Files
aios/services/aios_orchestrator_gateway/store.py
T

879 lines
30 KiB
Python

from __future__ import annotations
import json
from pathlib import Path
import sqlite3
import threading
import time
from typing import Any
from .errors import ConflictError
from .models import Decision, Event
from .securefs import ensure_secure_directory
class Store:
"""Durable state machine with idempotency, optimistic versioning, and leases."""
def __init__(self, path: Path):
self.path = Path(path)
ensure_secure_directory(self.path.parent)
self._local = threading.local()
self._initialize()
def _connect(self) -> sqlite3.Connection:
conn = sqlite3.connect(self.path, timeout=30, isolation_level=None)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA synchronous=FULL")
conn.execute("PRAGMA foreign_keys=ON")
conn.execute("PRAGMA busy_timeout=30000")
return conn
def _conn(self) -> sqlite3.Connection:
conn = getattr(self._local, "conn", None)
if conn is None:
conn = self._connect()
self._local.conn = conn
return conn
def _initialize(self) -> None:
conn = self._connect()
try:
conn.executescript(
"""
CREATE TABLE IF NOT EXISTS project_state (
project_key TEXT PRIMARY KEY,
contract_commit TEXT NOT NULL,
state_version INTEGER NOT NULL,
state_json TEXT NOT NULL,
hops INTEGER NOT NULL DEFAULT 0,
updated_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS gate_hops (
project_key TEXT NOT NULL,
gate_id TEXT NOT NULL,
hops INTEGER NOT NULL DEFAULT 0,
updated_at INTEGER NOT NULL,
PRIMARY KEY(project_key, gate_id)
);
CREATE TABLE IF NOT EXISTS events (
event_id TEXT PRIMARY KEY,
project_key TEXT NOT NULL,
digest TEXT NOT NULL,
event_json TEXT NOT NULL,
status TEXT NOT NULL,
channel TEXT,
remote_id TEXT,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_events_poll
ON events(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS decisions (
event_id TEXT PRIMARY KEY REFERENCES events(event_id),
project_key TEXT NOT NULL,
decision_json TEXT NOT NULL,
state_version_after INTEGER NOT NULL,
created_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS outbox (
work_unit_id TEXT PRIMARY KEY,
event_id TEXT NOT NULL REFERENCES events(event_id),
assigned_agent TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_outbox_poll
ON outbox(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS lifecycle (
sync_id TEXT PRIMARY KEY,
project_key TEXT NOT NULL,
work_unit_id TEXT,
kind TEXT NOT NULL,
payload_json TEXT NOT NULL,
status TEXT NOT NULL,
attempts INTEGER NOT NULL DEFAULT 0,
next_attempt_at INTEGER NOT NULL DEFAULT 0,
lease_owner TEXT,
lease_until INTEGER,
created_at INTEGER NOT NULL,
updated_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_lifecycle_poll
ON lifecycle(status, next_attempt_at, lease_until, created_at);
CREATE TABLE IF NOT EXISTS blocker_history (
project_key TEXT NOT NULL,
gate_id TEXT NOT NULL,
blocker TEXT NOT NULL,
repetitions INTEGER NOT NULL,
updated_at INTEGER NOT NULL,
PRIMARY KEY(project_key, gate_id, blocker)
);
CREATE TABLE IF NOT EXISTS summaries (
project_key TEXT PRIMARY KEY,
last_emitted_at INTEGER NOT NULL DEFAULT 0,
last_digest TEXT
);
CREATE TABLE IF NOT EXISTS observed_refs (
refname TEXT PRIMARY KEY,
object_id TEXT NOT NULL,
observed_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS metadata (
key TEXT PRIMARY KEY,
value TEXT NOT NULL
);
"""
)
finally:
conn.close()
def register_event(self, event: Event) -> tuple[bool, dict[str, Any]]:
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
existing = conn.execute(
"SELECT digest, event_json FROM events WHERE event_id=?",
(event.event_id,),
).fetchone()
if existing:
if existing["digest"] != event.digest():
raise ConflictError("event_id_payload_conflict")
conn.execute("COMMIT")
return False, json.loads(existing["event_json"])
state = conn.execute(
"SELECT contract_commit, state_version FROM project_state WHERE project_key=?",
(event.project_key,),
).fetchone()
if state is None:
conn.execute(
"""
INSERT INTO project_state(
project_key, contract_commit, state_version, state_json,
hops, updated_at
) VALUES (?, ?, ?, '{}', 0, ?)
""",
(event.project_key, event.contract_commit, event.state_version, now),
)
else:
if state["contract_commit"] != event.contract_commit:
raise ConflictError("contract_version_mismatch")
if state["state_version"] != event.state_version:
raise ConflictError("stale_state_version")
conn.execute(
"""
INSERT INTO events(
event_id, project_key, digest, event_json, status,
next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, 'RECEIVED', ?, ?, ?)
""",
(
event.event_id,
event.project_key,
event.digest(),
event.canonical_json(),
now,
now,
now,
),
)
conn.execute("COMMIT")
return True, event.to_dict()
except Exception:
conn.execute("ROLLBACK")
raise
def claim_events(
self,
*,
owner: str,
statuses: tuple[str, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
if not statuses:
return []
now = int(time.time())
placeholders = ",".join("?" for _ in statuses)
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT event_id FROM events
WHERE status IN ({placeholders})
AND next_attempt_at <= ?
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY
CASE json_extract(event_json, '$.event_type')
WHEN 'central_gpt_health_probe' THEN 0
WHEN 'a0_unattended_acceptance_requested' THEN 0
ELSE 1
END,
created_at
LIMIT ?
""",
(*statuses, now, now, limit),
).fetchall()
ids = [row["event_id"] for row in rows]
for event_id in ids:
conn.execute(
"""
UPDATE events SET lease_owner=?, lease_until=?, updated_at=?
WHERE event_id=?
""",
(owner, now + lease_seconds, now, event_id),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not ids:
return []
placeholders = ",".join("?" for _ in ids)
claimed = {
str(row["event_id"]): dict(row)
for row in conn.execute(
f"SELECT * FROM events WHERE event_id IN ({placeholders})",
ids,
).fetchall()
}
return [claimed[str(event_id)] for event_id in ids]
def update_event_trigger(
self,
event_id: str,
*,
status: str,
channel: str | None,
remote_id: str | None,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
now = int(time.time())
self._conn().execute(
"""
UPDATE events
SET status=?, channel=?, remote_id=?,
attempts=attempts + ?,
next_attempt_at=?,
lease_owner=NULL, lease_until=NULL, updated_at=?
WHERE event_id=?
""",
(
status,
channel,
remote_id,
1 if increment_attempt else 0,
now + max(0, retry_after),
now,
event_id,
),
)
def claim_workspace_timeouts(
self,
*,
owner: str,
older_than: int,
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
return self._claim_event_subset(
owner=owner,
where_sql="status='AWAITING_DECISION' AND channel='workspace_agent' AND updated_at <= ?",
where_params=(older_than,),
limit=limit,
lease_seconds=lease_seconds,
)
def claim_response_polls(
self,
*,
owner: str,
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
now = int(time.time())
return self._claim_event_subset(
owner=owner,
where_sql="status='POLLING_RESPONSE' AND next_attempt_at <= ?",
where_params=(now,),
limit=limit,
lease_seconds=lease_seconds,
)
def _claim_event_subset(
self,
*,
owner: str,
where_sql: str,
where_params: tuple[Any, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
allowed = {
"status='AWAITING_DECISION' AND channel='workspace_agent' AND updated_at <= ?",
"status='POLLING_RESPONSE' AND next_attempt_at <= ?",
}
if where_sql not in allowed:
raise ValueError("invalid_event_claim_query")
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT event_id FROM events
WHERE {where_sql}
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY updated_at
LIMIT ?
""",
(*where_params, now, limit),
).fetchall()
ids = [str(row["event_id"]) for row in rows]
for event_id in ids:
conn.execute(
"""
UPDATE events SET lease_owner=?, lease_until=?
WHERE event_id=?
""",
(owner, now + lease_seconds, event_id),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not ids:
return []
placeholders = ",".join("?" for _ in ids)
return [
dict(row)
for row in conn.execute(
f"SELECT * FROM events WHERE event_id IN ({placeholders})",
ids,
).fetchall()
]
def apply_decision(
self,
decision: Decision,
*,
max_hops_per_gate: int,
max_same_blocker_retries: int,
) -> int:
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
event = conn.execute(
"SELECT project_key FROM events WHERE event_id=?",
(decision.event_id,),
).fetchone()
if event is None:
raise ConflictError("event_not_found")
if event["project_key"] != decision.project_key:
raise ConflictError("event_project_mismatch")
existing = conn.execute(
"SELECT decision_json, state_version_after FROM decisions WHERE event_id=?",
(decision.event_id,),
).fetchone()
if existing:
if json.loads(existing["decision_json"]) != decision.to_dict():
raise ConflictError("decision_idempotency_conflict")
conn.execute("COMMIT")
return int(existing["state_version_after"])
state = conn.execute(
"SELECT * FROM project_state WHERE project_key=?",
(decision.project_key,),
).fetchone()
if state is None:
raise ConflictError("project_state_not_found")
if state["contract_commit"] != decision.contract_commit:
raise ConflictError("contract_version_mismatch")
if state["state_version"] != decision.expected_state_version:
raise ConflictError("stale_decision_state_version")
state_json = json.loads(state["state_json"])
gate = str(
decision.state_updates.get(
"current_gate", state_json.get("current_gate", "unknown")
)
)
gate_hops = conn.execute(
"SELECT hops FROM gate_hops WHERE project_key=? AND gate_id=?",
(decision.project_key, gate),
).fetchone()
if gate_hops is not None and int(gate_hops["hops"]) >= max_hops_per_gate:
raise ConflictError("max_hops_exceeded")
state_json.update(decision.state_updates)
next_version = int(state["state_version"]) + 1
if decision.stop_reason:
row = conn.execute(
"""
SELECT repetitions FROM blocker_history
WHERE project_key=? AND gate_id=? AND blocker=?
""",
(decision.project_key, gate, decision.stop_reason),
).fetchone()
repetitions = (int(row["repetitions"]) if row else 0) + 1
conn.execute(
"""
INSERT INTO blocker_history(
project_key, gate_id, blocker, repetitions, updated_at
) VALUES (?, ?, ?, ?, ?)
ON CONFLICT(project_key, gate_id, blocker)
DO UPDATE SET repetitions=excluded.repetitions,
updated_at=excluded.updated_at
""",
(decision.project_key, gate, decision.stop_reason, repetitions, now),
)
if repetitions > max_same_blocker_retries:
raise ConflictError("same_blocker_retry_limit_exceeded")
conn.execute(
"""
INSERT INTO gate_hops(project_key, gate_id, hops, updated_at)
VALUES (?, ?, 1, ?)
ON CONFLICT(project_key, gate_id)
DO UPDATE SET hops=gate_hops.hops + 1, updated_at=excluded.updated_at
""",
(decision.project_key, gate, now),
)
conn.execute(
"""
UPDATE project_state
SET state_version=?, state_json=?, hops=hops+1, updated_at=?
WHERE project_key=?
""",
(
next_version,
json.dumps(state_json, separators=(",", ":"), sort_keys=True),
now,
decision.project_key,
),
)
conn.execute(
"""
INSERT INTO decisions(
event_id, project_key, decision_json,
state_version_after, created_at
) VALUES (?, ?, ?, ?, ?)
""",
(
decision.event_id,
decision.project_key,
json.dumps(decision.to_dict(), separators=(",", ":"), sort_keys=True),
next_version,
now,
),
)
for unit in decision.next_work_units:
conn.execute(
"""
INSERT INTO outbox(
work_unit_id, event_id, assigned_agent, payload_json,
status, next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, 'PENDING', ?, ?, ?)
""",
(
unit.id,
decision.event_id,
unit.primary_agent,
json.dumps(unit.to_dict(), separators=(",", ":"), sort_keys=True),
now,
now,
now,
),
)
conn.execute(
"""
UPDATE events SET status='DECIDED', lease_owner=NULL,
lease_until=NULL, updated_at=?
WHERE event_id=?
""",
(now, decision.event_id),
)
conn.execute("COMMIT")
return next_version
except Exception:
conn.execute("ROLLBACK")
raise
def claim_outbox(self, *, owner: str, limit: int, lease_seconds: int) -> list[dict[str, Any]]:
rows = self._claim_table(
table="outbox",
key="work_unit_id",
owner=owner,
statuses=("PENDING", "RETRY"),
limit=limit,
lease_seconds=lease_seconds,
)
for row in rows:
context = self._conn().execute(
"""
SELECT e.project_key, d.state_version_after
FROM events e JOIN decisions d ON d.event_id=e.event_id
WHERE e.event_id=?
""",
(row["event_id"],),
).fetchone()
if context is not None:
row["project_key"] = str(context["project_key"])
row["state_version"] = int(context["state_version_after"])
return rows
def event_status(self, event_id: str) -> dict[str, Any] | None:
row = self._conn().execute(
"""
SELECT e.event_id, e.status, e.channel, d.state_version_after
FROM events e LEFT JOIN decisions d ON d.event_id=e.event_id
WHERE e.event_id=?
""",
(event_id,),
).fetchone()
if row is None:
return None
raw = str(row["status"])
if raw == "DECIDED":
public_status = "DECIDED"
elif raw in {"DEAD_LETTER", "TRIGGER_FAILED"}:
public_status = "TRIGGER_FAILED"
elif raw in {"AWAITING_DECISION", "POLLING_RESPONSE"}:
public_status = "AWAITING_DECISION"
else:
public_status = "RECEIVED"
channel = row["channel"]
if channel not in {"workspace_agent", "responses_api"}:
channel = None
version = row["state_version_after"]
return {
"event_id": str(row["event_id"]),
"status": public_status,
"trigger_channel": channel,
"decision_applied": raw == "DECIDED" and version is not None,
"state_version_after": None if version is None else int(version),
}
def mark_outbox(
self,
work_unit_id: str,
*,
status: str,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
self._mark_table(
table="outbox",
key="work_unit_id",
value=work_unit_id,
status=status,
retry_after=retry_after,
increment_attempt=increment_attempt,
)
def enqueue_lifecycle(
self,
*,
sync_id: str,
project_key: str,
work_unit_id: str | None,
kind: str,
payload: dict[str, Any],
) -> None:
now = int(time.time())
encoded = json.dumps(payload, separators=(",", ":"), sort_keys=True)
self._conn().execute(
"""
INSERT OR IGNORE INTO lifecycle(
sync_id, project_key, work_unit_id, kind, payload_json,
status, next_attempt_at, created_at, updated_at
) VALUES (?, ?, ?, ?, ?, 'PENDING', ?, ?, ?)
""",
(sync_id, project_key, work_unit_id, kind, encoded, now, now, now),
)
def claim_lifecycle(self, *, owner: str, limit: int, lease_seconds: int) -> list[dict[str, Any]]:
return self._claim_table(
table="lifecycle",
key="sync_id",
owner=owner,
statuses=("PENDING", "RETRY"),
limit=limit,
lease_seconds=lease_seconds,
)
def mark_lifecycle(
self,
sync_id: str,
*,
status: str,
retry_after: int = 0,
increment_attempt: bool = False,
) -> None:
self._mark_table(
table="lifecycle",
key="sync_id",
value=sync_id,
status=status,
retry_after=retry_after,
increment_attempt=increment_attempt,
)
def _claim_table(
self,
*,
table: str,
key: str,
owner: str,
statuses: tuple[str, ...],
limit: int,
lease_seconds: int,
) -> list[dict[str, Any]]:
if table not in {"outbox", "lifecycle"} or key not in {"work_unit_id", "sync_id"}:
raise ValueError("invalid_claim_table")
now = int(time.time())
placeholders = ",".join("?" for _ in statuses)
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
rows = conn.execute(
f"""
SELECT {key} FROM {table}
WHERE status IN ({placeholders})
AND next_attempt_at <= ?
AND (lease_until IS NULL OR lease_until < ?)
ORDER BY created_at
LIMIT ?
""",
(*statuses, now, now, limit),
).fetchall()
values = [row[key] for row in rows]
for item in values:
conn.execute(
f"""
UPDATE {table} SET lease_owner=?, lease_until=?, updated_at=?
WHERE {key}=?
""",
(owner, now + lease_seconds, now, item),
)
conn.execute("COMMIT")
except Exception:
conn.execute("ROLLBACK")
raise
if not values:
return []
placeholders = ",".join("?" for _ in values)
return [
dict(row)
for row in conn.execute(
f"SELECT * FROM {table} WHERE {key} IN ({placeholders})",
values,
).fetchall()
]
def _mark_table(
self,
*,
table: str,
key: str,
value: str,
status: str,
retry_after: int,
increment_attempt: bool,
) -> None:
if table not in {"outbox", "lifecycle"} or key not in {"work_unit_id", "sync_id"}:
raise ValueError("invalid_mark_table")
now = int(time.time())
self._conn().execute(
f"""
UPDATE {table}
SET status=?, attempts=attempts + ?, next_attempt_at=?,
lease_owner=NULL, lease_until=NULL, updated_at=?
WHERE {key}=?
""",
(
status,
1 if increment_attempt else 0,
now + max(0, retry_after),
now,
value,
),
)
def project_state(self, project_key: str) -> dict[str, Any] | None:
row = self._conn().execute(
"SELECT * FROM project_state WHERE project_key=?",
(project_key,),
).fetchone()
if row is None:
return None
result = dict(row)
result["state"] = json.loads(result.pop("state_json"))
return result
def all_project_states(self) -> list[dict[str, Any]]:
result = []
for row in self._conn().execute("SELECT * FROM project_state ORDER BY project_key").fetchall():
item = dict(row)
item["state"] = json.loads(item.pop("state_json"))
result.append(item)
return result
def summary_due(self, project_key: str, interval: int) -> bool:
now = int(time.time())
row = self._conn().execute(
"SELECT last_emitted_at FROM summaries WHERE project_key=?",
(project_key,),
).fetchone()
return row is None or now - int(row["last_emitted_at"]) >= interval
def mark_summary(self, project_key: str, digest: str) -> None:
now = int(time.time())
self._conn().execute(
"""
INSERT INTO summaries(project_key, last_emitted_at, last_digest)
VALUES (?, ?, ?)
ON CONFLICT(project_key)
DO UPDATE SET last_emitted_at=excluded.last_emitted_at,
last_digest=excluded.last_digest
""",
(project_key, now, digest),
)
def project_summary(self, project_key: str) -> dict[str, Any] | None:
state = self.project_state(project_key)
if state is None:
return None
conn = self._conn()
event_counts = {
row["status"]: int(row["count"])
for row in conn.execute(
"""
SELECT status, COUNT(*) AS count FROM events
WHERE project_key=? GROUP BY status
""",
(project_key,),
).fetchall()
}
outbox_counts = {
row["status"]: int(row["count"])
for row in conn.execute(
"""
SELECT o.status, COUNT(*) AS count
FROM outbox o JOIN events e ON e.event_id=o.event_id
WHERE e.project_key=? GROUP BY o.status
""",
(project_key,),
).fetchall()
}
return {
"project_key": project_key,
"contract_commit": state["contract_commit"],
"state_version": state["state_version"],
"state": state["state"],
"event_counts": event_counts,
"work_unit_counts": outbox_counts,
"updated_at": state["updated_at"],
}
def metadata_get(self, key: str) -> str | None:
row = self._conn().execute(
"SELECT value FROM metadata WHERE key=?",
(key,),
).fetchone()
return None if row is None else str(row["value"])
def metadata_set(self, key: str, value: str) -> None:
self._conn().execute(
"""
INSERT INTO metadata(key, value) VALUES (?, ?)
ON CONFLICT(key) DO UPDATE SET value=excluded.value
""",
(key, value),
)
def observe_refs(self, refs: dict[str, str]) -> tuple[bool, list[tuple[str, str | None, str]]]:
"""Persist a Git snapshot and return changes after the initial baseline."""
now = int(time.time())
conn = self._conn()
conn.execute("BEGIN IMMEDIATE")
try:
initialized = conn.execute(
"SELECT value FROM metadata WHERE key='git_poll_initialized'"
).fetchone()
previous = {
row["refname"]: row["object_id"]
for row in conn.execute("SELECT refname, object_id FROM observed_refs").fetchall()
}
changes: list[tuple[str, str | None, str]] = []
if initialized is not None:
for refname, oid in refs.items():
old = previous.get(refname)
if old != oid:
changes.append((refname, old, oid))
for refname, old in previous.items():
if refname not in refs:
changes.append((refname, old, "0" * 40))
conn.execute("DELETE FROM observed_refs")
for refname, oid in refs.items():
conn.execute(
"""
INSERT INTO observed_refs(refname, object_id, observed_at)
VALUES (?, ?, ?)
""",
(refname, oid, now),
)
conn.execute(
"""
INSERT INTO metadata(key, value)
VALUES ('git_poll_initialized', '1')
ON CONFLICT(key) DO UPDATE SET value='1'
"""
)
conn.execute("COMMIT")
return initialized is not None, changes
except Exception:
conn.execute("ROLLBACK")
raise
def close(self) -> None:
conn = getattr(self._local, "conn", None)
if conn is not None:
conn.close()
self._local.conn = None