fix(search): match both slash-split and literal slash forms in FTS queries (#2380 review)

Review finding on the normalize-only approach: Postgres' text-search
parser emits the joined file-alias lexeme on the INDEX side too
(to_tsvector('english','acme/widget') -> 'acme/widget'), so replacing
'/' with whitespace in the query made documents containing the literal
slash form (file paths, URLs, pasted titles) unreachable — the split-word
AND pass can't match the joined lexeme and the OR fallback can't either.
Pre-fix, those exact-form queries DID match.

Replace the TS-side normalizeKeywordQuery with buildWebsearchQueryExpr
in sql-ranking.ts (shared by both engines, keeping them in lockstep): a
slash-bearing query now binds the raw text once and matches
(websearch_to_tsquery(translate($1,'/',' ')) || websearch_to_tsquery($1))
— split-word prose AND literal slash forms alike. Slash-free queries keep
the byte-identical single-parse SQL and identical ts_rank.

New regression test pins the literal-slash arm (verified failing under
the normalize-only expression); the two AND-vs-OR slash tests still pass.

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

src/commands/doctor.ts

@@ -820,6 +820,10 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
   // v0.42.x (#1794, 4A): pool-budget nudge when GBRAIN_MAX_CONNECTIONS is set.
   checks.push(await checkPoolBudget(engine));
 
+  // #2552: warn when an explicit embed-concurrency override fans out against
+  // a local single-slot embedding endpoint (silent backfill starvation).
+  checks.push(await checkEmbedConcurrency());
+
   // v0.42.7 (#1696): link-extraction lag. Strictly SQL (single indexed COUNT),
   // safe on the thin-client/remote path — remote operators on checkout-less
   // Postgres brains are exactly who can't otherwise see the extraction backlog.
@@ -3815,6 +3819,61 @@ export function computePoolBudgetCheck(
   };
 }
 
+/**
+ * #2552: warn when an explicit GBRAIN_EMBED_CONCURRENCY override fans out
+ * against a local single-slot embedding endpoint (Ollama / llama-server /
+ * localhost base URL). Requests serialize on the one loaded model, so N
+ * parallel pages multiply latency xN and can exceed the fetch timeout with
+ * no surfaced error — the backfill silently starves. (When the env var is
+ * unset, embed auto-caps at LOCAL_EMBED_CONCURRENCY_CAP and this check
+ * reports ok.) Pure; exported for tests.
+ */
+export function computeEmbedConcurrencyCheck(
+  isLocalEndpoint: boolean,
+  envValue: string | undefined,
+  localCap: number,
+): Check {
+  const name = 'embed_concurrency';
+  if (!isLocalEndpoint) {
+    return { name, status: 'ok', message: 'Embedding endpoint is not a local inference server — cloud concurrency defaults apply.' };
+  }
+  const parsed = envValue ? parseInt(envValue, 10) : NaN;
+  if (envValue && Number.isFinite(parsed) && parsed > localCap) {
+    return {
+      name,
+      status: 'warn',
+      message:
+        `GBRAIN_EMBED_CONCURRENCY=${parsed} against a local embedding endpoint. ` +
+        `Local inference servers serialize requests, so ${parsed} parallel pages multiply ` +
+        `latency x${parsed} and can exceed the fetch timeout — the embed backfill stalls ` +
+        `with no error. Unset GBRAIN_EMBED_CONCURRENCY (auto-caps at ${localCap}) or set it <= ${localCap}.`,
+    };
+  }
+  return {
+    name,
+    status: 'ok',
+    message: `Local embedding endpoint detected; embed concurrency capped at ${envValue ? parsed : localCap}.`,
+  };
+}
+
+/** Thin gateway/env wrapper over `computeEmbedConcurrencyCheck`. */
+export async function checkEmbedConcurrency(): Promise<Check> {
+  try {
+    const { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } = await import('../core/ai/gateway.ts');
+    return computeEmbedConcurrencyCheck(
+      isLocalEmbeddingEndpoint(),
+      process.env.GBRAIN_EMBED_CONCURRENCY,
+      LOCAL_EMBED_CONCURRENCY_CAP,
+    );
+  } catch (err) {
+    return {
+      name: 'embed_concurrency',
+      status: 'ok',
+      message: `Skipped (${err instanceof Error ? err.message : String(err)})`,
+    };
+  }
+}
+
 /** Thin env/engine wrapper over `computePoolBudgetCheck`. */
 export async function checkPoolBudget(_engine: BrainEngine): Promise<Check> {
   try {

src/commands/embed.ts

@@ -1,5 +1,6 @@
 import type { BrainEngine } from '../core/engine.ts';
 import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
+import { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } from '../core/ai/gateway.ts';
 import type { ChunkInput } from '../core/types.ts';
 import { chunkText } from '../core/chunkers/recursive.ts';
 import { createProgress, type ProgressReporter } from '../core/progress.ts';
@@ -176,6 +177,31 @@ export class EmbeddingDimMismatchError extends Error {
   }
 }
 
+/**
+ * #2552: resolve the bulk-embed worker count. Env override or the
+ * cloud-tuned default of 20 — but when the operator did NOT set
+ * GBRAIN_EMBED_CONCURRENCY and the embedding endpoint is a local inference
+ * server (Ollama / llama-server / localhost base URL), cap at
+ * LOCAL_EMBED_CONCURRENCY_CAP: 20 parallel pages against a single-slot
+ * server serialize on the one loaded model, multiply latency x20 past the
+ * fetch timeout, and starve the backfill with no surfaced error. An
+ * explicit env value always wins (`gbrain doctor` warns instead).
+ * Pacing only ever LOWERS concurrency (Codex P2).
+ */
+export function resolveEmbedConcurrency(paceMaxConcurrency?: number): number {
+  const envSet = !!process.env.GBRAIN_EMBED_CONCURRENCY;
+  const base = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
+  let resolved = base;
+  if (!envSet && isLocalEmbeddingEndpoint() && base > LOCAL_EMBED_CONCURRENCY_CAP) {
+    resolved = LOCAL_EMBED_CONCURRENCY_CAP;
+    serr(
+      `[embed] local embedding endpoint detected — capping concurrency at ` +
+      `${LOCAL_EMBED_CONCURRENCY_CAP} (set GBRAIN_EMBED_CONCURRENCY to override)`,
+    );
+  }
+  return paceMaxConcurrency ? Math.min(resolved, paceMaxConcurrency) : resolved;
+}
+
 /**
  * Pre-flight check: read the actual schema column dim and compare to the
  * gateway's resolved dim. Throws `EmbeddingDimMismatchError` on mismatch
@@ -677,10 +703,8 @@ async function embedAll(
   // Paced runs lower this to the resolved cap (the real lever vs pooler-slot
   // starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
   // never raise above an operator's existing env cap.
-  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  const CONCURRENCY = staleOpts?.paceMaxConcurrency
-    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
-    : BASE_CONCURRENCY;
+  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
+  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
 
   async function embedOnePage(page: typeof pages[number]) {
     // #1737: bail before doing any work for this page if the run was aborted.
@@ -855,10 +879,8 @@ async function embedAllStale(
   // Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
   // lever on this single pool, no separate permit). Codex P2: pacing only ever
   // LOWERS concurrency — never raise above an operator's existing env cap.
-  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  const CONCURRENCY = staleOpts?.paceMaxConcurrency
-    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
-    : BASE_CONCURRENCY;
+  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
+  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
   const pacer = staleOpts?.pacer ?? createNoopPacer();
 
   // D3 + D3a + D8: wall-clock budget. 30 min default; env override.

src/commands/models.ts

@@ -50,10 +50,6 @@ 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/core/ai/gateway.ts

@@ -683,6 +683,33 @@ export function getEmbeddingDimensions(): number {
   return requireConfig().embedding_dimensions ?? DEFAULT_EMBEDDING_DIMENSIONS;
 }
 
+/**
+ * #2552: cap for parallel bulk-embed workers against a local inference
+ * server. A single-slot Ollama/llama-server serializes requests, so the
+ * cloud-tuned 20-worker fan-out multiplies latency x20 and blows past the
+ * fetch timeout with no surfaced error (the backfill silently starves).
+ */
+export const LOCAL_EMBED_CONCURRENCY_CAP = 2;
+
+/**
+ * #2552: true when the configured embedding model routes to a local
+ * inference server — the `ollama` / `llama-server` recipes, or any recipe
+ * whose base URL was explicitly pointed at localhost. Bulk callers use this
+ * to pick CPU-safe concurrency defaults; `gbrain doctor` uses it to warn
+ * about an explicit cloud-sized override. Fail-open: unconfigured or
+ * unresolvable gateway → false (cloud behavior, the historical default).
+ */
+export function isLocalEmbeddingEndpoint(): boolean {
+  try {
+    const { recipe } = resolveRecipe(getEmbeddingModel());
+    if (recipe.id === 'ollama' || recipe.id === 'llama-server') return true;
+    const base = requireConfig().base_urls?.[recipe.id] ?? '';
+    return /\/\/(localhost|127\.0\.0\.1|\[::1\])(:|\/|$)/i.test(base);
+  } catch {
+    return false;
+  }
+}
+
 /**
  * v0.28.11: returns the configured multimodal embedding model when set,
  * or undefined if the brain falls back to `embedding_model` for multimodal

src/core/ai/recipes/ollama.ts

@@ -29,9 +29,17 @@ export const ollama: Recipe = {
       trust_custom_dims: true, // #2271: local models carry varied native dims
       cost_per_1m_tokens_usd: 0,
       price_last_verified: '2026-04-20',
-      // Ollama's batch capacity depends on the locally loaded model + the
-      // OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
-      no_batch_cap: true,
+      // #2552: Ollama's true batch capacity depends on the locally loaded
+      // model + OLLAMA_NUM_PARALLEL, but the previous `no_batch_cap: true`
+      // meant a whole page went out in ONE request — on a CPU-only box that
+      // multiplies latency past the fetch timeout and the backfill starves
+      // with no surfaced error. Ollama doesn't return a recognizable
+      // token-limit error either, so the recursive-halving safety net never
+      // fires; a conservative static pre-split cap is the only guard.
+      // 4096 tokens x 2 chars/token ~= 8K chars per request (code-dense
+      // pages run ~2 chars/token, not the tiktoken-ish 4).
+      max_batch_tokens: 4096,
+      chars_per_token: 2,
     },
   },
   setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',

src/core/brainstorm/judges.ts

@@ -61,10 +61,7 @@ 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

@@ -32,7 +32,6 @@
  */
 
 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';
@@ -539,14 +538,7 @@ async function _runBrainstormInner(
   const embedFn = opts.embedQueryFn ?? embedQuery;
 
   // ---- Phase 0: cost preview + TTY grace ----
-  // 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 modelStr = opts.modelOverride ?? 'anthropic:claude-sonnet-4-6';
   const { aborted, estimate } = await previewCostAndWait({
     profile,
     model: modelStr,

src/core/cycle/calibration-profile.ts

@@ -26,8 +26,8 @@
  */
 
 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 { chat as gatewayChat } from '../ai/gateway.ts';
+import { TIER_DEFAULTS } 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
@@ -229,16 +229,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
   ): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
     const holder = opts.holder ?? 'garry';
     const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
-    // 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 modelId = opts.model ?? TIER_DEFAULTS.reasoning;
     const gradeCompletion = opts.gradeCompletion ?? 1.0;
     const patternsGenerator = opts.patternsGenerator ?? defaultPatternsGenerator;
     const biasTagsGenerator = opts.biasTagsGenerator ?? defaultBiasTagsGenerator;
@@ -274,7 +265,6 @@ class CalibrationProfilePhase extends BaseCyclePhase {
         scorecard,
         holder,
         attempt,
-        modelHint: modelId,
         ...(feedback !== undefined ? { feedback } : {}),
       });
       return lines.join('\n');

src/core/cycle/grade-takes.ts

@@ -36,9 +36,7 @@
 
 import { 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 { splitProviderModelId } from '../model-id.ts';
+import { chat as gatewayChat } from '../ai/gateway.ts';
 import { GBrainError } from '../types.ts';
 import type { OperationContext } from '../operations.ts';
 import type { BrainEngine, Take, TakeResolution } from '../engine.ts';
@@ -397,24 +395,7 @@ 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';
-    // 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 judgeModelId = opts.model ?? 'claude-sonnet-4-6';
 
     const useEnsemble = opts.useEnsemble ?? false;
     const ensembleThreshold = opts.ensembleThreshold ?? 0.85;
@@ -487,7 +468,7 @@ 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: judgeModelFull });
+        verdict = await judge({ take, evidence, modelHint: opts.model });
       } 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

@@ -5,16 +5,11 @@
  * 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; 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.
+ * 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.
  *
  * F2 fence dedup:
  *   The phase reads the page's existing `<!-- gbrain:takes:begin -->` fence
@@ -45,7 +40,6 @@
 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';
@@ -313,18 +307,6 @@ 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 = {
@@ -348,6 +330,8 @@ 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);
@@ -377,7 +361,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
 
       // Budget pre-check before the LLM call. Estimate: ~1500 input tokens + 500 output.
       const budget = this.checkBudget({
-        modelId: extractorModelId,
+        modelId,
         estimatedInputTokens: 1500,
         maxOutputTokens: 500,
       });
@@ -396,7 +380,7 @@ class ProposeTakesPhase extends BaseCyclePhase {
           pagePath: page.slug,
           pageBody: body,
           existingTakes,
-          modelHint: extractorModelId,
+          modelHint: opts.model,
         });
       } catch (err) {
         const msg = err instanceof Error ? err.message : String(err);
@@ -404,42 +388,16 @@ class ProposeTakesPhase extends BaseCyclePhase {
         continue;
       }
 
-      // 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.
+      // 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) {
-        const landed = await engine.executeRaw<{ id: number }>(
+        await engine.executeRaw(
           `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, md5(claim_text)) DO NOTHING
-           RETURNING id`,
+           ON CONFLICT (source_id, page_slug, content_hash, prompt_version) DO NOTHING`,
           [
             sourceId,
             page.slug,
@@ -452,10 +410,10 @@ class ProposeTakesPhase extends BaseCyclePhase {
             p.weight,
             p.domain ?? null,
             JSON.stringify(existingTakes),
-            extractorModelId,
+            modelId,
           ],
         );
-        if (landed.length > 0) result.proposals_inserted += 1;
+        result.proposals_inserted += 1;
       }
     }
 

src/core/cycle/synthesize.ts

@@ -58,11 +58,8 @@ 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/doctor-categories.ts

@@ -141,6 +141,7 @@ export const OPS_CHECK_NAMES: ReadonlySet<string> = new Set([
   'pgbouncer_prepare',
   'pgvector',
   'pool_budget',
+  'embed_concurrency',
   'progressive_batch_audit_health',
   'queue_health',
   'reranker_health',

src/core/migrate.ts

@@ -5671,41 +5671,6 @@ 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/pglite-engine.ts

@@ -56,7 +56,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
 import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -1591,6 +1591,8 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, innerLimit, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -1630,6 +1632,7 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const keywordSql =
       `WITH ranked AS (
@@ -1637,14 +1640,14 @@ export class PGLiteEngine implements BrainEngine {
            p.slug, p.id as page_id, p.title, p.type, p.source_id,
            p.effective_date, p.effective_date_source,
            cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-           ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+           ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
            CASE WHEN p.updated_at < (
              SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
            ) THEN true ELSE false END AS stale
          FROM content_chunks cc
          JOIN pages p ON p.id = cc.page_id
          JOIN sources s ON s.id = p.source_id
-         WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+         WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
            -- v0.27.1: hide image rows from default text-keyword search so
            -- OCR text doesn't drown text-page hits. Image-similarity queries
            -- run a separate vector path on embedding_image.
@@ -1712,7 +1715,10 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.type) {
@@ -1760,7 +1766,7 @@ export class PGLiteEngine implements BrainEngine {
          COALESCE(rep.chunk_index, 0) as chunk_index,
          COALESCE(rep.chunk_text, '') as chunk_text,
          COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-         ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+         ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
@@ -1775,7 +1781,7 @@ export class PGLiteEngine implements BrainEngine {
          ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
          LIMIT 1
        ) rep ON true
-       WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
+       WHERE p.search_vector @@ ${ftsQueryExpr}
          ${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC, p.id ASC
        LIMIT $2 OFFSET $3`;
@@ -1962,6 +1968,8 @@ export class PGLiteEngine implements BrainEngine {
       });
     }
 
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -1996,20 +2004,21 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const { rows } = await this.db.query(
       `SELECT
          p.slug, p.id as page_id, p.title, p.type, p.source_id,
          p.effective_date, p.effective_date_source,
          cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-         ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+         ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
        FROM content_chunks cc
        JOIN pages p ON p.id = cc.page_id
        JOIN sources s ON s.id = p.source_id
-       WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC
        LIMIT $2 OFFSET $3`,
       params

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','empty')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
   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, md5(claim_text));
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

src/core/postgres-engine.ts

@@ -64,7 +64,7 @@ import { ConnectionManager } from './connection-manager.ts';
 import { logConnectionEvent } from './connection-audit.ts';
 import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
 
@@ -1691,6 +1691,8 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -1761,6 +1763,7 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       WITH ranked_chunks AS (
@@ -1768,11 +1771,11 @@ export class PostgresEngine implements BrainEngine {
           p.slug, p.id as page_id, p.title, p.type, p.source_id,
           p.effective_date, p.effective_date_source,
           cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-          ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
+          ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
         FROM content_chunks cc
         JOIN pages p ON p.id = cc.page_id
         JOIN sources s ON s.id = p.source_id
-        WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
+        WHERE cc.search_vector @@ ${ftsQueryExpr}
           ${typeClause}
           ${typesClause}
           ${excludeSlugsClause}
@@ -1863,7 +1866,10 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (opts?.type) {
@@ -1923,7 +1929,7 @@ export class PostgresEngine implements BrainEngine {
         COALESCE(rep.chunk_index, 0) as chunk_index,
         COALESCE(rep.chunk_text, '') as chunk_text,
         COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-        ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+        ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
         false AS stale
       FROM pages p
       JOIN sources s ON s.id = p.source_id
@@ -1936,7 +1942,7 @@ export class PostgresEngine implements BrainEngine {
         ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
         LIMIT 1
       ) rep ON true
-      WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
+      WHERE p.search_vector @@ ${ftsQueryExpr}
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}
@@ -2000,6 +2006,8 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
+    // #2380: slash-bearing queries match both the split-word and literal
+    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -2060,18 +2068,19 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
+    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       SELECT
         p.slug, p.id as page_id, p.title, p.type, p.source_id,
         p.effective_date, p.effective_date_source,
         cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-        ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
+        ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
         false AS stale
       FROM content_chunks cc
       JOIN pages p ON p.id = cc.page_id
       JOIN sources s ON s.id = p.source_id
-      WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
+      WHERE cc.search_vector @@ ${ftsQueryExpr}
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}

src/core/schema-embedded.ts

@@ -1274,14 +1274,8 @@ 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,
--- 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.
+-- composite unique index (source_id, page_slug, content_hash, prompt_version)
+-- mirrors v0.23 dream_verdicts. 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,
@@ -1292,7 +1286,7 @@ 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','empty')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
   claim_text                  TEXT         NOT NULL,
   kind                        TEXT         NOT NULL,
   holder                      TEXT         NOT NULL,
@@ -1307,7 +1301,7 @@ 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, md5(claim_text));
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

src/core/search/sql-ranking.ts

@@ -251,6 +251,28 @@ export function buildOrFallbackWebsearchQuery(query: string): string | null {
   return tokens.join(' OR ');
 }
 
+/**
+ * #2380: FTS query expression for slash-bearing queries. Postgres' default
+ * text-search parser classifies `foo/bar` as a single `file`-alias lexeme —
+ * on BOTH the query side and the index side. So a raw `foo/bar` query only
+ * matched documents carrying the identical joined lexeme (literal paths),
+ * and a slash-split query only matches documents whose text had the words
+ * separated. Neither form alone covers both document shapes; OR the two
+ * parses so a slash query matches prose ("foo and bar", stemmed, AND
+ * semantics) AND literal slash forms ("src/core/x.ts") alike.
+ *
+ * Slash-free queries return the plain single-parse expression — byte-
+ * identical SQL and identical ts_rank to the historical behavior.
+ *
+ * `ftsLang` is validated by getFtsLanguage() (safe to interpolate);
+ * `param` is a `$N` placeholder, never user text.
+ */
+export function buildWebsearchQueryExpr(ftsLang: string, param: string, query: string): string {
+  const plain = `websearch_to_tsquery('${ftsLang}', ${param})`;
+  if (!query.includes('/')) return plain;
+  return `(websearch_to_tsquery('${ftsLang}', translate(${param}, '/', ' ')) || ${plain})`;
+}
+
 // ============================================================
 // v0.29.1 — Recency component SQL builder
 // ============================================================

src/schema.sql

@@ -1270,14 +1270,8 @@ 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,
--- 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.
+-- composite unique index (source_id, page_slug, content_hash, prompt_version)
+-- mirrors v0.23 dream_verdicts. 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,
@@ -1288,7 +1282,7 @@ 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','empty')),
+                                           CHECK (status IN ('pending','accepted','rejected','superseded')),
   claim_text                  TEXT         NOT NULL,
   kind                        TEXT         NOT NULL,
   holder                      TEXT         NOT NULL,
@@ -1303,7 +1297,7 @@ 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, md5(claim_text));
+  ON take_proposals (source_id, page_slug, content_hash, prompt_version);
 CREATE INDEX IF NOT EXISTS take_proposals_pending_idx
   ON take_proposals (source_id, status, proposed_at DESC)
   WHERE status = 'pending';

test/ai/no-batch-cap-suppression.serial.test.ts

@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     resetGateway();
   });
 
-  test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
-    for (const id of ['ollama', 'litellm', 'llama-server']) {
+  test('LiteLLM and llama-server declare no_batch_cap: true', () => {
+    for (const id of ['litellm', 'llama-server']) {
       const r = getRecipe(id);
       expect(r, `${id} not registered`).toBeDefined();
       expect(
@@ -39,6 +39,18 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     }
   });
 
+  test('#2552: Ollama declares a conservative static batch cap, not no_batch_cap', () => {
+    // A CPU-only Ollama box wedges when a whole page ships in one request;
+    // Ollama never returns a token-limit error so the recursive-halving
+    // safety net can't fire. The pre-split cap is the only guard.
+    const r = getRecipe('ollama');
+    expect(r).toBeDefined();
+    const e = r!.touchpoints.embedding!;
+    expect(e.no_batch_cap).toBeUndefined();
+    expect(e.max_batch_tokens).toBe(4096);
+    expect(e.chars_per_token).toBe(2);
+  });
+
   test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
     warnSpy.mockClear();
     resetGateway();

test/calibration-profile.test.ts

@@ -38,7 +38,6 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
 } {
   const captured: CapturedSql[] = [];
   const engine = {
-    async getConfig() { return null; },
     kind: 'pglite',
     async getScorecard() {
       return opts.scorecard;

test/embed-local-endpoint.serial.test.ts

@@ -0,0 +1,118 @@
+/**
+ * #2552: cloud-tuned embedding defaults silently wedge CPU-only local
+ * endpoints (Ollama). Three-part fix under test:
+ *
+ *  1. `isLocalEmbeddingEndpoint()` — gateway helper detecting local
+ *     inference servers (ollama / llama-server recipes, localhost base URL).
+ *  2. `resolveEmbedConcurrency()` — embed auto-caps the 20-worker fan-out
+ *     at LOCAL_EMBED_CONCURRENCY_CAP for local endpoints unless the
+ *     operator set GBRAIN_EMBED_CONCURRENCY explicitly.
+ *  3. `computeEmbedConcurrencyCheck()` — doctor warns when an explicit env
+ *     override fans out against a local endpoint.
+ *
+ * Serial: mutates process.env and the module-global gateway config.
+ */
+
+import { afterAll, afterEach, describe, expect, test } from 'bun:test';
+import {
+  configureGateway,
+  resetGateway,
+  isLocalEmbeddingEndpoint,
+  LOCAL_EMBED_CONCURRENCY_CAP,
+} from '../src/core/ai/gateway.ts';
+import { resolveEmbedConcurrency } from '../src/commands/embed.ts';
+import { computeEmbedConcurrencyCheck } from '../src/commands/doctor.ts';
+
+const SAVED_ENV = process.env.GBRAIN_EMBED_CONCURRENCY;
+
+afterEach(() => {
+  resetGateway();
+  if (SAVED_ENV === undefined) delete process.env.GBRAIN_EMBED_CONCURRENCY;
+  else process.env.GBRAIN_EMBED_CONCURRENCY = SAVED_ENV;
+});
+
+afterAll(() => {
+  resetGateway();
+});
+
+describe('#2552 isLocalEmbeddingEndpoint', () => {
+  test('false when the gateway is not configured (fail-open to cloud behavior)', () => {
+    resetGateway();
+    expect(isLocalEmbeddingEndpoint()).toBe(false);
+  });
+
+  test('true for the ollama recipe', () => {
+    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
+    expect(isLocalEmbeddingEndpoint()).toBe(true);
+  });
+
+  test('true for the llama-server recipe', () => {
+    configureGateway({ embedding_model: 'llama-server:my-gguf', env: {} });
+    expect(isLocalEmbeddingEndpoint()).toBe(true);
+  });
+
+  test('false for a cloud recipe', () => {
+    configureGateway({
+      embedding_model: 'openai:text-embedding-3-small',
+      env: { OPENAI_API_KEY: 'fake' },
+    });
+    expect(isLocalEmbeddingEndpoint()).toBe(false);
+  });
+
+  test('true when a cloud recipe base URL is explicitly pointed at localhost', () => {
+    configureGateway({
+      embedding_model: 'openai:text-embedding-3-small',
+      env: { OPENAI_API_KEY: 'fake' },
+      base_urls: { openai: 'http://localhost:8080/v1' },
+    });
+    expect(isLocalEmbeddingEndpoint()).toBe(true);
+  });
+});
+
+describe('#2552 resolveEmbedConcurrency', () => {
+  test('caps at LOCAL_EMBED_CONCURRENCY_CAP for a local endpoint when env is unset', () => {
+    delete process.env.GBRAIN_EMBED_CONCURRENCY;
+    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
+    expect(resolveEmbedConcurrency()).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
+  });
+
+  test('explicit env override always wins, even against a local endpoint', () => {
+    process.env.GBRAIN_EMBED_CONCURRENCY = '10';
+    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
+    expect(resolveEmbedConcurrency()).toBe(10);
+  });
+
+  test('cloud endpoints keep the historical default of 20', () => {
+    delete process.env.GBRAIN_EMBED_CONCURRENCY;
+    configureGateway({ env: { OPENAI_API_KEY: 'fake' } });
+    expect(resolveEmbedConcurrency()).toBe(20);
+  });
+
+  test('pacing only ever lowers concurrency', () => {
+    delete process.env.GBRAIN_EMBED_CONCURRENCY;
+    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
+    expect(resolveEmbedConcurrency(1)).toBe(1);
+    expect(resolveEmbedConcurrency(16)).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
+  });
+});
+
+describe('#2552 computeEmbedConcurrencyCheck (doctor)', () => {
+  test('ok for non-local endpoints', () => {
+    expect(computeEmbedConcurrencyCheck(false, '20', 2).status).toBe('ok');
+  });
+
+  test('warn when an explicit override exceeds the local cap', () => {
+    const check = computeEmbedConcurrencyCheck(true, '20', 2);
+    expect(check.status).toBe('warn');
+    expect(check.message).toContain('GBRAIN_EMBED_CONCURRENCY=20');
+  });
+
+  test('ok when env is unset against a local endpoint (auto-cap applies)', () => {
+    expect(computeEmbedConcurrencyCheck(true, undefined, 2).status).toBe('ok');
+  });
+
+  test('ok when the override is at or under the cap', () => {
+    expect(computeEmbedConcurrencyCheck(true, '2', 2).status).toBe('ok');
+    expect(computeEmbedConcurrencyCheck(true, '1', 2).status).toBe('ok');
+  });
+});

test/grade-takes-ensemble.test.ts

@@ -47,7 +47,6 @@ 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

@@ -46,14 +46,12 @@ 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;
@@ -226,28 +224,6 @@ 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/pglite-engine.test.ts

@@ -216,6 +216,67 @@ describe('PGLiteEngine: Search', () => {
     expect(results.length).toBe(0);
   });
 
+  // Regression (#2380): queries containing `/` used to bypass FTS AND
+  // semantics. Postgres' default text-search parser classifies `foo/bar` as
+  // a `file`-alias token mapped to the `simple` dictionary, so it became a
+  // single un-stemmed lexeme `'foo/bar'` that never matches indexed text —
+  // the primary FTS pass returned 0 and the OR fallback took over, matching
+  // pages that contain EITHER term. searchKeyword/searchTitles now normalize
+  // `/` to whitespace before websearch_to_tsquery parses, so the primary
+  // AND pass matches directly.
+  test('searchKeyword: slash query matches with AND semantics, not OR fallback', async () => {
+    // Decoy shares only ONE of the two query terms ('enterprise').
+    await engine.putPage('concepts/enterprise-pricing', {
+      type: 'concept', title: 'Widget Pricing',
+      compiled_truth: 'Enterprise pricing for widgets.',
+    });
+    await engine.upsertChunks('concepts/enterprise-pricing', [
+      { chunk_index: 0, chunk_text: 'Enterprise pricing for widgets', chunk_source: 'compiled_truth' },
+    ]);
+
+    // Both terms co-occur only in the novamind chunk. Pre-fix this returned
+    // BOTH pages (primary pass zero-hit → OR fallback); post-fix the primary
+    // AND pass returns exactly the co-occurrence page.
+    const results = await engine.searchKeyword('NovaMind/enterprise');
+    expect(results.length).toBe(1);
+    expect(results[0].slug).toBe('companies/novamind');
+  });
+
+  test('searchTitles: slash query matches with AND semantics, not OR fallback', async () => {
+    await engine.putPage('companies/novamind-enterprise', {
+      type: 'company', title: 'NovaMind Enterprise Platform',
+      compiled_truth: 'Placeholder body.',
+    });
+    await engine.putPage('guides/enterprise-sales', {
+      type: 'concept', title: 'Enterprise Sales Guide',
+      compiled_truth: 'Placeholder body.',
+    });
+
+    // Pre-fix: `NovaMind/Enterprise` parsed as one file-alias lexeme → the
+    // primary title pass returned 0 and the OR fallback matched BOTH titles.
+    const results = await engine.searchTitles('NovaMind/Enterprise');
+    expect(results.length).toBe(1);
+    expect(results[0].slug).toBe('companies/novamind-enterprise');
+  });
+
+  test('searchKeyword: slash query still matches the literal slash form (file paths)', async () => {
+    // The INDEX side also emits the joined file-alias lexeme for literal
+    // `foo/bar` text, so a query normalized to split words alone would go
+    // blind to documents containing the literal slash form (paths, URLs).
+    // buildWebsearchQueryExpr ORs both parses; this pins the raw arm.
+    await engine.putPage('runbooks/widget-deploy', {
+      type: 'concept', title: 'Widget Deploy Runbook',
+      compiled_truth: 'Runbook for the acme/widget deployment pipeline.',
+    });
+    await engine.upsertChunks('runbooks/widget-deploy', [
+      { chunk_index: 0, chunk_text: 'Runbook for the acme/widget deployment pipeline', chunk_source: 'compiled_truth' },
+    ]);
+
+    const results = await engine.searchKeyword('acme/widget');
+    expect(results.length).toBe(1);
+    expect(results[0].slug).toBe('runbooks/widget-deploy');
+  });
+
   test('tsvector trigger populates search_vector on insert', async () => {
     // Verify the PL/pgSQL trigger fires and content_chunks.search_vector is
     // populated from chunk_text. v0.20.0 Cathedral II Layer 3 moved FTS from

test/propose-takes-rescan.test.ts

@@ -1,160 +0,0 @@
-/**
- * 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

@@ -41,16 +41,12 @@ 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;
     },
@@ -63,12 +59,7 @@ function buildMockEngine(opts: {
         if (existing.has(key)) return [{ id: 1 } as unknown as T];
         return [];
       }
-      // 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];
-      }
+      // INSERT — return nothing
       return [];
     },
   } as unknown as BrainEngine;
@@ -276,29 +267,6 @@ 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 })];