mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-31 04:07:52 +00:00
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>
This commit is contained in:
Garry Tan
co-authored by
p3ob7o
Claude Fable 5
p3ob7o
Claude Fable 5
parent
0612b0daa8
commit
f68eb9d905
@@ -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 {
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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';
|
||||
@@ -538,7 +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,
|
||||
|
||||
@@ -26,8 +26,8 @@
|
||||
*/
|
||||
|
||||
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.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
|
||||
@@ -229,7 +229,16 @@ 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;
|
||||
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;
|
||||
@@ -265,6 +274,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
scorecard,
|
||||
holder,
|
||||
attempt,
|
||||
modelHint: modelId,
|
||||
...(feedback !== undefined ? { feedback } : {}),
|
||||
});
|
||||
return lines.join('\n');
|
||||
|
||||
@@ -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}`);
|
||||
|
||||
@@ -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, $12)
|
||||
ON CONFLICT (source_id, page_slug, content_hash, prompt_version) DO NOTHING`,
|
||||
ON CONFLICT (source_id, page_slug, content_hash, prompt_version, md5(claim_text)) DO NOTHING
|
||||
RETURNING id`,
|
||||
[
|
||||
sourceId,
|
||||
page.slug,
|
||||
@@ -410,10 +452,10 @@ class ProposeTakesPhase extends BaseCyclePhase {
|
||||
p.weight,
|
||||
p.domain ?? null,
|
||||
JSON.stringify(existingTakes),
|
||||
modelId,
|
||||
extractorModelId,
|
||||
],
|
||||
);
|
||||
result.proposals_inserted += 1;
|
||||
if (landed.length > 0) result.proposals_inserted += 1;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -58,8 +58,11 @@ const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
* 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,
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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';
|
||||
|
||||
@@ -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';
|
||||
|
||||
+10
-4
@@ -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';
|
||||
|
||||
@@ -38,6 +38,7 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
} {
|
||||
const captured: CapturedSql[] = [];
|
||||
const engine = {
|
||||
async getConfig() { return null; },
|
||||
kind: 'pglite',
|
||||
async getScorecard() {
|
||||
return opts.scorecard;
|
||||
|
||||
@@ -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;
|
||||
|
||||
@@ -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 });
|
||||
|
||||
@@ -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']);
|
||||
});
|
||||
});
|
||||
@@ -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 })];
|
||||
|
||||
Reference in New Issue
Block a user