Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 edf7fc6b5a fix(skills): green CI for vault skills — resolver health, fixture lint, privacy literal, llms bundle
- RESOLVER.md rows now round-trip against SKILL.md frontmatter triggers
  ('put this setup change in the vault'; replace 'safe/free gbrain index'
  with 'import my vault to gbrain').
- Rewrite both routing-eval.jsonl fixture sets: positives embed a trigger
  phrase in natural context (fixture linter rejects verbatim tautologies),
  declare ambiguous_with for legitimate co-fires (capture, idea-ingest),
  and negatives no longer collide with skillpack-harvest/setup triggers.
  check:resolver --strict is clean (0 errors, 0 warnings).
- Privacy: the vault-capture regression test sources the banned fork-name
  pattern from harvest-lint's DEFAULT_PRIVATE_PATTERNS instead of the
  literal, so scripts/check-privacy.sh passes.
- Regenerate llms-full.txt after the RESOLVER.md edit (build-llms
  freshness gate).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:03:38 -07:00
b7f42f099a feat(skills): skillify vault skills — obsidian-gbrain-safe-index + skill-vault-capture-policy (takeover of #2685)
Salvages the intended 8-file change from PR #2685 (two vault skills with
routing-eval fixtures + unit/E2E tests, registered in RESOLVER.md,
manifest.json, and openclaw.plugin.json) without the ~670 unrelated
third-party skill dumps that contaminated that branch.

Also scrubs private user/agent names from skill-vault-capture-policy per
the repo privacy rule, with a regression test.

Takeover of #2685.

Co-authored-by: MortdAdam <MortdAdam@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:27:59 -07:00
16 changed files with 510 additions and 270 deletions
+3 -1
View File
@@ -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) |
+3 -2
View File
@@ -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
View File
@@ -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
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 \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": {
+137
View File
@@ -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}
+100
View File
@@ -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}
+2 -11
View File
@@ -808,20 +808,12 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
// 'default'. Wrapped in try/catch so a doctor / single-source brain that
// never set up sources still returns 'default' silently.
let sourceId: string | undefined;
// #2561: when the source resolved via a NON-explicit tier (path-match /
// brain default / sole-non-default / seed default), unqualified search-shaped
// reads span every `config.federated = true` source. Computed here (the
// trusted local boundary) and consumed by federatedSearchScope in
// operations.ts, which additionally gates on ctx.remote === false.
let localFederated: string[] | undefined;
try {
const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
const { resolveSourceId } = await import('./core/source-resolver.ts');
// params.source is set when a CLI flag was parsed for the op (rare; most
// CLI ops don't take --source). Falls through to env/dotfile/path-match.
const explicit = (params.source as string | undefined) ?? null;
const resolved = await resolveSourceWithTier(engine, explicit);
sourceId = resolved.source_id;
localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
sourceId = await resolveSourceId(engine, explicit);
} catch {
// Source resolution failed (e.g. sources table doesn't exist on a fresh
// pre-init brain). Leave sourceId unset; engine read methods fall through
@@ -842,7 +834,6 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
// table). Matches dispatch.ts's auto-fill so the contract holds across
// every transport.
sourceId: sourceId ?? 'default',
...(localFederated ? { localFederatedSourceIds: localFederated } : {}),
};
}
+2 -61
View File
@@ -424,23 +424,6 @@ export interface OperationContext {
* satisfied even on single-source brains.
*/
sourceId: string;
/**
* #2561 — federated read scope for UNQUALIFIED local CLI reads.
*
* Set ONLY by the local CLI's context builder (src/cli.ts makeContext), and
* only when the source resolved via a non-explicit tier (local_path /
* brain_default / sole_non_default / seed_default — NOT --source, NOT
* GBRAIN_SOURCE, NOT a .gbrain-source dotfile). Contains the resolved
* source first, then every other `config.federated = true` source, so an
* unqualified `gbrain search "X"` spans federated sources as
* docs/guides/multi-source-brains.md promises.
*
* Consumed exclusively by `federatedSearchScope` and ONLY when
* `ctx.remote === false` — a remote caller's scope stays governed by
* `ctx.auth.allowedSources` / scalar `ctx.sourceId` (source-isolation
* invariant, fail-closed).
*/
localFederatedSourceIds?: string[];
}
/**
@@ -556,45 +539,6 @@ export function resolveRequestedScope(
return sourceScopeOpts(ctx);
}
/**
* #2561 — source scope for the search-shaped read ops (`search`, `query`).
*
* Delegates to `resolveRequestedScope` (the single trust+grant resolver), then
* widens an UNQUALIFIED trusted-local scalar scope to the CLI-computed
* federated set (`ctx.localFederatedSourceIds`, resolved source first). This is
* what makes `sources add --federated` mean something for local search: a
* federated source participates in unqualified `gbrain search "X"` results.
*
* The expansion NEVER applies when:
* - the caller is not strictly trusted-local (`ctx.remote !== false`) —
* remote scope stays grant-governed (fail-closed source isolation);
* - a per-call `source_id` was passed (explicit wins, including `__all__`);
* - the resolver already produced a federated array (OAuth grant);
* - the CLI resolved the source from an explicit signal (--source / env /
* dotfile) — makeContext leaves `localFederatedSourceIds` unset then.
*
* Deliberately NOT inside `sourceScopeOpts`: code-intel ops collapse a
* multi-element scope to an error (`resolveCodeIntelScope`), and non-search
* reads (get_page, get_links, …) keep their long-standing scalar behavior.
*/
export function federatedSearchScope(
ctx: OperationContext,
sourceIdParam?: string,
): { sourceId?: string; sourceIds?: string[] } {
const scope = resolveRequestedScope(ctx, sourceIdParam);
if (
ctx.remote === false &&
sourceIdParam === undefined &&
scope.sourceId !== undefined &&
scope.sourceIds === undefined &&
ctx.localFederatedSourceIds !== undefined &&
ctx.localFederatedSourceIds.length > 1
) {
return { sourceIds: ctx.localFederatedSourceIds };
}
return scope;
}
/**
* Code-intel adapter for `resolveRequestedScope`. Graph traversal
* (code_callers/code_callees/code_blast/code_flow) is single-source by design —
@@ -1504,8 +1448,7 @@ const search: Operation = {
const queryText = p.query as string;
const limit = (p.limit as number) || 20;
const offset = (p.offset as number) || 0;
// #2561: unqualified trusted-local search spans federated sources.
const scope = federatedSearchScope(ctx);
const scope = sourceScopeOpts(ctx);
// T4/D5 — per-call mode honored ONLY for trusted/local callers so a remote
// OAuth client can't escalate to the costly tokenmax bundle. Local + unknown
@@ -1667,9 +1610,7 @@ const query: Operation = {
// is spread into BOTH the image-similarity searchVector path and the text
// hybridSearch path below, so both honor the same grant.
const sourceIdParam = typeof p.source_id === 'string' ? p.source_id : undefined;
// #2561: unqualified trusted-local query spans federated sources (per-call
// source_id / remote grants still resolve through resolveRequestedScope).
const querySourceScope = federatedSearchScope(ctx, sourceIdParam);
const querySourceScope = resolveRequestedScope(ctx, sourceIdParam);
// v0.27.1: image-similarity branch. Bypasses hybridSearch (which is
// text-only); embeds the image via embedMultimodal and runs a direct
-39
View File
@@ -353,45 +353,6 @@ export async function resolveSourceWithTier(
return { source_id: 'default', tier: 'seed_default' };
}
/**
* #2561 — compute the federated read scope for an UNQUALIFIED local CLI call.
*
* `sources add --federated` promises that a `config.federated = true` source
* "participates in unqualified `gbrain search` results"
* (docs/guides/multi-source-brains.md). This helper turns that promise into a
* scope: given the resolved source and WHICH tier resolved it, return
* `[resolvedSource, ...other federated source ids]` — or `undefined` when the
* expansion must not apply:
*
* - explicit tiers (`flag` / `env` / `dotfile`): the user named a source;
* scalar scope stands (that IS the qualified case);
* - no other federated source exists: keep the scalar fast path unchanged.
*
* Archived sources are excluded (same rationale as pickSoleNonDefaultSource);
* the archived column is v34+, so fall back to the un-archived query on older
* brains. Callers put the result on `OperationContext.localFederatedSourceIds`
* — consumed only by `federatedSearchScope` and only when `remote === false`.
*/
export async function localFederatedSourceIds(
engine: BrainEngine,
sourceId: string,
tier: SourceTier,
): Promise<string[] | undefined> {
if (tier === 'flag' || tier === 'env' || tier === 'dotfile') return undefined;
let rows: Array<{ id: string }>;
try {
rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE config->>'federated' = 'true' AND archived = false ORDER BY id`,
);
} catch {
rows = await engine.executeRaw<{ id: string }>(
`SELECT id FROM sources WHERE config->>'federated' = 'true' ORDER BY id`,
);
}
const ids = [sourceId, ...rows.map((r) => r.id).filter((id) => id !== sourceId)];
return ids.length > 1 ? ids : undefined;
}
/** Exposed for tests. */
export const __testing = {
readDotfileWalk,
@@ -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);
});
});
-154
View File
@@ -1,154 +0,0 @@
/**
* #2561 — sources.config.federated participates in UNQUALIFIED local CLI
* search/query.
*
* Pre-fix: the local CLI always emitted a scalar `{sourceId}` scope (required
* field, auto-filled 'default'), so a source registered with
* `gbrain sources add --federated` was invisible to an unqualified
* `gbrain search "X"` — contradicting docs/guides/multi-source-brains.md
* ("Source participates in unqualified `gbrain search` results").
*
* Fix: the CLI context builder computes `ctx.localFederatedSourceIds`
* (resolved source + every other federated source) whenever the source
* resolved via a NON-explicit tier; `federatedSearchScope` widens the scalar
* scope to that set for the `search` / `query` ops — trusted-local only
* (`ctx.remote === false`), never for remote callers, never when a per-call
* `source_id` or an explicit --source/env/dotfile was given.
*/
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { localFederatedSourceIds } from '../src/core/source-resolver.ts';
import {
federatedSearchScope,
operations,
type OperationContext,
} from '../src/core/operations.ts';
let engine: PGLiteEngine;
const search = operations.find((o) => o.name === 'search')!;
function ctxOf(overrides: Partial<OperationContext> = {}): OperationContext {
return {
engine: engine as any,
config: {} as any,
logger: console as any,
dryRun: false,
remote: false,
sourceId: 'default',
...overrides,
};
}
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
// Seeded 'default' source is federated=true. Add:
// wiki — federated (must join unqualified search)
// private — NOT federated (must stay invisible unless explicitly named)
// oldnews — federated but archived (must stay excluded)
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config) VALUES ('wiki', 'wiki', '/tmp/wiki', '{"federated": true}'::jsonb)`,
);
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config) VALUES ('private', 'private', '/tmp/private', '{}'::jsonb)`,
);
await engine.executeRaw(
`INSERT INTO sources (id, name, local_path, config, archived) VALUES ('oldnews', 'oldnews', '/tmp/oldnews', '{"federated": true}'::jsonb, true)`,
);
const pages: Array<[slug: string, sourceId: string, where: string]> = [
['notes/home', 'default', 'default'],
['wiki/topic', 'wiki', 'wiki'],
['private/topic', 'private', 'private'],
['old/topic', 'oldnews', 'oldnews'],
];
for (const [slug, sourceId, where] of pages) {
await engine.putPage(slug, {
type: 'note', title: `Topic in ${where}`, compiled_truth: `the zebra telescope in ${where}`, frontmatter: {},
}, { sourceId });
await engine.upsertChunks(slug, [
{ chunk_index: 0, chunk_text: `the zebra telescope in ${where}`, chunk_source: 'compiled_truth' },
], { sourceId });
}
// Keyword-only search path: no embedding provider needed in tests.
await engine.setConfig('search.mcp_keyword_only', 'true');
}, 60_000);
afterAll(async () => {
if (engine) await engine.disconnect();
}, 60_000);
describe('localFederatedSourceIds — CLI-side scope computation', () => {
test('non-explicit tier: resolved source first, then other federated, archived excluded', async () => {
expect(await localFederatedSourceIds(engine, 'default', 'seed_default')).toEqual(['default', 'wiki']);
});
test('non-federated resolved source still joins its own scope', async () => {
expect(await localFederatedSourceIds(engine, 'private', 'brain_default')).toEqual(['private', 'default', 'wiki']);
});
test('explicit tiers (--source / env / dotfile) never expand', async () => {
expect(await localFederatedSourceIds(engine, 'default', 'flag')).toBeUndefined();
expect(await localFederatedSourceIds(engine, 'default', 'env')).toBeUndefined();
expect(await localFederatedSourceIds(engine, 'default', 'dotfile')).toBeUndefined();
});
test('single federated source (the resolved one) keeps the scalar fast path', async () => {
const solo = { executeRaw: async () => [{ id: 'default' }] } as any;
expect(await localFederatedSourceIds(solo, 'default', 'seed_default')).toBeUndefined();
});
});
describe('federatedSearchScope — trust + explicitness matrix', () => {
test('trusted local + unqualified widens to the federated set', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['default', 'wiki'] });
});
test('remote caller NEVER widens (fail-closed), even if the field is set', () => {
const ctx = ctxOf({ remote: true, localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx)).toEqual({ sourceId: 'default' });
});
test('per-call source_id wins over the federated set', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx, 'wiki')).toEqual({ sourceId: 'wiki' });
});
test('per-call __all__ keeps the whole-brain semantics for trusted local', () => {
const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
expect(federatedSearchScope(ctx, '__all__')).toEqual({});
});
test('a federated OAuth grant wins over the local set', () => {
const ctx = ctxOf({
localFederatedSourceIds: ['default', 'wiki'],
auth: { allowedSources: ['a', 'b'] } as OperationContext['auth'],
});
expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['a', 'b'] });
});
test('no local federated set → unchanged scalar scope', () => {
expect(federatedSearchScope(ctxOf())).toEqual({ sourceId: 'default' });
});
});
describe('search op — unqualified local search spans federated sources', () => {
test('federated source results appear; non-federated + archived stay invisible', async () => {
const ctx = ctxOf({
localFederatedSourceIds: await localFederatedSourceIds(engine, 'default', 'seed_default'),
});
const results = (await search.handler(ctx, { query: 'zebra telescope' })) as Array<{ slug: string }>;
const slugs = results.map((r) => r.slug);
expect(slugs).toContain('notes/home');
expect(slugs).toContain('wiki/topic'); // pre-#2561 this was missing
expect(slugs).not.toContain('private/topic');
expect(slugs).not.toContain('old/topic');
});
test('explicit source resolution (no federated set on ctx) stays single-source', async () => {
const results = (await search.handler(ctxOf(), { query: 'zebra telescope' })) as Array<{ slug: string }>;
const slugs = results.map((r) => r.slug);
expect(slugs).toEqual(['notes/home']);
});
});
+51
View File
@@ -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 ${section}`).toBe(true);
}
});
it('is registered in RESOLVER.md', () => {
expect(existsSync(RESOLVER)).toBe(true);
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
});
it('has routing-eval fixtures that exercise real trigger phrasings', () => {
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
expect(existsSync(evalPath)).toBe(true);
const lines = readFileSync(evalPath, 'utf-8')
.split('\n')
.filter((l) => l.trim() && !l.trim().startsWith('//'))
.map((l) => JSON.parse(l));
const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
expect(positives.length).toBeGreaterThanOrEqual(5);
});
});
+64
View File
@@ -0,0 +1,64 @@
import { describe, expect, it } from 'bun:test';
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
function parseFrontmatter(raw: string): Record<string, unknown> {
const m = raw.match(/^---\n([\s\S]*?)\n---/);
if (!m) throw new Error('no frontmatter');
const out: Record<string, unknown> = {};
for (const line of m[1].split('\n')) {
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
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);
});
});