"""The single state-transition authority. Every job-status write goes through `transition`. Before phase 2a there were two write paths: `update_job_status` merged fields unconditionally, and `pick_pending` hand-rolled a correct pending->running swap plus its own audit mirror. Neither was wrong on its own; having two was the risk, because a fix or a rule added to one silently misses the other. It lives in `lib_py.delegation`, not `lib_py.loop`, because it writes the registry and the registry writers are here. A frozen loop can bind `lib_py.delegation` to a different tree than the parent package, so delegation importing a sibling would mix trees -- the rule this package states in its own __init__, and which caught this during implementation. Lock discipline (the reason this is a module and not a helper): with registry_lock: decide, write the record once, QUEUE notifications after the lock: flush notifications, publish, anything slow Nothing that can block on another process or the network may run while the lock is held. `pick_pending` already mirrored its audit entries after releasing the lock; this generalises that shape to every transition. `MAM_ENGINE_CAS=0` restores the previous unconditional-merge behaviour without a redeploy. The legacy bodies are preserved by their callers for that reason. """ from __future__ import annotations import logging import os from typing import Any, Dict, List, Optional from lib_py.delegation import mqtt_common logger = logging.getLogger("loop.engine") TERMINAL_STATUSES = ("completed", "error", "cancelled") NON_TERMINAL_STATUSES = ("pending", "running") # request -> the status it asks for. `merge`/`progress` ask for nothing. REQUEST_TO_STATUS = { "claim": "running", "started": "running", "progress": None, "permission_required": None, "completed": "completed", "error": "error", "cancelled": "cancelled", "deadline_timeout": "error", "merge": None, } # A caller that merges `status=` is making the request that owns that # value; mapping it here is what stops a raw field write from sidestepping the # CAS table. `pending` has no owning request (nothing transitions *to* pending), # so it stays an ordinary metadata merge, exactly as before. STATUS_TO_REQUEST = { "running": "started", "completed": "completed", "error": "error", "cancelled": "cancelled", } def cas_enabled() -> bool: """The rollback switch. Read per call so a test or operator can flip it.""" return os.environ.get("MAM_ENGINE_CAS", "1") != "0" class TransitionResult(object): __slots__ = ("committed", "from_status", "to_status", "reason", "record", "notifications") def __init__(self, committed, from_status, to_status, reason, record, notifications): self.committed = committed self.from_status = from_status self.to_status = to_status self.reason = reason self.record = record self.notifications = notifications def __repr__(self): # pragma: no cover - debugging aid return "TransitionResult(committed={!r}, {!r}->{!r}, {!r})".format( self.committed, self.from_status, self.to_status, self.reason) class _Decision(object): __slots__ = ("commit", "to_status", "reason", "conflict") def __init__(self, commit, to_status, reason, conflict=False): self.commit = commit self.to_status = to_status self.reason = reason self.conflict = conflict def _decide(record: Dict[str, Any], request: str, expected_status, expected_attempt) -> _Decision: """Pure CAS decision. No I/O, so it is safe to call under the lock. Implements the target table in docs/contracts/issue-5/state-transitions.md ยง3. """ current = record.get("status") # Stale attempt or generation loses before anything else is considered. if expected_attempt is not None: actual = record.get("attempt_id", record.get("iteration")) if actual is not None and actual != expected_attempt: return _Decision(False, current, "stale attempt: expected {!r}, record has {!r}".format( expected_attempt, actual)) if expected_status is not None and current != expected_status: return _Decision(False, current, "precondition failed: expected status {!r}, found {!r}".format( expected_status, current)) requested = REQUEST_TO_STATUS.get(request, None) if current in TERMINAL_STATUSES: # Idempotent re-receipt of the same terminal is a no-op ack. if requested == current: return _Decision(False, current, "idempotent: already {}".format(current)) if requested is None: return _Decision(False, current, "late {} after terminal {}; refusing".format(request, current), conflict=True) return _Decision(False, current, "conflicting {} after terminal {}; refusing".format(requested, current), conflict=True) if requested is None: # progress / permission_required / metadata-only merge: the engine does # not set a status, so any status in `fields` is applied as-is. return _Decision(True, None, "metadata updated ({})".format(request)) return _Decision(True, requested, "{} -> {}".format(current, requested)) def _notification(job_id, kind, **fields) -> Dict[str, Any]: payload = {"job_id": job_id, "kind": kind} payload.update(fields) return payload def transition(job_id, request="merge", *, registry_dir=None, expected_status=None, expected_attempt=None, fields=None, source="unknown") -> TransitionResult: """Decide and commit one state transition. The only writer of job status. Returns a result whose `notifications` have ALREADY been flushed; the field is kept so callers and tests can see what the transition emitted. """ registry_dir = registry_dir or mqtt_common.DEFAULT_REGISTRY_DIR fields = dict(fields or {}) # ---- short transaction: decide and write, never do I/O that can block ---- with mqtt_common.registry_lock(registry_dir): record = mqtt_common.load_job(job_id, registry_dir) from_status = record.get("status") decision = _decide(record, request, expected_status, expected_attempt) notifications: List[Dict[str, Any]] = [] if decision.commit: record.update(fields) if decision.to_status is not None: record["status"] = decision.to_status record["updated_at"] = mqtt_common._utcnow() # A monotonic counter so a late flush can still be ordered correctly # once the audit mirror happens outside the lock. record["transition_seq"] = int(record.get("transition_seq", 0)) + 1 mqtt_common._atomic_write_record(job_id, registry_dir, record) to_status = record.get("status") if to_status != from_status: notifications.append(_notification( job_id, "status_changed", **{ "from": from_status, "to": to_status, "by": source, "timestamp": record["updated_at"], "transition_seq": record["transition_seq"], })) else: to_status = from_status if decision.conflict: notifications.append(_notification( job_id, "conflict_refused", attempted=request, current=from_status, reason=decision.reason, by=source, timestamp=mqtt_common._utcnow())) # ---- lock released; everything below may block ---- _flush(notifications, registry_dir) if not decision.commit and decision.conflict: logger.warning("refused %s for job %s: %s", request, job_id, decision.reason) return TransitionResult(decision.commit, from_status, to_status, decision.reason, record, notifications) def _flush(notifications, registry_dir) -> None: """Mirror queued notifications into the audit log, outside the lock. Best effort by design: the registry record is already durable, and an audit write must never be able to fail a transition that has committed. """ for note in notifications: job_id = note["job_id"] kind = note["kind"] try: if kind == "status_changed": mqtt_common.update_logged_status( job_id, note["to"], updated_at=note.get("timestamp")) mqtt_common.append_event(job_id, { "event": "status_changed", "from": note.get("from"), "to": note.get("to"), "by": note.get("by"), "timestamp": note.get("timestamp"), "transition_seq": note.get("transition_seq"), }) elif kind == "conflict_refused": mqtt_common.append_event(job_id, { "event": "conflict_refused", "attempted": note.get("attempted"), "current": note.get("current"), "reason": note.get("reason"), "by": note.get("by"), "timestamp": note.get("timestamp"), }) except Exception as exc: # pragma: no cover - best effort logger.warning("audit mirror failed for %s: %s", job_id, exc)