Compare commits

...
65 changed files with 12194 additions and 125 deletions
+14 -7
View File
@@ -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"))
+12
View File
@@ -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)
+30 -6
View File
@@ -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 +1,427 @@
"""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()
@@ -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")
@@ -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
+131 -33
View File
@@ -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)
@@ -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")
+50 -4
View File
@@ -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()
@@ -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,
@@ -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))
@@ -0,0 +1,301 @@
"""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,
"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 +1,384 @@
"""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",
}
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"),
}
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 _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]],
) -> 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]]) -> tuple[list[str], list[str], list[str]]:
haystack = "\n".join(_surface_ref(item).lower() for item in symbols)
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: list[str] = []
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.")
reuse_points: list[str] = []
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"),
)
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")
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)
result = {
"schema": SCHEMA,
"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),
}
return _trim_to_budget(result)
@@ -0,0 +1,397 @@
"""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"})
SUPPORTED_ACTIONS = frozenset({"deterministic", "source_capture"})
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 _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")
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 [],
"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 = project_execution_envelope(binding, execution_request, 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
@@ -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,
+456
View File
@@ -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,
)
+9 -1
View File
@@ -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):
+70 -4
View File
@@ -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(
+8 -6
View File
@@ -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",
}
+56 -26
View File
@@ -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
+5
View File
@@ -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)
+828
View File
@@ -0,0 +1,828 @@
"""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 IN ('RESERVED','CLAIMED') 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()
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
)
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:
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 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
+27
View File
@@ -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),
+20 -1
View File
@@ -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 +74,13 @@ 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,
)
+181
View File
@@ -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,
)
+95 -11
View File
@@ -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 +1,36 @@
-- 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 +1,36 @@
[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 +1,33 @@
[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 +1,4 @@
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 +1,5 @@
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 -
+223
View File
@@ -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 +1,9 @@
# R4.2 P0-A TaskPlane Scope Isolation
Status: candidate implementation. This is not proof of protected-main promotion or production deployment.
Task scope is now represented by `scope_type`, `tenant_id`, `user_id`, `project_id`, `conversation_id`, and `run_id` in the model and SQLite persistence. Historical rows become `legacy`; their tenant is never guessed. Tenant tasks require `tenant_id`. System resources use `scope_type=system` without a fabricated tenant.
The HTTP adapter uses the authenticated identity. `PolicyEngine` resolves that identity through server-owned `identity_actor_contexts`; request payload fields do not grant scope. Public create binds the trusted scope, and public list/get apply parameterized scope predicates in `TaskPlaneStore`.
SQLite is the current runtime database. PostgreSQL remains a separate migration and runtime-acceptance gate.
@@ -0,0 +1,38 @@
# R4.2 P0-B — Durable Message / Handoff Fabric
Status: candidate implementation; not evidence of protected-main merge or Production deployment.
`MessageEnvelope` is the single durable handoff identity and carries source/target/type, tenant/user/
project/conversation/task/run scope, causation, sequence, capability scope, confidentiality scope,
idempotency key, expiry and delivery state.
Identity includes **target + scope + sequence + idempotency key + payload hash**, fixing the existing
AgentEventBus target collision. Server ActorContext is authoritative; caller scope may narrow but may
not widen/forge trusted tenant/user/project/conversation/run fields.
`DurableHandoffStore` provides SQLite durability in the current runtime. Each logical stream has
unique `(stream_key, idempotency_key)` and `(stream_key, sequence)`. Exact retry returns `REPLAY`;
changed payload under the same key is rejected; sequence gaps are rejected; expired messages are not
delivered.
Confidentiality scopes:
- public: no tenant requirement
- tenant: same tenant
- project: same tenant + project
- private: same tenant + project + user
- run: same tenant + project + user + run
Required `capability_scope` must be present on the authenticated delivery actor unless the actor is
explicitly administrative.
Compatibility adapters convert AgentEventBus events, TaskPlane CloudEvents and legacy Agent OS
MessageBus messages into the durable envelope. Existing message_outbox remains intact as a migration
source; P0-B does not delete or silently rewrite it.
Required gates:
`MESSAGE_SCOPE_MISMATCH_DENY`, `MESSAGE_TARGET_COLLISION_DENY`, `MESSAGE_IDEMPOTENCY_REPLAY`,
`MESSAGE_SEQUENCE_GAP_DETECT`, `MESSAGE_CONFIDENTIALITY_SCOPE_ENFORCE`,
`HANDOFF_CROSS_TENANT_DENY`, plus existing P0-A TaskPlane scope/security regressions.
SQLite remains current runtime persistence. PostgreSQL remains a separate migration gate.
+5
View File
@@ -48,3 +48,8 @@ class MessageBus:
messages = list(self.queue)
self.queue.clear()
return messages
# R4.2 P0-B compatibility adapter.
def to_handoff_envelope(message, *, target=None, sequence=1, idempotency_key=None, **scope):
from message_handoff_adapters import legacy_message_to_envelope
return legacy_message_to_envelope(message, target=target, sequence=sequence, idempotency_key=idempotency_key, **scope)
@@ -45,6 +45,9 @@ class ShadowClientRBACPublicInterfaceTests(unittest.TestCase):
identity_verifier=self.IdentityVerifier({"shadow-client"}),
execution_enabled=False,
identity_capabilities={"shadow-client": set(capabilities)},
identity_actor_contexts={
"shadow-client": {"scope_type": "system"}
},
)
service = self.TaskPlaneService(store, policy=policy)
@@ -0,0 +1,206 @@
from __future__ import annotations
from dataclasses import dataclass, field
from pathlib import Path
import sys
ROOT = Path(__file__).resolve().parents[3]
ACTIVE_RUNTIME = ROOT / "active-runtime"
if str(ACTIVE_RUNTIME) not in sys.path:
sys.path.insert(0, str(ACTIVE_RUNTIME))
import sqlite3
import threading
import pytest
from app.task_plane.fleet import FleetConflict, FleetScheduler
@dataclass
class Plan:
task_id: str
required_capabilities: list[str] = field(default_factory=lambda:["code.read"])
metadata: dict = field(default_factory=dict)
scope_type: str = "tenant"
tenant_id: str = "tenant-a"
project_id: str | None = "project-a"
user_id: str | None = None
@dataclass
class Task:
task_id: str
revision: int = 1
status: str = "QUEUED"
created_at: float = 1.0
task_plan: Plan | None = None
def __post_init__(self):
if self.task_plan is None:
self.task_plan=Plan(self.task_id)
@dataclass
class Worker:
worker_id: str
capabilities: list[str]=field(default_factory=lambda:["code.read"])
class Store:
def __init__(self, path=":memory:"):
self.conn=sqlite3.connect(path,check_same_thread=False)
self._lock=threading.RLock()
self.conn.executescript("""
CREATE TABLE IF NOT EXISTS claims(
claim_id TEXT PRIMARY KEY,task_id TEXT,worker_id TEXT,status TEXT,lease_expires_at REAL
);
""")
self.tasks=[]
self.workers={}
def list_tasks(self,_ctx=None):
return list(self.tasks)
def get_worker(self,worker_id):
return self.workers[worker_id]
class Registry:
def __init__(self):
self.online=set()
def is_online(self,worker_id,now=None):
return worker_id in self.online
@pytest.fixture
def fleet():
store=Store(); registry=Registry()
for wid in ("w-a","w-b","w-c"):
store.workers[wid]=Worker(wid)
registry.online.add(wid)
scheduler=FleetScheduler(store,registry,now_fn=lambda:1000.0)
scheduler.configure_worker("w-a",max_slots=1,failure_domain="zone-a",weight=1)
scheduler.configure_worker("w-b",max_slots=2,failure_domain="zone-b",weight=1)
scheduler.configure_worker("w-c",max_slots=1,failure_domain="zone-c",weight=2)
return store,registry,scheduler
def test_FLEET_AGENT_REGISTRATION_capacity_policy_is_durable(fleet):
store,_,scheduler=fleet
policy=scheduler.state.worker_policy("w-b")
assert policy.max_slots==2 and policy.failure_domain=="zone-b"
reloaded=type(scheduler)(store, scheduler.workers, now_fn=lambda:1000.0)
assert reloaded.state.worker_policy("w-b").max_slots==2
def test_FLEET_CAPACITY_SCHEDULING_does_not_oversubscribe_worker(fleet):
store,_,scheduler=fleet
store.tasks=[Task("task-1"),Task("task-2"),Task("task-3")]
decisions=scheduler.select(["w-a"],limit=3,now=1000.0)
assert [d.worker_id for d in decisions]==["w-a"]
def test_FLEET_CAPACITY_SCHEDULING_accounts_for_active_claims(fleet):
store,_,scheduler=fleet
store.conn.execute(
"INSERT INTO claims VALUES ('claim-1','other','w-a','ACTIVE',2000)"
)
store.tasks=[Task("task-1")]
assert scheduler.select(["w-a"],limit=1,now=1000.0)==[]
def test_FLEET_FAIRNESS_scope_virtual_finish_prevents_hot_scope_monopoly(fleet):
store,_,scheduler=fleet
store.tasks=[
Task("a1",created_at=1,task_plan=Plan("a1",tenant_id="tenant-a",project_id="p-a")),
Task("a2",created_at=2,task_plan=Plan("a2",tenant_id="tenant-a",project_id="p-a")),
Task("b1",created_at=3,task_plan=Plan("b1",tenant_id="tenant-b",project_id="p-b")),
]
first=scheduler.select(["w-b"],limit=1,now=1000.0)[0]
assert first.task_id=="a1"
scheduler.state.release("a1",state="COMPLETED",now=1000.1)
store.tasks=[task for task in store.tasks if task.task_id!="a1"]
second=scheduler.select(["w-b"],limit=1,now=1000.2)[0]
assert second.task_id=="b1"
def test_FLEET_FAULT_ISOLATION_opens_worker_circuit_after_threshold(fleet):
store,_,scheduler=fleet
store.tasks=[Task("task-1")]
for _ in range(3):
scheduler.state.record_worker_failure("w-a","runtime_crash",now=1000.0)
assert scheduler.state.worker_circuit_open("w-a",1001.0)
assert scheduler.select(["w-a"],limit=1,now=1001.0)==[]
def test_FLEET_WORKER_REASSIGNMENT_avoids_quarantined_worker(fleet):
store,_,scheduler=fleet
store.tasks=[Task("task-1")]
scheduler.state.record_task_worker_failure(
"task-1","w-a","lease_expired",quarantine_seconds=60,now=1000.0
)
decision=scheduler.select(["w-a","w-b"],limit=1,now=1001.0)[0]
assert decision.worker_id=="w-b"
def test_FLEET_SCOPE_ISOLATION_uses_tenant_project_fairness_keys(fleet):
store,_,scheduler=fleet
store.tasks=[
Task("a",task_plan=Plan("a",tenant_id="tenant-a",project_id="p")),
Task("b",task_plan=Plan("b",tenant_id="tenant-b",project_id="p")),
]
decisions=scheduler.select(["w-b"],limit=2,now=1000.0)
assert {d.scope_key for d in decisions}=={
"tenant:tenant-a|project:p","tenant:tenant-b|project:p"
}
def test_FLEET_IDEMPOTENT_DISPATCH_replay_same_task_worker(fleet):
store,_,scheduler=fleet
store.tasks=[Task("task-1")]
one=scheduler.select(["w-b"],limit=1,now=1000.0)[0]
# Reservation remains authoritative; a conflicting second worker cannot steal it.
with pytest.raises(FleetConflict):
scheduler.state.reserve(
task_id="task-1",worker_id="w-c",task_revision=1,
scope_key=one.scope_key,failure_domain="zone-c",score=one.score,
reservation_seconds=30,now=1001.0,scope_weight=1.0,
)
def test_FLEET_FAILURE_RECOVERY_worker_success_closes_circuit(fleet):
store,_,scheduler=fleet
for _ in range(3):
scheduler.state.record_worker_failure("w-a","runtime_crash",now=1000.0)
scheduler.state.record_worker_success("w-a",now=1001.0)
assert not scheduler.state.worker_circuit_open("w-a",1001.1)
def test_affinity_and_failure_domain_anti_affinity(fleet):
store,_,scheduler=fleet
scheduler.configure_worker("w-b",max_slots=2,failure_domain="zone-b",labels={"gpu":"false"})
scheduler.configure_worker("w-c",max_slots=1,failure_domain="zone-c",labels={"gpu":"true"})
task=Task("gpu-task")
task.task_plan.metadata={
"fleet_affinity_labels":{"gpu":"true"},
"fleet_avoid_failure_domains":["zone-b"],
}
store.tasks=[task]
decision=scheduler.select(["w-b","w-c"],limit=1,now=1000.0)[0]
assert decision.worker_id=="w-c"
def test_FLEET_FAILURE_RECOVERY_state_survives_sqlite_restart(tmp_path):
path=tmp_path/"task-plane.sqlite3"
first=Store(str(path)); registry=Registry()
first.workers["w-a"]=Worker("w-a"); registry.online.add("w-a")
scheduler=FleetScheduler(first,registry,now_fn=lambda:1000.0)
scheduler.configure_worker("w-a",max_slots=3,failure_domain="zone-a")
scheduler.state.record_worker_failure("w-a","runtime_crash",threshold=1,now=1000.0)
first.conn.close()
second=Store(str(path)); second.workers["w-a"]=Worker("w-a")
resumed=FleetScheduler(second,registry,now_fn=lambda:1001.0)
assert resumed.state.worker_policy("w-a").max_slots==3
assert resumed.state.worker_circuit_open("w-a",1001.0)
@@ -0,0 +1,298 @@
from __future__ import annotations
import json
import os
import sqlite3
import sys
import threading
import urllib.error
import urllib.request
from http.server import ThreadingHTTPServer
import pytest
ROOT = os.getcwd()
if os.path.join(ROOT, "active-runtime") not in sys.path:
sys.path.append(os.path.join(ROOT, "active-runtime"))
from app.task_plane.api import TaskPlaneRequestHandler, TaskPlaneService
from app.task_plane.errors import ForbiddenError, NotFoundError, ValidationError
from app.task_plane.models import TaskPlan
from app.task_plane.policy import PolicyEngine
from app.task_plane.store import TaskPlaneStore
def _policy() -> PolicyEngine:
return PolicyEngine(
identity_capabilities={
"actor-a": {"task.creator", "task.read"},
"actor-b": {"task.creator", "task.read"},
"reader-a": {"task.read"},
"reader-b": {"task.read"},
"owner": {"task.creator", "task.read", "task.read.all"},
"unbound": {"task.creator", "task.read"},
},
identity_actor_contexts={
"actor-a": {
"scope_type": "tenant",
"tenant_id": "tenant-a",
"user_id": "user-a",
"project_id": "project-a",
"conversation_id": "conversation-a",
"run_id": "run-a",
},
"reader-a": {
"scope_type": "tenant",
"tenant_id": "tenant-a",
"user_id": "user-a",
"project_id": "project-a",
"conversation_id": "conversation-a",
"run_id": "run-a",
},
"actor-b": {
"scope_type": "tenant",
"tenant_id": "tenant-b",
"user_id": "user-b",
"project_id": "project-b",
},
"reader-b": {
"scope_type": "tenant",
"tenant_id": "tenant-b",
"user_id": "user-b",
"project_id": "project-b",
},
"owner": {"scope_type": "system"},
},
)
def _service() -> TaskPlaneService:
return TaskPlaneService(TaskPlaneStore(":memory:"), policy=_policy())
def test_taskplan_scope_fields_round_trip_as_first_class_values() -> None:
plan = TaskPlan.from_dict(
{
"task_id": "task-scope-roundtrip",
"scope_type": "tenant",
"tenant_id": "tenant-a",
"user_id": "user-a",
"project_id": "project-a",
"conversation_id": "conversation-a",
"run_id": "run-a",
}
)
payload = plan.to_dict()
assert TaskPlan.from_dict(payload).to_dict() == payload
def test_tenant_scope_requires_tenant_id_and_system_scope_does_not() -> None:
with pytest.raises(ValidationError) as exc:
TaskPlan.from_dict({"task_id": "task-missing-tenant", "scope_type": "tenant"})
assert exc.value.error_code == "TASK_SCOPE_TENANT_ID_REQUIRED"
system = TaskPlan.from_dict(
{"task_id": "task-system", "scope_type": "system", "run_id": "system-run"}
)
assert system.tenant_id is None
def test_ACTOR_BINDING_AUTHZ_MERGE_uses_server_scope() -> None:
service = _service()
created = service.create_task(
{"task_id": "task-a", "task_type": "code.change"},
actor_identity="actor-a",
)
assert created["plan"]["tenant_id"] == "tenant-a"
assert created["plan"]["user_id"] == "user-a"
assert created["plan"]["project_id"] == "project-a"
declared = service.create_task(
{
"task_id": "task-a-declared",
"tenant_id": "tenant-a",
"user_id": "user-a",
"project_id": "project-a",
"conversation_id": "conversation-a",
"run_id": "run-a",
},
actor_identity="actor-a",
)
assert declared["plan"]["scope_type"] == "tenant"
def test_TASK_SCOPE_MISMATCH_DENY_rejects_forged_client_scope() -> None:
service = _service()
with pytest.raises(ForbiddenError) as exc:
service.create_task(
{
"task_id": "task-forged",
"scope_type": "tenant",
"tenant_id": "tenant-b",
"user_id": "user-b",
"project_id": "project-b",
},
actor_identity="actor-a",
)
assert exc.value.error_code == "TASK_SCOPE_MISMATCH_DENY"
def test_public_create_fails_closed_without_server_actor_scope() -> None:
service = _service()
with pytest.raises(ForbiddenError) as exc:
service.create_task(
{"task_id": "task-unbound"}, actor_identity="unbound"
)
assert exc.value.error_code == "TASK_ACTOR_SCOPE_UNAVAILABLE"
def test_TASKPLANE_LIST_AUTHZ_DENY_and_TASK_OWNERSHIP_FILTER() -> None:
service = _service()
service.create_task({"task_id": "task-a"}, actor_identity="actor-a")
service.create_task({"task_id": "task-b"}, actor_identity="actor-b")
assert [item["task_id"] for item in service.list_tasks("reader-a")] == ["task-a"]
assert [item["task_id"] for item in service.list_tasks("reader-b")] == ["task-b"]
def test_TASKPLANE_GET_AUTHZ_DENY_does_not_disclose_cross_tenant_task() -> None:
service = _service()
service.create_task({"task_id": "task-a"}, actor_identity="actor-a")
with pytest.raises(NotFoundError):
service.get_task("task-a", "reader-b")
def test_http_authentication_drives_server_scope_and_cross_tenant_404() -> None:
service = _service()
class Handler(TaskPlaneRequestHandler):
pass
Handler.service = service
Handler.authenticator = lambda token: {
"token-a": "actor-a",
"token-b": "reader-b",
}.get(token)
server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
thread = threading.Thread(target=server.serve_forever, daemon=True)
thread.start()
base = f"http://127.0.0.1:{server.server_port}"
try:
request = urllib.request.Request(
base + "/tasks",
data=json.dumps({"task_id": "task-http-a"}).encode(),
headers={
"Authorization": "Bearer token-a",
"Content-Type": "application/json",
},
method="POST",
)
with urllib.request.urlopen(request, timeout=3) as response:
created = json.loads(response.read())
assert created["plan"]["tenant_id"] == "tenant-a"
denied = urllib.request.Request(
base + "/tasks/task-http-a",
headers={"Authorization": "Bearer token-b"},
)
with pytest.raises(urllib.error.HTTPError) as exc:
urllib.request.urlopen(denied, timeout=3)
assert exc.value.code == 404
finally:
server.shutdown()
server.server_close()
thread.join(timeout=3)
def test_mutating_endpoint_is_scoped_before_cancel() -> None:
policy = PolicyEngine(
execution_enabled=True,
identity_capabilities={
"actor-a": {"task.creator", "task.read"},
"actor-b": {"task.cancel"},
},
identity_actor_contexts={
"actor-a": {"scope_type": "tenant", "tenant_id": "tenant-a"},
"actor-b": {"scope_type": "tenant", "tenant_id": "tenant-b"},
},
)
service = TaskPlaneService(TaskPlaneStore(":memory:"), policy=policy)
service.create_task({"task_id": "task-a"}, actor_identity="actor-a")
with pytest.raises(NotFoundError):
service.cancel("task-a", {"actor_identity": "actor-b"})
def test_privileged_server_actor_can_cross_scope() -> None:
service = _service()
service.create_task({"task_id": "task-a"}, actor_identity="actor-a")
service.create_task({"task_id": "task-b"}, actor_identity="actor-b")
assert {item["task_id"] for item in service.list_tasks("owner")} == {
"task-a",
"task-b",
}
def test_scope_sql_parameters_do_not_interpolate_tenant_values() -> None:
service = _service()
service.create_task({"task_id": "task-a"}, actor_identity="actor-a")
policy = PolicyEngine(
identity_capabilities={"attacker": {"task.read"}},
identity_actor_contexts={
"attacker": {
"scope_type": "tenant",
"tenant_id": "tenant-a' OR 1=1 --",
}
},
)
attacker_service = TaskPlaneService(service.store, policy=policy)
assert attacker_service.list_tasks("attacker") == []
def test_existing_sqlite_rows_migrate_to_legacy_without_tenant_guess(tmp_path) -> None:
path = tmp_path / "legacy.sqlite3"
connection = sqlite3.connect(path)
connection.execute(
"""
CREATE TABLE tasks (
task_id TEXT PRIMARY KEY, revision INTEGER NOT NULL, status TEXT NOT NULL,
task_json TEXT NOT NULL, task_type TEXT NOT NULL, root_task_id TEXT NOT NULL,
parent_task_id TEXT, correlation_id TEXT, idempotency_key TEXT UNIQUE,
created_at REAL NOT NULL, updated_at REAL NOT NULL, failure_reason TEXT
)
"""
)
connection.execute(
"INSERT INTO tasks VALUES (?,?,?,?,?,?,?,?,?,?,?,?)",
(
"task-legacy",
1,
"CREATED",
json.dumps({"task_id": "task-legacy"}),
"code.change",
"task-legacy",
None,
None,
"legacy-key",
1.0,
1.0,
None,
),
)
connection.commit()
connection.close()
store = TaskPlaneStore(str(path))
task = store.get_task("task-legacy")
assert task.task_plan.scope_type == "legacy"
assert task.task_plan.tenant_id is None
replay = store.create_task(
TaskPlan.from_dict({"task_id": "task-legacy"}),
idempotency_key="legacy-key",
)
assert replay.task_id == "task-legacy"
assert tuple(
store.conn.execute(
"SELECT scope_type,tenant_id FROM tasks WHERE task_id='task-legacy'"
).fetchone()
) == ("legacy", None)
tenant_context = _policy().actor_context("reader-a")
with pytest.raises(NotFoundError):
store.get_task("task-legacy", tenant_context)
store.close()
+9
View File
@@ -20,3 +20,12 @@ def test_unified_event_flow():
dashboard = AgentEventDashboard(bus).overview()
assert dashboard["audit"]["enabled"] is True
def test_target_changes_event_identity(tmp_path):
bus = AgentEventBus(tmp_path)
first = bus.publish('test', 'same', 'user-a', 'same summary', {'value': 1})
second = bus.publish('test', 'same', 'user-b', 'same summary', {'value': 1})
first_id = first.get('id') if isinstance(first, dict) else getattr(first, 'id', first)
second_id = second.get('id') if isinstance(second, dict) else getattr(second, 'id', second)
assert first_id != second_id
+117
View File
@@ -0,0 +1,117 @@
from pathlib import Path
import hashlib, json, sqlite3, sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
from aios_agent_task_retry_extension import RetryExtensionRequest, RetryExtensionStore, RetryExtensionError
AUTHORIZATION_ID="owner-scheme-a-20260817"
@pytest.fixture(autouse=True)
def _authorization_id(monkeypatch):
monkeypatch.setenv("AIOS_AGENT_TASK_AUTHORIZATION_ID", AUTHORIZATION_ID)
def canon(v):
return hashlib.sha256(json.dumps(v,sort_keys=True,separators=(",",":")).encode()).hexdigest()
def db(tmp_path):
p=tmp_path/"state.sqlite3"
c=sqlite3.connect(p)
c.executescript("""
CREATE TABLE tasks(
task_id TEXT PRIMARY KEY,status TEXT,attempt INTEGER,max_attempts INTEGER,revision INTEGER,
claimed_by TEXT,lease_token_hash TEXT,lease_expires_at TEXT,verification_json TEXT,result_json TEXT
);
CREATE TABLE task_events(
event_id INTEGER PRIMARY KEY AUTOINCREMENT,task_id TEXT,event_type TEXT,agent_id TEXT,
payload_json TEXT,created_at TEXT
);
""")
verification={"decision":"NEEDS_REWORK","reason":"BASE_OID_BINDING_INVALID"}
c.execute("INSERT INTO tasks VALUES (?,?,?,?,?,?,?,?,?,?)",
("task-a","FAILED",10,10,41,None,None,None,json.dumps(verification),json.dumps({"status":"FAILED"})))
c.commit(); c.close()
return p,verification
def request(v):
return RetryExtensionRequest.from_mapping({
"expected_status":"FAILED","expected_revision":41,"expected_attempt":10,"expected_max_attempts":10,
"next_max_attempts":11,"previous_verification_sha256":canon(v),
"authorization_id":AUTHORIZATION_ID,"idempotency_key":"retry-task-a-attempt11",
})
def test_retry_extension_cas_and_audit(tmp_path):
p,v=db(tmp_path)
out=RetryExtensionStore(p).extend("task-a",request(v))
assert out["status"]=="QUEUED" and out["max_attempts"]==11 and out["revision"]==42
c=sqlite3.connect(p)
assert c.execute("select status,attempt,max_attempts,revision from tasks").fetchone()==("QUEUED",10,11,42)
event=c.execute("select event_type,payload_json from task_events").fetchone()
assert event[0]=="TASK_RETRY_EXTENSION_AUTHORIZED"
assert json.loads(event[1])["authorization_id"]=="owner-scheme-a-20260817"
def test_retry_extension_idempotent_replay(tmp_path):
p,v=db(tmp_path); store=RetryExtensionStore(p); req=request(v)
first=store.extend("task-a",req); second=store.extend("task-a",req)
assert first["idempotent"] is False and second["idempotent"] is True
c=sqlite3.connect(p)
assert c.execute("select count(*) from task_retry_extensions").fetchone()[0]==1
def test_retry_extension_normalizes_stale_terminal_claim_without_active_lease(tmp_path):
p,v=db(tmp_path)
c=sqlite3.connect(p)
c.execute("update tasks set claimed_by='previous-worker'")
c.commit(); c.close()
out=RetryExtensionStore(p).extend("task-a",request(v))
assert out["status"]=="QUEUED"
c=sqlite3.connect(p)
assert c.execute(
"select claimed_by,lease_token_hash,lease_expires_at from tasks"
).fetchone()==(None,None,None)
payload=json.loads(c.execute("select payload_json from task_events").fetchone()[0])
assert payload["previous_claimed_by"]=="previous-worker"
assert payload["stale_terminal_claim_normalized"] is True
assert c.execute("select count(*) from task_events").fetchone()[0]==1
def test_retry_extension_verification_drift_denied(tmp_path):
p,v=db(tmp_path)
bad=request({"decision":"NEEDS_REWORK","reason":"other"})
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_VERIFICATION_DRIFT"):
RetryExtensionStore(p).extend("task-a",bad)
def test_retry_extension_authorization_id_mismatch_rejected(tmp_path, monkeypatch):
p,v=db(tmp_path)
monkeypatch.setenv("AIOS_AGENT_TASK_AUTHORIZATION_ID", "other-owner-id")
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_AUTHORIZATION_ID_MISMATCH"):
RetryExtensionStore(p).extend("task-a",request(v))
def test_retry_extension_bounded_one_step():
v={"decision":"NEEDS_REWORK"}
data={
"expected_status":"FAILED","expected_revision":41,"expected_attempt":10,"expected_max_attempts":10,
"next_max_attempts":12,"previous_verification_sha256":canon(v),
"authorization_id":"owner-scheme-a-20260817","idempotency_key":"retry-task-a-attempt11",
}
with pytest.raises(RetryExtensionError,match="RETRY_EXTENSION_MUST_BE_BOUNDED_ONE_STEP"):
RetryExtensionRequest.from_mapping(data)
def test_retry_extension_unit_is_unprivileged_and_requires_owner_binding():
unit=(ROOT/"deploy/systemd/aios-agent-task-retry-extension.service").read_text()
assert "User=aios-agent-task" in unit
assert "Group=aios-agent-task" in unit
assert "LoadCredential=agent_task_control_token:" in unit
assert "EnvironmentFile=/etc/aios-gitops/agent-task-retry-extension.env" in unit
assert "User=root" not in unit
+122 -1
View File
@@ -2,6 +2,7 @@ import base64
from pathlib import Path
from aios_authority_git_executor import AuthorityGitExecutor
from aios_chatgpt_bridge_v2 import BridgeV2Adapter, OPERATION_REQUIRED_FIELDS
from aios_chatgpt_bridge_v2_server import BridgeHandler, RuntimeConfig
from aios_continuation_executor import GiteaContinuationRemote, ServerSideCredentialProjection
from aios_continuation_lease import WriterLeaseRequestV2
@@ -26,6 +27,7 @@ class Probe:
def test_create_new_lease_is_exact_base_and_absent():
request = WriterLeaseRequestV2(
job_id="job-bridge-runtime-lineage-test",
task_id="TASK-P0-BRIDGE-V21-DURABLE-RECONCILIATION-20260809",
repository="aios/aios",
branch_mode="CREATE_NEW",
@@ -39,6 +41,7 @@ def test_create_new_lease_is_exact_base_and_absent():
def test_create_new_lease_rejects_existing_target():
request = WriterLeaseRequestV2(
job_id="job-bridge-runtime-lineage-test",
task_id="task",
repository="aios/aios",
branch_mode="CREATE_NEW",
@@ -75,7 +78,7 @@ def test_slash_branch_uses_paginated_collection():
def test_http_route_contract_is_complete():
expected = {
"/v2/runtime", "/v2/capabilities", "/v2/governed-task",
"/v2/writer-lease", "/v2/commit-file", "/v2/commit-files",
"/v2/writer-lease", "/v2/writer-lease/bootstrap", "/v2/writer-lease/renew", "/v2/commit-file", "/v2/commit-files",
"/v2/job", "/v2/job/resume", "/v2/job/reconcile",
"/v2/tag/approval-request",
"/v2/tag/publish",
@@ -88,3 +91,121 @@ def test_http_route_contract_is_complete():
from aios_chatgpt_bridge_v2_server import ROUTES
assert set(ROUTES) == expected
def test_renew_writer_lease_is_exposed_in_action_and_capability_contracts():
adapter = BridgeV2Adapter(runtime_status={})
capabilities = adapter.getGovernedWriteCapabilities()
contract = capabilities["operation_contracts"]["renewWriterLease"]
assert contract["method"] == "POST"
assert contract["path"] == "/v2/writer-lease/renew"
assert tuple(contract["required_fields"]) == OPERATION_REQUIRED_FIELDS["renewWriterLease"]
assert "runtime_rehydrated" in contract["response_fields"]
action_schema = Path("docs/gitops/openapi-chatgpt-actions.yaml").read_text(encoding="utf-8")
assert "/v2/writer-lease/renew:" in action_schema
assert "operationId: renewWriterLease" in action_schema
assert "BridgeWriterLeaseRecoveryRequest" in action_schema
assert "BridgeWriterLeaseRecoveryResponse" in action_schema
assert {
capabilities["operation_contracts"][operation]["path"]
for operation in (
"acquireWriterLease",
"renewWriterLease",
"commitFileGoverned",
"commitFilesGoverned",
)
} == {
"/v2/writer-lease",
"/v2/writer-lease/renew",
"/v2/commit-file",
"/v2/commit-files",
}
def test_bootstrap_writer_lease_is_exposed_in_action_and_capability_contracts():
adapter = BridgeV2Adapter(runtime_status={})
capabilities = adapter.getGovernedWriteCapabilities()
contract = capabilities["operation_contracts"]["bootstrapWriterLease"]
assert contract["method"] == "POST"
assert contract["path"] == "/v2/writer-lease/bootstrap"
assert tuple(contract["required_fields"]) == OPERATION_REQUIRED_FIELDS["bootstrapWriterLease"]
assert "bootstrapped" in contract["response_fields"]
assert "durable_branch_lease_present" in contract["response_fields"]
action_schema = Path("docs/gitops/openapi-chatgpt-actions.yaml").read_text(encoding="utf-8")
assert "/v2/writer-lease/bootstrap:" in action_schema
assert "operationId: bootstrapWriterLease" in action_schema
assert "bootstrapped: {type: boolean}" in action_schema
assert "durable_branch_lease_present: {type: boolean}" in action_schema
def test_http_allows_explicit_job_id_on_lease_and_commit_requests():
handler = BridgeHandler.__new__(BridgeHandler)
lease_body = {
"schema": WriterLeaseRequestV2.schema,
"task_id": "task",
"job_id": "job-explicit-runtime-lineage",
"repository": "aios/aios",
"branch_mode": "CONTINUE_EXISTING",
"base_oid": "a" * 40,
"expected_branch_oid": "a" * 40,
"target_branch": "agent/explicit-runtime-lineage",
"generation": 2,
"lease_seconds": 120,
}
handler._allowed("acquireWriterLease", lease_body)
handler._allowed(
"commitFilesGoverned",
{
"task_id": "task",
"job_id": "job-explicit-runtime-lineage",
"repository": "aios/aios",
"expected_branch_oid": "a" * 40,
"target_branch": "agent/explicit-runtime-lineage",
"generation": 2,
"idempotency_key": "commit-explicit-runtime-lineage",
"files": {"docs/x.txt": "eA=="},
"message": "test",
},
)
def test_http_allows_omitted_job_id_for_durable_server_resolution():
handler = BridgeHandler.__new__(BridgeHandler)
lease_body = {
"schema": WriterLeaseRequestV2.schema,
"task_id": "task",
"repository": "aios/aios",
"branch_mode": "CONTINUE_EXISTING",
"base_oid": "a" * 40,
"expected_branch_oid": "a" * 40,
"target_branch": "agent/implicit-runtime-lineage",
"generation": 2,
"lease_seconds": 120,
}
handler._allowed("acquireWriterLease", lease_body)
handler._allowed(
"commitFilesGoverned",
{
"task_id": "task",
"repository": "aios/aios",
"expected_branch_oid": "a" * 40,
"target_branch": "agent/implicit-runtime-lineage",
"generation": 2,
"idempotency_key": "commit-implicit-runtime-lineage",
"files": {"docs/x.txt": "eA=="},
"message": "test",
},
)
def test_capability_contracts_return_exact_job_id_lineage():
contracts = BridgeV2Adapter(runtime_status={}).getGovernedWriteCapabilities()["operation_contracts"]
for operation in ("acquireWriterLease", "bootstrapWriterLease", "renewWriterLease"):
assert "job_id" in contracts[operation]["response_fields"]
for operation in ("commitFileGoverned", "commitFilesGoverned"):
assert "job_id" in contracts[operation]["response_fields"]
@@ -0,0 +1,304 @@
from __future__ import annotations
from pathlib import Path
import re
import json
from types import SimpleNamespace
import pytest
import yaml
from aios_chatgpt_bridge_v2_server import GovernedRuntime
from aios_continuation_executor import ContinuationExecutor
from aios_continuation_lease import WriterLeaseRequestV2
from aios_gitops_job_controller import JobState
TASK = "continuation-normalization-test"
JOB = "job-continuation-normalization-test"
REPO = "aios/aios"
BASE = "a" * 40
BRANCH = "agent/continuation-normalization-test"
class Authority:
def __init__(self, head: str | None) -> None:
self.head = head
def read_ref(self, ref: str) -> str | None:
assert ref == "refs/heads/" + BRANCH
return self.head
def commit_exists(self, oid: str) -> bool:
return oid == BASE
def branch_exists(self, branch: str) -> bool:
assert branch == BRANCH
return self.head is not None
def branch_head(self, branch: str) -> str:
assert branch == BRANCH and self.head is not None
return self.head
def is_ancestor(self, older: str, newer: str) -> bool:
return older == BASE and newer == BASE
def lease(**overrides: object) -> WriterLeaseRequestV2:
values = {
"task_id": TASK,
"job_id": JOB,
"repository": REPO,
"branch_mode": "CREATE_NEW",
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": BRANCH,
"generation": 1,
"lease_seconds": 120,
}
values.update(overrides)
return WriterLeaseRequestV2(**values)
def runtime(*, head: str | None = BASE, **binding_overrides: object) -> GovernedRuntime:
value = GovernedRuntime.__new__(GovernedRuntime)
value.authority = Authority(head)
binding = {
"task_id": TASK,
"job_id": JOB,
"repository": REPO,
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": BRANCH,
"generation": 1,
"branch_mode": "CREATE_NEW",
}
binding.update(binding_overrides)
value.bindings = {TASK: binding}
return value
def test_same_lineage_create_new_normalizes_to_continue_existing() -> None:
normalized = runtime()._normalize_runtime_lease(lease())
assert normalized.branch_mode == "CONTINUE_EXISTING"
assert normalized.task_id == TASK
assert normalized.job_id == JOB
assert normalized.repository == REPO
assert normalized.target_branch == BRANCH
assert normalized.expected_branch_oid == BASE
assert normalized.generation == 1
def test_unprovisioned_create_new_stays_create_new() -> None:
assert runtime(head=None)._normalize_runtime_lease(lease()).branch_mode == "CREATE_NEW"
@pytest.mark.parametrize(
("field", "value"),
(
("repository", "other/repo"),
("base_oid", "b" * 40),
("expected_branch_oid", "b" * 40),
("target_branch", "agent/foreign"),
("generation", 2),
),
)
def test_binding_mismatch_fails_closed(field: str, value: object) -> None:
with pytest.raises(RuntimeError, match="LEASE_BINDING_CONFLICT"):
runtime(**{field: value})._normalize_runtime_lease(lease())
def test_drifted_existing_head_fails_closed() -> None:
with pytest.raises(RuntimeError, match="EXPECTED_BRANCH_OID_CONFLICT"):
runtime(head="b" * 40)._normalize_runtime_lease(lease())
def test_openapi_contract_parses_and_requires_exact_commit_lineage() -> None:
document = yaml.safe_load(
Path("docs/gitops/openapi-chatgpt-actions.yaml").read_text(encoding="utf-8")
)
schema = document["components"]["schemas"]["BridgeCommitResponse"]
assert {
"job_id",
"commit_oid",
"commit_visible",
"branch_mode",
"target_branch",
"generation",
} <= set(schema["required"])
def test_changed_production_files_pass_secret_scan() -> None:
paths = [
Path("active-runtime/app/aios_authority_git_executor.py"),
Path("active-runtime/app/aios_chatgpt_bridge_v2_server.py"),
Path("active-runtime/app/aios_continuation_executor.py"),
Path("active-runtime/app/aios_continuation_lease.py"),
Path("active-runtime/app/authorized_task_writer_provisioning.py"),
Path("active-runtime/app/aios_chatgpt_bridge_v2.py"),
Path("docs/gitops/openapi-chatgpt-actions.yaml"),
]
expression = re.compile(
r"(?i)(BEGIN (RSA|OPENSSH|EC) PRIVATE KEY|"
r"authorization:\\s*bearer\\s+[A-Za-z0-9._-]{12,}|"
r"api[_-]?key\\s*[:=]\\s*['\\\"][^'\\\"]{12,})"
)
hits = []
for path in paths:
for number, line in enumerate(
path.read_text(encoding="utf-8", errors="replace").splitlines(), 1
):
if expression.search(line):
hits.append(f"{path}:{number}")
assert hits == []
def test_remote_verified_job_is_not_completed_when_head_cas_callback_fails() -> None:
class Store:
def read(self, _job_id):
return {
"branch": BRANCH,
"request_json": json.dumps(
{"binding": {"expected_branch_oid": BASE}}
),
}
class Controller:
def __init__(self):
self.store = Store()
self.states = []
def advance(self, _job_id, state, **_kwargs):
self.states.append(state)
return SimpleNamespace(as_dict=lambda: {"state": state.value})
executor = ContinuationExecutor.__new__(ContinuationExecutor)
executor.controller = Controller()
executor._observe_remote = lambda _branch, oid: (oid, oid, True)
def fail_cas(_oid):
raise RuntimeError("LEASE_CAS_CONFLICT")
with pytest.raises(RuntimeError, match="LEASE_CAS_CONFLICT"):
executor._finish_remote_verification(
JOB,
"b" * 40,
"b" * 40,
before_complete=fail_cas,
)
assert executor.controller.states == [JobState.REMOTE_VERIFIED]
@pytest.mark.parametrize("branch_mode", ("CREATE_NEW", "CONTINUE_EXISTING"))
def test_executor_preflight_accepts_the_exact_mode_dependent_normalized_shape(
branch_mode: str,
) -> None:
from datetime import datetime, timedelta, timezone
from aios_continuation_executor import (
ContinuationPermissions,
ContinuationRuntimeBinding,
)
request = lease(branch_mode=branch_mode)
now = datetime.now(timezone.utc)
executor = ContinuationExecutor.__new__(ContinuationExecutor)
executor.authority = Authority(None if branch_mode == "CREATE_NEW" else BASE)
executor.now = lambda: now
executor._max_generation = lambda _branch, *, exclude_job_id=None: 0
executor.workspace = SimpleNamespace(
is_detached=lambda: True,
head_oid=lambda: BASE,
)
executor.remote = SimpleNamespace(repository_identity=lambda: REPO)
binding = ContinuationRuntimeBinding(
request=request,
job_id=JOB,
workspace_path=Path("/tmp/continuation-normalization-test"),
lease_not_before=now - timedelta(seconds=1),
lease_expires_at=now + timedelta(seconds=60),
original_receipt_valid=True,
original_grant_consumed=True,
permissions=ContinuationPermissions(),
)
executor._validate_preflight(binding, job_id=JOB)
def test_create_new_executor_resumes_executing_and_uses_absence_bound_writers() -> None:
from datetime import datetime, timedelta, timezone
from aios_continuation_executor import (
ContinuationCommit,
ContinuationPermissions,
ContinuationRuntimeBinding,
)
new_oid = "b" * 40
class Store:
def read(self, _job_id: str) -> dict[str, object]:
return {"state": "EXECUTING", "revision": 4}
class Controller:
def __init__(self) -> None:
self.store = Store()
self.advanced: list[str] = []
def advance(self, _job_id: str, state: JobState, **_kwargs: object) -> object:
self.advanced.append(state.value)
return SimpleNamespace(as_dict=lambda: {"state": state.value})
class Workspace:
def commit_files(self, _files: object, _message: str) -> str:
return new_oid
class CreateAuthority:
def __init__(self) -> None:
self.created: list[tuple[str, str, str]] = []
def is_ancestor(self, older: str, newer: str) -> bool:
return older == BASE and newer == new_oid
def create_task_branch_cas(self, branch: str, base: str, new: str) -> str:
self.created.append((branch, base, new))
return new
def compare_and_swap_branch(self, *_args: object) -> str:
raise AssertionError("existing-branch CAS must not serve CREATE_NEW")
class CreateRemote:
def __init__(self) -> None:
self.created: list[tuple[str, str]] = []
def push_new_exact(self, branch: str, new: str) -> None:
self.created.append((branch, new))
def push_exact(self, *_args: object) -> None:
raise AssertionError("existing-branch push must not serve CREATE_NEW")
class Credential:
def project(self) -> None: pass
def revoke(self) -> None: pass
controller=Controller(); authority=CreateAuthority(); remote=CreateRemote()
executor=ContinuationExecutor(controller,authority,Workspace(),remote,Credential())
executor._validate_preflight=lambda *_args,**_kwargs: None
executor._finish_remote_verification=lambda *_args,**_kwargs: {
"job_id":JOB,"state":"COMPLETED","receipt":{"authority_oid":new_oid,"commit_visible":True}
}
now=datetime.now(timezone.utc)
binding=ContinuationRuntimeBinding(
request=lease(branch_mode="CREATE_NEW"),job_id=JOB,
workspace_path=Path("/tmp/create-new-executor-resume"),
lease_not_before=now-timedelta(seconds=1),lease_expires_at=now+timedelta(seconds=60),
original_receipt_valid=True,original_grant_consumed=True,
permissions=ContinuationPermissions(),
)
result=executor.execute(
binding,ContinuationCommit("create-new-test",{"docs/test.txt":b"ok"},"test")
)
assert result["state"]=="COMPLETED"
assert authority.created==[(BRANCH,BASE,new_oid)]
assert remote.created==[(BRANCH,new_oid)]
assert controller.advanced==["LOCAL_VERIFIED","REMOTE_SYNCING"]
+67
View File
@@ -0,0 +1,67 @@
from pathlib import Path
import hashlib,json,os,tarfile,sys,tempfile
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
import aios_isolated_executor as mod
def make_archive(tmp_path):
root=tmp_path/"src"; root.mkdir()
(root/"hello.py").write_text("VALUE = 1\n")
archive=tmp_path/"source.tgz"
with tarfile.open(archive,"w:gz") as tf: tf.add(root/"hello.py",arcname="hello.py")
return archive
def test_isolated_executor_applies_hash_bound_change(tmp_path,monkeypatch):
archive=make_archive(tmp_path)
monkeypatch.delenv("CREDENTIALS_DIRECTORY",raising=False)
monkeypatch.setattr(mod,"assert_uncredentialed",lambda:None)
request={
"schema":"aios.isolated-execution.request.v1",
"request_id":"task-req-0000000000000000",
"source_archive":str(archive),
"source_archive_sha256":mod.sha256(archive.read_bytes()),
"change_set":[{
"path":"hello.py","operation":"replace_text","old":"VALUE = 1","new":"VALUE = 2","count":1,
"expected_sha256":mod.sha256(b"VALUE = 1\n")
}],
"verification":[{"label":"compile","argv":["/usr/bin/python3","-m","py_compile","hello.py"],"cwd":".","timeout_seconds":30}]
}
req=tmp_path/"req.json"; res=tmp_path/"res.json"
req.write_text(json.dumps(request))
mod.execute_request(req,res)
out=json.loads(res.read_text())
assert out["request_id"]=="task-req-0000000000000000"
assert out["credential_isolation"]["credential_env_absent"] is True
changed=out["changed_files"][0]
assert changed["path"]=="hello.py" and changed["deleted"] is False
def test_isolated_executor_source_drift_denied(tmp_path,monkeypatch):
archive=make_archive(tmp_path); monkeypatch.setattr(mod,"assert_uncredentialed",lambda:None)
request={
"schema":"aios.isolated-execution.request.v1","request_id":"task-req-0000000000000001",
"source_archive":str(archive),
"source_archive_sha256":mod.sha256(archive.read_bytes()),
"change_set":[{"path":"hello.py","operation":"write_file","content":"x\n","expected_sha256":"0"*64}],
"verification":[]
}
req=tmp_path/"req.json"; res=tmp_path/"res.json"; req.write_text(json.dumps(request))
with pytest.raises(mod.IsolatedExecutorError,match="SOURCE_DRIFT"):
mod.execute_request(req,res)
def test_credential_boundary_eacces_is_accepted(monkeypatch):
class DeniedDirectory:
def exists(self): return True
def is_symlink(self): return False
def is_dir(self): return True
def iterdir(self): raise PermissionError(13,"permission denied")
monkeypatch.setattr(mod.os,"access",lambda *_args,**_kwargs:False)
assert mod._credential_exposure(DeniedDirectory()) is None
def test_systemd_unit_has_no_credentials_and_private_network():
unit=(ROOT/"deploy/systemd/aios-online-agent-isolated-executor.service").read_text()
assert "PrivateNetwork=true" in unit
assert "InaccessiblePaths=/run/credentials" in unit
assert "LoadCredential" not in unit
assert "SupplementaryGroups=gitops" not in unit
+127
View File
@@ -0,0 +1,127 @@
from __future__ import annotations
import datetime as dt
import pathlib
import sys
import pytest
APP = pathlib.Path(__file__).resolve().parents[1] / "active-runtime" / "app"
if str(APP) not in sys.path:
sys.path.insert(0, str(APP))
from message_handoff import (
ConfidentialityScopeDenied,
DeliveryContext,
DurableHandoffStore,
HandoffFabric,
IdempotencyConflict,
MessageEnvelope,
MessageExpired,
MessageScopeMismatch,
SequenceGap,
authorize_delivery,
bind_envelope_scope,
stable_event_id,
)
def actor(**overrides):
values = dict(
tenant_id="tenant-a", user_id="user-a", project_id="project-a",
conversation_id="conversation-a", run_id="run-a",
capabilities=("task.read", "message.read"),
)
values.update(overrides)
return DeliveryContext(**values)
def envelope(**overrides):
values = dict(
source="agent-a", target="agent-b", message_type="handoff.request", payload={"value": 1},
tenant_id="tenant-a", user_id="user-a", project_id="project-a",
conversation_id="conversation-a", task_id="task-a", run_id="run-a",
sequence=1, idempotency_key="idem-1", capability_scope=("message.read",),
confidentiality_scope="private",
)
values.update(overrides)
return MessageEnvelope(**values)
def test_MESSAGE_TARGET_COLLISION_DENY():
a = stable_event_id(source="a", target="user-a", message_type="event", payload={"x": 1},
tenant_id="tenant-a", sequence=1, idempotency_key="same")
b = stable_event_id(source="a", target="user-b", message_type="event", payload={"x": 1},
tenant_id="tenant-a", sequence=1, idempotency_key="same")
assert a != b
def test_MESSAGE_SCOPE_MISMATCH_DENY():
with pytest.raises(MessageScopeMismatch, match="MESSAGE_SCOPE_MISMATCH_DENY"):
bind_envelope_scope(envelope(tenant_id="tenant-b"), actor())
def test_HANDOFF_CROSS_TENANT_DENY(tmp_path):
store = DurableHandoffStore(tmp_path / "handoff.sqlite3")
env = envelope()
store.put(env)
with pytest.raises(MessageScopeMismatch, match="MESSAGE_SCOPE_MISMATCH_DENY"):
store.get(env.envelope_id, actor=actor(tenant_id="tenant-b"))
def test_MESSAGE_CONFIDENTIALITY_SCOPE_ENFORCE():
with pytest.raises(ConfidentialityScopeDenied, match="MESSAGE_CONFIDENTIALITY_SCOPE_ENFORCE"):
authorize_delivery(actor(project_id="project-b"), envelope(confidentiality_scope="project"))
with pytest.raises(ConfidentialityScopeDenied, match="MESSAGE_CONFIDENTIALITY_SCOPE_ENFORCE"):
authorize_delivery(actor(), envelope(capability_scope=("message.read", "secret.read")))
def test_MESSAGE_IDEMPOTENCY_REPLAY(tmp_path):
store = DurableHandoffStore(tmp_path / "handoff.sqlite3")
env = envelope()
assert store.put(env)[0] == "CREATED"
status, replay = store.put(env)
assert status == "REPLAY"
assert replay.envelope_id == env.envelope_id
with pytest.raises(IdempotencyConflict, match="MESSAGE_IDEMPOTENCY_CONFLICT"):
store.put(envelope(payload={"value": 2}))
def test_MESSAGE_SEQUENCE_GAP_DETECT(tmp_path):
store = DurableHandoffStore(tmp_path / "handoff.sqlite3")
store.put(envelope(sequence=1, idempotency_key="one"))
with pytest.raises(SequenceGap, match="MESSAGE_SEQUENCE_GAP_DETECT"):
store.put(envelope(sequence=3, idempotency_key="three"))
def test_sequence_advances_and_scope_filters_pending(tmp_path):
store = DurableHandoffStore(tmp_path / "handoff.sqlite3")
store.put(envelope(sequence=1, idempotency_key="one"))
store.put(envelope(sequence=2, idempotency_key="two", payload={"value": 2}))
assert [item.sequence for item in store.pending(target="agent-b", actor=actor())] == [1, 2]
assert store.pending(target="agent-b", actor=actor(tenant_id="tenant-b")) == []
def test_expired_message_rejected(tmp_path):
expired = (dt.datetime.now(dt.timezone.utc) - dt.timedelta(seconds=1)).isoformat()
with pytest.raises(MessageExpired, match="MESSAGE_EXPIRED"):
DurableHandoffStore(tmp_path / "handoff.sqlite3").put(envelope(expires_at=expired))
def test_server_actor_binding_fills_scope_and_recomputes_identity():
public = MessageEnvelope(
source="agent-a", target="agent-b", message_type="handoff.request", payload={"value": 1},
sequence=1, idempotency_key="bind-1", confidentiality_scope="public",
)
bound = bind_envelope_scope(public, actor())
assert (bound.tenant_id, bound.user_id, bound.project_id, bound.run_id) == (
"tenant-a", "user-a", "project-a", "run-a"
)
assert bound.envelope_id != public.envelope_id
def test_handoff_fabric_publish_is_durable(tmp_path):
store = DurableHandoffStore(tmp_path / "handoff.sqlite3")
status, env = HandoffFabric(store).publish(envelope(), actor=actor())
assert status == "CREATED"
assert store.get(env.envelope_id, actor=actor()).payload == {"value": 1}
@@ -0,0 +1,244 @@
from __future__ import annotations
from pathlib import Path
import json
import sys
import pytest
ROOT = Path(__file__).resolve().parents[1]
APP = ROOT / "active-runtime/app"
sys.path.insert(0, str(APP))
from aios_online_agent_compact_map import (
MAX_RESULT_BYTES,
build_compact_interface_map,
)
from aios_online_agent_execution import (
ExecutionProjectionError,
GovernedExecutionBinding,
project_execution_envelope,
validate_execution_envelope,
)
import aios_online_agent_worker as worker
from aios_online_agent_worker import (
CompactInterfaceMapExecutor,
ExecutionEnvelope,
build_compact_interface_map_result,
)
BASE = "68b95fea0d9af3b52269e79b7cf878254f191b61"
def make_repo(tmp_path: Path) -> Path:
root = tmp_path / "repo"
(root / "active-runtime/app").mkdir(parents=True)
(root / "tests").mkdir(parents=True)
(root / "db/migrations").mkdir(parents=True)
(root / "deploy/systemd").mkdir(parents=True)
(root / "active-runtime/app/fleet.py").write_text(
"""
class WorkerRegistry:
def register_worker(self, worker_id, capabilities):
return {"worker_id": worker_id, "capabilities": capabilities}
class TaskScheduler:
def claim_next(self, tenant_id, capacity):
return None
def recover_assignment(task_id, worker_id):
return task_id, worker_id
TOKEN = "fixturetok"
""".strip() + "\n",
encoding="utf-8",
)
(root / "active-runtime/app/checkpoint.py").write_text(
"""
class CheckpointStore:
def resume(self, task_id, attempt):
return None
""".strip() + "\n",
encoding="utf-8",
)
(root / "tests/test_fleet.py").write_text(
"""
def test_scheduler_fairness():
assert True
def test_worker_reassignment():
assert True
""".strip() + "\n",
encoding="utf-8",
)
(root / "db/migrations/20260817_fleet.sql").write_text(
"CREATE TABLE IF NOT EXISTS worker_slots (worker_id TEXT, capacity INTEGER);\n",
encoding="utf-8",
)
(root / "deploy/systemd/aios-fleet-worker.service").write_text(
"[Service]\nExecStart=/usr/bin/true\n",
encoding="utf-8",
)
return root
def binding() -> GovernedExecutionBinding:
return GovernedExecutionBinding.from_mapping(
{
"task_id": "r42-p2-agent-fleet-interface-map-20260817",
"job_id": "job-2c451360f78ef595e41663e3b444a8fb",
"repository": "aios/aios",
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": "agent/r42-p2-agent-fleet-interface-map-20260817",
"branch_mode": "CREATE_NEW",
"generation": 1,
"idempotency_key": "r42-p2-agent-fleet-interface-map-68b95fe-v1",
}
)
def envelope_mapping():
return project_execution_envelope(
binding(),
{
"action": "source_capture",
"adapter": "compact_interface_map",
"capability_scope": ["git.read", "git.test"],
"source_signals": [
"worker registry scheduler capacity fairness fault isolation",
"checkpoint resume retry scope trace message",
],
},
required_capabilities=["git.read", "git.test"],
)
def task_for(envelope):
return {
"task_id": envelope["task_id"],
"metadata": {"execution": envelope},
"required_capabilities": ["git.read", "git.test"],
}
def test_compact_map_bounds_and_surfaces(tmp_path):
root = make_repo(tmp_path)
result = build_compact_interface_map(
root,
["worker scheduler capacity fairness checkpoint recovery"],
source_commit=BASE,
)
encoded = json.dumps(result, ensure_ascii=False, sort_keys=True, separators=(",", ":")).encode()
assert result["schema"] == "aios.engineering.interface-map.v1"
assert len(encoded) <= MAX_RESULT_BYTES
assert len(result["implementation_map"]["modules"]) <= 40
assert len(result["bounded_excerpts"]) <= 25
assert len(result["implementation_map"]["tests"]) <= 40
assert any(item["symbol"] == "WorkerRegistry" for item in result["implementation_map"]["classes"])
assert any(item["table"] == "worker_slots" for item in result["implementation_map"]["tables"])
assert any(item["unit"] == "aios-fleet-worker.service" for item in result["implementation_map"]["systemd_units"])
def test_compact_map_redacts_sensitive_source_patterns(tmp_path):
root = make_repo(tmp_path)
result = build_compact_interface_map(root, ["token fleet"], source_commit=BASE)
excerpts = json.dumps(result["bounded_excerpts"], ensure_ascii=False)
assert "fixturetok" not in excerpts
def test_compact_execution_projection_is_read_only():
envelope = envelope_mapping()
assert envelope["action"] == "source_capture"
assert envelope["adapter"] == "compact_interface_map"
assert envelope["governance"]["writer_lease"] is False
assert envelope["change_set"] == []
assert envelope["verification"] == []
validate_execution_envelope(envelope, binding=binding(), worker_capabilities=["git.read", "git.test"])
def test_compact_execution_rejects_mutation():
with pytest.raises(ExecutionProjectionError, match="SOURCE_CAPTURE_MUTATION_DENY"):
project_execution_envelope(
binding(),
{
"action": "source_capture",
"adapter": "compact_interface_map",
"change_set": [{"path": "x.py", "operation": "write_file", "content": "x=1\n"}],
},
)
def test_worker_accepts_compact_adapter_and_builds_result(tmp_path, monkeypatch):
root = make_repo(tmp_path)
monkeypatch.setattr(worker, "audit", lambda *args, **kwargs: None)
mapped = envelope_mapping()
envelope = ExecutionEnvelope.from_task(
task_for(mapped),
worker_capabilities=("git.read", "git.test"),
)
execution = CompactInterfaceMapExecutor().execute(envelope, root)
result = build_compact_interface_map_result(envelope.task_id, envelope, execution)
assert result["status"] == "SUCCEEDED"
assert result["classification"] == "P2_INTERFACE_MAP_CAPTURED"
assert result["execution_mode"] == "compact_interface_map"
assert result["writer_lease"] == "NONE"
assert "source_snapshot" not in result
assert result["result_bytes"] <= 120 * 1024
assert result["source_commit"] == BASE
def test_compact_contract_keys_are_complete(tmp_path):
root = make_repo(tmp_path)
result = build_compact_interface_map(root, ["fleet worker scheduler retry"], source_commit=BASE)
assert set(result["contracts"]) == {
"FLEET_AGENT_REGISTRATION",
"FLEET_CAPACITY_SCHEDULING",
"FLEET_FAIRNESS",
"FLEET_FAULT_ISOLATION",
"FLEET_WORKER_REASSIGNMENT",
"FLEET_SCOPE_ISOLATION",
"FLEET_IDEMPOTENT_DISPATCH",
"FLEET_FAILURE_RECOVERY",
}
def test_compact_result_has_no_source_archive(tmp_path):
root = make_repo(tmp_path)
result = build_compact_interface_map(root, ["fleet"], source_commit=BASE)
serialized = json.dumps(result)
assert "payload_b64" not in serialized
assert "tar.gz+base64" not in serialized
def test_create_new_retries_discard_known_policy_reconciliation_marker(tmp_path, monkeypatch):
task_id = "r42-p2-compact-interface-map-runtime-20260817"
job_id = "job-74d0982f616a7f2653ef346144139044"
monkeypatch.setattr(worker, "STATE_ROOT", tmp_path / "worker-state")
state_path = worker.task_state_path(task_id)
state_path.parent.mkdir(parents=True)
state_path.write_text(
json.dumps(
{
"task_id": task_id,
"execution_digest": "old-digest",
"phase": "reconciliation_required",
"attempt": 16,
"job_id": job_id,
"details": {
"api_status": 503,
"error": "SECRET_LIKE_PAYLOAD_REJECTED",
},
}
),
encoding="utf-8",
)
assert worker.load_task_state(
task_id,
"new-digest",
attempt=18,
continuation_head_oid=None,
continuation_job_id=job_id,
commit_idempotency_key="r42-p2-compact-interface-map-runtime-commit-v1",
) is None
@@ -0,0 +1,216 @@
from __future__ import annotations
from pathlib import Path
import json
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
APP=ROOT/"active-runtime/app"
sys.path.insert(0,str(APP))
from aios_online_agent_checkpoint import (
CheckpointBinding,
CheckpointError,
CheckpointStore,
)
import aios_online_agent_worker as worker
def binding(attempt: int = 1, *, tenant_head: str = "b"*40):
return CheckpointBinding(
task_id="task-p1-a",
attempt=attempt,
execution_digest="d"*64,
job_id="job-p1-a",
repository="aios/aios",
base_oid="a"*40,
expected_branch_oid=tenant_head,
target_branch="agent/task-p1-a",
generation=1,
)
def test_CHECKPOINT_DURABLE_WRITE(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
first=store.append(binding(), "claimed", {"phase":"claimed","attempt":1})
second=store.append(binding(), "workspace_prepared", {"phase":"workspace_prepared","attempt":1})
assert first["sequence"] == 1
assert second["sequence"] == 2
latest=store.latest("task-p1-a")
assert latest["phase"]=="workspace_prepared"
assert latest["payload"]["attempt"]==1
def test_CHECKPOINT_SCOPE_ISOLATION(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(), "claimed", {"phase":"claimed"})
changed=CheckpointBinding(
task_id="task-p1-a",attempt=1,execution_digest="d"*64,job_id="job-p1-a",
repository="aios/other",base_oid="a"*40,expected_branch_oid="b"*40,
target_branch="agent/task-p1-a",generation=1,
)
with pytest.raises(CheckpointError,match="CHECKPOINT_SCOPE_MISMATCH_DENY"):
store.append(changed,"workspace_prepared",{"phase":"workspace_prepared"})
def test_RESUME_FROM_CHECKPOINT_across_attempt_same_binding(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(1), "source_capture_done", {
"phase":"source_capture_done",
"attempt":1,
"result":{"status":"SUCCEEDED","classification":"NEEDS_REWORK_SOURCE_CAPTURE"},
})
resumed=store.verify_latest_binding(binding(2))
assert resumed is not None
assert resumed["attempt"]==1
assert resumed["phase"]=="source_capture_done"
def test_checkpoint_new_attempt_can_start_from_claimed(tmp_path):
store=CheckpointStore(tmp_path/"checkpoints.sqlite3")
store.append(binding(1),"result_submitted",{"phase":"result_submitted"})
cp=store.append(binding(2),"claimed",{"phase":"claimed"})
assert cp["attempt"]==2
assert cp["sequence"]==1
def envelope():
return worker.ExecutionEnvelope(
task_id="task-p1-a",
job_id="job-p1-a",
repository="aios/aios",
base_oid="a"*40,
expected_branch_oid="b"*40,
target_branch="agent/task-p1-a",
branch_mode="CONTINUE_EXISTING",
generation=1,
idempotency_key="governed-p1-a",
action="source_capture",
adapter="source_capture",
capability_scope=("git.read","git.test"),
source_signals=(),
change_set=(),
verification=(),
governance={"task_id":"task-p1-a","job_id":"job-p1-a"},
workspace={},
digest="d"*64,
)
def test_RESULT_SUBMISSION_REPLAY_SAFE_attempt_aware_key():
env=envelope()
result={"status":"SUCCEEDED","execution_digest":env.digest}
one=worker.result_idempotency_key(env.task_id,1,env,result)
two=worker.result_idempotency_key(env.task_id,2,env,result)
assert one != two
assert "-a1-result-" in one
assert "-a2-result-" in two
assert one == worker.result_idempotency_key(env.task_id,1,env,result)
class RetryClient:
def __init__(self):
self.calls=[]
def result(self,task_id,lease_token,key,result):
self.calls.append((task_id,key,dict(result)))
return (599,{"error":"SERVICE_UNAVAILABLE"}) if len(self.calls)==1 else (201,{"status":"VERIFYING"})
def get(self,task_id):
return 500,{}
def test_RETRY_IDEMPOTENT_NO_DUPLICATE_SIDE_EFFECT_reuses_same_key(monkeypatch):
client=RetryClient()
monkeypatch.setattr(worker.time,"sleep",lambda _:None)
status,response=worker.submit_result_replay_safe(
client,"task-p1-a","lease-token-"+"x"*32,"stable-key",{"status":"SUCCEEDED"}
)
assert status==201
assert [item[1] for item in client.calls]==["stable-key","stable-key"]
class ConflictClient:
def __init__(self,result):
self.result_value=result
def result(self,*args):
return 409,{"error":"IDEMPOTENCY_CONFLICT"}
def get(self,task_id):
return 200,{"status":"VERIFYING","result":dict(self.result_value)}
def test_RESULT_SUBMISSION_REPLAY_SAFE_reconciles_exact_result():
result={"status":"SUCCEEDED","value":1}
status,response=worker.submit_result_replay_safe(
ConflictClient(result),"task-p1-a","lease-token-"+"x"*32,"stable-key",result
)
assert status==200
assert response["idempotent"] is True
assert response["reconciled"] is True
def test_RESULT_SUBMISSION_REPLAY_SAFE_rejects_conflicting_result():
status,response=worker.submit_result_replay_safe(
ConflictClient({"status":"SUCCEEDED","value":2}),
"task-p1-a","lease-token-"+"x"*32,"stable-key",
{"status":"SUCCEEDED","value":1},
)
assert status==409
assert response["error"]=="IDEMPOTENCY_CONFLICT"
def test_WORKSPACE_CLEANUP_RECOVERY(tmp_path,monkeypatch):
root=tmp_path/"workspaces"; root.mkdir()
stale=root/"task-old"; stale.mkdir(); (stale/"x").write_text("x")
monkeypatch.setattr(worker,"WORKSPACE_ROOT",root)
monkeypatch.setattr(worker,"STATE_ROOT",tmp_path/"state")
removed=worker.recover_stale_workspaces()
assert removed==1
assert not stale.exists()
class LeaseBridge:
def __init__(self):
self.calls=0
def call(self,route,body):
assert route=="/v2/writer-lease"
self.calls+=1
if self.calls==1:
return 599,{"error":"SERVICE_UNAVAILABLE"}
return 200,{
"lease_id":"lease-p1-a",
"job_id":"job-p1-a",
"task_id":"task-p1-a",
"repository":"aios/aios",
"base_oid":"a"*40,
"expected_branch_oid":"b"*40,
"branch_mode":"CONTINUE_EXISTING",
"generation":1,
"target_branch":"agent/task-p1-a",
"state":"ACTIVE",
}
class LeaseHeartbeatStub:
def ensure(self):
return None
def test_LEASE_RENEWAL_RECOVERY_retries_same_binding(monkeypatch):
env=envelope()
env=worker.ExecutionEnvelope(
task_id=env.task_id,job_id=env.job_id,repository=env.repository,
base_oid=env.base_oid,expected_branch_oid=env.expected_branch_oid,
target_branch=env.target_branch,branch_mode=env.branch_mode,generation=env.generation,
idempotency_key=env.idempotency_key,action=env.action,adapter=env.adapter,
capability_scope=env.capability_scope,source_signals=env.source_signals,
change_set=env.change_set,verification=env.verification,
governance={"task_id":env.task_id,"job_id":env.job_id,"lease_seconds":900},
workspace=env.workspace,digest=env.digest,
)
bridge=LeaseBridge()
monkeypatch.setattr(worker.time,"sleep",lambda _:None)
monkeypatch.setattr(worker,"STATE_ROOT",Path("/tmp")/"aios-p1-test-state")
response=worker.acquire_writer_lease_replay_safe(env,bridge,LeaseHeartbeatStub())
assert response["lease_id"]=="lease-p1-a"
assert bridge.calls==2
+60
View File
@@ -0,0 +1,60 @@
from pathlib import Path
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
sys.path.insert(0,str(ROOT/"active-runtime/app"))
from aios_online_agent_execution import GovernedExecutionBinding
from aios_online_agent_plan_store import ExecutionPlanStore, ExecutionPlanError
BASE="a642b045775b9154a00ae78543037fbef4fb447b"
HEAD="71523aef6e48b1e2fa516c456ca189b7a039104b"
def binding(head=HEAD):
return GovernedExecutionBinding.from_mapping({
"task_id":"task-plan-a","job_id":"job-plan-a","repository":"aios/aios","base_oid":BASE,
"expected_branch_oid":head,"target_branch":"agent/task-plan-a","branch_mode":"CONTINUE_EXISTING",
"generation":1,"idempotency_key":"governed-plan-a",
})
def request():
return {
"schema":"aios.online-agent.plan.v1","task_id":"task-plan-a","job_id":"job-plan-a",
"source_head_oid":HEAD,"generation":1,"idempotency_key":"plan-task-a-v1",
"execution":{
"action":"deterministic",
"change_set":[{"path":"x.py","operation":"write_file","content":"x=1\n"}],
"verification":[{"label":"compile","argv":["/usr/bin/python3","-m","py_compile","x.py"],"cwd":".","timeout_seconds":30}],
"capability_scope":["git.read","git.test"],
}
}
def test_plan_register_and_resolve(tmp_path):
store=ExecutionPlanStore(tmp_path)
created=store.register(binding(),request())
assert created["idempotent"] is False
resolved=store.resolve(binding())
assert resolved["plan_digest"]==created["plan_digest"]
assert resolved["execution"]["action"]=="deterministic"
def test_plan_is_idempotent(tmp_path):
store=ExecutionPlanStore(tmp_path); req=request()
first=store.register(binding(),req); second=store.register(binding(),req)
assert second["idempotent"] is True
assert first["plan_digest"]==second["plan_digest"]
def test_plan_source_head_drift_denied(tmp_path):
store=ExecutionPlanStore(tmp_path); store.register(binding(),request())
with pytest.raises(ExecutionPlanError,match="SOURCE_HEAD_DRIFT"):
store.resolve(binding("b"*40))
def test_plan_replacement_requires_cas(tmp_path):
store=ExecutionPlanStore(tmp_path); first=store.register(binding(),request())
changed=request(); changed["idempotency_key"]="plan-task-a-v2"
changed["execution"]["change_set"][0]["content"]="x=2\n"
with pytest.raises(ExecutionPlanError,match="REPLACEMENT_CAS_MISMATCH"):
store.register(binding(),changed)
changed["expected_previous_plan_digest"]=first["plan_digest"]
second=store.register(binding(),changed)
assert second["plan_digest"]!=first["plan_digest"]
@@ -0,0 +1,487 @@
from datetime import datetime, timedelta, timezone
from pathlib import Path
import pytest
from active_runtime.app.aios_credential_broker import CredentialBroker
from active_runtime.app.agent_observability_hooks import AgentObservabilityHooks
from active_runtime.app.message_handoff import DurableHandoffStore, MessageEnvelope
from active_runtime.app.search_gateway import (
SearchEvidence,
SearchGateway,
SearchProviderAttempt,
SearchRequest,
)
from active_runtime.app.search_gateway_orchestrator import SearchGatewayOrchestrator
from active_runtime.app.trace_tool_credential_governance import (
CredentialGrant,
GovernanceActor,
GovernanceError,
GovernanceScope,
GovernanceStore,
ToolDescriptor,
TraceContext,
bind_trace_lineage,
)
TENANT_SCOPE = GovernanceScope(
"tenant",
tenant_id="tenant-a",
user_id="user-a",
project_id="project-a",
conversation_id="conversation-a",
run_id="run-a",
)
def actor(*capabilities: str, tenant_id: str = "tenant-a") -> GovernanceActor:
return GovernanceActor(
"actor-a",
GovernanceScope(
"tenant",
tenant_id=tenant_id,
user_id="user-a",
project_id="project-a",
conversation_id="conversation-a",
run_id="run-a",
),
tuple(capabilities),
)
def owner() -> GovernanceActor:
return GovernanceActor("owner-control", GovernanceScope("system"), ("system.admin",))
def message(**changes):
values = dict(
source="task-plane",
target="worker-a",
message_type="tool.invoke",
payload={"query": "safe"},
sequence=1,
idempotency_key="message-a-1",
tenant_id="tenant-a",
user_id="user-a",
project_id="project-a",
conversation_id="conversation-a",
task_id="task-a",
run_id="run-a",
confidentiality_scope="run",
)
values.update(changes)
return MessageEnvelope(**values)
def task(**changes):
value = {
"task_id": "task-a",
"claim_id": "claim-a",
"correlation_id": "correlation-a",
"scope_type": "tenant",
"tenant_id": "tenant-a",
"user_id": "user-a",
"project_id": "project-a",
"conversation_id": "conversation-a",
"run_id": "run-a",
}
value.update(changes)
return value
def root_trace():
return bind_trace_lineage(
actor=actor("tool.search"),
task=task(),
message=message(),
trace_id="trace-a",
span_id="span-root",
)
def test_trace_lineage_continuity_and_durable_restart(tmp_path: Path) -> None:
store = GovernanceStore(tmp_path / "governance.sqlite3")
root = root_trace()
child = root.child(span_id="span-tool", actor=actor("tool.search"))
store.record_trace(root, actor("tool.search"))
store.record_trace(child, actor("tool.search"))
reopened = GovernanceStore(tmp_path / "governance.sqlite3")
assert reopened.verify_audit_chain(("TRACE_RECORDED",))
assert child.trace_id == root.trace_id
assert child.parent_span_id == root.span_id
assert child.task_id == "task-a"
assert child.claim_id == "claim-a"
def test_trace_lineage_continuity_rejects_task_change() -> None:
with pytest.raises(GovernanceError, match="TRACE_LINEAGE_CONTINUITY"):
bind_trace_lineage(
actor=actor("tool.search"),
task=task(task_id="task-b"),
message=message(),
trace_id="trace-a",
span_id="span-root",
)
def test_trace_scope_mismatch_deny() -> None:
with pytest.raises(GovernanceError, match="TRACE_SCOPE_MISMATCH_DENY"):
bind_trace_lineage(
actor=actor("tool.search"),
task=task(),
message=message(tenant_id="tenant-b"),
trace_id="trace-a",
span_id="span-root",
)
def test_message_correlation_is_identity_bound() -> None:
first = message(correlation_id="correlation-a")
second = message(correlation_id="correlation-b")
assert first.envelope_id != second.envelope_id
assert first.as_record()["correlation_id"] == "correlation-a"
def test_message_handoff_legacy_schema_migrates_without_changing_id(tmp_path: Path) -> None:
import sqlite3
path = tmp_path / "legacy.sqlite3"
legacy = message()
record = legacy.as_record()
record.pop("correlation_id")
with sqlite3.connect(path) as connection:
connection.executescript(
"""
CREATE TABLE 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, 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)
);
"""
)
columns = tuple(record)
connection.execute(
f"INSERT INTO message_handoff ({','.join(columns)}) VALUES ({','.join('?' for _ in columns)})",
tuple(record[name] for name in columns),
)
store = DurableHandoffStore(path)
loaded = store.get(
legacy.envelope_id,
actor={
"tenant_id": "tenant-a", "user_id": "user-a", "project_id": "project-a",
"conversation_id": "conversation-a", "run_id": "run-a",
"capabilities": [],
},
)
assert loaded.envelope_id == legacy.envelope_id
assert loaded.correlation_id is None
def test_message_handoff_rejects_raw_credential_material(tmp_path: Path) -> None:
with pytest.raises(ValueError, match="CREDENTIAL_SECRET_EXPOSURE_DENY"):
message(payload={"value": "Bearer " + "x" * 24})
DurableHandoffStore(tmp_path / "handoff.sqlite3")
import sqlite3
with sqlite3.connect(tmp_path / "handoff.sqlite3") as connection:
assert connection.execute("SELECT count(*) FROM message_handoff").fetchone()[0] == 0
def test_tool_mcp_authz_deny_and_scope_propagation(tmp_path: Path) -> None:
store = GovernanceStore(tmp_path / "governance.sqlite3")
store.register_tool(
ToolDescriptor("mcp.search", "mcp", TENANT_SCOPE, ("tool.search",)),
owner(),
)
trace = root_trace()
store.record_trace(trace, actor("tool.search"))
with pytest.raises(GovernanceError, match="TOOL_MCP_AUTHZ_DENY"):
store.authorize_tool(
actor=actor(), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-deny-capability",
)
with pytest.raises(GovernanceError, match="TOOL_SCOPE_PROPAGATION"):
store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=GovernanceScope("tenant", tenant_id="tenant-b"),
input_digest="a" * 64, invocation_key="invoke-deny-scope",
)
invocation = store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-search-a",
)
assert invocation["trace_id"] == "trace-a"
assert invocation["evidence"]["action"] == "TOOL_AUTHORIZED"
def test_tool_requires_recorded_trace_and_receipt_is_idempotent(tmp_path: Path) -> None:
store = GovernanceStore(tmp_path / "governance.sqlite3")
store.register_tool(
ToolDescriptor(
"mcp.search", "mcp", TENANT_SCOPE, ("tool.search",),
credential_ref="systemd-credential:search-provider-a",
),
owner(),
)
trace = root_trace()
with pytest.raises(GovernanceError, match="TOOL_MCP_AUTHZ_DENY:trace"):
store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-unrecorded",
)
store.record_trace(trace, actor("tool.search"))
authorized = store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-replay-a",
)
assert authorized["credential_required"] is True
assert "credential_ref" not in authorized
receipt = store.record_tool_receipt(
invocation_key="invoke-replay-a", result_digest="b" * 64,
actor=actor("tool.search"), trace=trace,
)
assert receipt["status"] == "VERIFIED"
replay = store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-replay-a",
)
assert replay["idempotent"] is True
assert replay["receipt_sha256"] == "b" * 64
assert store.verify_audit_chain(
("TRACE_RECORDED", "TOOL_AUTHORIZED", "TOOL_RESULT_VERIFIED")
)
def test_system_and_global_resources_do_not_use_fake_tenants(tmp_path: Path) -> None:
with pytest.raises(GovernanceError, match="GOVERNANCE_NON_TENANT_SCOPE_INVALID"):
GovernanceScope("system", tenant_id="fake-tenant")
store = GovernanceStore(tmp_path / "governance.sqlite3")
descriptor = ToolDescriptor("system.health", "tool", GovernanceScope("global"), ("system.admin",))
registered = store.register_tool(descriptor, owner())
assert registered["descriptor"]["scope_type"] == "global"
assert registered["descriptor"]["tenant_id"] is None
def test_credential_scope_and_secret_exposure_deny(tmp_path: Path) -> None:
store = GovernanceStore(tmp_path / "governance.sqlite3")
grant = CredentialGrant(
"grant-search-a",
"systemd-credential:search-provider-a",
TENANT_SCOPE,
("search.invoke",),
task_id="task-a",
tool_name="mcp.search",
expires_at=(datetime.now(timezone.utc) + timedelta(minutes=5)).isoformat(),
)
stored = store.store_grant(grant, owner())
assert "secret" not in stored["grant"]
trace = root_trace()
store.record_trace(trace, actor("tool.search"))
with pytest.raises(GovernanceError, match="CREDENTIAL_SCOPE_DENY"):
store.authorize_credential(
grant_id=grant.grant_id,
actor=actor("tool.search", tenant_id="tenant-b"),
trace=trace,
operation="search.invoke",
task_id="task-a",
tool_name="mcp.search",
)
with pytest.raises(GovernanceError, match="CREDENTIAL_SECRET_EXPOSURE_DENY"):
CredentialGrant("grant-raw", "Bearer raw-secret", TENANT_SCOPE, ("search.invoke",))
authorized = store.authorize_credential(
grant_id=grant.grant_id,
actor=actor("tool.search"),
trace=trace,
operation="search.invoke",
task_id="task-a",
tool_name="mcp.search",
)
assert authorized["credential_ref"] == "systemd-credential:search-provider-a"
assert "credential_ref" not in authorized["evidence"]["details"]
def test_audit_evidence_completeness_and_tamper_detection(tmp_path: Path) -> None:
path = tmp_path / "governance.sqlite3"
store = GovernanceStore(path)
trace = root_trace()
store.record_trace(trace, actor("tool.search"))
store.register_tool(
ToolDescriptor("mcp.search", "mcp", TENANT_SCOPE, ("tool.search",)), owner()
)
store.authorize_tool(
actor=actor("tool.search"), tool_name="mcp.search", trace=trace,
requested_scope=TENANT_SCOPE, input_digest="a" * 64,
invocation_key="invoke-audit-a",
)
assert store.verify_audit_chain(("TRACE_RECORDED", "TOOL_REGISTERED", "TOOL_AUTHORIZED"))
assert not store.verify_audit_chain(("CREDENTIAL_AUTHORIZED",))
import sqlite3
with sqlite3.connect(path) as connection:
connection.execute(
"UPDATE governance_audit_evidence SET outcome='DENY' WHERE sequence=1"
)
assert not GovernanceStore(path).verify_audit_chain()
def test_observability_record_carries_governed_trace(tmp_path: Path) -> None:
from active_runtime.app.agent_observability_store import AgentObservabilityStore
hooks = AgentObservabilityHooks(AgentObservabilityStore(tmp_path / "observability"))
trace = root_trace()
started = hooks.start(
"user-a", "project-a", "openclaw",
actor=actor("tool.search"), trace=trace,
)
record = hooks.finish(started["execution_id"])["record"]
assert record["trace_id"] == "trace-a"
assert record["tenant_id"] == "tenant-a"
assert record["task_id"] == "task-a"
assert record["message_id"] == message().envelope_id
def test_active_runtime_credential_broker_scope_and_raw_secret_deny() -> None:
class Provider:
def environment(self, lease):
return {"ACCESS_TOKEN": "raw-secret"}
broker = CredentialBroker(Provider())
lease = broker.issue(
task_id="task-a", repository="aios/aios", target_branch="agent/task-a",
generation=1, scopes=("tool.invoke",), scope_type="tenant",
tenant_id="tenant-a", user_id="user-a", project_id="project-a", run_id="run-a",
)
with pytest.raises(RuntimeError, match="CREDENTIAL_SCOPE_DENY"):
broker.authorize(
lease["lease_id"], task_id="task-a", operation="tool.invoke",
scope_type="tenant", tenant_id="tenant-b", user_id="user-a",
project_id="project-a", run_id="run-a",
)
with pytest.raises(RuntimeError, match="CREDENTIAL_SECRET_EXPOSURE_DENY"):
broker.authorize(
lease["lease_id"], task_id="task-a", operation="tool.invoke",
scope_type="tenant", tenant_id="tenant-a", user_id="user-a",
project_id="project-a", run_id="run-a",
)
def test_search_gateway_uses_governed_tool_boundary(tmp_path: Path) -> None:
class Provider:
name = "official_site"
called = False
def search(self, request, queries):
self.called = True
return (
[SearchEvidence("Official", "https://example.test", self.name, "safe")],
SearchProviderAttempt(self.name, "ok", 1),
)
store = GovernanceStore(tmp_path / "governance.sqlite3")
store.register_tool(
ToolDescriptor("search.official_site", "tool", TENANT_SCOPE, ("tool.search",)),
owner(),
)
provider = Provider()
gateway = SearchGateway([provider], governance_store=store)
trace = root_trace()
store.record_trace(trace, actor("tool.search"))
response = gateway.search(
SearchRequest(
query="AIOS", requester="actor-a", correlation_id="trace-a",
authorized_sources=["official_site"],
),
actor=actor("tool.search"),
trace=trace,
)
assert response.status == "found"
assert provider.called is True
assert store.verify_audit_chain(
("TOOL_REGISTERED", "TRACE_RECORDED", "TOOL_AUTHORIZED", "TOOL_RESULT_VERIFIED")
)
with pytest.raises(GovernanceError, match="TOOL_MCP_AUTHZ_DENY"):
gateway.search(
SearchRequest(query="AIOS", requester="forged", correlation_id="trace-a"),
actor=actor("tool.search"),
trace=trace,
)
def test_search_gateway_redacts_provider_exception() -> None:
class Provider:
name = "general_web"
def search(self, request, queries):
raise RuntimeError("Bearer should-not-leak")
response = SearchGateway([Provider()]).search(SearchRequest(query="AIOS", requester="legacy"))
assert response.attempts[0].reason == "PROVIDER_FAILURE"
assert "should-not-leak" not in str(response.to_dict())
def test_search_runtime_default_path_requires_governance(tmp_path: Path) -> None:
orchestrator = SearchGatewayOrchestrator(
governance_store=GovernanceStore(tmp_path / "search-governance.sqlite3")
)
assert orchestrator.status()["governance"] == "required"
with pytest.raises(GovernanceError, match="TOOL_MCP_AUTHZ_DENY"):
orchestrator.execute({"query": "AIOS", "requester": "actor-a"})
def test_governance_newer_schema_fails_closed(tmp_path: Path) -> None:
import sqlite3
path = tmp_path / "newer.sqlite3"
with sqlite3.connect(path) as connection:
connection.execute(
"CREATE TABLE governance_schema_metadata(singleton INTEGER PRIMARY KEY, schema_version INTEGER NOT NULL)"
)
connection.execute(
"INSERT INTO governance_schema_metadata(singleton,schema_version) VALUES(1,999)"
)
with pytest.raises(GovernanceError, match="GOVERNANCE_SCHEMA_VERSION_UNSUPPORTED"):
GovernanceStore(path)
def test_changed_production_files_have_no_embedded_secret_material() -> None:
import re
root = Path(__file__).resolve().parents[1]
paths = (
"active-runtime/app/agent_event_bus.py",
"active-runtime/app/agent_event_observability_bridge.py",
"active-runtime/app/agent_observability.py",
"active-runtime/app/agent_observability_api.py",
"active-runtime/app/agent_observability_hooks.py",
"active-runtime/app/agent_observability_store.py",
"active-runtime/app/aios_credential_broker.py",
"active-runtime/app/message_handoff.py",
"active-runtime/app/search_agent_adapter.py",
"active-runtime/app/search_gateway.py",
"active-runtime/app/search_gateway_api.py",
"active-runtime/app/search_gateway_orchestrator.py",
"active-runtime/app/trace_tool_credential_governance.py",
)
patterns = (
re.compile(r"BEGIN (?:RSA|OPENSSH|EC) PRIVATE KEY"),
re.compile(r"Bearer\s+[A-Za-z0-9._~+/-]{24,}"),
)
hits = [path for path in paths for pattern in patterns if pattern.search((root / path).read_text(encoding="utf-8"))]
assert hits == []
+763
View File
@@ -0,0 +1,763 @@
from __future__ import annotations
from concurrent.futures import ThreadPoolExecutor
from datetime import datetime, timedelta, timezone
import hashlib
from dataclasses import asdict
from pathlib import Path
import sqlite3
import json
from types import SimpleNamespace
import threading
import pytest
from aios_chatgpt_bridge_v2_server import GovernedRuntime
from aios_continuation_executor import ContinuationPermissions, ContinuationRuntimeBinding
from aios_continuation_lease import WriterLeaseRequestV2
from aios_gitops_job_controller import GitOpsJobController, JobError, JobStore
from aios_governed_task_bootstrap import GovernedTaskBootstrap
TASK_ID = "gov-writer-lease-recovery-test"
BRANCH = "agent/writer-lease-recovery-test"
BASE = "a" * 40
JOB_ID_PREFIX = "writer-lease-runtime-lineage"
class LocalAuthority:
def __init__(self, head: str | None = None) -> None:
self.head = head
def read_ref(self, _ref: str) -> str | None:
return self.head
def commit_exists(self, _oid: str) -> bool:
return True
def ancestry_check(self, _older: str, _newer: str) -> bool:
return True
def writer_request(task_id: str = TASK_ID, **overrides: object) -> dict[str, object]:
request: dict[str, object] = {
"schema": WriterLeaseRequestV2.schema,
"task_id": task_id,
"repository": "aios/aios",
"branch_mode": "CREATE_NEW",
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": BRANCH,
"generation": 1,
"lease_seconds": 120,
}
request.update(overrides)
return request
def make_runtime(tmp_path: Path, task_id: str = TASK_ID, *, authority_head: str | None = None) -> GovernedRuntime:
runtime = GovernedRuntime.__new__(GovernedRuntime)
runtime.config = SimpleNamespace(repository="aios/aios", state_root=tmp_path)
runtime.authority = LocalAuthority(authority_head)
runtime.bindings = {
task_id: {
"task_id": task_id,
"repository": "aios/aios",
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": BRANCH,
"branch_mode": "CREATE_NEW",
"generation": 1,
}
}
runtime.runtimes = {}
runtime.controllers = {}
runtime.bootstrap = GovernedTaskBootstrap(
runtime.authority,
tmp_path,
remote_name="test",
token_path=tmp_path / "token",
ssh_key_path=tmp_path / "key",
)
runtime.bindings = {}
runtime.create_task(
{
"task_id": task_id,
"repository": "aios/aios",
"base_oid": BASE,
"expected_branch_oid": BASE,
"target_branch": BRANCH,
"risk": "engineering",
"description": "governed runtime lineage test",
"idempotency_key": JOB_ID_PREFIX + "-" + task_id,
}
)
job_root = runtime._job_root(task_id)
runtime.controllers[task_id] = GitOpsJobController(
JobStore(job_root, payload_root=job_root / "payloads")
)
def build(
lease: WriterLeaseRequestV2,
*,
job_id: str,
lease_not_before: datetime | None = None,
lease_expires_at: datetime | None = None,
) -> tuple[ContinuationRuntimeBinding, GitOpsJobController, object]:
controller = runtime.controllers.get(lease.task_id)
if controller is None:
root = runtime._job_root(lease.task_id)
controller = GitOpsJobController(JobStore(root, payload_root=root / "payloads"))
now = datetime.now(timezone.utc)
return (
ContinuationRuntimeBinding(
request=lease,
job_id=job_id,
workspace_path=tmp_path / "worktrees" / lease.task_id,
lease_not_before=lease_not_before or now - timedelta(seconds=1),
lease_expires_at=lease_expires_at or now + timedelta(seconds=lease.lease_seconds),
original_receipt_valid=True,
original_grant_consumed=True,
permissions=ContinuationPermissions(),
),
controller,
object(),
)
runtime._build_runtime = build
return runtime
def create_durable_lease(
runtime: GovernedRuntime,
*,
expires_at: str = "2020-01-01T00:00:00+00:00",
) -> GitOpsJobController:
root = runtime._job_root(TASK_ID)
controller = GitOpsJobController(JobStore(root, payload_root=root / "payloads"))
receipt = SimpleNamespace(job_id=runtime.bindings[TASK_ID]["job_id"])
controller.lease_job(
receipt.job_id,
lease_id="writer-lease-recovery",
lineage_anchor_oid=BASE,
current_head_oid=BASE,
generation=1,
lease_expires_at=expires_at,
expected_revision=0,
)
runtime.controllers[TASK_ID] = controller
return controller
def durable_row(runtime: GovernedRuntime) -> tuple[str, int]:
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
row = connection.execute(
"SELECT lease_expires_at, revision FROM branch_leases WHERE lease_id=?",
("writer-lease-recovery",),
).fetchone()
assert row is not None
return row
def test_first_bootstrap_refreshes_only_runtime_without_durable_lease(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
result = runtime.bootstrap_writer_lease(writer_request())
assert result["bootstrapped"] is True
assert result["runtime_rehydrated"] is False
assert result["durable_branch_lease_present"] is False
assert result["idempotent"] is False
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
assert connection.execute("SELECT COUNT(*) FROM branch_leases").fetchone()[0] == 0
def test_duplicate_bootstrap_is_idempotent_without_consuming_generation(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
first = runtime.bootstrap_writer_lease(writer_request())
second = runtime.bootstrap_writer_lease(writer_request())
assert first["bootstrapped"] is True
assert first["generation"] == 1
assert second["bootstrapped"] is False
assert second["idempotent"] is True
assert second["generation"] == 1
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
assert connection.execute("SELECT COUNT(*) FROM branch_leases").fetchone()[0] == 0
def test_commit_after_bootstrap_reuses_the_exact_runtime_binding(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
class RecordingWorkspace:
def __init__(self) -> None:
self.files: dict[str, bytes] = {}
def materialize_files(self, files: dict[str, bytes]) -> None:
self.files = dict(files)
class RecordingExecutor:
def __init__(self) -> None:
self.workspace = RecordingWorkspace()
self.binding = None
self.commit = None
def execute(self, binding: object, commit: object) -> dict[str, object]:
self.binding = binding
self.commit = commit
return {'task_id': binding.request.task_id, 'generation': binding.request.generation, 'files': sorted(self.workspace.files)}
executor = RecordingExecutor()
original_build = runtime._build_runtime
def build(lease: WriterLeaseRequestV2, *, job_id: str, lease_not_before: datetime | None=None, lease_expires_at: datetime | None=None) -> tuple[ContinuationRuntimeBinding, GitOpsJobController, object]:
binding, controller, _ = original_build(lease, job_id=job_id, lease_not_before=lease_not_before, lease_expires_at=lease_expires_at)
return (binding, controller, executor)
runtime._build_runtime = build
runtime.bootstrap_writer_lease(writer_request())
lease_response = runtime.acquire_lease(writer_request())
binding, controller, executor = runtime.runtimes[TASK_ID, 1]
assert lease_response['job_id'] == binding.job_id
assert lease_response['durable_branch_lease_present'] is True
_original_execute = executor.execute
def _execute_with_governed_commit_contract(*args, **kwargs):
_before_complete = kwargs.pop('before_complete', None)
_legacy = dict(_original_execute(*args, **kwargs))
_result = {**_legacy, 'job_id': binding.job_id, 'state': 'COMPLETED', 'side_effect_state': 'REMOTE_VERIFIED', 'receipt': {'authority_oid': 'b' * 40, 'git_remote_oid': 'b' * 40, 'api_branch_oid': 'b' * 40, 'commit_visible': True, 'remote_verified': True, 'force_push': False}}
if _before_complete is not None:
_before_complete('b' * 40)
return _result
executor.execute = _execute_with_governed_commit_contract
_bound_job_id = binding.job_id
result = runtime.commit_files({'task_id': TASK_ID, 'repository': 'aios/aios', 'generation': 1, 'target_branch': BRANCH, 'expected_branch_oid': BASE, 'idempotency_key': 'commit-after-bootstrap-v1', 'path': 'docs/recovery.txt', 'content_base64': 'YQ==', 'message': 'test commit after bootstrap'})
assert result['task_id'] == TASK_ID
assert result['generation'] == 1
assert result['files'] == ['docs/recovery.txt']
assert executor.binding.request.task_id == TASK_ID
assert executor.binding.request.generation == 1
database = runtime._job_root(TASK_ID) / 'state.sqlite3'
with sqlite3.connect(f'file:{database}?mode=ro', uri=True) as connection:
assert connection.execute('SELECT COUNT(*) FROM branch_leases').fetchone()[0] == 1
assert connection.execute('PRAGMA foreign_key_check(branch_leases)').fetchall() == []
assert result['commit_oid'] == 'b' * 40
assert result['commit_visible'] is True
assert result['branch_mode'] == 'CONTINUE_EXISTING'
assert result['target_branch'] == BRANCH
assert int(result['generation']) == 1
with controller.store._connect() as connection:
_persisted = connection.execute('SELECT current_head_oid,revision FROM branch_leases WHERE lease_id=?', ('lease-' + str(_bound_job_id),)).fetchone()
assert _persisted is not None
assert _persisted[0] == 'b' * 40
assert int(_persisted[1]) == 1
fresh_runtime = make_runtime(tmp_path, authority_head='b' * 40)
fresh_response = fresh_runtime.bootstrap_writer_lease(writer_request(branch_mode='CONTINUE_EXISTING', expected_branch_oid='b' * 40))
fresh_binding, _, _ = fresh_runtime.runtimes[TASK_ID, 1]
assert fresh_response['job_id'] == str(_bound_job_id)
assert fresh_response['runtime_rehydrated'] is True
assert fresh_binding.job_id == str(_bound_job_id)
assert fresh_binding.request.expected_branch_oid == 'b' * 40
with fresh_runtime.controllers[TASK_ID].store._connect() as connection:
_fresh_lease = connection.execute('SELECT job_id,current_head_oid,revision FROM branch_leases WHERE lease_id=?', ('lease-' + str(_bound_job_id),)).fetchone()
assert tuple(_fresh_lease) == (str(_bound_job_id), 'b' * 40, 1)
@pytest.mark.parametrize(
("field", "value", "error"),
(
("repository", "other/repository", "LEASE_BINDING_CONFLICT"),
("base_oid", "b" * 40, "LEASE_BINDING_CONFLICT"),
("expected_branch_oid", "b" * 40, "LEASE_BINDING_CONFLICT"),
("target_branch", "agent/wrong-target", "LEASE_BINDING_CONFLICT"),
("generation", 2, "GENERATION_BINDING_CONFLICT"),
),
)
def test_bootstrap_rejects_any_nonmatching_binding_field(
tmp_path: Path, field: str, value: object, error: str
) -> None:
runtime = make_runtime(tmp_path)
with pytest.raises(RuntimeError, match=error):
runtime.bootstrap_writer_lease(writer_request(**{field: value}))
def test_bootstrap_rejects_unknown_task_ownership(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
with pytest.raises(RuntimeError, match="TASK_OWNERSHIP_INVALID"):
runtime.bootstrap_writer_lease(writer_request(task_id="unknown-task"))
def test_renew_missing_durable_lease_is_not_bootstrap(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
with pytest.raises(RuntimeError, match="LEASE_NOT_FOUND"):
runtime.renew_writer_lease(writer_request())
def test_renew_is_generation_scoped_before_durable_lookup(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
create_durable_lease(runtime)
with pytest.raises(RuntimeError, match="GENERATION_BINDING_CONFLICT"):
runtime.renew_writer_lease(writer_request(generation=2))
assert durable_row(runtime) == ("2020-01-01T00:00:00+00:00", 0)
def test_restart_rehydrates_only_from_matching_durable_lease(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
create_durable_lease(runtime)
runtime.runtimes.clear()
result = runtime.renew_writer_lease(writer_request())
expires_at, revision = durable_row(runtime)
assert result["recovered"] is True
assert result["runtime_rehydrated"] is True
assert result["durable_branch_lease_present"] is True
assert revision == 1
assert datetime.fromisoformat(expires_at) > datetime.now(timezone.utc)
def test_duplicate_renewal_is_idempotent_after_first_durable_recovery(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
create_durable_lease(runtime)
first = runtime.renew_writer_lease(writer_request())
second = runtime.renew_writer_lease(writer_request())
assert first["recovered"] is True
assert first["idempotent"] is False
assert second["recovered"] is False
assert second["idempotent"] is True
assert durable_row(runtime)[1] == 1
def test_update_lease_keeps_expiry_without_optional_argument_and_keeps_cas(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
controller = create_durable_lease(runtime)
controller.update_lease(
"writer-lease-recovery",
expected_revision=0,
current_head_oid=BASE,
generation=1,
)
assert durable_row(runtime) == ("2020-01-01T00:00:00+00:00", 1)
with pytest.raises(JobError, match="LEASE_REVISION_CAS_CONFLICT"):
controller.update_lease(
"writer-lease-recovery",
expected_revision=0,
current_head_oid=BASE,
generation=1,
)
def test_two_runtime_connections_resolve_renewal_cas_race_idempotently(tmp_path: Path) -> None:
first = make_runtime(tmp_path)
first_controller = create_durable_lease(first)
second = make_runtime(tmp_path)
second_controller = GitOpsJobController(
JobStore(second._job_root(TASK_ID), payload_root=second._job_root(TASK_ID) / "payloads")
)
second.controllers[TASK_ID] = second_controller
gate = threading.Barrier(2)
def gate_update(controller: GitOpsJobController) -> None:
original = controller.update_lease
def update(*args: object, **kwargs: object) -> None:
gate.wait(timeout=5)
original(*args, **kwargs)
controller.update_lease = update
gate_update(first_controller)
gate_update(second_controller)
with ThreadPoolExecutor(max_workers=2) as pool:
results = list(pool.map(lambda runtime: runtime.renew_writer_lease(writer_request()), (first, second)))
assert sorted((item["recovered"], item["idempotent"]) for item in results) == [
(False, True),
(True, False),
]
assert durable_row(first)[1] == 1
def test_bootstrap_preserves_exact_governed_job_lineage(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
response = runtime.bootstrap_writer_lease(writer_request())
binding, _, _ = runtime.runtimes[(TASK_ID, 1)]
assert response["job_id"] == expected_job_id
assert binding.job_id == expected_job_id
assert binding.request.job_id == expected_job_id
def test_restart_rehydrate_preserves_exact_governed_job_lineage(tmp_path: Path) -> None:
first = make_runtime(tmp_path)
expected_job_id = first.bindings[TASK_ID]["job_id"]
first.acquire_lease(writer_request())
runtime = make_runtime(tmp_path)
assert runtime is not first
assert runtime.runtimes == {}
response = runtime.bootstrap_writer_lease(writer_request())
binding, _, _ = runtime.runtimes[(TASK_ID, 1)]
assert response["job_id"] == expected_job_id
assert binding.job_id == expected_job_id
assert binding.request.job_id == expected_job_id
def test_wrong_governed_job_id_is_denied_before_runtime_or_lease_side_effect(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
with pytest.raises(RuntimeError, match="LEASE_BINDING_CONFLICT"):
runtime.bootstrap_writer_lease(writer_request(job_id="job-wrong-lineage"))
assert runtime.runtimes == {}
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
assert connection.execute("SELECT COUNT(*) FROM branch_leases").fetchone()[0] == 0
assert connection.execute("PRAGMA foreign_key_check(branch_leases)").fetchall() == []
def test_acquire_creates_exact_governed_writer_lease_with_fk_and_cas(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
response = runtime.acquire_lease(writer_request())
assert response["job_id"] == expected_job_id
assert response["durable_branch_lease_present"] is True
assert response["idempotent"] is False
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
foreign_keys = connection.execute(
"PRAGMA foreign_key_list(branch_leases)"
).fetchall()
row = connection.execute(
"SELECT job_id,branch,lineage_anchor_oid,current_head_oid,generation,state,revision "
"FROM branch_leases"
).fetchone()
job = connection.execute(
"SELECT state,side_effect_state,revision FROM jobs WHERE job_id=?",
(expected_job_id,),
).fetchone()
assert connection.execute("PRAGMA foreign_key_check(branch_leases)").fetchall() == []
assert any(
fk[2] == "jobs" and fk[3] == "job_id" and fk[4] == "job_id"
for fk in foreign_keys
)
assert row == (expected_job_id, BRANCH, BASE, BASE, 1, "ACTIVE", 0)
assert job == ("LEASED", "LEASED", 2)
def test_duplicate_acquire_observes_same_durable_writer_lease(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
first = runtime.acquire_lease(writer_request())
second = runtime.acquire_lease(writer_request())
assert first["job_id"] == expected_job_id
assert second["job_id"] == expected_job_id
assert second["idempotent"] is True
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
leases = connection.execute(
"SELECT lease_id,job_id,revision FROM branch_leases"
).fetchall()
job = connection.execute(
"SELECT state,revision FROM jobs WHERE job_id=?",
(expected_job_id,),
).fetchone()
assert leases == [("lease-" + expected_job_id, expected_job_id, 0)]
assert job == ("LEASED", 2)
def test_wrong_job_acquire_is_denied_before_authorize_or_lease(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
with pytest.raises(RuntimeError, match="LEASE_BINDING_CONFLICT"):
runtime.acquire_lease(writer_request(job_id="job-wrong-lineage"))
database = runtime._job_root(TASK_ID) / "state.sqlite3"
with sqlite3.connect(f"file:{database}?mode=ro", uri=True) as connection:
job = connection.execute(
"SELECT state,side_effect_state,revision FROM jobs WHERE job_id=?",
(expected_job_id,),
).fetchone()
lease_count = connection.execute("SELECT COUNT(*) FROM branch_leases").fetchone()[0]
assert job == ("REQUESTED", "NONE", 0)
assert lease_count == 0
def test_omitted_request_job_id_resolves_the_exact_durable_parent(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
raw = dict(writer_request())
response = runtime.acquire_lease(raw)
binding, _, _ = runtime.runtimes[(TASK_ID, 1)]
assert response["job_id"] == expected_job_id
assert binding.job_id == expected_job_id
assert binding.request.job_id == expected_job_id
def test_durable_job_expected_head_mismatch_is_denied(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
expected_job_id = runtime.bindings[TASK_ID]["job_id"]
controller = runtime.controllers[TASK_ID]
with controller.store._connect() as connection:
row = connection.execute(
"SELECT request_json FROM jobs WHERE job_id=?", (expected_job_id,)
).fetchone()
request = json.loads(row[0])
request["expected_branch_oid"] = "c" * 40
request["binding"]["expected_branch_oid"] = "c" * 40
connection.execute(
"UPDATE jobs SET request_json=? WHERE job_id=?",
(json.dumps(request, sort_keys=True, separators=(",", ":")), expected_job_id),
)
connection.commit()
with pytest.raises(RuntimeError, match="RUNTIME_GOVERNED_JOB_UNRESOLVED"):
runtime.bootstrap_writer_lease(writer_request())
assert runtime.runtimes == {}
def _commit_ready_runtime(tmp_path: Path):
runtime = make_runtime(tmp_path)
runtime.bootstrap_writer_lease(writer_request())
binding, controller, _ = runtime.runtimes[(TASK_ID, 1)]
class Workspace:
def materialize_files(self, _files):
return None
class Executor:
def __init__(self):
self.workspace = Workspace()
self.calls = 0
def execute(self, _binding, _commit, *, before_complete=None):
self.calls += 1
result = {
"job_id": binding.job_id,
"state": "COMPLETED",
"side_effect_state": "REMOTE_VERIFIED",
"receipt": {
"authority_oid": "b" * 40,
"git_remote_oid": "b" * 40,
"api_branch_oid": "b" * 40,
"commit_visible": True,
"remote_verified": True,
"force_push": False,
},
}
if before_complete is not None:
before_complete("b" * 40)
return result
executor = Executor()
runtime.runtimes[(TASK_ID, 1)] = (binding, controller, executor)
runtime.acquire_lease(writer_request())
return runtime, binding, controller, executor
def _commit_request():
return {
"task_id": TASK_ID,
"repository": "aios/aios",
"generation": 1,
"target_branch": BRANCH,
"expected_branch_oid": BASE,
"idempotency_key": "commit-cas-test-v1",
"path": "docs/cas.txt",
"content_base64": "YQ==",
"message": "test commit cas",
}
def test_commit_lease_revision_cas_conflict_is_preserved(tmp_path: Path) -> None:
runtime, _binding, controller, _executor = _commit_ready_runtime(tmp_path)
def conflict(*_args, **_kwargs):
raise JobError("LEASE_REVISION_CAS_CONFLICT")
controller.update_lease = conflict
with pytest.raises(RuntimeError, match="LEASE_CAS_CONFLICT"):
runtime.commit_files(_commit_request())
def test_commit_divergent_durable_head_fails_before_executor(tmp_path: Path) -> None:
runtime, binding, controller, executor = _commit_ready_runtime(tmp_path)
controller.update_lease(
"lease-" + binding.job_id,
expected_revision=0,
current_head_oid="c" * 40,
generation=1,
)
with pytest.raises(RuntimeError, match="LEASE_HEAD_RECONCILIATION_REQUIRED"):
runtime.commit_files(_commit_request())
assert executor.calls == 0
def test_remote_pending_never_advances_durable_head(tmp_path: Path) -> None:
runtime, binding, controller, executor = _commit_ready_runtime(tmp_path)
def pending(_binding, _commit, **_kwargs):
executor.calls += 1
return {
"job_id": binding.job_id,
"state": "RECONCILIATION_REQUIRED",
"side_effect_state": "REMOTE_PUSH_PENDING",
"receipt": {
"authority_oid": "b" * 40,
"desired_remote_oid": "b" * 40,
"remote_verified": False,
},
}
executor.execute = pending
with pytest.raises(RuntimeError, match="RECONCILIATION_REQUIRED"):
runtime.commit_files(_commit_request())
with controller.store._connect() as connection:
row = connection.execute(
"SELECT current_head_oid,revision FROM branch_leases WHERE lease_id=?",
("lease-" + binding.job_id,),
).fetchone()
assert tuple(row) == (BASE, 0)
def test_retry_accepts_exact_head_already_advanced_at_remote_verified_boundary(tmp_path: Path) -> None:
runtime, binding, controller, executor = _commit_ready_runtime(tmp_path)
commit_oid = "b" * 40
controller.update_lease(
"lease-" + binding.job_id,
expected_revision=0,
current_head_oid=commit_oid,
generation=1,
)
receipt = {
"authority_oid": commit_oid,
"git_remote_oid": commit_oid,
"api_branch_oid": commit_oid,
"commit_visible": True,
"remote_verified": True,
"force_push": False,
}
with controller.store._connect() as connection:
connection.execute(
"UPDATE jobs SET state='REMOTE_VERIFIED',side_effect_state='REMOTE_VERIFIED',"
"receipt_json=? WHERE job_id=?",
(json.dumps(receipt, sort_keys=True, separators=(",", ":")), binding.job_id),
)
connection.commit()
result = runtime.commit_files(_commit_request())
assert result["commit_oid"] == commit_oid
assert executor.calls == 1
with controller.store._connect() as connection:
row = connection.execute(
"SELECT current_head_oid,revision FROM branch_leases WHERE lease_id=?",
("lease-" + binding.job_id,),
).fetchone()
assert tuple(row) == (commit_oid, 1)
def test_completed_response_with_invalid_oid_uses_canonical_oid_error(tmp_path: Path) -> None:
runtime, binding, controller, executor = _commit_ready_runtime(tmp_path)
def invalid_oid(_binding, _commit, **_kwargs):
executor.calls += 1
return {
"job_id": binding.job_id,
"state": "COMPLETED",
"side_effect_state": "REMOTE_VERIFIED",
"receipt": {
"authority_oid": "not-an-oid",
"commit_visible": True,
"remote_verified": True,
},
}
executor.execute = invalid_oid
with pytest.raises(RuntimeError, match="GOVERNED_COMMIT_OID_INVALID"):
runtime.commit_files(_commit_request())
with controller.store._connect() as connection:
row = connection.execute(
"SELECT current_head_oid,revision FROM branch_leases WHERE lease_id=?",
("lease-" + binding.job_id,),
).fetchone()
assert tuple(row) == (BASE, 0)
def test_acquire_renews_an_expired_matching_durable_lease_with_revision_cas(tmp_path: Path) -> None:
runtime = make_runtime(tmp_path)
create_durable_lease(runtime)
runtime.runtimes.clear()
result = runtime.acquire_lease(writer_request())
expires_at, revision = durable_row(runtime)
assert result["recovered"] is True
assert result["runtime_rehydrated"] is False
assert result["durable_branch_lease_present"] is True
assert revision == 1
assert datetime.fromisoformat(expires_at) > datetime.now(timezone.utc)
def test_authority_recovers_only_clean_detached_single_attempt_worktree(tmp_path: Path) -> None:
import subprocess
from aios_authority_git_executor import AuthorityGitExecutor
bare = tmp_path / "authority.git"
seed = tmp_path / "seed"
subprocess.run(["git", "init", "--bare", str(bare)], check=True, capture_output=True)
subprocess.run(["git", "init", str(seed)], check=True, capture_output=True)
(seed / "base.txt").write_text("base\n", encoding="utf-8")
subprocess.run(["git", "-C", str(seed), "add", "base.txt"], check=True)
subprocess.run(
["git", "-C", str(seed), "-c", "user.name=test", "-c", "user.email=test@example.invalid",
"commit", "-m", "base"], check=True, capture_output=True,
)
base = subprocess.check_output(["git", "-C", str(seed), "rev-parse", "HEAD"], text=True).strip()
subprocess.run(["git", "-C", str(seed), "push", str(bare), "HEAD:refs/heads/main"], check=True, capture_output=True)
root = tmp_path / "worktrees"
authority = AuthorityGitExecutor(bare, root)
worktree = authority.create_detached_worktree(base, "task")
(worktree / "attempt.txt").write_text("attempt\n", encoding="utf-8")
subprocess.run(["git", "-C", str(worktree), "add", "attempt.txt"], check=True)
subprocess.run(
["git", "-C", str(worktree), "-c", "user.name=test", "-c", "user.email=test@example.invalid",
"commit", "-m", "failed attempt"], check=True, capture_output=True,
)
stale = subprocess.check_output(["git", "-C", str(worktree), "rev-parse", "HEAD"], text=True).strip()
recovered = authority.recover_failed_detached_worktree_exact(
path=worktree,
expected_oid=base,
stale_oid=stale,
target_ref="refs/heads/agent/recovery-test",
)
assert recovered == stale
assert subprocess.check_output(["git", "-C", str(worktree), "rev-parse", "HEAD"], text=True).strip() == base
assert subprocess.run(["git", "-C", str(worktree), "symbolic-ref", "-q", "HEAD"]).returncode == 1
assert subprocess.check_output(["git", "-C", str(worktree), "status", "--porcelain"], text=True) == ""