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
|
5882d5261a | ||
|
|
a5a80549e5 |
+1
-3
@@ -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) |
|
||||
|
||||
@@ -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
@@ -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
@@ -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": {
|
||||
|
||||
@@ -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}
|
||||
@@ -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}
|
||||
@@ -820,6 +820,10 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
|
||||
// v0.42.x (#1794, 4A): pool-budget nudge when GBRAIN_MAX_CONNECTIONS is set.
|
||||
checks.push(await checkPoolBudget(engine));
|
||||
|
||||
// #2552: warn when an explicit embed-concurrency override fans out against
|
||||
// a local single-slot embedding endpoint (silent backfill starvation).
|
||||
checks.push(await checkEmbedConcurrency());
|
||||
|
||||
// v0.42.7 (#1696): link-extraction lag. Strictly SQL (single indexed COUNT),
|
||||
// safe on the thin-client/remote path — remote operators on checkout-less
|
||||
// Postgres brains are exactly who can't otherwise see the extraction backlog.
|
||||
@@ -3815,6 +3819,61 @@ export function computePoolBudgetCheck(
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: warn when an explicit GBRAIN_EMBED_CONCURRENCY override fans out
|
||||
* against a local single-slot embedding endpoint (Ollama / llama-server /
|
||||
* localhost base URL). Requests serialize on the one loaded model, so N
|
||||
* parallel pages multiply latency xN and can exceed the fetch timeout with
|
||||
* no surfaced error — the backfill silently starves. (When the env var is
|
||||
* unset, embed auto-caps at LOCAL_EMBED_CONCURRENCY_CAP and this check
|
||||
* reports ok.) Pure; exported for tests.
|
||||
*/
|
||||
export function computeEmbedConcurrencyCheck(
|
||||
isLocalEndpoint: boolean,
|
||||
envValue: string | undefined,
|
||||
localCap: number,
|
||||
): Check {
|
||||
const name = 'embed_concurrency';
|
||||
if (!isLocalEndpoint) {
|
||||
return { name, status: 'ok', message: 'Embedding endpoint is not a local inference server — cloud concurrency defaults apply.' };
|
||||
}
|
||||
const parsed = envValue ? parseInt(envValue, 10) : NaN;
|
||||
if (envValue && Number.isFinite(parsed) && parsed > localCap) {
|
||||
return {
|
||||
name,
|
||||
status: 'warn',
|
||||
message:
|
||||
`GBRAIN_EMBED_CONCURRENCY=${parsed} against a local embedding endpoint. ` +
|
||||
`Local inference servers serialize requests, so ${parsed} parallel pages multiply ` +
|
||||
`latency x${parsed} and can exceed the fetch timeout — the embed backfill stalls ` +
|
||||
`with no error. Unset GBRAIN_EMBED_CONCURRENCY (auto-caps at ${localCap}) or set it <= ${localCap}.`,
|
||||
};
|
||||
}
|
||||
return {
|
||||
name,
|
||||
status: 'ok',
|
||||
message: `Local embedding endpoint detected; embed concurrency capped at ${envValue ? parsed : localCap}.`,
|
||||
};
|
||||
}
|
||||
|
||||
/** Thin gateway/env wrapper over `computeEmbedConcurrencyCheck`. */
|
||||
export async function checkEmbedConcurrency(): Promise<Check> {
|
||||
try {
|
||||
const { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } = await import('../core/ai/gateway.ts');
|
||||
return computeEmbedConcurrencyCheck(
|
||||
isLocalEmbeddingEndpoint(),
|
||||
process.env.GBRAIN_EMBED_CONCURRENCY,
|
||||
LOCAL_EMBED_CONCURRENCY_CAP,
|
||||
);
|
||||
} catch (err) {
|
||||
return {
|
||||
name: 'embed_concurrency',
|
||||
status: 'ok',
|
||||
message: `Skipped (${err instanceof Error ? err.message : String(err)})`,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
/** Thin env/engine wrapper over `computePoolBudgetCheck`. */
|
||||
export async function checkPoolBudget(_engine: BrainEngine): Promise<Check> {
|
||||
try {
|
||||
|
||||
+30
-8
@@ -1,5 +1,6 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
|
||||
import { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } from '../core/ai/gateway.ts';
|
||||
import type { ChunkInput } from '../core/types.ts';
|
||||
import { chunkText } from '../core/chunkers/recursive.ts';
|
||||
import { createProgress, type ProgressReporter } from '../core/progress.ts';
|
||||
@@ -176,6 +177,31 @@ export class EmbeddingDimMismatchError extends Error {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: resolve the bulk-embed worker count. Env override or the
|
||||
* cloud-tuned default of 20 — but when the operator did NOT set
|
||||
* GBRAIN_EMBED_CONCURRENCY and the embedding endpoint is a local inference
|
||||
* server (Ollama / llama-server / localhost base URL), cap at
|
||||
* LOCAL_EMBED_CONCURRENCY_CAP: 20 parallel pages against a single-slot
|
||||
* server serialize on the one loaded model, multiply latency x20 past the
|
||||
* fetch timeout, and starve the backfill with no surfaced error. An
|
||||
* explicit env value always wins (`gbrain doctor` warns instead).
|
||||
* Pacing only ever LOWERS concurrency (Codex P2).
|
||||
*/
|
||||
export function resolveEmbedConcurrency(paceMaxConcurrency?: number): number {
|
||||
const envSet = !!process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
const base = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
let resolved = base;
|
||||
if (!envSet && isLocalEmbeddingEndpoint() && base > LOCAL_EMBED_CONCURRENCY_CAP) {
|
||||
resolved = LOCAL_EMBED_CONCURRENCY_CAP;
|
||||
serr(
|
||||
`[embed] local embedding endpoint detected — capping concurrency at ` +
|
||||
`${LOCAL_EMBED_CONCURRENCY_CAP} (set GBRAIN_EMBED_CONCURRENCY to override)`,
|
||||
);
|
||||
}
|
||||
return paceMaxConcurrency ? Math.min(resolved, paceMaxConcurrency) : resolved;
|
||||
}
|
||||
|
||||
/**
|
||||
* Pre-flight check: read the actual schema column dim and compare to the
|
||||
* gateway's resolved dim. Throws `EmbeddingDimMismatchError` on mismatch
|
||||
@@ -677,10 +703,8 @@ async function embedAll(
|
||||
// Paced runs lower this to the resolved cap (the real lever vs pooler-slot
|
||||
// starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
|
||||
// never raise above an operator's existing env cap.
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
// #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
|
||||
const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
|
||||
|
||||
async function embedOnePage(page: typeof pages[number]) {
|
||||
// #1737: bail before doing any work for this page if the run was aborted.
|
||||
@@ -855,10 +879,8 @@ async function embedAllStale(
|
||||
// Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
|
||||
// lever on this single pool, no separate permit). Codex P2: pacing only ever
|
||||
// LOWERS concurrency — never raise above an operator's existing env cap.
|
||||
const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
|
||||
const CONCURRENCY = staleOpts?.paceMaxConcurrency
|
||||
? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
|
||||
: BASE_CONCURRENCY;
|
||||
// #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
|
||||
const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
|
||||
const pacer = staleOpts?.pacer ?? createNoopPacer();
|
||||
|
||||
// D3 + D3a + D8: wall-clock budget. 30 min default; env override.
|
||||
|
||||
@@ -683,6 +683,33 @@ export function getEmbeddingDimensions(): number {
|
||||
return requireConfig().embedding_dimensions ?? DEFAULT_EMBEDDING_DIMENSIONS;
|
||||
}
|
||||
|
||||
/**
|
||||
* #2552: cap for parallel bulk-embed workers against a local inference
|
||||
* server. A single-slot Ollama/llama-server serializes requests, so the
|
||||
* cloud-tuned 20-worker fan-out multiplies latency x20 and blows past the
|
||||
* fetch timeout with no surfaced error (the backfill silently starves).
|
||||
*/
|
||||
export const LOCAL_EMBED_CONCURRENCY_CAP = 2;
|
||||
|
||||
/**
|
||||
* #2552: true when the configured embedding model routes to a local
|
||||
* inference server — the `ollama` / `llama-server` recipes, or any recipe
|
||||
* whose base URL was explicitly pointed at localhost. Bulk callers use this
|
||||
* to pick CPU-safe concurrency defaults; `gbrain doctor` uses it to warn
|
||||
* about an explicit cloud-sized override. Fail-open: unconfigured or
|
||||
* unresolvable gateway → false (cloud behavior, the historical default).
|
||||
*/
|
||||
export function isLocalEmbeddingEndpoint(): boolean {
|
||||
try {
|
||||
const { recipe } = resolveRecipe(getEmbeddingModel());
|
||||
if (recipe.id === 'ollama' || recipe.id === 'llama-server') return true;
|
||||
const base = requireConfig().base_urls?.[recipe.id] ?? '';
|
||||
return /\/\/(localhost|127\.0\.0\.1|\[::1\])(:|\/|$)/i.test(base);
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.28.11: returns the configured multimodal embedding model when set,
|
||||
* or undefined if the brain falls back to `embedding_model` for multimodal
|
||||
|
||||
@@ -29,9 +29,17 @@ export const ollama: Recipe = {
|
||||
trust_custom_dims: true, // #2271: local models carry varied native dims
|
||||
cost_per_1m_tokens_usd: 0,
|
||||
price_last_verified: '2026-04-20',
|
||||
// Ollama's batch capacity depends on the locally loaded model + the
|
||||
// OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
|
||||
no_batch_cap: true,
|
||||
// #2552: Ollama's true batch capacity depends on the locally loaded
|
||||
// model + OLLAMA_NUM_PARALLEL, but the previous `no_batch_cap: true`
|
||||
// meant a whole page went out in ONE request — on a CPU-only box that
|
||||
// multiplies latency past the fetch timeout and the backfill starves
|
||||
// with no surfaced error. Ollama doesn't return a recognizable
|
||||
// token-limit error either, so the recursive-halving safety net never
|
||||
// fires; a conservative static pre-split cap is the only guard.
|
||||
// 4096 tokens x 2 chars/token ~= 8K chars per request (code-dense
|
||||
// pages run ~2 chars/token, not the tiktoken-ish 4).
|
||||
max_batch_tokens: 4096,
|
||||
chars_per_token: 2,
|
||||
},
|
||||
},
|
||||
setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',
|
||||
|
||||
@@ -141,6 +141,7 @@ export const OPS_CHECK_NAMES: ReadonlySet<string> = new Set([
|
||||
'pgbouncer_prepare',
|
||||
'pgvector',
|
||||
'pool_budget',
|
||||
'embed_concurrency',
|
||||
'progressive_batch_audit_health',
|
||||
'queue_health',
|
||||
'reranker_health',
|
||||
|
||||
@@ -56,7 +56,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
|
||||
import { finalizeLastSeen } from './chronicle/last-seen.ts';
|
||||
import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
|
||||
import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
|
||||
import {
|
||||
normalizeEngineColumn,
|
||||
buildVectorCastFragment,
|
||||
@@ -1591,6 +1591,8 @@ export class PGLiteEngine implements BrainEngine {
|
||||
}
|
||||
|
||||
// v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, innerLimit, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.language) {
|
||||
@@ -1630,6 +1632,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const keywordSql =
|
||||
`WITH ranked AS (
|
||||
@@ -1637,14 +1640,14 @@ export class PGLiteEngine implements BrainEngine {
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
-- v0.27.1: hide image rows from default text-keyword search so
|
||||
-- OCR text doesn't drown text-page hits. Image-similarity queries
|
||||
-- run a separate vector path on embedding_image.
|
||||
@@ -1712,7 +1715,10 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.type) {
|
||||
@@ -1760,7 +1766,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
COALESCE(rep.chunk_index, 0) as chunk_index,
|
||||
COALESCE(rep.chunk_text, '') as chunk_text,
|
||||
COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
|
||||
ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
@@ -1775,7 +1781,7 @@ export class PGLiteEngine implements BrainEngine {
|
||||
ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
|
||||
LIMIT 1
|
||||
) rep ON true
|
||||
WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
WHERE p.search_vector @@ ${ftsQueryExpr}
|
||||
${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
ORDER BY score DESC, p.id ASC
|
||||
LIMIT $2 OFFSET $3`;
|
||||
@@ -1962,6 +1968,8 @@ export class PGLiteEngine implements BrainEngine {
|
||||
});
|
||||
}
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query, limit, offset];
|
||||
let extraFilter = '';
|
||||
if (opts?.language) {
|
||||
@@ -1996,20 +2004,21 @@ export class PGLiteEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const { rows } = await this.db.query(
|
||||
`SELECT
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
CASE WHEN p.updated_at < (
|
||||
SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
|
||||
) THEN true ELSE false END AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
|
||||
ORDER BY score DESC
|
||||
LIMIT $2 OFFSET $3`,
|
||||
params
|
||||
|
||||
@@ -64,7 +64,7 @@ import { ConnectionManager } from './connection-manager.ts';
|
||||
import { logConnectionEvent } from './connection-audit.ts';
|
||||
import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
|
||||
import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
|
||||
import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
|
||||
import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
|
||||
import { DELETE_BATCH_SIZE } from './engine-constants.ts';
|
||||
|
||||
@@ -1691,6 +1691,8 @@ export class PostgresEngine implements BrainEngine {
|
||||
const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
|
||||
const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (type) {
|
||||
@@ -1761,6 +1763,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const rawQuery = `
|
||||
WITH ranked_chunks AS (
|
||||
@@ -1768,11 +1771,11 @@ export class PostgresEngine implements BrainEngine {
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr}
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
@@ -1863,7 +1866,10 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (opts?.type) {
|
||||
@@ -1923,7 +1929,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
COALESCE(rep.chunk_index, 0) as chunk_index,
|
||||
COALESCE(rep.chunk_text, '') as chunk_text,
|
||||
COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
|
||||
ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
false AS stale
|
||||
FROM pages p
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
@@ -1936,7 +1942,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
|
||||
LIMIT 1
|
||||
) rep ON true
|
||||
WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
WHERE p.search_vector @@ ${ftsQueryExpr}
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
@@ -2000,6 +2006,8 @@ export class PostgresEngine implements BrainEngine {
|
||||
const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
|
||||
const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
|
||||
|
||||
// #2380: slash-bearing queries match both the split-word and literal
|
||||
// slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
|
||||
const params: unknown[] = [query];
|
||||
let typeClause = '';
|
||||
if (type) {
|
||||
@@ -2060,18 +2068,19 @@ export class PostgresEngine implements BrainEngine {
|
||||
// FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
|
||||
// — safe to interpolate into raw SQL.
|
||||
const ftsLang = getFtsLanguage();
|
||||
const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
|
||||
|
||||
const rawQuery = `
|
||||
SELECT
|
||||
p.slug, p.id as page_id, p.title, p.type, p.source_id,
|
||||
p.effective_date, p.effective_date_source,
|
||||
cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
|
||||
ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
|
||||
ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
|
||||
false AS stale
|
||||
FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
JOIN sources s ON s.id = p.source_id
|
||||
WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
|
||||
WHERE cc.search_vector @@ ${ftsQueryExpr}
|
||||
${typeClause}
|
||||
${typesClause}
|
||||
${excludeSlugsClause}
|
||||
|
||||
@@ -251,6 +251,28 @@ export function buildOrFallbackWebsearchQuery(query: string): string | null {
|
||||
return tokens.join(' OR ');
|
||||
}
|
||||
|
||||
/**
|
||||
* #2380: FTS query expression for slash-bearing queries. Postgres' default
|
||||
* text-search parser classifies `foo/bar` as a single `file`-alias lexeme —
|
||||
* on BOTH the query side and the index side. So a raw `foo/bar` query only
|
||||
* matched documents carrying the identical joined lexeme (literal paths),
|
||||
* and a slash-split query only matches documents whose text had the words
|
||||
* separated. Neither form alone covers both document shapes; OR the two
|
||||
* parses so a slash query matches prose ("foo and bar", stemmed, AND
|
||||
* semantics) AND literal slash forms ("src/core/x.ts") alike.
|
||||
*
|
||||
* Slash-free queries return the plain single-parse expression — byte-
|
||||
* identical SQL and identical ts_rank to the historical behavior.
|
||||
*
|
||||
* `ftsLang` is validated by getFtsLanguage() (safe to interpolate);
|
||||
* `param` is a `$N` placeholder, never user text.
|
||||
*/
|
||||
export function buildWebsearchQueryExpr(ftsLang: string, param: string, query: string): string {
|
||||
const plain = `websearch_to_tsquery('${ftsLang}', ${param})`;
|
||||
if (!query.includes('/')) return plain;
|
||||
return `(websearch_to_tsquery('${ftsLang}', translate(${param}, '/', ' ')) || ${plain})`;
|
||||
}
|
||||
|
||||
// ============================================================
|
||||
// v0.29.1 — Recency component SQL builder
|
||||
// ============================================================
|
||||
|
||||
@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
|
||||
for (const id of ['ollama', 'litellm', 'llama-server']) {
|
||||
test('LiteLLM and llama-server declare no_batch_cap: true', () => {
|
||||
for (const id of ['litellm', 'llama-server']) {
|
||||
const r = getRecipe(id);
|
||||
expect(r, `${id} not registered`).toBeDefined();
|
||||
expect(
|
||||
@@ -39,6 +39,18 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
|
||||
}
|
||||
});
|
||||
|
||||
test('#2552: Ollama declares a conservative static batch cap, not no_batch_cap', () => {
|
||||
// A CPU-only Ollama box wedges when a whole page ships in one request;
|
||||
// Ollama never returns a token-limit error so the recursive-halving
|
||||
// safety net can't fire. The pre-split cap is the only guard.
|
||||
const r = getRecipe('ollama');
|
||||
expect(r).toBeDefined();
|
||||
const e = r!.touchpoints.embedding!;
|
||||
expect(e.no_batch_cap).toBeUndefined();
|
||||
expect(e.max_batch_tokens).toBe(4096);
|
||||
expect(e.chars_per_token).toBe(2);
|
||||
});
|
||||
|
||||
test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
|
||||
warnSpy.mockClear();
|
||||
resetGateway();
|
||||
|
||||
@@ -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);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,118 @@
|
||||
/**
|
||||
* #2552: cloud-tuned embedding defaults silently wedge CPU-only local
|
||||
* endpoints (Ollama). Three-part fix under test:
|
||||
*
|
||||
* 1. `isLocalEmbeddingEndpoint()` — gateway helper detecting local
|
||||
* inference servers (ollama / llama-server recipes, localhost base URL).
|
||||
* 2. `resolveEmbedConcurrency()` — embed auto-caps the 20-worker fan-out
|
||||
* at LOCAL_EMBED_CONCURRENCY_CAP for local endpoints unless the
|
||||
* operator set GBRAIN_EMBED_CONCURRENCY explicitly.
|
||||
* 3. `computeEmbedConcurrencyCheck()` — doctor warns when an explicit env
|
||||
* override fans out against a local endpoint.
|
||||
*
|
||||
* Serial: mutates process.env and the module-global gateway config.
|
||||
*/
|
||||
|
||||
import { afterAll, afterEach, describe, expect, test } from 'bun:test';
|
||||
import {
|
||||
configureGateway,
|
||||
resetGateway,
|
||||
isLocalEmbeddingEndpoint,
|
||||
LOCAL_EMBED_CONCURRENCY_CAP,
|
||||
} from '../src/core/ai/gateway.ts';
|
||||
import { resolveEmbedConcurrency } from '../src/commands/embed.ts';
|
||||
import { computeEmbedConcurrencyCheck } from '../src/commands/doctor.ts';
|
||||
|
||||
const SAVED_ENV = process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
|
||||
afterEach(() => {
|
||||
resetGateway();
|
||||
if (SAVED_ENV === undefined) delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
else process.env.GBRAIN_EMBED_CONCURRENCY = SAVED_ENV;
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
describe('#2552 isLocalEmbeddingEndpoint', () => {
|
||||
test('false when the gateway is not configured (fail-open to cloud behavior)', () => {
|
||||
resetGateway();
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(false);
|
||||
});
|
||||
|
||||
test('true for the ollama recipe', () => {
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
|
||||
test('true for the llama-server recipe', () => {
|
||||
configureGateway({ embedding_model: 'llama-server:my-gguf', env: {} });
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
|
||||
test('false for a cloud recipe', () => {
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-small',
|
||||
env: { OPENAI_API_KEY: 'fake' },
|
||||
});
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(false);
|
||||
});
|
||||
|
||||
test('true when a cloud recipe base URL is explicitly pointed at localhost', () => {
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-small',
|
||||
env: { OPENAI_API_KEY: 'fake' },
|
||||
base_urls: { openai: 'http://localhost:8080/v1' },
|
||||
});
|
||||
expect(isLocalEmbeddingEndpoint()).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#2552 resolveEmbedConcurrency', () => {
|
||||
test('caps at LOCAL_EMBED_CONCURRENCY_CAP for a local endpoint when env is unset', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency()).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
|
||||
});
|
||||
|
||||
test('explicit env override always wins, even against a local endpoint', () => {
|
||||
process.env.GBRAIN_EMBED_CONCURRENCY = '10';
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency()).toBe(10);
|
||||
});
|
||||
|
||||
test('cloud endpoints keep the historical default of 20', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ env: { OPENAI_API_KEY: 'fake' } });
|
||||
expect(resolveEmbedConcurrency()).toBe(20);
|
||||
});
|
||||
|
||||
test('pacing only ever lowers concurrency', () => {
|
||||
delete process.env.GBRAIN_EMBED_CONCURRENCY;
|
||||
configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
|
||||
expect(resolveEmbedConcurrency(1)).toBe(1);
|
||||
expect(resolveEmbedConcurrency(16)).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
|
||||
});
|
||||
});
|
||||
|
||||
describe('#2552 computeEmbedConcurrencyCheck (doctor)', () => {
|
||||
test('ok for non-local endpoints', () => {
|
||||
expect(computeEmbedConcurrencyCheck(false, '20', 2).status).toBe('ok');
|
||||
});
|
||||
|
||||
test('warn when an explicit override exceeds the local cap', () => {
|
||||
const check = computeEmbedConcurrencyCheck(true, '20', 2);
|
||||
expect(check.status).toBe('warn');
|
||||
expect(check.message).toContain('GBRAIN_EMBED_CONCURRENCY=20');
|
||||
});
|
||||
|
||||
test('ok when env is unset against a local endpoint (auto-cap applies)', () => {
|
||||
expect(computeEmbedConcurrencyCheck(true, undefined, 2).status).toBe('ok');
|
||||
});
|
||||
|
||||
test('ok when the override is at or under the cap', () => {
|
||||
expect(computeEmbedConcurrencyCheck(true, '2', 2).status).toBe('ok');
|
||||
expect(computeEmbedConcurrencyCheck(true, '1', 2).status).toBe('ok');
|
||||
});
|
||||
});
|
||||
@@ -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);
|
||||
});
|
||||
});
|
||||
@@ -216,6 +216,67 @@ describe('PGLiteEngine: Search', () => {
|
||||
expect(results.length).toBe(0);
|
||||
});
|
||||
|
||||
// Regression (#2380): queries containing `/` used to bypass FTS AND
|
||||
// semantics. Postgres' default text-search parser classifies `foo/bar` as
|
||||
// a `file`-alias token mapped to the `simple` dictionary, so it became a
|
||||
// single un-stemmed lexeme `'foo/bar'` that never matches indexed text —
|
||||
// the primary FTS pass returned 0 and the OR fallback took over, matching
|
||||
// pages that contain EITHER term. searchKeyword/searchTitles now normalize
|
||||
// `/` to whitespace before websearch_to_tsquery parses, so the primary
|
||||
// AND pass matches directly.
|
||||
test('searchKeyword: slash query matches with AND semantics, not OR fallback', async () => {
|
||||
// Decoy shares only ONE of the two query terms ('enterprise').
|
||||
await engine.putPage('concepts/enterprise-pricing', {
|
||||
type: 'concept', title: 'Widget Pricing',
|
||||
compiled_truth: 'Enterprise pricing for widgets.',
|
||||
});
|
||||
await engine.upsertChunks('concepts/enterprise-pricing', [
|
||||
{ chunk_index: 0, chunk_text: 'Enterprise pricing for widgets', chunk_source: 'compiled_truth' },
|
||||
]);
|
||||
|
||||
// Both terms co-occur only in the novamind chunk. Pre-fix this returned
|
||||
// BOTH pages (primary pass zero-hit → OR fallback); post-fix the primary
|
||||
// AND pass returns exactly the co-occurrence page.
|
||||
const results = await engine.searchKeyword('NovaMind/enterprise');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('companies/novamind');
|
||||
});
|
||||
|
||||
test('searchTitles: slash query matches with AND semantics, not OR fallback', async () => {
|
||||
await engine.putPage('companies/novamind-enterprise', {
|
||||
type: 'company', title: 'NovaMind Enterprise Platform',
|
||||
compiled_truth: 'Placeholder body.',
|
||||
});
|
||||
await engine.putPage('guides/enterprise-sales', {
|
||||
type: 'concept', title: 'Enterprise Sales Guide',
|
||||
compiled_truth: 'Placeholder body.',
|
||||
});
|
||||
|
||||
// Pre-fix: `NovaMind/Enterprise` parsed as one file-alias lexeme → the
|
||||
// primary title pass returned 0 and the OR fallback matched BOTH titles.
|
||||
const results = await engine.searchTitles('NovaMind/Enterprise');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('companies/novamind-enterprise');
|
||||
});
|
||||
|
||||
test('searchKeyword: slash query still matches the literal slash form (file paths)', async () => {
|
||||
// The INDEX side also emits the joined file-alias lexeme for literal
|
||||
// `foo/bar` text, so a query normalized to split words alone would go
|
||||
// blind to documents containing the literal slash form (paths, URLs).
|
||||
// buildWebsearchQueryExpr ORs both parses; this pins the raw arm.
|
||||
await engine.putPage('runbooks/widget-deploy', {
|
||||
type: 'concept', title: 'Widget Deploy Runbook',
|
||||
compiled_truth: 'Runbook for the acme/widget deployment pipeline.',
|
||||
});
|
||||
await engine.upsertChunks('runbooks/widget-deploy', [
|
||||
{ chunk_index: 0, chunk_text: 'Runbook for the acme/widget deployment pipeline', chunk_source: 'compiled_truth' },
|
||||
]);
|
||||
|
||||
const results = await engine.searchKeyword('acme/widget');
|
||||
expect(results.length).toBe(1);
|
||||
expect(results[0].slug).toBe('runbooks/widget-deploy');
|
||||
});
|
||||
|
||||
test('tsvector trigger populates search_vector on insert', async () => {
|
||||
// Verify the PL/pgSQL trigger fires and content_chunks.search_vector is
|
||||
// populated from chunk_text. v0.20.0 Cathedral II Layer 3 moved FTS from
|
||||
|
||||
@@ -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);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user