Files
claude-mem/src/server/generation/processGeneratedResponse.ts
T
Alex Newman e7bbb2a9aa server-beta: Phases 4–13 — event pipeline, generation, MCP, compat, Docker, team audit, observability (#2383)
* feat(server-beta): Phase 4 — Postgres event-to-generation-job pipeline

Adds POST /v1/events, /v1/events/batch, GET /v1/jobs/:id, GET /v1/events/:id,
and POST /v1/memories on the server-beta runtime, backed by Postgres.

- Event row + outbox generation-job row insert in one withPostgresTransaction.
- BullMQ enqueue happens after commit; enqueue failure leaves the row queued
  for Phase 3 startup reconciliation.
- ?generate=false skips the outbox; ?wait=true returns queue status only,
  never observation IDs (provider generation is Phase 5).
- Batch pre-validates all event projectIds against api-key scope before any
  write; mixed-project batches reject 403 with zero side effects.
- /v1/memories is a direct insert alias — no generator, no outbox.
- Cross-tenant /v1/jobs/:id returns 404 to avoid leaking row existence.
- New PostgresAuthMiddleware reads api_keys by SHA-256 hash; populates
  req.authContext.teamId/projectId; legacy ServerV1Routes (SQLite, used by
  worker runtime) is left untouched.
- Tests: unit suite hardened with stubbed pool.query so route registration
  is safe; integration tests skip cleanly without CLAUDE_MEM_TEST_POSTGRES_URL.

Verification: 87 pass / 1 skip / 0 fail. No new typecheck errors. Required
greps for WorkerService and MemoryItemsRepository in src/server/routes/v1
and src/server/runtime return no hits.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 5 — provider observation generator

Adds independent provider generation under src/server/generation/ with no
worker coupling. Server beta can now generate observations end-to-end:
event -> outbox -> BullMQ -> provider -> parser -> persisted observation.

- ProviderObservationGenerator orchestrates: lock outbox (queued -> processing),
  reload agent_event from Postgres (BullMQ payload is advisory only), call
  provider, hand raw text to processGeneratedResponse, route errors via
  markGenerationFailed with retryable flag from ServerClassifiedProviderError.
- processGeneratedResponse parses with parseAgentXml, persists via
  PostgresObservationRepository with deterministic
  generation_key = generation:v1:{job_id}:{index}:{fingerprint},
  links via PostgresObservationSourcesRepository, advances outbox status,
  appends observation_generation_job_events, audits — all in one
  withPostgresTransaction. Idempotent on retry via UNIQUE constraints.
- Three provider adapters under src/server/generation/providers/:
  Claude, Gemini, OpenRouter. Self-contained — no imports from
  src/services/worker/*. Worker providers unchanged.
- Shared error classification + prompt builder under providers/shared/.
  Prompt builder strips <private> at the edge; fully-private batches
  emit <skip_summary /> without billing the provider.
- ActiveServerBetaGenerationWorkerManager wires BullMQ Worker via
  ServerJobQueue.start(...) with concurrency 1 + autorun:false +
  worker.on('error') per BullMQ docs.
- New GET /v1/events/:id/observations on ServerV1PostgresRoutes returns
  observations linked via observation_sources, team/project scoped.

Verification: 104 pass / 4 skip / 0 fail. No typecheck regressions.
Anti-pattern greps clean for services/worker imports under src/server,
WorkerRef/ActiveSession/SessionStore in src/server/generation.

Deferred: ModeManager loading uses a stable fallback observation type
list; summary and reindex queue lanes are not yet wired.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 6 — independent server session semantics

server_sessions is now the canonical Server beta session model. Sessions
are independent of legacy worker ActiveSession state.

- PostgresServerSessionRepository extended: findByExternalIdForScope,
  endSession (idempotent via COALESCE(ended_at, now())),
  markGenerationStarted/Completed/Failed, listUnprocessedEvents (filters
  agent_events with completed agent_event jobs).
- ServerSessionRuntimeRepository wraps the repo; every method requires
  explicit team_id + project_id and validates scope via assertProjectOwnership.
- SessionGenerationPolicy supports per-event (default), debounce
  (BullMQ delayed-job replace via getJob+remove+add), and end-of-session.
  Configured via CLAUDE_MEM_SERVER_SESSION_POLICY and
  CLAUDE_MEM_SERVER_SESSION_DEBOUNCE_MS env vars; per-team override hooks
  are exposed on ServerV1PostgresRoutesOptions for future settings layer.
- POST /v1/sessions/start (find-or-create on (project_id, external_session_id),
  GET /v1/sessions/:id (scoped 404), POST /v1/sessions/:id/end
  (transactional: end + create summary outbox via UNIQUE collapse +
  enqueue post-commit). Re-ending is fully idempotent.
- processSessionSummaryResponse persists summary as kind='summary'
  observation with the same idempotency model
  (generation_key + observation_sources UNIQUE).
- ProviderObservationGenerator dispatches on source_type:
  agent_event -> processGeneratedResponse, session_summary ->
  processSessionSummaryResponse; loadEvents handles session-summary
  by loading unprocessed events.
- ActiveServerBetaGenerationWorkerManager wires summary BullMQ lane
  alongside event lane (concurrency=1, autorun=false, error listener
  attached per BullMQ docs).

Verification: 110 pass / 6 skip / 0 fail. Net typecheck error count
unchanged at 24 (pre-existing, none in Phase 6 files). Anti-pattern
greps clean for ActiveSession/SessionStore in src/server/runtime,
no worker imports anywhere in src/server.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 7 — hook routing without worker dependency

Hooks can now talk directly to server-beta when CLAUDE_MEM_RUNTIME=server-beta
is selected, with a clean worker fallback when server-beta is unhealthy.

- src/services/hooks/server-beta-client.ts — typed HTTP client for
  /v1/sessions/start, /v1/events, /v1/sessions/:id/end. Throws
  ServerBetaClientError with kind classification (missing_api_key,
  transport, timeout, http_error, invalid_response) and isFallbackEligible
  helper. Zero imports from services/worker/.
- src/services/hooks/runtime-selector.ts — reads CLAUDE_MEM_RUNTIME from
  settings, returns worker or server-beta context, logs
  [server-beta-fallback] reason=<code> on every config-time fallback.
- src/services/hooks/server-beta-bootstrap.ts — Postgres-backed API key
  bootstrap. Find-or-creates local-hook-team + local-hook-project,
  generates cmem_<random> key (SHA-256 hashed), inserts into api_keys
  with scopes events:write/sessions:write/observations:read/jobs:read.
  Settings file written with chmod 0600. rotateServerBetaApiKey() wired
  to a new `claude-mem server keys rotate` command.
- src/cli/handlers/{observation,session-init,summarize}.ts — every hook
  handler tries server-beta first when configured, falls through to the
  existing worker path on transport/5xx/429/missing-key. One WARN line
  per fallback. Hook JSON output shape unchanged.
- src/shared/SettingsDefaultsManager.ts — three new keys with defaults:
  CLAUDE_MEM_SERVER_BETA_URL, CLAUDE_MEM_SERVER_BETA_API_KEY,
  CLAUDE_MEM_SERVER_BETA_PROJECT_ID.
- src/npx-cli/commands/install.ts — when installer selects server-beta
  runtime and CLAUDE_MEM_SERVER_DATABASE_URL is set, bootstraps a local
  API key automatically. Warns and continues if the DB URL is missing.

plugin/scripts/*.cjs bundles rebuilt via npm run build to pick up the
new hook handler code path. No plaintext keys in the bundle (verified).

Verification: 16 hook unit tests pass; 275 server/storage/services tests
pass with 7 pre-existing failures (verified independent of this change
via git stash --include-untracked). Build clean. No new typecheck
errors in Phase 7 files.

Anti-pattern guards verified:
- /api/sessions/observations only reached via explicit fallback path
- server-beta runtime never starts the worker process
- API keys live only in ~/.claude-mem/settings.json (chmod 0600), never
  in the bundle (grep confirmed)
- Worker fallback preserved, observable via single WARN line per call

Deferred: semantic context injection (UserPromptSubmit hook) stays
worker-only; server-beta does not yet expose /v1/context/semantic.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 8 — MCP backed by server-beta core

MCP tools now route through server-beta in server-beta mode while keeping
worker-mode search/timeline/get_observations tools fully working.

- src/servers/mcp-server.ts — five new observation_* tools registered:
  observation_add, observation_record_event, observation_search,
  observation_context, observation_generation_status. Three memory_*
  compatibility aliases delegate to the canonical handlers. Worker
  auto-start is gated when selectRuntime() === 'server-beta' so MCP
  in server-beta mode never spawns the worker.
- src/services/hooks/server-beta-client.ts — addObservation,
  searchObservations, contextObservations, getJobStatus added so MCP
  shares one transport with hooks (Phase 7).
- src/server/routes/v1/ServerV1PostgresRoutes.ts — POST /v1/search and
  POST /v1/context REST cores backed by PostgresObservationRepository
  full-text search (GIN tsvector from Phase 1).
- Existing memory_search/timeline/get_observations tools call
  callWorkerAPI unchanged in worker mode; worker tests unaffected.

Verification: 39 pass / 4 skip / 0 fail on targeted suite. Pre-existing
7 baseline failures verified independent (git stash). No new typecheck
errors. WorkerService grep clean across src/servers/mcp-server.ts and
src/server/.

Anti-pattern guards verified:
- No duplicate generation logic in MCP — observation_record_event hits
  /v1/events which owns event+outbox+enqueue inside one tx
- WorkerService not imported anywhere under MCP server-beta path
- No hardcoded worker URLs — all transport via Phase 7 ServerBetaClient
- memory_* aliases retained, single handler per pair

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 9 — compatibility adapters without coupling

Legacy /api/sessions/observations and /api/sessions/summarize endpoints
keep working on server-beta runtime by translating to AgentEvent and
session-end calls — no worker code, no route duplication.

- src/server/services/IngestEventsService.ts — shared event-ingest path
  used by both /v1/events and the compat adapter. Owns transactional
  event row + outbox row + lifecycle log + post-commit BullMQ enqueue,
  honors Phase 6 SessionGenerationPolicy.
- src/server/services/EndSessionService.ts — shared session-end path
  used by both /v1/sessions/:id/end and the compat adapter. Idempotent
  ended_at + summary outbox + deterministic summary job id.
- src/server/compat/SessionsObservationsAdapter.ts — translates legacy
  POST /api/sessions/observations payload (Claude Code transcript shape)
  -> AgentEvent (source_adapter='claude-code-compat',
  event_type='tool_use') -> IngestEventsService.ingestOne. Resolves
  contentSessionId to server_sessions via find-or-create.
- src/server/compat/SessionsSummarizeAdapter.ts — translates legacy
  POST /api/sessions/summarize -> EndSessionService.end. Preserves the
  legacy agentId -> {status:'skipped', reason:'subagent_context'}
  behavior so existing clients see the same response shape.
- src/server/routes/v1/ServerV1PostgresRoutes.ts — refactored to
  delegate to the new shared services (-203 LoC net) so /v1 and
  /api compat both call the SAME canonical code path.
- src/server/runtime/ServerBetaService.ts — registers both compat
  adapters alongside ServerV1PostgresRoutes, sharing service instances.
- docs/server-beta-parity-map.md — full enumeration of legacy /api/*
  routes labeled native, adapter, or unsupported (with reasons).
  Viewer read-path adapters explicitly listed as unsupported pending
  a future viewer-rewrite phase.

Verification: 7 compat tests pass, 6 v1-routes tests still pass
(refactor preserved behavior), 4 session-routes tests pass. Pre-
existing 16 baseline failures verified independent via git stash.
Zero new typecheck errors.

Anti-pattern guards verified:
- No services/worker/http/routes or WorkerService imports under
  src/server/compat or src/server/runtime
- Compat adapters are thin translators with names ending in *Adapter
  and a top-of-file comment noting they are legacy compatibility
- /v1/* remains the canonical Server beta API; compat adapters
  call shared services rather than acting as a parallel API

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 10 — Docker stack and deployable runtime

Server beta now ships as a Docker stack with no worker process anywhere
and a separate horizontal generation worker for scaling.

- src/server/runtime/create-server-beta-service.ts — validateServerBetaEnv()
  fails fast on missing CLAUDE_MEM_SERVER_DATABASE_URL, requires
  CLAUDE_MEM_QUEUE_ENGINE=bullmq in Docker, rejects
  CLAUDE_MEM_AUTH_MODE=local-dev and CLAUDE_MEM_ALLOW_LOCAL_DEV_BYPASS
  inside containers (detected via /.dockerenv or CLAUDE_MEM_DOCKER=1).
  Adds CLAUDE_MEM_GENERATION_DISABLED so the HTTP service can run
  generator-free.
- src/server/runtime/ServerBetaService.ts — runServerBetaGenerationWorker
  for the dedicated consumer process; runServerBetaApiKeyCli is a new
  Postgres-backed `server api-key` command (the legacy worker CLI wrote
  to SQLite and was invisible to the Postgres runtime); getQueueHealth
  shim feeds /api/health a consistent ObservationQueueHealth shape.
- src/npx-cli/commands/{runtime,server}.ts — `claude-mem server worker
  start` subcommand that boots only the BullMQ consumer.
- docker/claude-mem/{Dockerfile,entrypoint.sh} — entrypoint forces
  CLAUDE_MEM_DOCKER=1 + CLAUDE_MEM_RUNTIME=server-beta and exposes
  three modes: server (HTTP only, generation disabled), worker (BullMQ
  consumer), shell. Worker bundle is no longer the default CMD.
- docker-compose.yml — full stack: postgres + valkey + claude-mem-server
  (HTTP-only) + claude-mem-worker (generation consumer). Wires
  service-to-service env vars.
- scripts/e2e-server-beta-docker.sh + docker/e2e/server-beta-e2e.mjs —
  E2E now hits /v1/sessions/start, /v1/events?wait=true, /v1/jobs/:id;
  asserts no worker-service.cjs process anywhere in the stack;
  one-shot docker compose run --rm verifies local-dev auth is
  rejected with the expected stderr; restart-and-verify confirms
  Postgres durability and BullMQ retry idempotency.
- docs/server.md — full Phase 10 doc: stack diagram, env table,
  worker mode, auth-in-Docker policy.
- docs/api.md — event generation semantics (wait=true, generationJob).

Verification: full Docker E2E PASSED on live daemon
(phase1 + phase2 + restart-and-verify + revoked-key + no-worker-
process + local-dev-rejected). Unit tests 292 pass / 9 skip / 7 fail
(7 fails pre-existing baseline). Zero new typecheck errors.

Anti-pattern guards verified:
- entrypoint never execs worker-service.cjs; E2E greps prove no
  worker process anywhere in the stack
- validateServerBetaEnv refuses local-dev auth in Docker with explicit
  remediation message; ALLOW_LOCAL_DEV_BYPASS rejected the same way
- Docker requires CLAUDE_MEM_QUEUE_ENGINE=bullmq; in-process queue
  rejected at startup
- claude-mem worker / worker-service / WorkerService greps clean
  in docker/

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 11 — team-aware generation with audit chain

Generation jobs now carry team_id/project_id/api_key_id/actor_id/
source_adapter from enqueue through execution; the outbox is reloaded
from Postgres before any side effect so BullMQ payload can never act
as auth authority.

- src/server/jobs/types.ts — ServerGenerationJobPayloadSchema (Zod
  discriminated union) requires team_id, project_id, generation_job_id,
  source_adapter, api_key_id, actor_id (nullable), source_type, source_id,
  plus event_id / server_session_id per kind. assertServerGenerationJobPayload
  is called at enqueue (outbox.ts) and again at execution boundary.
- src/server/services/{IngestEventsService,EndSessionService}.ts +
  SessionGenerationPolicy.ts — thread identity context (apiKeyId, actorId,
  sourceAdapter) into both event and summary BullMQ payloads.
- src/server/generation/ProviderObservationGenerator.ts —
  loadCanonicalOutbox loads the outbox row WITHOUT scope filter, then
  compares candidate.team_id/project_id to payload.team_id/project_id;
  mismatch -> ServerGenerationScopeViolationError (non-retryable),
  failed status, generation_job.scope_violation audit. isApiKeyRevoked
  checks api_keys (revoked_at, expires_at, row missing) before any
  provider call; revoked -> generation_job.revoked_key audit + non-
  retryable failure. generation_job.processing audit emitted on lock.
- src/server/generation/processGeneratedResponse.ts — generated
  observations carry team_id/project_id/server_session_id from the
  reloaded source row (not job payload). observation_sources.metadata
  records source_adapter, actor_id, api_key_id for traceability.
  observation.created audit per observation; generation_job.completed
  audit per terminal transition. All audit rows reference the same
  generation_job_id in details.
- src/server/routes/v1/ServerV1PostgresRoutes.ts — GET /v1/teams/:id/jobs
  and GET /v1/projects/:id/jobs with SQL-layer scoping (WHERE team_id=$1
  [AND project_id=$2] [AND status=$3]); cross-tenant returns 404 to
  avoid leaking row existence. Pagination via status/limit/offset.
  audit_log rows for event.received, event.batch_received, observation.read.
- src/server/compat/{SessionsObservationsAdapter,SessionsSummarizeAdapter}.ts —
  propagate apiKeyId and sourceAdapter='claude-code-compat'.

Verification: 162 pass / 10 skip / 0 fail. Pre-existing failures in
tests/services/queue and tests/services/worker confirmed independent
via git stash. Zero new typecheck errors in server-beta files.
Required greps:
  rg "team_id.*req\.body|project_id.*req\.body" src/server -> 0 matches
Audit chain integration test passes — generation_job.processing,
observation.created, and generation_job.completed audit rows all
share the same generation_job_id reference.

Anti-pattern guards verified:
- BullMQ payload never acts as auth authority — Postgres outbox
  reload with mismatch check happens before every side effect
- team_id / project_id never derived from request body for scope
  decisions; always req.authContext.teamId / projectId
- Application-layer team/project filtering forbidden — listJobsForScope
  pushes scope into the SQL WHERE clause
- Project-scoped key on cross-project /v1/teams/:id/jobs returns 404
- Revoked api keys cause non-retryable failure with audit before
  any provider call

Deferred: a redundant generation_job.queued audit_log row (already
covered by observation_generation_job_events lifecycle log per Phase 1
schema split). Compat adapters set actor_id=null but propagate
api_key_id which is the canonical reference downstream.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(server-beta): Phase 12 — observability and operations

Operators can now inspect, retry, and cancel generation jobs from the
CLI; queue lane metrics flow into /api/health and /v1/info; every
request gets a stable request_id that flows through HTTP -> audit ->
outbox -> generator -> completion log.

- src/server/middleware/request-id.ts — honors safe inbound X-Request-Id,
  mints uuid v4 otherwise. Set on req.requestId and echoed via response
  header so external traces can correlate.
- src/server/jobs/ServerJobQueue.ts — QueueEvents wired with completed,
  failed, progress, stalled, error listeners; lifecycle counters
  exposed via observe() API. Logs emitted as
  [generation] job=<id> source_type=<...> duration=<ms> attempts=<N>
  reason=<message>. Stalled and error counters survive worker restart.
- src/server/jobs/types.ts — ServerGenerationJob payload schema
  extended with optional request_id; flows through from HTTP into
  every BullMQ job.
- src/server/queue/ObservationQueueEngine.ts — health snapshot now
  carries per-lane (event, summary) counts via
  ObservationQueueHealthLaneSnapshot.
- src/server/runtime/{ActiveServerBetaQueueManager,
  ActiveServerBetaGenerationWorkerManager,ServerBetaService}.ts —
  per-lane getJobCounts feed /api/health and /v1/info; stalled events
  audit through audit_log with action generation_job.stalled.
- src/server/routes/v1/ServerV1PostgresRoutes.ts —
  GET /v1/jobs (status/source_type/since/limit/offset, scope from
  api-key, payload stripped unless ?include=payload AND admin scope),
  POST /v1/jobs/:id/retry (idempotent; queued -> no-op; audit
  generation_job.retried_by_operator), POST /v1/jobs/:id/cancel
  (terminal -> no-op; audit generation_job.cancelled_by_operator;
  generator reload-before-side-effects already prevents double work).
- src/server/services/IngestEventsService.ts +
  SessionGenerationPolicy.ts + ProviderObservationGenerator.ts —
  request_id propagated end to end. Generator extracts request_id
  from BullMQ payload and includes it in lock/processing/completion
  logs and audit details.
- src/npx-cli/commands/server-jobs.ts +
  src/npx-cli/commands/server.ts — `claude-mem server jobs
  status|failed|retry|cancel`. status compares Postgres outbox counts
  to BullMQ queue counts and surfaces divergence. failed prints
  attempts + last_error message. --team and --project filters.

Verification: 350 pass / 12 skip / 7 fail (pre-existing baseline,
verified independent via git stash). 18 new tests added (request-id
middleware, server-jobs CLI seams, jobs list/retry/cancel routes
Postgres-gated). Zero new typecheck errors.

Anti-pattern guards verified:
- agent_events.payload only emitted in /v1/jobs response inside the
  admin-gated branch (?include=payload + admin scope) — returns 403
  otherwise
- jobs retry on a queued row is a no-op (no double BullMQ enqueue,
  no double UPDATE)
- Every operator action writes to audit_log with the
  *_by_operator action and request_id correlation in details
- Stalled events audit through generation_job.stalled

Sample correlated trace (one request_id end to end):
  HTTP middleware: req.requestId = 'req-abc'
  audit event.received: details.requestId = 'req-abc'
  BullMQ payload: { request_id: 'req-abc', generation_job_id: 'gj_x' }
  generator lock log: [generation] job locked { jobId, requestId }
  audit generation_job.processing: details.requestId = 'req-abc'
  completion log: [generation] job=evt_... duration=1230ms

Deferred: live /api/health round-trip integration test (needs
Redis); stalled event live integration test (needs Redis); storing
request_id on the observations row itself (spec did not require).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(server-beta): add Phase 13 release readiness report

Captures the final verification gate: tests (1749 pass, 45 fail all
pre-existing baseline, zero regressions), required greps clean,
Docker E2E green end-to-end, all 7 exit criteria met, build clean,
typecheck unchanged from main. Documents deferred items.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(server-beta): rebuild server-beta-service bundle

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): address Greptile review on PR #2383

- ProviderObservationGenerator.lockOutbox: skip duplicate worker run when
  another lock is active instead of returning the row, which previously let
  two BullMQ workers issue the (paid, rate-limited) external provider call
  before the persistence-layer terminal-status guard collapsed the duplicate.
  Reconciliation still recovers from a stale lock on startup or next retry.
- docker-compose.yml: require POSTGRES_USER/PASSWORD/DB env vars (no
  defaults). Stack refuses to start without explicit secrets. Added a header
  warning that the file must not be deployed unmodified.
- e2e-server-beta-docker.sh: export ephemeral test creds for the new
  required env vars so the Docker E2E driver still runs unattended.
- ServerBetaService api-key list: bound query with LIMIT/OFFSET (default 100,
  max 500) and add optional --team filter to prevent unintentional
  cross-tenant key metadata disclosure on shared admin hosts.
- SessionGenerationPolicy: fix dead `??` fallback for NaN parseInt result;
  use `||` so DEFAULT_DEBOUNCE_MS actually applies.
- ServerV1PostgresRoutes: `?wait=true` now actually waits — polls the outbox
  row until terminal status (timeout 30s, 100ms interval) on both
  /v1/events and /v1/events/batch. Returns `waitTimedOut: true` if the cap
  is hit so callers can re-poll the status endpoints.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): address CodeRabbit + Greptile second review on PR #2383

P1 fixes
- Operator retry endpoint was re-publishing the Postgres outbox metadata
  column as the BullMQ payload; the worker's
  assertServerGenerationJobPayload always rejected it, leaving the row
  stuck in queued until startup reconciliation. Persist the BullMQ payload
  on the outbox row at create-time inside IngestEventsService and
  EndSessionService, then re-enqueue that canonical payload on retry.

Major fixes
- prompt-builder: escape server_session_id when interpolating into the
  XML prompt; previously a session id containing `<`, `&`, or quotes
  could inject XML into the provider input.
- ServerJobQueue: route both worker.on('stalled') and the QueueEvents
  'stalled' subscriber through a single notifyStalled helper that
  dedupes by jobId for 30s, so counters.stalled increments once per
  stall. QueueEvents 'error' now routes through notifyQueueError so
  it increments counters.errored and runs onError listeners — keeping
  observability symmetric across both sources.
- ServerV1PostgresRoutes: convert PostgresObservationRepository from
  three dynamic imports to a single static import for consistency.
- mcp-server / ServerBetaClient: actually forward the
  observation_record_event tool's `generate` flag through to the
  /v1/events endpoint as `?generate=false` instead of voiding it.
- server-sessions.markGenerationFailed: guard jsonb_set against a null
  error payload so the failure path can't null out metadata before the
  generation_status='failed' write commits.

Minor fixes
- server-sessions.endSession: keep updated_at stable on repeated calls
  so the documented idempotency contract holds.
- SettingsDefaultsManager + ServerBetaService.getServerBetaPort: derive
  the server-beta default port from UID (37877 + uid%100), matching the
  worker port pattern, so two users on the same host don't collide.
  Docker stacks always pass CLAUDE_MEM_SERVER_PORT explicitly so the
  containerized deployment is unaffected.
- server-session-runtime test: close the pg.Pool in afterAll.
- server-beta-release-readiness.md: escape pipes inside table inline
  code, add `text` language tag to the fenced log block.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): address Greptile + CodeRabbit third review on PR #2383

P1 fixes
- SessionsObservationsAdapter.resolveServerSession: catch unique-violation
  (23505) on concurrent compat inserts and re-fetch instead of returning
  500. Two compat callers carrying the same contentSessionId can both
  observe `existing===null` and race on the (project_id,
  external_session_id) unique constraint; the second now resolves to the
  raced row instead of dropping the event.
- /v1/events/batch: pass `sourceAdapter: null` to ingestBatch so each
  event's BullMQ payload (and persisted outbox payload column) reflects
  its own event.sourceAdapter via buildEventBullmqPayload's fallback,
  rather than stamping the whole batch with the first event's adapter.

Minor
- server-session-runtime test afterEach: wrap DROP SCHEMA in try/finally
  so client.release() always runs even if the drop throws.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(test): drop `pool as never` cast — pg.Pool already matches PostgresPool

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): retry of completed job now 409s instead of duplicating

retryGenerationJob previously fell through to the reset+re-enqueue path
when called on a job in `completed` status. The observations index
dedupes on (generation_job_id, parsed_observation_index, content) but
LLM output is non-deterministic, so a second provider run almost always
produced a different content string and bypassed the index, persisting a
parallel set of observation rows attributed to the same generation job.

Match cancelGenerationJob's 409 guard for completed jobs. failed and
cancelled remain valid retry targets.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build(server-beta): rebuild bundles after rebase onto main

Regenerates the three plugin bundles so they reflect the rebased source
state. Mechanical rebuild output only — no source changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): wrap resolveServerSession in try/catch for structured error response

Greptile P1 on PR #2383: resolveServerSession was called before the try/catch
in both compat adapters, so Postgres errors during session lookup (timeout,
pool exhaustion, etc.) escaped to Express's default error handler and returned
HTML/text 500s. Legacy clients calling response.json() would get a parse
failure instead of the documented { stored: false, reason: 'internal_error' }
(or { status: 'error', reason: 'internal_error' } for the summarize adapter)
shape.

Move the resolveServerSession call inside the existing try block in both
adapters so any failure flows through the structured catch handler.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(server-beta): catch 23505 unique violation in POST /v1/sessions/start

Greptile P1 on PR #2383: concurrent requests with the same externalSessionId
can both pass the findByExternalIdForScope check, both call repo.create,
and the loser hits the (project_id, external_session_id) unique constraint.
The handler treated that as an unknown error and returned a 500.

Apply the same pattern resolveServerSession already uses: catch error.code
'23505' when externalSessionId is set, refetch the row inserted by the
winning request, and return 200 with that session.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 00:26:11 -07:00

540 lines
19 KiB
TypeScript

// SPDX-License-Identifier: Apache-2.0
import { parseAgentXml, type ParsedObservation, type ParsedSummary } from '../../sdk/parser.js';
import { logger } from '../../utils/logger.js';
import {
PostgresObservationRepository,
PostgresObservationSourcesRepository,
buildObservationGenerationKey,
type PostgresObservation,
} from '../../storage/postgres/observations.js';
import {
PostgresObservationGenerationJobEventsRepository,
PostgresObservationGenerationJobRepository,
type PostgresObservationGenerationJob,
} from '../../storage/postgres/generation-jobs.js';
import { PostgresAuthRepository } from '../../storage/postgres/auth.js';
import {
withPostgresTransaction,
type PostgresPool,
} from '../../storage/postgres/pool.js';
import { stripTags } from '../../utils/tag-stripping.js';
// processGeneratedResponse owns the full "we got XML from a provider →
// persist + link + advance outbox" pipeline. Every side-effect runs inside
// a single Postgres transaction so retries are idempotent:
//
// - observations.generation_key (UNIQUE per team/project) collapses retry
// duplicates to a single row.
// - observation_sources (UNIQUE on observation_id, source_type, source_id)
// collapses duplicate source links.
// - observation_generation_jobs.transitionStatus is the lifecycle gate.
//
// The function NEVER touches worker SessionStore tables, NEVER assumes a
// Claude Code transcript shape, and ALWAYS reloads the job before mutating.
// BullMQ payload data is advisory; the outbox row is canonical.
export type ProcessGeneratedResponseOutcome =
| {
kind: 'completed';
jobId: string;
observations: PostgresObservation[];
privateContentDetected: boolean;
}
| { kind: 'parse_error'; jobId: string; reason: string };
export interface ProcessGeneratedResponseInput {
pool: PostgresPool;
job: PostgresObservationGenerationJob;
rawText: string;
modelId?: string;
providerLabel: string;
workerId?: string;
// Phase 11 — identity context propagated from the BullMQ payload (and
// ultimately the API-key that ingested the source row). Persisted on
// observation_sources.metadata for traceability and re-emitted in the
// observation.created audit row.
apiKeyId?: string | null;
actorId?: string | null;
sourceAdapter?: string | null;
}
export async function processGeneratedResponse(
input: ProcessGeneratedResponseInput,
): Promise<ProcessGeneratedResponseOutcome> {
const { job, rawText } = input;
const parsed = parseAgentXml(rawText, job.id);
if (!parsed.valid) {
return { kind: 'parse_error', jobId: job.id, reason: 'parser rejected response' };
}
// Skip-summary or zero-observation responses are still a success — the
// provider explicitly decided there's nothing worth recording (e.g.
// privacy-stripped batch). Mark the job completed with no observations.
const observationsToWrite = parsed.observations ?? [];
const skipped = parsed.summary?.skipped === true;
const privateContentDetected = skipped || observationsToWrite.length === 0;
return await withPostgresTransaction(input.pool, async (client) => {
const obsRepo = new PostgresObservationRepository(client);
const sourcesRepo = new PostgresObservationSourcesRepository(client);
const jobsRepo = new PostgresObservationGenerationJobRepository(client);
const eventsLogRepo = new PostgresObservationGenerationJobEventsRepository(client);
const auditRepo = new PostgresAuthRepository(client);
// Reload the job inside the transaction. If it was already completed
// by another worker, return its existing observations idempotently.
const fresh = await jobsRepo.getByIdForScope({
id: job.id,
projectId: job.projectId,
teamId: job.teamId,
});
if (!fresh) {
throw new Error(`generation job ${job.id} not found in scope`);
}
if (fresh.status === 'completed' || fresh.status === 'cancelled' || fresh.status === 'failed') {
logger.info('SYSTEM', 'generation job already in terminal status; skipping persistence', {
jobId: fresh.id,
status: fresh.status,
});
return {
kind: 'completed' as const,
jobId: fresh.id,
observations: [],
privateContentDetected,
};
}
const persisted: PostgresObservation[] = [];
for (let index = 0; index < observationsToWrite.length; index++) {
const parsedObservation = observationsToWrite[index]!;
const content = renderObservationContent(parsedObservation);
if (!content || content.trim().length === 0) {
continue;
}
// Defense-in-depth: even if the parser slipped a private-tagged
// string through, scrub before persisting.
const scrubbed = stripTags(content);
if (!scrubbed.stripped || scrubbed.stripped.trim().length === 0) {
continue;
}
const generationKey = buildObservationGenerationKey({
generationJobId: fresh.id,
parsedObservationIndex: index,
content: scrubbed.stripped,
});
const observation = await obsRepo.create({
projectId: fresh.projectId,
teamId: fresh.teamId,
serverSessionId: fresh.serverSessionId,
kind: parsedObservation.type ?? 'observation',
content: scrubbed.stripped,
generationKey,
metadata: {
title: parsedObservation.title,
subtitle: parsedObservation.subtitle,
facts: parsedObservation.facts,
narrative: parsedObservation.narrative,
concepts: parsedObservation.concepts,
files_read: parsedObservation.files_read,
files_modified: parsedObservation.files_modified,
provider: input.providerLabel,
model: input.modelId ?? null,
},
createdByJobId: fresh.id,
});
persisted.push(observation);
await sourcesRepo.addSource({
observationId: observation.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
sourceType: fresh.sourceType,
sourceId: fresh.sourceId,
agentEventId: fresh.agentEventId ?? null,
generationJobId: fresh.id,
metadata: {
provider: input.providerLabel,
parsedObservationIndex: index,
// Phase 11 — denormalize identity context for traceability so an
// operator can answer "which api key produced this observation?"
// without joining back through generation_job → outbox → key.
source_adapter: input.sourceAdapter ?? null,
actor_id: input.actorId ?? null,
api_key_id: input.apiKeyId ?? null,
},
});
// Phase 11 — audit each generated observation. Using the SAME
// generation_job_id reference so the audit chain (event_received →
// generation_job.queued → generation_job.processing → observation.
// created → observation.read) can be reconstructed.
try {
await auditRepo.createAuditLog({
teamId: fresh.teamId,
projectId: fresh.projectId,
actorId: input.actorId ?? null,
apiKeyId: input.apiKeyId ?? null,
action: 'observation.created',
resourceType: 'observation',
resourceId: observation.id,
details: {
generationJobId: fresh.id,
sourceType: fresh.sourceType,
sourceId: fresh.sourceId,
provider: input.providerLabel,
model: input.modelId ?? null,
sourceAdapter: input.sourceAdapter ?? null,
parsedObservationIndex: index,
},
});
} catch (auditError) {
logger.warn('SYSTEM', 'audit_log observation.created insert failed', {
observationId: observation.id,
error: auditError instanceof Error ? auditError.message : String(auditError),
});
}
}
// Advance outbox status. Phase 1 transitionStatus enforces legal
// transitions and tenant scope inside its WHERE clause.
await jobsRepo.transitionStatus({
id: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
status: 'completed',
});
await eventsLogRepo.append({
generationJobId: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
eventType: 'completed',
statusAfter: 'completed',
attempt: fresh.attempts,
details: {
provider: input.providerLabel,
model: input.modelId ?? null,
observationCount: persisted.length,
privateContentDetected,
workerId: input.workerId ?? null,
},
});
// Audit log — best-effort; failure here would already be inside the
// transaction so any insert error rolls everything back. We accept
// that to keep the pipeline observable end-to-end.
try {
await auditRepo.createAuditLog({
teamId: fresh.teamId,
projectId: fresh.projectId,
actorId: input.actorId ?? null,
apiKeyId: input.apiKeyId ?? null,
action: 'generation_job.completed',
resourceType: 'observation_generation_job',
resourceId: fresh.id,
details: {
generationJobId: fresh.id,
provider: input.providerLabel,
model: input.modelId ?? null,
observationCount: persisted.length,
observationIds: persisted.map(o => o.id),
sourceAdapter: input.sourceAdapter ?? null,
},
});
} catch (auditError) {
// The audit log table may not have a metadata column on older
// schemas; swallow rather than failing generation.
logger.warn('SYSTEM', 'audit log insert failed during generation', {
jobId: fresh.id,
error: auditError instanceof Error ? auditError.message : String(auditError),
});
}
return {
kind: 'completed' as const,
jobId: fresh.id,
observations: persisted,
privateContentDetected,
};
});
}
export interface MarkGenerationFailedInput {
pool: PostgresPool;
job: PostgresObservationGenerationJob;
reason: string;
classification?: string;
retryable: boolean;
workerId?: string;
}
/**
* Move a generation job to a non-success terminal state. Used when the
* provider returned an error or invalid XML. Retryable failures move the
* job back to `queued` so reconciliation can re-enqueue; non-retryable
* failures move to `failed`.
*/
export async function markGenerationFailed(input: MarkGenerationFailedInput): Promise<void> {
await withPostgresTransaction(input.pool, async (client) => {
const jobsRepo = new PostgresObservationGenerationJobRepository(client);
const eventsLogRepo = new PostgresObservationGenerationJobEventsRepository(client);
const fresh = await jobsRepo.getByIdForScope({
id: input.job.id,
projectId: input.job.projectId,
teamId: input.job.teamId,
});
if (!fresh || fresh.status === 'completed' || fresh.status === 'cancelled') {
return;
}
const canRetry = input.retryable && fresh.attempts < fresh.maxAttempts;
const target = canRetry ? 'queued' : 'failed';
await jobsRepo.transitionStatus({
id: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
status: target,
lastError: { reason: input.reason, classification: input.classification ?? null },
...(canRetry ? { nextAttemptAt: new Date(Date.now() + retryDelayMs(fresh.attempts)) } : {}),
});
await eventsLogRepo.append({
generationJobId: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
eventType: canRetry ? 'retry_scheduled' : 'failed',
statusAfter: target,
attempt: fresh.attempts,
details: {
reason: input.reason,
classification: input.classification ?? null,
workerId: input.workerId ?? null,
},
});
});
}
/**
* Persist a parsed session summary as an observations row with kind='summary'.
*
* Wraps the same outbox transition / source-link / audit pipeline as
* processGeneratedResponse but emits a single 'summary'-kind observation
* derived from the summary fields. Idempotency is enforced through the same
* `observations.generation_key` UNIQUE index — re-running the summary job
* after a restart will collapse to one row.
*/
export async function processSessionSummaryResponse(
input: ProcessGeneratedResponseInput,
): Promise<ProcessGeneratedResponseOutcome> {
const { job, rawText } = input;
if (job.sourceType !== 'session_summary') {
return { kind: 'parse_error', jobId: job.id, reason: 'session summary processor invoked on non-summary job' };
}
const parsed = parseAgentXml(rawText, job.id);
if (!parsed.valid) {
return { kind: 'parse_error', jobId: job.id, reason: 'parser rejected summary response' };
}
const summary = parsed.summary ?? null;
const skipped = summary?.skipped === true;
const summaryContent = summary ? renderSummaryContent(summary) : '';
const privateContentDetected = skipped || summaryContent.trim().length === 0;
return await withPostgresTransaction(input.pool, async (client) => {
const obsRepo = new PostgresObservationRepository(client);
const sourcesRepo = new PostgresObservationSourcesRepository(client);
const jobsRepo = new PostgresObservationGenerationJobRepository(client);
const eventsLogRepo = new PostgresObservationGenerationJobEventsRepository(client);
const auditRepo = new PostgresAuthRepository(client);
const fresh = await jobsRepo.getByIdForScope({
id: job.id,
projectId: job.projectId,
teamId: job.teamId,
});
if (!fresh) {
throw new Error(`session summary generation job ${job.id} not found in scope`);
}
if (fresh.status === 'completed' || fresh.status === 'cancelled' || fresh.status === 'failed') {
logger.info('SYSTEM', 'session summary job already in terminal status; skipping persistence', {
jobId: fresh.id,
status: fresh.status,
});
return {
kind: 'completed' as const,
jobId: fresh.id,
observations: [],
privateContentDetected,
};
}
const persisted: PostgresObservation[] = [];
if (!privateContentDetected) {
const scrubbed = stripTags(summaryContent);
const scrubbedContent = scrubbed.stripped ?? '';
if (scrubbedContent.trim().length > 0) {
const generationKey = buildObservationGenerationKey({
generationJobId: fresh.id,
parsedObservationIndex: 0,
content: scrubbedContent,
});
const observation = await obsRepo.create({
projectId: fresh.projectId,
teamId: fresh.teamId,
serverSessionId: fresh.serverSessionId,
kind: 'summary',
content: scrubbedContent,
generationKey,
metadata: {
request: summary?.request ?? null,
investigated: summary?.investigated ?? null,
learned: summary?.learned ?? null,
completed: summary?.completed ?? null,
next_steps: summary?.next_steps ?? null,
notes: summary?.notes ?? null,
provider: input.providerLabel,
model: input.modelId ?? null,
},
createdByJobId: fresh.id,
});
persisted.push(observation);
await sourcesRepo.addSource({
observationId: observation.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
sourceType: 'session_summary',
sourceId: fresh.sourceId,
generationJobId: fresh.id,
metadata: {
provider: input.providerLabel,
parsedObservationIndex: 0,
source_adapter: input.sourceAdapter ?? null,
actor_id: input.actorId ?? null,
api_key_id: input.apiKeyId ?? null,
},
});
// Phase 11 — observation.created audit for the summary observation.
try {
await auditRepo.createAuditLog({
teamId: fresh.teamId,
projectId: fresh.projectId,
actorId: input.actorId ?? null,
apiKeyId: input.apiKeyId ?? null,
action: 'observation.created',
resourceType: 'observation',
resourceId: observation.id,
details: {
generationJobId: fresh.id,
sourceType: 'session_summary',
sourceId: fresh.sourceId,
provider: input.providerLabel,
model: input.modelId ?? null,
sourceAdapter: input.sourceAdapter ?? null,
kind: 'summary',
},
});
} catch (auditError) {
logger.warn('SYSTEM', 'audit_log observation.created (summary) insert failed', {
observationId: observation.id,
error: auditError instanceof Error ? auditError.message : String(auditError),
});
}
}
}
await jobsRepo.transitionStatus({
id: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
status: 'completed',
});
await eventsLogRepo.append({
generationJobId: fresh.id,
projectId: fresh.projectId,
teamId: fresh.teamId,
eventType: 'completed',
statusAfter: 'completed',
attempt: fresh.attempts,
details: {
provider: input.providerLabel,
model: input.modelId ?? null,
observationCount: persisted.length,
privateContentDetected,
workerId: input.workerId ?? null,
sourceType: 'session_summary',
},
});
try {
await auditRepo.createAuditLog({
teamId: fresh.teamId,
projectId: fresh.projectId,
actorId: input.actorId ?? null,
apiKeyId: input.apiKeyId ?? null,
action: 'generation_job.completed',
resourceType: 'observation_generation_job',
resourceId: fresh.id,
details: {
generationJobId: fresh.id,
provider: input.providerLabel,
model: input.modelId ?? null,
observationCount: persisted.length,
observationIds: persisted.map(o => o.id),
sourceAdapter: input.sourceAdapter ?? null,
sourceType: 'session_summary',
},
});
} catch (auditError) {
logger.warn('SYSTEM', 'audit log insert failed during summary generation', {
jobId: fresh.id,
error: auditError instanceof Error ? auditError.message : String(auditError),
});
}
return {
kind: 'completed' as const,
jobId: fresh.id,
observations: persisted,
privateContentDetected,
};
});
}
function renderSummaryContent(summary: ParsedSummary): string {
const parts: string[] = [];
if (summary.request) parts.push(`Request: ${summary.request}`);
if (summary.investigated) parts.push(`Investigated: ${summary.investigated}`);
if (summary.learned) parts.push(`Learned: ${summary.learned}`);
if (summary.completed) parts.push(`Completed: ${summary.completed}`);
if (summary.next_steps) parts.push(`Next steps: ${summary.next_steps}`);
if (summary.notes) parts.push(`Notes: ${summary.notes}`);
return parts.join('\n\n').trim();
}
function renderObservationContent(observation: ParsedObservation): string {
const parts: string[] = [];
if (observation.title) parts.push(observation.title);
if (observation.subtitle) parts.push(observation.subtitle);
if (observation.narrative) parts.push(observation.narrative);
if (observation.facts && observation.facts.length > 0) {
parts.push(observation.facts.map(f => `- ${f}`).join('\n'));
}
return parts.join('\n\n').trim();
}
function retryDelayMs(attempts: number): number {
// Exponential backoff: 5s, 25s, 125s, capped at 10 minutes.
const base = 5000 * Math.pow(5, Math.max(0, attempts));
return Math.min(base, 10 * 60 * 1000);
}