The skill previously listed 3 manifest paths and omitted `npm publish`
entirely, which meant `npx claude-mem@X.Y.Z` only resolved when someone
ran publish out-of-band. Now the skill:
- Enumerates all 6 version-bearing files (package.json, plugin/package.json,
.claude-plugin/marketplace.json, .claude-plugin/plugin.json,
plugin/.claude-plugin/plugin.json, .codex-plugin/plugin.json).
- Adds an explicit `npm publish` step with `npm view claude-mem@X.Y.Z version`
verification so the npx-distributed version is the one users actually pin.
- Documents `npm run release:patch|minor|major` (np helper) as an alternative.
- Adds `git grep` pre-flight so new manifests are discovered automatically.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: security observation types + Telegram notifier
Adds two severity-axis security observation types (security_alert, security_note)
to the code mode and a fire-and-forget Telegram notifier that posts when a saved
observation matches configured type or concept triggers. Default trigger fires on
security_alert only; notifier is disabled until BOT_TOKEN and CHAT_ID are set.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(telegram): honor CLAUDE_MEM_TELEGRAM_ENABLED master toggle
Adds an explicit on/off flag (default 'true') so users can disable the
notifier without clearing credentials.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* perf(stop-hook): make summarize handler fire-and-forget
Stop hook previously blocked the Claude Code session for up to 110
seconds while polling the worker for summary completion. The handler
now returns as soon as the enqueue POST is acked.
- summarize.ts: drop the 500ms polling loop and /api/sessions/complete
call; tighten SUMMARIZE_TIMEOUT_MS from 300s to 5s since the worker
acks the enqueue synchronously.
- SessionCompletionHandler: extract idempotent finalizeSession() for
DB mark + orphaned-pending-queue drain + broadcast. completeByDbId
now delegates so the /api/sessions/complete HTTP route is backward
compatible.
- SessionRoutes: wire finalizeSession into the SDK-agent generator's
finally block, gated on lastSummaryStored + empty pending queue so
only Stop events produce finalize (not every idle tick).
- WorkerService: own the single SessionCompletionHandler instance and
inject it into SessionRoutes to avoid duplicate construction.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(pr2084): address reviewer findings
CodeRabbit:
- SessionStore.getSessionById now returns status; without it, the
finalizeSession idempotency guard always evaluated false and
re-fired drain/broadcast on every call.
- worker-service.ts: three call sites that remove the in-memory session
after finalizeSession now do so only on success. On failure the
session is left in place so the 60s orphan reaper can retry; removing
it would orphan an 'active' DB row indefinitely under the fire-and-
forget Stop hook.
- runFallbackForTerminatedSession no longer emits a second
session_completed event; finalizeSession already broadcasts one.
The explicit broadcast now runs only on the finalize-failure fallback.
Greptile:
- TelegramNotifier reads via loadFromFile(USER_SETTINGS_PATH) so values
in ~/.claude-mem/settings.json actually take effect; SettingsDefaultsManager.get()
alone skipped the file and silently ignored user-configured credentials.
- Emoji is derived from obs.type (security_alert → 🚨, security_note → 🔐,
fallback 🔔) instead of hardcoded 🚨 for every observation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(hooks): worker-port mismatch on Windows and settings.json overrides (#2086)
Hooks computed the health-check port as \$((37700 + id -u % 100)),
ignoring ~/.claude-mem/settings.json. Two failure modes resulted:
1. Users upgrading from pre-per-uid builds kept CLAUDE_MEM_WORKER_PORT
set to '37777' in settings.json. The worker bound 37777 (settings
wins), but hooks queried 37701 (uid 501 on macOS), so every
SessionStart/UserPromptSubmit health check failed.
2. Windows Git Bash/PowerShell returns a real Windows UID for 'id -u'
(e.g. 209), producing port 37709 while the Node worker fell back
to 37777 (process.getuid?.() ?? 77). Every prompt hit the 60s hook
timeout.
hooks.json now resolves the port in this order, matching how the
worker itself resolves it:
1. sed CLAUDE_MEM_WORKER_PORT from ~/.claude-mem/settings.json
2. If absent, and uname is MINGW/CYGWIN/MSYS → 37777
3. Otherwise 37700 + (id -u || 77) % 100
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(pr2084): sync DatabaseManager.getSessionById return type
CodeRabbit round 2: the DatabaseManager.getSessionById return type
was missing platform_source, custom_title, and status fields that
SessionStore.getSessionById actually returns. Structural typing
hid the mismatch at compile time, but it prevents callers going
through DatabaseManager from seeing the status field that the
idempotency guard in SessionCompletionHandler relies on.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(pr2084): hooks honor env vars and host; looser port regex (#2086 followup)
CodeRabbit round 3: match the worker's env > file > defaults precedence
and resolve host the same way as port.
- Env: CLAUDE_MEM_WORKER_PORT and CLAUDE_MEM_WORKER_HOST win first.
- File: sed now accepts both quoted ('"37777"') and unquoted (37777)
JSON values for the port; a separate sed reads CLAUDE_MEM_WORKER_HOST.
- Defaults: port per-uid formula (Windows: 37777), host 127.0.0.1.
- Health-check URL uses the resolved $HOST instead of hardcoded localhost.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: detect PID reuse in worker start-guard to survive container restarts
The 'Worker already running' guard checked PID liveness with kill(0), which
false-positives when a persistent PID file outlives the PID namespace (docker
stop / docker start, pm2 graceful reloads). The new worker comes up with the
same low PID (e.g. 11) as the old one, kill(0) says 'alive', and the worker
refuses to start against its own prior incarnation.
Capture a process-start token alongside the PID and verify identity, not just
liveness:
- Linux: /proc/<pid>/stat field 22 (starttime, jiffies since boot)
- macOS/POSIX: `ps -p <pid> -o lstart=`
- Windows: unchanged (returns null, falls back to liveness)
PID files written by older versions are token-less, so verifyPidFileOwnership
falls back to the current liveness-only behavior for backwards compatibility.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor: apply review feedback to PID identity helpers
- Collapse ProcessManager re-export down to a single import/export statement.
- Make verifyPidFileOwnership a type predicate (info is PidInfo) so callers
don't need non-null assertions on the narrowed value.
- Drop the `!` assertions at the worker-service GUARD 1 call site now that
the predicate narrows.
- Tighten the captureProcessStartToken platform doc comment to enumerate
process.platform values explicitly.
No behavior change — esbuild output is byte-identical (type-only edits).
Addresses items 1-3 of the claude-review comment on PR #2082.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: pin LC_ALL=C for `ps lstart=` in captureProcessStartToken
Without a locale pin, `ps -o lstart=` emits month/weekday names in the
system locale. A bind-mounted PID file written under one locale and read
under another would hash to different tokens and the live worker would
incorrectly appear stale — reintroducing the very bug this helper exists
to prevent.
Flagged by Greptile on PR #2082.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor: address second-round review on PID identity helpers
- verifyPidFileOwnership: log a DEBUG diagnostic when the PID is alive but
the start-token mismatches. Without it, callers can't distinguish the
"process dead" path from the "PID reused" path in production logs — the
exact case this helper exists to catch.
- writePidFile: drop the redundant `?? undefined` coercion. `null` and
`undefined` are both falsy for the subsequent ternary, so the coercion
was purely cosmetic noise that suggested an important distinction.
- Add a unit test for the win32 fallback path in captureProcessStartToken
(mocks process.platform) — previously uncovered in CI.
Addresses items 1, 2, and 5 of the second claude-review on PR #2082.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: resolve search, database, and docker bugs (#1913, #1916, #1956, #1957, #2048)
- Fix concept/concepts param mismatch in SearchManager.normalizeParams (#1916)
- Add FTS5 keyword fallback when ChromaDB is unavailable (#1913, #2048)
- Add periodic WAL checkpoint and journal_size_limit to prevent unbounded WAL growth (#1956)
- Add periodic clearFailed() to purge stale pending_messages (#1957)
- Fix nounset-safe TTY_ARGS expansion in docker/claude-mem/run.sh
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: prevent silent data loss on non-XML responses, add queue info to /health (#1867, #1874)
- ResponseProcessor: mark messages as failed (with retry) instead of confirming
when the LLM returns non-XML garbage (auth errors, rate limits) (#1874)
- Health endpoint: include activeSessions count for queue liveness monitoring (#1867)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: cache isFts5Available() at construction time
Addresses Greptile review: avoid DDL probe (CREATE + DROP) on every text
query. Result is now cached in _fts5Available at construction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve worker stability bugs — pool deadlock, MCP loopback, restart guard (#1868, #1876, #2053)
- Replace flat consecutiveRestarts counter with time-windowed RestartGuard:
only counts restarts within 60s window (cap=10), decays after 5min of
success. Prevents stranding pending messages on long-running sessions. (#2053)
- Add idle session eviction to pool slot allocation: when all slots are full,
evict the idlest session (no pending work, oldest activity) to free a slot
for new requests, preventing 60s timeout deadlock. (#1868)
- Fix MCP loopback self-check: use process.execPath instead of bare 'node'
which fails on non-interactive PATH. Fix crash misclassification by removing
false "Generator exited unexpectedly" error log on normal completion. (#1876)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve hooks reliability bugs — summarize exit code, session-init health wait (#1896, #1901, #1903, #1907)
- Wrap summarize hook's workerHttpRequest in try/catch to prevent exit
code 2 (blocking error) on network failures or malformed responses.
Session exit no longer blocks on worker errors. (#1901)
- Add health-check wait loop to UserPromptSubmit session-init command in
hooks.json. On Linux/WSL where hook ordering fires UserPromptSubmit
before SessionStart, session-init now waits up to 10s for worker health
before proceeding. Also wrap session-init HTTP call in try/catch. (#1907)
- Close#1896 as already-fixed: mtime comparison at file-context.ts:255-267
bypasses truncation when file is newer than latest observation.
- Close#1903 as no-repro: hooks.json correctly declares all hook events.
Issue was Claude Code 12.0.1/macOS platform event-dispatch bug.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: security hardening — bearer auth, path validation, rate limits, per-user port (#1932, #1933, #1934, #1935, #1936)
- Add bearer token auth to all API endpoints: auto-generated 32-byte
token stored at ~/.claude-mem/worker-auth-token (mode 0600). All hook,
MCP, viewer, and OpenCode requests include Authorization header.
Health/readiness endpoints exempt for polling. (#1932, #1933)
- Add path traversal protection: watch.context.path validated against
project root and ~/.claude-mem/ before write. Rejects ../../../etc
style attacks. (#1934)
- Reduce JSON body limit from 50MB to 5MB. Add in-memory rate limiter
(300 req/min/IP) to prevent abuse. (#1935)
- Derive default worker port from UID (37700 + uid%100) to prevent
cross-user data leakage on multi-user macOS. Windows falls back to
37777. Shell hooks use same formula via id -u. (#1936)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve search project filtering and import Chroma sync (#1911, #1912, #1914, #1918)
- Fix per-type search endpoints to pass project filter to Chroma queries
and SQLite hydration. searchObservations/Sessions/UserPrompts now use
$or clause matching project + merged_into_project. (#1912)
- Fix timeline/search methods to pass project to Chroma anchor queries.
Prevents cross-project result leakage when project param omitted. (#1911)
- Sync imported observations to ChromaDB after FTS rebuild. Import
endpoint now calls chromaSync.syncObservation() for each imported
row, making them visible to MCP search(). (#1914)
- Fix session-init cwd fallback to match context.ts (process.cwd()).
Prevents project key mismatch that caused "no previous sessions"
on fresh sessions. (#1918)
- Fix sync-marketplace restart to include auth token and per-user port.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve all CodeRabbit and Greptile review comments on PR #2080
- Fix run.sh comment mismatch (no-op flag vs empty array)
- Gate session-init on health check success (prevent running when worker unreachable)
- Fix date_desc ordering ignored in FTS session search
- Age-scope failed message purge (1h retention) instead of clearing all
- Anchor RestartGuard decay to real successes (null init, not Date.now())
- Add recordSuccess() calls in ResponseProcessor and completion path
- Prevent caller headers from overriding bearer auth token
- Add lazy cleanup for rate limiter map to prevent unbounded growth
- Bound post-import Chroma sync with concurrency limit of 8
- Add doc_type:'observation' filter to Chroma queries feeding observation hydration
- Add FTS fallback to all specialized search handlers (observations, sessions, prompts, timeline)
- Add response.ok check and error handling in viewer saveSettings
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve CodeRabbit round-2 review comments
- Use failure timestamp (COALESCE) instead of created_at_epoch for stale purge
- Downgrade _fts5Available flag when FTS table creation fails
- Escape FTS5 MATCH input by quoting user queries as literal phrases
- Escape LIKE metacharacters (%, _, \) in prompt text search
- Add response.ok check in initial settings load (matches save flow)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve CodeRabbit round-3 review comments
- Include failed_at_epoch in COALESCE for age-scoped purge
- Re-throw FTS5 errors so callers can distinguish failure from no-results
- Wrap all FTS fallback calls in SearchManager with try/catch
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: remove bearer auth and platform_source from context inject
Bearer token auth (#1932/#1933) added friction for all localhost API
clients with no benefit — the worker already binds localhost-only (CORS
restriction + host binding). Removed auth-token module, requireAuth
middleware, and Authorization headers from all internal callers.
platform_source filtering from the /api/context/inject path was never
used by any caller and silently filtered out observations. The underlying
platform_source column stays; only the query-time filter and its plumbing
through ContextBuilder, ObservationCompiler, SearchRoutes, context.ts,
and transcripts/processor.ts are removed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: resolve CodeRabbit + Greptile + claude-review comments on PR #2081
- middleware.ts: drop 'Authorization' from CORS allowedHeaders (Greptile)
- middleware.ts: rate limiter falls back to req.socket.remoteAddress; add Retry-After on 429 (claude-review)
- SearchRoutes.ts: drop leftover platformSource read+pass in handleContextPreview (Greptile)
- .docker-blowout-data/: stop tracking the empty SQLite placeholder and gitignore the dir (claude-review)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: tighten rate limiter — correct boundary + drop dead cleanup branch
- `entry.count >= RATE_LIMIT_MAX_REQUESTS` so the 300th request is the
first rejected (was 301).
- Removed the `requestCounts.size > 100` lazy-cleanup block — on a
localhost-only server the map tops out at 1–2 entries, so the branch
was dead code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: rate limiter correctly allows exactly 300 req/min; doc localhost scope
- Check `entry.count >= max` BEFORE incrementing so the cap matches the
comment: 300 requests pass, the 301st gets 429.
- Added a comment noting the limiter is effectively a global cap on a
localhost-only worker (all callers share the 127.0.0.1/::1 bucket).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: normalise IPv4-mapped IPv6 in rate limiter client IP
Strip the `::ffff:` prefix so a localhost caller routed as
`::ffff:127.0.0.1` shares a bucket with `127.0.0.1`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: size-guarded prune of rate limiter map for non-localhost deploys
Prune expired entries only when the map exceeds 1000 keys and we're
already doing a window reset, so the cost is zero on the localhost hot
path (1–2 keys) and the map can't grow unbounded if the worker is ever
bound on a non-loopback interface.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Removes the 300 req/min rate limiter from the worker's HTTP middleware.
The worker is localhost-only (enforced via CORS), so rate limiting was
pointless security theater — but it broke the viewer, which polls logs
and stats frequently enough to trip the limit within seconds.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
SessionStart context injection regressed in v12.3.3 — no memory
context is being delivered to new sessions. Rolling back to the
v12.3.2 tree state while the regression is investigated.
Reverts #2080.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: resolve search, database, and docker bugs (#1913, #1916, #1956, #1957, #2048)
- Fix concept/concepts param mismatch in SearchManager.normalizeParams (#1916)
- Add FTS5 keyword fallback when ChromaDB is unavailable (#1913, #2048)
- Add periodic WAL checkpoint and journal_size_limit to prevent unbounded WAL growth (#1956)
- Add periodic clearFailed() to purge stale pending_messages (#1957)
- Fix nounset-safe TTY_ARGS expansion in docker/claude-mem/run.sh
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: prevent silent data loss on non-XML responses, add queue info to /health (#1867, #1874)
- ResponseProcessor: mark messages as failed (with retry) instead of confirming
when the LLM returns non-XML garbage (auth errors, rate limits) (#1874)
- Health endpoint: include activeSessions count for queue liveness monitoring (#1867)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: cache isFts5Available() at construction time
Addresses Greptile review: avoid DDL probe (CREATE + DROP) on every text
query. Result is now cached in _fts5Available at construction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve worker stability bugs — pool deadlock, MCP loopback, restart guard (#1868, #1876, #2053)
- Replace flat consecutiveRestarts counter with time-windowed RestartGuard:
only counts restarts within 60s window (cap=10), decays after 5min of
success. Prevents stranding pending messages on long-running sessions. (#2053)
- Add idle session eviction to pool slot allocation: when all slots are full,
evict the idlest session (no pending work, oldest activity) to free a slot
for new requests, preventing 60s timeout deadlock. (#1868)
- Fix MCP loopback self-check: use process.execPath instead of bare 'node'
which fails on non-interactive PATH. Fix crash misclassification by removing
false "Generator exited unexpectedly" error log on normal completion. (#1876)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve hooks reliability bugs — summarize exit code, session-init health wait (#1896, #1901, #1903, #1907)
- Wrap summarize hook's workerHttpRequest in try/catch to prevent exit
code 2 (blocking error) on network failures or malformed responses.
Session exit no longer blocks on worker errors. (#1901)
- Add health-check wait loop to UserPromptSubmit session-init command in
hooks.json. On Linux/WSL where hook ordering fires UserPromptSubmit
before SessionStart, session-init now waits up to 10s for worker health
before proceeding. Also wrap session-init HTTP call in try/catch. (#1907)
- Close#1896 as already-fixed: mtime comparison at file-context.ts:255-267
bypasses truncation when file is newer than latest observation.
- Close#1903 as no-repro: hooks.json correctly declares all hook events.
Issue was Claude Code 12.0.1/macOS platform event-dispatch bug.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: security hardening — bearer auth, path validation, rate limits, per-user port (#1932, #1933, #1934, #1935, #1936)
- Add bearer token auth to all API endpoints: auto-generated 32-byte
token stored at ~/.claude-mem/worker-auth-token (mode 0600). All hook,
MCP, viewer, and OpenCode requests include Authorization header.
Health/readiness endpoints exempt for polling. (#1932, #1933)
- Add path traversal protection: watch.context.path validated against
project root and ~/.claude-mem/ before write. Rejects ../../../etc
style attacks. (#1934)
- Reduce JSON body limit from 50MB to 5MB. Add in-memory rate limiter
(300 req/min/IP) to prevent abuse. (#1935)
- Derive default worker port from UID (37700 + uid%100) to prevent
cross-user data leakage on multi-user macOS. Windows falls back to
37777. Shell hooks use same formula via id -u. (#1936)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve search project filtering and import Chroma sync (#1911, #1912, #1914, #1918)
- Fix per-type search endpoints to pass project filter to Chroma queries
and SQLite hydration. searchObservations/Sessions/UserPrompts now use
$or clause matching project + merged_into_project. (#1912)
- Fix timeline/search methods to pass project to Chroma anchor queries.
Prevents cross-project result leakage when project param omitted. (#1911)
- Sync imported observations to ChromaDB after FTS rebuild. Import
endpoint now calls chromaSync.syncObservation() for each imported
row, making them visible to MCP search(). (#1914)
- Fix session-init cwd fallback to match context.ts (process.cwd()).
Prevents project key mismatch that caused "no previous sessions"
on fresh sessions. (#1918)
- Fix sync-marketplace restart to include auth token and per-user port.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve all CodeRabbit and Greptile review comments on PR #2080
- Fix run.sh comment mismatch (no-op flag vs empty array)
- Gate session-init on health check success (prevent running when worker unreachable)
- Fix date_desc ordering ignored in FTS session search
- Age-scope failed message purge (1h retention) instead of clearing all
- Anchor RestartGuard decay to real successes (null init, not Date.now())
- Add recordSuccess() calls in ResponseProcessor and completion path
- Prevent caller headers from overriding bearer auth token
- Add lazy cleanup for rate limiter map to prevent unbounded growth
- Bound post-import Chroma sync with concurrency limit of 8
- Add doc_type:'observation' filter to Chroma queries feeding observation hydration
- Add FTS fallback to all specialized search handlers (observations, sessions, prompts, timeline)
- Add response.ok check and error handling in viewer saveSettings
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve CodeRabbit round-2 review comments
- Use failure timestamp (COALESCE) instead of created_at_epoch for stale purge
- Downgrade _fts5Available flag when FTS table creation fails
- Escape FTS5 MATCH input by quoting user queries as literal phrases
- Escape LIKE metacharacters (%, _, \) in prompt text search
- Add response.ok check in initial settings load (matches save flow)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve CodeRabbit round-3 review comments
- Include failed_at_epoch in COALESCE for age-scoped purge
- Re-throw FTS5 errors so callers can distinguish failure from no-results
- Wrap all FTS fallback calls in SearchManager with try/catch
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve search, database, and docker bugs (#1913, #1916, #1956, #1957, #2048)
- Fix concept/concepts param mismatch in SearchManager.normalizeParams (#1916)
- Add FTS5 keyword fallback when ChromaDB is unavailable (#1913, #2048)
- Add periodic WAL checkpoint and journal_size_limit to prevent unbounded WAL growth (#1956)
- Add periodic clearFailed() to purge stale pending_messages (#1957)
- Fix nounset-safe TTY_ARGS expansion in docker/claude-mem/run.sh
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: prevent silent data loss on non-XML responses, add queue info to /health (#1867, #1874)
- ResponseProcessor: mark messages as failed (with retry) instead of confirming
when the LLM returns non-XML garbage (auth errors, rate limits) (#1874)
- Health endpoint: include activeSessions count for queue liveness monitoring (#1867)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: cache isFts5Available() at construction time
Addresses Greptile review: avoid DDL probe (CREATE + DROP) on every text
query. Result is now cached in _fts5Available at construction.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(evals): SWE-bench Docker scaffolding for claude-mem resolve-rate measurement
Adds evals/swebench/ scaffolding per .claude/plans/swebench-claude-mem-docker.md.
Agent image builds Claude Code 2.1.114 + locally-built claude-mem plugin;
run-instance.sh executes the two-turn ingest/fix protocol per instance;
run-batch.py orchestrates parallel Docker runs with per-instance isolation;
eval.sh wraps the upstream SWE-bench harness; summarize.py aggregates reports.
Orchestrator owns JSONL writes under a lock to avoid racy concurrent appends;
agent writes its authoritative diff to CLAUDE_MEM_OUTPUT_DIR (/scratch in
container mode) and the orchestrator reads it back. Scaffolding only — no
Docker build or smoke test run yet.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(evals): OAuth credential mounting for Claude Max/Pro subscriptions
Skips per-call API billing by extracting OAuth creds from host Keychain
(macOS) or ~/.claude/.credentials.json (Linux) and bind-mounting them
read-only into each agent container. Creds are copied into HOME=$SCRATCH/.claude
at container start so the per-instance isolation model still holds.
Adds run-batch.py --auth {oauth,api-key,auto} (auto prefers OAuth, falls
back to API key). run-instance.sh accepts either ANTHROPIC_API_KEY or
CLAUDE_MEM_CREDENTIALS_FILE. smoke-test.sh runs one instance end-to-end
using OAuth for quick verification before batch runs.
Caveat surfaced in docstrings: Max/Pro has per-window usage limits and is
framed for individual developer use — batch evaluation may exhaust the
quota or raise compliance questions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(docker): basic claude-mem container for ad-hoc testing
Adds docker/claude-mem/ with a fresh spin-up image:
- Dockerfile: FROM node:20 (reproduces anthropics/claude-code .devcontainer
pattern — Anthropic ships the Dockerfile, not a pullable image); layers
Bun + uv + locally-built plugin/; runs as non-root node user
- entrypoint.sh: seeds OAuth creds from CLAUDE_MEM_CREDENTIALS_FILE into
$HOME/.claude/.credentials.json, then exec's the command (default: bash)
- build.sh: npm run build + docker build
- run.sh: interactive launcher; auto-extracts OAuth from macOS Keychain
(security find-generic-password) or ~/.claude/.credentials.json on Linux,
mounts host .docker-claude-mem-data/ at /home/node/.claude-mem so the
observations DB survives container exit
Validated end-to-end: PostToolUse hook fires, queue enqueues, worker's SDK
compression runs under subscription OAuth, observations row lands with
populated facts/concepts/files_read, Chroma sync triggers.
Also updates .gitignore/.dockerignore for the new runtime-output paths.
Built plugin artifacts refreshed by the build step.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(evals/swebench): non-root user, OAuth mount, Lite dataset default
- Dockerfile.agent: switch to non-root \`node\` user (uid 1000); Claude Code
refuses --permission-mode bypassPermissions when euid==0, which made every
agent run exit 1 before producing a diff. Also move Bun + uv installs to
system paths so the non-root user can exec them.
- run-batch.py: add extract_oauth_credentials() that pulls from macOS
Keychain / Linux ~/.claude/.credentials.json into a temp file and bind-
mounts it at /auth/.credentials.json:ro with CLAUDE_MEM_CREDENTIALS_FILE.
New --auth {oauth,api-key,auto} flag. New --dataset flag so the batch can
target SWE-bench_Lite without editing the script.
- smoke-test.sh: default DATASET to princeton-nlp/SWE-bench_Lite (Lite
contains sympy__sympy-24152, Verified does not); accept DATASET env
override.
Caveat surfaced during testing: Max/Pro subscriptions have per-window usage
limits; running 5 instances in parallel with the "read every source file"
ingest prompt exhausted the 5h window within ~25 minutes (3/5 hit HTTP 429).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address PR #2076 review comments
- docker/claude-mem/run.sh: chmod 600 (not 644) on extracted OAuth creds
to match what `claude login` writes; avoids exposing tokens to other
host users. Verified readable inside the container under Docker
Desktop's UID translation.
- docker/claude-mem/Dockerfile: pin Bun + uv via --build-arg BUN_VERSION
/ UV_VERSION (defaults: 1.3.12, 0.11.7). Bun via `bash -s "bun-v<V>"`;
uv via versioned installer URL `https://astral.sh/uv/<V>/install.sh`.
- evals/swebench/smoke-test.sh: pipe JSON through stdin to `python3 -c`
so paths with spaces/special chars can't break shell interpolation.
- evals/swebench/run-batch.py: add --overwrite flag; abort by default
when predictions.jsonl for the run-id already exists, preventing
accidental silent discard of partial results.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address coderabbit review on PR #2076
Actionable (4):
- Dockerfile uv install: wrap `chmod ... || true` in braces so the trailing
`|| true` no longer masks failures from `curl|sh` via bash operator
precedence (&& binds tighter than ||). Applied to both docker/claude-mem/
and evals/swebench/Dockerfile.agent. Added `set -eux` to the RUN lines.
- docker/claude-mem/Dockerfile: drop unused `sudo` apt package (~2 MB).
- run-batch.py: name each agent container (`swebench-agent-<id>-<pid>-<tid>`)
and force-remove via `docker rm -f <name>` in the TimeoutExpired handler
so timed-out runs don't leave orphan containers.
Nitpicks (2):
- smoke-test.sh: collapse 3 python3 invocations into 1 — parse the instance
JSON once, print `repo base_commit`, and write problem.txt in the same
call.
- run-instance.sh: shallow clone via `--depth 1 --no-single-branch` +
`fetch --depth 1 origin $BASE_COMMIT`. Falls back to a full clone if the
server rejects the by-commit fetch.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address second coderabbit review on PR #2076
Actionable (3):
- docker/claude-mem/run.sh: on macOS, fall back to ~/.claude/.credentials.json
when the Keychain lookup misses (some setups still have file-only creds).
Unified into a single creds_obtained gate so the error surface lists both
sources tried.
- docker/claude-mem/run.sh: drop `exec docker run` — `exec` replaces the shell
so the EXIT trap (`rm -f "$CREDS_FILE"`) never fires and the extracted
OAuth JSON leaks to disk until tmpfs cleanup. Run as a child instead so
the trap runs on exit.
- evals/swebench/smoke-test.sh: actually enforce the TIMEOUT env var. Pick
`timeout` or `gtimeout` (coreutils on macOS), fall back to uncapped with
a warning. Name the container so exit-124 from timeout can `docker rm -f`
it deterministically.
Nitpick from the same review (consolidated python3 calls in smoke-test.sh)
was already addressed in the prior commit ef621e00.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address third coderabbit review on PR #2076
Actionable (1):
- evals/swebench/smoke-test.sh: the consolidated python heredoc had competing
stdin redirections — `<<'PY'` (script body) AND `< "$INSTANCE_JSON"` (data).
The heredoc won, so `json.load(sys.stdin)` saw an empty stream and the parse
would have failed at runtime. Pass INSTANCE_JSON as argv[2] and `open()` it
inside the script instead; the heredoc is now only the script body, which
is what `python3 -` needs.
Nitpicks (2):
- evals/swebench/smoke-test.sh: macOS Keychain lookup now falls through to
~/.claude/.credentials.json on miss (matches docker/claude-mem/run.sh).
- evals/swebench/run-batch.py: extract_oauth_credentials() no longer
early-returns on Darwin keychain miss; falls through to the on-disk creds
file so macOS setups with file-only credentials work in batch mode too.
Functional spot-check of the parse fix confirmed: REPO/BASE_COMMIT populated
and problem.txt written from a synthetic INSTANCE_JSON.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
parseSummary runs on every agent response, not just summary turns. When the
turn is a normal observation, the LLM correctly emits <observation> and no
<summary> — but the fallthrough branch from #1345 treated this as prompt
misbehavior and logged "prompt conditioning may need strengthening" every
time. That assumption stopped holding after #1633 refactored the caller to
always invoke parseSummary with a coerceFromObservation flag.
Gate the whole observation-on-summary path on coerceFromObservation. On a
real summary turn, coercion still runs and logs the legitimate "coercion
failed" warning when the response has no usable content. On an observation
turn, parseSummary returns null silently, which is the correct behavior.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: disable subagent summaries and label subagent observations
Detect Claude Code subagent hook context via `agent_id`/`agent_type` on
stdin, short-circuit the Stop-hook summary path when present, and thread
the subagent identity end-to-end onto observation rows (new `agent_type`
and `agent_id` columns, migration 010 at version 27). Main-session rows
remain NULL; content-hash dedup is unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address PR #2073 review feedback
- Narrow summarize subagent guard to agentId only so --agent-started
main sessions still own their summary (agentType alone is main-session).
- Remove now-dead agentId/agentType spreads from the summarize POST body.
- Always overwrite pendingAgentId/pendingAgentType in SDK/Gemini/OpenRouter
agents (clears stale subagent identity on main-session messages after
a subagent message in the same batch).
- Add idx_observations_agent_id index in migration 010 + the mirror
migration in SessionStore + the runner.
- Replace console.log in migration010 with logger.debug.
- Update summarize test: agentType alone no longer short-circuits.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address CodeRabbit + claude-review iteration 4 feedback
- SessionRoutes.handleSummarizeByClaudeId: narrow worker-side guard to
agentId only (matches hook-side). agentType alone = --agent main
session, which still owns its summary.
- ResponseProcessor: wrap storeObservations in try/finally so
pendingAgentId/Type clear even if storage throws. Prevents stale
subagent identity from leaking into the next batch on error.
- SessionStore.importObservation + bulk.importObservation: persist
agent_type/agent_id so backup/import round-trips preserve subagent
attribution.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* polish: claude-review iteration 5 cleanup
- Use ?? not || for nullable subagent fields in PendingMessageStore
(prevents treating empty string as null).
- Simplify observation.ts body spread — include fields unconditionally;
JSON.stringify drops undefined anyway.
- Narrow any[] to Array<{ name: string }> in migration010 column checks.
- Add trailing newline to migrations.ts.
- Document in observations/store.ts why the dedup hash intentionally
excludes agent fields.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* polish: claude-review iteration 7 feedback
- claude-code adapter: add 128-char safety cap on agent_id/agent_type
so a malformed Claude Code payload cannot balloon DB rows. Empty
strings now also treated as absent.
- migration010: state-aware debug log lists only columns actually
added; idempotent re-runs log "already present; ensured indexes".
- Add 3 adapter tests covering the length cap boundary and empty-string
rejection.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* perf: skip subagent summary before worker bootstrap
Move the agentId short-circuit above ensureWorkerRunning() so a Stop
hook fired inside a subagent does not trigger worker startup just to
return early. Addresses CodeRabbit nit on summarize.ts:36-47.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Addresses unresolved CodeRabbit finding on WorktreeAdoption.ts:296.
Previously, Chroma patch failures stranded rows permanently: adoptedSqliteIds
was built only from rows where merged_into_project IS NULL, so once SQL
committed, reruns couldn't rediscover them for retry.
The Chroma id set is now built from ALL observations whose project matches a
merged worktree — including rows already stamped to this parent. Combined
with the idempotent updateMergedIntoProject, transient Chroma failures
self-heal on the next adoption pass.
SQL writes remain idempotent (UPDATE still guards on merged_into_project IS
NULL), so adoptedObservations / adoptedSummaries continue to count only
newly-adopted rows. chromaUpdates now counts total Chroma writes per pass
(may exceed adoptedObservations when retrying).
Addresses six CodeRabbit/Greptile findings on PR #2052:
- Schema guard in adoptMergedWorktrees probes for merged_into_project
columns before preparing statements; returns early when absent so first
boot after upgrade (pre-migration) doesn't silently fail.
- Startup adoption now iterates distinct cwds from pending_messages and
dedupes via resolveMainRepoPath — the worker daemon runs with
cwd=plugin scripts dir, so process.cwd() fallback was a no-op.
- ObservationCompiler single-project queries (queryObservations /
querySummaries) OR merged_into_project into WHERE so injected context
surfaces adopted worktree rows, matching the Multi variants.
- SessionStore constructor now calls ensureMergedIntoProjectColumns so
bundled artifacts (context-generator.cjs) that embed SessionStore get
the merged_into_project column on DBs that only went through the
bundled migration chain.
- OBSERVER_SESSIONS_PROJECT constant is now derived from
basename(OBSERVER_SESSIONS_DIR) and used across PaginationHelper,
SessionStore, and timeline queries instead of hardcoded strings.
- Corrected misleading Chroma retry docstring in WorktreeAdoption to
match actual behavior (no auto-retry once SQL commits).
Observer sessions (internal SDK-driven worker queries) run under a
synthetic project name 'observer-sessions' to keep them out of
claude --resume. They were still surfacing in the viewer project
picker and unfiltered observation/summary/prompt feeds.
Filter them out at every UI-facing query:
- SessionStore.getAllProjects and getProjectCatalog
- timeline/queries.ts getAllProjects
- PaginationHelper observations/summaries/prompts when no project is selected
When a caller explicitly requests project='observer-sessions',
results are still returned (not a hard ban, just hidden by default).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Document --branch override in npx-cli help text
- Guard ContextBuilder against empty projects[] override; fall back to cwd-derived primary
- Ensure merged_into_project indexes are created even if ALTER ran in a prior partial migration
- Reject adopt --branch/--cwd flags with missing or flag-like values
- Use defined --color-border-primary token for merged badge border
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Update allProjects test expectation to match [parent, composite] (matches JSDoc + callers in ContextBuilder/context handlers).
- Replace string-matched __DRY_RUN_ROLLBACK__ sentinel with dedicated DryRunRollback class to avoid swallowing unrelated errors.
- Add 5000ms timeout to spawnSync git calls in WorktreeAdoption and ProcessManager so worker startup can't hang on a stuck git process.
- Drop unreachable break after process.exit(0) in adopt case.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Regenerated worker-service.cjs, context-generator.cjs, viewer.html, and
viewer-bundle.js to reflect all six implementation phases of the merged-
worktree adoption feature.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Worktrees are branches off main; the parent holds the architecture,
decisions, and long-tail history the worktree inherits. Scoping reads
to the worktree alone meant every new worktree started cold on any
question that required prior context.
Expand `allProjects` in a worktree to `[parent, composite]` so reads
pull both. Writes still go through `.primary` (the composite), so
sibling worktrees don't leak into each other.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ports scripts/cwd-remap.ts into ProcessManager.runOneTimeCwdRemap() and
invokes it in initializeBackground() alongside the existing chroma
migration. Uses pending_messages.cwd as the source of truth to rewrite
pre-worktree bare project names into the parent/worktree composite
format so search and context are consistent.
- Backs up the DB to .bak-cwd-remap-<ts> before any writes.
- Idempotent: marker file .cwd-remap-applied-v1 short-circuits reruns.
- No-ops on fresh installs (no DB, or no pending_messages table).
- On failure, logs and skips the marker so the next restart retries.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Leftover artifacts from an abandoned context-injection feature. The
project-level CLAUDE.md stays; the directory-level ones were generated
timeline scaffolding that never panned out.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three sites didn't account for parent/worktree composite naming:
- PaginationHelper.stripProjectPath: marker used full composite, breaking
path sanitization for worktrees checked out outside a parent/leaf layout.
Now extracts the leaf segment.
- observations/store.ts: fallback imported getCurrentProjectName from
shared/paths.ts (a duplicate impl without worktree detection). Switched
to getProjectContext().primary so writes key into the same project as
reads.
- SearchManager.getRecentContext: fallback used basename(cwd) and lost
the parent prefix, making the MCP tool find nothing in worktrees.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a caller (e.g. worker context-inject route) passes a `projects`
array without a matching cwd, the cwd-derived `context.primary` drifted
from the projects being queried — producing an empty-state header for
one project while querying another. Use the last entry of `projects` so
header and query target stay in sync.
Revert of #1820 behavior. Each worktree now gets its own bucket:
- In a worktree, primary = `parent/worktree` (e.g. `claude-mem/dar-es-salaam`)
- In a main repo, primary = basename (unchanged)
- allProjects is always `[primary]` — strict isolation at query time
Includes a one-off maintenance script (scripts/worktree-remap.ts) that
retroactively reattributes past sessions to their worktree using path
signals in observations and user prompts. Two-rule inference keeps the
remap high-confidence:
1. The worktree basename in the path matches the session's current
plain project name (pre-#1820 era; trusted).
2. Or all worktree path signals converge on a single (parent, worktree)
across the session.
Ambiguous sessions are skipped.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Observations were 100% failing on Claude Code 2.1.109+ because the Agent
SDK emits ["--setting-sources", ""] when settingSources defaults to [].
The existing Bun-workaround filter stripped the empty string but left
the orphan --setting-sources flag, which then consumed --permission-mode
as its value, crashing the subprocess with:
Error processing --setting-sources:
Invalid setting source: --permission-mode.
Make the filter pair-aware: when an empty arg follows a --flag, drop
both so the SDK default (no setting sources) is preserved by omission.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The synthetic summary salvage feature created fake summaries from observation
data when the AI returned <observation> instead of <summary> tags. This was
overengineered — missing a summary is preferable to fabricating one from
observation fields that don't map cleanly to summary semantics.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve Setup hook broken reference and warn on macOS-only binary (#1547)
On Linux ARM64, the plugin silently failed because:
1. The Setup hook called setup.sh which was removed; the hook exited 127
(file not found), causing the plugin to appear uninstalled.
2. The committed plugin/scripts/claude-mem binary is macOS arm64 only;
no warning was shown when it could not execute on other platforms.
Fix the Setup hook to call smart-install.js (the current setup mechanism)
and add checkBinaryPlatformCompatibility() to smart-install.js, which reads
the Mach-O magic bytes from the bundled binary and warns users on non-macOS
platforms that the JS fallback (bun-runner.js + worker-service.cjs) is active.
Generated by Claude Code
Vibe coded by ousamabenyounes
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: close fd in finally block, strengthen smart-install tests to use production function
- Wrap openSync/readSync in checkBinaryPlatformCompatibility with a finally block so the file descriptor is always closed even if readSync throws
- Export checkBinaryPlatformCompatibility with an optional binaryPath param for testability
- Refactor Mach-O detection tests to call the production function directly, mocking process.platform and passing controlled binary paths, eliminating duplicated inline logic
- Strengthen plugin-distribution test to assert at least one command hook exists before checking for smart-install.js, preventing vacuous pass
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix: replace hardcoded nvm/homebrew PATH with universal login shell resolution
Hook commands previously hardcoded PATH entries for nvm and homebrew,
causing `node: command not found` for users with other Node version
managers (mise, asdf, volta, fnm, Nix, etc.).
Replace with `$($SHELL -lc 'echo $PATH')` which inherits the user's
login shell PATH regardless of how Node was installed. Also adds the
missing PATH export to the PreToolUse hook (#1702).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add cache-path fallback to PreToolUse hook
Aligns PreToolUse _R resolution with all other hooks by adding the
cache directory lookup before falling back to the marketplace path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: exclude primary key index from unique constraint check in migration 7
PRAGMA index_list returns all indexes including those backing PRIMARY KEY
columns (origin='pk'), which always have unique=1. The check was therefore
always true, causing migration 7 to run the full DROP/CREATE/RENAME table
sequence on every worker startup instead of short-circuiting once the
UNIQUE constraint had already been removed.
Fix: filter to non-PK indexes by requiring idx.origin !== 'pk'. The
origin field is already present on the existing IndexInfo interface.
Fixes#1749
* fix: apply pk-origin guard to all three migration code paths
CodeRabbit correctly identified that the origin !== 'pk' fix was only
applied to MigrationRunner.ts but not to the two other active code paths
that run the same removeSessionSummariesUniqueConstraint logic:
- SessionStore.ts:220 — used by DatabaseManager and worker-service
- plugin/scripts/context-generator.cjs — bundled artifact (minified)
All three paths now consistently exclude primary-key indexes when
detecting unique constraints on session_summaries.
syncAndBroadcastSummary was using the raw ParsedSummary (null when salvaged)
instead of summaryForStore for the SSE broadcast, causing a crash when the
LLM returns <observation> without <summary> tags. Also removes misplaced
tree-sitter docs from mem-search/SKILL.md (belongs in smart-explore).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
