Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 9e044021ef test(supervisor): update runner fixture mock for #2750 lock path
tryAcquireDbLock now acquires via engine.executeRaw (signal-boundable)
and releases via engine.executeRawDirect instead of the sql tagged
template. The fixture's mock engine returned [] from executeRaw, so
every spawned supervisor failed lock acquisition and exited LOCK_HELD
(2), breaking all 8 supervisor integration tests. The mock now returns
the lock row for gbrain_cycle_locks queries and stubs executeRawDirect.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:53:10 -07:00
553515c82c fix(cycle): enforce the extract-atoms drain deadline end to end (#2750)
The drain window was only checked BETWEEN batches: one batch (sequential
LLM calls per page) plus lock acquire/release and the backlog count ran
unbounded, so window=120s runs were observed overrunning to 282.5s.

The drain now derives a real-time deadline signal (window timeout + the
Minion job.signal) and threads it through everything the loop awaits:

- extract-atoms-drain: signal-driven loop; hung count/batch/lock-acquire
  are cancelled at the deadline; no post-window final count (remaining
  reports null instead of overrunning); external worker abort rethrows
  after the lock is released.
- extract-atoms phase: abortSignal forwarded to every gateway chat call,
  discovery/count/idempotency queries, and putPage writes, plus a
  cooperative between-item check (the bound on PGLite, whose query abort
  only abandons the waiter — the default engine keeps a working drain).
  Billable usage is recorded before the post-chat abort check; receipt +
  rollup bookkeeping runs on a fresh 5s grace signal so committed atoms
  never lose their cost trail; deadline-truncated runs don't count as
  completed rounds (deadline_aborted detail).
- db-lock: tryAcquireDbLock/withRefreshingLock accept a deadline signal;
  release routes through the direct session pool with a fresh grace
  timeout; deadline-bound callers skip the unbounded same-host takeover
  path (honest busy result; TTL stays the backstop).
- engines: putPage accepts an optional signal (Postgres cancels the
  in-flight statement; PGLite pre-checks); executeRawDirect short-circuits
  an already-fired signal before pool routing and bounds a stalled
  direct-pool acquisition.

Takeover of PR #2752: keeps its signal-threading design, but retains the
putPage write path (so the chunker_version default from #2988 applies —
the PR's bulk INSERT bypassed it), drops the PGLite hard refusal in favor
of cooperative abort, and reverts the unsanctioned transcript-suppression
scope change (_transcripts: []).

Fixes #2750

Co-authored-by: panda850819 <panda850819@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:41:34 -07:00
25 changed files with 622 additions and 583 deletions
+1 -3
View File
@@ -1411,8 +1411,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
| Save or load reports | `skills/reports/SKILL.md` |
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -1430,7 +1429,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
+2 -3
View File
@@ -39,8 +39,8 @@
"skills/briefing",
"skills/citation-fixer",
"skills/concept-synthesis",
"skills/cron-scheduler",
"skills/cross-modal-review",
"skills/cron-scheduler",
"skills/daily-task-manager",
"skills/daily-task-prep",
"skills/data-research",
@@ -54,11 +54,10 @@
"skills/media-ingest",
"skills/meeting-ingestion",
"skills/minion-orchestrator",
"skills/obsidian-gbrain-safe-index",
"skills/perplexity-research",
"skills/query",
"skills/repo-architecture",
"skills/reports",
"skills/repo-architecture",
"skills/signal-detector",
"skills/skill-creator",
"skills/skillify",
+1 -3
View File
@@ -60,8 +60,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
| Save or load reports | `skills/reports/SKILL.md` |
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -79,7 +78,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
+1 -11
View File
@@ -2,7 +2,7 @@
"name": "gbrain",
"version": "0.32.3.0",
"conformance_version": "1.0.0",
"description": "Personal knowledge brain with hybrid RAG search GStack mod for agent platforms",
"description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
"skills": [
{
"name": "ingest",
@@ -34,11 +34,6 @@
"path": "migrate/SKILL.md",
"description": "Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam"
},
{
"name": "obsidian-gbrain-safe-index",
"path": "obsidian-gbrain-safe-index/SKILL.md",
"description": "Connect and sync an Obsidian-style Markdown vault with gbrain using a cost-controlled import-first workflow, explicit embedding gates, and durable skill/workflow capture."
},
{
"name": "setup",
"path": "setup/SKILL.md",
@@ -268,11 +263,6 @@
"name": "skill-optimizer",
"path": "skill-optimizer/SKILL.md",
"description": "Self-evolving skill optimization via gbrain skillopt — SkillOpt-paper-grounded text-space optimizer with validation gating (median-of-3 + epsilon=0.05), bundled-skill safety, bootstrap review sentinel, per-skill DB lock, and atomic versioned writes."
},
{
"name": "skill-vault-capture-policy",
"path": "skill-vault-capture-policy/SKILL.md",
"description": "Capture durable operational learnings, new agent skills, and environment/setup changes into the Obsidian vault instead of transient chat memory."
}
],
"dependencies": {
-137
View File
@@ -1,137 +0,0 @@
---
name: obsidian-gbrain-safe-index
version: 1.0.0
description: |
Connect, maintain, and sync an Obsidian-style Markdown vault with gbrain while preserving a cost-controlled workflow: the vault remains the source of truth, gbrain is the searchable/embedded index, durable skills/workflows are captured into the vault, and paid embedding runs only after explicit approval.
triggers:
- "connect Obsidian to gbrain"
- "import my vault to gbrain"
- "sync vault and gbrain"
- "capture this skill in my vault"
- "embed gbrain after vault update"
- "is gbrain synced with my vault"
tools:
- terminal
- read_file
- search_files
- write_file
- patch
mutating: true
---
# Obsidian → gbrain Safe Index and Capture
## Contract
This skill guarantees:
- Treats the user's Obsidian-style Markdown vault as the source of truth before gbrain indexing.
- Keeps gbrain in conservative mode unless the user explicitly approves a more expensive mode.
- Imports vault changes with `--no-embed` first, then embeds only after explicit approval for the specific paid action.
- Captures durable new skills, workflows, and environment learnings into the vault instead of leaving them only in chat memory.
- Verifies every sync with concrete `gbrain stats`, search mode, and, when embeddings run, exact embedded chunk counts.
## Phases
1. **Resolve the vault path.**
- Prefer an existing environment variable such as `OBSIDIAN_VAULT_PATH` or `WIKI_PATH`.
- If no path is configured, search likely note directories and ask the user before writing.
- Verify the directory exists and contains markdown files or an `.obsidian` directory.
2. **Read vault operating rules before writing.**
- If the vault has `SCHEMA.md`, `index.md`, `log.md`, `AGENTS.md`, or similar operating files, read them before ingest/query/major edit.
- Respect immutable source folders such as `raw/` when the vault declares them.
- Use the vault's native link convention, usually Obsidian `[[wikilinks]]`, for durable relationships.
3. **MECE/capture decision.**
- If new knowledge belongs on an existing page, update that page.
- If it is a distinct recurring workflow or operational policy, create a small meta or concept page following the vault schema.
- Update the vault index/catalog for every new page when the vault maintains one.
- Append a log entry for meaningful vault updates when the vault maintains a log.
4. **Safe gbrain import path.**
- Pre-check source directory; do not import a nonexistent path.
- Run `gbrain config set search.mode conservative` before/after risky reinit steps.
- Run `gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed`.
- Run `gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"` when wikilinks changed materially.
5. **Paid embedding gate.**
- Do not run `gbrain embed --stale` unless the user explicitly asks or a prior instruction clearly approved this exact paid action.
- Before embedding, verify provider readiness with `gbrain providers test --model <provider:model>`.
- Confirm the configured embedding dimensions match the local schema.
- After embedding, verify `gbrain stats` and record exact `Pages`, `Chunks`, `Embedded`, and `Links` counts.
6. **Final verification and vault echo.**
- Run `gbrain stats` and `gbrain search modes`.
- If vault files changed, re-import with `--no-embed`; if embedding was approved, embed stale chunks afterward.
- Report what changed, what was free/local, what used API billing, and what remains pending.
## Output Format
Use a compact status table:
| Item | Status |
|---|---|
| Vault path | `/path` |
| Vault updated | yes/no + files |
| gbrain mode | conservative/balanced/tokenmax |
| Import | `--no-embed` completed / skipped / failed |
| Pages/chunks | exact counts from `gbrain stats` |
| Embeddings | exact count; note whether this run used API billing |
| Links | exact count |
| Background jobs | none / list exact jobs |
Then include:
- **Safe next step:** free/local action.
- **Paid next step:** embedding/LLM action, if any, with explicit approval requirement.
## Anti-Patterns
- Creating a duplicate skill/page when an existing Obsidian, gbrain, or vault-ingest skill already covers the workflow.
- Running `gbrain embed --stale`, `gbrain dream`, `gbrain autopilot --install`, `gbrain onboard --auto`, or `tokenmax` without explicit cost approval.
- Importing a nonexistent or wrong directory and treating a zero-page import as success.
- Forgetting to update the vault index/catalog and log after creating or materially updating vault pages.
- Recording API keys, tokens, or raw secrets in the vault or final response.
## Tools Used
- `read_file` — read vault schema/index/log and target notes.
- `search_files` — find existing vault pages and avoid duplicates.
- `write_file` / `patch` — create or update vault pages.
- `terminal` — run `gbrain`, `git`, and environment checks with secret values redacted.
## Safe Commands
```bash
export PATH="$HOME/.bun/bin:$PATH"
gbrain config set search.mode conservative
gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed
gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"
gbrain stats
gbrain search modes
```
## Paid / Approval-Gated Commands
```bash
gbrain providers test --model <provider:model>
gbrain embed --stale
gbrain dream
gbrain autopilot --install
gbrain onboard --auto --max-usd 5
gbrain config set search.mode tokenmax
```
## Verification Checklist
- [ ] Vault path exists and is the intended source.
- [ ] Vault operating files were read before edits when present.
- [ ] Existing pages/skills were searched to avoid duplicates.
- [ ] New/updated vault pages follow the vault schema and link convention.
- [ ] Vault index/catalog updated for new pages when present.
- [ ] Vault log appended for meaningful actions when present.
- [ ] `gbrain import ... --no-embed` completed.
- [ ] `gbrain stats` recorded pages/chunks/embeddings/links.
- [ ] `gbrain search modes` confirms conservative mode unless a different mode was explicitly approved.
- [ ] No paid/background commands ran without approval.
@@ -1,11 +0,0 @@
// Routing eval fixtures for skills/obsidian-gbrain-safe-index.
// Positive cases: intents embed a trigger phrase in natural surrounding context
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
{"intent": "help me connect Obsidian to gbrain for my notes", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "import my vault to gbrain but skip embeddings for now", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "please sync vault and gbrain after I edit notes", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "run embed gbrain after vault update tonight", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "hey is gbrain synced with my vault right now", "expected_skill": "obsidian-gbrain-safe-index"}
// Negative cases: related but owned by other skills. Assert NO route to this skill.
{"intent": "migrate my notes from Notion to gbrain", "expected_skill": null}
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
-100
View File
@@ -1,100 +0,0 @@
---
name: skill-vault-capture-policy
version: 1.0.0
description: |
Use when the user wants a durable operational learning, new agent skill, or
important environment/setup change to be captured into the Obsidian vault
instead of left only in transient chat memory. Covers the capture rule,
preferred page patterns, and index/log update obligations.
triggers:
- "save this learning to the vault"
- "capture this skill in Obsidian"
- "record this workflow in my notes"
- "put this setup change in the vault"
- "should we add this to the knowledge base"
tools:
- read_file
- search_files
- write_file
- patch
mutating: true
---
# Skill Vault Capture Policy
## Contract
This skill guarantees:
- Durable operational learnings, newly adopted skills, and important environment/setup changes are captured into the Obsidian vault rather than left only in chat memory.
- An existing page is updated when the knowledge clearly belongs there; a new page is created only when the topic is distinct and likely to recur.
- Every new vault page is added to `index.md`.
- Every meaningful create/update appends a dated entry to `log.md`.
- Small linked pages are preferred over one giant running note.
## Phases
1. **Classify the learning.**
- New gbrain operating rule, cost control, or embedding/provider change.
- New agent-fork / harness / coding-tool integration fact.
- New Obsidian vault workflow or structure decision.
- New recurring agent skill that changes how the agent should operate here.
2. **Avoid duplicates.**
- Search the vault for an existing page that already owns the topic.
- If found, update it with a new section or dated note rather than creating a near-duplicate.
3. **Create when distinct.**
- Place new pages under the vault schema: `_meta/` for operating notes, `concepts/` for workflows, `entities/` for tools/people.
- Use YAML frontmatter and at least two `[[wikilinks]]` unless it is a short seed page.
4. **Update navigation.**
- Add the page to `index.md` under the correct type heading.
- Append a `## [YYYY-MM-DD] create|update | subject` entry to `log.md`.
5. **Report the capture.**
- State which files changed and whether `index.md` / `log.md` were updated.
## Output Format
Use a short status block:
| Item | Status |
|---|---|
| Learning classified | type |
| Page created/updated | path |
| index.md updated | yes/no |
| log.md updated | yes/no |
## Anti-Patterns
- Leaving durable learnings only in chat memory.
- Creating a near-duplicate page instead of updating the existing one.
- Forgetting to update `index.md` and `log.md`.
- Writing one giant running note instead of small linked pages.
- Recording secrets, API keys, or raw credentials in the vault.
## Tools Used
- `read_file` — read `SCHEMA.md`, `index.md`, `log.md`, and target pages.
- `search_files` — find existing pages to avoid duplicates.
- `write_file` / `patch` — create or update vault pages and navigation.
## Safe Commands
```bash
# inspect vault navigation before writing
read SCHEMA.md index.md log.md
# create or update a page, then refresh catalog/log
# index.md: add [[page-slug]] under the matching type heading
# log.md: append ## [YYYY-MM-DD] create|update | subject
```
## Verification Checklist
- [ ] Vault schema/read files were checked before writing.
- [ ] Existing pages were searched to avoid duplicates.
- [ ] New/updated page has frontmatter and wikilinks.
- [ ] `index.md` updated for new pages.
- [ ] `log.md` appended for meaningful actions.
- [ ] No secrets or raw credentials were written.
@@ -1,10 +0,0 @@
// Routing eval fixtures for skills/skill-vault-capture-policy.
// Positive cases: intents embed a trigger phrase in natural surrounding context
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
{"intent": "please save this learning to the vault so we keep it", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["idea-ingest"]}
{"intent": "we should capture this skill in Obsidian for reuse", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["capture"]}
{"intent": "can you record this workflow in my notes for next time", "expected_skill": "skill-vault-capture-policy"}
{"intent": "put this setup change in the vault before we forget", "expected_skill": "skill-vault-capture-policy"}
// Negative cases: related but owned by other skills or out of scope.
{"intent": "connect my Obsidian vault to gbrain", "expected_skill": null}
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
+2
View File
@@ -2059,6 +2059,8 @@ export async function registerBuiltinHandlers(
sourceId,
windowSeconds,
brainDir: repoPath,
// #2750: worker cancel/timeout/lock-loss propagates into the drain.
abortSignal: job.signal,
});
} catch (e) {
if (e instanceof LockUnavailableError) {
+77 -16
View File
@@ -23,6 +23,10 @@
*/
import type { BrainEngine } from '../engine.ts';
import { anySignal } from '../abort-check.ts';
/** Fresh cleanup budget for the lock release after the window signal fires. */
const LOCK_RELEASE_GRACE_MS = 5_000;
export interface ExtractAtomsDrainDeps {
/**
@@ -30,13 +34,13 @@ export interface ExtractAtomsDrainDeps {
* via `withRefreshingLock`. MUST throw when the lock is held by another
* process (e.g. `LockUnavailableError`) — the drain lets that propagate so
* the caller can report `cycle_already_running` and exit, matching the
* routine cycle's skip contract.
* routine cycle's skip contract. The signal bounds lock acquisition too.
*/
withLock: <T>(work: () => Promise<T>) => Promise<T>;
/** Process one bounded batch (rediscovers eligibility). Returns counts. */
runBatch: () => Promise<{ extracted: number; skipped: number }>;
withLock: <T>(work: () => Promise<T>, signal: AbortSignal) => Promise<T>;
/** Process one batch. The signal fires at the drain wallclock deadline. */
runBatch: (signal: AbortSignal) => Promise<{ extracted: number; skipped: number }>;
/** Count remaining eligible-but-unextracted pages, or null on query error. */
countRemaining: () => Promise<number | null>;
countRemaining: (signal: AbortSignal) => Promise<number | null>;
/** Injectable clock. Production: Date.now. */
now: () => number;
/** Optional progress sink (one line per batch). */
@@ -48,6 +52,8 @@ export interface ExtractAtomsDrainOpts {
windowMs: number;
/** Hard cap on batches (belt-and-suspenders against a 0-progress loop). Default 1000. */
maxBatches?: number;
/** External caller cancellation (worker timeout / shutdown). */
abortSignal?: AbortSignal;
}
export interface ExtractAtomsDrainResult {
@@ -68,35 +74,79 @@ export async function runExtractAtomsDrain(
opts: ExtractAtomsDrainOpts,
): Promise<ExtractAtomsDrainResult> {
const maxBatches = opts.maxBatches ?? 1000;
return deps.withLock(async () => {
const deadline = deps.now() + opts.windowMs;
const deadline = deps.now() + opts.windowMs;
// #2750: the window used to be checked only BETWEEN batches, so one slow
// batch (sequential LLM calls) or a hung lock/count/write overran it without
// bound (observed window=120s → 282.5s). A real-time deadline signal now
// cancels (Postgres) or abandons (PGLite, cooperative) whatever is in
// flight; the injected clock still drives loop-boundary checks so the pure
// loop stays unit-testable.
const signal = anySignal(
AbortSignal.timeout(Math.max(1, opts.windowMs)),
opts.abortSignal,
);
const result: ExtractAtomsDrainResult = await deps.withLock(async () => {
let extracted = 0;
let skipped = 0;
let batches = 0;
let stopped: ExtractAtomsDrainResult['stopped'] = 'window';
while (deps.now() < deadline) {
while (deps.now() < deadline && !signal.aborted) {
if (batches >= maxBatches) { stopped = 'max_batches'; break; }
const before = await deps.countRemaining();
let before: number | null;
try {
before = await deps.countRemaining(signal);
} catch (err) {
if (signal.aborted) break;
throw err;
}
if (before === 0) { stopped = 'drained'; break; }
const r = await deps.runBatch();
// The backlog count consumed the same wallclock budget — re-check so a
// slow count can't hand the batch a window that already expired.
if (deps.now() >= deadline || signal.aborted) break;
let r: { extracted: number; skipped: number };
try {
r = await deps.runBatch(signal);
} catch (err) {
if (signal.aborted) break;
throw err;
}
extracted += r.extracted;
skipped += r.skipped;
batches++;
deps.onBatch?.({ batch: batches, extracted: r.extracted, remaining: before });
// A deadline abort inside the batch can surface as zero progress;
// window exhaustion wins over the generic no_progress label.
if (deps.now() >= deadline || signal.aborted) break;
// Stop if a batch made zero forward progress — extraction is failing or
// everything left is ineligible (e.g. all skipped). Prevents a hot loop
// that spends budget without draining.
if (r.extracted === 0 && r.skipped === 0) { stopped = 'no_progress'; break; }
}
const remaining = await deps.countRemaining();
// After the window elapsed, don't spend more unbounded time on a final
// count — report remaining as unknown instead of overrunning further.
const windowElapsed = signal.aborted || deps.now() >= deadline;
let remaining: number | null = null;
if (!windowElapsed) {
try {
remaining = await deps.countRemaining(signal);
} catch (err) {
if (!signal.aborted) throw err;
}
}
if (remaining === 0) stopped = 'drained';
return { phase: 'extract_atoms', status: 'ok', extracted, skipped, remaining, batches, stopped };
});
}, signal);
// Internal window expiry is a normal partial result. An EXTERNAL abort
// (worker cancel/timeout/shutdown) must reject so Minion records the abort.
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
return result;
}
// ─── Shared wiring helper (v0.42.x #1685 DECISION 5A) ──────────────────────
@@ -134,6 +184,8 @@ export interface DrainForSourceOpts {
maxBatches?: number;
/** Optional per-batch progress sink (stderr line in dream; job progress in the handler). */
onBatch?: ExtractAtomsDrainDeps['onBatch'];
/** Worker cancellation / shutdown signal (Minion `job.signal`). */
abortSignal?: AbortSignal;
}
export async function runExtractAtomsDrainForSource(
@@ -149,12 +201,17 @@ export async function runExtractAtomsDrainForSource(
return runExtractAtomsDrain(
{
withLock: (work) => withRefreshingLock(engine, lockId, work, { ttlMinutes: 5 }),
runBatch: async () => {
withLock: (work, signal) => withRefreshingLock(engine, lockId, work, {
ttlMinutes: 5,
signal,
releaseTimeoutMs: LOCK_RELEASE_GRACE_MS,
}),
runBatch: async (signal) => {
const r = await runPhaseExtractAtoms(engine, {
sourceId: extractionSourceId,
dryRun: false,
brainDir: opts.brainDir,
abortSignal: signal,
});
const d = (r.details ?? {}) as Record<string, unknown>;
return {
@@ -162,10 +219,14 @@ export async function runExtractAtomsDrainForSource(
skipped: Number(d.duplicates_skipped ?? 0),
};
},
countRemaining: () => countExtractAtomsBacklog(engine, extractionSourceId),
countRemaining: (signal) => countExtractAtomsBacklog(engine, extractionSourceId, signal),
now: Date.now,
onBatch: opts.onBatch,
},
{ windowMs: opts.windowSeconds * 1000, maxBatches: opts.maxBatches },
{
windowMs: opts.windowSeconds * 1000,
maxBatches: opts.maxBatches,
abortSignal: opts.abortSignal,
},
);
}
+68 -17
View File
@@ -58,6 +58,10 @@ import { createHash } from 'crypto';
import { slugifySegment } from '../sync.ts';
const DEFAULT_BUDGET_USD = 0.3;
// #2750: fresh wallclock budget for the receipt/rollup bookkeeping writes when
// the caller's deadline already fired — committed atoms must not lose their
// cost/receipt trail, but the writes can't be unbounded either.
const BOOKKEEPING_GRACE_MS = 5_000;
// v0.42+ TODO: read atom_type enum from active pack manifest at runtime.
const ATOM_TYPES = [
@@ -155,6 +159,13 @@ export interface ExtractAtomsOpts {
* `heartbeat()` on the passed reporter.
*/
progress?: ProgressReporter;
/**
* #2750: caller deadline/cancellation. Forwarded to every gateway call and
* DB query/write so the drain window bounds real lifetime, plus a
* cooperative between-item check (the PGLite path, where query abort only
* abandons the waiter).
*/
abortSignal?: AbortSignal;
}
interface ExtractedAtom {
@@ -212,6 +223,7 @@ export async function discoverExtractablePages(
engine: BrainEngine,
sourceId: string,
affectedSlugs?: string[],
abortSignal?: AbortSignal,
): Promise<DiscoveredPage[]> {
const hasFilter = Array.isArray(affectedSlugs) && affectedSlugs.length > 0;
const sql = `
@@ -251,13 +263,16 @@ export async function discoverExtractablePages(
slug: string;
compiled_truth: string;
content_hash: string;
}>(sql, params);
}>(sql, params, { signal: abortSignal });
return rows.map((r) => ({
slug: r.slug,
content: r.compiled_truth,
contentHash: r.content_hash,
}));
} catch (err) {
// A deadline abort is not a fail-soft condition — propagate so the
// caller stops instead of proceeding with an empty page list.
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] page-discovery query failed: ${msg}`);
return []; // fail-soft: transcript path still proceeds
@@ -282,6 +297,7 @@ export async function discoverExtractablePages(
export async function countExtractAtomsBacklog(
engine: BrainEngine,
sourceId?: string,
abortSignal?: AbortSignal,
): Promise<number | null> {
try {
// Two modes: scoped (the phase's per-source `remaining`) vs brain-wide
@@ -321,9 +337,10 @@ export async function countExtractAtomsBacklog(
const params = scoped
? [sourceId, extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION]
: [extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION];
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params);
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params, { signal: abortSignal });
return Number(rows[0]?.cnt ?? 0);
} catch (err) {
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] backlog count failed: ${msg}`);
return null;
@@ -350,6 +367,7 @@ export async function atomsExistingForHashes(
engine: BrainEngine,
sourceId: string,
contentHash16s: string[],
abortSignal?: AbortSignal,
): Promise<Set<string>> {
if (contentHash16s.length === 0) return new Set();
try {
@@ -361,9 +379,11 @@ export async function atomsExistingForHashes(
AND deleted_at IS NULL
AND frontmatter->>'source_hash' = ANY($2::text[])`,
[sourceId, contentHash16s],
{ signal: abortSignal },
);
return new Set(rows.map(r => r.h));
} catch (err) {
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] batch idempotency check failed (assuming none extracted): ${msg}`);
return new Set();
@@ -384,6 +404,7 @@ export async function runPhaseExtractAtoms(
): Promise<PhaseResult> {
const sourceId = opts.sourceId ?? 'default';
const chat = opts._chat ?? gatewayChat;
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
// 1a. Get transcripts (test seam OR production discovery).
// v0.41.2.1: config loader switched to loadConfigWithEngine() so the
@@ -425,7 +446,7 @@ export async function runPhaseExtractAtoms(
if (opts._pages !== undefined) {
pages = opts._pages;
} else {
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs);
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs, opts.abortSignal);
}
// 2. Apply transcript-side source-hash idempotency in ONE batch query
@@ -437,7 +458,7 @@ export async function runPhaseExtractAtoms(
// Surface a heartbeat before the batch query so even an instant
// short-circuit shows a sign of life (closes Issue 2 silent-phase pain).
opts.progress?.heartbeat(`checking existing atoms for ${allHashes16.length} transcripts`);
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16);
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16, opts.abortSignal);
for (const t of transcripts) {
if (existingHashes.has(t.contentHash.slice(0, 16))) {
duplicatesSkipped++;
@@ -501,6 +522,7 @@ export async function runPhaseExtractAtoms(
const failures: Array<{ source: string; error: string }> = [];
let estimatedSpendUsd = 0;
const budgetCap = DEFAULT_BUDGET_USD;
let deadlineAborted = false;
// v0.41.19.0 (T3): throttled yield helper. Fires `opts.yieldDuringPhase`
// every 30s. Cycle.ts threads `buildYieldDuringPhase(lock, outer)` so
@@ -526,6 +548,12 @@ export async function runPhaseExtractAtoms(
}
for (const item of work) {
// #2750: cooperative between-item abort. Works on every engine — this is
// the primary bound on PGLite, where query abort only abandons the waiter.
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
await maybeYield();
if (estimatedSpendUsd >= budgetCap) {
if (item.kind === 'transcript') transcriptsSkipped++;
@@ -544,16 +572,22 @@ export async function runPhaseExtractAtoms(
},
],
maxTokens: 2000,
abortSignal: opts.abortSignal,
});
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output.
// A completed gateway call is billable even if the deadline fires
// immediately afterward, so record usage BEFORE the abort check.
estimatedSpendUsd +=
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
// Post-await yield: closes the "long LLM call past TTL" hazard
// codex flagged. The 30s throttle inside maybeYield bounds the
// actual refresh rate so this is cheap when calls are fast.
await maybeYield();
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output
estimatedSpendUsd +=
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
const atoms = parseAtomsResponse(result.text);
if (atoms.length === 0) {
if (item.kind === 'transcript') transcriptsProcessed++;
@@ -592,7 +626,7 @@ export async function runPhaseExtractAtoms(
},
timeline: '',
},
{ sourceId },
{ sourceId, signal: opts.abortSignal },
);
totalAtomsExtracted++;
}
@@ -605,6 +639,11 @@ export async function runPhaseExtractAtoms(
// Reporter rate-limits to ~1 line/sec; safe to tick every iter.
opts.progress?.tick(1, `${totalAtomsExtracted} atoms / ${duplicatesSkipped} skipped`);
} catch (err) {
// A deadline abort is a partial result, not a per-item failure.
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
failures.push({
source: originLabel,
error: err instanceof Error ? err.message : String(err),
@@ -615,6 +654,12 @@ export async function runPhaseExtractAtoms(
// v0.42 Wave B2: write extract receipt + rollup row when the phase
// actually extracted atoms. Both are best-effort per F-OUT-19 —
// audit-trail / search-visibility surfaces don't block the phase result.
//
// #2750: bookkeeping runs on a FRESH short grace signal, never the caller's
// work deadline — the deadline may have already fired (partial run) and
// committed atoms must not lose their receipt/cost trail; but the writes
// stay bounded so the overrun is capped at the grace window.
const bookkeepingSignal = opts.dryRun ? undefined : AbortSignal.timeout(BOOKKEEPING_GRACE_MS);
if (!opts.dryRun && totalAtomsExtracted > 0) {
const runId = `atoms-${Date.now().toString(36)}-${sourceId.slice(0, 4)}`;
try {
@@ -629,19 +674,24 @@ export async function runPhaseExtractAtoms(
summary:
`Extracted ${totalAtomsExtracted} atoms from ` +
`${transcriptsProcessed} transcripts + ${pagesProcessed} pages.`,
});
}, { signal: bookkeepingSignal });
} catch (err) {
console.error(`[extract_atoms] receipt write failed: ${(err as Error).message}`);
}
}
if (!opts.dryRun) {
await upsertExtractRollup(engine, {
kind: 'atoms',
source_id: sourceId,
cost_delta: estimatedSpendUsd,
round_completed_delta: failures.length === 0 ? 1 : 0,
halt_delta: failures.length > 0 ? 1 : 0,
});
try {
await upsertExtractRollup(engine, {
kind: 'atoms',
source_id: sourceId,
cost_delta: estimatedSpendUsd,
// A deadline-truncated run is not a completed round.
round_completed_delta: failures.length === 0 && !deadlineAborted ? 1 : 0,
halt_delta: failures.length > 0 ? 1 : 0,
}, { signal: bookkeepingSignal });
} catch (err) {
console.error(`[extract_atoms] rollup write failed: ${(err as Error).message}`);
}
}
return {
@@ -670,6 +720,7 @@ export async function runPhaseExtractAtoms(
budget_usd: budgetCap,
source_id: sourceId,
dry_run: opts.dryRun ?? false,
deadline_aborted: deadlineAborted,
},
};
}
+50 -22
View File
@@ -26,7 +26,8 @@ import type { BrainEngine } from './engine.ts';
export interface DbLockHandle {
id: string;
release: () => Promise<void>;
/** Optional signal bounds the release DELETE (deadline-bound callers). */
release: (signal?: AbortSignal) => Promise<void>;
refresh: () => Promise<void>;
}
@@ -173,6 +174,7 @@ export async function tryAcquireDbLock(
engine: BrainEngine,
lockId: string,
ttlMinutes: number = DEFAULT_TTL_MINUTES,
opts: { signal?: AbortSignal } = {},
): Promise<DbLockHandle | null> {
const pid = process.pid;
const host = hostname();
@@ -205,20 +207,26 @@ export async function tryAcquireDbLock(
// `gbrain sync --break-lock --max-age <s>` uses last_refreshed_at (not
// acquired_at) to identify wedged-but-alive holders without stealing
// healthy long-running holders that are actively refreshing.
const rows: Array<{ id: string }> = await sql`
INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES (${lockId}, ${pid}, ${host}, NOW(), NOW() + ${ttl}::interval, NOW())
ON CONFLICT (id) DO UPDATE
SET holder_pid = ${pid},
holder_host = ${host},
acquired_at = NOW(),
ttl_expires_at = NOW() + ${ttl}::interval,
last_refreshed_at = NOW()
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
OR gbrain_cycle_locks.last_refreshed_at < NOW() - ${stealGraceSeconds} * INTERVAL '1 second')
RETURNING id
`;
// #2750: routed through executeRaw so a deadline-bound caller's signal
// can cancel a hung acquire (pool exhaustion). Cancellation is
// transactional; in the rare ambiguous-commit case the row's TTL is the
// backstop (drain locks use a short 5-minute TTL).
const rows = await engine.executeRaw<{ id: string }>(
`INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES ($1, $2, $3, NOW(), NOW() + $4::interval, NOW())
ON CONFLICT (id) DO UPDATE
SET holder_pid = $2,
holder_host = $3,
acquired_at = NOW(),
ttl_expires_at = NOW() + $4::interval,
last_refreshed_at = NOW()
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
OR gbrain_cycle_locks.last_refreshed_at < NOW() - $5 * INTERVAL '1 second')
RETURNING id`,
[lockId, pid, host, ttl, stealGraceSeconds],
{ signal: opts.signal },
);
if (rows.length === 0) return null;
const deregister = registerCleanup(`db-lock:${lockId}`, async () => {
await sql`
@@ -241,12 +249,17 @@ export async function tryAcquireDbLock(
[ttl, lockId, pid],
);
},
release: async () => {
release: async (signal?: AbortSignal) => {
deregister();
await sql`
DELETE FROM gbrain_cycle_locks
WHERE id = ${lockId} AND holder_pid = ${pid}
`;
// Direct session pool (same rationale as refresh, #1794) + optional
// signal so a deadline-bound caller's release can't hang forever on
// an exhausted pooler. TTL is the backstop if the DELETE is cancelled.
await engine.executeRawDirect(
`DELETE FROM gbrain_cycle_locks
WHERE id = $1 AND holder_pid = $2`,
[lockId, pid],
{ signal },
);
},
};
}
@@ -303,6 +316,11 @@ export async function tryAcquireDbLock(
const first = await acquireOnce();
if (first) return first;
// #2750: deadline-bound callers prefer an honest busy result over the
// best-effort same-host takeover below, whose inspect/delete/retry calls
// are not signal-bounded. The initial upsert already reclaims expired locks.
if (opts.signal) return null;
// v0.42 (#1780 Gap 3): the lock is held and its TTL hasn't expired (the
// upsert's ON CONFLICT ... WHERE ttl_expires_at < NOW() returned no row).
// If the holder is on THIS host, provably dead, and past the grace window,
@@ -796,6 +814,10 @@ export interface WithRefreshingLockOpts {
ttlMinutes?: number;
/** Heartbeat-fail threshold in ms — abort if SELECT 1 takes longer. Default 30000. */
heartbeatTimeoutMs?: number;
/** #2750: bound lock acquisition with the caller's deadline signal. */
signal?: AbortSignal;
/** Fresh cleanup budget for the release DELETE when `signal` is set. Default 5000. */
releaseTimeoutMs?: number;
}
/**
@@ -815,7 +837,7 @@ export async function withRefreshingLock<T>(
// Refresh 6x per TTL window so a missed tick doesn't expire the lock.
const refreshIntervalMs = Math.max(15000, (ttlMinutes * 60 * 1000) / 6);
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes);
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes, { signal: opts.signal });
if (!handle) throw new LockUnavailableError(lockId);
let healthOk = true;
@@ -854,7 +876,13 @@ export async function withRefreshingLock<T>(
return await work();
} finally {
clearInterval(interval);
try { await handle.release(); } catch { /* idempotent */ }
// #2750: when the caller is deadline-bound, its work signal may already
// have fired — release on a FRESH short grace signal so cleanup neither
// inherits the spent deadline nor hangs unbounded. TTL is the backstop.
const releaseSignal = opts.signal
? AbortSignal.timeout(opts.releaseTimeoutMs ?? 5_000)
: undefined;
try { await handle.release(releaseSignal); } catch { /* idempotent; TTL backstop */ }
if (!healthOk) {
// Surface that the heartbeat detected backend trouble — caller can
// log to the connection-events audit if desired.
+9 -1
View File
@@ -696,8 +696,16 @@ export interface BrainEngine {
* is included in the INSERT column list so ON CONFLICT (source_id, slug)
* DO UPDATE actually targets the intended row instead of fabricating a
* duplicate at (default, slug). Multi-source brains MUST pass sourceId.
*
* `opts.signal` (#2750): optional cancellation for deadline-bound writers.
* Postgres cancels the in-flight statement; PGLite pre-checks only (query
* cancellation is not possible in-process — cooperative abort between calls).
*/
putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page>;
putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page>;
/**
* v0.41.13 (#1309) — identity-based dedup pre-check for the import pipeline.
*
+2 -1
View File
@@ -187,6 +187,7 @@ function buildReceiptFrontmatter(input: ExtractReceiptInput): Record<string, unk
export async function writeReceipt(
engine: BrainEngine,
input: ExtractReceiptInput,
opts?: { signal?: AbortSignal },
): Promise<{ slug: string; page: Page }> {
const slug = receiptSlug(input);
const title = `${input.kind}${input.round}${input.source_id}`;
@@ -201,7 +202,7 @@ export async function writeReceipt(
compiled_truth,
frontmatter,
},
{ sourceId: input.source_id },
{ sourceId: input.source_id, signal: opts?.signal },
);
return { slug, page };
+4
View File
@@ -70,6 +70,7 @@ function today(): string {
export async function upsertExtractRollup(
engine: BrainEngine,
input: RollupUpsertInput,
opts?: { signal?: AbortSignal },
): Promise<{ ok: boolean; error?: string }> {
const day = input.day ?? today();
const cost = input.cost_delta ?? 0;
@@ -96,9 +97,12 @@ export async function upsertExtractRollup(
rollup_write_failures = extract_rollup_7d.rollup_write_failures + EXCLUDED.rollup_write_failures,
updated_at = now()`,
[input.kind, input.source_id, day, cost, halts, evalFails, evalPasses, completed, failures],
{ signal: opts?.signal },
);
return { ok: true };
} catch (err) {
// Signal-bounded callers get the abort surfaced, not a swallowed `ok:false`.
if (opts?.signal?.aborted) throw err;
const msg = (err as Error).message || String(err);
// Don't spam: log once per process per (kind, day) error class.
rollupErrorLogOnce(input.kind, day, msg);
+9 -1
View File
@@ -1003,7 +1003,15 @@ export class PGLiteEngine implements BrainEngine {
return { slug: r.slug, id: Number(r.id) };
}
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
async putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page> {
// #2750: PGLite is in-process WASM — no query cancellation. Pre-check so
// an already-fired deadline skips the write; abort is cooperative
// between calls (same posture as executeRaw's documented gap).
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
slug = validateSlug(slug);
const hash = page.content_hash || contentHash(page);
const frontmatter = page.frontmatter || {};
+55 -3
View File
@@ -72,6 +72,32 @@ function escapeSqlStringLiteral(value: string): string {
return value.replace(/'/g, "''");
}
/**
* #2750: race a promise against an AbortSignal, detaching the listener once
* settled (long-lived drain signals are reused across many calls, so a bare
* Promise.race would leak one listener per call). The abandoned promise keeps
* running; used only for pool-acquisition waits where that is harmless.
*/
function waitForSignal<T>(work: Promise<T>, signal?: AbortSignal): Promise<T> {
if (!signal) return work;
if (signal.aborted) return Promise.reject(new DOMException('aborted', 'AbortError'));
return new Promise<T>((resolve, reject) => {
let settled = false;
const finish = (fn: () => void) => {
if (settled) return;
settled = true;
signal.removeEventListener('abort', onAbort);
fn();
};
const onAbort = () => finish(() => reject(new DOMException('aborted', 'AbortError')));
signal.addEventListener('abort', onAbort, { once: true });
work.then(
(value) => finish(() => resolve(value)),
(err) => finish(() => reject(err)),
);
});
}
export function getPostgresSchema(
dims: number = DEFAULT_EMBEDDING_DIMENSIONS,
model: string = DEFAULT_EMBEDDING_MODEL,
@@ -1061,7 +1087,12 @@ export class PostgresEngine implements BrainEngine {
});
}
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
async putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page> {
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
slug = validateSlug(slug);
const sql = this.sql;
const hash = page.content_hash || contentHash(page);
@@ -1096,7 +1127,7 @@ export class PostgresEngine implements BrainEngine {
const sourceUri = page.source_uri ?? null;
const ingestedVia = page.ingested_via ?? null;
const ingestedAt = (sourceKind || sourceUri || ingestedVia) ? new Date() : null;
const rows = await sql`
const pending = sql`
INSERT INTO pages (source_id, slug, type, page_kind, title, compiled_truth, timeline, frontmatter, content_hash, updated_at, effective_date, effective_date_source, import_filename, chunker_version, source_path, source_kind, source_uri, ingested_via, ingested_at)
VALUES (${sourceId}, ${slug}, ${page.type}, ${pageKind}, ${page.title}, ${page.compiled_truth}, ${page.timeline || ''}, ${sql.json(frontmatter as Parameters<typeof sql.json>[0])}, ${hash}, now(), ${effectiveDate}, ${effectiveDateSource}, ${importFilename}, COALESCE(${chunkerVersion}::smallint, ${MARKDOWN_CHUNKER_VERSION}), ${sourcePath}, ${sourceKind}, ${sourceUri}, ${ingestedVia}, ${ingestedAt})
ON CONFLICT (source_id, slug) DO UPDATE SET
@@ -1119,6 +1150,22 @@ export class PostgresEngine implements BrainEngine {
ingested_at = COALESCE(EXCLUDED.ingested_at, pages.ingested_at)
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
`;
// #2750: cancel the in-flight statement when the caller's deadline fires,
// same .cancel() wiring as runUnsafe (postgres.js pending queries).
if (opts?.signal) {
const signal = opts.signal;
const onAbort = () => {
try { (pending as unknown as { cancel?: () => void }).cancel?.(); } catch { /* best-effort */ }
};
signal.addEventListener('abort', onAbort, { once: true });
try {
const rows = await pending;
return rowToPage(rows[0]);
} finally {
signal.removeEventListener('abort', onAbort);
}
}
const rows = await pending;
return rowToPage(rows[0]);
}
@@ -5807,11 +5854,16 @@ export class PostgresEngine implements BrainEngine {
params?: unknown[],
opts?: { signal?: AbortSignal },
): Promise<T[]> {
// #2750: an already-fired signal short-circuits BEFORE any pool routing,
// and the direct-pool acquisition itself is signal-bounded — under pooler
// exhaustion `ddl()` can stall indefinitely, which used to make even a
// "bounded" lock release hang past its caller's deadline.
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
// Inside an open transaction, _sql is the reserved tx connection (set via
// defineProperty in transaction()); never reroute off it.
const inTransaction = this._sql !== null && this.connectionManager?.peekReadPool() !== this._sql;
const conn = (!inTransaction && this.connectionManager?.isDualPoolActive())
? await this.connectionManager.ddl()
? await waitForSignal(this.connectionManager.ddl(), opts?.signal)
: this.sql;
return this.runUnsafe<T>(conn, sql, params, opts);
}
@@ -17,6 +17,7 @@ import { runPhaseExtractAtoms, parseAtomsResponse } from '../../src/core/cycle/e
import { runPhaseSynthesizeConcepts } from '../../src/core/cycle/synthesize-concepts.ts';
import { resetPgliteState } from '../helpers/reset-pglite.ts';
import type { ChatResult, ChatOpts } from '../../src/core/ai/gateway.ts';
import type { BrainEngine } from '../../src/core/engine.ts';
let engine: PGLiteEngine;
@@ -177,6 +178,180 @@ describe('v0.41 T5: runPhaseExtractAtoms via stubbed chat', () => {
expect((result.details?.failures as unknown[]).length).toBe(1);
});
// ── #2750: caller deadline bounds the phase ────────────────────────────
test('caller deadline aborts a hung chat before processing the next item', async () => {
let calls = 0;
const chat = async (opts: ChatOpts) => {
calls++;
return await new Promise<never>((_resolve, reject) => {
const signal = opts.abortSignal;
if (!signal) return reject(new Error('missing abort signal'));
if (signal.aborted) return reject(signal.reason);
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
};
const started = Date.now();
const result = await runPhaseExtractAtoms(engine, {
_transcripts: [
{ filePath: '/hung.txt', content: 'a', contentHash: 'hung-a' },
{ filePath: '/never.txt', content: 'b', contentHash: 'hung-b' },
],
_pages: [],
_chat: chat as typeof import('../../src/core/ai/gateway.ts').chat,
abortSignal: AbortSignal.timeout(25),
});
expect(Date.now() - started).toBeLessThan(2_000);
expect(calls).toBe(1);
expect(result.status).toBe('ok');
expect(result.details?.deadline_aborted).toBe(true);
expect(result.details?.atoms_extracted).toBe(0);
expect(result.details?.failures).toEqual([]);
});
test('billable chat usage is counted when the deadline fires as the response resolves', async () => {
const controller = new AbortController();
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
controller.abort(new DOMException('deadline', 'TimeoutError'));
return stubChat(`[{"title":"late","atom_type":"insight","body":"b"}]`, {
input_tokens: 1_000,
output_tokens: 500,
})(opts);
};
const result = await runPhaseExtractAtoms(engine, {
_transcripts: [{ filePath: '/late.txt', content: 'a', contentHash: 'late' }],
_pages: [],
_chat: chat,
abortSignal: controller.signal,
});
expect(result.details?.deadline_aborted).toBe(true);
expect(Number(result.details?.estimated_spend_usd)).toBeGreaterThan(0);
expect(result.details?.atoms_extracted).toBe(0);
});
test('deadline after partial progress still writes receipt and incomplete rollup', async () => {
const controller = new AbortController();
let calls = 0;
let notifySecondChat!: () => void;
const secondChatStarted = new Promise<void>((resolve) => { notifySecondChat = resolve; });
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
calls++;
if (calls === 1) {
return stubChat(`[{"title":"committed","atom_type":"insight","body":"b"}]`)(opts);
}
notifySecondChat();
return await new Promise<never>((_resolve, reject) => {
const signal = opts.abortSignal;
if (!signal) return reject(new Error('missing abort signal'));
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
};
const pending = runPhaseExtractAtoms(engine, {
_transcripts: [
{ filePath: '/committed.txt', content: 'a', contentHash: 'committed-a' },
{ filePath: '/hung.txt', content: 'b', contentHash: 'hung-b' },
],
_pages: [],
_chat: chat,
abortSignal: controller.signal,
});
await secondChatStarted;
controller.abort(new DOMException('deadline', 'TimeoutError'));
const result = await pending;
const atoms = await engine.executeRaw<{ n: number }>(
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'atom'`,
);
const receipts = await engine.executeRaw<{ n: number }>(
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'extract_receipt'`,
);
const rollups = await engine.executeRaw<{
cost_usd: string | number;
round_completed_count: string | number;
}>(
`SELECT cost_usd, round_completed_count
FROM extract_rollup_7d
WHERE kind = 'atoms' AND source_id = 'default'`,
);
expect(result.details?.deadline_aborted).toBe(true);
expect(atoms[0].n).toBe(1);
expect(receipts[0].n).toBe(1);
expect(Number(rollups[0].cost_usd)).toBeGreaterThan(0);
expect(Number(rollups[0].round_completed_count)).toBe(0);
});
test('bookkeeping runs on a fresh grace signal, not the fired work deadline', async () => {
const controller = new AbortController();
let putCalls = 0;
let receiptSignal: AbortSignal | undefined;
let rollupSignal: AbortSignal | undefined;
const signalAwareEngine = {
executeRaw: async (sql: string, _params?: unknown[], opts?: { signal?: AbortSignal }) => {
if (sql.includes('INSERT INTO extract_rollup_7d')) rollupSignal = opts?.signal;
return [];
},
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
putCalls++;
if (putCalls === 1) {
// Atom write in flight; the work deadline fires before bookkeeping.
controller.abort(new DOMException('work deadline', 'TimeoutError'));
} else {
receiptSignal = opts?.signal;
}
return {};
},
} as unknown as BrainEngine;
const result = await runPhaseExtractAtoms(signalAwareEngine, {
_transcripts: [{ filePath: '/one.txt', content: 'a', contentHash: 'one' }],
_pages: [],
_chat: stubChat(`[{"title":"one","atom_type":"insight","body":"b"}]`),
abortSignal: controller.signal,
});
expect(result.details?.atoms_extracted).toBe(1);
expect(putCalls).toBe(2); // atom write + receipt write
expect(receiptSignal).toBeDefined();
expect(receiptSignal).not.toBe(controller.signal);
expect(receiptSignal?.aborted).toBe(false);
expect(rollupSignal).toBe(receiptSignal);
});
test('caller deadline cancels a hung atom write and stops the phase', async () => {
const controller = new AbortController();
let notifyWriteStarted!: () => void;
const writeStarted = new Promise<void>((resolve) => { notifyWriteStarted = resolve; });
let writeCalls = 0;
const signalAwareEngine = {
executeRaw: async () => [],
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
writeCalls++;
notifyWriteStarted();
return await new Promise<never>((_resolve, reject) => {
const signal = opts?.signal;
if (!signal) return reject(new Error('missing abort signal'));
if (signal.aborted) return reject(signal.reason);
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
},
} as unknown as BrainEngine;
const pending = runPhaseExtractAtoms(signalAwareEngine, {
_transcripts: [{ filePath: '/hung-write.txt', content: 'a', contentHash: 'hung-write' }],
_pages: [],
_chat: stubChat(`[{"title":"hung write","atom_type":"insight","body":"b"}]`),
abortSignal: controller.signal,
});
await writeStarted;
controller.abort(new DOMException('deadline', 'TimeoutError'));
const result = await pending;
expect(writeCalls).toBe(1);
expect(result.details?.deadline_aborted).toBe(true);
expect(result.details?.atoms_extracted).toBe(0);
});
// v0.41.2.1 regression case (D9 #14 wording): with _pages:[] and same
// _transcripts, all PRE-EXISTING PhaseResult.details fields match
// pre-fix values byte-for-byte. The new fields (pages_processed,
@@ -1,61 +0,0 @@
/**
* E2E smoke for skills/obsidian-gbrain-safe-index.
*
* Verifies the from-trigger-to-side-effect path that skillify requires:
* a real user trigger phrase routes to the skill, the resolver/check
* pipeline treats it as reachable, and the skill file exposes the
* gbrain commands the workflow actually runs.
*
* This stays local-only (no paid embedding, no external API): it asserts
* the documented safe/import path is present and parseable, not that it
* mutates a live brain.
*/
import { describe, expect, it } from 'bun:test';
import { existsSync, readFileSync } from 'fs';
import { join } from 'path';
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
const SKILL_MD = join(SKILLS, 'obsidian-gbrain-safe-index', 'SKILL.md');
const RESOLVER = join(SKILLS, 'RESOLVER.md');
const TRIGGER_PHRASES = [
'connect my Obsidian vault to gbrain',
'import my vault to gbrain',
'sync vault and gbrain',
'capture this skill in my vault',
'embed gbrain after vault update',
'is gbrain synced with my vault',
];
describe('obsidian-gbrain-safe-index E2E', () => {
it('resolver maps real trigger phrasings to the skill', () => {
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver).toContain('obsidian-gbrain-safe-index/SKILL.md');
// Each representative phrase shares a token substring with a resolver row.
const rows = resolver
.split('\n')
.filter((l) => l.includes('obsidian-gbrain-safe-index/SKILL.md'))
.join('\n');
for (const phrase of TRIGGER_PHRASES) {
const hit = phrase
.toLowerCase()
.split(/\s+/)
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
}
});
it('skill documents the gbrain import-first safe path', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
expect(body).toContain('gbrain import');
expect(body).toContain('--no-embed');
expect(body).toContain('gbrain config set search.mode conservative');
// Paid gate must be explicit, not a silent default.
expect(body).toContain('gbrain embed --stale');
});
it('skill is reachable from the skill tree', () => {
expect(existsSync(SKILL_MD)).toBe(true);
});
});
@@ -1,52 +0,0 @@
/**
* E2E smoke for skills/skill-vault-capture-policy.
*
* Verifies the from-trigger-to-side-effect path: a real capture request
* routes to the skill, and the skill documents the vault navigation
* obligations (index.md / log.md) that make a capture durable.
*
* Local-only: it asserts documented behavior, not live vault writes.
*/
import { describe, expect, it } from 'bun:test';
import { existsSync, readFileSync } from 'fs';
import { join } from 'path';
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
const SKILL_MD = join(SKILLS, 'skill-vault-capture-policy', 'SKILL.md');
const RESOLVER = join(SKILLS, 'RESOLVER.md');
const TRIGGER_PHRASES = [
'save this learning to the vault',
'capture this skill in Obsidian',
'record this workflow in my notes',
'put this setup change in the knowledge base',
];
describe('skill-vault-capture-policy E2E', () => {
it('resolver maps real capture phrasings to the skill', () => {
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver).toContain('skill-vault-capture-policy/SKILL.md');
const rows = resolver
.split('\n')
.filter((l) => l.includes('skill-vault-capture-policy/SKILL.md'))
.join('\n');
for (const phrase of TRIGGER_PHRASES) {
const hit = phrase
.toLowerCase()
.split(/\s+/)
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
}
});
it('skill documents index.md and log.md update obligations', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
expect(body).toContain('index.md');
expect(body).toContain('log.md');
});
it('skill is reachable from the skill tree', () => {
expect(existsSync(SKILL_MD)).toBe(true);
});
});
+131 -9
View File
@@ -43,26 +43,135 @@ describe('runExtractAtomsDrain (issue #1678)', () => {
expect(batches).toBe(3);
});
it('stops at the wallclock window with remaining > 0', async () => {
// SYNC stepping clock: now() #1 sets deadline (0+100=100); the while-check
// then sees 50, 50 (two batches), then 999999 → past deadline → stop.
const times = [0, 50, 50, 999_999];
let ti = 0;
const now = () => times[Math.min(ti++, times.length - 1)];
it('stops at the wallclock window; remaining is unknown (no post-window count)', async () => {
// Each batch consumes 60ms of the 100ms window: two batches fit, the
// third boundary check sees 120 ≥ 100 and stops. #2750: after the window
// elapses the final countRemaining is SKIPPED (it would overrun the
// window), so remaining reports null.
let now = 0;
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async () => 5, // never drains
runBatch: async () => ({ extracted: 1, skipped: 0 }),
now,
runBatch: async () => {
now += 60;
return { extracted: 1, skipped: 0 };
},
now: () => now,
},
{ windowMs: 100 },
);
expect(result.stopped).toBe('window');
expect(result.remaining).toBe(5);
expect(result.remaining).toBeNull();
expect(result.batches).toBe(2);
});
it('passes one drain-level deadline signal into count and batch', async () => {
const seen: AbortSignal[] = [];
const controller = new AbortController();
let now = 0;
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async (signal) => {
seen.push(signal);
return 5;
},
runBatch: async (signal) => {
seen.push(signal);
now = 100;
return { extracted: 1, skipped: 0 };
},
now: () => now,
},
{ windowMs: 100, abortSignal: controller.signal },
);
expect(result.stopped).toBe('window');
expect(result.batches).toBe(1);
expect(seen.length).toBe(2);
expect(seen[0]).toBe(seen[1]);
// Combined (timeout + external) signal, not the raw external one.
expect(seen[0]).not.toBe(controller.signal);
});
it('aborts a hung backlog count at the window deadline and releases the lock', async () => {
let released = false;
const result = await runExtractAtomsDrain(
{
withLock: async (work) => {
try { return await work(); }
finally { released = true; }
},
// Hangs until the drain's real-time deadline signal fires (10ms).
countRemaining: (signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: () => 0, // injected clock never advances — the SIGNAL must save us
},
{ windowMs: 10 },
);
expect(result.stopped).toBe('window');
expect(result.remaining).toBeNull();
expect(released).toBe(true);
});
it('rethrows external cancellation after releasing the lock', async () => {
const controller = new AbortController();
let released = false;
const pending = runExtractAtomsDrain(
{
withLock: async (work) => {
try { return await work(); }
finally { released = true; }
},
countRemaining: (signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: () => 0,
},
{ windowMs: 1_000_000, abortSignal: controller.signal },
);
controller.abort(new DOMException('worker timeout', 'AbortError'));
await expect(pending).rejects.toThrow('worker timeout');
expect(released).toBe(true);
});
it('classifies a deadline-exhausted zero-progress batch as window, not no_progress', async () => {
let now = 0;
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async () => 5,
runBatch: async () => {
now = 100; // batch consumed the whole window and returned nothing
return { extracted: 0, skipped: 0 };
},
now: () => now,
},
{ windowMs: 100 },
);
expect(result.stopped).toBe('window');
expect(result.batches).toBe(1);
});
it('bounds a hung lock acquisition with the drain deadline signal', async () => {
const started = Date.now();
await expect(runExtractAtomsDrain(
{
withLock: (_work, signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
countRemaining: async () => 1,
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: Date.now,
},
{ windowMs: 10 },
)).rejects.toThrow();
expect(Date.now() - started).toBeLessThan(1_000);
});
it('stops on a zero-progress batch (no hot loop)', async () => {
let batches = 0;
const result = await runExtractAtomsDrain(
@@ -133,4 +242,17 @@ describe('shared wiring helper holds the cycle lock (5A)', () => {
expect(src).toContain('cycleLockIdFor(opts.sourceId)');
expect(src).toContain('withRefreshingLock(engine, lockId');
});
// #2750: the deadline signal must reach the phase, the backlog count, AND
// the lock wrapper — and the transcript path (brainDir) must stay wired
// exactly as the routine callers expect (PR #2752 takeover reverted its
// unsanctioned transcript-suppression scope change).
it('threads the drain deadline signal through phase, count, and lock', () => {
const jobsSrc = readFileSync(join(import.meta.dir, '../src/commands/jobs.ts'), 'utf8');
expect(src).toContain('abortSignal: signal');
expect(src).toContain('countExtractAtomsBacklog(engine, extractionSourceId, signal)');
expect(src).toContain('brainDir: opts.brainDir');
expect(src).not.toContain('_transcripts');
expect(jobsSrc).toContain('abortSignal: job.signal');
});
});
+9 -6
View File
@@ -24,15 +24,18 @@ import type { BrainEngine } from '../../src/core/engine.ts';
// Mock engine: healthCheck() calls engine.executeRaw; return empty rows so
// the query path exercises without needing Postgres.
//
// #1849: start() now acquires the queue-scoped DB singleton lock via
// tryAcquireDbLock, which uses the postgres `sql` tagged-template escape hatch.
// The stub returns a single row from every call so acquire succeeds (length 1
// → acquired) and refresh/release are no-ops. Each spawned runner is a fresh
// process, so there's no cross-test lock state to clean up.
// #1849: start() acquires the queue-scoped DB singleton lock via
// tryAcquireDbLock. #2750 routed the acquire upsert through engine.executeRaw
// (signal-boundable) and release through engine.executeRawDirect, so the
// stub returns a single row from the lock upsert (length 1 → acquired) and
// empty rows everywhere else. Each spawned runner is a fresh process, so
// there's no cross-test lock state to clean up.
const sqlStub = (..._args: unknown[]) => Promise.resolve([{ id: 'supervisor-lock' }]);
const mockEngine: Partial<BrainEngine> = {
kind: 'postgres' as const,
executeRaw: async () => [],
executeRaw: async (query: string) =>
query.includes('gbrain_cycle_locks') ? [{ id: 'supervisor-lock' }] : [],
executeRawDirect: async () => [],
sql: sqlStub,
} as unknown as BrainEngine;
-51
View File
@@ -1,51 +0,0 @@
import { describe, expect, it } from 'bun:test';
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'obsidian-gbrain-safe-index');
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
function parseFrontmatter(raw: string): Record<string, unknown> {
const m = raw.match(/^---\n([\s\S]*?)\n---/);
if (!m) throw new Error('no frontmatter');
const out: Record<string, unknown> = {};
for (const line of m[1].split('\n')) {
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
if (mm) out[mm[1]] = mm[2].trim();
}
return out;
}
describe('obsidian-gbrain-safe-index skill', () => {
it('has a SKILL.md with required frontmatter', () => {
expect(existsSync(SKILL_MD)).toBe(true);
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
expect(fm['name']).toBe('obsidian-gbrain-safe-index');
expect(fm['description']).toBeTruthy();
});
it('has the required conformance sections', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
expect(body.includes(section), `missing ${section}`).toBe(true);
}
});
it('is registered in RESOLVER.md', () => {
expect(existsSync(RESOLVER)).toBe(true);
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
});
it('has routing-eval fixtures that exercise real trigger phrasings', () => {
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
expect(existsSync(evalPath)).toBe(true);
const lines = readFileSync(evalPath, 'utf-8')
.split('\n')
.filter((l) => l.trim() && !l.trim().startsWith('//'))
.map((l) => JSON.parse(l));
const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
expect(positives.length).toBeGreaterThanOrEqual(5);
});
});
+26 -1
View File
@@ -98,14 +98,39 @@ describe('PostgresEngine.executeRawDirect — routing decision (PR #1816)', () =
});
test('already-aborted signal short-circuits with AbortError before routing the query', async () => {
const readConn = fakeSql('read');
let unsafeCalls = 0;
let ddlCalls = 0;
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
const directConn = fakeSql('direct');
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
e.connectionManager.ddl = async () => { ddlCalls++; return directConn; };
const ac = new AbortController();
ac.abort();
await expect(
engine.executeRawDirect('UPDATE minion_jobs SET x=1', [], { signal: ac.signal }),
).rejects.toThrow(/abort/i);
// #2750: short-circuits BEFORE pool routing — no ddl(), no unsafe().
expect(ddlCalls).toBe(0);
expect(unsafeCalls).toBe(0);
});
test('#2750: signal bounds a stalled direct-pool acquisition before unsafe starts', async () => {
let unsafeCalls = 0;
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
const directConn = fakeSql('direct');
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
e.connectionManager.ddl = () => new Promise<FakeSql>(() => {}); // pooler exhausted: never resolves
const started = Date.now();
await expect(engine.executeRawDirect(
'DELETE FROM gbrain_cycle_locks',
[],
{ signal: AbortSignal.timeout(10) },
)).rejects.toThrow(/abort/i);
expect(Date.now() - started).toBeLessThan(1_000);
expect(unsafeCalls).toBe(0);
});
});
-64
View File
@@ -1,64 +0,0 @@
import { describe, expect, it } from 'bun:test';
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
function parseFrontmatter(raw: string): Record<string, unknown> {
const m = raw.match(/^---\n([\s\S]*?)\n---/);
if (!m) throw new Error('no frontmatter');
const out: Record<string, unknown> = {};
for (const line of m[1].split('\n')) {
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
if (mm) out[mm[1]] = mm[2].trim();
}
return out;
}
describe('skill-vault-capture-policy skill', () => {
it('has a SKILL.md with required frontmatter', () => {
expect(existsSync(SKILL_MD)).toBe(true);
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
expect(fm['name']).toBe('skill-vault-capture-policy');
expect(fm['description']).toBeTruthy();
});
it('has the required conformance sections', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
expect(body.includes(section), `missing ${section}`).toBe(true);
}
});
it('is registered in RESOLVER.md', () => {
expect(existsSync(RESOLVER)).toBe(true);
expect(readFileSync(RESOLVER, 'utf-8').includes('skill-vault-capture-policy/SKILL.md')).toBe(true);
});
it('contains no private user or agent-fork names (privacy rule)', () => {
for (const file of [SKILL_MD, join(SKILL_DIR, 'routing-eval.jsonl')]) {
const body = readFileSync(file, 'utf-8');
// DEFAULT_PRIVATE_PATTERNS[0] is the banned fork-name pattern; sourced
// from harvest-lint so this file never contains the literal itself
// (scripts/check-privacy.sh would reject it).
const forkName = new RegExp(DEFAULT_PRIVATE_PATTERNS[0], 'i');
for (const name of [/\bAdam\b/, /\bHermes\b/, /\bHerdr\b/, /\bArk\b/, forkName]) {
expect(name.test(body), `private name ${name} in ${file}`).toBe(false);
}
}
});
it('has routing-eval fixtures', () => {
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
expect(existsSync(evalPath)).toBe(true);
const positives = readFileSync(evalPath, 'utf-8')
.split('\n')
.filter((l) => l.trim() && !l.trim().startsWith('//'))
.map((l) => JSON.parse(l))
.filter((l) => l.expected_skill === 'skill-vault-capture-policy');
expect(positives.length).toBeGreaterThanOrEqual(4);
});
});