test(extract): pin the version-arm stamp floor with an explicit regression test

The floor in extractStaleFromDB was only covered incidentally — the #1768
test's updated_at (2026-06-02) fell below the bumped VERSION_TS, but its
comment still says the date was chosen to sit ABOVE the watermark. A future
date 'repair' there would silently drop floor coverage. This test pins it
directly: pre-watermark page clears after --stale and stays cleared.
Verified fail-without-fix against master's extract.ts.

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

src/commands/extract.ts

@@ -1743,7 +1743,15 @@ async function extractStaleFromDB(
       // `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
       // µs-precision DB updated_at stayed strictly greater and the page never
       // cleared on Postgres. Stamping the exact value makes them equal.
-      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
+      //
+      // Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
+      // would otherwise be stamped below the version watermark and stay
+      // permanently stale (`links_extracted_at < versionTs` re-fires every run).
+      // Stamp max(updated_at, versionTs) — versionTs is always a past release
+      // date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
+      // Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
+      const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
+      processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
     }
 
     // Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so

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/link-extraction.ts

@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
  * OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
  * the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
  */
-export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
+export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
 
 // ─── Entity references ──────────────────────────────────────────
 
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
  * Directory prefix whitelist. These are the top-level slug dirs the extractor
  * recognizes as entity references. Upstream canonical + our extensions:
  *   - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
- *   - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
+ *   - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
  *   - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
  */
-const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
+const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
 
 /**
  * Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,7 +865,16 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
   if (!name || typeof name !== 'string') return [];
   const trimmed = name.trim();
   if (!trimmed) return [];
-  const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
+  let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
+  // Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
+  // outside DIR_PATTERN reach here, but normalizeBasename strips slashes
+  // into a garbage key (`runbooks2026-05-01-x`) that can never hit the
+  // tail-keyed index. Fall back to the path tail so qualified refs resolve
+  // by basename like everything else.
+  if (!hit && trimmed.includes('/')) {
+    const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
+    if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
+  }
   return hit ? [...hit].sort(basenameSort) : [];
 }
 

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/extract-stale.test.ts

@@ -209,6 +209,24 @@ describe('gbrain extract --stale', () => {
     expect(usRows[0]?.eq).toBe(true);
   });
 
+  test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
+    // A page whose updated_at predates the version watermark used to be
+    // stamped at its updated_at (< versionTs), so the version arm re-fired
+    // every run — permanently stale. The sweep now floors the stamp at
+    // versionTs. (The #1768 test above also covers this since the v0.42.x
+    // VERSION_TS bump moved its date below the watermark, but this pins the
+    // behavior explicitly so a date "repair" there can't drop coverage.)
+    await engine.putPage('people/alice', personPage('Alice'));
+    await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
+    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
+
+    await runExtract(engine, ['--stale']);
+    // Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
+    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
+    await runExtract(engine, ['--stale']);
+    expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
+  });
+
   test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
     await engine.putPage('people/alice', personPage('Alice'));
     await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));

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/link-extraction.test.ts

@@ -140,6 +140,15 @@ describe('extractEntityRefs', () => {
     expect(wikiRefs[0].needsResolution).toBe(true);
   });
 
+  test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
+    // `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
+    // the generic 2c pass (needsResolution) instead of being a real ref.
+    const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
+    expect(refs.length).toBe(1);
+    expect(refs[0].slug).toBe('ops/services/pointer-agent');
+    expect(refs[0].needsResolution).toBeUndefined();
+  });
+
   test('skips qualified-syntax tokens (those belong to 2a)', () => {
     // [[wiki:topics/ai]] looks like 2a's qualified shape — even though
     // it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1069,6 +1078,15 @@ describe('makeResolver — fallback chain', () => {
     ]);
   });
 
+  test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
+    // normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
+    // used to normalize to a garbage key that never hit the tail-keyed index.
+    const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
+    const r = makeResolver(engine);
+    expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
+      .toEqual(['ops/changes/2026-05-01-pointer-agent']);
+  });
+
   test('resolveBasenameMatches: case-insensitive fallback', async () => {
     const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
     const r = makeResolver(engine);

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.