mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Garry TanandClaude Fable 5
|
edf7fc6b5a | ||
|
|
b7f42f099a |
+3
-1
@@ -1411,7 +1411,8 @@ 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` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/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` |
|
||||
| "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` |
|
||||
@@ -1429,6 +1430,7 @@ 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) |
|
||||
|
||||
@@ -39,8 +39,8 @@
|
||||
"skills/briefing",
|
||||
"skills/citation-fixer",
|
||||
"skills/concept-synthesis",
|
||||
"skills/cross-modal-review",
|
||||
"skills/cron-scheduler",
|
||||
"skills/cross-modal-review",
|
||||
"skills/daily-task-manager",
|
||||
"skills/daily-task-prep",
|
||||
"skills/data-research",
|
||||
@@ -54,10 +54,11 @@
|
||||
"skills/media-ingest",
|
||||
"skills/meeting-ingestion",
|
||||
"skills/minion-orchestrator",
|
||||
"skills/obsidian-gbrain-safe-index",
|
||||
"skills/perplexity-research",
|
||||
"skills/query",
|
||||
"skills/reports",
|
||||
"skills/repo-architecture",
|
||||
"skills/reports",
|
||||
"skills/signal-detector",
|
||||
"skills/skill-creator",
|
||||
"skills/skillify",
|
||||
|
||||
+3
-1
@@ -60,7 +60,8 @@ 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` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/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` |
|
||||
| "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` |
|
||||
@@ -78,6 +79,7 @@ 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) |
|
||||
|
||||
+11
-1
@@ -2,7 +2,7 @@
|
||||
"name": "gbrain",
|
||||
"version": "0.32.3.0",
|
||||
"conformance_version": "1.0.0",
|
||||
"description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
|
||||
"description": "Personal knowledge brain with hybrid RAG search — GStack mod for agent platforms",
|
||||
"skills": [
|
||||
{
|
||||
"name": "ingest",
|
||||
@@ -34,6 +34,11 @@
|
||||
"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",
|
||||
@@ -263,6 +268,11 @@
|
||||
"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": {
|
||||
|
||||
@@ -0,0 +1,137 @@
|
||||
---
|
||||
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.
|
||||
@@ -0,0 +1,11 @@
|
||||
// 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}
|
||||
@@ -0,0 +1,100 @@
|
||||
---
|
||||
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.
|
||||
@@ -0,0 +1,10 @@
|
||||
// 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}
|
||||
@@ -686,7 +686,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
try {
|
||||
const { MinionQueue } = await import('../core/minions/queue.ts');
|
||||
const { computeRecommendations, embeddingProviderConfigured, HOSTED_EMBED_KEY_CONFIG } = await import('../core/brain-score-recommendations.ts');
|
||||
const { countExtractionLag } = await import('../core/remediation/context.ts');
|
||||
const queue = new MinionQueue(engine);
|
||||
const slotMs = Math.floor(Date.now() / (baseInterval * 1000)) * baseInterval * 1000;
|
||||
const slot = new Date(slotMs).toISOString();
|
||||
@@ -878,9 +877,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
return !!(process.env[envVar] || (cfgField ? embedKeyCfg[cfgField] : undefined));
|
||||
}),
|
||||
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || await engine.getConfig('anthropic_api_key')),
|
||||
// Real extraction-lag gate for sync.repo/extract.all — same counter
|
||||
// loadRecommendationContext uses (replaces the health.stale_pages proxy).
|
||||
extractionLagPages: await countExtractionLag(engine),
|
||||
};
|
||||
// v0.41.18.0 (A5 + A19 + A22, T15): consult onboard recommendations
|
||||
// ALONGSIDE doctor's brain-score recommendations. Onboard's 4 new
|
||||
|
||||
@@ -146,16 +146,6 @@ export interface RecommendationContext {
|
||||
chatModel?: string;
|
||||
/** Whether the chat provider has a usable API key. */
|
||||
hasChatApiKey?: boolean;
|
||||
/**
|
||||
* Count of pages needing link/timeline extraction — the SAME staleness the
|
||||
* `gbrain extract --stale` walk and doctor's `links_extraction_lag` check use
|
||||
* (`engine.countStalePagesForExtraction`). Gates the sync→extract pipeline
|
||||
* (sync.repo / extract.all). Replaces the old `health.stale_pages` gate, which
|
||||
* counted "pages whose updated_at predates their newest timeline entry" — a
|
||||
* proxy that broke when the updated_at-on-timeline-insert trigger was dropped
|
||||
* (migration v10) and never reflected real extraction work.
|
||||
*/
|
||||
extractionLagPages?: number;
|
||||
}
|
||||
|
||||
/** Triage result for one check. */
|
||||
@@ -202,28 +192,20 @@ export function computeRecommendations(
|
||||
const source = ctx.sourceId ?? 'default';
|
||||
|
||||
// ---------------------------------------------------------------------
|
||||
// sync.repo + extract.all — the materialization pipeline, gated on the REAL
|
||||
// extraction lag (pages whose link/timeline edges are stale), NOT on the
|
||||
// legacy `health.stale_pages` proxy. `extractionLagPages` comes from the same
|
||||
// counter the `extract --stale` walk + doctor's `links_extraction_lag` use, so
|
||||
// the recommendation can only fire when running extract will actually reduce
|
||||
// it (and clear the rec). See RecommendationContext.extractionLagPages.
|
||||
// sync.repo is the prerequisite: re-sync so pages are current before extract
|
||||
// materializes their edges.
|
||||
// sync.repo — fires when sync hasn't run recently OR pages are stale
|
||||
// ---------------------------------------------------------------------
|
||||
const extractionLag = ctx.extractionLagPages ?? 0;
|
||||
if (ctx.repoPath && extractionLag > 0) {
|
||||
if (ctx.repoPath && health.stale_pages > 0) {
|
||||
const params = { repoPath: ctx.repoPath, sourceId: ctx.sourceId, noEmbed: true };
|
||||
out.push({
|
||||
id: 'sync.repo',
|
||||
job: 'sync',
|
||||
params,
|
||||
idempotency_key: idemKey(source, 'sync', params),
|
||||
severity: extractionLag > 50 ? 'high' : 'medium',
|
||||
est_seconds: Math.min(600, 30 + extractionLag * 0.5),
|
||||
severity: health.stale_pages > 50 ? 'high' : 'medium',
|
||||
est_seconds: Math.min(600, 30 + health.stale_pages * 0.5),
|
||||
est_usd_cost: 0, // sync is fs+DB only
|
||||
depends_on: [],
|
||||
rationale: `Sync before extracting ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale link/timeline edges`,
|
||||
rationale: `${health.stale_pages} stale page${health.stale_pages === 1 ? '' : 's'} on disk`,
|
||||
status: 'remediable',
|
||||
});
|
||||
}
|
||||
@@ -255,7 +237,7 @@ export function computeRecommendations(
|
||||
est_seconds: Math.min(3600, 5 + health.missing_embeddings * 0.05),
|
||||
est_usd_cost,
|
||||
// sync should run first so embed sees fresh pages.
|
||||
depends_on: ctx.repoPath && extractionLag > 0 ? ['sync.repo'] : [],
|
||||
depends_on: ctx.repoPath && health.stale_pages > 0 ? ['sync.repo'] : [],
|
||||
rationale: `${health.missing_embeddings} chunk${health.missing_embeddings === 1 ? '' : 's'} invisible to vector search`,
|
||||
status: 'remediable',
|
||||
});
|
||||
@@ -285,7 +267,7 @@ export function computeRecommendations(
|
||||
// Triggered when sync.repo fires (because sync was set to noEmbed:true,
|
||||
// and noExtract:true after T5 lands → extract job is the materializer).
|
||||
// ---------------------------------------------------------------------
|
||||
if (ctx.repoPath && extractionLag > 0) {
|
||||
if (ctx.repoPath && health.stale_pages > 0) {
|
||||
const params = { mode: 'all', dir: ctx.repoPath };
|
||||
out.push({
|
||||
id: 'extract.all',
|
||||
@@ -296,7 +278,7 @@ export function computeRecommendations(
|
||||
est_seconds: Math.min(600, 30 + health.page_count * 0.01),
|
||||
est_usd_cost: 0,
|
||||
depends_on: ['sync.repo'],
|
||||
rationale: `Materialize link + timeline edges for ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale extraction`,
|
||||
rationale: 'Materialize link + timeline edges from fresh pages',
|
||||
status: 'remediable',
|
||||
});
|
||||
}
|
||||
|
||||
@@ -8,7 +8,6 @@
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import type { RecommendationContext } from '../brain-score-recommendations.ts';
|
||||
import { LINK_EXTRACTOR_VERSION_TS } from '../link-extraction.ts';
|
||||
|
||||
// Re-export so consumers can `import { RecommendationContext } from '../remediation'`
|
||||
// — the canonical RecommendationContext type still lives in
|
||||
@@ -69,29 +68,5 @@ export async function loadRecommendationContext(
|
||||
embeddingDimensions,
|
||||
embeddingProviderConfigured: embeddingConfigured,
|
||||
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || fileCfg?.anthropic_api_key),
|
||||
extractionLagPages: await countExtractionLag(engine),
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Real extraction-lag count — the SAME staleness `gbrain extract --stale`
|
||||
* processes (engine.countStalePagesForExtraction with
|
||||
* versionTs=LINK_EXTRACTOR_VERSION_TS, matching doctor's links_extraction_lag
|
||||
* check — without versionTs, pages stamped before an extractor version bump
|
||||
* would lag for doctor/extract but never trip this gate). Drives the
|
||||
* sync→extract recommendation pipeline; replaces the legacy
|
||||
* `health.stale_pages` proxy that no longer reflected real extraction work
|
||||
* after the v10 trigger drop.
|
||||
*
|
||||
* Shared by loadRecommendationContext AND the D7 per-step recheck in
|
||||
* runRemediation — the recheck MUST refresh this gate alongside getHealth,
|
||||
* or a completed extract step keeps re-firing off the frozen initial count.
|
||||
*/
|
||||
export async function countExtractionLag(engine: BrainEngine): Promise<number> {
|
||||
try {
|
||||
return await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
|
||||
} catch {
|
||||
/* counter unavailable (very old brain / mid-migration) — treat as 0 */
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@ import {
|
||||
computeRecommendations,
|
||||
} from '../brain-score-recommendations.ts';
|
||||
import type { RemediationStep } from '../remediation-step.ts';
|
||||
import { countExtractionLag, loadRecommendationContext } from './context.ts';
|
||||
import { loadRecommendationContext } from './context.ts';
|
||||
import { computeRemediationPlan } from './plan.ts';
|
||||
import type {
|
||||
RemediationHooks,
|
||||
@@ -65,7 +65,7 @@ export async function runRemediation(
|
||||
clearRemediationCheckpoint,
|
||||
} = await import('../remediation-checkpoint.ts');
|
||||
|
||||
let ctx = await loadRecommendationContext(engine);
|
||||
const ctx = await loadRecommendationContext(engine);
|
||||
|
||||
// Pre-flight ceiling check via the shared plan computation.
|
||||
const initialPlan = await computeRemediationPlan(engine, { targetScore });
|
||||
@@ -305,11 +305,6 @@ export async function runRemediation(
|
||||
// steps with bumped retry suffix (D1).
|
||||
if (recs.length === 0 || stepCount >= maxJobs) break;
|
||||
const freshHealth = await engine.getHealth();
|
||||
// Refresh the extraction-lag gate alongside health: ctx was loaded once
|
||||
// before the loop, and a completed sync/extract step is exactly what
|
||||
// drives the count down. Reusing the frozen initial count would re-fire
|
||||
// sync.repo/extract.all every recheck until maxJobs.
|
||||
ctx = { ...ctx, extractionLagPages: await countExtractionLag(engine) };
|
||||
recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
|
||||
}
|
||||
};
|
||||
|
||||
@@ -1423,15 +1423,6 @@ export interface BrainStats {
|
||||
export interface BrainHealth {
|
||||
page_count: number;
|
||||
embed_coverage: number;
|
||||
/**
|
||||
* LEGACY proxy: count of pages whose `updated_at` predates their newest
|
||||
* timeline entry. This bumped meaningfully only while a trigger updated
|
||||
* `pages.updated_at` on timeline insert; that trigger was dropped in
|
||||
* migration v10, so the metric no longer reflects real "needs work" state.
|
||||
* NO LONGER gates remediations — the sync→extract pipeline now gates on
|
||||
* `RecommendationContext.extractionLagPages` (the real extraction-lag from
|
||||
* `countStalePagesForExtraction`). Retained for the CLI health line + back-compat.
|
||||
*/
|
||||
stale_pages: number;
|
||||
/**
|
||||
* Islanded pages — zero inbound AND zero outbound links. A hub page
|
||||
|
||||
@@ -119,12 +119,13 @@ describe('computeRecommendations', () => {
|
||||
expect(recs.find((r) => r.id === 'embed.stale')).toBeUndefined();
|
||||
});
|
||||
|
||||
test('extraction lag + dead links produce sync + backlinks + extract', () => {
|
||||
test('stale pages + dead links produce sync + backlinks + extract', () => {
|
||||
const health = makeHealth({
|
||||
stale_pages: 25,
|
||||
dead_links: 8,
|
||||
brain_score: 70,
|
||||
});
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 25 });
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
|
||||
const ids = recs.map((r) => r.id);
|
||||
expect(ids).toContain('sync.repo');
|
||||
expect(ids).toContain('backlinks.fix');
|
||||
@@ -132,17 +133,18 @@ describe('computeRecommendations', () => {
|
||||
});
|
||||
|
||||
test('extract.all depends on sync.repo (D14: stable ids)', () => {
|
||||
const health = makeHealth();
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
|
||||
const health = makeHealth({ stale_pages: 10 });
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
|
||||
const extract = recs.find((r) => r.id === 'extract.all');
|
||||
expect(extract?.depends_on).toContain('sync.repo');
|
||||
});
|
||||
|
||||
test('embed.stale depends on sync.repo when extraction also needed', () => {
|
||||
test('embed.stale depends on sync.repo when sync also needed', () => {
|
||||
const health = makeHealth({
|
||||
stale_pages: 10,
|
||||
missing_embeddings: 100,
|
||||
});
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
|
||||
const embed = recs.find((r) => r.id === 'embed.stale');
|
||||
expect(embed?.depends_on).toContain('sync.repo');
|
||||
});
|
||||
@@ -157,9 +159,9 @@ describe('computeRecommendations', () => {
|
||||
test('severity ordering: critical before high before medium', () => {
|
||||
const health = makeHealth({
|
||||
missing_embeddings: 100, // critical
|
||||
stale_pages: 80, // high
|
||||
});
|
||||
// extractionLagPages > 50 → sync.repo fires at 'high' severity.
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 80 });
|
||||
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
|
||||
const critIdx = recs.findIndex((r) => r.severity === 'critical');
|
||||
const highIdx = recs.findIndex((r) => r.severity === 'high');
|
||||
expect(critIdx).toBeLessThan(highIdx);
|
||||
@@ -168,10 +170,11 @@ describe('computeRecommendations', () => {
|
||||
// D6 #5 — THE critical regression test for the agent contract.
|
||||
test('D6 #5: determinism — same input twice produces identical output', () => {
|
||||
const health = makeHealth({
|
||||
stale_pages: 10,
|
||||
missing_embeddings: 50,
|
||||
dead_links: 3,
|
||||
});
|
||||
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default', extractionLagPages: 10 };
|
||||
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default' };
|
||||
const run1 = computeRecommendations(health, ctx);
|
||||
const run2 = computeRecommendations(health, ctx);
|
||||
expect(JSON.stringify(run1)).toBe(JSON.stringify(run2));
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
/**
|
||||
* 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);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* 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: ${phrase}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('skill documents index.md and log.md update obligations', () => {
|
||||
const body = readFileSync(SKILL_MD, 'utf-8');
|
||||
expect(body).toContain('index.md');
|
||||
expect(body).toContain('log.md');
|
||||
});
|
||||
|
||||
it('skill is reachable from the skill tree', () => {
|
||||
expect(existsSync(SKILL_MD)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,51 @@
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { readFileSync, existsSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
|
||||
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'obsidian-gbrain-safe-index');
|
||||
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
|
||||
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
|
||||
|
||||
function parseFrontmatter(raw: string): Record<string, unknown> {
|
||||
const m = raw.match(/^---\n([\s\S]*?)\n---/);
|
||||
if (!m) throw new Error('no frontmatter');
|
||||
const out: Record<string, unknown> = {};
|
||||
for (const line of m[1].split('\n')) {
|
||||
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
|
||||
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);
|
||||
});
|
||||
});
|
||||
@@ -1,62 +0,0 @@
|
||||
// test/remediation-context-extraction-lag.test.ts
|
||||
//
|
||||
// Pins the v-next fix: the sync→extract remediation pipeline gates on REAL
|
||||
// extraction lag, not the legacy `health.stale_pages` proxy (which counted
|
||||
// "updated_at predates newest timeline entry" — meaningless after the v10
|
||||
// trigger drop). loadRecommendationContext now populates `extractionLagPages`
|
||||
// from `engine.countStalePagesForExtraction` — the SAME counter the
|
||||
// `gbrain extract --stale` walk and doctor's `links_extraction_lag` use — so a
|
||||
// recommendation can only fire when running extract will actually reduce it.
|
||||
|
||||
import { afterAll, beforeAll, describe, expect, it } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { loadRecommendationContext } from '../src/core/remediation/context.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
describe('loadRecommendationContext — extractionLagPages wiring', () => {
|
||||
it('is 0 on an empty brain (nothing to extract)', async () => {
|
||||
const ctx = await loadRecommendationContext(engine);
|
||||
expect(ctx.extractionLagPages).toBe(0);
|
||||
});
|
||||
|
||||
it('reflects the real extraction-lag count once a page needs extraction', async () => {
|
||||
// A freshly-imported page has links_extracted_at = NULL, which the canonical
|
||||
// countStalePagesForExtraction predicate counts as stale-for-extraction.
|
||||
await engine.putPage('p0', {
|
||||
title: 'p0',
|
||||
type: 'note' as never,
|
||||
compiled_truth: 'body that is long enough to pass any minimum-length guards in the codebase',
|
||||
timeline: '',
|
||||
frontmatter: {},
|
||||
source_path: 'p0.md',
|
||||
});
|
||||
const ctx = await loadRecommendationContext(engine);
|
||||
expect(ctx.extractionLagPages).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
it('counts pages stamped before LINK_EXTRACTOR_VERSION_TS (version-bump arm)', async () => {
|
||||
// Backdate p0 so BOTH the NULL arm and the updated_at arm are quiet:
|
||||
// updated_at < links_extracted_at, but links_extracted_at predates the
|
||||
// extractor version stamp. doctor's links_extraction_lag and
|
||||
// `extract --stale` both count this page; the remediation gate must too.
|
||||
await engine.executeRaw(
|
||||
`UPDATE pages SET updated_at = '2020-01-01T00:00:00Z'::timestamptz,
|
||||
links_extracted_at = '2020-01-02T00:00:00Z'::timestamptz
|
||||
WHERE slug = 'p0'`,
|
||||
[],
|
||||
);
|
||||
const ctx = await loadRecommendationContext(engine);
|
||||
expect(ctx.extractionLagPages).toBeGreaterThan(0);
|
||||
});
|
||||
});
|
||||
@@ -1,81 +0,0 @@
|
||||
// test/remediation-run-d7-refresh.serial.test.ts
|
||||
//
|
||||
// Pins the D7-recheck half of the extraction-lag gate fix: runRemediation
|
||||
// loads RecommendationContext ONCE before the step loop, and the per-step
|
||||
// recheck (D7) must REFRESH ctx.extractionLagPages alongside getHealth.
|
||||
// Without the refresh, a completed sync/extract step keeps re-firing off
|
||||
// the frozen initial count — the plan never converges and the loop burns
|
||||
// steps until maxJobs.
|
||||
//
|
||||
// SERIAL (R2): uses top-level mock.module for the minion queue +
|
||||
// wait-for-completion so no real worker is needed — mocks leak across
|
||||
// files in a shard process, so this file must run in its own process.
|
||||
|
||||
import { describe, expect, mock, test } from 'bun:test';
|
||||
|
||||
// The fake brain: sync.repo clears the extraction lag when it "runs"
|
||||
// (today's sync materializes link/timeline edges; extract.all is the
|
||||
// explicit re-materializer). The frozen-ctx bug makes runRemediation
|
||||
// ignore that and resubmit sync.repo on every D7 recheck.
|
||||
let extractionLag = 25;
|
||||
const submittedJobs: string[] = [];
|
||||
|
||||
mock.module('../src/core/minions/queue.ts', () => ({
|
||||
MinionQueue: class {
|
||||
constructor(_engine: unknown) {}
|
||||
async add(job: string): Promise<{ id: number }> {
|
||||
submittedJobs.push(job);
|
||||
if (job === 'sync' || job === 'extract') extractionLag = 0;
|
||||
return { id: submittedJobs.length };
|
||||
}
|
||||
},
|
||||
}));
|
||||
|
||||
mock.module('../src/core/minions/wait-for-completion.ts', () => ({
|
||||
waitForCompletion: async () => ({ status: 'completed' }),
|
||||
}));
|
||||
|
||||
const health = () => ({
|
||||
page_count: 100,
|
||||
embed_coverage: 1.0,
|
||||
stale_pages: 0, // legacy proxy stays 0 — the real counter drives the gate
|
||||
orphan_pages: 0,
|
||||
missing_embeddings: 0,
|
||||
brain_score: 70,
|
||||
dead_links: 0,
|
||||
link_coverage: 1.0,
|
||||
timeline_coverage: 1.0,
|
||||
most_connected: [],
|
||||
embed_coverage_score: 35,
|
||||
link_density_score: 25,
|
||||
timeline_coverage_score: 15,
|
||||
no_orphans_score: 15,
|
||||
no_dead_links_score: 10,
|
||||
});
|
||||
|
||||
const fakeEngine = {
|
||||
kind: 'pglite' as const,
|
||||
getHealth: async () => health(),
|
||||
getConfig: async (key: string) =>
|
||||
key === 'sync.repo_path' ? '/tmp/brain-example' : null,
|
||||
countStalePagesForExtraction: async () => extractionLag,
|
||||
};
|
||||
|
||||
describe('runRemediation D7 recheck — extraction-lag gate refresh', () => {
|
||||
test('a completed materializer step clears the gate; the pipeline is not resubmitted', async () => {
|
||||
const { runRemediation } = await import('../src/core/remediation/run.ts');
|
||||
const result = await runRemediation(
|
||||
// Only the methods the orchestrator touches are needed.
|
||||
fakeEngine as never,
|
||||
{ targetScore: 0, maxJobs: 6 },
|
||||
);
|
||||
// Frozen-ctx bug: extractionLagPages stays 25 forever, so every D7
|
||||
// recheck re-introduces the sync/extract pipeline and the loop burns
|
||||
// all 6 maxJobs. With the refresh, the plan converges after the first
|
||||
// completed step: no step id is ever submitted twice.
|
||||
const ids = result.submitted.map((s) => s.id);
|
||||
expect(new Set(ids).size).toBe(ids.length);
|
||||
expect(submittedJobs.length).toBeLessThan(3);
|
||||
expect(extractionLag).toBe(0);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,64 @@
|
||||
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);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user