mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 18:32:41 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
aa45398d83 |
+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}
|
||||
@@ -14,7 +14,7 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from './engine.ts';
|
||||
import { PGVECTOR_HNSW_VECTOR_MAX_DIMS } from './vector-index.ts';
|
||||
import { PGVECTOR_HNSW_VECTOR_MAX_DIMS, hnswMaxDimsForType } from './vector-index.ts';
|
||||
import { gbrainPath } from './config.ts';
|
||||
import { resolveRecipe } from './ai/model-resolver.ts';
|
||||
import type { Recipe } from './ai/types.ts';
|
||||
@@ -609,6 +609,17 @@ export function buildFactsAlterRecipe(
|
||||
const opclass = columnType === 'halfvec' ? 'halfvec_cosine_ops' : 'vector_cosine_ops';
|
||||
const targetType = columnType === 'halfvec' ? `halfvec(${configuredDims})` : `vector(${configuredDims})`;
|
||||
const dimsChanged = columnDims !== configuredDims;
|
||||
const hnswMaxDims = hnswMaxDimsForType(columnType);
|
||||
const indexLines = configuredDims <= hnswMaxDims
|
||||
? [
|
||||
`CREATE INDEX idx_facts_embedding_hnsw`,
|
||||
` ON facts USING hnsw (embedding ${opclass})`,
|
||||
` WHERE embedding IS NOT NULL AND expired_at IS NULL;`,
|
||||
]
|
||||
: [
|
||||
`-- Skip reindex. ${columnType}(${configuredDims}) exceeds pgvector's HNSW cap of ${hnswMaxDims};`,
|
||||
`-- fact similarity falls back to exact scans.`,
|
||||
];
|
||||
return [
|
||||
`-- ALTER ${columnType}(${columnDims}) → ${columnType}(${configuredDims}) on indexed column.`,
|
||||
`-- HOLD a maintenance window: this rewrites every row's embedding.`,
|
||||
@@ -629,9 +640,7 @@ export function buildFactsAlterRecipe(
|
||||
: []),
|
||||
`ALTER TABLE facts ALTER COLUMN embedding TYPE ${targetType}`,
|
||||
` USING embedding::${targetType};`,
|
||||
`CREATE INDEX idx_facts_embedding_hnsw`,
|
||||
` ON facts USING hnsw (embedding ${opclass})`,
|
||||
` WHERE embedding IS NOT NULL AND expired_at IS NULL;`,
|
||||
...indexLines,
|
||||
].join('\n');
|
||||
}
|
||||
|
||||
|
||||
+21
-8
@@ -1,6 +1,7 @@
|
||||
import type { BrainEngine } from './engine.ts';
|
||||
import { slugifyPath } from './sync.ts';
|
||||
import { getFtsLanguage } from './fts-language.ts';
|
||||
import { hnswMaxDimsForType } from './vector-index.ts';
|
||||
|
||||
/**
|
||||
* Schema migrations — run automatically on initSchema().
|
||||
@@ -2276,11 +2277,19 @@ export const MIGRATIONS: Migration[] = [
|
||||
useHalfvec = true;
|
||||
}
|
||||
|
||||
const vecType = useHalfvec ? 'HALFVEC' : 'VECTOR';
|
||||
const columnType = useHalfvec ? 'halfvec' : 'vector';
|
||||
const vecType = columnType.toUpperCase();
|
||||
// HNSW operator class must match the column type:
|
||||
// VECTOR(n) → vector_cosine_ops
|
||||
// HALFVEC(n) → halfvec_cosine_ops
|
||||
const opclass = useHalfvec ? 'halfvec_cosine_ops' : 'vector_cosine_ops';
|
||||
const hnswMaxDims = hnswMaxDimsForType(columnType);
|
||||
const factsEmbeddingIndexSql = embeddingDim <= hnswMaxDims
|
||||
? `CREATE INDEX IF NOT EXISTS idx_facts_embedding_hnsw
|
||||
ON facts USING hnsw (embedding ${opclass})
|
||||
WHERE embedding IS NOT NULL AND expired_at IS NULL;`
|
||||
: `-- idx_facts_embedding_hnsw skipped: pgvector HNSW ${columnType} indexes support
|
||||
-- at most ${hnswMaxDims} dimensions; exact vector scans remain available.`;
|
||||
// FK to sources is added in a separate ALTER TABLE rather than inline
|
||||
// on the column. Inline `REFERENCES` worked on PGLite but silently
|
||||
// got dropped by postgres.js's `unsafe()` multi-statement path on
|
||||
@@ -2354,9 +2363,7 @@ export const MIGRATIONS: Migration[] = [
|
||||
ON facts(source_id, entity_slug)
|
||||
WHERE consolidated_at IS NULL AND expired_at IS NULL;
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_facts_embedding_hnsw
|
||||
ON facts USING hnsw (embedding ${opclass})
|
||||
WHERE embedding IS NOT NULL AND expired_at IS NULL;
|
||||
${factsEmbeddingIndexSql}
|
||||
`;
|
||||
|
||||
await engine.runMigration(40, factsDDL);
|
||||
@@ -2870,8 +2877,16 @@ export const MIGRATIONS: Migration[] = [
|
||||
useHalfvec = true;
|
||||
}
|
||||
|
||||
const vecType = useHalfvec ? 'HALFVEC' : 'VECTOR';
|
||||
const columnType = useHalfvec ? 'halfvec' : 'vector';
|
||||
const vecType = columnType.toUpperCase();
|
||||
const opclass = useHalfvec ? 'halfvec_cosine_ops' : 'vector_cosine_ops';
|
||||
const hnswMaxDims = hnswMaxDimsForType(columnType);
|
||||
const queryCacheEmbeddingIndexSql = embeddingDim <= hnswMaxDims
|
||||
? `CREATE INDEX IF NOT EXISTS idx_query_cache_embedding_hnsw
|
||||
ON query_cache USING hnsw (embedding ${opclass})
|
||||
WHERE embedding IS NOT NULL;`
|
||||
: `-- idx_query_cache_embedding_hnsw skipped: pgvector HNSW ${columnType} indexes support
|
||||
-- at most ${hnswMaxDims} dimensions; exact vector scans remain available.`;
|
||||
|
||||
const ddl = `
|
||||
CREATE TABLE IF NOT EXISTS query_cache (
|
||||
@@ -2890,9 +2905,7 @@ export const MIGRATIONS: Migration[] = [
|
||||
CREATE INDEX IF NOT EXISTS idx_query_cache_source_created
|
||||
ON query_cache(source_id, created_at DESC);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_query_cache_embedding_hnsw
|
||||
ON query_cache USING hnsw (embedding ${opclass})
|
||||
WHERE embedding IS NOT NULL;
|
||||
${queryCacheEmbeddingIndexSql}
|
||||
`;
|
||||
|
||||
await engine.runMigration(55, ddl);
|
||||
|
||||
@@ -17,6 +17,7 @@
|
||||
import type { BrainEngine } from './engine.ts';
|
||||
|
||||
export const PGVECTOR_HNSW_VECTOR_MAX_DIMS = 2000;
|
||||
export const PGVECTOR_HNSW_HALFVEC_MAX_DIMS = 4000;
|
||||
|
||||
const CHUNK_EMBEDDING_HNSW_INDEX =
|
||||
'CREATE INDEX IF NOT EXISTS idx_chunks_embedding ON content_chunks USING hnsw (embedding vector_cosine_ops);';
|
||||
@@ -29,6 +30,10 @@ export function chunkEmbeddingIndexSql(dims: number): string {
|
||||
].join('\n');
|
||||
}
|
||||
|
||||
export function hnswMaxDimsForType(columnType: 'vector' | 'halfvec'): number {
|
||||
return columnType === 'halfvec' ? PGVECTOR_HNSW_HALFVEC_MAX_DIMS : PGVECTOR_HNSW_VECTOR_MAX_DIMS;
|
||||
}
|
||||
|
||||
export function applyChunkEmbeddingIndexPolicy(sql: string, dims: number): string {
|
||||
return sql.replaceAll(CHUNK_EMBEDDING_HNSW_INDEX, chunkEmbeddingIndexSql(dims));
|
||||
}
|
||||
|
||||
@@ -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);
|
||||
});
|
||||
});
|
||||
@@ -122,9 +122,9 @@ describe('buildFactsAlterRecipe', () => {
|
||||
});
|
||||
|
||||
test('vector recipe uses vector_cosine_ops + vector(N) USING cast', () => {
|
||||
const recipe = buildFactsAlterRecipe(1024, 2048, 'vector');
|
||||
expect(recipe).toContain('vector(2048)');
|
||||
expect(recipe).toContain('USING embedding::vector(2048)');
|
||||
const recipe = buildFactsAlterRecipe(1024, 1536, 'vector');
|
||||
expect(recipe).toContain('vector(1536)');
|
||||
expect(recipe).toContain('USING embedding::vector(1536)');
|
||||
expect(recipe).toContain('vector_cosine_ops');
|
||||
expect(recipe).not.toContain('halfvec_cosine_ops');
|
||||
});
|
||||
@@ -163,6 +163,14 @@ describe('buildFactsAlterRecipe', () => {
|
||||
expect(recipe).not.toContain('UPDATE facts SET embedding = NULL');
|
||||
expect(recipe).toContain('USING embedding::vector(1536)');
|
||||
});
|
||||
|
||||
test('halfvec recipe skips HNSW rebuild above pgvector cap', () => {
|
||||
const recipe = buildFactsAlterRecipe(1536, 4096, 'halfvec');
|
||||
expect(recipe).toContain('halfvec(4096)');
|
||||
expect(recipe).toContain('Skip reindex');
|
||||
expect(recipe).toContain("exceeds pgvector's HNSW cap of 4000");
|
||||
expect(recipe).not.toMatch(/CREATE INDEX idx_facts_embedding_hnsw[\s\S]*USING hnsw/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('FactsEmbeddingDimMismatchError', () => {
|
||||
|
||||
@@ -11,6 +11,7 @@
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { configureGateway, resetGateway } from '../src/core/ai/gateway.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
@@ -93,4 +94,60 @@ describe('migration v45 facts column shape', () => {
|
||||
);
|
||||
expect(after[0].udt_name).toBe(before[0].udt_name);
|
||||
});
|
||||
|
||||
});
|
||||
|
||||
describe('migration v45/v55 large-dim HNSW policy', () => {
|
||||
let largeDimEngine: PGLiteEngine;
|
||||
|
||||
beforeAll(async () => {
|
||||
configureGateway({
|
||||
embedding_model: 'litellm:custom-4096d',
|
||||
embedding_dimensions: 4096,
|
||||
env: { ...process.env },
|
||||
});
|
||||
|
||||
largeDimEngine = new PGLiteEngine();
|
||||
await largeDimEngine.connect({});
|
||||
await largeDimEngine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await largeDimEngine.disconnect();
|
||||
resetGateway();
|
||||
});
|
||||
|
||||
test('4096d init skips unsupported HNSW indexes but keeps vector columns', async () => {
|
||||
const formatRows = await largeDimEngine.executeRaw<{ format_type: string }>(
|
||||
`SELECT format_type(atttypid, atttypmod) AS format_type
|
||||
FROM pg_attribute
|
||||
WHERE attrelid = 'facts'::regclass AND attname = 'embedding'`,
|
||||
);
|
||||
expect(formatRows[0]?.format_type).toMatch(/(halfvec|vector)\(4096\)/);
|
||||
|
||||
const indexRows = await largeDimEngine.executeRaw<{ exists: boolean }>(
|
||||
`SELECT EXISTS (
|
||||
SELECT 1 FROM pg_indexes
|
||||
WHERE tablename = 'facts'
|
||||
AND indexname = 'idx_facts_embedding_hnsw'
|
||||
) AS exists`,
|
||||
);
|
||||
expect(indexRows[0]?.exists).toBe(false);
|
||||
|
||||
const queryCacheFormatRows = await largeDimEngine.executeRaw<{ format_type: string }>(
|
||||
`SELECT format_type(atttypid, atttypmod) AS format_type
|
||||
FROM pg_attribute
|
||||
WHERE attrelid = 'query_cache'::regclass AND attname = 'embedding'`,
|
||||
);
|
||||
expect(queryCacheFormatRows[0]?.format_type).toMatch(/(halfvec|vector)\(4096\)/);
|
||||
|
||||
const queryCacheIndexRows = await largeDimEngine.executeRaw<{ exists: boolean }>(
|
||||
`SELECT EXISTS (
|
||||
SELECT 1 FROM pg_indexes
|
||||
WHERE tablename = 'query_cache'
|
||||
AND indexname = 'idx_query_cache_embedding_hnsw'
|
||||
) AS exists`,
|
||||
);
|
||||
expect(queryCacheIndexRows[0]?.exists).toBe(false);
|
||||
}, 60000);
|
||||
});
|
||||
|
||||
@@ -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 ${section}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('is registered in RESOLVER.md', () => {
|
||||
expect(existsSync(RESOLVER)).toBe(true);
|
||||
const resolver = readFileSync(RESOLVER, 'utf-8');
|
||||
expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
|
||||
});
|
||||
|
||||
it('has routing-eval fixtures that exercise real trigger phrasings', () => {
|
||||
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
|
||||
expect(existsSync(evalPath)).toBe(true);
|
||||
const lines = readFileSync(evalPath, 'utf-8')
|
||||
.split('\n')
|
||||
.filter((l) => l.trim() && !l.trim().startsWith('//'))
|
||||
.map((l) => JSON.parse(l));
|
||||
const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
|
||||
expect(positives.length).toBeGreaterThanOrEqual(5);
|
||||
});
|
||||
});
|
||||
@@ -1,64 +0,0 @@
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { readFileSync, existsSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
|
||||
|
||||
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
|
||||
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
|
||||
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
|
||||
|
||||
function parseFrontmatter(raw: string): Record<string, unknown> {
|
||||
const m = raw.match(/^---\n([\s\S]*?)\n---/);
|
||||
if (!m) throw new Error('no frontmatter');
|
||||
const out: Record<string, unknown> = {};
|
||||
for (const line of m[1].split('\n')) {
|
||||
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
|
||||
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