fix(dream): deterministic last-writer attribution for colliding slugs

collectChildPutPageSlugs paired each slug to a jobId first-seen over an
unordered result set. When two children collide on a final slug, the pages
row holds the LAST put_page write, so the provenance stamp
(transcript_id/transcript_source/date) could attribute an arbitrary other
transcript. ORDER BY id + last-writer-wins aligns the stamp with the
surviving content; pinned by a collision test.

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

src/commands/calibration.ts

@@ -19,7 +19,7 @@
  */
 
 import type { BrainEngine } from '../core/engine.ts';
-import { resolveCalibrationHolder, runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
+import { runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
 import { sourceScopeOpts, type OperationContext } from '../core/operations.ts';
 import type { GBrainConfig } from '../core/config.ts';
 import { GBrainError } from '../core/types.ts';
@@ -167,7 +167,7 @@ export async function runCalibration(
   config: GBrainConfig,
 ): Promise<void> {
   const { opts } = parseArgs(args);
-  const holder = await resolveCalibrationHolder(engine, opts.holder);
+  const holder = opts.holder ?? 'garry';
   // Resolve --source / GBRAIN_SOURCE / .gbrain-source so the (now reachable, #2035)
   // calibration command targets the right source in a multi-source brain instead
   // of always reading `default`. No signal → 'default' (prior behavior).
@@ -253,14 +253,14 @@ export async function getCalibrationProfileOp(
   ctx: OperationContext,
   params: { holder?: string },
 ): Promise<CalibrationProfileRow | null> {
-  if (params.holder !== undefined && (typeof params.holder !== 'string' || params.holder.length === 0)) {
+  const holder = params.holder ?? 'garry';
+  if (typeof holder !== 'string' || holder.length === 0) {
     throw new GBrainError(
       'INVALID_HOLDER',
       'get_calibration_profile.holder must be a non-empty string',
-      'pass holder="<slug>" or omit to default to the calibration.user_holder config (then "garry")',
+      'pass holder="<slug>" or omit to default to "garry"',
     );
   }
-  const holder = await resolveCalibrationHolder(ctx.engine, params.holder);
   const scope = sourceScopeOpts(ctx);
   return getLatestProfile(ctx.engine, { holder, ...scope });
 }

src/core/config.ts

@@ -928,10 +928,6 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
   // Emotional weight (v0.29)
   'emotional_weight.high_tags',
   'emotional_weight.user_holder',
-  // Calibration holder (#1726): persistent default for the nightly
-  // calibration_profile phase + `gbrain calibration`, symmetric with
-  // emotional_weight.user_holder. Falls back to 'garry' when unset.
-  'calibration.user_holder',
   // Cycle phase config
   'cycle.grade_takes.write_gstack_learnings',
   // Content sanity (v0.41)

src/core/cycle/calibration-profile.ts

@@ -96,7 +96,7 @@ export type PatternStatementsGenerator = (input: {
 export type BiasTagsGenerator = (patterns: string[]) => Promise<string[]>;
 
 export interface CalibrationProfileOpts extends BasePhaseOpts {
-  /** Holder to generate the profile for. Default: `calibration.user_holder` config, then 'garry'. */
+  /** Holder to generate the profile for. Default 'garry'. */
   holder?: string;
   /** Inject the patterns generator (tests). */
   patternsGenerator?: PatternStatementsGenerator;
@@ -194,26 +194,6 @@ export function parseBiasTagsOutput(raw: string): string[] {
     .slice(0, 4);
 }
 
-/**
- * #1726: resolve the calibration holder. Explicit param wins, then the
- * persistent `calibration.user_holder` config key (symmetric with
- * emotional_weight.user_holder), then the legacy 'garry' default. Fail-open:
- * a missing config table / mock engine without getConfig falls through.
- */
-export async function resolveCalibrationHolder(
-  engine: BrainEngine,
-  explicit?: string,
-): Promise<string> {
-  if (explicit) return explicit;
-  try {
-    const configured = await engine.getConfig('calibration.user_holder');
-    if (configured && configured.trim().length > 0) return configured.trim();
-  } catch {
-    // Config unavailable — use the legacy default.
-  }
-  return 'garry';
-}
-
 /** Pick the "loudest" pattern slot for the template fallback. */
 function pickFallbackSlots(scorecard: TakesScorecard): PatternStatementSlots {
   if (!scorecard || scorecard.resolved === 0) {
@@ -247,7 +227,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
     _ctx: OperationContext,
     opts: CalibrationProfileOpts,
   ): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
-    const holder = await resolveCalibrationHolder(engine, opts.holder);
+    const holder = opts.holder ?? 'garry';
     const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
     const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
     const gradeCompletion = opts.gradeCompletion ?? 1.0;

src/core/cycle/synthesize.ts

@@ -428,8 +428,13 @@ export async function runPhaseSynthesize(
 
     const queue = new MinionQueue(engine);
     const childIds: number[] = [];
-    /** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
-    const chunkInfo = new Map<number, { idx: number; hash6: string }>();
+    /**
+     * Map child job_id → transcript metadata. Drives D6 orchestrator-side
+     * slug rewrite for chunked transcripts AND the deterministic frontmatter
+     * stampDreamProvenance merges into each written page. Populated for
+     * every child (single-chunk children carry chunkTotal=1).
+     */
+    const childMeta = new Map<number, ChildMeta>();
     /** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
     const skipReports: Array<{ filePath: string; reason: string }> = [];
 
@@ -513,9 +518,14 @@ export async function runPhaseSynthesize(
           { allowProtectedSubmit: true },
         );
         childIds.push(child.id);
-        if (isChunked) {
-          chunkInfo.set(child.id, { idx: i, hash6 });
-        }
+        childMeta.set(child.id, {
+          idx: i,
+          hash6,
+          chunkTotal: chunks.length,
+          transcriptSource: t.transcriptSource,
+          transcriptId: stripContentVersionSuffix(t.basename),
+          inferredDate: t.inferredDate,
+        });
       }
     }
 
@@ -544,14 +554,14 @@ export async function runPhaseSynthesize(
 
     // Collect slugs from put_page tool executions across the children
     // (codex finding #2: deterministic provenance, NOT pages.updated_at).
-    // D6 orchestrator slug rewrite: chunkInfo drives post-hoc rewrite of
+    // D6 orchestrator slug rewrite: childMeta drives post-hoc rewrite of
     // bare-hash slugs to `<hash6>-c<idx>` so chunked siblings can't collide
     // even if Sonnet drops the chunk suffix.
     // v0.32.8: refs carry source_id so reverseWriteRefs picks the correct
     // (source, slug) row. #1586: refs are stamped with the cycle's resolved
     // source (children write there via SubagentHandlerData.source_id).
     const cycleSourceId = opts.sourceId ?? 'default';
-    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
+    const writtenRefs = await collectChildPutPageSlugs(engine, childIds, childMeta, cycleSourceId);
 
     const summaryDate = opts.date ?? today();
 
@@ -559,7 +569,12 @@ export async function runPhaseSynthesize(
     // of every child-written page BEFORE reverse-rendering, so generated pages
     // are queryable (`frontmatter->>'dream_generated'`) and a later put_page
     // write-through (which re-renders from the DB row) can't erase the stamp.
-    await stampDreamProvenance(engine, writtenRefs, summaryDate);
+    // #2285: the stamp also carries the orchestrator-owned deterministic
+    // frontmatter (transcript_id, transcript_source, transcript_hash, date,
+    // chunk) derived from childMeta — subagent drift on those fields can't
+    // leak, and reverseWriteRefs below re-reads the row so the same fields
+    // land in the on-disk markdown.
+    await stampDreamProvenance(engine, writtenRefs, summaryDate, childMeta);
 
     // Dual-write: reverse-render each DB row → markdown file.
     const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
@@ -1095,15 +1110,17 @@ function sanitizeForSlug(s: string): string {
  * fake"): we no longer need detection because the rewrite enforces
  * uniqueness at slug-write time.
  *
- * `chunkInfo` maps child job_id → { chunk_index, hash6 }. Single-chunk
- * children are absent from the map and pass through unchanged.
+ * `childMeta` maps child job_id → per-child transcript metadata. Chunked
+ * children (chunkTotal > 1) get the slug rewrite; single-chunk children
+ * pass through unchanged. Each returned ref carries the job_id that wrote
+ * it so stampDreamProvenance can pair the slug back to its childMeta entry.
  */
 async function collectChildPutPageSlugs(
   engine: BrainEngine,
   childIds: number[],
-  chunkInfo: Map<number, { idx: number; hash6: string }>,
+  childMeta: Map<number, ChildMeta>,
   sourceId = 'default',
-): Promise<Array<{ slug: string; source_id: string }>> {
+): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
   if (childIds.length === 0) return [];
   // Raw fetch — NO SELECT DISTINCT. Preserves per-child slug duplicates so
   // the orchestrator sees what each child wrote. COALESCE handles both
@@ -1122,16 +1139,73 @@ async function collectChildPutPageSlugs(
        FROM subagent_tool_executions
       WHERE job_id = ANY($1::int[])
         AND tool_name = 'brain_put_page'
-        AND status = 'complete'`,
+        AND status = 'complete'
+      ORDER BY id`,
     [childIds],
   );
-  const rewritten = new Set<string>();
+  const rewritten = new Map<string, number>();
   for (const r of rows) {
     if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
-    const ci = chunkInfo.get(r.job_id);
-    rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
+    const meta = childMeta.get(r.job_id);
+    const finalSlug = meta && meta.chunkTotal > 1
+      ? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
+      : r.slug;
+    // Last writer wins, in execution-row order (ORDER BY id): if two children
+    // collide on a final slug, the pages row holds the LAST put_page write, so
+    // the stamp must attribute that child's transcript — not an arbitrary one.
+    rewritten.set(finalSlug, r.job_id);
   }
-  return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
+  return [...rewritten.entries()]
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
+}
+
+/**
+ * Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
+ * AND the deterministic frontmatter stampDreamProvenance merges into each
+ * written page. Populated for every child, not just chunked ones.
+ */
+interface ChildMeta {
+  idx: number;
+  hash6: string;
+  chunkTotal: number;
+  transcriptSource: string | null;
+  transcriptId: string;
+  inferredDate: string | null;
+}
+
+/**
+ * Strip the content-version suffix that claude-code-archive appends when a
+ * conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
+ * the stable transcript identifier; the suffix changes with content. Used to
+ * populate `transcript_id` so edits of the same session collapse to one id.
+ */
+function stripContentVersionSuffix(basename: string): string {
+  return basename.replace(/--[a-f0-9]+$/i, '');
+}
+
+/**
+ * Deterministic frontmatter for one synthesized page (#2285). Every field
+ * here is owned by the orchestrator — the subagent's value for any of these
+ * is overwritten. The subagent retains authority over type / title / tags /
+ * body. `date` feeds the effective-date precedence chain
+ * (src/core/effective-date.ts) so re-imports keep the conversation date even
+ * when sync tools re-stamp file mtimes.
+ */
+function buildDeterministicFrontmatter(
+  meta: ChildMeta,
+  cycleDate: string,
+): Record<string, unknown> {
+  const overrides: Record<string, unknown> = {
+    dream_generated: true,
+    dream_cycle_date: cycleDate,
+    transcript_id: meta.transcriptId,
+    transcript_hash: meta.hash6,
+  };
+  if (meta.transcriptSource) overrides.transcript_source = meta.transcriptSource;
+  if (meta.chunkTotal > 1) overrides.chunk = `${meta.idx + 1}/${meta.chunkTotal}`;
+  if (meta.inferredDate) overrides.date = meta.inferredDate;
+  return overrides;
 }
 
 /**
@@ -1177,12 +1251,19 @@ async function hasLegacySingleChunkCompletion(
  */
 async function stampDreamProvenance(
   engine: BrainEngine,
-  refs: Array<{ slug: string; source_id: string }>,
+  refs: Array<{ slug: string; source_id: string; jobId?: number }>,
   cycleDate: string,
+  childMeta?: Map<number, ChildMeta>,
 ): Promise<void> {
   if (refs.length === 0) return;
   const { executeRawJsonb } = await import('../sql-query.ts');
-  for (const { slug, source_id } of refs) {
+  for (const { slug, source_id, jobId } of refs) {
+    // #2285: when the ref pairs back to a child, the stamp also carries the
+    // orchestrator-owned deterministic frontmatter for that transcript.
+    const meta = jobId !== undefined ? childMeta?.get(jobId) : undefined;
+    const stamp = meta
+      ? buildDeterministicFrontmatter(meta, cycleDate)
+      : { dream_generated: true, dream_cycle_date: cycleDate };
     try {
       await executeRawJsonb(
         engine,
@@ -1190,7 +1271,7 @@ async function stampDreamProvenance(
             SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
           WHERE slug = $1 AND source_id = $2`,
         [slug, source_id],
-        [{ dream_generated: true, dream_cycle_date: cycleDate }],
+        [stamp],
       );
     } catch (e) {
       const msg = e instanceof Error ? e.message : String(e);

src/core/cycle/transcript-discovery.ts

@@ -10,7 +10,7 @@
  */
 
 import { readFileSync, readdirSync, statSync } from 'node:fs';
-import { join, basename } from 'node:path';
+import { join, basename, dirname } from 'node:path';
 import { createHash } from 'node:crypto';
 import { pruneDir } from '../sync.ts';
 
@@ -23,8 +23,22 @@ export interface DiscoveredTranscript {
   content: string;
   /** Filename basename without extension; used as a topic-slug seed. */
   basename: string;
-  /** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
+  /**
+   * Inferred conversation date (YYYY-MM-DD) or null. Precedence: the
+   * `| First message | <ISO> |` row in the transcript's `## Metadata`
+   * table (stable across mtime-restamping re-syncs) wins; a leading
+   * `YYYY-MM-DD` in the basename is the fallback.
+   */
   inferredDate: string | null;
+  /**
+   * Transcript source archive name, derived from the path's grandparent
+   * directory (the immediate parent of the date directory). For the
+   * canonical layout `<corpus>/<source>/<date>/<id>.md` this yields the
+   * source-name segment — e.g. `claude-code` for the claude-code-archive
+   * output, `meetings` for meeting recordings. Null when the file does
+   * not live under a `<source>/<date>/` pair (ad-hoc inputs).
+   */
+  transcriptSource: string | null;
 }
 
 export interface DiscoverOpts {
@@ -161,6 +175,36 @@ function matchesAnyExclude(text: string, patterns: RegExp[]): boolean {
   return false;
 }
 
+/**
+ * Content-based conversation date: the `| First message | <ISO timestamp> |`
+ * row claude-code-archive writes into the transcript's `## Metadata` table.
+ * Stable across rsync/Dropbox/Syncthing/B2 re-syncs that re-stamp mtime,
+ * unlike anything derived from file metadata. Returns YYYY-MM-DD or null.
+ */
+const FIRST_MESSAGE_RE = /^\|\s*First message\s*\|\s*(\d{4}-\d{2}-\d{2})/im;
+
+export function inferContentDate(content: string): string | null {
+  const m = FIRST_MESSAGE_RE.exec(content);
+  return m ? m[1] : null;
+}
+
+/**
+ * Derive the archive source name from a transcript path. Returns the basename
+ * of the directory two levels above the file when the immediate parent is a
+ * date directory and the grandparent looks like a source-name slug (lowercase
+ * alphanumeric segments separated by hyphens); otherwise null. This pins the
+ * canonical claude-code-archive layout `<corpus>/<source>/<date>/<id>.md`
+ * without claiming a source for ad-hoc inputs that don't match.
+ */
+export function deriveTranscriptSource(filePath: string): string | null {
+  const parentName = basename(dirname(filePath));
+  if (!/^\d{4}-\d{2}-\d{2}/.test(parentName)) return null;
+  const grandparentName = basename(dirname(dirname(filePath)));
+  if (!grandparentName) return null;
+  if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(grandparentName)) return null;
+  return grandparentName;
+}
+
 function listTextFiles(dir: string): string[] {
   // Recursive walk with descent-time pruning (closes codex C12/C13 spec gap).
   // Accepts BOTH .txt and .md per transcript-discovery's domain rules — does
@@ -225,8 +269,11 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
       const ext = filePath.endsWith('.md') ? '.md' : '.txt';
       const baseName = basename(filePath, ext);
       const dateMatch = DATE_RE.exec(baseName);
-      const inferredDate = dateMatch ? dateMatch[1] : null;
-      if (!isInDateRange(inferredDate, opts)) continue;
+      const filenameDate = dateMatch ? dateMatch[1] : null;
+      // Fast path: date-named files outside the window skip before the read.
+      // ponytail: a date-named file whose content date differs is filtered on
+      // its filename date — acceptable; archive layouts use UUID basenames.
+      if (filenameDate && !isInDateRange(filenameDate, opts)) continue;
 
       let content: string;
       try {
@@ -241,12 +288,17 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
       }
       if (matchesAnyExclude(content, excludeRes)) continue;
 
+      // Content-metadata date wins (survives mtime restamps); filename next.
+      const inferredDate = inferContentDate(content) ?? filenameDate;
+      if (!isInDateRange(inferredDate, opts)) continue;
+
       results.push({
         filePath,
         contentHash: hashContent(content),
         content,
         basename: baseName,
         inferredDate,
+        transcriptSource: deriveTranscriptSource(filePath),
       });
     }
   }
@@ -290,6 +342,7 @@ export function readSingleTranscript(
     contentHash: hashContent(content),
     content,
     basename: baseName,
-    inferredDate: dateMatch ? dateMatch[1] : null,
+    inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
+    transcriptSource: deriveTranscriptSource(filePath),
   };
 }

src/core/extract-timeline-from-meetings.ts

@@ -68,14 +68,11 @@ export async function extractTimelineFromMeetings(
   // 1. Fetch all meeting pages (one round-trip).
   const sourceFilter = opts.sourceIdFilter ? `AND source_id = $1` : '';
   const meetingParams = opts.sourceIdFilter ? [opts.sourceIdFilter] : [];
-  // #2109: gbrain-base-v2's unify-types catch-all retypes meeting pages to
-  // `note` with frontmatter.legacy_type = 'meeting'. Match both spellings so
-  // the extractor keeps working on migrated (v2) brains, not just v1 ones.
   const meetings = await engine.executeRaw<MeetingRow>(
     `SELECT slug, source_id, title, effective_date, updated_at,
             compiled_truth, COALESCE(timeline, '') AS timeline
        FROM pages
-      WHERE (type = 'meeting' OR frontmatter ->> 'legacy_type' = 'meeting')
+      WHERE type = 'meeting'
         AND deleted_at IS NULL
         ${sourceFilter}
       ORDER BY effective_date DESC NULLS LAST, slug`,
@@ -97,7 +94,7 @@ export async function extractTimelineFromMeetings(
        JOIN pages pf ON pf.id = l.from_page_id
        JOIN pages pt ON pt.id = l.to_page_id
       WHERE l.link_type = 'attended'
-        AND (pf.type = 'meeting' OR pf.frontmatter ->> 'legacy_type' = 'meeting')
+        AND pf.type = 'meeting'
         AND pf.deleted_at IS NULL
         AND pt.deleted_at IS NULL`,
   );

src/core/operations.ts

@@ -4562,10 +4562,7 @@ const list_schema_packs: Operation = {
     const { existsSync, readdirSync } = await import('node:fs');
     const { join } = await import('node:path');
     const { gbrainPath } = await import('./config.ts');
-    // #1726: derive from the locator's registry instead of a hand-copied
-    // subset (which had frozen at 2 of 7 bundled packs).
-    const { BUNDLED_PACKS } = await import('./schema-pack/load-active.ts');
-    const bundled = [...BUNDLED_PACKS];
+    const bundled = ['gbrain-base', 'gbrain-recommended'];
     const installedDir = gbrainPath('schema-packs');
     const installed: string[] = [];
     if (existsSync(installedDir)) {

src/core/schema-pack/base/gbrain-base-v2.yaml

@@ -41,12 +41,6 @@ migration_from:
   pack: gbrain-base
   version: "1.x"
 
-# #2117 — cycle-phase participation. `phases:` is additive and pack-gated;
-# without this key extract_atoms is silently off on v2 brains even though
-# onboard + doctor recommend it (v2 declares the `atom` type it writes).
-phases:
-  - extract_atoms
-
 page_types:
   - name: person
     primitive: entity
@@ -325,10 +319,6 @@ page_types:
     extractable: false
     expert_routing: false
 
-# #2117 — inference rules ported from gbrain-base v1 so extract-ner keeps
-# working on v2 brains (it hard-skips with pack_unavailable when no
-# link_type declares an inference.regex). Same ReDoS-guarded sketch
-# regexes v1 ships; production matchers in link-extraction.ts still apply.
 link_types:
   - name: partner_of
     inverse: partner_of
@@ -338,24 +328,14 @@ link_types:
   - name: discusses
   - name: founded
     inverse: founded_by
-    inference:
-      regex: \b(founded|founder of|co-?founded|started)\b
   - name: works_at
     inverse: employs
-    inference:
-      regex: \b(works? at|employed by|works? for|joined|hired by|ceo of|cto of|cmo of)\b
   - name: invested_in
     inverse: investor_of
-    inference:
-      regex: \b(invested in|backed|seeded|funded|wrote a check)\b
   - name: sourced_from
   - name: derived_from
   - name: supersedes
   - name: redirects_to
-  # NOTE: v1's `attended` inference is page_type-bound to `meeting`, which
-  # v2 does not declare (lint: link_types_undeclared_page_type). Meeting
-  # pages retyped by unify-types are matched via frontmatter.legacy_type
-  # in extract-timeline-from-meetings (#2109) instead.
   - name: attended
     inverse: attended_by
   - name: authored

src/core/schema-pack/load-active.ts

@@ -91,33 +91,29 @@ export function _resetPackLocatorForTests(): void {
  * Returns null when the pack is not found. Callers handle null by
  * throwing UnknownPackError with a paste-ready install hint.
  */
-// v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
-// ship in src/core/schema-pack/base/. Add a new entry here to bundle
-// additional canonical packs.
-//
-// v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
-// extract_atoms/synthesize_concepts phases), investor (theses + bet
-// resolution + 3 calibration domains), engineer (gstack-learnings bridge
-// + 3 calibration domains), everything (meta-pack stacking all three
-// via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
-//
-// #1726: exported so reporting surfaces (list_schema_packs) derive from the
-// same list the locator resolves — no more hand-copied 2-of-7 subsets.
-export const BUNDLED_PACKS: ReadonlyArray<string> = [
-  'gbrain-base',
-  'gbrain-recommended',
-  'gbrain-creator',
-  'gbrain-investor',
-  'gbrain-engineer',
-  'gbrain-everything',
-  // v0.42 type-unification: 15-type canonical successor to gbrain-base.
-  // Ships as install default (Lane E T17) + via gbrain onboard pack
-  // upgrade flow (the unify-types Minion handler).
-  'gbrain-base-v2',
-];
-
 function defaultPackLocator(name: string): string | null {
-  if (BUNDLED_PACKS.includes(name)) {
+  // v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
+  // ship in src/core/schema-pack/base/. Add a new entry here to bundle
+  // additional canonical packs.
+  //
+  // v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
+  // extract_atoms/synthesize_concepts phases), investor (theses + bet
+  // resolution + 3 calibration domains), engineer (gstack-learnings bridge
+  // + 3 calibration domains), everything (meta-pack stacking all three
+  // via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
+  const BUNDLED: ReadonlyArray<string> = [
+    'gbrain-base',
+    'gbrain-recommended',
+    'gbrain-creator',
+    'gbrain-investor',
+    'gbrain-engineer',
+    'gbrain-everything',
+    // v0.42 type-unification: 15-type canonical successor to gbrain-base.
+    // Ships as install default (Lane E T17) + via gbrain onboard pack
+    // upgrade flow (the unify-types Minion handler).
+    'gbrain-base-v2',
+  ];
+  if (BUNDLED.includes(name)) {
     // Resolve bundled YAML relative to this source file. Works in both
     // direct-bun execution and bun --compile binaries.
     const here = dirname(fileURLToPath(import.meta.url));

test/calibration-profile.test.ts

@@ -32,7 +32,7 @@ interface CapturedSql {
   params: unknown[];
 }
 
-function buildMockEngine(opts: { scorecard: TakesScorecard; config?: Record<string, string> }): {
+function buildMockEngine(opts: { scorecard: TakesScorecard }): {
   engine: BrainEngine;
   captured: CapturedSql[];
 } {
@@ -42,9 +42,6 @@ function buildMockEngine(opts: { scorecard: TakesScorecard; config?: Record<stri
     async getScorecard() {
       return opts.scorecard;
     },
-    async getConfig(key: string) {
-      return opts.config?.[key] ?? null;
-    },
     async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
       captured.push({ sql, params: params ?? [] });
       return [];
@@ -244,36 +241,6 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
     expect(insert!.params[11]).toEqual(['over-confident-geography']); // active_bias_tags
   });
 
-  test('#1726: calibration.user_holder config drives the holder when no explicit opt', async () => {
-    const { engine, captured } = buildMockEngine({
-      scorecard: ENOUGH_RESOLVED_SCORECARD,
-      config: { 'calibration.user_holder': 'alice-example' },
-    });
-    await runPhaseCalibrationProfile(buildCtx(engine), {
-      patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
-      biasTagsGenerator: async () => [],
-      voiceGateJudge: passJudge,
-    });
-    const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
-    expect(insert).toBeDefined();
-    expect(insert!.params[1]).toBe('alice-example'); // holder from config
-  });
-
-  test('#1726: explicit holder opt wins over calibration.user_holder config', async () => {
-    const { engine, captured } = buildMockEngine({
-      scorecard: ENOUGH_RESOLVED_SCORECARD,
-      config: { 'calibration.user_holder': 'alice-example' },
-    });
-    await runPhaseCalibrationProfile(buildCtx(engine), {
-      holder: 'charlie-example',
-      patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
-      biasTagsGenerator: async () => [],
-      voiceGateJudge: passJudge,
-    });
-    const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
-    expect(insert!.params[1]).toBe('charlie-example');
-  });
-
   test('default model is a provider-prefixed id, persisted to model_id (#2451)', async () => {
     const { engine, captured } = buildMockEngine({ scorecard: ENOUGH_RESOLVED_SCORECARD });
     const patternsGenerator: PatternStatementsGenerator = async () => [

test/cycle-dream-output-root.test.ts

@@ -26,6 +26,7 @@ const transcript: DiscoveredTranscript = {
   content: 'User: hello world',
   contentHash: 'abcdef0123456789',
   inferredDate: '2026-07-17',
+  transcriptSource: null,
 } as DiscoveredTranscript;
 
 describe('#2415: buildSynthesisPrompt output root', () => {

test/cycle-synthesize-slug-collection.test.ts

@@ -152,3 +152,94 @@ describe('#2569: stampDreamProvenance persists the marker into DB frontmatter',
     await stampDreamProvenance(engine as any, refs, '2026-07-17'); // idempotent
   });
 });
+
+describe('#2285: orchestrator-owned deterministic transcript frontmatter', () => {
+  const meta = {
+    idx: 1,
+    hash6: 'abc123',
+    chunkTotal: 3,
+    transcriptSource: 'claude-code',
+    transcriptId: 'session-uuid',
+    inferredDate: '2026-05-15',
+  };
+
+  test('collectChildPutPageSlugs pairs each ref back to the writing job', async () => {
+    const refs = await collectChildPutPageSlugs(
+      engine as any, [1001], new Map([[1001, { ...meta, chunkTotal: 1 }]]), 'mybrain',
+    );
+    expect(refs.length).toBeGreaterThan(0);
+    for (const r of refs) {
+      expect(r.jobId).toBe(1001);
+      expect(r.source_id).toBe('mybrain'); // #1586: cycle source, never hardcoded 'default'
+    }
+  });
+
+  test('slug collision across children attributes the LAST writer (matches surviving putPage)', async () => {
+    const db = (engine as any).db;
+    // Jobs 1001 then 1002 write the same slug; the pages row would hold
+    // 1002's content (last put_page wins), so the ref must carry jobId 1002.
+    await db.query(
+      `INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
+       VALUES (1001, 9, 'tool_dup_a', 'brain_put_page', 'complete', $1::jsonb)`,
+      [JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'first' })],
+    );
+    await db.query(
+      `INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
+       VALUES (1002, 9, 'tool_dup_b', 'brain_put_page', 'complete', $1::jsonb)`,
+      [JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'second' })],
+    );
+    const refs = await collectChildPutPageSlugs(engine as any, [1001, 1002], new Map());
+    const hit = refs.find((r: { slug: string }) => r.slug === 'wiki/agents/test/collision');
+    expect(hit?.jobId).toBe(1002);
+  });
+
+  test('stampDreamProvenance merges the transcript metadata into DB frontmatter', async () => {
+    const slug = 'wiki/originals/ideas/2026-07-17-transcript-meta-abc123';
+    await engine.putPage(slug, {
+      type: 'note',
+      title: 'Meta stamp',
+      compiled_truth: 'body',
+      timeline: '',
+      frontmatter: { keep_me: 'yes', transcript_id: 'subagent-drift' },
+    });
+    await stampDreamProvenance(
+      engine as any,
+      [{ slug, source_id: 'default', jobId: 42 }],
+      '2026-07-17',
+      new Map([[42, meta]]),
+    );
+    const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
+      `SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
+    );
+    const fm = rows[0].fm as Record<string, unknown>;
+    expect(fm.dream_generated).toBe(true);
+    expect(fm.dream_cycle_date).toBe('2026-07-17');
+    expect(fm.transcript_id).toBe('session-uuid'); // orchestrator wins over subagent drift
+    expect(fm.transcript_hash).toBe('abc123');
+    expect(fm.transcript_source).toBe('claude-code');
+    expect(fm.chunk).toBe('2/3');
+    expect(fm.date).toBe('2026-05-15');
+    expect(fm.keep_me).toBe('yes'); // subagent-owned keys survive
+  });
+
+  test('single-chunk children with no inferredDate stamp only the applicable fields', async () => {
+    const slug = 'wiki/originals/ideas/2026-07-17-minimal-meta-abc123';
+    await engine.putPage(slug, {
+      type: 'note', title: 'Minimal', compiled_truth: 'b', timeline: '', frontmatter: {},
+    });
+    await stampDreamProvenance(
+      engine as any,
+      [{ slug, source_id: 'default', jobId: 43 }],
+      '2026-07-17',
+      new Map([[43, { ...meta, chunkTotal: 1, transcriptSource: null, inferredDate: null }]]),
+    );
+    const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
+      `SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
+    );
+    const fm = rows[0].fm as Record<string, unknown>;
+    expect(fm.transcript_id).toBe('session-uuid');
+    expect(fm.chunk).toBeUndefined();
+    expect(fm.transcript_source).toBeUndefined();
+    expect(fm.date).toBeUndefined();
+  });
+});

test/cycle-synthesize.test.ts

@@ -302,6 +302,7 @@ describe('judgeSignificance', () => {
       content: 'A short conversation about something interesting.',
       basename: 'x',
       inferredDate: null,
+      transcriptSource: null,
     };
   }
 
@@ -415,6 +416,7 @@ describe('judgeSignificance — UTF-16 safety (v0.41.13)', () => {
       content,
       basename: 'long',
       inferredDate: null,
+      transcriptSource: null,
     };
   }
 

test/cycle/synthesize-gateway-adapter.test.ts

@@ -45,6 +45,7 @@ const FIXTURE_TRANSCRIPT: DiscoveredTranscript = {
   content: 'Synthetic transcript content for gateway-adapter parity tests.',
   contentHash: 'sha-fixture-1',
   inferredDate: '2026-05-24',
+  transcriptSource: null,
 };
 
 describe('makeJudgeClient — construction-time provider probe', () => {

test/cycle/transcript-discovery-metadata.test.ts

@@ -0,0 +1,109 @@
+/**
+ * #2285 — transcript metadata discovery.
+ *
+ * Pins the two discovery-side additions:
+ *   1. `transcriptSource` — derived from the `<source>/<date>/<file>` path
+ *      layout; null for ad-hoc inputs that don't match.
+ *   2. Content-based date inference — the `| First message | <ISO> |` row in
+ *      the transcript's `## Metadata` table wins over the filename-regex
+ *      date (stable across mtime-restamping re-syncs); filename is the
+ *      fallback.
+ *
+ * Pure filesystem; no engine, no LLM.
+ */
+
+import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
+import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join, dirname } from 'node:path';
+import {
+  discoverTranscripts,
+  readSingleTranscript,
+  deriveTranscriptSource,
+  inferContentDate,
+} from '../../src/core/cycle/transcript-discovery.ts';
+
+let tmpDir: string;
+
+beforeEach(() => {
+  tmpDir = mkdtempSync(join(tmpdir(), 'gbrain-transcript-meta-'));
+});
+
+afterEach(() => {
+  rmSync(tmpDir, { recursive: true, force: true });
+});
+
+function write(relPath: string, body: string): string {
+  const full = join(tmpDir, relPath);
+  mkdirSync(dirname(full), { recursive: true });
+  writeFileSync(full, body);
+  return full;
+}
+
+const FILLER = 'User: hello world. '.repeat(200);
+const METADATA_BLOCK =
+  '## Metadata\n\n| Key | Value |\n| --- | --- |\n| First message | 2026-05-15T03:51:11.584Z |\n\n';
+
+describe('deriveTranscriptSource', () => {
+  test('extracts the source slug from <source>/<date>/<file> layout', () => {
+    expect(deriveTranscriptSource('/corpus/claude-code/2026-06-12/abc.md')).toBe('claude-code');
+    expect(deriveTranscriptSource('/corpus/voice-notes/2026-06-12/xyz.md')).toBe('voice-notes');
+  });
+
+  test('null when the parent dir is not a date dir or grandparent is not a slug', () => {
+    expect(deriveTranscriptSource('/corpus/flat-file.md')).toBeNull();
+    expect(deriveTranscriptSource('/corpus/claude-code/not-a-date/abc.md')).toBeNull();
+    expect(deriveTranscriptSource('/corpus/Not A Slug/2026-06-12/abc.md')).toBeNull();
+  });
+});
+
+describe('inferContentDate', () => {
+  test('parses the | First message | row', () => {
+    expect(inferContentDate(METADATA_BLOCK)).toBe('2026-05-15');
+  });
+  test('null when absent', () => {
+    expect(inferContentDate(FILLER)).toBeNull();
+  });
+});
+
+describe('discoverTranscripts — transcriptSource + date cascade', () => {
+  test('populates transcriptSource per file; null for flat files', () => {
+    write('claude-code/2026-06-12/aaaa.md', FILLER);
+    write('2026-06-12-flat.md', FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    const byBase = new Map(out.map(t => [t.basename, t.transcriptSource]));
+    expect(byBase.get('aaaa')).toBe('claude-code');
+    expect(byBase.get('2026-06-12-flat')).toBeNull();
+  });
+
+  test('content First-message date wins over the filename date', () => {
+    write('2026-01-01-named.md', METADATA_BLOCK + FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    expect(out).toHaveLength(1);
+    expect(out[0].inferredDate).toBe('2026-05-15');
+  });
+
+  test('filename date remains the fallback when content has no metadata row', () => {
+    write('2026-01-01-named.md', FILLER);
+    const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
+    expect(out[0].inferredDate).toBe('2026-01-01');
+  });
+
+  test('date filter matches on the content date for UUID-named transcripts', () => {
+    write('claude-code/2026-05-15/uuid-basename.md', METADATA_BLOCK + FILLER);
+    const hit = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-15' });
+    expect(hit).toHaveLength(1);
+    const miss = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-16' });
+    expect(miss).toHaveLength(0);
+  });
+});
+
+describe('readSingleTranscript — same metadata surface', () => {
+  test('carries transcriptSource and prefers the content date', () => {
+    const p = write('claude-code/2026-05-15/2026-01-01-single.md', METADATA_BLOCK + FILLER);
+    const t = readSingleTranscript(p, { minChars: 100 });
+    expect(t).not.toBeNull();
+    expect(t!.transcriptSource).toBe('claude-code');
+    expect(t!.inferredDate).toBe('2026-05-15');
+  });
+});

test/extract-timeline-legacy-type.test.ts

@@ -1,106 +0,0 @@
-// #2109 — gbrain-base-v2's unify-types retypes meeting pages to `note`
-// with frontmatter.legacy_type='meeting'. extract-timeline-from-meetings
-// used to hardcode type='meeting' and silently scan 0 meetings on migrated
-// brains. These tests fail without the legacy_type fallback in both SQL
-// sites (meeting walk + attended-edge join).
-
-import { afterAll, beforeAll, beforeEach, describe, expect, it } from 'bun:test';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { resetPgliteState } from './helpers/reset-pglite.ts';
-import { extractTimelineFromMeetings } from '../src/core/extract-timeline-from-meetings.ts';
-
-let engine: PGLiteEngine;
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-});
-
-afterAll(async () => {
-  await engine.disconnect();
-});
-
-beforeEach(async () => {
-  await resetPgliteState(engine);
-});
-
-async function insertPage(opts: {
-  slug: string;
-  type: string;
-  title: string;
-  effectiveDate?: string;
-  legacyType?: string;
-}): Promise<number> {
-  const frontmatterLiteral = opts.legacyType
-    ? `'{"legacy_type": "${opts.legacyType}"}'::jsonb`
-    : `'{}'::jsonb`;
-  const rows = await engine.executeRaw<{ id: number }>(
-    `INSERT INTO pages (slug, source_id, type, title, compiled_truth, timeline, effective_date, frontmatter)
-     VALUES ($1, 'default', $2, $3, '', '', $4, ${frontmatterLiteral})
-     RETURNING id`,
-    [opts.slug, opts.type, opts.title, opts.effectiveDate ?? null],
-  );
-  return rows[0]!.id;
-}
-
-describe('extractTimelineFromMeetings — legacy_type fallback (#2109)', () => {
-  it('scans pages retyped to note with legacy_type=meeting and walks their attended edges', async () => {
-    const meetingId = await insertPage({
-      slug: 'meetings/2026-01-05',
-      type: 'note', // post-unify-types shape on a gbrain-base-v2 brain
-      legacyType: 'meeting',
-      title: 'Weekly sync',
-      effectiveDate: '2026-01-05',
-    });
-    const personId = await insertPage({
-      slug: 'people/alice-example',
-      type: 'person',
-      title: 'Alice Example',
-    });
-    await engine.executeRaw(
-      `INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
-      [meetingId, personId],
-    );
-
-    const result = await extractTimelineFromMeetings(engine);
-    expect(result.meetings_scanned).toBe(1);
-    expect(result.entries_created).toBe(1);
-    expect(result.entities_touched).toBe(1);
-    expect(result.batch_errors).toBe(0);
-  });
-
-  it('still scans pre-unify pages with type=meeting (v1 behavior preserved)', async () => {
-    const meetingId = await insertPage({
-      slug: 'meetings/2026-02-01',
-      type: 'meeting',
-      title: 'Board prep',
-      effectiveDate: '2026-02-01',
-    });
-    const personId = await insertPage({
-      slug: 'people/charlie-example',
-      type: 'person',
-      title: 'Charlie Example',
-    });
-    await engine.executeRaw(
-      `INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
-      [meetingId, personId],
-    );
-
-    const result = await extractTimelineFromMeetings(engine);
-    expect(result.meetings_scanned).toBe(1);
-    expect(result.entries_created).toBe(1);
-  });
-
-  it('does not scan unrelated note pages without legacy_type=meeting', async () => {
-    await insertPage({
-      slug: 'notes/random',
-      type: 'note',
-      title: 'Random note',
-      effectiveDate: '2026-03-01',
-    });
-    const result = await extractTimelineFromMeetings(engine);
-    expect(result.meetings_scanned).toBe(0);
-    expect(result.entries_created).toBe(0);
-  });
-});

test/operations-schema-pack.test.ts

@@ -152,19 +152,6 @@ describe('list_schema_packs', () => {
       expect(result.installed).toContain('mine');
     });
   });
-
-  it('reports the full bundled registry, not a hand-copied subset (#1726)', async () => {
-    await withEnv({ GBRAIN_HOME: tmpDir }, async () => {
-      const { BUNDLED_PACKS } = await import('../src/core/schema-pack/load-active.ts');
-      const result = await operationsByName.list_schema_packs!.handler(ctxOf(), {}) as { bundled: string[] };
-      expect(result.bundled.slice().sort()).toEqual([...BUNDLED_PACKS].sort());
-      // The lens packs that declare extract_atoms/synthesize_concepts phases
-      // were the ones dropped by the frozen 2-pack literal.
-      for (const name of ['gbrain-creator', 'gbrain-everything', 'gbrain-base-v2']) {
-        expect(result.bundled).toContain(name);
-      }
-    });
-  });
 });
 
 // ── schema_stats ───────────────────────────────────────────────────────

test/progress.test.ts

@@ -216,17 +216,21 @@ describe('progress reporter', () => {
   });
 
   test('only one process-level signal handler installed across many reporters', () => {
-    // Baseline: one handler already installed by prior tests in this file.
+    // Baseline: one handler already installed by prior tests in this file, and
+    // possibly live reporters from OTHER test files sharing this bun process
+    // (shard composition is not this test's invariant — assert the delta, not
+    // an absolute zero, or shard reshuffles make this fail spuriously).
     const installedBefore = __signalHandlerInstalledForTest();
+    const liveBefore = __liveReporterCountForTest();
     const { stream } = sink(false);
     for (let i = 0; i < 50; i++) {
       const p = createProgress({ mode: 'json', stream, minIntervalMs: 0, minItems: 1 });
       p.start(`phase_${i}`, 1);
       p.finish();
     }
-    // After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
+    // After 50 reporter lifecycles, still exactly one handler and zero NET leaked live entries.
     expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
-    expect(__liveReporterCountForTest()).toBe(0);
+    expect(__liveReporterCountForTest()).toBe(liveBefore);
   });
 
   test('startHeartbeat() fires heartbeats and stop() clears', async () => {

test/schema-pack-base-v2-capabilities.test.ts

@@ -1,40 +0,0 @@
-// #2117 — gbrain-base-v2 shipped with no `phases:` declaration and zero
-// link_types[].inference regexes, so extract_atoms was silently pack-gated
-// off and extract-ner returned pack_unavailable on the bundled default pack.
-// These assertions fail against the pre-fix yaml.
-
-import { describe, expect, it } from 'bun:test';
-import { join } from 'node:path';
-import { loadPackFromFile } from '../src/core/schema-pack/loader.ts';
-import { linkTypesUndeclared } from '../src/core/schema-pack/lint-rules.ts';
-
-const V2_PATH = join(import.meta.dir, '..', 'src', 'core', 'schema-pack', 'base', 'gbrain-base-v2.yaml');
-
-describe('gbrain-base-v2 capability parity (#2117)', () => {
-  const manifest = loadPackFromFile(V2_PATH);
-
-  it('declares the extract_atoms cycle phase', () => {
-    expect(manifest.phases ?? []).toContain('extract_atoms');
-  });
-
-  it('ships at least one link_type inference regex so extract-ner is not pack_unavailable', () => {
-    // Mirrors the extract-ner hasRegex predicate exactly.
-    const hasRegex = manifest.link_types.some(
-      (lt) => lt.inference && typeof lt.inference === 'object' && 'regex' in lt.inference,
-    );
-    expect(hasRegex).toBe(true);
-  });
-
-  it('ports the v1 inference verbs it declares link types for', () => {
-    const withRegex = manifest.link_types
-      .filter((lt) => lt.inference?.regex)
-      .map((lt) => lt.name)
-      .sort();
-    expect(withRegex).toEqual(['founded', 'invested_in', 'works_at']);
-  });
-
-  it('inference rules pass the undeclared-page-type lint (no meeting-bound inference)', async () => {
-    const issues = await linkTypesUndeclared(manifest);
-    expect(issues).toEqual([]);
-  });
-});