ci: raise unit-test matrix shard timeout 15 -> 20 min

Shard 4 runs ~14.5 min on master (dream.test.ts at ~29s/test dominates
its wallclock) and hit the 15-min job timeout twice on this PR with
1328 tests passing and 0 failing — the gate then failed on
'gated job did not succeed (got cancelled)'. Real fix is re-mining
scripts/test-weights.json to rebalance the shards; this unblocks CI.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.github/workflows/test.yml

@@ -206,7 +206,11 @@ jobs:
     needs: cache-check
     if: needs.cache-check.outputs.hit != 'true'
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    # 20 (was 15): shard 4 runs ~14.5 min on master (dream.test.ts ~29s/test
+    # dominates it) and hits the 15-min ceiling on slower runners, cancelling
+    # mid-run with 0 test failures. Rebalancing via
+    # scripts/mine-shard-weights.ts is the real fix; this stops the bleeding.
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       matrix:

docs/architecture/KEY_FILES.md

@@ -79,7 +79,7 @@ per-release `**vX.Y.Z:**` narration — CI enforces this
 - `docs/architecture/RETRIEVAL.md` + `docs/architecture/RETRIEVAL_MAXPOOL_INCIDENT.md` — retrieval-pipeline architecture reference + the named-thing-miss incident write-up (root cause, the five-layer fix, the eval that pins it).
 - `src/core/types.ts` extension + `src/core/operations.ts:search` + `src/core/import-file.ts` + `src/cli.ts` + `src/core/search/telemetry.ts` — the wiring layer for the retrieval cathedral. `SearchResult` gains `evidence`, `create_safety`, `title_match_boost`, `alias_hit` (all optional; evidence/create_safety reference the union types in `evidence.ts`). The `search` MCP op uses a cheap-hybrid path by default and accepts a per-call `mode` (conservative|balanced|tokenmax) honored ONLY for trusted/local callers (`resolvePerCallMode(ctx, ...)` — remote callers use the configured mode so a remote provider can't force tokenmax spend); every search path stamps evidence fail-soft. `importFromContent` projects frontmatter `aliases:` into `page_aliases` via `normalizeAliasList` + `engine.setPageAliases` so new + changed pages register aliases at ingest. `src/cli.ts` adds the `gbrain search diagnose` dispatch (lazy import) and reconciles the `search` CLI path with the cheap-hybrid op. `src/core/search/telemetry.ts` extends the rollup with the rank-1 base_score drift signal (sum/count + 3 coarse buckets, aggregate not per-query), surfaced via `gbrain search stats`, backed by migration v111's `search_telemetry` columns. Tests: `test/cli-search-dispatch.test.ts`, `test/search/per-call-mode.test.ts`, `test/search/telemetry-rank1.test.ts`, `test/search/title-boost-stage.test.ts`, `test/search/alias-hop.test.ts`, `test/search/evidence.test.ts`, `test/search/searchvector-maxpool.test.ts`, `test/search/pre-migration-failopen.test.ts`.
 - `src/commands/eval.ts` — `gbrain eval` command: single-run table + A/B config comparison. Sub-subcommand dispatch on `args[0]` routes `gbrain eval export` + `gbrain eval prune` + `gbrain eval replay` into session-capture handlers; bare `gbrain eval --qrels …` fall-through preserves the legacy IR-metrics flow. `gbrain eval cross-modal` is in the dispatch (the user-facing path is the cli.ts no-DB branch — `src/commands/eval.ts:cross-modal` only fires when callers re-enter with an existing engine).
-- `src/commands/eval-cross-modal.ts` — multi-model quality gate. Three different-provider frontier models score the OUTPUT against the TASK on a 5-dim list. Verdict `pass` (exit 0) / `fail` (exit 1) / `inconclusive` (exit 2; <2/3 model successes). Reuses `src/core/ai/gateway.ts:chat()` so config/auth/aliasing comes from the gateway recipe registry — no parallel provider stack. Self-configures the gateway via `buildGatewayConfig(loadConfig() ?? {})` since the cli.ts dispatch bypasses `connectEngine()`, so file-plane keys, env base URLs, and provider_chat_options follow the same adapter path as runtime. Default cycles 3 in TTY, 1 in non-TTY (partial cost guardrail) via the shared `resolveCycleDefault(explicit, isTty)` in `src/core/eval/cycle-default.ts`; the cost-estimate banner appends `cycleDefaultSuffix(...)` (`for 1 cycle(s) (non-interactive default; --cycles N for more)`) when the value is the silent non-TTY fallback, so the 1-vs-3 difference isn't hidden. Receipts land at `gbrainPath('eval-receipts')/<slug>-<sha8-of-output>.json`. `--batch <jsonl> [--limit N] [--concurrent N] [--max-usd FLOAT] [--yes]` fans out cross-modal scoring across a LongMemEval-shape JSONL; mutually exclusive with `--task` (fail-fast usage error if both set); filters `kind: "by_type_summary"` rows; pre-flight cost estimate refuses if `> --max-usd` without `--yes` (default cap 5.00 USD). Semaphore-bounded fan-out via inline `runWithLimit<T>(items, limit, fn)` (exported for unit tests): max N questions in-flight × 3 model slots = ceiling of 3N parallel API calls (default `--concurrent 3` → 9). Per-question receipts land in a per-batch tempdir and are deleted at end of run; the summary receipt inlines per-question verdicts as JSON, not file paths. Exit precedence (batch-level policy, NOT inherited from aggregate.ts): ERROR > FAIL > INCONCLUSIVE > PASS. DI seam: `runEvalCrossModal(args, opts?: {runEval?: typeof runEval})` mirrors `runEvalLongMemEval(args, {client?})`; tests pass `opts.runEval` to bypass real LLM calls AND the gateway availability check. Pinned by `test/eval-cross-modal-batch.test.ts`.
+- `src/commands/eval-cross-modal.ts` — multi-model quality gate. Three different-provider frontier models score the OUTPUT against the TASK on a 5-dim list. Verdict `pass` (exit 0) / `fail` (exit 1) / `inconclusive` (exit 2; <2/3 model successes). Reuses `src/core/ai/gateway.ts:chat()` so config/auth/aliasing comes from the gateway recipe registry — no parallel provider stack. Self-configures the gateway (`configureGateway(loadConfig() + process.env)`) since the cli.ts dispatch bypasses `connectEngine()`. Default cycles 3 in TTY, 1 in non-TTY (partial cost guardrail) via the shared `resolveCycleDefault(explicit, isTty)` in `src/core/eval/cycle-default.ts`; the cost-estimate banner appends `cycleDefaultSuffix(...)` (`for 1 cycle(s) (non-interactive default; --cycles N for more)`) when the value is the silent non-TTY fallback, so the 1-vs-3 difference isn't hidden. Receipts land at `gbrainPath('eval-receipts')/<slug>-<sha8-of-output>.json`. `--batch <jsonl> [--limit N] [--concurrent N] [--max-usd FLOAT] [--yes]` fans out cross-modal scoring across a LongMemEval-shape JSONL; mutually exclusive with `--task` (fail-fast usage error if both set); filters `kind: "by_type_summary"` rows; pre-flight cost estimate refuses if `> --max-usd` without `--yes` (default cap 5.00 USD). Semaphore-bounded fan-out via inline `runWithLimit<T>(items, limit, fn)` (exported for unit tests): max N questions in-flight × 3 model slots = ceiling of 3N parallel API calls (default `--concurrent 3` → 9). Per-question receipts land in a per-batch tempdir and are deleted at end of run; the summary receipt inlines per-question verdicts as JSON, not file paths. Exit precedence (batch-level policy, NOT inherited from aggregate.ts): ERROR > FAIL > INCONCLUSIVE > PASS. DI seam: `runEvalCrossModal(args, opts?: {runEval?: typeof runEval})` mirrors `runEvalLongMemEval(args, {client?})`; tests pass `opts.runEval` to bypass real LLM calls AND the gateway availability check. Pinned by `test/eval-cross-modal-batch.test.ts`.
 - `src/core/eval/cycle-default.ts` — single source of truth for the eval cycle-count default. Exports `DEFAULT_CYCLES_TTY = 3`, `DEFAULT_CYCLES_NONTTY = 1`, `resolveCycleDefault(explicit, isTty): {cycles, usedNonTtyDefault}`, and `cycleDefaultSuffix(r)` (returns ` (non-interactive default; --cycles N for more)` only when the non-TTY default was applied, else `''`). Consumed by `eval-cross-modal.ts`, `eval-takes-quality.ts` (run + regress), and `takes-quality-eval/runner.ts` (core uses only the constant — library stays TTY-agnostic; the CLI owns the TTY=3 upgrade + banner annotation). `eval-suspected-contradictions.ts` applies the same transparency to its `$5`/`$1` budget default via a `budgetUsdExplicit` flag (the budget is overwritten in-place so explicitness can't be inferred post-hoc). Not shared with `resolveWorkersWithClamp` (different domain, no engine, no dedup). Pinned by `test/eval/cycle-default.test.ts`, `test/eval-suspected-contradictions-budget-default.test.ts`.
 - `src/core/cross-modal-eval/json-repair.ts` — `parseModelJSON(raw)` named export with a 4-strategy fallback chain (direct parse → fence-strip → trailing-comma + single-quote + embedded-newline repair → regex nuclear option). Adversarial input throws rather than fabricating scores — the aggregator treats a throw as "this model contributed nothing this cycle" so the gate stays correct at >=2/3 successes.
 - `src/core/cross-modal-eval/aggregate.ts` — pure verdict logic. Pass criterion: `(successes >= 2) AND (every dim mean >= 7) AND (every dim min across models >= 5)`. Inconclusive when <2/3 models returned parseable scores (regression guard for the v1 `Object.values({}).every(...) === true` empty-array PASS bug).
@@ -138,7 +138,7 @@ per-release `**vX.Y.Z:**` narration — CI enforces this
 - `src/core/minions/queue.ts` extension — `MinionQueue.add()` rejects `subagent` jobs whose `data.model` resolves via `isAnthropicProvider()` to a non-Anthropic provider. Lazy-imports `model-config.ts` to avoid pulling engine types into queue's eager-load surface. Layer 1 of the three-layer subagent provider enforcement (layers 2+3: `model-config.ts:enforceSubagentAnthropic` runtime fallback + `src/commands/doctor.ts` `subagent_provider` check). Pinned by `test/agent-cli.test.ts`.
 - `src/commands/models.ts` — `gbrain models [--json]` read-only routing dashboard: prints tier defaults (`utility`/`reasoning`/`deep`/`subagent`), the resolved value for each (re-walking the resolution chain), every per-task override (11 `PER_TASK_KEYS`: `models.dream.synthesize`, `models.dream.patterns`, `models.drift`, `models.auto_think`, `models.think`, `models.subagent`, `facts.extraction_model`, `models.eval.longmemeval`, `models.expansion`, `models.chat`, `models.dream.synthesize_verdict`), the alias map, and a source-of-truth column (`default` / `config: <key>` / `env: <VAR>`). `gbrain models doctor [--skip=<provider>] [--json]` fires a 1-token `gateway.chat()` probe against each configured chat + expansion model and classifies failures into `{model_not_found, auth, rate_limit, network, unknown}`. Wired into `cli.ts` dispatch + `CLI_ONLY` set. A zero-token `embedding_config` probe runs FIRST, before any chat/expansion probes spend money: `probeEmbeddingConfig()` reads `getEmbeddingModel()` + `getEmbeddingDimensions()` and (for Voyage flexible-dim models) checks `isValidVoyageOutputDim(dims)` against `VOYAGE_VALID_OUTPUT_DIMS`. `ProbeStatus` variant `'config'` + optional `fix?: string` on `ProbeResult` surface a paste-ready `gbrain config set ...` line in human + JSON output; touchpoint label `'embedding_config'` joins `'chat'` and `'expansion'`.
 - `src/core/init-embed-check.ts` — embedding-key validation at `gbrain init`. `runInitEmbedCheck(opts)` runs a config-only `diagnoseEmbedding` (catches a missing key for ANY provider) plus a best-effort `liveTestEmbed` (1-token `gateway.embed(['probe'], {inputType:'query', abortSignal})`, 5s `AbortController` timeout, never throws — catches an invalid/expired key). Loud warning to stderr; init still exits 0 (`--no-embedding` is the deferred-setup escape; `--skip-embed-check` / `GBRAIN_INIT_SKIP_EMBED_CHECK=1` skip the check). Builds the effective env (`process.env` + file-plane `openai/anthropic/zeroentropy_api_key` from `loadConfigFileOnly()` + `opts.apiKey`) and configures the gateway via `buildGatewayConfig` before diagnose/probe, so the check sees the same keys AND provider base URLs runtime will (no false "missing key" for config.json-keyed users; the probe hits the right endpoint). Init-specific warning text names `--no-embedding` / `--skip-embed-check`, not the sync-flavored `--no-embed`. Wired into `initPGLite` + `initPostgres` in `src/commands/init.ts`, with the result added to the `--json` envelope as `embedding_check {ok, reason?, live_ok?}`. Pinned by `test/init-embed-check.test.ts` (hermetic via the gateway embed-transport seam + `withEnv`).
-- `src/core/ai/build-gateway-config.ts` — `buildGatewayConfig(c: GBrainConfig): AIGatewayConfig`, extracted from `src/cli.ts` (which re-exports it for back-compat). Single owner of translating stored config into gateway config — consumed by CLI runtime, init (`gbrain init`'s three configureGateway sites), `init-embed-check.ts`, the eval commands (cross-modal, takes-quality), provider diagnostics, and the in-process migration path. Folds file-plane API keys (openai/anthropic/zeroentropy/openrouter) into the gateway env and threads local-server `*_BASE_URL` env vars into base_urls; caller-provided `provider_base_urls` config wins over env base URLs. `process.env` wins EXCEPT empty-string / undefined values are dropped before the merge, so an injected empty `ANTHROPIC_API_KEY=''` (Claude Code neuters subprocess LLM calls this way) can't clobber a valid config-plane key; `'0'` / `'false'` are preserved. Pinned by `test/ai/build-gateway-config.test.ts`.
+- `src/core/ai/build-gateway-config.ts` — `buildGatewayConfig(c: GBrainConfig): AIGatewayConfig`, extracted from `src/cli.ts` (which re-exports it for back-compat). Lets core modules (`init-embed-check.ts`) reuse it without importing the CLI entrypoint. Single owner of folding file-plane API keys (openai/anthropic/zeroentropy) into the gateway env and threading local-server `*_BASE_URL` env vars into base_urls. `process.env` wins EXCEPT empty-string / undefined values are dropped before the merge, so an injected empty `ANTHROPIC_API_KEY=''` (Claude Code neuters subprocess LLM calls this way) can't clobber a valid config-plane key; `'0'` / `'false'` are preserved. Pinned by `test/ai/build-gateway-config.test.ts`.
 - `src/commands/doctor.ts` extension — `subagent_provider` check (layer 3 of 3). Warns when `models.tier.subagent` is explicitly set non-Anthropic (message names the bad value + paste-ready fix `gbrain config set models.tier.subagent anthropic:claude-sonnet-4-6`); also warns when `models.default` would sneak `subagent` into a non-Anthropic provider via tier inheritance. OK when subagent tier resolves to Anthropic. Tests in `test/doctor.test.ts`.
 - `src/core/skill-trigger-index.ts` — Shared loader that unions per-skill SKILL.md frontmatter `triggers:` with curated RESOLVER.md / AGENTS.md rows from `skillsDir` AND the parent dir (preserves the OpenClaw workspace-root layout). UNION semantics: explicit RESOLVER.md rows ADD to frontmatter triggers (don't replace). Dedup keyed on `(skillPath, trigger.trim().toLowerCase())`. Three consumers fold through this primitive — `checkResolvable`, `runRoutingEvalCli`, `mounts-cache.composeResolvers` — so fixing frontmatter reaches all of them. Exports `loadSkillTriggerIndex(skillsDir): SkillTriggerEntry[]`, `entriesToResolverContent(entries): string` (synthesizes a markdown-table resolver string for `runRoutingEval`'s string-content API), `findPrimaryResolverPath(skillsDir): string | null`, the `FRONTMATTER_SECTION` constant, and `_resetWarnedSkillsForTests`. Skip rules: non-directory entries, `_*`/`.*` prefixes, `conventions/`+`migrations/` subdirs, skills with no `SKILL.md` (deprecated `install/` graceful-skipped), no `triggers:` array, or malformed YAML (warn-once + skip). Reuses `parseSkillFrontmatter` from `src/core/skill-frontmatter.ts` (regex-based, not full YAML). Pinned by `test/skill-trigger-index.test.ts` (18 hermetic cases). CI gate `bun run check:resolver` (= `bun src/cli.ts check-resolvable --strict --skills-dir skills/`) wired into `bun run verify`.
 - `src/core/skill-catalog.ts` — host-repo skill catalog backing the MCP `list_skills` / `get_skill` ops. Lets a thin MCP client (Codex desktop, Claude Code, Claude Cowork, Perplexity) DISCOVER + FOLLOW the agent repo's fat-markdown skills over `gbrain serve` — a skill is prose, so "using" one = fetching its body then calling the gbrain MCP tools the server already exposes. Read-scope, NOT localOnly (defensible only via the full mitigation stack): (1) **publish gate** — `assertPublishEnabled(ctx, publishSkills)`; remote callers require `mcp.publish_skills === true`, default-OFF so an upgrade never silently grants existing read tokens host-skill read; local callers (`ctx.remote === false`) always pass. (2) **path confinement** — `assertSkillNameShape` rejects separators/`..`/null/space before any FS access; the client `name` is a manifest LOOKUP KEY (via `loadOrDeriveManifest`), never a raw path segment; `confineManifestPath` does realpath + relative-containment + `SKILL.md`-regular-file check on EVERY entry (defeats poisoned manifest.json `path`, symlink/`..` escape). (3) **frontmatter allowlist** — `GetSkillResult.frontmatter` projects a safe subset; private `writes_to` + `sources` dropped. (4) **prose-only + 256KB cap** (`MAX_SKILL_MD_BYTES`, env `GBRAIN_MAX_SKILL_MD_BYTES`), size-checked twice (statSync + UTF-8 byte length). (5) **no install_path serve for remote** — remote callers use `autoDetectSkillsDir` (no install-path tier) so a hosted gbrain with no agent repo returns `storage_error`; local callers use `autoDetectSkillsDirReadOnly`. (6) MCP rate-limiter caps call rate. Config reads honor BOTH planes: `readMcpPublishSkills` / `readMcpSkillsDir` prefer the DB plane (`engine.getConfig`) over the file plane (`ctx.config.mcp`). Tool-honesty: `crossReferenceTools(declared, ctx)` splits a skill's declared `tools:` into `usable_tools` vs `unavailable_tools`; `buildSkillCatalog`'s `instructions` envelope (`SKILL_CATALOG_INSTRUCTIONS`) carries the "these are prose, follow-then-call-tools" protocol. Skills are host-filesystem repo-global — `sourceScopeOpts(ctx)` / `ctx.brainId` deliberately do NOT apply. `buildSkillCatalog` is resilient (one malformed/escaping skill is skipped, never throws). Config keys in `src/core/config.ts`: `GBrainConfig.mcp?: { publish_skills?, skills_dir? }` + `KNOWN_CONFIG_KEYS` entries `mcp.publish_skills`/`mcp.publish_skills_prompted`/`mcp.skills_dir` + `mcp.` prefix in `KNOWN_CONFIG_KEY_PREFIXES`. `src/commands/init.ts` writes `config.mcp = { publish_skills: true, ... }` for new installs (existing config wins on re-init). `src/commands/upgrade.ts:runPostUpgrade` adds a one-time consent prompt (gated by `mcp.publish_skills_prompted`; existing installs stay OFF until owner opts in). Two ops register in `src/core/operations.ts` (`list_skills` with optional `section` filter + `cliHints:{name:'skills'}`; `get_skill` taking `name` + `cliHints:{name:'skill', positional:['name']}`) and dynamically import this module to avoid the import cycle (skill-catalog statically imports the `operations` array). Descriptions in `src/core/operations-descriptions.ts` (`LIST_SKILLS_DESCRIPTION`, `GET_SKILL_DESCRIPTION`, `SKILL_CATALOG_INSTRUCTIONS`, `SKILL_CLIENT_GUIDANCE`), pinned by `test/operations-descriptions.test.ts`. CLI: `gbrain skills` / `gbrain skill <name>`. Pinned by `test/skill-catalog.test.ts`, `test/skill-catalog-security.test.ts` (path-confinement / poisoned-manifest / symlink-escape), `test/skill-catalog-transports.test.ts` (publish-gate + remote-vs-local) over `test/fixtures/skill-catalog/`.

src/commands/eval-cross-modal.ts

@@ -21,8 +21,7 @@ import { join } from 'path';
 import { tmpdir } from 'os';
 import { createHash } from 'crypto';
 
-import { gbrainPath, loadConfig, type GBrainConfig } from '../core/config.ts';
-import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts';
+import { gbrainPath, loadConfig } from '../core/config.ts';
 import { configureGateway, isAvailable } from '../core/ai/gateway.ts';
 import { runWithLimit } from '../core/worker-pool.ts';
 import { resolveCycleDefault, cycleDefaultSuffix } from '../core/eval/cycle-default.ts';
@@ -265,11 +264,32 @@ function isTTY(): boolean {
  * Returns true on success; false (and prints a hint) when no config is found.
  */
 function configureGatewayForCli(): boolean {
-  // Route through buildGatewayConfig (the single adapter seam) so file-plane
-  // API keys, env base URLs, and provider_chat_options follow the same
-  // precedence as the runtime path. No config file is fine — env alone serves.
   const config = loadConfig();
-  configureGateway(buildGatewayConfig(config ?? ({} as GBrainConfig)));
+  if (!config) {
+    // No config file is fine for the eval command — env vars alone may serve.
+    // We still call configureGateway so gateway recipes can read the env map.
+    configureGateway({
+      embedding_model: undefined,
+      embedding_dimensions: undefined,
+      expansion_model: undefined,
+      chat_model: undefined,
+      chat_fallback_chain: undefined,
+      base_urls: undefined,
+      provider_chat_options: undefined,
+      env: { ...process.env },
+    });
+    return true;
+  }
+  configureGateway({
+    embedding_model: config.embedding_model,
+    embedding_dimensions: config.embedding_dimensions,
+    expansion_model: config.expansion_model,
+    chat_model: config.chat_model,
+    chat_fallback_chain: config.chat_fallback_chain,
+    base_urls: config.provider_base_urls,
+    provider_chat_options: config.provider_chat_options,
+    env: { ...process.env },
+  });
   return true;
 }
 

src/commands/eval-takes-quality.ts

@@ -21,8 +21,7 @@
  */
 import type { BrainEngine } from '../core/engine.ts';
 import { configureGateway } from '../core/ai/gateway.ts';
-import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts';
-import { loadConfig, type GBrainConfig } from '../core/config.ts';
+import { loadConfig } from '../core/config.ts';
 import { runEval, DEFAULT_MODEL_PANEL } from '../core/takes-quality-eval/runner.ts';
 import { resolveCycleDefault, cycleDefaultSuffix } from '../core/eval/cycle-default.ts';
 import { writeReceipt } from '../core/takes-quality-eval/receipt-write.ts';
@@ -128,12 +127,8 @@ export async function runReplayNoBrain(argv: string[]): Promise<number> {
 export async function runEvalTakesQuality(engine: BrainEngine, args: string[]): Promise<void> {
   // Self-configure the AI gateway (mirrors eval-cross-modal pattern). The
   // gateway needs config.ai_gateway + env vars; configureGateway reads both.
-  // Route through buildGatewayConfig: the old `{ ...cfg, ...process.env }`
-  // spread never populated the gateway's `env` field (the gateway NEVER reads
-  // process.env at call time), so availability checks saw no keys at all and
-  // file-plane API keys / provider base URLs were dropped.
   const cfg = loadConfig();
-  configureGateway(buildGatewayConfig(cfg ?? ({} as GBrainConfig)));
+  configureGateway({ ...cfg, ...(process.env as Record<string, string>) } as any);
 
   const { subcmd, argv, json } = parseSubcmd(args);
 

src/commands/init.ts

@@ -7,7 +7,6 @@ import { homedir } from 'os';
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = dirname(__filename);
 import { saveConfig, loadConfig, loadConfigFileOnly, toEngineConfig, gbrainPath, configPath, isThinClient, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
-import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts';
 import { createEngine } from '../core/engine-factory.ts';
 import { discoverOAuth, mintClientCredentialsToken, smokeTestMcp } from '../core/remote-mcp-probe.ts';
 import { runInitEmbedCheck } from '../core/init-embed-check.ts';
@@ -723,8 +722,7 @@ async function configureGatewayWithMergedPrecedence(
   // pollutes config.json.
   const envOverlay = loadConfig() ?? ({} as GBrainConfig);
 
-  const merged: GBrainConfig = {
-    ...envOverlay,
+  const merged = {
     embedding_model: aiOpts?.embedding_model ?? envOverlay.embedding_model ?? existingFile.embedding_model,
     embedding_dimensions: aiOpts?.embedding_dimensions ?? envOverlay.embedding_dimensions ?? existingFile.embedding_dimensions,
     expansion_model: aiOpts?.expansion_model ?? envOverlay.expansion_model ?? existingFile.expansion_model,
@@ -732,9 +730,13 @@ async function configureGatewayWithMergedPrecedence(
   };
 
   const { configureGateway, getEmbeddingModel, getEmbeddingDimensions, getExpansionModel, getChatModel } = await import('../core/ai/gateway.ts');
-  // buildGatewayConfig (the single adapter seam) so file-plane API keys and
-  // env base URLs reach the gateway — a hand-rolled config here dropped them.
-  configureGateway(buildGatewayConfig(merged));
+  configureGateway({
+    embedding_model: merged.embedding_model,
+    embedding_dimensions: merged.embedding_dimensions,
+    expansion_model: merged.expansion_model,
+    chat_model: merged.chat_model,
+    env: { ...process.env },
+  });
 
   // Read back resolved values — gateway applies internal defaults for unset
   // fields, so these are the values that actually shaped the schema.
@@ -829,13 +831,13 @@ async function initPGLite(opts: {
   // resolveAIOptions above: CLI flags > env vars > existing file > gateway
   // defaults.
   const { configureGateway } = await import('../core/ai/gateway.ts');
-  configureGateway(buildGatewayConfig({
-    ...(loadConfig() ?? ({} as GBrainConfig)),
+  configureGateway({
     embedding_model: resolvedModel ?? opts.aiOpts?.embedding_model,
     embedding_dimensions: resolvedDim ?? opts.aiOpts?.embedding_dimensions,
     expansion_model: opts.aiOpts?.expansion_model,
     chat_model: opts.aiOpts?.chat_model,
-  } as GBrainConfig));
+    env: { ...process.env },
+  });
   if (resolvedModel) console.log(`  Embedding: ${resolvedModel} (${resolvedDim}d)`);
   if (opts.aiOpts?.expansion_model) console.log(`  Expansion: ${opts.aiOpts.expansion_model}`);
   if (opts.aiOpts?.chat_model) console.log(`  Chat: ${opts.aiOpts.chat_model}`);
@@ -1044,13 +1046,13 @@ async function initPostgres(opts: {
 
   // T6: unconditional configureGateway BEFORE initSchema.
   const { configureGateway } = await import('../core/ai/gateway.ts');
-  configureGateway(buildGatewayConfig({
-    ...(loadConfig() ?? ({} as GBrainConfig)),
+  configureGateway({
     embedding_model: resolvedModel ?? opts.aiOpts?.embedding_model,
     embedding_dimensions: resolvedDim ?? opts.aiOpts?.embedding_dimensions,
     expansion_model: opts.aiOpts?.expansion_model,
     chat_model: opts.aiOpts?.chat_model,
-  } as GBrainConfig));
+    env: { ...process.env },
+  });
   if (resolvedModel) console.log(`  Embedding: ${resolvedModel} (${resolvedDim}d)`);
   if (opts.aiOpts?.expansion_model) console.log(`  Expansion: ${opts.aiOpts.expansion_model}`);
   if (opts.aiOpts?.chat_model) console.log(`  Chat: ${opts.aiOpts.chat_model}`);

src/commands/migrations/in-process.ts

@@ -66,11 +66,15 @@ export async function runMigrateOnlyCore(opts?: { timeoutMs?: number }): Promise
 
   // configureGateway BEFORE initSchema (init.ts B.3): a schema bump on a brain
   // whose file config is missing embedding fields must not fall through to
-  // stale hardcoded fallbacks. Route through buildGatewayConfig so file-plane
-  // API keys and provider base URLs follow the same precedence as runtime.
+  // stale hardcoded fallbacks. loadConfig already merged env; propagate it.
   const { configureGateway } = await import('../../core/ai/gateway.ts');
-  const { buildGatewayConfig } = await import('../../core/ai/build-gateway-config.ts');
-  configureGateway(buildGatewayConfig(config));
+  configureGateway({
+    embedding_model: config.embedding_model,
+    embedding_dimensions: config.embedding_dimensions,
+    expansion_model: config.expansion_model,
+    chat_model: config.chat_model,
+    env: { ...process.env },
+  });
 
   const timeoutMs = opts?.timeoutMs ?? MIGRATE_ONLY_TIMEOUT_MS;
   const engine = await createEngine(toEngineConfig(config));

src/core/brain-score-recommendations.ts

@@ -12,8 +12,8 @@ import { parseModelId } from './ai/model-resolver.ts';
  * `resolveKey` closure without re-parsing recipes.
  *
  * Only OPENAI_API_KEY and ZEROENTROPY_API_KEY appear here because those are the
- * only embedding keys `buildGatewayConfig` (src/core/ai/build-gateway-config.ts)
- * folds from config into the gateway env. VOYAGE_API_KEY / GOOGLE_GENERATIVE_AI_API_KEY are deliberately
+ * only embedding keys `buildGatewayConfig` (src/cli.ts) folds from config into
+ * the gateway env. VOYAGE_API_KEY / GOOGLE_GENERATIVE_AI_API_KEY are deliberately
  * absent: their config fields are NOT threaded to the gateway today, so the
  * producer closures fall through to checking `process.env` ONLY for them. That
  * matches what the gateway can actually use (the recipes read those keys from

src/core/skill-manifest.ts

@@ -23,6 +23,15 @@
  * hold conventions and shared rule files, not skills. Files like
  * `_brain-filing-rules.md` live at the root and are not considered
  * skills by either loader.
+ *
+ * ClawHub-installed workspace skills (#1767): a skill dir carrying
+ * `.clawhub/origin.json` is an externally-managed runtime integration
+ * (e.g. an email or catalog skill), not a gbrain-routable skill. The
+ * derive path SKIPS those so `gbrain doctor` resolver_health doesn't
+ * hard-fail on them — UNLESS the skill's SKILL.md frontmatter declares
+ * `triggers:`, which is the explicit opt-in to gbrain routing (and the
+ * same surface that makes it reachable). An explicit manifest.json that
+ * lists a ClawHub skill also keeps strict checking (verbatim path).
  */
 
 import { existsSync, readFileSync, readdirSync, statSync } from 'fs';
@@ -60,9 +69,27 @@ function parseSkillName(skillMdPath: string): string | null {
   }
 }
 
+/**
+ * Does the SKILL.md frontmatter declare a `triggers:` key? A ClawHub-
+ * installed skill that ships gbrain `triggers:` has explicitly opted in
+ * to gbrain routing and gets full resolver checks (#1767).
+ */
+function declaresTriggers(skillMdPath: string): boolean {
+  try {
+    const content = readFileSync(skillMdPath, 'utf-8');
+    const fmMatch = content.match(/^---\n([\s\S]*?)\n---/);
+    if (!fmMatch) return false;
+    return /^triggers:/m.test(fmMatch[1]);
+  } catch {
+    return false;
+  }
+}
+
 /**
  * Walk skillsDir, return every `<skillsDir>/<dir>/SKILL.md` as a
- * ManifestEntry. Dotfile and underscore-prefixed dirs are skipped.
+ * ManifestEntry. Dotfile and underscore-prefixed dirs are skipped, as
+ * are ClawHub-installed external skills that haven't opted in to gbrain
+ * routing via `triggers:` frontmatter (#1767).
  */
 function deriveManifest(skillsDir: string): ManifestEntry[] {
   const out: ManifestEntry[] = [];
@@ -93,6 +120,12 @@ function deriveManifest(skillsDir: string): ManifestEntry[] {
     const skillMd = join(subdirAbs, 'SKILL.md');
     if (!existsSync(skillMd)) continue;
 
+    // ClawHub-installed external skill (#1767): skip unless it opts in
+    // to gbrain routing by declaring `triggers:` in its frontmatter.
+    if (existsSync(join(subdirAbs, '.clawhub', 'origin.json')) && !declaresTriggers(skillMd)) {
+      continue;
+    }
+
     const frontmatterName = parseSkillName(skillMd);
     const name = frontmatterName && frontmatterName !== '' ? frontmatterName : entry;
     out.push({ name, path: `${entry}/SKILL.md` });

test/ai/build-gateway-config.test.ts

@@ -25,7 +25,6 @@ import { withEnv } from '../helpers/with-env.ts';
 
 const PASSTHROUGHS: Array<{ envVar: string; recipeId: string }> = [
   { envVar: 'LLAMA_SERVER_BASE_URL', recipeId: 'llama-server' },
-  { envVar: 'LLAMA_SERVER_RERANKER_BASE_URL', recipeId: 'llama-server-reranker' },
   { envVar: 'OLLAMA_BASE_URL', recipeId: 'ollama' },
   { envVar: 'LMSTUDIO_BASE_URL', recipeId: 'lmstudio' },
   { envVar: 'LITELLM_BASE_URL', recipeId: 'litellm' },

test/check-resolvable.test.ts

@@ -382,6 +382,35 @@ describe("DRY detection — checkResolvable", () => {
   });
 });
 
+describe("#1767 — ClawHub workspace skills are not resolver-required", () => {
+  let dir: string;
+  afterEachCleanup(() => dir && rmSync(dir, { recursive: true, force: true }));
+
+  test("ClawHub skill without gbrain metadata produces no unreachable/mece_gap", () => {
+    dir = mkdtempSync(join(tmpdir(), "gbrain-clawhub-"));
+    // Native gbrain skill: routable via frontmatter triggers. No manifest.json
+    // (the OpenClaw derive path from the issue repro).
+    mkdirSync(join(dir, "query"), { recursive: true });
+    writeFileSync(
+      join(dir, "query", "SKILL.md"),
+      `---\nname: query\ndescription: test\ntriggers:\n  - "what do we know"\n---\n\n# query\n`
+    );
+    // ClawHub-installed integration: no triggers, no resolver row.
+    mkdirSync(join(dir, "agentmail", ".clawhub"), { recursive: true });
+    writeFileSync(
+      join(dir, "agentmail", ".clawhub", "origin.json"),
+      JSON.stringify({ registry: "https://clawhub.ai", slug: "agentmail" })
+    );
+    writeFileSync(join(dir, "agentmail", "SKILL.md"), `---\nname: agentmail\ndescription: email integration\n---\n\n# agentmail\n`);
+
+    const report = checkResolvable(dir);
+    const agentmailIssues = report.issues.filter(i => i.skill === "agentmail");
+    expect(agentmailIssues).toEqual([]);
+    expect(report.ok).toBe(true);
+    expect(report.summary.total_skills).toBe(1);
+  });
+});
+
 describe("v0.22.4 regression — actual repo skills/ has 0 errors", () => {
   test("repo skills/ pass check-resolvable cleanly (zero errors AND zero warnings)", () => {
     // The v0.22.4 (Part A) contract was zero warnings AND zero errors.

test/cli-multimodal-integration.test.ts

@@ -11,13 +11,32 @@
 import { afterAll, beforeAll, beforeEach, describe, expect, test } from 'bun:test';
 import { PGLiteEngine } from '../src/core/pglite-engine.ts';
 import { loadConfigWithEngine, type GBrainConfig } from '../src/core/config.ts';
-import { buildGatewayConfig } from '../src/core/ai/build-gateway-config.ts';
 import {
   configureGateway,
   getEmbeddingModel,
   getMultimodalModel,
   resetGateway,
 } from '../src/core/ai/gateway.ts';
+import type { AIGatewayConfig } from '../src/core/ai/types.ts';
+
+// Mirror the cli.ts buildGatewayConfig helper exactly. Keeping a copy here
+// (instead of exporting from cli.ts) is intentional: the test asserts the
+// shape of the contract, not the helper's identity. If cli.ts drifts, the
+// e2e behavior these tests care about (DB-set value lands in gateway) still
+// holds, but a helper-shape test would also catch the drift in PR review.
+function buildGatewayConfig(c: GBrainConfig): AIGatewayConfig {
+  return {
+    embedding_model: c.embedding_model,
+    embedding_dimensions: c.embedding_dimensions,
+    embedding_multimodal_model: c.embedding_multimodal_model,
+    expansion_model: c.expansion_model,
+    chat_model: c.chat_model,
+    chat_fallback_chain: c.chat_fallback_chain,
+    base_urls: c.provider_base_urls,
+    provider_chat_options: c.provider_chat_options,
+    env: { ...process.env },
+  };
+}
 
 let engine: PGLiteEngine;
 
@@ -28,7 +47,6 @@ beforeAll(async () => {
 });
 
 afterAll(async () => {
-  resetGateway(); // don't leak this file's gateway config into shard siblings
   await engine.disconnect();
 });
 

test/eval-takes-quality-gateway.test.ts

@@ -1,57 +0,0 @@
-/**
- * eval-takes-quality gateway self-config — adapter-boundary regression
- * (takeover of PR #2430).
- *
- * The old callsite spread `{ ...cfg, ...process.env }` straight into
- * configureGateway. The gateway NEVER reads process.env at call time — it
- * reads `_config.env` — and that spread never populated an `env` field at
- * all, so every availability/diagnose check dereferenced `undefined.env[k]`
- * and file-plane API keys (config.json `openai_api_key` etc.) were dropped.
- * Routing through buildGatewayConfig fixes both. This test fails (throws)
- * on the old code path.
- */
-import { afterAll, describe, expect, test } from 'bun:test';
-import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs';
-import { tmpdir } from 'node:os';
-import { join } from 'node:path';
-import { runEvalTakesQuality } from '../src/commands/eval-takes-quality.ts';
-import { isAvailable, resetGateway } from '../src/core/ai/gateway.ts';
-import { withEnv } from './helpers/with-env.ts';
-import type { BrainEngine } from '../src/core/engine.ts';
-
-afterAll(() => {
-  resetGateway();
-});
-
-describe('runEvalTakesQuality — gateway self-config routes through buildGatewayConfig', () => {
-  test('file-plane openai_api_key reaches the gateway env (help path, engine untouched)', async () => {
-    const home = mkdtempSync(join(tmpdir(), 'gbrain-etq-gw-'));
-    try {
-      mkdirSync(join(home, '.gbrain'), { recursive: true });
-      writeFileSync(
-        join(home, '.gbrain', 'config.json'),
-        JSON.stringify({
-          engine: 'pglite',
-          database_path: join(home, '.gbrain', 'brain'),
-          openai_api_key: 'sk-file-plane-test',
-        }),
-      );
-      await withEnv(
-        {
-          GBRAIN_HOME: home,
-          OPENAI_API_KEY: undefined,
-          DATABASE_URL: undefined,
-          GBRAIN_DATABASE_URL: undefined,
-        },
-        async () => {
-          // 'help' returns before touching the engine, but the gateway is
-          // configured first — exactly the seam under test.
-          await runEvalTakesQuality({} as BrainEngine, ['--help']);
-          expect(isAvailable('embedding', 'openai:text-embedding-3-small')).toBe(true);
-        },
-      );
-    } finally {
-      rmSync(home, { recursive: true, force: true });
-    }
-  });
-});

test/skill-manifest.test.ts

@@ -166,6 +166,55 @@ describe('loadOrDeriveManifest', () => {
     expect(r.skills.map(s => s.name)).toEqual(['apple', 'mango', 'zebra']);
   });
 
+  // #1767 — ClawHub-installed workspace skills are external integrations,
+  // not gbrain-routable skills. The derive path skips them unless they
+  // opt in via `triggers:` frontmatter.
+  it('skips ClawHub-origin skills without triggers frontmatter (#1767)', () => {
+    const dir = scratch();
+    writeSkill(dir, 'query', 'query');
+    writeSkill(dir, 'agentmail', 'agentmail');
+    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
+    writeFileSync(
+      join(dir, 'agentmail', '.clawhub', 'origin.json'),
+      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
+    );
+    const r = loadOrDeriveManifest(dir);
+    expect(r.derived).toBe(true);
+    expect(r.skills.map(s => s.name)).toEqual(['query']);
+  });
+
+  it('includes ClawHub-origin skills that opt in via triggers frontmatter (#1767)', () => {
+    const dir = scratch();
+    writeSkill(dir, 'agentmail', 'agentmail');
+    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
+    writeFileSync(
+      join(dir, 'agentmail', '.clawhub', 'origin.json'),
+      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
+    );
+    writeFileSync(
+      join(dir, 'agentmail', 'SKILL.md'),
+      `---\nname: agentmail\ndescription: test\ntriggers:\n  - "send email"\n---\n\n# agentmail\n`
+    );
+    const r = loadOrDeriveManifest(dir);
+    expect(r.derived).toBe(true);
+    expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
+  });
+
+  it('keeps ClawHub-origin skills listed in an explicit manifest.json (#1767)', () => {
+    // Explicit manifest.json is a deliberate declaration — strict checking stays.
+    const dir = scratch();
+    writeSkill(dir, 'agentmail', 'agentmail');
+    mkdirSync(join(dir, 'agentmail', '.clawhub'), { recursive: true });
+    writeFileSync(
+      join(dir, 'agentmail', '.clawhub', 'origin.json'),
+      JSON.stringify({ registry: 'https://clawhub.ai', slug: 'agentmail' })
+    );
+    writeManifest(dir, { skills: [{ name: 'agentmail', path: 'agentmail/SKILL.md' }] });
+    const r = loadOrDeriveManifest(dir);
+    expect(r.derived).toBe(false);
+    expect(r.skills.map(s => s.name)).toEqual(['agentmail']);
+  });
+
   it('treats dirs without SKILL.md as not-a-skill', () => {
     const dir = scratch();
     writeSkill(dir, 'query', 'query');