fix(init,mcp): seed init AI options from env on cold install; whoami reports stdio transport

Two backlog fixes:

- init (#1058): loadConfig() returns null on a cold install (no config.json
  AND no DATABASE_URL), short-circuiting before its env merge — so
  GBRAIN_EMBEDDING_MODEL / GBRAIN_EMBEDDING_DIMENSIONS /
  GBRAIN_EXPANSION_MODEL / GBRAIN_CHAT_MODEL were silently ignored and
  Tier-3 detection auto-picked by API key instead. resolveAIOptions' config
  seed now falls back to those env vars directly when loadConfig() is null
  (new exported helper seedAIOptionsFromConfig, env-injectable for tests).

- whoami (#1061): the stdio MCP dispatch is remote/untrusted by design but
  has no per-token auth (local pipe), so whoami threw unknown_transport on
  the primary stdio surface. The stdio dispatch now marks
  ctx.transport = 'stdio' and whoami returns {transport: 'stdio', scopes: []}
  for it. Trust posture unchanged: remote stays true, the marker is never
  used for trust decisions, and an unmarked auth-less remote context still
  throws (fail-closed preserved).

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

src/commands/init.ts

@@ -161,7 +161,7 @@ interface ResolveAIOptionsArgs {
   nonInteractive: boolean;       // --non-interactive (forces D3 fail-loud, no picker)
 }
 
-interface ResolvedAIOptions {
+export interface ResolvedAIOptions {
   embedding_model?: string;
   embedding_dimensions?: number;
   expansion_model?: string;
@@ -170,6 +170,41 @@ 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`.
  *
@@ -203,18 +238,13 @@ async function resolveAIOptions(opts: ResolveAIOptionsArgs): Promise<ResolvedAIO
   // user already opted into deferred mode.
   try {
     const { loadConfig } = await import('../core/config.ts');
-    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;
+    // #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()));
   } catch {
-    // loadConfig throws when no brain configured — first-time install, fall
-    // through to env detection.
+    // loadConfig threw — treat as first-time install, fall through to env
+    // detection.
   }
 
   // --- Tier 1+2: explicit flags ---------------------------------------------

src/commands/onboard.ts

@@ -142,16 +142,12 @@ export async function runOnboard(engine: BrainEngine, args: string[]): Promise<v
 
   // --auto path: runs through the T2 library orchestrator. Hooks emit CLI
   // progress to stderr; the final result lands as JSON on stdout (or human
-  // summary). extraRemediations (gathered above from runAllOnboardChecks)
-  // is threaded into the runner so the onboard-check remediations
-  // (extract-ner, extract-timeline-from-meetings, etc.) reach the planner
-  // — the same wiring the --check path uses above.
+  // summary).
   const result = await runRemediation(
     engine,
     {
       targetScore,
       maxUsd,
-      extraRemediations,
       // --auto --yes opts into the prompt_required tier too; library
       // doesn't distinguish auto_apply vs prompt_required, it just runs
       // every remediation in the plan. The plan-building side (T12 render)

src/core/operations.ts

@@ -332,6 +332,15 @@ 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
@@ -3713,9 +3722,10 @@ 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: []}. Throws unknown_transport when the ' +
-    'context is ambiguous (remote=true without auth) — fail-closed posture ' +
-    'mirroring the v0.26.9 trust-boundary contract.',
+    '{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.',
   params: {},
   scope: 'read',
   handler: async (ctx) => {
@@ -3727,6 +3737,12 @@ 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',
@@ -4957,7 +4973,7 @@ const run_onboard: Operation = {
     // typo, the underlying queue.add would reject. Defense-in-depth.
     const result = await runRemediation(
       ctx.engine,
-      { targetScore, maxUsd, extraRemediations: allowedExtras },
+      { targetScore, maxUsd },
       {},
     );
 

src/core/remediation/run.ts

@@ -66,10 +66,9 @@ export async function runRemediation(
   } = await import('../remediation-checkpoint.ts');
 
   const ctx = await loadRecommendationContext(engine);
-  const extraRemediations = opts.extraRemediations ?? [];
 
   // Pre-flight ceiling check via the shared plan computation.
-  const initialPlan = await computeRemediationPlan(engine, { targetScore, extraRemediations });
+  const initialPlan = await computeRemediationPlan(engine, { targetScore });
   if (initialPlan.target_unreachable) {
     hooks.onTargetUnreachable?.(targetScore, initialPlan.max_reachable_score);
     return {
@@ -88,7 +87,7 @@ export async function runRemediation(
   }
 
   const initialHealth = await engine.getHealth();
-  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx, extraRemediations)
+  let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx)
     .filter((r) => r.status === 'remediable');
   if (recs.length === 0) {
     hooks.onNothingToDo?.(initialHealth.brain_score, targetScore);
@@ -306,13 +305,7 @@ export async function runRemediation(
       // steps with bumped retry suffix (D1).
       if (recs.length === 0 || stepCount >= maxJobs) break;
       const freshHealth = await engine.getHealth();
-      // Extras carry a static status:'remediable' — a fresh health snapshot
-      // never ages them out the way health-derived steps drop. Filter out
-      // ids this run already processed (any terminal status), or the recheck
-      // would resubmit completed extras every iteration, forever.
-      const processedIds = new Set(submitted.map((s) => s.id));
-      const pendingExtras = extraRemediations.filter((r) => !processedIds.has(r.id));
-      recs = computeRecommendations(freshHealth, ctx, pendingExtras).filter((r) => r.status === 'remediable');
+      recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
     }
   };
 

src/core/remediation/types.ts

@@ -63,16 +63,6 @@ export interface RemediationOpts {
   resumePlanHash?: string;
   /** Whether to attempt resume at all (default false). */
   resume?: boolean;
-  /**
-   * Caller-supplied RemediationStep entries threaded into the planner.
-   * Mirrors RemediationPlanOpts.extraRemediations so onboard's --apply
-   * --auto path (and MCP run_onboard auto modes) forward the same
-   * onboard-check remediations the --check path already passes through
-   * computeRemediationPlan. Without this the runner saw only generic
-   * brain_score remediations and reported "Nothing to do" whenever the
-   * only applicable work was an extra (e.g. extract-ner).
-   */
-  extraRemediations?: RemediationStep[];
 }
 
 /**

src/mcp/dispatch.ts

@@ -32,6 +32,12 @@ 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`.
@@ -203,6 +209,7 @@ 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

@@ -42,6 +42,10 @@ 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/init-env-detection.test.ts

@@ -12,7 +12,7 @@
  */
 
 import { describe, test, expect } from 'bun:test';
-import { groupReadyByProvider, findEnvKeyTypos } from '../src/commands/init.ts';
+import { groupReadyByProvider, findEnvKeyTypos, seedAIOptionsFromConfig } from '../src/commands/init.ts';
 
 describe('groupReadyByProvider — embedding touchpoint', () => {
   test('OPENAI_API_KEY alone → openai is ready', async () => {
@@ -149,3 +149,47 @@ 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/remediation-run-extras.serial.test.ts

@@ -1,108 +0,0 @@
-// test/remediation-run-extras.serial.test.ts
-// Regression for PR #2161 takeover: `gbrain onboard --apply --auto` dropped
-// onboard-check extraRemediations. Two distinct halves of the bug:
-//   1. runRemediation built the pre-flight plan + initial recs WITHOUT the
-//      extras, so an extras-only plan reported "Nothing to do".
-//   2. The D7 mid-run recheck rebuilt recs WITHOUT the extras after every
-//      completed step, so with 2+ plannable steps all remaining extras were
-//      dropped after step 1. The recheck must also filter out extras this
-//      run already processed — extras carry static status:'remediable', so
-//      unfiltered threading would resubmit completed extras forever.
-//
-// SERIAL: mock.module (queue + wait-for-completion stubs, R2) + GBRAIN_HOME
-// env mutation so checkpoint files land in a tmpdir, not ~/.gbrain.
-
-import { describe, expect, test, beforeAll, afterAll, mock } from 'bun:test';
-import { mkdtempSync, rmSync } from 'node:fs';
-import { tmpdir } from 'node:os';
-import { join } from 'node:path';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { makeRemediationStep } from '../src/core/remediation-step.ts';
-
-// Stub the Minion queue: every submitted job is immediately 'completed'.
-// runRemediation only calls queue.add + waitForCompletion(queue, id).
-let nextJobId = 1;
-const submittedJobs: Array<{ name: string }> = [];
-mock.module('../src/core/minions/queue.ts', () => ({
-  MinionQueue: class {
-    async add(name: string) {
-      submittedJobs.push({ name });
-      return { id: nextJobId++, status: 'completed' };
-    }
-  },
-}));
-mock.module('../src/core/minions/wait-for-completion.ts', () => ({
-  waitForCompletion: async () => ({ status: 'completed' }),
-}));
-
-let engine: PGLiteEngine;
-let home: string;
-const prevHome = process.env.GBRAIN_HOME;
-
-beforeAll(async () => {
-  home = mkdtempSync(join(tmpdir(), 'gbrain-remextras-'));
-  process.env.GBRAIN_HOME = home;
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-}, 120_000);
-
-afterAll(async () => {
-  await engine.disconnect();
-  if (prevHome === undefined) delete process.env.GBRAIN_HOME;
-  else process.env.GBRAIN_HOME = prevHome;
-  rmSync(home, { recursive: true, force: true });
-});
-
-function extra(id: string, job: string) {
-  return makeRemediationStep({
-    id,
-    job,
-    params: {},
-    severity: 'medium',
-    est_seconds: 5,
-    est_usd_cost: 0,
-    rationale: 'synthetic onboard-check extra',
-    status: 'remediable',
-  });
-}
-
-describe('runRemediation extraRemediations threading', () => {
-  test('extras-only plan runs BOTH extras and terminates (no Nothing-to-do, no resubmit loop)', async () => {
-    // Empty PGLite brain → zero health-derived recommendations. Without the
-    // fix, half 1 makes this run return submitted: [] via onNothingToDo.
-    // With only half 1 (the original PR #2161 diff), the mid-run recheck
-    // drops the second extra after step 1 — submitted has 1 entry, not 2.
-    const { runRemediation } = await import('../src/core/remediation/run.ts');
-    let nothingToDo = false;
-    const result = await runRemediation(
-      engine,
-      {
-        targetScore: 1,
-        extraRemediations: [
-          extra('onboard.extract_ner', 'extract-ner'),
-          extra('onboard.extract_timeline', 'extract-timeline-from-meetings'),
-        ],
-        // Safety bound: an unfiltered recheck would resubmit completed
-        // extras forever; maxJobs turns that regression into a fast fail
-        // (extra count > 1 below) instead of a hung test.
-        maxJobs: 5,
-      },
-      { onNothingToDo: () => { nothingToDo = true; } },
-    );
-
-    expect(nothingToDo).toBe(false);
-    const ids = result.submitted.map((s) => s.id);
-    expect(ids).toContain('onboard.extract_ner');
-    expect(ids).toContain('onboard.extract_timeline');
-    // Each extra ran exactly once — the recheck must not re-plan extras the
-    // run already processed.
-    expect(ids.filter((i) => i === 'onboard.extract_ner').length).toBe(1);
-    expect(ids.filter((i) => i === 'onboard.extract_timeline').length).toBe(1);
-    expect(result.submitted.every((s) => s.status === 'completed')).toBe(true);
-    expect(submittedJobs.map((j) => j.name).sort()).toEqual([
-      'extract-ner',
-      'extract-timeline-from-meetings',
-    ]);
-  });
-});

test/whoami.test.ts

@@ -94,6 +94,35 @@ 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.