fix(brainstorm): price cost preview against the configured chat model + models.brainstorm.judge config key

Takeover of PR #1855 by @starm2010, shrunk to the brainstorm-only
portion (the cycle-phase hunks are superseded by the resolveModel-in-
phase approach already on master). The cost preview + hard cost ceiling
previously always priced anthropic:claude-sonnet-4-6 even when the
configured chat_model (which the gateway actually runs) was something
else; modelStr now resolves override → config.chat_model → fallback.
The judge phase honors a new models.brainstorm.judge config key when no
--judge-model flag is passed, resolved in the orchestrator so every
caller (brainstorm, lsd, eval-brainstorm) benefits.

Co-authored-by: starm2010 <starm2010@users.noreply.github.com>

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

src/core/brainstorm/orchestrator.ts

@@ -485,9 +485,44 @@ const DEFAULT_PARALLELISM = 4;
  * src/core/errors.ts (the v0.19.0 envelope every new agent-facing
  * surface uses) rather than introducing a new BrainstormError class.
  */
+/** File-config slice the orchestrator reads (see loadConfig in core/config.ts). */
+export interface BrainstormRunConfig {
+  embedding_model?: string;
+  chat_model?: string;
+  emotional_weight?: { user_holder?: string };
+}
+
+/**
+ * Model used for the cost preview + hard cost ceiling. Mirrors what the
+ * gateway will actually run: explicit --model override, else the configured
+ * chat_model (gateway default), else the hardcoded gateway fallback. Before
+ * this resolved through config, a non-Sonnet chat_model got its preview
+ * priced against the wrong model. (Takeover of PR #1855 by @starm2010.)
+ */
+export function resolveBrainstormChatModel(
+  config: { chat_model?: string },
+  modelOverride?: string,
+): string {
+  return modelOverride ?? config.chat_model ?? 'anthropic:claude-sonnet-4-6';
+}
+
+/**
+ * Judge-phase model precedence: --judge-model flag, else the
+ * `models.brainstorm.judge` config key, else undefined (falls back to
+ * `modelOverride` then the gateway default at the runJudge callsite).
+ */
+export async function resolveBrainstormJudgeModel(
+  engine: BrainEngine,
+  judgeModelFlag?: string,
+): Promise<string | undefined> {
+  if (judgeModelFlag) return judgeModelFlag;
+  const configured = await engine.getConfig('models.brainstorm.judge');
+  return configured ?? undefined;
+}
+
 export async function runBrainstorm(
   engine: BrainEngine,
-  config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
+  config: BrainstormRunConfig,
   opts: BrainstormOptions
 ): Promise<BrainstormResult> {
   // v0.39.3.0 (Phase 5, CV11+T4): outer try/catch around the orchestrator
@@ -509,7 +544,7 @@ export async function runBrainstorm(
 
 async function runBrainstormImpl(
   engine: BrainEngine,
-  config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
+  config: BrainstormRunConfig,
   opts: BrainstormOptions,
 ): Promise<BrainstormResult> {
   // v0.39.0.0 T10: install a gateway-layer BudgetTracker scope around the
@@ -529,7 +564,7 @@ async function runBrainstormImpl(
 
 async function _runBrainstormInner(
   engine: BrainEngine,
-  config: { embedding_model?: string; emotional_weight?: { user_holder?: string } },
+  config: BrainstormRunConfig,
   opts: BrainstormOptions,
 ): Promise<BrainstormResult> {
   const profile = opts.profile ?? BRAINSTORM_PROFILE;
@@ -538,7 +573,7 @@ async function _runBrainstormInner(
   const embedFn = opts.embedQueryFn ?? embedQuery;
 
   // ---- Phase 0: cost preview + TTY grace ----
-  const modelStr = opts.modelOverride ?? 'anthropic:claude-sonnet-4-6';
+  const modelStr = resolveBrainstormChatModel(config, opts.modelOverride);
   const { aborted, estimate } = await previewCostAndWait({
     profile,
     model: modelStr,
@@ -847,7 +882,7 @@ async function _runBrainstormInner(
       far_slug: i.far_slug,
     }));
     const judgeResult = await runJudge(profile.judge_config, judgeInput, {
-      modelOverride: opts.judgeModel ?? opts.modelOverride,
+      modelOverride: (await resolveBrainstormJudgeModel(engine, opts.judgeModel)) ?? opts.modelOverride,
       chatFn: opts.chatFn,
       activeBiasTags: activeBiasTags ?? undefined,
       abortSignal: opts.abortSignal,

src/core/config.ts

@@ -904,6 +904,7 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   'models.subagent',
   'models.expansion',
   'models.chat',
+  'models.brainstorm.judge',
   'models.eval.longmemeval',
   'facts.extraction_model',
   // #2113: output-token cap for the per-turn facts extractor (default 4000).

test/brainstorm/model-config.test.ts

@@ -0,0 +1,65 @@
+/**
+ * Brainstorm model configurability (takeover of PR #1855 by @starm2010).
+ *
+ * - The cost preview + hard cost ceiling price the model that will actually
+ *   run: --model override → configured chat_model → gateway fallback. Before
+ *   this, the preview always priced anthropic:claude-sonnet-4-6 even when
+ *   the configured chat_model was something else.
+ * - The judge phase honors the `models.brainstorm.judge` config key when no
+ *   --judge-model flag is passed.
+ */
+
+import { describe, test, expect } from 'bun:test';
+import {
+  resolveBrainstormChatModel,
+  resolveBrainstormJudgeModel,
+} from '../../src/core/brainstorm/orchestrator.ts';
+import type { BrainEngine } from '../../src/core/engine.ts';
+
+function mockEngine(configValues: Record<string, string>): { engine: BrainEngine; reads: string[] } {
+  const reads: string[] = [];
+  const engine = {
+    async getConfig(key: string): Promise<string | null> {
+      reads.push(key);
+      return configValues[key] ?? null;
+    },
+  } as unknown as BrainEngine;
+  return { engine, reads };
+}
+
+describe('resolveBrainstormChatModel', () => {
+  test('--model override wins over config', () => {
+    expect(resolveBrainstormChatModel({ chat_model: 'openai:gpt-5' }, 'anthropic:claude-opus-4-6'))
+      .toBe('anthropic:claude-opus-4-6');
+  });
+
+  test('configured chat_model wins over the hardcoded fallback', () => {
+    expect(resolveBrainstormChatModel({ chat_model: 'openai:gpt-5' }))
+      .toBe('openai:gpt-5');
+  });
+
+  test('falls back to the gateway default model when nothing is configured', () => {
+    expect(resolveBrainstormChatModel({})).toBe('anthropic:claude-sonnet-4-6');
+  });
+});
+
+describe('resolveBrainstormJudgeModel', () => {
+  test('--judge-model flag wins without touching config', async () => {
+    const { engine, reads } = mockEngine({ 'models.brainstorm.judge': 'openai:gpt-5' });
+    const out = await resolveBrainstormJudgeModel(engine, 'anthropic:claude-opus-4-6');
+    expect(out).toBe('anthropic:claude-opus-4-6');
+    expect(reads).toHaveLength(0);
+  });
+
+  test('models.brainstorm.judge config key is honored when no flag is passed', async () => {
+    const { engine, reads } = mockEngine({ 'models.brainstorm.judge': 'openai:gpt-5' });
+    const out = await resolveBrainstormJudgeModel(engine);
+    expect(out).toBe('openai:gpt-5');
+    expect(reads).toEqual(['models.brainstorm.judge']);
+  });
+
+  test('returns undefined (defer to modelOverride / gateway default) when unset', async () => {
+    const { engine } = mockEngine({});
+    expect(await resolveBrainstormJudgeModel(engine)).toBeUndefined();
+  });
+});