Package-facing patch bump so 13.24.17 ships #4026/#3575 (health probe deadline cap), #3445 (desktop-bundled Codex CLI on macOS), and #4027 (register memory_session_id, do not re-register). Rebuilds plugin bundles so the injected version matches.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Package-facing patch bump so 13.24.15 ships #3727 / #3706 (daemon no longer inherits user project cwd). Rebuilds plugin bundles so the injected version matches.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Package-facing patch bump so 13.24.14 ships the commits now on main after v13.24.13. Rebuilds plugin bundles so the injected version matches.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Package-facing patch bump so 13.24.13 ships the commits now on main after v13.24.12. Rebuilds plugin bundles so the injected version matches.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Package-facing security patch for the #3861 / #3985 credential-leak fixes
(unauthenticated /api/settings redaction, MCP workspace containment, host
bind tightening). Publish-ready; do not npm publish from this PR.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Quota cooldown is an intentional pause, not a failure, so observer-health
stayed green and the session-start banner stayed silent while the worker
queued work. Mirror the breaker into observer-health.json and show a
pause notice on the existing health/banner path without changing
queue-accept or drain-on-clear.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
Raw tool I/O had no durable home. `pending_messages` is the generation
queue -- rows are claimed, summarized, and deleted -- so once an
observation existed the original tool_input/tool_response were gone.
Adds `tool_uses` (schema v51) as a by-reference side index for those
bodies, written from the one ingest choke point both the PostToolUse hook
route and the transcript-watch processor already share. The JSONL
transcripts and `src/services/transcripts/*` remain the spine and are
untouched.
Schema (Receipt freeze 2026-09-06): UNIQUE(content_session_id,
tool_use_id), nullable `or_generation_id` / `or_session_id` as join keys
back to an OpenRouter spend line, and deliberately no cost_usd/micros --
this table carries tool identity, dollars stay on the OR stamp. No FK on
session_db_id/observation_id: a FK there can abort the constructor
migration chain (#3378), and observation_id is linked late by design.
Write path dual-writes alongside -- never instead of -- the
pending_messages enqueue, and swallows its own failures so an observation
is never lost to a backup-index error. `toolUseId` now actually reaches
the worker from hooks: it was missing from NormalizedHookInput and every
hook adapter, so only the transcript path supplied it. ResponseProcessor
links the batch's claimed ids to the first stored observation.
Read path is progressive-disclosure layer 4: POST /api/tool-uses/batch
requires explicit ids (never a full-table scan), GET /api/tool-uses
returns a cheap index shape with size hints and never the payloads, and
the `get_tool_uses` MCP tool is described as a last resort. claude-mem's
own read tools are skipped by the writer -- without that, every call to
get_tool_uses would store the bodies it just returned.
Payloads are stored in-row with a 64 KB soft cap and a UTF-8-safe
truncation marker; content_hash is computed over the original.
Join contract for Receipt: RECEIPT-JOIN.md
Claude-Session: https://claude.ai/code/session_01QgdJ6gExgBirDoAxknt94m
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Patch release so marketplace and npm installs actually pick up the rebuilt
plugin bundles from #3878. 13.24.0 shipped manifests that claimed 13.24.0
while plugin/scripts/*.cjs still carried 13.23.1 bytes; the artifacts were
corrected in place, but existing 13.24.0 installs have no version change to
trigger an upgrade. 13.24.1 gives them one.
Version bumped across all 11 manifests and the README badge, then
regenerated via `npm run build-and-sync`. All four .cjs bundles are
byte-identical to 13.24.0 after normalizing the version string -- no source
changed since 4da9ffc6, so this is a pure version delta.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fu9bpdG4AWZNq3m8zkUkYg
* fix: rebuild plugin bundles so committed artifacts match manifest 13.24.0
The 13.24.0 release commit (85ccd626) bumped the manifests and CHANGELOG
but never re-ran the build, so plugin/scripts/*.cjs kept the 13.23.1 bytes
last produced by 89ca057a. The Claude Code marketplace installs straight
from this repo (.claude-plugin/marketplace.json -> "source": "./plugin"),
so every marketplace user on 13.24.0 has been executing 13.23.1 code.
ensureWorkerRunning() compares the resolved plugin version (13.24.0, taken
from the plugin cache directory name) against the worker's baked-in
__DEFAULT_PACKAGE_VERSION__ (13.23.1, reported by /api/health). The
mismatch SIGKILLs the worker and respawns the same stale file on every
hook event, with no state that survives the hook process to bound it --
an unbounded kill/respawn loop that takes the in-flight observer
generator down with it, so no observations get written.
This is a genuine `npm run build`, not a version-string patch. The
bundles were stale in code, not merely in the constant: src/ moved 704
insertions across 12 files since 13.23.1, including the observer's
<skip_summary reason="noise" /> protocol change, the new manual-session
module, and the platform_source plumbing in SessionStore and MemoryRoutes.
No version bump: the manifests were already correct at 13.24.0. It is the
artifacts that were wrong.
Fixes#3857
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Bshprs1vjut2XmaGTRESqX
* fix(tests): restore module mocks so worker-spawner stubs stop leaking
bun runs the whole suite in one process and mock.module is process-global
and sticky, so stubs installed by one test file stay installed for every
file loaded after it.
tests/services/worker-spawner.test.ts mocked
src/services/infrastructure/{ProcessManager,HealthMonitor}.js and never
restored them. tests/infrastructure/{health-monitor,process-manager}.test.ts
import the same symbols through the src/services/infrastructure/index.js
barrel, so they silently exercised those stubs instead of the real code:
isPortInUse returned false without touching net.createServer, waitForHealth
returned false without fetching, getPlatformTimeout skipped the Windows
doubling, cleanStalePidFile always reported 'dead', and spawnDaemon never
returned undefined. waitForPortFree stayed real but resolved through the
stubbed isPortInUse binding, inverting its timeout case.
This is order-dependent, not new: bun walks test files in filesystem order,
and a fresh CI checkout loads worker-spawner (59) well before health-monitor
(169) and process-manager (172), while many local checkouts load
tests/infrastructure first and pass. That ordering is what surfaced 19
failures in Actions run 33939805959.
Snapshot the real namespaces eagerly, before the mock.module calls, and
reinstall them in afterAll. The snapshot must be eager: `import * as x`
yields a live namespace object that bun re-points when the module is mocked,
so spreading it inside afterAll copies the stubs back in. That is exactly
the latent bug in tests/cli/handlers/context-session-start.test.ts, whose
restore was re-installing its own hook-settings, oauth-token, project-name
and worker-utils stubs; fixed here the same way.
Tests only. No source, plugin bundle, or version changes — the committed
artifacts still match manifest 13.24.0.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LcjsK6QqeBcYXbJ8gqBsea
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
The gateway fallback said "allow one normal gateway request as a probe", but
nothing made it one. shouldUseCmemFallback is a subtraction and a less-than,
and ensureGeneratorRunning gates per session, so 28-69 live sessions are 28-69
independent callers.
It is worse than the in-memory case. The marker lives on disk
(CLAUDE_MEM_PRO_FALLBACK_AT in settings.json, loaded uncached), so every
process parses the same ISO string and computes the same expiry instant -- the
herd was handed a shared clock to synchronize on. Each member's failure then
does a read-modify-write of the user's whole settings.json to re-arm the
marker; the write is atomic but the sequence is not, so concurrent settings
edits can be clobbered.
The re-probe is now claimed through the breaker's existing machinery under a
DISTINCT key, 'cmem-gateway'. Distinct because tryAdmitQuotaProbe takes the
cooldown per call: this path's 15 minutes against the provider breaker's 30
would otherwise let two callers reach contradictory answers about whether the
same breaker is armed, and provider switches (which this branch makes routine)
make the collision reachable in both directions -- a fresh funded key born into
an armed breaker and withheld for a refusal it never earned.
getSelectedProvider stays read-only for diagnostics and status; only the new
selectProviderForGenerator claims. Every path out of ensureGeneratorRunning
that does not actually send releases the claim, including the one where a
generator is already running, so a claim cannot outlive the call that took it.
Also regenerates the plugin bundles rather than hand-merging them, which is
what the five .cjs conflicts in this consolidation always needed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AWmJDjFM6BNmGaLJ7Xbrsy
The five Windows branches each carried their own build of
plugin/scripts/*.cjs; merging them conflicted on those artifacts. Rebuilt
once from the merged src/ so the shipped scripts contain all five fixes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WVK8iVC2dnrqE1fV4ogp2a
* docs: add observer error-path implementation plan
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BPptieMC1vzUNGtUErU3UM
* fix(worker): carry the gateway error envelope, stop retrying quota errors, log once
The OpenRouter classifier discarded the upstream body (which contains the
remedy — e.g. "Key limit exceeded … Manage it using <url>"), treated 402 as
unrecoverable, never used the request id it was handed, and each failure
fanned out to five log lines plus two pointless retries.
- provider-errors.ts: ClassifiedProviderError gains optional code/action/url/
requestId; describeProviderError() is the single renderer
(message — action url (req id)).
- OpenRouterProvider.ts: classifyOpenRouterError parses the cmem.ai gateway
envelope {code,message,action,url,request_id} first (six taxonomy codes →
worker kinds), otherwise legacy classification now includes the upstream
body in every message, maps 402 and "key limit exceeded"/"limit exceeded"/
"negative credit" bodies to quota_exhausted (bare "limit exceeded" excluded
on 429 so real rate limits stay retryable), and sets requestId. The
200-with-error path now forwards bodyText + requestId.
- error-classification.ts (server mirror): same marker list, no imports.
- Log once: init/message-loop/handleSessionError log at debug for classified
errors; SessionRoutes emits one "Observer failed" error line with kind/code/
requestId and the rendered message string (no errorSink re-fire).
- Tests: envelope + legacy cases assert message/code/action/url/requestId;
new retry-policy.test.ts pins isRetryableKind; server mirror pinned.
Plan: plans/2026-08-16-observer-error-path.md (Phase 2)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BPptieMC1vzUNGtUErU3UM
* feat(worker): observer-health ledger and session-start warning carry the structured error
Users don't read worker logs; they open Claude Code. The session-start
health warning from #3538 said "check ~/.claude-mem/settings.json", which is
wrong for a Pro user whose allowance is exhausted.
- observer-health.ts: ObserverHealthState gains lastErrorCode/Action/Url/
RequestId (null by default; old ledgers read back unchanged);
recordObserverFailure accepts string | ObserverFailureDetail — objects
populate the new fields (message/action scrubbed, url/requestId as-is);
renderObserverHealthWarning emits "What to do:", "Link:", "Request id:"
and drops the generic settings.json remedy when an action exists.
scrubErrorMessage also masks cm_pro_ tokens.
- SessionRoutes.ts: classified errors record {message, code, action, url,
requestId} in the ledger — the same words as the "Observer failed" log line.
- tests/observer-health.test.ts: round-trip, backward compat, render with/
without action, scrub.
Plan: plans/2026-08-16-observer-error-path.md (Phase 3)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BPptieMC1vzUNGtUErU3UM
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat(worker): surface observer outages at session start via observer-health ledger
Generator failures now record to a file-backed ledger
(~/.claude-mem/observer-health.json); successful observation stores reset
it. Session-start context injection prepends a loud outage warning (with
the provider's last error, which often embeds the remedy URL) once 3+
consecutive failures are newer than the last success — including on the
empty-state and missing-DB paths. Prevents a repeat of the silent
17-hour 2026-08-09 provider-quota outage.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(observer-health): lock the ledger, widen credential redaction, plain-language warning
Greptile P1s on #3538:
- Credential redaction leaked provider secrets into injected context.
scrubErrorMessage only caught `sk-…` and `Bearer …`, so `api_key=…`,
JSON `"apiKey": "…"`, `Authorization: Basic …` and query-string secrets
were persisted in observer-health.json and rendered verbatim at session
start. Redaction now covers the common key/value, JSON, authorization and
query-string shapes, skips purely numeric values so `max_tokens: 200000`
style diagnostics survive, and runs again at render time so a ledger
written by an older build cannot leak.
- Concurrent failure writes could suppress the outage warning. The ledger's
read-modify-write was unlocked, so simultaneous writers overwrote each
other's increments and consecutiveFailures stayed under the threshold.
Serialized with a `wx` lockfile (same idiom as worker-spawn-gate.ts),
stale-breaking at 5s and failing open after a 2s wait — a racy count beats
no count. Regression test drives three synchronized writer processes and
requires the threshold to be reached; it fails ~2 in 3 runs without the lock.
Also rewrites the warning for humans (it is read by the user, not just the
agent) with a describeDuration helper, and rebuilds the plugin artifacts —
the committed context-generator.cjs was stale and shipped without the
observer-health injection.
* test(worker): restore the real ModeManager after session-manager-project mocks it
bun's mock.module is process-global and mock.restore() does not undo it, so
this file's partial ModeManager stub (no class prototype, no loadMode) leaked
into every later test file in the run. When readdir order put it before
tests/server/server-boot.test.ts and the server-runtime smoke, loadServerMode()
hit `modeManager.loadMode is not a function` and CI went red — which is exactly
what happened on this PR while main stayed green.
Applies the snapshot + afterAll re-register pattern already used in
agent-formatter, SearchManager.timeline-anchor, and response-processor tests;
session-manager-project was the last ModeManager mock without it.
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Alex Newman