feat(ai): adjacent fixes — no_batch_cap (#779) + config-key fallbacks (#121)

Two small ergonomics fixes folded together (#765 deferred — see TODOS.md
follow-up; the CJK PGLite extraction was bigger than the plan estimated).

#779 reworked (alexandreroumieu-codeapprentice): silence the
missing-max_batch_tokens startup warning for recipes with genuinely
dynamic batch capacity. New `EmbeddingTouchpoint.no_batch_cap?: true`
field. Set on ollama (capacity depends on locally loaded model +
OLLAMA_NUM_PARALLEL), litellm-proxy (depends on backend), llama-server
(set by --ctx-size at server launch). Three less stderr warnings on
every gateway configure; google still warns (it's a real fixed-cap
provider that ought to ship a max_batch_tokens declaration).

Bonus: litellm-proxy now declares `user_provided_models: true`, removing
the last consumer of the legacy `recipe.id === 'litellm'` hardcode in
gateway.ts:223 (D8=A wire-through completion).

#121 reworked (vinsew): self-contained API keys. Two parts:

  1. config.ts: ANTHROPIC_API_KEY env merge was silently missing.
     loadConfig() merged OPENAI_API_KEY but not ANTHROPIC_API_KEY into
     the file-config-shape result. One-line addition.

  2. cli.ts:buildGatewayConfig: when ~/.gbrain/config.json declares
     openai_api_key / anthropic_api_key but the process env doesn't
     have those env vars set (common for launchd-spawned daemons,
     agent subprocess tools, containers that don't propagate
     ~/.zshrc), fold the config-file values into the gateway env
     snapshot. Process env still wins (loaded last) so per-process
     overrides keep working.

Tests (4 cases in test/ai/no-batch-cap-suppression.test.ts):
- Ollama / LiteLLM / llama-server all declare no_batch_cap: true
- configureGateway does NOT warn for those three
- configureGateway STILL warns for google (regression guard)
- Cross-cutting invariant: empty-models recipes declare user_provided_models

Tests: bun test test/ai/ — 128/128 (4 new + 124 prior).

Plan: ~/.claude/plans/ok-lets-turn-this-enumerated-sonnet.md (commit 9 of 11).
#765 (Hunyuan PGLite + CJK keyword fallback) deferred to TODOS.md
follow-up; the CJK extraction (~150 lines + scoring logic + tests) is
larger than the wave's adjacent-fix lane should carry. Closes that PR
with a deferral note.

Co-Authored-By: alexandreroumieu-codeapprentice <noreply@github.com>
Co-Authored-By: vinsew <noreply@github.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/cli.ts

@@ -1116,6 +1116,15 @@ async function handleCliOnly(command: string, args: string[]) {
 // but not the other previously required remembering to mirror the change;
 // the helper makes that structural.
 function buildGatewayConfig(c: GBrainConfig): AIGatewayConfig {
+  // v0.32 (#121 reworked): when ~/.gbrain/config.json declares
+  // openai_api_key / anthropic_api_key, fold them into the gateway env so
+  // recipes that read OPENAI_API_KEY / ANTHROPIC_API_KEY find them. Process
+  // env still wins (it's loaded last) — this is a fallback for daemons /
+  // launchd-spawned subprocesses that don't propagate ~/.zshrc-sourced keys.
+  const envFromConfig: Record<string, string> = {};
+  if (c.openai_api_key) envFromConfig.OPENAI_API_KEY = c.openai_api_key;
+  if (c.anthropic_api_key) envFromConfig.ANTHROPIC_API_KEY = c.anthropic_api_key;
+
   return {
     embedding_model: c.embedding_model,
     embedding_dimensions: c.embedding_dimensions,
@@ -1124,7 +1133,7 @@ function buildGatewayConfig(c: GBrainConfig): AIGatewayConfig {
     chat_model: c.chat_model,
     chat_fallback_chain: c.chat_fallback_chain,
     base_urls: c.provider_base_urls,
-    env: { ...process.env },
+    env: { ...envFromConfig, ...process.env }, // process.env wins
   };
 }
 

src/core/ai/gateway.ts

@@ -234,6 +234,10 @@ function warnRecipesMissingBatchTokens(): void {
     // recipe; suppress the warning for it. Every other recipe missing the
     // field is suspicious.
     if (recipe.id === 'openai') continue;
+    // v0.32 (#779): explicit opt-out for dynamic-cap recipes (Ollama,
+    // LiteLLM proxy, llama-server) — they ship without a static cap because
+    // the cap depends on a user-launched server. Warning is noise for them.
+    if (embedding.no_batch_cap === true) continue;
     if (_warnedRecipes.has(recipe.id)) continue;
     _warnedRecipes.add(recipe.id);
     // eslint-disable-next-line no-console

src/core/ai/recipes/litellm-proxy.ts

@@ -23,9 +23,13 @@ export const litellmProxy: Recipe = {
     embedding: {
       // Models depend on the proxy's config; declare empties so wizard prompts user.
       models: [],
+      user_provided_models: true, // v0.32 D8=A wire-through for the litellm hardcode
       default_dims: 0, // user must declare --embedding-dimensions explicitly
       cost_per_1m_tokens_usd: undefined,
       price_last_verified: '2026-04-20',
+      // LiteLLM's batch capacity is determined by the backend it proxies;
+      // no static cap to declare here. v0.32 (#779).
+      no_batch_cap: true,
     },
   },
   setup_hint: 'Run LiteLLM (https://docs.litellm.ai) in front of any provider; set LITELLM_BASE_URL + pass --embedding-model litellm:<model> and --embedding-dimensions <N>.',

src/core/ai/recipes/llama-server.ts

@@ -33,7 +33,10 @@ export const llamaServer: Recipe = {
       user_provided_models: true,
       default_dims: 0, // forces explicit --embedding-dimensions
       cost_per_1m_tokens_usd: 0,
-      price_last_verified: '2026-05-09',
+      price_last_verified: '2026-05-10',
+      // llama-server's batch capacity is set by `--ctx-size` at launch
+      // time; no static cap to declare. v0.32 (#779).
+      no_batch_cap: true,
     },
   },
   /**

src/core/ai/recipes/ollama.ts

@@ -17,6 +17,9 @@ export const ollama: Recipe = {
       default_dims: 768, // nomic-embed-text native dim
       cost_per_1m_tokens_usd: 0,
       price_last_verified: '2026-04-20',
+      // Ollama's batch capacity depends on the locally loaded model + the
+      // OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
+      no_batch_cap: true,
     },
   },
   setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',

src/core/ai/types.ts

@@ -86,6 +86,19 @@ export interface EmbeddingTouchpoint {
    *    for shorthand `--model <provider>` and prints a setup hint.
    */
   user_provided_models?: true;
+  /**
+   * v0.32 (#779 reworked): explicit opt-out of the missing-max_batch_tokens
+   * startup warning. Set to `true` for recipes whose batch capacity is
+   * genuinely dynamic (Ollama: depends on user-loaded model; LiteLLM proxy:
+   * depends on backend; llama.cpp: depends on `--ctx-size` at server launch).
+   *
+   * Without this flag, missing `max_batch_tokens` triggers a once-per-process
+   * stderr warning so future recipes that forget the cap (and would
+   * silently rely on recursive-halving) don't ship un-noticed. Recipes that
+   * declare `no_batch_cap: true` are explicitly opting out — the warning is
+   * noise for them.
+   */
+  no_batch_cap?: true;
 }
 
 /**

src/core/config.ts

@@ -144,6 +144,7 @@ export function loadConfig(): GBrainConfig | null {
     engine: inferredEngine,
     ...(dbUrl ? { database_url: dbUrl } : {}),
     ...(process.env.OPENAI_API_KEY ? { openai_api_key: process.env.OPENAI_API_KEY } : {}),
+    ...(process.env.ANTHROPIC_API_KEY ? { anthropic_api_key: process.env.ANTHROPIC_API_KEY } : {}),
     ...(process.env.GBRAIN_EMBEDDING_MODEL ? { embedding_model: process.env.GBRAIN_EMBEDDING_MODEL } : {}),
     ...(process.env.GBRAIN_EMBEDDING_DIMENSIONS ? { embedding_dimensions: parseInt(process.env.GBRAIN_EMBEDDING_DIMENSIONS, 10) } : {}),
     ...(process.env.GBRAIN_EXPANSION_MODEL ? { expansion_model: process.env.GBRAIN_EXPANSION_MODEL } : {}),

test/ai/no-batch-cap-suppression.test.ts

@@ -0,0 +1,79 @@
+/**
+ * #779 + #121 adjacent fixes (Commit 9 of v0.32 wave).
+ *
+ * Coverage:
+ *  - Recipes with `embedding.no_batch_cap: true` suppress the
+ *    missing-max_batch_tokens startup warning (#779)
+ *  - Real-provider recipes without the flag still warn (regression guard)
+ *  - listRecipes returns expected dynamic-cap recipes (ollama, litellm,
+ *    llama-server) all flagged
+ */
+
+import { afterAll, beforeAll, describe, expect, mock, test } from 'bun:test';
+import { configureGateway, resetGateway } from '../../src/core/ai/gateway.ts';
+import { listRecipes, getRecipe } from '../../src/core/ai/recipes/index.ts';
+
+describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warning', () => {
+  let warnSpy: ReturnType<typeof mock>;
+  let realWarn: typeof console.warn;
+
+  beforeAll(() => {
+    realWarn = console.warn;
+    warnSpy = mock(() => {});
+    console.warn = warnSpy as any;
+  });
+
+  afterAll(() => {
+    console.warn = realWarn;
+    resetGateway();
+  });
+
+  test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
+    for (const id of ['ollama', 'litellm', 'llama-server']) {
+      const r = getRecipe(id);
+      expect(r, `${id} not registered`).toBeDefined();
+      expect(
+        r!.touchpoints.embedding?.no_batch_cap,
+        `${id} should declare no_batch_cap: true`,
+      ).toBe(true);
+    }
+  });
+
+  test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
+    warnSpy.mockClear();
+    resetGateway();
+    configureGateway({ env: {} });
+    const messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
+    for (const id of ['ollama', 'litellm', 'llama-server']) {
+      expect(
+        messages.some(m => m.includes(`"${id}"`)),
+        `should NOT warn for ${id}`,
+      ).toBe(false);
+    }
+  });
+
+  test('configureGateway STILL warns for google (real provider, no cap declared)', () => {
+    warnSpy.mockClear();
+    resetGateway();
+    configureGateway({ env: {} });
+    const messages = warnSpy.mock.calls.map(c => String(c[0] ?? ''));
+    expect(
+      messages.some(m => m.includes('"google"') && m.includes('without max_batch_tokens')),
+      'google should warn (it has fixed-cap models)',
+    ).toBe(true);
+  });
+
+  test('every recipe with empty models[] declares user_provided_models OR has openai-fast-path', () => {
+    // Cross-cutting invariant: contracts should not silently disagree.
+    for (const r of listRecipes()) {
+      const e = r.touchpoints.embedding;
+      if (!e) continue;
+      if (e.models.length === 0) {
+        expect(
+          e.user_provided_models === true || r.id === 'litellm',
+          `${r.id} has empty models[] — must declare user_provided_models: true`,
+        ).toBe(true);
+      }
+    }
+  });
+});