|
||||
if status != 200:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_CLAIM_FAILED",
|
||||
phase="claim",
|
||||
)
|
||||
lease_token = str(claimed.get("lease_token") or "")
|
||||
if len(lease_token) < 16:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_LEASE_TOKEN_INVALID",
|
||||
phase="claim",
|
||||
)
|
||||
attempt = int(claimed.get("attempt") or 0)
|
||||
audit(
|
||||
"TASK_CLAIMED",
|
||||
task_id=task_id,
|
||||
attempt=attempt,
|
||||
)
|
||||
|
||||
heartbeat = Heartbeat(agent_token, task_id, lease_token)
|
||||
heartbeat.first()
|
||||
heartbeat.thread.start()
|
||||
try:
|
||||
heartbeat.stage = "release_candidate"
|
||||
heartbeat.ensure()
|
||||
status, builder = http_json(
|
||||
RELEASE_API,
|
||||
"POST",
|
||||
"/createReleaseCandidate",
|
||||
release_token,
|
||||
release.body(),
|
||||
timeout=120,
|
||||
)
|
||||
if status not in {200, 201, 202}:
|
||||
raise ReleaseWorkerError(
|
||||
"RELEASE_CANDIDATE_CREATE_FAILED:"
|
||||
+ str(builder.get("error") or status),
|
||||
phase="release",
|
||||
)
|
||||
heartbeat.ensure()
|
||||
result = result_payload(task_id, release, builder)
|
||||
idempotency_key = (
|
||||
f"{task_id}-attempt-{attempt}-release-result-v1"
|
||||
)
|
||||
status, submitted = http_json(
|
||||
TASK_API,
|
||||
"POST",
|
||||
f"/v1/tasks/{task_id}/result",
|
||||
agent_token,
|
||||
{
|
||||
"lease_token": lease_token,
|
||||
"idempotency_key": idempotency_key,
|
||||
"result": result,
|
||||
},
|
||||
)
|
||||
if status not in {200, 201, 202}:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_RESULT_SUBMIT_FAILED",
|
||||
phase="result",
|
||||
)
|
||||
audit(
|
||||
"RESULT_SUBMITTED",
|
||||
task_id=task_id,
|
||||
attempt=attempt,
|
||||
release_candidate_id=release.candidate_id,
|
||||
)
|
||||
return True
|
||||
finally:
|
||||
heartbeat.close()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
if not RELEASE_API:
|
||||
raise SystemExit("FATAL:AIOS_RELEASE_API_URL_REQUIRED")
|
||||
agent_token = load_credential("agent_token")
|
||||
release_token = load_credential("release_candidate_token")
|
||||
STATE_ROOT.mkdir(parents=True, exist_ok=True, mode=0o750)
|
||||
audit(
|
||||
"WORKER_STARTED",
|
||||
capabilities=sorted(EXPECTED_CAPABILITIES),
|
||||
release_api=RELEASE_API,
|
||||
)
|
||||
write_liveness("STARTING", stage="startup")
|
||||
sd_notify("READY=1\nSTATUS=release worker ready")
|
||||
while True:
|
||||
try:
|
||||
status, response = http_json(
|
||||
TASK_API,
|
||||
"POST",
|
||||
"/v1/tasks/poll",
|
||||
agent_token,
|
||||
{"limit": 100},
|
||||
)
|
||||
if status != 200:
|
||||
raise ReleaseWorkerError(
|
||||
"TASK_POLL_FAILED",
|
||||
phase="poll",
|
||||
)
|
||||
tasks = response.get("tasks")
|
||||
if not isinstance(tasks, list):
|
||||
tasks = []
|
||||
write_liveness(
|
||||
"IDLE",
|
||||
stage="poll",
|
||||
visible_count=len(tasks),
|
||||
)
|
||||
sd_notify("WATCHDOG=1\nSTATUS=release worker poll ok")
|
||||
handled = False
|
||||
for raw in tasks:
|
||||
if not isinstance(raw, Mapping):
|
||||
continue
|
||||
caps = raw.get("required_capabilities")
|
||||
if (
|
||||
not isinstance(caps, list)
|
||||
or frozenset(caps) != EXPECTED_CAPABILITIES
|
||||
):
|
||||
continue
|
||||
try:
|
||||
handled = execute_task(
|
||||
raw,
|
||||
agent_token=agent_token,
|
||||
release_token=release_token,
|
||||
) or handled
|
||||
except ReleaseWorkerError as exc:
|
||||
failure = classify_failure(exc.code, phase=exc.phase)
|
||||
repair = repair_for_failure(failure)
|
||||
audit(
|
||||
"TASK_EXECUTION_FAILED",
|
||||
task_id=raw.get("task_id"),
|
||||
phase=exc.phase,
|
||||
error=exc.code,
|
||||
failure_class=failure.value,
|
||||
repair=repair.as_dict(),
|
||||
)
|
||||
time.sleep(0 if handled else POLL_SECONDS)
|
||||
except KeyboardInterrupt:
|
||||
return 0
|
||||
except Exception as exc:
|
||||
audit(
|
||||
"WORKER_LOOP_ERROR",
|
||||
error=type(exc).__name__,
|
||||
)
|
||||
write_liveness(
|
||||
"DEGRADED",
|
||||
stage="loop",
|
||||
error=type(exc).__name__,
|
||||
)
|
||||
time.sleep(POLL_SECONDS)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,287 @@
|
||||
"""Credential-isolated durable coordinator for the release-preparation supervisor.
|
||||
|
||||
The coordinator owns only its Online Task agent credential. It never forwards
|
||||
that credential to Hermes/OpenClaw and never submits a Task result while the
|
||||
supervision goal is incomplete. Its job is deliberately small: claim the one
|
||||
fixed supervisor Task after an exact coordinator projection and keep a durable
|
||||
heartbeat lease while later phases observe and repair through governed APIs.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timezone
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import time
|
||||
from typing import Any, Mapping
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
|
||||
API_BASE = os.environ.get(
|
||||
"AIOS_AGENT_TASK_API_URL", "http://127.0.0.1:18940"
|
||||
).rstrip("/")
|
||||
AGENT_ID = os.environ.get(
|
||||
"AIOS_AGENT_ID",
|
||||
"online-engineering-worker-cn-network-mkt-autonomous-20260815",
|
||||
)
|
||||
TASK_ID = os.environ.get(
|
||||
"AIOS_RELEASE_PREPARATION_SUPERVISOR_TASK_ID",
|
||||
"r42-release-preparation-autonomous-supervisor-20260820",
|
||||
)
|
||||
EXPECTED_EXECUTION_DIGEST = os.environ.get(
|
||||
"AIOS_RELEASE_PREPARATION_SUPERVISOR_EXECUTION_DIGEST", ""
|
||||
)
|
||||
RUNTIME_CAPABILITY = "agent.runtime.openclaw"
|
||||
COORDINATOR_CAPABILITY = "engineering.autonomous"
|
||||
REQUIRED_CAPABILITIES = [RUNTIME_CAPABILITY, COORDINATOR_CAPABILITY]
|
||||
POLL_SECONDS = int(os.environ.get("AIOS_SUPERVISOR_COORDINATOR_POLL_SECONDS", "5"))
|
||||
HEARTBEAT_SECONDS = int(
|
||||
os.environ.get("AIOS_SUPERVISOR_COORDINATOR_HEARTBEAT_SECONDS", "10")
|
||||
)
|
||||
LEASE_SECONDS = int(os.environ.get("AIOS_SUPERVISOR_COORDINATOR_LEASE_SECONDS", "300"))
|
||||
STATE_ROOT = Path(
|
||||
os.environ.get(
|
||||
"AIOS_SUPERVISOR_COORDINATOR_STATE_ROOT",
|
||||
"/var/lib/aios-release-preparation-supervisor-coordinator",
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
class CoordinatorError(RuntimeError):
|
||||
def __init__(self, code: str) -> None:
|
||||
super().__init__(code)
|
||||
self.code = code
|
||||
|
||||
|
||||
def now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def canonical(value: object) -> bytes:
|
||||
return json.dumps(
|
||||
value, sort_keys=True, separators=(",", ":"), ensure_ascii=False
|
||||
).encode("utf-8")
|
||||
|
||||
|
||||
def atomic_json(path: Path, value: Mapping[str, Any]) -> None:
|
||||
path.parent.mkdir(parents=True, mode=0o750, exist_ok=True)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise CoordinatorError("COORDINATOR_STATE_SYMLINK_REJECTED")
|
||||
fd, temporary = tempfile.mkstemp(prefix=f".{path.name}.", dir=str(path.parent))
|
||||
try:
|
||||
os.fchmod(fd, 0o640)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
json.dump(dict(value), handle, ensure_ascii=False, sort_keys=True)
|
||||
handle.write("\n")
|
||||
handle.flush()
|
||||
os.fsync(handle.fileno())
|
||||
os.replace(temporary, path)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def audit(event_type: str, **fields: Any) -> None:
|
||||
record = {
|
||||
"event_type": event_type,
|
||||
"created_at": now(),
|
||||
"agent_id": AGENT_ID,
|
||||
"task_id": TASK_ID,
|
||||
"credential_material_exposed": False,
|
||||
"planner_credential_material_exposed": False,
|
||||
"lease_material_exposed": False,
|
||||
**fields,
|
||||
}
|
||||
STATE_ROOT.mkdir(parents=True, mode=0o750, exist_ok=True)
|
||||
with (STATE_ROOT / "events.jsonl").open("a", encoding="utf-8") as handle:
|
||||
handle.write(json.dumps(record, ensure_ascii=False, sort_keys=True) + "\n")
|
||||
atomic_json(STATE_ROOT / "liveness.json", record)
|
||||
|
||||
|
||||
def api_call(
|
||||
method: str,
|
||||
route: str,
|
||||
token: str,
|
||||
body: Mapping[str, Any] | None = None,
|
||||
) -> tuple[int, dict[str, Any]]:
|
||||
payload = None if body is None else canonical(dict(body))
|
||||
headers = {"Authorization": "Bearer " + token, "Accept": "application/json"}
|
||||
if payload is not None:
|
||||
headers["Content-Type"] = "application/json"
|
||||
request = urllib.request.Request(
|
||||
API_BASE + route, data=payload, headers=headers, method=method
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=20) as response:
|
||||
value = json.loads(response.read().decode("utf-8"))
|
||||
return response.status, value if isinstance(value, dict) else {}
|
||||
except urllib.error.HTTPError as exc:
|
||||
try:
|
||||
value = json.loads(exc.read(4096).decode("utf-8", "replace"))
|
||||
except Exception:
|
||||
value = {"error": "HTTP_ERROR"}
|
||||
return exc.code, value if isinstance(value, dict) else {"error": "HTTP_ERROR"}
|
||||
except (urllib.error.URLError, TimeoutError):
|
||||
return 599, {"error": "AGENT_TASK_API_UNAVAILABLE"}
|
||||
|
||||
|
||||
def load_agent_token() -> str:
|
||||
path = Path(os.environ.get("CREDENTIALS_DIRECTORY", "")) / "agent_token"
|
||||
if path.is_symlink() or not path.is_file():
|
||||
raise CoordinatorError("COORDINATOR_AGENT_CREDENTIAL_UNAVAILABLE")
|
||||
token = path.read_text(encoding="utf-8").strip()
|
||||
if len(token) < 24 or any(character.isspace() for character in token):
|
||||
raise CoordinatorError("COORDINATOR_AGENT_CREDENTIAL_INVALID")
|
||||
return token
|
||||
|
||||
|
||||
def validate_task(task: Mapping[str, Any]) -> dict[str, Any]:
|
||||
if task.get("task_id") != TASK_ID or task.get("status") != "QUEUED":
|
||||
raise CoordinatorError("SUPERVISOR_TASK_STATE_INVALID")
|
||||
if task.get("required_capabilities") != REQUIRED_CAPABILITIES:
|
||||
raise CoordinatorError("SUPERVISOR_COORDINATOR_CAPABILITIES_INVALID")
|
||||
metadata = task.get("metadata")
|
||||
if not isinstance(metadata, Mapping):
|
||||
raise CoordinatorError("SUPERVISOR_EXECUTION_METADATA_MISSING")
|
||||
execution = metadata.get("execution")
|
||||
if not isinstance(execution, Mapping):
|
||||
raise CoordinatorError("SUPERVISOR_EXECUTION_METADATA_MISSING")
|
||||
governance = execution.get("governance")
|
||||
if (
|
||||
execution.get("action") != "agent_runtime"
|
||||
or execution.get("adapter") != "openclaw"
|
||||
or execution.get("capability_scope") != REQUIRED_CAPABILITIES
|
||||
or execution.get("execution_digest") != EXPECTED_EXECUTION_DIGEST
|
||||
or execution.get("change_set") != []
|
||||
or execution.get("verification") != []
|
||||
or not isinstance(governance, Mapping)
|
||||
or governance.get("writer_lease") is not False
|
||||
or any(
|
||||
governance.get(field) is not False
|
||||
for field in (
|
||||
"main_write",
|
||||
"production_write",
|
||||
"tag_write",
|
||||
"baseline_write",
|
||||
"force_push",
|
||||
"protected_ref_bypass",
|
||||
)
|
||||
)
|
||||
):
|
||||
raise CoordinatorError("SUPERVISOR_COORDINATOR_ENVELOPE_INVALID")
|
||||
return dict(execution)
|
||||
|
||||
|
||||
def heartbeat_progress(sequence: int) -> dict[str, Any]:
|
||||
return {
|
||||
"stage": "supervisor_coordinator_active",
|
||||
"phase": "external_caller_projection",
|
||||
"state": "PENDING_EXTERNAL_CONNECTOR_ACK",
|
||||
"sequence": sequence,
|
||||
"control_plane_access_granted": True,
|
||||
"external_planner_role": "UNPRIVILEGED_PLANNER",
|
||||
"credential_forwarded_to_planner": False,
|
||||
"main_write": False,
|
||||
"production_write": False,
|
||||
"owner_approval_submitted": False,
|
||||
}
|
||||
|
||||
|
||||
def coordinate_claim(
|
||||
claim: Mapping[str, Any],
|
||||
token: str,
|
||||
*,
|
||||
max_heartbeats: int | None = None,
|
||||
) -> int:
|
||||
lease_token = claim.get("lease_token")
|
||||
if not isinstance(lease_token, str) or len(lease_token) < 24:
|
||||
raise CoordinatorError("COORDINATOR_LEASE_TOKEN_MISSING")
|
||||
sequence = 0
|
||||
while max_heartbeats is None or sequence < max_heartbeats:
|
||||
sequence += 1
|
||||
status, response = api_call(
|
||||
"POST",
|
||||
f"/v1/tasks/{TASK_ID}/heartbeat",
|
||||
token,
|
||||
{
|
||||
"lease_token": lease_token,
|
||||
"lease_seconds": LEASE_SECONDS,
|
||||
"progress": heartbeat_progress(sequence),
|
||||
},
|
||||
)
|
||||
if status != 200:
|
||||
raise CoordinatorError(
|
||||
"COORDINATOR_HEARTBEAT_FAILED_" + str(response.get("error") or status)
|
||||
)
|
||||
audit(
|
||||
"SUPERVISOR_COORDINATOR_HEARTBEAT",
|
||||
sequence=sequence,
|
||||
task_status=response.get("status"),
|
||||
lease_expires_at=response.get("lease_expires_at"),
|
||||
control_plane_access_granted=True,
|
||||
external_planner_role="UNPRIVILEGED_PLANNER",
|
||||
)
|
||||
if max_heartbeats is None or sequence < max_heartbeats:
|
||||
time.sleep(HEARTBEAT_SECONDS)
|
||||
return sequence
|
||||
|
||||
|
||||
def worker_once(token: str) -> bool:
|
||||
status, poll = api_call("POST", "/v1/tasks/poll", token, {"limit": 100})
|
||||
if status != 200:
|
||||
audit("SUPERVISOR_COORDINATOR_POLL_FAILED", error=poll.get("error") or status)
|
||||
return False
|
||||
task = next(
|
||||
(
|
||||
item
|
||||
for item in poll.get("tasks", [])
|
||||
if isinstance(item, Mapping) and item.get("task_id") == TASK_ID
|
||||
),
|
||||
None,
|
||||
)
|
||||
if task is None:
|
||||
audit("SUPERVISOR_COORDINATOR_WAITING_FOR_TASK")
|
||||
return False
|
||||
validate_task(task)
|
||||
status, claim = api_call(
|
||||
"POST", f"/v1/tasks/{TASK_ID}/claim", token, {"lease_seconds": LEASE_SECONDS}
|
||||
)
|
||||
if status != 200:
|
||||
audit("SUPERVISOR_COORDINATOR_CLAIM_FAILED", error=claim.get("error") or status)
|
||||
return False
|
||||
audit(
|
||||
"SUPERVISOR_COORDINATOR_CLAIMED",
|
||||
attempt=claim.get("attempt"),
|
||||
revision=claim.get("revision"),
|
||||
claim_mode="server_atomic",
|
||||
control_plane_access_granted=True,
|
||||
)
|
||||
coordinate_claim(claim, token)
|
||||
return True
|
||||
|
||||
|
||||
def main() -> int:
|
||||
if not EXPECTED_EXECUTION_DIGEST or len(EXPECTED_EXECUTION_DIGEST) != 64:
|
||||
raise CoordinatorError("SUPERVISOR_EXECUTION_DIGEST_CONFIG_INVALID")
|
||||
token = load_agent_token()
|
||||
audit(
|
||||
"SUPERVISOR_COORDINATOR_READY",
|
||||
required_capabilities=REQUIRED_CAPABILITIES,
|
||||
control_plane_access_granted=True,
|
||||
external_planner_role="UNPRIVILEGED_PLANNER",
|
||||
)
|
||||
while True:
|
||||
try:
|
||||
worker_once(token)
|
||||
except Exception as exc:
|
||||
audit(
|
||||
"SUPERVISOR_COORDINATOR_LOOP_ERROR",
|
||||
error=exc.code if isinstance(exc, CoordinatorError) else type(exc).__name__,
|
||||
)
|
||||
time.sleep(POLL_SECONDS)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,462 @@
|
||||
"""Self-healing availability guard for persistent Online Agent workers.
|
||||
|
||||
The guard never claims Tasks and never writes Task/Job/Git databases. It only:
|
||||
- ensures required worker/executor systemd units are enabled + active;
|
||||
- checks worker-owned liveness JSON written by the real poll/heartbeat loop;
|
||||
- restarts an active worker only when its liveness is stale;
|
||||
- honors an explicit maintenance inhibit file;
|
||||
- writes a bounded status JSON under /run for observability.
|
||||
|
||||
Idle liveness is the successful poll loop itself. Busy liveness is refreshed by the
|
||||
Task lease-heartbeat thread, so long-running Tasks are not mistaken for hung workers.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import shlex
|
||||
import subprocess
|
||||
import tempfile
|
||||
import time
|
||||
from typing import Any, Callable, Mapping, Sequence
|
||||
|
||||
SCHEMA = "aios.worker-availability.status.v1"
|
||||
DEFAULT_WORKER_UNITS = (
|
||||
"aios-online-agent-worker-20260815.service",
|
||||
"aios-hermes-online-agent-worker.service",
|
||||
"aios-openclaw-online-agent-worker.service",
|
||||
)
|
||||
DEFAULT_DEPENDENCY_UNITS = (
|
||||
"aios-external-agent-executor.service",
|
||||
)
|
||||
DEFAULT_RUN_ROOT = Path("/run/aios-worker-availability")
|
||||
DEFAULT_STATUS = DEFAULT_RUN_ROOT / "status.json"
|
||||
DEFAULT_RECOVERY = DEFAULT_RUN_ROOT / "recovery.json"
|
||||
DEFAULT_INHIBIT = DEFAULT_RUN_ROOT / "maintenance.lock"
|
||||
DEFAULT_MAX_STALE_SECONDS = 90
|
||||
DEFAULT_RESTART_COOLDOWN_SECONDS = 60
|
||||
DEFAULT_STARTUP_WAIT_SECONDS = 10
|
||||
ACCEPTED_ENABLED_STATES = frozenset({"enabled", "enabled-runtime", "static", "indirect", "generated"})
|
||||
|
||||
|
||||
class AvailabilityGuardError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class UnitSnapshot:
|
||||
unit: str
|
||||
role: str
|
||||
load_state: str
|
||||
active_state: str
|
||||
unit_file_state: str
|
||||
enabled_ok: bool
|
||||
liveness_path: str | None = None
|
||||
liveness_state: str | None = None
|
||||
last_seen_epoch: float | None = None
|
||||
liveness_age_seconds: float | None = None
|
||||
fresh: bool | None = None
|
||||
action: str = "NONE"
|
||||
detail: str | None = None
|
||||
|
||||
|
||||
class Systemd:
|
||||
def __init__(
|
||||
self,
|
||||
runner: Callable[..., subprocess.CompletedProcess[str]] | None = None,
|
||||
) -> None:
|
||||
self.runner = runner or subprocess.run
|
||||
|
||||
def _run(self, args: Sequence[str], *, check: bool = False) -> subprocess.CompletedProcess[str]:
|
||||
result = self.runner(
|
||||
["/usr/bin/systemctl", *args],
|
||||
text=True,
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=20,
|
||||
)
|
||||
if check and result.returncode != 0:
|
||||
raise AvailabilityGuardError(
|
||||
"SYSTEMD_COMMAND_FAILED:"
|
||||
+ ":".join(args)
|
||||
+ ":"
|
||||
+ str(result.returncode)
|
||||
)
|
||||
return result
|
||||
|
||||
def property(self, unit: str, name: str) -> str:
|
||||
result = self._run(["show", unit, f"--property={name}", "--value"])
|
||||
if result.returncode != 0:
|
||||
return ""
|
||||
return result.stdout.strip()
|
||||
|
||||
def environment(self, unit: str) -> dict[str, str]:
|
||||
text = self.property(unit, "Environment")
|
||||
result: dict[str, str] = {}
|
||||
for item in shlex.split(text):
|
||||
if "=" not in item:
|
||||
continue
|
||||
key, value = item.split("=", 1)
|
||||
result[key] = value
|
||||
return result
|
||||
|
||||
def enable(self, unit: str) -> None:
|
||||
self._run(["enable", unit], check=True)
|
||||
|
||||
def start(self, unit: str) -> None:
|
||||
self._run(["start", unit], check=True)
|
||||
|
||||
def restart(self, unit: str) -> None:
|
||||
self._run(["restart", unit], check=True)
|
||||
|
||||
|
||||
def _atomic_json(path: Path, value: Mapping[str, Any]) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True, mode=0o755)
|
||||
if path.parent.is_symlink() or path.is_symlink():
|
||||
raise AvailabilityGuardError("STATUS_PATH_SYMLINK_REJECTED")
|
||||
fd, temporary = tempfile.mkstemp(prefix=f".{path.name}.", dir=path.parent)
|
||||
try:
|
||||
os.fchmod(fd, 0o644)
|
||||
with os.fdopen(fd, "w", encoding="utf-8") as handle:
|
||||
json.dump(value, handle, ensure_ascii=False, sort_keys=True, indent=2)
|
||||
handle.write("\n")
|
||||
handle.flush()
|
||||
os.fsync(handle.fileno())
|
||||
os.replace(temporary, path)
|
||||
os.chmod(path, 0o644)
|
||||
finally:
|
||||
if os.path.exists(temporary):
|
||||
os.unlink(temporary)
|
||||
|
||||
|
||||
def _load_json(path: Path) -> dict[str, Any] | None:
|
||||
if path.is_symlink() or not path.is_file():
|
||||
return None
|
||||
try:
|
||||
value = json.loads(path.read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError):
|
||||
return None
|
||||
return dict(value) if isinstance(value, Mapping) else None
|
||||
|
||||
|
||||
def _state_root(environment: Mapping[str, str], unit: str) -> Path:
|
||||
explicit = environment.get("AIOS_WORKER_STATE_ROOT")
|
||||
if explicit:
|
||||
return Path(explicit)
|
||||
fallbacks = {
|
||||
"aios-online-agent-worker-20260815.service": Path(
|
||||
"/var/lib/aios-online-agent-worker-20260815"
|
||||
),
|
||||
"aios-hermes-online-agent-worker.service": Path(
|
||||
"/var/lib/aios-online-agent-hermes"
|
||||
),
|
||||
"aios-openclaw-online-agent-worker.service": Path(
|
||||
"/var/lib/aios-online-agent-openclaw"
|
||||
),
|
||||
}
|
||||
if unit not in fallbacks:
|
||||
raise AvailabilityGuardError("WORKER_STATE_ROOT_UNAVAILABLE:" + unit)
|
||||
return fallbacks[unit]
|
||||
|
||||
|
||||
def _liveness_path(environment: Mapping[str, str], unit: str) -> Path:
|
||||
explicit = environment.get("AIOS_WORKER_LIVENESS_PATH")
|
||||
if explicit:
|
||||
return Path(explicit)
|
||||
return _state_root(environment, unit) / "worker-liveness.json"
|
||||
|
||||
|
||||
class AvailabilityGuard:
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
systemd: Systemd | None = None,
|
||||
worker_units: Sequence[str] = DEFAULT_WORKER_UNITS,
|
||||
dependency_units: Sequence[str] = DEFAULT_DEPENDENCY_UNITS,
|
||||
status_path: Path = DEFAULT_STATUS,
|
||||
recovery_path: Path = DEFAULT_RECOVERY,
|
||||
inhibit_path: Path = DEFAULT_INHIBIT,
|
||||
max_stale_seconds: int = DEFAULT_MAX_STALE_SECONDS,
|
||||
restart_cooldown_seconds: int = DEFAULT_RESTART_COOLDOWN_SECONDS,
|
||||
startup_wait_seconds: int = DEFAULT_STARTUP_WAIT_SECONDS,
|
||||
now_fn: Callable[[], float] = time.time,
|
||||
sleep_fn: Callable[[float], None] = time.sleep,
|
||||
) -> None:
|
||||
self.systemd = systemd or Systemd()
|
||||
self.worker_units = tuple(worker_units)
|
||||
self.dependency_units = tuple(dependency_units)
|
||||
self.status_path = Path(status_path)
|
||||
self.recovery_path = Path(recovery_path)
|
||||
self.inhibit_path = Path(inhibit_path)
|
||||
self.max_stale_seconds = int(max_stale_seconds)
|
||||
self.restart_cooldown_seconds = int(restart_cooldown_seconds)
|
||||
self.startup_wait_seconds = int(startup_wait_seconds)
|
||||
self.now_fn = now_fn
|
||||
self.sleep_fn = sleep_fn
|
||||
if self.max_stale_seconds < 15:
|
||||
raise AvailabilityGuardError("MAX_STALE_SECONDS_TOO_SMALL")
|
||||
if self.restart_cooldown_seconds < 15:
|
||||
raise AvailabilityGuardError("RESTART_COOLDOWN_TOO_SMALL")
|
||||
if self.startup_wait_seconds < 0 or self.startup_wait_seconds > 60:
|
||||
raise AvailabilityGuardError("STARTUP_WAIT_INVALID")
|
||||
|
||||
def _recovery_state(self) -> dict[str, float]:
|
||||
value = _load_json(self.recovery_path) or {}
|
||||
raw = value.get("last_restart_epoch")
|
||||
if not isinstance(raw, Mapping):
|
||||
return {}
|
||||
result: dict[str, float] = {}
|
||||
for unit, epoch in raw.items():
|
||||
try:
|
||||
result[str(unit)] = float(epoch)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
return result
|
||||
|
||||
def _save_recovery_state(self, state: Mapping[str, float]) -> None:
|
||||
_atomic_json(
|
||||
self.recovery_path,
|
||||
{
|
||||
"schema": "aios.worker-availability.recovery.v1",
|
||||
"last_restart_epoch": dict(state),
|
||||
},
|
||||
)
|
||||
|
||||
def _basic_snapshot(self, unit: str, role: str) -> tuple[str, str, str, bool]:
|
||||
load = self.systemd.property(unit, "LoadState")
|
||||
active = self.systemd.property(unit, "ActiveState")
|
||||
enabled = self.systemd.property(unit, "UnitFileState")
|
||||
return load, active, enabled, enabled in ACCEPTED_ENABLED_STATES
|
||||
|
||||
def _ensure_enabled_active(self, unit: str, role: str) -> tuple[str, bool]:
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, role)
|
||||
if load != "loaded":
|
||||
raise AvailabilityGuardError("REQUIRED_UNIT_NOT_LOADED:" + unit)
|
||||
action = "NONE"
|
||||
if not enabled_ok:
|
||||
self.systemd.enable(unit)
|
||||
action = "ENABLE"
|
||||
if active != "active":
|
||||
self.systemd.start(unit)
|
||||
action = "START" if action == "NONE" else "ENABLE_START"
|
||||
return action, active == "active"
|
||||
|
||||
def _wait_for_liveness(self, path: Path) -> dict[str, Any] | None:
|
||||
deadline = self.now_fn() + self.startup_wait_seconds
|
||||
while True:
|
||||
value = _load_json(path)
|
||||
if value is not None:
|
||||
try:
|
||||
epoch = float(value.get("last_seen_epoch"))
|
||||
except (TypeError, ValueError):
|
||||
epoch = 0.0
|
||||
if epoch > 0 and self.now_fn() - epoch <= self.max_stale_seconds:
|
||||
return value
|
||||
if self.now_fn() >= deadline:
|
||||
return value
|
||||
self.sleep_fn(0.5)
|
||||
|
||||
def run(self, *, heal: bool) -> dict[str, Any]:
|
||||
now = self.now_fn()
|
||||
if self.inhibit_path.exists():
|
||||
result = {
|
||||
"schema": SCHEMA,
|
||||
"status": "MAINTENANCE_INHIBITED",
|
||||
"generated_at_epoch": now,
|
||||
"maintenance_inhibit": str(self.inhibit_path),
|
||||
"workers": [],
|
||||
"dependencies": [],
|
||||
"all_fresh": False,
|
||||
"actions": [],
|
||||
}
|
||||
_atomic_json(self.status_path, result)
|
||||
return result
|
||||
|
||||
actions: list[dict[str, str]] = []
|
||||
dependencies: list[UnitSnapshot] = []
|
||||
for unit in self.dependency_units:
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, "dependency")
|
||||
action = "NONE"
|
||||
if heal:
|
||||
if load != "loaded":
|
||||
raise AvailabilityGuardError("REQUIRED_UNIT_NOT_LOADED:" + unit)
|
||||
if not enabled_ok:
|
||||
self.systemd.enable(unit)
|
||||
action = "ENABLE"
|
||||
if active != "active":
|
||||
self.systemd.start(unit)
|
||||
action = "START" if action == "NONE" else "ENABLE_START"
|
||||
if action != "NONE":
|
||||
actions.append({"unit": unit, "action": action})
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, "dependency")
|
||||
dependencies.append(
|
||||
UnitSnapshot(
|
||||
unit=unit,
|
||||
role="dependency",
|
||||
load_state=load,
|
||||
active_state=active,
|
||||
unit_file_state=enabled,
|
||||
enabled_ok=enabled_ok,
|
||||
fresh=(active == "active"),
|
||||
action=action,
|
||||
)
|
||||
)
|
||||
|
||||
recovery = self._recovery_state()
|
||||
workers: list[UnitSnapshot] = []
|
||||
for unit in self.worker_units:
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, "worker")
|
||||
environment = self.systemd.environment(unit) if load == "loaded" else {}
|
||||
path = _liveness_path(environment, unit) if load == "loaded" else None
|
||||
action = "NONE"
|
||||
|
||||
if heal:
|
||||
if load != "loaded":
|
||||
raise AvailabilityGuardError("REQUIRED_UNIT_NOT_LOADED:" + unit)
|
||||
if not enabled_ok:
|
||||
self.systemd.enable(unit)
|
||||
action = "ENABLE"
|
||||
if active != "active":
|
||||
self.systemd.start(unit)
|
||||
action = "START" if action == "NONE" else "ENABLE_START"
|
||||
actions.append({"unit": unit, "action": action})
|
||||
if path is not None:
|
||||
self._wait_for_liveness(path)
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, "worker")
|
||||
|
||||
live = _load_json(path) if path is not None else None
|
||||
last_seen: float | None = None
|
||||
state: str | None = None
|
||||
age: float | None = None
|
||||
fresh = False
|
||||
detail: str | None = None
|
||||
if live is not None:
|
||||
state = str(live.get("state") or "")
|
||||
try:
|
||||
last_seen = float(live.get("last_seen_epoch"))
|
||||
except (TypeError, ValueError):
|
||||
last_seen = None
|
||||
if last_seen is not None:
|
||||
age = max(0.0, now - last_seen)
|
||||
fresh = age <= self.max_stale_seconds
|
||||
if live.get("agent_id") in (None, ""):
|
||||
fresh = False
|
||||
detail = "LIVENESS_AGENT_ID_MISSING"
|
||||
else:
|
||||
detail = "LIVENESS_MISSING"
|
||||
|
||||
if heal and active == "active" and not fresh:
|
||||
previous = float(recovery.get(unit, 0.0))
|
||||
if now - previous >= self.restart_cooldown_seconds:
|
||||
self.systemd.restart(unit)
|
||||
recovery[unit] = now
|
||||
action = "RESTART_STALE"
|
||||
actions.append({"unit": unit, "action": action})
|
||||
if path is not None:
|
||||
live = self._wait_for_liveness(path)
|
||||
load, active, enabled, enabled_ok = self._basic_snapshot(unit, "worker")
|
||||
if live is not None:
|
||||
state = str(live.get("state") or "")
|
||||
try:
|
||||
last_seen = float(live.get("last_seen_epoch"))
|
||||
except (TypeError, ValueError):
|
||||
last_seen = None
|
||||
if last_seen is not None:
|
||||
age = max(0.0, self.now_fn() - last_seen)
|
||||
fresh = age <= self.max_stale_seconds
|
||||
detail = None if fresh else "LIVENESS_STALE_AFTER_RESTART"
|
||||
else:
|
||||
detail = "RESTART_COOLDOWN_ACTIVE"
|
||||
|
||||
workers.append(
|
||||
UnitSnapshot(
|
||||
unit=unit,
|
||||
role="worker",
|
||||
load_state=load,
|
||||
active_state=active,
|
||||
unit_file_state=enabled,
|
||||
enabled_ok=enabled_ok,
|
||||
liveness_path=str(path) if path is not None else None,
|
||||
liveness_state=state,
|
||||
last_seen_epoch=last_seen,
|
||||
liveness_age_seconds=age,
|
||||
fresh=bool(active == "active" and enabled_ok and fresh),
|
||||
action=action,
|
||||
detail=detail,
|
||||
)
|
||||
)
|
||||
|
||||
if heal:
|
||||
self._save_recovery_state(recovery)
|
||||
|
||||
all_fresh = (
|
||||
all(item.active_state == "active" and item.enabled_ok and item.fresh for item in workers)
|
||||
and all(item.active_state == "active" for item in dependencies)
|
||||
)
|
||||
result = {
|
||||
"schema": SCHEMA,
|
||||
"status": "HEALTHY" if all_fresh else "DEGRADED",
|
||||
"generated_at_epoch": self.now_fn(),
|
||||
"max_stale_seconds": self.max_stale_seconds,
|
||||
"maintenance_inhibit": str(self.inhibit_path),
|
||||
"workers": [asdict(item) for item in workers],
|
||||
"dependencies": [asdict(item) for item in dependencies],
|
||||
"all_fresh": all_fresh,
|
||||
"actions": actions,
|
||||
}
|
||||
_atomic_json(self.status_path, result)
|
||||
return result
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
mode = parser.add_mutually_exclusive_group(required=True)
|
||||
mode.add_argument("--heal", action="store_true")
|
||||
mode.add_argument("--check", action="store_true")
|
||||
parser.add_argument("--status-file", default=str(DEFAULT_STATUS))
|
||||
parser.add_argument("--recovery-file", default=str(DEFAULT_RECOVERY))
|
||||
parser.add_argument("--inhibit-file", default=str(DEFAULT_INHIBIT))
|
||||
parser.add_argument(
|
||||
"--max-stale-seconds",
|
||||
type=int,
|
||||
default=int(
|
||||
os.environ.get(
|
||||
"AIOS_WORKER_AVAILABILITY_MAX_STALE_SECONDS",
|
||||
str(DEFAULT_MAX_STALE_SECONDS),
|
||||
)
|
||||
),
|
||||
)
|
||||
parser.add_argument(
|
||||
"--restart-cooldown-seconds",
|
||||
type=int,
|
||||
default=int(
|
||||
os.environ.get(
|
||||
"AIOS_WORKER_AVAILABILITY_RESTART_COOLDOWN_SECONDS",
|
||||
str(DEFAULT_RESTART_COOLDOWN_SECONDS),
|
||||
)
|
||||
),
|
||||
)
|
||||
args = parser.parse_args()
|
||||
guard = AvailabilityGuard(
|
||||
status_path=Path(args.status_file),
|
||||
recovery_path=Path(args.recovery_file),
|
||||
inhibit_path=Path(args.inhibit_file),
|
||||
max_stale_seconds=args.max_stale_seconds,
|
||||
restart_cooldown_seconds=args.restart_cooldown_seconds,
|
||||
)
|
||||
try:
|
||||
result = guard.run(heal=args.heal)
|
||||
except AvailabilityGuardError as exc:
|
||||
print(json.dumps({"status": "FAILED", "error": str(exc)}, sort_keys=True))
|
||||
return 20
|
||||
print(json.dumps(result, ensure_ascii=False, sort_keys=True))
|
||||
if args.check and not result.get("all_fresh"):
|
||||
return 10
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -964,6 +964,7 @@ def validate_writer_lease_request_v2(raw: Mapping[str, Any], probe: Any) -> dict
|
||||
required = {
|
||||
"schema",
|
||||
"task_id",
|
||||
"job_id",
|
||||
"repository",
|
||||
"branch_mode",
|
||||
"base_oid",
|
||||
@@ -976,6 +977,7 @@ def validate_writer_lease_request_v2(raw: Mapping[str, Any], probe: Any) -> dict
|
||||
raise ProvisioningError("LEASE_REQUEST_V2_FIELDS_REJECTED", 409)
|
||||
request = WriterLeaseRequestV2(
|
||||
task_id=str(raw["task_id"]),
|
||||
job_id=str(raw["job_id"]),
|
||||
repository=str(raw["repository"]),
|
||||
branch_mode=str(raw["branch_mode"]),
|
||||
base_oid=str(raw["base_oid"]),
|
||||
@@ -988,6 +990,7 @@ def validate_writer_lease_request_v2(raw: Mapping[str, Any], probe: Any) -> dict
|
||||
return {
|
||||
"schema": WriterLeaseRequestV2.schema,
|
||||
"task_id": request.task_id,
|
||||
"job_id": request.job_id,
|
||||
"repository": request.repository,
|
||||
"branch_mode": request.branch_mode,
|
||||
"base_oid": request.base_oid,
|
||||
|
||||
@@ -0,0 +1,456 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import datetime as dt
|
||||
import hashlib
|
||||
import json
|
||||
import sqlite3
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable, Mapping
|
||||
|
||||
UTC = dt.timezone.utc
|
||||
_ALLOWED_CONFIDENTIALITY = frozenset({"public", "tenant", "project", "private", "run"})
|
||||
_PRIVILEGED = frozenset({"*", "admin", "system.admin", "message.admin", "task.admin"})
|
||||
|
||||
|
||||
class HandoffError(RuntimeError):
|
||||
code = "HANDOFF_ERROR"
|
||||
|
||||
|
||||
class MessageScopeMismatch(HandoffError):
|
||||
code = "MESSAGE_SCOPE_MISMATCH_DENY"
|
||||
|
||||
|
||||
class ConfidentialityScopeDenied(HandoffError):
|
||||
code = "MESSAGE_CONFIDENTIALITY_SCOPE_ENFORCE"
|
||||
|
||||
|
||||
class MessageExpired(HandoffError):
|
||||
code = "MESSAGE_EXPIRED"
|
||||
|
||||
|
||||
class SequenceGap(HandoffError):
|
||||
code = "MESSAGE_SEQUENCE_GAP_DETECT"
|
||||
|
||||
|
||||
class SequenceConflict(HandoffError):
|
||||
code = "MESSAGE_SEQUENCE_CONFLICT"
|
||||
|
||||
|
||||
class IdempotencyConflict(HandoffError):
|
||||
code = "MESSAGE_IDEMPOTENCY_CONFLICT"
|
||||
|
||||
|
||||
def _utcnow() -> dt.datetime:
|
||||
return dt.datetime.now(UTC)
|
||||
|
||||
|
||||
def _iso(value: dt.datetime | str | None) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
parsed = dt.datetime.fromisoformat(value.replace("Z", "+00:00")) if isinstance(value, str) else value
|
||||
if parsed.tzinfo is None:
|
||||
parsed = parsed.replace(tzinfo=UTC)
|
||||
return parsed.astimezone(UTC).isoformat()
|
||||
|
||||
|
||||
def _canonical(value: Any) -> str:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False, default=str)
|
||||
|
||||
|
||||
def _sha(value: Any) -> str:
|
||||
return hashlib.sha256(_canonical(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _clean(value: Any) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
text = str(value).strip()
|
||||
return text or None
|
||||
|
||||
|
||||
def _tuple_scope(value: Iterable[str] | str | None) -> tuple[str, ...]:
|
||||
if value is None:
|
||||
return ()
|
||||
if isinstance(value, str):
|
||||
value = value.split(",")
|
||||
return tuple(sorted({str(item).strip() for item in value if str(item).strip()}))
|
||||
|
||||
|
||||
_SECRET_KEY = re.compile(r"(?i)(?:token|secret|password|private[_-]?key|api[_-]?key)")
|
||||
_SECRET_VALUE = re.compile(r"(?i)bearer\s+[A-Za-z0-9._~+/-]{8,}|(?:token|secret|password|api[_-]?key)\s*[:=]\s*\S+")
|
||||
_SAFE_REFERENCE = re.compile(r"^(?:systemd-credential|vault|secret-manager):[A-Za-z0-9][A-Za-z0-9._:/#-]{0,255}$")
|
||||
|
||||
|
||||
def assert_payload_secret_safe(value: Any, *, key: str = "") -> None:
|
||||
if isinstance(value, Mapping):
|
||||
for child_key, child in value.items():
|
||||
assert_payload_secret_safe(child, key=str(child_key))
|
||||
return
|
||||
if isinstance(value, (list, tuple)):
|
||||
for child in value:
|
||||
assert_payload_secret_safe(child, key=key)
|
||||
return
|
||||
if isinstance(value, (bytes, bytearray)):
|
||||
raise ValueError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
if isinstance(value, str):
|
||||
if _SECRET_VALUE.search(value):
|
||||
raise ValueError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
if _SECRET_KEY.search(key) and value and _SAFE_REFERENCE.fullmatch(value) is None:
|
||||
raise ValueError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
|
||||
|
||||
@dataclasses.dataclass(frozen=True)
|
||||
class DeliveryContext:
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
run_id: str | None = None
|
||||
capabilities: tuple[str, ...] = ()
|
||||
|
||||
@classmethod
|
||||
def from_actor(cls, actor: Any) -> "DeliveryContext":
|
||||
def get(name: str) -> Any:
|
||||
if isinstance(actor, Mapping):
|
||||
return actor.get(name)
|
||||
return getattr(actor, name, None)
|
||||
return cls(
|
||||
tenant_id=_clean(get("tenant_id")),
|
||||
user_id=_clean(get("user_id")),
|
||||
project_id=_clean(get("project_id")),
|
||||
conversation_id=_clean(get("conversation_id")),
|
||||
run_id=_clean(get("run_id")),
|
||||
capabilities=_tuple_scope(get("capabilities") or get("capability_scope")),
|
||||
)
|
||||
|
||||
@property
|
||||
def privileged(self) -> bool:
|
||||
return bool(set(self.capabilities) & _PRIVILEGED)
|
||||
|
||||
|
||||
@dataclasses.dataclass(frozen=True)
|
||||
class MessageEnvelope:
|
||||
source: str
|
||||
target: str
|
||||
message_type: str
|
||||
payload: Mapping[str, Any]
|
||||
sequence: int
|
||||
idempotency_key: str
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
task_id: str | None = None
|
||||
run_id: str | None = None
|
||||
correlation_id: str | None = None
|
||||
causation_id: str | None = None
|
||||
capability_scope: tuple[str, ...] = ()
|
||||
confidentiality_scope: str = "private"
|
||||
expires_at: str | None = None
|
||||
created_at: str = dataclasses.field(default_factory=lambda: _iso(_utcnow()) or "")
|
||||
envelope_id: str = ""
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
assert_payload_secret_safe(self.payload)
|
||||
for field in ("source", "target", "message_type", "idempotency_key", "tenant_id", "user_id",
|
||||
"project_id", "conversation_id", "task_id", "run_id", "correlation_id", "causation_id"):
|
||||
object.__setattr__(self, field, _clean(getattr(self, field)) if field not in {
|
||||
"source", "target", "message_type", "idempotency_key"
|
||||
} else (_clean(getattr(self, field)) or ""))
|
||||
object.__setattr__(self, "capability_scope", _tuple_scope(self.capability_scope))
|
||||
object.__setattr__(self, "confidentiality_scope", (_clean(self.confidentiality_scope) or "private").lower())
|
||||
object.__setattr__(self, "expires_at", _iso(self.expires_at))
|
||||
object.__setattr__(self, "created_at", _iso(self.created_at) or "")
|
||||
if not self.source or not self.target or not self.message_type or not self.idempotency_key:
|
||||
raise ValueError("MESSAGE_ENVELOPE_IDENTITY_REQUIRED")
|
||||
if not isinstance(self.sequence, int) or self.sequence < 1:
|
||||
raise ValueError("MESSAGE_SEQUENCE_MUST_BE_POSITIVE")
|
||||
if self.confidentiality_scope not in _ALLOWED_CONFIDENTIALITY:
|
||||
raise ValueError("MESSAGE_CONFIDENTIALITY_SCOPE_INVALID")
|
||||
if self.confidentiality_scope != "public" and self.tenant_id is None:
|
||||
raise ValueError("MESSAGE_TENANT_REQUIRED")
|
||||
if self.confidentiality_scope in {"project", "private", "run"} and self.project_id is None:
|
||||
raise ValueError("MESSAGE_PROJECT_REQUIRED")
|
||||
if self.confidentiality_scope in {"private", "run"} and self.user_id is None:
|
||||
raise ValueError("MESSAGE_USER_REQUIRED")
|
||||
if self.confidentiality_scope == "run" and self.run_id is None:
|
||||
raise ValueError("MESSAGE_RUN_REQUIRED")
|
||||
expected = stable_event_id(
|
||||
source=self.source, target=self.target, message_type=self.message_type, payload=self.payload,
|
||||
tenant_id=self.tenant_id, user_id=self.user_id, project_id=self.project_id,
|
||||
conversation_id=self.conversation_id, task_id=self.task_id, run_id=self.run_id,
|
||||
correlation_id=self.correlation_id, causation_id=self.causation_id,
|
||||
sequence=self.sequence, idempotency_key=self.idempotency_key,
|
||||
)
|
||||
if self.envelope_id and self.envelope_id != expected:
|
||||
raise ValueError("MESSAGE_ENVELOPE_ID_MISMATCH")
|
||||
object.__setattr__(self, "envelope_id", expected)
|
||||
|
||||
@property
|
||||
def payload_sha256(self) -> str:
|
||||
return _sha(self.payload)
|
||||
|
||||
@property
|
||||
def stream_key(self) -> str:
|
||||
return _sha({
|
||||
"tenant_id": self.tenant_id, "source": self.source, "target": self.target,
|
||||
"conversation_id": self.conversation_id, "task_id": self.task_id, "run_id": self.run_id,
|
||||
})
|
||||
|
||||
def is_expired(self, *, now: dt.datetime | None = None) -> bool:
|
||||
if self.expires_at is None:
|
||||
return False
|
||||
return dt.datetime.fromisoformat(self.expires_at) <= (now or _utcnow()).astimezone(UTC)
|
||||
|
||||
def as_record(self) -> dict[str, Any]:
|
||||
return {
|
||||
"envelope_id": self.envelope_id, "stream_key": self.stream_key, "source": self.source,
|
||||
"target": self.target, "message_type": self.message_type, "payload_json": _canonical(self.payload),
|
||||
"payload_sha256": self.payload_sha256, "tenant_id": self.tenant_id, "user_id": self.user_id,
|
||||
"project_id": self.project_id, "conversation_id": self.conversation_id, "task_id": self.task_id,
|
||||
"run_id": self.run_id, "correlation_id": self.correlation_id,
|
||||
"causation_id": self.causation_id, "sequence": self.sequence,
|
||||
"capability_scope_json": _canonical(self.capability_scope),
|
||||
"confidentiality_scope": self.confidentiality_scope, "idempotency_key": self.idempotency_key,
|
||||
"expires_at": self.expires_at, "created_at": self.created_at,
|
||||
}
|
||||
|
||||
|
||||
def stable_event_id(*, source: Any, target: Any, message_type: Any, payload: Any,
|
||||
tenant_id: Any = None, user_id: Any = None, project_id: Any = None,
|
||||
conversation_id: Any = None, task_id: Any = None, run_id: Any = None,
|
||||
correlation_id: Any = None, causation_id: Any = None,
|
||||
sequence: Any = None, idempotency_key: Any = None) -> str:
|
||||
assert_payload_secret_safe(payload)
|
||||
material = {
|
||||
"source": _clean(source), "target": _clean(target), "message_type": _clean(message_type),
|
||||
"payload_sha256": _sha(payload), "tenant_id": _clean(tenant_id), "user_id": _clean(user_id),
|
||||
"project_id": _clean(project_id), "conversation_id": _clean(conversation_id),
|
||||
"task_id": _clean(task_id), "run_id": _clean(run_id), "causation_id": _clean(causation_id),
|
||||
"sequence": sequence, "idempotency_key": _clean(idempotency_key),
|
||||
}
|
||||
# Preserve historical envelope IDs for legacy rows that predate correlation_id.
|
||||
if _clean(correlation_id) is not None:
|
||||
material["correlation_id"] = _clean(correlation_id)
|
||||
return _sha(material)
|
||||
|
||||
|
||||
def bind_envelope_scope(envelope: MessageEnvelope, actor: Any) -> MessageEnvelope:
|
||||
ctx = DeliveryContext.from_actor(actor)
|
||||
if ctx.privileged:
|
||||
return envelope
|
||||
if ctx.tenant_id is None:
|
||||
if envelope.tenant_id is not None:
|
||||
raise MessageScopeMismatch(MessageScopeMismatch.code)
|
||||
return envelope
|
||||
updates: dict[str, Any] = {}
|
||||
for field in ("tenant_id", "user_id", "project_id", "conversation_id", "run_id"):
|
||||
trusted = getattr(ctx, field)
|
||||
requested = getattr(envelope, field)
|
||||
if requested is not None and requested != trusted:
|
||||
raise MessageScopeMismatch(f"{MessageScopeMismatch.code}:{field}")
|
||||
if requested is None and trusted is not None:
|
||||
updates[field] = trusted
|
||||
if not updates:
|
||||
return envelope
|
||||
data = dataclasses.asdict(envelope)
|
||||
data.update(updates)
|
||||
data["envelope_id"] = ""
|
||||
return MessageEnvelope(**data)
|
||||
|
||||
|
||||
def authorize_delivery(actor: Any, envelope: MessageEnvelope) -> None:
|
||||
ctx = DeliveryContext.from_actor(actor)
|
||||
if ctx.privileged:
|
||||
return
|
||||
if not set(envelope.capability_scope).issubset(set(ctx.capabilities)):
|
||||
raise ConfidentialityScopeDenied(f"{ConfidentialityScopeDenied.code}:capability")
|
||||
if envelope.confidentiality_scope == "public":
|
||||
return
|
||||
if ctx.tenant_id != envelope.tenant_id:
|
||||
raise MessageScopeMismatch(f"{MessageScopeMismatch.code}:tenant_id")
|
||||
if envelope.confidentiality_scope in {"project", "private", "run"} and ctx.project_id != envelope.project_id:
|
||||
raise ConfidentialityScopeDenied(f"{ConfidentialityScopeDenied.code}:project_id")
|
||||
if envelope.confidentiality_scope in {"private", "run"} and ctx.user_id != envelope.user_id:
|
||||
raise ConfidentialityScopeDenied(f"{ConfidentialityScopeDenied.code}:user_id")
|
||||
if envelope.confidentiality_scope == "run" and ctx.run_id != envelope.run_id:
|
||||
raise ConfidentialityScopeDenied(f"{ConfidentialityScopeDenied.code}:run_id")
|
||||
|
||||
|
||||
_SCHEMA = """
|
||||
CREATE TABLE IF NOT EXISTS message_handoff (
|
||||
envelope_id TEXT PRIMARY KEY,
|
||||
stream_key TEXT NOT NULL,
|
||||
source TEXT NOT NULL,
|
||||
target TEXT NOT NULL,
|
||||
message_type TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
payload_sha256 TEXT NOT NULL,
|
||||
tenant_id TEXT,
|
||||
user_id TEXT,
|
||||
project_id TEXT,
|
||||
conversation_id TEXT,
|
||||
task_id TEXT,
|
||||
run_id TEXT,
|
||||
correlation_id TEXT,
|
||||
causation_id TEXT,
|
||||
sequence INTEGER NOT NULL CHECK(sequence >= 1),
|
||||
capability_scope_json TEXT NOT NULL,
|
||||
confidentiality_scope TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL,
|
||||
expires_at TEXT,
|
||||
created_at TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'PENDING',
|
||||
delivered_at TEXT,
|
||||
acked_at TEXT,
|
||||
UNIQUE(stream_key, idempotency_key),
|
||||
UNIQUE(stream_key, sequence)
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS idx_message_handoff_target_status
|
||||
ON message_handoff(target, status, created_at);
|
||||
CREATE INDEX IF NOT EXISTS idx_message_handoff_scope
|
||||
ON message_handoff(tenant_id, project_id, user_id, conversation_id, run_id);
|
||||
"""
|
||||
|
||||
|
||||
class DurableHandoffStore:
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with self._connect() as conn:
|
||||
conn.executescript(_SCHEMA)
|
||||
columns = {str(row[1]) for row in conn.execute("PRAGMA table_info(message_handoff)")}
|
||||
if "correlation_id" not in columns:
|
||||
conn.execute("ALTER TABLE message_handoff ADD COLUMN correlation_id TEXT")
|
||||
conn.execute(
|
||||
"CREATE INDEX IF NOT EXISTS idx_message_handoff_lineage "
|
||||
"ON message_handoff(correlation_id, causation_id)"
|
||||
)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
conn = sqlite3.connect(self.path, timeout=30.0)
|
||||
conn.row_factory = sqlite3.Row
|
||||
conn.execute("PRAGMA foreign_keys=ON")
|
||||
conn.execute("PRAGMA busy_timeout=30000")
|
||||
return conn
|
||||
|
||||
@staticmethod
|
||||
def _from_row(row: sqlite3.Row) -> MessageEnvelope:
|
||||
return MessageEnvelope(
|
||||
source=row["source"], target=row["target"], message_type=row["message_type"],
|
||||
payload=json.loads(row["payload_json"]), tenant_id=row["tenant_id"], user_id=row["user_id"],
|
||||
project_id=row["project_id"], conversation_id=row["conversation_id"], task_id=row["task_id"],
|
||||
run_id=row["run_id"], correlation_id=row["correlation_id"],
|
||||
causation_id=row["causation_id"], sequence=int(row["sequence"]),
|
||||
capability_scope=tuple(json.loads(row["capability_scope_json"])),
|
||||
confidentiality_scope=row["confidentiality_scope"], idempotency_key=row["idempotency_key"],
|
||||
expires_at=row["expires_at"], created_at=row["created_at"], envelope_id=row["envelope_id"],
|
||||
)
|
||||
|
||||
def put(self, envelope: MessageEnvelope) -> tuple[str, MessageEnvelope]:
|
||||
if envelope.is_expired():
|
||||
raise MessageExpired(MessageExpired.code)
|
||||
record = envelope.as_record()
|
||||
with self._connect() as conn:
|
||||
conn.execute("BEGIN IMMEDIATE")
|
||||
replay = conn.execute(
|
||||
"SELECT * FROM message_handoff WHERE stream_key=? AND idempotency_key=?",
|
||||
(envelope.stream_key, envelope.idempotency_key),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
existing = self._from_row(replay)
|
||||
if existing.envelope_id != envelope.envelope_id or existing.payload_sha256 != envelope.payload_sha256:
|
||||
raise IdempotencyConflict(IdempotencyConflict.code)
|
||||
conn.commit()
|
||||
return "REPLAY", existing
|
||||
seq = conn.execute(
|
||||
"SELECT * FROM message_handoff WHERE stream_key=? AND sequence=?",
|
||||
(envelope.stream_key, envelope.sequence),
|
||||
).fetchone()
|
||||
if seq is not None:
|
||||
existing = self._from_row(seq)
|
||||
if existing.envelope_id == envelope.envelope_id:
|
||||
conn.commit()
|
||||
return "REPLAY", existing
|
||||
raise SequenceConflict(SequenceConflict.code)
|
||||
maximum = int(conn.execute(
|
||||
"SELECT COALESCE(MAX(sequence),0) FROM message_handoff WHERE stream_key=?",
|
||||
(envelope.stream_key,),
|
||||
).fetchone()[0])
|
||||
expected = maximum + 1
|
||||
if envelope.sequence != expected:
|
||||
raise SequenceGap(f"{SequenceGap.code}:expected={expected}:actual={envelope.sequence}")
|
||||
columns = tuple(record)
|
||||
placeholders = ",".join("?" for _ in columns)
|
||||
conn.execute(
|
||||
f"INSERT INTO message_handoff ({','.join(columns)}) VALUES ({placeholders})",
|
||||
tuple(record[column] for column in columns),
|
||||
)
|
||||
conn.commit()
|
||||
return "CREATED", envelope
|
||||
|
||||
def get(self, envelope_id: str, *, actor: Any) -> MessageEnvelope:
|
||||
with self._connect() as conn:
|
||||
row = conn.execute("SELECT * FROM message_handoff WHERE envelope_id=?", (envelope_id,)).fetchone()
|
||||
if row is None:
|
||||
raise KeyError(envelope_id)
|
||||
envelope = self._from_row(row)
|
||||
if envelope.is_expired():
|
||||
conn.execute("UPDATE message_handoff SET status='EXPIRED' WHERE envelope_id=?", (envelope_id,))
|
||||
conn.commit()
|
||||
raise MessageExpired(MessageExpired.code)
|
||||
authorize_delivery(actor, envelope)
|
||||
return envelope
|
||||
|
||||
def pending(self, *, target: str, actor: Any, limit: int = 100) -> list[MessageEnvelope]:
|
||||
if not 1 <= limit <= 1000:
|
||||
raise ValueError("MESSAGE_PENDING_LIMIT_INVALID")
|
||||
visible: list[MessageEnvelope] = []
|
||||
with self._connect() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM message_handoff WHERE target=? AND status='PENDING' ORDER BY created_at, sequence LIMIT ?",
|
||||
(target, limit),
|
||||
).fetchall()
|
||||
for row in rows:
|
||||
envelope = self._from_row(row)
|
||||
if envelope.is_expired():
|
||||
conn.execute("UPDATE message_handoff SET status='EXPIRED' WHERE envelope_id=?", (envelope.envelope_id,))
|
||||
continue
|
||||
try:
|
||||
authorize_delivery(actor, envelope)
|
||||
except HandoffError:
|
||||
continue
|
||||
visible.append(envelope)
|
||||
conn.commit()
|
||||
return visible
|
||||
|
||||
def mark_delivered(self, envelope_id: str, *, actor: Any) -> MessageEnvelope:
|
||||
envelope = self.get(envelope_id, actor=actor)
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"UPDATE message_handoff SET status='DELIVERED', delivered_at=? "
|
||||
"WHERE envelope_id=? AND status='PENDING'",
|
||||
(_iso(_utcnow()), envelope_id),
|
||||
)
|
||||
conn.commit()
|
||||
return envelope
|
||||
|
||||
def acknowledge(self, envelope_id: str, *, actor: Any) -> MessageEnvelope:
|
||||
envelope = self.get(envelope_id, actor=actor)
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"UPDATE message_handoff SET status='ACKED', acked_at=? WHERE envelope_id=?",
|
||||
(_iso(_utcnow()), envelope_id),
|
||||
)
|
||||
conn.commit()
|
||||
return envelope
|
||||
|
||||
|
||||
class HandoffFabric:
|
||||
def __init__(self, store: DurableHandoffStore) -> None:
|
||||
self.store = store
|
||||
|
||||
def publish(self, envelope: MessageEnvelope, *, actor: Any | None = None) -> tuple[str, MessageEnvelope]:
|
||||
return self.store.put(bind_envelope_scope(envelope, actor) if actor is not None else envelope)
|
||||
@@ -0,0 +1,68 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Mapping
|
||||
|
||||
from message_handoff import MessageEnvelope
|
||||
|
||||
|
||||
def _get(value: Any, *names: str, default: Any = None) -> Any:
|
||||
for name in names:
|
||||
if isinstance(value, Mapping) and name in value:
|
||||
return value[name]
|
||||
if hasattr(value, name):
|
||||
return getattr(value, name)
|
||||
return default
|
||||
|
||||
|
||||
def agent_event_to_envelope(event: Any, *, target: str | None = None, sequence: int = 1,
|
||||
idempotency_key: str | None = None, **scope: Any) -> MessageEnvelope:
|
||||
payload = _get(event, "payload", "data", default={}) or {}
|
||||
target = target or _get(event, "target", "recipient")
|
||||
if not target:
|
||||
raise ValueError("MESSAGE_TARGET_REQUIRED")
|
||||
return MessageEnvelope(
|
||||
source=str(_get(event, "source", "producer", "agent_id", default="agent-event")),
|
||||
target=str(target),
|
||||
message_type=str(_get(event, "event_type", "type", "message_type", default="agent.event")),
|
||||
payload=dict(payload),
|
||||
sequence=sequence,
|
||||
idempotency_key=idempotency_key or str(_get(event, "id", "event_id", default="")) or f"agent-event:{sequence}",
|
||||
causation_id=_get(event, "causation_id"),
|
||||
**scope,
|
||||
)
|
||||
|
||||
|
||||
def taskplane_event_to_envelope(event: Any, *, target: str, sequence: int = 1,
|
||||
idempotency_key: str | None = None, **scope: Any) -> MessageEnvelope:
|
||||
data = _get(event, "data", "payload", default={}) or {}
|
||||
event_id = str(_get(event, "id", "event_id", default=""))
|
||||
return MessageEnvelope(
|
||||
source=str(_get(event, "source", default="task-plane")),
|
||||
target=target,
|
||||
message_type=str(_get(event, "type", "event_type", default="task.event")),
|
||||
payload=dict(data),
|
||||
sequence=sequence,
|
||||
idempotency_key=idempotency_key or event_id or f"task-event:{sequence}",
|
||||
causation_id=event_id or None,
|
||||
**scope,
|
||||
)
|
||||
|
||||
|
||||
def legacy_message_to_envelope(message: Any, *, target: str | None = None, sequence: int = 1,
|
||||
idempotency_key: str | None = None, **scope: Any) -> MessageEnvelope:
|
||||
payload = _get(message, "payload", "data", "body", "content", default={})
|
||||
if not isinstance(payload, Mapping):
|
||||
payload = {"value": payload}
|
||||
target = target or _get(message, "target", "recipient", "receiver")
|
||||
if not target:
|
||||
raise ValueError("MESSAGE_TARGET_REQUIRED")
|
||||
source = _get(message, "source", "sender", "agent_id", default="legacy-message-bus")
|
||||
kind = _get(message, "message_type", "type", "kind", default="legacy.message")
|
||||
identifier = _get(message, "id", "message_id", "event_id")
|
||||
return MessageEnvelope(
|
||||
source=str(source), target=str(target), message_type=str(kind), payload=dict(payload),
|
||||
sequence=sequence,
|
||||
idempotency_key=idempotency_key or (str(identifier) if identifier else f"legacy:{sequence}"),
|
||||
causation_id=str(identifier) if identifier else None,
|
||||
**scope,
|
||||
)
|
||||
@@ -11,6 +11,7 @@ from dataclasses import asdict, dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from .search_gateway_orchestrator import SearchGatewayOrchestrator
|
||||
from .trace_tool_credential_governance import GovernanceActor, TraceContext
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -43,6 +44,9 @@ class SearchGatewayAgentAdapter:
|
||||
domain_profiles: list[str] | None = None,
|
||||
user_scope: str = "public",
|
||||
correlation_id: str | None = None,
|
||||
*,
|
||||
actor: GovernanceActor | dict[str, Any] | None = None,
|
||||
trace: TraceContext | None = None,
|
||||
) -> dict[str, Any]:
|
||||
payload = {
|
||||
"query": query,
|
||||
@@ -59,7 +63,11 @@ class SearchGatewayAgentAdapter:
|
||||
"session_profile": context.session_profile,
|
||||
"correlation_id": correlation_id,
|
||||
}
|
||||
return self.orchestrator.execute(payload)
|
||||
if actor is None and trace is None:
|
||||
# Preserve adapter compatibility; the governed orchestrator itself
|
||||
# still fails closed when trusted context is absent.
|
||||
return self.orchestrator.execute(payload)
|
||||
return self.orchestrator.execute(payload, actor=actor, trace=trace)
|
||||
|
||||
|
||||
class OpenClawSearchClient(SearchGatewayAgentAdapter):
|
||||
|
||||
@@ -13,10 +13,18 @@ from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
import hashlib
|
||||
import json
|
||||
from typing import Any, Protocol
|
||||
from uuid import uuid4
|
||||
|
||||
from .search_profile_resolver import DomainQueryProfileRegistry, SearchProfile, SearchProfileResolver
|
||||
from .trace_tool_credential_governance import (
|
||||
GovernanceActor,
|
||||
GovernanceError,
|
||||
GovernanceStore,
|
||||
TraceContext,
|
||||
)
|
||||
|
||||
|
||||
def utc_now() -> str:
|
||||
@@ -156,13 +164,25 @@ class SearchPolicyGuard:
|
||||
|
||||
|
||||
class SearchGateway:
|
||||
def __init__(self, providers: list[SearchProvider] | None = None):
|
||||
def __init__(self, providers: list[SearchProvider] | None = None, *, governance_store: GovernanceStore | None = None):
|
||||
self.providers = providers or []
|
||||
self.governance_store = governance_store
|
||||
self.profile_resolver = SearchProfileResolver()
|
||||
self.planner = QueryPlanner()
|
||||
self.guard = SearchPolicyGuard()
|
||||
|
||||
def search(self, request: SearchRequest) -> SearchResponse:
|
||||
def search(self, request: SearchRequest, *, actor: GovernanceActor | dict[str, Any] | None = None, trace: TraceContext | None = None) -> SearchResponse:
|
||||
trusted_actor: GovernanceActor | None = None
|
||||
if self.governance_store is not None:
|
||||
if actor is None or trace is None:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
trusted_actor = GovernanceActor.from_value(actor)
|
||||
if request.requester != trusted_actor.identity:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY", field="requester")
|
||||
if request.correlation_id is not None and request.correlation_id not in {
|
||||
trace.trace_id, trace.correlation_id
|
||||
}:
|
||||
raise GovernanceError("TOOL_SCOPE_PROPAGATION", field="correlation_id")
|
||||
request_id = request.correlation_id or f"search_{uuid4().hex[:12]}"
|
||||
profile = self.profile_resolver.resolve(request.group_profile, request.user_profile, request.session_profile)
|
||||
expanded_queries = self.planner.expand(request, profile)
|
||||
@@ -184,14 +204,60 @@ class SearchGateway:
|
||||
attempts: list[SearchProviderAttempt] = []
|
||||
providers = self._ordered_providers(profile)
|
||||
for provider in providers:
|
||||
if request.authorized_sources and provider.name not in request.authorized_sources:
|
||||
attempts.append(SearchProviderAttempt(provider=provider.name, status="denied", reason="SOURCE_AUTHZ_DENY"))
|
||||
continue
|
||||
if request.user_scope != "public" and provider.name not in request.authorized_sources:
|
||||
attempts.append(SearchProviderAttempt(provider=provider.name, status="denied", reason="SOURCE_AUTHZ_REQUIRED"))
|
||||
continue
|
||||
try:
|
||||
if self.governance_store is not None:
|
||||
assert trusted_actor is not None and trace is not None
|
||||
input_digest = hashlib.sha256(
|
||||
json.dumps(
|
||||
{"query": request.query, "intent": request.intent, "provider": provider.name},
|
||||
sort_keys=True, separators=(",", ":"), ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
).hexdigest()
|
||||
invocation_key = hashlib.sha256(
|
||||
f"{trace.trace_id}:{trace.span_id}:{provider.name}:{input_digest}".encode("utf-8")
|
||||
).hexdigest()
|
||||
authorization = self.governance_store.authorize_tool(
|
||||
actor=trusted_actor,
|
||||
tool_name=f"search.{provider.name}",
|
||||
trace=trace,
|
||||
requested_scope=trace.scope,
|
||||
input_digest=input_digest,
|
||||
invocation_key=invocation_key,
|
||||
)
|
||||
if authorization.get("idempotent"):
|
||||
raise GovernanceError("TOOL_INVOCATION_REPLAY")
|
||||
provider_evidence, attempt = provider.search(request, expanded_queries)
|
||||
if self.governance_store is not None:
|
||||
result_digest = hashlib.sha256(
|
||||
json.dumps(
|
||||
{
|
||||
"evidence": [item.to_dict() for item in provider_evidence],
|
||||
"attempt": attempt.to_dict(),
|
||||
},
|
||||
sort_keys=True, separators=(",", ":"), ensure_ascii=False,
|
||||
).encode("utf-8")
|
||||
).hexdigest()
|
||||
self.governance_store.record_tool_receipt(
|
||||
invocation_key=invocation_key,
|
||||
result_digest=result_digest,
|
||||
actor=trusted_actor,
|
||||
trace=trace,
|
||||
)
|
||||
evidence.extend(provider_evidence)
|
||||
attempts.append(attempt)
|
||||
if provider_evidence:
|
||||
break
|
||||
except Exception as exc:
|
||||
attempts.append(SearchProviderAttempt(provider=getattr(provider, "name", "unknown"), status="failed", reason=str(exc)))
|
||||
except GovernanceError:
|
||||
raise
|
||||
except Exception:
|
||||
# Provider exceptions may contain URLs, tokens, or local paths.
|
||||
attempts.append(SearchProviderAttempt(provider=getattr(provider, "name", "unknown"), status="failed", reason="PROVIDER_FAILURE"))
|
||||
|
||||
if evidence:
|
||||
return SearchResponse(
|
||||
|
||||
@@ -7,27 +7,29 @@ try:
|
||||
except Exception:
|
||||
APIRouter = None
|
||||
|
||||
from .search_gateway import SearchGateway, SearchRequest
|
||||
from .search_gateway import SearchRequest
|
||||
from .search_gateway_orchestrator import SearchGatewayOrchestrator
|
||||
from .trace_tool_credential_governance import GovernanceActor, TraceContext
|
||||
from .search_gateway_dashboard import SearchGatewayDashboard
|
||||
|
||||
|
||||
gateway = SearchGateway()
|
||||
orchestrator = SearchGatewayOrchestrator()
|
||||
dashboard = SearchGatewayDashboard()
|
||||
|
||||
|
||||
def search_gateway_request(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
request = SearchRequest(**payload)
|
||||
return gateway.search(request).to_dict()
|
||||
def search_gateway_request(payload: dict[str, Any], *, actor: GovernanceActor | dict[str, Any] | None = None, trace: TraceContext | None = None) -> dict[str, Any]:
|
||||
return orchestrator.execute(payload, actor=actor, trace=trace)
|
||||
|
||||
|
||||
def get_search_gateway_status() -> dict[str, Any]:
|
||||
return {
|
||||
"module": "search-gateway",
|
||||
"status": "ready",
|
||||
"providers_configured": len(gateway.providers),
|
||||
"providers_configured": len(orchestrator.gateway.providers),
|
||||
"policy_guard": "enabled",
|
||||
"profile_customization": "enabled",
|
||||
"fallback_required_when_provider_unavailable": True,
|
||||
"governance": "required",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -3,24 +3,49 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
import os
|
||||
|
||||
from .search_audit_store import SearchAuditStore
|
||||
from .search_event_bridge import SearchEventBridge
|
||||
from .search_gateway import SearchGateway, SearchRequest
|
||||
from .search_provider_registry import SearchProviderRegistry
|
||||
from .trace_tool_credential_governance import (
|
||||
GovernanceActor,
|
||||
GovernanceScope,
|
||||
GovernanceStore,
|
||||
ToolDescriptor,
|
||||
TraceContext,
|
||||
)
|
||||
|
||||
|
||||
class SearchGatewayOrchestrator:
|
||||
def __init__(self):
|
||||
def __init__(self, *, governance_store: GovernanceStore | None = None):
|
||||
self.registry = SearchProviderRegistry()
|
||||
self.audit = SearchAuditStore()
|
||||
self.events = SearchEventBridge()
|
||||
self.gateway = SearchGateway(self.registry.ordered())
|
||||
self.governance = governance_store or GovernanceStore(
|
||||
os.environ.get("AIOS_SEARCH_GOVERNANCE_DB", "runtime/search-governance.sqlite3")
|
||||
)
|
||||
registrar = GovernanceActor(
|
||||
"search-runtime-bootstrap", GovernanceScope("system"), ("system.admin",)
|
||||
)
|
||||
for provider in self.registry.ordered():
|
||||
self.governance.register_tool(
|
||||
ToolDescriptor(
|
||||
f"search.{provider.name}", "tool", GovernanceScope("global"), ("tool.search",)
|
||||
),
|
||||
registrar,
|
||||
)
|
||||
self.gateway = SearchGateway(self.registry.ordered(), governance_store=self.governance)
|
||||
|
||||
def execute(self, payload: dict[str, Any]) -> dict[str, Any]:
|
||||
def execute(self, payload: dict[str, Any], *, actor: GovernanceActor | dict[str, Any] | None = None, trace: TraceContext | None = None) -> dict[str, Any]:
|
||||
if actor is None or trace is None:
|
||||
from .trace_tool_credential_governance import GovernanceError
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
self.governance.record_trace(trace, actor)
|
||||
request = SearchRequest(**payload)
|
||||
self.events.search_started(request.to_dict())
|
||||
response = self.gateway.search(request)
|
||||
response = self.gateway.search(request, actor=actor, trace=trace)
|
||||
result = response.to_dict()
|
||||
for attempt in result.get("attempts", []):
|
||||
self.events.provider_attempted(result["request_id"], attempt)
|
||||
@@ -35,6 +60,7 @@ class SearchGatewayOrchestrator:
|
||||
"registry": self.registry.status(),
|
||||
"audit": "enabled",
|
||||
"events": "enabled",
|
||||
"governance": "required",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -34,6 +34,7 @@ from .models import (
|
||||
)
|
||||
from .policy import PolicyEngine
|
||||
from .store import TaskPlaneStore
|
||||
from .scope import bind_task_scope
|
||||
from .worker_registry import WorkerRegistry
|
||||
|
||||
|
||||
@@ -68,28 +69,54 @@ class TaskPlaneService:
|
||||
self.delegation = DelegationEngine(store)
|
||||
self.store.probe_attestation_verifier = self.policy.probe_attestation_verifier
|
||||
|
||||
def create_task(self, body: dict[str, Any], idempotency_key: str | None = None) -> dict[str, Any]:
|
||||
def _authorized_task(self, task_id: str, actor: str, action: str) -> TaskRecord:
|
||||
task = self.store.get_task(task_id, self.policy.actor_context(actor))
|
||||
self.policy.assert_allowed(action, actor, task=task)
|
||||
return task
|
||||
|
||||
def create_task(
|
||||
self,
|
||||
body: dict[str, Any],
|
||||
idempotency_key: str | None = None,
|
||||
*,
|
||||
actor_identity: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
if body.get("parent_task_id"):
|
||||
raise ForbiddenError("child tasks must use the delegate endpoint")
|
||||
issuer = body.get("issuer", {})
|
||||
actor = issuer.get("id", "anon") if isinstance(issuer, dict) else "anon"
|
||||
declared_actor = issuer.get("id", "anon") if isinstance(issuer, dict) else "anon"
|
||||
actor = actor_identity or declared_actor
|
||||
self.policy.assert_allowed("create", actor)
|
||||
try:
|
||||
plan = TaskPlan.from_dict(body)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError("invalid task plan") from exc
|
||||
if actor_identity is not None:
|
||||
plan = bind_task_scope(
|
||||
plan, self.policy.actor_context(actor_identity), public_create=True
|
||||
)
|
||||
task = self.store.create_task_with_event(plan, idempotency_key=idempotency_key)
|
||||
return task.to_dict()
|
||||
|
||||
def list_tasks(self, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
context = None
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor)
|
||||
return [task.to_dict(include_task=False) for task in self.store.list_tasks()]
|
||||
context = self.policy.actor_context(actor)
|
||||
return [
|
||||
task.to_dict(include_task=False)
|
||||
for task in self.store.list_tasks(context)
|
||||
]
|
||||
|
||||
def get_task(self, task_id: str, actor: str | None = None) -> dict[str, Any]:
|
||||
context = None
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
|
||||
return self.store.get_task(task_id).to_dict()
|
||||
self.policy.assert_allowed("read", actor)
|
||||
context = self.policy.actor_context(actor)
|
||||
task = self.store.get_task(task_id, context)
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor, task=task)
|
||||
return task.to_dict()
|
||||
|
||||
def get_worker(self, worker_id: str, actor: str | None = None) -> dict[str, Any]:
|
||||
if actor is not None:
|
||||
@@ -163,9 +190,8 @@ class TaskPlaneService:
|
||||
if not worker_id:
|
||||
raise ValidationError("worker_id required")
|
||||
|
||||
task = self.store.get_task(task_id)
|
||||
task = self._authorized_task(task_id, actor, "claim")
|
||||
self.policy.assert_readonly_worker_binding(actor, str(worker_id))
|
||||
self.policy.assert_allowed("claim", actor, task=task)
|
||||
lease_seconds = _bounded_int(
|
||||
body.get("lease_seconds", 30), "lease_seconds", 1, 3600
|
||||
)
|
||||
@@ -184,10 +210,9 @@ class TaskPlaneService:
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
task = self.store.get_task(task_id)
|
||||
task = self._authorized_task(task_id, actor, "heartbeat")
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("heartbeat", actor, task=task)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
lease_seconds = _bounded_int(
|
||||
@@ -206,10 +231,9 @@ class TaskPlaneService:
|
||||
message = body.get("message")
|
||||
if progress is None:
|
||||
raise ValidationError("progress required")
|
||||
task = self.store.get_task(task_id)
|
||||
task = self._authorized_task(task_id, actor, "progress")
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("progress", actor, task=task)
|
||||
if task.task_plan.data_classification == "credential-secret":
|
||||
if message not in {None, ""} or contains_secret_text(stage):
|
||||
raise ValidationError(
|
||||
@@ -234,7 +258,7 @@ class TaskPlaneService:
|
||||
if not claim_id:
|
||||
raise ValidationError("claim_id required")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
task = self.store.get_task(task_id)
|
||||
task = self._authorized_task(task_id, actor, "result")
|
||||
|
||||
status = body.get("status", "COMPLETED")
|
||||
outputs = body.get("outputs", [])
|
||||
@@ -247,7 +271,6 @@ class TaskPlaneService:
|
||||
raise ValidationError("evidence items must be objects")
|
||||
claim = self.store.get_claim(claim_id)
|
||||
self.policy.assert_readonly_worker_binding(actor, claim.worker_id)
|
||||
self.policy.assert_allowed("result", actor, task=task)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
if task.task_plan.data_classification == "credential-secret":
|
||||
@@ -326,8 +349,7 @@ class TaskPlaneService:
|
||||
reason = body.get("reason", "failed")
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "worker"
|
||||
self.policy.assert_allowed("fail", actor)
|
||||
task = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("fail", actor, task=task)
|
||||
task = self._authorized_task(task_id, actor, "fail")
|
||||
claim = self.store.get_claim(claim_id)
|
||||
if claim.worker_identity != actor:
|
||||
raise ForbiddenError("claim identity mismatch")
|
||||
@@ -339,8 +361,7 @@ class TaskPlaneService:
|
||||
actor = body.get("actor_identity") or body.get("worker_identity") or "owner"
|
||||
self.policy.assert_allowed("cancel", actor)
|
||||
reason = body.get("reason", "cancelled")
|
||||
task = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("cancel", actor, task=task)
|
||||
task = self._authorized_task(task_id, actor, "cancel")
|
||||
updated = self.store.cancel_task_with_event(
|
||||
task_id, task.revision, reason=reason
|
||||
)
|
||||
@@ -349,8 +370,7 @@ class TaskPlaneService:
|
||||
def delegate(self, task_id: str, body: dict[str, Any]) -> dict[str, Any]:
|
||||
actor = body.get("actor_identity") or "owner"
|
||||
self.policy.assert_allowed("delegate", actor)
|
||||
parent = self.store.get_task(task_id)
|
||||
self.policy.assert_allowed("delegate", actor, task=parent)
|
||||
parent = self._authorized_task(task_id, actor, "delegate")
|
||||
if "task" in body:
|
||||
try:
|
||||
child_plan = TaskPlan.from_dict(body["task"])
|
||||
@@ -364,25 +384,31 @@ class TaskPlaneService:
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise ValidationError("invalid child task plan") from exc
|
||||
child_plan.parent_task_id = task_id
|
||||
child_plan = bind_task_scope(
|
||||
child_plan, self.policy.actor_context(actor), public_create=False
|
||||
)
|
||||
child = self.delegation.delegate(task_id, child_plan, caller=actor)
|
||||
return child.to_dict()
|
||||
|
||||
def get_events(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
self._authorized_task(task_id, actor, "audit")
|
||||
else:
|
||||
self.store.get_task(task_id)
|
||||
return self.store.list_events(task_id)
|
||||
|
||||
def get_evidence(self, task_id: str, actor: str | None = None) -> list[dict[str, Any]]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("audit", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
self._authorized_task(task_id, actor, "audit")
|
||||
else:
|
||||
self.store.get_task(task_id)
|
||||
return self.evidence.list(task_id)
|
||||
|
||||
def get_children(self, task_id: str, actor: str | None = None) -> list[str]:
|
||||
if actor is not None:
|
||||
self.policy.assert_allowed("read", actor, task=self.store.get_task(task_id))
|
||||
self.store.get_task(task_id)
|
||||
self._authorized_task(task_id, actor, "read")
|
||||
else:
|
||||
self.store.get_task(task_id)
|
||||
return self.store.list_children(task_id)
|
||||
|
||||
|
||||
@@ -506,7 +532,11 @@ class TaskPlaneRequestHandler(BaseHTTPRequestHandler):
|
||||
):
|
||||
raise ForbiddenError("issuer identity mismatch")
|
||||
body["issuer"] = {"type": "authenticated", "id": identity}
|
||||
return 201, self.service.create_task(body or {}, headers.get("idempotency-key"))
|
||||
return 201, self.service.create_task(
|
||||
body or {},
|
||||
headers.get("idempotency-key"),
|
||||
actor_identity=identity,
|
||||
)
|
||||
if body.get("actor_identity") not in {None, identity}:
|
||||
raise ForbiddenError("actor identity mismatch")
|
||||
body["actor_identity"] = identity
|
||||
|
||||
@@ -106,3 +106,8 @@ class DurableOutboxDispatcher:
|
||||
receipt=str(receipt) if receipt else None,
|
||||
error=None if receipt else f"{adapter.name} receipt unavailable",
|
||||
)
|
||||
|
||||
# R4.2 P0-B compatibility adapter.
|
||||
def to_handoff_envelope(event, *, target, sequence=1, idempotency_key=None, **scope):
|
||||
from message_handoff_adapters import taskplane_event_to_envelope
|
||||
return taskplane_event_to_envelope(event, target=target, sequence=sequence, idempotency_key=idempotency_key, **scope)
|
||||
|
||||
@@ -0,0 +1,911 @@
|
||||
"""Durable multi-agent fleet scheduling for TaskPlane.
|
||||
|
||||
The fleet layer decides *which* eligible worker should receive *which* queued task.
|
||||
It never replaces TaskPlane claim/lease ownership: callers must still perform the
|
||||
authoritative TaskPlane claim CAS after a reservation is returned.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from contextlib import contextmanager
|
||||
from dataclasses import dataclass
|
||||
import hashlib
|
||||
import json
|
||||
import math
|
||||
import sqlite3
|
||||
import threading
|
||||
import time
|
||||
from typing import Any, Iterable, Mapping, Sequence
|
||||
|
||||
DEFAULT_RESERVATION_SECONDS = 30
|
||||
DEFAULT_CIRCUIT_THRESHOLD = 3
|
||||
DEFAULT_CIRCUIT_SECONDS = 30
|
||||
MAX_CIRCUIT_SECONDS = 15 * 60
|
||||
MAX_SLOTS = 128
|
||||
|
||||
|
||||
class FleetError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
class FleetConflict(FleetError):
|
||||
pass
|
||||
|
||||
|
||||
def _canonical(value: object) -> bytes:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
|
||||
|
||||
|
||||
def _sha(value: object) -> str:
|
||||
return hashlib.sha256(_canonical(value)).hexdigest()
|
||||
|
||||
|
||||
def _text(value: object, default: str = "") -> str:
|
||||
if value is None:
|
||||
return default
|
||||
return str(value).strip() or default
|
||||
|
||||
|
||||
def _int(value: object, default: int, minimum: int, maximum: int) -> int:
|
||||
if value is None:
|
||||
return default
|
||||
if isinstance(value, bool):
|
||||
raise FleetError("FLEET_INTEGER_INVALID")
|
||||
try:
|
||||
result = int(value)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise FleetError("FLEET_INTEGER_INVALID") from exc
|
||||
if result < minimum or result > maximum:
|
||||
raise FleetError("FLEET_INTEGER_OUT_OF_RANGE")
|
||||
return result
|
||||
|
||||
|
||||
def _float(value: object, default: float, minimum: float, maximum: float) -> float:
|
||||
if value is None:
|
||||
return default
|
||||
try:
|
||||
result = float(value)
|
||||
except (TypeError, ValueError) as exc:
|
||||
raise FleetError("FLEET_NUMBER_INVALID") from exc
|
||||
if not math.isfinite(result) or result < minimum or result > maximum:
|
||||
raise FleetError("FLEET_NUMBER_OUT_OF_RANGE")
|
||||
return result
|
||||
|
||||
|
||||
def _mapping(value: object) -> Mapping[str, Any]:
|
||||
if isinstance(value, Mapping):
|
||||
return value
|
||||
if hasattr(value, "to_dict"):
|
||||
data = value.to_dict()
|
||||
if isinstance(data, Mapping):
|
||||
return data
|
||||
if hasattr(value, "__dict__"):
|
||||
return vars(value)
|
||||
return {}
|
||||
|
||||
|
||||
def _attr(value: object, name: str, default: Any = None) -> Any:
|
||||
if isinstance(value, Mapping):
|
||||
return value.get(name, default)
|
||||
return getattr(value, name, default)
|
||||
|
||||
|
||||
def _task_plan(task: object) -> object:
|
||||
return _attr(task, "task_plan", _attr(task, "plan", task))
|
||||
|
||||
|
||||
def _task_id(task: object) -> str:
|
||||
return _text(_attr(task, "task_id", _attr(_task_plan(task), "task_id", "")))
|
||||
|
||||
|
||||
def _task_status(task: object) -> str:
|
||||
return _text(_attr(task, "status", "")).upper()
|
||||
|
||||
|
||||
def _task_revision(task: object) -> int:
|
||||
return _int(_attr(task, "revision", 0), 0, 0, 2**31 - 1)
|
||||
|
||||
|
||||
def _task_created_at(task: object) -> float:
|
||||
value = _attr(task, "created_at", _attr(task, "updated_at", 0.0))
|
||||
try:
|
||||
return float(value or 0.0)
|
||||
except (TypeError, ValueError):
|
||||
return 0.0
|
||||
|
||||
|
||||
def _task_required_capabilities(task: object) -> frozenset[str]:
|
||||
plan = _task_plan(task)
|
||||
value = _attr(plan, "required_capabilities", ())
|
||||
if not isinstance(value, Sequence) or isinstance(value, (str, bytes)):
|
||||
return frozenset()
|
||||
return frozenset(_text(item) for item in value if _text(item))
|
||||
|
||||
|
||||
def _task_metadata(task: object) -> Mapping[str, Any]:
|
||||
plan = _task_plan(task)
|
||||
value = _attr(plan, "metadata", {})
|
||||
return value if isinstance(value, Mapping) else {}
|
||||
|
||||
|
||||
def _task_scope_key(task: object) -> str:
|
||||
plan = _task_plan(task)
|
||||
scope_type = _text(_attr(plan, "scope_type", "legacy"), "legacy")
|
||||
tenant = _text(_attr(plan, "tenant_id", ""))
|
||||
project = _text(_attr(plan, "project_id", ""))
|
||||
user = _text(_attr(plan, "user_id", ""))
|
||||
if scope_type == "tenant":
|
||||
return "tenant:" + tenant + "|project:" + (project or "*")
|
||||
if scope_type == "system":
|
||||
return "system"
|
||||
return "legacy:" + (user or "*")
|
||||
|
||||
|
||||
def _worker_id(worker: object) -> str:
|
||||
return _text(_attr(worker, "worker_id", ""))
|
||||
|
||||
|
||||
def _worker_capabilities(worker: object) -> frozenset[str]:
|
||||
value = _attr(worker, "capabilities", ())
|
||||
if isinstance(value, Mapping):
|
||||
value = value.keys()
|
||||
if not isinstance(value, Iterable) or isinstance(value, (str, bytes)):
|
||||
return frozenset()
|
||||
return frozenset(_text(item) for item in value if _text(item))
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FleetWorkerPolicy:
|
||||
worker_id: str
|
||||
max_slots: int = 1
|
||||
failure_domain: str = "default"
|
||||
weight: float = 1.0
|
||||
labels: Mapping[str, str] | None = None
|
||||
revision: int = 1
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FleetDispatchDecision:
|
||||
reservation_id: str
|
||||
task_id: str
|
||||
worker_id: str
|
||||
task_revision: int
|
||||
scope_key: str
|
||||
failure_domain: str
|
||||
reserved_until: float
|
||||
score: tuple[float, float, float, str]
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"reservation_id": self.reservation_id,
|
||||
"task_id": self.task_id,
|
||||
"worker_id": self.worker_id,
|
||||
"task_revision": self.task_revision,
|
||||
"scope_key": self.scope_key,
|
||||
"failure_domain": self.failure_domain,
|
||||
"reserved_until": self.reserved_until,
|
||||
"score": list(self.score),
|
||||
}
|
||||
|
||||
|
||||
class FleetStateStore:
|
||||
"""Small durable fleet journal colocated in the existing TaskPlane SQLite database."""
|
||||
|
||||
def __init__(self, connection: sqlite3.Connection, lock: threading.RLock | None = None) -> None:
|
||||
self.conn = connection
|
||||
self.lock = lock or threading.RLock()
|
||||
self._savepoint_counter = 0
|
||||
self._ensure_schema()
|
||||
|
||||
@contextmanager
|
||||
def _transaction(self):
|
||||
with self.lock:
|
||||
self._savepoint_counter += 1
|
||||
name = f"fleet_{threading.get_ident()}_{self._savepoint_counter}"
|
||||
self.conn.execute(f"SAVEPOINT {name}")
|
||||
try:
|
||||
yield
|
||||
except Exception:
|
||||
self.conn.execute(f"ROLLBACK TO {name}")
|
||||
self.conn.execute(f"RELEASE {name}")
|
||||
raise
|
||||
else:
|
||||
self.conn.execute(f"RELEASE {name}")
|
||||
|
||||
def _ensure_schema(self) -> None:
|
||||
with self.lock:
|
||||
self.conn.executescript(
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS fleet_worker_capacity (
|
||||
worker_id TEXT PRIMARY KEY,
|
||||
max_slots INTEGER NOT NULL,
|
||||
failure_domain TEXT NOT NULL,
|
||||
weight REAL NOT NULL,
|
||||
labels_json TEXT NOT NULL,
|
||||
revision INTEGER NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS fleet_scope_state (
|
||||
scope_key TEXT PRIMARY KEY,
|
||||
virtual_finish REAL NOT NULL,
|
||||
dispatch_count INTEGER NOT NULL,
|
||||
last_dispatched_at REAL,
|
||||
revision INTEGER NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS fleet_dispatches (
|
||||
reservation_id TEXT PRIMARY KEY,
|
||||
task_id TEXT NOT NULL UNIQUE,
|
||||
worker_id TEXT NOT NULL,
|
||||
task_revision INTEGER NOT NULL,
|
||||
scope_key TEXT NOT NULL,
|
||||
failure_domain TEXT NOT NULL,
|
||||
state TEXT NOT NULL,
|
||||
reserved_until REAL NOT NULL,
|
||||
claim_id TEXT,
|
||||
created_at REAL NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE INDEX IF NOT EXISTS ix_fleet_dispatch_worker_state
|
||||
ON fleet_dispatches(worker_id, state, reserved_until);
|
||||
CREATE TABLE IF NOT EXISTS fleet_worker_failures (
|
||||
worker_id TEXT PRIMARY KEY,
|
||||
consecutive_failures INTEGER NOT NULL,
|
||||
circuit_open_until REAL,
|
||||
last_failure_class TEXT,
|
||||
revision INTEGER NOT NULL,
|
||||
updated_at REAL NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS fleet_task_worker_failures (
|
||||
task_id TEXT NOT NULL,
|
||||
worker_id TEXT NOT NULL,
|
||||
failure_count INTEGER NOT NULL,
|
||||
blocked_until REAL,
|
||||
last_failure_class TEXT,
|
||||
revision INTEGER NOT NULL,
|
||||
updated_at REAL NOT NULL,
|
||||
PRIMARY KEY(task_id, worker_id)
|
||||
);
|
||||
"""
|
||||
)
|
||||
|
||||
def configure_worker(
|
||||
self,
|
||||
worker_id: str,
|
||||
*,
|
||||
max_slots: int = 1,
|
||||
failure_domain: str = "default",
|
||||
weight: float = 1.0,
|
||||
labels: Mapping[str, str] | None = None,
|
||||
expected_revision: int | None = None,
|
||||
now: float | None = None,
|
||||
) -> FleetWorkerPolicy:
|
||||
worker_id = _text(worker_id)
|
||||
if not worker_id:
|
||||
raise FleetError("FLEET_WORKER_ID_REQUIRED")
|
||||
max_slots = _int(max_slots, 1, 1, MAX_SLOTS)
|
||||
weight = _float(weight, 1.0, 0.05, 100.0)
|
||||
failure_domain = _text(failure_domain, "default")
|
||||
normalized_labels = {
|
||||
_text(k): _text(v)
|
||||
for k, v in dict(labels or {}).items()
|
||||
if _text(k) and _text(v)
|
||||
}
|
||||
now = float(time.time() if now is None else now)
|
||||
with self._transaction():
|
||||
row = self.conn.execute(
|
||||
"SELECT revision FROM fleet_worker_capacity WHERE worker_id=?",
|
||||
(worker_id,),
|
||||
).fetchone()
|
||||
current = int(row[0]) if row else 0
|
||||
if expected_revision is not None and current != int(expected_revision):
|
||||
raise FleetConflict("FLEET_WORKER_POLICY_CAS_MISMATCH")
|
||||
revision = current + 1
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_worker_capacity(
|
||||
worker_id,max_slots,failure_domain,weight,labels_json,revision,updated_at
|
||||
) VALUES (?,?,?,?,?,?,?)
|
||||
ON CONFLICT(worker_id) DO UPDATE SET
|
||||
max_slots=excluded.max_slots,
|
||||
failure_domain=excluded.failure_domain,
|
||||
weight=excluded.weight,
|
||||
labels_json=excluded.labels_json,
|
||||
revision=excluded.revision,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(
|
||||
worker_id,
|
||||
max_slots,
|
||||
failure_domain,
|
||||
weight,
|
||||
json.dumps(normalized_labels, sort_keys=True, separators=(",", ":")),
|
||||
revision,
|
||||
now,
|
||||
),
|
||||
)
|
||||
return FleetWorkerPolicy(
|
||||
worker_id, max_slots, failure_domain, weight, normalized_labels, revision
|
||||
)
|
||||
|
||||
def worker_policy(self, worker_id: str) -> FleetWorkerPolicy:
|
||||
worker_id = _text(worker_id)
|
||||
with self.lock:
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT worker_id,max_slots,failure_domain,weight,labels_json,revision
|
||||
FROM fleet_worker_capacity WHERE worker_id=?
|
||||
""",
|
||||
(worker_id,),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
return FleetWorkerPolicy(worker_id=worker_id)
|
||||
return FleetWorkerPolicy(
|
||||
worker_id=str(row[0]),
|
||||
max_slots=int(row[1]),
|
||||
failure_domain=str(row[2]),
|
||||
weight=float(row[3]),
|
||||
labels=json.loads(row[4] or "{}"),
|
||||
revision=int(row[5]),
|
||||
)
|
||||
|
||||
def _cleanup_expired(self, now: float) -> None:
|
||||
self.conn.execute(
|
||||
"""
|
||||
UPDATE fleet_dispatches
|
||||
SET state='EXPIRED', updated_at=?
|
||||
WHERE state='RESERVED' AND reserved_until<=?
|
||||
""",
|
||||
(now, now),
|
||||
)
|
||||
|
||||
def reserved_slots(self, worker_id: str, now: float) -> int:
|
||||
with self.lock:
|
||||
self._cleanup_expired(now)
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT COUNT(*) FROM fleet_dispatches
|
||||
WHERE worker_id=? AND state='RESERVED' AND reserved_until>?
|
||||
""",
|
||||
(worker_id, now),
|
||||
).fetchone()
|
||||
return int(row[0] if row else 0)
|
||||
|
||||
def scope_virtual_finish(self, scope_key: str) -> float:
|
||||
with self.lock:
|
||||
row = self.conn.execute(
|
||||
"SELECT virtual_finish FROM fleet_scope_state WHERE scope_key=?",
|
||||
(scope_key,),
|
||||
).fetchone()
|
||||
return float(row[0]) if row else 0.0
|
||||
|
||||
def reserve(
|
||||
self,
|
||||
*,
|
||||
task_id: str,
|
||||
worker_id: str,
|
||||
task_revision: int,
|
||||
scope_key: str,
|
||||
failure_domain: str,
|
||||
score: tuple[float, float, float, str],
|
||||
reservation_seconds: int,
|
||||
now: float,
|
||||
scope_weight: float,
|
||||
) -> FleetDispatchDecision:
|
||||
reservation_seconds = _int(
|
||||
reservation_seconds, DEFAULT_RESERVATION_SECONDS, 1, 300
|
||||
)
|
||||
reservation_id = "fleet-" + _sha(
|
||||
{
|
||||
"task_id": task_id,
|
||||
"worker_id": worker_id,
|
||||
"task_revision": task_revision,
|
||||
"scope_key": scope_key,
|
||||
}
|
||||
)[:32]
|
||||
reserved_until = now + reservation_seconds
|
||||
with self._transaction():
|
||||
self._cleanup_expired(now)
|
||||
existing = self.conn.execute(
|
||||
"""
|
||||
SELECT reservation_id,worker_id,task_revision,scope_key,failure_domain,
|
||||
reserved_until,state
|
||||
FROM fleet_dispatches WHERE task_id=?
|
||||
""",
|
||||
(task_id,),
|
||||
).fetchone()
|
||||
# Capacity is rechecked inside the same durable reservation transaction.
|
||||
# This closes the cross-thread/process race between eligibility scoring and reserve.
|
||||
policy_row = self.conn.execute(
|
||||
"SELECT max_slots FROM fleet_worker_capacity WHERE worker_id=?",
|
||||
(worker_id,),
|
||||
).fetchone()
|
||||
max_slots = int(policy_row[0]) if policy_row else 1
|
||||
if existing and str(existing[6]) in {"RESERVED", "CLAIMED"} and float(existing[5]) > now:
|
||||
if str(existing[1]) != worker_id or int(existing[2]) != task_revision:
|
||||
raise FleetConflict("FLEET_TASK_ALREADY_RESERVED")
|
||||
return FleetDispatchDecision(
|
||||
str(existing[0]), task_id, worker_id, task_revision, str(existing[3]),
|
||||
str(existing[4]), float(existing[5]), score
|
||||
)
|
||||
|
||||
claim_columns = {
|
||||
str(row[1])
|
||||
for row in self.conn.execute("PRAGMA table_info(claims)").fetchall()
|
||||
}
|
||||
active_claims = 0
|
||||
if {"worker_id", "status"}.issubset(claim_columns):
|
||||
sql = "SELECT COUNT(*) FROM claims WHERE worker_id=? AND status='ACTIVE'"
|
||||
params: list[Any] = [worker_id]
|
||||
if "lease_expires_at" in claim_columns:
|
||||
sql += " AND lease_expires_at>?"
|
||||
params.append(now)
|
||||
row = self.conn.execute(sql, tuple(params)).fetchone()
|
||||
active_claims = int(row[0] if row else 0)
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT COUNT(*) FROM fleet_dispatches
|
||||
WHERE worker_id=? AND task_id<>?
|
||||
AND state='RESERVED' AND reserved_until>?
|
||||
""",
|
||||
(worker_id, task_id, now),
|
||||
).fetchone()
|
||||
active_reservations = int(row[0] if row else 0)
|
||||
if active_claims + active_reservations >= max_slots:
|
||||
raise FleetConflict("FLEET_WORKER_CAPACITY_EXHAUSTED")
|
||||
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_dispatches(
|
||||
reservation_id,task_id,worker_id,task_revision,scope_key,failure_domain,
|
||||
state,reserved_until,claim_id,created_at,updated_at
|
||||
) VALUES (?,?,?,?,?,?,'RESERVED',?,NULL,?,?)
|
||||
ON CONFLICT(task_id) DO UPDATE SET
|
||||
reservation_id=excluded.reservation_id,
|
||||
worker_id=excluded.worker_id,
|
||||
task_revision=excluded.task_revision,
|
||||
scope_key=excluded.scope_key,
|
||||
failure_domain=excluded.failure_domain,
|
||||
state='RESERVED',
|
||||
reserved_until=excluded.reserved_until,
|
||||
claim_id=NULL,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(
|
||||
reservation_id, task_id, worker_id, task_revision, scope_key,
|
||||
failure_domain, reserved_until, now, now,
|
||||
),
|
||||
)
|
||||
row = self.conn.execute(
|
||||
"SELECT virtual_finish,dispatch_count,revision FROM fleet_scope_state WHERE scope_key=?",
|
||||
(scope_key,),
|
||||
).fetchone()
|
||||
current_finish = float(row[0]) if row else 0.0
|
||||
dispatch_count = int(row[1]) if row else 0
|
||||
revision = int(row[2]) if row else 0
|
||||
next_finish = max(current_finish, 0.0) + 1.0 / max(scope_weight, 0.05)
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_scope_state(
|
||||
scope_key,virtual_finish,dispatch_count,last_dispatched_at,revision
|
||||
) VALUES (?,?,?,?,?)
|
||||
ON CONFLICT(scope_key) DO UPDATE SET
|
||||
virtual_finish=excluded.virtual_finish,
|
||||
dispatch_count=excluded.dispatch_count,
|
||||
last_dispatched_at=excluded.last_dispatched_at,
|
||||
revision=excluded.revision
|
||||
""",
|
||||
(scope_key, next_finish, dispatch_count + 1, now, revision + 1),
|
||||
)
|
||||
return FleetDispatchDecision(
|
||||
reservation_id, task_id, worker_id, task_revision, scope_key,
|
||||
failure_domain, reserved_until, score
|
||||
)
|
||||
|
||||
def bind_claim(self, reservation_id: str, claim_id: str, *, now: float | None = None) -> None:
|
||||
now = float(time.time() if now is None else now)
|
||||
with self._transaction():
|
||||
row = self.conn.execute(
|
||||
"SELECT state FROM fleet_dispatches WHERE reservation_id=?",
|
||||
(reservation_id,),
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise FleetError("FLEET_RESERVATION_NOT_FOUND")
|
||||
if str(row[0]) not in {"RESERVED", "CLAIMED"}:
|
||||
raise FleetConflict("FLEET_RESERVATION_NOT_ACTIVE")
|
||||
self.conn.execute(
|
||||
"""
|
||||
UPDATE fleet_dispatches
|
||||
SET state='CLAIMED', claim_id=?, updated_at=?
|
||||
WHERE reservation_id=?
|
||||
""",
|
||||
(claim_id, now, reservation_id),
|
||||
)
|
||||
|
||||
def release(
|
||||
self,
|
||||
task_id: str,
|
||||
*,
|
||||
state: str = "RELEASED",
|
||||
now: float | None = None,
|
||||
) -> None:
|
||||
if state not in {"RELEASED", "COMPLETED", "FAILED", "EXPIRED"}:
|
||||
raise FleetError("FLEET_RESERVATION_STATE_INVALID")
|
||||
now = float(time.time() if now is None else now)
|
||||
with self._transaction():
|
||||
self.conn.execute(
|
||||
"UPDATE fleet_dispatches SET state=?,updated_at=? WHERE task_id=?",
|
||||
(state, now, task_id),
|
||||
)
|
||||
|
||||
def worker_circuit_open(self, worker_id: str, now: float) -> bool:
|
||||
with self.lock:
|
||||
row = self.conn.execute(
|
||||
"SELECT circuit_open_until FROM fleet_worker_failures WHERE worker_id=?",
|
||||
(worker_id,),
|
||||
).fetchone()
|
||||
return bool(row and row[0] is not None and float(row[0]) > now)
|
||||
|
||||
def task_worker_blocked(self, task_id: str, worker_id: str, now: float) -> bool:
|
||||
with self.lock:
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT blocked_until FROM fleet_task_worker_failures
|
||||
WHERE task_id=? AND worker_id=?
|
||||
""",
|
||||
(task_id, worker_id),
|
||||
).fetchone()
|
||||
return bool(row and row[0] is not None and float(row[0]) > now)
|
||||
|
||||
def record_worker_failure(
|
||||
self,
|
||||
worker_id: str,
|
||||
failure_class: str,
|
||||
*,
|
||||
threshold: int = DEFAULT_CIRCUIT_THRESHOLD,
|
||||
base_circuit_seconds: int = DEFAULT_CIRCUIT_SECONDS,
|
||||
now: float | None = None,
|
||||
) -> dict[str, Any]:
|
||||
now = float(time.time() if now is None else now)
|
||||
threshold = _int(threshold, DEFAULT_CIRCUIT_THRESHOLD, 1, 20)
|
||||
base_circuit_seconds = _int(base_circuit_seconds, DEFAULT_CIRCUIT_SECONDS, 1, 3600)
|
||||
with self._transaction():
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT consecutive_failures,revision FROM fleet_worker_failures
|
||||
WHERE worker_id=?
|
||||
""",
|
||||
(worker_id,),
|
||||
).fetchone()
|
||||
failures = (int(row[0]) if row else 0) + 1
|
||||
revision = (int(row[1]) if row else 0) + 1
|
||||
open_until = None
|
||||
if failures >= threshold:
|
||||
exponent = min(failures - threshold, 8)
|
||||
open_until = now + min(
|
||||
MAX_CIRCUIT_SECONDS, base_circuit_seconds * (2**exponent)
|
||||
)
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_worker_failures(
|
||||
worker_id,consecutive_failures,circuit_open_until,last_failure_class,
|
||||
revision,updated_at
|
||||
) VALUES (?,?,?,?,?,?)
|
||||
ON CONFLICT(worker_id) DO UPDATE SET
|
||||
consecutive_failures=excluded.consecutive_failures,
|
||||
circuit_open_until=excluded.circuit_open_until,
|
||||
last_failure_class=excluded.last_failure_class,
|
||||
revision=excluded.revision,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(worker_id, failures, open_until, _text(failure_class, "unknown"), revision, now),
|
||||
)
|
||||
return {
|
||||
"worker_id": worker_id,
|
||||
"consecutive_failures": failures,
|
||||
"circuit_open_until": open_until,
|
||||
"revision": revision,
|
||||
}
|
||||
|
||||
def record_worker_success(self, worker_id: str, *, now: float | None = None) -> None:
|
||||
now = float(time.time() if now is None else now)
|
||||
with self._transaction():
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_worker_failures(
|
||||
worker_id,consecutive_failures,circuit_open_until,last_failure_class,
|
||||
revision,updated_at
|
||||
) VALUES (?,0,NULL,NULL,1,?)
|
||||
ON CONFLICT(worker_id) DO UPDATE SET
|
||||
consecutive_failures=0,
|
||||
circuit_open_until=NULL,
|
||||
last_failure_class=NULL,
|
||||
revision=revision+1,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(worker_id, now),
|
||||
)
|
||||
|
||||
def record_task_worker_failure(
|
||||
self,
|
||||
task_id: str,
|
||||
worker_id: str,
|
||||
failure_class: str,
|
||||
*,
|
||||
quarantine_seconds: int = 60,
|
||||
now: float | None = None,
|
||||
) -> dict[str, Any]:
|
||||
now = float(time.time() if now is None else now)
|
||||
quarantine_seconds = _int(quarantine_seconds, 60, 1, 3600)
|
||||
with self._transaction():
|
||||
row = self.conn.execute(
|
||||
"""
|
||||
SELECT failure_count,revision FROM fleet_task_worker_failures
|
||||
WHERE task_id=? AND worker_id=?
|
||||
""",
|
||||
(task_id, worker_id),
|
||||
).fetchone()
|
||||
count = (int(row[0]) if row else 0) + 1
|
||||
revision = (int(row[1]) if row else 0) + 1
|
||||
blocked_until = now + quarantine_seconds
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO fleet_task_worker_failures(
|
||||
task_id,worker_id,failure_count,blocked_until,last_failure_class,
|
||||
revision,updated_at
|
||||
) VALUES (?,?,?,?,?,?,?)
|
||||
ON CONFLICT(task_id,worker_id) DO UPDATE SET
|
||||
failure_count=excluded.failure_count,
|
||||
blocked_until=excluded.blocked_until,
|
||||
last_failure_class=excluded.last_failure_class,
|
||||
revision=excluded.revision,
|
||||
updated_at=excluded.updated_at
|
||||
""",
|
||||
(
|
||||
task_id, worker_id, count, blocked_until,
|
||||
_text(failure_class, "unknown"), revision, now,
|
||||
),
|
||||
)
|
||||
return {
|
||||
"task_id": task_id,
|
||||
"worker_id": worker_id,
|
||||
"failure_count": count,
|
||||
"blocked_until": blocked_until,
|
||||
"revision": revision,
|
||||
}
|
||||
|
||||
|
||||
class FleetScheduler:
|
||||
"""Deterministic capacity/fairness scheduler over existing TaskPlane records."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
store: Any,
|
||||
workers: Any,
|
||||
*,
|
||||
now_fn: Any = time.time,
|
||||
reservation_seconds: int = DEFAULT_RESERVATION_SECONDS,
|
||||
) -> None:
|
||||
self.store = store
|
||||
self.workers = workers
|
||||
self.now_fn = now_fn
|
||||
self.reservation_seconds = _int(
|
||||
reservation_seconds, DEFAULT_RESERVATION_SECONDS, 1, 300
|
||||
)
|
||||
connection = getattr(store, "conn", None)
|
||||
if not isinstance(connection, sqlite3.Connection):
|
||||
raise FleetError("FLEET_TASKPLANE_SQLITE_CONNECTION_REQUIRED")
|
||||
lock = getattr(store, "_lock", None)
|
||||
self.state = FleetStateStore(connection, lock)
|
||||
|
||||
def configure_worker(self, worker_id: str, **kwargs: Any) -> FleetWorkerPolicy:
|
||||
return self.state.configure_worker(worker_id, **kwargs)
|
||||
|
||||
def _online(self, worker_id: str, now: float) -> bool:
|
||||
method = getattr(self.workers, "is_online", None)
|
||||
if not callable(method):
|
||||
raise FleetError("FLEET_WORKER_REGISTRY_ONLINE_CHECK_REQUIRED")
|
||||
try:
|
||||
return bool(method(worker_id, now=now))
|
||||
except TypeError:
|
||||
return bool(method(worker_id))
|
||||
|
||||
def _worker_record(self, worker_id: str) -> object:
|
||||
getter = getattr(self.store, "get_worker", None)
|
||||
if not callable(getter):
|
||||
raise FleetError("FLEET_WORKER_LOOKUP_REQUIRED")
|
||||
return getter(worker_id)
|
||||
|
||||
def _active_claims(self, worker_id: str, now: float) -> int:
|
||||
# The TaskPlane store owns one SQLite connection in the current runtime.
|
||||
# Fleet reads must share its lock just like fleet writes do, otherwise two
|
||||
# concurrent pullers can issue overlapping operations on the same handle.
|
||||
with self.state.lock:
|
||||
columns = {
|
||||
str(row[1])
|
||||
for row in self.store.conn.execute("PRAGMA table_info(claims)").fetchall()
|
||||
}
|
||||
required = {"worker_id", "status"}
|
||||
if not required.issubset(columns):
|
||||
raise FleetError("FLEET_CLAIMS_SCHEMA_UNSUPPORTED")
|
||||
sql = "SELECT COUNT(*) FROM claims WHERE worker_id=? AND status='ACTIVE'"
|
||||
params: list[Any] = [worker_id]
|
||||
if "lease_expires_at" in columns:
|
||||
sql += " AND lease_expires_at>?"
|
||||
params.append(now)
|
||||
row = self.store.conn.execute(sql, tuple(params)).fetchone()
|
||||
return int(row[0] if row else 0)
|
||||
|
||||
@staticmethod
|
||||
def _labels_match(policy: FleetWorkerPolicy, task: object) -> bool:
|
||||
metadata = _task_metadata(task)
|
||||
affinity = metadata.get("fleet_affinity_labels") or {}
|
||||
if affinity and not isinstance(affinity, Mapping):
|
||||
return False
|
||||
labels = dict(policy.labels or {})
|
||||
for key, value in dict(affinity).items():
|
||||
if labels.get(_text(key)) != _text(value):
|
||||
return False
|
||||
avoid = metadata.get("fleet_avoid_failure_domains") or []
|
||||
if isinstance(avoid, Sequence) and not isinstance(avoid, (str, bytes)):
|
||||
if policy.failure_domain in {_text(item) for item in avoid}:
|
||||
return False
|
||||
return True
|
||||
|
||||
def _eligible_worker(self, worker_id: str, task: object, now: float) -> tuple[bool, int, FleetWorkerPolicy]:
|
||||
if not self._online(worker_id, now):
|
||||
return False, 0, self.state.worker_policy(worker_id)
|
||||
worker = self._worker_record(worker_id)
|
||||
policy = self.state.worker_policy(worker_id)
|
||||
if self.state.worker_circuit_open(worker_id, now):
|
||||
return False, 0, policy
|
||||
if self.state.task_worker_blocked(_task_id(task), worker_id, now):
|
||||
return False, 0, policy
|
||||
if not self._labels_match(policy, task):
|
||||
return False, 0, policy
|
||||
required = _task_required_capabilities(task)
|
||||
capabilities = _worker_capabilities(worker)
|
||||
if required and not required.issubset(capabilities):
|
||||
return False, 0, policy
|
||||
active = self._active_claims(worker_id, now)
|
||||
reserved = self.state.reserved_slots(worker_id, now)
|
||||
load = active + reserved
|
||||
if load >= policy.max_slots:
|
||||
return False, load, policy
|
||||
return True, load, policy
|
||||
|
||||
@staticmethod
|
||||
def _task_priority(task: object, now: float) -> float:
|
||||
metadata = _task_metadata(task)
|
||||
base = _int(metadata.get("fleet_priority"), 0, -100, 100)
|
||||
created = _task_created_at(task)
|
||||
waited = max(0.0, now - created) if created > 0 else 0.0
|
||||
aging = min(100.0, waited / 60.0)
|
||||
return float(base) + aging
|
||||
|
||||
def _task_score(self, task: object, now: float) -> tuple[float, float, float, str]:
|
||||
scope = _task_scope_key(task)
|
||||
virtual_finish = self.state.scope_virtual_finish(scope)
|
||||
priority = self._task_priority(task, now)
|
||||
return (virtual_finish, -priority, _task_created_at(task), _task_id(task))
|
||||
|
||||
def _tasks(self, actor_context: Any = None) -> list[object]:
|
||||
lister = getattr(self.store, "list_tasks", None)
|
||||
if not callable(lister):
|
||||
raise FleetError("FLEET_TASK_LIST_REQUIRED")
|
||||
try:
|
||||
tasks = lister(actor_context)
|
||||
except TypeError:
|
||||
tasks = lister()
|
||||
return [
|
||||
task for task in tasks
|
||||
if _task_status(task) in {"CREATED", "QUEUED"}
|
||||
and _task_id(task)
|
||||
]
|
||||
|
||||
def rank_for_worker(
|
||||
self,
|
||||
worker_id: str,
|
||||
*,
|
||||
actor_context: Any = None,
|
||||
now: float | None = None,
|
||||
) -> list[object]:
|
||||
"""Return fleet-ranked tasks without reserving or claiming anything."""
|
||||
now = float(self.now_fn() if now is None else now)
|
||||
worker_id = _text(worker_id)
|
||||
if not worker_id:
|
||||
return []
|
||||
ranked: list[object] = []
|
||||
for task in self._tasks(actor_context):
|
||||
eligible, _, _ = self._eligible_worker(worker_id, task, now)
|
||||
if eligible:
|
||||
ranked.append(task)
|
||||
return sorted(ranked, key=lambda task: self._task_score(task, now))
|
||||
|
||||
def reserve_for_worker(
|
||||
self,
|
||||
worker_id: str,
|
||||
task: object,
|
||||
*,
|
||||
now: float | None = None,
|
||||
) -> FleetDispatchDecision:
|
||||
"""Reserve exactly one already-ranked task, rechecking eligibility and capacity."""
|
||||
now = float(self.now_fn() if now is None else now)
|
||||
worker_id = _text(worker_id)
|
||||
eligible, _, policy = self._eligible_worker(worker_id, task, now)
|
||||
if not eligible:
|
||||
raise FleetConflict("FLEET_WORKER_NOT_ELIGIBLE")
|
||||
metadata = _task_metadata(task)
|
||||
scope_weight = _float(metadata.get("fleet_scope_weight"), 1.0, 0.05, 100.0)
|
||||
return self.state.reserve(
|
||||
task_id=_task_id(task),
|
||||
worker_id=worker_id,
|
||||
task_revision=_task_revision(task),
|
||||
scope_key=_task_scope_key(task),
|
||||
failure_domain=policy.failure_domain,
|
||||
score=self._task_score(task, now),
|
||||
reservation_seconds=self.reservation_seconds,
|
||||
now=now,
|
||||
scope_weight=scope_weight,
|
||||
)
|
||||
|
||||
def select(
|
||||
self,
|
||||
worker_ids: Sequence[str],
|
||||
*,
|
||||
actor_context: Any = None,
|
||||
limit: int = 1,
|
||||
now: float | None = None,
|
||||
) -> list[FleetDispatchDecision]:
|
||||
now = float(self.now_fn() if now is None else now)
|
||||
limit = _int(limit, 1, 1, 100)
|
||||
worker_ids = tuple(dict.fromkeys(_text(item) for item in worker_ids if _text(item)))
|
||||
tasks = sorted(self._tasks(actor_context), key=lambda task: self._task_score(task, now))
|
||||
decisions: list[FleetDispatchDecision] = []
|
||||
local_load: dict[str, int] = {}
|
||||
for task in tasks:
|
||||
if len(decisions) >= limit:
|
||||
break
|
||||
candidates: list[tuple[int, float, str, FleetWorkerPolicy]] = []
|
||||
for worker_id in worker_ids:
|
||||
eligible, load, policy = self._eligible_worker(worker_id, task, now)
|
||||
if not eligible:
|
||||
continue
|
||||
effective_load = local_load.get(worker_id, load)
|
||||
if effective_load >= policy.max_slots:
|
||||
continue
|
||||
candidates.append(
|
||||
(
|
||||
effective_load,
|
||||
-policy.weight,
|
||||
worker_id,
|
||||
policy,
|
||||
)
|
||||
)
|
||||
if not candidates:
|
||||
continue
|
||||
candidates.sort(key=lambda item: (item[0], item[1], item[2]))
|
||||
_, _, worker_id, policy = candidates[0]
|
||||
score = self._task_score(task, now)
|
||||
metadata = _task_metadata(task)
|
||||
scope_weight = _float(metadata.get("fleet_scope_weight"), 1.0, 0.05, 100.0)
|
||||
try:
|
||||
decision = self.state.reserve(
|
||||
task_id=_task_id(task),
|
||||
worker_id=worker_id,
|
||||
task_revision=_task_revision(task),
|
||||
scope_key=_task_scope_key(task),
|
||||
failure_domain=policy.failure_domain,
|
||||
score=score,
|
||||
reservation_seconds=self.reservation_seconds,
|
||||
now=now,
|
||||
scope_weight=scope_weight,
|
||||
)
|
||||
except FleetConflict:
|
||||
continue
|
||||
local_load[worker_id] = local_load.get(
|
||||
worker_id,
|
||||
self._active_claims(worker_id, now)
|
||||
+ self.state.reserved_slots(worker_id, now)
|
||||
- 1,
|
||||
) + 1
|
||||
decisions.append(decision)
|
||||
return decisions
|
||||
@@ -13,6 +13,8 @@ from dataclasses import dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any
|
||||
|
||||
from .scope import normalize_task_scope
|
||||
|
||||
|
||||
SENSITIVE_KEYS = {
|
||||
"secret",
|
||||
@@ -66,6 +68,12 @@ TASK_PLAN_KEYS = {
|
||||
"allowed_input_paths",
|
||||
"allowed_output_paths",
|
||||
"output_policy",
|
||||
"scope_type",
|
||||
"tenant_id",
|
||||
"user_id",
|
||||
"project_id",
|
||||
"conversation_id",
|
||||
"run_id",
|
||||
}
|
||||
|
||||
|
||||
@@ -237,6 +245,12 @@ class TaskPlan:
|
||||
schema_version: int = 1
|
||||
task_id: str | None = None
|
||||
task_type: str = "code.change"
|
||||
scope_type: str = "legacy"
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
run_id: str | None = None
|
||||
issuer: dict[str, Any] = field(default_factory=dict)
|
||||
intent: str | None = None
|
||||
required_capabilities: list[str] = field(default_factory=list)
|
||||
@@ -311,10 +325,17 @@ class TaskPlan:
|
||||
raise ValueError("credential-secret requires metadata-only logging")
|
||||
if output_policy != "hash-count-status-only":
|
||||
raise ValueError("credential-secret requires restricted output")
|
||||
scope = normalize_task_scope(data)
|
||||
return cls(
|
||||
schema_version=schema_version,
|
||||
task_id=validate_identifier(data["task_id"], "task_id"),
|
||||
task_type=validate_type(data.get("task_type", "code.change"), "task_type"),
|
||||
scope_type=scope.scope_type,
|
||||
tenant_id=scope.tenant_id,
|
||||
user_id=scope.user_id,
|
||||
project_id=scope.project_id,
|
||||
conversation_id=scope.conversation_id,
|
||||
run_id=scope.run_id,
|
||||
issuer=issuer,
|
||||
intent=data.get("intent"),
|
||||
required_capabilities=_normalize_list(data.get("required_capabilities", [])),
|
||||
@@ -348,6 +369,12 @@ class TaskPlan:
|
||||
"schema_version": self.schema_version,
|
||||
"task_id": self.task_id,
|
||||
"task_type": self.task_type,
|
||||
"scope_type": self.scope_type,
|
||||
"tenant_id": self.tenant_id,
|
||||
"user_id": self.user_id,
|
||||
"project_id": self.project_id,
|
||||
"conversation_id": self.conversation_id,
|
||||
"run_id": self.run_id,
|
||||
"issuer": self.issuer,
|
||||
"intent": self.intent,
|
||||
"required_capabilities": list(self.required_capabilities),
|
||||
|
||||
@@ -3,10 +3,11 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Callable
|
||||
from typing import Any, Callable, Mapping
|
||||
|
||||
from .errors import ForbiddenError, LockedError
|
||||
from .models import ProbeEvidence, ResultEnvelope, TaskRecord
|
||||
from .scope import TaskActorContext, actor_context as build_actor_context
|
||||
|
||||
|
||||
RISK_RANK = {"low": 1, "medium": 2, "high": 3}
|
||||
@@ -93,6 +94,10 @@ class PolicyEngine:
|
||||
result_signature_verifier: Callable[[ResultEnvelope], bool] | None = None,
|
||||
probe_attestation_verifier: Callable[[ProbeEvidence], bool] | None = None,
|
||||
identity_capabilities: dict[str, set[str]] | None = None,
|
||||
identity_actor_contexts: Mapping[
|
||||
str, TaskActorContext | Mapping[str, Any]
|
||||
]
|
||||
| None = None,
|
||||
admin_identities: set[str] | None = None,
|
||||
readonly_worker_execution_enabled: bool = False,
|
||||
readonly_worker_profiles: list[ReadonlyWorkerProfile] | None = None,
|
||||
@@ -109,12 +114,26 @@ class PolicyEngine:
|
||||
identity: set(capabilities)
|
||||
for identity, capabilities in (identity_capabilities or {}).items()
|
||||
}
|
||||
self.identity_actor_contexts = dict(identity_actor_contexts or {})
|
||||
self.admin_identities = set(admin_identities or ())
|
||||
self.readonly_worker_execution_enabled = readonly_worker_execution_enabled
|
||||
self.readonly_worker_profiles = {
|
||||
profile.identity: profile for profile in (readonly_worker_profiles or [])
|
||||
}
|
||||
|
||||
def actor_context(self, identity: str) -> TaskActorContext:
|
||||
configured = self.identity_actor_contexts.get(
|
||||
identity, self.identity_actor_contexts.get("*")
|
||||
)
|
||||
capabilities = set(
|
||||
self.identity_capabilities.get(
|
||||
identity, self.identity_capabilities.get("*", set())
|
||||
)
|
||||
)
|
||||
if identity in self.admin_identities:
|
||||
capabilities.add("task.admin")
|
||||
return build_actor_context(identity, configured, capabilities)
|
||||
|
||||
def _readonly_worker_allows(
|
||||
self, action: str, actor: str, task: TaskRecord | None
|
||||
) -> bool:
|
||||
|
||||
@@ -74,3 +74,203 @@ class TaskScheduler:
|
||||
operation_digest=task.task_plan.operation_digest(),
|
||||
)
|
||||
return claim
|
||||
|
||||
# R4.2 P2 durable multi-agent fleet scheduling public surface.
|
||||
from .fleet import (
|
||||
FleetConflict,
|
||||
FleetDispatchDecision,
|
||||
FleetError,
|
||||
FleetScheduler,
|
||||
FleetStateStore,
|
||||
FleetWorkerPolicy,
|
||||
)
|
||||
# R4.2 P2-B fleet-aware pull scheduling.
|
||||
#
|
||||
# The original TaskScheduler remains the security oracle and claim-CAS implementation.
|
||||
# Fleet ordering only controls the order presented to that oracle.
|
||||
import inspect as _fleet_inspect
|
||||
import threading as _fleet_threading
|
||||
from collections.abc import Mapping as _FleetMapping
|
||||
|
||||
from .worker_registry import WorkerRegistry as _FleetWorkerRegistry
|
||||
from .errors import NotFoundError as _FleetNotFoundError
|
||||
|
||||
_LegacyTaskScheduler = TaskScheduler
|
||||
_LegacyScheduleParameters = _fleet_inspect.signature(
|
||||
_LegacyTaskScheduler.schedule_for_worker
|
||||
).parameters
|
||||
_LegacyNextParameters = _fleet_inspect.signature(
|
||||
_LegacyTaskScheduler.next_queued_task
|
||||
).parameters
|
||||
|
||||
|
||||
class _FleetOrderedStoreProxy:
|
||||
def __init__(self, delegate, tasks):
|
||||
self._delegate = delegate
|
||||
self._tasks = tuple(tasks)
|
||||
|
||||
def list_tasks(self, *args, **kwargs):
|
||||
return list(self._tasks)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self._delegate, name)
|
||||
|
||||
|
||||
def _fleet_claim_field(claim, name, default=None):
|
||||
if isinstance(claim, _FleetMapping):
|
||||
return claim.get(name, default)
|
||||
return getattr(claim, name, default)
|
||||
|
||||
|
||||
class TaskScheduler(_LegacyTaskScheduler):
|
||||
"""Fleet-integrated pull scheduler preserving legacy security and claim semantics."""
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
store = getattr(self, "store", args[0] if args else None)
|
||||
if store is None:
|
||||
raise FleetError("FLEET_SCHEDULER_STORE_REQUIRED")
|
||||
registry = getattr(self, "workers", None)
|
||||
if registry is None:
|
||||
registry = _FleetWorkerRegistry(store)
|
||||
self.fleet_scheduler = FleetScheduler(store, registry)
|
||||
self._fleet_local = _fleet_threading.local()
|
||||
|
||||
def _fleet_legacy_next(self, worker_id, tasks, *args, **kwargs):
|
||||
proxy = _FleetOrderedStoreProxy(self.store, tasks)
|
||||
legacy = _LegacyTaskScheduler(proxy)
|
||||
legacy_kwargs = dict(kwargs)
|
||||
if "actor_context" not in _LegacyNextParameters:
|
||||
legacy_kwargs.pop("actor_context", None)
|
||||
return legacy.next_queued_task(worker_id, *args, **legacy_kwargs)
|
||||
|
||||
def next_queued_task(self, worker_id, *args, **kwargs):
|
||||
actor_context = kwargs.get(
|
||||
"actor_context", getattr(self._fleet_local, "actor_context", None)
|
||||
)
|
||||
|
||||
# Preserve legacy fail-closed worker checks before fleet ordering.
|
||||
probe_kwargs = dict(kwargs)
|
||||
if "actor_context" not in _LegacyNextParameters:
|
||||
probe_kwargs.pop("actor_context", None)
|
||||
legacy_probe = _LegacyTaskScheduler(self.store).next_queued_task(
|
||||
worker_id, *args, **probe_kwargs
|
||||
)
|
||||
if legacy_probe is None:
|
||||
return None
|
||||
|
||||
ranked = self.fleet_scheduler.rank_for_worker(
|
||||
worker_id, actor_context=actor_context
|
||||
)
|
||||
# Preserve FleetScheduler fairness order. The legacy scheduler is used
|
||||
# only as a fail-closed security oracle: present one fleet-ranked task
|
||||
# at a time so its internal sort cannot reorder across scopes.
|
||||
# Keep the legacy priority dimension ahead of Fleet fairness for
|
||||
# compatibility with existing TaskPlane scheduling contracts; the
|
||||
# Fleet order remains authoritative among equal-priority tasks.
|
||||
def _legacy_priority(task):
|
||||
plan = getattr(task, "task_plan", task)
|
||||
metadata = getattr(plan, "metadata", {}) or {}
|
||||
if not isinstance(metadata, _FleetMapping):
|
||||
return 0
|
||||
try:
|
||||
return int(metadata.get("priority", 0))
|
||||
except (TypeError, ValueError):
|
||||
return 0
|
||||
|
||||
ranked = sorted(ranked, key=lambda task: -_legacy_priority(task))
|
||||
for ranked_candidate in ranked:
|
||||
try:
|
||||
candidate = self._fleet_legacy_next(
|
||||
worker_id, [ranked_candidate], *args, **kwargs
|
||||
)
|
||||
except _FleetNotFoundError:
|
||||
continue
|
||||
if candidate is None:
|
||||
continue
|
||||
|
||||
ranked_id = getattr(
|
||||
ranked_candidate,
|
||||
"task_id",
|
||||
getattr(getattr(ranked_candidate, "task_plan", None), "task_id", None),
|
||||
)
|
||||
candidate_id = getattr(
|
||||
candidate,
|
||||
"task_id",
|
||||
getattr(getattr(candidate, "task_plan", None), "task_id", None),
|
||||
)
|
||||
if candidate_id != ranked_id:
|
||||
raise FleetConflict("FLEET_LEGACY_ORACLE_ORDER_VIOLATION")
|
||||
|
||||
try:
|
||||
decision = self.fleet_scheduler.reserve_for_worker(
|
||||
worker_id, candidate
|
||||
)
|
||||
except FleetConflict:
|
||||
continue
|
||||
self._fleet_local.pending = decision
|
||||
return candidate
|
||||
return None
|
||||
|
||||
def schedule_for_worker(self, worker_id, *args, **kwargs):
|
||||
actor_context = kwargs.get("actor_context")
|
||||
legacy_kwargs = dict(kwargs)
|
||||
if "actor_context" not in _LegacyScheduleParameters:
|
||||
legacy_kwargs.pop("actor_context", None)
|
||||
self._fleet_local.actor_context = actor_context
|
||||
self._fleet_local.pending = None
|
||||
try:
|
||||
claim = _LegacyTaskScheduler.schedule_for_worker(
|
||||
self, worker_id, *args, **legacy_kwargs
|
||||
)
|
||||
decision = getattr(self._fleet_local, "pending", None)
|
||||
if claim is None:
|
||||
if decision is not None:
|
||||
self.fleet_scheduler.state.release(
|
||||
decision.task_id, state="RELEASED"
|
||||
)
|
||||
return None
|
||||
if decision is not None:
|
||||
claim_id = _fleet_claim_field(claim, "claim_id")
|
||||
claim_task_id = _fleet_claim_field(claim, "task_id", decision.task_id)
|
||||
if not claim_id:
|
||||
self.fleet_scheduler.state.release(
|
||||
decision.task_id, state="RELEASED"
|
||||
)
|
||||
raise FleetError("FLEET_CLAIM_ID_REQUIRED")
|
||||
if claim_task_id != decision.task_id:
|
||||
self.fleet_scheduler.state.release(
|
||||
decision.task_id, state="RELEASED"
|
||||
)
|
||||
raise FleetConflict("FLEET_CLAIM_TASK_MISMATCH")
|
||||
self.fleet_scheduler.state.bind_claim(
|
||||
decision.reservation_id, str(claim_id)
|
||||
)
|
||||
return claim
|
||||
except Exception:
|
||||
decision = getattr(self._fleet_local, "pending", None)
|
||||
if decision is not None:
|
||||
self.fleet_scheduler.state.release(
|
||||
decision.task_id, state="RELEASED"
|
||||
)
|
||||
raise
|
||||
finally:
|
||||
self._fleet_local.pending = None
|
||||
self._fleet_local.actor_context = None
|
||||
|
||||
def record_worker_failure(self, worker_id, failure_class, **kwargs):
|
||||
return self.fleet_scheduler.state.record_worker_failure(
|
||||
worker_id, failure_class, **kwargs
|
||||
)
|
||||
|
||||
def record_worker_success(self, worker_id, **kwargs):
|
||||
return self.fleet_scheduler.state.record_worker_success(
|
||||
worker_id, **kwargs
|
||||
)
|
||||
|
||||
def quarantine_task_worker(
|
||||
self, task_id, worker_id, failure_class, **kwargs
|
||||
):
|
||||
return self.fleet_scheduler.state.record_task_worker_failure(
|
||||
task_id, worker_id, failure_class, **kwargs
|
||||
)
|
||||
|
||||
@@ -0,0 +1,181 @@
|
||||
"""Trusted TaskPlane scope model and SQL authorization helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, replace
|
||||
from typing import Any, Mapping
|
||||
|
||||
from .errors import ForbiddenError, ValidationError
|
||||
|
||||
SCOPE_FIELDS = ("tenant_id", "user_id", "project_id", "conversation_id", "run_id")
|
||||
PRIVILEGED_CAPABILITIES = frozenset(
|
||||
{"*", "admin", "system.admin", "task.admin", "task.read.all"}
|
||||
)
|
||||
|
||||
|
||||
def _value(value: Any, field: str) -> Any:
|
||||
if hasattr(value, "task_plan"):
|
||||
value = value.task_plan
|
||||
if isinstance(value, Mapping):
|
||||
return value.get(field)
|
||||
return getattr(value, field, None)
|
||||
|
||||
|
||||
def _text(value: Any) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
result = str(value).strip()
|
||||
return result or None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskScope:
|
||||
scope_type: str
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
run_id: str | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TaskActorContext:
|
||||
identity: str
|
||||
scope_type: str = "legacy"
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
run_id: str | None = None
|
||||
capabilities: frozenset[str] = frozenset()
|
||||
|
||||
|
||||
def normalize_task_scope(value: Any) -> TaskScope:
|
||||
fields = {field: _text(_value(value, field)) for field in SCOPE_FIELDS}
|
||||
declared = _text(_value(value, "scope_type"))
|
||||
if declared is None:
|
||||
declared = "tenant" if fields["tenant_id"] else "legacy"
|
||||
if declared == "tenant":
|
||||
if fields["tenant_id"] is None:
|
||||
raise ValidationError(
|
||||
"tenant scope requires tenant_id", code="TASK_SCOPE_TENANT_ID_REQUIRED"
|
||||
)
|
||||
elif declared == "legacy":
|
||||
if any(fields.values()):
|
||||
raise ValidationError(
|
||||
"legacy scope cannot contain scoped ownership",
|
||||
code="TASK_SCOPE_LEGACY_WITH_SCOPED_FIELDS",
|
||||
)
|
||||
elif declared == "system":
|
||||
if any(fields[field] for field in ("tenant_id", "user_id", "project_id", "conversation_id")):
|
||||
raise ValidationError(
|
||||
"system scope cannot contain tenant ownership",
|
||||
code="TASK_SCOPE_SYSTEM_WITH_TENANT_FIELDS",
|
||||
)
|
||||
else:
|
||||
raise ValidationError("invalid task scope type", code="TASK_SCOPE_TYPE_INVALID")
|
||||
return TaskScope(declared, **fields)
|
||||
|
||||
|
||||
def actor_is_privileged(actor: TaskActorContext) -> bool:
|
||||
return bool(actor.capabilities & PRIVILEGED_CAPABILITIES)
|
||||
|
||||
|
||||
def actor_context(
|
||||
identity: str,
|
||||
configured: TaskActorContext | Mapping[str, Any] | None,
|
||||
capabilities: set[str] | frozenset[str],
|
||||
) -> TaskActorContext:
|
||||
if isinstance(configured, TaskActorContext):
|
||||
context = configured
|
||||
else:
|
||||
data = dict(configured or {})
|
||||
data.pop("identity", None)
|
||||
data.pop("capabilities", None)
|
||||
context = TaskActorContext(identity=str(identity), **data)
|
||||
scope = normalize_task_scope(context)
|
||||
return replace(
|
||||
context,
|
||||
identity=str(identity),
|
||||
scope_type=scope.scope_type,
|
||||
tenant_id=scope.tenant_id,
|
||||
user_id=scope.user_id,
|
||||
project_id=scope.project_id,
|
||||
conversation_id=scope.conversation_id,
|
||||
run_id=scope.run_id,
|
||||
capabilities=frozenset(str(item) for item in capabilities),
|
||||
)
|
||||
|
||||
|
||||
def bind_task_scope(plan: Any, actor: TaskActorContext, *, public_create: bool) -> Any:
|
||||
requested = normalize_task_scope(plan)
|
||||
if actor_is_privileged(actor):
|
||||
trusted = normalize_task_scope(actor)
|
||||
if requested.scope_type == "legacy" and trusted.scope_type != "legacy":
|
||||
plan.scope_type = trusted.scope_type
|
||||
for field in SCOPE_FIELDS:
|
||||
setattr(plan, field, getattr(actor, field))
|
||||
return plan
|
||||
trusted = normalize_task_scope(actor)
|
||||
if public_create and trusted.scope_type == "legacy":
|
||||
raise ForbiddenError(
|
||||
"authenticated identity has no tenant scope",
|
||||
code="TASK_ACTOR_SCOPE_UNAVAILABLE",
|
||||
)
|
||||
if trusted.scope_type != "tenant":
|
||||
if requested.scope_type == "legacy":
|
||||
plan.scope_type = trusted.scope_type
|
||||
for field in SCOPE_FIELDS:
|
||||
setattr(plan, field, getattr(actor, field))
|
||||
return plan
|
||||
if requested.scope_type != trusted.scope_type:
|
||||
raise ForbiddenError("task scope mismatch", code="TASK_SCOPE_MISMATCH_DENY")
|
||||
return plan
|
||||
if requested.scope_type not in {"legacy", "tenant"}:
|
||||
raise ForbiddenError("task scope mismatch", code="TASK_SCOPE_MISMATCH_DENY")
|
||||
updates: dict[str, Any] = {"scope_type": "tenant"}
|
||||
for field in SCOPE_FIELDS:
|
||||
declared = getattr(requested, field)
|
||||
authoritative = getattr(actor, field)
|
||||
if declared is not None and declared != authoritative:
|
||||
raise ForbiddenError(
|
||||
"task scope mismatch",
|
||||
code="TASK_SCOPE_MISMATCH_DENY",
|
||||
details={"field": field},
|
||||
)
|
||||
updates[field] = authoritative
|
||||
for field, item in updates.items():
|
||||
setattr(plan, field, item)
|
||||
return plan
|
||||
|
||||
|
||||
def actor_scope_sql(actor: TaskActorContext | None) -> tuple[str, tuple[Any, ...]]:
|
||||
if actor is None or actor_is_privileged(actor):
|
||||
return "", ()
|
||||
scope = normalize_task_scope(actor)
|
||||
if scope.scope_type == "legacy":
|
||||
return "scope_type = 'legacy'", ()
|
||||
if scope.scope_type == "system":
|
||||
return "scope_type = 'system'", ()
|
||||
clauses = ["scope_type = 'tenant'", "tenant_id = ?"]
|
||||
params: list[Any] = [scope.tenant_id]
|
||||
for field in ("user_id", "project_id", "conversation_id", "run_id"):
|
||||
value = getattr(scope, field)
|
||||
if value is None:
|
||||
clauses.append(f"{field} IS NULL")
|
||||
else:
|
||||
clauses.append(f"({field} IS NULL OR {field} = ?)")
|
||||
params.append(value)
|
||||
return " AND ".join(clauses), tuple(params)
|
||||
|
||||
|
||||
def task_scope_values(value: Any) -> tuple[str | None, ...]:
|
||||
scope = normalize_task_scope(value)
|
||||
return (
|
||||
scope.scope_type,
|
||||
scope.tenant_id,
|
||||
scope.user_id,
|
||||
scope.project_id,
|
||||
scope.conversation_id,
|
||||
scope.run_id,
|
||||
)
|
||||
@@ -32,6 +32,7 @@ from .models import (
|
||||
redact_value,
|
||||
validate_identifier,
|
||||
)
|
||||
from .scope import TaskActorContext, actor_scope_sql, task_scope_values
|
||||
|
||||
|
||||
EventEnvelope = tuple[str, str, str, str, str, float]
|
||||
@@ -134,6 +135,12 @@ class TaskPlaneStore:
|
||||
status TEXT NOT NULL,
|
||||
task_json TEXT NOT NULL,
|
||||
task_type TEXT NOT NULL,
|
||||
scope_type TEXT NOT NULL DEFAULT 'legacy',
|
||||
tenant_id TEXT,
|
||||
user_id TEXT,
|
||||
project_id TEXT,
|
||||
conversation_id TEXT,
|
||||
run_id TEXT,
|
||||
root_task_id TEXT NOT NULL,
|
||||
parent_task_id TEXT,
|
||||
correlation_id TEXT,
|
||||
@@ -272,6 +279,21 @@ class TaskPlaneStore:
|
||||
)
|
||||
"""
|
||||
)
|
||||
self._ensure_columns(
|
||||
"tasks",
|
||||
{
|
||||
"scope_type": "TEXT NOT NULL DEFAULT 'legacy'",
|
||||
"tenant_id": "TEXT",
|
||||
"user_id": "TEXT",
|
||||
"project_id": "TEXT",
|
||||
"conversation_id": "TEXT",
|
||||
"run_id": "TEXT",
|
||||
},
|
||||
)
|
||||
self.conn.execute(
|
||||
"UPDATE tasks SET scope_type='legacy' "
|
||||
"WHERE scope_type IS NULL OR TRIM(scope_type)=''"
|
||||
)
|
||||
self._ensure_columns(
|
||||
"workers",
|
||||
{
|
||||
@@ -299,6 +321,14 @@ class TaskPlaneStore:
|
||||
)
|
||||
self.conn.execute("CREATE INDEX IF NOT EXISTS ix_tasks_status ON tasks(status)")
|
||||
self.conn.execute("CREATE INDEX IF NOT EXISTS ix_tasks_parent ON tasks(parent_task_id)")
|
||||
self.conn.execute(
|
||||
"CREATE INDEX IF NOT EXISTS ix_tasks_scope_tenant_project "
|
||||
"ON tasks(scope_type, tenant_id, project_id)"
|
||||
)
|
||||
self.conn.execute(
|
||||
"CREATE INDEX IF NOT EXISTS ix_tasks_scope_owner "
|
||||
"ON tasks(scope_type, tenant_id, user_id, conversation_id, run_id)"
|
||||
)
|
||||
self.conn.execute("CREATE INDEX IF NOT EXISTS ix_workers_status ON workers(status)")
|
||||
self.conn.execute("CREATE INDEX IF NOT EXISTS ix_claims_task ON claims(task_id)")
|
||||
self.conn.execute(
|
||||
@@ -347,6 +377,42 @@ class TaskPlaneStore:
|
||||
raise NotFoundError("task")
|
||||
task_json = json.loads(row["task_json"])
|
||||
task_plan = TaskPlan.from_dict(task_json)
|
||||
stored_scope = tuple(
|
||||
row[field]
|
||||
for field in (
|
||||
"scope_type",
|
||||
"tenant_id",
|
||||
"user_id",
|
||||
"project_id",
|
||||
"conversation_id",
|
||||
"run_id",
|
||||
)
|
||||
)
|
||||
json_has_scope = any(
|
||||
field in task_json
|
||||
for field in (
|
||||
"scope_type",
|
||||
"tenant_id",
|
||||
"user_id",
|
||||
"project_id",
|
||||
"conversation_id",
|
||||
"run_id",
|
||||
)
|
||||
)
|
||||
if json_has_scope and stored_scope != task_scope_values(task_plan):
|
||||
raise ConflictError(
|
||||
"task scope persistence mismatch",
|
||||
code="TASK_SCOPE_PERSISTENCE_MISMATCH",
|
||||
)
|
||||
if not json_has_scope:
|
||||
(
|
||||
task_plan.scope_type,
|
||||
task_plan.tenant_id,
|
||||
task_plan.user_id,
|
||||
task_plan.project_id,
|
||||
task_plan.conversation_id,
|
||||
task_plan.run_id,
|
||||
) = stored_scope
|
||||
task_plan.parent_task_id = row["parent_task_id"]
|
||||
task_plan.correlation_id = row["correlation_id"]
|
||||
return TaskRecord(
|
||||
@@ -389,6 +455,7 @@ class TaskPlaneStore:
|
||||
task_id = task_plan.task_id or f"task-{uuid.uuid4()}"
|
||||
task_plan.task_id = task_id
|
||||
task_json = redact_value(task_plan.to_dict(redact=False))
|
||||
scope_values = task_scope_values(task_plan)
|
||||
now = _now()
|
||||
with self._transaction():
|
||||
if idempotency_key:
|
||||
@@ -397,7 +464,11 @@ class TaskPlaneStore:
|
||||
(idempotency_key,),
|
||||
).fetchone()
|
||||
if existing:
|
||||
if _canonical(json.loads(existing["task_json"])) != _canonical(task_json):
|
||||
existing_plan = TaskPlan.from_dict(
|
||||
json.loads(existing["task_json"])
|
||||
)
|
||||
existing_json = redact_value(existing_plan.to_dict(redact=False))
|
||||
if _canonical(existing_json) != _canonical(task_json):
|
||||
raise ConflictError("idempotency key payload mismatch")
|
||||
return self.get_task(existing["task_id"])
|
||||
root_task_id = task_id
|
||||
@@ -412,14 +483,18 @@ class TaskPlaneStore:
|
||||
self.conn.execute(
|
||||
"""
|
||||
INSERT INTO tasks
|
||||
(task_id, revision, status, task_json, task_type, root_task_id, parent_task_id, correlation_id, idempotency_key, created_at, updated_at, failure_reason)
|
||||
VALUES (?, 1, ?, ?, ?, ?, ?, ?, ?, ?, ?, NULL)
|
||||
(task_id, revision, status, task_json, task_type,
|
||||
scope_type, tenant_id, user_id, project_id, conversation_id, run_id,
|
||||
root_task_id, parent_task_id, correlation_id, idempotency_key,
|
||||
created_at, updated_at, failure_reason)
|
||||
VALUES (?, 1, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, NULL)
|
||||
""",
|
||||
(
|
||||
task_id,
|
||||
"CREATED",
|
||||
json.dumps(task_json, ensure_ascii=False),
|
||||
task_plan.task_type,
|
||||
*scope_values,
|
||||
root_task_id,
|
||||
task_plan.parent_task_id,
|
||||
task_plan.correlation_id,
|
||||
@@ -451,21 +526,30 @@ class TaskPlaneStore:
|
||||
)
|
||||
return self.get_task(task.task_id)
|
||||
|
||||
def get_task(self, task_id: str) -> TaskRecord:
|
||||
def get_task(
|
||||
self, task_id: str, actor_context: TaskActorContext | None = None
|
||||
) -> TaskRecord:
|
||||
task_id = _validated_id(task_id, "task_id")
|
||||
predicate, scope_params = actor_scope_sql(actor_context)
|
||||
sql = "SELECT * FROM tasks WHERE task_id=?"
|
||||
if predicate:
|
||||
sql += f" AND ({predicate})"
|
||||
with self._lock:
|
||||
row = self.conn.execute(
|
||||
"SELECT * FROM tasks WHERE task_id=?", (task_id,)
|
||||
).fetchone()
|
||||
row = self.conn.execute(sql, (task_id, *scope_params)).fetchone()
|
||||
if row is None:
|
||||
raise NotFoundError(f"task {task_id} not found")
|
||||
return self._row_to_task(row)
|
||||
|
||||
def list_tasks(self) -> list[TaskRecord]:
|
||||
def list_tasks(
|
||||
self, actor_context: TaskActorContext | None = None
|
||||
) -> list[TaskRecord]:
|
||||
predicate, scope_params = actor_scope_sql(actor_context)
|
||||
sql = "SELECT * FROM tasks"
|
||||
if predicate:
|
||||
sql += f" WHERE ({predicate})"
|
||||
sql += " ORDER BY created_at DESC"
|
||||
with self._lock:
|
||||
rows = self.conn.execute(
|
||||
"SELECT * FROM tasks ORDER BY created_at DESC"
|
||||
).fetchall()
|
||||
rows = self.conn.execute(sql, scope_params).fetchall()
|
||||
return [self._row_to_task(row) for row in rows]
|
||||
|
||||
def get_task_budget(self, task_id: str) -> Budget:
|
||||
|
||||
@@ -0,0 +1,759 @@
|
||||
"""Scope-bound governance for traces, Tool/MCP calls, and credentials.
|
||||
|
||||
This module deliberately stores references and audit metadata only. Secret
|
||||
material remains in the configured credential provider boundary.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import asdict, dataclass, field
|
||||
from datetime import datetime, timezone
|
||||
from contextlib import contextmanager
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
import sqlite3
|
||||
from pathlib import Path
|
||||
from typing import Any, Iterable, Mapping
|
||||
|
||||
|
||||
SCOPE_FIELDS = ("tenant_id", "user_id", "project_id", "conversation_id", "run_id")
|
||||
PRIVILEGED_CAPABILITIES = frozenset({"*", "admin", "system.admin", "governance.admin"})
|
||||
REFERENCE_RE = re.compile(r"^(systemd-credential|vault|secret-manager):[A-Za-z0-9][A-Za-z0-9._:/#-]{0,255}$")
|
||||
IDENTIFIER_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{0,179}$")
|
||||
|
||||
|
||||
class GovernanceError(RuntimeError):
|
||||
def __init__(self, code: str, *, field: str | None = None) -> None:
|
||||
super().__init__(code if field is None else f"{code}:{field}")
|
||||
self.code = code
|
||||
self.field = field
|
||||
|
||||
|
||||
def _clean(value: Any) -> str | None:
|
||||
if value is None:
|
||||
return None
|
||||
text = str(value).strip()
|
||||
return text or None
|
||||
|
||||
|
||||
def _scope_tuple(value: Iterable[str] | str | None) -> tuple[str, ...]:
|
||||
if value is None:
|
||||
return ()
|
||||
if isinstance(value, str):
|
||||
value = value.split(",")
|
||||
return tuple(sorted({_clean(item) for item in value if _clean(item)}))
|
||||
|
||||
|
||||
def _canonical(value: Any) -> str:
|
||||
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False, default=str)
|
||||
|
||||
|
||||
def _sha(value: Any) -> str:
|
||||
return hashlib.sha256(_canonical(value).encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def _now() -> str:
|
||||
return datetime.now(timezone.utc).isoformat()
|
||||
|
||||
|
||||
def _identifier(value: Any, code: str) -> str:
|
||||
text = _clean(value)
|
||||
if text is None or IDENTIFIER_RE.fullmatch(text) is None:
|
||||
raise GovernanceError(code)
|
||||
return text
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GovernanceScope:
|
||||
"""Explicit resource scope; system/global resources never get fake tenants."""
|
||||
|
||||
scope_type: str
|
||||
tenant_id: str | None = None
|
||||
user_id: str | None = None
|
||||
project_id: str | None = None
|
||||
conversation_id: str | None = None
|
||||
run_id: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
object.__setattr__(self, "scope_type", (_clean(self.scope_type) or "").lower())
|
||||
for name in SCOPE_FIELDS:
|
||||
object.__setattr__(self, name, _clean(getattr(self, name)))
|
||||
if self.scope_type == "tenant":
|
||||
if self.tenant_id is None:
|
||||
raise GovernanceError("GOVERNANCE_TENANT_ID_REQUIRED")
|
||||
elif self.scope_type in {"system", "global"}:
|
||||
if any(getattr(self, name) is not None for name in SCOPE_FIELDS):
|
||||
raise GovernanceError("GOVERNANCE_NON_TENANT_SCOPE_INVALID")
|
||||
elif self.scope_type == "legacy":
|
||||
if any(getattr(self, name) is not None for name in SCOPE_FIELDS):
|
||||
raise GovernanceError("GOVERNANCE_LEGACY_SCOPE_INVALID")
|
||||
else:
|
||||
raise GovernanceError("GOVERNANCE_SCOPE_TYPE_INVALID")
|
||||
|
||||
@classmethod
|
||||
def from_value(cls, value: Any) -> "GovernanceScope":
|
||||
def get(name: str) -> Any:
|
||||
return value.get(name) if isinstance(value, Mapping) else getattr(value, name, None)
|
||||
|
||||
declared = _clean(get("scope_type"))
|
||||
tenant_id = _clean(get("tenant_id"))
|
||||
return cls(
|
||||
scope_type=declared or ("tenant" if tenant_id else "legacy"),
|
||||
tenant_id=tenant_id,
|
||||
user_id=get("user_id"),
|
||||
project_id=get("project_id"),
|
||||
conversation_id=get("conversation_id"),
|
||||
run_id=get("run_id"),
|
||||
)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GovernanceActor:
|
||||
identity: str
|
||||
scope: GovernanceScope
|
||||
capabilities: tuple[str, ...] = ()
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
object.__setattr__(self, "identity", _identifier(self.identity, "GOVERNANCE_ACTOR_INVALID"))
|
||||
object.__setattr__(self, "capabilities", _scope_tuple(self.capabilities))
|
||||
|
||||
@classmethod
|
||||
def from_value(cls, value: Any) -> "GovernanceActor":
|
||||
if isinstance(value, cls):
|
||||
return value
|
||||
if not isinstance(value, Mapping):
|
||||
raise GovernanceError("GOVERNANCE_ACTOR_INVALID")
|
||||
return cls(
|
||||
identity=value.get("identity") or value.get("actor_id") or value.get("user_id"),
|
||||
scope=GovernanceScope.from_value(value),
|
||||
capabilities=_scope_tuple(value.get("capabilities") or value.get("capability_scope")),
|
||||
)
|
||||
|
||||
@property
|
||||
def privileged(self) -> bool:
|
||||
return bool(set(self.capabilities) & PRIVILEGED_CAPABILITIES)
|
||||
|
||||
|
||||
def authorize_scope(actor: GovernanceActor | Mapping[str, Any], resource: GovernanceScope | Mapping[str, Any]) -> None:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
resource = resource if isinstance(resource, GovernanceScope) else GovernanceScope.from_value(resource)
|
||||
if actor.privileged:
|
||||
return
|
||||
if resource.scope_type in {"system", "global"}:
|
||||
raise GovernanceError("GOVERNANCE_SYSTEM_SCOPE_AUTHZ_DENY")
|
||||
if resource.scope_type == "legacy":
|
||||
if actor.scope.scope_type != "legacy":
|
||||
raise GovernanceError("GOVERNANCE_LEGACY_SCOPE_AUTHZ_DENY")
|
||||
return
|
||||
if actor.scope.scope_type != "tenant":
|
||||
raise GovernanceError("GOVERNANCE_SCOPE_MISMATCH_DENY", field="scope_type")
|
||||
for name in SCOPE_FIELDS:
|
||||
expected = getattr(resource, name)
|
||||
actual = getattr(actor.scope, name)
|
||||
if expected is not None and expected != actual:
|
||||
raise GovernanceError("GOVERNANCE_SCOPE_MISMATCH_DENY", field=name)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TraceContext:
|
||||
trace_id: str
|
||||
span_id: str
|
||||
scope: GovernanceScope
|
||||
parent_span_id: str | None = None
|
||||
correlation_id: str | None = None
|
||||
causation_id: str | None = None
|
||||
task_id: str | None = None
|
||||
claim_id: str | None = None
|
||||
message_id: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
object.__setattr__(self, "trace_id", _identifier(self.trace_id, "TRACE_ID_INVALID"))
|
||||
object.__setattr__(self, "span_id", _identifier(self.span_id, "TRACE_SPAN_ID_INVALID"))
|
||||
for name in ("parent_span_id", "correlation_id", "causation_id", "task_id", "claim_id", "message_id"):
|
||||
value = _clean(getattr(self, name))
|
||||
if value is not None and IDENTIFIER_RE.fullmatch(value) is None:
|
||||
raise GovernanceError("TRACE_LINEAGE_IDENTIFIER_INVALID", field=name)
|
||||
object.__setattr__(self, name, value)
|
||||
|
||||
def child(self, *, span_id: str, actor: GovernanceActor | Mapping[str, Any], **lineage: Any) -> "TraceContext":
|
||||
authorize_scope(actor, self.scope)
|
||||
for name in ("trace_id", "task_id", "claim_id", "message_id", "correlation_id"):
|
||||
supplied = _clean(lineage.get(name))
|
||||
expected = getattr(self, name)
|
||||
if supplied is not None and expected is not None and supplied != expected:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONTINUITY", field=name)
|
||||
requested_scope = lineage.pop("scope", self.scope)
|
||||
requested_scope = requested_scope if isinstance(requested_scope, GovernanceScope) else GovernanceScope.from_value(requested_scope)
|
||||
if requested_scope != self.scope:
|
||||
raise GovernanceError("TRACE_SCOPE_MISMATCH_DENY")
|
||||
return TraceContext(
|
||||
trace_id=self.trace_id,
|
||||
span_id=span_id,
|
||||
parent_span_id=self.span_id,
|
||||
correlation_id=self.correlation_id,
|
||||
causation_id=_clean(lineage.get("causation_id")) or self.span_id,
|
||||
task_id=self.task_id,
|
||||
claim_id=self.claim_id,
|
||||
message_id=self.message_id,
|
||||
scope=self.scope,
|
||||
)
|
||||
|
||||
def as_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"trace_id": self.trace_id,
|
||||
"span_id": self.span_id,
|
||||
"parent_span_id": self.parent_span_id,
|
||||
"correlation_id": self.correlation_id,
|
||||
"causation_id": self.causation_id,
|
||||
"task_id": self.task_id,
|
||||
"claim_id": self.claim_id,
|
||||
"message_id": self.message_id,
|
||||
**self.scope.as_dict(),
|
||||
}
|
||||
|
||||
|
||||
def bind_trace_lineage(
|
||||
*,
|
||||
actor: GovernanceActor | Mapping[str, Any],
|
||||
task: Any,
|
||||
message: Any,
|
||||
trace_id: str,
|
||||
span_id: str,
|
||||
parent: TraceContext | None = None,
|
||||
) -> TraceContext:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
task_scope = GovernanceScope.from_value(task)
|
||||
message_scope = GovernanceScope.from_value(message)
|
||||
if task_scope != message_scope:
|
||||
raise GovernanceError("TRACE_SCOPE_MISMATCH_DENY")
|
||||
authorize_scope(actor, task_scope)
|
||||
|
||||
def get(value: Any, name: str) -> Any:
|
||||
return value.get(name) if isinstance(value, Mapping) else getattr(value, name, None)
|
||||
|
||||
task_id = _clean(get(task, "task_id"))
|
||||
message_task = _clean(get(message, "task_id"))
|
||||
if task_id and message_task and task_id != message_task:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONTINUITY", field="task_id")
|
||||
context = TraceContext(
|
||||
trace_id=trace_id,
|
||||
span_id=span_id,
|
||||
parent_span_id=parent.span_id if parent else None,
|
||||
correlation_id=_clean(get(task, "correlation_id")) or _clean(get(message, "correlation_id")),
|
||||
causation_id=_clean(get(message, "causation_id")) or (parent.span_id if parent else None),
|
||||
task_id=task_id or message_task,
|
||||
claim_id=_clean(get(task, "claim_id")) or _clean(get(message, "claim_id")),
|
||||
message_id=_clean(get(message, "envelope_id")) or _clean(get(message, "id")),
|
||||
scope=task_scope,
|
||||
)
|
||||
if parent is not None:
|
||||
if parent.trace_id != context.trace_id or parent.scope != context.scope:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONTINUITY")
|
||||
if parent.task_id and context.task_id and parent.task_id != context.task_id:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONTINUITY", field="task_id")
|
||||
return context
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ToolDescriptor:
|
||||
name: str
|
||||
kind: str
|
||||
scope: GovernanceScope
|
||||
required_capabilities: tuple[str, ...] = ()
|
||||
credential_ref: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
object.__setattr__(self, "name", _identifier(self.name, "TOOL_NAME_INVALID"))
|
||||
object.__setattr__(self, "kind", (_clean(self.kind) or "").lower())
|
||||
if self.kind not in {"tool", "mcp"}:
|
||||
raise GovernanceError("TOOL_KIND_INVALID")
|
||||
object.__setattr__(self, "required_capabilities", _scope_tuple(self.required_capabilities))
|
||||
if self.credential_ref is not None and REFERENCE_RE.fullmatch(self.credential_ref) is None:
|
||||
raise GovernanceError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CredentialGrant:
|
||||
grant_id: str
|
||||
credential_ref: str
|
||||
scope: GovernanceScope
|
||||
operations: tuple[str, ...]
|
||||
task_id: str | None = None
|
||||
tool_name: str | None = None
|
||||
expires_at: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
object.__setattr__(self, "grant_id", _identifier(self.grant_id, "CREDENTIAL_GRANT_ID_INVALID"))
|
||||
if REFERENCE_RE.fullmatch(self.credential_ref or "") is None:
|
||||
raise GovernanceError("CREDENTIAL_SECRET_EXPOSURE_DENY")
|
||||
object.__setattr__(self, "operations", _scope_tuple(self.operations))
|
||||
if not self.operations:
|
||||
raise GovernanceError("CREDENTIAL_OPERATIONS_REQUIRED")
|
||||
if self.expires_at is not None:
|
||||
parsed = datetime.fromisoformat(self.expires_at.replace("Z", "+00:00"))
|
||||
if parsed.tzinfo is None:
|
||||
raise GovernanceError("CREDENTIAL_EXPIRY_INVALID")
|
||||
|
||||
def authorize(
|
||||
self,
|
||||
actor: GovernanceActor | Mapping[str, Any],
|
||||
*,
|
||||
operation: str,
|
||||
task_id: str | None = None,
|
||||
tool_name: str | None = None,
|
||||
now: datetime | None = None,
|
||||
) -> str:
|
||||
try:
|
||||
authorize_scope(actor, self.scope)
|
||||
except GovernanceError as exc:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field=exc.field) from exc
|
||||
if operation not in self.operations:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field="operation")
|
||||
if self.task_id is not None and self.task_id != _clean(task_id):
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field="task_id")
|
||||
if self.tool_name is not None and self.tool_name != _clean(tool_name):
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field="tool_name")
|
||||
if self.expires_at is not None:
|
||||
current = (now or datetime.now(timezone.utc)).astimezone(timezone.utc)
|
||||
expiry = datetime.fromisoformat(self.expires_at.replace("Z", "+00:00")).astimezone(timezone.utc)
|
||||
if current >= expiry:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field="expires_at")
|
||||
return self.credential_ref
|
||||
|
||||
def public(self) -> dict[str, Any]:
|
||||
return {
|
||||
"grant_id": self.grant_id,
|
||||
"credential_ref": self.credential_ref,
|
||||
"operations": list(self.operations),
|
||||
"task_id": self.task_id,
|
||||
"tool_name": self.tool_name,
|
||||
"expires_at": self.expires_at,
|
||||
**self.scope.as_dict(),
|
||||
}
|
||||
|
||||
|
||||
_SCHEMA = """
|
||||
CREATE TABLE IF NOT EXISTS governance_schema_metadata (
|
||||
singleton INTEGER PRIMARY KEY CHECK(singleton=1),
|
||||
schema_version INTEGER NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS governed_tools (
|
||||
name TEXT PRIMARY KEY,
|
||||
kind TEXT NOT NULL,
|
||||
scope_json TEXT NOT NULL,
|
||||
required_capabilities_json TEXT NOT NULL,
|
||||
credential_ref TEXT,
|
||||
descriptor_sha256 TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS governed_trace_spans (
|
||||
trace_id TEXT NOT NULL,
|
||||
span_id TEXT NOT NULL,
|
||||
parent_span_id TEXT,
|
||||
context_json TEXT NOT NULL,
|
||||
context_sha256 TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
PRIMARY KEY(trace_id, span_id)
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS governed_credential_grants (
|
||||
grant_id TEXT PRIMARY KEY,
|
||||
grant_json TEXT NOT NULL,
|
||||
grant_sha256 TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS governed_tool_invocations (
|
||||
invocation_key TEXT PRIMARY KEY,
|
||||
request_sha256 TEXT NOT NULL,
|
||||
tool_name TEXT NOT NULL,
|
||||
task_id TEXT NOT NULL,
|
||||
claim_id TEXT NOT NULL,
|
||||
trace_id TEXT NOT NULL,
|
||||
span_id TEXT NOT NULL,
|
||||
status TEXT NOT NULL,
|
||||
receipt_sha256 TEXT,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL
|
||||
);
|
||||
CREATE TABLE IF NOT EXISTS governance_audit_evidence (
|
||||
sequence INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
evidence_id TEXT NOT NULL UNIQUE,
|
||||
action TEXT NOT NULL,
|
||||
actor_identity TEXT NOT NULL,
|
||||
trace_id TEXT,
|
||||
span_id TEXT,
|
||||
resource_id TEXT NOT NULL,
|
||||
outcome TEXT NOT NULL,
|
||||
details_json TEXT NOT NULL,
|
||||
previous_sha256 TEXT NOT NULL,
|
||||
evidence_sha256 TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL
|
||||
);
|
||||
"""
|
||||
|
||||
|
||||
class GovernanceStore:
|
||||
def __init__(self, path: str | Path) -> None:
|
||||
self.path = Path(path)
|
||||
self.path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with self._connection() as connection:
|
||||
has_metadata = connection.execute(
|
||||
"SELECT 1 FROM sqlite_master WHERE type='table' AND name='governance_schema_metadata'"
|
||||
).fetchone()
|
||||
if has_metadata:
|
||||
row = connection.execute(
|
||||
"SELECT schema_version FROM governance_schema_metadata WHERE singleton=1"
|
||||
).fetchone()
|
||||
if row is not None and int(row[0]) != 1:
|
||||
raise GovernanceError("GOVERNANCE_SCHEMA_VERSION_UNSUPPORTED")
|
||||
connection.executescript(_SCHEMA)
|
||||
row = connection.execute(
|
||||
"SELECT schema_version FROM governance_schema_metadata WHERE singleton=1"
|
||||
).fetchone()
|
||||
if row is None:
|
||||
connection.execute(
|
||||
"INSERT INTO governance_schema_metadata(singleton,schema_version) VALUES(1,1)"
|
||||
)
|
||||
connection.commit()
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
connection = sqlite3.connect(self.path, timeout=30.0)
|
||||
connection.row_factory = sqlite3.Row
|
||||
connection.execute("PRAGMA foreign_keys=ON")
|
||||
connection.execute("PRAGMA busy_timeout=30000")
|
||||
return connection
|
||||
|
||||
@contextmanager
|
||||
def _connection(self):
|
||||
connection = self._connect()
|
||||
try:
|
||||
yield connection
|
||||
connection.commit()
|
||||
except Exception:
|
||||
connection.rollback()
|
||||
raise
|
||||
finally:
|
||||
connection.close()
|
||||
|
||||
def _audit(
|
||||
self,
|
||||
connection: sqlite3.Connection,
|
||||
*,
|
||||
action: str,
|
||||
actor: GovernanceActor,
|
||||
resource_id: str,
|
||||
outcome: str,
|
||||
trace: TraceContext | None,
|
||||
details: Mapping[str, Any],
|
||||
) -> dict[str, Any]:
|
||||
previous = connection.execute(
|
||||
"SELECT evidence_sha256 FROM governance_audit_evidence ORDER BY sequence DESC LIMIT 1"
|
||||
).fetchone()
|
||||
previous_sha = str(previous[0]) if previous else ""
|
||||
created_at = _now()
|
||||
material = {
|
||||
"action": action,
|
||||
"actor_identity": actor.identity,
|
||||
"trace_id": trace.trace_id if trace else None,
|
||||
"span_id": trace.span_id if trace else None,
|
||||
"resource_id": resource_id,
|
||||
"outcome": outcome,
|
||||
"details": dict(details),
|
||||
"previous_sha256": previous_sha,
|
||||
"created_at": created_at,
|
||||
}
|
||||
digest = _sha(material)
|
||||
evidence_id = "gev-" + digest[:32]
|
||||
connection.execute(
|
||||
"""INSERT INTO governance_audit_evidence
|
||||
(evidence_id,action,actor_identity,trace_id,span_id,resource_id,outcome,
|
||||
details_json,previous_sha256,evidence_sha256,created_at)
|
||||
VALUES (?,?,?,?,?,?,?,?,?,?,?)""",
|
||||
(
|
||||
evidence_id, action, actor.identity, material["trace_id"], material["span_id"],
|
||||
resource_id, outcome, _canonical(material["details"]), previous_sha, digest, created_at,
|
||||
),
|
||||
)
|
||||
return {"evidence_id": evidence_id, "evidence_sha256": digest, **material}
|
||||
|
||||
def record_trace(self, trace: TraceContext, actor: GovernanceActor | Mapping[str, Any]) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
authorize_scope(actor, trace.scope)
|
||||
context = trace.as_dict()
|
||||
digest = _sha(context)
|
||||
with self._connection() as connection:
|
||||
existing = connection.execute(
|
||||
"SELECT context_sha256 FROM governed_trace_spans WHERE trace_id=? AND span_id=?",
|
||||
(trace.trace_id, trace.span_id),
|
||||
).fetchone()
|
||||
if existing is not None and existing[0] != digest:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONFLICT")
|
||||
if existing is not None:
|
||||
return {"context": context, "context_sha256": digest, "idempotent": True}
|
||||
if trace.parent_span_id:
|
||||
parent = connection.execute(
|
||||
"SELECT context_json FROM governed_trace_spans WHERE trace_id=? AND span_id=?",
|
||||
(trace.trace_id, trace.parent_span_id),
|
||||
).fetchone()
|
||||
if parent is None:
|
||||
raise GovernanceError("TRACE_LINEAGE_CONTINUITY", field="parent_span_id")
|
||||
parent_context = json.loads(parent[0])
|
||||
if GovernanceScope.from_value(parent_context) != trace.scope:
|
||||
raise GovernanceError("TRACE_SCOPE_MISMATCH_DENY")
|
||||
connection.execute(
|
||||
"INSERT OR IGNORE INTO governed_trace_spans VALUES (?,?,?,?,?,?)",
|
||||
(trace.trace_id, trace.span_id, trace.parent_span_id, _canonical(context), digest, _now()),
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="TRACE_RECORDED", actor=actor,
|
||||
resource_id=f"{trace.trace_id}:{trace.span_id}", outcome="ALLOW", trace=trace,
|
||||
details={"context_sha256": digest},
|
||||
)
|
||||
return {"context": context, "context_sha256": digest, "evidence": evidence}
|
||||
|
||||
def register_tool(self, descriptor: ToolDescriptor, actor: GovernanceActor | Mapping[str, Any]) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
if not actor.privileged:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
public = {
|
||||
"name": descriptor.name,
|
||||
"kind": descriptor.kind,
|
||||
"required_capabilities": list(descriptor.required_capabilities),
|
||||
"credential_ref": descriptor.credential_ref,
|
||||
**descriptor.scope.as_dict(),
|
||||
}
|
||||
digest = _sha(public)
|
||||
with self._connection() as connection:
|
||||
existing = connection.execute(
|
||||
"SELECT descriptor_sha256 FROM governed_tools WHERE name=?", (descriptor.name,)
|
||||
).fetchone()
|
||||
if existing is not None and existing[0] != digest:
|
||||
raise GovernanceError("TOOL_DESCRIPTOR_CONFLICT")
|
||||
if existing is not None:
|
||||
return {"descriptor": public, "descriptor_sha256": digest, "idempotent": True}
|
||||
connection.execute(
|
||||
"INSERT OR IGNORE INTO governed_tools VALUES (?,?,?,?,?,?)",
|
||||
(descriptor.name, descriptor.kind, _canonical(descriptor.scope.as_dict()),
|
||||
_canonical(descriptor.required_capabilities), descriptor.credential_ref, digest),
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="TOOL_REGISTERED", actor=actor, resource_id=descriptor.name,
|
||||
outcome="ALLOW", trace=None, details={"descriptor_sha256": digest},
|
||||
)
|
||||
return {"descriptor": public, "descriptor_sha256": digest, "evidence": evidence}
|
||||
|
||||
def authorize_tool(
|
||||
self,
|
||||
*,
|
||||
actor: GovernanceActor | Mapping[str, Any],
|
||||
tool_name: str,
|
||||
trace: TraceContext,
|
||||
requested_scope: GovernanceScope | Mapping[str, Any],
|
||||
input_digest: str,
|
||||
invocation_key: str,
|
||||
) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
invocation_key = _identifier(invocation_key, "TOOL_INVOCATION_KEY_INVALID")
|
||||
if not re.fullmatch(r"[0-9a-f]{64}", input_digest):
|
||||
raise GovernanceError("TOOL_INPUT_DIGEST_INVALID")
|
||||
if trace.task_id is None or trace.claim_id is None:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY", field="active_claim")
|
||||
requested_scope = requested_scope if isinstance(requested_scope, GovernanceScope) else GovernanceScope.from_value(requested_scope)
|
||||
if requested_scope != trace.scope:
|
||||
raise GovernanceError("TOOL_SCOPE_PROPAGATION")
|
||||
authorize_scope(actor, requested_scope)
|
||||
with self._connection() as connection:
|
||||
persisted_trace = connection.execute(
|
||||
"SELECT context_sha256 FROM governed_trace_spans WHERE trace_id=? AND span_id=?",
|
||||
(trace.trace_id, trace.span_id),
|
||||
).fetchone()
|
||||
if persisted_trace is None or persisted_trace[0] != _sha(trace.as_dict()):
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY", field="trace")
|
||||
row = connection.execute("SELECT * FROM governed_tools WHERE name=?", (tool_name,)).fetchone()
|
||||
if row is None:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
descriptor_scope = GovernanceScope.from_value(json.loads(row["scope_json"]))
|
||||
if descriptor_scope.scope_type == "tenant" and descriptor_scope != requested_scope:
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
required = set(json.loads(row["required_capabilities_json"]))
|
||||
if not required.issubset(set(actor.capabilities)):
|
||||
raise GovernanceError("TOOL_MCP_AUTHZ_DENY")
|
||||
request_sha = _sha({
|
||||
"tool_name": tool_name, "input_digest": input_digest,
|
||||
"task_id": trace.task_id, "claim_id": trace.claim_id,
|
||||
"trace_id": trace.trace_id, "span_id": trace.span_id,
|
||||
"scope": requested_scope.as_dict(),
|
||||
})
|
||||
replay = connection.execute(
|
||||
"SELECT * FROM governed_tool_invocations WHERE invocation_key=?",
|
||||
(invocation_key,),
|
||||
).fetchone()
|
||||
if replay is not None:
|
||||
if replay["request_sha256"] != request_sha:
|
||||
raise GovernanceError("TOOL_INVOCATION_IDEMPOTENCY_CONFLICT")
|
||||
if replay["status"] != "VERIFIED":
|
||||
raise GovernanceError("TOOL_INVOCATION_RECONCILIATION_REQUIRED")
|
||||
return {
|
||||
"tool_name": tool_name, "trace_id": trace.trace_id,
|
||||
"span_id": trace.span_id, "invocation_key": invocation_key,
|
||||
"status": "VERIFIED", "receipt_sha256": replay["receipt_sha256"],
|
||||
"idempotent": True,
|
||||
}
|
||||
created_at = _now()
|
||||
connection.execute(
|
||||
"""INSERT INTO governed_tool_invocations
|
||||
(invocation_key,request_sha256,tool_name,task_id,claim_id,trace_id,span_id,
|
||||
status,receipt_sha256,created_at,updated_at)
|
||||
VALUES(?,?,?,?,?,?,?,?,?,?,?)""",
|
||||
(invocation_key, request_sha, tool_name, trace.task_id, trace.claim_id,
|
||||
trace.trace_id, trace.span_id, "AUTHORIZED", None, created_at, created_at),
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="TOOL_AUTHORIZED", actor=actor, resource_id=tool_name,
|
||||
outcome="ALLOW", trace=trace,
|
||||
details={"input_sha256": input_digest, "scope_sha256": _sha(requested_scope.as_dict()),
|
||||
"invocation_key": invocation_key},
|
||||
)
|
||||
return {
|
||||
"tool_name": tool_name,
|
||||
"trace_id": trace.trace_id,
|
||||
"span_id": trace.span_id,
|
||||
"invocation_key": invocation_key,
|
||||
"status": "AUTHORIZED",
|
||||
"credential_required": row["credential_ref"] is not None,
|
||||
"evidence": evidence,
|
||||
}
|
||||
|
||||
def record_tool_receipt(
|
||||
self,
|
||||
*,
|
||||
invocation_key: str,
|
||||
result_digest: str,
|
||||
actor: GovernanceActor | Mapping[str, Any],
|
||||
trace: TraceContext,
|
||||
) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
invocation_key = _identifier(invocation_key, "TOOL_INVOCATION_KEY_INVALID")
|
||||
if not re.fullmatch(r"[0-9a-f]{64}", result_digest):
|
||||
raise GovernanceError("TOOL_RECEIPT_DIGEST_INVALID")
|
||||
authorize_scope(actor, trace.scope)
|
||||
with self._connection() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT * FROM governed_tool_invocations WHERE invocation_key=?",
|
||||
(invocation_key,),
|
||||
).fetchone()
|
||||
if row is None or row["trace_id"] != trace.trace_id or row["span_id"] != trace.span_id:
|
||||
raise GovernanceError("TOOL_RECEIPT_BINDING_INVALID")
|
||||
if row["status"] == "VERIFIED":
|
||||
if row["receipt_sha256"] != result_digest:
|
||||
raise GovernanceError("TOOL_RECEIPT_CONFLICT")
|
||||
return {"invocation_key": invocation_key, "status": "VERIFIED", "idempotent": True}
|
||||
if row["status"] != "AUTHORIZED":
|
||||
raise GovernanceError("TOOL_INVOCATION_RECONCILIATION_REQUIRED")
|
||||
connection.execute(
|
||||
"UPDATE governed_tool_invocations SET status='VERIFIED',receipt_sha256=?,updated_at=? "
|
||||
"WHERE invocation_key=? AND status='AUTHORIZED'",
|
||||
(result_digest, _now(), invocation_key),
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="TOOL_RESULT_VERIFIED", actor=actor,
|
||||
resource_id=row["tool_name"], outcome="ALLOW", trace=trace,
|
||||
details={"invocation_key": invocation_key, "result_sha256": result_digest},
|
||||
)
|
||||
return {"invocation_key": invocation_key, "status": "VERIFIED", "evidence": evidence}
|
||||
|
||||
def store_grant(self, grant: CredentialGrant, actor: GovernanceActor | Mapping[str, Any]) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
if not actor.privileged:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY")
|
||||
public = grant.public()
|
||||
digest = _sha(public)
|
||||
with self._connection() as connection:
|
||||
existing = connection.execute(
|
||||
"SELECT grant_sha256 FROM governed_credential_grants WHERE grant_id=?", (grant.grant_id,)
|
||||
).fetchone()
|
||||
if existing is not None and existing[0] != digest:
|
||||
raise GovernanceError("CREDENTIAL_GRANT_CONFLICT")
|
||||
connection.execute(
|
||||
"INSERT OR IGNORE INTO governed_credential_grants VALUES (?,?,?,?)",
|
||||
(grant.grant_id, _canonical(public), digest, _now()),
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="CREDENTIAL_GRANT_STORED", actor=actor,
|
||||
resource_id=grant.grant_id, outcome="ALLOW", trace=None,
|
||||
details={"grant_sha256": digest},
|
||||
)
|
||||
return {"grant": public, "grant_sha256": digest, "evidence": evidence}
|
||||
|
||||
def authorize_credential(
|
||||
self,
|
||||
*,
|
||||
grant_id: str,
|
||||
actor: GovernanceActor | Mapping[str, Any],
|
||||
trace: TraceContext,
|
||||
operation: str,
|
||||
task_id: str | None,
|
||||
tool_name: str | None,
|
||||
now: datetime | None = None,
|
||||
) -> dict[str, Any]:
|
||||
actor = GovernanceActor.from_value(actor)
|
||||
with self._connection() as connection:
|
||||
row = connection.execute(
|
||||
"SELECT grant_json FROM governed_credential_grants WHERE grant_id=?", (grant_id,)
|
||||
).fetchone()
|
||||
if row is None:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY")
|
||||
raw = json.loads(row[0])
|
||||
grant = CredentialGrant(
|
||||
grant_id=raw["grant_id"], credential_ref=raw["credential_ref"],
|
||||
scope=GovernanceScope.from_value(raw), operations=tuple(raw["operations"]),
|
||||
task_id=raw.get("task_id"), tool_name=raw.get("tool_name"),
|
||||
expires_at=raw.get("expires_at"),
|
||||
)
|
||||
if trace.scope != grant.scope:
|
||||
raise GovernanceError("CREDENTIAL_SCOPE_DENY", field="trace_scope")
|
||||
reference = grant.authorize(
|
||||
actor, operation=operation, task_id=task_id, tool_name=tool_name, now=now
|
||||
)
|
||||
evidence = self._audit(
|
||||
connection, action="CREDENTIAL_AUTHORIZED", actor=actor,
|
||||
resource_id=grant_id, outcome="ALLOW", trace=trace,
|
||||
details={"operation": operation, "task_id": task_id, "tool_name": tool_name,
|
||||
"credential_ref_sha256": _sha(reference)},
|
||||
)
|
||||
return {"credential_ref": reference, "evidence": evidence}
|
||||
|
||||
def verify_audit_chain(self, required_actions: Iterable[str] = ()) -> bool:
|
||||
ordered_actions: list[str] = []
|
||||
previous = ""
|
||||
with self._connection() as connection:
|
||||
rows = connection.execute("SELECT * FROM governance_audit_evidence ORDER BY sequence").fetchall()
|
||||
for row in rows:
|
||||
details = json.loads(row["details_json"])
|
||||
material = {
|
||||
"action": row["action"], "actor_identity": row["actor_identity"],
|
||||
"trace_id": row["trace_id"], "span_id": row["span_id"],
|
||||
"resource_id": row["resource_id"], "outcome": row["outcome"],
|
||||
"details": details, "previous_sha256": row["previous_sha256"],
|
||||
"created_at": row["created_at"],
|
||||
}
|
||||
if row["previous_sha256"] != previous or row["evidence_sha256"] != _sha(material):
|
||||
return False
|
||||
previous = row["evidence_sha256"]
|
||||
ordered_actions.append(row["action"])
|
||||
position = 0
|
||||
for required in required_actions:
|
||||
try:
|
||||
position = ordered_actions.index(required, position) + 1
|
||||
except ValueError:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
__all__ = [
|
||||
"CredentialGrant", "GovernanceActor", "GovernanceError", "GovernanceScope",
|
||||
"GovernanceStore", "ToolDescriptor", "TraceContext", "authorize_scope",
|
||||
"bind_trace_lineage",
|
||||
]
|
||||
@@ -0,0 +1,9 @@
|
||||
providers:
|
||||
oneapi:
|
||||
name: oneapi
|
||||
base_url: http://172.18.0.2:3000/v1
|
||||
key_env: OPENAI_API_KEY
|
||||
default_model: deepseek-v4-flash
|
||||
model:
|
||||
provider: oneapi
|
||||
name: deepseek-v4-flash
|
||||
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"argv": [
|
||||
"/usr/local/bin/hermes",
|
||||
"run",
|
||||
"--non-interactive"
|
||||
],
|
||||
"input_mode": "stdin_text",
|
||||
"max_output_bytes": 131072,
|
||||
"output_mode": "stdout_text",
|
||||
"runtime": "hermes",
|
||||
"schema": "aios.external-agent-runtime.profile.v1",
|
||||
"timeout_seconds": 900
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"argv": [
|
||||
"/opt/aios-hermes-agent/hermes-agent/.venv/bin/hermes",
|
||||
"-z",
|
||||
"{prompt}",
|
||||
"--provider",
|
||||
"oneapi",
|
||||
"-m",
|
||||
"{model_id}",
|
||||
"--no-restore-cwd"
|
||||
],
|
||||
"credential_env": {
|
||||
"OPENAI_API_KEY": {
|
||||
"credential": "aios-external-agent-oneapi-env",
|
||||
"format": "dotenv",
|
||||
"key": "ONEAPI_REGULAR_TOKEN"
|
||||
}
|
||||
},
|
||||
"environment": {
|
||||
"HERMES_HOME": "/etc/aios/external-agent-runtime.d/hermes-home"
|
||||
},
|
||||
"input_mode": "stdin_text",
|
||||
"max_output_bytes": 131072,
|
||||
"model_governance": {
|
||||
"max_output_tokens": 512,
|
||||
"model_capabilities": [
|
||||
"text"
|
||||
],
|
||||
"provider_ids": [
|
||||
"oneapi"
|
||||
],
|
||||
"required": true
|
||||
},
|
||||
"output_mode": "stdout_text",
|
||||
"runtime": "hermes",
|
||||
"schema": "aios.external-agent-runtime.profile.v1",
|
||||
"timeout_seconds": 180
|
||||
}
|
||||
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"tools": {
|
||||
"profile": "minimal"
|
||||
},
|
||||
"memory": {
|
||||
"search": {
|
||||
"enabled": false
|
||||
}
|
||||
},
|
||||
"agents": {
|
||||
"defaults": {
|
||||
"workspace": "/var/lib/aios-external-agent-executor/openclaw-workspace",
|
||||
"model": {
|
||||
"primary": "openai/deepseek-v4-flash"
|
||||
},
|
||||
"thinkingDefault": "off"
|
||||
},
|
||||
"entries": {
|
||||
"main": {
|
||||
"default": true,
|
||||
"workspace": "/var/lib/aios-external-agent-executor/openclaw-workspace"
|
||||
}
|
||||
}
|
||||
},
|
||||
"models": {
|
||||
"providers": {
|
||||
"openai": {
|
||||
"baseUrl": "http://172.18.0.2:3000/v1",
|
||||
"api": "openai-completions",
|
||||
"models": [
|
||||
{
|
||||
"id": "deepseek-v4-flash",
|
||||
"name": "deepseek-v4-flash",
|
||||
"contextWindow": 32768,
|
||||
"maxTokens": 256
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"argv": [
|
||||
"/usr/local/bin/openclaw",
|
||||
"run",
|
||||
"--non-interactive"
|
||||
],
|
||||
"input_mode": "stdin_text",
|
||||
"max_output_bytes": 131072,
|
||||
"output_mode": "stdout_text",
|
||||
"runtime": "openclaw",
|
||||
"schema": "aios.external-agent-runtime.profile.v1",
|
||||
"timeout_seconds": 900
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"argv": [
|
||||
"/usr/bin/node",
|
||||
"/opt/aios/openclaw-engineering/v2026.7.2-beta.7/openclaw.mjs",
|
||||
"agent",
|
||||
"--local",
|
||||
"--json",
|
||||
"--agent",
|
||||
"main",
|
||||
"--thinking",
|
||||
"off",
|
||||
"--message",
|
||||
"{prompt}",
|
||||
"--model",
|
||||
"{model_id}",
|
||||
"--timeout",
|
||||
"180"
|
||||
],
|
||||
"credential_env": {
|
||||
"OPENAI_API_KEY": {
|
||||
"credential": "aios-external-agent-oneapi-env",
|
||||
"format": "dotenv",
|
||||
"key": "ONEAPI_REGULAR_TOKEN"
|
||||
}
|
||||
},
|
||||
"environment": {
|
||||
"OPENCLAW_CONFIG_PATH": "/etc/aios/external-agent-runtime.d/openclaw-config.json",
|
||||
"OPENCLAW_HOME": "/var/lib/aios-external-agent-executor/openclaw-home",
|
||||
"OPENCLAW_STATE_DIR": "/var/lib/aios-external-agent-executor/openclaw-state"
|
||||
},
|
||||
"input_mode": "stdin_text",
|
||||
"max_output_bytes": 131072,
|
||||
"model_governance": {
|
||||
"input_reservation_floor_tokens": 16384,
|
||||
"max_output_tokens": 256,
|
||||
"model_capabilities": [
|
||||
"text"
|
||||
],
|
||||
"provider_ids": [
|
||||
"openai"
|
||||
],
|
||||
"required": true
|
||||
},
|
||||
"output_mode": "stdout_json",
|
||||
"runtime": "openclaw",
|
||||
"schema": "aios.external-agent-runtime.profile.v1",
|
||||
"timeout_seconds": 240
|
||||
}
|
||||
@@ -0,0 +1,95 @@
|
||||
{
|
||||
"models": [
|
||||
{
|
||||
"capabilities": [
|
||||
"agent.runtime.hermes",
|
||||
"text"
|
||||
],
|
||||
"enabled": true,
|
||||
"evaluation_sha256": "43ae0db1640daeb6d33e2787769732844f366d36070065d3a2239905bd9a823b",
|
||||
"evaluation_state": "APPROVED",
|
||||
"input_cost_micros_per_1k": 0,
|
||||
"max_input_tokens": 32768,
|
||||
"max_output_tokens": 512,
|
||||
"model_id": "deepseek-v4-flash",
|
||||
"output_cost_micros_per_1k": 0,
|
||||
"priority": 10,
|
||||
"provider_id": "oneapi",
|
||||
"version": "profile-sha:54615e533bfdb6a2e8b870ae74bb8cd7fc45177495bcf6e8c45a50837cefb85a"
|
||||
},
|
||||
{
|
||||
"capabilities": [
|
||||
"agent.runtime.openclaw",
|
||||
"text"
|
||||
],
|
||||
"enabled": true,
|
||||
"evaluation_sha256": "7b1c89634eb9c0e7cb5a3d75323d904ebbd91b3ae5494ce938bd8316a4cf5b12",
|
||||
"evaluation_state": "APPROVED",
|
||||
"input_cost_micros_per_1k": 0,
|
||||
"max_input_tokens": 32768,
|
||||
"max_output_tokens": 256,
|
||||
"model_id": "openai/deepseek-v4-flash",
|
||||
"output_cost_micros_per_1k": 0,
|
||||
"priority": 10,
|
||||
"provider_id": "openai",
|
||||
"version": "profile-sha:2a31c480226aa78d44ed9692bddcedc99c3aa03c23c0dd5f031a5cbbb8bbd7ba"
|
||||
}
|
||||
],
|
||||
"policies": [
|
||||
{
|
||||
"allowed_models": [
|
||||
"deepseek-v4-flash",
|
||||
"openai/deepseek-v4-flash"
|
||||
],
|
||||
"daily_cost_budget_micros": 0,
|
||||
"daily_token_budget": 250000,
|
||||
"denied_providers": [],
|
||||
"fallback_limit": 1,
|
||||
"max_input_tokens_per_request": 16384,
|
||||
"max_output_tokens_per_request": 512,
|
||||
"project_id": null,
|
||||
"required_capabilities": [
|
||||
"text"
|
||||
],
|
||||
"scope_type": "legacy",
|
||||
"tenant_id": null
|
||||
},
|
||||
{
|
||||
"allowed_models": [
|
||||
"deepseek-v4-flash",
|
||||
"openai/deepseek-v4-flash"
|
||||
],
|
||||
"daily_cost_budget_micros": 0,
|
||||
"daily_token_budget": 250000,
|
||||
"denied_providers": [],
|
||||
"fallback_limit": 1,
|
||||
"max_input_tokens_per_request": 16384,
|
||||
"max_output_tokens_per_request": 512,
|
||||
"project_id": "staging",
|
||||
"required_capabilities": [
|
||||
"text"
|
||||
],
|
||||
"scope_type": "tenant",
|
||||
"tenant_id": "model-governance-live"
|
||||
}
|
||||
],
|
||||
"providers": [
|
||||
{
|
||||
"cooldown_seconds": 60,
|
||||
"credential_ref": "runtime-profile:hermes",
|
||||
"enabled": true,
|
||||
"failure_domain": "oneapi",
|
||||
"max_failures": 2,
|
||||
"provider_id": "oneapi"
|
||||
},
|
||||
{
|
||||
"cooldown_seconds": 60,
|
||||
"credential_ref": "runtime-profile:openclaw",
|
||||
"enabled": true,
|
||||
"failure_domain": "oneapi",
|
||||
"max_failures": 2,
|
||||
"provider_id": "openai"
|
||||
}
|
||||
],
|
||||
"schema": "aios.model-governance.bootstrap.v1"
|
||||
}
|
||||
@@ -0,0 +1,36 @@
|
||||
-- R4.2 P0-B durable Message/Handoff Fabric.
|
||||
-- Forward-only. The existing 20260707 message_outbox remains a compatibility source.
|
||||
|
||||
CREATE TABLE IF NOT EXISTS message_handoff (
|
||||
envelope_id TEXT PRIMARY KEY,
|
||||
stream_key TEXT NOT NULL,
|
||||
source TEXT NOT NULL,
|
||||
target TEXT NOT NULL,
|
||||
message_type TEXT NOT NULL,
|
||||
payload_json TEXT NOT NULL,
|
||||
payload_sha256 TEXT NOT NULL,
|
||||
tenant_id TEXT,
|
||||
user_id TEXT,
|
||||
project_id TEXT,
|
||||
conversation_id TEXT,
|
||||
task_id TEXT,
|
||||
run_id TEXT,
|
||||
causation_id TEXT,
|
||||
sequence INTEGER NOT NULL CHECK(sequence >= 1),
|
||||
capability_scope_json TEXT NOT NULL,
|
||||
confidentiality_scope TEXT NOT NULL,
|
||||
idempotency_key TEXT NOT NULL,
|
||||
expires_at TEXT,
|
||||
created_at TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'PENDING',
|
||||
delivered_at TEXT,
|
||||
acked_at TEXT,
|
||||
UNIQUE(stream_key, idempotency_key),
|
||||
UNIQUE(stream_key, sequence)
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_message_handoff_target_status
|
||||
ON message_handoff(target, status, created_at);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_message_handoff_scope
|
||||
ON message_handoff(tenant_id, project_id, user_id, conversation_id, run_id);
|
||||
@@ -0,0 +1,37 @@
|
||||
[Unit]
|
||||
Description=AIOS owner-controlled Task execution-rebind API
|
||||
After=aios-agent-task-api.service
|
||||
Wants=aios-agent-task-api.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-agent-task
|
||||
Group=aios-agent-task
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
EnvironmentFile=/etc/aios-gitops/agent-task-execution-rebind.env
|
||||
Environment=AIOS_AGENT_TASK_DB=/var/lib/aios-agent-task/state.sqlite3
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_TASK_EXECUTION_REBIND_HOST=127.0.0.1
|
||||
Environment=AIOS_TASK_EXECUTION_REBIND_PORT=18942
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_agent_task_execution_rebind.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
ReadWritePaths=/var/lib/aios-agent-task
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,37 @@
|
||||
[Unit]
|
||||
Description=AIOS owner-controlled Task initial execution projection API
|
||||
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-agent-task
|
||||
Group=aios-agent-task
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
Environment=AIOS_AGENT_TASK_DB=/var/lib/aios-agent-task/state.sqlite3
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_TASK_INITIAL_EXECUTION_PROJECTION_AUTHORIZATION_ID=owner-initial-execution-projection-recovery-20260820
|
||||
Environment=AIOS_TASK_INITIAL_EXECUTION_PROJECTION_HOST=127.0.0.1
|
||||
Environment=AIOS_TASK_INITIAL_EXECUTION_PROJECTION_PORT=18943
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_agent_task_initial_execution_projection.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
ReadWritePaths=/var/lib/aios-agent-task
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,36 @@
|
||||
[Unit]
|
||||
Description=AIOS owner-controlled Task retry-extension API
|
||||
After=aios-agent-task-api.service
|
||||
Wants=aios-agent-task-api.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-agent-task
|
||||
Group=aios-agent-task
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
EnvironmentFile=/etc/aios-gitops/agent-task-retry-extension.env
|
||||
Environment=AIOS_AGENT_TASK_DB=/var/lib/aios-agent-task/state.sqlite3
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_TASK_RETRY_HOST=127.0.0.1
|
||||
Environment=AIOS_TASK_RETRY_PORT=18941
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_agent_task_retry_extension.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
ReadWritePaths=/var/lib/aios-agent-task
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,37 @@
|
||||
[Unit]
|
||||
Description=AIOS owner-controlled supervisor coordinator projection API
|
||||
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-agent-task
|
||||
Group=aios-agent-task
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
Environment=AIOS_AGENT_TASK_DB=/var/lib/aios-agent-task/state.sqlite3
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_TASK_INITIAL_EXECUTION_PROJECTION_AUTHORIZATION_ID=owner-supervisor-coordinator-projection-recovery-20260820
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_PROJECTION_HOST=127.0.0.1
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_PROJECTION_PORT=18944
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_agent_task_supervisor_coordinator_projection.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
ReadWritePaths=/var/lib/aios-agent-task
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,43 @@
|
||||
[Unit]
|
||||
Description=AIOS credential-isolated external Agent runtime executor
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-engineering-executor
|
||||
Group=aios-executor-exchange
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_external_agent_runtime.py --root /var/lib/aios-external-agent-executor --profile-root /etc/aios/external-agent-runtime.d
|
||||
Restart=always
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
|
||||
IPAddressDeny=127.0.0.0/8
|
||||
IPAddressDeny=::1/128
|
||||
IPAddressAllow=172.18.0.2/32
|
||||
LoadCredential=aios-external-agent-oneapi-env:/data/agent/secrets/oneapi-model-ready.env
|
||||
InaccessiblePaths=/etc/aios-gitops
|
||||
InaccessiblePaths=/data/aios-gitops
|
||||
InaccessiblePaths=/data/agent/secrets
|
||||
ReadOnlyPaths=/etc/aios/external-agent-runtime.d
|
||||
ReadOnlyPaths=/opt/aios-hermes-agent
|
||||
ReadOnlyPaths=/opt/aios/openclaw-engineering
|
||||
Environment=AIOS_MODEL_GOVERNANCE_DB=/var/lib/aios-model-governance/state.sqlite3
|
||||
Environment=AIOS_MODEL_GOVERNANCE_ENABLED=1
|
||||
ReadWritePaths=/var/lib/aios-external-agent-executor
|
||||
ReadWritePaths=/var/lib/aios-model-governance
|
||||
UMask=0027
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,41 @@
|
||||
[Unit]
|
||||
Description=AIOS disabled-by-default HTTPS edge for GPT read-only Online Task ingress
|
||||
After=network-online.target aios-gpt-online-task-ingress.service
|
||||
Wants=network-online.target aios-gpt-online-task-ingress.service
|
||||
ConditionPathExists=/etc/aios-gitops/gpt-https-edge.approved
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
DynamicUser=yes
|
||||
LoadCredential=tls_cert:/etc/aios-gitops/gpt-https-edge-tls.crt
|
||||
LoadCredential=tls_key:/etc/aios-gitops/gpt-https-edge-tls.key
|
||||
Environment=AIOS_GPT_EDGE_TLS_CERT_FILE=%d/tls_cert
|
||||
Environment=AIOS_GPT_EDGE_TLS_KEY_FILE=%d/tls_key
|
||||
Environment=AIOS_GPT_EDGE_HOST=127.0.0.1
|
||||
Environment=AIOS_GPT_EDGE_PORT=18443
|
||||
Environment=AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=0
|
||||
Environment=AIOS_GPT_EDGE_PUBLIC_DOMAIN=
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_gpt_https_edge.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=yes
|
||||
PrivateTmp=yes
|
||||
PrivateDevices=yes
|
||||
ProtectSystem=strict
|
||||
ProtectHome=yes
|
||||
ProtectKernelTunables=yes
|
||||
ProtectKernelModules=yes
|
||||
ProtectControlGroups=yes
|
||||
ProtectKernelLogs=yes
|
||||
ProtectClock=yes
|
||||
LockPersonality=yes
|
||||
RestrictSUIDSGID=yes
|
||||
RestrictRealtime=yes
|
||||
RestrictNamespaces=yes
|
||||
MemoryDenyWriteExecute=yes
|
||||
RestrictAddressFamilies=AF_INET AF_INET6
|
||||
InaccessiblePaths=/data/aios-gitops /etc/aios-gitops /home /var/lib/aios-agent-task
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,45 @@
|
||||
[Unit]
|
||||
Description=AIOS external GPT read-only Online Task ingress
|
||||
After=network.target aios-chatgpt-bridge-v2-staging.service aios-agent-task-api.service
|
||||
Wants=aios-chatgpt-bridge-v2-staging.service aios-agent-task-api.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
DynamicUser=yes
|
||||
StateDirectory=aios-gpt-online-task-ingress
|
||||
StateDirectoryMode=0750
|
||||
LoadCredential=gpt_ingress_token:/etc/aios-gitops/gpt-online-task-ingress.token
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
Environment=AIOS_GPT_INGRESS_TOKEN_FILE=%d/gpt_ingress_token
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_GPT_INGRESS_STATE_ROOT=%S/aios-gpt-online-task-ingress
|
||||
Environment=AIOS_GPT_INGRESS_HOST=127.0.0.1
|
||||
Environment=AIOS_GPT_INGRESS_PORT=18945
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_gpt_online_task_ingress.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=yes
|
||||
PrivateTmp=yes
|
||||
PrivateDevices=yes
|
||||
ProtectSystem=strict
|
||||
ProtectHome=yes
|
||||
ProtectKernelTunables=yes
|
||||
ProtectKernelModules=yes
|
||||
ProtectControlGroups=yes
|
||||
ProtectKernelLogs=yes
|
||||
ProtectClock=yes
|
||||
LockPersonality=yes
|
||||
RestrictSUIDSGID=yes
|
||||
RestrictRealtime=yes
|
||||
RestrictNamespaces=yes
|
||||
MemoryDenyWriteExecute=yes
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
IPAddressDeny=any
|
||||
IPAddressAllow=127.0.0.0/8
|
||||
InaccessiblePaths=/data/aios-gitops /etc/aios-gitops /home
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,48 @@
|
||||
[Unit]
|
||||
Description=AIOS Hermes Online Agent Worker
|
||||
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service aios-external-agent-executor.service
|
||||
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service aios-external-agent-executor.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-engineering-worker
|
||||
Group=aios-engineering-worker
|
||||
SupplementaryGroups=gitops aios-executor-exchange
|
||||
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-online-agent-worker-20260815/agent_token
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_ID=online-hermes-worker-cn-network-mkt
|
||||
Environment=AIOS_AGENT_TYPE=external-agent-runtime-worker
|
||||
Environment=AIOS_AGENT_VERSION=2026-08-18.1-hermes-runtime
|
||||
Environment=AIOS_WORKER_CAPABILITIES=agent.runtime.hermes
|
||||
Environment=AIOS_WORKER_ALLOWED_ADAPTERS=hermes
|
||||
Environment=AIOS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
|
||||
Environment=AIOS_EXTERNAL_AGENT_EXECUTOR_ROOT=/var/lib/aios-external-agent-executor
|
||||
Environment=AIOS_WORKER_STATE_ROOT=/var/lib/aios-online-agent-hermes
|
||||
Environment=AIOS_WORKER_CHECKPOINT_DB=/var/lib/aios-online-agent-hermes/checkpoints.sqlite3
|
||||
Environment=AIOS_WORKER_WORKSPACE_ROOT=/var/lib/aios-online-agent-hermes/workspaces
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_online_agent_worker.py
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
TimeoutStopSec=20
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
|
||||
ReadOnlyPaths=/data/aios-gitops/repo.git
|
||||
ReadWritePaths=/var/lib/aios-online-agent-hermes
|
||||
ReadWritePaths=/var/lib/aios-external-agent-executor
|
||||
UMask=0027
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,33 @@
|
||||
[Unit]
|
||||
Description=AIOS uncredentialed deterministic Planner/Executor
|
||||
After=local-fs.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-engineering-executor
|
||||
Group=aios-executor-exchange
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_isolated_executor.py --root /var/lib/aios-online-agent-executor
|
||||
Restart=always
|
||||
RestartSec=2
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
PrivateNetwork=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
IPAddressDeny=any
|
||||
IPAddressAllow=localhost
|
||||
InaccessiblePaths=/run/credentials
|
||||
ReadWritePaths=/var/lib/aios-online-agent-executor
|
||||
UMask=0027
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,46 @@
|
||||
[Unit]
|
||||
Description=AIOS governed Online Agent Worker
|
||||
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-engineering-worker
|
||||
Group=aios-engineering-worker
|
||||
SupplementaryGroups=gitops aios-executor-exchange
|
||||
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-online-agent-worker-20260815/agent_token
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_ID=online-engineering-worker
|
||||
Environment=AIOS_AGENT_TYPE=trusted-online-engineering-worker
|
||||
Environment=AIOS_AGENT_VERSION=2026-08-17.2-durable
|
||||
Environment=AIOS_WORKER_CAPABILITIES=git.read,git.test,governed.write.branch,governed.write.file
|
||||
Environment=AIOS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
|
||||
Environment=AIOS_ISOLATED_EXECUTOR_ROOT=/var/lib/aios-online-agent-executor
|
||||
Environment=AIOS_WORKER_STATE_ROOT=/var/lib/aios-online-agent-worker
|
||||
Environment=AIOS_WORKER_CHECKPOINT_DB=/var/lib/aios-online-agent-worker/checkpoints.sqlite3
|
||||
Environment=AIOS_WORKER_WORKSPACE_ROOT=/var/lib/aios-online-agent-worker/workspaces
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_online_agent_worker.py
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
TimeoutStopSec=20
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
|
||||
ReadOnlyPaths=/data/aios-gitops/repo.git
|
||||
ReadWritePaths=/var/lib/aios-online-agent-worker
|
||||
UMask=0027
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,48 @@
|
||||
[Unit]
|
||||
Description=AIOS OpenClaw Online Agent Worker
|
||||
After=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service aios-external-agent-executor.service
|
||||
Wants=aios-agent-task-api.service aios-chatgpt-bridge-v2-staging.service aios-external-agent-executor.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-engineering-worker
|
||||
Group=aios-engineering-worker
|
||||
SupplementaryGroups=gitops aios-executor-exchange
|
||||
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-online-agent-worker-20260815/agent_token
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
|
||||
Environment=AIOS_AGENT_ID=online-openclaw-worker-cn-network-mkt
|
||||
Environment=AIOS_AGENT_TYPE=external-agent-runtime-worker
|
||||
Environment=AIOS_AGENT_VERSION=2026-08-18.1-openclaw-runtime
|
||||
Environment=AIOS_WORKER_CAPABILITIES=agent.runtime.openclaw
|
||||
Environment=AIOS_WORKER_ALLOWED_ADAPTERS=openclaw
|
||||
Environment=AIOS_AUTHORITY_GIT_DIR=/data/aios-gitops/repo.git
|
||||
Environment=AIOS_EXTERNAL_AGENT_EXECUTOR_ROOT=/var/lib/aios-external-agent-executor
|
||||
Environment=AIOS_WORKER_STATE_ROOT=/var/lib/aios-online-agent-openclaw
|
||||
Environment=AIOS_WORKER_CHECKPOINT_DB=/var/lib/aios-online-agent-openclaw/checkpoints.sqlite3
|
||||
Environment=AIOS_WORKER_WORKSPACE_ROOT=/var/lib/aios-online-agent-openclaw/workspaces
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_online_agent_worker.py
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
TimeoutStopSec=20
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
|
||||
ReadOnlyPaths=/data/aios-gitops/repo.git
|
||||
ReadWritePaths=/var/lib/aios-online-agent-openclaw
|
||||
ReadWritePaths=/var/lib/aios-external-agent-executor
|
||||
UMask=0027
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,47 @@
|
||||
[Unit]
|
||||
Description=AIOS durable Owner authorization broker
|
||||
After=network.target aios-chatgpt-bridge-v2-staging.service
|
||||
Wants=aios-chatgpt-bridge-v2-staging.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=root
|
||||
Group=aios-executor-exchange
|
||||
RuntimeDirectory=aios-owner-authorization-broker
|
||||
RuntimeDirectoryMode=0750
|
||||
StateDirectory=aios-owner-authorization-broker
|
||||
StateDirectoryMode=0750
|
||||
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
|
||||
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
|
||||
Environment=AIOS_OWNER_DURABLE_AUTHORIZATION_POLICY=/etc/aios-gitops/owner-durable-authorization.json
|
||||
Environment=AIOS_OWNER_DURABLE_AUTHORIZATION_REVOCATIONS=/etc/aios-gitops/owner-durable-authorization-revocations.json
|
||||
Environment=AIOS_OWNER_AUTH_BROKER_ACCOUNT=chatgpt-governed-implementer-singlehost
|
||||
Environment=AIOS_OWNER_AUTH_BROKER_SOCKET=%t/aios-owner-authorization-broker/broker.sock
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_durable_owner_authorization.py
|
||||
Restart=on-failure
|
||||
RestartSec=2
|
||||
NoNewPrivileges=yes
|
||||
PrivateTmp=yes
|
||||
PrivateDevices=yes
|
||||
ProtectSystem=strict
|
||||
ProtectHome=yes
|
||||
ProtectKernelTunables=yes
|
||||
ProtectKernelModules=yes
|
||||
ProtectControlGroups=yes
|
||||
ProtectKernelLogs=yes
|
||||
ProtectClock=yes
|
||||
LockPersonality=yes
|
||||
RestrictSUIDSGID=yes
|
||||
RestrictRealtime=yes
|
||||
RestrictNamespaces=yes
|
||||
MemoryDenyWriteExecute=yes
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
IPAddressDeny=any
|
||||
IPAddressAllow=127.0.0.0/8
|
||||
ReadOnlyPaths=/etc/aios-gitops/owner-durable-authorization.json
|
||||
ReadOnlyPaths=/etc/aios-gitops/owner-durable-authorization-revocations.json
|
||||
InaccessiblePaths=/data/aios-gitops /home
|
||||
UMask=0007
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,50 @@
|
||||
[Unit]
|
||||
Description=AIOS release-candidate Online Agent worker
|
||||
After=network.target aios-agent-task-api.service
|
||||
Wants=aios-agent-task-api.service
|
||||
|
||||
[Service]
|
||||
Type=notify
|
||||
NotifyAccess=main
|
||||
WatchdogSec=90
|
||||
User=root
|
||||
Group=root
|
||||
StateDirectory=aios-online-agent-release
|
||||
StateDirectoryMode=0750
|
||||
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-release-online-agent-worker/agent_token
|
||||
LoadCredentialEncrypted=release_candidate_token:/etc/credstore.encrypted/aios-release-online-agent-worker/release_candidate_token
|
||||
Environment=AIOS_RELEASE_WORKER_AGENT_ID=online-release-worker-cn-network-mkt-20260819
|
||||
Environment=AIOS_RELEASE_WORKER_AGENT_VERSION=2026-08-19.1-release-candidate
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
Environment=AIOS_RELEASE_WORKER_STATE_ROOT=/var/lib/aios-online-agent-release
|
||||
Environment=AIOS_WORKER_STATE_ROOT=/var/lib/aios-online-agent-release
|
||||
Environment=AIOS_RELEASE_WORKER_POLL_SECONDS=3
|
||||
Environment=AIOS_RELEASE_WORKER_LEASE_SECONDS=60
|
||||
Environment=AIOS_RELEASE_WORKER_HEARTBEAT_SECONDS=15
|
||||
Environment=AIOS_RELEASE_API_URL=http://127.0.0.1:18890
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_release_online_agent_worker.py
|
||||
Restart=always
|
||||
RestartSec=2
|
||||
NoNewPrivileges=yes
|
||||
PrivateTmp=yes
|
||||
PrivateDevices=yes
|
||||
ProtectSystem=strict
|
||||
ProtectHome=yes
|
||||
ProtectKernelTunables=yes
|
||||
ProtectKernelModules=yes
|
||||
ProtectControlGroups=yes
|
||||
ProtectKernelLogs=yes
|
||||
ProtectClock=yes
|
||||
LockPersonality=yes
|
||||
RestrictSUIDSGID=yes
|
||||
RestrictRealtime=yes
|
||||
RestrictNamespaces=yes
|
||||
MemoryDenyWriteExecute=yes
|
||||
RestrictAddressFamilies=AF_UNIX AF_INET
|
||||
IPAddressDeny=any
|
||||
IPAddressAllow=127.0.0.0/8
|
||||
InaccessiblePaths=/data/aios-gitops /home
|
||||
UMask=0077
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,45 @@
|
||||
[Unit]
|
||||
Description=AIOS credential-isolated release-preparation supervisor coordinator
|
||||
After=network-online.target aios-agent-task-api.service aios-autonomous-agent-register.service
|
||||
Wants=network-online.target aios-agent-task-api.service
|
||||
Requires=aios-autonomous-agent-register.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=aios-autonomous-agent-worker
|
||||
Group=aios-autonomous-agent-worker
|
||||
SupplementaryGroups=aios-agent-runtime
|
||||
LoadCredentialEncrypted=agent_token:/etc/credstore.encrypted/aios-autonomous-agent-worker/agent_token
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
|
||||
Environment=AIOS_AGENT_ID=online-engineering-worker-cn-network-mkt-autonomous-20260815
|
||||
Environment=AIOS_RELEASE_PREPARATION_SUPERVISOR_TASK_ID=r42-release-preparation-autonomous-supervisor-20260820
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_STATE_ROOT=/var/lib/aios-release-preparation-supervisor-coordinator
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_POLL_SECONDS=5
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_HEARTBEAT_SECONDS=10
|
||||
Environment=AIOS_SUPERVISOR_COORDINATOR_LEASE_SECONDS=300
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_release_preparation_supervisor_coordinator.py
|
||||
Restart=always
|
||||
RestartSec=5
|
||||
TimeoutStopSec=20
|
||||
UMask=0027
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_INET AF_UNIX
|
||||
ReadWritePaths=/var/lib/aios-release-preparation-supervisor-coordinator
|
||||
InaccessiblePaths=-/etc/credstore.encrypted
|
||||
CapabilityBoundingSet=
|
||||
AmbientCapabilities=
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
@@ -0,0 +1,27 @@
|
||||
[Unit]
|
||||
Description=AIOS persistent Online Agent worker availability guard
|
||||
After=local-fs.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=root
|
||||
Group=root
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Environment=AIOS_WORKER_AVAILABILITY_MAX_STALE_SECONDS=90
|
||||
Environment=AIOS_WORKER_AVAILABILITY_RESTART_COOLDOWN_SECONDS=60
|
||||
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_worker_availability_guard.py --heal
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ProtectKernelTunables=true
|
||||
ProtectKernelModules=true
|
||||
ProtectControlGroups=true
|
||||
LockPersonality=true
|
||||
RestrictSUIDSGID=true
|
||||
RestrictRealtime=true
|
||||
RestrictNamespaces=true
|
||||
MemoryDenyWriteExecute=true
|
||||
RestrictAddressFamilies=AF_UNIX
|
||||
ReadWritePaths=/run/aios-worker-availability
|
||||
UMask=0022
|
||||
@@ -0,0 +1,13 @@
|
||||
[Unit]
|
||||
Description=Periodically ensure AIOS Online Agent workers remain available
|
||||
|
||||
[Timer]
|
||||
OnBootSec=15s
|
||||
OnUnitActiveSec=30s
|
||||
AccuracySec=5s
|
||||
RandomizedDelaySec=3s
|
||||
Persistent=true
|
||||
Unit=aios-worker-availability-guard.service
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
@@ -0,0 +1,4 @@
|
||||
g aios-executor-exchange -
|
||||
u aios-engineering-executor - "AIOS isolated engineering executor" /var/lib/aios-online-agent-executor /usr/sbin/nologin
|
||||
m aios-engineering-executor aios-executor-exchange
|
||||
m aios-engineering-worker aios-executor-exchange
|
||||
@@ -0,0 +1,12 @@
|
||||
d /var/lib/aios-external-agent-executor 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/requests 2770 aios-engineering-worker aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/results 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/failed 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/openclaw-workspace 0750 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/openclaw-state 0750 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-external-agent-executor/openclaw-home 0750 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-online-agent-hermes 0750 aios-engineering-worker aios-engineering-worker -
|
||||
d /var/lib/aios-online-agent-hermes/workspaces 0750 aios-engineering-worker aios-engineering-worker -
|
||||
d /var/lib/aios-online-agent-openclaw 0750 aios-engineering-worker aios-engineering-worker -
|
||||
d /var/lib/aios-online-agent-openclaw/workspaces 0750 aios-engineering-worker aios-engineering-worker -
|
||||
d /etc/aios/external-agent-runtime.d 0755 root root -
|
||||
@@ -0,0 +1 @@
|
||||
d /var/lib/aios-model-governance 0750 aios-engineering-executor aios-executor-exchange -
|
||||
@@ -0,0 +1,5 @@
|
||||
d /var/lib/aios-online-agent-executor 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-online-agent-executor/requests 2770 aios-engineering-worker aios-executor-exchange -
|
||||
d /var/lib/aios-online-agent-executor/results 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-online-agent-executor/failed 2770 aios-engineering-executor aios-executor-exchange -
|
||||
d /var/lib/aios-online-agent-executor/sources 2770 aios-engineering-worker aios-executor-exchange -
|
||||
@@ -0,0 +1 @@
|
||||
d /run/aios-worker-availability 0755 root root -
|
||||
@@ -240,6 +240,114 @@ components:
|
||||
additionalProperties: false
|
||||
properties:
|
||||
candidate_id: {type: string}
|
||||
BridgeWriterLeaseRecoveryRequest:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
required: [schema, task_id, repository, branch_mode, base_oid, expected_branch_oid, target_branch, generation, lease_seconds]
|
||||
properties:
|
||||
schema:
|
||||
type: string
|
||||
enum: [aios.task-writer-lease.v2, aios.task-writer-lease-request.v2]
|
||||
task_id: {type: string, minLength: 1, maxLength: 256}
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
repository: {type: string, const: aios/aios}
|
||||
branch_mode: {type: string, enum: [CREATE_NEW, CONTINUE_EXISTING]}
|
||||
base_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
expected_branch_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
lease_seconds: {type: integer, minimum: 1, maximum: 86400}
|
||||
BridgeWriterLeaseResponse:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
required: [schema, task_id, job_id, repository, branch_mode, base_oid, expected_branch_oid, target_branch, generation, lease_seconds, create_target_branch, worktree_mode, cas_ref_update_required]
|
||||
properties:
|
||||
schema: {type: string, enum: [aios.task-writer-lease.v2]}
|
||||
task_id: {type: string}
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
repository: {type: string, const: aios/aios}
|
||||
branch_mode: {type: string, enum: [CREATE_NEW, CONTINUE_EXISTING]}
|
||||
base_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
expected_branch_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
lease_seconds: {type: integer, minimum: 1, maximum: 86400}
|
||||
create_target_branch: {type: boolean}
|
||||
worktree_mode: {type: string, enum: [detached_at_base_oid, detached_at_expected_head]}
|
||||
cas_ref_update_required: {type: boolean, const: true}
|
||||
lease_expires_at: {type: string, format: date-time}
|
||||
BridgeWriterLeaseRecoveryResponse:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
required: [schema, task_id, job_id, repository, branch_mode, base_oid, expected_branch_oid, target_branch, generation, lease_seconds, lease_expires_at, create_target_branch, worktree_mode, cas_ref_update_required, recovered, bootstrapped, idempotent, runtime_rehydrated, durable_branch_lease_present]
|
||||
properties:
|
||||
schema: {type: string, enum: [aios.task-writer-lease.v2]}
|
||||
task_id: {type: string}
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
repository: {type: string, const: aios/aios}
|
||||
branch_mode: {type: string, enum: [CREATE_NEW, CONTINUE_EXISTING]}
|
||||
base_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
expected_branch_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
lease_seconds: {type: integer, minimum: 1, maximum: 86400}
|
||||
lease_expires_at: {type: string, format: date-time}
|
||||
create_target_branch: {type: boolean, const: false}
|
||||
worktree_mode: {type: string, enum: [detached_at_base_oid, detached_at_expected_head]}
|
||||
cas_ref_update_required: {type: boolean, const: true}
|
||||
recovered: {type: boolean}
|
||||
bootstrapped: {type: boolean}
|
||||
idempotent: {type: boolean}
|
||||
runtime_rehydrated: {type: boolean}
|
||||
durable_branch_lease_present: {type: boolean}
|
||||
BridgeCommitFileRequest:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
required: [task_id, repository, expected_branch_oid, target_branch, generation, idempotency_key, path, content_base64, message]
|
||||
properties:
|
||||
task_id: {type: string, minLength: 1}
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
repository: {type: string, const: aios/aios}
|
||||
expected_branch_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
idempotency_key: {type: string, minLength: 1, maxLength: 256}
|
||||
path: {type: string, minLength: 1, maxLength: 512}
|
||||
content_base64: {type: string, format: byte}
|
||||
message: {type: string, minLength: 1, maxLength: 200}
|
||||
BridgeCommitFilesRequest:
|
||||
type: object
|
||||
additionalProperties: false
|
||||
required: [task_id, repository, expected_branch_oid, target_branch, generation, idempotency_key, files, message]
|
||||
properties:
|
||||
task_id: {type: string, minLength: 1}
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
repository: {type: string, const: aios/aios}
|
||||
expected_branch_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
idempotency_key: {type: string, minLength: 1, maxLength: 256}
|
||||
files: {type: object, additionalProperties: {type: string, format: byte}, minProperties: 1}
|
||||
message: {type: string, minLength: 1, maxLength: 200}
|
||||
BridgeCommitResponse:
|
||||
type: object
|
||||
additionalProperties: true
|
||||
required: [job_id, commit_oid, commit_visible, branch_mode, target_branch, generation]
|
||||
properties:
|
||||
job_id: {type: string, pattern: '^job-[A-Za-z0-9][A-Za-z0-9._-]{7,255}$'}
|
||||
commit_oid: {type: string, pattern: '^[0-9a-f]{40}$'}
|
||||
commit_visible: {type: boolean}
|
||||
branch_mode: {type: string, enum: [CONTINUE_EXISTING]}
|
||||
target_branch: {type: string, pattern: '^agent/[A-Za-z0-9][A-Za-z0-9._/-]{2,179}$'}
|
||||
generation: {type: integer, minimum: 1}
|
||||
BridgeGovernedCapabilities:
|
||||
type: object
|
||||
required: [bridge_schema_version, governed_writes_enabled, operations, operation_contracts]
|
||||
properties:
|
||||
bridge_schema_version: {type: string, const: aios.chatgpt-gitops-bridge.v2}
|
||||
governed_writes_enabled: {type: boolean, const: true}
|
||||
operations: {type: array, items: {type: string}}
|
||||
operation_contracts: {type: object, additionalProperties: true}
|
||||
paths:
|
||||
/createReleaseIntent:
|
||||
post:
|
||||
@@ -567,3 +675,118 @@ paths:
|
||||
'200': {description: Safe GitOps plan}
|
||||
'401': {description: Unauthorized}
|
||||
x-openai-isConsequential: true
|
||||
/v2/capabilities:
|
||||
get:
|
||||
operationId: getGovernedWriteCapabilities
|
||||
summary: Read the governed Bridge v2 capability contract
|
||||
responses:
|
||||
'200':
|
||||
description: Governed operations and their request/response contracts
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeGovernedCapabilities'}
|
||||
/v2/writer-lease:
|
||||
post:
|
||||
operationId: acquireWriterLease
|
||||
summary: Acquire the exact governed writer lease for a task generation
|
||||
security: [{bearerAuth: []}]
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseRecoveryRequest'}
|
||||
responses:
|
||||
'200':
|
||||
description: Exact detached worktree lease binding
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseResponse'}
|
||||
'400': {description: Invalid lease binding}
|
||||
'409': {description: Branch, base, or generation conflict}
|
||||
x-openai-isConsequential: true
|
||||
/v2/writer-lease/bootstrap:
|
||||
post:
|
||||
operationId: bootstrapWriterLease
|
||||
summary: Bootstrap a governed writer runtime without creating a durable lease
|
||||
description: >
|
||||
Staging-only runtime recovery. It validates the exact task, repository,
|
||||
base OID, expected branch OID, target branch, and generation. It must
|
||||
not create a branch, insert a branch lease, or consume a generation.
|
||||
security: [{bearerAuth: []}]
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseRecoveryRequest'}
|
||||
responses:
|
||||
'200':
|
||||
description: Runtime binding bootstrapped or returned idempotently
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseRecoveryResponse'}
|
||||
'400': {description: Invalid lease binding}
|
||||
'409': {description: A matching durable lease already exists or binding conflicts}
|
||||
'503': {description: Runtime or durable state unavailable}
|
||||
x-openai-isConsequential: true
|
||||
/v2/writer-lease/renew:
|
||||
post:
|
||||
operationId: renewWriterLease
|
||||
summary: Recover an expired governed writer lease without changing its binding
|
||||
description: >
|
||||
Renews only the current task generation and exact repository, base OID,
|
||||
expected branch OID, and target branch. Durable renewal is revision-CAS
|
||||
protected; runtime rehydration is reported separately.
|
||||
security: [{bearerAuth: []}]
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseRecoveryRequest'}
|
||||
responses:
|
||||
'200':
|
||||
description: Lease recovered or idempotently observed as already active
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeWriterLeaseRecoveryResponse'}
|
||||
'400': {description: Invalid schema, generation, or lease duration}
|
||||
'409': {description: Task, base, repository, branch, generation, or durable lease conflict}
|
||||
'503': {description: Durable job store or runtime unavailable}
|
||||
x-openai-isConsequential: true
|
||||
/v2/commit-file:
|
||||
post:
|
||||
operationId: commitFileGoverned
|
||||
summary: Commit one file through the governed writer lease
|
||||
security: [{bearerAuth: []}]
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeCommitFileRequest'}
|
||||
responses:
|
||||
'200':
|
||||
description: Authority and remote visibility receipt
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeCommitResponse'}
|
||||
'409': {description: Lease, expected-head, idempotency, or repository conflict}
|
||||
'503': {description: Reconciliation required}
|
||||
x-openai-isConsequential: true
|
||||
/v2/commit-files:
|
||||
post:
|
||||
operationId: commitFilesGoverned
|
||||
summary: Atomically commit a bounded set of files through the governed writer lease
|
||||
security: [{bearerAuth: []}]
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeCommitFilesRequest'}
|
||||
responses:
|
||||
'200':
|
||||
description: Authority and remote visibility receipt
|
||||
content:
|
||||
application/json:
|
||||
schema: {$ref: '#/components/schemas/BridgeCommitResponse'}
|
||||
'409': {description: Lease, expected-head, idempotency, or repository conflict}
|
||||
'503': {description: Reconciliation required}
|
||||
x-openai-isConsequential: true
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
# R4.2 P0-A TaskPlane Scope Isolation Design
|
||||
|
||||
Status: approved candidate design. This document is not evidence of a protected-main merge or production deployment.
|
||||
|
||||
## Boundary
|
||||
|
||||
- Task: `r42-p0a-taskplane-scope-isolation-20260816`
|
||||
- Governed Job: `job-3fd743b51971c6007923699c1233f84c`
|
||||
- Repository: `aios/aios`
|
||||
- Base: `0eb6e1a864edfdaeef37b438991707a110e21558`
|
||||
- Target branch: `agent/r42-p0a-taskplane-scope-isolation-20260816`
|
||||
- Generation: `1`
|
||||
|
||||
The implementation reuses this exact boundary. It does not create a replacement Task, Job, branch, generation, or idempotency key.
|
||||
|
||||
## Model and invariants
|
||||
|
||||
`TaskPlan` gains first-class `scope_type`, `tenant_id`, `user_id`, `project_id`, `conversation_id`, and `run_id` fields. The fields participate in accepted-key validation, parsing, serialization, persistence, and authorization.
|
||||
|
||||
Historical rows without scope data normalize to `scope_type=legacy`; no tenant is inferred. Tenant-scoped tasks require a non-empty `tenant_id`. System/global resources use an explicit `scope_type=system` invariant and do not receive a fabricated tenant. A task may add user, project, conversation, and run ownership within its tenant.
|
||||
|
||||
## Trusted ActorContext
|
||||
|
||||
TaskPlane defines a small immutable `TaskActorContext` used only for authorization. The HTTP authenticator returns an identity. `PolicyEngine` resolves that identity through server-owned policy configuration into the effective context and capabilities. Request fields such as `tenant_id`, `user_id`, `group_id`, and `role` are declarations only and never expand authority.
|
||||
|
||||
Public create, list, and get paths always use the resolved context. Internal compatibility calls may omit a context and retain explicit legacy behavior, but the HTTP adapter never uses that path.
|
||||
|
||||
## Persistence
|
||||
|
||||
SQLite remains the current runtime. `_create_schema()` performs an idempotent forward migration that adds the six scope columns and indexes, then backfills only missing `scope_type` values to `legacy`.
|
||||
|
||||
New writes persist scope in both the canonical `task_json` representation and first-class columns. Reads accept historical JSON without scope, using legacy columns, but reject a new-row mismatch between JSON and columns. SQL list/get predicates are parameterized and applied before row hydration.
|
||||
|
||||
PostgreSQL remains a separate migration target and is not claimed by this change.
|
||||
|
||||
## Authorization flow
|
||||
|
||||
1. HTTP bearer authentication yields an identity.
|
||||
2. `PolicyEngine` verifies capability and resolves the identity to `TaskActorContext`.
|
||||
3. Create binds the requested scope to the trusted context and rejects mismatches.
|
||||
4. List/get pass the trusted context to `TaskPlaneStore`.
|
||||
5. Store applies tenant and ownership predicates in SQL; privileged capabilities may explicitly cross scope.
|
||||
|
||||
Tenant actors cannot read legacy tasks, another tenant, or mismatched owned resources. Legacy actors can only read legacy tasks. System actors require explicit privileged capability for cross-scope access.
|
||||
|
||||
## Failure behavior
|
||||
|
||||
Missing tenant scope, forged scope, unknown scope types, JSON/column divergence, and unauthorized list/get operations fail closed with canonical TaskPlane errors. Public get does not reveal whether an out-of-scope task exists.
|
||||
|
||||
## Verification
|
||||
|
||||
Tests exercise real model round trips, SQLite migration/restart, Service/Policy/Store wiring, tenant A versus tenant B list/get denial, ownership filtering, forged create payload rejection, legacy isolation, privileged access, and SQL parameterization. Existing TaskPlane API, RBAC, recovery/security, and security-contract suites remain mandatory.
|
||||
|
||||
The candidate is complete only after real `TASK_CLAIMED`, `TASK_HEARTBEAT`, exact WriterLease, governed commit, OID convergence, result submission, and `TASK_VERIFIED`. Protected main and production remain unchanged.
|
||||
@@ -0,0 +1,90 @@
|
||||
# R4.2 P0-C Trace / Tool-MCP / Credential Governance
|
||||
|
||||
## Status boundary
|
||||
|
||||
This change is a candidate implementation on the governed P0-C branch. It does
|
||||
not promote protected `main`, deploy Production, or assert that all R4.2 target
|
||||
architecture is complete.
|
||||
|
||||
## Scope model
|
||||
|
||||
Governance resources use an explicit `scope_type`:
|
||||
|
||||
- `tenant` requires `tenant_id` and may narrow to user, project,
|
||||
conversation, and run;
|
||||
- `system` and `global` prohibit tenant ownership fields;
|
||||
- `legacy` preserves unscoped historical records without inventing ownership.
|
||||
|
||||
System and global tools therefore never receive a synthetic tenant merely to
|
||||
satisfy a tenant-oriented schema.
|
||||
|
||||
## Trace lineage
|
||||
|
||||
`TaskPlan` and `MessageEnvelope` scope is bound to a `TraceContext`. The trace
|
||||
records `trace_id`, `span_id`, parent span, correlation, causation, task,
|
||||
message, and the canonical P0-A scope. Child spans must keep the parent's trace,
|
||||
task, and scope. Privileged visibility does not permit cross-scope trace
|
||||
splicing.
|
||||
|
||||
`MessageEnvelope.correlation_id` is persisted and identity-bound. Existing
|
||||
handoff databases are upgraded in place with an idempotent column migration;
|
||||
legacy rows retain their prior event IDs because a null correlation field is
|
||||
not added to the historical identity material.
|
||||
|
||||
Observability keeps its legacy presentation fields, but new governed records
|
||||
also carry immutable trace and scope fields. Scoped records require a trusted
|
||||
server actor for queries. A repeated execution ID is an idempotent replay only
|
||||
when the complete record matches; conflicting overwrites are denied.
|
||||
|
||||
## Tool and MCP governance
|
||||
|
||||
`ToolDescriptor` binds a tool or MCP server to:
|
||||
|
||||
- an explicit resource scope;
|
||||
- required actor capabilities;
|
||||
- an optional credential reference.
|
||||
|
||||
Invocation authorization requires exact propagation of the trace scope and a
|
||||
capability superset. Unknown tools, cross-tenant calls, scope substitution, and
|
||||
non-privileged access to system/global resources fail closed. Every successful
|
||||
registration and invocation appends hash-chained audit evidence.
|
||||
|
||||
## Credential governance
|
||||
|
||||
Credentials are represented only by references whose schemes are
|
||||
`systemd-credential`, `vault`, or `secret-manager`. Raw bearer tokens, passwords,
|
||||
and arbitrary values are rejected. Grants are bound to scope, operation, task,
|
||||
tool, and expiry. Public/audit records contain a reference hash where disclosure
|
||||
is unnecessary; secret material is never persisted by this module.
|
||||
|
||||
The existing runtime credential broker remains backward compatible for system
|
||||
leases, adds explicit tenant/system/global invariants, and rejects providers
|
||||
that attempt to return raw token/secret/password environment values instead of
|
||||
file/reference indirection.
|
||||
|
||||
## Durable evidence
|
||||
|
||||
The SQLite governance store is restart-safe and idempotently initializes four
|
||||
tables: governed tools, trace spans, credential grants, and audit evidence.
|
||||
Audit entries form a SHA-256 chain. Acceptance requires the chain to verify and
|
||||
contain the required actions; missing evidence is not treated as success.
|
||||
|
||||
## Acceptance tests
|
||||
|
||||
The candidate must pass:
|
||||
|
||||
- `TRACE_LINEAGE_CONTINUITY`;
|
||||
- `TRACE_SCOPE_MISMATCH_DENY`;
|
||||
- `TOOL_MCP_AUTHZ_DENY`;
|
||||
- `TOOL_SCOPE_PROPAGATION`;
|
||||
- `CREDENTIAL_SCOPE_DENY`;
|
||||
- `CREDENTIAL_SECRET_EXPOSURE_DENY`;
|
||||
- `AUDIT_EVIDENCE_COMPLETENESS`;
|
||||
- P0-A scope and P0-B handoff regression suites;
|
||||
- Python compilation, `git diff --check`, and a diff-scoped secret scan.
|
||||
|
||||
The repository-wide baseline currently has seven unrelated failures in the
|
||||
isolated host environment (five stale continuation-contract fixtures and two
|
||||
host-permission fixtures). The same seven failures reproduce at the untouched
|
||||
`a642b045775b9154a00ae78543037fbef4fb447b` base; they are not suppressed or
|
||||
modified by P0-C.
|
||||
@@ -0,0 +1,75 @@
|
||||
# R4.2 P1 — Durable Online Agent Execution
|
||||
|
||||
Status: candidate implementation. This document does not imply protected-main promotion or Production deployment.
|
||||
|
||||
## State model
|
||||
|
||||
The generic worker uses two local durable layers:
|
||||
|
||||
1. `tasks/<task_id>.json`: atomic fast-state cache for compatibility and quick restart.
|
||||
2. `checkpoints.sqlite3`: append-only attempt/phase journal with `synchronous=FULL`.
|
||||
|
||||
Checkpoint identity is bound to:
|
||||
|
||||
- task_id
|
||||
- attempt
|
||||
- execution_digest
|
||||
- job_id
|
||||
- repository
|
||||
- base_oid
|
||||
- expected_branch_oid
|
||||
- target_branch
|
||||
- generation
|
||||
|
||||
A checkpoint from another repository/branch/generation is never reused.
|
||||
|
||||
Phases are monotonic within an attempt:
|
||||
|
||||
`claimed → workspace_prepared → verification_passed → source_capture_done|commit_done → result_pending → result_submitted`
|
||||
|
||||
`reconciliation_required` is an explicit recovery phase.
|
||||
|
||||
## Attempt-aware result idempotency
|
||||
|
||||
Result submission idempotency keys include the official Task attempt and the execution digest. The same
|
||||
attempt reuses the same key after a timeout/restart; a later official attempt cannot collide with an
|
||||
earlier result.
|
||||
|
||||
Before submitting a result the worker durably writes `result_pending`, including the result hash and
|
||||
idempotency key. After a successful or exact-idempotency-reconciled API response it writes
|
||||
`result_submitted`.
|
||||
|
||||
A 409 is accepted only if the Task API already contains the exact same result body and the Task is
|
||||
VERIFYING/SUCCEEDED. A conflicting result remains a hard failure.
|
||||
|
||||
## Resume rules
|
||||
|
||||
- `source_capture_done` and `result_pending` may be reused across later official attempts only when the
|
||||
execution/scope binding is identical. This avoids repeating read-only source capture.
|
||||
- A deterministic task that crashed before governed commit replays from a new clean detached worktree.
|
||||
This is safe because there is no external side effect yet.
|
||||
- `commit_done` is never recommitted. Recovery requires exact Job receipt OID convergence plus exactly
|
||||
one ACTIVE WriterLease whose `current_head_oid` equals the governed commit.
|
||||
- delayed Git visibility remains `RECONCILIATION_REQUIRED`, preserving an explicit recovery entry.
|
||||
|
||||
## Crash cleanup
|
||||
|
||||
On worker startup, stale `task-*` workspaces under the configured workspace root are removed before
|
||||
polling begins. The path boundary is verified before deletion.
|
||||
|
||||
## Contracts
|
||||
|
||||
P1 gates include:
|
||||
|
||||
- CHECKPOINT_DURABLE_WRITE
|
||||
- RESUME_FROM_CHECKPOINT
|
||||
- RETRY_IDEMPOTENT_NO_DUPLICATE_SIDE_EFFECT
|
||||
- CRASH_RECOVERY_CONVERGENCE
|
||||
- WORKER_RESTART_RESUME
|
||||
- CHECKPOINT_SCOPE_ISOLATION
|
||||
- RESULT_SUBMISSION_REPLAY_SAFE
|
||||
- WORKSPACE_CLEANUP_RECOVERY
|
||||
- LEASE_RENEWAL_RECOVERY
|
||||
|
||||
WriterLease and governed Job authority remain in the existing Bridge/GitOps durable stores; the worker
|
||||
checkpoint DB is not a competing authority for Git state.
|
||||
@@ -0,0 +1,18 @@
|
||||
# R4.2 P2 Agent Fleet / Multi-Agent Scheduling / Fault Isolation
|
||||
|
||||
P2 adds a durable fleet decision layer inside TaskPlane without replacing TaskPlane claim/lease
|
||||
ownership. Worker registration/heartbeat remains authoritative for liveness. TaskPlane claim CAS
|
||||
remains authoritative for ownership. Probe-before-reassignment remains mandatory after an expired
|
||||
lease. P1 checkpoint/result replay remains authoritative after worker restart.
|
||||
|
||||
`FleetScheduler` adds durable worker capacity slots, weighted scope fairness, starvation aging,
|
||||
affinity/anti-affinity labels, worker circuit breakers, per-task/worker quarantine and idempotent
|
||||
dispatch reservations. Fleet state is colocated in the existing TaskPlane SQLite database and is
|
||||
created idempotently; no new daemon or database is introduced.
|
||||
|
||||
A fleet reservation is only a scheduling decision. It does not claim a Task. Callers must perform
|
||||
the normal TaskPlane claim and may then bind the returned claim ID to the reservation. This preserves
|
||||
the existing ownership and recovery invariants.
|
||||
|
||||
Failure recovery never bypasses probe evidence. When TaskPlane recovery places work back in a
|
||||
claimable state, P2 may quarantine the failed worker and prefer another worker/failure domain.
|
||||
@@ -0,0 +1,79 @@
|
||||
# R4.2 P2 Compact Interface Map Runtime
|
||||
|
||||
## Purpose
|
||||
|
||||
The persistent Online Agent already supports the canonical read-only `source_capture` action, but
|
||||
its `SourceCaptureExecutor` always returns an `aios.engineering.source-snapshot.v2` tar.gz+base64
|
||||
payload. That is correct for implementation source transfer, but too large for control-plane
|
||||
consumers that only need a bounded implementation map.
|
||||
|
||||
P2 adds a new **adapter**, not a new execution action:
|
||||
|
||||
```text
|
||||
action=source_capture
|
||||
adapter=compact_interface_map
|
||||
```
|
||||
|
||||
This preserves the existing execution-v2 schema and Bridge policy:
|
||||
|
||||
- read-only repository;
|
||||
- no change set;
|
||||
- no verification commands;
|
||||
- `writer_lease=false`;
|
||||
- no branch or commit;
|
||||
- existing capability and execution-digest validation.
|
||||
|
||||
## Compact map contract
|
||||
|
||||
`aios_online_agent_compact_map.py` scans only approved repository roots and source suffixes. It
|
||||
returns:
|
||||
|
||||
- at most 40 relevant modules;
|
||||
- at most 80 selected Python symbols in total;
|
||||
- at most 40 test symbols;
|
||||
- at most 25 excerpts;
|
||||
- at most 1200 characters per excerpt;
|
||||
- SQL table names;
|
||||
- systemd unit names;
|
||||
- current invariants, failure windows and reuse points;
|
||||
- P2 fleet contract-to-surface mappings.
|
||||
|
||||
The result is hard-bounded to 120 KiB and contains no source archive or `payload_b64`.
|
||||
|
||||
Source excerpts apply a conservative sensitive-pattern redaction before result construction.
|
||||
|
||||
## P2 contracts
|
||||
|
||||
The map supplies evidence surfaces for:
|
||||
|
||||
- `FLEET_AGENT_REGISTRATION`
|
||||
- `FLEET_CAPACITY_SCHEDULING`
|
||||
- `FLEET_FAIRNESS`
|
||||
- `FLEET_FAULT_ISOLATION`
|
||||
- `FLEET_WORKER_REASSIGNMENT`
|
||||
- `FLEET_SCOPE_ISOLATION`
|
||||
- `FLEET_IDEMPOTENT_DISPATCH`
|
||||
- `FLEET_FAILURE_RECOVERY`
|
||||
|
||||
Missing first-class scheduling/fleet primitives are reported as gaps rather than invented.
|
||||
|
||||
## Result
|
||||
|
||||
When the adapter is selected, the worker returns:
|
||||
|
||||
```text
|
||||
status=SUCCEEDED
|
||||
classification=P2_INTERFACE_MAP_CAPTURED
|
||||
execution_mode=compact_interface_map
|
||||
writer_lease=NONE
|
||||
```
|
||||
|
||||
The existing `source_capture_done` / P1 checkpoint/retry path is reused, so the compact analysis
|
||||
inherits attempt-aware result idempotency and restart-safe result submission.
|
||||
|
||||
## Governance
|
||||
|
||||
This capability is runtime infrastructure only. The implementation candidate may use a governed
|
||||
branch/WriterLease for its own code change, but any task executed through `compact_interface_map`
|
||||
is read-only and must not create a WriterLease, branch, commit, protected-ref write, or Production
|
||||
side effect.
|
||||
@@ -0,0 +1,17 @@
|
||||
# R4.2 P2-B Fleet Order Preservation Repair
|
||||
|
||||
P2-C live acceptance exposed a real integration defect in the verified P2-B candidate. The fleet
|
||||
scheduler correctly produced durable cross-scope fairness order, but the integration passed the
|
||||
entire ranked list to the legacy scheduler. The legacy scheduler then applied its own priority /
|
||||
created_at / task_id sort and silently discarded fleet ordering.
|
||||
|
||||
The repair preserves the legacy scheduler as the fail-closed security oracle while changing how it
|
||||
is called: one fleet-ranked candidate is presented at a time. A candidate rejected by legacy
|
||||
security/policy advances to the next fleet candidate. A candidate returned by the oracle must have
|
||||
the same task ID as the candidate presented, otherwise execution fails closed.
|
||||
|
||||
Task ownership remains unchanged: the original schedule_for_worker/claim_task CAS remains
|
||||
authoritative, and a fleet reservation is still only bound after the claim succeeds.
|
||||
|
||||
This repair does not modify FleetScheduler state semantics, capacity, WriterLease, checkpoint,
|
||||
protected refs or Production behavior.
|
||||
@@ -0,0 +1,23 @@
|
||||
# R4.2 P2-B Fleet Runtime Integration
|
||||
|
||||
P2-B connects the verified P2 fleet primitives to the existing TaskPlane pull scheduler without
|
||||
replacing its security or ownership logic.
|
||||
|
||||
The integration uses two stages. `FleetScheduler.rank_for_worker()` performs only read-only
|
||||
capacity/fairness/fault-isolation ranking. The original `TaskScheduler.next_queued_task()` is then
|
||||
run over that ordered list and remains the fail-closed security oracle for worker liveness,
|
||||
capabilities, data classification, execution zone and other existing policy checks. Only a task
|
||||
accepted by the original scheduler receives a short durable fleet reservation.
|
||||
|
||||
The original `TaskScheduler.schedule_for_worker()` remains the sole claim path and continues to call
|
||||
the existing TaskPlane `claim_task` CAS. After a successful claim, the claim ID is bound to the
|
||||
fleet reservation. A claim error releases the reservation. A fleet reservation is never treated as
|
||||
task ownership.
|
||||
|
||||
P2-B also makes the reservation capacity check atomic inside the fleet SQLite transaction so two
|
||||
concurrent pullers cannot oversubscribe the same worker slot. Circuit and task/worker quarantine
|
||||
state are enforced on the real pull path. Explicit execution-failure signals can be recorded through
|
||||
the integrated scheduler's failure/success/quarantine methods; policy/claim failures are not
|
||||
automatically mislabeled as worker crashes.
|
||||
|
||||
No new daemon, database or production write path is introduced.
|
||||
@@ -0,0 +1,123 @@
|
||||
# External Agent Attempt-Scoped Request Identity
|
||||
|
||||
## Problem
|
||||
|
||||
External Agent execution previously derived its durable request ID from:
|
||||
|
||||
```text
|
||||
task_id
|
||||
job_id
|
||||
execution_digest
|
||||
runtime
|
||||
```
|
||||
|
||||
The Online Task attempt was missing.
|
||||
|
||||
That is incorrect for retryable external side effects. A failed Model Governance route reservation is
|
||||
durable and terminal for that request ID. Reusing the same external request ID on a later official
|
||||
Task attempt therefore reuses the old route decision/reservation and can fail settlement with:
|
||||
|
||||
```text
|
||||
MODEL_RESERVATION_STATE_INVALID
|
||||
```
|
||||
|
||||
Archiving an exchange failed marker does not fix the root cause because the Model Governance
|
||||
reservation remains intentionally durable.
|
||||
|
||||
## Contract
|
||||
|
||||
External request identity is now:
|
||||
|
||||
```text
|
||||
hash(
|
||||
task_id,
|
||||
job_id,
|
||||
execution_digest,
|
||||
runtime,
|
||||
attempt
|
||||
)
|
||||
```
|
||||
|
||||
The attempt is a **transient execution coordinate**. It is not added to the signed governed execution
|
||||
envelope and does not alter the Task/Job binding or execution digest.
|
||||
|
||||
The worker gets the authoritative attempt from the successful claim response and passes it through:
|
||||
|
||||
```text
|
||||
process_claim
|
||||
→ RuntimeAdapter.execute(..., attempt=N)
|
||||
→ ExternalAgentExecutor
|
||||
→ ExternalAgentExchange
|
||||
→ external request JSON
|
||||
→ external result JSON
|
||||
```
|
||||
|
||||
The external result must bind the same attempt.
|
||||
|
||||
## Idempotency
|
||||
|
||||
This gives the intended two-level behavior:
|
||||
|
||||
```text
|
||||
same Task/Job/execution/runtime + same attempt
|
||||
→ same external request ID
|
||||
→ same external result/reservation can be replayed safely
|
||||
|
||||
same Task/Job/execution/runtime + next official attempt
|
||||
→ different external request ID
|
||||
→ different Model Governance request ID
|
||||
→ new reservation
|
||||
```
|
||||
|
||||
Old FAILED reservations are retained for audit. No Model Governance DB cleanup is required or
|
||||
permitted.
|
||||
|
||||
## Model Governance
|
||||
|
||||
Model Governance already derives its route request ID from:
|
||||
|
||||
```text
|
||||
external_request_id + ":model"
|
||||
```
|
||||
|
||||
Therefore making the external request ID attempt-scoped automatically makes route decisions and
|
||||
reservations attempt-scoped without creating another state authority.
|
||||
|
||||
## Recovery
|
||||
|
||||
For the current Hermes live Task:
|
||||
|
||||
```text
|
||||
attempt 6
|
||||
→ old request/reservation remains FAILED
|
||||
|
||||
official NEEDS_REWORK
|
||||
→ bounded retry extension 6 → 7
|
||||
|
||||
attempt 7
|
||||
→ new external request ID
|
||||
→ new route request ID
|
||||
→ new reservation
|
||||
→ provider execution
|
||||
→ settlement
|
||||
```
|
||||
|
||||
No replacement Task/Job, direct DB rewrite, failed-reservation deletion or marker deletion is
|
||||
required.
|
||||
|
||||
## Worker Availability
|
||||
|
||||
The repair must preserve the already verified Worker Availability runtime. Runtime switches use the
|
||||
maintenance inhibit and must finish with the guard healthy and all three workers fresh.
|
||||
|
||||
## Verification
|
||||
|
||||
Required regression coverage:
|
||||
|
||||
- request ID stable within one attempt;
|
||||
- request ID different across attempts;
|
||||
- request schema requires a valid attempt;
|
||||
- external result binds attempt;
|
||||
- old failed Model Governance reservation remains FAILED;
|
||||
- next attempt gets a new reservation and can settle;
|
||||
- existing external-agent and Model Governance runtime tests still pass.
|
||||
@@ -0,0 +1,18 @@
|
||||
# Generic Compact Interface-Map Profiles
|
||||
|
||||
The compact interface-map runtime is a reusable read-only control-plane capability. It keeps the
|
||||
canonical `source_capture` action and `compact_interface_map` adapter, but selects a bounded semantic
|
||||
profile from the task's source signals.
|
||||
|
||||
The existing `fleet` profile remains backward compatible and returns
|
||||
`P2_INTERFACE_MAP_CAPTURED` with the `FLEET_*` contracts.
|
||||
|
||||
The new `model_governance` profile is selected when model/provider/routing/budget/evaluation terms
|
||||
are present. It returns `MODEL_GOVERNANCE_INTERFACE_MAP_CAPTURED` and model-specific contracts for
|
||||
provider registry, selection policy, version pinning, budget accounting, fallback, scope isolation,
|
||||
credential boundary, trace/audit, evaluation gates and routing resilience.
|
||||
|
||||
Profile and classification are emitted by the compact-map module and revalidated by the worker
|
||||
before result submission. Unknown or mismatched profile/classification pairs fail closed.
|
||||
|
||||
No new Bridge action, daemon, database, WriterLease, mutation path or credential surface is added.
|
||||
@@ -0,0 +1,142 @@
|
||||
# Hermes / OpenClaw Online Agent Runtime
|
||||
|
||||
## Goal
|
||||
|
||||
Promote Hermes and OpenClaw from shadow-only adapter descriptions to real Online Agent workers
|
||||
without creating a second Task/claim protocol.
|
||||
|
||||
Both workers reuse the existing P1/P2 Online Agent lifecycle:
|
||||
|
||||
```text
|
||||
Online Task projected
|
||||
→ capability-filtered poll
|
||||
→ automatic claim
|
||||
→ heartbeat
|
||||
→ durable checkpoint
|
||||
→ external Agent execution
|
||||
→ attempt-aware result submission
|
||||
→ official verification
|
||||
```
|
||||
|
||||
They do **not** change the existing TaskPlane `OpenClawAdapter/HermesAdapter` shadow contract. Those
|
||||
adapters remain side-effect-free compatibility surfaces.
|
||||
|
||||
## Execution action
|
||||
|
||||
The canonical execution envelope adds a read-only action:
|
||||
|
||||
```text
|
||||
action=agent_runtime
|
||||
adapter=hermes | openclaw
|
||||
```
|
||||
|
||||
The action requires capability `agent.runtime.<adapter>`, has an empty change set, no verification
|
||||
commands, and `writer_lease=false`.
|
||||
|
||||
`project_online_task()` copies only bounded task fields into the signed execution envelope:
|
||||
|
||||
- goal;
|
||||
- instructions;
|
||||
- success criteria;
|
||||
- non-secret constraints.
|
||||
|
||||
The task may not choose a command, executable, URL, credential path, environment, or shell string.
|
||||
|
||||
## Worker separation
|
||||
|
||||
The generic engineering worker defaults to:
|
||||
|
||||
```text
|
||||
AIOS_WORKER_ALLOWED_ADAPTERS=deterministic,source_capture,compact_interface_map,codex
|
||||
```
|
||||
|
||||
so it skips Hermes/OpenClaw tasks before claim.
|
||||
|
||||
Dedicated services advertise:
|
||||
|
||||
```text
|
||||
Hermes:
|
||||
AIOS_WORKER_CAPABILITIES=agent.runtime.hermes
|
||||
AIOS_WORKER_ALLOWED_ADAPTERS=hermes
|
||||
|
||||
OpenClaw:
|
||||
AIOS_WORKER_CAPABILITIES=agent.runtime.openclaw
|
||||
AIOS_WORKER_ALLOWED_ADAPTERS=openclaw
|
||||
```
|
||||
|
||||
This makes adapter selection a pre-claim capability/fleet decision instead of a post-claim failure.
|
||||
|
||||
## Credential-isolated executor
|
||||
|
||||
The Online Agent worker itself still owns only Task API/Bridge coordination credentials. It writes
|
||||
a hash-bound request to `/var/lib/aios-external-agent-executor`.
|
||||
|
||||
`aios-external-agent-executor.service` runs as the existing uncredentialed engineering executor user.
|
||||
It has:
|
||||
|
||||
- one provider-only `LoadCredential` projection for the model-ready OneAPI environment;
|
||||
- `/etc/aios-gitops`, `/data/aios-gitops`, and the original provider-secret directory inaccessible;
|
||||
- no repository path;
|
||||
- no shell execution;
|
||||
- loopback denied, preventing direct access to the AIOS Task/Bridge control plane;
|
||||
- only the staging OneAPI container address allowed for the installed Agent runtime/provider;
|
||||
- only the exchange directory writable.
|
||||
|
||||
The root-owned runtime profile in `/etc/aios/external-agent-runtime.d/<runtime>.json` decides the
|
||||
absolute executable, fixed non-secret environment, provider-only credential mapping, and I/O mode.
|
||||
A task cannot override any of these values. The profile may select `OPENAI_API_KEY` only from the
|
||||
systemd credential named `aios-external-agent-oneapi-env`; it cannot name a credential, inject an
|
||||
environment variable, or carry an inline secret. The runtime executor parses only the selected
|
||||
`ONEAPI_REGULAR_TOKEN` entry and does not expose the source file or other provider tiers to the
|
||||
child.
|
||||
|
||||
## Runtime profile
|
||||
|
||||
A profile supports:
|
||||
|
||||
- `argv`: fixed argv, absolute allowlisted executable;
|
||||
- `input_mode`: `stdin_text`, `stdin_json`, or `file_json`;
|
||||
- `output_mode`: `stdout_text`, `stdout_json`, or `file_json`;
|
||||
- timeout;
|
||||
- bounded output size.
|
||||
|
||||
`{input_json}` and `{output_json}` placeholders are allowed only for file modes. `{prompt}` is a
|
||||
root-profile-only argv placeholder populated from the bounded, signed task projection.
|
||||
|
||||
The repository includes the staging profile templates validated against the installed Hermes
|
||||
v0.20.0 and OpenClaw v2026.7.2-beta.7 CLIs. Before activation, the Agent must re-run the actual
|
||||
`--help`/version probes and install the profiles and static configs root-owned. If the installed
|
||||
CLI differs, update only the root-owned profile/config projection and record the observed command;
|
||||
do not modify the Task contract to compensate.
|
||||
|
||||
The provider projection is staging-only and uses the existing model-ready OneAPI source. It is not
|
||||
an AIOS Task, Bridge, GitOps, SSH, or Writer credential. Live activation remains blocked if the
|
||||
model-ready source cannot be projected through systemd or if the selected provider credential is
|
||||
missing/quota-invalid. This worker never passes API keys through task metadata or arbitrary
|
||||
environment variables.
|
||||
|
||||
## Retry/restart
|
||||
|
||||
The external request ID is deterministic over Task/Job/execution digest/runtime. The exchange keeps
|
||||
the request/result across worker restart. A repeated attempt with the exact execution digest reuses
|
||||
the durable external result instead of invoking the Agent twice.
|
||||
|
||||
The normal P1 result idempotency/checkpoint path remains authoritative for Task result submission.
|
||||
|
||||
## Result
|
||||
|
||||
Successful execution returns:
|
||||
|
||||
```text
|
||||
status=SUCCEEDED
|
||||
classification=EXTERNAL_AGENT_RUNTIME_SUCCEEDED
|
||||
execution_mode=agent_runtime
|
||||
agent_runtime=hermes | openclaw
|
||||
writer_lease=NONE
|
||||
changed_files=[]
|
||||
credential_material_exposed=false
|
||||
control_plane_access_granted_to_runtime=false
|
||||
```
|
||||
|
||||
This first runtime version is intentionally read-only with respect to the repository. Engineering
|
||||
changes continue to use assistant-authored deterministic plans and governed WriterLease/commit.
|
||||
+109
@@ -0,0 +1,109 @@
|
||||
# Model Governance Policy / Profile Floor Compatibility
|
||||
|
||||
## Problem
|
||||
|
||||
The root-owned OpenClaw runtime profile reserves a minimum of 16,384 input tokens so Model
|
||||
Governance can cover OpenClaw-injected workspace, skills and system context before provider
|
||||
execution.
|
||||
|
||||
The staging scope policies still limited input to 16,000 tokens per request. Route selection
|
||||
therefore failed before reservation with:
|
||||
|
||||
```text
|
||||
MODEL_INPUT_TOKEN_LIMIT_DENY
|
||||
```
|
||||
|
||||
This was a configuration invariant violation:
|
||||
|
||||
```text
|
||||
scope max_input_tokens_per_request
|
||||
<
|
||||
root-owned profile input_reservation_floor_tokens
|
||||
```
|
||||
|
||||
The registered OpenClaw model itself supports 32,768 input tokens, so the model capability was not
|
||||
the blocker.
|
||||
|
||||
## Invariant
|
||||
|
||||
For every Model Governance scope that allows a model/runtime whose root-owned profile declares an
|
||||
input reservation floor:
|
||||
|
||||
```text
|
||||
scope.max_input_tokens_per_request
|
||||
>=
|
||||
profile.model_governance.input_reservation_floor_tokens
|
||||
```
|
||||
|
||||
The profile floor remains root-owned. Task payloads cannot alter it.
|
||||
|
||||
## Staging policy
|
||||
|
||||
The two staging policies that allow `openai/deepseek-v4-flash` are updated from:
|
||||
|
||||
```text
|
||||
16000
|
||||
```
|
||||
|
||||
to:
|
||||
|
||||
```text
|
||||
16384
|
||||
```
|
||||
|
||||
This is the minimum compatible value. It intentionally remains below the model's 32,768-token
|
||||
technical input ceiling.
|
||||
|
||||
The daily token budget is unchanged.
|
||||
|
||||
## Governance path
|
||||
|
||||
The live SQLite policy must be changed only through the repository bootstrap and
|
||||
`aios_model_governance_admin.py`.
|
||||
|
||||
The admin reconciler:
|
||||
|
||||
- reads the governed repository config;
|
||||
- uses current policy revision as CAS;
|
||||
- calls `ModelGovernanceStore.set_scope_policy`;
|
||||
- appends normal Model Governance audit evidence;
|
||||
- verifies the audit chain.
|
||||
|
||||
Direct SQL updates remain forbidden.
|
||||
|
||||
## Exhausted OpenClaw recovery
|
||||
|
||||
The fixed OpenClaw live Task has exhausted its normal three attempts.
|
||||
|
||||
After the governed policy candidate is officially verified and the live policy is reconciled:
|
||||
|
||||
```text
|
||||
attempt 3 VERIFYING/FAILED result
|
||||
→ official NEEDS_REWORK
|
||||
→ Task becomes FAILED 3/3
|
||||
→ official bounded retry extension 3 → 4
|
||||
→ same Task / same Job returns QUEUED
|
||||
→ persistent OpenClaw worker auto-claims attempt 4
|
||||
```
|
||||
|
||||
AR1 attempt-scoped external request identity ensures attempt 4 receives a new external request and a
|
||||
new Model Governance reservation.
|
||||
|
||||
No historical reservation is deleted or rewritten.
|
||||
|
||||
## Acceptance
|
||||
|
||||
Attempt 4 must prove:
|
||||
|
||||
```text
|
||||
scope max_input_tokens_per_request=16384
|
||||
profile input_reservation_floor_tokens=16384
|
||||
reserved_estimated_input_tokens>=16384
|
||||
actual input <= reserved input
|
||||
settlement=SETTLED
|
||||
usage_source=runtime
|
||||
audit_chain_valid=true
|
||||
```
|
||||
|
||||
If attempt 4 exposes a new failure, stop. No additional retry extension is authorized by this
|
||||
repair.
|
||||
@@ -0,0 +1,211 @@
|
||||
# AIOS Model Governance Runtime
|
||||
|
||||
## Status and purpose
|
||||
|
||||
This component turns the previously `PARTIAL` Model Governance interface map into an enforceable
|
||||
runtime policy for the already verified Hermes/OpenClaw Online Agent path.
|
||||
|
||||
It is intentionally a **single SQLite library**, not a new network service. The existing external
|
||||
Agent executor calls the library immediately before launching a model-backed runtime and settles the
|
||||
same reservation immediately after the result.
|
||||
|
||||
The authoritative execution chain remains:
|
||||
|
||||
```text
|
||||
Online Task scope / trace
|
||||
→ dedicated worker claim + heartbeat
|
||||
→ external Agent executor
|
||||
→ ModelGovernanceStore.route()
|
||||
→ root-owned runtime profile binds provider/model/version
|
||||
→ Hermes / OpenClaw process
|
||||
→ ModelGovernanceStore.record_success() / record_failure()
|
||||
→ durable Online Agent checkpoint/result
|
||||
```
|
||||
|
||||
P0 scope/trace/credential, P1 checkpoint/retry, P2 fleet scheduling and the existing external Agent
|
||||
credential boundary remain authoritative.
|
||||
|
||||
## Ten Model Governance contracts
|
||||
|
||||
### MODEL_PROVIDER_REGISTRY
|
||||
|
||||
`model_governance_providers` stores provider identity, failure domain, circuit policy and an opaque
|
||||
credential reference. Raw credentials are rejected.
|
||||
|
||||
Allowed reference prefixes:
|
||||
|
||||
- `systemd-credential:`
|
||||
- `runtime-profile:`
|
||||
- `credential-broker:`
|
||||
|
||||
### MODEL_SELECTION_POLICY
|
||||
|
||||
`model_governance_scope_policies` constrains eligible models/providers/capabilities. Routing is
|
||||
deterministic: explicit preferred models, then configured priority, then stable provider/model IDs.
|
||||
|
||||
### MODEL_VERSION_PINNING
|
||||
|
||||
A registry row always includes a model version. A scope can additionally pin a model ID + exact
|
||||
version. Every route decision persists both model ID and version plus model/policy revisions.
|
||||
|
||||
### MODEL_BUDGET_ACCOUNTING
|
||||
|
||||
A route first reserves estimated input/output tokens and estimated cost inside `BEGIN IMMEDIATE`.
|
||||
Settled usage and outstanding reservations both count against the daily scope budget, preventing two
|
||||
concurrent requests from oversubscribing the same budget.
|
||||
|
||||
Runtime-reported usage is preferred. When telemetry is absent, the reserved upper bound is charged
|
||||
rather than silently under-counting.
|
||||
|
||||
OpenClaw's verified result shape is supported directly:
|
||||
|
||||
```text
|
||||
meta.agentMeta.usage.input
|
||||
meta.agentMeta.usage.output
|
||||
meta.agentMeta.costUsd
|
||||
```
|
||||
|
||||
Hermes currently has no structured usage in the verified output, so it uses conservative
|
||||
reservation settlement.
|
||||
|
||||
### MODEL_FALLBACK_POLICY
|
||||
|
||||
Provider failures are durable. Repeated failures open a circuit for the configured cooldown. A
|
||||
fallback request excludes the failed provider and increments `fallback_index`; the scope policy
|
||||
bounds the number of fallback attempts.
|
||||
|
||||
### MODEL_SCOPE_ISOLATION
|
||||
|
||||
The signed `agent_runtime` execution envelope now carries authoritative Task scope + trace identity.
|
||||
|
||||
The projection layer always overwrites `runtime_input.scope` and `runtime_input.trace_id` from the
|
||||
Online Task, even if an execution request attempts to supply different values.
|
||||
|
||||
Tenant/project lookup may fall back only to the same tenant's policy. It never falls back to a
|
||||
system or legacy policy. `system` and `legacy` require their own explicit policies, avoiding fake
|
||||
tenant identities.
|
||||
|
||||
### MODEL_CREDENTIAL_BOUNDARY
|
||||
|
||||
Model governance stores credential references only. The root-owned external-runtime profile still
|
||||
owns the actual provider credential projection. Task payloads cannot select executable, argv,
|
||||
environment, provider credential, or credential path.
|
||||
|
||||
The external child process remains unable to reach the AIOS control plane.
|
||||
|
||||
### MODEL_TRACE_AUDIT
|
||||
|
||||
Every route, failure, provider/model/policy update and settlement appends to a SHA-256 hash-chained
|
||||
audit table with task ID, trace ID and scope key. `verify_audit_chain()` detects tampering.
|
||||
|
||||
### MODEL_EVALUATION_GATE
|
||||
|
||||
A model cannot enter the registry unless its state is `APPROVED` and it has a 64-hex evaluation
|
||||
evidence digest.
|
||||
|
||||
The staging bootstrap uses the already verified Hermes/OpenClaw E2E external-result SHA256 values as
|
||||
evaluation evidence, rather than a configuration-file hash.
|
||||
|
||||
### MODEL_ROUTING_RESILIENCE
|
||||
|
||||
Route request IDs are idempotent and bound to a canonical request hash. Conflicting replay is
|
||||
rejected. Provider health, reservations, usage settlement and policy/provider/model updates use
|
||||
transaction/CAS semantics.
|
||||
|
||||
## Runtime profile contract
|
||||
|
||||
A root-owned Hermes/OpenClaw profile may declare:
|
||||
|
||||
```json
|
||||
{
|
||||
"model_governance": {
|
||||
"required": true,
|
||||
"provider_ids": ["provider-a"],
|
||||
"model_capabilities": ["text"],
|
||||
"max_output_tokens": 512
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
When `required=true`:
|
||||
|
||||
- `provider_ids` must be non-empty;
|
||||
- `max_output_tokens` must be positive;
|
||||
- argv/environment must contain at least one governance-controlled marker:
|
||||
`{provider_id}`, `{model_id}`, or `{model_version}`;
|
||||
- `AIOS_MODEL_GOVERNANCE_ENABLED` must be enabled;
|
||||
- a matching scope policy/model/provider must exist;
|
||||
- budget reservation must succeed before the child process is launched.
|
||||
|
||||
The task cannot provide these markers or their values.
|
||||
|
||||
## SQLite authority
|
||||
|
||||
Default database:
|
||||
|
||||
```text
|
||||
/var/lib/aios-model-governance/state.sqlite3
|
||||
```
|
||||
|
||||
The executor process already owns the only runtime mutation path. The directory is created by
|
||||
tmpfiles and is the only new writable path added to that executor.
|
||||
|
||||
No direct Task/Job/Git database writes are introduced.
|
||||
|
||||
## Bootstrap/reconciliation
|
||||
|
||||
`aios_model_governance_admin.py` applies a root-owned JSON bootstrap idempotently. It compares desired
|
||||
state to current rows and uses the current revision as the CAS input only when a change is actually
|
||||
required.
|
||||
|
||||
The repository staging bootstrap is not a Production policy. It exists only to reproduce and
|
||||
govern the already verified non-production Hermes/OpenClaw runtimes.
|
||||
|
||||
## Cost caveat
|
||||
|
||||
The current verified OneAPI-backed runtime evidence reports zero authoritative provider cost for
|
||||
OpenClaw and no structured cost for Hermes. The staging bootstrap therefore does **not** invent
|
||||
pricing and sets cost rates/budget to zero/unbounded.
|
||||
|
||||
Token budgets remain enforced. Real monetary budget enforcement becomes effective as soon as
|
||||
authoritative per-model pricing is entered into the root-owned registry.
|
||||
|
||||
## OpenClaw JIT/WASM compatibility
|
||||
|
||||
The previous live acceptance proved that OpenClaw Node/WASM requires
|
||||
`MemoryDenyWriteExecute=no`. Model Governance must preserve that already-evidenced runtime exception;
|
||||
it must not further weaken `NoNewPrivileges`, `ProtectSystem=strict`, `ProtectHome`, loopback deny,
|
||||
credential isolation or repository isolation.
|
||||
|
||||
## Failure/recovery invariants
|
||||
|
||||
- Budget denial occurs before provider execution.
|
||||
- Missing scope policy fails closed.
|
||||
- Missing/disabled governance fails closed when a profile requires it.
|
||||
- Actual usage cannot exceed the reservation.
|
||||
- Provider failure releases that reservation into `FAILED` state before fallback.
|
||||
- Settlement is idempotent.
|
||||
- Route replay is idempotent only for the exact canonical request.
|
||||
- Audit corruption is detectable.
|
||||
- Online Agent checkpoint/result retry remains unchanged and remains the outer recovery authority.
|
||||
|
||||
## Verification
|
||||
|
||||
Required unit/integration coverage includes:
|
||||
|
||||
- registry/evaluation/CAS;
|
||||
- scope isolation and no system→tenant fallback;
|
||||
- model/version pinning;
|
||||
- atomic budget reservation;
|
||||
- settlement/replay;
|
||||
- missing telemetry conservative settlement;
|
||||
- provider circuit/fallback;
|
||||
- trace/audit tamper detection;
|
||||
- authoritative scope/trace projection;
|
||||
- task runtime-input scope override attack;
|
||||
- root-owned provider/model binding;
|
||||
- OpenClaw nested usage extraction;
|
||||
- real Hermes/OpenClaw staging live tasks with Model Governance evidence.
|
||||
|
||||
The governed implementation is not complete without the unified all-modified-files bundle for the
|
||||
candidate delta and the cumulative lineage bundle.
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user