@tangle-network/agent-eval 0.199.0 → 0.200.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +10 -1
- package/dist/adapters/http.d.ts +2 -2
- package/dist/analyst/index.d.ts +9 -69
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +1 -1
- package/dist/{benchmark-command-CoBwYvau.js → benchmark-command-EBmuMUBo.js} +5 -3
- package/dist/benchmark-command-EBmuMUBo.js.map +1 -0
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +2 -2
- package/dist/campaign/index.d.ts +4 -4
- package/dist/campaign/index.js +6 -6
- package/dist/{campaign-BIqhoN9r.js → campaign-L391bmir.js} +7 -7
- package/dist/{campaign-BIqhoN9r.js.map → campaign-L391bmir.js.map} +1 -1
- package/dist/cli.js +11 -9
- package/dist/cli.js.map +1 -1
- package/dist/contract/index.d.ts +7 -7
- package/dist/contract/index.js +3 -3
- package/dist/{default-registry-oK9hHfX_.d.ts → default-registry-D1rNS2yB.d.ts} +3 -3
- package/dist/{default-registry-oK9hHfX_.d.ts.map → default-registry-D1rNS2yB.d.ts.map} +1 -1
- package/dist/{define-agent-eval-Bgwt5ZcC.d.ts → define-agent-eval-1YuvJpOs.d.ts} +5 -5
- package/dist/{define-agent-eval-Bgwt5ZcC.d.ts.map → define-agent-eval-1YuvJpOs.d.ts.map} +1 -1
- package/dist/{define-agent-eval-BRCLti7N.js → define-agent-eval-7q_UwsTt.js} +3 -3
- package/dist/{define-agent-eval-BRCLti7N.js.map → define-agent-eval-7q_UwsTt.js.map} +1 -1
- package/dist/{engine-Dc996kAg.d.ts → engine-DlKIzDKo.d.ts} +2 -2
- package/dist/{engine-Dc996kAg.d.ts.map → engine-DlKIzDKo.d.ts.map} +1 -1
- package/dist/evaluation.d.ts +1 -1
- package/dist/experiment/index.d.ts +1 -1
- package/dist/hosted/index.js +1 -1
- package/dist/{index-lbwvO9vJ.d.ts → index-Bi2fLITd.d.ts} +3 -3
- package/dist/{index-lbwvO9vJ.d.ts.map → index-Bi2fLITd.d.ts.map} +1 -1
- package/dist/{index-D4pC7Tvd.d.ts → index-D4pC7Tvd2.d.ts} +1 -1
- package/dist/index-D4pC7Tvd2.d.ts.map +1 -0
- package/dist/{index-OuIM7sJz.d.ts → index-DKmrHA02.d.ts} +4 -4
- package/dist/{index-OuIM7sJz.d.ts.map → index-DKmrHA02.d.ts.map} +1 -1
- package/dist/{index-DNgf5gyG.d.ts → index-DNgf5gyG2.d.ts} +1 -1
- package/dist/index-DNgf5gyG2.d.ts.map +1 -0
- package/dist/{index-J8BB_NYv.d.ts → index-EkRNsLr4.d.ts} +6 -6
- package/dist/{index-J8BB_NYv.d.ts.map → index-EkRNsLr4.d.ts.map} +1 -1
- package/dist/index.d.ts +10 -10
- package/dist/index.js +4 -4
- package/dist/jev-protocol-CpKI7XSu.d.ts +82 -0
- package/dist/jev-protocol-CpKI7XSu.d.ts.map +1 -0
- package/dist/jev-protocol.d.ts +2 -82
- package/dist/jev-review-Cu9xtIu4.js +155 -0
- package/dist/jev-review-Cu9xtIu4.js.map +1 -0
- package/dist/jev-review-D4ynCORp.d.ts +76 -0
- package/dist/jev-review-D4ynCORp.d.ts.map +1 -0
- package/dist/jev.d.ts +3 -74
- package/dist/jev.d.ts.map +1 -1
- package/dist/jev.js +2 -151
- package/dist/jev.js.map +1 -1
- package/dist/{llm-judge-GSlZ0eG8.js → llm-judge-CL6f3utD.js} +4 -4
- package/dist/{llm-judge-GSlZ0eG8.js.map → llm-judge-CL6f3utD.js.map} +1 -1
- package/dist/matrix/index.d.ts +1 -1
- package/dist/{matrix-BnksRaDD.d.ts → matrix-_NLSWsKM.d.ts} +3 -3
- package/dist/{matrix-BnksRaDD.d.ts.map → matrix-_NLSWsKM.d.ts.map} +1 -1
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/golden/index.js +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/multishot/index.js +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{produced-state-D2ff-Dyo.js → produced-state-DZMW8cuF.js} +2 -2
- package/dist/{produced-state-D2ff-Dyo.js.map → produced-state-DZMW8cuF.js.map} +1 -1
- package/dist/rl.d.ts +279 -2
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +576 -2
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +1 -1
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-CumYAjA3.js → search-kernel-AVgIjXaI.js} +56 -15
- package/dist/search-kernel-AVgIjXaI.js.map +1 -0
- package/dist/{search-kernel-DA2-mS4N.d.ts → search-kernel-C9CXvFR7.d.ts} +6 -4
- package/dist/search-kernel-C9CXvFR7.d.ts.map +1 -0
- package/dist/{search-ledger-BnUytR8X.js → search-ledger-CL0-mXQ8.js} +4 -2
- package/dist/search-ledger-CL0-mXQ8.js.map +1 -0
- package/dist/{search-shipper-Cn8cxcyp.js → search-shipper-Cs6K4km9.js} +2 -2
- package/dist/{search-shipper-Cn8cxcyp.js.map → search-shipper-Cs6K4km9.js.map} +1 -1
- package/dist/{search-summary-dJOaZ3Dw.js → search-summary-DvWk0hb3.js} +2 -2
- package/dist/{search-summary-dJOaZ3Dw.js.map → search-summary-DvWk0hb3.js.map} +1 -1
- package/dist/{skillopt-optimization-method-DDt77V-N.js → skillopt-optimization-method-B2syNik0.js} +3 -3
- package/dist/{skillopt-optimization-method-DDt77V-N.js.map → skillopt-optimization-method-B2syNik0.js.map} +1 -1
- package/dist/{statistical-heldout-CMpxMjlQ.d.ts → statistical-heldout-HswMvzbP.d.ts} +2 -2
- package/dist/{statistical-heldout-CMpxMjlQ.d.ts.map → statistical-heldout-HswMvzbP.d.ts.map} +1 -1
- package/dist/{store-tool-spans-CUwWSXoj.d.ts → store-tool-spans-Dv9x4XYG.d.ts} +3 -3
- package/dist/{store-tool-spans-CUwWSXoj.d.ts.map → store-tool-spans-Dv9x4XYG.d.ts.map} +1 -1
- package/dist/{tool-groups-DVJAR1GE.d.ts → tool-groups-BY1MdSIE.d.ts} +2 -2
- package/dist/tool-groups-BY1MdSIE.d.ts.map +1 -0
- package/dist/trace-questions-DnqdmwyV.d.ts +68 -0
- package/dist/trace-questions-DnqdmwyV.d.ts.map +1 -0
- package/dist/trace-repair/index.d.ts +1 -1
- package/dist/traces.d.ts +2 -2
- package/dist/{tree-DxGfhISA.js → tree-Ki_gW7z8.js} +25 -26
- package/dist/{tree-DxGfhISA.js.map → tree-Ki_gW7z8.js.map} +1 -1
- package/dist/{types-B3jzCp0p2.js → types-B3jzCp0p.js} +1 -1
- package/dist/types-B3jzCp0p.js.map +1 -0
- package/dist/{types-D94EanDL.d.ts → types-C4hH69a9.d.ts} +2 -2
- package/dist/{types-D94EanDL.d.ts.map → types-C4hH69a9.d.ts.map} +1 -1
- package/dist/{types-EBUav9Bu.d.ts → types-DfvQOe91.d.ts} +4 -1
- package/dist/types-DfvQOe91.d.ts.map +1 -0
- package/docs/jev-behavior-review.md +24 -0
- package/docs/public-api.md +50 -31
- package/docs/search-ledger.md +20 -2
- package/package.json +1 -1
- package/dist/benchmark-command-CoBwYvau.js.map +0 -1
- package/dist/index-D4pC7Tvd.d.ts.map +0 -1
- package/dist/index-DNgf5gyG.d.ts.map +0 -1
- package/dist/jev-protocol.d.ts.map +0 -1
- package/dist/search-kernel-CumYAjA3.js.map +0 -1
- package/dist/search-kernel-DA2-mS4N.d.ts.map +0 -1
- package/dist/search-ledger-BnUytR8X.js.map +0 -1
- package/dist/tool-groups-DVJAR1GE.d.ts.map +0 -1
- package/dist/types-B3jzCp0p2.js.map +0 -1
- package/dist/types-EBUav9Bu.d.ts.map +0 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,7 +4,16 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
-
##
|
|
7
|
+
## [0.200.0] — 2026-09-27
|
|
8
|
+
|
|
9
|
+
- feat(rl): decide whether a checker-verified claim is a result about its source or only about its checker (#882)
|
|
10
|
+
|
|
11
|
+
## [0.199.1] — 2026-09-27
|
|
12
|
+
|
|
13
|
+
- fix(release): keep the analyst dependency pin stable across version bumps (#883)
|
|
14
|
+
- fix(search-lenses): charge an operator only for producing and screening its node (#881)
|
|
15
|
+
- build(release): move version and changelog prep to release time (#860)
|
|
16
|
+
- fix(search): preserve complete matrix output and bound clustering work (#880)
|
|
8
17
|
|
|
9
18
|
## [0.199.0] — 2026-09-27
|
|
10
19
|
|
package/dist/adapters/http.d.ts
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { m as CostReceipt } from "../cost-ledger-DbQdN3nO.js";
|
|
2
|
-
import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-
|
|
3
|
-
import "../index-
|
|
2
|
+
import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-DfvQOe91.js";
|
|
3
|
+
import "../index-EkRNsLr4.js";
|
|
4
4
|
//#region src/adapters/http.d.ts
|
|
5
5
|
interface HttpDispatchOptions<TScenario extends Scenario, _TArtifact> {
|
|
6
6
|
/** Static endpoint URL. Mutually exclusive with `resolveUrl`. */
|
package/dist/analyst/index.d.ts
CHANGED
|
@@ -4,12 +4,13 @@ import { A as createChatClient, C as ChatResponse, D as MockTransportOpts, E as
|
|
|
4
4
|
import { A as runAnalystBenchmark, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, M as scoreAnalystFindings, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, V as ExternalOptimizerModelCall, W as ExternalOptimizerModelExecutionObservation, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, j as traceStoreEvidenceResolver, k as registryBenchmarkRunner, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, q as ExternalOptimizerRunnerCommand, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner } from "../agent-profile-DDfIjdyS.js";
|
|
5
5
|
import { a as ExactAnalystRunPolicySnapshot, c as ExactAnalystSnapshot, d as ExactExecutionComponentSnapshot, i as ExactAnalystRunEvent, l as ExactCapableAnalyst, n as ExactAnalystExecutionPlanSnapshot, o as ExactAnalystRunResult, r as ExactAnalystRunCompletion, s as ExactAnalystRunSummary, t as ExactAnalystBudgetSnapshot, u as ExactExecutionComponentIdentity } from "../exact-types-KGxBWH4b.js";
|
|
6
6
|
import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-Bu3lNole.js";
|
|
7
|
-
import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-
|
|
8
|
-
import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-
|
|
9
|
-
import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-
|
|
10
|
-
import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-
|
|
7
|
+
import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-D1rNS2yB.js";
|
|
8
|
+
import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-DlKIzDKo.js";
|
|
9
|
+
import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-BY1MdSIE.js";
|
|
10
|
+
import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-Bi2fLITd.js";
|
|
11
11
|
import { A as ReplyRowDecoded, C as primeProtocolSha256, D as DecodedReply, E as runPrimeExchange, M as decodeReplyRows, O as ReplyContract, S as normalizePrimeUsage, T as projectPrimeTrajectory, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as extractPrimeJsonObject, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, j as ReplyRowRejection, k as ReplyEnvelope, l as PrimeRawUsage, m as PrimeRowDecoded, n as PrimeExchangeOutcome, o as PrimeProjectionSource, p as PrimeReplyContract, r as PrimeFailure, s as PrimePromptSpec, t as PrimeExchangeOptions, u as PrimeRejectedRow, v as buildPrimeRepairPrompt, w as primeReplyDefect, x as mergePrimeRawUsage, y as emptyPrimeRawUsage } from "../prime-protocol-T0i6xcAs.js";
|
|
12
12
|
import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
|
|
13
|
+
import { a as askTraceQuestions, i as VerifiedTraceFinding, n as TraceQuestionOutcome, o as citedSpansOnly, r as TraceQuestionSpec, t as AskTraceQuestionsOptions } from "../trace-questions-DnqdmwyV.js";
|
|
13
14
|
import { z } from "zod";
|
|
14
15
|
//#region src/analyst/adapters.d.ts
|
|
15
16
|
interface SemanticConceptJudgeAdapterOpts {
|
|
@@ -1179,9 +1180,11 @@ declare function runAnalystBenchmarkCommand(argv: readonly string[], env?: NodeJ
|
|
|
1179
1180
|
//#endregion
|
|
1180
1181
|
//#region src/analyst/benchmark-implementation.d.ts
|
|
1181
1182
|
declare const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256-canonical-source-manifest";
|
|
1182
|
-
|
|
1183
|
+
/** The dependency files' manifest digest with the package's own version
|
|
1184
|
+
* fields blanked, so a release that only bumps the version keeps the pin. */
|
|
1185
|
+
declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest-without-own-version";
|
|
1183
1186
|
declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES: readonly string[];
|
|
1184
|
-
declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "
|
|
1187
|
+
declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "007041f0de3b376aa3def1d3efe8221a724030a22ac0a7988921db12c4624c09";
|
|
1185
1188
|
declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
|
|
1186
1189
|
declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
|
|
1187
1190
|
declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
|
|
@@ -1355,68 +1358,5 @@ declare function isProposalFinding(finding: unknown): finding is ProposalFinding
|
|
|
1355
1358
|
*/
|
|
1356
1359
|
declare function assertProposalFindings(findings: unknown, context?: string): ReadonlyArray<ProposalFinding>;
|
|
1357
1360
|
//#endregion
|
|
1358
|
-
//#region src/analyst/trace-questions.d.ts
|
|
1359
|
-
/** One question to ask of the store. */
|
|
1360
|
-
interface TraceQuestionSpec {
|
|
1361
|
-
/** Stable id: letters, digits, dot, underscore, hyphen. */
|
|
1362
|
-
readonly id: string;
|
|
1363
|
-
readonly question: string;
|
|
1364
|
-
/** Guidance for this question only, after the shared rules. */
|
|
1365
|
-
readonly instructions?: string;
|
|
1366
|
-
}
|
|
1367
|
-
interface AskTraceQuestionsOptions {
|
|
1368
|
-
readonly questions: readonly TraceQuestionSpec[];
|
|
1369
|
-
readonly store: TraceAnalysisStore;
|
|
1370
|
-
readonly engine: TraceAnalysisEngine;
|
|
1371
|
-
/** Every question and verifier charges this ledger; its ceiling bounds the whole call. */
|
|
1372
|
-
readonly costLedger: CostLedgerHandle;
|
|
1373
|
-
/** Stable id for cost attribution and logs. */
|
|
1374
|
-
readonly runId: string;
|
|
1375
|
-
/** Material every question receives before its first model call, such as the check's verdict. */
|
|
1376
|
-
readonly context?: string;
|
|
1377
|
-
/** Investigations running at once. Default 4. */
|
|
1378
|
-
readonly concurrency?: number;
|
|
1379
|
-
/** Distinct citations a finding needs. Default 2. */
|
|
1380
|
-
readonly minimumEvidenceCitations?: number;
|
|
1381
|
-
/** Run the independent verifier on every admitted finding. Default true. */
|
|
1382
|
-
readonly verify?: boolean;
|
|
1383
|
-
readonly limits?: Partial<TraceAnalystLimits>;
|
|
1384
|
-
readonly signal?: AbortSignal;
|
|
1385
|
-
readonly log?: (message: string, fields?: Record<string, unknown>) => void;
|
|
1386
|
-
}
|
|
1387
|
-
/** A finding and what the verifier, shown only its cited spans, concluded. */
|
|
1388
|
-
interface VerifiedTraceFinding {
|
|
1389
|
-
readonly finding: RawAnalystFinding;
|
|
1390
|
-
/** The finding's trace citations, as `trace://` URIs. */
|
|
1391
|
-
readonly citations: readonly string[];
|
|
1392
|
-
/** `true` supported, `false` not supported, `null` when verification was off or failed. */
|
|
1393
|
-
readonly verified: boolean | null;
|
|
1394
|
-
/** The verifier's own words, when it answered. */
|
|
1395
|
-
readonly verifierAnswer?: string;
|
|
1396
|
-
}
|
|
1397
|
-
interface TraceQuestionOutcome {
|
|
1398
|
-
readonly id: string;
|
|
1399
|
-
readonly question: string;
|
|
1400
|
-
readonly status: 'answered' | 'failed';
|
|
1401
|
-
readonly failure?: string;
|
|
1402
|
-
/** The engine's prose answer, verbatim; `null` when it returned none. */
|
|
1403
|
-
readonly answer: string | null;
|
|
1404
|
-
readonly findings: readonly VerifiedTraceFinding[];
|
|
1405
|
-
/** `null` when the engine failed before reporting. */
|
|
1406
|
-
readonly modelCalls: number | null;
|
|
1407
|
-
readonly toolCalls: number | null;
|
|
1408
|
-
}
|
|
1409
|
-
/**
|
|
1410
|
-
* Ask every question, then verify every admitted finding. Never throws for a failed question or
|
|
1411
|
-
* verifier: each failure is recorded on its outcome. Throws before any model call for a malformed
|
|
1412
|
-
* question list or options.
|
|
1413
|
-
*/
|
|
1414
|
-
declare function askTraceQuestions(opts: AskTraceQuestionsOptions): Promise<TraceQuestionOutcome[]>;
|
|
1415
|
-
/**
|
|
1416
|
-
* A store that exposes exactly the cited spans. Discovery and whole-trace reads refuse, so the
|
|
1417
|
-
* verifier cannot go looking for other support; the underlying store's bounds still apply.
|
|
1418
|
-
*/
|
|
1419
|
-
declare function citedSpansOnly(store: TraceAnalysisStore, allowed: ReadonlyMap<string, ReadonlySet<string>>): TraceAnalysisStore;
|
|
1420
|
-
//#endregion
|
|
1421
1361
|
export { AGENT_RX_UPSTREAM_REVISION, ANALYST_BENCHMARK_COST_LEDGER_FILE, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, ANALYST_BENCHMARK_IMPLEMENTATION_FILES, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, ANALYST_BENCHMARK_MANIFEST_FILE, ANALYST_BENCHMARK_OBSERVATIONS_FILE, type AgentRxBenchmarkCaseOptions, type AgentRxCalibrationRunnerSummary, type AgentRxCalibrationSummary, type AgentRxFailure, type AgentRxPrediction, type AgentRxPredictionReport, type AgentRxRow, type Analyst, type AnalystBenchmarkArtifact, type AnalystBenchmarkCase, type AnalystBenchmarkCommandConfig, type AnalystBenchmarkCommandDependencies, type AnalystBenchmarkDatasetRef, type AnalystBenchmarkDescriptor, type AnalystBenchmarkError, type AnalystBenchmarkLabelState, type AnalystBenchmarkLocalRunReceipt, type AnalystBenchmarkObservation, type AnalystBenchmarkOutput, type AnalystBenchmarkProgressRow, type AnalystBenchmarkProvenance, type AnalystBenchmarkResult, type AnalystBenchmarkRunIdentity, type AnalystBenchmarkRunManifest, type AnalystBenchmarkRunner, type AnalystBenchmarkSummary, type AnalystBudgetDeclaration, type AnalystComparisonMetric, type AnalystContext, type AnalystCost, type AnalystDefinition, type AnalystDefinitionAsymmetry, type AnalystDefinitionAsymmetryReport, type AnalystEvidenceBinding, type AnalystEvidenceExpectation, type AnalystEvidenceResolution, type AnalystEvidenceResolutionError, type AnalystEvidenceResolver, AnalystExpressivenessError, type AnalystFinding, type AnalystFindingScore, type AnalystHooks, type AnalystInputKind, type AnalystInstructionsOverride, type AnalystIssueExpectation, type AnalystLatencyDistribution, type AnalystMetricComparison, type AnalystProfileFragment, AnalystRegistry, type AnalystRegistryOptions, type AnalystRepairDeclaration, type AnalystRequirements, type AnalystRowExpansion, type AnalystRunEvent, type AnalystRunInputs, type AnalystRunResult, type AnalystRunSummary, type AnalystRunnerComparison, type AnalystSeverity, type AnalystTransportBinding, type AnalystUsageReceipt, type AskTraceQuestionsOptions, type BehavioralAnalystOptions, type BudgetPolicy, CODE_TRACE_BENCH_ANALYST_PROMPT, CONTROL_INTEGRITY_ANALYST, type ChatCallOpts, type ChatClient, type ChatRequest, type ChatResponse, type ChatTraceEngineOptions, type ChatTransport, type ChunkedEvidenceBinding, type CodeTraceBenchCaseOptions, type CodeTraceBenchLabelOptions, type CodeTraceBenchLabelSet, type CodeTraceBenchRow, type CodeTraceBlockDiagnostics, type CodeTraceCalibrationRunnerSummary, type CodeTraceCalibrationSummary, type CodeTraceFailureBlock, type CodeTraceStageAnnotation, type CodeTracerLabelGroup, type CodeTracerPredictionAdapterOptions, type CodeTracerPredictions, type CodeTracerStepLabel, ControlIntegrityAnalyst, type CreateChatClientOpts, type CreateTraceAnalystOptions, type CustomTransportOpts, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, DEFAULT_TRACE_ANALYST_KINDS, DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, type DecodedReply, type DefaultAnalystRegistryOptions, type DefineCustomAnalystOptions, type DefineExactCustomAnalystOptions, type DiffPolicy, type DspyRlmTraceEngineOptions, type EvidenceProjection, type EvidenceRef, type ExactAnalystBudgetPolicy, type ExactAnalystBudgetSnapshot, type ExactAnalystExecutionPlanSnapshot, type ExactAnalystRunCompletion, type ExactAnalystRunEvent, ExactAnalystRunExecutionError, type ExactAnalystRunPolicySnapshot, type ExactAnalystRunResult, type ExactAnalystRunSummary, type ExactAnalystSnapshot, type ExactCapableAnalyst, type ExactExecutionComponentIdentity, type ExactExecutionComponentSnapshot, type ExactRegistryRunOpts, type ExecutionProbe, type ExecutionProbeOutcome, type ExecutionProbeRequest, type ExpandRowsArgs, FAILURE_MODE_KIND_SPEC, FINDING_SUBJECT_KINDS, FINDING_SUBJECT_SYNTAX, type FindingSubject, type FindingSubjectKind, type FindingsDiff, FindingsStore, IMPROVEMENT_KIND_SPEC, type InlineEvidenceBinding, KIND_EXPECTED_SUBJECTS, KNOWLEDGE_GAP_KIND_SPEC, KNOWLEDGE_POISONING_KIND_SPEC, type LoadedVerificationArtifacts, MAX_INCORRECT_BLOCKS, MAX_INCORRECT_BLOCK_STEPS, type MockTransportOpts, type OpenAiCompatibleTransportOpts, type PersistedFinding, type PreparedPublicAnalystBenchmark, type PrimeBenchmarkRunnerOptions, type PrimeBridgeTransport, type PrimeBridgeTransportRequest, type PrimeBridgeTransportResult, type PrimeCodeTraceDefinitionArgs, type PrimeExchangeOptions, type PrimeExchangeOutcome, type PrimeFailure, type PrimeProjectionDelivery, type PrimeProjectionOutcome, type PrimeProjectionSource, type PrimePromptSpec, type PrimeProtocolIdentity, type PrimeRawUsage, type PrimeRejectedRow, type PrimeRepairPromptSpec, type PrimeRepairState, type PrimeReplyContract, type PrimeRowDecoded, type PrimeTurnRecord, type ProposalFinding, type ProposalFindingOrigin, type PublicAnalystBenchmarkDataset, type PublicAnalystBenchmarkModelConfig, type PublicAnalystBenchmarkModelOwner, type PublicAnalystBenchmarkModelSettings, type PublicBenchmarkDistributions, type PublicBenchmarkModelPrediction, type PublicBenchmarkSelectionReport, type PublicBenchmarkValueDistribution, type PublicDirectDefinitionArgs, type PublicRlmDefinitionArgs, RAW_FINDING_SCHEMA_PROMPT, type RawAnalystEvidence, type RawAnalystFinding, RawAnalystFindingSchema, type RegistryRunOpts, type ReplVariableConsensusPort, type ReplVariableEvidenceBinding, type ReplyContract, type ReplyEnvelope, type ReplyRowDecoded, type ReplyRowRejection, type RunAnalystBenchmarkOptions, SKILL_USAGE_ANALYST, type SandboxSdkTransportOpts, type SemanticConceptJudgeAdapterOpts, type SkillUsageRecord, type SkillUsageReport, type SkillUsageScanConfig, type StepLabelAdapterOptions, type TraceAnalysisEngine, type TraceAnalysisEngineRequest, type TraceAnalysisEngineResult, type TraceAnalystDefinition, type TraceAnalystLimits, type TraceQuestionOutcome, type TraceQuestionSpec, type TraceToolGroupName, type UpstreamPredictionAdapterOptions, type VerificationArtifactFile, type VerificationArtifactManifest, type VerificationArtifactRole, type VerificationAvailabilitySummary, type VerificationOutcome, type VerificationOutcomeSource, type VerificationOutcomeStatus, type VerificationResultFile, type VerifiedTraceFinding, adaptPublicBenchmarkFindings, agentRxBenchmarkCase, agentRxPredictionsToFindings, analystBenchmarkDependencyLockDigest, analystBenchmarkImplementationDigest, analystDefinitionAsymmetries, analystDefinitionProtocolSha256, analystInstructionsOverrideFromText, analystUsageReceiptFromPrimeUsage, appendVerificationArtifactsToOtlp, askTraceQuestions, assertProposalFindings, behavioralAnalyst, bindAnalyst, buildDefaultAnalystRegistry, buildPrimePrompt, buildPrimeRepairPrompt, buildSkillUsageReport, buildTraceToolsForGroup, citedSpansOnly, codeTraceBenchCase, codeTracerPredictionsToFindings, coerceJson, compareAnalystRunners, computeFindingId, createChatClient, createChatTraceEngine, createDspyRlmTraceEngine, createPrimeBenchmarkRunner, createPublicBenchmarkDirectRunner, createPublicBenchmarkRlmRunner, createSemanticConceptJudgeAdapter, createTraceAnalyst, decodeReplyRows, defaultIsMaterial, defineCustomAnalyst, defineTraceAnalyst, deriveEfficiencyFindings, diffFindings, effectiveAnalystProtocolSha256, emitControlIntegrityFindings, emitSkillUsageFindings, emptyPrimeRawUsage, emptyPublicBenchmarkRunner, evidenceRefsFromRawFinding, expandCodeTraceFailureBlocks, extractPrimeJsonObject, findingSubjectGrammarPromptFor, isProposalFinding, loadCodeTraceVerificationArtifacts, loadPublicBenchmarkRows, makeFinding, makeProposalFinding, mergePrimeRawUsage, nodeHttpPrimeBridgeTransport, normalizeAgentRxCategory, normalizeBenchmarkLabel, normalizePrimeUsage, parseFindingSubject, parseRawFinding, parseVerificationOutcome, preparePublicAnalystBenchmark, primeAnalystProtocolSha256, primeCodeTraceAnalystDefinition, primeProtocolSha256, primeReplyDefect, projectPrimeTrajectory, publicBenchmarkDistributions, publicBenchmarkProtocolSha256, publicBenchmarkRlmInstructions, publicBenchmarkSelectionReport, publicBenchmarkSystemPrompt, publicDirectAnalystDefinition, publicRlmAnalystDefinition, readAnalystBenchmarkArtifact, readAnalystInstructionsOverride, registryBenchmarkRunner, renderAgentRxCalibrationMarkdown, renderAnalystBenchmarkMarkdown, renderCodeTraceCalibrationMarkdown, renderFindingSubject, renderPriorFindings, resolveTraceAnalystLimits, rlmEngineLimits, roundAgentRxStep, runAnalystBenchmark, runAnalystBenchmarkCommand, runPrimeExchange, runTraceAnalyst, scoreAnalystFindings, selectPublicBenchmarkRows, stripCodeFences, summarizeAgentRxCalibration, summarizeAnalystBenchmarkRunner, summarizeCodeTraceCalibration, traceStoreEvidenceResolver };
|
|
1422
1362
|
//# sourceMappingURL=index.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","names":[],"sources":["../../src/analyst/adapters.ts","../../src/analyst/benchmark-agentrx-calibration.ts","../../src/analyst/benchmark-dataset-types.ts","../../src/analyst/benchmark-dataset-agentrx.ts","../../src/analyst/benchmark-dataset-codetrace.ts","../../src/analyst/benchmark-dataset-utils.ts","../../src/analyst/benchmark-verification-outcome.ts","../../src/analyst/benchmark-verification-artifacts.ts","../../src/analyst/benchmark-public-types.ts","../../src/analyst/benchmark-public-adapters.ts","../../src/analyst/benchmark-public-data.ts","../../src/analyst/definition.ts","../../src/analyst/benchmark-public-prompt.ts","../../src/analyst/benchmark-public-model.ts","../../src/analyst/benchmark-public-rlm.ts","../../src/analyst/benchmark-runner-prime.ts","../../src/analyst/benchmark-comparison.ts","../../src/analyst/benchmark-public-calibration.ts","../../src/analyst/benchmark-command-artifact.ts","../../src/analyst/benchmark-command-result.ts","../../src/analyst/benchmark-command.ts","../../src/analyst/benchmark-implementation.ts","../../src/analyst/benchmark-instructions-override.ts","../../src/analyst/benchmark-report.ts","../../src/analyst/benchmark-summary.ts","../../src/analyst/bind.ts","../../src/analyst/define.ts","../../src/analyst/kinds/skill-usage.ts","../../src/analyst/parse-tolerant.ts","../../src/analyst/proposal-findings.ts"
|
|
1
|
+
{"version":3,"file":"index.d.ts","names":[],"sources":["../../src/analyst/adapters.ts","../../src/analyst/benchmark-agentrx-calibration.ts","../../src/analyst/benchmark-dataset-types.ts","../../src/analyst/benchmark-dataset-agentrx.ts","../../src/analyst/benchmark-dataset-codetrace.ts","../../src/analyst/benchmark-dataset-utils.ts","../../src/analyst/benchmark-verification-outcome.ts","../../src/analyst/benchmark-verification-artifacts.ts","../../src/analyst/benchmark-public-types.ts","../../src/analyst/benchmark-public-adapters.ts","../../src/analyst/benchmark-public-data.ts","../../src/analyst/definition.ts","../../src/analyst/benchmark-public-prompt.ts","../../src/analyst/benchmark-public-model.ts","../../src/analyst/benchmark-public-rlm.ts","../../src/analyst/benchmark-runner-prime.ts","../../src/analyst/benchmark-comparison.ts","../../src/analyst/benchmark-public-calibration.ts","../../src/analyst/benchmark-command-artifact.ts","../../src/analyst/benchmark-command-result.ts","../../src/analyst/benchmark-command.ts","../../src/analyst/benchmark-implementation.ts","../../src/analyst/benchmark-instructions-override.ts","../../src/analyst/benchmark-report.ts","../../src/analyst/benchmark-summary.ts","../../src/analyst/bind.ts","../../src/analyst/define.ts","../../src/analyst/kinds/skill-usage.ts","../../src/analyst/parse-tolerant.ts","../../src/analyst/proposal-findings.ts"],"mappings":";;;;;;;;;;;;;;;UA8CiB;EACf;EACA;;EAEA,SAAS,KAAK;;EAEd;;iBAGc,kCACd,MAAM,kCACL,QAAQ;;;cCtDE;UAEI;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA,SAAS;;iBAGK,4BACd,QAAQ,wBACR,2BACC;iBAkBa,iCAAiC,SAAS;;;KCtD9C;UAEK;EACf,YAAY;EACZ;EACA;EACA;EACA;EACA;;UAGe;EACf,eAAe;EACf,mBAAmB;EACnB;IAAe,YAAY;IAAY;;EACvC,wBAAwB;EACxB;EACA;EACA;;UAGe;EACf,UAAU;EACV;EACA;EACA;EACA;;UAGe;EACf,UAAU;EACV,mBAAmB;EACnB;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA,iBAAiB;;KAGP,0CAEC,sCACA,iCACA;UAEI;EACf;EACA;EACA;EACA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA,oCAAoC;;UAGrB;EACf,eAAe;EACf,WAAW,sBAAsB;;KAGvB;UAEK;;;;;EAKf,WAAW;;UAGI,kCACP,yBACN;UAEa,oCAAoC;EACnD;;EAEA;;UAGe,yCAAyC;EACxD;EACA;EACA;EACA;;UAGe,2CACP,kCACN;;;iBCtGY,qBAAqB,QACnC,KAAK,YACL,OAAO,QACP,UAAS,8BACR,qBAAqB;;iBAsGR,6BACd,mBAAmB,YACnB,iBACA,UAAS,mCACR;iBA6Ea,yBAAyB;;iBAoNzB,iBAAiB;;;iBC/YjB,mBAAmB,QACjC,KAAK,mBACL,OAAO,QACP,UAAS,4BACR,qBAAqB;;iBAwFR,gCACd,2BACA,aAAa,uBACb,UAAS,qCACR;;;iBClHa,wBAAwB;;;KCA5B;UAEK;EACf;EACA;EACA,QAAQ;;UAGO;EACf,QAAQ;EACR;EAKA;IAAe;IAAe;;EAC9B,SAAS;EACT;EACA;EACA;EACA;;UAGe;EACf;EACA;;iBA8Ec,yBACd,gBAAgB,2BACf;;;cC/FU;KAED;UAEK;EACf,MAAM;EACN;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,SAAS;EACT;EACA;EACA;EACA;EACA;EACA,OAAO;EACP,cAAc;EACd,UAAU,OAAO;;UAGF;EACf,UAAU;EACV,SAAS;EACT,OAAO,MAAM;IAA6B;;;iBAatB,mCAAmC;EACvD;EACA,KAAK;EACL;IACE,QAAQ;iBAwHI,kCACd,kBACA,iBACA,WAAW,6BACX;;;KC7KU;;;;;;;;UASK;;WAEN;;WAEA;;;UAIM;EACf,MAAM;EACN;EACA,kBAAkB,aAAa;;EAE/B,UAAU;;UAGK;;EAEf,MAAM;;EAEN;;EAEA,kBAAkB,aAAa;EAC/B;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,UAAU;;EAEV;;EAEA,uBAAuB;EACvB;IACE,SAAS;IACT;IACA;IACA;IACA;IACA;IACA;IACA;IACA;;;;;;IAMA;;EAEF,aAAa;EACb;IACE;IACA;;;;;;;;;KAUQ,sCAAsC,KAChD,iEAGA,QAAQ,KAAK;UAEE;EACf,OAAO,qBAAqB;EAC5B;EACA;EACA;EACA,YAAY;IACV;IACA;IACA;;EAEF,uBAAuB;EACvB,WAAW;;UAGI;EACf;EACA;EACA,QAAQ;;UAGO;EACf,OAAO;EACP,OAAO;EACP,OAAO;EACP,YAAY;EACZ,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;EACA;EACA,QAAQ;EACR,UAAU;;;;;;;;;;UChHK;EACf;EACA;;EAEA;EACA;EACA,UAAU;EACV;EACA;EACA;EACA;EACA,WAAW;;;;;;;;;UAUI;EACf;EACA;;EAEA,kCAAkC;;EAElC;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;;UASe;EACf;EACA,OAAO;;iBAGO,8BAA8B,uBAAuB;iBAiB/C,6BAA6B;EACjD,SAAS;EACT;EACA,mBAAmB;EACnB;EACA,OAAO;EACP,SAAS;IACP;EACF,UAAU;EACV,aAAa;;EAEb,aAAa;;;;;;;;;iBA4MO,6BAA6B;EACjD;EACA,iBAAiB;EACjB,OAAO;EACP;EACA;EACA,SAAS;IACP;EACF,UAAU;EACV,aAAa;EACb,YAAY;;;;iBCrQQ,wBACpB,eACC,QAAQ,MAAM;iBA2BD,0BACd,SAAS,+BACT,eAAe,2BACf;EAAW;EAAe;IACzB,MAAM;iBAwBO,6BACd,SAAS,+BACT,eAAe,4BACd;iBAyCa,+BACd,SAAS,+BACT,iBAAiB,2BACjB,mBAAmB,2BACnB,eACC;iBAcmB,8BAA8B;EAClD,SAAS;EACT;EACA;EACA;EACA;EACA;EACA;IACE,QAAQ;;;;;;;;KCnIA,yBAAyB,KAAK;;;;;;KAS9B;WAEG;;WAEA;;;;;;WAMA;;WAGA;;WAEA;;;WAIA;WACA,WAAW;;;WAIX;WACA,WAAW;;UAKT;;WAEN;;WAEA;;WAEA;;WAEA,eAAe;;UAGT;;;;;WAKN;;UAKM;EACf,UAAU;;EAEV;;UAGe,eAAe;;EAE9B;EACA,eAAe;EACf,OAAO;EACP;EACA;;EAEA;EACA,SAAS;;;UAIM,sBAAsB;WAC5B;EACT,kBAAkB;;WAET,cAAc,SAAS;;;;;EAKhC,OAAO,iBAAiB,gBAAgB;;EAExC,QAAQ,iBAAiB,gBAAgB;EACzC,WAAW,MAAM,eAAe,QAAQ,QAAQ;;;UAIjC,uBAAuB;WAC7B;EACT,kBAAkB;WACT,cAAc,SAAS;;WAEvB;;WAEA;;EAET,YAAY;EACZ,WAAW,MAAM,eAAe,QAAQ,QAAQ;;EAEhD,gBAAgB;IACd;IACA,mBAAmB;IACnB,OAAO;IACP,SAAS;MACP;;;UAIW,0BAA0B,aAAa;;EAEtD,KAAK,SAAS,uBAAuB;IACnC,iBAAiB;IACjB;;;EAGF,OAAO;IACL;IACA,iBAAiB;IACjB,OAAO;IACP;IACA;IACA,SAAS;MACP,QAAQ;;EAEZ,aAAa,sBAAsB,gBAAgB;;;UAIpC,4BAA4B,uBAAuB;WACzD;;WAEA;EACT,kBAAkB;WACT,cAAc,SAAS;;WAEvB,qBAAqB,SAAS;;WAE9B;;EAET,qBAAqB,8BAA8B;;EAEnD,MAAM;IACJ;IACA,mBAAmB;IACnB;IACA,OAAO;IACP,SAAS;MACP;IAAU,UAAU;IAAkB,aAAa;IAAe;;;EAEtE,YAAY,0BAA0B,aAAa;;EAEnD,mBACE,QAAQ,oCACP,uBAAuB;;KAGhB,uBAAuB,MAAM,uBAAuB,oBAC5D,sBAAsB,QACtB,uBAAuB,QACvB,4BAA4B,aAAa;UAI5B,kBAAkB,gBAAgB,uBAAuB;;WAE/D;WACA;WACA;;WAEA;WACA,SAAS;;WAET;;WAEA;WACA,YAAY;WACZ,eAAe,cAAc;;;;;;WAM7B,gBAAgB,SAAS;WACzB,QAAQ;WACR,QAAQ;;;;;;WAMR;WACA,SAAS,uBAAuB,MAAM,aAAa;;;;;;;;;cAUjD,mCAAmC;;;;;;;iBAUhC,gCAAgC,MAAM,aAAa,QACjE,YAAY,kBAAkB,MAAM,aAAa;;UAwClC;WACN;WACA,gBAAgB;WAChB,iBAAiB,YAAY;WAC7B;WACA;WACA;;WAEA;;WAEA;;UAGM;WACN;;WAEA;;WAEA,sBAAsB;WACtB,sBAAsB;;;;;;;;;iBAUjB,6BACd,aAAa,cAAc,gDAC1B;;;;;;;cCzUU;;;;cAKA;cAMA;;iBA8GG,4BAA4B,SAAS;;iBASrC,+BAA+B,SAAS;;;;iBAcxC,8BAA8B,SAAS;;;;;;;;;;;;;UC5EtC;;EAEf;;EAEA;;EAEA;;;iBAIc,8BACd,SAAS,+BACT,MAAM,6BACL,kBAAkB;;iBAsEL,kCACd,SAAS,+BACT,QAAQ,oCACP,uBAAuB;cAwhBpB,yBAAuB,EAAA;;;;;;;;;;;;;GASlB,EAAA,KAAA;cACL,gCAA8B,EAAA;;;;;;;;;;;;;;;;;;;GAsChC,EAAA,KAAA;cACE,uBAAqB,EAAA;;;;;;;;;;;;KA2BtB,yBAAyB,EAAE,aAAa;EAC3C,WAAW,EAAE,aAAa;;KAEvB,2BAA2B,EAAE,aAAa;KACnC,iCAAiC,yBAAyB;;;;;;;;;;;;;UCjtBrD;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,cAAc;;;iBAIA,2BACd,SAAS,+BACT,MAAM,0BACL,kBAAkB,mBAAmB;;iBA+GxB,+BACd,SAAS,+BACT,QAAQ,oCACP,uBAAuB;;iBAwBV,gBAAgB,QAAQ,oCAAoC;;;UCtI3D;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA,UAAU;;EAEV,YAAY;;;;;;iBA8EE;UAIC;;EAEf;;EAEA;;;;;;iBAOc,gCACd,MAAM,+BACL,kBAAkB;;iBAyDL,2BACd,SAAS,8BACR,uBAAuB;;;;;;;;;;cC5OpB;WACQ;WACC;WACK;WACd;WACkB;WACJ;WACO;WACD;WACJ;WACK;WACd;WACJ;WACM;WACC;WACG;WACH;WACI;WACT;;KAGC,uCAAuC;UAgBlC;EACf,QAAQ;EACR;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,SAAS;;iBASK,sBACd,QAAQ,wBACR;EACE;EACA;EACA;EACA;EACA;IAED;;;UC3Fc;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,SAAS;;iBAGK,8BACd,QAAQ,yBACP;iBAca,mCAAmC,SAAS;;;UCpC3C;EACf;EACA;EACA;IACE,SAAS;IACT;IACA;IACA;IACA;IACA,YAAY;MAAQ;MAAiB;MAAsB;;IAC3D,uBAAuB;IACvB,0BAA0B;IAC1B;MACE;MACA;MACA;MACA,QAAQ;;IAEV;MACE;MACA;;MAEA;MACA;;MAEA;MACA;MACA;MACA;MACA;MACA;MACA;MACA,UAAU;MACV;QACE;QACA;QACA;QACA;QACA;QACA;QACA;QACA;;MAEF;QACE;QACA;QACA;;MAEF;MACA;MACA;;MAEA;MACA;MACA;;;EAGJ,QAAQ;EACR,aAAa;EACb,uBAAuB;EACvB,qBAAqB;;UAGN;EACf;EACA;EACA;EACA;IACE;IACA;IACA;;;UAIa;EACf;IACE,SAAS;IACT;IACA;IACA;MACE;MACA;MACA;MACA;MACA;MACA;MACA;MACA;MACA,SAAS;MACT;QACE;QACA;QACA;QACA;QACA;QACA;QACA;QACA;;MAEF;QACE;QACA;QACA;;;IAGJ;IACA;IACA;IACA;;IAEA;IACA;IACA;IACA;;IAEA;IACA;IACA;IACA;;EAEF;IACE;IACA;IACA;IACA,YAAY;MAAQ;MAAiB;MAAsB;;IAC3D;IACA;;;UAIa;EACf;EACA;EACA;EACA;EACA,UAAU;;UAGK;EACf;EACA;EACA;EACA;IACE;IACA;IACA;IACA;;IAEA;;EAEF;EACA;IACE;IACA;IACA;;EAEF;IACE;IACA;IACA;IACA;IACA;IACA;;;UAIa;EACf;EACA;EACA;EACA,aAAa;EACb;;cAGW;cACA;cACA;cACA;;;iBC5KS,6BACpB,eACC,QAAQ;;;UCuEM;EACf,uBACE,SAAS,+BACT,QAAQ,wCACL,uBAAuB;EAC5B,2BACE,mBACA;IACE;IACA,aAAa,SAAS,OAAO;QAE5B,QAAQ;;;;;;;;;KAUH;;UAGK;EACf;EACA;;UAGe;EACf,SAAS;EACT,SAAS;EACT;EACA;EACA;EACA;EACA;EACA;EACA,OAAO;EACP;EACA;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;EAEA,QAAQ;EACR;EACA;;iBAKoB,2BACpB,yBACA,MAAK,OAAO,YACZ,eAAc,sCACb;;;cCzJU;;;cAIA;cAGA;cAOA;cAYA;cAGA;cAGA;cAiHA;iBAGG;iBAIA;;;;iBC/IA,oCAAoC,eAAe;;iBAQnD,gCAAgC,eAAe;;;;;;;;;;;iBAyB/C,+BACd,SAAS,+BACT,WAAW,KAAK;;;iBCzCF,+BACd,QAAQ,wBACR,uBAAsB;;;iBCIR,gCACd,kBACA,uBAAuB,gCACtB;;;;KCcS;;WAGG;WACA;WACA;WACA,YAAY;WACZ,UAAU;;;WAIV;WACA,QAAQ;;;;;;iBAOP,YAAY,MAAM,aAAa,QAC7C,YAAY,kBAAkB,MAAM,aAAa,SACjD,YAAY,0BACX,uBAAuB;;;;;;;;;;iBCpCV,mBAAmB,YAAY,yBAAyB;UAkBvD;EACf;EACA;EACA;EACA,MAAM;EACN,SAAS,QAAQ;;UAGF,wCAAwC;;EAEvD,iBAAiB,SAAS;;;iBAIZ,oBACd,SAAS,kCACR,oBAAoB;iBACP,oBACd,SAAS,6BACR,QAAQ;;;KCpBC;;UAGK;EACf;EACA,MAAM;;EAEN;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;EACA;EACA;;EAEA;;EAEA;;UAGe;EACf;EACA,SAAS;;UAGM;;EAEf;;EAEA;IAAc;IAAc,MAAM;;;EAElC;;;EAGA,kBAAkB;;EAElB;;;iBA2Ec,sBAAsB,QAAQ,uBAAuB;;iBAiHrD,uBACd,QAAQ,kBACR,qBACC;cA2HG,6BAA6B,oBAAoB;WAC5C;WACA;WAEA;WACA;IAAS;IAAgC;;WACzC;WACA;aACP;aACA;aACA;;EAGI,QAAQ,OAAO,kBAAkB,KAAK,iBAAiB,QAAQ;;cAS1D,qBAAmB;;;;;;;;;;;;;;;iBC5YhB,gBAAgB;;;;;iBAgBhB,WAAW;;;;iBCIX,kBAAkB,mBAAmB,WAAW;;;;;;iBAShD,uBACd,mBACA,mBACC,cAAc"}
|
package/dist/analyst/index.js
CHANGED
|
@@ -8,7 +8,7 @@ import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-B5T43BkZ.js";
|
|
|
8
8
|
import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, o as createChatTraceEngine, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-2SE_kXGF.js";
|
|
9
9
|
import { t as createChatClient } from "../chat-client-CJORSG_J.js";
|
|
10
10
|
import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BeQJyrRC.js";
|
|
11
|
-
import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-
|
|
11
|
+
import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-EBmuMUBo.js";
|
|
12
12
|
import { a as extractPrimeJsonObject, c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, i as emptyPrimeRawUsage, l as primeReplyDefect, n as buildPrimePrompt, o as mergePrimeRawUsage, r as buildPrimeRepairPrompt, s as normalizePrimeUsage, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "../prime-protocol-DcAK9pC8.js";
|
|
13
13
|
import { t as nodeHttpPrimeBridgeTransport } from "../prime-bridge-transport-Z3cpKGoV.js";
|
|
14
14
|
import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
|
|
@@ -1409,14 +1409,16 @@ function isSha256(value) {
|
|
|
1409
1409
|
//#endregion
|
|
1410
1410
|
//#region src/analyst/benchmark-implementation.ts
|
|
1411
1411
|
const ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM = "sha256-canonical-source-manifest";
|
|
1412
|
-
|
|
1412
|
+
/** The dependency files' manifest digest with the package's own version
|
|
1413
|
+
* fields blanked, so a release that only bumps the version keeps the pin. */
|
|
1414
|
+
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM = "sha256-canonical-file-manifest-without-own-version";
|
|
1413
1415
|
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES = Object.freeze([
|
|
1414
1416
|
"clients/python/pyproject.toml",
|
|
1415
1417
|
"clients/python/uv.lock",
|
|
1416
1418
|
"package.json",
|
|
1417
1419
|
"pnpm-lock.yaml"
|
|
1418
1420
|
]);
|
|
1419
|
-
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "
|
|
1421
|
+
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "007041f0de3b376aa3def1d3efe8221a724030a22ac0a7988921db12c4624c09";
|
|
1420
1422
|
const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
|
|
1421
1423
|
const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
|
|
1422
1424
|
const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
@@ -6317,4 +6319,4 @@ function shellQuote(value) {
|
|
|
6317
6319
|
//#endregion
|
|
6318
6320
|
export { ANALYST_BENCHMARK_MANIFEST_FILE as $, readAnalystInstructionsOverride as A, parseVerificationOutcome as B, emptyPublicBenchmarkRunner as C, summarizeCodeTraceCalibration as D, renderCodeTraceCalibrationMarkdown as E, publicBenchmarkRlmInstructions as F, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as H, publicBenchmarkSystemPrompt as I, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as J, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as K, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as L, MAX_INCORRECT_BLOCKS as M, MAX_INCORRECT_BLOCK_STEPS as N, analystInstructionsOverrideFromText as O, publicBenchmarkProtocolSha256 as P, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as Q, appendVerificationArtifactsToOtlp as R, adaptPublicBenchmarkFindings as S, readAnalystBenchmarkArtifact as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as U, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as V, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkImplementationDigest as X, analystBenchmarkDependencyLockDigest as Y, ANALYST_BENCHMARK_COST_LEDGER_FILE as Z, publicDirectAnalystDefinition as _, primeCodeTraceAnalystDefinition as a, codeTraceBenchCase as at, analystDefinitionAsymmetries as b, preparePublicAnalystBenchmark as c, agentRxPredictionsToFindings as ct, selectPublicBenchmarkRows as d, normalizeBenchmarkLabel as dt, ANALYST_BENCHMARK_OBSERVATIONS_FILE as et, createPublicBenchmarkRlmRunner as f, createPublicBenchmarkDirectRunner as g, runReplVariableAnalystDefinition as h, primeAnalystProtocolSha256 as i, summarizeAgentRxCalibration as it, CODE_TRACE_BENCH_ANALYST_PROMPT as j, effectiveAnalystProtocolSha256 as k, publicBenchmarkDistributions as l, normalizeAgentRxCategory as lt, rlmEngineLimits as m, renderAnalystBenchmarkMarkdown as n, AGENT_RX_UPSTREAM_REVISION as nt, runInlineAnalystDefinition as o, codeTracerPredictionsToFindings as ot, publicRlmAnalystDefinition as p, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as q, createPrimeBenchmarkRunner as r, renderAgentRxCalibrationMarkdown as rt, loadPublicBenchmarkRows as s, agentRxBenchmarkCase as st, runAnalystBenchmarkCommand as t, compareAnalystRunners as tt, publicBenchmarkSelectionReport as u, roundAgentRxStep as ut, runChunkedAnalystDefinition as v, expandCodeTraceFailureBlocks as w, analystDefinitionProtocolSha256 as x, AnalystExpressivenessError as y, loadCodeTraceVerificationArtifacts as z };
|
|
6319
6321
|
|
|
6320
|
-
//# sourceMappingURL=benchmark-command-
|
|
6322
|
+
//# sourceMappingURL=benchmark-command-EBmuMUBo.js.map
|