- Skip gate for files under 1,500 bytes — timeline (~370 tokens) costs
more than just reading small files directly
- Deduplicate observations by memory_session_id (one per session)
- Rank by specificity: files_modified > files_read, fewer tagged files > many
- Fetch 40 candidates, dedup/score down to 15 for display
- Reduce default by-file query limit from 30 to 15
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The compiled binary (v10.6.3) creates these columns at runtime via
MigrationRunner, but no corresponding migration exists in the TypeScript
source. Anyone building from source gets observations without these
columns, breaking the feedback pipeline and model tracking.
This migration conditionally adds both columns using PRAGMA table_info
checks, making it safe for databases that already have them.
Refs: #1626
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The per-prompt Chroma vector search injection on UserPromptSubmit adds latency
and context noise. Disable by default while we iterate on a more precise
file-context approach. Users can still opt in via CLAUDE_MEM_SEMANTIC_INJECT=true.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PHP was listed as a supported language in CHANGELOG and .php files were
scanned by search.ts, but parser.ts was missing:
- .php extension in LANG_MAP (causing detectLanguage to return 'unknown')
- 'php' entry in GRAMMAR_PACKAGES (no grammar path to resolve)
- PHP query patterns for symbol extraction
- PHP case in getQueryKey()
This meant smart_search/smart_outline/smart_unfold scanned PHP files
but extracted 0 symbols because the grammar could not be resolved.
Changes:
- Add '.php' -> 'php' to LANG_MAP
- Add 'php' -> 'tree-sitter-php/php' to GRAMMAR_PACKAGES
- Add PHP tree-sitter query patterns (functions, methods, classes, interfaces, traits, use statements)
- Add 'php' case to getQueryKey()
- Add tree-sitter-php ^0.24.2 to devDependencies
sort -V is a GNU extension not available on macOS/BSD sort. Replaced
with sed 's/^v//' | sort -t. -k1,1n -k2,2n -k3,3n which strips the
'v' prefix, sorts numerically by major.minor.patch, then re-prepends
'v' for the final path. Works on both GNU and BSD sort.
Prepend a PATH export to every hook command that invokes node, so that
/bin/sh can locate the binary when Node.js is managed by nvm or
installed via Homebrew. Falls back gracefully when nvm is not present.
Closes#1598
On Bun/Windows, `require.main !== module` in CJS mode causes the worker
to exit silently with code 0. The wrapper already sets CLAUDE_MEM_MANAGED=true
when spawning the inner worker, so checking this env var is a safe fallback
that doesn't affect standalone execution.
Ref #1450 (incomplete fix in PR #1518 — ESM path fixed but CJS branch not).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: wire up Cursor integration in installer — was incorrectly marked "coming soon"
CursorHooksInstaller.ts was fully built but never connected to the
installer. Set supported: true in IDE detection and call installCursorHooks
in the setup flow, matching the pattern used by other integrations.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: wire up Cursor MCP configuration during install
PR review flagged that the hint says "hooks + MCP integration" but
configureCursorMcp() was never called during install. Now invoked
after hooks install with graceful fallback if MCP setup fails.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Observer prompt now explicitly requires XML observation blocks or empty
responses — prose explanations like "Skipping" are discarded. ResponseProcessor
logs a warning when non-XML content is received. Recording focus expanded to
include concrete debugging findings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The parser correctly strips observation types from concepts arrays when the
LLM ignores the prompt instruction. This is routine data normalization, not
an error — downgrade to debug to reduce log noise.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The install simplification in 21b10b46 over-applied scope: it replaced the
entire runInstallCommand (interactive IDE multi-select, --ide flag, 13 IDE
setup dispatchers) with just two `claude` CLI commands. The intent was to
simplify the Claude Code path only.
Now: Claude Code uses `claude plugin marketplace add` + `claude plugin install`.
All other IDEs get the full installer flow (file copy, registration, IDE-specific
setup). Interactive multi-select and --ide flag are restored.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The generated_by_model column was added to the observations table in the
Phase 0 governance schema migration but never wired into the INSERT
statements. All 3,878+ observations in production have this field NULL.
This fix threads the model ID from each agent (SDKAgent, GeminiAgent,
OpenRouterAgent) through processAgentResponse() into storeObservation(),
storeObservations(), and storeObservationsAndMarkComplete().
Unblocks Thompson Sampling RFC (#1571) which needs {obs_type}:{model}
as the bandit arm key.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- architecture-overview: add 'text' language to all fenced code blocks (MD040)
- architecture-overview: split 'Stop' lifecycle into 'Summary' + 'SessionEnd'
to match canonical 5-hook naming
- production-guide: reference PR numbers for proposed settings not yet upstream
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Architecture overview covers the 4-layer system design, hook lifecycle,
data flow, and key patterns (CLAIM-CONFIRM, circuit-breaker, graceful
degradation, deduplication, dual session IDs).
Production guide provides recommended settings, health monitoring
metrics and thresholds, quick health check commands, multi-machine
sync setup, growth expectations, common issues with solutions, and
log analysis tips.
Based on 23 days of production usage with 3,400+ observations
across two physical servers and 8 projects.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Critical:
- migrations: change version 8 → 25 to avoid collision with
MigrationRunner.addObservationHierarchicalFields (uses version 8)
- SessionRoutes: remove duplicate imports that prevent compilation
Major:
- SessionRoutes: call applyTierRouting() before every generator spawn
(stale-recovery and crash-recovery paths were missing it)
- applyTierRouting: clear session.modelOverride at top before re-evaluating
to prevent stale tier from persisting across spawns
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tier Routing:
- Inspect pending queue before starting generator
- Summarize messages → CLAUDE_MEM_TIER_SUMMARY_MODEL (e.g., Opus)
- All simple tools (Read, Glob, Grep, LS) → CLAUDE_MEM_TIER_SIMPLE_MODEL (Haiku)
- Mixed/complex → default model (no override)
- session.modelOverride in ActiveSession, used by SDKAgent.getModelId()
- peekPendingTypes() in PendingMessageStore for non-claiming inspection
- Configurable via CLAUDE_MEM_TIER_ROUTING_ENABLED (default: true)
Feedback Collection (schema only):
- New observation_feedback table via MigrationRunner (schema version 24)
- Tracks signal_type (semantic_inject_hit, search_accessed, etc.)
- Indexes on observation_id and signal_type
- Foundation for future Thompson Sampling optimization
Production data (24h tier routing test):
- 36 Haiku observations in 4 min, quality indistinguishable from Sonnet
- Estimated ~52% cost reduction on SDK Agent usage
- 835 → 6,695 feedback signals collected over 13 days
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Follow-up to PR #1568: fix stale doc comment that still said GET, and add
limit parameter validation (default 5, clamped to 1-20 range).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: semantic context injection via Chroma on every UserPromptSubmit
On each prompt, queries ChromaDB for the top-N most relevant past
observations and injects them as additionalContext. Replaces the
recency-based "last N observations" approach with relevance-based
semantic search.
Changes:
- session-init.ts: After session init, query /api/context/semantic
with user's prompt text. If results found, return as
hookSpecificOutput with hookEventName 'UserPromptSubmit'.
- SearchRoutes.ts: New GET /api/context/semantic endpoint that queries
SearchManager with format='json' and formats results as markdown.
- SettingsDefaultsManager.ts: New settings CLAUDE_MEM_SEMANTIC_INJECT
(default: true) and CLAUDE_MEM_SEMANTIC_INJECT_LIMIT (default: 5).
Key behaviors:
- Fires on every UserPromptSubmit (not just SessionStart)
- Minimum prompt length: 20 chars (skips "ok", "yes", etc.)
- Skips media-only prompts
- Graceful degradation: if worker/Chroma unavailable, no injection
- Survives /clear: re-injects on next prompt (not session-bound)
- Uses workerHttpRequest (v10.6.3 API, not raw fetch)
Production data (23 days, 3,400+ observations):
- Before: 8 most recent observations (often irrelevant to current topic)
- After: 5 most relevant observations (semantic match)
- Token cost: ~1800 → ~800-1200 per injection
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address CodeRabbit review on PR #1568
- session-init: don't skip semantic injection when contextInjected=true
(only skip agent re-init, semantic lookup must run every prompt)
- session-init: normalize SEMANTIC_INJECT toggle via String().toLowerCase()
- semantic endpoint: change from GET to POST to avoid URL-length limits
and prompt exposure in access logs. Handler accepts both body and query
for backwards compatibility.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Alessandro Costa <alessandro@claudio.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: resolve 3 upstream bugs in summarize, ChromaSync, and HealthMonitor
1. summarize.ts: Skip summary when transcript has no assistant message.
Prevents error loop where empty transcripts cause repeated failed
summarize attempts (~30 errors/day observed in production).
2. ChromaSync.ts: Fallback to chroma_update_documents when add fails
with "IDs already exist". Handles partial writes after MCP timeout
without waiting for next backfill cycle.
3. HealthMonitor.ts: Replace HTTP-based isPortInUse with atomic socket
bind on Unix. Eliminates TOCTOU race when two sessions start
simultaneously (HTTP check is non-atomic — both see "port free"
before either completes listen()). Updated tests accordingly.
All three bugs are pre-existing in v10.5.5. Confirmed via log analysis
of 543K lines over 17 days of production usage across two servers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: add CONTRIB_NOTES.md to gitignore
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: address CodeRabbit review on PR #1566
- HealthMonitor: add APPROVED OVERRIDE annotation for Win32 HTTP fallback
- ChromaSync: replace chroma_update_documents with delete+add for proper
upsert (update only modifies existing IDs, silently ignores missing ones)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Alessandro Costa <alessandro@claudio.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bidirectional sync of observations and session summaries between
machines via SSH/SCP. Exports to JSON, transfers, imports with
deduplication by (created_at, title).
Commands:
claude-mem-sync push <remote-host> # local → remote
claude-mem-sync pull <remote-host> # remote → local
claude-mem-sync sync <remote-host> # bidirectional
claude-mem-sync status <remote-host> # compare counts
Features:
- Deduplication prevents duplicates on repeated runs
- Configurable paths via CLAUDE_MEM_DB / CLAUDE_MEM_REMOTE_DB
- Automatic temp file cleanup
- Requires only Python 3 + SSH on both machines
Tested syncing 3,400+ observations between two physical servers.
After sync, a session on the remote server used the transferred
memory to deliver a real feature PR — proving productive
cross-machine workflows.
Co-authored-by: Alessandro Costa <alessandro@claudio.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: drain orphaned pending messages on session completion (SIGTERM)
When deleteSession() aborts the SDK agent via SIGTERM, pending messages
in the queue are never processed. Without drain, they remain in
'pending' status forever — no future generator picks them up because
the session is already completed.
Adds markAllSessionMessagesAbandoned() call after deleteSession() in
completeByDbId(). This reuses the existing PendingMessageStore method
already used by worker-service.ts terminateSession().
Production evidence: 15 orphaned summarize messages found across
completed sessions (ages 3h to 3 days) before this fix. After fix:
0 orphaned messages over 23 days of operation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: document best-effort drain limitation per CodeRabbit review #1567
Add comment noting the rare race condition when generators outlive the
30s SIGTERM timeout. Practical risk is negligible (0 orphans over 23 days).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Alessandro Costa <alessandro@claudio.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Alex Newman