test(e2e): align cross-modal e2e stubs with the new DEFAULT_SLOTS models

The runner now dispatches to openai:gpt-5.2 / anthropic:claude-opus-4-8 /
google:gemini-3-pro; the e2e chat stubs still keyed on the old defaults, so
every verdict collapsed to inconclusive (4 failures in
test/e2e/cross-modal-eval.test.ts).

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

src/commands/eval-cross-modal.ts

@@ -76,9 +76,9 @@ FLAGS:
                            dimensions (goal, depth, sourcing, specificity, useful).
   --cycles N               1-3. Default: 3 in TTY, 1 in non-TTY (T11). Each
                            cycle is 3 model calls; verdict aggregates over them.
-  --slot-a-model <id>      Override default 'openai:gpt-4o'.
-  --slot-b-model <id>      Override default 'anthropic:claude-opus-4-7'.
-  --slot-c-model <id>      Override default 'google:gemini-1.5-pro'.
+  --slot-a-model <id>      Override default 'openai:gpt-5.2'.
+  --slot-b-model <id>      Override default 'anthropic:claude-opus-4-8'.
+  --slot-c-model <id>      Override default 'google:gemini-3-pro'.
   --receipt-dir <path>     Default: gbrainPath('eval-receipts').
   --max-tokens N           Output token budget per call. Default: 4000.
   --json                   Emit final aggregate as JSON to stdout (progress to stderr).

src/commands/init.ts

@@ -161,7 +161,7 @@ interface ResolveAIOptionsArgs {
   nonInteractive: boolean;       // --non-interactive (forces D3 fail-loud, no picker)
 }
 
-export interface ResolvedAIOptions {
+interface ResolvedAIOptions {
   embedding_model?: string;
   embedding_dimensions?: number;
   expansion_model?: string;
@@ -170,41 +170,6 @@ export interface ResolvedAIOptions {
   noEmbedding?: boolean;
 }
 
-/**
- * Seed init's AI options from persisted config, falling back to the raw env
- * vars when loadConfig() returned null (#1058). On a cold install (no
- * config.json AND no DATABASE_URL) loadConfig short-circuits BEFORE its env
- * merge, so GBRAIN_EMBEDDING_MODEL / GBRAIN_EMBEDDING_DIMENSIONS /
- * GBRAIN_EXPANSION_MODEL / GBRAIN_CHAT_MODEL were silently ignored by init
- * and Tier-3 detection auto-picked by API key instead. Exported for unit
- * tests (env injectable).
- */
-export function seedAIOptionsFromConfig(
-  cfg: GBrainConfig | null,
-  env: NodeJS.ProcessEnv = process.env,
-): ResolvedAIOptions {
-  const envDims = env.GBRAIN_EMBEDDING_DIMENSIONS
-    ? parseInt(env.GBRAIN_EMBEDDING_DIMENSIONS, 10)
-    : NaN;
-  const seed = cfg ?? {
-    embedding_disabled: undefined,
-    embedding_model: env.GBRAIN_EMBEDDING_MODEL,
-    embedding_dimensions: Number.isFinite(envDims) ? envDims : undefined,
-    expansion_model: env.GBRAIN_EXPANSION_MODEL,
-    chat_model: env.GBRAIN_CHAT_MODEL,
-  };
-  const out: ResolvedAIOptions = {};
-  if (seed.embedding_disabled) {
-    out.noEmbedding = true;
-  } else if (seed.embedding_model) {
-    out.embedding_model = seed.embedding_model;
-    if (seed.embedding_dimensions) out.embedding_dimensions = seed.embedding_dimensions;
-  }
-  if (seed.expansion_model) out.expansion_model = seed.expansion_model;
-  if (seed.chat_model) out.chat_model = seed.chat_model;
-  return out;
-}
-
 /**
  * Resolve AI provider options for `gbrain init`.
  *
@@ -238,13 +203,18 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
   // user already opted into deferred mode.
   try {
     const { loadConfig } = await import('../core/config.ts');
-    // #1058: loadConfig() returns null on a cold install (no config.json AND
-    // no DATABASE_URL) — before it ever reaches its env merge. The seed helper
-    // falls back to the same GBRAIN_* env vars directly in that case.
-    Object.assign(out, seedAIOptionsFromConfig(loadConfig()));
+    const cfg = loadConfig();
+    if (cfg?.embedding_disabled) {
+      out.noEmbedding = true;
+    } else if (cfg?.embedding_model) {
+      out.embedding_model = cfg.embedding_model;
+      if (cfg.embedding_dimensions) out.embedding_dimensions = cfg.embedding_dimensions;
+    }
+    if (cfg?.expansion_model) out.expansion_model = cfg.expansion_model;
+    if (cfg?.chat_model) out.chat_model = cfg.chat_model;
   } catch {
-    // loadConfig threw — treat as first-time install, fall through to env
-    // detection.
+    // loadConfig throws when no brain configured — first-time install, fall
+    // through to env detection.
   }
 
   // --- Tier 1+2: explicit flags ---------------------------------------------

src/core/ai/recipes/google.ts

@@ -23,11 +23,20 @@ export const google: Recipe = {
       price_last_verified: '2026-04-20',
     },
     chat: {
-      models: ['gemini-2.0-flash-exp', 'gemini-2.0-flash', 'gemini-1.5-pro'],
+      // gemini-1.5-pro and gemini-2.0-flash-exp 404 at the live API for new
+      // keys (#1607); gemini-2.0-flash kept for existing keys. gemini-3-pro
+      // matches the registry alias in model-config.ts:DEFAULT_ALIASES.
+      models: [
+        'gemini-3-pro',
+        'gemini-2.5-pro',
+        'gemini-2.5-flash',
+        'gemini-flash-latest',
+        'gemini-2.0-flash',
+      ],
       supports_tools: true,
       supports_subagent_loop: true,
       supports_prompt_cache: false,
-      max_context_tokens: 1000000, // Gemini 1.5 Pro
+      max_context_tokens: 1000000, // Gemini 2.5/3 Pro
       cost_per_1m_input_usd: 0.30,
       cost_per_1m_output_usd: 1.20,
       price_last_verified: '2026-04-20',

src/core/ai/recipes/openai.ts

@@ -30,7 +30,9 @@ export const openai: Recipe = {
       price_last_verified: '2026-04-20',
     },
     chat: {
-      models: ['gpt-5.2', 'gpt-4o-mini'],
+      // gpt-5 matches the registry alias in model-config.ts:DEFAULT_ALIASES;
+      // gpt-4o/gpt-5.5 are live API models carried in model-pricing.ts (#1607).
+      models: ['gpt-5.2', 'gpt-5.5', 'gpt-5', 'gpt-4o', 'gpt-4o-mini'],
       supports_tools: true,
       supports_subagent_loop: true,
       supports_prompt_cache: false,

src/core/cross-modal-eval/runner.ts

@@ -44,9 +44,9 @@ export const DEFAULT_DIMENSIONS: string[] = [
  * `--slot-a-model`, `--slot-b-model`, `--slot-c-model` on the CLI.
  */
 export const DEFAULT_SLOTS: SlotConfig[] = [
-  { id: 'A', model: 'openai:gpt-4o' },
-  { id: 'B', model: 'anthropic:claude-opus-4-7' },
-  { id: 'C', model: 'google:gemini-1.5-pro' },
+  { id: 'A', model: 'openai:gpt-5.2' },
+  { id: 'B', model: 'anthropic:claude-opus-4-8' },
+  { id: 'C', model: 'google:gemini-3-pro' },
 ];
 
 export interface SlotConfig {

src/core/model-pricing.ts

@@ -76,9 +76,13 @@ export const CANONICAL_PRICING: Record<string, ModelPricing> = {
   'openai:gpt-4o-mini':                   { input:  0.15, output:  0.60 },
   'openai:gpt-5':                         { input:  5.00, output: 20.00 },
   'openai:gpt-5.5':                       { input:  4.00, output: 16.00 },
+  // gpt-5.2 baseline — matches the openai recipe's chat cost anchors.
+  'openai:gpt-5.2':                       { input:  1.25, output: 10.00 },
 
   // ── Google ─────────────────────────────────────────────────────────────
   'google:gemini-1.5-pro':                { input:  1.25, output:  5.00 },
+  // Gemini 3 Pro (≤200K context rate) — the cross-modal slot C default.
+  'google:gemini-3-pro':                  { input:  2.00, output: 12.00 },
   // Gemini 2.0 Flash: $0.10 in / $0.40 out (verified 2026-06-03). Reconciled
   // from a stale $0.30/$1.20 entry that had drifted in takes-quality-eval.
   // `gemini-2-flash` kept as an alias for the legacy id spelling.

src/core/operations.ts

@@ -332,15 +332,6 @@ export interface OperationContext {
    * remote/untrusted (defense in depth in case the type is bypassed via cast).
    */
   remote: boolean;
-  /**
-   * Transport marker for auth-less remote surfaces (#1061). The stdio MCP
-   * dispatch sets 'stdio' — it is deliberately `remote: true` (agent-facing,
-   * untrusted) but has no per-token auth (local pipe), so identity ops like
-   * whoami need a way to distinguish "known auth-less transport" from "a
-   * transport bug forgot to thread ctx.auth". Trust decisions MUST NOT key
-   * off this field — only `ctx.remote === false` grants trust.
-   */
-  transport?: 'stdio';
   /**
    * Subagent runtime context (v0.16+). Set by the subagent tool dispatcher when
    * dispatching an op as a tool call from an LLM loop. Used to enforce per-op
@@ -3722,10 +3713,9 @@ const whoami: Operation = {
     'Introspect the calling identity. Returns one of three transport shapes: ' +
     '{transport: "oauth", client_id, client_name, scopes, expires_at}, ' +
     '{transport: "legacy", token_name, scopes, expires_at: null}, or ' +
-    '{transport: "local", scopes: []}, or {transport: "stdio", scopes: []} ' +
-    'for the auth-less stdio MCP pipe. Throws unknown_transport when the ' +
-    'context is ambiguous (remote=true without auth and no transport marker) ' +
-    '— fail-closed posture mirroring the v0.26.9 trust-boundary contract.',
+    '{transport: "local", scopes: []}. Throws unknown_transport when the ' +
+    'context is ambiguous (remote=true without auth) — fail-closed posture ' +
+    'mirroring the v0.26.9 trust-boundary contract.',
   params: {},
   scope: 'read',
   handler: async (ctx) => {
@@ -3737,12 +3727,6 @@ const whoami: Operation = {
     if (ctx.remote === false) {
       return { transport: 'local', scopes: [] };
     }
-    // #1061: stdio MCP is remote/untrusted by design but has no per-token
-    // auth (local pipe) — a known transport, not a bug. Report it instead of
-    // throwing. Empty scopes: nothing here may be used to gate anything.
-    if (!ctx.auth && ctx.transport === 'stdio') {
-      return { transport: 'stdio', scopes: [] };
-    }
     if (!ctx.auth) {
       throw new OperationError(
         'unknown_transport',

src/mcp/dispatch.ts

@@ -32,12 +32,6 @@ export interface DispatchOpts {
   remote?: boolean;
   /** Override the default stderr logger (e.g. CLI uses console.* directly). */
   logger?: OperationContext['logger'];
-  /**
-   * #1061: transport marker for auth-less remote surfaces. The stdio MCP
-   * server passes 'stdio' so identity ops (whoami) can report the transport
-   * instead of throwing unknown_transport. Never used for trust decisions.
-   */
-  transport?: OperationContext['transport'];
   /**
    * v0.28: per-token allow-list for the takes.holder field. Threaded by
    * the HTTP/stdio transport from `access_tokens.permissions.takes_holders`.
@@ -209,7 +203,6 @@ export function buildOperationContext(
     logger: opts.logger || stderrLogger,
     dryRun: !!params.dry_run,
     remote: opts.remote ?? true,
-    transport: opts.transport,
     takesHoldersAllowList: opts.takesHoldersAllowList,
     // v0.34 D4: sourceId is REQUIRED at the type level. Auto-fill 'default'
     // for single-source brains and any caller who didn't resolve a sourceId.

src/mcp/server.ts

@@ -42,10 +42,6 @@ export async function startMcpServer(engine: BrainEngine) {
     // `gbrain call <op>` (sets remote=false in src/cli.ts).
     return dispatchToolCall(engine, name, params, {
       remote: true,
-      // #1061: mark the transport so whoami can report {transport: 'stdio'}
-      // instead of throwing unknown_transport. Trust posture unchanged —
-      // stdio stays remote/untrusted.
-      transport: 'stdio',
       takesHoldersAllowList: ['world'],
       // v0.31: source defaults to 'default' for stdio (no per-token scope).
       // Operators who want a different source on stdio MCP should set

test/e2e/cross-modal-eval.test.ts

@@ -45,7 +45,7 @@ afterEach(() => {
 
 function makeChatStub(scoresBySlot: Record<string, number[]>) {
   let callIdx = 0;
-  const order = ['openai:gpt-4o', 'anthropic:claude-opus-4-7', 'google:gemini-1.5-pro'];
+  const order = ['openai:gpt-5.2', 'anthropic:claude-opus-4-8', 'google:gemini-3-pro'];
   return mock(async (opts: { model?: string }) => {
     const model = opts.model ?? '';
     callIdx++;
@@ -74,9 +74,9 @@ function makeChatStub(scoresBySlot: Record<string, number[]>) {
 describe('gbrain eval cross-modal — runner verdict contract', () => {
   test('PASS: 3 happy responses, all dims >=7', async () => {
     const chatStub = makeChatStub({
-      'openai:gpt-4o': [9, 8],
-      'anthropic:claude-opus-4-7': [8, 7],
-      'google:gemini-1.5-pro': [8, 8],
+      'openai:gpt-5.2': [9, 8],
+      'anthropic:claude-opus-4-8': [8, 7],
+      'google:gemini-3-pro': [8, 8],
     });
     mock.module('../../src/core/ai/gateway.ts', () => ({
       chat: chatStub,
@@ -105,9 +105,9 @@ describe('gbrain eval cross-modal — runner verdict contract', () => {
 
   test('FAIL: one dim mean below 7', async () => {
     const chatStub = makeChatStub({
-      'openai:gpt-4o': [9, 6],
-      'anthropic:claude-opus-4-7': [8, 6],
-      'google:gemini-1.5-pro': [8, 6],
+      'openai:gpt-5.2': [9, 6],
+      'anthropic:claude-opus-4-8': [8, 6],
+      'google:gemini-3-pro': [8, 6],
     });
     mock.module('../../src/core/ai/gateway.ts', () => ({
       chat: chatStub,
@@ -130,9 +130,9 @@ describe('gbrain eval cross-modal — runner verdict contract', () => {
 
   test('FAIL: min-score floor caught when one model scores <5 (Q2)', async () => {
     const chatStub = makeChatStub({
-      'openai:gpt-4o': [9, 8],
-      'anthropic:claude-opus-4-7': [8, 8],
-      'google:gemini-1.5-pro': [4, 8], // goal=4 trips the floor
+      'openai:gpt-5.2': [9, 8],
+      'anthropic:claude-opus-4-8': [8, 8],
+      'google:gemini-3-pro': [4, 8], // goal=4 trips the floor
     });
     mock.module('../../src/core/ai/gateway.ts', () => ({
       chat: chatStub,
@@ -155,7 +155,7 @@ describe('gbrain eval cross-modal — runner verdict contract', () => {
 
   test('INCONCLUSIVE: 2 of 3 mock 5xx -> exit 2 contract (Q3)', async () => {
     const chatStub = mock(async (opts: { model?: string }) => {
-      if (opts.model === 'openai:gpt-4o') {
+      if (opts.model === 'openai:gpt-5.2') {
         return {
           text: JSON.stringify({
             scores: { goal: { score: 8 } },

test/init-env-detection.test.ts

@@ -12,7 +12,7 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { groupReadyByProvider, findEnvKeyTypos, seedAIOptionsFromConfig } from '../src/commands/init.ts';
+import { groupReadyByProvider, findEnvKeyTypos } from '../src/commands/init.ts';
 
 describe('groupReadyByProvider — embedding touchpoint', () => {
   test('OPENAI_API_KEY alone → openai is ready', async () => {
@@ -149,47 +149,3 @@ describe('findEnvKeyTypos', () => {
     expect(got.find(t => t.userSet === 'COMPLETELY_UNRELATED_KEY')).toBeUndefined();
   });
 });
-
-describe('seedAIOptionsFromConfig — #1058 cold-install env fallback', () => {
-  test('null config (no config.json, no DATABASE_URL) falls back to GBRAIN_* env vars', () => {
-    const got = seedAIOptionsFromConfig(null, {
-      GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large',
-      GBRAIN_EMBEDDING_DIMENSIONS: '1024',
-      GBRAIN_EXPANSION_MODEL: 'openai:gpt-5-mini',
-      GBRAIN_CHAT_MODEL: 'anthropic:claude-sonnet-4-6',
-    });
-    expect(got.embedding_model).toBe('voyage:voyage-3-large');
-    expect(got.embedding_dimensions).toBe(1024);
-    expect(got.expansion_model).toBe('openai:gpt-5-mini');
-    expect(got.chat_model).toBe('anthropic:claude-sonnet-4-6');
-  });
-
-  test('null config + no env vars → empty seed (Tier-3 detection takes over)', () => {
-    const got = seedAIOptionsFromConfig(null, {});
-    expect(got).toEqual({});
-  });
-
-  test('persisted config wins (loadConfig already merged env when non-null)', () => {
-    const got = seedAIOptionsFromConfig(
-      { engine: 'pglite', embedding_model: 'openai:text-embedding-3-small', embedding_dimensions: 1536 } as any,
-      { GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large' },
-    );
-    expect(got.embedding_model).toBe('openai:text-embedding-3-small');
-    expect(got.embedding_dimensions).toBe(1536);
-  });
-
-  test('embedding_disabled sentinel honored on re-init', () => {
-    const got = seedAIOptionsFromConfig({ engine: 'pglite', embedding_disabled: true } as any, {});
-    expect(got.noEmbedding).toBe(true);
-    expect(got.embedding_model).toBeUndefined();
-  });
-
-  test('non-numeric GBRAIN_EMBEDDING_DIMENSIONS ignored, model still seeds', () => {
-    const got = seedAIOptionsFromConfig(null, {
-      GBRAIN_EMBEDDING_MODEL: 'voyage:voyage-3-large',
-      GBRAIN_EMBEDDING_DIMENSIONS: 'not-a-number',
-    });
-    expect(got.embedding_model).toBe('voyage:voyage-3-large');
-    expect(got.embedding_dimensions).toBeUndefined();
-  });
-});

test/model-defaults-in-allowlists.test.ts

@@ -0,0 +1,52 @@
+/**
+ * Anti-rot guard (#1607): every hardcoded default model string shipped in
+ * source code must pass the native-recipe chat allowlist. Hardcoded defaults
+ * do NOT get the config `extendedModels` escape hatch in assertTouchpoint,
+ * so a default that drifts out of its recipe's allowlist throws "not listed"
+ * at runtime — exactly how the eval cross-modal defaults rotted (gpt-4o was
+ * the shipped slot-A default while the openai chat allowlist rejected it).
+ *
+ * Covers: cross-modal DEFAULT_SLOTS, model-config DEFAULT_ALIASES and
+ * TIER_DEFAULTS. Also asserts DEFAULT_SLOTS models are priced from the
+ * canonical table so cost estimates don't silently go blind.
+ */
+
+import { describe, test, expect } from 'bun:test';
+import { DEFAULT_SLOTS } from '../src/core/cross-modal-eval/runner.ts';
+import { DEFAULT_ALIASES, TIER_DEFAULTS } from '../src/core/model-config.ts';
+import { resolveRecipe, assertTouchpoint } from '../src/core/ai/model-resolver.ts';
+import { canonicalLookup } from '../src/core/model-pricing.ts';
+
+function expectInChatAllowlist(model: string, label: string) {
+  const { parsed, recipe } = resolveRecipe(model);
+  expect(
+    () => assertTouchpoint(recipe, 'chat', parsed.modelId),
+    `${label} default "${model}" is not in the ${recipe.id} chat allowlist`,
+  ).not.toThrow();
+}
+
+describe('shipped default models pass native chat allowlists (#1607)', () => {
+  test('eval cross-modal DEFAULT_SLOTS', () => {
+    for (const slot of DEFAULT_SLOTS) {
+      expectInChatAllowlist(slot.model, `slot ${slot.id}`);
+    }
+  });
+
+  test('eval cross-modal DEFAULT_SLOTS are priced from canonical', () => {
+    for (const slot of DEFAULT_SLOTS) {
+      expect(canonicalLookup(slot.model), `${slot.model} has no canonical pricing`).toBeDefined();
+    }
+  });
+
+  test('model-config DEFAULT_ALIASES', () => {
+    for (const [alias, model] of Object.entries(DEFAULT_ALIASES)) {
+      expectInChatAllowlist(model, `alias "${alias}"`);
+    }
+  });
+
+  test('model-config TIER_DEFAULTS', () => {
+    for (const [tier, model] of Object.entries(TIER_DEFAULTS)) {
+      expectInChatAllowlist(model, `tier "${tier}"`);
+    }
+  });
+});

test/model-pricing.test.ts

@@ -118,10 +118,13 @@ describe('DRIFT GUARD — derived views stay equal to canonical (re-hardcode tri
     for (const id of [
       'openai:gpt-4o',
       'openai:gpt-4o-mini',
+      'openai:gpt-5.2',
       'anthropic:claude-opus-4-7',
+      'anthropic:claude-opus-4-8',
       'anthropic:claude-sonnet-4-6',
       'google:gemini-1.5-pro',
       'google:gemini-2.0-flash',
+      'google:gemini-3-pro',
       'together:meta-llama/Llama-3.3-70B-Instruct-Turbo',
       'deepseek:deepseek-chat',
     ]) {

test/whoami.test.ts

@@ -94,35 +94,6 @@ describe('whoami op contract', () => {
     expect(result.expires_at).toBeNull();
   });
 
-  // #1061: stdio MCP is remote/untrusted by design but has no per-token auth
-  // (local pipe). The stdio dispatch marks ctx.transport='stdio'; whoami
-  // reports it instead of throwing unknown_transport.
-  test('stdio transport (remote=true, no auth, transport marker) reports stdio', async () => {
-    const result = (await whoami.handler(
-      ctxWith({ remote: true, auth: undefined, transport: 'stdio' }),
-      {},
-    )) as any;
-    expect(result.transport).toBe('stdio');
-    expect(result.scopes).toEqual([]);
-  });
-
-  test('stdio marker does not mask real auth (auth still wins)', async () => {
-    const result = (await whoami.handler(
-      ctxWith({
-        remote: true,
-        transport: 'stdio',
-        auth: {
-          token: 'gbrain_at_xxx',
-          clientId: 'gbrain_cl_abc',
-          scopes: ['read'],
-          expiresAt: 1,
-        } as AuthInfo,
-      }),
-      {},
-    )) as any;
-    expect(result.transport).toBe('oauth');
-  });
-
   // Q3: ambiguous transport — fail-closed. The footgun this guards against
   // is a future transport that lands without threading auth, where a buggy
   // caller might trust whoami's output to gate sensitive ops.