Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 76589d3ddc fix(facts): fold visibility tier into hot-memory meta cache key
trustedFactReads is re-read from config on every stdio tool call, so the
reader's visibility tier can now flip within one server process. The
meta-hook cache key (source, session, allow-list hash) didn't capture it,
so a mid-session opt-out of facts.trust_local_reads could keep serving a
private-inclusive cached payload for the 30s TTL. Compute the visibility
filter before the cache lookup and append the tier to the key, restoring
the header's cross-tier no-bleed invariant.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:10:57 -07:00
d6b0253c59 feat(facts): owner-trusted local fact reads via facts.trust_local_reads (takeover of #2427)
Salvages the owner-trusted-reads half of #2427 with the trust regression
repaired. (The other half of #2427 — dating conversation facts at claim
time — already landed on master via #2958 and is dropped here.)

Fact rows are private|world; remote callers are world-only. The stdio MCP
server is a local unauthenticated pipe on a single-owner machine, yet it
defaults remote:true — so the owner's own agent got empty find_trajectory
and world-only recall over MCP. This adds `trustedFactReads`, a narrow
READ-ONLY trust elevation decoupled from `remote` (file confinement,
source isolation, fence stripping, takes scoping all stay in force),
opted in via the new `facts.trust_local_reads` config (default off).
Only the stdio server sets it; HTTP dispatch never does.

Repair vs #2427 as submitted: its `factsWorldOnly` was fail-OPEN
(`remote === true && …`) — an unset `remote` read private rows — and it
replaced two fail-closed sites (recall's visibility filter and the facts
meta-hook), with a test codifying the regression. Now fail-closed
(`remote !== false && trustedFactReads !== true`) per the CLAUDE.md trust
invariant; the truth-table test pins it. The two engine findTrajectory
sites keep their direct-engine default-local contract by normalizing to
explicit booleans before the helper (both engines in lockstep).

Tests: test/facts-reader-trust.test.ts (fail-closed truth table);
test/engine-find-trajectory.test.ts new case (remote=true +
trustedFactReads returns private points; plain remote=true stays
world-only).

Takeover of #2427.

Co-authored-by: jeanpierre121 <jeanpierre121@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:34:48 -07:00
23 changed files with 169 additions and 520 deletions
+1 -3
View File
@@ -1411,8 +1411,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
| Save or load reports | `skills/reports/SKILL.md` |
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -1430,7 +1429,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
+2 -3
View File
@@ -39,8 +39,8 @@
"skills/briefing",
"skills/citation-fixer",
"skills/concept-synthesis",
"skills/cron-scheduler",
"skills/cross-modal-review",
"skills/cron-scheduler",
"skills/daily-task-manager",
"skills/daily-task-prep",
"skills/data-research",
@@ -54,11 +54,10 @@
"skills/media-ingest",
"skills/meeting-ingestion",
"skills/minion-orchestrator",
"skills/obsidian-gbrain-safe-index",
"skills/perplexity-research",
"skills/query",
"skills/repo-architecture",
"skills/reports",
"skills/repo-architecture",
"skills/signal-detector",
"skills/skill-creator",
"skills/skillify",
+1 -3
View File
@@ -60,8 +60,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
| Save or load reports | `skills/reports/SKILL.md` |
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -79,7 +78,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
+1 -11
View File
@@ -2,7 +2,7 @@
"name": "gbrain",
"version": "0.32.3.0",
"conformance_version": "1.0.0",
"description": "Personal knowledge brain with hybrid RAG search GStack mod for agent platforms",
"description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
"skills": [
{
"name": "ingest",
@@ -34,11 +34,6 @@
"path": "migrate/SKILL.md",
"description": "Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam"
},
{
"name": "obsidian-gbrain-safe-index",
"path": "obsidian-gbrain-safe-index/SKILL.md",
"description": "Connect and sync an Obsidian-style Markdown vault with gbrain using a cost-controlled import-first workflow, explicit embedding gates, and durable skill/workflow capture."
},
{
"name": "setup",
"path": "setup/SKILL.md",
@@ -268,11 +263,6 @@
"name": "skill-optimizer",
"path": "skill-optimizer/SKILL.md",
"description": "Self-evolving skill optimization via gbrain skillopt — SkillOpt-paper-grounded text-space optimizer with validation gating (median-of-3 + epsilon=0.05), bundled-skill safety, bootstrap review sentinel, per-skill DB lock, and atomic versioned writes."
},
{
"name": "skill-vault-capture-policy",
"path": "skill-vault-capture-policy/SKILL.md",
"description": "Capture durable operational learnings, new agent skills, and environment/setup changes into the Obsidian vault instead of transient chat memory."
}
],
"dependencies": {
-137
View File
@@ -1,137 +0,0 @@
---
name: obsidian-gbrain-safe-index
version: 1.0.0
description: |
Connect, maintain, and sync an Obsidian-style Markdown vault with gbrain while preserving a cost-controlled workflow: the vault remains the source of truth, gbrain is the searchable/embedded index, durable skills/workflows are captured into the vault, and paid embedding runs only after explicit approval.
triggers:
- "connect Obsidian to gbrain"
- "import my vault to gbrain"
- "sync vault and gbrain"
- "capture this skill in my vault"
- "embed gbrain after vault update"
- "is gbrain synced with my vault"
tools:
- terminal
- read_file
- search_files
- write_file
- patch
mutating: true
---
# Obsidian → gbrain Safe Index and Capture
## Contract
This skill guarantees:
- Treats the user's Obsidian-style Markdown vault as the source of truth before gbrain indexing.
- Keeps gbrain in conservative mode unless the user explicitly approves a more expensive mode.
- Imports vault changes with `--no-embed` first, then embeds only after explicit approval for the specific paid action.
- Captures durable new skills, workflows, and environment learnings into the vault instead of leaving them only in chat memory.
- Verifies every sync with concrete `gbrain stats`, search mode, and, when embeddings run, exact embedded chunk counts.
## Phases
1. **Resolve the vault path.**
- Prefer an existing environment variable such as `OBSIDIAN_VAULT_PATH` or `WIKI_PATH`.
- If no path is configured, search likely note directories and ask the user before writing.
- Verify the directory exists and contains markdown files or an `.obsidian` directory.
2. **Read vault operating rules before writing.**
- If the vault has `SCHEMA.md`, `index.md`, `log.md`, `AGENTS.md`, or similar operating files, read them before ingest/query/major edit.
- Respect immutable source folders such as `raw/` when the vault declares them.
- Use the vault's native link convention, usually Obsidian `[[wikilinks]]`, for durable relationships.
3. **MECE/capture decision.**
- If new knowledge belongs on an existing page, update that page.
- If it is a distinct recurring workflow or operational policy, create a small meta or concept page following the vault schema.
- Update the vault index/catalog for every new page when the vault maintains one.
- Append a log entry for meaningful vault updates when the vault maintains a log.
4. **Safe gbrain import path.**
- Pre-check source directory; do not import a nonexistent path.
- Run `gbrain config set search.mode conservative` before/after risky reinit steps.
- Run `gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed`.
- Run `gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"` when wikilinks changed materially.
5. **Paid embedding gate.**
- Do not run `gbrain embed --stale` unless the user explicitly asks or a prior instruction clearly approved this exact paid action.
- Before embedding, verify provider readiness with `gbrain providers test --model <provider:model>`.
- Confirm the configured embedding dimensions match the local schema.
- After embedding, verify `gbrain stats` and record exact `Pages`, `Chunks`, `Embedded`, and `Links` counts.
6. **Final verification and vault echo.**
- Run `gbrain stats` and `gbrain search modes`.
- If vault files changed, re-import with `--no-embed`; if embedding was approved, embed stale chunks afterward.
- Report what changed, what was free/local, what used API billing, and what remains pending.
## Output Format
Use a compact status table:
| Item | Status |
|---|---|
| Vault path | `/path` |
| Vault updated | yes/no + files |
| gbrain mode | conservative/balanced/tokenmax |
| Import | `--no-embed` completed / skipped / failed |
| Pages/chunks | exact counts from `gbrain stats` |
| Embeddings | exact count; note whether this run used API billing |
| Links | exact count |
| Background jobs | none / list exact jobs |
Then include:
- **Safe next step:** free/local action.
- **Paid next step:** embedding/LLM action, if any, with explicit approval requirement.
## Anti-Patterns
- Creating a duplicate skill/page when an existing Obsidian, gbrain, or vault-ingest skill already covers the workflow.
- Running `gbrain embed --stale`, `gbrain dream`, `gbrain autopilot --install`, `gbrain onboard --auto`, or `tokenmax` without explicit cost approval.
- Importing a nonexistent or wrong directory and treating a zero-page import as success.
- Forgetting to update the vault index/catalog and log after creating or materially updating vault pages.
- Recording API keys, tokens, or raw secrets in the vault or final response.
## Tools Used
- `read_file` — read vault schema/index/log and target notes.
- `search_files` — find existing vault pages and avoid duplicates.
- `write_file` / `patch` — create or update vault pages.
- `terminal` — run `gbrain`, `git`, and environment checks with secret values redacted.
## Safe Commands
```bash
export PATH="$HOME/.bun/bin:$PATH"
gbrain config set search.mode conservative
gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed
gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"
gbrain stats
gbrain search modes
```
## Paid / Approval-Gated Commands
```bash
gbrain providers test --model <provider:model>
gbrain embed --stale
gbrain dream
gbrain autopilot --install
gbrain onboard --auto --max-usd 5
gbrain config set search.mode tokenmax
```
## Verification Checklist
- [ ] Vault path exists and is the intended source.
- [ ] Vault operating files were read before edits when present.
- [ ] Existing pages/skills were searched to avoid duplicates.
- [ ] New/updated vault pages follow the vault schema and link convention.
- [ ] Vault index/catalog updated for new pages when present.
- [ ] Vault log appended for meaningful actions when present.
- [ ] `gbrain import ... --no-embed` completed.
- [ ] `gbrain stats` recorded pages/chunks/embeddings/links.
- [ ] `gbrain search modes` confirms conservative mode unless a different mode was explicitly approved.
- [ ] No paid/background commands ran without approval.
@@ -1,11 +0,0 @@
// Routing eval fixtures for skills/obsidian-gbrain-safe-index.
// Positive cases: intents embed a trigger phrase in natural surrounding context
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
{"intent": "help me connect Obsidian to gbrain for my notes", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "import my vault to gbrain but skip embeddings for now", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "please sync vault and gbrain after I edit notes", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "run embed gbrain after vault update tonight", "expected_skill": "obsidian-gbrain-safe-index"}
{"intent": "hey is gbrain synced with my vault right now", "expected_skill": "obsidian-gbrain-safe-index"}
// Negative cases: related but owned by other skills. Assert NO route to this skill.
{"intent": "migrate my notes from Notion to gbrain", "expected_skill": null}
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
-100
View File
@@ -1,100 +0,0 @@
---
name: skill-vault-capture-policy
version: 1.0.0
description: |
Use when the user wants a durable operational learning, new agent skill, or
important environment/setup change to be captured into the Obsidian vault
instead of left only in transient chat memory. Covers the capture rule,
preferred page patterns, and index/log update obligations.
triggers:
- "save this learning to the vault"
- "capture this skill in Obsidian"
- "record this workflow in my notes"
- "put this setup change in the vault"
- "should we add this to the knowledge base"
tools:
- read_file
- search_files
- write_file
- patch
mutating: true
---
# Skill Vault Capture Policy
## Contract
This skill guarantees:
- Durable operational learnings, newly adopted skills, and important environment/setup changes are captured into the Obsidian vault rather than left only in chat memory.
- An existing page is updated when the knowledge clearly belongs there; a new page is created only when the topic is distinct and likely to recur.
- Every new vault page is added to `index.md`.
- Every meaningful create/update appends a dated entry to `log.md`.
- Small linked pages are preferred over one giant running note.
## Phases
1. **Classify the learning.**
- New gbrain operating rule, cost control, or embedding/provider change.
- New agent-fork / harness / coding-tool integration fact.
- New Obsidian vault workflow or structure decision.
- New recurring agent skill that changes how the agent should operate here.
2. **Avoid duplicates.**
- Search the vault for an existing page that already owns the topic.
- If found, update it with a new section or dated note rather than creating a near-duplicate.
3. **Create when distinct.**
- Place new pages under the vault schema: `_meta/` for operating notes, `concepts/` for workflows, `entities/` for tools/people.
- Use YAML frontmatter and at least two `[[wikilinks]]` unless it is a short seed page.
4. **Update navigation.**
- Add the page to `index.md` under the correct type heading.
- Append a `## [YYYY-MM-DD] create|update | subject` entry to `log.md`.
5. **Report the capture.**
- State which files changed and whether `index.md` / `log.md` were updated.
## Output Format
Use a short status block:
| Item | Status |
|---|---|
| Learning classified | type |
| Page created/updated | path |
| index.md updated | yes/no |
| log.md updated | yes/no |
## Anti-Patterns
- Leaving durable learnings only in chat memory.
- Creating a near-duplicate page instead of updating the existing one.
- Forgetting to update `index.md` and `log.md`.
- Writing one giant running note instead of small linked pages.
- Recording secrets, API keys, or raw credentials in the vault.
## Tools Used
- `read_file` — read `SCHEMA.md`, `index.md`, `log.md`, and target pages.
- `search_files` — find existing pages to avoid duplicates.
- `write_file` / `patch` — create or update vault pages and navigation.
## Safe Commands
```bash
# inspect vault navigation before writing
read SCHEMA.md index.md log.md
# create or update a page, then refresh catalog/log
# index.md: add [[page-slug]] under the matching type heading
# log.md: append ## [YYYY-MM-DD] create|update | subject
```
## Verification Checklist
- [ ] Vault schema/read files were checked before writing.
- [ ] Existing pages were searched to avoid duplicates.
- [ ] New/updated page has frontmatter and wikilinks.
- [ ] `index.md` updated for new pages.
- [ ] `log.md` appended for meaningful actions.
- [ ] No secrets or raw credentials were written.
@@ -1,10 +0,0 @@
// Routing eval fixtures for skills/skill-vault-capture-policy.
// Positive cases: intents embed a trigger phrase in natural surrounding context
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
{"intent": "please save this learning to the vault so we keep it", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["idea-ingest"]}
{"intent": "we should capture this skill in Obsidian for reuse", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["capture"]}
{"intent": "can you record this workflow in my notes for next time", "expected_skill": "skill-vault-capture-policy"}
{"intent": "put this setup change in the vault before we forget", "expected_skill": "skill-vault-capture-policy"}
// Negative cases: related but owned by other skills or out of scope.
{"intent": "connect my Obsidian vault to gbrain", "expected_skill": null}
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
+4
View File
@@ -908,6 +908,10 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
'facts.extraction_model',
// #2113: output-token cap for the per-turn facts extractor (default 4000).
'facts.extraction_max_tokens',
// Owner opt-in: let the local stdio MCP pipe read this owner's private facts
// (find_trajectory / recall). Default off; HTTP transport ignores it. See
// src/core/facts/reader-trust.ts.
'facts.trust_local_reads',
// Dream cycle config
'dream.synthesize.session_corpus_dir',
'dream.synthesize.meeting_transcripts_dir',
+2
View File
@@ -591,6 +591,8 @@ export interface TrajectoryOpts {
sourceIds?: string[];
/** When true, filters to visibility='world' only. Set by MCP layer from ctx.remote. */
remote?: boolean;
/** Owner opt-in: read private facts despite `remote`. See facts/reader-trust.ts. */
trustedFactReads?: boolean;
/** Metric filter. When set, only facts with this canonical metric label participate. */
metric?: string;
/**
+8 -5
View File
@@ -17,6 +17,7 @@
import type { OperationContext } from './../operations.ts';
import type { FactRow } from './../engine.ts';
import { effectiveConfidence } from './decay.ts';
import { readableFactVisibilities } from './reader-trust.ts';
const DEFAULT_TTL_MS = 30_000;
const DEFAULT_TOP_K = 10;
@@ -50,7 +51,13 @@ export async function getBrainHotMemoryMeta(
const sessionId = (ctx as { source_session?: string }).source_session
?? null;
const allowListHash = hashAllowList(ctx.takesHoldersAllowList);
const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}`;
// Visibility tier: untrusted remote → world-only; trusted local +
// owner-trusted reads → all rows. Folded into the cache key (the header's
// "cache entries don't bleed across tiers" invariant): trustedFactReads is
// re-read from config per call, so a mid-session opt-out must not keep
// serving a private-inclusive cached payload for the TTL window.
const visibility = readableFactVisibilities(ctx);
const cacheKey = `${sourceId}::${sessionId ?? '_'}::${allowListHash}::${visibility ? 'world' : 'all'}`;
const ttl = Math.max(1000, opts.ttlMs ?? DEFAULT_TTL_MS);
const topK = Math.max(1, Math.min(opts.topK ?? DEFAULT_TOP_K, 25));
@@ -61,10 +68,6 @@ export async function getBrainHotMemoryMeta(
return cached.payload;
}
// Build a fresh payload. Visibility tier: remote → world-only;
// local → all rows.
const visibility = ctx.remote === false ? undefined : ['world'] as ('world' | 'private')[];
let rows: FactRow[] = [];
if (sessionId) {
rows = await ctx.engine.listFactsBySession(sourceId, sessionId, {
+48
View File
@@ -0,0 +1,48 @@
/**
* Fact-read visibility trust.
*
* Fact rows are tagged `private` | `world`. Remote/untrusted callers
* (`remote === true`) see only `world` rows — the posture that keeps a
* published or HTTP-served brain from leaking private claims to strangers.
*
* But the stdio MCP server is an unauthenticated LOCAL pipe: on a single-owner
* machine the caller IS the owner, yet it still defaults `remote: true` for
* safety, so the owner's own agent is denied the owner's own private facts
* (e.g. `find_trajectory` returns empty over MCP even though the facts exist).
*
* `trustedFactReads` is a narrow, READ-ONLY trust elevation, deliberately
* DECOUPLED from `remote` so every other remote protection — file_upload
* confinement, source isolation, fence stripping, takes-holder scoping — stays
* fully in force. The stdio MCP server sets it ONLY when the brain owner opts
* in via the `facts.trust_local_reads` config (default off). The HTTP/published
* transport never sets it, so a served brain stays world-only regardless.
*/
export interface FactReaderTrust {
/**
* Mirrors OperationContext.remote. FAIL-CLOSED: anything not strictly
* `false` is treated as remote/untrusted (CLAUDE.md trust invariant).
*/
remote?: boolean;
/** Owner opt-in: this remote caller may read private facts. */
trustedFactReads?: boolean;
}
/**
* True when the reader is restricted to `visibility = 'world'` rows.
* Fail-closed: an unset/undefined `remote` is untrusted — only an explicit
* `remote: false` (trusted local CLI) or an explicit owner opt-in
* (`trustedFactReads: true`) reads private rows.
*/
export function factsWorldOnly(t: FactReaderTrust): boolean {
return t.remote !== false && t.trustedFactReads !== true;
}
/**
* Visibility filter for list-style fact reads: `['world']` when the reader is
* world-only, `undefined` (no filter — all rows) when it is trusted.
*/
export function readableFactVisibilities(
t: FactReaderTrust,
): ('private' | 'world')[] | undefined {
return factsWorldOnly(t) ? ['world'] : undefined;
}
+14 -7
View File
@@ -18,6 +18,7 @@ import { captureEvalCandidate, isEvalCaptureEnabled, isEvalScrubEnabled } from '
import type { HybridSearchMeta } from './types.ts';
import { extractPageLinks, isAutoLinkEnabled, isAutoTimelineEnabled, isGlobalBasenameEnabled, parseTimelineEntries, makeResolver, type UnresolvedFrontmatterRef } from './link-extraction.ts';
import { isFactsBackstopEligible } from './facts/eligibility.ts';
import { readableFactVisibilities } from './facts/reader-trust.ts';
import { stripTakesFence } from './takes-fence.ts';
import { stripFactsFence } from './facts-fence.ts';
import { getContentFlag } from './quarantine.ts';
@@ -332,6 +333,15 @@ export interface OperationContext {
* remote/untrusted (defense in depth in case the type is bypassed via cast).
*/
remote: boolean;
/**
* Owner opt-in (`facts.trust_local_reads`): allow this remote caller to read
* `private` facts. A NARROW, read-only trust elevation decoupled from
* `remote` — every other remote protection (file confinement, source
* isolation, fence stripping, takes scoping) stays in force. Set ONLY by the
* stdio MCP server when the config is on; the HTTP transport never sets it.
* Consulted via `src/core/facts/reader-trust.ts`.
*/
trustedFactReads?: boolean;
/**
* Subagent runtime context (v0.16+). Set by the subagent tool dispatcher when
* dispatching an op as a tool call from an LLM loop. Used to enforce per-op
@@ -3629,6 +3639,7 @@ const find_trajectory: Operation = {
entitySlug: p.entity_slug,
...scope,
remote: ctx.remote === true,
trustedFactReads: ctx.trustedFactReads === true,
metric,
kind,
since,
@@ -3989,13 +4000,9 @@ const recall: Operation = {
const includeExpired = p.include_expired === true;
const grep = typeof p.grep === 'string' ? p.grep.toLowerCase() : null;
// Visibility filter: remote callers see world-only unless their token
// grants elevated visibility (future-proofing; v0.31 ships world-only
// for remote, all for local CLI).
const visibility =
ctx.remote === false
? undefined
: ['world'] as ('private' | 'world')[];
// Visibility filter: world-only for untrusted remote callers; all rows for
// trusted local CLI and owner-trusted reads (facts.trust_local_reads).
const visibility = readableFactVisibilities(ctx);
let rows: Awaited<ReturnType<typeof ctx.engine.listFactsByEntity>> = [];
+5 -1
View File
@@ -18,6 +18,7 @@ import type {
} from './engine.ts';
import { MAX_SEARCH_LIMIT, clampSearchLimit } from './engine.ts';
import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
import { factsWorldOnly } from './facts/reader-trust.ts';
import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
import { runMigrations } from './migrate.ts';
import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
@@ -4318,7 +4319,10 @@ export class PGLiteEngine implements BrainEngine {
const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
const sourceIds = useArray ? opts.sourceIds! : null;
const sourceId = opts.sourceId ?? 'default';
const remoteFilter = opts.remote === true;
// Direct-engine contract: unset `remote` here means a trusted in-process
// caller (CLI/tests) — the fail-closed default lives in the op layer, which
// always passes explicit booleans. Normalize before the fail-closed helper.
const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
// Build SQL dynamically. PGLite uses $N positional params; we
// assemble the WHERE clauses + params array in tandem to keep them
+5 -1
View File
@@ -14,6 +14,7 @@ import type {
SourceRow,
} from './engine.ts';
import { withRetry, BULK_RETRY_OPTS, resolveBulkRetryOpts, computeNextDelay, type BatchAuditSite } from './retry.ts';
import { factsWorldOnly } from './facts/reader-trust.ts';
import { logBatchRetry as auditLogBatchRetry, logBatchExhausted as auditLogBatchExhausted } from './audit/batch-retry-audit.ts';
import type {
DomainBankSampleOpts, CorpusSampleOpts, DomainBankRow,
@@ -4532,7 +4533,10 @@ export class PostgresEngine implements BrainEngine {
const useArray = Array.isArray(opts.sourceIds) && opts.sourceIds.length > 0;
const sourceIds = useArray ? opts.sourceIds! : null;
const sourceId = opts.sourceId ?? 'default';
const remoteFilter = opts.remote === true;
// Direct-engine contract: unset `remote` here means a trusted in-process
// caller (CLI/tests) — the fail-closed default lives in the op layer, which
// always passes explicit booleans. Normalize before the fail-closed helper.
const remoteFilter = factsWorldOnly({ remote: opts.remote === true, trustedFactReads: opts.trustedFactReads === true });
// Source-scope predicate: array path (federated) wins over scalar.
// Engine.ts contract: returns chronological points; regressions +
+8
View File
@@ -30,6 +30,13 @@ export interface ToolResult {
export interface DispatchOpts {
/** Defaults to true (remote/untrusted). Local CLI callers (`gbrain call`) pass false. */
remote?: boolean;
/**
* Owner opt-in (`facts.trust_local_reads`): let this remote caller read
* `private` facts. Set ONLY by the stdio MCP server; the HTTP transport
* leaves it unset so a served brain stays world-only. See
* `src/core/facts/reader-trust.ts`.
*/
trustedFactReads?: boolean;
/** Override the default stderr logger (e.g. CLI uses console.* directly). */
logger?: OperationContext['logger'];
/**
@@ -203,6 +210,7 @@ export function buildOperationContext(
logger: opts.logger || stderrLogger,
dryRun: !!params.dry_run,
remote: opts.remote ?? true,
trustedFactReads: opts.trustedFactReads === true,
takesHoldersAllowList: opts.takesHoldersAllowList,
// v0.34 D4: sourceId is REQUIRED at the type level. Auto-fill 'default'
// for single-source brains and any caller who didn't resolve a sourceId.
+11
View File
@@ -35,6 +35,16 @@ export async function startMcpServer(engine: BrainEngine) {
// shape and cast through `any` (the SDK accepts it via the ServerResult union).
server.setRequestHandler(CallToolRequestSchema, async (request: any): Promise<any> => {
const { name, arguments: params } = request.params;
// Owner opt-in: the stdio pipe is local + unauthenticated, so on a
// single-owner machine its caller is the owner. When facts.trust_local_reads
// is on, let fact reads (find_trajectory / recall) see this owner's own
// private facts. Narrow + read-only — every other remote protection stays
// on (remote stays true). HTTP transport never sets this. Best-effort: a
// config read blip falls back to the safe world-only default.
let trustedFactReads = false;
try {
trustedFactReads = (await engine.getConfig('facts.trust_local_reads')) === 'true';
} catch { /* keep world-only default */ }
// v0.28: stdio MCP has no per-token auth (local pipe). Default the
// takes-holder allow-list to ['world'] so agent-facing callers don't
// see private hunches via takes_list / takes_search / query. Operators
@@ -42,6 +52,7 @@ export async function startMcpServer(engine: BrainEngine) {
// `gbrain call <op>` (sets remote=false in src/cli.ts).
return dispatchToolCall(engine, name, params, {
remote: true,
trustedFactReads,
takesHoldersAllowList: ['world'],
// v0.31: source defaults to 'default' for stdio (no per-token scope).
// Operators who want a different source on stdio MCP should set
@@ -1,61 +0,0 @@
/**
* E2E smoke for skills/obsidian-gbrain-safe-index.
*
* Verifies the from-trigger-to-side-effect path that skillify requires:
* a real user trigger phrase routes to the skill, the resolver/check
* pipeline treats it as reachable, and the skill file exposes the
* gbrain commands the workflow actually runs.
*
* This stays local-only (no paid embedding, no external API): it asserts
* the documented safe/import path is present and parseable, not that it
* mutates a live brain.
*/
import { describe, expect, it } from 'bun:test';
import { existsSync, readFileSync } from 'fs';
import { join } from 'path';
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
const SKILL_MD = join(SKILLS, 'obsidian-gbrain-safe-index', 'SKILL.md');
const RESOLVER = join(SKILLS, 'RESOLVER.md');
const TRIGGER_PHRASES = [
'connect my Obsidian vault to gbrain',
'import my vault to gbrain',
'sync vault and gbrain',
'capture this skill in my vault',
'embed gbrain after vault update',
'is gbrain synced with my vault',
];
describe('obsidian-gbrain-safe-index E2E', () => {
it('resolver maps real trigger phrasings to the skill', () => {
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver).toContain('obsidian-gbrain-safe-index/SKILL.md');
// Each representative phrase shares a token substring with a resolver row.
const rows = resolver
.split('\n')
.filter((l) => l.includes('obsidian-gbrain-safe-index/SKILL.md'))
.join('\n');
for (const phrase of TRIGGER_PHRASES) {
const hit = phrase
.toLowerCase()
.split(/\s+/)
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
}
});
it('skill documents the gbrain import-first safe path', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
expect(body).toContain('gbrain import');
expect(body).toContain('--no-embed');
expect(body).toContain('gbrain config set search.mode conservative');
// Paid gate must be explicit, not a silent default.
expect(body).toContain('gbrain embed --stale');
});
it('skill is reachable from the skill tree', () => {
expect(existsSync(SKILL_MD)).toBe(true);
});
});
@@ -1,52 +0,0 @@
/**
* E2E smoke for skills/skill-vault-capture-policy.
*
* Verifies the from-trigger-to-side-effect path: a real capture request
* routes to the skill, and the skill documents the vault navigation
* obligations (index.md / log.md) that make a capture durable.
*
* Local-only: it asserts documented behavior, not live vault writes.
*/
import { describe, expect, it } from 'bun:test';
import { existsSync, readFileSync } from 'fs';
import { join } from 'path';
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
const SKILL_MD = join(SKILLS, 'skill-vault-capture-policy', 'SKILL.md');
const RESOLVER = join(SKILLS, 'RESOLVER.md');
const TRIGGER_PHRASES = [
'save this learning to the vault',
'capture this skill in Obsidian',
'record this workflow in my notes',
'put this setup change in the knowledge base',
];
describe('skill-vault-capture-policy E2E', () => {
it('resolver maps real capture phrasings to the skill', () => {
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver).toContain('skill-vault-capture-policy/SKILL.md');
const rows = resolver
.split('\n')
.filter((l) => l.includes('skill-vault-capture-policy/SKILL.md'))
.join('\n');
for (const phrase of TRIGGER_PHRASES) {
const hit = phrase
.toLowerCase()
.split(/\s+/)
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
}
});
it('skill documents index.md and log.md update obligations', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
expect(body).toContain('index.md');
expect(body).toContain('log.md');
});
it('skill is reachable from the skill tree', () => {
expect(existsSync(SKILL_MD)).toBe(true);
});
});
+16
View File
@@ -165,6 +165,22 @@ describe('findTrajectory — visibility filter (D-CDX-1 / R6)', () => {
const all = await engine.findTrajectory({ entitySlug: 'traj-vis-default' });
expect(all.length).toBe(2);
});
test('remote=true + trustedFactReads bypasses world-only (owner-trusted reads)', async () => {
await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 50000, visibility: 'private', valid_from: new Date('2026-01-15') });
await insertTyped({ entity_slug: 'traj-vis-trusted', metric: 'mrr', value: 99999, visibility: 'world', valid_from: new Date('2026-04-12') });
// Untrusted remote: world only.
const untrusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true });
expect(untrusted.length).toBe(1);
expect(untrusted[0].value).toBe(99999);
// Owner-trusted remote: sees the private point too. remote stays true — only
// fact-read visibility is elevated.
const trusted = await engine.findTrajectory({ entitySlug: 'traj-vis-trusted', remote: true, trustedFactReads: true });
expect(trusted.length).toBe(2);
expect(trusted.map(p => p.value).sort((a, b) => (a! - b!))).toEqual([50000, 99999]);
});
});
describe('findTrajectory — metric + since + until filters', () => {
+43
View File
@@ -0,0 +1,43 @@
import { describe, test, expect } from 'bun:test';
import {
factsWorldOnly,
readableFactVisibilities,
} from '../src/core/facts/reader-trust.ts';
describe('factsWorldOnly', () => {
test('FAIL-CLOSED: unset remote is untrusted (world-only)', () => {
expect(factsWorldOnly({})).toBe(true);
expect(factsWorldOnly({ remote: undefined })).toBe(true);
expect(factsWorldOnly({ trustedFactReads: false })).toBe(true);
});
test('explicit remote=false (trusted local CLI) sees all', () => {
expect(factsWorldOnly({ remote: false })).toBe(false);
expect(factsWorldOnly({ remote: false, trustedFactReads: false })).toBe(false);
});
test('untrusted remote callers are world-only', () => {
expect(factsWorldOnly({ remote: true })).toBe(true);
expect(factsWorldOnly({ remote: true, trustedFactReads: false })).toBe(true);
});
test('owner-trusted remote reads bypass the world-only filter', () => {
expect(factsWorldOnly({ remote: true, trustedFactReads: true })).toBe(false);
});
test('trustedFactReads is a no-op for an already-trusted local caller', () => {
expect(factsWorldOnly({ remote: false, trustedFactReads: true })).toBe(false);
});
});
describe('readableFactVisibilities', () => {
test("world-only readers get the ['world'] filter (incl. unset remote)", () => {
expect(readableFactVisibilities({ remote: true })).toEqual(['world']);
expect(readableFactVisibilities({})).toEqual(['world']);
});
test('trusted readers get undefined (no filter — all rows)', () => {
expect(readableFactVisibilities({ remote: false })).toBeUndefined();
expect(readableFactVisibilities({ remote: true, trustedFactReads: true })).toBeUndefined();
});
});
-51
View File
@@ -1,51 +0,0 @@
import { describe, expect, it } from 'bun:test';
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'obsidian-gbrain-safe-index');
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
function parseFrontmatter(raw: string): Record<string, unknown> {
const m = raw.match(/^---\n([\s\S]*?)\n---/);
if (!m) throw new Error('no frontmatter');
const out: Record<string, unknown> = {};
for (const line of m[1].split('\n')) {
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
if (mm) out[mm[1]] = mm[2].trim();
}
return out;
}
describe('obsidian-gbrain-safe-index skill', () => {
it('has a SKILL.md with required frontmatter', () => {
expect(existsSync(SKILL_MD)).toBe(true);
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
expect(fm['name']).toBe('obsidian-gbrain-safe-index');
expect(fm['description']).toBeTruthy();
});
it('has the required conformance sections', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
expect(body.includes(section), `missing ${section}`).toBe(true);
}
});
it('is registered in RESOLVER.md', () => {
expect(existsSync(RESOLVER)).toBe(true);
const resolver = readFileSync(RESOLVER, 'utf-8');
expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
});
it('has routing-eval fixtures that exercise real trigger phrasings', () => {
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
expect(existsSync(evalPath)).toBe(true);
const lines = readFileSync(evalPath, 'utf-8')
.split('\n')
.filter((l) => l.trim() && !l.trim().startsWith('//'))
.map((l) => JSON.parse(l));
const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
expect(positives.length).toBeGreaterThanOrEqual(5);
});
});
-64
View File
@@ -1,64 +0,0 @@
import { describe, expect, it } from 'bun:test';
import { readFileSync, existsSync } from 'fs';
import { join } from 'path';
import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
function parseFrontmatter(raw: string): Record<string, unknown> {
const m = raw.match(/^---\n([\s\S]*?)\n---/);
if (!m) throw new Error('no frontmatter');
const out: Record<string, unknown> = {};
for (const line of m[1].split('\n')) {
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
if (mm) out[mm[1]] = mm[2].trim();
}
return out;
}
describe('skill-vault-capture-policy skill', () => {
it('has a SKILL.md with required frontmatter', () => {
expect(existsSync(SKILL_MD)).toBe(true);
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
expect(fm['name']).toBe('skill-vault-capture-policy');
expect(fm['description']).toBeTruthy();
});
it('has the required conformance sections', () => {
const body = readFileSync(SKILL_MD, 'utf-8');
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
expect(body.includes(section), `missing ${section}`).toBe(true);
}
});
it('is registered in RESOLVER.md', () => {
expect(existsSync(RESOLVER)).toBe(true);
expect(readFileSync(RESOLVER, 'utf-8').includes('skill-vault-capture-policy/SKILL.md')).toBe(true);
});
it('contains no private user or agent-fork names (privacy rule)', () => {
for (const file of [SKILL_MD, join(SKILL_DIR, 'routing-eval.jsonl')]) {
const body = readFileSync(file, 'utf-8');
// DEFAULT_PRIVATE_PATTERNS[0] is the banned fork-name pattern; sourced
// from harvest-lint so this file never contains the literal itself
// (scripts/check-privacy.sh would reject it).
const forkName = new RegExp(DEFAULT_PRIVATE_PATTERNS[0], 'i');
for (const name of [/\bAdam\b/, /\bHermes\b/, /\bHerdr\b/, /\bArk\b/, forkName]) {
expect(name.test(body), `private name ${name} in ${file}`).toBe(false);
}
}
});
it('has routing-eval fixtures', () => {
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
expect(existsSync(evalPath)).toBe(true);
const positives = readFileSync(evalPath, 'utf-8')
.split('\n')
.filter((l) => l.trim() && !l.trim().startsWith('//'))
.map((l) => JSON.parse(l))
.filter((l) => l.expected_skill === 'skill-vault-capture-policy');
expect(positives.length).toBeGreaterThanOrEqual(4);
});
});