mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-15 17:32:37 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Garry TanandClaude Fable 5
|
edf7fc6b5a | ||
|
|
b7f42f099a |
+3
-1
@@ -1411,7 +1411,8 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
|
||||
| Save or load reports | `skills/reports/SKILL.md` |
|
||||
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
|
||||
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
|
||||
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
|
||||
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
|
||||
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
|
||||
@@ -1429,6 +1430,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
|
||||
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
|
||||
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
|
||||
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
|
||||
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
|
||||
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
|
||||
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
|
||||
|
||||
@@ -39,8 +39,8 @@
|
||||
"skills/briefing",
|
||||
"skills/citation-fixer",
|
||||
"skills/concept-synthesis",
|
||||
"skills/cross-modal-review",
|
||||
"skills/cron-scheduler",
|
||||
"skills/cross-modal-review",
|
||||
"skills/daily-task-manager",
|
||||
"skills/daily-task-prep",
|
||||
"skills/data-research",
|
||||
@@ -54,10 +54,11 @@
|
||||
"skills/media-ingest",
|
||||
"skills/meeting-ingestion",
|
||||
"skills/minion-orchestrator",
|
||||
"skills/obsidian-gbrain-safe-index",
|
||||
"skills/perplexity-research",
|
||||
"skills/query",
|
||||
"skills/reports",
|
||||
"skills/repo-architecture",
|
||||
"skills/reports",
|
||||
"skills/signal-detector",
|
||||
"skills/skill-creator",
|
||||
"skills/skillify",
|
||||
|
||||
+3
-1
@@ -60,7 +60,8 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
|
||||
| Save or load reports | `skills/reports/SKILL.md` |
|
||||
| "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
|
||||
| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
|
||||
| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
|
||||
| "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
|
||||
| "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
|
||||
| "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
|
||||
@@ -78,6 +79,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
|
||||
| "Set up GBrain", first boot | `skills/setup/SKILL.md` |
|
||||
| "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
|
||||
| "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
|
||||
| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
|
||||
| Brain health check, maintenance run | `skills/maintain/SKILL.md` |
|
||||
| "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
|
||||
| "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |
|
||||
|
||||
+11
-1
@@ -2,7 +2,7 @@
|
||||
"name": "gbrain",
|
||||
"version": "0.32.3.0",
|
||||
"conformance_version": "1.0.0",
|
||||
"description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
|
||||
"description": "Personal knowledge brain with hybrid RAG search — GStack mod for agent platforms",
|
||||
"skills": [
|
||||
{
|
||||
"name": "ingest",
|
||||
@@ -34,6 +34,11 @@
|
||||
"path": "migrate/SKILL.md",
|
||||
"description": "Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam"
|
||||
},
|
||||
{
|
||||
"name": "obsidian-gbrain-safe-index",
|
||||
"path": "obsidian-gbrain-safe-index/SKILL.md",
|
||||
"description": "Connect and sync an Obsidian-style Markdown vault with gbrain using a cost-controlled import-first workflow, explicit embedding gates, and durable skill/workflow capture."
|
||||
},
|
||||
{
|
||||
"name": "setup",
|
||||
"path": "setup/SKILL.md",
|
||||
@@ -263,6 +268,11 @@
|
||||
"name": "skill-optimizer",
|
||||
"path": "skill-optimizer/SKILL.md",
|
||||
"description": "Self-evolving skill optimization via gbrain skillopt — SkillOpt-paper-grounded text-space optimizer with validation gating (median-of-3 + epsilon=0.05), bundled-skill safety, bootstrap review sentinel, per-skill DB lock, and atomic versioned writes."
|
||||
},
|
||||
{
|
||||
"name": "skill-vault-capture-policy",
|
||||
"path": "skill-vault-capture-policy/SKILL.md",
|
||||
"description": "Capture durable operational learnings, new agent skills, and environment/setup changes into the Obsidian vault instead of transient chat memory."
|
||||
}
|
||||
],
|
||||
"dependencies": {
|
||||
|
||||
@@ -0,0 +1,137 @@
|
||||
---
|
||||
name: obsidian-gbrain-safe-index
|
||||
version: 1.0.0
|
||||
description: |
|
||||
Connect, maintain, and sync an Obsidian-style Markdown vault with gbrain while preserving a cost-controlled workflow: the vault remains the source of truth, gbrain is the searchable/embedded index, durable skills/workflows are captured into the vault, and paid embedding runs only after explicit approval.
|
||||
triggers:
|
||||
- "connect Obsidian to gbrain"
|
||||
- "import my vault to gbrain"
|
||||
- "sync vault and gbrain"
|
||||
- "capture this skill in my vault"
|
||||
- "embed gbrain after vault update"
|
||||
- "is gbrain synced with my vault"
|
||||
tools:
|
||||
- terminal
|
||||
- read_file
|
||||
- search_files
|
||||
- write_file
|
||||
- patch
|
||||
mutating: true
|
||||
---
|
||||
|
||||
# Obsidian → gbrain Safe Index and Capture
|
||||
|
||||
## Contract
|
||||
|
||||
This skill guarantees:
|
||||
|
||||
- Treats the user's Obsidian-style Markdown vault as the source of truth before gbrain indexing.
|
||||
- Keeps gbrain in conservative mode unless the user explicitly approves a more expensive mode.
|
||||
- Imports vault changes with `--no-embed` first, then embeds only after explicit approval for the specific paid action.
|
||||
- Captures durable new skills, workflows, and environment learnings into the vault instead of leaving them only in chat memory.
|
||||
- Verifies every sync with concrete `gbrain stats`, search mode, and, when embeddings run, exact embedded chunk counts.
|
||||
|
||||
## Phases
|
||||
|
||||
1. **Resolve the vault path.**
|
||||
- Prefer an existing environment variable such as `OBSIDIAN_VAULT_PATH` or `WIKI_PATH`.
|
||||
- If no path is configured, search likely note directories and ask the user before writing.
|
||||
- Verify the directory exists and contains markdown files or an `.obsidian` directory.
|
||||
|
||||
2. **Read vault operating rules before writing.**
|
||||
- If the vault has `SCHEMA.md`, `index.md`, `log.md`, `AGENTS.md`, or similar operating files, read them before ingest/query/major edit.
|
||||
- Respect immutable source folders such as `raw/` when the vault declares them.
|
||||
- Use the vault's native link convention, usually Obsidian `[[wikilinks]]`, for durable relationships.
|
||||
|
||||
3. **MECE/capture decision.**
|
||||
- If new knowledge belongs on an existing page, update that page.
|
||||
- If it is a distinct recurring workflow or operational policy, create a small meta or concept page following the vault schema.
|
||||
- Update the vault index/catalog for every new page when the vault maintains one.
|
||||
- Append a log entry for meaningful vault updates when the vault maintains a log.
|
||||
|
||||
4. **Safe gbrain import path.**
|
||||
- Pre-check source directory; do not import a nonexistent path.
|
||||
- Run `gbrain config set search.mode conservative` before/after risky reinit steps.
|
||||
- Run `gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed`.
|
||||
- Run `gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"` when wikilinks changed materially.
|
||||
|
||||
5. **Paid embedding gate.**
|
||||
- Do not run `gbrain embed --stale` unless the user explicitly asks or a prior instruction clearly approved this exact paid action.
|
||||
- Before embedding, verify provider readiness with `gbrain providers test --model <provider:model>`.
|
||||
- Confirm the configured embedding dimensions match the local schema.
|
||||
- After embedding, verify `gbrain stats` and record exact `Pages`, `Chunks`, `Embedded`, and `Links` counts.
|
||||
|
||||
6. **Final verification and vault echo.**
|
||||
- Run `gbrain stats` and `gbrain search modes`.
|
||||
- If vault files changed, re-import with `--no-embed`; if embedding was approved, embed stale chunks afterward.
|
||||
- Report what changed, what was free/local, what used API billing, and what remains pending.
|
||||
|
||||
## Output Format
|
||||
|
||||
Use a compact status table:
|
||||
|
||||
| Item | Status |
|
||||
|---|---|
|
||||
| Vault path | `/path` |
|
||||
| Vault updated | yes/no + files |
|
||||
| gbrain mode | conservative/balanced/tokenmax |
|
||||
| Import | `--no-embed` completed / skipped / failed |
|
||||
| Pages/chunks | exact counts from `gbrain stats` |
|
||||
| Embeddings | exact count; note whether this run used API billing |
|
||||
| Links | exact count |
|
||||
| Background jobs | none / list exact jobs |
|
||||
|
||||
Then include:
|
||||
|
||||
- **Safe next step:** free/local action.
|
||||
- **Paid next step:** embedding/LLM action, if any, with explicit approval requirement.
|
||||
|
||||
## Anti-Patterns
|
||||
|
||||
- Creating a duplicate skill/page when an existing Obsidian, gbrain, or vault-ingest skill already covers the workflow.
|
||||
- Running `gbrain embed --stale`, `gbrain dream`, `gbrain autopilot --install`, `gbrain onboard --auto`, or `tokenmax` without explicit cost approval.
|
||||
- Importing a nonexistent or wrong directory and treating a zero-page import as success.
|
||||
- Forgetting to update the vault index/catalog and log after creating or materially updating vault pages.
|
||||
- Recording API keys, tokens, or raw secrets in the vault or final response.
|
||||
|
||||
## Tools Used
|
||||
|
||||
- `read_file` — read vault schema/index/log and target notes.
|
||||
- `search_files` — find existing vault pages and avoid duplicates.
|
||||
- `write_file` / `patch` — create or update vault pages.
|
||||
- `terminal` — run `gbrain`, `git`, and environment checks with secret values redacted.
|
||||
|
||||
## Safe Commands
|
||||
|
||||
```bash
|
||||
export PATH="$HOME/.bun/bin:$PATH"
|
||||
gbrain config set search.mode conservative
|
||||
gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed
|
||||
gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"
|
||||
gbrain stats
|
||||
gbrain search modes
|
||||
```
|
||||
|
||||
## Paid / Approval-Gated Commands
|
||||
|
||||
```bash
|
||||
gbrain providers test --model <provider:model>
|
||||
gbrain embed --stale
|
||||
gbrain dream
|
||||
gbrain autopilot --install
|
||||
gbrain onboard --auto --max-usd 5
|
||||
gbrain config set search.mode tokenmax
|
||||
```
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
- [ ] Vault path exists and is the intended source.
|
||||
- [ ] Vault operating files were read before edits when present.
|
||||
- [ ] Existing pages/skills were searched to avoid duplicates.
|
||||
- [ ] New/updated vault pages follow the vault schema and link convention.
|
||||
- [ ] Vault index/catalog updated for new pages when present.
|
||||
- [ ] Vault log appended for meaningful actions when present.
|
||||
- [ ] `gbrain import ... --no-embed` completed.
|
||||
- [ ] `gbrain stats` recorded pages/chunks/embeddings/links.
|
||||
- [ ] `gbrain search modes` confirms conservative mode unless a different mode was explicitly approved.
|
||||
- [ ] No paid/background commands ran without approval.
|
||||
@@ -0,0 +1,11 @@
|
||||
// Routing eval fixtures for skills/obsidian-gbrain-safe-index.
|
||||
// Positive cases: intents embed a trigger phrase in natural surrounding context
|
||||
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
|
||||
{"intent": "help me connect Obsidian to gbrain for my notes", "expected_skill": "obsidian-gbrain-safe-index"}
|
||||
{"intent": "import my vault to gbrain but skip embeddings for now", "expected_skill": "obsidian-gbrain-safe-index"}
|
||||
{"intent": "please sync vault and gbrain after I edit notes", "expected_skill": "obsidian-gbrain-safe-index"}
|
||||
{"intent": "run embed gbrain after vault update tonight", "expected_skill": "obsidian-gbrain-safe-index"}
|
||||
{"intent": "hey is gbrain synced with my vault right now", "expected_skill": "obsidian-gbrain-safe-index"}
|
||||
// Negative cases: related but owned by other skills. Assert NO route to this skill.
|
||||
{"intent": "migrate my notes from Notion to gbrain", "expected_skill": null}
|
||||
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
|
||||
@@ -0,0 +1,100 @@
|
||||
---
|
||||
name: skill-vault-capture-policy
|
||||
version: 1.0.0
|
||||
description: |
|
||||
Use when the user wants a durable operational learning, new agent skill, or
|
||||
important environment/setup change to be captured into the Obsidian vault
|
||||
instead of left only in transient chat memory. Covers the capture rule,
|
||||
preferred page patterns, and index/log update obligations.
|
||||
triggers:
|
||||
- "save this learning to the vault"
|
||||
- "capture this skill in Obsidian"
|
||||
- "record this workflow in my notes"
|
||||
- "put this setup change in the vault"
|
||||
- "should we add this to the knowledge base"
|
||||
tools:
|
||||
- read_file
|
||||
- search_files
|
||||
- write_file
|
||||
- patch
|
||||
mutating: true
|
||||
---
|
||||
|
||||
# Skill Vault Capture Policy
|
||||
|
||||
## Contract
|
||||
|
||||
This skill guarantees:
|
||||
|
||||
- Durable operational learnings, newly adopted skills, and important environment/setup changes are captured into the Obsidian vault rather than left only in chat memory.
|
||||
- An existing page is updated when the knowledge clearly belongs there; a new page is created only when the topic is distinct and likely to recur.
|
||||
- Every new vault page is added to `index.md`.
|
||||
- Every meaningful create/update appends a dated entry to `log.md`.
|
||||
- Small linked pages are preferred over one giant running note.
|
||||
|
||||
## Phases
|
||||
|
||||
1. **Classify the learning.**
|
||||
- New gbrain operating rule, cost control, or embedding/provider change.
|
||||
- New agent-fork / harness / coding-tool integration fact.
|
||||
- New Obsidian vault workflow or structure decision.
|
||||
- New recurring agent skill that changes how the agent should operate here.
|
||||
|
||||
2. **Avoid duplicates.**
|
||||
- Search the vault for an existing page that already owns the topic.
|
||||
- If found, update it with a new section or dated note rather than creating a near-duplicate.
|
||||
|
||||
3. **Create when distinct.**
|
||||
- Place new pages under the vault schema: `_meta/` for operating notes, `concepts/` for workflows, `entities/` for tools/people.
|
||||
- Use YAML frontmatter and at least two `[[wikilinks]]` unless it is a short seed page.
|
||||
|
||||
4. **Update navigation.**
|
||||
- Add the page to `index.md` under the correct type heading.
|
||||
- Append a `## [YYYY-MM-DD] create|update | subject` entry to `log.md`.
|
||||
|
||||
5. **Report the capture.**
|
||||
- State which files changed and whether `index.md` / `log.md` were updated.
|
||||
|
||||
## Output Format
|
||||
|
||||
Use a short status block:
|
||||
|
||||
| Item | Status |
|
||||
|---|---|
|
||||
| Learning classified | type |
|
||||
| Page created/updated | path |
|
||||
| index.md updated | yes/no |
|
||||
| log.md updated | yes/no |
|
||||
|
||||
## Anti-Patterns
|
||||
|
||||
- Leaving durable learnings only in chat memory.
|
||||
- Creating a near-duplicate page instead of updating the existing one.
|
||||
- Forgetting to update `index.md` and `log.md`.
|
||||
- Writing one giant running note instead of small linked pages.
|
||||
- Recording secrets, API keys, or raw credentials in the vault.
|
||||
|
||||
## Tools Used
|
||||
|
||||
- `read_file` — read `SCHEMA.md`, `index.md`, `log.md`, and target pages.
|
||||
- `search_files` — find existing pages to avoid duplicates.
|
||||
- `write_file` / `patch` — create or update vault pages and navigation.
|
||||
|
||||
## Safe Commands
|
||||
|
||||
```bash
|
||||
# inspect vault navigation before writing
|
||||
read SCHEMA.md index.md log.md
|
||||
# create or update a page, then refresh catalog/log
|
||||
# index.md: add [[page-slug]] under the matching type heading
|
||||
# log.md: append ## [YYYY-MM-DD] create|update | subject
|
||||
```
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
- [ ] Vault schema/read files were checked before writing.
|
||||
- [ ] Existing pages were searched to avoid duplicates.
|
||||
- [ ] New/updated page has frontmatter and wikilinks.
|
||||
- [ ] `index.md` updated for new pages.
|
||||
- [ ] `log.md` appended for meaningful actions.
|
||||
- [ ] No secrets or raw credentials were written.
|
||||
@@ -0,0 +1,10 @@
|
||||
// Routing eval fixtures for skills/skill-vault-capture-policy.
|
||||
// Positive cases: intents embed a trigger phrase in natural surrounding context
|
||||
// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
|
||||
{"intent": "please save this learning to the vault so we keep it", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["idea-ingest"]}
|
||||
{"intent": "we should capture this skill in Obsidian for reuse", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["capture"]}
|
||||
{"intent": "can you record this workflow in my notes for next time", "expected_skill": "skill-vault-capture-policy"}
|
||||
{"intent": "put this setup change in the vault before we forget", "expected_skill": "skill-vault-capture-policy"}
|
||||
// Negative cases: related but owned by other skills or out of scope.
|
||||
{"intent": "connect my Obsidian vault to gbrain", "expected_skill": null}
|
||||
{"intent": "what is on my calendar tomorrow", "expected_skill": null}
|
||||
@@ -50,10 +50,6 @@ const PER_TASK_KEYS: Array<{ key: string; tier: ModelTier; description: string }
|
||||
{ key: 'models.eval.contradictions_judge', tier: 'utility', description: 'Contradiction probe judge (v0.34 temporal-aware)' },
|
||||
{ key: 'models.expansion', tier: 'utility', description: 'Query expansion for hybrid search' },
|
||||
{ key: 'models.chat', tier: 'reasoning', description: 'Default `gateway.chat()` model' },
|
||||
{ key: 'models.propose_takes', tier: 'reasoning', description: 'propose_takes claim extractor' },
|
||||
{ key: 'models.grade_takes', tier: 'reasoning', description: 'grade_takes verdict judge' },
|
||||
{ key: 'models.calibration_profile', tier: 'reasoning', description: 'Calibration profile generator' },
|
||||
{ key: 'models.brainstorm', tier: 'reasoning', description: '`gbrain brainstorm` orchestrator' },
|
||||
];
|
||||
|
||||
interface ModelEntry {
|
||||
|
||||
@@ -61,10 +61,7 @@ export const MAX_OUTPUT_TOKENS_CEIL = 32_000;
|
||||
* (with a readable error) instead of the provider's opaque HTTP 400.
|
||||
*/
|
||||
export const ANTHROPIC_OUTPUT_CAPS: Record<string, number> = {
|
||||
'claude-fable-5': 64_000,
|
||||
'claude-opus-4-8': 32_000,
|
||||
'claude-opus-4-7': 32_000,
|
||||
'claude-sonnet-5': 64_000,
|
||||
'claude-sonnet-4-6': 64_000,
|
||||
'claude-haiku-4-5': 64_000,
|
||||
'claude-haiku-4-5-20251001': 64_000,
|
||||
|
||||
@@ -32,7 +32,6 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import { resolveModel } from '../model-config.ts';
|
||||
import { chat as defaultChat, embedQuery, type ChatResult, type ChatOpts } from '../ai/gateway.ts';
|
||||
import { hybridSearch, hybridSearchCached } from '../search/hybrid.ts';
|
||||
import { fetchFar, type CloseRef, type FarPage } from './domain-bank.ts';
|
||||
@@ -539,14 +538,7 @@ async function _runBrainstormInner(
|
||||
const embedFn = opts.embedQueryFn ?? embedQuery;
|
||||
|
||||
// ---- Phase 0: cost preview + TTY grace ----
|
||||
// Tier-resolved (mirrors the cycle phases): honors models.brainstorm >
|
||||
// models.default > models.tier.reasoning; the fallback keeps stock
|
||||
// behavior identical (reasoning tier default IS claude-sonnet-4-6).
|
||||
const modelStr = opts.modelOverride ?? await resolveModel(engine, {
|
||||
configKey: 'models.brainstorm',
|
||||
tier: 'reasoning',
|
||||
fallback: 'anthropic:claude-sonnet-4-6',
|
||||
});
|
||||
const modelStr = opts.modelOverride ?? 'anthropic:claude-sonnet-4-6';
|
||||
const { aborted, estimate } = await previewCostAndWait({
|
||||
profile,
|
||||
model: modelStr,
|
||||
|
||||
@@ -26,8 +26,8 @@
|
||||
*/
|
||||
|
||||
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
|
||||
import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
|
||||
import { resolveModel } from '../model-config.ts';
|
||||
import { chat as gatewayChat } from '../ai/gateway.ts';
|
||||
import { TIER_DEFAULTS } from '../model-config.ts';
|
||||
import { gateVoice, type VoiceGateGenerator, type VoiceGateJudge } from '../calibration/voice-gate.ts';
|
||||
import { patternStatementTemplate, type PatternStatementSlots } from '../calibration/templates.ts';
|
||||
// v0.41 T10 — domain widening. The aggregator module resolves the active
|
||||
@@ -229,16 +229,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
|
||||
// Resolved once (see propose-takes.ts for the chain): models.calibration_profile
|
||||
// > models.default > env > the gateway's chat model (itself resolved
|
||||
// through models.chat + the reasoning tier). Provider-prefixed per #2451
|
||||
// — a bare id would make gateway.chat() throw "missing a provider
|
||||
// prefix". Drives the generator's chat call, the budget label, and the
|
||||
// persisted model_id, so the three can never disagree.
|
||||
const modelId = opts.model ?? await resolveModel(engine, {
|
||||
configKey: 'models.calibration_profile',
|
||||
fallback: getChatModel(),
|
||||
});
|
||||
const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
|
||||
const gradeCompletion = opts.gradeCompletion ?? 1.0;
|
||||
const patternsGenerator = opts.patternsGenerator ?? defaultPatternsGenerator;
|
||||
const biasTagsGenerator = opts.biasTagsGenerator ?? defaultBiasTagsGenerator;
|
||||
@@ -274,7 +265,6 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
scorecard,
|
||||
holder,
|
||||
attempt,
|
||||
modelHint: modelId,
|
||||
...(feedback !== undefined ? { feedback } : {}),
|
||||
});
|
||||
return lines.join('\n');
|
||||
|
||||
@@ -36,9 +36,7 @@
|
||||
|
||||
import { createHash } from 'node:crypto';
|
||||
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
|
||||
import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
|
||||
import { resolveModel } from '../model-config.ts';
|
||||
import { splitProviderModelId } from '../model-id.ts';
|
||||
import { chat as gatewayChat } from '../ai/gateway.ts';
|
||||
import { GBrainError } from '../types.ts';
|
||||
import type { OperationContext } from '../operations.ts';
|
||||
import type { BrainEngine, Take, TakeResolution } from '../engine.ts';
|
||||
@@ -397,24 +395,7 @@ class GradeTakesPhase extends BaseCyclePhase {
|
||||
const autoResolve = opts.autoResolve ?? false; // D17 default OFF
|
||||
const autoResolveThreshold = opts.autoResolveThreshold ?? 0.95; // D12 conservative
|
||||
const resolvedByLabel = opts.resolvedByLabel ?? 'gbrain:grade_takes';
|
||||
// Resolve the judge model ONCE (see propose-takes.ts for the chain —
|
||||
// same label-vs-actual split fixed here: the judge call rode the
|
||||
// gateway's chat_model while the grade cache key, evidence signature,
|
||||
// and budget label recorded a hardcoded 4.6).
|
||||
// NOTE: changing the resolved judge model invalidates the grade cache
|
||||
// (judge_model_id is part of its key) — a one-time, budget-capped
|
||||
// re-grade wave that is CORRECT, since the actual judge did change.
|
||||
const judgeModelFull = opts.model ?? await resolveModel(engine, {
|
||||
configKey: 'models.grade_takes',
|
||||
fallback: getChatModel(),
|
||||
});
|
||||
// Bare tail for cache keys / evidence signatures / stored ids — the
|
||||
// grade cache has always been keyed on bare ids; the gateway default
|
||||
// resolves provider-prefixed, and normalizing preserves cache continuity
|
||||
// on stock installs (no spurious re-judge wave from a prefix change). A
|
||||
// genuinely different configured judge still invalidates, which is
|
||||
// correct. The FULL string drives the actual judge call.
|
||||
const judgeModelId = splitProviderModelId(judgeModelFull).model || judgeModelFull;
|
||||
const judgeModelId = opts.model ?? 'claude-sonnet-4-6';
|
||||
|
||||
const useEnsemble = opts.useEnsemble ?? false;
|
||||
const ensembleThreshold = opts.ensembleThreshold ?? 0.85;
|
||||
@@ -487,7 +468,7 @@ class GradeTakesPhase extends BaseCyclePhase {
|
||||
// Call the single-model judge. Errors on a single take log warning + continue.
|
||||
let verdict: JudgeVerdict;
|
||||
try {
|
||||
verdict = await judge({ take, evidence, modelHint: judgeModelFull });
|
||||
verdict = await judge({ take, evidence, modelHint: opts.model });
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
result.warnings.push(`judge failed on take ${take.id}: ${msg}`);
|
||||
|
||||
@@ -5,16 +5,11 @@
|
||||
* a tuned LLM extractor, writes the extracted gradeable claims to the
|
||||
* `take_proposals` queue. User accepts/rejects via `gbrain takes propose`.
|
||||
*
|
||||
* Idempotency contract (D17 schema spec; per-claim rows since migration v125):
|
||||
* Every scan of a (source_id, page_slug, content_hash, prompt_version)
|
||||
* tuple leaves at least one row — one per extracted claim, or a single
|
||||
* status='empty' sentinel when extraction yields nothing — so an unchanged
|
||||
* page never re-spends LLM tokens. Pre-v125 only proposal rows were
|
||||
* written: a zero-claim page never entered the cache and was re-extracted
|
||||
* on EVERY cycle (observed live: ~60 such pages × every cycle ≈ 1,400
|
||||
* wasted extractor calls / ~$15 per day — ~90% of total autopilot spend).
|
||||
* Bumping PROPOSE_TAKES_PROMPT_VERSION cleanly invalidates the cache so a
|
||||
* tuned prompt re-runs proposals on every page.
|
||||
* Idempotency contract (D17 schema spec):
|
||||
* The unique index on (source_id, page_slug, content_hash, prompt_version)
|
||||
* means an unchanged page never re-spends LLM tokens. Bumping
|
||||
* PROPOSE_TAKES_PROMPT_VERSION cleanly invalidates the cache so a tuned
|
||||
* prompt re-runs proposals on every page.
|
||||
*
|
||||
* F2 fence dedup:
|
||||
* The phase reads the page's existing `<!-- gbrain:takes:begin -->` fence
|
||||
@@ -45,7 +40,6 @@
|
||||
import { randomUUID, createHash } from 'node:crypto';
|
||||
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
|
||||
import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
|
||||
import { resolveModel } from '../model-config.ts';
|
||||
import { writeReceipt } from '../extract/receipt-writer.ts';
|
||||
import { upsertExtractRollup } from '../extract/rollup-writer.ts';
|
||||
import { GBrainError } from '../types.ts';
|
||||
@@ -313,18 +307,6 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
const promptVersion = opts.promptVersion ?? PROPOSE_TAKES_PROMPT_VERSION;
|
||||
const pageLimit = opts.pageLimit ?? 100;
|
||||
const skipPagesWithFence = opts.skipPagesWithFence ?? false;
|
||||
// Resolve the extractor model ONCE: models.propose_takes >
|
||||
// models.default > GBRAIN_MODEL env > the gateway's chat model (which
|
||||
// reconfigureGatewayWithEngine already resolved through models.chat +
|
||||
// the reasoning tier). One resolved provider-prefixed string drives the
|
||||
// actual chat call, the budget estimate, AND the stored model_id — so
|
||||
// the recorded model can never disagree with the model that ran (#2451
|
||||
// convention: stored ids are provider-prefixed, nested prefixes like
|
||||
// openrouter:anthropic/... stay intact).
|
||||
const extractorModelId = opts.model ?? await resolveModel(engine, {
|
||||
configKey: 'models.propose_takes',
|
||||
fallback: getChatModel(),
|
||||
});
|
||||
const proposalRunId = `propose-${new Date().toISOString().slice(0, 19).replace(/[-:T]/g, '')}-${randomUUID().slice(0, 8)}`;
|
||||
|
||||
const result: ProposeTakesResult = {
|
||||
@@ -348,6 +330,8 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
opts.reporter.start('propose_takes.pages' as never, pages.length);
|
||||
}
|
||||
|
||||
const modelId = opts.model ?? getChatModel();
|
||||
|
||||
for (const page of pages) {
|
||||
result.pages_scanned += 1;
|
||||
this.tick(opts);
|
||||
@@ -377,7 +361,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
|
||||
// Budget pre-check before the LLM call. Estimate: ~1500 input tokens + 500 output.
|
||||
const budget = this.checkBudget({
|
||||
modelId: extractorModelId,
|
||||
modelId,
|
||||
estimatedInputTokens: 1500,
|
||||
maxOutputTokens: 500,
|
||||
});
|
||||
@@ -396,7 +380,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
pagePath: page.slug,
|
||||
pageBody: body,
|
||||
existingTakes,
|
||||
modelHint: extractorModelId,
|
||||
modelHint: opts.model,
|
||||
});
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
@@ -404,42 +388,16 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Zero-claim scans MUST still enter the idempotency cache. Pre-v125
|
||||
// only proposal rows were written, so a page whose extraction yielded
|
||||
// no gradeable claims never got a row for its (page, content_hash) —
|
||||
// the cache check above missed on every subsequent cycle and the LLM
|
||||
// call was re-spent on the same unchanged page, forever. The sentinel
|
||||
// row (status='empty', empty claim_text) is invisible to the review
|
||||
// queue (pending_idx is partial on status='pending'); it exists only
|
||||
// so the cache check hits.
|
||||
if (proposals.length === 0) {
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO take_proposals
|
||||
(source_id, page_slug, content_hash, prompt_version, proposal_run_id,
|
||||
status, claim_text, kind, holder, weight, domain, dedup_against_fence_rows, model_id)
|
||||
VALUES ($1, $2, $3, $4, $5, 'empty', '', 'none', 'brain', 0, NULL, NULL, $6)
|
||||
ON CONFLICT (source_id, page_slug, content_hash, prompt_version, md5(claim_text)) DO NOTHING`,
|
||||
[sourceId, page.slug, ch, promptVersion, proposalRunId, extractorModelId],
|
||||
);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Write proposals to take_proposals, one row per claim. The v125
|
||||
// idempotency index includes md5(claim_text), so a same-page
|
||||
// multi-claim run keeps EVERY claim — the pre-v125 four-column unique
|
||||
// index made claims 2..N conflict with claim 1 and ON CONFLICT DO
|
||||
// NOTHING silently dropped them (the review queue only ever saw the
|
||||
// first claim of each page version). RETURNING id keeps
|
||||
// proposals_inserted honest: it counts rows that actually landed,
|
||||
// not insert attempts.
|
||||
// Write proposals to take_proposals. Each row is a separate INSERT
|
||||
// because the composite idempotency key is on the per-page tuple — a
|
||||
// bulk UPSERT would collapse a same-page-multi-claim run into one row.
|
||||
for (const p of proposals) {
|
||||
const landed = await engine.executeRaw<{ id: number }>(
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO take_proposals
|
||||
(source_id, page_slug, content_hash, prompt_version, proposal_run_id,
|
||||
claim_text, kind, holder, weight, domain, dedup_against_fence_rows, model_id)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
|
||||
ON CONFLICT (source_id, page_slug, content_hash, prompt_version, md5(claim_text)) DO NOTHING
|
||||
RETURNING id`,
|
||||
ON CONFLICT (source_id, page_slug, content_hash, prompt_version) DO NOTHING`,
|
||||
[
|
||||
sourceId,
|
||||
page.slug,
|
||||
@@ -452,10 +410,10 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
p.weight,
|
||||
p.domain ?? null,
|
||||
JSON.stringify(existingTakes),
|
||||
extractorModelId,
|
||||
modelId,
|
||||
],
|
||||
);
|
||||
if (landed.length > 0) result.proposals_inserted += 1;
|
||||
result.proposals_inserted += 1;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -58,11 +58,8 @@ const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
* resolver returns for known Anthropic aliases.
|
||||
*/
|
||||
const MODEL_CONTEXT_TOKENS: Record<string, number> = {
|
||||
'claude-fable-5': 1_000_000,
|
||||
'claude-opus-4-8': 1_000_000,
|
||||
'claude-opus-4-7': 1_000_000,
|
||||
'claude-opus-4-6': 1_000_000,
|
||||
'claude-sonnet-5': 1_000_000,
|
||||
'claude-sonnet-4-6': 200_000,
|
||||
'claude-sonnet-4-5': 200_000,
|
||||
'claude-haiku-4-5-20251001': 200_000,
|
||||
|
||||
@@ -5671,41 +5671,6 @@ export const MIGRATIONS: Migration[] = [
|
||||
`);
|
||||
},
|
||||
},
|
||||
{
|
||||
version: 125,
|
||||
name: 'take_proposals_empty_scan_sentinels_and_per_claim_rows',
|
||||
// v0.42.x — kill the propose_takes rescan loop + stop dropping claims.
|
||||
//
|
||||
// Two defects, one schema touch:
|
||||
// 1. Zero-claim scans never entered the idempotency cache (only
|
||||
// proposal rows were written), so pages whose extraction yielded
|
||||
// nothing were re-extracted on EVERY cycle. Observed live: ~60
|
||||
// such pages per run ≈ 1,400 wasted extractor calls / ~$15 per
|
||||
// day — ~90% of total autopilot LLM spend. Fix: the phase now
|
||||
// writes a status='empty' sentinel row per zero-claim scan; the
|
||||
// status CHECK gains the 'empty' value. Sentinels are excluded
|
||||
// from the partial pending index, so the review queue never sees
|
||||
// them.
|
||||
// 2. The 4-column unique index collapsed a same-page multi-claim run
|
||||
// to its FIRST claim: rows 2..N conflicted and ON CONFLICT DO
|
||||
// NOTHING silently dropped them (verified live: exactly one row
|
||||
// per (page, hash) across 3 days of runs). Fix: the idempotency
|
||||
// index gains md5(claim_text) — per-claim rows, while the
|
||||
// 4-column prefix still serves the per-scan cache lookup.
|
||||
//
|
||||
// Existing data is index-safe by construction: the old index guaranteed
|
||||
// at most one row per 4-tuple, so the widened index has no duplicates
|
||||
// to trip on. The DROP+ADD CONSTRAINT pair is idempotent as a unit.
|
||||
idempotent: true,
|
||||
sql: `
|
||||
ALTER TABLE take_proposals DROP CONSTRAINT IF EXISTS take_proposals_status_check;
|
||||
ALTER TABLE take_proposals ADD CONSTRAINT take_proposals_status_check
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded','empty'));
|
||||
DROP INDEX IF EXISTS take_proposals_idempotency_idx;
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
|
||||
`,
|
||||
},
|
||||
];
|
||||
|
||||
export const LATEST_VERSION = MIGRATIONS.length > 0
|
||||
|
||||
@@ -762,7 +762,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
proposed_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
proposal_run_id TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'pending'
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded')),
|
||||
claim_text TEXT NOT NULL,
|
||||
kind TEXT NOT NULL,
|
||||
holder TEXT NOT NULL,
|
||||
@@ -777,7 +777,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
predicted_brier_bucket_n INTEGER
|
||||
);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version);
|
||||
CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
|
||||
ON take_proposals (source_id, status, proposed_at DESC)
|
||||
WHERE status = 'pending';
|
||||
|
||||
@@ -1274,14 +1274,8 @@ CREATE INDEX IF NOT EXISTS calibration_profiles_published_idx
|
||||
WHERE published = true;
|
||||
|
||||
-- take_proposals: propose_takes phase queue. Idempotency cache via the
|
||||
-- composite unique index (source_id, page_slug, content_hash, prompt_version,
|
||||
-- md5(claim_text)) — the 4-column prefix is the per-scan cache key (mirrors
|
||||
-- v0.23 dream_verdicts); md5(claim_text) makes rows per-claim so multi-claim
|
||||
-- pages keep every claim (v125). status='empty' rows are zero-claim scan
|
||||
-- sentinels: they hold the cache slot for a page version whose extraction
|
||||
-- yielded nothing — the phase never re-spends the LLM call on that page
|
||||
-- version. Excluded from the partial pending index. proposal_run_id supports
|
||||
-- --rollback by run.
|
||||
-- composite unique index (source_id, page_slug, content_hash, prompt_version)
|
||||
-- mirrors v0.23 dream_verdicts. proposal_run_id supports --rollback by run.
|
||||
CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
id BIGSERIAL PRIMARY KEY,
|
||||
source_id TEXT NOT NULL REFERENCES sources(id) ON DELETE CASCADE,
|
||||
@@ -1292,7 +1286,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
proposed_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
proposal_run_id TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'pending'
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded')),
|
||||
claim_text TEXT NOT NULL,
|
||||
kind TEXT NOT NULL,
|
||||
holder TEXT NOT NULL,
|
||||
@@ -1307,7 +1301,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
predicted_brier_bucket_n INTEGER
|
||||
);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version);
|
||||
CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
|
||||
ON take_proposals (source_id, status, proposed_at DESC)
|
||||
WHERE status = 'pending';
|
||||
|
||||
+4
-10
@@ -1270,14 +1270,8 @@ CREATE INDEX IF NOT EXISTS calibration_profiles_published_idx
|
||||
WHERE published = true;
|
||||
|
||||
-- take_proposals: propose_takes phase queue. Idempotency cache via the
|
||||
-- composite unique index (source_id, page_slug, content_hash, prompt_version,
|
||||
-- md5(claim_text)) — the 4-column prefix is the per-scan cache key (mirrors
|
||||
-- v0.23 dream_verdicts); md5(claim_text) makes rows per-claim so multi-claim
|
||||
-- pages keep every claim (v125). status='empty' rows are zero-claim scan
|
||||
-- sentinels: they hold the cache slot for a page version whose extraction
|
||||
-- yielded nothing — the phase never re-spends the LLM call on that page
|
||||
-- version. Excluded from the partial pending index. proposal_run_id supports
|
||||
-- --rollback by run.
|
||||
-- composite unique index (source_id, page_slug, content_hash, prompt_version)
|
||||
-- mirrors v0.23 dream_verdicts. proposal_run_id supports --rollback by run.
|
||||
CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
id BIGSERIAL PRIMARY KEY,
|
||||
source_id TEXT NOT NULL REFERENCES sources(id) ON DELETE CASCADE,
|
||||
@@ -1288,7 +1282,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
proposed_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||||
proposal_run_id TEXT NOT NULL,
|
||||
status TEXT NOT NULL DEFAULT 'pending'
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
|
||||
CHECK (status IN ('pending','accepted','rejected','superseded')),
|
||||
claim_text TEXT NOT NULL,
|
||||
kind TEXT NOT NULL,
|
||||
holder TEXT NOT NULL,
|
||||
@@ -1303,7 +1297,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
|
||||
predicted_brier_bucket_n INTEGER
|
||||
);
|
||||
CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
|
||||
ON take_proposals (source_id, page_slug, content_hash, prompt_version);
|
||||
CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
|
||||
ON take_proposals (source_id, status, proposed_at DESC)
|
||||
WHERE status = 'pending';
|
||||
|
||||
@@ -38,7 +38,6 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
} {
|
||||
const captured: CapturedSql[] = [];
|
||||
const engine = {
|
||||
async getConfig() { return null; },
|
||||
kind: 'pglite',
|
||||
async getScorecard() {
|
||||
return opts.scorecard;
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
/**
|
||||
* E2E smoke for skills/obsidian-gbrain-safe-index.
|
||||
*
|
||||
* Verifies the from-trigger-to-side-effect path that skillify requires:
|
||||
* a real user trigger phrase routes to the skill, the resolver/check
|
||||
* pipeline treats it as reachable, and the skill file exposes the
|
||||
* gbrain commands the workflow actually runs.
|
||||
*
|
||||
* This stays local-only (no paid embedding, no external API): it asserts
|
||||
* the documented safe/import path is present and parseable, not that it
|
||||
* mutates a live brain.
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { existsSync, readFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
|
||||
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
|
||||
const SKILL_MD = join(SKILLS, 'obsidian-gbrain-safe-index', 'SKILL.md');
|
||||
const RESOLVER = join(SKILLS, 'RESOLVER.md');
|
||||
|
||||
const TRIGGER_PHRASES = [
|
||||
'connect my Obsidian vault to gbrain',
|
||||
'import my vault to gbrain',
|
||||
'sync vault and gbrain',
|
||||
'capture this skill in my vault',
|
||||
'embed gbrain after vault update',
|
||||
'is gbrain synced with my vault',
|
||||
];
|
||||
|
||||
describe('obsidian-gbrain-safe-index E2E', () => {
|
||||
it('resolver maps real trigger phrasings to the skill', () => {
|
||||
const resolver = readFileSync(RESOLVER, 'utf-8');
|
||||
expect(resolver).toContain('obsidian-gbrain-safe-index/SKILL.md');
|
||||
// Each representative phrase shares a token substring with a resolver row.
|
||||
const rows = resolver
|
||||
.split('\n')
|
||||
.filter((l) => l.includes('obsidian-gbrain-safe-index/SKILL.md'))
|
||||
.join('\n');
|
||||
for (const phrase of TRIGGER_PHRASES) {
|
||||
const hit = phrase
|
||||
.toLowerCase()
|
||||
.split(/\s+/)
|
||||
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
|
||||
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('skill documents the gbrain import-first safe path', () => {
|
||||
const body = readFileSync(SKILL_MD, 'utf-8');
|
||||
expect(body).toContain('gbrain import');
|
||||
expect(body).toContain('--no-embed');
|
||||
expect(body).toContain('gbrain config set search.mode conservative');
|
||||
// Paid gate must be explicit, not a silent default.
|
||||
expect(body).toContain('gbrain embed --stale');
|
||||
});
|
||||
|
||||
it('skill is reachable from the skill tree', () => {
|
||||
expect(existsSync(SKILL_MD)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* E2E smoke for skills/skill-vault-capture-policy.
|
||||
*
|
||||
* Verifies the from-trigger-to-side-effect path: a real capture request
|
||||
* routes to the skill, and the skill documents the vault navigation
|
||||
* obligations (index.md / log.md) that make a capture durable.
|
||||
*
|
||||
* Local-only: it asserts documented behavior, not live vault writes.
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { existsSync, readFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
|
||||
const SKILLS = join(import.meta.dir, '..', '..', 'skills');
|
||||
const SKILL_MD = join(SKILLS, 'skill-vault-capture-policy', 'SKILL.md');
|
||||
const RESOLVER = join(SKILLS, 'RESOLVER.md');
|
||||
|
||||
const TRIGGER_PHRASES = [
|
||||
'save this learning to the vault',
|
||||
'capture this skill in Obsidian',
|
||||
'record this workflow in my notes',
|
||||
'put this setup change in the knowledge base',
|
||||
];
|
||||
|
||||
describe('skill-vault-capture-policy E2E', () => {
|
||||
it('resolver maps real capture phrasings to the skill', () => {
|
||||
const resolver = readFileSync(RESOLVER, 'utf-8');
|
||||
expect(resolver).toContain('skill-vault-capture-policy/SKILL.md');
|
||||
const rows = resolver
|
||||
.split('\n')
|
||||
.filter((l) => l.includes('skill-vault-capture-policy/SKILL.md'))
|
||||
.join('\n');
|
||||
for (const phrase of TRIGGER_PHRASES) {
|
||||
const hit = phrase
|
||||
.toLowerCase()
|
||||
.split(/\s+/)
|
||||
.some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
|
||||
expect(hit, `no resolver token for: ${phrase}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('skill documents index.md and log.md update obligations', () => {
|
||||
const body = readFileSync(SKILL_MD, 'utf-8');
|
||||
expect(body).toContain('index.md');
|
||||
expect(body).toContain('log.md');
|
||||
});
|
||||
|
||||
it('skill is reachable from the skill tree', () => {
|
||||
expect(existsSync(SKILL_MD)).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -47,7 +47,6 @@ function buildMockEngine(opts: { takes: Take[] }): {
|
||||
const captured: CapturedSql[] = [];
|
||||
const resolves: CapturedResolve[] = [];
|
||||
const engine = {
|
||||
async getConfig() { return null; },
|
||||
kind: 'pglite',
|
||||
async listTakes() {
|
||||
return opts.takes;
|
||||
|
||||
@@ -46,14 +46,12 @@ interface CapturedResolve {
|
||||
function buildMockEngine(opts: {
|
||||
takes: Take[];
|
||||
cachedGrades?: Set<string>; // composite-key strings already in take_grade_cache
|
||||
config?: Record<string, string>; // engine.getConfig plane (models.grade_takes etc.)
|
||||
}): { engine: BrainEngine; captured: CapturedSql[]; resolves: CapturedResolve[] } {
|
||||
const captured: CapturedSql[] = [];
|
||||
const resolves: CapturedResolve[] = [];
|
||||
const cached = opts.cachedGrades ?? new Set<string>();
|
||||
|
||||
const engine = {
|
||||
async getConfig(key: string) { return opts.config?.[key] ?? null; },
|
||||
kind: 'pglite',
|
||||
async listTakes() {
|
||||
return opts.takes;
|
||||
@@ -226,28 +224,6 @@ describe('runPhaseGradeTakes — phase integration', () => {
|
||||
expect(resolves).toHaveLength(0); // no canonical mutation
|
||||
});
|
||||
|
||||
test('models.grade_takes config drives the judge call; cache key stays bare-tailed', async () => {
|
||||
// Pre-fix the judge call rode the gateway's chat_model while the cache
|
||||
// key / budget label recorded a hardcoded 'claude-sonnet-4-6'. The phase
|
||||
// now resolves models.grade_takes; the judge gets the FULL string and
|
||||
// the cache row keys on the bare tail (continuity with historical rows).
|
||||
const takes = [buildTake({ id: 1, sinceDate: '2023-01-01' })];
|
||||
const { engine, captured } = buildMockEngine({
|
||||
takes,
|
||||
config: { 'models.grade_takes': 'anthropic:claude-sonnet-5' },
|
||||
});
|
||||
const hints: Array<string | undefined> = [];
|
||||
const judge: JudgeFn = async ({ modelHint }) => {
|
||||
hints.push(modelHint);
|
||||
return { verdict: 'correct', confidence: 0.9, reasoning: 'held' };
|
||||
};
|
||||
const result = await runPhaseGradeTakes(buildCtx(engine), { judge });
|
||||
expect(result.status).toBe('ok');
|
||||
expect(hints).toEqual(['anthropic:claude-sonnet-5']); // actual call gets the FULL string
|
||||
const inserts = captured.filter(c => c.sql.includes('INSERT INTO take_grade_cache'));
|
||||
expect(inserts[0]!.params[2]).toBe('claude-sonnet-5'); // judge_model_id is the bare tail
|
||||
});
|
||||
|
||||
test('D17: auto-resolve OFF by default — even high-confidence verdict does NOT mutate takes', async () => {
|
||||
const takes = [buildTake({ id: 1, sinceDate: '2023-01-01' })];
|
||||
const { engine, resolves } = buildMockEngine({ takes });
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { readFileSync, existsSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
|
||||
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'obsidian-gbrain-safe-index');
|
||||
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
|
||||
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
|
||||
|
||||
function parseFrontmatter(raw: string): Record<string, unknown> {
|
||||
const m = raw.match(/^---\n([\s\S]*?)\n---/);
|
||||
if (!m) throw new Error('no frontmatter');
|
||||
const out: Record<string, unknown> = {};
|
||||
for (const line of m[1].split('\n')) {
|
||||
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
|
||||
if (mm) out[mm[1]] = mm[2].trim();
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
describe('obsidian-gbrain-safe-index skill', () => {
|
||||
it('has a SKILL.md with required frontmatter', () => {
|
||||
expect(existsSync(SKILL_MD)).toBe(true);
|
||||
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
|
||||
expect(fm['name']).toBe('obsidian-gbrain-safe-index');
|
||||
expect(fm['description']).toBeTruthy();
|
||||
});
|
||||
|
||||
it('has the required conformance sections', () => {
|
||||
const body = readFileSync(SKILL_MD, 'utf-8');
|
||||
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
|
||||
expect(body.includes(section), `missing ${section}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('is registered in RESOLVER.md', () => {
|
||||
expect(existsSync(RESOLVER)).toBe(true);
|
||||
const resolver = readFileSync(RESOLVER, 'utf-8');
|
||||
expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
|
||||
});
|
||||
|
||||
it('has routing-eval fixtures that exercise real trigger phrasings', () => {
|
||||
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
|
||||
expect(existsSync(evalPath)).toBe(true);
|
||||
const lines = readFileSync(evalPath, 'utf-8')
|
||||
.split('\n')
|
||||
.filter((l) => l.trim() && !l.trim().startsWith('//'))
|
||||
.map((l) => JSON.parse(l));
|
||||
const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
|
||||
expect(positives.length).toBeGreaterThanOrEqual(5);
|
||||
});
|
||||
});
|
||||
@@ -1,160 +0,0 @@
|
||||
/**
|
||||
* propose_takes rescan-loop + dropped-claims regression tests (migration v125).
|
||||
*
|
||||
* Two live-observed defects, both fixed by the v125 schema + phase change:
|
||||
*
|
||||
* 1. RESCAN LOOP — a page whose extraction yielded zero claims never
|
||||
* entered the idempotency cache (only proposal rows were written), so
|
||||
* every cycle re-spent the extractor call on the same unchanged page.
|
||||
* Live impact: ~60 such pages × every cycle ≈ 1,400 wasted LLM calls
|
||||
* (~$15) per day — ~90% of total autopilot spend. Fix: status='empty'
|
||||
* sentinel row per zero-claim scan.
|
||||
*
|
||||
* 2. DROPPED CLAIMS — the 4-column unique index collapsed a same-page
|
||||
* multi-claim run to its first claim (rows 2..N conflicted, ON CONFLICT
|
||||
* DO NOTHING dropped them silently; verified live: exactly 1 row per
|
||||
* (page, hash) over 3 days). Fix: idempotency index gains
|
||||
* md5(claim_text).
|
||||
*
|
||||
* Hermetic: PGLite engine + injected extractor; no gateway, no LLM.
|
||||
*/
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { runPhaseProposeTakes, type ProposeTakesExtractor, type ProposedTake } from '../src/core/cycle/propose-takes.ts';
|
||||
import type { OperationContext } from '../src/core/operations.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
function ctx(): OperationContext {
|
||||
return {
|
||||
engine,
|
||||
remote: false,
|
||||
config: {} as OperationContext['config'],
|
||||
logger: { info() {}, warn() {}, error() {}, debug() {} } as unknown as OperationContext['logger'],
|
||||
} as unknown as OperationContext;
|
||||
}
|
||||
|
||||
/** Extractor stub that counts invocations per page slug. */
|
||||
function countingExtractor(
|
||||
claimsBySlug: Record<string, ProposedTake[]>,
|
||||
): { extractor: ProposeTakesExtractor; calls: string[] } {
|
||||
const calls: string[] = [];
|
||||
const extractor: ProposeTakesExtractor = async ({ pagePath }) => {
|
||||
calls.push(pagePath);
|
||||
return claimsBySlug[pagePath] ?? [];
|
||||
};
|
||||
return { extractor, calls };
|
||||
}
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
await engine.putPage('notes/zero-claims', {
|
||||
type: 'note',
|
||||
title: 'pure narrative',
|
||||
compiled_truth: 'A quiet walk in the park. Nothing opinionated happened at all today.',
|
||||
});
|
||||
await engine.putPage('notes/three-claims', {
|
||||
type: 'note',
|
||||
title: 'opinionated',
|
||||
compiled_truth: 'I bet acme-example wins the market. widget-co will struggle. fund-a is overexposed.',
|
||||
});
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
describe('rescan loop — zero-claim scans enter the cache', () => {
|
||||
test('second run cache-hits: extractor is NOT called again on unchanged pages', async () => {
|
||||
const claims = {
|
||||
'notes/three-claims': [
|
||||
{ claim_text: 'acme-example wins the market', kind: 'bet' as const, holder: 'brain', weight: 0.7 },
|
||||
{ claim_text: 'widget-co will struggle', kind: 'take' as const, holder: 'brain', weight: 0.6 },
|
||||
{ claim_text: 'fund-a is overexposed', kind: 'take' as const, holder: 'brain', weight: 0.55 },
|
||||
],
|
||||
};
|
||||
|
||||
const first = countingExtractor(claims);
|
||||
const r1 = await runPhaseProposeTakes(ctx(), { extractor: first.extractor });
|
||||
expect(r1.status).toBe('ok');
|
||||
// Both pages extracted on the first pass.
|
||||
expect(first.calls).toContain('notes/zero-claims');
|
||||
expect(first.calls).toContain('notes/three-claims');
|
||||
|
||||
const second = countingExtractor(claims);
|
||||
const r2 = await runPhaseProposeTakes(ctx(), { extractor: second.extractor });
|
||||
expect(r2.status).toBe('ok');
|
||||
// THE regression: pre-fix the zero-claim page missed the cache every
|
||||
// run and was re-extracted here. (Run 1's receipt page legitimately
|
||||
// appears once — it's a new page — and its zero-claim scan now caches
|
||||
// too; pre-fix, receipts re-scanned forever as well.)
|
||||
expect(second.calls).not.toContain('notes/zero-claims');
|
||||
expect(second.calls).not.toContain('notes/three-claims');
|
||||
|
||||
// Run 2 inserted nothing, so no new receipt page exists: run 3 must be
|
||||
// fully quiescent — zero extractor calls, zero cache misses.
|
||||
const third = countingExtractor(claims);
|
||||
const r3 = await runPhaseProposeTakes(ctx(), { extractor: third.extractor });
|
||||
expect(r3.status).toBe('ok');
|
||||
expect(third.calls).toEqual([]);
|
||||
expect((r3.details as Record<string, unknown>).cache_misses).toBe(0);
|
||||
});
|
||||
|
||||
test('zero-claim scan wrote an "empty" sentinel invisible to the pending queue', async () => {
|
||||
const sentinel = await engine.executeRaw<{ status: string; claim_text: string }>(
|
||||
`SELECT status, claim_text FROM take_proposals WHERE page_slug = 'notes/zero-claims'`,
|
||||
[],
|
||||
);
|
||||
expect(sentinel.length).toBe(1);
|
||||
expect(sentinel[0].status).toBe('empty');
|
||||
expect(sentinel[0].claim_text).toBe('');
|
||||
const pending = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT COUNT(*)::int AS n FROM take_proposals WHERE page_slug = 'notes/zero-claims' AND status = 'pending'`,
|
||||
[],
|
||||
);
|
||||
expect(Number(pending[0].n)).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('dropped claims — per-claim rows survive the idempotency index', () => {
|
||||
test('a 3-claim page stores 3 rows and reports an honest inserted count', async () => {
|
||||
const rows = await engine.executeRaw<{ claim_text: string }>(
|
||||
`SELECT claim_text FROM take_proposals WHERE page_slug = 'notes/three-claims' AND status = 'pending' ORDER BY id`,
|
||||
[],
|
||||
);
|
||||
// Pre-fix the 4-column unique index kept only the FIRST claim.
|
||||
expect(rows.length).toBe(3);
|
||||
expect(rows.map(r => r.claim_text)).toEqual([
|
||||
'acme-example wins the market',
|
||||
'widget-co will struggle',
|
||||
'fund-a is overexposed',
|
||||
]);
|
||||
});
|
||||
|
||||
test('content change re-extracts and stores the new version separately', async () => {
|
||||
await engine.putPage('notes/zero-claims', {
|
||||
type: 'note',
|
||||
title: 'pure narrative',
|
||||
compiled_truth: 'Updated: I now believe acme-example is undervalued and will re-rate within a year.',
|
||||
});
|
||||
const claims = {
|
||||
'notes/zero-claims': [
|
||||
{ claim_text: 'acme-example is undervalued', kind: 'take' as const, holder: 'brain', weight: 0.6 },
|
||||
],
|
||||
};
|
||||
const run = countingExtractor(claims);
|
||||
const r = await runPhaseProposeTakes(ctx(), { extractor: run.extractor });
|
||||
expect(r.status).toBe('ok');
|
||||
// Changed page re-extracts; the unchanged 3-claim page stays cached.
|
||||
expect(run.calls).toEqual(['notes/zero-claims']);
|
||||
expect((r.details as Record<string, unknown>).proposals_inserted).toBe(1);
|
||||
const all = await engine.executeRaw<{ status: string }>(
|
||||
`SELECT status FROM take_proposals WHERE page_slug = 'notes/zero-claims' ORDER BY id`,
|
||||
[],
|
||||
);
|
||||
// Old hash's sentinel + new hash's pending claim coexist.
|
||||
expect(all.map(r2 => r2.status).sort()).toEqual(['empty', 'pending']);
|
||||
});
|
||||
});
|
||||
@@ -41,16 +41,12 @@ interface CapturedSql {
|
||||
function buildMockEngine(opts: {
|
||||
pages: Page[];
|
||||
existingProposals?: Set<string>; // composite-key strings already in take_proposals
|
||||
config?: Record<string, string>; // engine.getConfig plane (models.tier.* etc.)
|
||||
}): { engine: BrainEngine; captured: CapturedSql[] } {
|
||||
const captured: CapturedSql[] = [];
|
||||
const existing = opts.existingProposals ?? new Set<string>();
|
||||
|
||||
const engine = {
|
||||
kind: 'pglite',
|
||||
async getConfig(key: string) {
|
||||
return opts.config?.[key] ?? null;
|
||||
},
|
||||
async listPages() {
|
||||
return opts.pages;
|
||||
},
|
||||
@@ -63,12 +59,7 @@ function buildMockEngine(opts: {
|
||||
if (existing.has(key)) return [{ id: 1 } as unknown as T];
|
||||
return [];
|
||||
}
|
||||
// INSERT ... RETURNING id — emulate a successful insert so the
|
||||
// honest proposals_inserted counter (counts RETURNING rows, not
|
||||
// attempts) sees the row land. Conflicted inserts would return [].
|
||||
if (sql.includes('INSERT INTO take_proposals') && sql.includes('RETURNING id')) {
|
||||
return [{ id: 1 } as unknown as T];
|
||||
}
|
||||
// INSERT — return nothing
|
||||
return [];
|
||||
},
|
||||
} as unknown as BrainEngine;
|
||||
@@ -276,29 +267,6 @@ describe('runPhaseProposeTakes — phase integration', () => {
|
||||
expect(inserts[0]!.params[9]).toBe('market'); // domain
|
||||
});
|
||||
|
||||
test('extractor model resolves through models.propose_takes config', async () => {
|
||||
// Pre-fix the phase's only model knob was the gateway chat model — there
|
||||
// was no per-phase config key. The phase now resolves once via
|
||||
// resolveModel(models.propose_takes > models.default > env > gateway
|
||||
// chat model); the extractor hint and the stored model_id must both
|
||||
// reflect the configured override (full provider-prefixed string, #2451).
|
||||
const pages = [buildPage({ slug: 'wiki/concepts/tier-routing', body: 'Tier-routed models will win.' })];
|
||||
const { engine, captured } = buildMockEngine({
|
||||
pages,
|
||||
config: { 'models.propose_takes': 'anthropic:claude-sonnet-5' },
|
||||
});
|
||||
const seen: Array<string | undefined> = [];
|
||||
const extractor: ProposeTakesExtractor = async ({ modelHint }) => {
|
||||
seen.push(modelHint);
|
||||
return [{ claim_text: 'tier-routed models win', kind: 'bet', holder: 'brain', weight: 0.7 }];
|
||||
};
|
||||
const result = await runPhaseProposeTakes(buildCtx(engine), { extractor });
|
||||
expect(result.status).toBe('ok');
|
||||
expect(seen).toEqual(['anthropic:claude-sonnet-5']); // chat call gets the FULL string
|
||||
const inserts = captured.filter(c => c.sql.includes('INSERT INTO take_proposals'));
|
||||
expect(inserts[0]!.params[11]).toBe('anthropic:claude-sonnet-5'); // stored model_id matches the call
|
||||
});
|
||||
|
||||
test('cache hit: page already in take_proposals is skipped', async () => {
|
||||
const body = 'A page that was already processed.';
|
||||
const pages = [buildPage({ slug: 'wiki/old-page', body })];
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { readFileSync, existsSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
|
||||
|
||||
const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
|
||||
const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
|
||||
const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
|
||||
|
||||
function parseFrontmatter(raw: string): Record<string, unknown> {
|
||||
const m = raw.match(/^---\n([\s\S]*?)\n---/);
|
||||
if (!m) throw new Error('no frontmatter');
|
||||
const out: Record<string, unknown> = {};
|
||||
for (const line of m[1].split('\n')) {
|
||||
const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
|
||||
if (mm) out[mm[1]] = mm[2].trim();
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
describe('skill-vault-capture-policy skill', () => {
|
||||
it('has a SKILL.md with required frontmatter', () => {
|
||||
expect(existsSync(SKILL_MD)).toBe(true);
|
||||
const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
|
||||
expect(fm['name']).toBe('skill-vault-capture-policy');
|
||||
expect(fm['description']).toBeTruthy();
|
||||
});
|
||||
|
||||
it('has the required conformance sections', () => {
|
||||
const body = readFileSync(SKILL_MD, 'utf-8');
|
||||
for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
|
||||
expect(body.includes(section), `missing ${section}`).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
it('is registered in RESOLVER.md', () => {
|
||||
expect(existsSync(RESOLVER)).toBe(true);
|
||||
expect(readFileSync(RESOLVER, 'utf-8').includes('skill-vault-capture-policy/SKILL.md')).toBe(true);
|
||||
});
|
||||
|
||||
it('contains no private user or agent-fork names (privacy rule)', () => {
|
||||
for (const file of [SKILL_MD, join(SKILL_DIR, 'routing-eval.jsonl')]) {
|
||||
const body = readFileSync(file, 'utf-8');
|
||||
// DEFAULT_PRIVATE_PATTERNS[0] is the banned fork-name pattern; sourced
|
||||
// from harvest-lint so this file never contains the literal itself
|
||||
// (scripts/check-privacy.sh would reject it).
|
||||
const forkName = new RegExp(DEFAULT_PRIVATE_PATTERNS[0], 'i');
|
||||
for (const name of [/\bAdam\b/, /\bHermes\b/, /\bHerdr\b/, /\bArk\b/, forkName]) {
|
||||
expect(name.test(body), `private name ${name} in ${file}`).toBe(false);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
it('has routing-eval fixtures', () => {
|
||||
const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
|
||||
expect(existsSync(evalPath)).toBe(true);
|
||||
const positives = readFileSync(evalPath, 'utf-8')
|
||||
.split('\n')
|
||||
.filter((l) => l.trim() && !l.trim().startsWith('//'))
|
||||
.map((l) => JSON.parse(l))
|
||||
.filter((l) => l.expected_skill === 'skill-vault-capture-policy');
|
||||
expect(positives.length).toBeGreaterThanOrEqual(4);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user