airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chore: merge upstream v12.3.1 + keep local fixes

Browse Source 
Upstream brings:
- 12.2.1: Break infinite summary-retry loop (#2072)
- 12.2.2: Subagent observation labeling + schema migration (#2073)
- 12.2.3: Silence parser warning on normal observation responses (#2074)
- 12.3.0: Docker harness + SWE-bench eval harness (#2076)
- 12.3.1: Error handling anti-pattern cleanup across 91 files (#2078)

Local fixes preserved through merge:
- env-sanitizer PATH extension for claude CLI lookup
- SessionStore stale session reset (mac sleep / 4h wall-clock)

Built artifacts rebuilt from merged sources; fixes verified present
in worker-service.cjs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
JOUNGWOOK KWON
2026-04-20 13:33:47 +09:00
parent d6ad6e29f0 8b6e61c70b
commit 8500c2f6ca
133 changed files with 8672 additions and 4000 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude-plugin/marketplace.json
+1 -1
View File
@@ -10,7 +10,7 @@
"plugins": [ "plugins": [
{ {
"name": "claude-mem", "name": "claude-mem",
"version": "12.2.0", "version": "12.3.1",
"source": "./plugin", "source": "./plugin",
"description": "Persistent memory system for Claude Code - context compression across sessions" "description": "Persistent memory system for Claude Code - context compression across sessions"
} }
.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "claude-mem", "name": "claude-mem",
"version": "12.2.0", "version": "12.3.1",
"description": "Memory compression system for Claude Code - persist context across sessions", "description": "Memory compression system for Claude Code - persist context across sessions",
"author": { "author": {
"name": "Alex Newman" "name": "Alex Newman"
.claude/scheduled_tasks.lock
-1
View File
@@ -1 +0,0 @@
{"sessionId":"6a00de6e-282e-4cd8-98ec-b5afb73c468d","pid":50072,"acquiredAt":1775678989779}
.codex-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "claude-mem", "name": "claude-mem",
"version": "12.2.0", "version": "12.3.1",
"description": "Memory compression system for Claude Code - persist context across sessions", "description": "Memory compression system for Claude Code - persist context across sessions",
"author": { "author": {
"name": "Alex Newman", "name": "Alex Newman",
.dockerignore
+9
View File
@@ -0,0 +1,9 @@
# Keep the build context small for evals/swebench/Dockerfile.agent.
# The Dockerfile needs `plugin/` and `evals/swebench/` — do NOT exclude them.
node_modules/
.git/
logs/
evals/swebench/runs/
.docker-claude-mem-data/
.venv
.venv-*
.gitignore
+13
View File
@@ -34,7 +34,20 @@ src/ui/viewer.html
.claude-octopus/ .claude-octopus/
.claude/session-intent.md .claude/session-intent.md
.claude/session-plan.md .claude/session-plan.md
.claude/scheduled_tasks.lock
.octo/ .octo/
# Installer marker — dropped by the claude-mem CLI at install time
plugin/.cli-installed
# Local contribution analysis (not part of upstream) # Local contribution analysis (not part of upstream)
CONTRIB_NOTES.md CONTRIB_NOTES.md
# Docker container runtime data (basic claude-mem container)
.docker-claude-mem-data/
# SWE-bench eval outputs
evals/swebench/runs/
claude-opus-4-7+claude-mem.*.json
logs/run_evaluation/
.venv-swebench/
.plan/subagent-summary-disable-and-labeling.md
+315
View File
@@ -0,0 +1,315 @@
# Plan: Disable Summaries for Subagents + Label Subagent Observations
## Goal
1. **Disable summaries for subagents** — prevent any summary generation path (hook → worker → SDK agent) from firing for events originating in a Claude Code subagent.
2. **Label observations from subagents** — tag every observation with the subagent identity (agent_id + agent_type) so downstream queries can distinguish main-session work from subagent work.
## Phase 0 — Documentation Discovery (COMPLETE)
### Claude Code hook payload fields (source: https://code.claude.com/docs/en/hooks.md)
- `agent_id` — present **only** when the hook fires inside a subagent invocation (e.g., `"agent-def456"`). Absent in the main session.
- `agent_type` — the subagent identifier (built-in like `"Bash"`, `"Explore"`, `"Plan"`, or a custom agent name). Present in subagents **and** when `--agent` flag is used.
- `session_id` — shared across main and subagents in the same session. Cannot distinguish contexts on its own.
- `transcript_path` — shared session transcript. Not a reliable discriminator.
- `SubagentStop` — dedicated event that fires when a subagent finishes. Currently **NOT registered** in `plugin/hooks/hooks.json`.
- `Stop` — fires for the main Claude agent (not subagents). Currently registered → wired to `summarize` handler.
**Discriminator for subagent context**: presence of `agent_id` OR `agent_type` in the hook stdin JSON.
### Current claude-mem architecture (grepped + read)
- `src/cli/types.ts:1-15` — `NormalizedHookInput` lacks `agentId` / `agentType`.
- `src/cli/adapters/claude-code.ts:5-17` — Claude Code adapter does NOT extract `agent_id` / `agent_type`.
- `src/cli/handlers/summarize.ts:27-143` — Stop-hook handler posts to `/api/sessions/summarize` without guarding on subagent context.
- `src/cli/handlers/observation.ts:51-62` — PostToolUse handler POSTs observation body without subagent fields.
- `src/services/worker/http/routes/SessionRoutes.ts:555-646` — `handleObservationsByClaudeId` destructures only `{ contentSessionId, tool_name, tool_input, tool_response, cwd }`; `queueObservation` call at line 620 has no subagent field.
- `src/services/sqlite/observations/store.ts:75-80` — `INSERT INTO observations` column list has no `agent_type` / `agent_id`.
- `src/services/sqlite/migrations.ts:578-588` — migrations array ends with `migration009` (version 26). Next migration slot is `migration010` (version 27).
- `src/utils/logger.ts:195-203` — already reads `input.subagent_type` for formatting Task tool invocations (reference pattern, no downstream storage).
### Allowed APIs / patterns to copy
- **Adapter metadata extension pattern**: `src/cli/adapters/gemini-cli.ts:77-96` already collects platform-specific metadata into `metadata` and returns it on `NormalizedHookInput`. Copy this pattern.
- **Migration pattern**: `src/services/sqlite/migrations.ts:556-573` (migration009) is a copy-ready template for conditional `ALTER TABLE ADD COLUMN` additions.
- **Observation INSERT column extension pattern**: `src/services/sqlite/observations/store.ts:75-98` — add `agent_type`, `agent_id` to the column list and to `stmt.run(...)` bindings.
### Anti-patterns to avoid
- Do NOT assume `agent_id` is present on the main session — it is undefined there. Treat presence as the discriminator.
- Do NOT register SubagentStop as a new hook in `hooks.json` just to "disable" summaries — defensively short-circuiting in the handler is simpler and covers both current and future Claude Code versions where Stop might fire in subagent contexts.
- Do NOT rely on `session_id` to distinguish — it is shared.
- Do NOT invent a `parent_tool_use_id` field in hook input. The Claude Code docs do not expose parent tool use ID on hook payloads. Only use `agent_id` + `agent_type`.
- Do NOT break the existing observation hash-dedup logic in `store.ts:19-28` — leave the hash inputs as-is.
---
## Phase 1 — Extend hook input surface to carry subagent fields
**What to implement** (COPY pattern from gemini-cli adapter metadata handling):
1. Edit `src/cli/types.ts:1-15` — add two optional fields to `NormalizedHookInput`:
```ts
agentId?: string; // Claude Code subagent agent_id (undefined in main session)
agentType?: string; // Claude Code subagent agent_type (undefined in main session)
```
2. Edit `src/cli/adapters/claude-code.ts:5-17` — in `normalizeInput`, extract `r.agent_id` and `r.agent_type`:
```ts
return {
sessionId: r.session_id ?? r.id ?? r.sessionId,
cwd: r.cwd ?? process.cwd(),
prompt: r.prompt,
toolName: r.tool_name,
toolInput: r.tool_input,
toolResponse: r.tool_response,
transcriptPath: r.transcript_path,
agentId: typeof r.agent_id === 'string' ? r.agent_id : undefined,
agentType: typeof r.agent_type === 'string' ? r.agent_type : undefined,
};
```
3. Edit `src/cli/adapters/gemini-cli.ts:88-97` — return matching `undefined` defaults so the interface contract is consistent across adapters. (No behavior change; just explicit `agentId: undefined, agentType: undefined` on the return object, or rely on the optional-field default by leaving it out. Leave it out — TypeScript optional is fine.)
**Documentation references**: Claude Code hooks docs section "Subagent Identification Fields"; gemini-cli adapter metadata pattern at `src/cli/adapters/gemini-cli.ts:77-96`.
**Verification checklist**:
- `grep -n "agentId" src/cli/types.ts` → finds the new field.
- `grep -n "agent_id" src/cli/adapters/claude-code.ts` → finds the extraction.
- `npm run build` succeeds.
**Anti-pattern guards**:
- Do NOT rename `agent_id` / `agent_type` snake_case raw fields. Camel-case only in `NormalizedHookInput`.
- Do NOT default to a sentinel string like `"main"`; leave undefined when absent.
---
## Phase 2 — Short-circuit summary generation in subagent context
**What to implement**:
1. Edit `src/cli/handlers/summarize.ts:27-36`, immediately after the worker-ready check (line 34) and before any processing:
```ts
// Skip summaries in subagent context — subagents do not own the session summary.
// Main Stop hook owns it; SubagentStop (if ever registered) must no-op.
if (input.agentId || input.agentType) {
logger.debug('HOOK', 'Skipping summary: subagent context detected', {
sessionId: input.sessionId,
agentId: input.agentId,
agentType: input.agentType
});
return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
}
```
2. (Safety) Edit `src/services/worker/http/routes/SessionRoutes.ts` in `handleSummarizeByClaudeId` (around line 655-692): add a defensive guard that rejects the summarize request if the body includes `agentId` or `agentType`. Return `{ status: 'skipped', reason: 'subagent_context' }`. This is belt-and-suspenders in case any caller bypasses the hook layer.
3. Extend the `/api/sessions/summarize` body in `src/cli/handlers/summarize.ts:73-82` to include `agentId` and `agentType` (passthrough) so the worker can make the same decision independently. Only pass fields when defined:
```ts
body: JSON.stringify({
contentSessionId: sessionId,
last_assistant_message: lastAssistantMessage,
platformSource,
...(input.agentId ? { agentId: input.agentId } : {}),
...(input.agentType ? { agentType: input.agentType } : {}),
}),
```
**Documentation references**: summarize.ts handler flow at `src/cli/handlers/summarize.ts:27-143`; summarize route at `src/services/worker/http/routes/SessionRoutes.ts:655-692`.
**Verification checklist**:
- Unit test or manual dispatch with a payload containing `agent_id: "agent-abc"` → summarize handler returns before calling `/api/sessions/summarize`.
- `grep -n "subagent" src/cli/handlers/summarize.ts` → finds the new guard.
- `grep -n "subagent_context\|agentId" src/services/worker/http/routes/SessionRoutes.ts` → finds the server-side guard.
**Anti-pattern guards**:
- Do NOT also short-circuit in `session-complete` or `context` handlers — the session's main Stop still cleans up.
- Do NOT log at info level (spammy); `logger.debug` only.
---
## Phase 3 — Database schema migration for subagent labels on observations
**What to implement** (COPY migration009 pattern from `src/services/sqlite/migrations.ts:556-573`):
1. Append a new migration to `src/services/sqlite/migrations.ts` right after `migration009` (before the `migrations` array at line 578):
```ts
export const migration010: Migration = {
version: 27,
up: (db: Database) => {
const columns = db.prepare('PRAGMA table_info(observations)').all() as any[];
const hasAgentType = columns.some((c: any) => c.name === 'agent_type');
const hasAgentId = columns.some((c: any) => c.name === 'agent_id');
if (!hasAgentType) {
db.run('ALTER TABLE observations ADD COLUMN agent_type TEXT');
}
if (!hasAgentId) {
db.run('ALTER TABLE observations ADD COLUMN agent_id TEXT');
}
db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_type ON observations(agent_type)');
console.log('[migration010] Added agent_type, agent_id columns to observations');
},
down: (_db: Database) => {
// SQLite DROP COLUMN not fully supported; no-op
}
};
```
2. Add `migration010` to the `migrations` array at `src/services/sqlite/migrations.ts:578-588`.
3. Check `src/services/sqlite/migrations/runner.ts` to see if there's a parallel registration site; if so, mirror the addition there. (Investigation step — if `runner.ts` replicates migration definitions, extend it the same way. Otherwise, importing `migrations` from `migrations.ts` is sufficient.)
**Documentation references**: migration007 and migration009 at `src/services/sqlite/migrations.ts:491-509` and `556-573` as copy-ready templates.
**Verification checklist**:
- Run worker; check logs for `[migration010]`.
- `sqlite3 ~/.claude-mem/claude-mem.db "PRAGMA table_info(observations);"` → shows `agent_type` and `agent_id` columns.
- `sqlite3 ~/.claude-mem/claude-mem.db ".indexes observations"` → shows `idx_observations_agent_type`.
**Anti-pattern guards**:
- Do NOT drop or rename existing columns.
- Do NOT set NOT NULL constraints — main-session rows have NULL for these.
- Do NOT pick a version number that's already used (26 is migration009; use 27).
---
## Phase 4 — Thread subagent fields through hook → worker → SDK → DB
**What to implement**:
### 4a — Hook PostToolUse handler sends fields
Edit `src/cli/handlers/observation.ts:51-62`:
```ts
const response = await workerHttpRequest('/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
contentSessionId: sessionId,
platformSource,
tool_name: toolName,
tool_input: toolInput,
tool_response: toolResponse,
cwd,
...(input.agentId ? { agentId: input.agentId } : {}),
...(input.agentType ? { agentType: input.agentType } : {}),
})
});
```
### 4b — Worker observations route receives and forwards
Edit `src/services/worker/http/routes/SessionRoutes.ts:555-646`:
- Destructure: `const { contentSessionId, tool_name, tool_input, tool_response, cwd, agentId, agentType } = req.body;`
- Pass to `queueObservation` at line 620:
```ts
this.sessionManager.queueObservation(sessionDbId, {
tool_name,
tool_input: cleanedToolInput,
tool_response: cleanedToolResponse,
prompt_number: promptNumber,
cwd: cwd || ...,
agentId: typeof agentId === 'string' ? agentId : undefined,
agentType: typeof agentType === 'string' ? agentType : undefined,
});
```
### 4c — queueObservation type extension
Investigation: find the `queueObservation` signature in the session manager (likely `src/services/session/` or similar). Add optional `agentId?: string; agentType?: string;` to the payload type. These must ride through to the SDK agent's observation context so they land in `storeObservation()`.
### 4d — Observation input type + store.ts extension
- Edit `src/services/sqlite/observations/types.ts:10-19` — add:
```ts
agent_type?: string | null;
agent_id?: string | null;
```
- Edit `src/services/sqlite/observations/store.ts:75-98`:
- Column list: add `, agent_type, agent_id` before `content_hash`.
- Placeholders: add `, ?, ?`.
- Bindings: add `observation.agent_type ?? null, observation.agent_id ?? null`.
- Verify there are no other `INSERT INTO observations` sites that need updating. Sites already located (to re-check):
- `src/services/sqlite/SessionStore.ts:1755` / `1890` / `2022` / `2623` — each needs the same two columns added. If these are separate insertion paths, extend all of them; pass `null` for fields not available in that path.
### 4e — SDK agent observation parser forwards fields
The SDK agent parses `<observation>` XML into an `ObservationInput` and calls `storeObservation`. The tool_input passed in must carry `agentId`/`agentType` through to here so the row gets labeled. Investigation step: find where `storeObservation()` is called with an `ObservationInput` built from the queued observation, and inject `agent_type`/`agent_id` from the queue item's subagent fields onto the `ObservationInput`. Location likely in `src/services/sdk/` or adjacent.
**Documentation references**:
- observation handler at `src/cli/handlers/observation.ts:51-62`
- SessionRoutes observations endpoint at `src/services/worker/http/routes/SessionRoutes.ts:555-646`
- storeObservation at `src/services/sqlite/observations/store.ts:75-98`
- Existing observation INSERT sites at `src/services/sqlite/SessionStore.ts:1755, 1890, 2022, 2623` (audit required)
**Verification checklist**:
- `grep -rn "agent_type\|agentType" src/` → shows fields threaded through every layer.
- Simulate a Task subagent PostToolUse payload → observation row has non-null `agent_type`.
- Main-session PostToolUse → observation row has NULL `agent_type` (existing behavior preserved).
- No existing test suite breaks: `npm test` passes.
**Anti-pattern guards**:
- Do NOT include `agent_type` / `agent_id` in the content-hash computation (`src/services/sqlite/observations/store.ts:19-28`). The hash identity must remain stable for dedup.
- Do NOT add fields to the FTS5 `observations_fts` virtual table — not searchable text.
- Do NOT backfill — leave existing rows NULL.
---
## Phase 5 — Tests and verification
**What to implement**:
1. Add a unit test at `tests/cli/handlers/summarize-subagent-skip.test.ts` verifying:
- When `input.agentId` is set, handler returns early with `exitCode: SUCCESS` and does NOT call `workerHttpRequest`.
- When `input.agentType` is set, same behavior.
- When both are undefined, handler proceeds (mock worker response).
2. Add a unit test at `tests/cli/adapters/claude-code-subagent.test.ts` verifying:
- `normalizeInput({ agent_id: "agent-abc", agent_type: "Explore" })` returns `{ agentId: "agent-abc", agentType: "Explore" }`.
- `normalizeInput({})` returns `agentId: undefined, agentType: undefined`.
3. Add a unit test at `tests/services/sqlite/observations/store-subagent-label.test.ts` verifying:
- `storeObservation` with `agent_type: "Explore"` inserts row with `agent_type = "Explore"`.
- Omitted `agent_type` → NULL in DB.
- Content-hash dedup still works (two observations with same title/narrative but different `agent_type` should still collide on dedup — verify expected behavior; update test if product intent differs).
4. Manual integration check: start worker, simulate a hook payload with `agent_id`/`agent_type`, observe observation row in DB.
**Verification checklist**:
- `npm test` passes.
- `npm run build` succeeds.
- Database inspection shows expected rows.
**Anti-pattern guards**:
- Do NOT mock the entire storeObservation — use a real in-memory Bun SQLite DB if existing tests do.
- Do NOT add integration tests that require a running worker unless the suite already does.
---
## Phase 6 — Build + autonomous execution pipeline
After Phases 1-5 land and pass verification:
1. **Build**: `npm run build-and-sync`.
2. **Commit**: a single commit titled `feat: disable subagent summaries and label subagent observations` with co-author footer.
3. **Push branch**: push current worktree branch `trail-guarantee` (or a new feature branch — confirm with `git status`). Create PR via `gh pr create` with summary of both features.
4. **Run `/loop 5m`** to continuously re-check PR review comments: as each CodeRabbit/Greptile/human comment arrives, address it in a new commit, push, and re-check. Exit loop only when all actionable review comments are resolved and status checks pass.
5. **Merge to main** via `gh pr merge --squash --auto` (or `--merge` per repo convention — inspect `.github/` first).
6. **Version bump**: `cd ~/Scripts/claude-mem/` and run `/version-bump`.
**Anti-pattern guards for this phase**:
- Do NOT force-push to main.
- Do NOT skip hooks (`--no-verify`).
- Do NOT squash-merge if the repo uses rebase-merge; check `.github/` for branch-protection hints.
- Do NOT resolve a review comment without actually addressing it — every resolved thread must have a corresponding commit or a reply explaining why no change is needed.
---
## Final Verification (end of Phase 5, before Phase 6)
- `grep -rn "agent_id\|agentId" src/` → fields present in: `types.ts`, `claude-code.ts`, `summarize.ts`, `observation.ts`, `SessionRoutes.ts`, observation types, store, migration010.
- `grep -rn "subagent_context" src/services/worker/` → worker-side guard present.
- `sqlite3 ~/.claude-mem/claude-mem.db "PRAGMA table_info(observations);"` → includes `agent_type`, `agent_id`.
- `npm test && npm run build` → both green.
- Smoke test: simulate a subagent hook payload end-to-end → observation labeled, no summary fired.
ANTI-PATTERN-TODO.md
+488
View File
@@ -0,0 +1,488 @@
# Anti-Pattern Fix Checklist
**Total: 301 issues | Fixed: 289 | Approved Overrides: 12 | Remaining: 0**
**Detector passes clean: 0 issues to fix**
Every item gets fixed (logging added, try block narrowed, catch made specific, or error propagated) OR approved with a specific technical reason.
---
## src/services/worker-service.ts (14 issues)
- [x] :291 GENERIC_CATCH
- [x] :291 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :375 LARGE_TRY_BLOCK
- [x] :388 GENERIC_CATCH
- [x] :388 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :489 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :536 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :574 LARGE_TRY_BLOCK
- [x] :592 GENERIC_CATCH
- [x] :592 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :696 ERROR_MESSAGE_GUESSING
- [x] :837 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :849 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :912 LARGE_TRY_BLOCK
- [x] :941 GENERIC_CATCH
- [x] :941 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :961 LARGE_TRY_BLOCK
- [x] :979 GENERIC_CATCH
- [x] :979 CATCH_AND_CONTINUE_CRITICAL_PATH
## src/services/sqlite/SessionStore.ts (7 issues)
- [x] :449 LARGE_TRY_BLOCK
- [x] :477 GENERIC_CATCH
- [x] :477 CATCH_AND_CONTINUE_CRITICAL_PATH
- [x] :689 LARGE_TRY_BLOCK
- [x] :848 GENERIC_CATCH
- [x] :2302 GENERIC_CATCH
- [x] :2334 GENERIC_CATCH
## src/services/worker/SDKAgent.ts (1 issue)
- [x] :481 GENERIC_CATCH
## src/services/worker/GeminiAgent.ts (1 issue)
- [x] :138 LARGE_TRY_BLOCK
## src/services/worker/OpenRouterAgent.ts (1 issue)
- [x] :87 LARGE_TRY_BLOCK
## src/services/infrastructure/ProcessManager.ts (20 issues)
- [x] :56 LARGE_TRY_BLOCK
- [x] :69 NO_LOGGING_IN_CATCH
- [x] :205 GENERIC_CATCH
- [x] :219 GENERIC_CATCH
- [x] :263 GENERIC_CATCH
- [x] :290 GENERIC_CATCH
- [x] :307 GENERIC_CATCH
- [x] :307 NO_LOGGING_IN_CATCH (APPROVED OVERRIDE exists — review)
- [x] :375 LARGE_TRY_BLOCK
- [x] :443 GENERIC_CATCH
- [x] :470 GENERIC_CATCH
- [x] :479 GENERIC_CATCH
- [x] :525 LARGE_TRY_BLOCK
- [x] :608 GENERIC_CATCH
- [x] :628 GENERIC_CATCH
- [x] :636 GENERIC_CATCH
- [x] :751 LARGE_TRY_BLOCK
- [x] :828 GENERIC_CATCH
- [x] :899 GENERIC_CATCH
- [x] :963 NO_LOGGING_IN_CATCH
- [x] :963 GENERIC_CATCH
- [x] :986 NO_LOGGING_IN_CATCH
- [x] :1035 GENERIC_CATCH
## src/services/infrastructure/HealthMonitor.ts (3 issues)
- [x] :56 NO_LOGGING_IN_CATCH
- [x] :93 GENERIC_CATCH
- [x] :168 GENERIC_CATCH
## src/services/infrastructure/WorktreeAdoption.ts (3 issues)
- [x] :253 LARGE_TRY_BLOCK
- [x] :285 GENERIC_CATCH
- [x] :301 GENERIC_CATCH
## src/services/worker/SessionManager.ts (5 issues)
- [x] :72 NO_LOGGING_IN_CATCH
- [x] :294 GENERIC_CATCH
- [x] :345 GENERIC_CATCH
- [x] :399 GENERIC_CATCH
- [x] :471 GENERIC_CATCH
## src/services/worker/ProcessRegistry.ts (2 issues)
- [x] :398 NO_LOGGING_IN_CATCH
- [x] :497 GENERIC_CATCH
## src/services/worker/SearchManager.ts (8 issues)
- [x] :442 LARGE_TRY_BLOCK
- [x] :458 GENERIC_CATCH
- [x] :692 LARGE_TRY_BLOCK
- [x] :726 GENERIC_CATCH
- [x] :766 LARGE_TRY_BLOCK
- [x] :794 GENERIC_CATCH
- [x] :1375 GENERIC_CATCH
- [x] :1390 GENERIC_CATCH
## src/services/worker/BranchManager.ts (5 issues)
- [x] :121 LARGE_TRY_BLOCK
- [x] :139 GENERIC_CATCH
- [x] :244 GENERIC_CATCH
- [x] :269 LARGE_TRY_BLOCK
- [x] :301 GENERIC_CATCH
## src/services/worker/SettingsManager.ts (1 issue)
- [x] :45 GENERIC_CATCH
## src/services/worker/PaginationHelper.ts (1 issue)
- [x] :57 GENERIC_CATCH
## src/services/worker/knowledge/KnowledgeAgent.ts (4 issues)
- [x] :94 GENERIC_CATCH
- [x] :133 GENERIC_CATCH
- [x] :206 GENERIC_CATCH
- [x] :261 GENERIC_CATCH
## src/services/worker/knowledge/CorpusStore.ts (2 issues)
- [x] :48 GENERIC_CATCH
- [x] :75 GENERIC_CATCH
## src/services/worker/knowledge/CorpusBuilder.ts (1 issue)
- [x] :26 NO_LOGGING_IN_CATCH
## src/services/worker/http/BaseRouteHandler.ts (1 issue)
- [x] :29 GENERIC_CATCH
## src/services/worker/http/routes/SearchRoutes.ts (2 issues)
- [x] :272 LARGE_TRY_BLOCK
- [x] :297 GENERIC_CATCH
## src/services/worker/http/routes/SettingsRoutes.ts (1 issue)
- [x] :76 GENERIC_CATCH
## src/services/worker/http/routes/SessionRoutes.ts (5 issues)
- [x] :223 PROMISE_CATCH_NO_LOGGING
- [x] :259 GENERIC_CATCH
- [x] :288 LARGE_TRY_BLOCK
- [x] :589 LARGE_TRY_BLOCK
- [x] :643 GENERIC_CATCH
## src/services/worker/http/routes/CorpusRoutes.ts (1 issue)
- [x] :96 NO_LOGGING_IN_CATCH
## src/services/worker/http/routes/ViewerRoutes.ts (1 issue)
- [x] :74 NO_LOGGING_IN_CATCH
## src/services/worker/search/strategies/ChromaSearchStrategy.ts (2 issues)
- [x] :66 LARGE_TRY_BLOCK
- [x] :140 GENERIC_CATCH
## src/services/worker/search/strategies/HybridSearchStrategy.ts (6 issues)
- [x] :71 LARGE_TRY_BLOCK
- [x] :113 GENERIC_CATCH
- [x] :137 LARGE_TRY_BLOCK
- [x] :178 GENERIC_CATCH
- [x] :204 LARGE_TRY_BLOCK
- [x] :244 GENERIC_CATCH
## src/services/worker/search/strategies/SQLiteSearchStrategy.ts (2 issues)
- [x] :67 LARGE_TRY_BLOCK
- [x] :99 GENERIC_CATCH
## src/services/queue/SessionQueueProcessor.ts (2 issues)
- [x] :37 LARGE_TRY_BLOCK
- [x] :67 GENERIC_CATCH
## src/services/sync/ChromaMcpManager.ts (6 issues)
- [x] :79 GENERIC_CATCH
- [x] :310 NO_LOGGING_IN_CATCH
- [x] :325 NO_LOGGING_IN_CATCH
- [x] :344 GENERIC_CATCH
- [x] :397 NO_LOGGING_IN_CATCH
- [x] :411 NO_LOGGING_IN_CATCH
## src/services/sync/ChromaSync.ts (5 issues)
- [x] :565 LARGE_TRY_BLOCK
- [x] :731 LARGE_TRY_BLOCK
- [x] :788 ERROR_STRING_MATCHING
- [x] :789 ERROR_STRING_MATCHING
- [x] :828 GENERIC_CATCH
## src/services/context/ContextBuilder.ts (1 issue)
- [x] :52 GENERIC_CATCH
## src/services/context/ObservationCompiler.ts (2 issues)
- [x] :228 LARGE_TRY_BLOCK
- [x] :248 GENERIC_CATCH
## src/services/server/Server.ts (3 issues)
- [x] :211 LARGE_TRY_BLOCK
- [x] :235 NO_LOGGING_IN_CATCH
- [x] :235 GENERIC_CATCH
## src/services/worker-spawner.ts (1 issue)
- [x] :56 NO_LOGGING_IN_CATCH
## src/services/smart-file-read/search.ts (2 issues)
- [x] :81 NO_LOGGING_IN_CATCH
- [x] :117 NO_LOGGING_IN_CATCH
## src/services/smart-file-read/parser.ts (5 issues)
- [x] :162 NO_LOGGING_IN_CATCH
- [x] :277 NO_LOGGING_IN_CATCH
- [x] :284 NO_LOGGING_IN_CATCH
- [x] :553 NO_LOGGING_IN_CATCH
- [x] :588 NO_LOGGING_IN_CATCH
## src/services/sqlite/migrations/runner.ts (4 issues)
- [x] :421 LARGE_TRY_BLOCK
- [x] :449 GENERIC_CATCH
- [x] :661 LARGE_TRY_BLOCK
- [x] :817 GENERIC_CATCH
## src/services/sqlite/migrations.ts (1 issue)
- [x] :381 NO_LOGGING_IN_CATCH
## src/services/sqlite/observations/files.ts (1 issue)
- [x] :20 NO_LOGGING_IN_CATCH
## src/services/sqlite/timeline/queries.ts (2 issues)
- [x] :114 GENERIC_CATCH
- [x] :146 GENERIC_CATCH
## src/services/sqlite/SessionSearch.ts (5 issues)
- [x] :77 LARGE_TRY_BLOCK
- [x] :161 GENERIC_CATCH
- [x] :176 NO_LOGGING_IN_CATCH
- [x] :384 NO_LOGGING_IN_CATCH
- [x] :402 NO_LOGGING_IN_CATCH
## src/services/transcripts/watcher.ts (4 issues)
- [x] :46 NO_LOGGING_IN_CATCH
- [x] :155 NO_LOGGING_IN_CATCH
- [x] :183 NO_LOGGING_IN_CATCH
- [x] :219 GENERIC_CATCH
## src/services/transcripts/processor.ts (3 issues)
- [x] :280 NO_LOGGING_IN_CATCH
- [x] :325 LARGE_TRY_BLOCK
- [x] :355 LARGE_TRY_BLOCK
## src/services/transcripts/field-utils.ts (1 issue)
- [x] :145 NO_LOGGING_IN_CATCH
## src/services/integrations/CursorHooksInstaller.ts (11 issues)
- [x] :118 GENERIC_CATCH
- [x] :260 GENERIC_CATCH
- [x] :311 LARGE_TRY_BLOCK
- [x] :381 GENERIC_CATCH
- [x] :402 LARGE_TRY_BLOCK
- [x] :419 GENERIC_CATCH
- [x] :459 LARGE_TRY_BLOCK
- [x] :503 GENERIC_CATCH
- [x] :538 LARGE_TRY_BLOCK
- [x] :565 NO_LOGGING_IN_CATCH
- [x] :602 GENERIC_CATCH
## src/services/integrations/GeminiCliHooksInstaller.ts (6 issues)
- [x] :164 GENERIC_CATCH
- [x] :289 LARGE_TRY_BLOCK
- [x] :334 GENERIC_CATCH
- [x] :350 LARGE_TRY_BLOCK
- [x] :403 GENERIC_CATCH
- [x] :427 NO_LOGGING_IN_CATCH
- [x] :427 GENERIC_CATCH
## src/services/integrations/OpenCodeInstaller.ts (3 issues)
- [x] :166 LARGE_TRY_BLOCK
- [x] :214 LARGE_TRY_BLOCK
- [x] :312 LARGE_TRY_BLOCK
## src/services/integrations/OpenClawInstaller.ts (2 issues)
- [x] :149 NO_LOGGING_IN_CATCH
- [x] :253 LARGE_TRY_BLOCK
## src/services/integrations/WindsurfHooksInstaller.ts (13 issues)
- [x] :88 GENERIC_CATCH
- [x] :152 GENERIC_CATCH
- [x] :237 GENERIC_CATCH
- [x] :289 LARGE_TRY_BLOCK
- [x] :321 GENERIC_CATCH
- [x] :337 LARGE_TRY_BLOCK
- [x] :352 GENERIC_CATCH
- [x] :386 LARGE_TRY_BLOCK
- [x] :409 NO_LOGGING_IN_CATCH
- [x] :409 GENERIC_CATCH
- [x] :448 LARGE_TRY_BLOCK
- [x] :459 NO_LOGGING_IN_CATCH
## src/services/integrations/McpIntegrations.ts (4 issues)
- [x] :108 LARGE_TRY_BLOCK
- [x] :148 GENERIC_CATCH
- [x] :277 LARGE_TRY_BLOCK
- [x] :337 GENERIC_CATCH
## src/services/integrations/CodexCliInstaller.ts (9 issues)
- [x] :69 GENERIC_CATCH
- [x] :138 LARGE_TRY_BLOCK
- [x] :161 GENERIC_CATCH
- [x] :187 LARGE_TRY_BLOCK
- [x] :216 GENERIC_CATCH
- [x] :237 LARGE_TRY_BLOCK
- [x] :265 GENERIC_CATCH
- [x] :291 LARGE_TRY_BLOCK
- [x] :337 NO_LOGGING_IN_CATCH
## src/services/domain/ModeManager.ts (3 issues)
- [x] :146 GENERIC_CATCH
- [x] :163 GENERIC_CATCH
- [x] :173 GENERIC_CATCH
## src/supervisor/process-registry.ts (5 issues)
- [x] :35 NO_LOGGING_IN_CATCH
- [x] :35 GENERIC_CATCH
- [x] :68 GENERIC_CATCH
- [x] :170 GENERIC_CATCH
- [x] :197 GENERIC_CATCH
## src/supervisor/shutdown.ts (6 issues)
- [x] :38 GENERIC_CATCH
- [x] :52 GENERIC_CATCH
- [x] :71 GENERIC_CATCH
- [x] :94 GENERIC_CATCH
- [x] :139 GENERIC_CATCH
- [x] :154 NO_LOGGING_IN_CATCH
## src/supervisor/index.ts (2 issues)
- [x] :72 GENERIC_CATCH
- [x] :164 GENERIC_CATCH
## src/cli/hook-command.ts (1 issue)
- [x] :75 LARGE_TRY_BLOCK
## src/cli/stdin-reader.ts (4 issues)
- [x] :32 NO_LOGGING_IN_CATCH
- [x] :52 NO_LOGGING_IN_CATCH
- [x] :131 LARGE_TRY_BLOCK
- [x] :170 NO_LOGGING_IN_CATCH
## src/cli/claude-md-commands.ts (12 issues)
- [x] :79 LARGE_TRY_BLOCK
- [x] :97 GENERIC_CATCH
- [x] :144 NO_LOGGING_IN_CATCH
- [x] :190 NO_LOGGING_IN_CATCH
- [x] :203 NO_LOGGING_IN_CATCH
- [x] :319 LARGE_TRY_BLOCK
- [x] :345 NO_LOGGING_IN_CATCH
- [x] :345 GENERIC_CATCH
- [x] :357 LARGE_TRY_BLOCK
- [x] :430 GENERIC_CATCH
- [x] :508 LARGE_TRY_BLOCK
- [x] :525 GENERIC_CATCH
## src/cli/handlers/session-complete.ts (2 issues)
- [x] :38 LARGE_TRY_BLOCK
- [x] :58 GENERIC_CATCH
## src/cli/handlers/user-message.ts (1 issue)
- [x] :28 LARGE_TRY_BLOCK
## src/cli/handlers/context.ts (1 issue)
- [x] :48 LARGE_TRY_BLOCK
## src/cli/handlers/file-context.ts (3 issues)
- [x] :202 NO_LOGGING_IN_CATCH
- [x] :202 GENERIC_CATCH
- [x] :221 LARGE_TRY_BLOCK
## src/cli/handlers/summarize.ts (1 issue)
- [x] :111 LARGE_TRY_BLOCK
## src/cli/handlers/session-init.ts (1 issue)
- [x] :134 LARGE_TRY_BLOCK
## src/cli/handlers/file-edit.ts (1 issue)
- [x] :41 LARGE_TRY_BLOCK
## src/cli/handlers/observation.ts (1 issue)
- [x] :50 LARGE_TRY_BLOCK
## src/ui/viewer/hooks/useStats.ts (1 issue)
- [x] :13 GENERIC_CATCH
## src/ui/viewer/hooks/useTheme.ts (2 issues)
- [x] :19 GENERIC_CATCH
- [x] :64 GENERIC_CATCH
## src/ui/viewer/hooks/useContextPreview.ts (3 issues)
- [x] :40 LARGE_TRY_BLOCK
- [x] :63 GENERIC_CATCH
- [x] :108 NO_LOGGING_IN_CATCH
## src/bin/import-xml-observations.ts (7 issues)
- [x] :62 LARGE_TRY_BLOCK
- [x] :134 LARGE_TRY_BLOCK
- [x] :152 GENERIC_CATCH
- [x] :167 LARGE_TRY_BLOCK
- [x] :183 GENERIC_CATCH
- [x] :329 GENERIC_CATCH
- [x] :361 GENERIC_CATCH
## src/utils/project-filter.ts (1 issue)
- [x] :66 NO_LOGGING_IN_CATCH
## src/utils/worktree.ts (2 issues)
- [x] :41 NO_LOGGING_IN_CATCH
- [x] :55 NO_LOGGING_IN_CATCH
## src/utils/claude-md-utils.ts (2 issues)
- [x] :442 LARGE_TRY_BLOCK
- [x] :475 GENERIC_CATCH
## src/utils/logger.ts (5 issues)
- [x] :63 GENERIC_CATCH
- [x] :87 NO_LOGGING_IN_CATCH
- [x] :87 GENERIC_CATCH
- [x] :155 NO_LOGGING_IN_CATCH
- [x] :292 GENERIC_CATCH
## src/utils/json-utils.ts (1 issue)
- [x] :24 GENERIC_CATCH
## src/utils/agents-md-utils.ts (1 issue)
- [x] :34 GENERIC_CATCH
## src/shared/timeline-formatting.ts (1 issue)
- [x] :19 GENERIC_CATCH
## src/shared/plugin-state.ts (1 issue)
- [x] :25 NO_LOGGING_IN_CATCH
## src/shared/worker-utils.ts (2 issues)
- [x] :150 GENERIC_CATCH
- [x] :179 LARGE_TRY_BLOCK
## src/shared/SettingsDefaultsManager.ts (2 issues)
- [x] :224 GENERIC_CATCH
- [x] :244 GENERIC_CATCH
## src/shared/EnvManager.ts (3 issues)
- [x] :124 GENERIC_CATCH
- [x] :134 LARGE_TRY_BLOCK
- [x] :186 GENERIC_CATCH
## src/shared/paths.ts (1 issue)
- [x] :149 GENERIC_CATCH
## src/sdk/prompts.ts (2 issues)
- [x] :112 GENERIC_CATCH
- [x] :121 GENERIC_CATCH
## src/npx-cli/utils/bun-resolver.ts (1 issue)
- [x] :82 NO_LOGGING_IN_CATCH
## src/npx-cli/commands/install.ts (4 issues)
- [x] :131 NO_LOGGING_IN_CATCH
- [x] :375 NO_LOGGING_IN_CATCH
- [x] :412 NO_LOGGING_IN_CATCH
- [x] :501 NO_LOGGING_IN_CATCH
## src/npx-cli/commands/uninstall.ts (1 issue)
- [x] :123 NO_LOGGING_IN_CATCH
## src/npx-cli/commands/runtime.ts (2 issues)
- [x] :157 LARGE_TRY_BLOCK
- [x] :177 GENERIC_CATCH
## src/npx-cli/commands/ide-detection.ts (2 issues)
- [x] :41 NO_LOGGING_IN_CATCH
- [x] :56 NO_LOGGING_IN_CATCH
## src/servers/mcp-server.ts (4 issues)
- [x] :111 LARGE_TRY_BLOCK
- [x] :156 LARGE_TRY_BLOCK
- [x] :198 GENERIC_CATCH
- [x] :232 GENERIC_CATCH
## src/integrations/opencode-plugin/index.ts (3 issues)
- [x] :108 LARGE_TRY_BLOCK
- [x] :342 LARGE_TRY_BLOCK
- [x] :357 NO_LOGGING_IN_CATCH
CHANGELOG.md
+125
View File
@@ -4,6 +4,131 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/). The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
##
✅ CHANGELOG.md generated successfully!
237 new release(s) prepended
e resolves error handling anti-patterns across the entire codebase (91 files), improving resilience and correctness.
### Bug Fixes
- **OpenRouterAgent**: Restored assistant replies to `conversationHistory` — multi-turn context was lost after method extraction (#2078)
- **ChromaSync**: Fixed cross-type dedup collision where `observation#N`, `session_summary#N`, and `user_prompt#N` could silently drop results
- **Timeline queries**: Fixed logger calls wrapping Error inside an object instead of passing directly
- **FTS migrations**: Preserved non-Error failure details instead of silently dropping them
### Error Handling Improvements
- Replaced 301 error handling anti-patterns across 91 files:
- Narrowed overly broad try-catch blocks into focused error boundaries
- Replaced unsafe `error as Error` casts with `instanceof` checks
- Added structured error logging where catches were previously empty
- Extracted large try blocks into dedicated helper methods
- **Installer resilience**: Moved filesystem operations (`mkdirSync`) inside try/catch in Cursor, Gemini CLI, Goose MCP, and OpenClaw installers to maintain numeric return-code contracts
- **GeminiCliHooksInstaller**: Install/uninstall paths now catch `readGeminiSettings()` failures instead of throwing past the `0/1` return contract
- **OpenClawInstaller**: Malformed `openclaw.json` now throws instead of silently returning `{}` and potentially wiping user config
- **WindsurfHooksInstaller**: Added null-safe parsing of `hooks.json` with optional chaining
- **McpIntegrations**: Goose YAML updater now throws when claude-mem markers exist but regex replacement fails
- **EnvManager**: Directory setup and existing-file reads are now wrapped in structured error logging
- **WorktreeAdoption**: `adoptedSqliteIds` mutation delayed until SQL update succeeds
- **Import script**: Guard against malformed timestamps before `toISOString()`
- **Runtime CLI**: Guard `response.json()` parsing with controlled error output
### Documentation
- Added README for Docker claude-mem harness
## [12.3.0] - 2026-04-20
## New features
### Basic claude-mem Docker container (`docker/claude-mem/`)
A ready-to-run container for ad-hoc claude-mem testing with zero local setup beyond Docker.
- `FROM node:20`; layers pinned Bun (1.3.12) + uv (0.11.7) + the built plugin
- Non-root `node` user so `--permission-mode bypassPermissions` works headlessly
- `build.sh`, `run.sh` (auto-extracts OAuth from macOS Keychain or `~/.claude/.credentials.json`, falls back to `ANTHROPIC_API_KEY`), `entrypoint.sh`
- Persistent `.claude-mem/` mount so the observations DB survives container exit
Validated end-to-end: `PostToolUse` hook → queue → worker SDK call under subscription OAuth → `<observation>` XML → `observations` table → Chroma sync.
### SWE-bench evaluation harness (`evals/swebench/`)
Two-container split (our agent image + the upstream SWE-bench harness) for measuring claude-mem's effect on resolve rate.
- `Dockerfile.agent` → `claude-mem/swebench-agent:latest` (same non-root, version-pinned approach)
- `run-instance.sh` — two-turn ingest/fix protocol per instance; shallow clone at `base_commit` with full-clone fallback
- `run-batch.py` — parallel orchestrator with OAuth extraction, per-container naming, timeout enforcement + force-cleanup, `--overwrite` guard against silent truncation of partial results
- `eval.sh` — wraps `python -m swebench.harness.run_evaluation`
- `summarize.py` — aggregates per-instance reports
- `smoke-test.sh` — one-instance smoke test
### Fixes / hardening (from PR review)
- `chmod 600` on extracted OAuth creds files
- Grouped `{ chmod || true; }` so bash precedence can't mask failed `curl|sh` installs
- macOS creds: Keychain-first with file fallback for migrated / older setups
- `smoke-test.sh` `TIMEOUT` now actually enforced via `timeout`/`gtimeout` plus `docker rm -f` on exit 124
- Container naming + force-cleanup in `run-batch.py` timeout handler prevents orphan containers
- Fixed stdin-redirection collision in the consolidated `smoke-test.sh` JSON parser
- Drop `exec` in `run.sh` so the EXIT trap fires and cleans the temp creds file
**PR:** https://github.com/thedotmack/claude-mem/pull/2076
## [12.2.3] - 2026-04-19
## Fixed
- **Parser: stop warning on normal observation responses (#2074).** Eliminated the `PARSER Summary response contained <observation> tags instead of <summary> — prompt conditioning may need strengthening` warning that fired on every normal observation turn. The warning was inherited from #1345 when `parseSummary` was only called after summary prompts; after #1633's refactor it runs on every response, so the observation-only fallthrough always tripped. Gated the entire observation-on-summary path on `coerceFromObservation` so only genuine summary-turn coercion failures log.
**Full diff:** https://github.com/thedotmack/claude-mem/compare/v12.2.2...v12.2.3
## [12.2.2] - 2026-04-19
## Subagent summary disable + labeling
Claude Code subagents (the Task tool and built-in agents like Explore/Plan/Bash) no longer trigger a session summary on Stop, and every observation row now carries the originating subagent's identity.
### Features
- **Subagent Stop hooks skip summarization.** When a hook fires inside a subagent (identified by `agent_id` on stdin), the handler short-circuits before bootstrapping the worker. Only the main assistant owns the session summary. Sessions started with `--agent` (which set `agent_type` but not `agent_id`) still own their summary.
- **Observations are labeled by subagent.** The `observations` table gains two new nullable columns — `agent_type` and `agent_id` — populated end-to-end from the hook stdin through the pending queue into storage. Main-session rows remain `NULL`. Labels survive worker restarts via matching columns on `pending_messages`.
### Safety
- Defense-in-depth guard on the worker `/api/sessions/summarize` route so direct API callers can't bypass the hook-layer short-circuit.
- `pickAgentField` type guard at the adapter edge validates the hook input: must be a non-empty string ≤128 characters, otherwise dropped.
- Content-hash dedup intentionally excludes `agent_type`/`agent_id` so the same semantic observation from a subagent and its parent merges to a single row.
### Schema
- Migration 010 (version 27) adds the two columns to `observations` and `pending_messages`, plus indexes on `observations.agent_type` and `observations.agent_id`. Idempotent, state-aware logging.
### Tests
- 17 new unit tests: adapter extraction (length cap boundary, empty-string rejection, type guards), handler short-circuit behavior, DB-level labeling and dedup invariants.
PR: #2073
## [12.2.1] - 2026-04-19
## What's Fixed
### Break infinite summary-retry loop (#1633)
When the summary agent returned `<observation>` tags instead of `<summary>` tags, the parser rejected the response, no summary was stored, the session completed without a summary, and a new session was spawned with ~5–6 KB of extra prompt context — repeating indefinitely.
**Three layers of defense (PR #2072):**
- **Parser coercion** — when a summary is expected, observation fields are mapped to summary fields (title → request/completed, narrative → investigated, facts → learned) instead of discarding the response.
- **Stronger prompt** — summary prompts now include an explicit tag-requirement block and a closing reminder so the LLM is much less likely to emit observation tags in the first place.
- **Circuit breaker** — per-session counter caps consecutive summary failures at 3; further summarize requests are skipped until a success resets it. Explicit `<skip_summary/>` responses are treated as neutral, not failures.
**Edge cases handled:**
- Empty leading `<observation>` blocks fall through to the first populated one.
- Empty `<summary></summary>` wrappers fall back to observation coercion.
- Multiple observation blocks are iterated via a global regex.
Full details: #2072
## [12.2.0] - 2026-04-18 ## [12.2.0] - 2026-04-18
## Highlights ## Highlights
docker/claude-mem/Dockerfile
+93
View File
@@ -0,0 +1,93 @@
# Basic claude-mem container for ad-hoc testing.
#
# Base layout mirrors anthropics/claude-code .devcontainer
# (https://github.com/anthropics/claude-code/blob/main/.devcontainer/Dockerfile):
# FROM node:20, non-root `node` user, global npm install of @anthropic-ai/claude-code.
# We skip the firewall/zsh/fzf/delta/git-hist noise since this image is for
# exercising claude-mem, not as a full dev environment.
#
# On top of that base we install:
# - Bun (claude-mem worker service runtime)
# - uv (provides Python for Chroma per CLAUDE.md)
# - The locally-built plugin/ tree at /opt/claude-mem
#
# Usage:
# docker build -f docker/claude-mem/Dockerfile -t claude-mem:basic .
# docker run --rm -it \
# -v $(mktemp -d):/home/node/.claude-mem \
# -e CLAUDE_MEM_CREDENTIALS_FILE=/auth/.credentials.json \
# -v /path/to/extracted/creds.json:/auth/.credentials.json:ro \
# claude-mem:basic
FROM node:20
ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
git \
curl \
ca-certificates \
unzip \
jq \
less \
procps \
uuid-runtime \
sqlite3 \
&& apt-get clean && rm -rf /var/lib/apt/lists/*
# Bun — system-wide so the unprivileged `node` user can execute it.
# Pin via --build-arg BUN_VERSION=X.Y.Z; default is the version verified at PR time.
ARG BUN_VERSION=1.3.12
ENV BUN_INSTALL="/usr/local/bun"
RUN curl -fsSL https://bun.sh/install | bash -s "bun-v${BUN_VERSION}" \
&& chmod -R a+rX /usr/local/bun
ENV PATH="/usr/local/bun/bin:${PATH}"
# uv — system-wide, for Chroma's Python runtime. Pin via --build-arg UV_VERSION=X.Y.Z.
# Versioned installer URL per https://docs.astral.sh/uv/getting-started/installation/.
ARG UV_VERSION=0.11.7
ENV UV_INSTALL_DIR="/usr/local/bin"
# `&&` binds tighter than `||` in bash, so the previous form let `curl|sh` fail
# silently via the trailing `|| true`. Group the chmod so tolerated failure is
# scoped to perms-fixing only.
RUN set -eux \
&& curl -LsSf "https://astral.sh/uv/${UV_VERSION}/install.sh" | sh \
&& { chmod a+rX /usr/local/bin/uv /usr/local/bin/uvx 2>/dev/null || true; }
# Match the upstream devcontainer's npm-global prefix so `npm install -g`
# targets a dir the `node` user owns.
RUN mkdir -p /usr/local/share/npm-global \
&& chown -R node:node /usr/local/share/npm-global
ENV NPM_CONFIG_PREFIX=/usr/local/share/npm-global
ENV PATH="/usr/local/share/npm-global/bin:${PATH}"
# Claude Code CLI. Override at build-time with --build-arg CLAUDE_CODE_VERSION=X.Y.Z
# to pin; default tracks latest.
ARG CLAUDE_CODE_VERSION=latest
USER node
RUN npm install -g @anthropic-ai/claude-code@${CLAUDE_CODE_VERSION}
# Locally-built claude-mem plugin. COPY runs as root by default and layers are
# cached, so put this after the npm install so iterating on the plugin doesn't
# invalidate the CLI install layer.
USER root
COPY plugin/ /opt/claude-mem/
RUN chown -R node:node /opt/claude-mem
# Persistent mount points for ad-hoc testing — mount a host dir at either of
# these to inspect the claude-mem DB after a session.
RUN mkdir -p /home/node/.claude /home/node/.claude-mem \
&& chown -R node:node /home/node/.claude /home/node/.claude-mem
USER node
WORKDIR /home/node
# Helper: copies OAuth creds out of the read-only mount into $HOME/.claude/
# before exec'ing whatever you asked for. Saves the "cp + chmod" dance every
# time you drop in.
COPY --chown=node:node docker/claude-mem/entrypoint.sh /usr/local/bin/claude-mem-entrypoint
RUN chmod +x /usr/local/bin/claude-mem-entrypoint
ENTRYPOINT ["/usr/local/bin/claude-mem-entrypoint"]
CMD ["bash"]
docker/claude-mem/README.md
+135
View File
@@ -0,0 +1,135 @@
# claude-mem Docker harness
A minimal container for exercising claude-mem end-to-end without polluting your
host. Not a dev environment — just enough to boot `claude` with the locally-built
plugin and capture observations into a throwaway SQLite DB you can inspect
afterwards.
## Files
| File | Purpose |
|------|---------|
| `Dockerfile` | Image definition (node:20 + Bun + uv + Claude Code CLI + local `plugin/`) |
| `build.sh` | Runs `npm run build` then `docker build`. Tag defaults to `claude-mem:basic`. |
| `entrypoint.sh` | Runs inside the container. Seeds OAuth creds into `$HOME/.claude/` if mounted, then `exec "$@"`. |
| `run.sh` | Host-side launcher. Extracts creds (Keychain → file → env), mounts a persistent data dir, drops you into an interactive shell. |
## Quick start
```bash
# From the repo root:
docker/claude-mem/build.sh
docker/claude-mem/run.sh
```
`run.sh` drops you into `bash` inside the container with `claude` on `PATH` and
the plugin pre-staged at `/opt/claude-mem`. Launch it with:
```bash
claude --plugin-dir /opt/claude-mem
```
On exit, the SQLite DB survives at `./.docker-claude-mem-data/claude-mem.db` on
the host — inspect with:
```bash
sqlite3 .docker-claude-mem-data/claude-mem.db 'select count(*) from observations'
```
## What's in the image
Mirrors the layout of [anthropics/claude-code's devcontainer](https://github.com/anthropics/claude-code/blob/main/.devcontainer/Dockerfile):
`FROM node:20`, non-root `node` user, global `npm install -g @anthropic-ai/claude-code`.
Skips the firewall/zsh/fzf/delta/git-hist tooling since this image is about
running claude-mem, not editing code.
On top of that:
- **Bun** (`/usr/local/bun`) — claude-mem's worker service runtime
- **uv** (`/usr/local/bin/uv`) — provides Python for Chroma per `CLAUDE.md`
- **`plugin/`** copied to `/opt/claude-mem` — the locally-built plugin tree
- **`/home/node/.claude`** and **`/home/node/.claude-mem`** — pre-created mount points
Layer ordering is deliberate: plugin files are copied **after** the `npm install`
layer so iterating on the plugin doesn't bust the CLI install cache.
## Pinning versions
Everything that matters is a `--build-arg` — pin for reproducibility, omit for
latest:
```bash
docker build \
-f docker/claude-mem/Dockerfile \
--build-arg BUN_VERSION=1.3.12 \
--build-arg UV_VERSION=0.11.7 \
--build-arg CLAUDE_CODE_VERSION=1.2.3 \
-t claude-mem:basic .
```
| Arg | Default | Notes |
|-----|---------|-------|
| `BUN_VERSION` | `1.3.12` | Installed via the official `bun.sh/install` script, tag `bun-v${BUN_VERSION}`. |
| `UV_VERSION` | `0.11.7` | Installed via the versioned `astral.sh/uv/${UV_VERSION}/install.sh`. |
| `CLAUDE_CODE_VERSION` | `latest` | npm tag or exact version. Pin in CI, let it float locally. |
## Authentication
`run.sh` picks the first auth source that works, in this order:
1. **`ANTHROPIC_API_KEY`** env var — mounted straight into the container.
2. **macOS Keychain** — `security find-generic-password -s 'Claude Code-credentials'`.
3. **`~/.claude/.credentials.json`** — legacy on-disk form, still present on some
older CLI installs and migrated machines.
If a credentials file is used, it's written to a `mktemp` file with `chmod 600`,
mounted read-only at `/auth/.credentials.json`, and the container's entrypoint
copies it to `$HOME/.claude/.credentials.json` before exec. An `EXIT` trap
deletes the temp file when `run.sh` returns — `docker run` is deliberately **not**
`exec`'d so the trap gets a chance to fire.
If no auth source is found, `run.sh` exits with an error pointing you at
`claude login` or `ANTHROPIC_API_KEY`.
## Manual invocation (without `run.sh`)
```bash
docker run --rm -it \
-v $(mktemp -d):/home/node/.claude-mem \
-e CLAUDE_MEM_CREDENTIALS_FILE=/auth/.credentials.json \
-v /path/to/creds.json:/auth/.credentials.json:ro \
claude-mem:basic
```
Or with API key auth:
```bash
docker run --rm -it \
-v $(mktemp -d):/home/node/.claude-mem \
-e ANTHROPIC_API_KEY \
claude-mem:basic
```
## Environment variables
| Var | Where | Purpose |
|-----|-------|---------|
| `TAG` | `build.sh`, `run.sh` | Override image tag (default `claude-mem:basic`). |
| `HOST_MEM_DIR` | `run.sh` | Override host path for the persistent `.claude-mem` volume (default `$REPO_ROOT/.docker-claude-mem-data`). |
| `ANTHROPIC_API_KEY` | `run.sh`, entrypoint | API-key auth. Skips the OAuth creds extraction. |
| `CLAUDE_MEM_CREDENTIALS_FILE` | entrypoint | Path (inside the container) to a mounted OAuth creds JSON. Copied to `$HOME/.claude/.credentials.json` at startup. |
## Passing args through
Anything after `run.sh` is forwarded to the container as the command:
```bash
docker/claude-mem/run.sh claude --plugin-dir /opt/claude-mem --print "what did we learn yesterday?"
```
## Cleanup
```bash
rm -rf .docker-claude-mem-data # wipes the persistent DB + Chroma store
docker rmi claude-mem:basic # removes the image
```
docker/claude-mem/build.sh
Executable
+24
View File
@@ -0,0 +1,24 @@
#!/usr/bin/env bash
# Build the basic claude-mem Docker image from the current worktree.
#
# Usage:
# docker/claude-mem/build.sh # builds claude-mem:basic
# TAG=my-tag docker/claude-mem/build.sh # override the tag
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
TAG="${TAG:-claude-mem:basic}"
cd "$REPO_ROOT"
echo "[build] npm run build"
npm run build
echo "[build] docker build -t $TAG"
docker build \
-f docker/claude-mem/Dockerfile \
-t "$TAG" \
"$REPO_ROOT"
echo "[build] done: $TAG"
docker/claude-mem/entrypoint.sh
Executable
+28
View File
@@ -0,0 +1,28 @@
#!/usr/bin/env bash
# Entrypoint for the basic claude-mem container. Seeds OAuth creds if a
# credentials file is mounted, then exec's whatever was passed (default: bash).
#
# Env vars:
# CLAUDE_MEM_CREDENTIALS_FILE Path to a mounted OAuth credentials JSON file
# (e.g. /auth/.credentials.json). Copied into
# $HOME/.claude/.credentials.json at startup.
# ANTHROPIC_API_KEY Standard API-key auth; set when OAuth isn't used.
set -euo pipefail
mkdir -p "$HOME/.claude" "$HOME/.claude-mem"
if [[ -n "${CLAUDE_MEM_CREDENTIALS_FILE:-}" ]]; then
if [[ ! -f "$CLAUDE_MEM_CREDENTIALS_FILE" ]]; then
echo "ERROR: CLAUDE_MEM_CREDENTIALS_FILE set but file missing: $CLAUDE_MEM_CREDENTIALS_FILE" >&2
exit 1
fi
cp "$CLAUDE_MEM_CREDENTIALS_FILE" "$HOME/.claude/.credentials.json"
chmod 600 "$HOME/.claude/.credentials.json"
fi
# Helpful one-liner for interactive users: run `claude` with the plugin dir
# preconfigured. Don't force it — `exec "$@"` lets you override freely.
export PATH="/usr/local/bun/bin:/usr/local/share/npm-global/bin:$PATH"
exec "$@"
docker/claude-mem/run.sh
Executable
+69
View File
@@ -0,0 +1,69 @@
#!/usr/bin/env bash
# Drop into an interactive claude-mem container with OAuth creds + persistent
# memory volume. For ad-hoc testing / poking around.
#
# Usage:
# docker/claude-mem/run.sh
# docker/claude-mem/run.sh claude --plugin-dir /opt/claude-mem --print "hi"
#
# On exit, the mounted .claude-mem/ dir on the host survives so you can inspect
# the DB: `sqlite3 <HOST_MEM_DIR>/claude-mem.db 'select count(*) from observations'`.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
TAG="${TAG:-claude-mem:basic}"
HOST_MEM_DIR="${HOST_MEM_DIR:-$REPO_ROOT/.docker-claude-mem-data}"
mkdir -p "$HOST_MEM_DIR"
echo "[run] host .claude-mem dir: $HOST_MEM_DIR" >&2
# Auth. Prefer OAuth (extracted from macOS Keychain / Linux creds file);
# fall back to ANTHROPIC_API_KEY env.
CREDS_FILE=""
CREDS_MOUNT_ARGS=()
if [[ -z "${ANTHROPIC_API_KEY:-}" ]]; then
CREDS_FILE="$(mktemp -t claude-mem-creds.XXXXXX.json)"
trap 'rm -f "$CREDS_FILE"' EXIT
# Try macOS Keychain first (primary storage on Darwin), then fall back to
# the on-disk credentials file — some macOS setups (older CLI versions,
# users who migrated machines) still have the file-only form.
creds_obtained=0
if [[ "$(uname)" == "Darwin" ]]; then
if security find-generic-password -s 'Claude Code-credentials' -w > "$CREDS_FILE" 2>/dev/null \
&& [[ -s "$CREDS_FILE" ]]; then
creds_obtained=1
fi
fi
if [[ "$creds_obtained" -eq 0 && -f "$HOME/.claude/.credentials.json" ]]; then
cp "$HOME/.claude/.credentials.json" "$CREDS_FILE"
creds_obtained=1
fi
if [[ "$creds_obtained" -eq 0 ]]; then
echo "ERROR: no ANTHROPIC_API_KEY set and no Claude OAuth credentials found." >&2
echo " Tried: macOS Keychain ('Claude Code-credentials') and ~/.claude/.credentials.json." >&2
echo " Run \`claude login\` on the host first, or set ANTHROPIC_API_KEY." >&2
exit 1
fi
chmod 600 "$CREDS_FILE"
CREDS_MOUNT_ARGS=(
-e CLAUDE_MEM_CREDENTIALS_FILE=/auth/.credentials.json
-v "$CREDS_FILE:/auth/.credentials.json:ro"
)
else
CREDS_MOUNT_ARGS=(-e ANTHROPIC_API_KEY)
fi
# Pick -it only when a TTY is attached (keeps non-interactive callers working).
TTY_ARGS=()
[[ -t 0 && -t 1 ]] && TTY_ARGS=(-it)
# NOT `exec` — we want the EXIT trap above to run and remove $CREDS_FILE
# after the container exits. Running docker as a child keeps the shell
# alive long enough for the trap to fire.
docker run --rm "${TTY_ARGS[@]}" \
"${CREDS_MOUNT_ARGS[@]}" \
-v "$HOST_MEM_DIR:/home/node/.claude-mem" \
"$TAG" \
"$@"
evals/swebench/Dockerfile.agent
+74
View File
@@ -0,0 +1,74 @@
# claude-mem SWE-bench agent image
# Plan: .claude/plans/swebench-claude-mem-docker.md (Phase 1)
#
# Produces `claude-mem/swebench-agent:latest`: Claude Code CLI 2.1.114 +
# locally-built claude-mem plugin, ready to run headlessly per SWE-bench
# instance. Auth (ANTHROPIC_API_KEY) is passed at runtime, never baked in.
FROM node:20-bookworm-slim
ENV DEBIAN_FRONTEND=noninteractive
# System dependencies:
# git, curl, ca-certificates, unzip — base tooling (Bun installer needs unzip)
# jq — JSONL assembly in run-instance.sh
# uuid-runtime — uuidgen for per-instance session IDs (Phase 2)
# sqlite3 — verifies the claude-mem observations DB
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
git \
curl \
ca-certificates \
unzip \
jq \
uuid-runtime \
sqlite3 \
&& rm -rf /var/lib/apt/lists/*
# Bun (claude-mem worker service runs under Bun). Installed to a system
# location so the non-root runtime user can execute it.
ENV BUN_INSTALL="/usr/local/bun"
RUN curl -fsSL https://bun.sh/install | bash \
&& chmod -R a+rX /usr/local/bun
ENV PATH="/usr/local/bun/bin:${PATH}"
# uv (provides Python for Chroma per CLAUDE.md). Installed to a system
# location, same reason.
ENV UV_INSTALL_DIR="/usr/local/bin"
# Group the chmod so the trailing `|| true` only absorbs chmod failures; without
# this grouping, bash precedence (`&&` binds tighter than `||`) would silently
# mask a failed `curl|sh` install step.
RUN set -eux \
&& curl -LsSf https://astral.sh/uv/install.sh | sh \
&& { chmod a+rX /usr/local/bin/uv /usr/local/bin/uvx 2>/dev/null || true; }
# Claude Code CLI — PINNED to the version whose flag surface was verified in
# the plan (Phase 0). Do NOT bump without re-verifying flags.
RUN npm install -g @anthropic-ai/claude-code@2.1.114
# Locally-built claude-mem plugin. The build-agent-image.sh wrapper runs
# `npm run build` before `docker build`, so plugin/ is populated in the build
# context. We do NOT install claude-mem from npm — we want the current
# worktree under test.
COPY plugin/ /opt/claude-mem/
# Runner script — entrypoint for per-instance invocation (Phase 2 deliverable).
COPY evals/swebench/run-instance.sh /evals/swebench/run-instance.sh
RUN chmod +x /evals/swebench/run-instance.sh
# Pre-create per-instance config dirs. run-instance.sh overrides HOME to a
# scratch dir for isolation, but having these present keeps tools from
# bailing if they probe the default locations before HOME is set.
RUN mkdir -p /root/.claude /root/.claude-mem
# Non-root user. Claude Code refuses `--dangerously-skip-permissions` /
# `--permission-mode bypassPermissions` when euid==0 as a safety rail, so we
# need an unprivileged user for headless batch runs. node:20 already ships a
# `node` user at uid 1000 — reuse it.
RUN mkdir -p /home/node/.claude /home/node/.claude-mem \
&& chown -R node:node /home/node /opt/claude-mem
USER node
WORKDIR /home/node
ENTRYPOINT ["/evals/swebench/run-instance.sh"]
evals/swebench/build-agent-image.sh
Executable
+20
View File
@@ -0,0 +1,20 @@
#!/usr/bin/env bash
# Build the claude-mem SWE-bench agent image.
# Plan: .claude/plans/swebench-claude-mem-docker.md (Phase 1, step 2)
set -euo pipefail
# Resolve repo root (two levels up from this script: evals/swebench -> repo).
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$REPO_ROOT"
# 1. Build the plugin so plugin/ is populated for the COPY step in the Dockerfile.
npm run build
# 2. Build the agent image. Context is the repo root so both plugin/ and
# evals/swebench/run-instance.sh are reachable.
docker build \
-f evals/swebench/Dockerfile.agent \
-t claude-mem/swebench-agent:latest \
.
evals/swebench/eval.sh
Executable
+72
View File
@@ -0,0 +1,72 @@
#!/usr/bin/env bash
set -euo pipefail
# eval.sh — Thin wrapper around `python -m swebench.harness.run_evaluation`.
#
# Required env:
# RUN_ID Identifier for this evaluation run (matches predictions dir).
# Optional env:
# MAX_WORKERS Parallel worker count for the harness (default: 4).
# DATASET HF dataset name (default: princeton-nlp/SWE-bench_Verified).
# TIMEOUT Per-instance timeout in seconds (default: 1800).
#
# Reports land at:
# logs/run_evaluation/$RUN_ID/claude-opus-4-7+claude-mem/<instance_id>/report.json
: "${RUN_ID:?RUN_ID is required (e.g. RUN_ID=smoke-001)}"
MAX_WORKERS="${MAX_WORKERS:-4}"
DATASET="${DATASET:-princeton-nlp/SWE-bench_Verified}"
TIMEOUT="${TIMEOUT:-1800}"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
cd "$REPO_ROOT"
PREDICTIONS="evals/swebench/runs/$RUN_ID/predictions.jsonl"
if [[ ! -f "$PREDICTIONS" ]]; then
echo "ERROR: predictions file not found: $PREDICTIONS" >&2
echo "Hint: run Phase 3 agent loop first to produce predictions.jsonl for RUN_ID=$RUN_ID." >&2
exit 1
fi
# Harness REQUIRES Docker — fail fast with a clean message if it's not running.
if ! command -v docker >/dev/null 2>&1; then
echo "ERROR: docker CLI not found on PATH. The SWE-bench harness requires Docker." >&2
exit 1
fi
if ! docker info >/dev/null 2>&1; then
echo "ERROR: Docker daemon is not running. Start Docker Desktop (or the docker service) and retry." >&2
exit 1
fi
# Create/reuse a dedicated venv so we don't pollute the system Python.
VENV_DIR=".venv-swebench"
if [[ ! -d "$VENV_DIR" ]]; then
echo "[eval.sh] Creating Python venv at $VENV_DIR ..."
python3 -m venv "$VENV_DIR"
fi
# shellcheck disable=SC1091
source "$VENV_DIR/bin/activate"
echo "[eval.sh] Installing/updating swebench in $VENV_DIR ..."
pip install -q swebench
echo "[eval.sh] Running harness:"
echo " dataset: $DATASET"
echo " predictions: $PREDICTIONS"
echo " max_workers: $MAX_WORKERS"
echo " run_id: $RUN_ID"
echo " timeout: $TIMEOUT"
python -m swebench.harness.run_evaluation \
--dataset_name "$DATASET" \
--predictions_path "$PREDICTIONS" \
--max_workers "$MAX_WORKERS" \
--run_id "$RUN_ID" \
--timeout "$TIMEOUT"
REPORTS_DIR="logs/run_evaluation/$RUN_ID/claude-opus-4-7+claude-mem"
echo ""
echo "[eval.sh] Done. Per-instance reports at:"
echo " $REPORTS_DIR/<instance_id>/report.json"
evals/swebench/run-batch.py
Executable
+561
View File
@@ -0,0 +1,561 @@
#!/usr/bin/env python3
"""
Batch orchestrator for SWE-bench evaluation of Claude Code + claude-mem.
Iterates a list of SWE-bench Verified instances, launches a per-instance Docker
container (`claude-mem/swebench-agent:latest`) that runs the two-turn
ingest/fix protocol, and collects all resulting diffs into a single
`predictions.jsonl` compatible with the upstream SWE-bench harness.
Usage:
python evals/swebench/run-batch.py \
--run-id claude-mem-baseline-001 \
--limit 3 \
--max-concurrent 2
Rate-limit note: Anthropic API rate limits can bite quickly. The default
`--max-concurrent` is 4, but it is safer to START WITH 2 and raise the cap
only after observing no 429s in the logs.
"""
from __future__ import annotations
import argparse
import atexit
import json
import os
import platform
import shutil
import stat
import subprocess
import sys
import tempfile
import threading
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from typing import Any, Iterable
from datasets import load_dataset
# Hidden-from-agent fields per the plan. We MUST NOT pass these to the agent
# container — they are evaluator-only ground truth.
HIDDEN_AGENT_FIELDS = (
"patch",
"test_patch",
"FAIL_TO_PASS",
"PASS_TO_PASS",
"environment_setup_commit",
"version",
)
def extract_oauth_credentials() -> Path | None:
"""
Extract Claude Code OAuth credentials (from a Max/Pro subscription) to a
temp file the container can bind-mount. Returns the temp file path, or
None if extraction failed / no creds present.
macOS: creds live in the Keychain under service "Claude Code-credentials".
Linux: creds live at ~/.claude/.credentials.json.
CAVEAT: Anthropic Max/Pro subscriptions have usage limits (per ~5h window)
and their ToS is framed around individual developer use. Running batch
evaluation across parallel containers may exhaust the quota quickly or
raise compliance concerns. This helper exists because the user explicitly
requested it; the caller is responsible for the policy call.
The token may age out mid-run; we mount read-only so refresh writes fail
silently inside the container (the underlying token in the host
Keychain/file is untouched).
"""
temp = tempfile.NamedTemporaryFile(
prefix="claude-mem-creds-",
suffix=".json",
delete=False,
)
temp_path = Path(temp.name)
temp.close()
# Clean up on process exit, even on crash.
atexit.register(lambda: temp_path.unlink(missing_ok=True))
# macOS: try Keychain first (primary storage on Darwin). On miss, fall
# through to the on-disk credentials file — some macOS setups (older CLI,
# migrated machines) only have the file form.
if platform.system() == "Darwin":
try:
completed = subprocess.run(
[
"security",
"find-generic-password",
"-s",
"Claude Code-credentials",
"-w",
],
capture_output=True,
text=True,
check=False,
)
if completed.returncode == 0 and completed.stdout.strip():
temp_path.write_text(completed.stdout.strip(), encoding="utf-8")
temp_path.chmod(stat.S_IRUSR | stat.S_IWUSR)
return temp_path
# else fall through to the on-disk credentials check below
except FileNotFoundError:
print(
"WARN: `security` command not available; trying on-disk creds.",
file=sys.stderr,
)
# fall through to the on-disk credentials check below
# Both platforms (and macOS fallback): read the on-disk credentials file.
creds_file = Path.home() / ".claude" / ".credentials.json"
if creds_file.exists():
temp_path.write_text(creds_file.read_text(encoding="utf-8"), encoding="utf-8")
temp_path.chmod(stat.S_IRUSR | stat.S_IWUSR)
return temp_path
if platform.system() == "Darwin":
print(
"WARN: Claude Code-credentials not found in macOS Keychain and "
"~/.claude/.credentials.json missing. Run `claude login` on the "
"host first, or fall back to ANTHROPIC_API_KEY.",
file=sys.stderr,
)
return None
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Run the claude-mem SWE-bench agent on a batch of instances.",
)
parser.add_argument(
"--instance-ids",
nargs="+",
default=None,
help="Optional explicit list of instance_ids to run.",
)
parser.add_argument(
"--limit",
type=int,
default=None,
help="If set, process only the first N instances after filtering.",
)
parser.add_argument(
"--max-concurrent",
type=int,
default=4,
help="Max concurrent agent containers (default 4; start with 2 and raise after observing no 429s).",
)
parser.add_argument(
"--run-id",
type=str,
required=True,
help="Run identifier; used for output paths.",
)
parser.add_argument(
"--out",
type=str,
default=None,
help="Path to predictions.jsonl (default: evals/swebench/runs/<run_id>/predictions.jsonl).",
)
parser.add_argument(
"--timeout",
type=int,
default=1800,
help="Per-instance timeout in seconds (default 1800, matches upstream harness).",
)
parser.add_argument(
"--image",
type=str,
default="claude-mem/swebench-agent:latest",
help="Agent Docker image tag.",
)
parser.add_argument(
"--dataset",
type=str,
default="princeton-nlp/SWE-bench_Verified",
help="HuggingFace dataset name (e.g. princeton-nlp/SWE-bench_Lite, default Verified).",
)
parser.add_argument(
"--auth",
choices=["oauth", "api-key", "auto"],
default="auto",
help=(
"Auth mode. 'oauth' extracts Claude Max/Pro creds from host "
"Keychain (macOS) or ~/.claude/.credentials.json (Linux). "
"'api-key' uses ANTHROPIC_API_KEY env. 'auto' prefers oauth, "
"falls back to api-key."
),
)
parser.add_argument(
"--overwrite",
action="store_true",
help=(
"Truncate existing predictions.jsonl for this --run-id. "
"Without this flag, the run aborts if predictions already exist "
"(protects partial results from accidental re-runs)."
),
)
return parser.parse_args()
def select_instances(
dataset: Iterable[dict[str, Any]],
instance_ids: list[str] | None,
limit: int | None,
) -> list[dict[str, Any]]:
"""Filter dataset rows by instance_ids (if given) and apply limit."""
rows: list[dict[str, Any]] = list(dataset)
if instance_ids:
wanted = set(instance_ids)
rows = [r for r in rows if r["instance_id"] in wanted]
missing = wanted - {r["instance_id"] for r in rows}
if missing:
print(
f"WARN: {len(missing)} requested instance_ids not found in dataset: "
f"{sorted(missing)[:5]}{'...' if len(missing) > 5 else ''}",
file=sys.stderr,
)
if limit is not None:
rows = rows[:limit]
return rows
def append_prediction_row(
predictions_path: Path,
instance_id: str,
model_patch: str,
model_name_or_path: str,
lock: threading.Lock,
) -> None:
"""Append one JSONL prediction row under a lock (appends are NOT atomic across threads)."""
row = {
"instance_id": instance_id,
"model_patch": model_patch,
"model_name_or_path": model_name_or_path,
}
line = json.dumps(row, ensure_ascii=False) + "\n"
with lock:
with predictions_path.open("a", encoding="utf-8") as fp:
fp.write(line)
def copy_log_if_exists(src: Path, dst: Path) -> None:
"""Copy a log file from the shared scratch volume into the run-log directory, if present."""
if src.exists() and src.is_file():
dst.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(src, dst)
def run_one_instance(
instance: dict[str, Any],
image: str,
predictions_path: Path,
predictions_dir: Path,
run_dir: Path,
timeout: int,
predictions_lock: threading.Lock,
model_name_or_path: str,
oauth_creds_path: Path | None,
) -> tuple[str, str]:
"""
Run the agent container for a single instance.
Returns a (status, instance_id) tuple where status is one of:
"succeeded", "failed", "timed_out".
On ANY non-success (timeout, non-zero exit, missing diff), a prediction
row with model_patch="" is still appended — the plan requires we never
silently drop an instance.
"""
instance_id: str = instance["instance_id"]
repo: str = instance["repo"]
base_commit: str = instance["base_commit"]
problem_statement: str = instance["problem_statement"]
instance_log_dir = run_dir / instance_id
instance_log_dir.mkdir(parents=True, exist_ok=True)
stderr_log_path = instance_log_dir / "stderr.log"
# Per-instance scratch dir — MUST NOT be shared across containers.
scratch_dir = Path(tempfile.mkdtemp(prefix=f"swebench-{instance_id}-"))
problem_file = scratch_dir / "problem.txt"
problem_file.write_text(problem_statement, encoding="utf-8")
status: str = "failed"
model_patch: str = ""
# Uniquely named so the TimeoutExpired handler can kill it without racing
# other instances on the host.
container_name = f"swebench-agent-{instance_id}-{os.getpid()}-{threading.get_ident()}"
try:
# The orchestrator owns JSONL writes under `predictions_lock` to avoid
# racy concurrent appends across containers — so we DO NOT mount the
# predictions directory into the container. Instead, the agent writes
# its authoritative diff to /scratch/model_patch.diff (via
# CLAUDE_MEM_OUTPUT_DIR), plus ingest/fix logs to the same dir. The
# 5th CLI arg to run-instance.sh is only used in standalone smoke-test
# mode; here we point it at a throwaway path inside the container.
cmd: list[str] = [
"docker",
"run",
"--rm",
"--name",
container_name,
"-e",
"CLAUDE_MEM_OUTPUT_DIR=/scratch",
"-v",
f"{scratch_dir}:/scratch",
]
if oauth_creds_path is not None:
cmd += [
"-e",
"CLAUDE_MEM_CREDENTIALS_FILE=/auth/.credentials.json",
"-v",
f"{oauth_creds_path}:/auth/.credentials.json:ro",
]
else:
# Pay-per-call path.
cmd += ["-e", "ANTHROPIC_API_KEY"]
cmd += [
image,
instance_id,
repo,
base_commit,
"/scratch/problem.txt",
"/scratch/ignored-predictions.jsonl",
]
try:
completed = subprocess.run(
cmd,
timeout=timeout,
capture_output=True,
text=True,
check=False,
)
# Persist stderr so post-mortem is possible even on success.
stderr_log_path.write_text(
f"=== STDOUT ===\n{completed.stdout}\n=== STDERR ===\n{completed.stderr}\n",
encoding="utf-8",
)
if completed.returncode == 0:
# Read the diff the agent wrote to the shared predictions volume.
# The container writes its own prediction line; we prefer to
# write our own authoritative row here from the diff file the
# agent left in /scratch. If the agent wrote a diff file, use
# it; otherwise fall back to empty patch.
diff_file = scratch_dir / "model_patch.diff"
if diff_file.exists():
diff_text = diff_file.read_text(encoding="utf-8")
if diff_text.strip():
model_patch = diff_text
status = "succeeded"
else:
status = "failed" # empty diff
else:
# Container did not leave a diff file — treat as failure
# but still emit an empty-patch row below.
status = "failed"
else:
status = "failed"
except subprocess.TimeoutExpired as exc:
status = "timed_out"
# subprocess.run killed the docker CLI, but the container may
# still be running. Force-remove it by name so we don't leak
# containers across the batch.
subprocess.run(
["docker", "rm", "-f", container_name],
capture_output=True,
check=False,
timeout=30,
)
stderr_log_path.write_text(
f"TIMEOUT after {timeout}s (forced docker rm -f {container_name})\n"
f"=== STDOUT (partial) ===\n{exc.stdout or ''}\n"
f"=== STDERR (partial) ===\n{exc.stderr or ''}\n",
encoding="utf-8",
)
# Copy per-turn logs left by the agent in the shared scratch volume.
copy_log_if_exists(scratch_dir / "ingest.jsonl", instance_log_dir / "ingest.jsonl")
copy_log_if_exists(scratch_dir / "fix.jsonl", instance_log_dir / "fix.jsonl")
# Always write a row — never silently drop an instance.
append_prediction_row(
predictions_path=predictions_path,
instance_id=instance_id,
model_patch=model_patch,
model_name_or_path=model_name_or_path,
lock=predictions_lock,
)
except Exception as exc: # pragma: no cover — defensive
status = "failed"
try:
stderr_log_path.write_text(
f"ORCHESTRATOR EXCEPTION: {exc!r}\n",
encoding="utf-8",
)
except OSError:
pass
append_prediction_row(
predictions_path=predictions_path,
instance_id=instance_id,
model_patch="",
model_name_or_path=model_name_or_path,
lock=predictions_lock,
)
finally:
# Per-instance scratch must not leak across containers.
shutil.rmtree(scratch_dir, ignore_errors=True)
return status, instance_id
def main() -> int:
args = parse_args()
repo_root = Path(__file__).resolve().parents[2]
if args.out:
predictions_path = Path(args.out).resolve()
else:
predictions_path = (
repo_root
/ "evals"
/ "swebench"
/ "runs"
/ args.run_id
/ "predictions.jsonl"
)
predictions_dir = predictions_path.parent
run_dir = predictions_dir # logs land in evals/swebench/runs/<run_id>/<instance_id>/
predictions_dir.mkdir(parents=True, exist_ok=True)
# Don't silently discard partial results from a prior run.
if predictions_path.exists() and predictions_path.stat().st_size > 0:
if not args.overwrite:
print(
f"ERROR: {predictions_path} already exists and is non-empty. "
"Pass --overwrite to truncate, or pick a different --run-id.",
file=sys.stderr,
)
return 1
print(
f"WARN: --overwrite set; truncating existing {predictions_path}",
file=sys.stderr,
)
predictions_path.write_text("", encoding="utf-8")
# Resolve auth: OAuth (Max/Pro subscription) or API key.
oauth_creds_path: Path | None = None
if args.auth in ("oauth", "auto"):
oauth_creds_path = extract_oauth_credentials()
if oauth_creds_path is not None:
print(
f"Auth: OAuth credentials extracted to {oauth_creds_path} "
"(mounted read-only into each container). "
"NOTE: Max/Pro has per-window usage limits; batch runs may exhaust them.",
file=sys.stderr,
)
elif args.auth == "oauth":
print(
"ERROR: --auth=oauth requested but credentials extraction failed.",
file=sys.stderr,
)
return 1
if oauth_creds_path is None:
if not os.environ.get("ANTHROPIC_API_KEY"):
print(
"ERROR: no auth available. Either run `claude login` on host "
"(for OAuth) or set ANTHROPIC_API_KEY.",
file=sys.stderr,
)
return 1
print("Auth: ANTHROPIC_API_KEY (pay-per-call).", file=sys.stderr)
print(f"Loading dataset {args.dataset} (split=test)...", file=sys.stderr)
dataset = load_dataset(args.dataset, split="test")
instances = select_instances(dataset, args.instance_ids, args.limit)
total = len(instances)
if total == 0:
print("No instances selected; nothing to do.", file=sys.stderr)
return 0
# Scrub hidden-from-agent fields defensively. The agent container only
# receives instance_id/repo/base_commit/problem_statement via CLI args +
# the per-instance problem file — the hidden fields never leave this
# process. This loop makes that invariant explicit.
for row in instances:
for key in HIDDEN_AGENT_FIELDS:
row.pop(key, None)
model_name_or_path = "claude-opus-4-7+claude-mem"
print(
f"Launching {total} instance(s) with max_concurrent={args.max_concurrent}, "
f"timeout={args.timeout}s, image={args.image}",
file=sys.stderr,
)
predictions_lock = threading.Lock()
succeeded = 0
failed = 0
timed_out = 0
with ThreadPoolExecutor(max_workers=args.max_concurrent) as executor:
future_to_id = {
executor.submit(
run_one_instance,
instance=instance,
image=args.image,
predictions_path=predictions_path,
predictions_dir=predictions_dir,
run_dir=run_dir,
timeout=args.timeout,
predictions_lock=predictions_lock,
model_name_or_path=model_name_or_path,
oauth_creds_path=oauth_creds_path,
): instance["instance_id"]
for instance in instances
}
for future in as_completed(future_to_id):
instance_id = future_to_id[future]
try:
status, _ = future.result()
except Exception as exc: # pragma: no cover — defensive
status = "failed"
print(
f"[{instance_id}] orchestrator future raised: {exc!r}",
file=sys.stderr,
)
if status == "succeeded":
succeeded += 1
elif status == "timed_out":
timed_out += 1
else:
failed += 1
print(
f"[{instance_id}] {status} "
f"({succeeded + failed + timed_out}/{total} done)",
file=sys.stderr,
)
print(
f"{total} total, {succeeded} succeeded, {failed} failed, {timed_out} timed out",
)
# Per plan: exit 0 even if some instances failed.
return 0
if __name__ == "__main__":
sys.exit(main())
evals/swebench/run-instance.sh
Executable
+177
View File
@@ -0,0 +1,177 @@
#!/usr/bin/env bash
set -euo pipefail
# run-instance.sh — runs Claude Code + claude-mem against a single SWE-bench
# instance using the two-turn protocol (ingest, then fix), and appends a
# prediction JSONL row to OUT_PREDICTIONS_PATH.
#
# Usage:
# run-instance.sh INSTANCE_ID REPO_SLUG BASE_COMMIT PROBLEM_STATEMENT_FILE OUT_PREDICTIONS_PATH
#
# Required env:
# ANTHROPIC_API_KEY
if [[ $# -ne 5 ]]; then
echo "Usage: $0 INSTANCE_ID REPO_SLUG BASE_COMMIT PROBLEM_STATEMENT_FILE OUT_PREDICTIONS_PATH" >&2
exit 2
fi
INSTANCE_ID="$1"
REPO_SLUG="$2"
BASE_COMMIT="$3"
PROBLEM_STATEMENT_FILE="$4"
OUT_PREDICTIONS_PATH="$5"
# Auth: either ANTHROPIC_API_KEY (pay-per-call) OR a pre-extracted OAuth
# credentials file from a Claude Max/Pro subscription (flat-fee, but subject
# to Anthropic's usage limits — batch-scale runs may exhaust the 5h window).
# run-batch.py extracts OAuth creds from host Keychain/file and mounts them
# at CLAUDE_MEM_CREDENTIALS_FILE; standalone smoke-test can do the same, or
# set ANTHROPIC_API_KEY directly.
if [[ -z "${ANTHROPIC_API_KEY:-}" && -z "${CLAUDE_MEM_CREDENTIALS_FILE:-}" ]]; then
echo "ERROR: one of ANTHROPIC_API_KEY or CLAUDE_MEM_CREDENTIALS_FILE is required" >&2
exit 1
fi
if [[ -n "${CLAUDE_MEM_CREDENTIALS_FILE:-}" && ! -f "$CLAUDE_MEM_CREDENTIALS_FILE" ]]; then
echo "ERROR: CLAUDE_MEM_CREDENTIALS_FILE set but file missing: $CLAUDE_MEM_CREDENTIALS_FILE" >&2
exit 1
fi
if [[ ! -f "$PROBLEM_STATEMENT_FILE" ]]; then
echo "ERROR: PROBLEM_STATEMENT_FILE not found: $PROBLEM_STATEMENT_FILE" >&2
exit 1
fi
MODEL_NAME="claude-opus-4-7+claude-mem"
# Per-instance ephemeral scratch dir — isolates ~/.claude/ and ~/.claude-mem/.
SCRATCH=$(mktemp -d)
REPO_DIR="$SCRATCH/repo"
MEM_DIR="$SCRATCH/.claude-mem"
CLAUDE_DIR="$SCRATCH/.claude"
mkdir -p "$MEM_DIR" "$CLAUDE_DIR"
# If using OAuth, seed the isolated CLAUDE_DIR with the mounted credentials
# file so Claude Code finds them at HOME=$SCRATCH → ~/.claude/.credentials.json.
# chmod 600 to match what `claude login` writes (it checks permissions).
if [[ -n "${CLAUDE_MEM_CREDENTIALS_FILE:-}" ]]; then
cp "$CLAUDE_MEM_CREDENTIALS_FILE" "$CLAUDE_DIR/.credentials.json"
chmod 600 "$CLAUDE_DIR/.credentials.json"
fi
# Directory where artifacts the batch orchestrator reads (model_patch.diff,
# ingest.jsonl, fix.jsonl) are written. When run via `docker run -v
# <host-scratch>:/scratch` from run-batch.py, the orchestrator sets
# CLAUDE_MEM_OUTPUT_DIR=/scratch so these files are visible on the host. In
# standalone/smoke-test mode the default keeps artifacts in the ephemeral
# scratch dir alongside the repo.
OUTPUT_DIR="${CLAUDE_MEM_OUTPUT_DIR:-$SCRATCH}"
mkdir -p "$OUTPUT_DIR"
# Always write a prediction row (even on failure) so batch mode stays aligned.
# The trap emits an empty-patch row if we exit before the success path sets
# PREDICTION_EMITTED=1, then cleans up SCRATCH.
DIFF_OUT="$OUTPUT_DIR/model_patch.diff"
INGEST_LOG="$OUTPUT_DIR/ingest.jsonl"
FIX_LOG="$OUTPUT_DIR/fix.jsonl"
PREDICTION_EMITTED=0
cleanup() {
local exit_code=$?
if [[ "$PREDICTION_EMITTED" -ne 1 ]]; then
# Ensure the orchestrator sees an (empty) diff file even on early exit.
: > "$DIFF_OUT" 2>/dev/null || true
jq -nc \
--arg id "$INSTANCE_ID" \
--arg patch "" \
--arg model "$MODEL_NAME" \
'{instance_id:$id, model_patch:$patch, model_name_or_path:$model}' \
>> "$OUT_PREDICTIONS_PATH" || true
fi
rm -rf "$SCRATCH"
exit "$exit_code"
}
trap cleanup EXIT
# Shallow clone + fetch the exact commit. Saves minutes on large repos
# (sympy/django/scikit-learn) vs. a full-history clone. Fallback to a full
# clone if the server rejects the by-commit fetch (GitHub supports
# uploadpack.allowReachableSHA1InWant by default on public repos, but mirrors
# may not).
if ! { git clone --depth 1 --no-single-branch "https://github.com/${REPO_SLUG}.git" "$REPO_DIR" \
&& git -C "$REPO_DIR" fetch --depth 1 origin "$BASE_COMMIT"; }; then
echo "WARN: shallow fetch failed; falling back to full clone" >&2
rm -rf "$REPO_DIR"
git clone "https://github.com/${REPO_SLUG}.git" "$REPO_DIR"
fi
git -C "$REPO_DIR" reset --hard "$BASE_COMMIT"
# ---------- Turn 1: Ingest (populate memory via PostToolUse hook) ----------
INGEST_PROMPT="Please learn about the codebase by systematically and thoroughly reading EVERY SOURCE FILE IN FULL, no matter how many there are. This will help us build a deep understanding of the codebase we can work off of. Don't worry about cost. This is critical and non-negotiable."
SESSION_ID=$(uuidgen | tr '[:upper:]' '[:lower:]')
set +e
(
cd "$REPO_DIR" && HOME="$SCRATCH" claude \
--print \
--session-id "$SESSION_ID" \
--plugin-dir /opt/claude-mem \
--permission-mode bypassPermissions \
--allowedTools "Read,Glob,Grep,Bash(ls *),Bash(wc *)" \
--max-budget-usd 5.00 \
--output-format json \
"$INGEST_PROMPT"
) > "$INGEST_LOG" 2>&1
INGEST_EXIT=$?
set -e
if [[ "$INGEST_EXIT" -ne 0 ]]; then
echo "WARN: ingest turn exited with $INGEST_EXIT; continuing to fix turn" >&2
fi
# ---------- Turn 2: Fix (consume memory via mem-search slash command) ----------
PROBLEM=$(cat "$PROBLEM_STATEMENT_FILE")
QUERY=$(printf '%s' "$PROBLEM" | tr -s '[:space:]' ' ' | cut -c1-200)
FIX_PROMPT="/claude-mem:mem-search ${QUERY}
Problem statement:
${PROBLEM}
Using what you've learned from the codebase (see memory above), produce a minimal unified diff that fixes this bug. Edit files in place. Do NOT commit."
set +e
(
cd "$REPO_DIR" && HOME="$SCRATCH" claude \
--print \
--resume "$SESSION_ID" \
--plugin-dir /opt/claude-mem \
--permission-mode bypassPermissions \
--allowedTools "Read,Glob,Grep,Edit,Write,Bash(git *),Bash(ls *)" \
--max-budget-usd 5.00 \
--output-format json \
"$FIX_PROMPT"
) > "$FIX_LOG" 2>&1
FIX_EXIT=$?
set -e
if [[ "$FIX_EXIT" -ne 0 ]]; then
echo "WARN: fix turn exited with $FIX_EXIT; will still emit prediction row" >&2
fi
# ---------- Capture diff and emit prediction row ----------
# Write the diff to DIFF_OUT first (authoritative for the batch orchestrator),
# then read it back for the JSONL row (kept for standalone/smoke-test use).
git -C "$REPO_DIR" diff > "$DIFF_OUT" || : > "$DIFF_OUT"
DIFF=$(cat "$DIFF_OUT")
jq -nc \
--arg id "$INSTANCE_ID" \
--arg patch "$DIFF" \
--arg model "$MODEL_NAME" \
'{instance_id:$id, model_patch:$patch, model_name_or_path:$model}' \
>> "$OUT_PREDICTIONS_PATH"
PREDICTION_EMITTED=1
evals/swebench/smoke-test.sh
Executable
+152
View File
@@ -0,0 +1,152 @@
#!/usr/bin/env bash
set -euo pipefail
# smoke-test.sh — runs ONE SWE-bench instance end-to-end against the agent
# container using OAuth credentials extracted from the host. Use this to
# verify the two-turn protocol + /claude-mem:mem-search slash resolution
# before kicking off a batch run.
#
# Usage:
# evals/swebench/smoke-test.sh [INSTANCE_ID]
#
# Defaults to sympy__sympy-24152 (an easy Verified instance) if no arg given.
#
# Outputs:
# evals/swebench/runs/smoke/<INSTANCE_ID>/{ingest.jsonl,fix.jsonl,model_patch.diff}
# evals/swebench/runs/smoke/predictions.jsonl
INSTANCE_ID="${1:-sympy__sympy-24152}"
DATASET="${DATASET:-princeton-nlp/SWE-bench_Lite}"
IMAGE="${IMAGE:-claude-mem/swebench-agent:latest}"
TIMEOUT="${TIMEOUT:-1800}"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
RUN_DIR="$REPO_ROOT/evals/swebench/runs/smoke/$INSTANCE_ID"
PREDICTIONS="$REPO_ROOT/evals/swebench/runs/smoke/predictions.jsonl"
mkdir -p "$RUN_DIR" "$(dirname "$PREDICTIONS")"
# --- Extract OAuth credentials ---
CREDS_FILE="$(mktemp -t claude-mem-creds.XXXXXX.json)"
trap 'rm -f "$CREDS_FILE"' EXIT
# Try macOS Keychain first (primary on Darwin), then fall through to the
# on-disk credentials file — matches docker/claude-mem/run.sh behavior.
creds_obtained=0
if [[ "$(uname)" == "Darwin" ]]; then
if security find-generic-password -s 'Claude Code-credentials' -w > "$CREDS_FILE" 2>/dev/null \
&& [[ -s "$CREDS_FILE" ]]; then
creds_obtained=1
fi
fi
if [[ "$creds_obtained" -eq 0 && -f "$HOME/.claude/.credentials.json" ]]; then
cp "$HOME/.claude/.credentials.json" "$CREDS_FILE"
creds_obtained=1
fi
if [[ "$creds_obtained" -eq 0 ]]; then
echo "ERROR: no Claude OAuth creds found (macOS Keychain or ~/.claude/.credentials.json)" >&2
exit 1
fi
chmod 600 "$CREDS_FILE"
# --- Fetch instance data from HuggingFace via a small Python helper ---
INSTANCE_JSON="$(mktemp)"
trap 'rm -f "$CREDS_FILE" "$INSTANCE_JSON"' EXIT
python3 - "$INSTANCE_ID" "$DATASET" > "$INSTANCE_JSON" <<'PY'
import json, sys
from datasets import load_dataset
target = sys.argv[1]
dataset = sys.argv[2]
ds = load_dataset(dataset, split="test")
for row in ds:
if row["instance_id"] == target:
print(json.dumps({
"instance_id": row["instance_id"],
"repo": row["repo"],
"base_commit": row["base_commit"],
"problem_statement": row["problem_statement"],
}))
break
else:
print(f"ERROR: instance {target} not found", file=sys.stderr)
sys.exit(1)
PY
SCRATCH="$(mktemp -d -t claude-mem-smoke.XXXXXX)"
trap 'rm -f "$CREDS_FILE" "$INSTANCE_JSON"; rm -rf "$SCRATCH"' EXIT
# Parse the instance JSON once: print repo + base_commit to stdout, write the
# problem statement directly to $SCRATCH/problem.txt. INSTANCE_JSON is passed
# as argv so stdin is free for the `python3 -` heredoc script body (previously
# both were competing for stdin, which made json.load see the heredoc's EOF).
read -r REPO BASE_COMMIT < <(
python3 - "$SCRATCH" "$INSTANCE_JSON" <<'PY'
import json, os, sys
scratch, instance_json = sys.argv[1], sys.argv[2]
with open(instance_json) as f:
d = json.load(f)
open(os.path.join(scratch, "problem.txt"), "w").write(d["problem_statement"])
print(d["repo"], d["base_commit"])
PY
)
echo "=== Running $INSTANCE_ID ($REPO @ $BASE_COMMIT) ===" >&2
echo "Scratch: $SCRATCH" >&2
echo "Logs will land in: $RUN_DIR" >&2
# Pick a wall-clock timeout binary. Linux ships `timeout`; macOS needs
# `gtimeout` from coreutils (brew install coreutils). If neither is available,
# warn and run without a cap — the smoke test is manual anyway.
TIMEOUT_CMD=()
if command -v timeout >/dev/null 2>&1; then
TIMEOUT_CMD=(timeout "$TIMEOUT")
elif command -v gtimeout >/dev/null 2>&1; then
TIMEOUT_CMD=(gtimeout "$TIMEOUT")
else
echo "WARN: no \`timeout\`/\`gtimeout\` on PATH; container runs uncapped" >&2
fi
# Name the container so we can force-remove it if the wall-clock timeout
# fires (SIGTERM from timeout leaves the container state open briefly).
CONTAINER_NAME="claude-mem-smoke-$INSTANCE_ID-$$"
set +e
"${TIMEOUT_CMD[@]}" docker run --rm \
--name "$CONTAINER_NAME" \
-e CLAUDE_MEM_OUTPUT_DIR=/scratch \
-e CLAUDE_MEM_CREDENTIALS_FILE=/auth/.credentials.json \
-v "$SCRATCH:/scratch" \
-v "$CREDS_FILE:/auth/.credentials.json:ro" \
"$IMAGE" \
"$INSTANCE_ID" "$REPO" "$BASE_COMMIT" /scratch/problem.txt /scratch/ignored-predictions.jsonl
DOCKER_EXIT=$?
set -e
if [[ "$DOCKER_EXIT" -eq 124 ]]; then
# `timeout` signals TERM and returns 124 on timeout. Force-remove the
# container in case docker hasn't reaped it yet.
echo "ERROR: docker run exceeded ${TIMEOUT}s wall-clock; removing container" >&2
docker rm -f "$CONTAINER_NAME" >/dev/null 2>&1 || true
fi
# Copy artifacts from scratch → RUN_DIR
for f in ingest.jsonl fix.jsonl model_patch.diff; do
[[ -f "$SCRATCH/$f" ]] && cp "$SCRATCH/$f" "$RUN_DIR/$f"
done
# Emit authoritative prediction row
DIFF_FILE="$SCRATCH/model_patch.diff"
DIFF=""
[[ -f "$DIFF_FILE" ]] && DIFF="$(cat "$DIFF_FILE")"
jq -nc \
--arg id "$INSTANCE_ID" \
--arg patch "$DIFF" \
--arg model "claude-opus-4-7+claude-mem" \
'{instance_id:$id, model_patch:$patch, model_name_or_path:$model}' \
>> "$PREDICTIONS"
echo "=== Done ===" >&2
echo "Diff size: $(wc -c < "$DIFF_FILE" 2>/dev/null || echo 0) bytes" >&2
echo "Predictions: $PREDICTIONS" >&2
echo "Verify mem-search invocation:" >&2
echo " grep -o '\"name\":\"[^\"]*mem-search[^\"]*\"' $RUN_DIR/fix.jsonl || echo 'NOT INVOKED'" >&2
evals/swebench/summarize.py
Executable
+308
View File
@@ -0,0 +1,308 @@
#!/usr/bin/env python3
"""Summarize SWE-bench evaluation run results.
Walks the SWE-bench harness output directory, tallies resolved/unresolved/error
counts, and emits a markdown summary. Optionally diffs against another run.
"""
import argparse
import json
import sys
from pathlib import Path
def load_expected_instance_ids(predictions_path: Path) -> list[str]:
"""Read instance_ids from a predictions.jsonl file (one JSON object per line)."""
instance_ids: list[str] = []
if not predictions_path.exists():
print(
f"warning: predictions file not found: {predictions_path}",
file=sys.stderr,
)
return instance_ids
with predictions_path.open("r", encoding="utf-8") as handle:
for line_number, raw_line in enumerate(handle, start=1):
stripped = raw_line.strip()
if not stripped:
continue
try:
record = json.loads(stripped)
except json.JSONDecodeError as exc:
print(
f"warning: could not parse predictions line {line_number}: {exc}",
file=sys.stderr,
)
continue
instance_id = record.get("instance_id")
if instance_id:
instance_ids.append(instance_id)
return instance_ids
def load_run_results(
run_id: str,
model_name: str,
expected_instance_ids: list[str],
repo_root: Path,
) -> dict:
"""Walk logs/run_evaluation/<run_id>/<model_name>/*/report.json and tally results.
Returns a dict:
{
"per_instance": {instance_id: {"resolved": bool|None, "notes": str}},
"resolved_count": int,
"unresolved_count": int,
"error_count": int,
}
"""
run_logs_root = repo_root / "logs" / "run_evaluation" / run_id / model_name
per_instance: dict[str, dict] = {}
resolved_count = 0
unresolved_count = 0
error_count = 0
for instance_id in expected_instance_ids:
report_path = run_logs_root / instance_id / "report.json"
if not report_path.exists():
per_instance[instance_id] = {
"resolved": None,
"notes": "missing report.json",
}
error_count += 1
continue
try:
with report_path.open("r", encoding="utf-8") as handle:
report_data = json.load(handle)
except (json.JSONDecodeError, OSError) as exc:
per_instance[instance_id] = {
"resolved": None,
"notes": f"failed to parse report.json: {exc}",
}
error_count += 1
continue
# SWE-bench harness typically nests per-instance data under the
# instance_id key; fall back to the top-level dict for flexibility.
inner = report_data.get(instance_id, report_data)
resolved_value = inner.get("resolved")
if resolved_value is True:
per_instance[instance_id] = {"resolved": True, "notes": ""}
resolved_count += 1
elif resolved_value is False:
notes_parts: list[str] = []
tests_status = inner.get("tests_status")
if isinstance(tests_status, dict):
fail_to_pass = tests_status.get("FAIL_TO_PASS", {})
if isinstance(fail_to_pass, dict):
failed = fail_to_pass.get("failure", []) or []
if failed:
notes_parts.append(f"FAIL_TO_PASS failures: {len(failed)}")
per_instance[instance_id] = {
"resolved": False,
"notes": "; ".join(notes_parts),
}
unresolved_count += 1
else:
per_instance[instance_id] = {
"resolved": None,
"notes": "report.json missing 'resolved' field",
}
error_count += 1
return {
"per_instance": per_instance,
"resolved_count": resolved_count,
"unresolved_count": unresolved_count,
"error_count": error_count,
}
def format_resolved_cell(resolved: bool | None) -> str:
if resolved is True:
return "yes"
if resolved is False:
return "no"
return "error"
def render_summary_markdown(run_id: str, results: dict) -> str:
total = (
results["resolved_count"]
+ results["unresolved_count"]
+ results["error_count"]
)
resolved = results["resolved_count"]
resolve_rate = (resolved / total * 100.0) if total > 0 else 0.0
lines: list[str] = []
lines.append(f"# Run {run_id}")
lines.append(f"- Total: {total}")
lines.append(f"- Resolved: {resolved} ({resolve_rate:.2f}%)")
lines.append(f"- Unresolved: {results['unresolved_count']}")
lines.append(f"- Errors: {results['error_count']}")
lines.append("")
lines.append("## Per-instance")
lines.append("| instance_id | resolved | notes |")
lines.append("|---|---|---|")
for instance_id, record in results["per_instance"].items():
resolved_cell = format_resolved_cell(record["resolved"])
notes_cell = record.get("notes", "") or ""
# Escape pipe chars in notes to avoid breaking markdown tables.
notes_cell = notes_cell.replace("|", "\\|")
lines.append(f"| {instance_id} | {resolved_cell} | {notes_cell} |")
lines.append("")
return "\n".join(lines)
def render_diff_markdown(
current_run_id: str,
other_run_id: str,
current_results: dict,
other_results: dict,
) -> str:
def resolve_rate(results: dict) -> tuple[int, float]:
total = (
results["resolved_count"]
+ results["unresolved_count"]
+ results["error_count"]
)
rate = (results["resolved_count"] / total * 100.0) if total > 0 else 0.0
return total, rate
current_total, current_rate = resolve_rate(current_results)
other_total, other_rate = resolve_rate(other_results)
rate_delta = current_rate - other_rate
lines: list[str] = []
lines.append(f"# Diff vs {other_run_id}")
lines.append(
f"- {current_run_id}: {current_results['resolved_count']}/{current_total} "
f"({current_rate:.2f}%)"
)
lines.append(
f"- {other_run_id}: {other_results['resolved_count']}/{other_total} "
f"({other_rate:.2f}%)"
)
lines.append(f"- Delta: {rate_delta:+.2f} percentage points")
lines.append("")
lines.append("## Per-instance status changes")
lines.append(f"| instance_id | {other_run_id} | {current_run_id} |")
lines.append("|---|---|---|")
all_instance_ids = set(current_results["per_instance"].keys()) | set(
other_results["per_instance"].keys()
)
changes_found = False
for instance_id in sorted(all_instance_ids):
current_record = current_results["per_instance"].get(instance_id)
other_record = other_results["per_instance"].get(instance_id)
current_status = (
format_resolved_cell(current_record["resolved"])
if current_record
else "absent"
)
other_status = (
format_resolved_cell(other_record["resolved"])
if other_record
else "absent"
)
if current_status != other_status:
lines.append(f"| {instance_id} | {other_status} | {current_status} |")
changes_found = True
if not changes_found:
lines.append("| (no status changes) | | |")
lines.append("")
return "\n".join(lines)
def main() -> int:
parser = argparse.ArgumentParser(
description="Summarize SWE-bench evaluation run results."
)
parser.add_argument(
"--run-id",
required=True,
help="Run identifier used in logs/run_evaluation/<run_id>/ and evals/swebench/runs/<run_id>/.",
)
parser.add_argument(
"--compare",
metavar="OTHER_RUN_ID",
default=None,
help="Optional other run_id to diff resolve rates and per-instance status changes against.",
)
parser.add_argument(
"--model-name",
default="claude-opus-4-7+claude-mem",
help="Model name directory inside logs/run_evaluation/<run_id>/.",
)
parser.add_argument(
"--out",
default=None,
help="Output path for the markdown summary (default: evals/swebench/runs/<run_id>/summary.md).",
)
args = parser.parse_args()
# Resolve repo root from this script's location: evals/swebench/summarize.py
script_path = Path(__file__).resolve()
repo_root = script_path.parent.parent.parent
current_predictions_path = (
repo_root / "evals" / "swebench" / "runs" / args.run_id / "predictions.jsonl"
)
current_instance_ids = load_expected_instance_ids(current_predictions_path)
current_results = load_run_results(
run_id=args.run_id,
model_name=args.model_name,
expected_instance_ids=current_instance_ids,
repo_root=repo_root,
)
summary_markdown = render_summary_markdown(args.run_id, current_results)
if args.compare:
other_predictions_path = (
repo_root
/ "evals"
/ "swebench"
/ "runs"
/ args.compare
/ "predictions.jsonl"
)
other_instance_ids = load_expected_instance_ids(other_predictions_path)
other_results = load_run_results(
run_id=args.compare,
model_name=args.model_name,
expected_instance_ids=other_instance_ids,
repo_root=repo_root,
)
diff_markdown = render_diff_markdown(
current_run_id=args.run_id,
other_run_id=args.compare,
current_results=current_results,
other_results=other_results,
)
summary_markdown = summary_markdown + "\n" + diff_markdown
if args.out:
output_path = Path(args.out)
if not output_path.is_absolute():
output_path = (Path.cwd() / output_path).resolve()
else:
output_path = (
repo_root
/ "evals"
/ "swebench"
/ "runs"
/ args.run_id
/ "summary.md"
)
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_text(summary_markdown, encoding="utf-8")
print(str(output_path))
return 0
if __name__ == "__main__":
raise SystemExit(main())
package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "claude-mem", "name": "claude-mem",
"version": "12.2.0", "version": "12.3.1",
"description": "Memory compression system for Claude Code - persist context across sessions", "description": "Memory compression system for Claude Code - persist context across sessions",
"keywords": [ "keywords": [
"claude", "claude",
plugin/.claude-plugin/plugin.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "claude-mem", "name": "claude-mem",
"version": "12.2.0", "version": "12.3.1",
"description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions", "description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
"author": { "author": {
"name": "Alex Newman" "name": "Alex Newman"
plugin/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "claude-mem-plugin", "name": "claude-mem-plugin",
"version": "12.2.0", "version": "12.3.1",
"private": true, "private": true,
"description": "Runtime dependencies for claude-mem bundled hooks", "description": "Runtime dependencies for claude-mem bundled hooks",
"type": "module", "type": "module",
plugin/scripts/context-generator.cjs
+64 -63
View File
File diff suppressed because one or more lines are too long
plugin/scripts/mcp-server.cjs
+20 -20
View File
File diff suppressed because one or more lines are too long
plugin/scripts/worker-service.cjs
+243 -238
View File
File diff suppressed because one or more lines are too long
plugin/ui/viewer-bundle.js
+6 -6
View File
File diff suppressed because one or more lines are too long
scripts/anti-pattern-test/detect-error-handling-antipatterns.ts
+3 -2
View File
@@ -224,8 +224,9 @@ function detectAntiPatterns(filePath: string, projectRoot: string): AntiPattern[
} }
} }
// Detect try block start // Detect try block start (only when NOT already inside a catch block —
if (trimmed.match(/^\s*try\s*{/) || trimmed.match(/}\s*try\s*{/)) { // nested try/catch inside a catch is just catch-block content)
if (!inCatch && (trimmed.match(/^\s*try\s*{/) || trimmed.match(/}\s*try\s*{/))) {
inTry = true; inTry = true;
tryStartLine = i + 1; tryStartLine = i + 1;
tryLines = [line]; tryLines = [line];
src/bin/import-xml-observations.ts
+18 -22
View File
@@ -59,8 +59,18 @@ function buildTimestampMap(): TimestampMapping {
for (let index = 0; index < lines.length; index++) { for (let index = 0; index < lines.length; index++) {
const line = lines[index]; const line = lines[index];
let data: any;
try { try {
const data = JSON.parse(line); data = JSON.parse(line);
} catch (e: unknown) {
logger.debug('IMPORT', 'Skipping invalid JSON line', {
lineNumber: index + 1,
filename,
error: e instanceof Error ? e.message : String(e)
});
continue;
}
const timestamp = data.timestamp; const timestamp = data.timestamp;
const sessionId = data.sessionId; const sessionId = data.sessionId;
const project = data.cwd; const project = data.cwd;
@@ -68,6 +78,9 @@ function buildTimestampMap(): TimestampMapping {
if (timestamp && sessionId) { if (timestamp && sessionId) {
// Round timestamp to second for matching with XML timestamps // Round timestamp to second for matching with XML timestamps
const roundedTimestamp = new Date(timestamp); const roundedTimestamp = new Date(timestamp);
if (Number.isNaN(roundedTimestamp.getTime())) {
continue;
}
roundedTimestamp.setMilliseconds(0); roundedTimestamp.setMilliseconds(0);
const key = roundedTimestamp.toISOString(); const key = roundedTimestamp.toISOString();
@@ -76,13 +89,6 @@ function buildTimestampMap(): TimestampMapping {
map[key] = { sessionId, project }; map[key] = { sessionId, project };
} }
} }
} catch (e) {
logger.debug('IMPORT', 'Skipping invalid JSON line', {
lineNumber: index + 1,
filename,
error: e instanceof Error ? e.message : String(e)
});
}
} }
} }
@@ -131,7 +137,6 @@ function parseObservation(xml: string): ObservationData | null {
return null; return null;
} }
try {
const observation: ObservationData = { const observation: ObservationData = {
type: extractTag(xml, 'type'), type: extractTag(xml, 'type'),
title: extractTag(xml, 'title'), title: extractTag(xml, 'title'),
@@ -149,10 +154,6 @@ function parseObservation(xml: string): ObservationData | null {
} }
return observation; return observation;
} catch (e) {
console.error('Error parsing observation:', e);
return null;
}
} }
/** /**
@@ -164,7 +165,6 @@ function parseSummary(xml: string): SummaryData | null {
return null; return null;
} }
try {
const summary: SummaryData = { const summary: SummaryData = {
request: extractTag(xml, 'request'), request: extractTag(xml, 'request'),
investigated: extractTag(xml, 'investigated'), investigated: extractTag(xml, 'investigated'),
@@ -180,10 +180,6 @@ function parseSummary(xml: string): SummaryData | null {
} }
return summary; return summary;
} catch (e) {
console.error('Error parsing summary:', e);
return null;
}
} }
/** /**
@@ -326,8 +322,8 @@ function main() {
if (importedObs % 50 === 0) { if (importedObs % 50 === 0) {
console.log(`Imported ${importedObs} observations...`); console.log(`Imported ${importedObs} observations...`);
} }
} catch (e) { } catch (e: unknown) {
console.error(`Error storing observation:`, e); console.error(`Error storing observation:`, e instanceof Error ? e.message : String(e));
skipped++; skipped++;
} }
continue; continue;
@@ -358,8 +354,8 @@ function main() {
if (importedSum % 10 === 0) { if (importedSum % 10 === 0) {
console.log(`Imported ${importedSum} summaries...`); console.log(`Imported ${importedSum} summaries...`);
} }
} catch (e) { } catch (e: unknown) {
console.error(`Error storing summary:`, e); console.error(`Error storing summary:`, e instanceof Error ? e.message : String(e));
skipped++; skipped++;
} }
continue; continue;
src/cli/adapters/claude-code.ts
+9
View File
@@ -2,6 +2,13 @@ import type { PlatformAdapter, NormalizedHookInput, HookResult } from '../types.
// Maps Claude Code stdin format (session_id, cwd, tool_name, etc.) // Maps Claude Code stdin format (session_id, cwd, tool_name, etc.)
// SessionStart hooks receive no stdin, so we must handle undefined input gracefully // SessionStart hooks receive no stdin, so we must handle undefined input gracefully
// Defensive cap: Claude Code's agent identifiers are short (e.g., "agent-abc123", "Explore").
// Ignore anything longer than 128 chars so a malformed payload cannot balloon DB rows.
const MAX_AGENT_FIELD_LEN = 128;
const pickAgentField = (v: unknown): string | undefined =>
typeof v === 'string' && v.length > 0 && v.length <= MAX_AGENT_FIELD_LEN ? v : undefined;
export const claudeCodeAdapter: PlatformAdapter = { export const claudeCodeAdapter: PlatformAdapter = {
normalizeInput(raw) { normalizeInput(raw) {
const r = (raw ?? {}) as any; const r = (raw ?? {}) as any;
@@ -13,6 +20,8 @@ export const claudeCodeAdapter: PlatformAdapter = {
toolInput: r.tool_input, toolInput: r.tool_input,
toolResponse: r.tool_response, toolResponse: r.tool_response,
transcriptPath: r.transcript_path, transcriptPath: r.transcript_path,
agentId: pickAgentField(r.agent_id),
agentType: pickAgentField(r.agent_type),
}; };
}, },
formatOutput(result) { formatOutput(result) {
src/cli/claude-md-commands.ts
+121 -84
View File
@@ -76,12 +76,19 @@ function estimateTokens(obs: ObservationRow): number {
function getTrackedFolders(workingDir: string): Set<string> { function getTrackedFolders(workingDir: string): Set<string> {
const folders = new Set<string>(); const folders = new Set<string>();
let output: string;
try { try {
const output = execSync('git ls-files', { output = execSync('git ls-files', {
cwd: workingDir, cwd: workingDir,
encoding: 'utf-8', encoding: 'utf-8',
maxBuffer: 50 * 1024 * 1024 maxBuffer: 50 * 1024 * 1024
}); });
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.warn('CLAUDE_MD', 'git ls-files failed, falling back to directory walk', { error: errorMessage });
walkDirectoriesWithIgnore(workingDir, folders);
return folders;
}
const files = output.trim().split('\n').filter(f => f); const files = output.trim().split('\n').filter(f => f);
@@ -94,10 +101,6 @@ function getTrackedFolders(workingDir: string): Set<string> {
dir = path.dirname(dir); dir = path.dirname(dir);
} }
} }
} catch (error) {
logger.warn('CLAUDE_MD', 'git ls-files failed, falling back to directory walk', { error: String(error) });
walkDirectoriesWithIgnore(workingDir, folders);
}
return folders; return folders;
} }
@@ -141,7 +144,9 @@ function hasDirectChildFile(obs: ObservationRow, folderPath: string): boolean {
if (Array.isArray(files)) { if (Array.isArray(files)) {
return files.some(f => isDirectChild(f, folderPath)); return files.some(f => isDirectChild(f, folderPath));
} }
} catch {} } catch (error) {
logger.warn('CLAUDE_MD', 'Failed to parse files JSON in hasDirectChildFile', { error: error instanceof Error ? error.message : String(error) });
}
return false; return false;
}; };
@@ -187,7 +192,9 @@ function extractRelevantFile(obs: ObservationRow, relativeFolder: string): strin
} }
} }
} }
} catch {} } catch (error) {
logger.warn('CLAUDE_MD', 'Failed to parse files_modified JSON', { error: error instanceof Error ? error.message : String(error) });
}
} }
if (obs.files_read) { if (obs.files_read) {
@@ -200,7 +207,9 @@ function extractRelevantFile(obs: ObservationRow, relativeFolder: string): strin
} }
} }
} }
} catch {} } catch (error) {
logger.warn('CLAUDE_MD', 'Failed to parse files_read JSON', { error: error instanceof Error ? error.message : String(error) });
}
} }
return 'General'; return 'General';
@@ -316,7 +325,6 @@ function regenerateFolder(
workingDir: string, workingDir: string,
observationLimit: number observationLimit: number
): { success: boolean; observationCount: number; error?: string } { ): { success: boolean; observationCount: number; error?: string } {
try {
if (!existsSync(absoluteFolder)) { if (!existsSync(absoluteFolder)) {
return { success: false, observationCount: 0, error: 'Folder no longer exists' }; return { success: false, observationCount: 0, error: 'Folder no longer exists' };
} }
@@ -338,48 +346,24 @@ function regenerateFolder(
return { success: true, observationCount: observations.length }; return { success: true, observationCount: observations.length };
} }
try {
const formatted = formatObservationsForClaudeMd(observations, relativeFolder); const formatted = formatObservationsForClaudeMd(observations, relativeFolder);
writeClaudeMdToFolder(absoluteFolder, formatted); writeClaudeMdToFolder(absoluteFolder, formatted);
return { success: true, observationCount: observations.length }; return { success: true, observationCount: observations.length };
} catch (error) { } catch (error) {
return { success: false, observationCount: 0, error: String(error) }; const errorMessage = error instanceof Error ? error.message : String(error);
logger.warn('CLAUDE_MD', 'Failed to regenerate folder', { folder: relativeFolder, error: errorMessage });
return { success: false, observationCount: 0, error: errorMessage };
} }
} }
/** function processAllFoldersForGeneration(
* Generate CLAUDE.md files for all folders with observations. trackedFolders: Set<string>,
* workingDir: string,
* @param dryRun - If true, only report what would be done without writing files project: string,
* @returns Exit code (0 for success, 1 for error) dryRun: boolean,
*/ observationLimit: number
export async function generateClaudeMd(dryRun: boolean): Promise<number> { ): number {
try {
const workingDir = process.cwd();
const settings = SettingsDefaultsManager.loadFromFile(SETTINGS_PATH);
const observationLimit = parseInt(settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS, 10) || 50;
logger.info('CLAUDE_MD', 'Starting CLAUDE.md generation', {
workingDir,
dryRun,
observationLimit
});
const project = path.basename(workingDir);
const trackedFolders = getTrackedFolders(workingDir);
if (trackedFolders.size === 0) {
logger.info('CLAUDE_MD', 'No folders found in project');
return 0;
}
logger.info('CLAUDE_MD', `Found ${trackedFolders.size} folders in project`);
if (!existsSync(DB_PATH)) {
logger.info('CLAUDE_MD', 'Database not found, no observations to process');
return 0;
}
const db = new Database(DB_PATH, { readonly: true, create: false }); const db = new Database(DB_PATH, { readonly: true, create: false });
let successCount = 0; let successCount = 0;
@@ -427,14 +411,103 @@ export async function generateClaudeMd(dryRun: boolean): Promise<number> {
}); });
return 0; return 0;
}
/**
* Generate CLAUDE.md files for all folders with observations.
*
* @param dryRun - If true, only report what would be done without writing files
* @returns Exit code (0 for success, 1 for error)
*/
export async function generateClaudeMd(dryRun: boolean): Promise<number> {
const workingDir = process.cwd();
const settings = SettingsDefaultsManager.loadFromFile(SETTINGS_PATH);
const observationLimit = parseInt(settings.CLAUDE_MEM_CONTEXT_OBSERVATIONS, 10) || 50;
logger.info('CLAUDE_MD', 'Starting CLAUDE.md generation', {
workingDir,
dryRun,
observationLimit
});
const project = path.basename(workingDir);
const trackedFolders = getTrackedFolders(workingDir);
if (trackedFolders.size === 0) {
logger.info('CLAUDE_MD', 'No folders found in project');
return 0;
}
logger.info('CLAUDE_MD', `Found ${trackedFolders.size} folders in project`);
if (!existsSync(DB_PATH)) {
logger.info('CLAUDE_MD', 'Database not found, no observations to process');
return 0;
}
try {
return processAllFoldersForGeneration(trackedFolders, workingDir, project, dryRun, observationLimit);
} catch (error) { } catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.error('CLAUDE_MD', 'Fatal error during CLAUDE.md generation', { logger.error('CLAUDE_MD', 'Fatal error during CLAUDE.md generation', {
error: String(error) error: errorMessage
}); });
return 1; return 1;
} }
} }
function processFilesForCleanup(
filesToProcess: string[],
workingDir: string,
dryRun: boolean
): number {
let deletedCount = 0;
let cleanedCount = 0;
let errorCount = 0;
for (const file of filesToProcess) {
const relativePath = path.relative(workingDir, file);
try {
const result = cleanSingleFile(file, relativePath, dryRun);
if (result === 'deleted') deletedCount++;
else cleanedCount++;
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.warn('CLAUDE_MD', `Error processing ${relativePath}`, { error: errorMessage });
errorCount++;
}
}
logger.info('CLAUDE_MD', 'CLAUDE.md cleanup complete', {
deleted: deletedCount,
cleaned: cleanedCount,
errors: errorCount,
dryRun
});
return 0;
}
function cleanSingleFile(file: string, relativePath: string, dryRun: boolean): 'deleted' | 'cleaned' {
const content = readFileSync(file, 'utf-8');
const stripped = content.replace(/<claude-mem-context>[\s\S]*?<\/claude-mem-context>/g, '').trim();
if (stripped === '') {
if (!dryRun) {
unlinkSync(file);
}
logger.debug('CLAUDE_MD', `${dryRun ? '[DRY-RUN] Would delete' : 'Deleted'} (empty): ${relativePath}`);
return 'deleted';
} else {
if (!dryRun) {
writeFileSync(file, stripped);
}
logger.debug('CLAUDE_MD', `${dryRun ? '[DRY-RUN] Would clean' : 'Cleaned'}: ${relativePath}`);
return 'cleaned';
}
}
/** /**
* Clean up auto-generated CLAUDE.md files. * Clean up auto-generated CLAUDE.md files.
* *
@@ -447,7 +520,6 @@ export async function generateClaudeMd(dryRun: boolean): Promise<number> {
* @returns Exit code (0 for success, 1 for error) * @returns Exit code (0 for success, 1 for error)
*/ */
export async function cleanClaudeMd(dryRun: boolean): Promise<number> { export async function cleanClaudeMd(dryRun: boolean): Promise<number> {
try {
const workingDir = process.cwd(); const workingDir = process.cwd();
logger.info('CLAUDE_MD', 'Starting CLAUDE.md cleanup', { logger.info('CLAUDE_MD', 'Starting CLAUDE.md cleanup', {
@@ -498,47 +570,12 @@ export async function cleanClaudeMd(dryRun: boolean): Promise<number> {
logger.info('CLAUDE_MD', `Found ${filesToProcess.length} CLAUDE.md files with auto-generated content`); logger.info('CLAUDE_MD', `Found ${filesToProcess.length} CLAUDE.md files with auto-generated content`);
let deletedCount = 0;
let cleanedCount = 0;
let errorCount = 0;
for (const file of filesToProcess) {
const relativePath = path.relative(workingDir, file);
try { try {
const content = readFileSync(file, 'utf-8'); return processFilesForCleanup(filesToProcess, workingDir, dryRun);
const stripped = content.replace(/<claude-mem-context>[\s\S]*?<\/claude-mem-context>/g, '').trim();
if (stripped === '') {
if (!dryRun) {
unlinkSync(file);
}
logger.debug('CLAUDE_MD', `${dryRun ? '[DRY-RUN] Would delete' : 'Deleted'} (empty): ${relativePath}`);
deletedCount++;
} else {
if (!dryRun) {
writeFileSync(file, stripped);
}
logger.debug('CLAUDE_MD', `${dryRun ? '[DRY-RUN] Would clean' : 'Cleaned'}: ${relativePath}`);
cleanedCount++;
}
} catch (error) {
logger.warn('CLAUDE_MD', `Error processing ${relativePath}`, { error: String(error) });
errorCount++;
}
}
logger.info('CLAUDE_MD', 'CLAUDE.md cleanup complete', {
deleted: deletedCount,
cleaned: cleanedCount,
errors: errorCount,
dryRun
});
return 0;
} catch (error) { } catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.error('CLAUDE_MD', 'Fatal error during CLAUDE.md cleanup', { logger.error('CLAUDE_MD', 'Fatal error during CLAUDE.md cleanup', {
error: String(error) error: errorMessage
}); });
return 1; return 1;
} }
src/cli/handlers/context.ts
+20 -21
View File
@@ -43,22 +43,29 @@ export const contextHandler: EventHandler = {
const apiPath = `/api/context/inject?projects=${encodeURIComponent(projectsParam)}&platformSource=${encodeURIComponent(platformSource)}`; const apiPath = `/api/context/inject?projects=${encodeURIComponent(projectsParam)}&platformSource=${encodeURIComponent(platformSource)}`;
const colorApiPath = input.platform === 'claude-code' ? `${apiPath}&colors=true` : apiPath; const colorApiPath = input.platform === 'claude-code' ? `${apiPath}&colors=true` : apiPath;
// Note: Removed AbortSignal.timeout due to Windows Bun cleanup issue (libuv assertion) const emptyResult = {
// Worker service has its own timeouts, so client-side timeout is redundant
try {
// Fetch markdown (for Claude context) and optionally colored (for user display)
const [response, colorResponse] = await Promise.all([
workerHttpRequest(apiPath),
showTerminalOutput ? workerHttpRequest(colorApiPath).catch(() => null) : Promise.resolve(null)
]);
if (!response.ok) {
// Log but don't throw — context fetch failure should not block session start
logger.warn('HOOK', 'Context generation failed, returning empty', { status: response.status });
return {
hookSpecificOutput: { hookEventName: 'SessionStart', additionalContext: '' }, hookSpecificOutput: { hookEventName: 'SessionStart', additionalContext: '' },
exitCode: HOOK_EXIT_CODES.SUCCESS exitCode: HOOK_EXIT_CODES.SUCCESS
}; };
// Note: Removed AbortSignal.timeout due to Windows Bun cleanup issue (libuv assertion)
// Worker service has its own timeouts, so client-side timeout is redundant
let response: Response;
let colorResponse: Response | null;
try {
[response, colorResponse] = await Promise.all([
workerHttpRequest(apiPath),
showTerminalOutput ? workerHttpRequest(colorApiPath).catch(() => null) : Promise.resolve(null)
]);
} catch (error) {
// Worker unreachable — return empty context gracefully
logger.warn('HOOK', 'Context fetch error, returning empty', { error: error instanceof Error ? error.message : String(error) });
return emptyResult;
}
if (!response.ok) {
logger.warn('HOOK', 'Context generation failed, returning empty', { status: response.status });
return emptyResult;
} }
const [contextResult, colorResult] = await Promise.all([ const [contextResult, colorResult] = await Promise.all([
@@ -86,13 +93,5 @@ const apiPath = `/api/context/inject?projects=${encodeURIComponent(projectsParam
}, },
systemMessage systemMessage
}; };
} catch (error) {
// Worker unreachable — return empty context gracefully
logger.warn('HOOK', 'Context fetch error, returning empty', { error: error instanceof Error ? error.message : String(error) });
return {
hookSpecificOutput: { hookEventName: 'SessionStart', additionalContext: '' },
exitCode: HOOK_EXIT_CODES.SUCCESS
};
}
} }
}; };
src/cli/handlers/file-context.ts
+15 -14
View File
@@ -199,9 +199,12 @@ export const fileContextHandler: EventHandler = {
return { continue: true, suppressOutput: true }; return { continue: true, suppressOutput: true };
} }
fileMtimeMs = stat.mtimeMs; fileMtimeMs = stat.mtimeMs;
} catch (err: any) { } catch (err) {
if (err.code === 'ENOENT') return { continue: true, suppressOutput: true }; if (err instanceof Error && 'code' in err && (err as NodeJS.ErrnoException).code === 'ENOENT') {
return { continue: true, suppressOutput: true };
}
// Other errors (symlink, permission denied) — fall through and let gate proceed // Other errors (symlink, permission denied) — fall through and let gate proceed
logger.debug('HOOK', 'File stat failed, proceeding with gate', { error: err instanceof Error ? err.message : String(err) });
} }
// Check if project is excluded from tracking // Check if project is excluded from tracking
@@ -218,9 +221,7 @@ export const fileContextHandler: EventHandler = {
} }
// Query worker for observations related to this file // Query worker for observations related to this file
try {
const context = getProjectContext(input.cwd); const context = getProjectContext(input.cwd);
// Observations store relative paths — convert absolute to relative using cwd
const cwd = input.cwd || process.cwd(); const cwd = input.cwd || process.cwd();
const absolutePath = path.isAbsolute(filePath) ? filePath : path.resolve(cwd, filePath); const absolutePath = path.isAbsolute(filePath) ? filePath : path.resolve(cwd, filePath);
const relativePath = path.relative(cwd, absolutePath).split(path.sep).join("/"); const relativePath = path.relative(cwd, absolutePath).split(path.sep).join("/");
@@ -231,16 +232,22 @@ export const fileContextHandler: EventHandler = {
} }
queryParams.set('limit', String(FETCH_LOOKAHEAD_LIMIT)); queryParams.set('limit', String(FETCH_LOOKAHEAD_LIMIT));
const response = await workerHttpRequest(`/api/observations/by-file?${queryParams.toString()}`, { let data: { observations: ObservationRow[]; count: number };
method: 'GET', try {
}); const response = await workerHttpRequest(`/api/observations/by-file?${queryParams.toString()}`, { method: 'GET' });
if (!response.ok) { if (!response.ok) {
logger.warn('HOOK', 'File context query failed, skipping', { status: response.status, filePath }); logger.warn('HOOK', 'File context query failed, skipping', { status: response.status, filePath });
return { continue: true, suppressOutput: true }; return { continue: true, suppressOutput: true };
} }
const data = await response.json() as { observations: ObservationRow[]; count: number }; data = await response.json() as { observations: ObservationRow[]; count: number };
} catch (error) {
logger.warn('HOOK', 'File context fetch error, skipping', {
error: error instanceof Error ? error.message : String(error),
});
return { continue: true, suppressOutput: true };
}
if (!data.observations || data.observations.length === 0) { if (!data.observations || data.observations.length === 0) {
return { continue: true, suppressOutput: true }; return { continue: true, suppressOutput: true };
@@ -285,11 +292,5 @@ export const fileContextHandler: EventHandler = {
updatedInput, updatedInput,
}, },
}; };
} catch (error) {
logger.warn('HOOK', 'File context fetch error, skipping', {
error: error instanceof Error ? error.message : String(error),
});
return { continue: true, suppressOutput: true };
}
}, },
}; };
src/cli/handlers/file-edit.ts
+18 -13
View File
@@ -11,6 +11,21 @@ import { logger } from '../../utils/logger.js';
import { HOOK_EXIT_CODES } from '../../shared/hook-constants.js'; import { HOOK_EXIT_CODES } from '../../shared/hook-constants.js';
import { normalizePlatformSource } from '../../shared/platform-source.js'; import { normalizePlatformSource } from '../../shared/platform-source.js';
async function sendFileEditObservation(requestBody: string, filePath: string): Promise<void> {
const response = await workerHttpRequest('/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: requestBody
});
if (!response.ok) {
logger.warn('HOOK', 'File edit observation storage failed, skipping', { status: response.status, filePath });
return;
}
logger.debug('HOOK', 'File edit observation sent successfully', { filePath });
}
export const fileEditHandler: EventHandler = { export const fileEditHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Ensure worker is running before any other logic // Ensure worker is running before any other logic
@@ -38,27 +53,17 @@ export const fileEditHandler: EventHandler = {
// Send to worker as an observation with file edit metadata // Send to worker as an observation with file edit metadata
// The observation handler on the worker will process this appropriately // The observation handler on the worker will process this appropriately
try { const requestBody = JSON.stringify({
const response = await workerHttpRequest('/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
contentSessionId: sessionId, contentSessionId: sessionId,
platformSource, platformSource,
tool_name: 'write_file', tool_name: 'write_file',
tool_input: { filePath, edits }, tool_input: { filePath, edits },
tool_response: { success: true }, tool_response: { success: true },
cwd cwd
})
}); });
if (!response.ok) { try {
// Log but don't throw — file edit observation failure should not block editing await sendFileEditObservation(requestBody, filePath);
logger.warn('HOOK', 'File edit observation storage failed, skipping', { status: response.status, filePath });
return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
}
logger.debug('HOOK', 'File edit observation sent successfully', { filePath });
} catch (error) { } catch (error) {
// Worker unreachable — skip file edit observation gracefully // Worker unreachable — skip file edit observation gracefully
logger.warn('HOOK', 'File edit observation fetch error, skipping', { error: error instanceof Error ? error.message : String(error) }); logger.warn('HOOK', 'File edit observation fetch error, skipping', { error: error instanceof Error ? error.message : String(error) });
src/cli/handlers/observation.ts
+21 -14
View File
@@ -13,6 +13,21 @@ import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js
import { USER_SETTINGS_PATH } from '../../shared/paths.js'; import { USER_SETTINGS_PATH } from '../../shared/paths.js';
import { normalizePlatformSource } from '../../shared/platform-source.js'; import { normalizePlatformSource } from '../../shared/platform-source.js';
async function sendObservationToWorker(requestBody: string, toolName: string): Promise<void> {
const response = await workerHttpRequest('/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: requestBody
});
if (!response.ok) {
logger.warn('HOOK', 'Observation storage failed, skipping', { status: response.status, toolName });
return;
}
logger.debug('HOOK', 'Observation sent successfully', { toolName });
}
export const observationHandler: EventHandler = { export const observationHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Ensure worker is running before any other logic // Ensure worker is running before any other logic
@@ -47,27 +62,19 @@ export const observationHandler: EventHandler = {
} }
// Send to worker - worker handles privacy check and database operations // Send to worker - worker handles privacy check and database operations
try { const requestBody = JSON.stringify({
const response = await workerHttpRequest('/api/sessions/observations', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
contentSessionId: sessionId, contentSessionId: sessionId,
platformSource, platformSource,
tool_name: toolName, tool_name: toolName,
tool_input: toolInput, tool_input: toolInput,
tool_response: toolResponse, tool_response: toolResponse,
cwd cwd,
}) agentId: input.agentId,
agentType: input.agentType
}); });
if (!response.ok) { try {
// Log but don't throw — observation storage failure should not block tool use await sendObservationToWorker(requestBody, toolName);
logger.warn('HOOK', 'Observation storage failed, skipping', { status: response.status, toolName });
return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
}
logger.debug('HOOK', 'Observation sent successfully', { toolName });
} catch (error) { } catch (error) {
// Worker unreachable — skip observation gracefully // Worker unreachable — skip observation gracefully
logger.warn('HOOK', 'Observation fetch error, skipping', { error: error instanceof Error ? error.message : String(error) }); logger.warn('HOOK', 'Observation fetch error, skipping', { error: error instanceof Error ? error.message : String(error) });
src/cli/handlers/session-complete.ts
+18 -20
View File
@@ -14,6 +14,21 @@ import { ensureWorkerRunning, workerHttpRequest } from '../../shared/worker-util
import { logger } from '../../utils/logger.js'; import { logger } from '../../utils/logger.js';
import { normalizePlatformSource } from '../../shared/platform-source.js'; import { normalizePlatformSource } from '../../shared/platform-source.js';
async function sendSessionCompleteRequest(sessionId: string, platformSource: string): Promise<void> {
const response = await workerHttpRequest('/api/sessions/complete', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ contentSessionId: sessionId, platformSource })
});
if (!response.ok) {
const text = await response.text();
logger.warn('HOOK', 'session-complete: Failed to complete session', { status: response.status, body: text });
} else {
logger.info('HOOK', 'Session completed successfully', { contentSessionId: sessionId });
}
}
export const sessionCompleteHandler: EventHandler = { export const sessionCompleteHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Ensure worker is running // Ensure worker is running
@@ -36,29 +51,12 @@ export const sessionCompleteHandler: EventHandler = {
}); });
try { try {
// Call the session complete endpoint by contentSessionId await sendSessionCompleteRequest(sessionId, platformSource);
const response = await workerHttpRequest('/api/sessions/complete', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
contentSessionId: sessionId,
platformSource
})
});
if (!response.ok) {
const text = await response.text();
logger.warn('HOOK', 'session-complete: Failed to complete session', {
status: response.status,
body: text
});
} else {
logger.info('HOOK', 'Session completed successfully', { contentSessionId: sessionId });
}
} catch (error) { } catch (error) {
// Log but don't fail - session may already be gone // Log but don't fail - session may already be gone
const errorMessage = error instanceof Error ? error.message : String(error);
logger.warn('HOOK', 'session-complete: Error completing session', { logger.warn('HOOK', 'session-complete: Error completing session', {
error: (error as Error).message error: errorMessage
}); });
} }
src/cli/handlers/session-init.ts
+23 -15
View File
@@ -14,6 +14,27 @@ import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js
import { USER_SETTINGS_PATH } from '../../shared/paths.js'; import { USER_SETTINGS_PATH } from '../../shared/paths.js';
import { normalizePlatformSource } from '../../shared/platform-source.js'; import { normalizePlatformSource } from '../../shared/platform-source.js';
async function fetchSemanticContext(
prompt: string,
project: string,
limit: string,
sessionDbId: number
): Promise<string> {
const semanticRes = await workerHttpRequest('/api/context/semantic', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ q: prompt, project, limit })
});
if (semanticRes.ok) {
const data = await semanticRes.json() as { context: string; count: number };
if (data.context) {
logger.debug('HOOK', `Semantic injection: ${data.count} observations for prompt`, { sessionId: sessionDbId, count: data.count });
return data.context;
}
}
return '';
}
export const sessionInitHandler: EventHandler = { export const sessionInitHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Ensure worker is running before any other logic // Ensure worker is running before any other logic
@@ -131,22 +152,9 @@ export const sessionInitHandler: EventHandler = {
let additionalContext = ''; let additionalContext = '';
if (semanticInject && prompt && prompt.length >= 20 && prompt !== '[media prompt]') { if (semanticInject && prompt && prompt.length >= 20 && prompt !== '[media prompt]') {
try {
const limit = settings.CLAUDE_MEM_SEMANTIC_INJECT_LIMIT || '5'; const limit = settings.CLAUDE_MEM_SEMANTIC_INJECT_LIMIT || '5';
const semanticRes = await workerHttpRequest('/api/context/semantic', { try {
method: 'POST', additionalContext = await fetchSemanticContext(prompt, project, limit, sessionDbId);
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ q: prompt, project, limit })
});
if (semanticRes.ok) {
const data = await semanticRes.json() as { context: string; count: number };
if (data.context) {
additionalContext = data.context;
logger.debug('HOOK', `Semantic injection: ${data.count} observations for prompt`, {
sessionId: sessionDbId, count: data.count
});
}
}
} catch (e) { } catch (e) {
// Graceful degradation — semantic injection is optional // Graceful degradation — semantic injection is optional
logger.debug('HOOK', 'Semantic injection unavailable', { logger.debug('HOOK', 'Semantic injection unavailable', {
src/cli/handlers/summarize.ts
+25 -7
View File
@@ -26,6 +26,20 @@ const MAX_WAIT_FOR_SUMMARY_MS = 110_000; // 110s — fits within Stop hook's 120
export const summarizeHandler: EventHandler = { export const summarizeHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Skip summaries in subagent context — subagents do not own the session summary.
// Gate on agentId only: that field is present exclusively for Task-spawned subagents.
// agentType alone (no agentId) indicates `--agent`-started main sessions, which still
// own their summary. Do this BEFORE ensureWorkerRunning() so a subagent Stop hook
// does not bootstrap the worker.
if (input.agentId) {
logger.debug('HOOK', 'Skipping summary: subagent context detected', {
sessionId: input.sessionId,
agentId: input.agentId,
agentType: input.agentType
});
return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
}
// Ensure worker is running before any other logic // Ensure worker is running before any other logic
const workerReady = await ensureWorkerRunning(); const workerReady = await ensureWorkerRunning();
if (!workerReady) { if (!workerReady) {
@@ -94,11 +108,18 @@ export const summarizeHandler: EventHandler = {
let summaryStored: boolean | null = null; let summaryStored: boolean | null = null;
while ((Date.now() - waitStart) < MAX_WAIT_FOR_SUMMARY_MS) { while ((Date.now() - waitStart) < MAX_WAIT_FOR_SUMMARY_MS) {
await new Promise(resolve => setTimeout(resolve, POLL_INTERVAL_MS)); await new Promise(resolve => setTimeout(resolve, POLL_INTERVAL_MS));
let statusResponse: Response;
let status: { queueLength?: number; summaryStored?: boolean | null };
try { try {
const statusResponse = await workerHttpRequest(`/api/sessions/status?contentSessionId=${encodeURIComponent(sessionId)}`, { statusResponse = await workerHttpRequest(`/api/sessions/status?contentSessionId=${encodeURIComponent(sessionId)}`, { timeoutMs: 5000 });
timeoutMs: 5000 status = await statusResponse.json() as { queueLength?: number; summaryStored?: boolean | null };
}); } catch (pollError) {
const status = await statusResponse.json() as { queueLength?: number; summaryStored?: boolean | null }; // Worker may be busy — keep polling
logger.debug('HOOK', 'Summary status poll failed, retrying', { error: pollError instanceof Error ? pollError.message : String(pollError) });
continue;
}
const queueLength = status.queueLength ?? 0; const queueLength = status.queueLength ?? 0;
// Only treat an empty queue as completion when the session exists (non-404). // Only treat an empty queue as completion when the session exists (non-404).
// A 404 means the session was not found — not that processing finished. // A 404 means the session was not found — not that processing finished.
@@ -118,9 +139,6 @@ export const summarizeHandler: EventHandler = {
} }
break; break;
} }
} catch {
// Worker may be busy — keep polling
}
} }
// 3. Complete the session — clean up active sessions map. // 3. Complete the session — clean up active sessions map.
src/cli/handlers/user-message.ts
+22 -27
View File
@@ -10,6 +10,25 @@ import type { EventHandler, NormalizedHookInput, HookResult } from '../types.js'
import { ensureWorkerRunning, getWorkerPort, workerHttpRequest } from '../../shared/worker-utils.js'; import { ensureWorkerRunning, getWorkerPort, workerHttpRequest } from '../../shared/worker-utils.js';
import { HOOK_EXIT_CODES } from '../../shared/hook-constants.js'; import { HOOK_EXIT_CODES } from '../../shared/hook-constants.js';
async function fetchAndDisplayContext(project: string, colorsParam: string, port: number): Promise<void> {
const response = await workerHttpRequest(
`/api/context/inject?project=${encodeURIComponent(project)}${colorsParam}`
);
if (!response.ok) {
return;
}
const output = await response.text();
process.stderr.write(
"\n\n" + String.fromCodePoint(0x1F4DD) + " Claude-Mem Context Loaded\n\n" +
output +
"\n\n" + String.fromCodePoint(0x1F4A1) + " Wrap any message with <private> ... </private> to prevent storing sensitive information.\n" +
"\n" + String.fromCodePoint(0x1F4AC) + " Community https://discord.gg/J4wttp9vDu" +
`\n` + String.fromCodePoint(0x1F4FA) + ` Watch live in browser http://localhost:${port}/\n`
);
}
export const userMessageHandler: EventHandler = { export const userMessageHandler: EventHandler = {
async execute(input: NormalizedHookInput): Promise<HookResult> { async execute(input: NormalizedHookInput): Promise<HookResult> {
// Ensure worker is running // Ensure worker is running
@@ -21,36 +40,12 @@ export const userMessageHandler: EventHandler = {
const port = getWorkerPort(); const port = getWorkerPort();
const project = basename(input.cwd ?? process.cwd()); const project = basename(input.cwd ?? process.cwd());
// Fetch formatted context directly from worker API
// Only request ANSI colors for platforms that render them (claude-code)
const colorsParam = input.platform === 'claude-code' ? '&colors=true' : ''; const colorsParam = input.platform === 'claude-code' ? '&colors=true' : '';
try { try {
const response = await workerHttpRequest( await fetchAndDisplayContext(project, colorsParam, port);
`/api/context/inject?project=${encodeURIComponent(project)}${colorsParam}` } catch {
);
if (!response.ok) {
// Don't throw - context fetch failure should not block the user's prompt
return { exitCode: HOOK_EXIT_CODES.SUCCESS };
}
const output = await response.text();
// Write to stderr for user visibility
// Note: Using process.stderr.write instead of console.error to avoid
// Claude Code treating this as a hook error. The actual hook output
// goes to stdout via hook-command.ts JSON serialization.
process.stderr.write(
"\n\n" + String.fromCodePoint(0x1F4DD) + " Claude-Mem Context Loaded\n\n" +
output +
"\n\n" + String.fromCodePoint(0x1F4A1) + " Wrap any message with <private> ... </private> to prevent storing sensitive information.\n" +
"\n" + String.fromCodePoint(0x1F4AC) + " Community https://discord.gg/J4wttp9vDu" +
`\n` + String.fromCodePoint(0x1F4FA) + ` Watch live in browser http://localhost:${port}/\n`
);
} catch (error) {
// Worker unreachable — skip user message gracefully // Worker unreachable — skip user message gracefully
// User message context error is non-critical — skip gracefully
} }
return { exitCode: HOOK_EXIT_CODES.SUCCESS }; return { exitCode: HOOK_EXIT_CODES.SUCCESS };
src/cli/hook-command.ts
+20 -11
View File
@@ -65,17 +65,12 @@ export function isWorkerUnavailableError(error: unknown): boolean {
return false; return false;
} }
export async function hookCommand(platform: string, event: string, options: HookCommandOptions = {}): Promise<number> { async function executeHookPipeline(
// Suppress stderr in hook context — Claude Code shows stderr as error UI (#1181) adapter: ReturnType<typeof getPlatformAdapter>,
// Exit 1: stderr shown to user. Exit 2: stderr fed to Claude for processing. handler: ReturnType<typeof getEventHandler>,
// All diagnostics go to log file via logger; stderr must stay clean. platform: string,
const originalStderrWrite = process.stderr.write.bind(process.stderr); options: HookCommandOptions
process.stderr.write = (() => true) as typeof process.stderr.write; ): Promise<number> {
try {
const adapter = getPlatformAdapter(platform);
const handler = getEventHandler(event);
const rawInput = await readJsonFromStdin(); const rawInput = await readJsonFromStdin();
const input = adapter.normalizeInput(rawInput); const input = adapter.normalizeInput(rawInput);
input.platform = platform; // Inject platform for handler-level decisions input.platform = platform; // Inject platform for handler-level decisions
@@ -88,6 +83,20 @@ export async function hookCommand(platform: string, event: string, options: Hook
process.exit(exitCode); process.exit(exitCode);
} }
return exitCode; return exitCode;
}
export async function hookCommand(platform: string, event: string, options: HookCommandOptions = {}): Promise<number> {
// Suppress stderr in hook context — Claude Code shows stderr as error UI (#1181)
// Exit 1: stderr shown to user. Exit 2: stderr fed to Claude for processing.
// All diagnostics go to log file via logger; stderr must stay clean.
const originalStderrWrite = process.stderr.write.bind(process.stderr);
process.stderr.write = (() => true) as typeof process.stderr.write;
const adapter = getPlatformAdapter(platform);
const handler = getEventHandler(event);
try {
return await executeHookPipeline(adapter, handler, platform, options);
} catch (error) { } catch (error) {
if (isWorkerUnavailableError(error)) { if (isWorkerUnavailableError(error)) {
// Worker unavailable — degrade gracefully, don't block the user // Worker unavailable — degrade gracefully, don't block the user
src/cli/stdin-reader.ts
+20 -11
View File
@@ -7,6 +7,8 @@
// to parse after each chunk. Once we have valid JSON, we resolve immediately // to parse after each chunk. Once we have valid JSON, we resolve immediately
// without waiting for EOF. This is the proper fix, not a timeout workaround. // without waiting for EOF. This is the proper fix, not a timeout workaround.
import { logger } from '../utils/logger.js';
/** /**
* Check if stdin is available and readable. * Check if stdin is available and readable.
* *
@@ -29,9 +31,10 @@ function isStdinAvailable(): boolean {
// eslint-disable-next-line @typescript-eslint/no-unused-expressions // eslint-disable-next-line @typescript-eslint/no-unused-expressions
stdin.readable; stdin.readable;
return true; return true;
} catch { } catch (error) {
// Bun crashed trying to access stdin (EINVAL from fstat) // Bun crashed trying to access stdin (EINVAL from fstat)
// This is expected when Claude Code doesn't provide valid stdin // This is expected when Claude Code doesn't provide valid stdin
logger.debug('HOOK', 'stdin not available (expected for some runtimes)', { error: error instanceof Error ? error.message : String(error) });
return false; return false;
} }
} }
@@ -49,8 +52,9 @@ function tryParseJson(input: string): { success: true; value: unknown } | { succ
try { try {
const value = JSON.parse(trimmed); const value = JSON.parse(trimmed);
return { success: true, value }; return { success: true, value };
} catch { } catch (error) {
// JSON is incomplete or invalid // JSON is incomplete or invalid — expected during incremental parsing
logger.debug('HOOK', 'JSON parse attempt incomplete', { error: error instanceof Error ? error.message : String(error) });
return { success: false }; return { success: false };
} }
} }
@@ -128,8 +132,7 @@ export async function readJsonFromStdin(): Promise<unknown> {
} }
}, SAFETY_TIMEOUT_MS); }, SAFETY_TIMEOUT_MS);
try { const onData = (chunk: Buffer | string) => {
process.stdin.on('data', (chunk) => {
input += chunk; input += chunk;
// Clear any pending parse delay // Clear any pending parse delay
@@ -148,9 +151,9 @@ export async function readJsonFromStdin(): Promise<unknown> {
parseDelayId = setTimeout(() => { parseDelayId = setTimeout(() => {
tryResolveWithJson(); tryResolveWithJson();
}, PARSE_DELAY_MS); }, PARSE_DELAY_MS);
}); };
process.stdin.on('end', () => { const onEnd = () => {
// stdin closed - parse whatever we have // stdin closed - parse whatever we have
if (!resolved) { if (!resolved) {
if (!tryResolveWithJson()) { if (!tryResolveWithJson()) {
@@ -158,17 +161,23 @@ export async function readJsonFromStdin(): Promise<unknown> {
resolveWith(input.trim() ? undefined : undefined); resolveWith(input.trim() ? undefined : undefined);
} }
} }
}); };
process.stdin.on('error', () => { const onError = () => {
if (!resolved) { if (!resolved) {
// Don't reject on stdin errors - just return undefined // Don't reject on stdin errors - just return undefined
// This is more graceful for hook execution // This is more graceful for hook execution
resolveWith(undefined); resolveWith(undefined);
} }
}); };
} catch {
try {
process.stdin.on('data', onData);
process.stdin.on('end', onEnd);
process.stdin.on('error', onError);
} catch (error) {
// If attaching listeners fails (Bun stdin issue), resolve with undefined // If attaching listeners fails (Bun stdin issue), resolve with undefined
logger.debug('HOOK', 'Failed to attach stdin listeners', { error: error instanceof Error ? error.message : String(error) });
resolved = true; resolved = true;
clearTimeout(safetyTimeoutId); clearTimeout(safetyTimeoutId);
cleanup(); cleanup();
src/cli/types.ts
+4
View File
@@ -12,6 +12,10 @@ export interface NormalizedHookInput {
edits?: unknown[]; // afterFileEdit edits?: unknown[]; // afterFileEdit
// Platform-specific metadata (source, reason, trigger, mcp_context, etc.) // Platform-specific metadata (source, reason, trigger, mcp_context, etc.)
metadata?: Record<string, unknown>; metadata?: Record<string, unknown>;
// Claude Code subagent identity — present only when hook fires inside a subagent.
// Main session has both undefined. Discriminator for subagent context.
agentId?: string; // Claude Code subagent agent_id (undefined in main session)
agentType?: string; // Claude Code subagent agent_type (undefined in main session)
} }
export interface HookResult { export interface HookResult {
src/integrations/opencode-plugin/index.ts
+15 -10
View File
@@ -105,17 +105,13 @@ async function workerPost(
path: string, path: string,
body: Record<string, unknown>, body: Record<string, unknown>,
): Promise<Record<string, unknown> | null> { ): Promise<Record<string, unknown> | null> {
let response: Response;
try { try {
const response = await fetch(`${WORKER_BASE_URL}${path}`, { response = await fetch(`${WORKER_BASE_URL}${path}`, {
method: "POST", method: "POST",
headers: { "Content-Type": "application/json" }, headers: { "Content-Type": "application/json" },
body: JSON.stringify(body), body: JSON.stringify(body),
}); });
if (!response.ok) {
console.warn(`[claude-mem] Worker POST ${path} returned ${response.status}`);
return null;
}
return (await response.json()) as Record<string, unknown>;
} catch (error: unknown) { } catch (error: unknown) {
// Gracefully handle ECONNREFUSED — worker may not be running // Gracefully handle ECONNREFUSED — worker may not be running
const message = error instanceof Error ? error.message : String(error); const message = error instanceof Error ? error.message : String(error);
@@ -124,6 +120,12 @@ async function workerPost(
} }
return null; return null;
} }
if (!response.ok) {
console.warn(`[claude-mem] Worker POST ${path} returned ${response.status}`);
return null;
}
return (await response.json()) as Record<string, unknown>;
} }
function workerPostFireAndForget( function workerPostFireAndForget(
@@ -339,8 +341,14 @@ export const ClaudeMemPlugin = async (ctx: OpenCodePluginContext) => {
return "claude-mem worker is not running. Start it with: npx claude-mem start"; return "claude-mem worker is not running. Start it with: npx claude-mem start";
} }
let data: any;
try { try {
const data = JSON.parse(text); data = JSON.parse(text);
} catch (error: unknown) {
console.warn('[claude-mem] Failed to parse search results:', error instanceof Error ? error.message : String(error));
return "Failed to parse search results.";
}
const items = Array.isArray(data.items) ? data.items : []; const items = Array.isArray(data.items) ? data.items : [];
if (items.length === 0) { if (items.length === 0) {
return `No results found for "${query}".`; return `No results found for "${query}".`;
@@ -354,9 +362,6 @@ export const ClaudeMemPlugin = async (ctx: OpenCodePluginContext) => {
return `${index + 1}. ${title}${project}`; return `${index + 1}. ${title}${project}`;
}) })
.join("\n"); .join("\n");
} catch {
return "Failed to parse search results.";
}
}, },
} satisfies ToolDefinition, } satisfies ToolDefinition,
}, },
src/npx-cli/commands/ide-detection.ts
+7 -2
View File
@@ -38,7 +38,11 @@ function isCommandInPath(command: string): boolean {
const whichCommand = IS_WINDOWS ? 'where' : 'which'; const whichCommand = IS_WINDOWS ? 'where' : 'which';
execSync(`${whichCommand} ${command}`, { stdio: 'pipe' }); execSync(`${whichCommand} ${command}`, { stdio: 'pipe' });
return true; return true;
} catch { } catch (error: unknown) {
// Command not found in PATH — expected for non-installed IDEs
if (process.env.DEBUG) {
console.error(`[ide-detection] ${command} not in PATH:`, error instanceof Error ? error.message : String(error));
}
return false; return false;
} }
} }
@@ -53,7 +57,8 @@ function hasVscodeExtension(extensionNameFragment: string): boolean {
try { try {
const entries = readdirSync(extensionsDirectory); const entries = readdirSync(extensionsDirectory);
return entries.some((entry) => entry.toLowerCase().includes(extensionNameFragment.toLowerCase())); return entries.some((entry) => entry.toLowerCase().includes(extensionNameFragment.toLowerCase()));
} catch { } catch (error: unknown) {
console.warn('[ide-detection] Failed to read VS Code extensions directory:', error instanceof Error ? error.message : String(error));
return false; return false;
} }
} }
src/npx-cli/commands/install.ts
+8 -4
View File
@@ -128,7 +128,8 @@ async function setupIDEs(selectedIDEs: string[]): Promise<string[]> {
{ stdio: 'inherit' }, { stdio: 'inherit' },
); );
log.success('Claude Code: plugin installed via CLI.'); log.success('Claude Code: plugin installed via CLI.');
} catch { } catch (error: unknown) {
console.error('[install] Claude Code plugin install error:', error instanceof Error ? error.message : String(error));
log.error('Claude Code: plugin install failed. Is `claude` CLI on your PATH?'); log.error('Claude Code: plugin install failed. Is `claude` CLI on your PATH?');
failedIDEs.push(ideId); failedIDEs.push(ideId);
} }
@@ -372,7 +373,8 @@ function runSmartInstall(): boolean {
...(IS_WINDOWS ? { shell: true as const } : {}), ...(IS_WINDOWS ? { shell: true as const } : {}),
}); });
return true; return true;
} catch { } catch (error: unknown) {
console.warn('[install] smart-install error:', error instanceof Error ? error.message : String(error));
log.warn('smart-install encountered an issue. You may need to install Bun/uv manually.'); log.warn('smart-install encountered an issue. You may need to install Bun/uv manually.');
return false; return false;
} }
@@ -409,7 +411,8 @@ export async function runInstallCommand(options: InstallOptions = {}): Promise<v
readFileSync(join(marketplaceDir, 'plugin', '.claude-plugin', 'plugin.json'), 'utf-8'), readFileSync(join(marketplaceDir, 'plugin', '.claude-plugin', 'plugin.json'), 'utf-8'),
); );
log.warn(`Existing installation detected (v${existingPluginJson.version ?? 'unknown'}).`); log.warn(`Existing installation detected (v${existingPluginJson.version ?? 'unknown'}).`);
} catch { } catch (error: unknown) {
console.warn('[install] Failed to read existing plugin version:', error instanceof Error ? error.message : String(error));
log.warn('Existing installation detected.'); log.warn('Existing installation detected.');
} }
@@ -498,7 +501,8 @@ export async function runInstallCommand(options: InstallOptions = {}): Promise<v
try { try {
runNpmInstallInMarketplace(); runNpmInstallInMarketplace();
return `Dependencies installed ${pc.green('OK')}`; return `Dependencies installed ${pc.green('OK')}`;
} catch { } catch (error: unknown) {
console.warn('[install] npm install error:', error instanceof Error ? error.message : String(error));
return `Dependencies may need manual install ${pc.yellow('!')}`; return `Dependencies may need manual install ${pc.yellow('!')}`;
} }
}, },
src/npx-cli/commands/runtime.ts
+21 -11
View File
@@ -154,8 +154,20 @@ export async function runSearchCommand(queryParts: string[]): Promise<void> {
const workerPort = process.env.CLAUDE_MEM_WORKER_PORT || '37777'; const workerPort = process.env.CLAUDE_MEM_WORKER_PORT || '37777';
const searchUrl = `http://127.0.0.1:${workerPort}/api/search?query=${encodeURIComponent(query)}`; const searchUrl = `http://127.0.0.1:${workerPort}/api/search?query=${encodeURIComponent(query)}`;
let response: Response;
try { try {
const response = await fetch(searchUrl); response = await fetch(searchUrl);
} catch (error: unknown) {
const message = error instanceof Error ? error.message : String(error);
const cause = error instanceof Error ? (error as any).cause : undefined;
if (cause?.code === 'ECONNREFUSED' || message.includes('ECONNREFUSED')) {
console.error(pc.red('Worker is not running.'));
console.error(`Start it with: ${pc.bold('npx claude-mem start')}`);
process.exit(1);
}
console.error(pc.red(`Search failed: ${message}`));
process.exit(1);
}
if (!response.ok) { if (!response.ok) {
if (response.status === 404) { if (response.status === 404) {
@@ -167,22 +179,20 @@ export async function runSearchCommand(queryParts: string[]): Promise<void> {
process.exit(1); process.exit(1);
} }
const data = await response.json(); let data: unknown;
try {
data = await response.json();
} catch (error: unknown) {
const message = error instanceof Error ? error.message : String(error);
console.error(pc.red(`Search failed: invalid JSON response (${message})`));
process.exit(1);
}
if (typeof data === 'object' && data !== null) { if (typeof data === 'object' && data !== null) {
console.log(JSON.stringify(data, null, 2)); console.log(JSON.stringify(data, null, 2));
} else { } else {
console.log(data); console.log(data);
} }
} catch (error: any) {
if (error?.cause?.code === 'ECONNREFUSED' || error?.message?.includes('ECONNREFUSED')) {
console.error(pc.red('Worker is not running.'));
console.error(`Start it with: ${pc.bold('npx claude-mem start')}`);
process.exit(1);
}
console.error(pc.red(`Search failed: ${error.message}`));
process.exit(1);
}
} }
/** /**
src/npx-cli/commands/uninstall.ts
+7 -4
View File
@@ -120,8 +120,10 @@ export async function runUninstallCommand(): Promise<void> {
signal: AbortSignal.timeout(1000), signal: AbortSignal.timeout(1000),
}); });
// Still alive — keep waiting // Still alive — keep waiting
} catch { } catch (error: unknown) {
break; // Connection refused = worker is gone // Connection refused = worker is gone (expected shutdown behavior)
console.error('[uninstall] Worker health check failed (worker stopped):', error instanceof Error ? error.message : String(error));
break;
} }
} }
p.log.info('Worker service stopped.'); p.log.info('Worker service stopped.');
@@ -201,8 +203,9 @@ export async function runUninstallCommand(): Promise<void> {
if (result === 0) { if (result === 0) {
p.log.info(`${label}: removed.`); p.log.info(`${label}: removed.`);
} }
} catch { } catch (error: unknown) {
// IDE not configured or uninstaller errored — skip silently // IDE not configured or uninstaller errored — log and continue
console.warn(`[uninstall] ${label} cleanup failed:`, error instanceof Error ? error.message : String(error));
} }
} }
src/npx-cli/utils/bun-resolver.ts
+2 -1
View File
@@ -79,7 +79,8 @@ export function getBunVersionString(): string | null {
shell: IS_WINDOWS, shell: IS_WINDOWS,
}); });
return result.status === 0 ? result.stdout.trim() : null; return result.status === 0 ? result.stdout.trim() : null;
} catch { } catch (error: unknown) {
console.error('[bun-resolver] Failed to get Bun version:', error instanceof Error ? error.message : String(error));
return null; return null;
} }
} }
src/sdk/parser.ts
+78 -5
View File
@@ -113,8 +113,13 @@ export function parseObservations(text: string, correlationId?: string): ParsedO
/** /**
* Parse summary XML block from SDK response * Parse summary XML block from SDK response
* Returns null if no valid summary found or if summary was skipped * Returns null if no valid summary found or if summary was skipped
*
* @param coerceFromObservation - When true, attempts to convert <observation> tags
* into summary fields if no <summary> tags are found. Only set this when the
* response was expected to be a summary (i.e., a summarize message was sent).
* Prevents the infinite retry loop described in #1633.
*/ */
export function parseSummary(text: string, sessionId?: number): ParsedSummary | null { export function parseSummary(text: string, sessionId?: number, coerceFromObservation: boolean = false): ParsedSummary | null {
// Check for skip_summary first // Check for skip_summary first
const skipRegex = /<skip_summary\s+reason="([^"]+)"\s*\/>/; const skipRegex = /<skip_summary\s+reason="([^"]+)"\s*\/>/;
const skipMatch = skipRegex.exec(text); const skipMatch = skipRegex.exec(text);
@@ -132,10 +137,23 @@ export function parseSummary(text: string, sessionId?: number): ParsedSummary |
const summaryMatch = summaryRegex.exec(text); const summaryMatch = summaryRegex.exec(text);
if (!summaryMatch) { if (!summaryMatch) {
// Log when the response contains <observation> instead of <summary> // When the LLM returns <observation> tags instead of <summary> tags on a
// to help diagnose prompt conditioning issues (see #1312) // summary turn, coerce the observation content into summary fields rather
if (/<observation>/.test(text)) { // than discarding it. This breaks the infinite retry loop described in
logger.warn('PARSER', 'Summary response contained <observation> tags instead of <summary> — prompt conditioning may need strengthening', { sessionId }); // #1633: without coercion, the summary is silently dropped, the session
// completes without a summary, a new session is spawned with an ever-growing
// prompt, and the cycle repeats.
//
// parseSummary is called on every response (see ResponseProcessor), not just
// summary turns — so the absence of <summary> in an observation response is
// expected, not a prompt-conditioning failure. Only act when the caller
// actually expected a summary (coerceFromObservation=true).
if (coerceFromObservation && /<observation>/.test(text)) {
const coerced = coerceObservationToSummary(text, sessionId);
if (coerced) {
return coerced;
}
logger.warn('PARSER', 'Summary response contained <observation> tags instead of <summary> — coercion failed, no usable content', { sessionId });
} }
return null; return null;
} }
@@ -171,6 +189,17 @@ export function parseSummary(text: string, sessionId?: number): ParsedSummary |
// This is NOT the same as missing some fields (which we intentionally allow above). // This is NOT the same as missing some fields (which we intentionally allow above).
// Fix for #1360. // Fix for #1360.
if (!request && !investigated && !learned && !completed && !next_steps) { if (!request && !investigated && !learned && !completed && !next_steps) {
// If the response also contains <observation> tags with real content, fall
// back to coercion rather than discarding the response entirely — this covers
// the case where the LLM wraps empty <summary></summary> around observation
// content, which would otherwise resurrect the #1633 retry loop.
if (coerceFromObservation && /<observation>/.test(text)) {
const coerced = coerceObservationToSummary(text, sessionId);
if (coerced) {
logger.warn('PARSER', 'Empty <summary> match rejected — coerced from <observation> fallback (#1633)', { sessionId });
return coerced;
}
}
logger.warn('PARSER', 'Summary match has no sub-tags — skipping false positive', { sessionId }); logger.warn('PARSER', 'Summary match has no sub-tags — skipping false positive', { sessionId });
return null; return null;
} }
@@ -185,6 +214,50 @@ export function parseSummary(text: string, sessionId?: number): ParsedSummary |
}; };
} }
/**
* Coerce <observation> response into a ParsedSummary when <summary> tags are missing.
* Maps observation fields to the closest summary equivalents so that a usable
* summary is stored instead of nothing — breaking the retry loop (#1633).
*/
function coerceObservationToSummary(text: string, sessionId?: number): ParsedSummary | null {
// Iterate all <observation> blocks — if the LLM emits multiple and the first is
// empty, we still want to salvage the first one that has usable content.
const obsRegex = /<observation>([\s\S]*?)<\/observation>/g;
let obsMatch: RegExpExecArray | null;
let blockIndex = 0;
while ((obsMatch = obsRegex.exec(text)) !== null) {
const obsContent = obsMatch[1];
const title = extractField(obsContent, 'title');
const subtitle = extractField(obsContent, 'subtitle');
const narrative = extractField(obsContent, 'narrative');
const facts = extractArrayElements(obsContent, 'facts', 'fact');
if (title || narrative || facts.length > 0) {
// Map observation fields → summary fields (best-effort)
const request = title || subtitle || null;
const investigated = narrative || null;
const learned = facts.length > 0 ? facts.join('; ') : null;
const completed = title ? `${title}${subtitle ? ' — ' + subtitle : ''}` : null;
const next_steps = null; // No direct observation equivalent
logger.warn('PARSER', 'Coerced <observation> response into <summary> to prevent retry loop (#1633)', {
sessionId,
blockIndex,
hasTitle: !!title,
hasNarrative: !!narrative,
factCount: facts.length,
});
return { request, investigated, learned, completed, next_steps, notes: null };
}
blockIndex++;
}
return null;
}
/** /**
* Extract a simple field value from XML content * Extract a simple field value from XML content
* Returns null for missing or empty/whitespace-only fields * Returns null for missing or empty/whitespace-only fields
src/sdk/prompts.ts
+24 -7
View File
@@ -6,6 +6,20 @@
import { logger } from '../utils/logger.js'; import { logger } from '../utils/logger.js';
import type { ModeConfig } from '../services/domain/types.js'; import type { ModeConfig } from '../services/domain/types.js';
/**
* Marker string embedded in summary prompts — used by ResponseProcessor to detect
* whether the most recent user message was a summary request (enables observation→summary
* coercion for #1633). Keep in sync with buildSummaryPrompt below.
*/
export const SUMMARY_MODE_MARKER = 'MODE SWITCH: PROGRESS SUMMARY';
/**
* Maximum consecutive summary failures before the circuit breaker opens.
* After this many failures, SessionManager.queueSummarize will skip further
* summarize requests to prevent the infinite retry loop (#1633).
*/
export const MAX_CONSECUTIVE_SUMMARY_FAILURES = 3;
export interface Observation { export interface Observation {
id: number; id: number;
tool_name: string; tool_name: string;
@@ -95,19 +109,19 @@ export function buildObservationPrompt(obs: Observation): string {
try { try {
toolInput = typeof obs.tool_input === 'string' ? JSON.parse(obs.tool_input) : obs.tool_input; toolInput = typeof obs.tool_input === 'string' ? JSON.parse(obs.tool_input) : obs.tool_input;
} catch (error) { } catch (error: unknown) {
logger.debug('SDK', 'Tool input is plain string, using as-is', { logger.debug('SDK', 'Tool input is plain string, using as-is', {
toolName: obs.tool_name toolName: obs.tool_name
}, error as Error); }, error instanceof Error ? error : new Error(String(error)));
toolInput = obs.tool_input; toolInput = obs.tool_input;
} }
try { try {
toolOutput = typeof obs.tool_output === 'string' ? JSON.parse(obs.tool_output) : obs.tool_output; toolOutput = typeof obs.tool_output === 'string' ? JSON.parse(obs.tool_output) : obs.tool_output;
} catch (error) { } catch (error: unknown) {
logger.debug('SDK', 'Tool output is plain string, using as-is', { logger.debug('SDK', 'Tool output is plain string, using as-is', {
toolName: obs.tool_name toolName: obs.tool_name
}, error as Error); }, error instanceof Error ? error : new Error(String(error)));
toolOutput = obs.tool_output; toolOutput = obs.tool_output;
} }
@@ -134,9 +148,11 @@ export function buildSummaryPrompt(session: SDKSession, mode: ModeConfig): strin
return ''; return '';
})(); })();
return `--- MODE SWITCH: PROGRESS SUMMARY --- return `--- ${SUMMARY_MODE_MARKER} ---
Do NOT output <observation> tags. This is a summary request, not an observation request. ⚠️ CRITICAL TAG REQUIREMENT — READ CAREFULLY:
Your response MUST use <summary> tags ONLY. Any <observation> output will be discarded. • You MUST wrap your ENTIRE response in <summary>...</summary> tags.
• Do NOT use <observation> tags. <observation> output will be DISCARDED and cause a system error.
• The ONLY accepted root tag is <summary>. Any other root tag is a protocol violation.
${mode.prompts.header_summary_checkpoint} ${mode.prompts.header_summary_checkpoint}
${mode.prompts.summary_instruction} ${mode.prompts.summary_instruction}
@@ -154,6 +170,7 @@ ${mode.prompts.summary_format_instruction}
<notes>${mode.prompts.xml_summary_notes_placeholder}</notes> <notes>${mode.prompts.xml_summary_notes_placeholder}</notes>
</summary> </summary>
REMINDER: Your response MUST use <summary> as the root tag, NOT <observation>.
${mode.prompts.summary_footer}`; ${mode.prompts.summary_footer}`;
} }
src/servers/mcp-server.ts
+27 -20
View File
@@ -108,7 +108,6 @@ async function callWorkerAPI(
): Promise<{ content: Array<{ type: 'text'; text: string }>; isError?: boolean }> { ): Promise<{ content: Array<{ type: 'text'; text: string }>; isError?: boolean }> {
logger.debug('SYSTEM', '→ Worker API', undefined, { endpoint, params }); logger.debug('SYSTEM', '→ Worker API', undefined, { endpoint, params });
try {
const searchParams = new URLSearchParams(); const searchParams = new URLSearchParams();
// Convert params to query string // Convert params to query string
@@ -119,6 +118,8 @@ async function callWorkerAPI(
} }
const apiPath = `${endpoint}?${searchParams}`; const apiPath = `${endpoint}?${searchParams}`;
try {
const response = await workerHttpRequest(apiPath); const response = await workerHttpRequest(apiPath);
if (!response.ok) { if (!response.ok) {
@@ -132,8 +133,8 @@ async function callWorkerAPI(
// Worker returns { content: [...] } format directly // Worker returns { content: [...] } format directly
return data; return data;
} catch (error) { } catch (error: unknown) {
logger.error('SYSTEM', '← Worker API error', { endpoint }, error as Error); logger.error('SYSTEM', '← Worker API error', { endpoint }, error instanceof Error ? error : new Error(String(error)));
return { return {
content: [{ content: [{
type: 'text' as const, type: 'text' as const,
@@ -144,16 +145,10 @@ async function callWorkerAPI(
} }
} }
/** async function executeWorkerPostRequest(
* Call Worker HTTP API with POST body
*/
async function callWorkerAPIPost(
endpoint: string, endpoint: string,
body: Record<string, any> body: Record<string, any>
): Promise<{ content: Array<{ type: 'text'; text: string }>; isError?: boolean }> { ): Promise<{ content: Array<{ type: 'text'; text: string }> }> {
logger.debug('HTTP', 'Worker API request (POST)', undefined, { endpoint });
try {
const response = await workerHttpRequest(endpoint, { const response = await workerHttpRequest(endpoint, {
method: 'POST', method: 'POST',
headers: { 'Content-Type': 'application/json' }, headers: { 'Content-Type': 'application/json' },
@@ -169,15 +164,27 @@ async function callWorkerAPIPost(
logger.debug('HTTP', 'Worker API success (POST)', undefined, { endpoint }); logger.debug('HTTP', 'Worker API success (POST)', undefined, { endpoint });
// Wrap raw data in MCP format
return { return {
content: [{ content: [{
type: 'text' as const, type: 'text' as const,
text: JSON.stringify(data, null, 2) text: JSON.stringify(data, null, 2)
}] }]
}; };
} catch (error) { }
logger.error('HTTP', 'Worker API error (POST)', { endpoint }, error as Error);
/**
* Call Worker HTTP API with POST body
*/
async function callWorkerAPIPost(
endpoint: string,
body: Record<string, any>
): Promise<{ content: Array<{ type: 'text'; text: string }>; isError?: boolean }> {
logger.debug('HTTP', 'Worker API request (POST)', undefined, { endpoint });
try {
return await executeWorkerPostRequest(endpoint, body);
} catch (error: unknown) {
logger.error('HTTP', 'Worker API error (POST)', { endpoint }, error instanceof Error ? error : new Error(String(error)));
return { return {
content: [{ content: [{
type: 'text' as const, type: 'text' as const,
@@ -195,9 +202,9 @@ async function verifyWorkerConnection(): Promise<boolean> {
try { try {
const response = await workerHttpRequest('/api/health'); const response = await workerHttpRequest('/api/health');
return response.ok; return response.ok;
} catch (error) { } catch (error: unknown) {
// Expected during worker startup or if worker is down // Expected during worker startup or if worker is down
logger.debug('SYSTEM', 'Worker health check failed', {}, error as Error); logger.debug('SYSTEM', 'Worker health check failed', {}, error instanceof Error ? error : new Error(String(error)));
return false; return false;
} }
} }
@@ -229,12 +236,12 @@ async function ensureWorkerConnection(): Promise<boolean> {
); );
} }
return started; return started;
} catch (error) { } catch (error: unknown) {
logger.error( logger.error(
'SYSTEM', 'SYSTEM',
'Worker auto-start threw — MCP tools that require the worker (search, timeline, get_observations) will fail until the worker is running.', 'Worker auto-start threw — MCP tools that require the worker (search, timeline, get_observations) will fail until the worker is running.',
undefined, undefined,
error as Error error instanceof Error ? error : new Error(String(error))
); );
return false; return false;
} }
@@ -593,8 +600,8 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
try { try {
return await tool.handler(request.params.arguments || {}); return await tool.handler(request.params.arguments || {});
} catch (error) { } catch (error: unknown) {
logger.error('SYSTEM', 'Tool execution failed', { tool: request.params.name }, error as Error); logger.error('SYSTEM', 'Tool execution failed', { tool: request.params.name }, error instanceof Error ? error : new Error(String(error)));
return { return {
content: [{ content: [{
type: 'text' as const, type: 'text' as const,
src/services/context/ContextBuilder.ts
+8 -4
View File
@@ -49,14 +49,18 @@ const VERSION_MARKER_PATH = path.join(
function initializeDatabase(): SessionStore | null { function initializeDatabase(): SessionStore | null {
try { try {
return new SessionStore(); return new SessionStore();
} catch (error: any) { } catch (error: unknown) {
if (error.code === 'ERR_DLOPEN_FAILED') { if (error instanceof Error && (error as NodeJS.ErrnoException).code === 'ERR_DLOPEN_FAILED') {
try { try {
unlinkSync(VERSION_MARKER_PATH); unlinkSync(VERSION_MARKER_PATH);
} catch (unlinkError) { } catch (unlinkError) {
logger.debug('SYSTEM', 'Marker file cleanup failed (may not exist)', {}, unlinkError as Error); if (unlinkError instanceof Error) {
logger.debug('WORKER', 'Marker file cleanup failed (may not exist)', {}, unlinkError);
} else {
logger.debug('WORKER', 'Marker file cleanup failed (may not exist)', { error: String(unlinkError) });
} }
logger.error('SYSTEM', 'Native module rebuild needed - restart Claude Code to auto-fix'); }
logger.error('WORKER', 'Native module rebuild needed - restart Claude Code to auto-fix');
return null; return null;
} }
throw error; throw error;
src/services/context/ObservationCompiler.ts
+35 -29
View File
@@ -208,52 +208,58 @@ function cwdToDashed(cwd: string): string {
} }
/** /**
* Extract prior messages from transcript file * Find the last assistant message text from parsed transcript lines.
*/ */
export function extractPriorMessages(transcriptPath: string): PriorMessages { function parseAssistantTextFromLine(line: string): string | null {
try { if (!line.includes('"type":"assistant"')) return null;
if (!existsSync(transcriptPath)) {
return { userMessage: '', assistantMessage: '' };
}
const content = readFileSync(transcriptPath, 'utf-8').trim();
if (!content) {
return { userMessage: '', assistantMessage: '' };
}
const lines = content.split('\n').filter(line => line.trim());
let lastAssistantMessage = '';
for (let i = lines.length - 1; i >= 0; i--) {
try {
const line = lines[i];
if (!line.includes('"type":"assistant"')) {
continue;
}
const entry = JSON.parse(line); const entry = JSON.parse(line);
if (entry.type === 'assistant' && entry.message?.content && Array.isArray(entry.message.content)) { if (entry.type === 'assistant' && entry.message?.content && Array.isArray(entry.message.content)) {
let text = ''; let text = '';
for (const block of entry.message.content) { for (const block of entry.message.content) {
if (block.type === 'text') { if (block.type === 'text') text += block.text;
text += block.text;
}
} }
text = text.replace(SYSTEM_REMINDER_REGEX, '').trim(); text = text.replace(SYSTEM_REMINDER_REGEX, '').trim();
if (text) { if (text) return text;
lastAssistantMessage = text;
break;
} }
return null;
} }
function findLastAssistantMessage(lines: string[]): string {
for (let i = lines.length - 1; i >= 0; i--) {
try {
const result = parseAssistantTextFromLine(lines[i]);
if (result) return result;
} catch (parseError) { } catch (parseError) {
logger.debug('PARSER', 'Skipping malformed transcript line', { lineIndex: i }, parseError as Error); if (parseError instanceof Error) {
logger.debug('WORKER', 'Skipping malformed transcript line', { lineIndex: i }, parseError);
} else {
logger.debug('WORKER', 'Skipping malformed transcript line', { lineIndex: i, error: String(parseError) });
}
continue; continue;
} }
} }
return '';
}
/**
* Extract prior messages from transcript file
*/
export function extractPriorMessages(transcriptPath: string): PriorMessages {
try {
if (!existsSync(transcriptPath)) return { userMessage: '', assistantMessage: '' };
const content = readFileSync(transcriptPath, 'utf-8').trim();
if (!content) return { userMessage: '', assistantMessage: '' };
const lines = content.split('\n').filter(line => line.trim());
const lastAssistantMessage = findLastAssistantMessage(lines);
return { userMessage: '', assistantMessage: lastAssistantMessage }; return { userMessage: '', assistantMessage: lastAssistantMessage };
} catch (error) { } catch (error) {
logger.failure('WORKER', `Failed to extract prior messages from transcript`, { transcriptPath }, error as Error); if (error instanceof Error) {
logger.failure('WORKER', 'Failed to extract prior messages from transcript', { transcriptPath }, error);
} else {
logger.warn('WORKER', 'Failed to extract prior messages from transcript', { transcriptPath, error: String(error) });
}
return { userMessage: '', assistantMessage: '' }; return { userMessage: '', assistantMessage: '' };
} }
} }
src/services/domain/ModeManager.ts
+15 -3
View File
@@ -144,7 +144,11 @@ export class ModeManager {
}); });
return mode; return mode;
} catch (error) { } catch (error) {
logger.warn('SYSTEM', `Mode file not found: ${modeId}, falling back to 'code'`); if (error instanceof Error) {
logger.warn('WORKER', `Mode file not found: ${modeId}, falling back to 'code'`, { message: error.message });
} else {
logger.warn('WORKER', `Mode file not found: ${modeId}, falling back to 'code'`, { error: String(error) });
}
// If we're already trying to load 'code', throw to prevent infinite recursion // If we're already trying to load 'code', throw to prevent infinite recursion
if (modeId === 'code') { if (modeId === 'code') {
throw new Error('Critical: code.json mode file missing'); throw new Error('Critical: code.json mode file missing');
@@ -161,7 +165,11 @@ export class ModeManager {
try { try {
parentMode = this.loadMode(parentId); parentMode = this.loadMode(parentId);
} catch (error) { } catch (error) {
logger.warn('SYSTEM', `Parent mode '${parentId}' not found for ${modeId}, falling back to 'code'`); if (error instanceof Error) {
logger.warn('WORKER', `Parent mode '${parentId}' not found for ${modeId}, falling back to 'code'`, { message: error.message });
} else {
logger.warn('WORKER', `Parent mode '${parentId}' not found for ${modeId}, falling back to 'code'`, { error: String(error) });
}
parentMode = this.loadMode('code'); parentMode = this.loadMode('code');
} }
@@ -171,7 +179,11 @@ export class ModeManager {
overrideConfig = this.loadModeFile(overrideId); overrideConfig = this.loadModeFile(overrideId);
logger.debug('SYSTEM', `Loaded override file: ${overrideId} for parent ${parentId}`); logger.debug('SYSTEM', `Loaded override file: ${overrideId} for parent ${parentId}`);
} catch (error) { } catch (error) {
logger.warn('SYSTEM', `Override file '${overrideId}' not found, using parent mode '${parentId}' only`); if (error instanceof Error) {
logger.warn('WORKER', `Override file '${overrideId}' not found, using parent mode '${parentId}' only`, { message: error.message });
} else {
logger.warn('WORKER', `Override file '${overrideId}' not found, using parent mode '${parentId}' only`, { error: String(error) });
}
this.activeMode = parentMode; this.activeMode = parentMode;
return parentMode; return parentMode;
} }
src/services/infrastructure/HealthMonitor.ts
+14 -2
View File
@@ -53,7 +53,12 @@ export async function isPortInUse(port: number): Promise<boolean> {
try { try {
const response = await fetch(`http://127.0.0.1:${port}/api/health`); const response = await fetch(`http://127.0.0.1:${port}/api/health`);
return response.ok; return response.ok;
} catch { } catch (error) {
if (error instanceof Error) {
logger.debug('SYSTEM', 'Windows health check failed (port not in use)', {}, error);
} else {
logger.debug('SYSTEM', 'Windows health check failed (port not in use)', { error: String(error) });
}
return false; return false;
} }
} }
@@ -92,7 +97,11 @@ async function pollEndpointUntilOk(
if (result.ok) return true; if (result.ok) return true;
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Retry loop - expected failures during startup, will retry // [ANTI-PATTERN IGNORED]: Retry loop - expected failures during startup, will retry
logger.debug('SYSTEM', retryLogMessage, {}, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', retryLogMessage, {}, error);
} else {
logger.debug('SYSTEM', retryLogMessage, { error: String(error) });
}
} }
await new Promise(r => setTimeout(r, 500)); await new Promise(r => setTimeout(r, 500));
} }
@@ -166,6 +175,7 @@ export function getInstalledPluginVersion(): string {
const packageJson = JSON.parse(readFileSync(packageJsonPath, 'utf-8')); const packageJson = JSON.parse(readFileSync(packageJsonPath, 'utf-8'));
return packageJson.version; return packageJson.version;
} catch (error: unknown) { } catch (error: unknown) {
if (error instanceof Error) {
const code = (error as NodeJS.ErrnoException).code; const code = (error as NodeJS.ErrnoException).code;
if (code === 'ENOENT' || code === 'EBUSY') { if (code === 'ENOENT' || code === 'EBUSY') {
logger.debug('SYSTEM', 'Could not read plugin version (shutdown race)', { code }); logger.debug('SYSTEM', 'Could not read plugin version (shutdown race)', { code });
@@ -173,6 +183,8 @@ export function getInstalledPluginVersion(): string {
} }
throw error; throw error;
} }
throw error;
}
} }
/** /**
src/services/infrastructure/ProcessManager.ts
+184 -78
View File
@@ -53,12 +53,21 @@ function isBunExecutablePath(executablePath: string | undefined | null): boolean
function lookupBinaryInPath(binaryName: string, platform: NodeJS.Platform): string | null { function lookupBinaryInPath(binaryName: string, platform: NodeJS.Platform): string | null {
const command = platform === 'win32' ? `where ${binaryName}` : `which ${binaryName}`; const command = platform === 'win32' ? `where ${binaryName}` : `which ${binaryName}`;
let output: string;
try { try {
const output = execSync(command, { output = execSync(command, {
stdio: ['ignore', 'pipe', 'ignore'], stdio: ['ignore', 'pipe', 'ignore'],
encoding: 'utf-8', encoding: 'utf-8',
windowsHide: true windowsHide: true
}); });
} catch (error: unknown) {
if (error instanceof Error) {
logger.debug('SYSTEM', `Binary lookup failed for ${binaryName}`, { command }, error);
} else {
logger.debug('SYSTEM', `Binary lookup failed for ${binaryName}`, { command }, new Error(String(error)));
}
return null;
}
const firstMatch = output const firstMatch = output
.split(/\r?\n/) .split(/\r?\n/)
@@ -66,9 +75,6 @@ function lookupBinaryInPath(binaryName: string, platform: NodeJS.Platform): stri
.find(line => line.length > 0); .find(line => line.length > 0);
return firstMatch || null; return firstMatch || null;
} catch {
return null;
}
} }
// Memoize the resolved runtime path for the no-options call site (which is // Memoize the resolved runtime path for the no-options call site (which is
@@ -202,8 +208,12 @@ export function readPidFile(): PidInfo | null {
try { try {
return JSON.parse(readFileSync(PID_FILE, 'utf-8')); return JSON.parse(readFileSync(PID_FILE, 'utf-8'));
} catch (error) { } catch (error: unknown) {
logger.warn('SYSTEM', 'Failed to parse PID file', { path: PID_FILE }, error as Error); if (error instanceof Error) {
logger.warn('SYSTEM', 'Failed to parse PID file', { path: PID_FILE }, error);
} else {
logger.warn('SYSTEM', 'Failed to parse PID file', { path: PID_FILE }, new Error(String(error)));
}
return null; return null;
} }
} }
@@ -216,9 +226,13 @@ export function removePidFile(): void {
try { try {
unlinkSync(PID_FILE); unlinkSync(PID_FILE);
} catch (error) { } catch (error: unknown) {
// [ANTI-PATTERN IGNORED]: Cleanup function - PID file removal failure is non-critical // [ANTI-PATTERN IGNORED]: Cleanup function - PID file removal failure is non-critical
logger.warn('SYSTEM', 'Failed to remove PID file', { path: PID_FILE }, error as Error); if (error instanceof Error) {
logger.warn('SYSTEM', 'Failed to remove PID file', { path: PID_FILE }, error);
} else {
logger.warn('SYSTEM', 'Failed to remove PID file', { path: PID_FILE }, new Error(String(error)));
}
} }
} }
@@ -260,9 +274,13 @@ export async function getChildProcesses(parentPid: number): Promise<number[]> {
.filter(line => line.length > 0 && /^\d+$/.test(line)) .filter(line => line.length > 0 && /^\d+$/.test(line))
.map(line => parseInt(line, 10)) .map(line => parseInt(line, 10))
.filter(pid => pid > 0); .filter(pid => pid > 0);
} catch (error) { } catch (error: unknown) {
// Shutdown cleanup - failure is non-critical, continue without child process cleanup // Shutdown cleanup - failure is non-critical, continue without child process cleanup
logger.error('SYSTEM', 'Failed to enumerate child processes', { parentPid }, error as Error); if (error instanceof Error) {
logger.error('SYSTEM', 'Failed to enumerate child processes', { parentPid }, error);
} else {
logger.error('SYSTEM', 'Failed to enumerate child processes', { parentPid }, new Error(String(error)));
}
return []; return [];
} }
} }
@@ -287,9 +305,13 @@ export async function forceKillProcess(pid: number): Promise<void> {
process.kill(pid, 'SIGKILL'); process.kill(pid, 'SIGKILL');
} }
logger.info('SYSTEM', 'Killed process', { pid }); logger.info('SYSTEM', 'Killed process', { pid });
} catch (error) { } catch (error: unknown) {
// [ANTI-PATTERN IGNORED]: Shutdown cleanup - process already exited, continue // [ANTI-PATTERN IGNORED]: Shutdown cleanup - process already exited, continue
logger.debug('SYSTEM', 'Process already exited during force kill', { pid }, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', 'Process already exited during force kill', { pid }, error);
} else {
logger.debug('SYSTEM', 'Process already exited during force kill', { pid }, new Error(String(error)));
}
} }
} }
@@ -304,7 +326,8 @@ export async function waitForProcessesExit(pids: number[], timeoutMs: number): P
try { try {
process.kill(pid, 0); process.kill(pid, 0);
return true; return true;
} catch (error) { } catch {
// process.kill(pid, 0) throws when PID doesn't exist — expected during cleanup
// [ANTI-PATTERN IGNORED]: Tight loop checking 100s of PIDs every 100ms during cleanup // [ANTI-PATTERN IGNORED]: Tight loop checking 100s of PIDs every 100ms during cleanup
return false; return false;
} }
@@ -358,21 +381,12 @@ export function parseElapsedTime(etime: string): number {
} }
/** /**
* Clean up orphaned claude-mem processes from previous worker sessions * Enumerate orphaned claude-mem processes matching ORPHAN_PROCESS_PATTERNS.
* * Returns PIDs of processes older than ORPHAN_MAX_AGE_MINUTES.
* Targets mcp-server.cjs, worker-service.cjs, and chroma-mcp processes
* that survived a previous daemon crash. Only kills processes older than
* ORPHAN_MAX_AGE_MINUTES to avoid killing the current session.
*
* The periodic ProcessRegistry reaper handles in-session orphans;
* this function handles cross-session orphans at startup.
*/ */
export async function cleanupOrphanedProcesses(): Promise<void> { async function enumerateOrphanedProcesses(isWindows: boolean, currentPid: number): Promise<number[]> {
const isWindows = process.platform === 'win32';
const currentPid = process.pid;
const pidsToKill: number[] = []; const pidsToKill: number[] = [];
try {
if (isWindows) { if (isWindows) {
// Windows: Use WQL -Filter for server-side filtering (no $_ pipeline syntax). // Windows: Use WQL -Filter for server-side filtering (no $_ pipeline syntax).
// Avoids Git Bash $_ interpretation (#1062) and PowerShell syntax errors (#1024). // Avoids Git Bash $_ interpretation (#1062) and PowerShell syntax errors (#1024).
@@ -385,7 +399,7 @@ export async function cleanupOrphanedProcesses(): Promise<void> {
if (!stdout.trim() || stdout.trim() === 'null') { if (!stdout.trim() || stdout.trim() === 'null') {
logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Windows)'); logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Windows)');
return; return [];
} }
const processes = JSON.parse(stdout); const processes = JSON.parse(stdout);
@@ -418,7 +432,7 @@ export async function cleanupOrphanedProcesses(): Promise<void> {
if (!stdout.trim()) { if (!stdout.trim()) {
logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Unix)'); logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Unix)');
return; return [];
} }
const lines = stdout.trim().split('\n'); const lines = stdout.trim().split('\n');
@@ -440,9 +454,34 @@ export async function cleanupOrphanedProcesses(): Promise<void> {
} }
} }
} }
} catch (error) {
return pidsToKill;
}
/**
* Clean up orphaned claude-mem processes from previous worker sessions
*
* Targets mcp-server.cjs, worker-service.cjs, and chroma-mcp processes
* that survived a previous daemon crash. Only kills processes older than
* ORPHAN_MAX_AGE_MINUTES to avoid killing the current session.
*
* The periodic ProcessRegistry reaper handles in-session orphans;
* this function handles cross-session orphans at startup.
*/
export async function cleanupOrphanedProcesses(): Promise<void> {
const isWindows = process.platform === 'win32';
const currentPid = process.pid;
let pidsToKill: number[];
try {
pidsToKill = await enumerateOrphanedProcesses(isWindows, currentPid);
} catch (error: unknown) {
// Orphan cleanup is non-critical - log and continue // Orphan cleanup is non-critical - log and continue
logger.error('SYSTEM', 'Failed to enumerate orphaned processes', {}, error as Error); if (error instanceof Error) {
logger.error('SYSTEM', 'Failed to enumerate orphaned processes', {}, error);
} else {
logger.error('SYSTEM', 'Failed to enumerate orphaned processes', {}, new Error(String(error)));
}
return; return;
} }
@@ -467,18 +506,26 @@ export async function cleanupOrphanedProcesses(): Promise<void> {
} }
try { try {
execSync(`taskkill /PID ${pid} /T /F`, { timeout: HOOK_TIMEOUTS.POWERSHELL_COMMAND, stdio: 'ignore', windowsHide: true }); execSync(`taskkill /PID ${pid} /T /F`, { timeout: HOOK_TIMEOUTS.POWERSHELL_COMMAND, stdio: 'ignore', windowsHide: true });
} catch (error) { } catch (error: unknown) {
// [ANTI-PATTERN IGNORED]: Cleanup loop - process may have exited, continue to next PID // [ANTI-PATTERN IGNORED]: Cleanup loop - process may have exited, continue to next PID
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, error);
} else {
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, new Error(String(error)));
}
} }
} }
} else { } else {
for (const pid of pidsToKill) { for (const pid of pidsToKill) {
try { try {
process.kill(pid, 'SIGKILL'); process.kill(pid, 'SIGKILL');
} catch (error) { } catch (error: unknown) {
// [ANTI-PATTERN IGNORED]: Cleanup loop - process may have exited, continue to next PID // [ANTI-PATTERN IGNORED]: Cleanup loop - process may have exited, continue to next PID
logger.debug('SYSTEM', 'Process already exited', { pid }, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', 'Process already exited', { pid }, error);
} else {
logger.debug('SYSTEM', 'Process already exited', { pid }, new Error(String(error)));
}
} }
} }
} }
@@ -494,35 +541,17 @@ const AGGRESSIVE_CLEANUP_PATTERNS = ['worker-service.cjs', 'chroma-mcp'];
const AGE_GATED_CLEANUP_PATTERNS = ['mcp-server.cjs']; const AGE_GATED_CLEANUP_PATTERNS = ['mcp-server.cjs'];
/** /**
* Aggressive startup cleanup for orphaned claude-mem processes. * Enumerate processes for aggressive startup cleanup. Aggressive patterns are
* * killed immediately; age-gated patterns only if older than ORPHAN_MAX_AGE_MINUTES.
* Unlike cleanupOrphanedProcesses() which age-gates everything at 30 minutes,
* this function kills worker-service.cjs and chroma-mcp processes immediately
* (they should not outlive their parent worker). Only mcp-server.cjs keeps
* the age threshold since it may be legitimately running.
*
* Called once at daemon startup.
*/ */
export async function aggressiveStartupCleanup(): Promise<void> { async function enumerateAggressiveCleanupProcesses(
const isWindows = process.platform === 'win32'; isWindows: boolean,
const currentPid = process.pid; currentPid: number,
protectedPids: Set<number>,
allPatterns: string[]
): Promise<number[]> {
const pidsToKill: number[] = []; const pidsToKill: number[] = [];
const allPatterns = [...AGGRESSIVE_CLEANUP_PATTERNS, ...AGE_GATED_CLEANUP_PATTERNS];
// Protect parent process (the hook that spawned us) from being killed.
// Without this, a new daemon kills its own parent hook process (#1426).
//
// Note: readPidFile() is not used here because start() writes the new PID
// before initializeBackground() calls this function, so readPidFile() would
// just return process.pid (already protected). If a pre-existing worker needs
// protection, ensureWorkerStarted() handles that by returning early when a
// healthy worker is detected — we never reach this code in that case.
const protectedPids = new Set<number>([currentPid]);
if (process.ppid && process.ppid > 0) {
protectedPids.add(process.ppid);
}
try {
if (isWindows) { if (isWindows) {
// Use WQL -Filter for server-side filtering (no $_ pipeline syntax). // Use WQL -Filter for server-side filtering (no $_ pipeline syntax).
// Avoids Git Bash $_ interpretation (#1062) and PowerShell syntax errors (#1024). // Avoids Git Bash $_ interpretation (#1062) and PowerShell syntax errors (#1024).
@@ -535,7 +564,7 @@ export async function aggressiveStartupCleanup(): Promise<void> {
if (!stdout.trim() || stdout.trim() === 'null') { if (!stdout.trim() || stdout.trim() === 'null') {
logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Windows)'); logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Windows)');
return; return [];
} }
const processes = JSON.parse(stdout); const processes = JSON.parse(stdout);
@@ -575,7 +604,7 @@ export async function aggressiveStartupCleanup(): Promise<void> {
if (!stdout.trim()) { if (!stdout.trim()) {
logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Unix)'); logger.debug('SYSTEM', 'No orphaned claude-mem processes found (Unix)');
return; return [];
} }
const lines = stdout.trim().split('\n'); const lines = stdout.trim().split('\n');
@@ -605,8 +634,47 @@ export async function aggressiveStartupCleanup(): Promise<void> {
} }
} }
} }
} catch (error) {
logger.error('SYSTEM', 'Failed to enumerate orphaned processes during aggressive cleanup', {}, error as Error); return pidsToKill;
}
/**
* Aggressive startup cleanup for orphaned claude-mem processes.
*
* Unlike cleanupOrphanedProcesses() which age-gates everything at 30 minutes,
* this function kills worker-service.cjs and chroma-mcp processes immediately
* (they should not outlive their parent worker). Only mcp-server.cjs keeps
* the age threshold since it may be legitimately running.
*
* Called once at daemon startup.
*/
export async function aggressiveStartupCleanup(): Promise<void> {
const isWindows = process.platform === 'win32';
const currentPid = process.pid;
const allPatterns = [...AGGRESSIVE_CLEANUP_PATTERNS, ...AGE_GATED_CLEANUP_PATTERNS];
// Protect parent process (the hook that spawned us) from being killed.
// Without this, a new daemon kills its own parent hook process (#1426).
//
// Note: readPidFile() is not used here because start() writes the new PID
// before initializeBackground() calls this function, so readPidFile() would
// just return process.pid (already protected). If a pre-existing worker needs
// protection, ensureWorkerStarted() handles that by returning early when a
// healthy worker is detected — we never reach this code in that case.
const protectedPids = new Set<number>([currentPid]);
if (process.ppid && process.ppid > 0) {
protectedPids.add(process.ppid);
}
let pidsToKill: number[];
try {
pidsToKill = await enumerateAggressiveCleanupProcesses(isWindows, currentPid, protectedPids, allPatterns);
} catch (error: unknown) {
if (error instanceof Error) {
logger.error('SYSTEM', 'Failed to enumerate orphaned processes during aggressive cleanup', {}, error);
} else {
logger.error('SYSTEM', 'Failed to enumerate orphaned processes during aggressive cleanup', {}, new Error(String(error)));
}
return; return;
} }
@@ -625,16 +693,24 @@ export async function aggressiveStartupCleanup(): Promise<void> {
if (!Number.isInteger(pid) || pid <= 0) continue; if (!Number.isInteger(pid) || pid <= 0) continue;
try { try {
execSync(`taskkill /PID ${pid} /T /F`, { timeout: HOOK_TIMEOUTS.POWERSHELL_COMMAND, stdio: 'ignore', windowsHide: true }); execSync(`taskkill /PID ${pid} /T /F`, { timeout: HOOK_TIMEOUTS.POWERSHELL_COMMAND, stdio: 'ignore', windowsHide: true });
} catch (error) { } catch (error: unknown) {
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, error);
} else {
logger.debug('SYSTEM', 'Failed to kill process, may have already exited', { pid }, new Error(String(error)));
}
} }
} }
} else { } else {
for (const pid of pidsToKill) { for (const pid of pidsToKill) {
try { try {
process.kill(pid, 'SIGKILL'); process.kill(pid, 'SIGKILL');
} catch (error) { } catch (error: unknown) {
logger.debug('SYSTEM', 'Process already exited', { pid }, error as Error); if (error instanceof Error) {
logger.debug('SYSTEM', 'Process already exited', { pid }, error);
} else {
logger.debug('SYSTEM', 'Process already exited', { pid }, new Error(String(error)));
}
} }
} }
} }
@@ -747,8 +823,22 @@ export function runOneTimeCwdRemap(dataDirectory?: string): void {
logger.warn('SYSTEM', 'Running one-time cwd-based project remap', { dbPath }); logger.warn('SYSTEM', 'Running one-time cwd-based project remap', { dbPath });
let db: import('bun:sqlite').Database | null = null;
try { try {
executeCwdRemap(dbPath, effectiveDataDir, markerPath);
} catch (err: unknown) {
if (err instanceof Error) {
logger.error('SYSTEM', 'cwd-remap failed, marker not written (will retry on next startup)', {}, err);
} else {
logger.error('SYSTEM', 'cwd-remap failed, marker not written (will retry on next startup)', {}, new Error(String(err)));
}
}
}
/**
* Execute the cwd-remap DB migration. Extracted to keep the try block small.
* Opens, queries, and updates the DB, then writes the marker file on success.
*/
function executeCwdRemap(dbPath: string, effectiveDataDir: string, markerPath: string): void {
const { Database } = require('bun:sqlite') as typeof import('bun:sqlite'); const { Database } = require('bun:sqlite') as typeof import('bun:sqlite');
const probe = new Database(dbPath, { readonly: true }); const probe = new Database(dbPath, { readonly: true });
@@ -768,8 +858,8 @@ export function runOneTimeCwdRemap(dataDirectory?: string): void {
copyFileSync(dbPath, backup); copyFileSync(dbPath, backup);
logger.info('SYSTEM', 'DB backed up before cwd-remap', { backup }); logger.info('SYSTEM', 'DB backed up before cwd-remap', { backup });
db = new Database(dbPath); const db = new Database(dbPath);
try {
const cwdRows = db.prepare(` const cwdRows = db.prepare(`
SELECT cwd FROM pending_messages SELECT cwd FROM pending_messages
WHERE cwd IS NOT NULL AND cwd != '' WHERE cwd IS NOT NULL AND cwd != ''
@@ -825,10 +915,8 @@ export function runOneTimeCwdRemap(dataDirectory?: string): void {
mkdirSync(effectiveDataDir, { recursive: true }); mkdirSync(effectiveDataDir, { recursive: true });
writeFileSync(markerPath, new Date().toISOString()); writeFileSync(markerPath, new Date().toISOString());
logger.info('SYSTEM', 'cwd-remap marker written', { markerPath }); logger.info('SYSTEM', 'cwd-remap marker written', { markerPath });
} catch (err) {
logger.error('SYSTEM', 'cwd-remap failed, marker not written (will retry on next startup)', {}, err as Error);
} finally { } finally {
db?.close(); db.close();
} }
} }
@@ -896,9 +984,13 @@ export function spawnDaemon(
// never falsy checks like `if (!pid)`, which would silently treat // never falsy checks like `if (!pid)`, which would silently treat
// success as failure here. // success as failure here.
return 0; return 0;
} catch (error) { } catch (error: unknown) {
// APPROVED OVERRIDE: Windows daemon spawn is best-effort; log and let callers fall back to health checks/retry flow. // APPROVED OVERRIDE: Windows daemon spawn is best-effort; log and let callers fall back to health checks/retry flow.
logger.error('SYSTEM', 'Failed to spawn worker daemon on Windows', { runtimePath }, error as Error); if (error instanceof Error) {
logger.error('SYSTEM', 'Failed to spawn worker daemon on Windows', { runtimePath }, error);
} else {
logger.error('SYSTEM', 'Failed to spawn worker daemon on Windows', { runtimePath }, new Error(String(error)));
}
return undefined; return undefined;
} }
} }
@@ -961,9 +1053,14 @@ export function isProcessAlive(pid: number): boolean {
process.kill(pid, 0); process.kill(pid, 0);
return true; return true;
} catch (error: unknown) { } catch (error: unknown) {
if (error instanceof Error) {
const code = (error as NodeJS.ErrnoException).code; const code = (error as NodeJS.ErrnoException).code;
// EPERM = process exists but different user/session — treat as alive // EPERM = process exists but different user/session — treat as alive
if (code === 'EPERM') return true; if (code === 'EPERM') return true;
logger.debug('SYSTEM', 'Process not alive', { pid, code });
} else {
logger.debug('SYSTEM', 'Process not alive (non-Error thrown)', { pid }, new Error(String(error)));
}
// ESRCH = no such process — it's dead // ESRCH = no such process — it's dead
return false; return false;
} }
@@ -983,7 +1080,12 @@ export function isPidFileRecent(thresholdMs: number = 15000): boolean {
try { try {
const stats = statSync(PID_FILE); const stats = statSync(PID_FILE);
return (Date.now() - stats.mtimeMs) < thresholdMs; return (Date.now() - stats.mtimeMs) < thresholdMs;
} catch { } catch (error: unknown) {
if (error instanceof Error) {
logger.debug('SYSTEM', 'PID file not accessible for recency check', { path: PID_FILE }, error);
} else {
logger.debug('SYSTEM', 'PID file not accessible for recency check', { path: PID_FILE }, new Error(String(error)));
}
return false; return false;
} }
} }
@@ -1032,9 +1134,13 @@ export function createSignalHandler(
try { try {
await shutdownFn(); await shutdownFn();
process.exit(0); process.exit(0);
} catch (error) { } catch (error: unknown) {
// Top-level signal handler - log any shutdown error and exit // Top-level signal handler - log any shutdown error and exit
logger.error('SYSTEM', 'Error during shutdown', {}, error as Error); if (error instanceof Error) {
logger.error('SYSTEM', 'Error during shutdown', {}, error);
} else {
logger.error('SYSTEM', 'Error during shutdown', {}, new Error(String(error)));
}
// Exit gracefully: Windows Terminal won't keep tab open on exit 0 // Exit gracefully: Windows Terminal won't keep tab open on exit 0
// Even on shutdown errors, exit cleanly to prevent tab accumulation // Even on shutdown errors, exit cleanly to prevent tab accumulation
process.exit(0); process.exit(0);
src/services/infrastructure/WorktreeAdoption.ts
+22 -8
View File
@@ -248,22 +248,24 @@ export async function adoptMergedWorktrees(opts: {
'UPDATE session_summaries SET merged_into_project = ? WHERE project = ? AND merged_into_project IS NULL' 'UPDATE session_summaries SET merged_into_project = ? WHERE project = ? AND merged_into_project IS NULL'
); );
const tx = db.transaction(() => { const adoptWorktreeInTransaction = (wt: WorktreeEntry) => {
for (const wt of targets) {
try {
const worktreeProject = getProjectContext(wt.path).primary; const worktreeProject = getProjectContext(wt.path).primary;
const rows = selectObsForPatch.all( const rows = selectObsForPatch.all(
worktreeProject, worktreeProject,
parentProject parentProject
) as Array<{ id: number }>; ) as Array<{ id: number }>;
for (const r of rows) adoptedSqliteIds.push(r.id);
// updateObs/updateSum only touch WHERE merged_into_project IS NULL,
// so .changes reflects only newly-adopted rows (not the re-patched ones).
const obsChanges = updateObs.run(parentProject, worktreeProject).changes; const obsChanges = updateObs.run(parentProject, worktreeProject).changes;
const sumChanges = updateSum.run(parentProject, worktreeProject).changes; const sumChanges = updateSum.run(parentProject, worktreeProject).changes;
for (const r of rows) adoptedSqliteIds.push(r.id);
result.adoptedObservations += obsChanges; result.adoptedObservations += obsChanges;
result.adoptedSummaries += sumChanges; result.adoptedSummaries += sumChanges;
};
const tx = db.transaction(() => {
for (const wt of targets) {
try {
adoptWorktreeInTransaction(wt);
} catch (err) { } catch (err) {
const message = err instanceof Error ? err.message : String(err); const message = err instanceof Error ? err.message : String(err);
logger.warn('SYSTEM', 'Worktree adoption skipped branch', { logger.warn('SYSTEM', 'Worktree adoption skipped branch', {
@@ -285,7 +287,11 @@ export async function adoptMergedWorktrees(opts: {
} catch (err) { } catch (err) {
if (err instanceof DryRunRollback) { if (err instanceof DryRunRollback) {
// Rolled back as intended for dry-run — counts are still useful. // Rolled back as intended for dry-run — counts are still useful.
} else if (err instanceof Error) {
logger.error('SYSTEM', 'Worktree adoption transaction failed', {}, err);
throw err;
} else { } else {
logger.error('SYSTEM', 'Worktree adoption transaction failed with non-Error', { error: String(err) });
throw err; throw err;
} }
} }
@@ -299,12 +305,20 @@ export async function adoptMergedWorktrees(opts: {
await chromaSync.updateMergedIntoProject(adoptedSqliteIds, parentProject); await chromaSync.updateMergedIntoProject(adoptedSqliteIds, parentProject);
result.chromaUpdates = adoptedSqliteIds.length; result.chromaUpdates = adoptedSqliteIds.length;
} catch (err) { } catch (err) {
if (err instanceof Error) {
logger.error( logger.error(
'CHROMA_SYNC', 'SYSTEM',
'Worktree adoption Chroma patch failed (SQL already committed)', 'Worktree adoption Chroma patch failed (SQL already committed)',
{ parentProject, sqliteIdCount: adoptedSqliteIds.length }, { parentProject, sqliteIdCount: adoptedSqliteIds.length },
err as Error err
); );
} else {
logger.error(
'SYSTEM',
'Worktree adoption Chroma patch failed (SQL already committed)',
{ parentProject, sqliteIdCount: adoptedSqliteIds.length, error: String(err) }
);
}
result.chromaFailed = adoptedSqliteIds.length; result.chromaFailed = adoptedSqliteIds.length;
} finally { } finally {
await chromaSync.close(); await chromaSync.close();
src/services/integrations/CodexCliInstaller.ts
+48 -29
View File
@@ -67,7 +67,11 @@ function loadExistingTranscriptWatchConfig(): TranscriptWatchConfig {
return parsed; return parsed;
} catch (parseError) { } catch (parseError) {
logger.error('SYSTEM', 'Corrupt transcript-watch.json, creating backup', { path: configPath }, parseError as Error); if (parseError instanceof Error) {
logger.error('WORKER', 'Corrupt transcript-watch.json, creating backup', { path: configPath }, parseError);
} else {
logger.error('WORKER', 'Corrupt transcript-watch.json, creating backup', { path: configPath }, new Error(String(parseError)));
}
// Back up corrupt file // Back up corrupt file
const backupPath = `${configPath}.backup.${Date.now()}`; const backupPath = `${configPath}.backup.${Date.now()}`;
@@ -135,13 +139,22 @@ function writeTranscriptWatchConfig(config: TranscriptWatchConfig): void {
* Preserves any existing user content outside the tags. * Preserves any existing user content outside the tags.
*/ */
function removeCodexAgentsMdContext(): void { function removeCodexAgentsMdContext(): void {
try {
if (!existsSync(CODEX_AGENTS_MD_PATH)) return; if (!existsSync(CODEX_AGENTS_MD_PATH)) return;
const content = readFileSync(CODEX_AGENTS_MD_PATH, 'utf-8');
const startTag = '<claude-mem-context>'; const startTag = '<claude-mem-context>';
const endTag = '</claude-mem-context>'; const endTag = '</claude-mem-context>';
try {
readAndStripContextTags(startTag, endTag);
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
logger.warn('WORKER', 'Failed to clean AGENTS.md context', { error: message });
}
}
function readAndStripContextTags(startTag: string, endTag: string): void {
const content = readFileSync(CODEX_AGENTS_MD_PATH, 'utf-8');
const startIdx = content.indexOf(startTag); const startIdx = content.indexOf(startTag);
const endIdx = content.indexOf(endTag); const endIdx = content.indexOf(endTag);
@@ -158,9 +171,6 @@ function removeCodexAgentsMdContext(): void {
} }
console.log(` Removed legacy global context from ${CODEX_AGENTS_MD_PATH}`); console.log(` Removed legacy global context from ${CODEX_AGENTS_MD_PATH}`);
} catch (error) {
logger.warn('SYSTEM', 'Failed to clean AGENTS.md context', { error: (error as Error).message });
}
} }
/** /**
@@ -184,16 +194,26 @@ const cleanupLegacyCodexAgentsMdContext = removeCodexAgentsMdContext;
export async function installCodexCli(): Promise<number> { export async function installCodexCli(): Promise<number> {
console.log('\nInstalling Claude-Mem for Codex CLI (transcript watching)...\n'); console.log('\nInstalling Claude-Mem for Codex CLI (transcript watching)...\n');
try {
// Step 1: Merge transcript-watch config // Step 1: Merge transcript-watch config
const existingConfig = loadExistingTranscriptWatchConfig(); const existingConfig = loadExistingTranscriptWatchConfig();
const mergedConfig = mergeCodexWatchConfig(existingConfig); const mergedConfig = mergeCodexWatchConfig(existingConfig);
try {
writeConfigAndShowCodexInstructions(mergedConfig);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
return 1;
}
}
function writeConfigAndShowCodexInstructions(mergedConfig: TranscriptWatchConfig): void {
writeTranscriptWatchConfig(mergedConfig); writeTranscriptWatchConfig(mergedConfig);
console.log(` Updated ${DEFAULT_CONFIG_PATH}`); console.log(` Updated ${DEFAULT_CONFIG_PATH}`);
console.log(` Watch path: ~/.codex/sessions/**/*.jsonl`); console.log(` Watch path: ~/.codex/sessions/**/*.jsonl`);
console.log(` Schema: codex (v${SAMPLE_CONFIG.schemas?.codex?.version ?? '?'})`); console.log(` Schema: codex (v${SAMPLE_CONFIG.schemas?.codex?.version ?? '?'})`);
// Step 2: Clean up legacy global AGENTS.md context
cleanupLegacyCodexAgentsMdContext(); cleanupLegacyCodexAgentsMdContext();
console.log(` console.log(`
@@ -211,12 +231,6 @@ Next steps:
1. Start claude-mem worker: npx claude-mem start 1. Start claude-mem worker: npx claude-mem start
2. Use Codex CLI as usual -- memory capture is automatic! 2. Use Codex CLI as usual -- memory capture is automatic!
`); `);
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
return 1;
}
} }
// --------------------------------------------------------------------------- // ---------------------------------------------------------------------------
@@ -234,23 +248,26 @@ Next steps:
export function uninstallCodexCli(): number { export function uninstallCodexCli(): number {
console.log('\nUninstalling Claude-Mem Codex CLI integration...\n'); console.log('\nUninstalling Claude-Mem Codex CLI integration...\n');
try {
// Step 1: Remove codex watch from transcript-watch.json // Step 1: Remove codex watch from transcript-watch.json
if (existsSync(DEFAULT_CONFIG_PATH)) { if (existsSync(DEFAULT_CONFIG_PATH)) {
const config = loadExistingTranscriptWatchConfig(); const config = loadExistingTranscriptWatchConfig();
// Remove codex watch
config.watches = config.watches.filter( config.watches = config.watches.filter(
(w: WatchTarget) => w.name !== CODEX_WATCH_NAME, (w: WatchTarget) => w.name !== CODEX_WATCH_NAME,
); );
// Remove codex schema
if (config.schemas) { if (config.schemas) {
delete config.schemas[CODEX_WATCH_NAME]; delete config.schemas[CODEX_WATCH_NAME];
} }
try {
writeTranscriptWatchConfig(config); writeTranscriptWatchConfig(config);
console.log(` Removed codex watch from ${DEFAULT_CONFIG_PATH}`); console.log(` Removed codex watch from ${DEFAULT_CONFIG_PATH}`);
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nUninstallation failed: ${message}`);
return 1;
}
} else { } else {
console.log(' No transcript-watch.json found -- nothing to remove.'); console.log(' No transcript-watch.json found -- nothing to remove.');
} }
@@ -262,10 +279,6 @@ export function uninstallCodexCli(): number {
console.log('Restart claude-mem worker to apply changes.\n'); console.log('Restart claude-mem worker to apply changes.\n');
return 0; return 0;
} catch (error) {
console.error(`\nUninstallation failed: ${(error as Error).message}`);
return 1;
}
} }
// --------------------------------------------------------------------------- // ---------------------------------------------------------------------------
@@ -288,8 +301,21 @@ export function checkCodexCliStatus(): number {
return 0; return 0;
} }
let config: TranscriptWatchConfig;
try { try {
const config = loadExistingTranscriptWatchConfig(); config = loadExistingTranscriptWatchConfig();
} catch (error) {
if (error instanceof Error) {
logger.error('WORKER', 'Could not parse transcript-watch.json', { path: DEFAULT_CONFIG_PATH }, error);
} else {
logger.error('WORKER', 'Could not parse transcript-watch.json', { path: DEFAULT_CONFIG_PATH }, new Error(String(error)));
}
console.log('Status: Unknown');
console.log(' Could not parse transcript-watch.json.');
console.log('');
return 0;
}
const codexWatch = config.watches.find( const codexWatch = config.watches.find(
(w: WatchTarget) => w.name === CODEX_WATCH_NAME, (w: WatchTarget) => w.name === CODEX_WATCH_NAME,
); );
@@ -308,14 +334,12 @@ export function checkCodexCliStatus(): number {
console.log(` Schema: ${codexSchema ? `codex (v${codexSchema.version ?? '?'})` : 'missing'}`); console.log(` Schema: ${codexSchema ? `codex (v${codexSchema.version ?? '?'})` : 'missing'}`);
console.log(` Start at end: ${codexWatch.startAtEnd ?? false}`); console.log(` Start at end: ${codexWatch.startAtEnd ?? false}`);
// Check context config
if (codexWatch.context) { if (codexWatch.context) {
console.log(` Context mode: ${codexWatch.context.mode}`); console.log(` Context mode: ${codexWatch.context.mode}`);
console.log(` Context path: ${codexWatch.context.path ?? '<workspace>/AGENTS.md (default)'}`); console.log(` Context path: ${codexWatch.context.path ?? '<workspace>/AGENTS.md (default)'}`);
console.log(` Context updates on: ${codexWatch.context.updateOn?.join(', ') ?? 'none'}`); console.log(` Context updates on: ${codexWatch.context.updateOn?.join(', ') ?? 'none'}`);
} }
// Check legacy global AGENTS.md usage
if (existsSync(CODEX_AGENTS_MD_PATH)) { if (existsSync(CODEX_AGENTS_MD_PATH)) {
const mdContent = readFileSync(CODEX_AGENTS_MD_PATH, 'utf-8'); const mdContent = readFileSync(CODEX_AGENTS_MD_PATH, 'utf-8');
if (mdContent.includes('<claude-mem-context>')) { if (mdContent.includes('<claude-mem-context>')) {
@@ -327,17 +351,12 @@ export function checkCodexCliStatus(): number {
console.log(` Legacy global context: None`); console.log(` Legacy global context: None`);
} }
// Check if ~/.codex/sessions exists (indicates Codex has been used)
const sessionsDir = path.join(CODEX_DIR, 'sessions'); const sessionsDir = path.join(CODEX_DIR, 'sessions');
if (existsSync(sessionsDir)) { if (existsSync(sessionsDir)) {
console.log(` Sessions directory: exists`); console.log(` Sessions directory: exists`);
} else { } else {
console.log(` Sessions directory: not yet created (use Codex CLI to generate sessions)`); console.log(` Sessions directory: not yet created (use Codex CLI to generate sessions)`);
} }
} catch {
console.log('Status: Unknown');
console.log(' Could not parse transcript-watch.json.');
}
console.log(''); console.log('');
return 0; return 0;
src/services/integrations/CursorHooksInstaller.ts
+94 -46
View File
@@ -117,7 +117,11 @@ export async function updateCursorContextForProject(projectName: string, _port:
logger.debug('CURSOR', 'Updated context file', { projectName, workspacePath: entry.workspacePath }); logger.debug('CURSOR', 'Updated context file', { projectName, workspacePath: entry.workspacePath });
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Background context update - failure is non-critical, user workflow continues // [ANTI-PATTERN IGNORED]: Background context update - failure is non-critical, user workflow continues
logger.error('CURSOR', 'Failed to update context file', { projectName }, error as Error); if (error instanceof Error) {
logger.error('WORKER', 'Failed to update context file', { projectName }, error);
} else {
logger.error('WORKER', 'Failed to update context file', { projectName }, new Error(String(error)));
}
} }
} }
@@ -259,7 +263,11 @@ export function configureCursorMcp(target: CursorInstallTarget): number {
} }
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Fallback behavior - corrupt config, continue with empty // [ANTI-PATTERN IGNORED]: Fallback behavior - corrupt config, continue with empty
logger.error('SYSTEM', 'Corrupt mcp.json, creating new config', { path: mcpJsonPath }, error as Error); if (error instanceof Error) {
logger.error('WORKER', 'Corrupt mcp.json, creating new config', { path: mcpJsonPath }, error);
} else {
logger.error('WORKER', 'Corrupt mcp.json, creating new config', { path: mcpJsonPath }, new Error(String(error)));
}
config = { mcpServers: {} }; config = { mcpServers: {} };
} }
} }
@@ -308,10 +316,6 @@ export async function installCursorHooks(target: CursorInstallTarget): Promise<n
const workspaceRoot = process.cwd(); const workspaceRoot = process.cwd();
try {
// Create target directory
mkdirSync(targetDir, { recursive: true });
// Generate hooks.json with unified CLI commands // Generate hooks.json with unified CLI commands
const hooksJsonPath = path.join(targetDir, 'hooks.json'); const hooksJsonPath = path.join(targetDir, 'hooks.json');
@@ -352,6 +356,29 @@ export async function installCursorHooks(target: CursorInstallTarget): Promise<n
} }
}; };
try {
// Create target directory inside try to catch EACCES/EPERM
mkdirSync(targetDir, { recursive: true });
await writeHooksJsonAndSetupProject(hooksJsonPath, hooksJson, workerServicePath, target, targetDir, workspaceRoot);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
if (target === 'enterprise') {
console.error(' Tip: Enterprise installation may require sudo/admin privileges');
}
return 1;
}
}
async function writeHooksJsonAndSetupProject(
hooksJsonPath: string,
hooksJson: CursorHooksJson,
workerServicePath: string,
target: CursorInstallTarget,
targetDir: string,
workspaceRoot: string,
): Promise<void> {
writeFileSync(hooksJsonPath, JSON.stringify(hooksJson, null, 2)); writeFileSync(hooksJsonPath, JSON.stringify(hooksJson, null, 2));
console.log(` Created hooks.json (unified CLI mode)`); console.log(` Created hooks.json (unified CLI mode)`);
console.log(` Worker service: ${workerServicePath}`); console.log(` Worker service: ${workerServicePath}`);
@@ -376,15 +403,6 @@ Context Injection:
Context from past sessions is stored in .cursor/rules/claude-mem-context.mdc Context from past sessions is stored in .cursor/rules/claude-mem-context.mdc
and automatically included in every chat. It updates after each session ends. and automatically included in every chat. It updates after each session ends.
`); `);
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
if (target === 'enterprise') {
console.error(' Tip: Enterprise installation may require sudo/admin privileges');
}
return 1;
}
} }
/** /**
@@ -400,25 +418,14 @@ async function setupProjectContext(targetDir: string, workspaceRoot: string): Pr
console.log(` Generating initial context...`); console.log(` Generating initial context...`);
try { try {
// Check if worker is running (uses socket or TCP automatically) contextGenerated = await fetchInitialContextFromWorker(projectName, workspaceRoot);
const healthResponse = await workerHttpRequest('/api/readiness');
if (healthResponse.ok) {
// Fetch context
const contextResponse = await workerHttpRequest(
`/api/context/inject?project=${encodeURIComponent(projectName)}`
);
if (contextResponse.ok) {
const context = await contextResponse.text();
if (context && context.trim()) {
writeContextFile(workspaceRoot, context);
contextGenerated = true;
console.log(` Generated initial context from existing memory`);
}
}
}
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Fallback behavior - worker not running, use placeholder // [ANTI-PATTERN IGNORED]: Fallback behavior - worker not running, use placeholder
logger.debug('CURSOR', 'Worker not running during install', {}, error as Error); if (error instanceof Error) {
logger.debug('WORKER', 'Worker not running during install', {}, error);
} else {
logger.debug('WORKER', 'Worker not running during install', {}, new Error(String(error)));
}
} }
if (!contextGenerated) { if (!contextGenerated) {
@@ -444,6 +451,27 @@ Use claude-mem's MCP search tools for manual memory queries.
console.log(` Registered for auto-context updates`); console.log(` Registered for auto-context updates`);
} }
async function fetchInitialContextFromWorker(
projectName: string,
workspaceRoot: string,
): Promise<boolean> {
const healthResponse = await workerHttpRequest('/api/readiness');
if (!healthResponse.ok) return false;
const contextResponse = await workerHttpRequest(
`/api/context/inject?project=${encodeURIComponent(projectName)}`,
);
if (!contextResponse.ok) return false;
const context = await contextResponse.text();
if (context && context.trim()) {
writeContextFile(workspaceRoot, context);
console.log(` Generated initial context from existing memory`);
return true;
}
return false;
}
/** /**
* Uninstall Cursor hooks * Uninstall Cursor hooks
*/ */
@@ -456,7 +484,6 @@ export function uninstallCursorHooks(target: CursorInstallTarget): number {
return 1; return 1;
} }
try {
const hooksDir = path.join(targetDir, 'hooks'); const hooksDir = path.join(targetDir, 'hooks');
const hooksJsonPath = path.join(targetDir, 'hooks.json'); const hooksJsonPath = path.join(targetDir, 'hooks.json');
@@ -468,6 +495,23 @@ export function uninstallCursorHooks(target: CursorInstallTarget): number {
const allScripts = [...bashScripts, ...psScripts]; const allScripts = [...bashScripts, ...psScripts];
try {
removeCursorHooksFiles(hooksDir, allScripts, hooksJsonPath, target, targetDir);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nUninstallation failed: ${message}`);
return 1;
}
}
function removeCursorHooksFiles(
hooksDir: string,
allScripts: string[],
hooksJsonPath: string,
target: CursorInstallTarget,
targetDir: string,
): void {
for (const script of allScripts) { for (const script of allScripts) {
const scriptPath = path.join(hooksDir, script); const scriptPath = path.join(hooksDir, script);
if (existsSync(scriptPath)) { if (existsSync(scriptPath)) {
@@ -476,13 +520,11 @@ export function uninstallCursorHooks(target: CursorInstallTarget): number {
} }
} }
// Remove hooks.json
if (existsSync(hooksJsonPath)) { if (existsSync(hooksJsonPath)) {
unlinkSync(hooksJsonPath); unlinkSync(hooksJsonPath);
console.log(` Removed hooks.json`); console.log(` Removed hooks.json`);
} }
// Remove context file and unregister if project-level
if (target === 'project') { if (target === 'project') {
const contextFile = path.join(targetDir, 'rules', 'claude-mem-context.mdc'); const contextFile = path.join(targetDir, 'rules', 'claude-mem-context.mdc');
if (existsSync(contextFile)) { if (existsSync(contextFile)) {
@@ -490,7 +532,6 @@ export function uninstallCursorHooks(target: CursorInstallTarget): number {
console.log(` Removed context file`); console.log(` Removed context file`);
} }
// Unregister from auto-context updates
const projectName = path.basename(process.cwd()); const projectName = path.basename(process.cwd());
unregisterCursorProject(projectName); unregisterCursorProject(projectName);
console.log(` Unregistered from auto-context updates`); console.log(` Unregistered from auto-context updates`);
@@ -498,12 +539,6 @@ export function uninstallCursorHooks(target: CursorInstallTarget): number {
console.log(`\nUninstallation complete!\n`); console.log(`\nUninstallation complete!\n`);
console.log('Restart Cursor to apply changes.'); console.log('Restart Cursor to apply changes.');
return 0;
} catch (error) {
console.error(`\nUninstallation failed: ${(error as Error).message}`);
return 1;
}
} }
/** /**
@@ -535,8 +570,19 @@ export function checkCursorHooksStatus(): number {
console.log(` Config: ${hooksJson}`); console.log(` Config: ${hooksJson}`);
// Check if using unified CLI mode or legacy shell scripts // Check if using unified CLI mode or legacy shell scripts
let hooksContent: any = null;
try { try {
const hooksContent = JSON.parse(readFileSync(hooksJson, 'utf-8')); hooksContent = JSON.parse(readFileSync(hooksJson, 'utf-8'));
} catch (error) {
if (error instanceof Error) {
logger.error('WORKER', 'Unable to parse hooks.json', { path: hooksJson }, error);
} else {
logger.error('WORKER', 'Unable to parse hooks.json', { path: hooksJson }, new Error(String(error)));
}
console.log(` Mode: Unable to parse hooks.json`);
}
if (hooksContent) {
const firstCommand = hooksContent?.hooks?.beforeSubmitPrompt?.[0]?.command || ''; const firstCommand = hooksContent?.hooks?.beforeSubmitPrompt?.[0]?.command || '';
if (firstCommand.includes('worker-service.cjs') && firstCommand.includes('hook cursor')) { if (firstCommand.includes('worker-service.cjs') && firstCommand.includes('hook cursor')) {
@@ -562,8 +608,6 @@ export function checkCursorHooksStatus(): number {
console.log(` Mode: Unknown configuration`); console.log(` Mode: Unknown configuration`);
} }
} }
} catch {
console.log(` Mode: Unable to parse hooks.json`);
} }
// Check for context file (project only) // Check for context file (project only)
@@ -601,7 +645,11 @@ export async function detectClaudeCode(): Promise<boolean> {
} }
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Fallback behavior - CLI not found, continue to directory check // [ANTI-PATTERN IGNORED]: Fallback behavior - CLI not found, continue to directory check
logger.debug('SYSTEM', 'Claude CLI not in PATH', {}, error as Error); if (error instanceof Error) {
logger.debug('WORKER', 'Claude CLI not in PATH', {}, error);
} else {
logger.debug('WORKER', 'Claude CLI not in PATH', {}, new Error(String(error)));
}
} }
// Check for Claude Code plugin directory (respects CLAUDE_CONFIG_DIR) // Check for Claude Code plugin directory (respects CLAUDE_CONFIG_DIR)
src/services/integrations/GeminiCliHooksInstaller.ts
+36 -17
View File
@@ -162,6 +162,11 @@ function readGeminiSettings(): GeminiSettingsJson {
try { try {
return JSON.parse(content) as GeminiSettingsJson; return JSON.parse(content) as GeminiSettingsJson;
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.error('WORKER', 'Corrupt JSON in Gemini settings', { path: GEMINI_SETTINGS_PATH }, error);
} else {
logger.error('WORKER', 'Corrupt JSON in Gemini settings', { path: GEMINI_SETTINGS_PATH }, new Error(String(error)));
}
throw new Error(`Corrupt JSON in ${GEMINI_SETTINGS_PATH}, refusing to overwrite user settings`); throw new Error(`Corrupt JSON in ${GEMINI_SETTINGS_PATH}, refusing to overwrite user settings`);
} }
} }
@@ -298,15 +303,22 @@ export async function installGeminiCliHooks(): Promise<number> {
const existingSettings = readGeminiSettings(); const existingSettings = readGeminiSettings();
const mergedSettings = mergeHooksIntoSettings(existingSettings, hooksConfig); const mergedSettings = mergeHooksIntoSettings(existingSettings, hooksConfig);
// Write back writeGeminiHooksAndSetupContext(mergedSettings);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
return 1;
}
}
function writeGeminiHooksAndSetupContext(mergedSettings: GeminiSettingsJson): void {
writeGeminiSettings(mergedSettings); writeGeminiSettings(mergedSettings);
console.log(` Merged hooks into ${GEMINI_SETTINGS_PATH}`); console.log(` Merged hooks into ${GEMINI_SETTINGS_PATH}`);
// Setup GEMINI.md context injection
setupGeminiMdContextSection(); setupGeminiMdContextSection();
console.log(` Setup context injection in ${GEMINI_MD_PATH}`); console.log(` Setup context injection in ${GEMINI_MD_PATH}`);
// List installed events
const eventNames = Object.keys(GEMINI_EVENT_TO_INTERNAL_EVENT); const eventNames = Object.keys(GEMINI_EVENT_TO_INTERNAL_EVENT);
console.log(` Registered ${eventNames.length} hook events:`); console.log(` Registered ${eventNames.length} hook events:`);
for (const event of eventNames) { for (const event of eventNames) {
@@ -329,12 +341,6 @@ Context Injection:
Context from past sessions is injected via ~/.gemini/GEMINI.md Context from past sessions is injected via ~/.gemini/GEMINI.md
and automatically included in Gemini CLI conversations. and automatically included in Gemini CLI conversations.
`); `);
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
return 1;
}
} }
/** /**
@@ -347,12 +353,12 @@ Context Injection:
export function uninstallGeminiCliHooks(): number { export function uninstallGeminiCliHooks(): number {
console.log('\nUninstalling Claude-Mem Gemini CLI hooks...\n'); console.log('\nUninstalling Claude-Mem Gemini CLI hooks...\n');
try {
if (!existsSync(GEMINI_SETTINGS_PATH)) { if (!existsSync(GEMINI_SETTINGS_PATH)) {
console.log(' No Gemini CLI settings found — nothing to uninstall.'); console.log(' No Gemini CLI settings found — nothing to uninstall.');
return 0; return 0;
} }
try {
const settings = readGeminiSettings(); const settings = readGeminiSettings();
if (!settings.hooks) { if (!settings.hooks) {
console.log(' No hooks found in Gemini CLI settings — nothing to uninstall.'); console.log(' No hooks found in Gemini CLI settings — nothing to uninstall.');
@@ -383,10 +389,22 @@ export function uninstallGeminiCliHooks(): number {
delete settings.hooks; delete settings.hooks;
} }
writeSettingsAndCleanupGeminiContext(settings, removedCount);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nUninstallation failed: ${message}`);
return 1;
}
}
function writeSettingsAndCleanupGeminiContext(
settings: GeminiSettingsJson,
removedCount: number,
): void {
writeGeminiSettings(settings); writeGeminiSettings(settings);
console.log(` Removed ${removedCount} claude-mem hook(s) from ${GEMINI_SETTINGS_PATH}`); console.log(` Removed ${removedCount} claude-mem hook(s) from ${GEMINI_SETTINGS_PATH}`);
// Remove claude-mem context section from GEMINI.md
if (existsSync(GEMINI_MD_PATH)) { if (existsSync(GEMINI_MD_PATH)) {
let mdContent = readFileSync(GEMINI_MD_PATH, 'utf-8'); let mdContent = readFileSync(GEMINI_MD_PATH, 'utf-8');
const contextRegex = /\n?<claude-mem-context>[\s\S]*?<\/claude-mem-context>\n?/; const contextRegex = /\n?<claude-mem-context>[\s\S]*?<\/claude-mem-context>\n?/;
@@ -399,11 +417,6 @@ export function uninstallGeminiCliHooks(): number {
console.log('\nUninstallation complete!\n'); console.log('\nUninstallation complete!\n');
console.log('Restart Gemini CLI to apply changes.'); console.log('Restart Gemini CLI to apply changes.');
return 0;
} catch (error) {
console.error(`\nUninstallation failed: ${(error as Error).message}`);
return 1;
}
} }
/** /**
@@ -425,7 +438,13 @@ export function checkGeminiCliHooksStatus(): number {
try { try {
settings = readGeminiSettings(); settings = readGeminiSettings();
} catch (error) { } catch (error) {
console.log(`Gemini CLI settings: ${(error as Error).message}\n`); const message = error instanceof Error ? error.message : String(error);
if (error instanceof Error) {
logger.error('WORKER', 'Failed to read Gemini CLI settings', { path: GEMINI_SETTINGS_PATH }, error);
} else {
logger.error('WORKER', 'Failed to read Gemini CLI settings', { path: GEMINI_SETTINGS_PATH }, new Error(String(error)));
}
console.log(`Gemini CLI settings: ${message}\n`);
return 0; return 0;
} }
src/services/integrations/McpIntegrations.ts
+42 -30
View File
@@ -105,27 +105,46 @@ function installMcpIntegration(config: McpInstallerConfig): () => Promise<number
return 1; return 1;
} }
try {
// Write MCP config
const configPath = config.configPath; const configPath = config.configPath;
// Warp special case: skip config write if ~/.warp/ doesn't exist // Warp special case: skip config write if ~/.warp/ doesn't exist
if (config.ideId === 'warp' && !existsSync(path.dirname(configPath))) { const skipWarpConfigWrite = config.ideId === 'warp' && !existsSync(path.dirname(configPath));
let contextPath: string | undefined;
if (config.contextFile) {
contextPath = config.contextFile.path;
}
try {
writeMcpConfigAndContext(config, configPath, mcpServerPath, skipWarpConfigWrite, contextPath);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
return 1;
}
};
}
function writeMcpConfigAndContext(
config: McpInstallerConfig,
configPath: string,
mcpServerPath: string,
skipWarpConfigWrite: boolean,
contextPath: string | undefined,
): void {
if (skipWarpConfigWrite) {
console.log(` Note: ~/.warp/ not found. MCP may need to be configured via Warp Drive UI.`); console.log(` Note: ~/.warp/ not found. MCP may need to be configured via Warp Drive UI.`);
} else { } else {
writeMcpJsonConfig(configPath, mcpServerPath, config.configKey); writeMcpJsonConfig(configPath, mcpServerPath, config.configKey);
console.log(` MCP config written to: ${configPath}`); console.log(` MCP config written to: ${configPath}`);
} }
// Inject context if configured if (contextPath) {
let contextPath: string | undefined;
if (config.contextFile) {
contextPath = config.contextFile.path;
injectContextIntoMarkdownFile(contextPath, PLACEHOLDER_CONTEXT); injectContextIntoMarkdownFile(contextPath, PLACEHOLDER_CONTEXT);
console.log(` Context placeholder written to: ${contextPath}`); console.log(` Context placeholder written to: ${contextPath}`);
} }
// Print summary
const summaryLines = [`\nInstallation complete!\n`]; const summaryLines = [`\nInstallation complete!\n`];
summaryLines.push(`MCP config: ${configPath}`); summaryLines.push(`MCP config: ${configPath}`);
if (contextPath) { if (contextPath) {
@@ -143,13 +162,6 @@ function installMcpIntegration(config: McpInstallerConfig): () => Promise<number
summaryLines.push(` 2. Restart ${config.ideLabel} to pick up the MCP server`); summaryLines.push(` 2. Restart ${config.ideLabel} to pick up the MCP server`);
summaryLines.push(''); summaryLines.push('');
console.log(summaryLines.join('\n')); console.log(summaryLines.join('\n'));
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
return 1;
}
};
} }
// ============================================================================ // ============================================================================
@@ -274,27 +286,35 @@ export async function installGooseMcpIntegration(): Promise<number> {
return 1; return 1;
} }
try {
const configPath = getGooseConfigPath(); const configPath = getGooseConfigPath();
const configDirectory = path.dirname(configPath); const configDirectory = path.dirname(configPath);
mkdirSync(configDirectory, { recursive: true });
try {
mkdirSync(configDirectory, { recursive: true });
mergeGooseYamlConfig(configPath, mcpServerPath);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
return 1;
}
}
function mergeGooseYamlConfig(configPath: string, mcpServerPath: string): void {
if (existsSync(configPath)) { if (existsSync(configPath)) {
let yamlContent = readFileSync(configPath, 'utf-8'); let yamlContent = readFileSync(configPath, 'utf-8');
if (gooseConfigHasClaudeMemEntry(yamlContent)) { if (gooseConfigHasClaudeMemEntry(yamlContent)) {
// Already configured — replace the claude-mem block
// Find the claude-mem entry and replace it
const claudeMemPattern = /( {2}claude-mem:\n(?:.*\n)*?(?= {2}\S|\n\n|^\S|$))/m; const claudeMemPattern = /( {2}claude-mem:\n(?:.*\n)*?(?= {2}\S|\n\n|^\S|$))/m;
const newEntry = buildGooseClaudeMemEntryYaml(mcpServerPath) + '\n'; const newEntry = buildGooseClaudeMemEntryYaml(mcpServerPath) + '\n';
if (claudeMemPattern.test(yamlContent)) { if (!claudeMemPattern.test(yamlContent)) {
yamlContent = yamlContent.replace(claudeMemPattern, newEntry); throw new Error('Found mcpServers/claude-mem markers but could not locate a replaceable claude-mem block');
} }
yamlContent = yamlContent.replace(claudeMemPattern, newEntry);
writeFileSync(configPath, yamlContent); writeFileSync(configPath, yamlContent);
console.log(` Updated existing claude-mem entry in: ${configPath}`); console.log(` Updated existing claude-mem entry in: ${configPath}`);
} else if (yamlContent.includes('mcpServers:')) { } else if (yamlContent.includes('mcpServers:')) {
// mcpServers section exists but no claude-mem entry — append under it
const mcpServersIndex = yamlContent.indexOf('mcpServers:'); const mcpServersIndex = yamlContent.indexOf('mcpServers:');
const insertionPoint = mcpServersIndex + 'mcpServers:'.length; const insertionPoint = mcpServersIndex + 'mcpServers:'.length;
const newEntry = '\n' + buildGooseClaudeMemEntryYaml(mcpServerPath); const newEntry = '\n' + buildGooseClaudeMemEntryYaml(mcpServerPath);
@@ -307,14 +327,12 @@ export async function installGooseMcpIntegration(): Promise<number> {
writeFileSync(configPath, yamlContent); writeFileSync(configPath, yamlContent);
console.log(` Added claude-mem to existing mcpServers in: ${configPath}`); console.log(` Added claude-mem to existing mcpServers in: ${configPath}`);
} else { } else {
// No mcpServers section — append the entire block
const mcpBlock = '\n' + buildGooseMcpYamlBlock(mcpServerPath) + '\n'; const mcpBlock = '\n' + buildGooseMcpYamlBlock(mcpServerPath) + '\n';
yamlContent = yamlContent.trimEnd() + '\n' + mcpBlock; yamlContent = yamlContent.trimEnd() + '\n' + mcpBlock;
writeFileSync(configPath, yamlContent); writeFileSync(configPath, yamlContent);
console.log(` Appended mcpServers section to: ${configPath}`); console.log(` Appended mcpServers section to: ${configPath}`);
} }
} else { } else {
// File doesn't exist — create from template
const templateContent = buildGooseMcpYamlBlock(mcpServerPath) + '\n'; const templateContent = buildGooseMcpYamlBlock(mcpServerPath) + '\n';
writeFileSync(configPath, templateContent); writeFileSync(configPath, templateContent);
console.log(` Created config with MCP server: ${configPath}`); console.log(` Created config with MCP server: ${configPath}`);
@@ -332,12 +350,6 @@ Next steps:
1. Start claude-mem worker: npx claude-mem start 1. Start claude-mem worker: npx claude-mem start
2. Restart Goose to pick up the MCP server 2. Restart Goose to pick up the MCP server
`); `);
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
return 1;
}
} }
// ============================================================================ // ============================================================================
src/services/integrations/OpenClawInstaller.ts
+44 -34
View File
@@ -146,8 +146,10 @@ function readOpenClawConfig(): Record<string, any> {
if (!existsSync(configFilePath)) return {}; if (!existsSync(configFilePath)) return {};
try { try {
return JSON.parse(readFileSync(configFilePath, 'utf-8')); return JSON.parse(readFileSync(configFilePath, 'utf-8'));
} catch { } catch (error) {
return {}; const normalizedError = error instanceof Error ? error : new Error(String(error));
logger.error('WORKER', 'Failed to parse openclaw.json', { path: configFilePath }, normalizedError);
throw normalizedError;
} }
} }
@@ -250,31 +252,10 @@ export function installOpenClawPlugin(): number {
const extensionDirectory = getOpenClawClaudeMemExtensionDirectory(); const extensionDirectory = getOpenClawClaudeMemExtensionDirectory();
const destinationDistDirectory = path.join(extensionDirectory, 'dist'); const destinationDistDirectory = path.join(extensionDirectory, 'dist');
try { // Locate optional assets before entering the try block
// Create the extension directory structure
mkdirSync(destinationDistDirectory, { recursive: true });
// Copy pre-built dist files
cpSync(preBuiltDistDirectory, destinationDistDirectory, { recursive: true, force: true });
console.log(` Plugin dist copied to: ${destinationDistDirectory}`);
// Copy openclaw.plugin.json if available
const manifestPath = findPluginManifestPath(); const manifestPath = findPluginManifestPath();
if (manifestPath) {
const destinationManifest = path.join(extensionDirectory, 'openclaw.plugin.json');
cpSync(manifestPath, destinationManifest, { force: true });
console.log(` Plugin manifest copied to: ${destinationManifest}`);
}
// Copy skills directory if available
const skillsDirectory = findPluginSkillsDirectory(); const skillsDirectory = findPluginSkillsDirectory();
if (skillsDirectory) {
const destinationSkills = path.join(extensionDirectory, 'skills');
cpSync(skillsDirectory, destinationSkills, { recursive: true, force: true });
console.log(` Skills copied to: ${destinationSkills}`);
}
// Create a minimal package.json for the extension (OpenClaw expects this)
const extensionPackageJson = { const extensionPackageJson = {
name: 'claude-mem', name: 'claude-mem',
version: '1.0.0', version: '1.0.0',
@@ -282,17 +263,11 @@ export function installOpenClawPlugin(): number {
main: 'dist/index.js', main: 'dist/index.js',
openclaw: { extensions: ['./dist/index.js'] }, openclaw: { extensions: ['./dist/index.js'] },
}; };
writeFileSync(
path.join(extensionDirectory, 'package.json'),
JSON.stringify(extensionPackageJson, null, 2) + '\n',
'utf-8',
);
// Register in openclaw.json (merge, not overwrite) try {
registerPluginInOpenClawConfig(); // Create the extension directory structure inside try to catch EACCES/ENOSPC
console.log(` Registered in openclaw.json`); mkdirSync(destinationDistDirectory, { recursive: true });
copyPluginFilesAndRegister(preBuiltDistDirectory, destinationDistDirectory, extensionDirectory, manifestPath, skillsDirectory, extensionPackageJson);
logger.info('OPENCLAW', 'Plugin installed', { destination: extensionDirectory });
return 0; return 0;
} catch (error) { } catch (error) {
const message = error instanceof Error ? error.message : String(error); const message = error instanceof Error ? error.message : String(error);
@@ -301,6 +276,41 @@ export function installOpenClawPlugin(): number {
} }
} }
function copyPluginFilesAndRegister(
preBuiltDistDirectory: string,
destinationDistDirectory: string,
extensionDirectory: string,
manifestPath: string | null,
skillsDirectory: string | null,
extensionPackageJson: Record<string, unknown>,
): void {
cpSync(preBuiltDistDirectory, destinationDistDirectory, { recursive: true, force: true });
console.log(` Plugin dist copied to: ${destinationDistDirectory}`);
if (manifestPath) {
const destinationManifest = path.join(extensionDirectory, 'openclaw.plugin.json');
cpSync(manifestPath, destinationManifest, { force: true });
console.log(` Plugin manifest copied to: ${destinationManifest}`);
}
if (skillsDirectory) {
const destinationSkills = path.join(extensionDirectory, 'skills');
cpSync(skillsDirectory, destinationSkills, { recursive: true, force: true });
console.log(` Skills copied to: ${destinationSkills}`);
}
writeFileSync(
path.join(extensionDirectory, 'package.json'),
JSON.stringify(extensionPackageJson, null, 2) + '\n',
'utf-8',
);
registerPluginInOpenClawConfig();
console.log(` Registered in openclaw.json`);
logger.info('OPENCLAW', 'Plugin installed', { destination: extensionDirectory });
}
// ============================================================================ // ============================================================================
// Uninstallation // Uninstallation
// ============================================================================ // ============================================================================
src/services/integrations/OpenCodeInstaller.ts
+71 -56
View File
@@ -164,10 +164,35 @@ export async function syncContextToAgentsMd(
project: string, project: string,
): Promise<void> { ): Promise<void> {
try { try {
await fetchAndInjectOpenCodeContext(port, project);
} catch (error) {
// Worker not available — non-critical
if (error instanceof Error) {
logger.debug('WORKER', 'Worker not available during context sync', {}, error);
} else {
logger.debug('WORKER', 'Worker not available during context sync', {}, new Error(String(error)));
}
}
}
async function fetchRealContextFromWorker(): Promise<string | null> {
const workerPort = getWorkerPort();
const healthResponse = await fetch(`http://127.0.0.1:${workerPort}/api/readiness`);
if (!healthResponse.ok) return null;
const contextResponse = await fetch(
`http://127.0.0.1:${workerPort}/api/context/inject?project=opencode`,
);
if (!contextResponse.ok) return null;
const realContext = await contextResponse.text();
return realContext && realContext.trim() ? realContext : null;
}
async function fetchAndInjectOpenCodeContext(port: number, project: string): Promise<void> {
const response = await fetch( const response = await fetch(
`http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(project)}`, `http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(project)}`,
); );
if (!response.ok) return; if (!response.ok) return;
const contextText = await response.text(); const contextText = await response.text();
@@ -177,15 +202,25 @@ export async function syncContextToAgentsMd(
logger.warn('OPENCODE', 'Failed to inject context into AGENTS.md during sync'); logger.warn('OPENCODE', 'Failed to inject context into AGENTS.md during sync');
} }
} }
} catch {
// Worker not available — non-critical
}
} }
// ============================================================================ // ============================================================================
// Uninstallation // Uninstallation
// ============================================================================ // ============================================================================
function writeOrRemoveCleanedAgentsMd(agentsMdPath: string, trimmedContent: string): void {
if (
trimmedContent.length === 0 ||
trimmedContent === '# Claude-Mem Memory Context'
) {
unlinkSync(agentsMdPath);
console.log(` Removed empty AGENTS.md`);
} else {
writeFileSync(agentsMdPath, trimmedContent + '\n', 'utf-8');
console.log(` Cleaned context from AGENTS.md`);
}
}
/** /**
* Remove the claude-mem plugin from OpenCode. * Remove the claude-mem plugin from OpenCode.
* Removes the plugin file and cleans up the AGENTS.md context section. * Removes the plugin file and cleans up the AGENTS.md context section.
@@ -211,8 +246,16 @@ export function uninstallOpenCodePlugin(): number {
// Remove context section from AGENTS.md // Remove context section from AGENTS.md
const agentsMdPath = getOpenCodeAgentsMdPath(); const agentsMdPath = getOpenCodeAgentsMdPath();
if (existsSync(agentsMdPath)) { if (existsSync(agentsMdPath)) {
let content: string;
try { try {
let content = readFileSync(agentsMdPath, 'utf-8'); content = readFileSync(agentsMdPath, 'utf-8');
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(` Failed to read AGENTS.md: ${message}`);
hasErrors = true;
content = '';
}
const tagStartIndex = content.indexOf(CONTEXT_TAG_OPEN); const tagStartIndex = content.indexOf(CONTEXT_TAG_OPEN);
const tagEndIndex = content.indexOf(CONTEXT_TAG_CLOSE); const tagEndIndex = content.indexOf(CONTEXT_TAG_CLOSE);
@@ -222,25 +265,16 @@ export function uninstallOpenCodePlugin(): number {
'\n' + '\n' +
content.slice(tagEndIndex + CONTEXT_TAG_CLOSE.length).trimStart(); content.slice(tagEndIndex + CONTEXT_TAG_CLOSE.length).trimStart();
// If the file is now essentially empty or only has our header, remove it
const trimmedContent = content.trim(); const trimmedContent = content.trim();
if ( try {
trimmedContent.length === 0 || writeOrRemoveCleanedAgentsMd(agentsMdPath, trimmedContent);
trimmedContent === '# Claude-Mem Memory Context'
) {
unlinkSync(agentsMdPath);
console.log(` Removed empty AGENTS.md`);
} else {
writeFileSync(agentsMdPath, trimmedContent + '\n', 'utf-8');
console.log(` Cleaned context from AGENTS.md`);
}
}
} catch (error) { } catch (error) {
const message = error instanceof Error ? error.message : String(error); const message = error instanceof Error ? error.message : String(error);
console.error(` Failed to clean AGENTS.md: ${message}`); console.error(` Failed to clean AGENTS.md: ${message}`);
hasErrors = true; hasErrors = true;
} }
} }
}
return hasErrors ? 1 : 0; return hasErrors ? 1 : 0;
} }
@@ -309,48 +343,29 @@ export async function installOpenCodeIntegration(): Promise<number> {
Use claude-mem search tools for manual memory queries.`; Use claude-mem search tools for manual memory queries.`;
// Try to fetch real context from worker first // Try to fetch real context from worker first
let contextToInject = placeholderContext;
let contextSource = 'placeholder';
try { try {
const workerPort = getWorkerPort(); const realContext = await fetchRealContextFromWorker();
const healthResponse = await fetch(`http://127.0.0.1:${workerPort}/api/readiness`); if (realContext) {
if (healthResponse.ok) { contextToInject = realContext;
const contextResponse = await fetch( contextSource = 'existing memory';
`http://127.0.0.1:${workerPort}/api/context/inject?project=opencode`, }
); } catch (error) {
if (contextResponse.ok) { // Worker not available — use placeholder
const realContext = await contextResponse.text(); if (error instanceof Error) {
if (realContext && realContext.trim()) { logger.debug('WORKER', 'Worker not available during OpenCode install', {}, error);
const injectResult = injectContextIntoAgentsMd(realContext);
if (injectResult !== 0) {
logger.warn('OPENCODE', 'Failed to inject real context into AGENTS.md during install');
} else { } else {
logger.debug('WORKER', 'Worker not available during OpenCode install', {}, new Error(String(error)));
}
}
const injectResult = injectContextIntoAgentsMd(contextToInject);
if (injectResult !== 0) {
logger.warn('OPENCODE', `Failed to inject ${contextSource} context into AGENTS.md during install`);
} else {
if (contextSource === 'existing memory') {
console.log(' Context injected from existing memory'); console.log(' Context injected from existing memory');
}
} else {
const injectResult = injectContextIntoAgentsMd(placeholderContext);
if (injectResult !== 0) {
logger.warn('OPENCODE', 'Failed to inject placeholder context into AGENTS.md during install');
} else {
console.log(' Placeholder context created (will populate after first session)');
}
}
} else {
const injectResult = injectContextIntoAgentsMd(placeholderContext);
if (injectResult !== 0) {
logger.warn('OPENCODE', 'Failed to inject placeholder context into AGENTS.md during install');
}
}
} else {
const injectResult = injectContextIntoAgentsMd(placeholderContext);
if (injectResult !== 0) {
logger.warn('OPENCODE', 'Failed to inject placeholder context into AGENTS.md during install');
} else {
console.log(' Placeholder context created (worker not running)');
}
}
} catch {
const injectResult = injectContextIntoAgentsMd(placeholderContext);
if (injectResult !== 0) {
logger.warn('OPENCODE', 'Failed to inject placeholder context into AGENTS.md during install');
} else { } else {
console.log(' Placeholder context created (worker not running)'); console.log(' Placeholder context created (worker not running)');
} }
src/services/integrations/WindsurfHooksInstaller.ts
+104 -54
View File
@@ -86,9 +86,11 @@ export function readWindsurfRegistry(): WindsurfProjectRegistry {
if (!existsSync(WINDSURF_REGISTRY_FILE)) return {}; if (!existsSync(WINDSURF_REGISTRY_FILE)) return {};
return JSON.parse(readFileSync(WINDSURF_REGISTRY_FILE, 'utf-8')); return JSON.parse(readFileSync(WINDSURF_REGISTRY_FILE, 'utf-8'));
} catch (error) { } catch (error) {
logger.error('WINDSURF', 'Failed to read registry, using empty', { if (error instanceof Error) {
file: WINDSURF_REGISTRY_FILE, logger.error('WORKER', 'Failed to read registry, using empty', { file: WINDSURF_REGISTRY_FILE }, error);
}, error as Error); } else {
logger.error('WORKER', 'Failed to read registry, using empty', { file: WINDSURF_REGISTRY_FILE }, new Error(String(error)));
}
return {}; return {};
} }
} }
@@ -151,7 +153,11 @@ export async function updateWindsurfContextForProject(projectName: string, works
logger.debug('WINDSURF', 'Updated context file', { projectName, workspacePath }); logger.debug('WINDSURF', 'Updated context file', { projectName, workspacePath });
} catch (error) { } catch (error) {
// Background context update — failure is non-critical // Background context update — failure is non-critical
logger.error('WINDSURF', 'Failed to update context file', { projectName, workspacePath }, error as Error); if (error instanceof Error) {
logger.error('WORKER', 'Failed to update context file', { projectName, workspacePath }, error);
} else {
logger.error('WORKER', 'Failed to update context file', { projectName, workspacePath }, new Error(String(error)));
}
} }
} }
@@ -235,6 +241,11 @@ function mergeAndWriteHooksJson(
existingConfig.hooks = {}; existingConfig.hooks = {};
} }
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.error('WORKER', 'Corrupt hooks.json, refusing to overwrite', { path: WINDSURF_HOOKS_JSON_PATH }, error);
} else {
logger.error('WORKER', 'Corrupt hooks.json, refusing to overwrite', { path: WINDSURF_HOOKS_JSON_PATH }, new Error(String(error)));
}
throw new Error(`Corrupt hooks.json at ${WINDSURF_HOOKS_JSON_PATH}, refusing to overwrite`); throw new Error(`Corrupt hooks.json at ${WINDSURF_HOOKS_JSON_PATH}, refusing to overwrite`);
} }
} }
@@ -286,16 +297,30 @@ export async function installWindsurfHooks(): Promise<number> {
// IMPORTANT: Tilde expansion is NOT supported in working_directory — use absolute paths // IMPORTANT: Tilde expansion is NOT supported in working_directory — use absolute paths
const workingDirectory = path.dirname(workerServicePath); const workingDirectory = path.dirname(workerServicePath);
try {
console.log(` Using Bun runtime: ${bunPath}`); console.log(` Using Bun runtime: ${bunPath}`);
console.log(` Worker service: ${workerServicePath}`); console.log(` Worker service: ${workerServicePath}`);
// Merge our hooks into the existing hooks.json const workspaceRoot = process.cwd();
try {
await writeWindsurfHooksAndSetupContext(bunPath, workerServicePath, workingDirectory, workspaceRoot);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nInstallation failed: ${message}`);
return 1;
}
}
async function writeWindsurfHooksAndSetupContext(
bunPath: string,
workerServicePath: string,
workingDirectory: string,
workspaceRoot: string,
): Promise<void> {
mergeAndWriteHooksJson(bunPath, workerServicePath, workingDirectory); mergeAndWriteHooksJson(bunPath, workerServicePath, workingDirectory);
console.log(` Created/merged hooks.json`); console.log(` Created/merged hooks.json`);
// Set up initial context for the current workspace
const workspaceRoot = process.cwd();
await setupWindsurfProjectContext(workspaceRoot); await setupWindsurfProjectContext(workspaceRoot);
console.log(` console.log(`
@@ -316,12 +341,6 @@ Next steps:
2. Restart Windsurf to load the hooks 2. Restart Windsurf to load the hooks
3. Context is injected via .windsurf/rules/claude-mem-context.md (workspace-level) 3. Context is injected via .windsurf/rules/claude-mem-context.md (workspace-level)
`); `);
return 0;
} catch (error) {
console.error(`\nInstallation failed: ${(error as Error).message}`);
return 1;
}
} }
/** /**
@@ -335,23 +354,14 @@ async function setupWindsurfProjectContext(workspaceRoot: string): Promise<void>
console.log(` Generating initial context...`); console.log(` Generating initial context...`);
try { try {
const healthResponse = await fetch(`http://127.0.0.1:${port}/api/readiness`); contextGenerated = await fetchWindsurfContextFromWorker(port, projectName, workspaceRoot);
if (healthResponse.ok) {
const contextResponse = await fetch(
`http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(projectName)}`
);
if (contextResponse.ok) {
const context = await contextResponse.text();
if (context && context.trim()) {
writeWindsurfContextFile(workspaceRoot, context);
contextGenerated = true;
console.log(` Generated initial context from existing memory`);
}
}
}
} catch (error) { } catch (error) {
// Worker not running during install — non-critical // Worker not running during install — non-critical
logger.debug('WINDSURF', 'Worker not running during install', {}, error as Error); if (error instanceof Error) {
logger.debug('WORKER', 'Worker not running during install', {}, error);
} else {
logger.debug('WORKER', 'Worker not running during install', {}, new Error(String(error)));
}
} }
if (!contextGenerated) { if (!contextGenerated) {
@@ -374,31 +384,78 @@ Use claude-mem's MCP search tools for manual memory queries.
console.log(` Registered for auto-context updates`); console.log(` Registered for auto-context updates`);
} }
async function fetchWindsurfContextFromWorker(
port: number,
projectName: string,
workspaceRoot: string,
): Promise<boolean> {
const healthResponse = await fetch(`http://127.0.0.1:${port}/api/readiness`);
if (!healthResponse.ok) return false;
const contextResponse = await fetch(
`http://127.0.0.1:${port}/api/context/inject?project=${encodeURIComponent(projectName)}`,
);
if (!contextResponse.ok) return false;
const context = await contextResponse.text();
if (context && context.trim()) {
writeWindsurfContextFile(workspaceRoot, context);
console.log(` Generated initial context from existing memory`);
return true;
}
return false;
}
/** /**
* Uninstall Windsurf hooks — removes claude-mem entries from hooks.json * Uninstall Windsurf hooks — removes claude-mem entries from hooks.json
*/ */
export function uninstallWindsurfHooks(): number { export function uninstallWindsurfHooks(): number {
console.log('\nUninstalling Claude-Mem Windsurf hooks...\n'); console.log('\nUninstalling Claude-Mem Windsurf hooks...\n');
try {
// Remove our entries from hooks.json (preserve other integrations) // Remove our entries from hooks.json (preserve other integrations)
if (existsSync(WINDSURF_HOOKS_JSON_PATH)) { if (existsSync(WINDSURF_HOOKS_JSON_PATH)) {
try { try {
const config: WindsurfHooksJson = JSON.parse(readFileSync(WINDSURF_HOOKS_JSON_PATH, 'utf-8')); removeClaudeMemHookEntries();
} catch (error) {
if (error instanceof Error) {
logger.error('WORKER', 'Could not parse hooks.json during uninstall', { path: WINDSURF_HOOKS_JSON_PATH }, error);
} else {
logger.error('WORKER', 'Could not parse hooks.json during uninstall', { path: WINDSURF_HOOKS_JSON_PATH }, new Error(String(error)));
}
console.log(` Warning: could not parse hooks.json — leaving file intact to preserve other hooks`);
}
} else {
console.log(` No hooks.json found`);
}
const workspaceRoot = process.cwd();
try {
removeWindsurfContextAndUnregister(workspaceRoot);
return 0;
} catch (error) {
const message = error instanceof Error ? error.message : String(error);
console.error(`\nUninstallation failed: ${message}`);
return 1;
}
}
function removeClaudeMemHookEntries(): void {
const parsed = JSON.parse(readFileSync(WINDSURF_HOOKS_JSON_PATH, 'utf-8')) as Partial<WindsurfHooksJson>;
const config: WindsurfHooksJson = { hooks: parsed.hooks ?? {} };
for (const eventName of WINDSURF_HOOK_EVENTS) { for (const eventName of WINDSURF_HOOK_EVENTS) {
if (config.hooks[eventName]) { const eventHooks = config.hooks[eventName] ?? [];
config.hooks[eventName] = config.hooks[eventName].filter( if (eventHooks.length > 0) {
(hook) => !hook.command.includes('worker-service') || !hook.command.includes('windsurf') config.hooks[eventName] = eventHooks.filter(
(hook) => !hook.command.includes('worker-service') || !hook.command.includes('windsurf'),
); );
// Remove empty arrays
if (config.hooks[eventName].length === 0) { if (config.hooks[eventName].length === 0) {
delete config.hooks[eventName]; delete config.hooks[eventName];
} }
} }
} }
// If no hooks remain, remove the file entirely
if (Object.keys(config.hooks).length === 0) { if (Object.keys(config.hooks).length === 0) {
unlinkSync(WINDSURF_HOOKS_JSON_PATH); unlinkSync(WINDSURF_HOOKS_JSON_PATH);
console.log(` Removed hooks.json (no hooks remaining)`); console.log(` Removed hooks.json (no hooks remaining)`);
@@ -406,33 +463,20 @@ export function uninstallWindsurfHooks(): number {
writeFileSync(WINDSURF_HOOKS_JSON_PATH, JSON.stringify(config, null, 2)); writeFileSync(WINDSURF_HOOKS_JSON_PATH, JSON.stringify(config, null, 2));
console.log(` Removed claude-mem entries from hooks.json (other hooks preserved)`); console.log(` Removed claude-mem entries from hooks.json (other hooks preserved)`);
} }
} catch (error) {
console.log(` Warning: could not parse hooks.json — leaving file intact to preserve other hooks`);
}
} else {
console.log(` No hooks.json found`);
} }
// Remove context file from the current workspace function removeWindsurfContextAndUnregister(workspaceRoot: string): void {
const workspaceRoot = process.cwd();
const contextFile = path.join(workspaceRoot, '.windsurf', 'rules', 'claude-mem-context.md'); const contextFile = path.join(workspaceRoot, '.windsurf', 'rules', 'claude-mem-context.md');
if (existsSync(contextFile)) { if (existsSync(contextFile)) {
unlinkSync(contextFile); unlinkSync(contextFile);
console.log(` Removed context file`); console.log(` Removed context file`);
} }
// Unregister project
unregisterWindsurfProject(workspaceRoot); unregisterWindsurfProject(workspaceRoot);
console.log(` Unregistered from auto-context updates`); console.log(` Unregistered from auto-context updates`);
console.log(`\nUninstallation complete!\n`); console.log(`\nUninstallation complete!\n`);
console.log('Restart Windsurf to apply changes.'); console.log('Restart Windsurf to apply changes.');
return 0;
} catch (error) {
console.error(`\nUninstallation failed: ${(error as Error).message}`);
return 1;
}
} }
/** /**
@@ -445,10 +489,18 @@ export function checkWindsurfHooksStatus(): number {
console.log(`User-level: Installed`); console.log(`User-level: Installed`);
console.log(` Config: ${WINDSURF_HOOKS_JSON_PATH}`); console.log(` Config: ${WINDSURF_HOOKS_JSON_PATH}`);
let parsedConfig: Partial<WindsurfHooksJson> | null = null;
try { try {
const config: WindsurfHooksJson = JSON.parse(readFileSync(WINDSURF_HOOKS_JSON_PATH, 'utf-8')); parsedConfig = JSON.parse(readFileSync(WINDSURF_HOOKS_JSON_PATH, 'utf-8'));
} catch (error) {
const normalizedError = error instanceof Error ? error : new Error(String(error));
logger.error('WORKER', 'Unable to parse hooks.json', { path: WINDSURF_HOOKS_JSON_PATH }, normalizedError);
console.log(` Mode: Unable to parse hooks.json`);
}
if (parsedConfig) {
const registeredEvents = WINDSURF_HOOK_EVENTS.filter( const registeredEvents = WINDSURF_HOOK_EVENTS.filter(
(event) => config.hooks[event]?.some( (event) => (parsedConfig?.hooks?.[event] ?? []).some(
(hook) => hook.command.includes('worker-service') && hook.command.includes('windsurf') (hook) => hook.command.includes('worker-service') && hook.command.includes('windsurf')
) )
); );
@@ -456,8 +508,6 @@ export function checkWindsurfHooksStatus(): number {
for (const event of registeredEvents) { for (const event of registeredEvents) {
console.log(` - ${event}`); console.log(` - ${event}`);
} }
} catch {
console.log(` Mode: Unable to parse hooks.json`);
} }
// Check for context file in current workspace // Check for context file in current workspace
src/services/queue/SessionQueueProcessor.ts
+48 -23
View File
@@ -34,40 +34,38 @@ export class SessionQueueProcessor {
let lastActivityTime = Date.now(); let lastActivityTime = Date.now();
while (!signal.aborted) { while (!signal.aborted) {
try { // Claim phase: atomically claim next pending message (marks as 'processing')
// Atomically claim next pending message (marks as 'processing')
// Self-heals any stale processing messages before claiming // Self-heals any stale processing messages before claiming
const persistentMessage = this.store.claimNextMessage(sessionDbId); let persistentMessage: PersistentPendingMessage | null = null;
try {
persistentMessage = this.store.claimNextMessage(sessionDbId);
} catch (error) {
if (signal.aborted) return;
const normalizedError = error instanceof Error ? error : new Error(String(error));
logger.error('QUEUE', 'Failed to claim next message', { sessionDbId }, normalizedError);
await new Promise(resolve => setTimeout(resolve, 1000));
continue;
}
if (persistentMessage) { if (persistentMessage) {
// Reset activity time when we successfully yield a message // Reset activity time when we successfully yield a message
lastActivityTime = Date.now(); lastActivityTime = Date.now();
// Yield the message for processing (it's marked as 'processing' in DB) // Yield the message for processing (it's marked as 'processing' in DB)
yield this.toPendingMessageWithId(persistentMessage); yield this.toPendingMessageWithId(persistentMessage);
} else { continue;
// Queue empty - wait for wake-up event or timeout }
const receivedMessage = await this.waitForMessage(signal, IDLE_TIMEOUT_MS);
if (!receivedMessage && !signal.aborted) { // Wait phase: queue empty - wait for wake-up event or timeout
// Timeout occurred - check if we've been idle too long try {
const idleDuration = Date.now() - lastActivityTime; const idleTimedOut = await this.handleWaitPhase(signal, lastActivityTime, sessionDbId, onIdleTimeout);
if (idleDuration >= IDLE_TIMEOUT_MS) { if (idleTimedOut) return;
logger.info('SESSION', 'Idle timeout reached, triggering abort to kill subprocess', { // Reset timer on spurious wakeup if not timed out
sessionDbId,
idleDurationMs: idleDuration,
thresholdMs: IDLE_TIMEOUT_MS
});
onIdleTimeout?.();
return;
}
// Reset timer on spurious wakeup - queue is empty but duration check failed
lastActivityTime = Date.now(); lastActivityTime = Date.now();
}
}
} catch (error) { } catch (error) {
if (signal.aborted) return; if (signal.aborted) return;
logger.error('SESSION', 'Error in queue processor loop', { sessionDbId }, error as Error); const normalizedError = error instanceof Error ? error : new Error(String(error));
// Small backoff to prevent tight loop on DB error logger.error('QUEUE', 'Error waiting for message', { sessionDbId }, normalizedError);
// Small backoff to prevent tight loop on error
await new Promise(resolve => setTimeout(resolve, 1000)); await new Promise(resolve => setTimeout(resolve, 1000));
} }
} }
@@ -82,6 +80,33 @@ export class SessionQueueProcessor {
}; };
} }
/**
* Handle the wait phase: wait for a message or check idle timeout.
* @returns true if idle timeout was reached (caller should return/exit iterator)
*/
private async handleWaitPhase(
signal: AbortSignal,
lastActivityTime: number,
sessionDbId: number,
onIdleTimeout?: () => void
): Promise<boolean> {
const receivedMessage = await this.waitForMessage(signal, IDLE_TIMEOUT_MS);
if (!receivedMessage && !signal.aborted) {
const idleDuration = Date.now() - lastActivityTime;
if (idleDuration >= IDLE_TIMEOUT_MS) {
logger.info('SESSION', 'Idle timeout reached, triggering abort to kill subprocess', {
sessionDbId,
idleDurationMs: idleDuration,
thresholdMs: IDLE_TIMEOUT_MS
});
onIdleTimeout?.();
return true;
}
}
return false;
}
/** /**
* Wait for a message event or timeout. * Wait for a message event or timeout.
* @param signal - AbortSignal to cancel waiting * @param signal - AbortSignal to cancel waiting
src/services/server/Server.ts
+25 -15
View File
@@ -208,31 +208,27 @@ export class Server {
return res.status(400).json({ error: 'Invalid topic' }); return res.status(400).json({ error: 'Invalid topic' });
} }
try { if (operation && !ALLOWED_OPERATIONS.includes(operation)) {
let content: string;
if (operation) {
// Validate operation
if (!ALLOWED_OPERATIONS.includes(operation)) {
return res.status(400).json({ error: 'Invalid operation' }); return res.status(400).json({ error: 'Invalid operation' });
} }
// Path boundary check
if (operation) {
const OPERATIONS_BASE_DIR = path.resolve(__dirname, '../skills/mem-search/operations'); const OPERATIONS_BASE_DIR = path.resolve(__dirname, '../skills/mem-search/operations');
const operationPath = path.resolve(OPERATIONS_BASE_DIR, `${operation}.md`); const operationPath = path.resolve(OPERATIONS_BASE_DIR, `${operation}.md`);
if (!operationPath.startsWith(OPERATIONS_BASE_DIR + path.sep)) { if (!operationPath.startsWith(OPERATIONS_BASE_DIR + path.sep)) {
return res.status(400).json({ error: 'Invalid request' }); return res.status(400).json({ error: 'Invalid request' });
} }
content = await fs.promises.readFile(operationPath, 'utf-8');
} else {
const skillPath = path.join(__dirname, '../skills/mem-search/SKILL.md');
const fullContent = await fs.promises.readFile(skillPath, 'utf-8');
content = this.extractInstructionSection(fullContent, topic);
} }
res.json({ try {
content: [{ type: 'text', text: content }] const content = await this.loadInstructionContent(operation, topic);
}); res.json({ content: [{ type: 'text', text: content }] });
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.debug('HTTP', 'Instruction file not found', { topic, operation, message: error.message });
} else {
logger.debug('HTTP', 'Instruction file not found', { topic, operation, error: String(error) });
}
res.status(404).json({ error: 'Instruction not found' }); res.status(404).json({ error: 'Instruction not found' });
} }
}); });
@@ -334,6 +330,20 @@ export class Server {
}); });
} }
/**
* Load instruction content from disk for the /api/instructions endpoint.
* Caller must validate operation/topic before calling.
*/
private async loadInstructionContent(operation: string | undefined, topic: string): Promise<string> {
if (operation) {
const operationPath = path.resolve(__dirname, '../skills/mem-search/operations', `${operation}.md`);
return fs.promises.readFile(operationPath, 'utf-8');
}
const skillPath = path.join(__dirname, '../skills/mem-search/SKILL.md');
const fullContent = await fs.promises.readFile(skillPath, 'utf-8');
return this.extractInstructionSection(fullContent, topic);
}
/** /**
* Extract a specific section from instruction content * Extract a specific section from instruction content
*/ */
src/services/smart-file-read/parser.ts
+11 -3
View File
@@ -15,6 +15,7 @@ import { writeFileSync, readFileSync, mkdtempSync, rmSync, existsSync } from "no
import { join, dirname } from "node:path"; import { join, dirname } from "node:path";
import { tmpdir } from "node:os"; import { tmpdir } from "node:os";
import { createRequire } from "node:module"; import { createRequire } from "node:module";
import { logger } from "../../utils/logger.js";
// CJS-safe require for resolving external packages at runtime. // CJS-safe require for resolving external packages at runtime.
// In ESM: import.meta.url works. In CJS bundle (esbuild): __filename works. // In ESM: import.meta.url works. In CJS bundle (esbuild): __filename works.
@@ -160,6 +161,7 @@ export function loadUserGrammars(projectRoot: string): UserGrammarConfig {
const content = readFileSync(configPath, "utf-8"); const content = readFileSync(configPath, "utf-8");
rawConfig = JSON.parse(content); rawConfig = JSON.parse(content);
} catch { } catch {
// [ANTI-PATTERN IGNORED]: .claude-mem.json missing is the normal case for most projects
userGrammarCache.set(projectRoot, EMPTY_USER_GRAMMAR_CONFIG); userGrammarCache.set(projectRoot, EMPTY_USER_GRAMMAR_CONFIG);
return EMPTY_USER_GRAMMAR_CONFIG; return EMPTY_USER_GRAMMAR_CONFIG;
} }
@@ -274,7 +276,9 @@ function resolveGrammarPath(language: string): string | null {
const rootPkgPath = _require.resolve(pkg + "/package.json"); const rootPkgPath = _require.resolve(pkg + "/package.json");
const resolved = join(dirname(rootPkgPath), subdir); const resolved = join(dirname(rootPkgPath), subdir);
if (existsSync(join(resolved, "src"))) return resolved; if (existsSync(join(resolved, "src"))) return resolved;
} catch { /* fall through */ } } catch {
// [ANTI-PATTERN IGNORED]: grammar package not installed is expected for unsupported languages
}
return null; return null;
} }
@@ -282,6 +286,7 @@ function resolveGrammarPath(language: string): string | null {
const packageJsonPath = _require.resolve(pkg + "/package.json"); const packageJsonPath = _require.resolve(pkg + "/package.json");
return dirname(packageJsonPath); return dirname(packageJsonPath);
} catch { } catch {
// [ANTI-PATTERN IGNORED]: grammar package not installed is expected for unsupported languages
return null; return null;
} }
} }
@@ -550,7 +555,9 @@ function getTreeSitterBin(): string {
cachedBinPath = binPath; cachedBinPath = binPath;
return binPath; return binPath;
} }
} catch { /* fall through */ } } catch {
// [ANTI-PATTERN IGNORED]: tree-sitter-cli not in node_modules is expected; falls back to PATH
}
// Fallback: assume it's on PATH // Fallback: assume it's on PATH
cachedBinPath = "tree-sitter"; cachedBinPath = "tree-sitter";
@@ -585,7 +592,8 @@ function runBatchQuery(queryFile: string, sourceFiles: string[], grammarPath: st
let output: string; let output: string;
try { try {
output = execFileSync(bin, execArgs, { encoding: "utf-8", timeout: 30000, stdio: ["pipe", "pipe", "pipe"] }); output = execFileSync(bin, execArgs, { encoding: "utf-8", timeout: 30000, stdio: ["pipe", "pipe", "pipe"] });
} catch { } catch (error) {
logger.debug('WORKER', `tree-sitter query failed for ${sourceFiles.length} file(s)`, undefined, error instanceof Error ? error : undefined);
return new Map(); return new Map();
} }
src/services/smart-file-read/search.ts
+5 -2
View File
@@ -13,6 +13,7 @@
import { readFile, readdir, stat } from "node:fs/promises"; import { readFile, readdir, stat } from "node:fs/promises";
import { join, relative } from "node:path"; import { join, relative } from "node:path";
import { parseFilesBatch, formatFoldedView, loadUserGrammars, type FoldedFile } from "./parser.js"; import { parseFilesBatch, formatFoldedView, loadUserGrammars, type FoldedFile } from "./parser.js";
import { logger } from "../../utils/logger.js";
const CODE_EXTENSIONS = new Set([ const CODE_EXTENSIONS = new Set([
".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs", ".js", ".jsx", ".ts", ".tsx", ".mjs", ".cjs",
@@ -78,7 +79,8 @@ async function* walkDir(dir: string, rootDir: string, maxDepth: number = 20, ext
let entries; let entries;
try { try {
entries = await readdir(dir, { withFileTypes: true }); entries = await readdir(dir, { withFileTypes: true });
} catch { } catch (error) {
logger.debug('WORKER', `walkDir: failed to read directory ${dir}`, undefined, error instanceof Error ? error : undefined);
return; // permission denied, etc. return; // permission denied, etc.
} }
@@ -114,7 +116,8 @@ async function safeReadFile(filePath: string): Promise<string | null> {
if (content.slice(0, 1000).includes("\0")) return null; if (content.slice(0, 1000).includes("\0")) return null;
return content; return content;
} catch { } catch (error) {
logger.debug('WORKER', `safeReadFile: failed to read ${filePath}`, undefined, error instanceof Error ? error : undefined);
return null; return null;
} }
} }
src/services/sqlite/PendingMessageStore.ts
+12 -4
View File
@@ -24,6 +24,9 @@ export interface PersistentPendingMessage {
created_at_epoch: number; created_at_epoch: number;
started_processing_at_epoch: number | null; started_processing_at_epoch: number | null;
completed_at_epoch: number | null; completed_at_epoch: number | null;
// Claude Code subagent identity — NULL for main-session messages.
agent_type: string | null;
agent_id: string | null;
} }
/** /**
@@ -64,8 +67,9 @@ export class PendingMessageStore {
session_db_id, content_session_id, message_type, session_db_id, content_session_id, message_type,
tool_name, tool_input, tool_response, cwd, tool_name, tool_input, tool_response, cwd,
last_assistant_message, last_assistant_message,
prompt_number, status, retry_count, created_at_epoch prompt_number, status, retry_count, created_at_epoch,
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 'pending', 0, ?) agent_type, agent_id
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, 'pending', 0, ?, ?, ?)
`); `);
const result = stmt.run( const result = stmt.run(
@@ -78,7 +82,9 @@ export class PendingMessageStore {
message.cwd || null, message.cwd || null,
message.last_assistant_message || null, message.last_assistant_message || null,
message.prompt_number || null, message.prompt_number || null,
now now,
message.agentType ?? null,
message.agentId ?? null
); );
return result.lastInsertRowid as number; return result.lastInsertRowid as number;
@@ -496,7 +502,9 @@ export class PendingMessageStore {
tool_response: persistent.tool_response ? JSON.parse(persistent.tool_response) : undefined, tool_response: persistent.tool_response ? JSON.parse(persistent.tool_response) : undefined,
prompt_number: persistent.prompt_number || undefined, prompt_number: persistent.prompt_number || undefined,
cwd: persistent.cwd || undefined, cwd: persistent.cwd || undefined,
last_assistant_message: persistent.last_assistant_message || undefined last_assistant_message: persistent.last_assistant_message || undefined,
agentId: persistent.agent_id ?? undefined,
agentType: persistent.agent_type ?? undefined
}; };
} }
} }
src/services/sqlite/SessionSearch.ts
+34 -23
View File
@@ -75,6 +75,34 @@ export class SessionSearch {
logger.info('DB', 'Creating FTS5 tables'); logger.info('DB', 'Creating FTS5 tables');
try { try {
this.createFTSTablesAndTriggers();
logger.info('DB', 'FTS5 tables created successfully');
} catch (error) {
// FTS5 creation failed at runtime despite probe succeeding — degrade gracefully
logger.warn('DB', 'FTS5 table creation failed — search will use ChromaDB and LIKE queries', {}, error instanceof Error ? error : undefined);
}
}
/**
* Probe whether the FTS5 extension is available in the current SQLite build.
* Creates and immediately drops a temporary FTS5 table.
*/
private isFts5Available(): boolean {
try {
this.db.run('CREATE VIRTUAL TABLE _fts5_probe USING fts5(test_column)');
this.db.run('DROP TABLE _fts5_probe');
return true;
} catch {
// [ANTI-PATTERN IGNORED]: FTS5 unavailability is an expected platform condition, not an error
return false;
}
}
/**
* Create FTS5 virtual tables and sync triggers for observations and session_summaries.
* Extracted from ensureFTSTables to keep try block small.
*/
private createFTSTablesAndTriggers(): void {
// Create observations_fts virtual table // Create observations_fts virtual table
this.db.run(` this.db.run(`
CREATE VIRTUAL TABLE IF NOT EXISTS observations_fts USING fts5( CREATE VIRTUAL TABLE IF NOT EXISTS observations_fts USING fts5(
@@ -156,28 +184,7 @@ export class SessionSearch {
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes); VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END; END;
`); `);
logger.info('DB', 'FTS5 tables created successfully');
} catch (error) {
// FTS5 creation failed at runtime despite probe succeeding — degrade gracefully
logger.warn('DB', 'FTS5 table creation failed — search will use ChromaDB and LIKE queries', {}, error as Error);
} }
}
/**
* Probe whether the FTS5 extension is available in the current SQLite build.
* Creates and immediately drops a temporary FTS5 table.
*/
private isFts5Available(): boolean {
try {
this.db.run('CREATE VIRTUAL TABLE _fts5_probe USING fts5(test_column)');
this.db.run('DROP TABLE _fts5_probe');
return true;
} catch {
return false;
}
}
/** /**
* Build WHERE clause for structured filters * Build WHERE clause for structured filters
@@ -381,7 +388,9 @@ export class SessionSearch {
if (Array.isArray(files)) { if (Array.isArray(files)) {
return files.some(f => isDirectChild(f, folderPath)); return files.some(f => isDirectChild(f, folderPath));
} }
} catch {} } catch (error) {
logger.debug('DB', `Failed to parse files JSON for observation ${obs.id}`, undefined, error instanceof Error ? error : undefined);
}
return false; return false;
}; };
@@ -399,7 +408,9 @@ export class SessionSearch {
if (Array.isArray(files)) { if (Array.isArray(files)) {
return files.some(f => isDirectChild(f, folderPath)); return files.some(f => isDirectChild(f, folderPath));
} }
} catch {} } catch (error) {
logger.debug('DB', `Failed to parse files JSON for session summary ${session.id}`, undefined, error instanceof Error ? error : undefined);
}
return false; return false;
}; };
src/services/sqlite/SessionStore.ts
+150 -68
View File
@@ -66,6 +66,7 @@ export class SessionStore {
this.addSessionPlatformSourceColumn(); this.addSessionPlatformSourceColumn();
this.addObservationModelColumns(); this.addObservationModelColumns();
this.ensureMergedIntoProjectColumns(); this.ensureMergedIntoProjectColumns();
this.addObservationSubagentColumns();
} }
/** /**
@@ -445,17 +446,14 @@ export class SessionStore {
// Create FTS5 virtual table — skip if FTS5 is unavailable (e.g., Bun on Windows #791). // Create FTS5 virtual table — skip if FTS5 is unavailable (e.g., Bun on Windows #791).
// The user_prompts table itself is still created; only FTS indexing is skipped. // The user_prompts table itself is still created; only FTS indexing is skipped.
try { const ftsCreateSQL = `
this.db.run(`
CREATE VIRTUAL TABLE user_prompts_fts USING fts5( CREATE VIRTUAL TABLE user_prompts_fts USING fts5(
prompt_text, prompt_text,
content='user_prompts', content='user_prompts',
content_rowid='id' content_rowid='id'
); );
`); `;
const ftsTriggersSQL = `
// Create triggers to sync FTS5
this.db.run(`
CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN
INSERT INTO user_prompts_fts(rowid, prompt_text) INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text); VALUES (new.id, new.prompt_text);
@@ -472,9 +470,22 @@ export class SessionStore {
INSERT INTO user_prompts_fts(rowid, prompt_text) INSERT INTO user_prompts_fts(rowid, prompt_text)
VALUES (new.id, new.prompt_text); VALUES (new.id, new.prompt_text);
END; END;
`); `;
try {
this.db.run(ftsCreateSQL);
this.db.run(ftsTriggersSQL);
} catch (ftsError) { } catch (ftsError) {
logger.warn('DB', 'FTS5 not available — user_prompts_fts skipped (search uses ChromaDB)', {}, ftsError as Error); if (ftsError instanceof Error) {
logger.warn('DB', 'FTS5 not available — user_prompts_fts skipped (search uses ChromaDB)', {}, ftsError);
} else {
logger.warn('DB', 'FTS5 not available — user_prompts_fts skipped (search uses ChromaDB)', {}, new Error(String(ftsError)));
}
// FTS is optional — commit the main table and indexes, then return
this.db.run('COMMIT');
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
logger.debug('DB', 'Created user_prompts table (without FTS5)');
return;
} }
// Commit transaction // Commit transaction
@@ -685,7 +696,6 @@ export class SessionStore {
this.db.run('PRAGMA foreign_keys = OFF'); this.db.run('PRAGMA foreign_keys = OFF');
this.db.run('BEGIN TRANSACTION'); this.db.run('BEGIN TRANSACTION');
try {
// ========================================== // ==========================================
// 1. Recreate observations table // 1. Recreate observations table
// ========================================== // ==========================================
@@ -698,7 +708,7 @@ export class SessionStore {
// Clean up leftover temp table from a previously-crashed run // Clean up leftover temp table from a previously-crashed run
this.db.run('DROP TABLE IF EXISTS observations_new'); this.db.run('DROP TABLE IF EXISTS observations_new');
this.db.run(` const observationsNewSQL = `
CREATE TABLE observations_new ( CREATE TABLE observations_new (
id INTEGER PRIMARY KEY AUTOINCREMENT, id INTEGER PRIMARY KEY AUTOINCREMENT,
memory_session_id TEXT NOT NULL, memory_session_id TEXT NOT NULL,
@@ -718,32 +728,21 @@ export class SessionStore {
created_at_epoch INTEGER NOT NULL, created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(memory_session_id) REFERENCES sdk_sessions(memory_session_id) ON DELETE CASCADE ON UPDATE CASCADE FOREIGN KEY(memory_session_id) REFERENCES sdk_sessions(memory_session_id) ON DELETE CASCADE ON UPDATE CASCADE
) )
`); `;
const observationsCopySQL = `
this.db.run(`
INSERT INTO observations_new INSERT INTO observations_new
SELECT id, memory_session_id, project, text, type, title, subtitle, facts, SELECT id, memory_session_id, project, text, type, title, subtitle, facts,
narrative, concepts, files_read, files_modified, prompt_number, narrative, concepts, files_read, files_modified, prompt_number,
discovery_tokens, created_at, created_at_epoch discovery_tokens, created_at, created_at_epoch
FROM observations FROM observations
`); `;
const observationsIndexesSQL = `
this.db.run('DROP TABLE observations');
this.db.run('ALTER TABLE observations_new RENAME TO observations');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_observations_sdk_session ON observations(memory_session_id); CREATE INDEX idx_observations_sdk_session ON observations(memory_session_id);
CREATE INDEX idx_observations_project ON observations(project); CREATE INDEX idx_observations_project ON observations(project);
CREATE INDEX idx_observations_type ON observations(type); CREATE INDEX idx_observations_type ON observations(type);
CREATE INDEX idx_observations_created ON observations(created_at_epoch DESC); CREATE INDEX idx_observations_created ON observations(created_at_epoch DESC);
`); `;
const observationsFTSTriggersSQL = `
// Recreate FTS triggers only if observations_fts exists
// (SessionSearch.ensureFTSTables creates it on first use with IF NOT EXISTS)
const hasFTS = (this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name='observations_fts'").all() as { name: string }[]).length > 0;
if (hasFTS) {
this.db.run(`
CREATE TRIGGER IF NOT EXISTS observations_ai AFTER INSERT ON observations BEGIN CREATE TRIGGER IF NOT EXISTS observations_ai AFTER INSERT ON observations BEGIN
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts) INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts); VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
@@ -760,17 +759,21 @@ export class SessionStore {
INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts) INSERT INTO observations_fts(rowid, title, subtitle, narrative, text, facts, concepts)
VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts); VALUES (new.id, new.title, new.subtitle, new.narrative, new.text, new.facts, new.concepts);
END; END;
`); `;
}
// ========================================== // ==========================================
// 2. Recreate session_summaries table // 2. Recreate session_summaries table
// ========================================== // ==========================================
// Drop session_summaries FTS triggers before dropping the table
this.db.run('DROP TRIGGER IF EXISTS session_summaries_ai');
this.db.run('DROP TRIGGER IF EXISTS session_summaries_ad');
this.db.run('DROP TRIGGER IF EXISTS session_summaries_au');
// Clean up leftover temp table from a previously-crashed run // Clean up leftover temp table from a previously-crashed run
this.db.run('DROP TABLE IF EXISTS session_summaries_new'); this.db.run('DROP TABLE IF EXISTS session_summaries_new');
this.db.run(` const summariesNewSQL = `
CREATE TABLE session_summaries_new ( CREATE TABLE session_summaries_new (
id INTEGER PRIMARY KEY AUTOINCREMENT, id INTEGER PRIMARY KEY AUTOINCREMENT,
memory_session_id TEXT NOT NULL, memory_session_id TEXT NOT NULL,
@@ -789,35 +792,20 @@ export class SessionStore {
created_at_epoch INTEGER NOT NULL, created_at_epoch INTEGER NOT NULL,
FOREIGN KEY(memory_session_id) REFERENCES sdk_sessions(memory_session_id) ON DELETE CASCADE ON UPDATE CASCADE FOREIGN KEY(memory_session_id) REFERENCES sdk_sessions(memory_session_id) ON DELETE CASCADE ON UPDATE CASCADE
) )
`); `;
const summariesCopySQL = `
this.db.run(`
INSERT INTO session_summaries_new INSERT INTO session_summaries_new
SELECT id, memory_session_id, project, request, investigated, learned, SELECT id, memory_session_id, project, request, investigated, learned,
completed, next_steps, files_read, files_edited, notes, completed, next_steps, files_read, files_edited, notes,
prompt_number, discovery_tokens, created_at, created_at_epoch prompt_number, discovery_tokens, created_at, created_at_epoch
FROM session_summaries FROM session_summaries
`); `;
const summariesIndexesSQL = `
// Drop session_summaries FTS triggers before dropping the table
this.db.run('DROP TRIGGER IF EXISTS session_summaries_ai');
this.db.run('DROP TRIGGER IF EXISTS session_summaries_ad');
this.db.run('DROP TRIGGER IF EXISTS session_summaries_au');
this.db.run('DROP TABLE session_summaries');
this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries');
// Recreate indexes
this.db.run(`
CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(memory_session_id); CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(memory_session_id);
CREATE INDEX idx_session_summaries_project ON session_summaries(project); CREATE INDEX idx_session_summaries_project ON session_summaries(project);
CREATE INDEX idx_session_summaries_created ON session_summaries(created_at_epoch DESC); CREATE INDEX idx_session_summaries_created ON session_summaries(created_at_epoch DESC);
`); `;
const summariesFTSTriggersSQL = `
// Recreate session_summaries FTS triggers if FTS table exists
const hasSummariesFTS = (this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name='session_summaries_fts'").all() as { name: string }[]).length > 0;
if (hasSummariesFTS) {
this.db.run(`
CREATE TRIGGER IF NOT EXISTS session_summaries_ai AFTER INSERT ON session_summaries BEGIN CREATE TRIGGER IF NOT EXISTS session_summaries_ai AFTER INSERT ON session_summaries BEGIN
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes) INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes); VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
@@ -834,21 +822,52 @@ export class SessionStore {
INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes) INSERT INTO session_summaries_fts(rowid, request, investigated, learned, completed, next_steps, notes)
VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes); VALUES (new.id, new.request, new.investigated, new.learned, new.completed, new.next_steps, new.notes);
END; END;
`); `;
}
try {
this.recreateObservationsWithCascade(observationsNewSQL, observationsCopySQL, observationsIndexesSQL, observationsFTSTriggersSQL);
this.recreateSessionSummariesWithCascade(summariesNewSQL, summariesCopySQL, summariesIndexesSQL, summariesFTSTriggersSQL);
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(21, new Date().toISOString()); this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(21, new Date().toISOString());
this.db.run('COMMIT'); this.db.run('COMMIT');
this.db.run('PRAGMA foreign_keys = ON'); this.db.run('PRAGMA foreign_keys = ON');
logger.debug('DB', 'Successfully added ON UPDATE CASCADE to FK constraints'); logger.debug('DB', 'Successfully added ON UPDATE CASCADE to FK constraints');
} catch (error) { } catch (error) {
this.db.run('ROLLBACK'); this.db.run('ROLLBACK');
this.db.run('PRAGMA foreign_keys = ON'); this.db.run('PRAGMA foreign_keys = ON');
if (error instanceof Error) {
throw error; throw error;
} }
throw new Error(String(error));
}
}
/** Recreate observations table with ON UPDATE CASCADE FK (used by migration 21) */
private recreateObservationsWithCascade(createSQL: string, copySQL: string, indexesSQL: string, ftsTriggersSQL: string): void {
this.db.run(createSQL);
this.db.run(copySQL);
this.db.run('DROP TABLE observations');
this.db.run('ALTER TABLE observations_new RENAME TO observations');
this.db.run(indexesSQL);
const hasFTS = (this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name='observations_fts'").all() as { name: string }[]).length > 0;
if (hasFTS) {
this.db.run(ftsTriggersSQL);
}
}
/** Recreate session_summaries table with ON UPDATE CASCADE FK (used by migration 21) */
private recreateSessionSummariesWithCascade(createSQL: string, copySQL: string, indexesSQL: string, ftsTriggersSQL: string): void {
this.db.run(createSQL);
this.db.run(copySQL);
this.db.run('DROP TABLE session_summaries');
this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries');
this.db.run(indexesSQL);
const hasSummariesFTS = (this.db.prepare("SELECT name FROM sqlite_master WHERE type='table' AND name='session_summaries_fts'").all() as { name: string }[]).length > 0;
if (hasSummariesFTS) {
this.db.run(ftsTriggersSQL);
}
} }
/** /**
@@ -975,6 +994,44 @@ export class SessionStore {
); );
} }
/**
* Add agent_type and agent_id columns to observations and pending_messages (migration 27).
* Mirrors MigrationRunner.addObservationSubagentColumns so bundled artifacts that embed
* SessionStore (e.g. context-generator.cjs) stay schema-consistent.
*/
private addObservationSubagentColumns(): void {
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(27) as SchemaVersion | undefined;
const obsCols = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const obsHasAgentType = obsCols.some(col => col.name === 'agent_type');
const obsHasAgentId = obsCols.some(col => col.name === 'agent_id');
if (!obsHasAgentType) {
this.db.run('ALTER TABLE observations ADD COLUMN agent_type TEXT');
}
if (!obsHasAgentId) {
this.db.run('ALTER TABLE observations ADD COLUMN agent_id TEXT');
}
this.db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_type ON observations(agent_type)');
this.db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_id ON observations(agent_id)');
const pendingCols = this.db.query('PRAGMA table_info(pending_messages)').all() as TableColumnInfo[];
if (pendingCols.length > 0) {
const pendingHasAgentType = pendingCols.some(col => col.name === 'agent_type');
const pendingHasAgentId = pendingCols.some(col => col.name === 'agent_id');
if (!pendingHasAgentType) {
this.db.run('ALTER TABLE pending_messages ADD COLUMN agent_type TEXT');
}
if (!pendingHasAgentId) {
this.db.run('ALTER TABLE pending_messages ADD COLUMN agent_id TEXT');
}
}
if (!applied) {
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(27, new Date().toISOString());
}
}
/** /**
* Update the memory session ID for a session * Update the memory session ID for a session
* Called by SDKAgent when it captures the session ID from the first SDK message * Called by SDKAgent when it captures the session ID from the first SDK message
@@ -1755,6 +1812,8 @@ export class SessionStore {
concepts: string[]; concepts: string[];
files_read: string[]; files_read: string[];
files_modified: string[]; files_modified: string[];
agent_type?: string | null;
agent_id?: string | null;
}, },
promptNumber?: number, promptNumber?: number,
discoveryTokens: number = 0, discoveryTokens: number = 0,
@@ -1775,9 +1834,9 @@ export class SessionStore {
const stmt = this.db.prepare(` const stmt = this.db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch, files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch,
generated_by_model) generated_by_model)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
const result = stmt.run( const result = stmt.run(
@@ -1793,6 +1852,8 @@ export class SessionStore {
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch, timestampEpoch,
@@ -1884,6 +1945,8 @@ export class SessionStore {
concepts: string[]; concepts: string[];
files_read: string[]; files_read: string[];
files_modified: string[]; files_modified: string[];
agent_type?: string | null;
agent_id?: string | null;
}>, }>,
summary: { summary: {
request: string; request: string;
@@ -1910,9 +1973,9 @@ export class SessionStore {
const obsStmt = this.db.prepare(` const obsStmt = this.db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch, files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch,
generated_by_model) generated_by_model)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
for (const observation of observations) { for (const observation of observations) {
@@ -1937,6 +2000,8 @@ export class SessionStore {
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch, timestampEpoch,
@@ -2014,6 +2079,8 @@ export class SessionStore {
concepts: string[]; concepts: string[];
files_read: string[]; files_read: string[];
files_modified: string[]; files_modified: string[];
agent_type?: string | null;
agent_id?: string | null;
}>, }>,
summary: { summary: {
request: string; request: string;
@@ -2042,9 +2109,9 @@ export class SessionStore {
const obsStmt = this.db.prepare(` const obsStmt = this.db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch, files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch,
generated_by_model) generated_by_model)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
for (const observation of observations) { for (const observation of observations) {
@@ -2069,6 +2136,8 @@ export class SessionStore {
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch, timestampEpoch,
@@ -2269,8 +2338,12 @@ export class SessionStore {
startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch; startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch;
endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch; endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch;
} catch (err: any) { } catch (err) {
logger.error('DB', 'Error getting boundary observations', undefined, { error: err, project }); if (err instanceof Error) {
logger.error('DB', 'Error getting boundary observations', { project }, err);
} else {
logger.error('DB', 'Error getting boundary observations with non-Error', {}, new Error(String(err)));
}
return { observations: [], sessions: [], prompts: [] }; return { observations: [], sessions: [], prompts: [] };
} }
} else { } else {
@@ -2301,8 +2374,12 @@ export class SessionStore {
startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch; startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch;
endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch; endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch;
} catch (err: any) { } catch (err) {
logger.error('DB', 'Error getting boundary timestamps', undefined, { error: err, project }); if (err instanceof Error) {
logger.error('DB', 'Error getting boundary timestamps', { project }, err);
} else {
logger.error('DB', 'Error getting boundary timestamps with non-Error', {}, new Error(String(err)));
}
return { observations: [], sessions: [], prompts: [] }; return { observations: [], sessions: [], prompts: [] };
} }
} }
@@ -2629,6 +2706,8 @@ export class SessionStore {
discovery_tokens: number; discovery_tokens: number;
created_at: string; created_at: string;
created_at_epoch: number; created_at_epoch: number;
agent_type?: string | null;
agent_id?: string | null;
}): { imported: boolean; id: number } { }): { imported: boolean; id: number } {
// Check if observation already exists // Check if observation already exists
const existing = this.db.prepare(` const existing = this.db.prepare(`
@@ -2644,8 +2723,9 @@ export class SessionStore {
INSERT INTO observations ( INSERT INTO observations (
memory_session_id, project, text, type, title, subtitle, memory_session_id, project, text, type, title, subtitle,
facts, narrative, concepts, files_read, files_modified, facts, narrative, concepts, files_read, files_modified,
prompt_number, discovery_tokens, created_at, created_at_epoch prompt_number, discovery_tokens, agent_type, agent_id,
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) created_at, created_at_epoch
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
const result = stmt.run( const result = stmt.run(
@@ -2662,6 +2742,8 @@ export class SessionStore {
obs.files_modified, obs.files_modified,
obs.prompt_number, obs.prompt_number,
obs.discovery_tokens || 0, obs.discovery_tokens || 0,
obs.agent_type ?? null,
obs.agent_id ?? null,
obs.created_at, obs.created_at,
obs.created_at_epoch obs.created_at_epoch
); );
src/services/sqlite/import/bulk.ts
+7 -2
View File
@@ -141,6 +141,8 @@ export function importObservation(
discovery_tokens: number; discovery_tokens: number;
created_at: string; created_at: string;
created_at_epoch: number; created_at_epoch: number;
agent_type?: string | null;
agent_id?: string | null;
} }
): ImportResult { ): ImportResult {
// Check if observation already exists // Check if observation already exists
@@ -163,8 +165,9 @@ export function importObservation(
INSERT INTO observations ( INSERT INTO observations (
memory_session_id, project, text, type, title, subtitle, memory_session_id, project, text, type, title, subtitle,
facts, narrative, concepts, files_read, files_modified, facts, narrative, concepts, files_read, files_modified,
prompt_number, discovery_tokens, created_at, created_at_epoch prompt_number, discovery_tokens, agent_type, agent_id,
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) created_at, created_at_epoch
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
const result = stmt.run( const result = stmt.run(
@@ -181,6 +184,8 @@ export function importObservation(
obs.files_modified, obs.files_modified,
obs.prompt_number, obs.prompt_number,
obs.discovery_tokens || 0, obs.discovery_tokens || 0,
obs.agent_type ?? null,
obs.agent_id ?? null,
obs.created_at, obs.created_at,
obs.created_at_epoch obs.created_at_epoch
); );
src/services/sqlite/migrations.ts
+60 -3
View File
@@ -1,5 +1,6 @@
import { Database } from 'bun:sqlite'; import { Database } from 'bun:sqlite';
import { Migration } from './Database.js'; import { Migration } from './Database.js';
import { logger } from '../../utils/logger.js';
// Re-export MigrationRunner for SessionStore migration extraction // Re-export MigrationRunner for SessionStore migration extraction
export { MigrationRunner } from './migrations/runner.js'; export { MigrationRunner } from './migrations/runner.js';
@@ -377,8 +378,8 @@ export const migration006: Migration = {
try { try {
db.run('CREATE VIRTUAL TABLE _fts5_probe USING fts5(test_column)'); db.run('CREATE VIRTUAL TABLE _fts5_probe USING fts5(test_column)');
db.run('DROP TABLE _fts5_probe'); db.run('DROP TABLE _fts5_probe');
} catch { } catch (error) {
console.log('⚠️ FTS5 not available on this platform — skipping FTS migration (search uses ChromaDB)'); logger.warn('DB', 'FTS5 not available on this platform — skipping FTS migration (search uses ChromaDB)', {}, error instanceof Error ? error : undefined);
return; return;
} }
@@ -572,6 +573,61 @@ export const migration009: Migration = {
} }
}; };
/**
* Migration 010: Label observations (and their queue rows) with the subagent identity.
*
* Claude Code hooks that fire inside a subagent carry agent_id and agent_type on the
* stdin payload. These flow hook → worker → pending_messages → SDK storage so that
* observation rows can be attributed to the originating subagent. Main-session rows
* keep NULL for both columns.
*/
export const migration010: Migration = {
version: 27,
up: (db: Database) => {
const added: string[] = [];
const obsColumns = db.prepare('PRAGMA table_info(observations)').all() as Array<{ name: string }>;
const obsHasAgentType = obsColumns.some(c => c.name === 'agent_type');
const obsHasAgentId = obsColumns.some(c => c.name === 'agent_id');
if (!obsHasAgentType) {
db.run('ALTER TABLE observations ADD COLUMN agent_type TEXT');
added.push('observations.agent_type');
}
if (!obsHasAgentId) {
db.run('ALTER TABLE observations ADD COLUMN agent_id TEXT');
added.push('observations.agent_id');
}
db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_type ON observations(agent_type)');
db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_id ON observations(agent_id)');
// Also thread the same fields through the pending_messages queue so the label
// survives worker restarts between enqueue and SDK-agent processing.
const pendingColumns = db.prepare('PRAGMA table_info(pending_messages)').all() as Array<{ name: string }>;
if (pendingColumns.length > 0) {
const pendingHasAgentType = pendingColumns.some(c => c.name === 'agent_type');
const pendingHasAgentId = pendingColumns.some(c => c.name === 'agent_id');
if (!pendingHasAgentType) {
db.run('ALTER TABLE pending_messages ADD COLUMN agent_type TEXT');
added.push('pending_messages.agent_type');
}
if (!pendingHasAgentId) {
db.run('ALTER TABLE pending_messages ADD COLUMN agent_id TEXT');
added.push('pending_messages.agent_id');
}
}
logger.debug(
'DB',
added.length > 0
? `[migration010] Added columns: ${added.join(', ')}`
: '[migration010] Subagent identity columns already present; ensured indexes'
);
},
down: (_db: Database) => {
// SQLite DROP COLUMN not fully supported; no-op
}
};
/** /**
* All migrations in order * All migrations in order
*/ */
@@ -584,5 +640,6 @@ export const migrations: Migration[] = [
migration006, migration006,
migration007, migration007,
migration008, migration008,
migration009 migration009,
migration010
]; ];
src/services/sqlite/migrations/runner.ts
+96 -33
View File
@@ -38,6 +38,7 @@ export class MigrationRunner {
this.createObservationFeedbackTable(); this.createObservationFeedbackTable();
this.addSessionPlatformSourceColumn(); this.addSessionPlatformSourceColumn();
this.ensureMergedIntoProjectColumns(); this.ensureMergedIntoProjectColumns();
this.addObservationSubagentColumns();
} }
/** /**
@@ -418,6 +419,25 @@ export class MigrationRunner {
// Create FTS5 virtual table — skip if FTS5 is unavailable (e.g., Bun on Windows #791). // Create FTS5 virtual table — skip if FTS5 is unavailable (e.g., Bun on Windows #791).
// The user_prompts table itself is still created; only FTS indexing is skipped. // The user_prompts table itself is still created; only FTS indexing is skipped.
try { try {
this.createUserPromptsFTS();
} catch (ftsError) {
logger.warn('DB', 'FTS5 not available — user_prompts_fts skipped (search uses ChromaDB)', {}, ftsError instanceof Error ? ftsError : new Error(String(ftsError)));
}
// Commit transaction
this.db.run('COMMIT');
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
logger.debug('DB', 'Successfully created user_prompts table');
}
/**
* Create FTS5 virtual table and sync triggers for user_prompts.
* Extracted from createUserPromptsTable to keep try block small.
*/
private createUserPromptsFTS(): void {
this.db.run(` this.db.run(`
CREATE VIRTUAL TABLE user_prompts_fts USING fts5( CREATE VIRTUAL TABLE user_prompts_fts USING fts5(
prompt_text, prompt_text,
@@ -426,7 +446,6 @@ export class MigrationRunner {
); );
`); `);
// Create triggers to sync FTS5
this.db.run(` this.db.run(`
CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN CREATE TRIGGER user_prompts_ai AFTER INSERT ON user_prompts BEGIN
INSERT INTO user_prompts_fts(rowid, prompt_text) INSERT INTO user_prompts_fts(rowid, prompt_text)
@@ -445,17 +464,6 @@ export class MigrationRunner {
VALUES (new.id, new.prompt_text); VALUES (new.id, new.prompt_text);
END; END;
`); `);
} catch (ftsError) {
logger.warn('DB', 'FTS5 not available — user_prompts_fts skipped (search uses ChromaDB)', {}, ftsError as Error);
}
// Commit transaction
this.db.run('COMMIT');
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(10, new Date().toISOString());
logger.debug('DB', 'Successfully created user_prompts table');
} }
/** /**
@@ -658,9 +666,29 @@ export class MigrationRunner {
this.db.run('BEGIN TRANSACTION'); this.db.run('BEGIN TRANSACTION');
try { try {
// =================================== this.recreateObservationsWithUpdateCascade();
// 1. Recreate observations table this.recreateSessionSummariesWithUpdateCascade();
// ===================================
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(21, new Date().toISOString());
this.db.run('COMMIT');
this.db.run('PRAGMA foreign_keys = ON');
logger.debug('DB', 'Successfully added ON UPDATE CASCADE to FK constraints');
} catch (error) {
this.db.run('ROLLBACK');
this.db.run('PRAGMA foreign_keys = ON');
if (error instanceof Error) {
throw error;
}
throw new Error(`Migration 21 failed: ${String(error)}`);
}
}
/**
* Recreate observations table with ON UPDATE CASCADE FK constraint.
* Called within a transaction by addOnUpdateCascadeToForeignKeys.
*/
private recreateObservationsWithUpdateCascade(): void {
// Drop FTS triggers first (they reference the observations table) // Drop FTS triggers first (they reference the observations table)
this.db.run('DROP TRIGGER IF EXISTS observations_ai'); this.db.run('DROP TRIGGER IF EXISTS observations_ai');
this.db.run('DROP TRIGGER IF EXISTS observations_ad'); this.db.run('DROP TRIGGER IF EXISTS observations_ad');
@@ -702,7 +730,6 @@ export class MigrationRunner {
this.db.run('DROP TABLE observations'); this.db.run('DROP TABLE observations');
this.db.run('ALTER TABLE observations_new RENAME TO observations'); this.db.run('ALTER TABLE observations_new RENAME TO observations');
// Recreate indexes
this.db.run(` this.db.run(`
CREATE INDEX idx_observations_sdk_session ON observations(memory_session_id); CREATE INDEX idx_observations_sdk_session ON observations(memory_session_id);
CREATE INDEX idx_observations_project ON observations(project); CREATE INDEX idx_observations_project ON observations(project);
@@ -732,10 +759,13 @@ export class MigrationRunner {
END; END;
`); `);
} }
}
// =================================== /**
// 2. Recreate session_summaries table * Recreate session_summaries table with ON UPDATE CASCADE FK constraint.
// =================================== * Called within a transaction by addOnUpdateCascadeToForeignKeys.
*/
private recreateSessionSummariesWithUpdateCascade(): void {
// Clean up leftover temp table from a previously-crashed run // Clean up leftover temp table from a previously-crashed run
this.db.run('DROP TABLE IF EXISTS session_summaries_new'); this.db.run('DROP TABLE IF EXISTS session_summaries_new');
@@ -776,7 +806,6 @@ export class MigrationRunner {
this.db.run('DROP TABLE session_summaries'); this.db.run('DROP TABLE session_summaries');
this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries'); this.db.run('ALTER TABLE session_summaries_new RENAME TO session_summaries');
// Recreate indexes
this.db.run(` this.db.run(`
CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(memory_session_id); CREATE INDEX idx_session_summaries_sdk_session ON session_summaries(memory_session_id);
CREATE INDEX idx_session_summaries_project ON session_summaries(project); CREATE INDEX idx_session_summaries_project ON session_summaries(project);
@@ -805,19 +834,6 @@ export class MigrationRunner {
END; END;
`); `);
} }
// Record migration
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(21, new Date().toISOString());
this.db.run('COMMIT');
this.db.run('PRAGMA foreign_keys = ON');
logger.debug('DB', 'Successfully added ON UPDATE CASCADE to FK constraints');
} catch (error) {
this.db.run('ROLLBACK');
this.db.run('PRAGMA foreign_keys = ON');
throw error;
}
} }
/** /**
@@ -952,4 +968,51 @@ export class MigrationRunner {
'CREATE INDEX IF NOT EXISTS idx_summaries_merged_into ON session_summaries(merged_into_project)' 'CREATE INDEX IF NOT EXISTS idx_summaries_merged_into ON session_summaries(merged_into_project)'
); );
} }
/**
* Add agent_type and agent_id columns to observations and pending_messages (migration 27).
*
* Labels observation rows with the originating Claude Code subagent identity so
* downstream queries can distinguish main-session work from subagent work.
* Main-session rows keep NULL for both columns.
*
* Also threads the same columns through pending_messages so the label survives
* between enqueue (hook) and SDK-agent processing (which re-inserts into observations).
*/
private addObservationSubagentColumns(): void {
const applied = this.db.prepare('SELECT version FROM schema_versions WHERE version = ?').get(27) as SchemaVersion | undefined;
const obsCols = this.db.query('PRAGMA table_info(observations)').all() as TableColumnInfo[];
const obsHasAgentType = obsCols.some(c => c.name === 'agent_type');
const obsHasAgentId = obsCols.some(c => c.name === 'agent_id');
if (!obsHasAgentType) {
this.db.run('ALTER TABLE observations ADD COLUMN agent_type TEXT');
logger.debug('DB', 'Added agent_type column to observations table');
}
if (!obsHasAgentId) {
this.db.run('ALTER TABLE observations ADD COLUMN agent_id TEXT');
logger.debug('DB', 'Added agent_id column to observations table');
}
this.db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_type ON observations(agent_type)');
this.db.run('CREATE INDEX IF NOT EXISTS idx_observations_agent_id ON observations(agent_id)');
const pendingCols = this.db.query('PRAGMA table_info(pending_messages)').all() as TableColumnInfo[];
if (pendingCols.length > 0) {
const pendingHasAgentType = pendingCols.some(c => c.name === 'agent_type');
const pendingHasAgentId = pendingCols.some(c => c.name === 'agent_id');
if (!pendingHasAgentType) {
this.db.run('ALTER TABLE pending_messages ADD COLUMN agent_type TEXT');
logger.debug('DB', 'Added agent_type column to pending_messages table');
}
if (!pendingHasAgentId) {
this.db.run('ALTER TABLE pending_messages ADD COLUMN agent_id TEXT');
logger.debug('DB', 'Added agent_id column to pending_messages table');
}
}
if (!applied) {
this.db.prepare('INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)').run(27, new Date().toISOString());
}
}
} }
src/services/sqlite/observations/files.ts
+1
View File
@@ -18,6 +18,7 @@ export function parseFileList(value: string | null | undefined): string[] {
const parsed = JSON.parse(value); const parsed = JSON.parse(value);
return Array.isArray(parsed) ? parsed : [String(parsed)]; return Array.isArray(parsed) ? parsed : [String(parsed)];
} catch { } catch {
// [ANTI-PATTERN IGNORED]: legacy bare-path strings are expected input, not errors
return [value]; return [value];
} }
} }
src/services/sqlite/observations/store.ts
+6 -2
View File
@@ -15,6 +15,8 @@ const DEDUP_WINDOW_MS = 30_000;
/** /**
* Compute a short content hash for deduplication. * Compute a short content hash for deduplication.
* Uses (memory_session_id, title, narrative) as the semantic identity of an observation. * Uses (memory_session_id, title, narrative) as the semantic identity of an observation.
* Subagent fields (agent_type, agent_id) are intentionally excluded so the same work
* described once by a subagent and once by its parent deduplicates across contexts.
*/ */
export function computeObservationContentHash( export function computeObservationContentHash(
memorySessionId: string, memorySessionId: string,
@@ -75,8 +77,8 @@ export function storeObservation(
const stmt = db.prepare(` const stmt = db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch) files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
const result = stmt.run( const result = stmt.run(
@@ -92,6 +94,8 @@ export function storeObservation(
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch timestampEpoch
src/services/sqlite/observations/types.ts
+3
View File
@@ -16,6 +16,9 @@ export interface ObservationInput {
concepts: string[]; concepts: string[];
files_read: string[]; files_read: string[];
files_modified: string[]; files_modified: string[];
// Claude Code subagent identity — NULL for main-session rows.
agent_type?: string | null;
agent_id?: string | null;
} }
/** /**
src/services/sqlite/timeline/queries.ts
+6 -4
View File
@@ -111,8 +111,9 @@ export function getTimelineAroundObservation(
startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch; startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch;
endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch; endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch;
} catch (err: any) { } catch (err) {
logger.error('DB', 'Error getting boundary observations', undefined, { error: err, project }); const normalizedError = err instanceof Error ? err : new Error(String(err));
logger.error('DB', 'Error getting boundary observations', { project }, normalizedError);
return { observations: [], sessions: [], prompts: [] }; return { observations: [], sessions: [], prompts: [] };
} }
} else { } else {
@@ -143,8 +144,9 @@ export function getTimelineAroundObservation(
startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch; startEpoch = beforeRecords.length > 0 ? beforeRecords[beforeRecords.length - 1].created_at_epoch : anchorEpoch;
endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch; endEpoch = afterRecords.length > 0 ? afterRecords[afterRecords.length - 1].created_at_epoch : anchorEpoch;
} catch (err: any) { } catch (err) {
logger.error('DB', 'Error getting boundary timestamps', undefined, { error: err, project }); const normalizedError = err instanceof Error ? err : new Error(String(err));
logger.error('DB', 'Error getting boundary timestamps', { project }, normalizedError);
return { observations: [], sessions: [], prompts: [] }; return { observations: [], sessions: [], prompts: [] };
} }
} }
src/services/sqlite/transactions.ts
+8 -4
View File
@@ -68,8 +68,8 @@ export function storeObservationsAndMarkComplete(
const obsStmt = db.prepare(` const obsStmt = db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch) files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
for (const observation of observations) { for (const observation of observations) {
@@ -93,6 +93,8 @@ export function storeObservationsAndMarkComplete(
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch timestampEpoch
@@ -187,8 +189,8 @@ export function storeObservations(
const obsStmt = db.prepare(` const obsStmt = db.prepare(`
INSERT INTO observations INSERT INTO observations
(memory_session_id, project, type, title, subtitle, facts, narrative, concepts, (memory_session_id, project, type, title, subtitle, facts, narrative, concepts,
files_read, files_modified, prompt_number, discovery_tokens, content_hash, created_at, created_at_epoch) files_read, files_modified, prompt_number, discovery_tokens, agent_type, agent_id, content_hash, created_at, created_at_epoch)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`); `);
for (const observation of observations) { for (const observation of observations) {
@@ -212,6 +214,8 @@ export function storeObservations(
JSON.stringify(observation.files_modified), JSON.stringify(observation.files_modified),
promptNumber || null, promptNumber || null,
discoveryTokens, discoveryTokens,
observation.agent_type ?? null,
observation.agent_id ?? null,
contentHash, contentHash,
timestampIso, timestampIso,
timestampEpoch timestampEpoch
src/services/sync/ChromaMcpManager.ts
+29 -5
View File
@@ -78,6 +78,11 @@ export class ChromaMcpManager {
await this.connecting; await this.connecting;
} catch (error) { } catch (error) {
this.lastConnectionFailureTimestamp = Date.now(); this.lastConnectionFailureTimestamp = Date.now();
if (error instanceof Error) {
logger.error('CHROMA_MCP', 'Connection attempt failed', {}, error);
} else {
logger.error('CHROMA_MCP', 'Connection attempt failed with non-Error value', { error: String(error) });
}
throw error; throw error;
} finally { } finally {
this.connecting = null; this.connecting = null;
@@ -307,9 +312,15 @@ export class ChromaMcpManager {
// Try JSON parse first; if it fails, return the raw text for non-error responses. // Try JSON parse first; if it fails, return the raw text for non-error responses.
try { try {
return JSON.parse(firstTextContent.text); return JSON.parse(firstTextContent.text);
} catch { } catch (parseError: unknown) {
// Plain text response (e.g. "Successfully created collection cm__foo") // Plain text response (e.g. "Successfully created collection cm__foo")
// Return null for void-like success messages, callers don't need the text // Return null for void-like success messages, callers don't need the text
if (parseError instanceof Error) {
logger.debug('CHROMA_MCP', 'Non-JSON response from tool, returning null', {
toolName,
textPreview: firstTextContent.text.slice(0, 100)
});
}
return null; return null;
} }
} }
@@ -322,7 +333,10 @@ export class ChromaMcpManager {
try { try {
await this.callTool('chroma_list_collections', { limit: 1 }); await this.callTool('chroma_list_collections', { limit: 1 });
return true; return true;
} catch { } catch (error) {
logger.warn('CHROMA_MCP', 'Health check failed', {
error: error instanceof Error ? error.message : String(error)
});
return false; return false;
} }
} }
@@ -342,7 +356,11 @@ export class ChromaMcpManager {
try { try {
await this.client.close(); await this.client.close();
} catch (error) { } catch (error) {
logger.debug('CHROMA_MCP', 'Error during client close (subprocess may already be dead)', {}, error as Error); if (error instanceof Error) {
logger.debug('CHROMA_MCP', 'Error during client close (subprocess may already be dead)', {}, error);
} else {
logger.debug('CHROMA_MCP', 'Error during client close (subprocess may already be dead)', { error: String(error) });
}
} }
getSupervisor().unregisterProcess(CHROMA_SUPERVISOR_ID); getSupervisor().unregisterProcess(CHROMA_SUPERVISOR_ID);
@@ -394,7 +412,10 @@ export class ChromaMcpManager {
'uvx --with certifi python -c "import certifi; print(certifi.where())"', 'uvx --with certifi python -c "import certifi; print(certifi.where())"',
{ encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'], timeout: 10000 } { encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'], timeout: 10000 }
).trim(); ).trim();
} catch { } catch (error) {
logger.debug('CHROMA_MCP', 'Failed to resolve certifi path via uvx', {
error: error instanceof Error ? error.message : String(error)
});
return undefined; return undefined;
} }
@@ -408,7 +429,10 @@ export class ChromaMcpManager {
'security find-certificate -a -c "Zscaler" -p /Library/Keychains/System.keychain', 'security find-certificate -a -c "Zscaler" -p /Library/Keychains/System.keychain',
{ encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'], timeout: 5000 } { encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'], timeout: 5000 }
); );
} catch { } catch (error) {
logger.debug('CHROMA_MCP', 'No Zscaler certificate found in system keychain', {
error: error instanceof Error ? error.message : String(error)
});
return undefined; return undefined;
} }
src/services/sync/ChromaSync.ts
+123 -70
View File
@@ -563,14 +563,53 @@ export class ChromaSync {
const db = new SessionStore(); const db = new SessionStore();
try { try {
// Build exclusion list for observations await this.runBackfillPipeline(db, backfillProject, existing);
// Filter to validated positive integers before interpolating into SQL } catch (error) {
const existingObsIds = Array.from(existing.observations).filter(id => Number.isInteger(id) && id > 0); logger.error('CHROMA_SYNC', 'Backfill failed', { project: backfillProject }, error instanceof Error ? error : new Error(String(error)));
throw new Error(`Backfill failed: ${error instanceof Error ? error.message : String(error)}`);
} finally {
db.close();
}
}
private async runBackfillPipeline(
db: SessionStore,
backfillProject: string,
existing: { observations: Set<number>; summaries: Set<number>; prompts: Set<number> }
): Promise<void> {
const allDocs = await this.backfillObservations(db, backfillProject, existing.observations);
const summaryDocs = await this.backfillSummaries(db, backfillProject, existing.summaries);
const promptDocs = await this.backfillPrompts(db, backfillProject, existing.prompts);
logger.info('CHROMA_SYNC', 'Smart backfill complete', {
project: backfillProject,
synced: {
observationDocs: allDocs.length,
summaryDocs: summaryDocs.length,
promptDocs: promptDocs.length
},
skipped: {
observations: existing.observations.size,
summaries: existing.summaries.size,
prompts: existing.prompts.size
}
});
}
/**
* Backfill observations missing from Chroma for a given project.
* Returns the formatted documents that were synced.
*/
private async backfillObservations(
db: SessionStore,
backfillProject: string,
existingObservationIds: Set<number>
): Promise<ChromaDocument[]> {
const existingObsIds = Array.from(existingObservationIds).filter(id => Number.isInteger(id) && id > 0);
const obsExclusionClause = existingObsIds.length > 0 const obsExclusionClause = existingObsIds.length > 0
? `AND id NOT IN (${existingObsIds.join(',')})` ? `AND id NOT IN (${existingObsIds.join(',')})`
: ''; : '';
// Get only observations missing from Chroma
const observations = db.db.prepare(` const observations = db.db.prepare(`
SELECT * FROM observations SELECT * FROM observations
WHERE project = ? ${obsExclusionClause} WHERE project = ? ${obsExclusionClause}
@@ -584,17 +623,15 @@ export class ChromaSync {
logger.info('CHROMA_SYNC', 'Backfilling observations', { logger.info('CHROMA_SYNC', 'Backfilling observations', {
project: backfillProject, project: backfillProject,
missing: observations.length, missing: observations.length,
existing: existing.observations.size, existing: existingObservationIds.size,
total: totalObsCount.count total: totalObsCount.count
}); });
// Format all observation documents
const allDocs: ChromaDocument[] = []; const allDocs: ChromaDocument[] = [];
for (const obs of observations) { for (const obs of observations) {
allDocs.push(...this.formatObservationDocs(obs)); allDocs.push(...this.formatObservationDocs(obs));
} }
// Sync in batches
for (let i = 0; i < allDocs.length; i += this.BATCH_SIZE) { for (let i = 0; i < allDocs.length; i += this.BATCH_SIZE) {
const batch = allDocs.slice(i, i + this.BATCH_SIZE); const batch = allDocs.slice(i, i + this.BATCH_SIZE);
await this.addDocuments(batch); await this.addDocuments(batch);
@@ -605,13 +642,23 @@ export class ChromaSync {
}); });
} }
// Build exclusion list for summaries return allDocs;
const existingSummaryIds = Array.from(existing.summaries).filter(id => Number.isInteger(id) && id > 0); }
/**
* Backfill summaries missing from Chroma for a given project.
* Returns the formatted documents that were synced.
*/
private async backfillSummaries(
db: SessionStore,
backfillProject: string,
existingSummaryIdSet: Set<number>
): Promise<ChromaDocument[]> {
const existingSummaryIds = Array.from(existingSummaryIdSet).filter(id => Number.isInteger(id) && id > 0);
const summaryExclusionClause = existingSummaryIds.length > 0 const summaryExclusionClause = existingSummaryIds.length > 0
? `AND id NOT IN (${existingSummaryIds.join(',')})` ? `AND id NOT IN (${existingSummaryIds.join(',')})`
: ''; : '';
// Get only summaries missing from Chroma
const summaries = db.db.prepare(` const summaries = db.db.prepare(`
SELECT * FROM session_summaries SELECT * FROM session_summaries
WHERE project = ? ${summaryExclusionClause} WHERE project = ? ${summaryExclusionClause}
@@ -625,17 +672,15 @@ export class ChromaSync {
logger.info('CHROMA_SYNC', 'Backfilling summaries', { logger.info('CHROMA_SYNC', 'Backfilling summaries', {
project: backfillProject, project: backfillProject,
missing: summaries.length, missing: summaries.length,
existing: existing.summaries.size, existing: existingSummaryIdSet.size,
total: totalSummaryCount.count total: totalSummaryCount.count
}); });
// Format all summary documents
const summaryDocs: ChromaDocument[] = []; const summaryDocs: ChromaDocument[] = [];
for (const summary of summaries) { for (const summary of summaries) {
summaryDocs.push(...this.formatSummaryDocs(summary)); summaryDocs.push(...this.formatSummaryDocs(summary));
} }
// Sync in batches
for (let i = 0; i < summaryDocs.length; i += this.BATCH_SIZE) { for (let i = 0; i < summaryDocs.length; i += this.BATCH_SIZE) {
const batch = summaryDocs.slice(i, i + this.BATCH_SIZE); const batch = summaryDocs.slice(i, i + this.BATCH_SIZE);
await this.addDocuments(batch); await this.addDocuments(batch);
@@ -646,13 +691,23 @@ export class ChromaSync {
}); });
} }
// Build exclusion list for prompts return summaryDocs;
const existingPromptIds = Array.from(existing.prompts).filter(id => Number.isInteger(id) && id > 0); }
/**
* Backfill user prompts missing from Chroma for a given project.
* Returns the formatted documents that were synced.
*/
private async backfillPrompts(
db: SessionStore,
backfillProject: string,
existingPromptIdSet: Set<number>
): Promise<ChromaDocument[]> {
const existingPromptIds = Array.from(existingPromptIdSet).filter(id => Number.isInteger(id) && id > 0);
const promptExclusionClause = existingPromptIds.length > 0 const promptExclusionClause = existingPromptIds.length > 0
? `AND up.id NOT IN (${existingPromptIds.join(',')})` ? `AND up.id NOT IN (${existingPromptIds.join(',')})`
: ''; : '';
// Get only user prompts missing from Chroma
const prompts = db.db.prepare(` const prompts = db.db.prepare(`
SELECT SELECT
up.*, up.*,
@@ -674,17 +729,15 @@ export class ChromaSync {
logger.info('CHROMA_SYNC', 'Backfilling user prompts', { logger.info('CHROMA_SYNC', 'Backfilling user prompts', {
project: backfillProject, project: backfillProject,
missing: prompts.length, missing: prompts.length,
existing: existing.prompts.size, existing: existingPromptIdSet.size,
total: totalPromptCount.count total: totalPromptCount.count
}); });
// Format all prompt documents
const promptDocs: ChromaDocument[] = []; const promptDocs: ChromaDocument[] = [];
for (const prompt of prompts) { for (const prompt of prompts) {
promptDocs.push(this.formatUserPromptDoc(prompt)); promptDocs.push(this.formatUserPromptDoc(prompt));
} }
// Sync in batches
for (let i = 0; i < promptDocs.length; i += this.BATCH_SIZE) { for (let i = 0; i < promptDocs.length; i += this.BATCH_SIZE) {
const batch = promptDocs.slice(i, i + this.BATCH_SIZE); const batch = promptDocs.slice(i, i + this.BATCH_SIZE);
await this.addDocuments(batch); await this.addDocuments(batch);
@@ -695,26 +748,7 @@ export class ChromaSync {
}); });
} }
logger.info('CHROMA_SYNC', 'Smart backfill complete', { return promptDocs;
project: backfillProject,
synced: {
observationDocs: allDocs.length,
summaryDocs: summaryDocs.length,
promptDocs: promptDocs.length
},
skipped: {
observations: existing.observations.size,
summaries: existing.summaries.size,
prompts: existing.prompts.size
}
});
} catch (error) {
logger.error('CHROMA_SYNC', 'Backfill failed', { project: backfillProject }, error as Error);
throw new Error(`Backfill failed: ${error instanceof Error ? error.message : String(error)}`);
} finally {
db.close();
}
} }
/** /**
@@ -728,27 +762,58 @@ export class ChromaSync {
): Promise<{ ids: number[]; distances: number[]; metadatas: any[] }> { ): Promise<{ ids: number[]; distances: number[]; metadatas: any[] }> {
await this.ensureCollectionExists(); await this.ensureCollectionExists();
let results: any;
try { try {
const chromaMcp = ChromaMcpManager.getInstance(); const chromaMcp = ChromaMcpManager.getInstance();
const results = await chromaMcp.callTool('chroma_query_documents', { results = await chromaMcp.callTool('chroma_query_documents', {
collection_name: this.collectionName, collection_name: this.collectionName,
query_texts: [query], query_texts: [query],
n_results: limit, n_results: limit,
...(whereFilter && { where: whereFilter }), ...(whereFilter && { where: whereFilter }),
include: ['documents', 'metadatas', 'distances'] include: ['documents', 'metadatas', 'distances']
}) as any; });
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
// chroma-mcp surfaces connection failures as Error messages with no structured
// error codes or typed error classes. String matching is the only way to distinguish
// transient connection errors (which need collection state reset) from semantic query errors.
const isConnectionError =
errorMessage.includes('ECONNREFUSED') || // [ANTI-PATTERN IGNORED]: chroma-mcp has no typed error classes, string matching is the only option
errorMessage.includes('ENOTFOUND') || // [ANTI-PATTERN IGNORED]: chroma-mcp has no typed error classes, string matching is the only option
errorMessage.includes('fetch failed') || // [ANTI-PATTERN IGNORED]: chroma-mcp has no typed error classes, string matching is the only option
errorMessage.includes('subprocess closed') || // [ANTI-PATTERN IGNORED]: chroma-mcp has no typed error classes, string matching is the only option
errorMessage.includes('timed out'); // [ANTI-PATTERN IGNORED]: chroma-mcp has no typed error classes, string matching is the only option
if (isConnectionError) {
// Reset collection state so next call attempts reconnect
this.collectionCreated = false;
logger.error('CHROMA_SYNC', 'Connection lost during query',
{ project: this.project, query }, error as Error);
throw new Error(`Chroma query failed - connection lost: ${errorMessage}`);
}
logger.error('CHROMA_SYNC', 'Query failed', { project: this.project, query }, error as Error);
throw error;
}
return this.deduplicateQueryResults(results);
}
/**
* Deduplicate Chroma query results by SQLite ID.
* Multiple Chroma docs map to the same SQLite ID (one per field).
* Keeps the first (best-ranked) distance and metadata per SQLite ID.
*/
private deduplicateQueryResults(results: any): { ids: number[]; distances: number[]; metadatas: any[] } {
// chroma_query_documents returns nested arrays (one per query text) // chroma_query_documents returns nested arrays (one per query text)
// We always pass a single query text, so we access [0] // We always pass a single query text, so we access [0]
const ids: number[] = []; const ids: number[] = [];
const seen = new Set<number>(); const seen = new Set<string>();
const docIds = results?.ids?.[0] || []; const docIds = results?.ids?.[0] || [];
const rawMetadatas = results?.metadatas?.[0] || []; const rawMetadatas = results?.metadatas?.[0] || [];
const rawDistances = results?.distances?.[0] || []; const rawDistances = results?.distances?.[0] || [];
// Build deduplicated arrays that stay index-aligned:
// Multiple Chroma docs map to the same SQLite ID (one per field).
// Keep the first (best-ranked) distance and metadata per SQLite ID.
const metadatas: any[] = []; const metadatas: any[] = [];
const distances: number[] = []; const distances: number[] = [];
@@ -763,16 +828,22 @@ export class ChromaSync {
const promptMatch = docId.match(/prompt_(\d+)/); const promptMatch = docId.match(/prompt_(\d+)/);
let sqliteId: number | null = null; let sqliteId: number | null = null;
let entityType: string | null = null;
if (obsMatch) { if (obsMatch) {
sqliteId = parseInt(obsMatch[1], 10); sqliteId = parseInt(obsMatch[1], 10);
entityType = 'observation';
} else if (summaryMatch) { } else if (summaryMatch) {
sqliteId = parseInt(summaryMatch[1], 10); sqliteId = parseInt(summaryMatch[1], 10);
entityType = 'session_summary';
} else if (promptMatch) { } else if (promptMatch) {
sqliteId = parseInt(promptMatch[1], 10); sqliteId = parseInt(promptMatch[1], 10);
entityType = 'user_prompt';
} }
if (sqliteId !== null && !seen.has(sqliteId)) { if (sqliteId !== null && entityType) {
seen.add(sqliteId); const dedupeKey = `${entityType}:${sqliteId}`;
if (seen.has(dedupeKey)) continue;
seen.add(dedupeKey);
ids.push(sqliteId); ids.push(sqliteId);
metadatas.push(rawMetadatas[i] ?? null); metadatas.push(rawMetadatas[i] ?? null);
distances.push(rawDistances[i] ?? 0); distances.push(rawDistances[i] ?? 0);
@@ -780,28 +851,6 @@ export class ChromaSync {
} }
return { ids, distances, metadatas }; return { ids, distances, metadatas };
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
// Check for connection errors
const isConnectionError =
errorMessage.includes('ECONNREFUSED') ||
errorMessage.includes('ENOTFOUND') ||
errorMessage.includes('fetch failed') ||
errorMessage.includes('subprocess closed') ||
errorMessage.includes('timed out');
if (isConnectionError) {
// Reset collection state so next call attempts reconnect
this.collectionCreated = false;
logger.error('CHROMA_SYNC', 'Connection lost during query',
{ project: this.project, query }, error as Error);
throw new Error(`Chroma query failed - connection lost: ${errorMessage}`);
}
logger.error('CHROMA_SYNC', 'Query failed', { project: this.project, query }, error as Error);
throw error;
}
} }
/** /**
@@ -826,7 +875,11 @@ export class ChromaSync {
try { try {
await sync.ensureBackfilled(project); await sync.ensureBackfilled(project);
} catch (error) { } catch (error) {
logger.error('CHROMA_SYNC', `Backfill failed for project: ${project}`, {}, error as Error); if (error instanceof Error) {
logger.error('CHROMA_SYNC', `Backfill failed for project: ${project}`, {}, error);
} else {
logger.error('CHROMA_SYNC', `Backfill failed for project: ${project}`, { error: String(error) });
}
// Continue to next project — don't let one failure stop others // Continue to next project — don't let one failure stop others
} }
} }
src/services/transcripts/field-utils.ts
+3 -1
View File
@@ -1,3 +1,4 @@
import { logger } from '../../utils/logger.js';
import type { FieldSpec, MatchRule, TranscriptSchema, WatchTarget } from './types.js'; import type { FieldSpec, MatchRule, TranscriptSchema, WatchTarget } from './types.js';
interface ResolveContext { interface ResolveContext {
@@ -142,7 +143,8 @@ export function matchesRule(
try { try {
const regex = new RegExp(rule.regex); const regex = new RegExp(rule.regex);
return regex.test(String(value ?? '')); return regex.test(String(value ?? ''));
} catch { } catch (error: unknown) {
logger.debug('WORKER', 'Invalid regex in match rule', { regex: rule.regex }, error instanceof Error ? error : undefined);
return false; return false;
} }
} }
src/services/transcripts/processor.ts
+21 -16
View File
@@ -277,7 +277,8 @@ export class TranscriptEventProcessor {
if (!(trimmed.startsWith('{') || trimmed.startsWith('['))) return value; if (!(trimmed.startsWith('{') || trimmed.startsWith('['))) return value;
try { try {
return JSON.parse(trimmed); return JSON.parse(trimmed);
} catch { } catch (error: unknown) {
logger.debug('WORKER', 'Failed to parse JSON string', { length: trimmed.length }, error instanceof Error ? error : undefined);
return value; return value;
} }
} }
@@ -321,18 +322,19 @@ export class TranscriptEventProcessor {
if (!workerReady) return; if (!workerReady) return;
const lastAssistantMessage = session.lastAssistantMessage ?? ''; const lastAssistantMessage = session.lastAssistantMessage ?? '';
const requestBody = JSON.stringify({
contentSessionId: session.sessionId,
last_assistant_message: lastAssistantMessage,
platformSource: session.platformSource
});
try { try {
await workerHttpRequest('/api/sessions/summarize', { await workerHttpRequest('/api/sessions/summarize', {
method: 'POST', method: 'POST',
headers: { 'Content-Type': 'application/json' }, headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ body: requestBody
contentSessionId: session.sessionId,
last_assistant_message: lastAssistantMessage,
platformSource: session.platformSource
})
}); });
} catch (error) { } catch (error: unknown) {
logger.warn('TRANSCRIPT', 'Summary request failed', { logger.warn('TRANSCRIPT', 'Summary request failed', {
error: error instanceof Error ? error.message : String(error) error: error instanceof Error ? error.message : String(error)
}); });
@@ -352,22 +354,25 @@ export class TranscriptEventProcessor {
const context = getProjectContext(cwd); const context = getProjectContext(cwd);
const projectsParam = context.allProjects.join(','); const projectsParam = context.allProjects.join(',');
const contextUrl = `/api/context/inject?projects=${encodeURIComponent(projectsParam)}&platformSource=${encodeURIComponent(session.platformSource)}`;
const agentsPath = expandHomePath(watch.context.path ?? `${cwd}/AGENTS.md`);
let response: Awaited<ReturnType<typeof workerHttpRequest>>;
try { try {
const response = await workerHttpRequest( response = await workerHttpRequest(contextUrl);
`/api/context/inject?projects=${encodeURIComponent(projectsParam)}&platformSource=${encodeURIComponent(session.platformSource)}` } catch (error: unknown) {
); logger.warn('TRANSCRIPT', 'Failed to fetch AGENTS.md context', {
error: error instanceof Error ? error.message : String(error)
});
return;
}
if (!response.ok) return; if (!response.ok) return;
const content = (await response.text()).trim(); const content = (await response.text()).trim();
if (!content) return; if (!content) return;
const agentsPath = expandHomePath(watch.context.path ?? `${cwd}/AGENTS.md`);
writeAgentsMd(agentsPath, content); writeAgentsMd(agentsPath, content);
logger.debug('TRANSCRIPT', 'Updated AGENTS.md context', { agentsPath, watch: watch.name }); logger.debug('TRANSCRIPT', 'Updated AGENTS.md context', { agentsPath, watch: watch.name });
} catch (error) {
logger.warn('TRANSCRIPT', 'Failed to update AGENTS.md context', {
error: error instanceof Error ? error.message : String(error)
});
}
} }
} }
src/services/transcripts/watcher.ts
+16 -5
View File
@@ -43,7 +43,8 @@ class FileTailer {
let size = 0; let size = 0;
try { try {
size = statSync(this.filePath).size; size = statSync(this.filePath).size;
} catch { } catch (error: unknown) {
logger.debug('WORKER', 'Failed to stat transcript file', { file: this.filePath }, error instanceof Error ? error : undefined);
return; return;
} }
@@ -152,7 +153,8 @@ export class TranscriptWatcher {
return globSync(pattern, { nodir: true, absolute: true }); return globSync(pattern, { nodir: true, absolute: true });
} }
return [inputPath]; return [inputPath];
} catch { } catch (error: unknown) {
logger.debug('WORKER', 'Failed to stat watch path', { path: inputPath }, error instanceof Error ? error : undefined);
return []; return [];
} }
} }
@@ -180,7 +182,8 @@ export class TranscriptWatcher {
if (offset === 0 && watch.startAtEnd && initialDiscovery) { if (offset === 0 && watch.startAtEnd && initialDiscovery) {
try { try {
offset = statSync(filePath).size; offset = statSync(filePath).size;
} catch { } catch (error: unknown) {
logger.debug('WORKER', 'Failed to stat file for startAtEnd offset', { file: filePath }, error instanceof Error ? error : undefined);
offset = 0; offset = 0;
} }
} }
@@ -216,11 +219,19 @@ export class TranscriptWatcher {
try { try {
const entry = JSON.parse(line); const entry = JSON.parse(line);
await this.processor.processEntry(entry, watch, schema, sessionIdOverride ?? undefined); await this.processor.processEntry(entry, watch, schema, sessionIdOverride ?? undefined);
} catch (error) { } catch (error: unknown) {
if (error instanceof Error) {
logger.debug('TRANSCRIPT', 'Failed to parse transcript line', { logger.debug('TRANSCRIPT', 'Failed to parse transcript line', {
watch: watch.name, watch: watch.name,
file: basename(filePath) file: basename(filePath)
}, error as Error); }, error);
} else {
logger.warn('TRANSCRIPT', 'Failed to parse transcript line (non-Error thrown)', {
watch: watch.name,
file: basename(filePath),
error: String(error)
});
}
} }
} }
src/services/worker-service.ts
+116 -45
View File
@@ -289,11 +289,16 @@ export class WorkerService {
await Promise.race([this.initializationComplete, timeoutPromise]); await Promise.race([this.initializationComplete, timeoutPromise]);
next(); next();
} catch (error) { } catch (error) {
logger.error('HTTP', `Request to ${req.method} ${req.path} rejected — DB not initialized`, {}, error as Error); if (error instanceof Error) {
logger.error('WORKER', `Request to ${req.method} ${req.path} rejected — DB not initialized`, {}, error);
} else {
logger.error('WORKER', `Request to ${req.method} ${req.path} rejected — DB not initialized with non-Error`, {}, new Error(String(error)));
}
res.status(503).json({ res.status(503).json({
error: 'Service initializing', error: 'Service initializing',
message: 'Database is still initializing, please retry' message: 'Database is still initializing, please retry'
}); });
return;
} }
}); });
@@ -372,8 +377,18 @@ export class WorkerService {
// The worker daemon is spawned with cwd=marketplace-plugin-dir (not a git // The worker daemon is spawned with cwd=marketplace-plugin-dir (not a git
// repo), so we can't seed adoption with process.cwd(). Instead, discover // repo), so we can't seed adoption with process.cwd(). Instead, discover
// parent repos from recorded pending_messages.cwd values. // parent repos from recorded pending_messages.cwd values.
let adoptions: Awaited<ReturnType<typeof adoptMergedWorktreesForAllKnownRepos>> | null = null;
try { try {
const adoptions = await adoptMergedWorktreesForAllKnownRepos({}); adoptions = await adoptMergedWorktreesForAllKnownRepos({});
} catch (err) {
// [ANTI-PATTERN IGNORED]: Worktree adoption is best-effort on startup; failure must not block worker initialization
if (err instanceof Error) {
logger.error('WORKER', 'Worktree adoption failed (non-fatal)', {}, err);
} else {
logger.error('WORKER', 'Worktree adoption failed (non-fatal) with non-Error', {}, new Error(String(err)));
}
}
if (adoptions) {
for (const adoption of adoptions) { for (const adoption of adoptions) {
if (adoption.adoptedObservations > 0 || adoption.adoptedSummaries > 0 || adoption.chromaUpdates > 0) { if (adoption.adoptedObservations > 0 || adoption.adoptedSummaries > 0 || adoption.chromaUpdates > 0) {
logger.info('SYSTEM', 'Merged worktrees adopted on startup', adoption); logger.info('SYSTEM', 'Merged worktrees adopted on startup', adoption);
@@ -385,8 +400,6 @@ export class WorkerService {
}); });
} }
} }
} catch (err) {
logger.error('SYSTEM', 'Worktree adoption failed (non-fatal)', {}, err as Error);
} }
// Initialize ChromaMcpManager only if Chroma is enabled // Initialize ChromaMcpManager only if Chroma is enabled
@@ -493,8 +506,11 @@ export class WorkerService {
}); });
try { try {
await transport.close(); await transport.close();
} catch { } catch (transportCloseError) {
// Best effort: the supervisor handles later process cleanup for survivors. // [ANTI-PATTERN IGNORED]: transport.close() is best-effort cleanup after MCP connection already failed; supervisor handles orphan processes
logger.debug('WORKER', 'transport.close() failed during MCP cleanup', {
error: transportCloseError instanceof Error ? transportCloseError.message : String(transportCloseError)
});
} }
logger.info('WORKER', 'Bundled MCP server remains available for external stdio clients', { logger.info('WORKER', 'Bundled MCP server remains available for external stdio clients', {
path: mcpServerPath path: mcpServerPath
@@ -534,7 +550,12 @@ export class WorkerService {
logger.info('SYSTEM', `Reaped ${reaped} stale sessions`); logger.info('SYSTEM', `Reaped ${reaped} stale sessions`);
} }
} catch (e) { } catch (e) {
logger.error('SYSTEM', 'Stale session reaper error', { error: e instanceof Error ? e.message : String(e) }); // [ANTI-PATTERN IGNORED]: setInterval callback cannot throw; reaper retries on next tick (every 2 min)
if (e instanceof Error) {
logger.error('WORKER', 'Stale session reaper error', {}, e);
} else {
logger.error('WORKER', 'Stale session reaper error with non-Error', {}, new Error(String(e)));
}
} }
}, 2 * 60 * 1000); }, 2 * 60 * 1000);
@@ -571,7 +592,7 @@ export class WorkerService {
const configPath = settings.CLAUDE_MEM_TRANSCRIPTS_CONFIG_PATH || DEFAULT_CONFIG_PATH; const configPath = settings.CLAUDE_MEM_TRANSCRIPTS_CONFIG_PATH || DEFAULT_CONFIG_PATH;
const resolvedConfigPath = expandHomePath(configPath); const resolvedConfigPath = expandHomePath(configPath);
try { // Ensure sample config exists (setup, outside try)
if (!existsSync(resolvedConfigPath)) { if (!existsSync(resolvedConfigPath)) {
writeSampleConfig(configPath); writeSampleConfig(configPath);
logger.info('TRANSCRIPT', 'Created default transcript watch config', { logger.info('TRANSCRIPT', 'Created default transcript watch config', {
@@ -582,20 +603,29 @@ export class WorkerService {
const transcriptConfig = loadTranscriptWatchConfig(configPath); const transcriptConfig = loadTranscriptWatchConfig(configPath);
const statePath = expandHomePath(transcriptConfig.stateFile ?? DEFAULT_STATE_PATH); const statePath = expandHomePath(transcriptConfig.stateFile ?? DEFAULT_STATE_PATH);
try {
this.transcriptWatcher = new TranscriptWatcher(transcriptConfig, statePath); this.transcriptWatcher = new TranscriptWatcher(transcriptConfig, statePath);
await this.transcriptWatcher.start(); await this.transcriptWatcher.start();
} catch (error) {
this.transcriptWatcher?.stop();
this.transcriptWatcher = null;
if (error instanceof Error) {
logger.error('WORKER', 'Failed to start transcript watcher (continuing without Codex ingestion)', {
configPath: resolvedConfigPath
}, error);
} else {
logger.error('WORKER', 'Failed to start transcript watcher with non-Error (continuing without Codex ingestion)', {
configPath: resolvedConfigPath
}, new Error(String(error)));
}
// [ANTI-PATTERN IGNORED]: Transcript watcher is intentionally non-fatal so Claude hooks remain usable even if transcript ingestion is misconfigured
return;
}
logger.info('TRANSCRIPT', 'Transcript watcher started', { logger.info('TRANSCRIPT', 'Transcript watcher started', {
configPath: resolvedConfigPath, configPath: resolvedConfigPath,
statePath, statePath,
watches: transcriptConfig.watches.length watches: transcriptConfig.watches.length
}); });
} catch (error) {
this.transcriptWatcher?.stop();
this.transcriptWatcher = null;
logger.error('TRANSCRIPT', 'Failed to start transcript watcher (continuing without Codex ingestion)', {
configPath: resolvedConfigPath
}, error as Error);
}
} }
/** /**
@@ -693,7 +723,8 @@ export class WorkerService {
} }
// Detect stale resume failures - SDK session context was lost // Detect stale resume failures - SDK session context was lost
if ((errorMessage.includes('aborted by user') || errorMessage.includes('No conversation found')) const staleResumePatterns = ['aborted by user', 'No conversation found'];
if (staleResumePatterns.some(p => errorMessage.includes(p))
&& session.memorySessionId) { && session.memorySessionId) {
logger.warn('SDK', 'Detected stale resume failure, clearing memorySessionId for fresh start', { logger.warn('SDK', 'Detected stale resume failure, clearing memorySessionId for fresh start', {
sessionId: session.sessionDbId, sessionId: session.sessionDbId,
@@ -798,16 +829,30 @@ export class WorkerService {
/** /**
* Match errors that indicate the Claude Code process/session is gone (resume impossible). * Match errors that indicate the Claude Code process/session is gone (resume impossible).
* Used to trigger graceful fallback instead of leaving pending messages stuck forever. * Used to trigger graceful fallback instead of leaving pending messages stuck forever.
*
* These patterns come from the Claude SDK's ProcessTransport and related internals.
* The SDK does not export typed error classes, so string matching on normalized
* messages is the only reliable detection method. Each pattern corresponds to a
* specific SDK failure mode:
* - 'process aborted by user': user cancelled the Claude Code session
* - 'processtransport': transport layer disconnected
* - 'not ready for writing': stdio pipe to Claude process is closed
* - 'session generator failed': wrapper error from our own agent layer
* - 'claude code process': process exited or was killed
*/ */
private static readonly SESSION_TERMINATED_PATTERNS = [
'process aborted by user',
'processtransport',
'not ready for writing',
'session generator failed',
'claude code process',
] as const;
private isSessionTerminatedError(error: unknown): boolean { private isSessionTerminatedError(error: unknown): boolean {
const msg = error instanceof Error ? error.message : String(error); const msg = error instanceof Error ? error.message : String(error);
const normalized = msg.toLowerCase(); const normalized = msg.toLowerCase();
return ( return WorkerService.SESSION_TERMINATED_PATTERNS.some(
normalized.includes('process aborted by user') || pattern => normalized.includes(pattern)
normalized.includes('processtransport') ||
normalized.includes('not ready for writing') ||
normalized.includes('session generator failed') ||
normalized.includes('claude code process')
); );
} }
@@ -835,10 +880,15 @@ export class WorkerService {
await this.geminiAgent.startSession(session, this); await this.geminiAgent.startSession(session, this);
return; return;
} catch (e) { } catch (e) {
logger.warn('SDK', 'Fallback Gemini failed, trying OpenRouter', { // [ANTI-PATTERN IGNORED]: Fallback chain by design — Gemini failure falls through to OpenRouter attempt
if (e instanceof Error) {
logger.warn('WORKER', 'Fallback Gemini failed, trying OpenRouter', {
sessionId: sessionDbId, sessionId: sessionDbId,
error: e instanceof Error ? e.message : String(e)
}); });
logger.error('WORKER', 'Gemini fallback error detail', { sessionId: sessionDbId }, e);
} else {
logger.error('WORKER', 'Gemini fallback failed with non-Error', { sessionId: sessionDbId }, new Error(String(e)));
}
} }
} }
@@ -847,10 +897,12 @@ export class WorkerService {
await this.openRouterAgent.startSession(session, this); await this.openRouterAgent.startSession(session, this);
return; return;
} catch (e) { } catch (e) {
logger.warn('SDK', 'Fallback OpenRouter failed', { // [ANTI-PATTERN IGNORED]: Last fallback in chain — failure falls through to message abandonment, which is the designed terminal behavior
sessionId: sessionDbId, if (e instanceof Error) {
error: e instanceof Error ? e.message : String(e) logger.error('WORKER', 'Fallback OpenRouter failed, will abandon messages', { sessionId: sessionDbId }, e);
}); } else {
logger.error('WORKER', 'Fallback OpenRouter failed with non-Error, will abandon messages', { sessionId: sessionDbId }, new Error(String(e)));
}
} }
} }
@@ -909,7 +961,6 @@ export class WorkerService {
const STALE_SESSION_THRESHOLD_MS = 6 * 60 * 60 * 1000; const STALE_SESSION_THRESHOLD_MS = 6 * 60 * 60 * 1000;
const staleThreshold = Date.now() - STALE_SESSION_THRESHOLD_MS; const staleThreshold = Date.now() - STALE_SESSION_THRESHOLD_MS;
try {
const staleSessionIds = sessionStore.db.prepare(` const staleSessionIds = sessionStore.db.prepare(`
SELECT id FROM sdk_sessions SELECT id FROM sdk_sessions
WHERE status = 'active' AND started_at_epoch < ? WHERE status = 'active' AND started_at_epoch < ?
@@ -918,28 +969,42 @@ export class WorkerService {
if (staleSessionIds.length > 0) { if (staleSessionIds.length > 0) {
const ids = staleSessionIds.map(r => r.id); const ids = staleSessionIds.map(r => r.id);
const placeholders = ids.map(() => '?').join(','); const placeholders = ids.map(() => '?').join(',');
const now = Date.now();
try {
sessionStore.db.prepare(` sessionStore.db.prepare(`
UPDATE sdk_sessions UPDATE sdk_sessions
SET status = 'failed', completed_at_epoch = ? SET status = 'failed', completed_at_epoch = ?
WHERE id IN (${placeholders}) WHERE id IN (${placeholders})
`).run(Date.now(), ...ids); `).run(now, ...ids);
logger.info('SYSTEM', `Marked ${ids.length} stale sessions as failed`); logger.info('SYSTEM', `Marked ${ids.length} stale sessions as failed`);
} catch (error) {
// [ANTI-PATTERN IGNORED]: Stale session cleanup is best-effort; pending queue processing below must still proceed
if (error instanceof Error) {
logger.error('WORKER', 'Failed to mark stale sessions as failed', { staleCount: ids.length }, error);
} else {
logger.error('WORKER', 'Failed to mark stale sessions as failed with non-Error', { staleCount: ids.length }, new Error(String(error)));
}
}
try {
const msgResult = sessionStore.db.prepare(` const msgResult = sessionStore.db.prepare(`
UPDATE pending_messages UPDATE pending_messages
SET status = 'failed', failed_at_epoch = ? SET status = 'failed', failed_at_epoch = ?
WHERE status = 'pending' WHERE status = 'pending'
AND session_db_id IN (${placeholders}) AND session_db_id IN (${placeholders})
`).run(Date.now(), ...ids); `).run(now, ...ids);
if (msgResult.changes > 0) { if (msgResult.changes > 0) {
logger.info('SYSTEM', `Marked ${msgResult.changes} pending messages from stale sessions as failed`); logger.info('SYSTEM', `Marked ${msgResult.changes} pending messages from stale sessions as failed`);
} }
}
} catch (error) { } catch (error) {
logger.error('SYSTEM', 'Failed to clean up stale sessions', {}, error as Error); // [ANTI-PATTERN IGNORED]: Pending message cleanup is best-effort; queue processing below must still proceed
if (error instanceof Error) {
logger.error('WORKER', 'Failed to clean up stale pending messages', { staleCount: ids.length }, error);
} else {
logger.error('WORKER', 'Failed to clean up stale pending messages with non-Error', { staleCount: ids.length }, new Error(String(error)));
}
}
} }
const orphanedSessionIds = pendingStore.getSessionsWithPendingMessages(); const orphanedSessionIds = pendingStore.getSessionsWithPendingMessages();
@@ -958,28 +1023,34 @@ export class WorkerService {
for (const sessionDbId of orphanedSessionIds) { for (const sessionDbId of orphanedSessionIds) {
if (result.sessionsStarted >= sessionLimit) break; if (result.sessionsStarted >= sessionLimit) break;
try {
const existingSession = this.sessionManager.getSession(sessionDbId); const existingSession = this.sessionManager.getSession(sessionDbId);
if (existingSession?.generatorPromise) { if (existingSession?.generatorPromise) {
result.sessionsSkipped++; result.sessionsSkipped++;
continue; continue;
} }
try {
const session = this.sessionManager.initializeSession(sessionDbId); const session = this.sessionManager.initializeSession(sessionDbId);
logger.info('SYSTEM', `Starting processor for session ${sessionDbId}`, {
project: session.project,
pendingCount: pendingStore.getPendingCount(sessionDbId)
});
this.startSessionProcessor(session, 'startup-recovery'); this.startSessionProcessor(session, 'startup-recovery');
result.sessionsStarted++; result.sessionsStarted++;
result.startedSessionIds.push(sessionDbId); result.startedSessionIds.push(sessionDbId);
} catch (error) {
if (error instanceof Error) {
logger.error('WORKER', `Failed to initialize/start session ${sessionDbId}`, { sessionDbId }, error);
} else {
logger.error('WORKER', `Failed to initialize/start session ${sessionDbId} with non-Error`, { sessionDbId }, new Error(String(error)));
}
result.sessionsSkipped++;
// [ANTI-PATTERN IGNORED]: Per-session failure must not abort the loop; other sessions may still be recoverable
continue;
}
logger.info('SYSTEM', `Starting processor for session ${sessionDbId}`, {
project: this.sessionManager.getSession(sessionDbId)?.project,
pendingCount: pendingStore.getPendingCount(sessionDbId)
});
await new Promise(resolve => setTimeout(resolve, 100)); await new Promise(resolve => setTimeout(resolve, 100));
} catch (error) {
logger.error('SYSTEM', `Failed to process session ${sessionDbId}`, {}, error as Error);
result.sessionsSkipped++;
}
} }
return result; return result;
src/services/worker-spawner.ts
+6 -1
View File
@@ -53,7 +53,12 @@ function shouldSkipSpawnOnWindows(): boolean {
try { try {
const modifiedTimeMs = statSync(lockPath).mtimeMs; const modifiedTimeMs = statSync(lockPath).mtimeMs;
return Date.now() - modifiedTimeMs < WINDOWS_SPAWN_COOLDOWN_MS; return Date.now() - modifiedTimeMs < WINDOWS_SPAWN_COOLDOWN_MS;
} catch { } catch (error) {
if (error instanceof Error) {
logger.debug('SYSTEM', 'Could not stat worker spawn lock file', {}, error);
} else {
logger.debug('SYSTEM', 'Could not stat worker spawn lock file', { error: String(error) });
}
return false; return false;
} }
} }
src/services/worker-types.ts
+14
View File
@@ -46,6 +46,14 @@ export interface ActiveSession {
// Track whether the most recent storage operation persisted a summary record. // Track whether the most recent storage operation persisted a summary record.
// Used by the status endpoint so the Stop hook can detect silent summary loss (#1633). // Used by the status endpoint so the Stop hook can detect silent summary loss (#1633).
lastSummaryStored?: boolean; lastSummaryStored?: boolean;
// Circuit breaker: track consecutive summary failures to prevent infinite retry loops (#1633).
// When this reaches MAX_CONSECUTIVE_SUMMARY_FAILURES, further summarize requests are skipped.
consecutiveSummaryFailures: number;
// Subagent identity carried forward from the most recent claimed pending message.
// When observations are parsed and stored, these fields label the resulting rows
// so subagent work is attributable. NULL / undefined means the batch came from the main session.
pendingAgentId?: string | null;
pendingAgentType?: string | null;
} }
export interface PendingMessage { export interface PendingMessage {
@@ -56,6 +64,9 @@ export interface PendingMessage {
prompt_number?: number; prompt_number?: number;
cwd?: string; cwd?: string;
last_assistant_message?: string; last_assistant_message?: string;
// Claude Code subagent identity — present only when the hook fired inside a subagent.
agentId?: string;
agentType?: string;
} }
/** /**
@@ -74,6 +85,9 @@ export interface ObservationData {
tool_response: any; tool_response: any;
prompt_number: number; prompt_number: number;
cwd?: string; cwd?: string;
// Claude Code subagent identity — present only when the hook fired inside a subagent.
agentId?: string;
agentType?: string;
} }
// ============================================================================ // ============================================================================
src/services/worker/BranchManager.ts
+32 -27
View File
@@ -118,15 +118,27 @@ export function getBranchInfo(): BranchInfo {
}; };
} }
try {
// Get current branch // Get current branch
const branch = execGit(['rev-parse', '--abbrev-ref', 'HEAD']); let branch: string;
let status: string;
try {
branch = execGit(['rev-parse', '--abbrev-ref', 'HEAD']);
status = execGit(['status', '--porcelain']);
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.error('WORKER', 'Failed to get branch info', {}, error instanceof Error ? error : new Error(errorMessage));
return {
branch: null,
isBeta: false,
isGitRepo: true,
isDirty: false,
canSwitch: false,
error: errorMessage
};
}
// Check if dirty (has uncommitted changes) // Determine branch state from git results
const status = execGit(['status', '--porcelain']);
const isDirty = status.length > 0; const isDirty = status.length > 0;
// Determine if on beta branch
const isBeta = branch.startsWith('beta'); const isBeta = branch.startsWith('beta');
return { return {
@@ -136,17 +148,6 @@ export function getBranchInfo(): BranchInfo {
isDirty, isDirty,
canSwitch: true // We can always switch (will discard local changes) canSwitch: true // We can always switch (will discard local changes)
}; };
} catch (error) {
logger.error('BRANCH', 'Failed to get branch info', {}, error as Error);
return {
branch: null,
isBeta: false,
isGitRepo: true,
isDirty: false,
canSwitch: false,
error: (error as Error).message
};
}
} }
/** /**
@@ -243,7 +244,8 @@ export async function switchBranch(targetBranch: string): Promise<SwitchResult>
} }
} catch (recoveryError) { } catch (recoveryError) {
// [POSSIBLY RELEVANT]: Recovery checkout failed, user needs manual intervention - already logging main error above // [POSSIBLY RELEVANT]: Recovery checkout failed, user needs manual intervention - already logging main error above
logger.error('BRANCH', 'Recovery checkout also failed', { originalBranch: info.branch }, recoveryError as Error); const recoveryErrorMessage = recoveryError instanceof Error ? recoveryError.message : String(recoveryError);
logger.error('WORKER', 'Recovery checkout also failed', { originalBranch: info.branch }, recoveryError instanceof Error ? recoveryError : new Error(recoveryErrorMessage));
} }
return { return {
@@ -266,7 +268,6 @@ export async function pullUpdates(): Promise<SwitchResult> {
}; };
} }
try {
// SECURITY: Validate branch name before use // SECURITY: Validate branch name before use
if (!isValidBranchName(info.branch)) { if (!isValidBranchName(info.branch)) {
return { return {
@@ -277,6 +278,10 @@ export async function pullUpdates(): Promise<SwitchResult> {
logger.info('BRANCH', 'Pulling updates', { branch: info.branch }); logger.info('BRANCH', 'Pulling updates', { branch: info.branch });
// Prepare install marker path
const installMarker = join(INSTALLED_PLUGIN_PATH, '.install-version');
try {
// Discard local changes first // Discard local changes first
execGit(['checkout', '--', '.']); execGit(['checkout', '--', '.']);
@@ -285,11 +290,18 @@ export async function pullUpdates(): Promise<SwitchResult> {
execGit(['pull', 'origin', info.branch]); execGit(['pull', 'origin', info.branch]);
// Clear install marker and reinstall // Clear install marker and reinstall
const installMarker = join(INSTALLED_PLUGIN_PATH, '.install-version');
if (existsSync(installMarker)) { if (existsSync(installMarker)) {
unlinkSync(installMarker); unlinkSync(installMarker);
} }
execNpm(['install'], NPM_INSTALL_TIMEOUT_MS); execNpm(['install'], NPM_INSTALL_TIMEOUT_MS);
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error);
logger.error('WORKER', 'Pull failed', {}, error instanceof Error ? error : new Error(errorMessage));
return {
success: false,
error: `Pull failed: ${errorMessage}`
};
}
logger.success('BRANCH', 'Updates pulled', { branch: info.branch }); logger.success('BRANCH', 'Updates pulled', { branch: info.branch });
@@ -298,13 +310,6 @@ export async function pullUpdates(): Promise<SwitchResult> {
branch: info.branch, branch: info.branch,
message: `Updated ${info.branch}. Worker will restart automatically.` message: `Updated ${info.branch}. Worker will restart automatically.`
}; };
} catch (error) {
logger.error('BRANCH', 'Pull failed', {}, error as Error);
return {
success: false,
error: `Pull failed: ${(error as Error).message}`
};
}
} }
/** /**
src/services/worker/GeminiAgent.ts
+98 -72
View File
@@ -22,6 +22,7 @@ import { USER_SETTINGS_PATH } from '../../shared/paths.js';
import { estimateTokens } from '../../shared/timeline-formatting.js'; import { estimateTokens } from '../../shared/timeline-formatting.js';
import type { ActiveSession, ConversationMessage } from '../worker-types.js'; import type { ActiveSession, ConversationMessage } from '../worker-types.js';
import { ModeManager } from '../domain/ModeManager.js'; import { ModeManager } from '../domain/ModeManager.js';
import type { ModeConfig } from '../domain/types.js';
import { import {
processAgentResponse, processAgentResponse,
shouldFallbackToClaude, shouldFallbackToClaude,
@@ -135,8 +136,7 @@ export class GeminiAgent {
* Uses multi-turn conversation to maintain context across messages * Uses multi-turn conversation to maintain context across messages
*/ */
async startSession(session: ActiveSession, worker?: WorkerRef): Promise<void> { async startSession(session: ActiveSession, worker?: WorkerRef): Promise<void> {
try { // --- Configuration & validation (no try needed - throws clear errors) ---
// Get Gemini configuration
const { apiKey, model, rateLimitingEnabled } = this.getGeminiConfig(); const { apiKey, model, rateLimitingEnabled } = this.getGeminiConfig();
if (!apiKey) { if (!apiKey) {
@@ -151,48 +151,69 @@ export class GeminiAgent {
logger.info('SESSION', `MEMORY_ID_GENERATED | sessionDbId=${session.sessionDbId} | provider=Gemini`); logger.info('SESSION', `MEMORY_ID_GENERATED | sessionDbId=${session.sessionDbId} | provider=Gemini`);
} }
// Load active mode // Load active mode and build initial prompt
const mode = ModeManager.getInstance().getActiveMode(); const mode = ModeManager.getInstance().getActiveMode();
// Build initial prompt
const initPrompt = session.lastPromptNumber === 1 const initPrompt = session.lastPromptNumber === 1
? buildInitPrompt(session.project, session.contentSessionId, session.userPrompt, mode) ? buildInitPrompt(session.project, session.contentSessionId, session.userPrompt, mode)
: buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.contentSessionId, mode); : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.contentSessionId, mode);
// Add to conversation history and query Gemini with full context // --- Init query: API call + response processing ---
session.conversationHistory.push({ role: 'user', content: initPrompt }); session.conversationHistory.push({ role: 'user', content: initPrompt });
const initResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled); let initResponse: { content: string; tokensUsed?: number };
try {
initResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
} catch (error: unknown) {
if (error instanceof Error) {
logger.error('SDK', 'Gemini init query failed', { sessionId: session.sessionDbId, model }, error);
} else {
logger.error('SDK', 'Gemini init query failed with non-Error', { sessionId: session.sessionDbId, model }, new Error(String(error)));
}
return this.handleGeminiError(error, session, worker);
}
if (initResponse.content) { if (initResponse.content) {
// Add response to conversation history
session.conversationHistory.push({ role: 'assistant', content: initResponse.content }); session.conversationHistory.push({ role: 'assistant', content: initResponse.content });
// Track token usage
const tokensUsed = initResponse.tokensUsed || 0; const tokensUsed = initResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7); // Rough estimate session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7); // Rough estimate
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3); session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
await processAgentResponse(initResponse.content, session, this.dbManager, this.sessionManager, worker, tokensUsed, null, 'Gemini', undefined, model);
// Process response using shared ResponseProcessor (no original timestamp for init - not from queue)
await processAgentResponse(
initResponse.content,
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
null,
'Gemini',
undefined,
model
);
} else { } else {
logger.error('SDK', 'Empty Gemini init response - session may lack context', { logger.error('SDK', 'Empty Gemini init response - session may lack context', { sessionId: session.sessionDbId, model });
}
// --- Message processing loop: iterate pending messages ---
try {
await this.processMessageLoop(session, worker, apiKey, model, rateLimitingEnabled, mode);
} catch (error: unknown) {
if (error instanceof Error) {
logger.error('SDK', 'Gemini message loop failed', { sessionId: session.sessionDbId, model }, error);
} else {
logger.error('SDK', 'Gemini message loop failed with non-Error', { sessionId: session.sessionDbId, model }, new Error(String(error)));
}
return this.handleGeminiError(error, session, worker);
}
// Mark session complete
const sessionDuration = Date.now() - session.startTime;
logger.success('SDK', 'Gemini agent completed', {
sessionId: session.sessionDbId, sessionId: session.sessionDbId,
model duration: `${(sessionDuration / 1000).toFixed(1)}s`,
historyLength: session.conversationHistory.length
}); });
} }
// Process pending messages /**
* Process pending messages from the session queue.
* Extracted from startSession to keep try blocks focused.
*/
private async processMessageLoop(
session: ActiveSession,
worker: WorkerRef | undefined,
apiKey: string,
model: GeminiModel,
rateLimitingEnabled: boolean,
mode: ModeConfig
): Promise<void> {
// Track cwd from messages for CLAUDE.md generation // Track cwd from messages for CLAUDE.md generation
let lastCwd: string | undefined; let lastCwd: string | undefined;
@@ -201,6 +222,13 @@ export class GeminiAgent {
// The message is now in 'processing' status in DB until ResponseProcessor calls confirmProcessed() // The message is now in 'processing' status in DB until ResponseProcessor calls confirmProcessed()
session.processingMessageIds.push(message._persistentId); session.processingMessageIds.push(message._persistentId);
// Capture subagent identity from the claimed message so ResponseProcessor
// can label observation rows with the originating Claude Code subagent.
// Always overwrite (even with null) so a main-session message after a subagent
// message clears the stale identity; otherwise mixed batches could mislabel.
session.pendingAgentId = message.agentId ?? null;
session.pendingAgentType = message.agentType ?? null;
// Capture cwd from each message for worktree support // Capture cwd from each message for worktree support
if (message.cwd) { if (message.cwd) {
lastCwd = message.cwd; lastCwd = message.cwd;
@@ -210,6 +238,26 @@ export class GeminiAgent {
const originalTimestamp = session.earliestPendingTimestamp; const originalTimestamp = session.earliestPendingTimestamp;
if (message.type === 'observation') { if (message.type === 'observation') {
await this.processObservationMessage(session, message, worker, apiKey, model, rateLimitingEnabled, originalTimestamp, lastCwd);
} else if (message.type === 'summarize') {
await this.processSummaryMessage(session, message, worker, apiKey, model, rateLimitingEnabled, mode, originalTimestamp, lastCwd);
}
}
}
/**
* Process a single observation message via Gemini API.
*/
private async processObservationMessage(
session: ActiveSession,
message: { type: string; prompt_number?: number; tool_name?: string; tool_input?: unknown; tool_response?: unknown; cwd?: string },
worker: WorkerRef | undefined,
apiKey: string,
model: GeminiModel,
rateLimitingEnabled: boolean,
originalTimestamp: number | null,
lastCwd: string | undefined
): Promise<void> {
// Update last prompt number // Update last prompt number
if (message.prompt_number !== undefined) { if (message.prompt_number !== undefined) {
session.lastPromptNumber = message.prompt_number; session.lastPromptNumber = message.prompt_number;
@@ -231,34 +279,19 @@ export class GeminiAgent {
cwd: message.cwd cwd: message.cwd
}); });
// Add to conversation history and query Gemini with full context
session.conversationHistory.push({ role: 'user', content: obsPrompt }); session.conversationHistory.push({ role: 'user', content: obsPrompt });
const obsResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled); const obsResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
let tokensUsed = 0; let tokensUsed = 0;
if (obsResponse.content) { if (obsResponse.content) {
// Add response to conversation history
session.conversationHistory.push({ role: 'assistant', content: obsResponse.content }); session.conversationHistory.push({ role: 'assistant', content: obsResponse.content });
tokensUsed = obsResponse.tokensUsed || 0; tokensUsed = obsResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7); session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3); session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
} }
// Process response using shared ResponseProcessor
if (obsResponse.content) { if (obsResponse.content) {
await processAgentResponse( await processAgentResponse(obsResponse.content, session, this.dbManager, this.sessionManager, worker, tokensUsed, originalTimestamp, 'Gemini', lastCwd, model);
obsResponse.content,
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
originalTimestamp,
'Gemini',
lastCwd,
model
);
} else { } else {
logger.warn('SDK', 'Empty Gemini observation response, skipping processing to preserve message', { logger.warn('SDK', 'Empty Gemini observation response, skipping processing to preserve message', {
sessionId: session.sessionDbId, sessionId: session.sessionDbId,
@@ -266,8 +299,22 @@ export class GeminiAgent {
}); });
// Don't confirm - leave message for stale recovery // Don't confirm - leave message for stale recovery
} }
}
} else if (message.type === 'summarize') { /**
* Process a single summary message via Gemini API.
*/
private async processSummaryMessage(
session: ActiveSession,
message: { type: string; last_assistant_message?: string },
worker: WorkerRef | undefined,
apiKey: string,
model: GeminiModel,
rateLimitingEnabled: boolean,
mode: ModeConfig,
originalTimestamp: number | null,
lastCwd: string | undefined
): Promise<void> {
// CRITICAL: Check memorySessionId BEFORE making expensive LLM call // CRITICAL: Check memorySessionId BEFORE making expensive LLM call
if (!session.memorySessionId) { if (!session.memorySessionId) {
throw new Error('Cannot process summary: memorySessionId not yet captured. This session may need to be reinitialized.'); throw new Error('Cannot process summary: memorySessionId not yet captured. This session may need to be reinitialized.');
@@ -282,34 +329,19 @@ export class GeminiAgent {
last_assistant_message: message.last_assistant_message || '' last_assistant_message: message.last_assistant_message || ''
}, mode); }, mode);
// Add to conversation history and query Gemini with full context
session.conversationHistory.push({ role: 'user', content: summaryPrompt }); session.conversationHistory.push({ role: 'user', content: summaryPrompt });
const summaryResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled); const summaryResponse = await this.queryGeminiMultiTurn(session.conversationHistory, apiKey, model, rateLimitingEnabled);
let tokensUsed = 0; let tokensUsed = 0;
if (summaryResponse.content) { if (summaryResponse.content) {
// Add response to conversation history
session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content }); session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content });
tokensUsed = summaryResponse.tokensUsed || 0; tokensUsed = summaryResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7); session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3); session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
} }
// Process response using shared ResponseProcessor
if (summaryResponse.content) { if (summaryResponse.content) {
await processAgentResponse( await processAgentResponse(summaryResponse.content, session, this.dbManager, this.sessionManager, worker, tokensUsed, originalTimestamp, 'Gemini', lastCwd, model);
summaryResponse.content,
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
originalTimestamp,
'Gemini',
lastCwd,
model
);
} else { } else {
logger.warn('SDK', 'Empty Gemini summary response, skipping processing to preserve message', { logger.warn('SDK', 'Empty Gemini summary response, skipping processing to preserve message', {
sessionId: session.sessionDbId, sessionId: session.sessionDbId,
@@ -318,17 +350,12 @@ export class GeminiAgent {
// Don't confirm - leave message for stale recovery // Don't confirm - leave message for stale recovery
} }
} }
}
// Mark session complete /**
const sessionDuration = Date.now() - session.startTime; * Handle errors from Gemini API calls with abort detection and Claude fallback.
logger.success('SDK', 'Gemini agent completed', { * Shared by init query and message processing try blocks.
sessionId: session.sessionDbId, */
duration: `${(sessionDuration / 1000).toFixed(1)}s`, private handleGeminiError(error: unknown, session: ActiveSession, worker?: WorkerRef): Promise<void> | never {
historyLength: session.conversationHistory.length
});
} catch (error: unknown) {
if (isAbortError(error)) { if (isAbortError(error)) {
logger.warn('SDK', 'Gemini agent aborted', { sessionId: session.sessionDbId }); logger.warn('SDK', 'Gemini agent aborted', { sessionId: session.sessionDbId });
throw error; throw error;
@@ -347,10 +374,9 @@ export class GeminiAgent {
return this.fallbackAgent.startSession(session, worker); return this.fallbackAgent.startSession(session, worker);
} }
logger.failure('SDK', 'Gemini agent error', { sessionDbId: session.sessionDbId }, error as Error); logger.failure('SDK', 'Gemini agent error', { sessionDbId: session.sessionDbId }, error instanceof Error ? error : new Error(String(error)));
throw error; throw error;
} }
}
/** /**
* Truncate conversation history to prevent runaway context costs. * Truncate conversation history to prevent runaway context costs.
src/services/worker/OpenRouterAgent.ts
+204 -137
View File
@@ -17,6 +17,7 @@ import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js
import { USER_SETTINGS_PATH } from '../../shared/paths.js'; import { USER_SETTINGS_PATH } from '../../shared/paths.js';
import { logger } from '../../utils/logger.js'; import { logger } from '../../utils/logger.js';
import { ModeManager } from '../domain/ModeManager.js'; import { ModeManager } from '../domain/ModeManager.js';
import type { ModeConfig } from '../domain/types.js';
import type { ActiveSession, ConversationMessage } from '../worker-types.js'; import type { ActiveSession, ConversationMessage } from '../worker-types.js';
import { DatabaseManager } from './DatabaseManager.js'; import { DatabaseManager } from './DatabaseManager.js';
import { SessionManager } from './SessionManager.js'; import { SessionManager } from './SessionManager.js';
@@ -84,8 +85,7 @@ export class OpenRouterAgent {
* Uses multi-turn conversation to maintain context across messages * Uses multi-turn conversation to maintain context across messages
*/ */
async startSession(session: ActiveSession, worker?: WorkerRef): Promise<void> { async startSession(session: ActiveSession, worker?: WorkerRef): Promise<void> {
try { // Get OpenRouter configuration (pure lookup, no external I/O)
// Get OpenRouter configuration
const { apiKey, model, siteUrl, appName } = this.getOpenRouterConfig(); const { apiKey, model, siteUrl, appName } = this.getOpenRouterConfig();
if (!apiKey) { if (!apiKey) {
@@ -108,148 +108,38 @@ export class OpenRouterAgent {
? buildInitPrompt(session.project, session.contentSessionId, session.userPrompt, mode) ? buildInitPrompt(session.project, session.contentSessionId, session.userPrompt, mode)
: buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.contentSessionId, mode); : buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.contentSessionId, mode);
// Add to conversation history and query OpenRouter with full context // Send init prompt to OpenRouter
session.conversationHistory.push({ role: 'user', content: initPrompt }); session.conversationHistory.push({ role: 'user', content: initPrompt });
try {
const initResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName); const initResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
await this.handleInitResponse(initResponse, session, worker, model);
if (initResponse.content) { } catch (error: unknown) {
// Add response to conversation history if (error instanceof Error) {
// session.conversationHistory.push({ role: 'assistant', content: initResponse.content }); logger.error('SDK', 'OpenRouter init failed', { sessionId: session.sessionDbId, model }, error);
// Track token usage
const tokensUsed = initResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7); // Rough estimate
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
// Process response using shared ResponseProcessor (no original timestamp for init - not from queue)
await processAgentResponse(
initResponse.content,
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
null,
'OpenRouter',
undefined, // No lastCwd yet - before message processing
model
);
} else { } else {
logger.error('SDK', 'Empty OpenRouter init response - session may lack context', { logger.error('SDK', 'OpenRouter init failed with non-Error', { sessionId: session.sessionDbId, model }, new Error(String(error)));
sessionId: session.sessionDbId, }
model await this.handleSessionError(error, session, worker);
}); return;
} }
// Track lastCwd from messages for CLAUDE.md generation // Track lastCwd from messages for CLAUDE.md generation
let lastCwd: string | undefined; let lastCwd: string | undefined;
// Process pending messages // Process pending messages
try {
for await (const message of this.sessionManager.getMessageIterator(session.sessionDbId)) { for await (const message of this.sessionManager.getMessageIterator(session.sessionDbId)) {
// CLAIM-CONFIRM: Track message ID for confirmProcessed() after successful storage lastCwd = await this.processOneMessage(session, message, lastCwd, apiKey, model, siteUrl, appName, worker, mode);
// The message is now in 'processing' status in DB until ResponseProcessor calls confirmProcessed()
session.processingMessageIds.push(message._persistentId);
// Capture cwd from messages for proper worktree support
if (message.cwd) {
lastCwd = message.cwd;
} }
// Capture earliest timestamp BEFORE processing (will be cleared after) } catch (error: unknown) {
const originalTimestamp = session.earliestPendingTimestamp; if (error instanceof Error) {
logger.error('SDK', 'OpenRouter message processing failed', { sessionId: session.sessionDbId, model }, error);
if (message.type === 'observation') { } else {
// Update last prompt number logger.error('SDK', 'OpenRouter message processing failed with non-Error', { sessionId: session.sessionDbId, model }, new Error(String(error)));
if (message.prompt_number !== undefined) {
session.lastPromptNumber = message.prompt_number;
}
// CRITICAL: Check memorySessionId BEFORE making expensive LLM call
// This prevents wasting tokens when we won't be able to store the result anyway
if (!session.memorySessionId) {
throw new Error('Cannot process observations: memorySessionId not yet captured. This session may need to be reinitialized.');
}
// Build observation prompt
const obsPrompt = buildObservationPrompt({
id: 0,
tool_name: message.tool_name!,
tool_input: JSON.stringify(message.tool_input),
tool_output: JSON.stringify(message.tool_response),
created_at_epoch: originalTimestamp ?? Date.now(),
cwd: message.cwd
});
// Add to conversation history and query OpenRouter with full context
session.conversationHistory.push({ role: 'user', content: obsPrompt });
const obsResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
let tokensUsed = 0;
if (obsResponse.content) {
// Add response to conversation history
// session.conversationHistory.push({ role: 'assistant', content: obsResponse.content });
tokensUsed = obsResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
}
// Process response using shared ResponseProcessor
await processAgentResponse(
obsResponse.content || '',
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
originalTimestamp,
'OpenRouter',
lastCwd,
model
);
} else if (message.type === 'summarize') {
// CRITICAL: Check memorySessionId BEFORE making expensive LLM call
if (!session.memorySessionId) {
throw new Error('Cannot process summary: memorySessionId not yet captured. This session may need to be reinitialized.');
}
// Build summary prompt
const summaryPrompt = buildSummaryPrompt({
id: session.sessionDbId,
memory_session_id: session.memorySessionId,
project: session.project,
user_prompt: session.userPrompt,
last_assistant_message: message.last_assistant_message || ''
}, mode);
// Add to conversation history and query OpenRouter with full context
session.conversationHistory.push({ role: 'user', content: summaryPrompt });
const summaryResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
let tokensUsed = 0;
if (summaryResponse.content) {
// Add response to conversation history
// session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content });
tokensUsed = summaryResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
}
// Process response using shared ResponseProcessor
await processAgentResponse(
summaryResponse.content || '',
session,
this.dbManager,
this.sessionManager,
worker,
tokensUsed,
originalTimestamp,
'OpenRouter',
lastCwd,
model
);
} }
await this.handleSessionError(error, session, worker);
return;
} }
// Mark session complete // Mark session complete
@@ -260,14 +150,191 @@ export class OpenRouterAgent {
historyLength: session.conversationHistory.length, historyLength: session.conversationHistory.length,
model model
}); });
}
} catch (error: unknown) { /**
* Prepare common message metadata before processing.
* Tracks message IDs and captures subagent identity.
*/
private prepareMessageMetadata(session: ActiveSession, message: { _persistentId: number; agentId?: string | null; agentType?: string | null }): void {
// CLAIM-CONFIRM: Track message ID for confirmProcessed() after successful storage
session.processingMessageIds.push(message._persistentId);
// Capture subagent identity from the claimed message so ResponseProcessor
// can label observation rows with the originating Claude Code subagent.
// Always overwrite (even with null) so a main-session message after a subagent
// message clears the stale identity; otherwise mixed batches could mislabel.
session.pendingAgentId = message.agentId ?? null;
session.pendingAgentType = message.agentType ?? null;
}
/**
* Handle the init response from OpenRouter: update token counts and process or log empty.
*/
private async handleInitResponse(
initResponse: { content: string; tokensUsed?: number },
session: ActiveSession,
worker: WorkerRef | undefined,
model: string
): Promise<void> {
if (initResponse.content) {
session.conversationHistory.push({ role: 'assistant', content: initResponse.content });
const tokensUsed = initResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
await processAgentResponse(
initResponse.content, session, this.dbManager, this.sessionManager,
worker, tokensUsed, null, 'OpenRouter', undefined, model
);
} else {
logger.error('SDK', 'Empty OpenRouter init response - session may lack context', {
sessionId: session.sessionDbId, model
});
}
}
/**
* Process one message from the iterator: prepare metadata, dispatch to observation or summary handler.
* Returns the updated lastCwd value.
*/
private async processOneMessage(
session: ActiveSession,
message: { _persistentId: number; agentId?: string | null; agentType?: string | null; type?: string; cwd?: string; prompt_number?: number; tool_name?: string; tool_input?: unknown; tool_response?: unknown; last_assistant_message?: string },
lastCwd: string | undefined,
apiKey: string,
model: string,
siteUrl: string | undefined,
appName: string | undefined,
worker: WorkerRef | undefined,
mode: ModeConfig
): Promise<string | undefined> {
this.prepareMessageMetadata(session, message);
if (message.cwd) {
lastCwd = message.cwd;
}
const originalTimestamp = session.earliestPendingTimestamp;
if (message.type === 'observation') {
await this.processObservationMessage(
session, message, originalTimestamp, lastCwd,
apiKey, model, siteUrl, appName, worker, mode
);
} else if (message.type === 'summarize') {
await this.processSummaryMessage(
session, message, originalTimestamp, lastCwd,
apiKey, model, siteUrl, appName, worker, mode
);
}
return lastCwd;
}
/**
* Process a single observation message: build prompt, call OpenRouter, store result.
*/
private async processObservationMessage(
session: ActiveSession,
message: { prompt_number?: number; tool_name?: string; tool_input?: unknown; tool_response?: unknown; cwd?: string },
originalTimestamp: number | null,
lastCwd: string | undefined,
apiKey: string,
model: string,
siteUrl: string | undefined,
appName: string | undefined,
worker: WorkerRef | undefined,
_mode: ModeConfig
): Promise<void> {
if (message.prompt_number !== undefined) {
session.lastPromptNumber = message.prompt_number;
}
// CRITICAL: Check memorySessionId BEFORE making expensive LLM call
if (!session.memorySessionId) {
throw new Error('Cannot process observations: memorySessionId not yet captured. This session may need to be reinitialized.');
}
const obsPrompt = buildObservationPrompt({
id: 0,
tool_name: message.tool_name!,
tool_input: JSON.stringify(message.tool_input),
tool_output: JSON.stringify(message.tool_response),
created_at_epoch: originalTimestamp ?? Date.now(),
cwd: message.cwd
});
session.conversationHistory.push({ role: 'user', content: obsPrompt });
const obsResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
let tokensUsed = 0;
if (obsResponse.content) {
session.conversationHistory.push({ role: 'assistant', content: obsResponse.content });
tokensUsed = obsResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
}
await processAgentResponse(
obsResponse.content || '', session, this.dbManager, this.sessionManager,
worker, tokensUsed, originalTimestamp, 'OpenRouter', lastCwd, model
);
}
/**
* Process a single summary message: build prompt, call OpenRouter, store result.
*/
private async processSummaryMessage(
session: ActiveSession,
message: { last_assistant_message?: string },
originalTimestamp: number | null,
lastCwd: string | undefined,
apiKey: string,
model: string,
siteUrl: string | undefined,
appName: string | undefined,
worker: WorkerRef | undefined,
mode: ModeConfig
): Promise<void> {
// CRITICAL: Check memorySessionId BEFORE making expensive LLM call
if (!session.memorySessionId) {
throw new Error('Cannot process summary: memorySessionId not yet captured. This session may need to be reinitialized.');
}
const summaryPrompt = buildSummaryPrompt({
id: session.sessionDbId,
memory_session_id: session.memorySessionId,
project: session.project,
user_prompt: session.userPrompt,
last_assistant_message: message.last_assistant_message || ''
}, mode);
session.conversationHistory.push({ role: 'user', content: summaryPrompt });
const summaryResponse = await this.queryOpenRouterMultiTurn(session.conversationHistory, apiKey, model, siteUrl, appName);
let tokensUsed = 0;
if (summaryResponse.content) {
session.conversationHistory.push({ role: 'assistant', content: summaryResponse.content });
tokensUsed = summaryResponse.tokensUsed || 0;
session.cumulativeInputTokens += Math.floor(tokensUsed * 0.7);
session.cumulativeOutputTokens += Math.floor(tokensUsed * 0.3);
}
await processAgentResponse(
summaryResponse.content || '', session, this.dbManager, this.sessionManager,
worker, tokensUsed, originalTimestamp, 'OpenRouter', lastCwd, model
);
}
/**
* Handle errors from session processing: abort re-throw, fallback to Claude, or log and re-throw.
*/
private async handleSessionError(error: unknown, session: ActiveSession, worker?: WorkerRef): Promise<never | void> {
if (isAbortError(error)) { if (isAbortError(error)) {
logger.warn('SDK', 'OpenRouter agent aborted', { sessionId: session.sessionDbId }); logger.warn('SDK', 'OpenRouter agent aborted', { sessionId: session.sessionDbId });
throw error; throw error;
} }
// Check if we should fall back to Claude
if (shouldFallbackToClaude(error) && this.fallbackAgent) { if (shouldFallbackToClaude(error) && this.fallbackAgent) {
logger.warn('SDK', 'OpenRouter API failed, falling back to Claude SDK', { logger.warn('SDK', 'OpenRouter API failed, falling back to Claude SDK', {
sessionDbId: session.sessionDbId, sessionDbId: session.sessionDbId,
@@ -277,13 +344,13 @@ export class OpenRouterAgent {
// Fall back to Claude - it will use the same session with shared conversationHistory // Fall back to Claude - it will use the same session with shared conversationHistory
// Note: With claim-and-delete queue pattern, messages are already deleted on claim // Note: With claim-and-delete queue pattern, messages are already deleted on claim
return this.fallbackAgent.startSession(session, worker); await this.fallbackAgent.startSession(session, worker);
return;
} }
logger.failure('SDK', 'OpenRouter agent error', { sessionDbId: session.sessionDbId }, error as Error); logger.failure('SDK', 'OpenRouter agent error', { sessionDbId: session.sessionDbId }, error instanceof Error ? error : new Error(String(error)));
throw error; throw error;
} }
}
/** /**
* Estimate token count from text (conservative estimate) * Estimate token count from text (conservative estimate)
src/services/worker/PaginationHelper.ts
+5 -1
View File
@@ -55,7 +55,11 @@ export class PaginationHelper {
// Return as JSON string // Return as JSON string
return JSON.stringify(strippedPaths); return JSON.stringify(strippedPaths);
} catch (err) { } catch (err) {
logger.debug('WORKER', 'File paths is plain string, using as-is', {}, err as Error); if (err instanceof Error) {
logger.debug('WORKER', 'File paths is plain string, using as-is', {}, err);
} else {
logger.debug('WORKER', 'File paths is plain string, using as-is', { rawError: String(err) });
}
return filePathsStr; return filePathsStr;
} }
} }
src/services/worker/ProcessRegistry.ts
+9 -2
View File
@@ -395,8 +395,11 @@ export function createPidCapturingSpawn(sessionDbId: number) {
try { try {
existing.process.kill('SIGTERM'); existing.process.kill('SIGTERM');
exited = existing.process.exitCode !== null; exited = existing.process.exitCode !== null;
} catch { } catch (error: unknown) {
// Already dead — safe to unregister immediately // Already dead — safe to unregister immediately
if (error instanceof Error) {
logger.warn('WORKER', `Failed to kill duplicate process PID ${existing.pid}, likely already dead`, { existingPid: existing.pid, sessionDbId }, error);
}
exited = true; exited = true;
} }
@@ -495,7 +498,11 @@ export function startOrphanReaper(getActiveSessionIds: () => Set<number>, interv
logger.info('PROCESS', `Reaper cleaned up ${killed} orphaned processes`, { killed }); logger.info('PROCESS', `Reaper cleaned up ${killed} orphaned processes`, { killed });
} }
} catch (error) { } catch (error) {
logger.error('PROCESS', 'Reaper error', {}, error as Error); if (error instanceof Error) {
logger.error('WORKER', 'Reaper error', {}, error);
} else {
logger.error('WORKER', 'Reaper error', { rawError: String(error) });
}
} }
}, intervalMs); }, intervalMs);
src/services/worker/SDKAgent.ts
+12 -1
View File
@@ -374,6 +374,13 @@ export class SDKAgent {
// The message is now in 'processing' status in DB until ResponseProcessor calls confirmProcessed() // The message is now in 'processing' status in DB until ResponseProcessor calls confirmProcessed()
session.processingMessageIds.push(message._persistentId); session.processingMessageIds.push(message._persistentId);
// Capture subagent identity from the claimed message so ResponseProcessor
// can label observation rows with the originating Claude Code subagent.
// Always overwrite (even with null) so a main-session message after a subagent
// message clears the stale identity; otherwise mixed batches could mislabel.
session.pendingAgentId = message.agentId ?? null;
session.pendingAgentType = message.agentType ?? null;
// Capture cwd from each message for worktree support // Capture cwd from each message for worktree support
if (message.cwd) { if (message.cwd) {
cwdTracker.lastCwd = message.cwd; cwdTracker.lastCwd = message.cwd;
@@ -473,7 +480,11 @@ export class SDKAgent {
if (claudePath) return claudePath; if (claudePath) return claudePath;
} catch (error) { } catch (error) {
// [ANTI-PATTERN IGNORED]: Fallback behavior - which/where failed, continue to throw clear error // [ANTI-PATTERN IGNORED]: Fallback behavior - which/where failed, continue to throw clear error
logger.debug('SDK', 'Claude executable auto-detection failed', {}, error as Error); if (error instanceof Error) {
logger.debug('SDK', 'Claude executable auto-detection failed', {}, error);
} else {
logger.debug('SDK', 'Claude executable auto-detection failed with non-Error', {}, new Error(String(error)));
}
} }
throw new Error('Claude executable not found. Please either:\n1. Add "claude" to your system PATH, or\n2. Set CLAUDE_CODE_PATH in ~/.claude-mem/settings.json'); throw new Error('Claude executable not found. Please either:\n1. Add "claude" to your system PATH, or\n2. Set CLAUDE_CODE_PATH in ~/.claude-mem/settings.json');
src/services/worker/SearchManager.ts
+39 -25
View File
@@ -67,6 +67,23 @@ export class SearchManager {
return await this.chromaSync.queryChroma(query, limit, whereFilter); return await this.chromaSync.queryChroma(query, limit, whereFilter);
} }
private async searchChromaForTimeline(query: string, ninetyDaysAgo: number): Promise<ObservationSearchResult[]> {
const chromaResults = await this.queryChroma(query, 100);
logger.debug('SEARCH', 'Chroma returned semantic matches for timeline', { matchCount: chromaResults?.ids?.length ?? 0 });
if (chromaResults?.ids && chromaResults.ids.length > 0) {
const recentIds = chromaResults.ids.filter((_id, idx) => {
const meta = chromaResults.metadatas[idx];
return meta && meta.created_at_epoch > ninetyDaysAgo;
});
if (recentIds.length > 0) {
return this.sessionStore.getObservationsByIds(recentIds, { orderBy: 'date_desc', limit: 1 });
}
}
return [];
}
/** /**
* Helper to normalize query parameters from URL-friendly format * Helper to normalize query parameters from URL-friendly format
* Converts comma-separated strings to arrays and flattens date params * Converts comma-separated strings to arrays and flattens date params
@@ -439,24 +456,13 @@ export class SearchManager {
let results: ObservationSearchResult[] = []; let results: ObservationSearchResult[] = [];
if (this.chromaSync) { if (this.chromaSync) {
try {
logger.debug('SEARCH', 'Using hybrid semantic search for timeline query', {}); logger.debug('SEARCH', 'Using hybrid semantic search for timeline query', {});
const chromaResults = await this.queryChroma(query, 100);
logger.debug('SEARCH', 'Chroma returned semantic matches for timeline', { matchCount: chromaResults?.ids?.length ?? 0 });
if (chromaResults?.ids && chromaResults.ids.length > 0) {
const ninetyDaysAgo = Date.now() - SEARCH_CONSTANTS.RECENCY_WINDOW_MS; const ninetyDaysAgo = Date.now() - SEARCH_CONSTANTS.RECENCY_WINDOW_MS;
const recentIds = chromaResults.ids.filter((_id, idx) => { try {
const meta = chromaResults.metadatas[idx]; results = await this.searchChromaForTimeline(query, ninetyDaysAgo);
return meta && meta.created_at_epoch > ninetyDaysAgo;
});
if (recentIds.length > 0) {
results = this.sessionStore.getObservationsByIds(recentIds, { orderBy: 'date_desc', limit: 1 });
}
}
} catch (chromaError) { } catch (chromaError) {
logger.error('SEARCH', 'Chroma search failed for timeline, continuing without semantic results', {}, chromaError as Error); const errorObject = chromaError instanceof Error ? chromaError : new Error(String(chromaError));
logger.error('WORKER', 'Chroma search failed for timeline, continuing without semantic results', {}, errorObject);
} }
} }
@@ -689,18 +695,21 @@ export class SearchManager {
// Search for decision-type observations // Search for decision-type observations
if (this.chromaSync) { if (this.chromaSync) {
try {
if (query) { if (query) {
// Semantic search filtered to decision type // Semantic search filtered to decision type
logger.debug('SEARCH', 'Using Chroma semantic search with type=decision filter', {}); logger.debug('SEARCH', 'Using Chroma semantic search with type=decision filter', {});
try {
const chromaResults = await this.queryChroma(query, Math.min((filters.limit || 20) * 2, 100), { type: 'decision' }); const chromaResults = await this.queryChroma(query, Math.min((filters.limit || 20) * 2, 100), { type: 'decision' });
const obsIds = chromaResults.ids; const obsIds = chromaResults.ids;
if (obsIds.length > 0) { if (obsIds.length > 0) {
results = this.sessionStore.getObservationsByIds(obsIds, { ...filters, type: 'decision' }); results = this.sessionStore.getObservationsByIds(obsIds, { ...filters, type: 'decision' });
// Preserve Chroma ranking order
results.sort((a, b) => obsIds.indexOf(a.id) - obsIds.indexOf(b.id)); results.sort((a, b) => obsIds.indexOf(a.id) - obsIds.indexOf(b.id));
} }
} catch (chromaError) {
const errorObject = chromaError instanceof Error ? chromaError : new Error(String(chromaError));
logger.error('WORKER', 'Chroma search failed for decisions, falling back to metadata search', {}, errorObject);
}
} else { } else {
// No query: get all decisions, rank by "decision" keyword // No query: get all decisions, rank by "decision" keyword
logger.debug('SEARCH', 'Using metadata-first + semantic ranking for decisions', {}); logger.debug('SEARCH', 'Using metadata-first + semantic ranking for decisions', {});
@@ -708,6 +717,7 @@ export class SearchManager {
if (metadataResults.length > 0) { if (metadataResults.length > 0) {
const ids = metadataResults.map(obs => obs.id); const ids = metadataResults.map(obs => obs.id);
try {
const chromaResults = await this.queryChroma('decision', Math.min(ids.length, 100)); const chromaResults = await this.queryChroma('decision', Math.min(ids.length, 100));
const rankedIds: number[] = []; const rankedIds: number[] = [];
@@ -721,10 +731,11 @@ export class SearchManager {
results = this.sessionStore.getObservationsByIds(rankedIds, { limit: filters.limit || 20 }); results = this.sessionStore.getObservationsByIds(rankedIds, { limit: filters.limit || 20 });
results.sort((a, b) => rankedIds.indexOf(a.id) - rankedIds.indexOf(b.id)); results.sort((a, b) => rankedIds.indexOf(a.id) - rankedIds.indexOf(b.id));
} }
}
}
} catch (chromaError) { } catch (chromaError) {
logger.error('SEARCH', 'Chroma search failed for decisions, falling back to metadata search', {}, chromaError as Error); const errorObject = chromaError instanceof Error ? chromaError : new Error(String(chromaError));
logger.error('WORKER', 'Chroma semantic ranking failed for decisions, falling back to metadata search', {}, errorObject);
}
}
} }
} }
@@ -763,7 +774,6 @@ export class SearchManager {
// Search for change-type observations and change-related concepts // Search for change-type observations and change-related concepts
if (this.chromaSync) { if (this.chromaSync) {
try {
logger.debug('SEARCH', 'Using hybrid search for change-related observations', {}); logger.debug('SEARCH', 'Using hybrid search for change-related observations', {});
// Get all observations with type="change" or concepts containing change // Get all observations with type="change" or concepts containing change
@@ -777,6 +787,7 @@ export class SearchManager {
if (allIds.size > 0) { if (allIds.size > 0) {
const idsArray = Array.from(allIds); const idsArray = Array.from(allIds);
try {
const chromaResults = await this.queryChroma('what changed', Math.min(idsArray.length, 100)); const chromaResults = await this.queryChroma('what changed', Math.min(idsArray.length, 100));
const rankedIds: number[] = []; const rankedIds: number[] = [];
@@ -790,9 +801,10 @@ export class SearchManager {
results = this.sessionStore.getObservationsByIds(rankedIds, { limit: filters.limit || 20 }); results = this.sessionStore.getObservationsByIds(rankedIds, { limit: filters.limit || 20 });
results.sort((a, b) => rankedIds.indexOf(a.id) - rankedIds.indexOf(b.id)); results.sort((a, b) => rankedIds.indexOf(a.id) - rankedIds.indexOf(b.id));
} }
}
} catch (chromaError) { } catch (chromaError) {
logger.error('SEARCH', 'Chroma search failed for changes, falling back to metadata search', {}, chromaError as Error); const errorObject = chromaError instanceof Error ? chromaError : new Error(String(chromaError));
logger.error('WORKER', 'Chroma search failed for changes, falling back to metadata search', {}, errorObject);
}
} }
} }
@@ -1373,7 +1385,8 @@ export class SearchManager {
lines.push(`**Files Read:** ${filesRead.join(', ')}`); lines.push(`**Files Read:** ${filesRead.join(', ')}`);
} }
} catch (error) { } catch (error) {
logger.debug('WORKER', 'files_read is plain string, using as-is', {}, error as Error); const errorObject = error instanceof Error ? error : new Error(String(error));
logger.debug('WORKER', 'files_read is plain string, using as-is', {}, errorObject);
if (summary.files_read.trim()) { if (summary.files_read.trim()) {
lines.push(`**Files Read:** ${summary.files_read}`); lines.push(`**Files Read:** ${summary.files_read}`);
} }
@@ -1388,7 +1401,8 @@ export class SearchManager {
lines.push(`**Files Edited:** ${filesEdited.join(', ')}`); lines.push(`**Files Edited:** ${filesEdited.join(', ')}`);
} }
} catch (error) { } catch (error) {
logger.debug('WORKER', 'files_edited is plain string, using as-is', {}, error as Error); const errorObject = error instanceof Error ? error : new Error(String(error));
logger.debug('WORKER', 'files_edited is plain string, using as-is', {}, errorObject);
if (summary.files_edited.trim()) { if (summary.files_edited.trim()) {
lines.push(`**Files Edited:** ${summary.files_edited}`); lines.push(`**Files Edited:** ${summary.files_edited}`);
} }
src/services/worker/SessionManager.ts
+52 -5
View File
@@ -16,6 +16,7 @@ import { PendingMessageStore } from '../sqlite/PendingMessageStore.js';
import { SessionQueueProcessor } from '../queue/SessionQueueProcessor.js'; import { SessionQueueProcessor } from '../queue/SessionQueueProcessor.js';
import { getProcessBySession, ensureProcessExit } from './ProcessRegistry.js'; import { getProcessBySession, ensureProcessExit } from './ProcessRegistry.js';
import { getSupervisor } from '../../supervisor/index.js'; import { getSupervisor } from '../../supervisor/index.js';
import { MAX_CONSECUTIVE_SUMMARY_FAILURES } from '../../sdk/prompts.js';
/** Idle threshold before a stuck generator (zombie subprocess) is force-killed. */ /** Idle threshold before a stuck generator (zombie subprocess) is force-killed. */
export const MAX_GENERATOR_IDLE_MS = 5 * 60 * 1000; // 5 minutes export const MAX_GENERATOR_IDLE_MS = 5 * 60 * 1000; // 5 minutes
@@ -68,7 +69,13 @@ export function detectStaleGenerator(
if (proc && proc.exitCode === null) { if (proc && proc.exitCode === null) {
try { try {
proc.kill('SIGKILL'); proc.kill('SIGKILL');
} catch {} } catch (error) {
if (error instanceof Error) {
logger.warn('SESSION', 'Failed to SIGKILL stale generator subprocess', {}, error);
} else {
logger.warn('SESSION', 'Failed to SIGKILL stale generator subprocess with non-Error', {}, new Error(String(error)));
}
}
} }
// Signal the SDK agent loop to exit // Signal the SDK agent loop to exit
session.abortController.abort(); session.abortController.abort();
@@ -219,7 +226,10 @@ export class SessionManager {
currentProvider: null, // Will be set when generator starts currentProvider: null, // Will be set when generator starts
consecutiveRestarts: 0, // Track consecutive restart attempts to prevent infinite loops consecutiveRestarts: 0, // Track consecutive restart attempts to prevent infinite loops
processingMessageIds: [], // CLAIM-CONFIRM: Track message IDs for confirmProcessed() processingMessageIds: [], // CLAIM-CONFIRM: Track message IDs for confirmProcessed()
lastGeneratorActivity: Date.now() // Initialize for stale detection (Issue #1099) lastGeneratorActivity: Date.now(), // Initialize for stale detection (Issue #1099)
consecutiveSummaryFailures: 0, // Circuit breaker for summary retry loop (#1633)
pendingAgentId: null, // Subagent identity carried from the most recent claimed message
pendingAgentType: null // (null for main-session messages)
}; };
logger.debug('SESSION', 'Creating new session object (memorySessionId cleared to prevent stale resume)', { logger.debug('SESSION', 'Creating new session object (memorySessionId cleared to prevent stale resume)', {
@@ -275,7 +285,9 @@ export class SessionManager {
tool_input: data.tool_input, tool_input: data.tool_input,
tool_response: data.tool_response, tool_response: data.tool_response,
prompt_number: data.prompt_number, prompt_number: data.prompt_number,
cwd: data.cwd cwd: data.cwd,
agentId: data.agentId,
agentType: data.agentType
}; };
try { try {
@@ -286,10 +298,17 @@ export class SessionManager {
sessionId: sessionDbId sessionId: sessionDbId
}); });
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.error('SESSION', 'Failed to persist observation to DB', { logger.error('SESSION', 'Failed to persist observation to DB', {
sessionId: sessionDbId, sessionId: sessionDbId,
tool: data.tool_name tool: data.tool_name
}, error); }, error);
} else {
logger.error('SESSION', 'Failed to persist observation to DB with non-Error', {
sessionId: sessionDbId,
tool: data.tool_name
}, new Error(String(error)));
}
throw error; // Don't continue if we can't persist throw error; // Don't continue if we can't persist
} }
@@ -312,6 +331,18 @@ export class SessionManager {
session = this.initializeSession(sessionDbId); session = this.initializeSession(sessionDbId);
} }
// Circuit breaker: skip summarize if too many consecutive failures (#1633).
// This prevents the infinite loop where each failed summary spawns a new session
// with an ever-growing prompt. Counter is in-memory per ActiveSession — it resets
// on worker restart, which is acceptable because session state is already ephemeral.
if (session.consecutiveSummaryFailures >= MAX_CONSECUTIVE_SUMMARY_FAILURES) {
logger.warn('SESSION', `Circuit breaker OPEN: skipping summarize after ${session.consecutiveSummaryFailures} consecutive failures (#1633)`, {
sessionId: sessionDbId,
contentSessionId: session.contentSessionId
});
return;
}
// CRITICAL: Persist to database FIRST // CRITICAL: Persist to database FIRST
const message: PendingMessage = { const message: PendingMessage = {
type: 'summarize', type: 'summarize',
@@ -325,9 +356,15 @@ export class SessionManager {
sessionId: sessionDbId sessionId: sessionDbId
}); });
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.error('SESSION', 'Failed to persist summarize to DB', { logger.error('SESSION', 'Failed to persist summarize to DB', {
sessionId: sessionDbId sessionId: sessionDbId
}, error); }, error);
} else {
logger.error('SESSION', 'Failed to persist summarize to DB with non-Error', {
sessionId: sessionDbId
}, new Error(String(error)));
}
throw error; // Don't continue if we can't persist throw error; // Don't continue if we can't persist
} }
@@ -379,9 +416,15 @@ export class SessionManager {
try { try {
await getSupervisor().getRegistry().reapSession(sessionDbId); await getSupervisor().getRegistry().reapSession(sessionDbId);
} catch (error) { } catch (error) {
if (error instanceof Error) {
logger.warn('SESSION', 'Supervisor reapSession failed (non-blocking)', { logger.warn('SESSION', 'Supervisor reapSession failed (non-blocking)', {
sessionId: sessionDbId sessionId: sessionDbId
}, error as Error); }, error);
} else {
logger.warn('SESSION', 'Supervisor reapSession failed (non-blocking) with non-Error', {
sessionId: sessionDbId
}, new Error(String(error)));
}
} }
// 4. Cleanup // 4. Cleanup
@@ -451,7 +494,11 @@ export class SessionManager {
try { try {
trackedProcess.process.kill('SIGKILL'); trackedProcess.process.kill('SIGKILL');
} catch (err) { } catch (err) {
logger.warn('SESSION', 'Failed to SIGKILL subprocess for stale generator', { sessionDbId }, err as Error); if (err instanceof Error) {
logger.warn('SESSION', 'Failed to SIGKILL subprocess for stale generator', { sessionDbId }, err);
} else {
logger.warn('SESSION', 'Failed to SIGKILL subprocess for stale generator with non-Error', { sessionDbId }, new Error(String(err)));
}
} }
} }
// Signal the SDK agent loop to exit after the subprocess dies // Signal the SDK agent loop to exit after the subprocess dies
src/services/worker/SettingsManager.ts
+5 -1
View File
@@ -43,7 +43,11 @@ export class SettingsManager {
return settings; return settings;
} catch (error) { } catch (error) {
logger.debug('WORKER', 'Failed to load settings, using defaults', {}, error as Error); if (error instanceof Error) {
logger.debug('WORKER', 'Failed to load settings, using defaults', {}, error);
} else {
logger.debug('WORKER', 'Failed to load settings, using defaults', { rawError: String(error) });
}
return { ...this.defaultSettings }; return { ...this.defaultSettings };
} }
} }
src/services/worker/agents/ResponseProcessor.ts
+59 -4
View File
@@ -13,6 +13,7 @@
import { logger } from '../../../utils/logger.js'; import { logger } from '../../../utils/logger.js';
import { parseObservations, parseSummary, type ParsedObservation, type ParsedSummary } from '../../../sdk/parser.js'; import { parseObservations, parseSummary, type ParsedObservation, type ParsedSummary } from '../../../sdk/parser.js';
import { SUMMARY_MODE_MARKER, MAX_CONSECUTIVE_SUMMARY_FAILURES } from '../../../sdk/prompts.js';
import { updateCursorContextForProject } from '../../integrations/CursorHooksInstaller.js'; import { updateCursorContextForProject } from '../../integrations/CursorHooksInstaller.js';
import { updateFolderClaudeMdFiles } from '../../../utils/claude-md-utils.js'; import { updateFolderClaudeMdFiles } from '../../../utils/claude-md-utils.js';
import { getWorkerPort } from '../../../shared/worker-utils.js'; import { getWorkerPort } from '../../../shared/worker-utils.js';
@@ -67,7 +68,17 @@ export async function processAgentResponse(
// Parse observations and summary // Parse observations and summary
const observations = parseObservations(text, session.contentSessionId); const observations = parseObservations(text, session.contentSessionId);
const summary = parseSummary(text, session.sessionDbId);
// Detect whether the most recent prompt was a summary request.
// If so, enable observation-to-summary coercion to prevent the infinite
// retry loop described in #1633.
const lastMessage = session.conversationHistory.at(-1);
const lastUserMessage = lastMessage?.role === 'user'
? lastMessage
: session.conversationHistory.findLast(m => m.role === 'user') ?? null;
const summaryExpected = lastUserMessage?.content?.includes(SUMMARY_MODE_MARKER) ?? false;
const summary = parseSummary(text, session.sessionDbId, summaryExpected);
if ( if (
text.trim() && text.trim() &&
@@ -107,18 +118,36 @@ export async function processAgentResponse(
memorySessionId: session.memorySessionId memorySessionId: session.memorySessionId
}); });
// Label observations with the subagent identity captured from the claimed messages.
// Main-session messages leave these null, so main-session rows stay NULL in the DB.
const labeledObservations = observations.map(obs => ({
...obs,
agent_type: session.pendingAgentType ?? null,
agent_id: session.pendingAgentId ?? null
}));
// ATOMIC TRANSACTION: Store observations + summary ONCE // ATOMIC TRANSACTION: Store observations + summary ONCE
// Messages are already deleted from queue on claim, so no completion tracking needed // Messages are already deleted from queue on claim, so no completion tracking needed.
const result = sessionStore.storeObservations( // Wrap in try/finally so the subagent tracker clears even if storage throws —
// otherwise stale identity could leak into the next batch and mislabel rows.
// Expected invariant: all observations in a batch share the same agent context,
// because ResponseProcessor runs after a single agent-response cycle.
let result: ReturnType<typeof sessionStore.storeObservations>;
try {
result = sessionStore.storeObservations(
session.memorySessionId, session.memorySessionId,
session.project, session.project,
observations, labeledObservations,
summaryForStore, summaryForStore,
session.lastPromptNumber, session.lastPromptNumber,
discoveryTokens, discoveryTokens,
originalTimestamp ?? undefined, originalTimestamp ?? undefined,
modelId modelId
); );
} finally {
session.pendingAgentId = null;
session.pendingAgentType = null;
}
// Log storage result with IDs for end-to-end traceability // Log storage result with IDs for end-to-end traceability
logger.info('DB', `STORED | sessionDbId=${session.sessionDbId} | memorySessionId=${session.memorySessionId} | obsCount=${result.observationIds.length} | obsIds=[${result.observationIds.join(',')}] | summaryId=${result.summaryId || 'none'}`, { logger.info('DB', `STORED | sessionDbId=${session.sessionDbId} | memorySessionId=${session.memorySessionId} | obsCount=${result.observationIds.length} | obsIds=[${result.observationIds.join(',')}] | summaryId=${result.summaryId || 'none'}`, {
@@ -130,6 +159,32 @@ export async function processAgentResponse(
// to the Stop hook for silent-summary-loss detection (#1633) // to the Stop hook for silent-summary-loss detection (#1633)
session.lastSummaryStored = result.summaryId !== null; session.lastSummaryStored = result.summaryId !== null;
// Circuit breaker: track consecutive summary failures (#1633).
// Only evaluate when a summary was actually expected (summarize message was sent).
// Without this guard, the counter would increment on every normal observation
// response, tripping the breaker after 3 observations and permanently blocking
// summarization — reproducing the data-loss scenario this fix is meant to prevent.
if (summaryExpected) {
const skippedIntentionally = /<skip_summary\b/.test(text);
if (summaryForStore !== null) {
// Summary was present in the response — reset the failure counter
session.consecutiveSummaryFailures = 0;
} else if (skippedIntentionally) {
// Explicit <skip_summary/> is a valid protocol response — neither success
// nor failure. Leave the counter unchanged so we don't mask a bad run that
// happens to end on a skip, but also don't punish intentional skips.
} else {
// Summary was expected but none was stored — count as failure
session.consecutiveSummaryFailures += 1;
if (session.consecutiveSummaryFailures >= MAX_CONSECUTIVE_SUMMARY_FAILURES) {
logger.error('SESSION', `Circuit breaker: ${session.consecutiveSummaryFailures} consecutive summary failures — further summarize requests will be skipped (#1633)`, {
sessionId: session.sessionDbId,
contentSessionId: session.contentSessionId
});
}
}
}
// CLAIM-CONFIRM: Now that storage succeeded, confirm all processing messages (delete from queue) // CLAIM-CONFIRM: Now that storage succeeded, confirm all processing messages (delete from queue)
// This is the critical step that prevents message loss on generator crash // This is the critical step that prevents message loss on generator crash
const pendingStore = sessionManager.getPendingMessageStore(); const pendingStore = sessionManager.getPendingMessageStore();
src/services/worker/http/BaseRouteHandler.ts
+3 -2
View File
@@ -27,8 +27,9 @@ export abstract class BaseRouteHandler {
result.catch(error => this.handleError(res, error as Error)); result.catch(error => this.handleError(res, error as Error));
} }
} catch (error) { } catch (error) {
logger.error('HTTP', 'Route handler error', { path: req.path }, error as Error); const normalizedError = error instanceof Error ? error : new Error(String(error));
this.handleError(res, error as Error); logger.error('HTTP', 'Route handler error', { path: req.path }, normalizedError);
this.handleError(res, normalizedError);
} }
}; };
} }
src/services/worker/http/routes/CorpusRoutes.ts
+5 -1
View File
@@ -7,6 +7,7 @@
import express, { Request, Response } from 'express'; import express, { Request, Response } from 'express';
import { BaseRouteHandler } from '../BaseRouteHandler.js'; import { BaseRouteHandler } from '../BaseRouteHandler.js';
import { logger } from '../../../../utils/logger.js';
import { CorpusStore } from '../../knowledge/CorpusStore.js'; import { CorpusStore } from '../../knowledge/CorpusStore.js';
import { CorpusBuilder } from '../../knowledge/CorpusBuilder.js'; import { CorpusBuilder } from '../../knowledge/CorpusBuilder.js';
import { KnowledgeAgent } from '../../knowledge/KnowledgeAgent.js'; import { KnowledgeAgent } from '../../knowledge/KnowledgeAgent.js';
@@ -93,7 +94,10 @@ export class CorpusRoutes extends BaseRouteHandler {
if (typeof value === 'string') { if (typeof value === 'string') {
try { try {
parsed = JSON.parse(value); parsed = JSON.parse(value);
} catch { } catch (parseError: unknown) {
if (parseError instanceof Error) {
logger.debug('HTTP', `${fieldName} is not valid JSON, treating as comma-separated string`, { value });
}
parsed = value.split(',').map(part => part.trim()).filter(Boolean); parsed = value.split(',').map(part => part.trim()).filter(Boolean);
} }
} }

Some files were not shown because too many files have changed in this diff Show More