Files
aios/services/aios_orchestrator_gateway/service.py
T

643 lines
25 KiB
Python

from __future__ import annotations
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import logging
import os
from pathlib import Path
import socket
import subprocess
import threading
import time
from typing import Any
from urllib.parse import urlparse
from .clients import ResponsesClient, WorkspaceAgentClient
from .config import Config
from .dispatch import DispatchSink
from .errors import (
AuthenticationError,
ConflictError,
DispatchError,
OrchestratorError,
TriggerError,
ValidationError,
)
from .models import Decision, Event
from .securefs import ensure_secure_directory, ensure_shared_directory, read_secure_json
from .store import Store
from .sync import OpenClawSynchronizer, lifecycle_record
LOG = logging.getLogger("aios-orchestrator-gateway")
class Runtime:
def __init__(self, config: Config):
self.config = config
self.store = Store(config.database_path)
self.dispatch = DispatchSink(
config.dispatch_outbox_dir,
config.command_queue_dir,
config.contract_commit,
)
self.workspace = None
workspace_token = config.workspace_token()
if config.workspace_trigger_id and workspace_token:
self.workspace = WorkspaceAgentClient(
config.workspace_trigger_id,
workspace_token,
)
self.responses = None
responses_key = config.responses_api_key()
if responses_key and config.responses_model:
self.responses = ResponsesClient(
responses_key,
config.responses_model,
)
self.synchronizer = OpenClawSynchronizer(
config.openclaw_sync_dir,
endpoint=config.openclaw_sync_endpoint,
bearer_token=config.openclaw_sync_token(),
)
self.worker_id = f"{socket.gethostname()}-{os.getpid()}-{threading.get_native_id()}"
self.stop_event = threading.Event()
self.worker = threading.Thread(target=self._loop, daemon=True)
self._next_git_poll = 0.0
for directory in (
config.event_inbox_dir,
config.decision_inbox_dir,
config.dispatch_outbox_dir,
config.openclaw_sync_dir,
):
ensure_secure_directory(directory)
ensure_shared_directory(config.command_queue_dir)
def start(self) -> None:
self.worker.start()
def stop(self) -> None:
self.stop_event.set()
if self.worker.is_alive():
self.worker.join(timeout=15)
self.store.close()
def submit_event(self, payload: dict[str, Any]) -> tuple[bool, dict[str, Any]]:
event = Event.from_dict(payload)
if event.contract_commit != self.config.contract_commit:
raise ConflictError("contract_version_mismatch")
created, stored = self.store.register_event(event)
if created:
self._enqueue_event_lifecycle(event)
return created, stored
def submit_decision(self, payload: dict[str, Any]) -> int:
decision = Decision.from_dict(payload)
if decision.contract_commit != self.config.contract_commit:
raise ConflictError("contract_version_mismatch")
version = self.store.apply_decision(
decision,
max_hops_per_gate=self.config.max_hops_per_gate,
max_same_blocker_retries=self.config.max_same_blocker_retries,
)
self._enqueue_decision_lifecycle(decision, version)
return version
def _loop(self) -> None:
next_summary = 0.0
while not self.stop_event.wait(self.config.poll_interval_seconds):
try:
self.poll_once()
if time.monotonic() >= next_summary:
self.enqueue_periodic_summaries()
next_summary = time.monotonic() + self.config.summary_interval_seconds
except Exception:
LOG.exception("poll_cycle_failed")
def poll_once(self) -> None:
"""One deterministic reliability cycle.
This is deliberately callable from a systemd timer or health supervisor
in addition to the internal loop.
"""
self.ingest_file_inboxes()
self.poll_git_refs()
self.process_new_events()
self.process_workspace_timeouts()
self.poll_background_responses()
self.dispatch_work_units()
self.synchronize_openclaw()
def ingest_file_inboxes(self) -> None:
self._ingest_directory(self.config.event_inbox_dir, kind="event")
self._ingest_directory(self.config.decision_inbox_dir, kind="decision")
def _ingest_directory(self, directory: Path, *, kind: str) -> None:
pending = directory / "pending"
processed = directory / "processed"
rejected = directory / "rejected"
ensure_shared_directory(pending, group_writable=True)
ensure_secure_directory(processed)
ensure_secure_directory(rejected)
for path in sorted(pending.glob("*.json"))[:128]:
try:
payload = read_secure_json(path, expected_uid=None)
if kind == "event":
self.submit_event(payload)
else:
self.submit_decision(payload)
target = processed / path.name
except Exception as exc:
LOG.warning("file_inbox_rejected path=%s error=%s", path, type(exc).__name__)
target = rejected / path.name
if target.exists():
# Same file name is an idempotency replay. Keep original audit copy.
path.unlink()
else:
path.replace(target)
def poll_git_refs(self) -> None:
"""Poll authoritative local bare refs so missed webhooks cannot stall the loop."""
if not self.config.git_poll_enabled or self.config.git_poll_bare_repo is None:
return
now = time.monotonic()
if now < self._next_git_poll:
return
self._next_git_poll = now + self.config.git_poll_interval_seconds
command = [
"git",
f"--git-dir={self.config.git_poll_bare_repo}",
"for-each-ref",
"--format=%(refname) %(objectname)",
*self.config.git_poll_ref_prefixes,
]
try:
result = subprocess.run(
command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
check=False,
timeout=30,
env={"PATH": "/usr/bin:/bin", "LANG": "C", "LC_ALL": "C"},
)
except (OSError, subprocess.SubprocessError):
LOG.exception("git_ref_poll_failed")
return
if result.returncode != 0:
LOG.warning("git_ref_poll_rc=%s", result.returncode)
return
refs: dict[str, str] = {}
for line in result.stdout.splitlines():
refname, sep, oid = line.partition(" ")
if not sep or not refname.startswith("refs/") or len(oid) != 40:
continue
if any(ch not in "0123456789abcdef" for ch in oid):
continue
refs[refname] = oid
initialized, changes = self.store.observe_refs(refs)
if not initialized or not changes:
return
payload_changes = [
{"ref": refname, "old_oid": old_oid, "new_oid": new_oid}
for refname, old_oid, new_oid in sorted(changes)
]
canonical = json.dumps(payload_changes, separators=(",", ":"), sort_keys=True)
event_id = "gitpoll-" + hashlib.sha256(canonical.encode()).hexdigest()[:40]
state = self.store.project_state(self.config.project_key)
state_version = 0 if state is None else int(state["state_version"])
event = Event.from_dict(
{
"schema_version": 1,
"project_key": self.config.project_key,
"contract_commit": self.config.contract_commit,
"event_id": event_id,
"source_agent": "gitea",
"event_type": "git_refs_changed",
"work_unit_id": "GIT-REF-POLL",
"status": "READY",
"state_version": state_version,
"implementation_commit": None,
"result_commit": None,
"blocker": None,
"evidence_refs": [],
"payload": {"changes": payload_changes},
}
)
try:
self.submit_event(event.to_dict())
except ConflictError:
LOG.info("git_ref_event_already_registered event_id=%s", event_id)
def process_new_events(self) -> None:
rows = self.store.claim_events(
owner=self.worker_id,
statuses=("RECEIVED", "TRIGGER_FAILED"),
limit=32,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
event = Event.from_dict(json.loads(row["event_json"]))
attempts = int(row["attempts"])
try:
if self.workspace is not None:
self.workspace.trigger(event)
self.store.update_event_trigger(
event.event_id,
status="AWAITING_DECISION",
channel="workspace_agent",
remote_id=None,
)
elif self.responses is not None:
response_id = self.responses.start(event)
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
)
else:
raise TriggerError("no_model_channel")
except TriggerError as exc:
self._retry_or_dead_letter(event, attempts, str(exc))
def process_workspace_timeouts(self) -> None:
cutoff = int(time.time()) - self.config.callback_timeout_seconds
for row in self.store.claim_workspace_timeouts(
owner=self.worker_id,
older_than=cutoff,
limit=32,
lease_seconds=self.config.lease_seconds,
):
event = Event.from_dict(json.loads(row["event_json"]))
if self.responses is None:
self._retry_or_dead_letter(
event,
int(row["attempts"]),
"workspace_callback_timeout",
)
continue
try:
response_id = self.responses.start(event)
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
increment_attempt=True,
)
except TriggerError as exc:
self._retry_or_dead_letter(event, int(row["attempts"]), str(exc))
def poll_background_responses(self) -> None:
if self.responses is None:
return
for row in self.store.claim_response_polls(
owner=self.worker_id,
limit=32,
lease_seconds=self.config.lease_seconds,
):
event = Event.from_dict(json.loads(row["event_json"]))
response_id = row.get("remote_id")
if not isinstance(response_id, str):
self._retry_or_dead_letter(event, int(row["attempts"]), "missing_response_id")
continue
try:
status, decision = self.responses.poll(response_id)
if status in {"queued", "in_progress"}:
attempts = int(row["attempts"])
if attempts + 1 > self.config.max_retries:
self._retry_or_dead_letter(
event, attempts, f"response_{status}_retry_limit"
)
continue
self.store.update_event_trigger(
event.event_id,
status="POLLING_RESPONSE",
channel="responses_api",
remote_id=response_id,
retry_after=self.config.poll_interval_seconds,
increment_attempt=True,
)
continue
if decision is None:
raise TriggerError("completed_without_decision")
self.submit_decision(decision.to_dict())
except OrchestratorError as exc:
self._retry_or_dead_letter(event, int(row["attempts"]), str(exc))
def dispatch_work_units(self) -> None:
rows = self.store.claim_outbox(
owner=self.worker_id,
limit=64,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
try:
outbox_path, queue_path = self.dispatch.dispatch(row)
self.store.mark_outbox(row["work_unit_id"], status="DISPATCHED")
payload = {
"assigned_agent": row["assigned_agent"],
"event_id": row["event_id"],
"dispatch_outbox": str(outbox_path),
"command_queue": str(queue_path),
}
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=self._project_for_event(row["event_id"]),
kind="TASK_DISPATCHED",
work_unit_id=row["work_unit_id"],
payload=payload,
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=record["project_key"],
work_unit_id=row["work_unit_id"],
kind=record["kind"],
payload=record,
)
except Exception:
attempts = int(row["attempts"])
status = "DEAD_LETTER" if attempts >= self.config.max_retries else "RETRY"
self.store.mark_outbox(
row["work_unit_id"],
status=status,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
LOG.exception("dispatch_failed work_unit=%s", row["work_unit_id"])
def synchronize_openclaw(self) -> None:
rows = self.store.claim_lifecycle(
owner=self.worker_id,
limit=64,
lease_seconds=self.config.lease_seconds,
)
for row in rows:
try:
payload = json.loads(row["payload_json"])
self.synchronizer.emit(payload)
self.store.mark_lifecycle(row["sync_id"], status="SENT")
except Exception:
attempts = int(row["attempts"])
status = "DEAD_LETTER" if attempts >= self.config.max_retries else "RETRY"
self.store.mark_lifecycle(
row["sync_id"],
status=status,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
LOG.exception("openclaw_sync_failed sync_id=%s", row["sync_id"])
def enqueue_periodic_summaries(self) -> None:
for state in self.store.all_project_states():
project_key = state["project_key"]
if not self.store.summary_due(project_key, self.config.summary_interval_seconds):
continue
summary = self.store.project_summary(project_key)
if summary is None:
continue
digest = hashlib.sha256(
json.dumps(summary, separators=(",", ":"), sort_keys=True).encode()
).hexdigest()
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=project_key,
kind="PROJECT_SUMMARY",
work_unit_id=None,
payload=summary,
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=project_key,
work_unit_id=None,
kind=record["kind"],
payload=record,
)
self.store.mark_summary(project_key, digest)
def _enqueue_event_lifecycle(self, event: Event) -> None:
if event.event_type == "work_unit_started":
kind = "TASK_STARTED"
elif event.event_type in {"work_unit_completed", "work_unit_failed", "work_unit_blocked"}:
kind = "TASK_ENDED"
else:
kind = "EVENT_RECEIVED"
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=event.project_key,
kind=kind,
work_unit_id=event.work_unit_id,
payload=event.to_dict(),
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=event.project_key,
work_unit_id=event.work_unit_id,
kind=kind,
payload=record,
)
def _enqueue_decision_lifecycle(self, decision: Decision, version: int) -> None:
kind = "PROJECT_COMPLETED" if decision.verdict == "COMPLETE" else "DECISION_APPLIED"
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=decision.project_key,
kind=kind,
work_unit_id=None,
payload={"decision": decision.to_dict(), "state_version": version},
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=decision.project_key,
work_unit_id=None,
kind=kind,
payload=record,
)
summary = self.store.project_summary(decision.project_key)
if summary:
summary_record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=decision.project_key,
kind="PROJECT_SUMMARY",
work_unit_id=None,
payload=summary,
)
self.store.enqueue_lifecycle(
sync_id=summary_record["sync_id"],
project_key=decision.project_key,
work_unit_id=None,
kind=summary_record["kind"],
payload=summary_record,
)
def _project_for_event(self, event_id: str) -> str:
rows = self.store._conn().execute(
"SELECT project_key FROM events WHERE event_id=?",
(event_id,),
).fetchone()
if rows is None:
raise ConflictError("event_not_found")
return str(rows["project_key"])
def _retry_or_dead_letter(self, event: Event, attempts: int, reason: str) -> None:
next_attempt = attempts + 1
if next_attempt > self.config.max_retries:
self.store.update_event_trigger(
event.event_id,
status="DEAD_LETTER",
channel=None,
remote_id=None,
increment_attempt=True,
)
record = lifecycle_record(
contract_commit=self.config.contract_commit,
project_key=event.project_key,
kind="TASK_ENDED",
work_unit_id=event.work_unit_id,
payload={
"status": "FAIL",
"reason": reason,
"event_id": event.event_id,
"attempts": next_attempt,
},
)
self.store.enqueue_lifecycle(
sync_id=record["sync_id"],
project_key=event.project_key,
work_unit_id=event.work_unit_id,
kind=record["kind"],
payload=record,
)
return
self.store.update_event_trigger(
event.event_id,
status="TRIGGER_FAILED",
channel=None,
remote_id=None,
retry_after=self._backoff(attempts),
increment_attempt=True,
)
def _backoff(self, attempts: int) -> int:
return min(3600, self.config.retry_base_seconds * (2 ** min(attempts, 10)))
class Handler(BaseHTTPRequestHandler):
runtime: Runtime
def log_message(self, fmt: str, *args: object) -> None:
LOG.info("%s %s", self.client_address[0], fmt % args)
def _reply(self, status: int, payload: dict[str, Any]) -> None:
body = json.dumps(payload, separators=(",", ":"), sort_keys=True).encode()
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.send_header("Cache-Control", "no-store")
self.end_headers()
self.wfile.write(body)
def _body(self) -> dict[str, Any]:
try:
length = int(self.headers.get("Content-Length", "0"))
except ValueError as exc:
raise ValidationError("invalid_content_length") from exc
if length <= 0 or length > 1_048_576:
raise ValidationError("invalid_body_size")
try:
value = json.loads(self.rfile.read(length))
except json.JSONDecodeError as exc:
raise ValidationError("invalid_json") from exc
if not isinstance(value, dict):
raise ValidationError("json_root_not_object")
return value
def _authenticate(self, expected: str) -> None:
header = self.headers.get("Authorization", "")
if not header.startswith("Bearer "):
raise AuthenticationError("missing_bearer")
if not hmac.compare_digest(header[7:], expected):
raise AuthenticationError("invalid_bearer")
def do_GET(self) -> None:
path = urlparse(self.path).path.rstrip("/") or "/"
try:
if path == "/healthz":
self._reply(
200,
{
"service": "aios-orchestrator-gateway",
"status": "active",
"contract_commit": self.runtime.config.contract_commit,
"polling": True,
},
)
return
if path.startswith("/v1/orchestrator/state/"):
self._authenticate(self.runtime.config.inbound_token())
key = path.rsplit("/", 1)[-1]
state = self.runtime.store.project_summary(key)
self._reply(200 if state else 404, state or {"error": "project_not_found"})
return
self._reply(404, {"error": "not_found"})
except AuthenticationError as exc:
self._reply(401, {"error": str(exc)})
except OrchestratorError as exc:
self._reply(400, {"error": str(exc)})
def do_POST(self) -> None:
path = urlparse(self.path).path.rstrip("/")
try:
if path == "/v1/orchestrator/events":
self._authenticate(self.runtime.config.inbound_token())
created, event = self.runtime.submit_event(self._body())
self._reply(202 if created else 200, {"created": created, "event": event})
return
if path == "/v1/orchestrator/decisions":
self._authenticate(self.runtime.config.callback_token())
version = self.runtime.submit_decision(self._body())
self._reply(202, {"accepted": True, "state_version": version})
return
if path == "/v1/orchestrator/poll":
self._authenticate(self.runtime.config.inbound_token())
self.runtime.poll_once()
self._reply(200, {"polled": True})
return
self._reply(404, {"error": "not_found"})
except AuthenticationError as exc:
self._reply(401, {"error": str(exc)})
except ConflictError as exc:
self._reply(409, {"error": str(exc)})
except ValidationError as exc:
self._reply(422, {"error": str(exc)})
except OrchestratorError as exc:
self._reply(400, {"error": str(exc)})
except Exception:
LOG.exception("request_failed path=%s", path)
self._reply(500, {"error": "internal_error"})
def serve(config_path: Path) -> None:
config = Config.from_file(config_path)
runtime = Runtime(config)
Handler.runtime = runtime
server = ThreadingHTTPServer((config.host, config.port), Handler)
runtime.start()
LOG.info(
"gateway_started host=%s port=%s contract=%s polling=%ss",
config.host,
config.port,
config.contract_commit,
config.poll_interval_seconds,
)
try:
server.serve_forever(poll_interval=0.5)
finally:
server.server_close()
runtime.stop()