fix(takes): kill propose_takes rescan loop, keep every claim, and route cycle/brainstorm models through config (#2804 #2805)

Takeover of #2804 and #2805 (stacked), rebased onto current master.

Rescan loop + dropped claims (#2804):
- Zero-claim scans now write a status='empty' sentinel row so the
  (source_id, page_slug, content_hash, prompt_version) cache hits on
  every subsequent cycle instead of re-spending the extractor LLM call
  on the same unchanged page forever.
- The idempotency index gains md5(claim_text): multi-claim pages keep
  every claim (the 4-column unique index silently dropped claims 2..N
  via ON CONFLICT DO NOTHING). proposals_inserted now counts rows that
  actually landed (RETURNING id), not insert attempts.
- Migration renumbered 123 -> 125 (master shipped v123
  configurable_fts_language and v124 after the PR was cut; the
  duplicate v123 would never have run under the version > current
  runner). Schema parity across schema.sql, pglite-schema.ts,
  schema-embedded.ts.

Model-tier honoring (#2805), reworked for current master:
- propose_takes, grade_takes, calibration_profile resolve their model
  through resolveModel(models.<phase> > models.default > env >
  getChatModel()) — per-phase config keys are now honored while the
  gateway chat model (already tier-resolved by
  reconfigureGatewayWithEngine) stays the default, preserving master's
  #2451 semantics (provider-prefixed stored ids, nested prefixes like
  openrouter:... intact) and the #2997 opts.model ?? getChatModel()
  idiom. The PR's original bare-tail-everywhere approach was dropped
  where it conflicted with #2451; grade_takes keeps the bare tail ONLY
  for its cache key / stored judge_model_id (continuity with historical
  rows), while the judge call itself gets the full resolved string —
  fixing the live label-vs-actual mismatch (call rode chat_model,
  telemetry recorded a hardcoded claude-sonnet-4-6).
- brainstorm resolves via models.brainstorm > tier chain (was
  hardcoded anthropic:claude-sonnet-4-6).
- gbrain models lists the four new per-task keys; output caps and
  context-window entries added for newer Claude models.

Tests: test/propose-takes-rescan.test.ts (new, hermetic PGLite);
config-key coverage in propose-takes/grade-takes tests; existing #2451
and gateway-chat-model tests pass unchanged.

Co-authored-by: p3ob7o <p3ob7o@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/architecture/KEY_FILES.md

@@ -457,7 +457,6 @@ unresolvable+true|false, pre-v80 NULL/NULL rows survive).
 - `src/core/think/prompt.ts` extension — anti-bias rewrite. `withCalibration` option on `buildThinkSystemPrompt` adds anti-bias rules. `buildCalibrationBlock()` emits the `<calibration>` XML. `buildThinkUserMessage` has TWO shapes: default (question first), and with-calibration (retrieval → calibration → question) when opt-in. Wired into `runThink` via `opts.withCalibration` + `opts.calibrationHolder`.
 - `src/commands/calibration.ts` — CLI: `gbrain calibration` (read + print), `--regenerate`, `--undo-wave <ver>`, `ab-report`. MCP op `get_calibration_profile` (scope: read) backs the same data path. Source-scoped via `sourceScopeOpts(ctx)`.
 - `src/commands/serve-http.ts` extension — three admin routes: `/admin/api/calibration/profile`, `/admin/api/calibration/charts/:type` (image/svg+xml; type in {brier-trend, domain-bars, pattern-statements, abandoned-threads}), `/admin/api/calibration/pattern/:id` (drill-down).
-- `src/core/owner-holder.ts` — single source of truth for "the brain owner" holder string. `DEFAULT_OWNER_HOLDER = 'self'` (matches the consolidate facts→takes writer + `docs/takes-vs-facts.md`); `resolveOwnerHolder({override, configValue})` returns override > `emotional_weight.user_holder` config > `'self'`. Consumed by the calibration_profile cycle phase, `gbrain calibration` CLI, the `get_calibration_profile` op, `think`'s calibration block, `emotional-weight`'s `DEFAULT_USER_HOLDER`, and doctor's `calibration_freshness`. Pure; unit-tested in `test/owner-holder.test.ts`. Does NOT unify owner-identity fragmentation (`self`/`brain`/`people-<owner>`) — tracked separately.
 - `src/commands/takes.ts` extension — `gbrain takes revisit <slug>` opens $EDITOR on the source page with a `<!-- gbrain:revisit -->` cursor marker.
 - `src/commands/doctor.ts` extension — 4 checks: `abandoned_threads`, `calibration_freshness`, `grade_confidence_drift` (mitigation surface; math ships later), `voice_gate_health`.
 - `admin/src/pages/Calibration.tsx` — Calibration tab. Single-column layout. `<TrustedSVG>` wrapper handles `dangerouslySetInnerHTML` for the server-rendered SVG.

docs/takes-vs-facts.md

@@ -91,18 +91,3 @@ First full takes extraction run on a ~100K-page brain:
 4. **Self-reported ≠ verified.** "Reports 7 figures" → holder=person, weight=0.75, NOT world/1.0
 5. **No false precision.** Use 0.05 increments (0.35, 0.55, 0.75), not 0.74 or 0.82
 6. **"So what" test.** Skip Twitter handles, follower counts, obvious metadata
-
-## Owner-holder canonicalization
-
-"The brain owner" is, by convention, the holder string **`self`** — the value the
-dream `consolidate` phase stamps when it promotes the owner's hot facts into cold
-takes. Calibration, `think`, and the `doctor` calibration check resolve the owner
-holder through `resolveOwnerHolder` (`src/core/owner-holder.ts`): explicit override
-> `emotional_weight.user_holder` config > `self`.
-
-Known limitation (tracked in garrytan/gbrain#2465): the owner can also
-appear under `brain` (a take the owner asserts, via `propose_takes`) and
-`people/<owner>` (extraction that names the owner). The resolver selects the
-*default* canonical owner string for reads; it does not merge those other
-strings. Per-take attribution for other people (e.g. `people/george`) is
-unaffected and correct.

src/commands/calibration.ts

@@ -23,7 +23,6 @@ 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';
-import { resolveOwnerHolder } from '../core/owner-holder.ts';
 
 export interface CalibrationProfileRow {
   /** BIGSERIAL → string (postgres.js int8 wire shape; never Number() — int8
@@ -168,10 +167,7 @@ export async function runCalibration(
   config: GBrainConfig,
 ): Promise<void> {
   const { opts } = parseArgs(args);
-  const holder = resolveOwnerHolder({
-    override: opts.holder,
-    configValue: await engine.getConfig('emotional_weight.user_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).
@@ -257,15 +253,12 @@ export async function getCalibrationProfileOp(
   ctx: OperationContext,
   params: { holder?: string },
 ): Promise<CalibrationProfileRow | null> {
-  const holder = resolveOwnerHolder({
-    override: params.holder,
-    configValue: await ctx.engine.getConfig('emotional_weight.user_holder'),
-  });
+  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 owner holder (config emotional_weight.user_holder, else "self")',
+      'pass holder="<slug>" or omit to default to "garry"',
     );
   }
   const scope = sourceScopeOpts(ctx);

src/commands/doctor.ts

@@ -28,7 +28,6 @@ import type { DbUrlSource } from '../core/config.ts';
 import { gbrainPath, loadConfig } from '../core/config.ts';
 import { reflexEnabled } from '../core/context/reflex.ts';
 import { resolveSocketPath } from '../core/context/resolve-ipc.ts';
-import { resolveOwnerHolder } from '../core/owner-holder.ts';
 import { homedir } from 'os';
 import { dirname, isAbsolute, join, resolve as resolvePath } from 'path';
 import { fileURLToPath } from 'url';
@@ -1288,19 +1287,14 @@ export async function checkAbandonedThreads(engine: BrainEngine): Promise<Check>
 
 /**
  * calibration_freshness: warns when the active calibration profile is
- * older than 7 days (configurable). Default holder resolves via resolveOwnerHolder
- * (config emotional_weight.user_holder, else 'self'). Multi-source
+ * older than 7 days (configurable). Default holder 'garry'. Multi-source
  * brains see one row per source; this check uses the most recent across
  * all sources.
  */
 export async function checkCalibrationFreshness(engine: BrainEngine): Promise<Check> {
   try {
-    const ownerHolder = resolveOwnerHolder({
-      configValue: await engine.getConfig('emotional_weight.user_holder'),
-    });
     const rows = await engine.executeRaw<{ generated_at: Date | null }>(
-      `SELECT MAX(generated_at) AS generated_at FROM calibration_profiles WHERE holder = $1`,
-      [ownerHolder],
+      `SELECT MAX(generated_at) AS generated_at FROM calibration_profiles WHERE holder = 'garry'`,
     );
     const generated = rows[0]?.generated_at;
     if (!generated) {

src/commands/models.ts

@@ -50,6 +50,10 @@ const PER_TASK_KEYS: Array<{ key: string; tier: ModelTier; description: string }
   { key: 'models.eval.contradictions_judge', tier: 'utility',  description: 'Contradiction probe judge (v0.34 temporal-aware)' },
   { key: 'models.expansion',                tier: 'utility',   description: 'Query expansion for hybrid search' },
   { key: 'models.chat',                     tier: 'reasoning', description: 'Default `gateway.chat()` model' },
+  { key: 'models.propose_takes',            tier: 'reasoning', description: 'propose_takes claim extractor' },
+  { key: 'models.grade_takes',              tier: 'reasoning', description: 'grade_takes verdict judge' },
+  { key: 'models.calibration_profile',      tier: 'reasoning', description: 'Calibration profile generator' },
+  { key: 'models.brainstorm',               tier: 'reasoning', description: '`gbrain brainstorm` orchestrator' },
 ];
 
 interface ModelEntry {

src/commands/serve-http.ts

@@ -45,7 +45,6 @@ import {
   type IngestionContentType,
   type IngestionEvent,
 } from '../core/ingestion/types.ts';
-import { resolveOwnerHolder } from '../core/owner-holder.ts';
 
 /**
  * /health endpoint timeout. 3s rather than 5s: Fly.io's default
@@ -1191,7 +1190,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
   app.get('/admin/api/calibration/pattern/:id', requireAdmin, async (req: Request, res: Response) => {
     try {
       const { getLatestProfile } = await import('./calibration.ts');
-      const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
+      const holder = (req.query.holder as string) || 'garry';
       const profile = await getLatestProfile(engine, { holder });
       if (!profile) {
         res.status(404).json({ error: 'no_profile' });
@@ -1241,7 +1240,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
   app.get('/admin/api/calibration/profile', requireAdmin, async (req: Request, res: Response) => {
     try {
       const { getLatestProfile } = await import('./calibration.ts');
-      const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
+      const holder = (req.query.holder as string) || 'garry';
       const profile = await getLatestProfile(engine, { holder });
       res.json(profile);
     } catch (err) {
@@ -1258,7 +1257,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
         renderAbandonedThreadsCard,
         renderPatternStatementsCard,
       } = await import('../core/calibration/svg-renderer.ts');
-      const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
+      const holder = (req.query.holder as string) || 'garry';
       const type = req.params.type;
       const profile = await getLatestProfile(engine, { holder });
 

src/commands/takes.ts

@@ -29,7 +29,6 @@ import {
 } from '../core/takes-fence.ts';
 import { withPageLock } from '../core/page-lock.ts';
 import { resolveSourceId } from '../core/source-resolver.ts';
-import { resolveOwnerHolder } from '../core/owner-holder.ts';
 
 // --- Helpers ---
 
@@ -365,7 +364,7 @@ async function cmdResolve(engine: BrainEngine, args: string[], sourceId?: string
   // --evidence is the v0.30.0 alias for --source on the resolve subcommand
   // (semantic clarity: "what evidence resolved this bet?").
   const source = flagValue(args, '--evidence') ?? flagValue(args, '--source');
-  const resolvedBy = flagValue(args, '--by') ?? resolveOwnerHolder({ configValue: await engine.getConfig('emotional_weight.user_holder') });
+  const resolvedBy = flagValue(args, '--by') ?? 'garry';
   const dirArg = flagValue(args, '--dir');
 
   const pageId = await getPageId(engine, slug, sourceId);

src/core/brainstorm/judges.ts

@@ -61,7 +61,10 @@ export const MAX_OUTPUT_TOKENS_CEIL = 32_000;
  * (with a readable error) instead of the provider's opaque HTTP 400.
  */
 export const ANTHROPIC_OUTPUT_CAPS: Record<string, number> = {
+  'claude-fable-5': 64_000,
+  'claude-opus-4-8': 32_000,
   'claude-opus-4-7': 32_000,
+  'claude-sonnet-5': 64_000,
   'claude-sonnet-4-6': 64_000,
   'claude-haiku-4-5': 64_000,
   'claude-haiku-4-5-20251001': 64_000,

src/core/brainstorm/orchestrator.ts

@@ -32,6 +32,7 @@
  */
 
 import type { BrainEngine } from '../engine.ts';
+import { resolveModel } from '../model-config.ts';
 import { chat as defaultChat, embedQuery, type ChatResult, type ChatOpts } from '../ai/gateway.ts';
 import { hybridSearch, hybridSearchCached } from '../search/hybrid.ts';
 import { fetchFar, type CloseRef, type FarPage } from './domain-bank.ts';
@@ -68,7 +69,6 @@ import {
   type BrainstormCheckpoint,
   type CheckpointCross,
 } from './checkpoint.ts';
-import { resolveOwnerHolder } from '../owner-holder.ts';
 
 export { BudgetExhausted };
 
@@ -140,7 +140,7 @@ export interface BrainstormOptions {
   modelOverride?: string;
   /** Skip the cost-preview TTY grace window. Required for non-interactive callers. */
   skipCostPreview?: boolean;
-  /** When set, force the user holder for calibration profile lookup. Falls back to config (`emotional_weight.user_holder`) then `'self'`. */
+  /** When set, force the user holder for calibration profile lookup. Falls back to config (`emotional_weight.user_holder`) then `'garry'`. */
   holderOverride?: string;
   /** Source scope. */
   sourceId?: string;
@@ -539,7 +539,14 @@ async function _runBrainstormInner(
   const embedFn = opts.embedQueryFn ?? embedQuery;
 
   // ---- Phase 0: cost preview + TTY grace ----
-  const modelStr = opts.modelOverride ?? 'anthropic:claude-sonnet-4-6';
+  // Tier-resolved (mirrors the cycle phases): honors models.brainstorm >
+  // models.default > models.tier.reasoning; the fallback keeps stock
+  // behavior identical (reasoning tier default IS claude-sonnet-4-6).
+  const modelStr = opts.modelOverride ?? await resolveModel(engine, {
+    configKey: 'models.brainstorm',
+    tier: 'reasoning',
+    fallback: 'anthropic:claude-sonnet-4-6',
+  });
   const { aborted, estimate } = await previewCostAndWait({
     profile,
     model: modelStr,
@@ -624,7 +631,7 @@ async function _runBrainstormInner(
   }
 
   // ---- Phase 3: calibration context (cold-start fallback) ----
-  const holder = resolveOwnerHolder({ override: opts.holderOverride, configValue: config.emotional_weight?.user_holder });
+  const holder = opts.holderOverride ?? config.emotional_weight?.user_holder ?? 'garry';
   const calibContext = await loadCalibrationContext(engine, {
     holder,
     sourceId: opts.sourceId,

src/core/calibration/think-ab.ts

@@ -25,7 +25,7 @@ import type { BrainEngine } from '../engine.ts';
 
 export interface ABRunInput {
   question: string;
-  /** Holder context for calibration. Resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
+  /** Holder context for calibration. Default 'garry'. */
   holder?: string;
   /** Engine for DB write. */
   engine: BrainEngine;

src/core/cycle/calibration-profile.ts

@@ -26,9 +26,8 @@
  */
 
 import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
-import { resolveOwnerHolder } from '../owner-holder.ts';
-import { chat as gatewayChat } from '../ai/gateway.ts';
-import { TIER_DEFAULTS } from '../model-config.ts';
+import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
+import { resolveModel } from '../model-config.ts';
 import { gateVoice, type VoiceGateGenerator, type VoiceGateJudge } from '../calibration/voice-gate.ts';
 import { patternStatementTemplate, type PatternStatementSlots } from '../calibration/templates.ts';
 // v0.41 T10 — domain widening. The aggregator module resolves the active
@@ -97,7 +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 resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
+  /** Holder to generate the profile for. Default 'garry'. */
   holder?: string;
   /** Inject the patterns generator (tests). */
   patternsGenerator?: PatternStatementsGenerator;
@@ -228,12 +227,18 @@ class CalibrationProfilePhase extends BaseCyclePhase {
     _ctx: OperationContext,
     opts: CalibrationProfileOpts,
   ): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
-    const holder = resolveOwnerHolder({
-      override: opts.holder,
-      configValue: await engine.getConfig('emotional_weight.user_holder'),
-    });
+    const holder = opts.holder ?? 'garry';
     const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
-    const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
+    // Resolved once (see propose-takes.ts for the chain): models.calibration_profile
+    // > models.default > env > the gateway's chat model (itself resolved
+    // through models.chat + the reasoning tier). Provider-prefixed per #2451
+    // — a bare id would make gateway.chat() throw "missing a provider
+    // prefix". Drives the generator's chat call, the budget label, and the
+    // persisted model_id, so the three can never disagree.
+    const modelId = opts.model ?? await resolveModel(engine, {
+      configKey: 'models.calibration_profile',
+      fallback: getChatModel(),
+    });
     const gradeCompletion = opts.gradeCompletion ?? 1.0;
     const patternsGenerator = opts.patternsGenerator ?? defaultPatternsGenerator;
     const biasTagsGenerator = opts.biasTagsGenerator ?? defaultBiasTagsGenerator;
@@ -269,6 +274,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
         scorecard,
         holder,
         attempt,
+        modelHint: modelId,
         ...(feedback !== undefined ? { feedback } : {}),
       });
       return lines.join('\n');

src/core/cycle/emotional-weight.ts

@@ -14,8 +14,6 @@
  * See `loadHighEmotionTags` for the resolution path.
  */
 
-import { DEFAULT_OWNER_HOLDER } from '../owner-holder.ts';
-
 /**
  * Default high-emotion tag seed list. Pages with any tag in this set get the
  * tag-emotion boost in the formula below. Override via config key
@@ -45,12 +43,11 @@ export const HIGH_EMOTION_TAGS: ReadonlySet<string> = new Set([
 ]);
 
 /**
- * Holder name treated as "the user" for the user-as-holder ratio. Configurable
- * via the `emotional_weight.user_holder` config key; defaults to the canonical
- * owner holder ('self', DEFAULT_OWNER_HOLDER) so it matches the consolidate
- * facts→takes writer instead of a hardcoded name.
+ * Holder name treated as "the user" for the Garry-as-holder ratio. Configurable
+ * via the `emotional_weight.user_holder` config key (defaults to 'garry' to
+ * match the v0.28 schema's takes table convention).
  */
-export const DEFAULT_USER_HOLDER = DEFAULT_OWNER_HOLDER;
+export const DEFAULT_USER_HOLDER = 'garry';
 
 export interface EmotionalWeightTake {
   holder: string;

src/core/cycle/grade-takes.ts

@@ -36,7 +36,9 @@
 
 import { createHash } from 'node:crypto';
 import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
-import { chat as gatewayChat } from '../ai/gateway.ts';
+import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
+import { resolveModel } from '../model-config.ts';
+import { splitProviderModelId } from '../model-id.ts';
 import { GBrainError } from '../types.ts';
 import type { OperationContext } from '../operations.ts';
 import type { BrainEngine, Take, TakeResolution } from '../engine.ts';
@@ -395,7 +397,24 @@ class GradeTakesPhase extends BaseCyclePhase {
     const autoResolve = opts.autoResolve ?? false; // D17 default OFF
     const autoResolveThreshold = opts.autoResolveThreshold ?? 0.95; // D12 conservative
     const resolvedByLabel = opts.resolvedByLabel ?? 'gbrain:grade_takes';
-    const judgeModelId = opts.model ?? 'claude-sonnet-4-6';
+    // Resolve the judge model ONCE (see propose-takes.ts for the chain —
+    // same label-vs-actual split fixed here: the judge call rode the
+    // gateway's chat_model while the grade cache key, evidence signature,
+    // and budget label recorded a hardcoded 4.6).
+    // NOTE: changing the resolved judge model invalidates the grade cache
+    // (judge_model_id is part of its key) — a one-time, budget-capped
+    // re-grade wave that is CORRECT, since the actual judge did change.
+    const judgeModelFull = opts.model ?? await resolveModel(engine, {
+      configKey: 'models.grade_takes',
+      fallback: getChatModel(),
+    });
+    // Bare tail for cache keys / evidence signatures / stored ids — the
+    // grade cache has always been keyed on bare ids; the gateway default
+    // resolves provider-prefixed, and normalizing preserves cache continuity
+    // on stock installs (no spurious re-judge wave from a prefix change). A
+    // genuinely different configured judge still invalidates, which is
+    // correct. The FULL string drives the actual judge call.
+    const judgeModelId = splitProviderModelId(judgeModelFull).model || judgeModelFull;
 
     const useEnsemble = opts.useEnsemble ?? false;
     const ensembleThreshold = opts.ensembleThreshold ?? 0.85;
@@ -468,7 +487,7 @@ class GradeTakesPhase extends BaseCyclePhase {
       // Call the single-model judge. Errors on a single take log warning + continue.
       let verdict: JudgeVerdict;
       try {
-        verdict = await judge({ take, evidence, modelHint: opts.model });
+        verdict = await judge({ take, evidence, modelHint: judgeModelFull });
       } catch (err) {
         const msg = err instanceof Error ? err.message : String(err);
         result.warnings.push(`judge failed on take ${take.id}: ${msg}`);

src/core/cycle/propose-takes.ts

@@ -5,11 +5,16 @@
  * a tuned LLM extractor, writes the extracted gradeable claims to the
  * `take_proposals` queue. User accepts/rejects via `gbrain takes propose`.
  *
- * Idempotency contract (D17 schema spec):
- *   The unique index on (source_id, page_slug, content_hash, prompt_version)
- *   means an unchanged page never re-spends LLM tokens. Bumping
- *   PROPOSE_TAKES_PROMPT_VERSION cleanly invalidates the cache so a tuned
- *   prompt re-runs proposals on every page.
+ * Idempotency contract (D17 schema spec; per-claim rows since migration v125):
+ *   Every scan of a (source_id, page_slug, content_hash, prompt_version)
+ *   tuple leaves at least one row — one per extracted claim, or a single
+ *   status='empty' sentinel when extraction yields nothing — so an unchanged
+ *   page never re-spends LLM tokens. Pre-v125 only proposal rows were
+ *   written: a zero-claim page never entered the cache and was re-extracted
+ *   on EVERY cycle (observed live: ~60 such pages × every cycle ≈ 1,400
+ *   wasted extractor calls / ~$15 per day — ~90% of total autopilot spend).
+ *   Bumping PROPOSE_TAKES_PROMPT_VERSION cleanly invalidates the cache so a
+ *   tuned prompt re-runs proposals on every page.
  *
  * F2 fence dedup:
  *   The phase reads the page's existing `<!-- gbrain:takes:begin -->` fence
@@ -40,6 +45,7 @@
 import { randomUUID, createHash } from 'node:crypto';
 import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
 import { chat as gatewayChat, getChatModel } from '../ai/gateway.ts';
+import { resolveModel } from '../model-config.ts';
 import { writeReceipt } from '../extract/receipt-writer.ts';
 import { upsertExtractRollup } from '../extract/rollup-writer.ts';
 import { GBrainError } from '../types.ts';
@@ -307,6 +313,18 @@ class ProposeTakesPhase extends BaseCyclePhase {
     const promptVersion = opts.promptVersion ?? PROPOSE_TAKES_PROMPT_VERSION;
     const pageLimit = opts.pageLimit ?? 100;
     const skipPagesWithFence = opts.skipPagesWithFence ?? false;
+    // Resolve the extractor model ONCE: models.propose_takes >
+    // models.default > GBRAIN_MODEL env > the gateway's chat model (which
+    // reconfigureGatewayWithEngine already resolved through models.chat +
+    // the reasoning tier). One resolved provider-prefixed string drives the
+    // actual chat call, the budget estimate, AND the stored model_id — so
+    // the recorded model can never disagree with the model that ran (#2451
+    // convention: stored ids are provider-prefixed, nested prefixes like
+    // openrouter:anthropic/... stay intact).
+    const extractorModelId = opts.model ?? await resolveModel(engine, {
+      configKey: 'models.propose_takes',
+      fallback: getChatModel(),
+    });
     const proposalRunId = `propose-${new Date().toISOString().slice(0, 19).replace(/[-:T]/g, '')}-${randomUUID().slice(0, 8)}`;
 
     const result: ProposeTakesResult = {
@@ -330,8 +348,6 @@ class ProposeTakesPhase extends BaseCyclePhase {
       opts.reporter.start('propose_takes.pages' as never, pages.length);
     }
 
-    const modelId = opts.model ?? getChatModel();
-
     for (const page of pages) {
       result.pages_scanned += 1;
       this.tick(opts);
@@ -361,7 +377,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
 
       // Budget pre-check before the LLM call. Estimate: ~1500 input tokens + 500 output.
       const budget = this.checkBudget({
-        modelId,
+        modelId: extractorModelId,
         estimatedInputTokens: 1500,
         maxOutputTokens: 500,
       });
@@ -380,7 +396,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
           pagePath: page.slug,
           pageBody: body,
           existingTakes,
-          modelHint: opts.model,
+          modelHint: extractorModelId,
         });
       } catch (err) {
         const msg = err instanceof Error ? err.message : String(err);
@@ -388,16 +404,42 @@ class ProposeTakesPhase extends BaseCyclePhase {
         continue;
       }
 
-      // Write proposals to take_proposals. Each row is a separate INSERT
-      // because the composite idempotency key is on the per-page tuple — a
-      // bulk UPSERT would collapse a same-page-multi-claim run into one row.
-      for (const p of proposals) {
+      // Zero-claim scans MUST still enter the idempotency cache. Pre-v125
+      // only proposal rows were written, so a page whose extraction yielded
+      // no gradeable claims never got a row for its (page, content_hash) —
+      // the cache check above missed on every subsequent cycle and the LLM
+      // call was re-spent on the same unchanged page, forever. The sentinel
+      // row (status='empty', empty claim_text) is invisible to the review
+      // queue (pending_idx is partial on status='pending'); it exists only
+      // so the cache check hits.
+      if (proposals.length === 0) {
         await engine.executeRaw(
+          `INSERT INTO take_proposals
+             (source_id, page_slug, content_hash, prompt_version, proposal_run_id,
+              status, claim_text, kind, holder, weight, domain, dedup_against_fence_rows, model_id)
+           VALUES ($1, $2, $3, $4, $5, 'empty', '', 'none', 'brain', 0, NULL, NULL, $6)
+           ON CONFLICT (source_id, page_slug, content_hash, prompt_version, md5(claim_text)) DO NOTHING`,
+          [sourceId, page.slug, ch, promptVersion, proposalRunId, extractorModelId],
+        );
+        continue;
+      }
+
+      // Write proposals to take_proposals, one row per claim. The v125
+      // idempotency index includes md5(claim_text), so a same-page
+      // multi-claim run keeps EVERY claim — the pre-v125 four-column unique
+      // index made claims 2..N conflict with claim 1 and ON CONFLICT DO
+      // NOTHING silently dropped them (the review queue only ever saw the
+      // first claim of each page version). RETURNING id keeps
+      // proposals_inserted honest: it counts rows that actually landed,
+      // not insert attempts.
+      for (const p of proposals) {
+        const landed = await engine.executeRaw<{ id: number }>(
           `INSERT INTO take_proposals
              (source_id, page_slug, content_hash, prompt_version, proposal_run_id,
               claim_text, kind, holder, weight, domain, dedup_against_fence_rows, model_id)
            VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12)
-           ON CONFLICT (source_id, page_slug, content_hash, prompt_version) DO NOTHING`,
+           ON CONFLICT (source_id, page_slug, content_hash, prompt_version, md5(claim_text)) DO NOTHING
+           RETURNING id`,
           [
             sourceId,
             page.slug,
@@ -410,10 +452,10 @@ class ProposeTakesPhase extends BaseCyclePhase {
             p.weight,
             p.domain ?? null,
             JSON.stringify(existingTakes),
-            modelId,
+            extractorModelId,
           ],
         );
-        result.proposals_inserted += 1;
+        if (landed.length > 0) result.proposals_inserted += 1;
       }
     }
 

src/core/cycle/synthesize.ts

@@ -58,8 +58,11 @@ const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
  * resolver returns for known Anthropic aliases.
  */
 const MODEL_CONTEXT_TOKENS: Record<string, number> = {
+  'claude-fable-5': 1_000_000,
+  'claude-opus-4-8': 1_000_000,
   'claude-opus-4-7': 1_000_000,
   'claude-opus-4-6': 1_000_000,
+  'claude-sonnet-5': 1_000_000,
   'claude-sonnet-4-6': 200_000,
   'claude-sonnet-4-5': 200_000,
   'claude-haiku-4-5-20251001': 200_000,

src/core/migrate.ts

@@ -5671,6 +5671,41 @@ export const MIGRATIONS: Migration[] = [
 `);
     },
   },
+  {
+    version: 125,
+    name: 'take_proposals_empty_scan_sentinels_and_per_claim_rows',
+    // v0.42.x — kill the propose_takes rescan loop + stop dropping claims.
+    //
+    // Two defects, one schema touch:
+    //   1. Zero-claim scans never entered the idempotency cache (only
+    //      proposal rows were written), so pages whose extraction yielded
+    //      nothing were re-extracted on EVERY cycle. Observed live: ~60
+    //      such pages per run ≈ 1,400 wasted extractor calls / ~$15 per
+    //      day — ~90% of total autopilot LLM spend. Fix: the phase now
+    //      writes a status='empty' sentinel row per zero-claim scan; the
+    //      status CHECK gains the 'empty' value. Sentinels are excluded
+    //      from the partial pending index, so the review queue never sees
+    //      them.
+    //   2. The 4-column unique index collapsed a same-page multi-claim run
+    //      to its FIRST claim: rows 2..N conflicted and ON CONFLICT DO
+    //      NOTHING silently dropped them (verified live: exactly one row
+    //      per (page, hash) across 3 days of runs). Fix: the idempotency
+    //      index gains md5(claim_text) — per-claim rows, while the
+    //      4-column prefix still serves the per-scan cache lookup.
+    //
+    // Existing data is index-safe by construction: the old index guaranteed
+    // at most one row per 4-tuple, so the widened index has no duplicates
+    // to trip on. The DROP+ADD CONSTRAINT pair is idempotent as a unit.
+    idempotent: true,
+    sql: `
+      ALTER TABLE take_proposals DROP CONSTRAINT IF EXISTS take_proposals_status_check;
+      ALTER TABLE take_proposals ADD CONSTRAINT take_proposals_status_check
+        CHECK (status IN ('pending','accepted','rejected','superseded','empty'));
+      DROP INDEX IF EXISTS take_proposals_idempotency_idx;
+      CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
+        ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
+    `,
+  },
 ];
 
 export const LATEST_VERSION = MIGRATIONS.length > 0

src/core/operations.ts

@@ -3289,7 +3289,7 @@ const get_calibration_profile: Operation = {
     holder: {
       type: 'string',
       description:
-        "Holder slug, e.g. 'self' or 'people/charlie-example'. Defaults to config emotional_weight.user_holder, else 'self', when omitted.",
+        "Holder slug, e.g. 'garry' or 'people/charlie-example'. Defaults to 'garry' when omitted.",
     },
   },
   handler: async (ctx, p) => {

src/core/owner-holder.ts

@@ -1,24 +0,0 @@
-/**
- * Canonical holder string for "the brain owner," resolved in ONE place so the
- * calibration / think / doctor / emotional-weight defaults stop disagreeing.
- *
- * The default matches the consolidate facts→takes writer
- * (src/core/cycle/phases/consolidate.ts: holder:'self') and docs/takes-vs-facts.md.
- * Do NOT introduce a fourth literal — three already exist historically
- * ('garry', 'system', 'self'); this is the source of truth.
- *
- * NORMALIZATION NOTE: the brain owner may also appear under other holder
- * strings — 'brain' (propose_takes when the author asserts a claim) and
- * people/<owner> (extraction that names the owner). This resolver only selects
- * the *default* canonical owner string for reads; it does NOT merge those other
- * strings. Unifying them is owner-identity entity-resolution, tracked separately
- * (see garrytan/gbrain#2465). Until then, historical owner takes
- * under 'brain'/people-<owner> are not folded into the default profile.
- */
-export const DEFAULT_OWNER_HOLDER = 'self';
-
-export function resolveOwnerHolder(
-  opts: { override?: string | null; configValue?: string | null },
-): string {
-  return opts.override ?? opts.configValue ?? DEFAULT_OWNER_HOLDER;
-}

src/core/pglite-schema.ts

@@ -762,7 +762,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   proposed_at                 TIMESTAMPTZ  NOT NULL DEFAULT now(),
   proposal_run_id             TEXT         NOT NULL,
   status                      TEXT         NOT NULL DEFAULT 'pending'
-                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
   claim_text                  TEXT         NOT NULL,
   kind                        TEXT         NOT NULL,
   holder                      TEXT         NOT NULL,
@@ -777,7 +777,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   predicted_brier_bucket_n    INTEGER
 );
 CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
-  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

src/core/schema-embedded.ts

@@ -1274,8 +1274,14 @@ CREATE INDEX IF NOT EXISTS calibration_profiles_published_idx
   WHERE published = true;
 
 -- take_proposals: propose_takes phase queue. Idempotency cache via the
--- composite unique index (source_id, page_slug, content_hash, prompt_version)
--- mirrors v0.23 dream_verdicts. proposal_run_id supports --rollback by run.
+-- composite unique index (source_id, page_slug, content_hash, prompt_version,
+-- md5(claim_text)) — the 4-column prefix is the per-scan cache key (mirrors
+-- v0.23 dream_verdicts); md5(claim_text) makes rows per-claim so multi-claim
+-- pages keep every claim (v125). status='empty' rows are zero-claim scan
+-- sentinels: they hold the cache slot for a page version whose extraction
+-- yielded nothing — the phase never re-spends the LLM call on that page
+-- version. Excluded from the partial pending index. proposal_run_id supports
+-- --rollback by run.
 CREATE TABLE IF NOT EXISTS take_proposals (
   id                          BIGSERIAL PRIMARY KEY,
   source_id                   TEXT         NOT NULL REFERENCES sources(id) ON DELETE CASCADE,
@@ -1286,7 +1292,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   proposed_at                 TIMESTAMPTZ  NOT NULL DEFAULT now(),
   proposal_run_id             TEXT         NOT NULL,
   status                      TEXT         NOT NULL DEFAULT 'pending'
-                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
   claim_text                  TEXT         NOT NULL,
   kind                        TEXT         NOT NULL,
   holder                      TEXT         NOT NULL,
@@ -1301,7 +1307,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   predicted_brier_bucket_n    INTEGER
 );
 CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
-  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

src/core/think/index.ts

@@ -23,7 +23,6 @@ import { runGather, renderPagesBlock, takesHitToTakeForPrompt } from './gather.t
 import { renderTakesBlock } from './sanitize.ts';
 import { buildThinkSystemPrompt, buildThinkUserMessage } from './prompt.ts';
 import { resolveCitations, type ParsedCitation } from './cite-render.ts';
-import { resolveOwnerHolder } from '../owner-holder.ts';
 import { resolveModel } from '../model-config.ts';
 import { chat as gatewayChat, probeChatModel, type ChatResult } from '../ai/gateway.ts';
 import { AIConfigError } from '../ai/errors.ts';
@@ -77,8 +76,8 @@ export interface RunThinkOpts {
    */
   withCalibration?: boolean;
   /**
-   * Holder to retrieve the calibration profile for. Resolves via resolveOwnerHolder
-   * (config emotional_weight.user_holder, else 'self'). Only consulted when withCalibration=true.
+   * Holder to retrieve the calibration profile for. Default 'garry'. Only
+   * consulted when withCalibration=true.
    */
   calibrationHolder?: string;
   /**
@@ -309,10 +308,7 @@ export async function runThink(
     try {
       const { getLatestProfile } = await import('../../commands/calibration.ts');
       const profile = await getLatestProfile(engine, {
-        holder: resolveOwnerHolder({
-          override: opts.calibrationHolder,
-          configValue: await engine.getConfig('emotional_weight.user_holder'),
-        }),
+        holder: opts.calibrationHolder ?? 'garry',
       });
       if (profile) {
         calibrationBlockOpts = {

src/schema.sql

@@ -1270,8 +1270,14 @@ CREATE INDEX IF NOT EXISTS calibration_profiles_published_idx
   WHERE published = true;
 
 -- take_proposals: propose_takes phase queue. Idempotency cache via the
--- composite unique index (source_id, page_slug, content_hash, prompt_version)
--- mirrors v0.23 dream_verdicts. proposal_run_id supports --rollback by run.
+-- composite unique index (source_id, page_slug, content_hash, prompt_version,
+-- md5(claim_text)) — the 4-column prefix is the per-scan cache key (mirrors
+-- v0.23 dream_verdicts); md5(claim_text) makes rows per-claim so multi-claim
+-- pages keep every claim (v125). status='empty' rows are zero-claim scan
+-- sentinels: they hold the cache slot for a page version whose extraction
+-- yielded nothing — the phase never re-spends the LLM call on that page
+-- version. Excluded from the partial pending index. proposal_run_id supports
+-- --rollback by run.
 CREATE TABLE IF NOT EXISTS take_proposals (
   id                          BIGSERIAL PRIMARY KEY,
   source_id                   TEXT         NOT NULL REFERENCES sources(id) ON DELETE CASCADE,
@@ -1282,7 +1288,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   proposed_at                 TIMESTAMPTZ  NOT NULL DEFAULT now(),
   proposal_run_id             TEXT         NOT NULL,
   status                      TEXT         NOT NULL DEFAULT 'pending'
-                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded','empty')),
   claim_text                  TEXT         NOT NULL,
   kind                        TEXT         NOT NULL,
   holder                      TEXT         NOT NULL,
@@ -1297,7 +1303,7 @@ CREATE TABLE IF NOT EXISTS take_proposals (
   predicted_brier_bucket_n    INTEGER
 );
 CREATE UNIQUE INDEX IF NOT EXISTS take_proposals_idempotency_idx
-  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version, md5(claim_text));
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

test/calibration-cli.test.ts

@@ -27,12 +27,6 @@ function buildMockEngine(opts: { rows: CalibrationProfileRow[] }): {
   const capturedParams: unknown[][] = [];
   const engine = {
     kind: 'pglite',
-    // #2464: getCalibrationProfileOp resolves the owner holder via
-    // resolveOwnerHolder(config emotional_weight.user_holder, else 'self'), so the
-    // mock must implement getConfig. null = key unset → resolver falls back to 'self'.
-    async getConfig(): Promise<string | null> {
-      return null;
-    },
     async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
       capturedSql.push(sql);
       capturedParams.push(params ?? []);
@@ -217,17 +211,17 @@ describe('formatProfileText', () => {
 // ─── getCalibrationProfileOp ────────────────────────────────────────
 
 describe('getCalibrationProfileOp (MCP)', () => {
-  test('defaults holder to "self" when omitted (config emotional_weight.user_holder unset)', async () => {
-    const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'self' })] });
+  test('defaults holder to "garry" when omitted', async () => {
+    const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'garry' })] });
     const ctx = buildCtx(engine);
     const result = await getCalibrationProfileOp(ctx, {});
-    expect(result?.holder).toBe('self');
+    expect(result?.holder).toBe('garry');
   });
 
   test('routes through sourceScopeOpts: scalar source-bound client gets source-scoped result', async () => {
     const rows = [
-      buildProfile({ holder: 'self', source_id: 'default' }),
-      buildProfile({ holder: 'self', source_id: 'tenant-b' }),
+      buildProfile({ holder: 'garry', source_id: 'default' }),
+      buildProfile({ holder: 'garry', source_id: 'tenant-b' }),
     ];
     const { engine } = buildMockEngine({ rows });
     const ctx = buildCtx(engine, { sourceId: 'tenant-b' });
@@ -237,8 +231,8 @@ describe('getCalibrationProfileOp (MCP)', () => {
 
   test('federated read scope sees the union of allowed sources', async () => {
     const rows = [
-      buildProfile({ holder: 'self', source_id: 'tenant-a' }),
-      buildProfile({ holder: 'self', source_id: 'tenant-z' }),
+      buildProfile({ holder: 'garry', source_id: 'tenant-a' }),
+      buildProfile({ holder: 'garry', source_id: 'tenant-z' }),
     ];
     const { engine } = buildMockEngine({ rows });
     const ctx = buildCtx(engine, { allowedSources: ['tenant-a', 'tenant-b'] });

test/calibration-profile.test.ts

@@ -32,20 +32,17 @@ interface CapturedSql {
   params: unknown[];
 }
 
-function buildMockEngine(opts: { scorecard: TakesScorecard; userHolder?: string | null }): {
+function buildMockEngine(opts: { scorecard: TakesScorecard }): {
   engine: BrainEngine;
   captured: CapturedSql[];
 } {
   const captured: CapturedSql[] = [];
   const engine = {
+    async getConfig() { return null; },
     kind: 'pglite',
     async getScorecard() {
       return opts.scorecard;
     },
-    async getConfig(key: string): Promise<string | null> {
-      if (key === 'emotional_weight.user_holder') return opts.userHolder ?? null;
-      return null;
-    },
     async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
       captured.push({ sql, params: params ?? [] });
       return [];
@@ -238,7 +235,7 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
     // grade_completion, domain_scorecards_json, patterns[], voice_passed, voice_attempts,
     // bias_tags[], model_id
     expect(insert!.params[0]).toBe('default'); // source_id
-    expect(insert!.params[1]).toBe('self'); // holder (resolved via resolveOwnerHolder, no override)
+    expect(insert!.params[1]).toBe('garry'); // holder
     expect(insert!.params[2]).toBe(12); // total_resolved
     expect(insert!.params[9]).toBe(true); // voice_gate_passed
     expect(insert!.params[10]).toBe(1); // voice_gate_attempts
@@ -334,24 +331,4 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
     const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
     expect(insert!.params[0]).toBe('tenant-b');
   });
-
-  test('cold-brain summary uses resolved owner holder self when user_holder unset', async () => {
-    const { engine } = buildMockEngine({
-      scorecard: { total_bets: 0, resolved: 0, correct: 0, incorrect: 0, partial: 0,
-        accuracy: null, brier: null, partial_rate: null, unresolvable_count: 0, unresolvable_rate: null },
-    });
-    const result = await runPhaseCalibrationProfile(buildCtx(engine), {});
-    expect(result.summary).toContain('holder=self');
-    expect(result.summary).not.toContain('holder=garry');
-  });
-
-  test('configured user_holder overrides the default in the cold-brain summary', async () => {
-    const { engine } = buildMockEngine({
-      scorecard: { total_bets: 0, resolved: 0, correct: 0, incorrect: 0, partial: 0,
-        accuracy: null, brier: null, partial_rate: null, unresolvable_count: 0, unresolvable_rate: null },
-      userHolder: 'people/charlie-example',
-    });
-    const result = await runPhaseCalibrationProfile(buildCtx(engine), {});
-    expect(result.summary).toContain('holder=people/charlie-example');
-  });
 });

test/doctor-calibration-checks.test.ts

@@ -32,12 +32,6 @@ function buildMockEngine(opts: {
 }): BrainEngine {
   return {
     kind: 'pglite',
-    // #2464: checkCalibrationFreshness resolves the owner holder via
-    // resolveOwnerHolder(config emotional_weight.user_holder, else 'self'), so the
-    // mock must implement getConfig. null = key unset → resolver falls back to 'self'.
-    async getConfig(): Promise<string | null> {
-      return null;
-    },
     async executeRaw<T>(sql: string): Promise<T[]> {
       if (opts.throwOn && opts.throwOn.test(sql)) {
         throw new Error('mock engine error: ' + sql.slice(0, 50));

test/emotional-weight.test.ts

@@ -112,7 +112,3 @@ describe('computeEmotionalWeight', () => {
     expect(HIGH_EMOTION_TAGS.has('mental-health')).toBe(true);
   });
 });
-
-test('DEFAULT_USER_HOLDER is the canonical owner holder self', () => {
-  expect(DEFAULT_USER_HOLDER).toBe('self');
-});

test/grade-takes-ensemble.test.ts

@@ -47,6 +47,7 @@ function buildMockEngine(opts: { takes: Take[] }): {
   const captured: CapturedSql[] = [];
   const resolves: CapturedResolve[] = [];
   const engine = {
+    async getConfig() { return null; },
     kind: 'pglite',
     async listTakes() {
       return opts.takes;

test/grade-takes.test.ts

@@ -46,12 +46,14 @@ interface CapturedResolve {
 function buildMockEngine(opts: {
   takes: Take[];
   cachedGrades?: Set<string>; // composite-key strings already in take_grade_cache
+  config?: Record<string, string>; // engine.getConfig plane (models.grade_takes etc.)
 }): { engine: BrainEngine; captured: CapturedSql[]; resolves: CapturedResolve[] } {
   const captured: CapturedSql[] = [];
   const resolves: CapturedResolve[] = [];
   const cached = opts.cachedGrades ?? new Set<string>();
 
   const engine = {
+    async getConfig(key: string) { return opts.config?.[key] ?? null; },
     kind: 'pglite',
     async listTakes() {
       return opts.takes;
@@ -224,6 +226,28 @@ describe('runPhaseGradeTakes — phase integration', () => {
     expect(resolves).toHaveLength(0); // no canonical mutation
   });
 
+  test('models.grade_takes config drives the judge call; cache key stays bare-tailed', async () => {
+    // Pre-fix the judge call rode the gateway's chat_model while the cache
+    // key / budget label recorded a hardcoded 'claude-sonnet-4-6'. The phase
+    // now resolves models.grade_takes; the judge gets the FULL string and
+    // the cache row keys on the bare tail (continuity with historical rows).
+    const takes = [buildTake({ id: 1, sinceDate: '2023-01-01' })];
+    const { engine, captured } = buildMockEngine({
+      takes,
+      config: { 'models.grade_takes': 'anthropic:claude-sonnet-5' },
+    });
+    const hints: Array<string | undefined> = [];
+    const judge: JudgeFn = async ({ modelHint }) => {
+      hints.push(modelHint);
+      return { verdict: 'correct', confidence: 0.9, reasoning: 'held' };
+    };
+    const result = await runPhaseGradeTakes(buildCtx(engine), { judge });
+    expect(result.status).toBe('ok');
+    expect(hints).toEqual(['anthropic:claude-sonnet-5']); // actual call gets the FULL string
+    const inserts = captured.filter(c => c.sql.includes('INSERT INTO take_grade_cache'));
+    expect(inserts[0]!.params[2]).toBe('claude-sonnet-5'); // judge_model_id is the bare tail
+  });
+
   test('D17: auto-resolve OFF by default — even high-confidence verdict does NOT mutate takes', async () => {
     const takes = [buildTake({ id: 1, sinceDate: '2023-01-01' })];
     const { engine, resolves } = buildMockEngine({ takes });

test/owner-holder.test.ts

@@ -1,27 +0,0 @@
-import { describe, test, expect } from 'bun:test';
-import { resolveOwnerHolder, DEFAULT_OWNER_HOLDER } from '../src/core/owner-holder.ts';
-
-describe('owner-holder', () => {
-  test('DEFAULT_OWNER_HOLDER is self', () => {
-    expect(DEFAULT_OWNER_HOLDER).toBe('self');
-  });
-
-  test('defaults to self when nothing provided', () => {
-    expect(resolveOwnerHolder({})).toBe('self');
-  });
-
-  test('null/undefined config falls back to self', () => {
-    expect(resolveOwnerHolder({ configValue: null })).toBe('self');
-    expect(resolveOwnerHolder({ configValue: undefined })).toBe('self');
-  });
-
-  test('uses config value when set and no override', () => {
-    expect(resolveOwnerHolder({ configValue: 'people/charlie-example' }))
-      .toBe('people/charlie-example');
-  });
-
-  test('override beats config and default', () => {
-    expect(resolveOwnerHolder({ override: 'world', configValue: 'people/charlie-example' }))
-      .toBe('world');
-  });
-});

test/propose-takes-rescan.test.ts

@@ -0,0 +1,160 @@
+/**
+ * propose_takes rescan-loop + dropped-claims regression tests (migration v125).
+ *
+ * Two live-observed defects, both fixed by the v125 schema + phase change:
+ *
+ *   1. RESCAN LOOP — a page whose extraction yielded zero claims never
+ *      entered the idempotency cache (only proposal rows were written), so
+ *      every cycle re-spent the extractor call on the same unchanged page.
+ *      Live impact: ~60 such pages × every cycle ≈ 1,400 wasted LLM calls
+ *      (~$15) per day — ~90% of total autopilot spend. Fix: status='empty'
+ *      sentinel row per zero-claim scan.
+ *
+ *   2. DROPPED CLAIMS — the 4-column unique index collapsed a same-page
+ *      multi-claim run to its first claim (rows 2..N conflicted, ON CONFLICT
+ *      DO NOTHING dropped them silently; verified live: exactly 1 row per
+ *      (page, hash) over 3 days). Fix: idempotency index gains
+ *      md5(claim_text).
+ *
+ * Hermetic: PGLite engine + injected extractor; no gateway, no LLM.
+ */
+import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { runPhaseProposeTakes, type ProposeTakesExtractor, type ProposedTake } from '../src/core/cycle/propose-takes.ts';
+import type { OperationContext } from '../src/core/operations.ts';
+
+let engine: PGLiteEngine;
+
+function ctx(): OperationContext {
+  return {
+    engine,
+    remote: false,
+    config: {} as OperationContext['config'],
+    logger: { info() {}, warn() {}, error() {}, debug() {} } as unknown as OperationContext['logger'],
+  } as unknown as OperationContext;
+}
+
+/** Extractor stub that counts invocations per page slug. */
+function countingExtractor(
+  claimsBySlug: Record<string, ProposedTake[]>,
+): { extractor: ProposeTakesExtractor; calls: string[] } {
+  const calls: string[] = [];
+  const extractor: ProposeTakesExtractor = async ({ pagePath }) => {
+    calls.push(pagePath);
+    return claimsBySlug[pagePath] ?? [];
+  };
+  return { extractor, calls };
+}
+
+beforeAll(async () => {
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+  await engine.putPage('notes/zero-claims', {
+    type: 'note',
+    title: 'pure narrative',
+    compiled_truth: 'A quiet walk in the park. Nothing opinionated happened at all today.',
+  });
+  await engine.putPage('notes/three-claims', {
+    type: 'note',
+    title: 'opinionated',
+    compiled_truth: 'I bet acme-example wins the market. widget-co will struggle. fund-a is overexposed.',
+  });
+});
+
+afterAll(async () => {
+  await engine.disconnect();
+});
+
+describe('rescan loop — zero-claim scans enter the cache', () => {
+  test('second run cache-hits: extractor is NOT called again on unchanged pages', async () => {
+    const claims = {
+      'notes/three-claims': [
+        { claim_text: 'acme-example wins the market', kind: 'bet' as const, holder: 'brain', weight: 0.7 },
+        { claim_text: 'widget-co will struggle', kind: 'take' as const, holder: 'brain', weight: 0.6 },
+        { claim_text: 'fund-a is overexposed', kind: 'take' as const, holder: 'brain', weight: 0.55 },
+      ],
+    };
+
+    const first = countingExtractor(claims);
+    const r1 = await runPhaseProposeTakes(ctx(), { extractor: first.extractor });
+    expect(r1.status).toBe('ok');
+    // Both pages extracted on the first pass.
+    expect(first.calls).toContain('notes/zero-claims');
+    expect(first.calls).toContain('notes/three-claims');
+
+    const second = countingExtractor(claims);
+    const r2 = await runPhaseProposeTakes(ctx(), { extractor: second.extractor });
+    expect(r2.status).toBe('ok');
+    // THE regression: pre-fix the zero-claim page missed the cache every
+    // run and was re-extracted here. (Run 1's receipt page legitimately
+    // appears once — it's a new page — and its zero-claim scan now caches
+    // too; pre-fix, receipts re-scanned forever as well.)
+    expect(second.calls).not.toContain('notes/zero-claims');
+    expect(second.calls).not.toContain('notes/three-claims');
+
+    // Run 2 inserted nothing, so no new receipt page exists: run 3 must be
+    // fully quiescent — zero extractor calls, zero cache misses.
+    const third = countingExtractor(claims);
+    const r3 = await runPhaseProposeTakes(ctx(), { extractor: third.extractor });
+    expect(r3.status).toBe('ok');
+    expect(third.calls).toEqual([]);
+    expect((r3.details as Record<string, unknown>).cache_misses).toBe(0);
+  });
+
+  test('zero-claim scan wrote an "empty" sentinel invisible to the pending queue', async () => {
+    const sentinel = await engine.executeRaw<{ status: string; claim_text: string }>(
+      `SELECT status, claim_text FROM take_proposals WHERE page_slug = 'notes/zero-claims'`,
+      [],
+    );
+    expect(sentinel.length).toBe(1);
+    expect(sentinel[0].status).toBe('empty');
+    expect(sentinel[0].claim_text).toBe('');
+    const pending = await engine.executeRaw<{ n: number }>(
+      `SELECT COUNT(*)::int AS n FROM take_proposals WHERE page_slug = 'notes/zero-claims' AND status = 'pending'`,
+      [],
+    );
+    expect(Number(pending[0].n)).toBe(0);
+  });
+});
+
+describe('dropped claims — per-claim rows survive the idempotency index', () => {
+  test('a 3-claim page stores 3 rows and reports an honest inserted count', async () => {
+    const rows = await engine.executeRaw<{ claim_text: string }>(
+      `SELECT claim_text FROM take_proposals WHERE page_slug = 'notes/three-claims' AND status = 'pending' ORDER BY id`,
+      [],
+    );
+    // Pre-fix the 4-column unique index kept only the FIRST claim.
+    expect(rows.length).toBe(3);
+    expect(rows.map(r => r.claim_text)).toEqual([
+      'acme-example wins the market',
+      'widget-co will struggle',
+      'fund-a is overexposed',
+    ]);
+  });
+
+  test('content change re-extracts and stores the new version separately', async () => {
+    await engine.putPage('notes/zero-claims', {
+      type: 'note',
+      title: 'pure narrative',
+      compiled_truth: 'Updated: I now believe acme-example is undervalued and will re-rate within a year.',
+    });
+    const claims = {
+      'notes/zero-claims': [
+        { claim_text: 'acme-example is undervalued', kind: 'take' as const, holder: 'brain', weight: 0.6 },
+      ],
+    };
+    const run = countingExtractor(claims);
+    const r = await runPhaseProposeTakes(ctx(), { extractor: run.extractor });
+    expect(r.status).toBe('ok');
+    // Changed page re-extracts; the unchanged 3-claim page stays cached.
+    expect(run.calls).toEqual(['notes/zero-claims']);
+    expect((r.details as Record<string, unknown>).proposals_inserted).toBe(1);
+    const all = await engine.executeRaw<{ status: string }>(
+      `SELECT status FROM take_proposals WHERE page_slug = 'notes/zero-claims' ORDER BY id`,
+      [],
+    );
+    // Old hash's sentinel + new hash's pending claim coexist.
+    expect(all.map(r2 => r2.status).sort()).toEqual(['empty', 'pending']);
+  });
+});

test/propose-takes.test.ts

@@ -41,12 +41,16 @@ interface CapturedSql {
 function buildMockEngine(opts: {
   pages: Page[];
   existingProposals?: Set<string>; // composite-key strings already in take_proposals
+  config?: Record<string, string>; // engine.getConfig plane (models.tier.* etc.)
 }): { engine: BrainEngine; captured: CapturedSql[] } {
   const captured: CapturedSql[] = [];
   const existing = opts.existingProposals ?? new Set<string>();
 
   const engine = {
     kind: 'pglite',
+    async getConfig(key: string) {
+      return opts.config?.[key] ?? null;
+    },
     async listPages() {
       return opts.pages;
     },
@@ -59,7 +63,12 @@ function buildMockEngine(opts: {
         if (existing.has(key)) return [{ id: 1 } as unknown as T];
         return [];
       }
-      // INSERT — return nothing
+      // INSERT ... RETURNING id — emulate a successful insert so the
+      // honest proposals_inserted counter (counts RETURNING rows, not
+      // attempts) sees the row land. Conflicted inserts would return [].
+      if (sql.includes('INSERT INTO take_proposals') && sql.includes('RETURNING id')) {
+        return [{ id: 1 } as unknown as T];
+      }
       return [];
     },
   } as unknown as BrainEngine;
@@ -267,6 +276,29 @@ describe('runPhaseProposeTakes — phase integration', () => {
     expect(inserts[0]!.params[9]).toBe('market'); // domain
   });
 
+  test('extractor model resolves through models.propose_takes config', async () => {
+    // Pre-fix the phase's only model knob was the gateway chat model — there
+    // was no per-phase config key. The phase now resolves once via
+    // resolveModel(models.propose_takes > models.default > env > gateway
+    // chat model); the extractor hint and the stored model_id must both
+    // reflect the configured override (full provider-prefixed string, #2451).
+    const pages = [buildPage({ slug: 'wiki/concepts/tier-routing', body: 'Tier-routed models will win.' })];
+    const { engine, captured } = buildMockEngine({
+      pages,
+      config: { 'models.propose_takes': 'anthropic:claude-sonnet-5' },
+    });
+    const seen: Array<string | undefined> = [];
+    const extractor: ProposeTakesExtractor = async ({ modelHint }) => {
+      seen.push(modelHint);
+      return [{ claim_text: 'tier-routed models win', kind: 'bet', holder: 'brain', weight: 0.7 }];
+    };
+    const result = await runPhaseProposeTakes(buildCtx(engine), { extractor });
+    expect(result.status).toBe('ok');
+    expect(seen).toEqual(['anthropic:claude-sonnet-5']); // chat call gets the FULL string
+    const inserts = captured.filter(c => c.sql.includes('INSERT INTO take_proposals'));
+    expect(inserts[0]!.params[11]).toBe('anthropic:claude-sonnet-5'); // stored model_id matches the call
+  });
+
   test('cache hit: page already in take_proposals is skipped', async () => {
     const body = 'A page that was already processed.';
     const pages = [buildPage({ slug: 'wiki/old-page', body })];