@tangle-network/agent-eval 0.218.1 → 0.220.0

package/docs/public-api.md

@@ -7,11 +7,11 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
 | measure | count |
 | --- | --- |
 | export subpaths | 34 |
-| published value exports (subpath x symbol) | 1225 |
-| distinct symbols | 1038 |
-| production | 904 |
-| planned | 286 |
-| none | 35 |
+| published value exports (subpath x symbol) | 1226 |
+| distinct symbols | 1039 |
+| production | 915 |
+| planned | 278 |
+| none | 33 |
 
 Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
 
@@ -23,47 +23,47 @@ Type-only exports are not listed: a type binds no runtime surface, and removing
 
 ## Consumer sweep
 
-Swept 2026-10-06 across 37 repositories, each on its default branch:
-
-| repository | ref | commit |
-| --- | --- | --- |
-| agent-app | main | `e6c001f` |
-| agent-builder | main | `6d67aab` |
-| agent-dev-container | develop | `0d14b1d` |
-| agent-knowledge | main | `49c7cca` |
-| agent-lab | main | `23fb048` |
-| agent-runtime | main | `a7752c5` |
-| agent-sdk | main | `648eaa7` |
-| ai-trading-blueprint | main | `e574633` |
-| blueprint-agent | develop | `517650b` |
-| braid | main | `b0fb773` |
-| browser-agent-driver | main | `8228dc3` |
-| chatgpt-plugins | main | `cdee294` |
-| creative-agent | master | `a7aca13` |
-| discovery | master | `f7ad3f3` |
-| discovery-lab | master | `5fe4b433` |
-| factory | main | `5e6f50c` |
-| gtm | master | `4938eaa` |
-| gtm-agent | master | `ec24bfa` |
-| hospitality-agent | main | `29d6e30` |
-| insurance-agent | main | `8ab1851` |
-| legal-agent | main | `2857927` |
-| ph0ny | main | `3af952b` |
-| physim | main | `6eae114` |
-| playproof | main | `c49a6a5` |
-| redteam | main | `41c648b` |
-| relationships-agent | main | `fe73c79` |
-| run-capsule | main | `0cd99e5` |
-| starter-foundry | main | `217328c` |
-| super-agent | main | `d0e9bc3` |
-| supervisor-lab | main | `0f3c189` |
-| tangle-router | main | `fa71feb` |
-| tangle-tools | main | `0d28216` |
-| tax-agent | main | `a395120` |
-| traces | main | `499261e` |
-| trustgate | main | `f7f91bd` |
-| tuner-agent | main | `794fb92` |
-| workcomp-agent | master | `5ab31cf` |
+Last refresh 2026-10-22; retained evidence across 37 repositories. Each row states its own sweep date and revision; older rows are historical, not fresh consumer checks:
+
+| repository | ref | commit | swept |
+| --- | --- | --- | --- |
+| agent-app | refs/remotes/origin/main | `77158737484569f4033703ce5477d509755bd711` | 2026-10-22 |
+| agent-builder | main | `6d67aab` | 2026-10-06 |
+| agent-dev-container | develop | `0d14b1d` | 2026-10-06 |
+| agent-knowledge | main | `49c7cca` | 2026-10-06 |
+| agent-lab | main | `23fb048` | 2026-10-06 |
+| agent-runtime | main | `a7752c5` | 2026-10-06 |
+| agent-sdk | main | `648eaa7` | 2026-10-06 |
+| ai-trading-blueprint | main | `e574633` | 2026-10-06 |
+| blueprint-agent | develop | `517650b` | 2026-10-06 |
+| braid | main | `b0fb773` | 2026-10-06 |
+| browser-agent-driver | main | `8228dc3` | 2026-10-06 |
+| chatgpt-plugins | main | `cdee294` | 2026-10-06 |
+| creative-agent | master | `a7aca13` | 2026-10-06 |
+| discovery | master | `f7ad3f3` | 2026-10-06 |
+| discovery-lab | master | `5fe4b433` | 2026-10-06 |
+| factory | main | `5e6f50c` | 2026-10-06 |
+| gtm | master | `4938eaa` | 2026-10-06 |
+| gtm-agent | refs/remotes/origin/master | `1719c4f9e01117f5e1577fb280eba201d5bb62b9` | 2026-10-22 |
+| hospitality-agent | main | `29d6e30` | 2026-10-06 |
+| insurance-agent | main | `8ab1851` | 2026-10-06 |
+| legal-agent | main | `2857927` | 2026-10-06 |
+| ph0ny | main | `3af952b` | 2026-10-06 |
+| physim | main | `6eae114` | 2026-10-06 |
+| playproof | main | `c49a6a5` | 2026-10-06 |
+| redteam | main | `41c648b` | 2026-10-06 |
+| relationships-agent | main | `fe73c79` | 2026-10-06 |
+| run-capsule | main | `0cd99e5` | 2026-10-06 |
+| starter-foundry | main | `217328c` | 2026-10-06 |
+| super-agent | main | `d0e9bc3` | 2026-10-06 |
+| supervisor-lab | main | `0f3c189` | 2026-10-06 |
+| tangle-router | main | `fa71feb` | 2026-10-06 |
+| tangle-tools | main | `0d28216` | 2026-10-06 |
+| tax-agent | main | `a395120` | 2026-10-06 |
+| traces | main | `499261e` | 2026-10-06 |
+| trustgate | main | `f7f91bd` | 2026-10-06 |
+| tuner-agent | main | `794fb92` | 2026-10-06 |
+| workcomp-agent | master | `5ab31cf` | 2026-10-06 |
 
 ## What this census cannot see
 
@@ -90,7 +90,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `.`
 
-321 value exports — 279 production, 41 planned, 1 none.
+321 value exports — 282 production, 39 planned, 0 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -99,7 +99,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
 | `AgentEvalError` | production | agent-runtime:src/errors.ts |
 | `agentProfileCellKey` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
-| `agentProfileHash` | production | ai-trading-blueprint:evals/src/trading/persona-agent-eval.ts |
+| `agentProfileHash` | production | agent-app:src/eval/scorecard.ts |
 | `agentProfileId` | production | agent-dev-container:products/intelligence/api/src/lib/project-profile-change-preflight.ts |
 | `aggregateJudgeVerdicts` | production | agent-app:src/eval-campaign/index.ts |
 | `aggregateRunScore` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
@@ -120,7 +120,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertProductBenchmarkRun` | production | creative-agent:eval/research-package.ts |
 | `assertRealBackend` | production | creative-agent:eval/canonical-runner.ts |
 | `assertRunCaptured` | production | creative-agent:eval/canonical-runner.ts |
-| `assertServedModel` | production | creative-agent:eval/lib/persona-driver.ts |
+| `assertServedModel` | production | agent-app:src/eval/persona-driver.ts |
 | `assertServedModels` | planned | doc: docs/building-doctrine.md |
 | `assertSingleBackend` | planned | consumer tests: insurance-agent:tests/eval/canonical.ts |
 | `assessShareSafety` | production | agent-dev-container:products/intelligence/api/src/lib/search-blobs.ts |
@@ -176,9 +176,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `CostCeilingReachedError` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `costForTokenPricing` | production | agent-runtime:src/improvement/search-executor.ts |
 | `costForUsage` | production | agent-builder:src/lib/.server/llm-cost.ts |
-| `CostLedger` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
-| `costReceiptFromLlm` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
-| `costReceiptFromLlmError` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
+| `CostLedger` | production | agent-app:src/eval/persona-driver.ts |
+| `costReceiptFromLlm` | production | agent-app:src/eval/persona-driver.ts |
+| `costReceiptFromLlmError` | production | agent-app:src/eval/persona-driver.ts |
 | `CostTracker` | production | creative-agent:eval/canonical-runner.ts |
 | `createAntiSlopJudge` | production | ph0ny:products/builder/api/src/eval/judges.ts |
 | `createBoundedTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
@@ -192,7 +192,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `CrossFamilyError` | production | creative-agent:eval/lib/judge-ensemble.ts |
 | `decidePairedPromotion` | production | discovery-lab:experiments/e1-checker/score.mjs |
 | `DEFAULT_BOUNDED_PROCESS_TIMEOUT_MS` | production | this package: src/command-runner.ts:28 |
-| `DEFAULT_JUDGE_GATE_POLICY` | none | — |
+| `DEFAULT_JUDGE_GATE_POLICY` | planned | consumer tests: gtm-agent:eval/creative-critic/calibration.test.ts |
 | `DEFAULT_RED_TEAM_CORPUS` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
 | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
 | `DEFAULT_TRACE_ANALYST_KINDS` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
@@ -201,7 +201,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `deployGateLayer` | production | blueprint-agent:scripts/experiments/lib/deploy-runner.ts |
 | `describeTraceInsightScope` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html.ts |
 | `diffFindings` | production | agent-runtime:src/analyst-loop/run-analyst-loop.ts |
-| `diffScorecard` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
+| `diffScorecard` | production | agent-app:src/eval/scorecard.ts |
 | `discoverPersonas` | production | insurance-agent:scripts/harvest-candidate-outputs.ts |
 | `domainEvidencePattern` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/session-loader.ts |
 | `dominates` | production | blueprint-agent:scripts/experiments/lib/competition-analytics.ts |
@@ -240,7 +240,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `fileVerdictCache` | production | blueprint-agent:scripts/experiments/calibrate-instrument.ts |
 | `FindingsStore` | production | agent-builder:scripts/run-canonical-analyst-loop.ts |
 | `fisherExactTwoSided` | production | agent-dev-container:packages/sdk-data/src/analysis/recommendations/statistics.ts |
-| `formatScorecardDiff` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
+| `formatScorecardDiff` | production | agent-app:src/eval/scorecard.ts |
 | `gainHistogram` | production | this package: src/research-report.ts:18 |
 | `gateTreatmentApplied` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `gradeSemanticStatus` | production | blueprint-agent:scripts/experiments/lib/verification-harness/primitives.ts |
@@ -271,7 +271,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `judgeAgreementView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
 | `JudgeError` | production | agent-runtime:src/errors.ts |
 | `judgeFamily` | production | agent-builder:frontier/judges/llm.ts |
-| `judgeGateDecision` | planned | doc: docs/concepts.md |
+| `judgeGateDecision` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `JudgeGateRefusedError` | planned | doc: docs/concepts.md |
 | `judgeSpans` | production | this package: src/builder-eval/three-layer-eval.ts:25 |
 | `knowledgeReadinessTracePayload` | production | agent-dev-container:products/intelligence/api/src/routes/project-engines.ts |
@@ -281,18 +281,18 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `LlmCallError` | production | agent-dev-container:products/platform/api/src/lib/router-model-owner.ts |
 | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
 | `LlmResponseError` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-router.ts |
-| `loadScorecard` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
+| `loadScorecard` | production | agent-app:src/eval/scorecard.ts |
 | `localCommandRunner` | production | blueprint-agent:scripts/experiments/lib/command-runner.ts |
 | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
 | `makePolicyEditCandidateRecord` | planned | doc: docs/campaign-proposers.md |
 | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
 | `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:36 |
 | `mannWhitneyU` | production | blueprint-agent:scripts/experiments/lib/competition-analytics.ts |
-| `maximumChargeForLlmRequest` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-router.ts |
+| `maximumChargeForLlmRequest` | production | agent-app:src/eval/persona-driver.ts |
 | `mcnemar` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `mcnemarPower` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
 | `mcnemarRequiredN` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
-| `measureJudgeAgreement` | planned | doc: docs/concepts.md |
+| `measureJudgeAgreement` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `minimumPairsForPairedDeltaTest` | production | agent-dev-container:products/intelligence/api/src/routes/optimizations.ts |
 | `mintRolloutRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
 | `MODEL_PRICING` | production | supervisor-lab:archive/bench/profile-arena.ts |
@@ -330,7 +330,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `passAtK` | planned | doc: docs/design/statistics-decisions.md |
 | `pearsonR` | production | this package: src/builder-eval/correlation.ts:18 |
 | `preflightModels` | planned | doc: docs/building-doctrine.md |
-| `productBenchmarkRepoIdentity` | production | creative-agent:eval/research-package.ts |
+| `productBenchmarkRepoIdentity` | production | agent-app:src/eval/research-plan.ts |
 | `ProductClient` | production | creative-agent:eval/e2e/creative-product-harness.ts |
 | `profile` | production | agent-app:src/profile/index.ts |
 | `projectRuntimeTrajectoryEvidence` | production | agent-dev-container:products/intelligence/api/src/lib/workflow-trace-preflight.ts |
@@ -339,7 +339,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `ranks` | production | discovery-lab:tools/evaluators/eval-discrimination/score.mjs |
 | `readProductBenchmarkManifest` | production | creative-agent:eval/research-package.ts |
 | `recordRuns` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/analyze.mjs |
-| `recordRunsToScorecard` | production | ai-trading-blueprint:evals/src/trading/persona-agent-eval.ts |
+| `recordRunsToScorecard` | production | agent-app:src/eval/scorecard.ts |
 | `redact` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
 | `redactForShare` | production | chatgpt-plugins:plugins/agents/inspection/src/index.ts |
 | `REDACTION_VERSION` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
@@ -377,7 +377,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `selfImprove` | production | agent-app:src/eval-campaign/index.ts |
 | `SEMANTIC_CONCEPT_JUDGE_VERSION` | production | blueprint-agent:scripts/experiments/lib/semantic-audit.ts |
 | `shareAllowed` | production | agent-dev-container:products/intelligence/api/src/lib/search-blobs.ts |
-| `snapshotFromJudgeAgreement` | planned | doc: docs/concepts.md |
+| `snapshotFromJudgeAgreement` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `spanRecordsToTraceAnalysisStore` | production | agent-dev-container:products/intelligence/api/src/lib/pg-trace-analyst-store.ts |
 | `spearmanR` | production | this package: scripts/synthetic-search-ledger.ts:71 |
 | `stripFencedJson` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
@@ -589,7 +589,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./campaign`
 
-131 value exports — 101 production, 25 planned, 5 none.
+132 value exports — 102 production, 25 planned, 5 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -635,7 +635,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `estimateNodeFromCells` | production | agent-dev-container:products/intelligence/api/src/lib/search-stats.ts |
 | `externalSurface` | production | agent-runtime:scripts/verify-official-optimizers-consumer.mjs |
 | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
-| `FileSearchLedger` | production | this package: src/campaign/search-kernel-runner.ts:25 |
+| `FileSearchLedger` | production | this package: src/campaign/search-kernel-runner.ts:27 |
 | `finalizeProfileMatrix` | planned | doc: docs/eval-surface-map.md |
 | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `gepaOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
@@ -653,6 +653,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `loadEvalFixture` | planned | doc: docs/eval-fixtures.md |
 | `loadEvalFixtureScenarios` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
 | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
+| `measureCampaignCost` | production | this package: scripts/creative-matrix-proof.ts:11 |
 | `neutralizationGate` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/evolve.ts |
 | `neutralizeText` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/compile-and-prove/compile-diff.ts |
 | `openSearchLedger` | production | agent-runtime:src/durable/pursuit-versions.ts |
@@ -727,7 +728,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./contract`
 
-55 value exports — 40 production, 15 planned, 0 none.
+55 value exports — 41 production, 14 planned, 0 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -763,7 +764,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `paretoPolicy` | planned | named in discovery-lab (bind not in the import graph) |
 | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
 | `parseAgentTrace` | planned | doc: docs/code-agent-intake.md |
-| `parseCodeAgentJsonl` | planned | doc: docs/code-agent-intake.md |
+| `parseCodeAgentJsonl` | production | gtm-agent:src/lib/.server/profile-learning-execution.ts |
 | `parseCodeAgentJsonlFile` | production | this package: src/contract/intake/code-agent-store.ts:38 |
 | `partitionRunsByAuthoringModel` | planned | doc: docs/code-agent-intake.md |
 | `runAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
@@ -968,7 +969,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./meta-eval`
 
-42 value exports — 27 production, 14 planned, 1 none.
+42 value exports — 30 production, 12 planned, 0 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -985,7 +986,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `clusterBootstrapMean` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
 | `continuousAgreement` | production | agent-builder:frontier/judges/eval-validity.ts |
 | `correlationStudy` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
-| `DEFAULT_JUDGE_GATE_POLICY` | none | — |
+| `DEFAULT_JUDGE_GATE_POLICY` | planned | consumer tests: gtm-agent:eval/creative-critic/calibration.test.ts |
 | `definePlant` | production | discovery-lab:experiments/e1-checker/score.mjs |
 | `evalHealthStamp` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `evaluatorAdmissionPolicySchema` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-factory.ts |
@@ -993,10 +994,10 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `fileSentinelStore` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `FileSystemOutcomeStore` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
 | `InMemoryOutcomeStore` | planned | consumer tests: ph0ny:products/builder/api/src/eval/outcomes-correlate.test.ts |
-| `judgeGateDecision` | planned | doc: docs/concepts.md |
+| `judgeGateDecision` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `JudgeGateRefusedError` | planned | doc: docs/concepts.md |
 | `judgeSentinelReport` | production | creative-agent:eval/lib/judge-sentinel.ts |
-| `measureJudgeAgreement` | planned | doc: docs/concepts.md |
+| `measureJudgeAgreement` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `multiclassBrierScore` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
 | `OutcomeStoreError` | planned | doc: docs/outcome-validity.md |
 | `perturbEvidence` | planned | doc: docs/plants.md |
@@ -1010,7 +1011,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `selfPreference` | production | ph0ny:products/builder/api/src/eval/judge-bias.ts |
 | `snapshotFromAgreement` | production | physim:apps/server/src/scripts/agent-eval/judge-sentinel.ts |
 | `snapshotFromCalibration` | production | gtm-agent:eval/calibrate-judges.ts |
-| `snapshotFromJudgeAgreement` | planned | doc: docs/concepts.md |
+| `snapshotFromJudgeAgreement` | production | gtm-agent:src/lib/.server/judges/quality.ts |
 | `snapshotFromSentinelSet` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `validateSentinelSnapshot` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `verbosityBias` | production | blueprint-agent:scripts/experiments/calibration/judge-agreement.ts |
@@ -1290,13 +1291,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./systemone`
 
-19 value exports — 10 production, 9 planned, 0 none.
+19 value exports — 13 production, 6 planned, 0 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `asAnalyst` | production | this package: src/systemone.ts:5 |
 | `asJudge` | production | this package: src/systemone.ts:5 |
-| `assessSystemOneDomainMatch` | planned | doc: docs/systemone-integrations.md |
+| `assessSystemOneDomainMatch` | production | gtm-agent:src/lib/.server/leads/domain-match.ts |
 | `assessSystemOneReview` | planned | doc: docs/changes/systemone-provider-neutral.md |
 | `createEvaluator` | production | blueprint-agent:scripts/experiments/app-grade/drive.ts |
 | `normalizedSystemOneScore` | planned | doc: docs/changes/systemone-provider-neutral.md |
@@ -1304,11 +1305,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `parseSystemOneRecordedRequest` | planned | example: examples/systemone-replay.ts:7 |
 | `parseSystemOneRequest` | production | discovery-lab:experiments/diu-campaign-v1/jev-review.mjs |
 | `parseSystemOneResult` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
-| `prepareSystemOneDomainMatch` | planned | doc: docs/systemone-integrations.md |
+| `prepareSystemOneDomainMatch` | production | gtm-agent:src/lib/.server/leads/domain-match.ts |
 | `prepareSystemOneReview` | production | this package: src/rl/claim-integrity.ts:47 |
 | `systemOneAnalyst` | production | this package: src/analyst/failure-modes.ts:20 |
 | `systemOneConfidence` | planned | doc: docs/changes/systemone-provider-neutral.md |
-| `systemOneEvaluator` | planned | doc: docs/changes/systemone-provider-neutral.md |
+| `systemOneEvaluator` | production | gtm-agent:src/lib/.server/leads/domain-match.ts |
 | `systemOneJudge` | planned | example: examples/systemone-product-integrity.ts:4 |
 | `SystemOneResponseError` | production | tangle-router:lib/systemone.ts |
 | `systemOneReviewFindings` | planned | example: examples/systemone-behavior-review.ts:3 |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.218.1",
+  "version": "0.220.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {
@@ -241,11 +241,9 @@
   },
   "devDependencies": {
     "@arethetypeswrong/cli": "^0.18.5",
-    "@arizeai/phoenix-evals": "^2.6.0",
     "@biomejs/biome": "^2.5.14",
     "@types/node": "^26.6.2",
     "ajv": "8.20.0",
-    "autoevals": "^0.3.0",
     "esbuild": "^0.28.2",
     "fast-check": "^4.10.2",
     "husky": "^9.1.7",
@@ -257,8 +255,7 @@
     "tsdown": "^0.23.0",
     "tsx": "^4.23.15",
     "typescript": "^7.0.2",
-    "vitest": "^5.0.1",
-    "yaml": "2.9.1"
+    "vitest": "^5.0.1"
   },
   "engines": {
     "node": ">=20.19.0"