diff --git a/docs/architecture/KEY_FILES.md b/docs/architecture/KEY_FILES.md index c102a7ef5..f0a069d1c 100644 --- a/docs/architecture/KEY_FILES.md +++ b/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 (`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')/-.json`. `--batch [--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(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 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')/-.json`. `--batch [--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(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: ` / `env: `). `gbrain models doctor [--skip=] [--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). 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/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/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 `. 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/`. diff --git a/src/commands/eval-cross-modal.ts b/src/commands/eval-cross-modal.ts index c466076b9..cfe555c4f 100644 --- a/src/commands/eval-cross-modal.ts +++ b/src/commands/eval-cross-modal.ts @@ -21,7 +21,8 @@ import { join } from 'path'; import { tmpdir } from 'os'; import { createHash } from 'crypto'; -import { gbrainPath, loadConfig } from '../core/config.ts'; +import { gbrainPath, loadConfig, type GBrainConfig } from '../core/config.ts'; +import { buildGatewayConfig } from '../core/ai/build-gateway-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'; @@ -264,32 +265,11 @@ 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(); - 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 }, - }); + configureGateway(buildGatewayConfig(config ?? ({} as GBrainConfig))); return true; } diff --git a/src/commands/eval-takes-quality.ts b/src/commands/eval-takes-quality.ts index b63303982..5542b7edf 100644 --- a/src/commands/eval-takes-quality.ts +++ b/src/commands/eval-takes-quality.ts @@ -21,7 +21,8 @@ */ import type { BrainEngine } from '../core/engine.ts'; import { configureGateway } from '../core/ai/gateway.ts'; -import { loadConfig } from '../core/config.ts'; +import { buildGatewayConfig } from '../core/ai/build-gateway-config.ts'; +import { loadConfig, type GBrainConfig } 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'; @@ -127,8 +128,12 @@ export async function runReplayNoBrain(argv: string[]): Promise { export async function runEvalTakesQuality(engine: BrainEngine, args: string[]): Promise { // 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({ ...cfg, ...(process.env as Record) } as any); + configureGateway(buildGatewayConfig(cfg ?? ({} as GBrainConfig))); const { subcmd, argv, json } = parseSubcmd(args); diff --git a/src/commands/init.ts b/src/commands/init.ts index 69e3d5b93..fdcf71148 100644 --- a/src/commands/init.ts +++ b/src/commands/init.ts @@ -7,6 +7,7 @@ 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'; @@ -722,7 +723,8 @@ async function configureGatewayWithMergedPrecedence( // pollutes config.json. const envOverlay = loadConfig() ?? ({} as GBrainConfig); - const merged = { + const merged: GBrainConfig = { + ...envOverlay, 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, @@ -730,13 +732,9 @@ async function configureGatewayWithMergedPrecedence( }; const { configureGateway, getEmbeddingModel, getEmbeddingDimensions, getExpansionModel, getChatModel } = await import('../core/ai/gateway.ts'); - configureGateway({ - embedding_model: merged.embedding_model, - embedding_dimensions: merged.embedding_dimensions, - expansion_model: merged.expansion_model, - chat_model: merged.chat_model, - env: { ...process.env }, - }); + // 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)); // Read back resolved values — gateway applies internal defaults for unset // fields, so these are the values that actually shaped the schema. @@ -831,13 +829,13 @@ async function initPGLite(opts: { // resolveAIOptions above: CLI flags > env vars > existing file > gateway // defaults. const { configureGateway } = await import('../core/ai/gateway.ts'); - configureGateway({ + configureGateway(buildGatewayConfig({ + ...(loadConfig() ?? ({} as GBrainConfig)), 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, - env: { ...process.env }, - }); + } as GBrainConfig)); 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}`); @@ -1046,13 +1044,13 @@ async function initPostgres(opts: { // T6: unconditional configureGateway BEFORE initSchema. const { configureGateway } = await import('../core/ai/gateway.ts'); - configureGateway({ + configureGateway(buildGatewayConfig({ + ...(loadConfig() ?? ({} as GBrainConfig)), 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, - env: { ...process.env }, - }); + } as GBrainConfig)); 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}`); diff --git a/src/commands/migrations/in-process.ts b/src/commands/migrations/in-process.ts index 784fea3df..8c0d2a390 100644 --- a/src/commands/migrations/in-process.ts +++ b/src/commands/migrations/in-process.ts @@ -66,15 +66,11 @@ 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. loadConfig already merged env; propagate it. + // stale hardcoded fallbacks. Route through buildGatewayConfig so file-plane + // API keys and provider base URLs follow the same precedence as runtime. const { configureGateway } = await import('../../core/ai/gateway.ts'); - 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 { buildGatewayConfig } = await import('../../core/ai/build-gateway-config.ts'); + configureGateway(buildGatewayConfig(config)); const timeoutMs = opts?.timeoutMs ?? MIGRATE_ONLY_TIMEOUT_MS; const engine = await createEngine(toEngineConfig(config)); diff --git a/src/core/brain-score-recommendations.ts b/src/core/brain-score-recommendations.ts index 810b43bed..719d0dbdf 100644 --- a/src/core/brain-score-recommendations.ts +++ b/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/cli.ts) folds from config into - * the gateway env. VOYAGE_API_KEY / GOOGLE_GENERATIVE_AI_API_KEY are deliberately + * 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 * 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 diff --git a/test/ai/build-gateway-config.test.ts b/test/ai/build-gateway-config.test.ts index e94ff39fe..feee5a883 100644 --- a/test/ai/build-gateway-config.test.ts +++ b/test/ai/build-gateway-config.test.ts @@ -25,6 +25,7 @@ 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' }, diff --git a/test/cli-multimodal-integration.test.ts b/test/cli-multimodal-integration.test.ts index 640ecf31c..a46d47e52 100644 --- a/test/cli-multimodal-integration.test.ts +++ b/test/cli-multimodal-integration.test.ts @@ -11,32 +11,13 @@ 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; diff --git a/test/eval-takes-quality-gateway.test.ts b/test/eval-takes-quality-gateway.test.ts new file mode 100644 index 000000000..78e6f4481 --- /dev/null +++ b/test/eval-takes-quality-gateway.test.ts @@ -0,0 +1,57 @@ +/** + * 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 }); + } + }); +});