@tangle-network/agent-eval 1.0.19 → 1.0.21

package/CHANGELOG.md

@@ -4,6 +4,25 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [1.0.21] — 2026-11-06
+
+- Add `independentRiskDifference`: Newcombe/Wilson intervals for independent before/after counts, with explicit uncertainty for empty arms.
+
+## [1.0.20] — 2026-11-06
+
+- docs(statistics): trim whitespace in interval guidance
+- fix(verification): retain valid replay baselines and current release evidence
+- chore(analyst): refresh manifest for shared statistics owner
+- fix(statistics): preserve degenerate bootstrap results and mean seed
+- feat(statistics): share stratified cluster resampling and calibrated placebo bands
+- fix(exports): ship ./statistics subpath, gpt-5-mini pricing, sequentialCrossingHorizon
+- fix(adopt-stack): qualify the committed caller tree
+- fix(adopt-stack): read large tracked path inventories
+- fix(adoption): read a Runtime release's evidence from its Publish run, and raise pins below a dependency floor (#1211)
+- fix(adoption): hold a Runtime release whose tag evidence failed or never ran
+- fix(adoption): gate stable-major candidates against installed versions
+- feat(app-grade): probes take a method and JSON body (#1208)
+
 ## [1.0.19] — 2026-11-04
 
 - perf(lock): owner records skip fsync; a torn record born before this boot is stale (#1206)
@@ -39,28 +58,17 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 - feat(supervisor-run): write a run's sessions as OTLP spans (#1186)
 - fix(supervisor-run): read whole Discovery episodes and screen rows on calibration (#1185)
 - feat(calibration): precision, recall, AUC and a cluster-bootstrap CI on every calibration row
-- chore(release): 1.0.12
 - fix(statistics): exact retired-contract compat for summarizeDistribution
-- chore(release): 1.0.11
 - fix(statistics): export summarizeDistribution from the package root
-- chore(release): 1.0.10
-- chore(release): 1.0.9
 - feat(statistics): summarizeDistribution + percentileNearestRank (consolidation home)
-- chore(release): 1.0.8
 - chore(analyst): re-pin the implementation manifest on merged main
 - feat(statistics,harness): two-sample Welch evidence + lifted sandbox assertion library
-- chore(release): 1.0.7 (#1172)
 - docs(statistics): keep inference policy and exports readable (#1173)
 - feat(statistics): own independent effect summaries and ROC area (#1171)
-- chore(release): 1.0.6 (#1170)
 - refactor(reporting): share text table layout and simplify summaries (#1169)
 - refactor(harness): retain unavailable verdicts through cleanup (#1168)
-- chore(release): 1.0.5 (#1167)
 - refactor(harness): normalize compact named expectations (#1166)
-- chore(release): 1.0.4 (#1165)
 - refactor(harness): own resource acquisition and readiness cleanup (#1164)
-- chore(release): 1.0.3 (#1163)
-- chore(release): declare the existing deployment runner for workflow lint
 - fix(release): bind bootstrap to the existing qualified action revision
 - fix(release): use the qualified pnpm bootstrap in publication workflows
 - Refactor sandbox integration scenarios into the eval harness (#1161)
@@ -68,26 +76,16 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 ## [1.0.12] — 2026-10-31
 
 - fix(statistics): exact retired-contract compat for summarizeDistribution
-- chore(release): 1.0.11
 - fix(statistics): export summarizeDistribution from the package root
-- chore(release): 1.0.10
-- chore(release): 1.0.9
 - feat(statistics): summarizeDistribution + percentileNearestRank (consolidation home)
-- chore(release): 1.0.8
 - chore(analyst): re-pin the implementation manifest on merged main
 - feat(statistics,harness): two-sample Welch evidence + lifted sandbox assertion library
-- chore(release): 1.0.7 (#1172)
 - docs(statistics): keep inference policy and exports readable (#1173)
 - feat(statistics): own independent effect summaries and ROC area (#1171)
-- chore(release): 1.0.6 (#1170)
 - refactor(reporting): share text table layout and simplify summaries (#1169)
 - refactor(harness): retain unavailable verdicts through cleanup (#1168)
-- chore(release): 1.0.5 (#1167)
 - refactor(harness): normalize compact named expectations (#1166)
-- chore(release): 1.0.4 (#1165)
 - refactor(harness): own resource acquisition and readiness cleanup (#1164)
-- chore(release): 1.0.3 (#1163)
-- chore(release): declare the existing deployment runner for workflow lint
 - fix(release): bind bootstrap to the existing qualified action revision
 - fix(release): use the qualified pnpm bootstrap in publication workflows
 - Refactor sandbox integration scenarios into the eval harness (#1161)
@@ -95,19 +93,13 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 ## [1.0.11] — 2026-10-30
 
 - fix(statistics): export summarizeDistribution from the package root
-- chore(release): 1.0.10
-- chore(release): 1.0.9
 - feat(statistics): summarizeDistribution + percentileNearestRank (consolidation home)
-- chore(release): 1.0.8
 - chore(analyst): re-pin the implementation manifest on merged main
 - feat(statistics,harness): two-sample Welch evidence + lifted sandbox assertion library
-- chore(release): 1.0.7 (#1172)
 - docs(statistics): keep inference policy and exports readable (#1173)
 - feat(statistics): own independent effect summaries and ROC area (#1171)
-- chore(release): 1.0.6 (#1170)
 - refactor(reporting): share text table layout and simplify summaries (#1169)
 - refactor(harness): retain unavailable verdicts through cleanup (#1168)
-- chore(release): 1.0.5 (#1167)
 - refactor(harness): normalize compact named expectations (#1166)
 - chore(release): 1.0.4 (#1165)
 - refactor(harness): own resource acquisition and readiness cleanup (#1164)

package/dist/adapters/http.d.ts

@@ -1,6 +1,6 @@
 import { d as CostReceipt } from "../cost-ledger-Czro9wmo.js";
-import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-wDBk14lj.js";
-import "../index-DLVbfss9.js";
+import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-ip2D3-Ib.js";
+import "../index-DFso1b2W.js";
 export interface HttpDispatchOptions<TScenario extends Scenario, _TArtifact> {
   /** Static endpoint URL. Mutually exclusive with `resolveUrl`. */
   url?: string;

package/dist/{agent-profile-CPv4tENR.d.ts → agent-profile-BO8ruI6R.d.ts}

@@ -1,6 +1,6 @@
 import { f as CostReceiptInput, m as CustomTokenPricing } from "./cost-ledger-Czro9wmo.js";
-import { X as TraceAnalysisStore, i as AnalystFinding, m as EvidenceRef, p as AnalystUsageReceipt } from "./types-B9s9Xo5_.js";
-import { C as ChatResponse, S as ChatRequest } from "./types-0KglnQ9o.js";
+import { Y as TraceAnalysisStore, i as AnalystFinding, m as EvidenceRef, p as AnalystUsageReceipt } from "./types-kBMNdo1X.js";
+import { A as ChatResponse, k as ChatRequest } from "./cluster-Cd0MRbr9.js";
 import { AgentProfile, AgentProfile as AgentProfile$1, HarnessType, HarnessType as HarnessType$1 } from "@tangle-network/agent-interface";
 interface ExternalOptimizerProcessLimits {
   /** Maximum serialized input written for the child process. */
@@ -466,4 +466,4 @@ declare function agentProfileId(profile: AgentProfile): string;
  */
 declare function agentProfileHash(profile: AgentProfile): string;
 export { traceStoreEvidenceResolver as A, ExternalOptimizerModelCallRequest as B, AnalystEvidenceResolutionError as C, AnalystLatencyDistribution as D, AnalystIssueExpectation as E, ExternalOptimizerEndpointFormat as F, ExternalOptimizerRunnerCommand as G, ExternalOptimizerModelExecutionObservation as H, ExternalOptimizerEvaluationObservation as I, ExternalTextEvaluationRequest as J, ExternalOptimizerWireCounts as K, ExternalOptimizerEvaluationRefusalReason as L, DEFAULT_EXTERNAL_OPTIMIZER_PROCESS_LIMITS as M, ExternalOptimizerCallbackLimits as N, RunAnalystBenchmarkOptions as O, ExternalOptimizerChatRequest as P, ExternalOptimizerModelBudget as R, AnalystEvidenceResolution as S, AnalystFindingScore as T, ExternalOptimizerProcessLimits as U, ExternalOptimizerModelCallResult as V, ExternalOptimizerResumeMode as W, AnalystBenchmarkProvenance as _, ProfileAxisSpec as a, AnalystBenchmarkSummary as b, expandProfileAxes as c, AnalystBenchmarkDatasetRef as d, AnalystBenchmarkDescriptor as f, AnalystBenchmarkOutput as g, AnalystBenchmarkObservation as h, HarnessType$1 as i, DEFAULT_EXTERNAL_OPTIMIZER_CALLBACK_LIMITS as j, runAnalystBenchmark as k, harnessAxisOf as l, AnalystBenchmarkLabelState as m, CODING_HARNESSES as n, agentProfileHash as o, AnalystBenchmarkError as p, ExternalTextCandidate as q, HARNESS_NATIVE_MODEL as r, agentProfileId as s, AgentProfile$1 as t, AnalystBenchmarkCase as u, AnalystBenchmarkResult as v, AnalystEvidenceResolver as w, AnalystEvidenceExpectation as x, AnalystBenchmarkRunner as y, ExternalOptimizerModelCall as z };
-//# sourceMappingURL=agent-profile-CPv4tENR.d.ts.map
+//# sourceMappingURL=agent-profile-BO8ruI6R.d.ts.map

package/dist/{agent-profile-CPv4tENR.d.ts.map → agent-profile-BO8ruI6R.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"agent-profile-CPv4tENR.d.ts","names":["_$___cost_ledger0.CostReceiptInput"],"sources":["../src/campaign/external-optimizer-contracts.ts","../src/analyst/benchmark.ts","../src/agent-profile.ts"],"mappings":";;;;UAciB;;EAEf;;EAEA;;EAEA;;cAGW,2CAA2C,SAAS;UAOhD;;EAEf;;EAEA;;cAGW,4CAA4C,SAAS;UAMjD;EACf;EACA;EACA,MAAM,OAAO;;EAEb,SAAS,QAAQ;;KAGP;KAEA,iCAAiC;UAE5B;EACf,WAAW;EACX;;KAqDG,aAAa,KAAK,eAAc,6BACjC,IACA,0BAA0B,gBACf,aAAa,OACtB,+BACc,WAAW,IAAI,aAAa,EAAE,SAC1C;;KAGI,+BAA+B,aACzC,KAAK;EAA0B;;KAGrB;;UAMK;;WAEN;;WAEA,SAAS;;WAET,iBAAiB;WACjB,QAAQ;;;KAIP;WAEG;;WAEA,UAAU;;;;;;;WAOV,SAPUA;;WASV;;WAGA;;WAEA;;WAEA,SATkCA;;WAWlC;;;;;;;;;;;;KAaH,8BACV,SAAS,sCACN,QAAQ;;KAGD;WAEG;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;WAGA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;KAGH;;;;;;KAUA;WAEG;WACA;WACA,WAAW;WACX;;WAGA;WACA;WACA,WAAW;WACX;WACA;;WAEA;WACA;;WAGA;WACA;WACA,QAAQ;WACR,YAAY;WACZ;WACA;;UAGE;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;;;;EAUA;;;;;;EAMA,UAAU;;EAEV;;;UAIe;;EAEf;;EAEA;;UCpQe;EACf;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,4BAA4B;;KAGlB;UAEK,qBAAqB;EACpC;;EAEA;;EAEA,YAAY;EACZ,OAAO;EACP,yBAAyB;;EAEzB,2BAA2B;EAC3B;EACA,WAAW;;UAGI;EACf;EACA;EACA;EACA;EACA;EACA,mBAAmB;EACnB;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;EACA;;UAGe;EACf,UAAU;EACV;EACA;;UAGe;EACf;EACA;EACA,oBAAoB;EACpB,QAAQ;;EAER;;KAGU,wBAAwB,qBAAqB;EACvD;EACA,WAAW;EACX,UAAU;EACV,SAAS;gBACK;;;;;iBAMA,2BAA2B,QACzC,WAAW,OAAO,WAAW,qBAC5B,wBAAwB;UAoBV;EACf,mBAAmB;EACnB,QAAQ;EACR,WAAW;;;;;EAKX;;EAEA,QAAQ;;UAGO;EACf;EACA;EACA;EACA;;UAGe,uBAAuB;EACtC;EACA,QACE,OAAO,QACP;IAAW;IAAgB;IAAoB,SAAS;MACvD,yBAAyB,QAAQ;;UAGrB;EACf;EACA;EACA;EACA,YAAY;EACZ;EACA;EACA;EACA;EACA,mBAAmB;EACnB,OAAO;EACP,qBAAqB;EACrB;EACA,eAAe;EACf,QAAQ;EACR,iBAAiB;EACjB,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;EACA,WAAW;EACX;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,UAAU;EACV;EACA,cAAc;EACd,WAAW;;UAGI,mCAAmC;EAClD;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf,YAAY;EACZ,cAAc;EACd,WAAW;;UAGI,2BAA2B;EAC1C,gBAAgB,qBAAqB;EACrC,kBAAkB,uBAAuB;EACzC;EACA;EACA;EACA,kBAAkB,wBAAwB;EAC1C,YAAY;;EAEZ,+BAA+B;EAC/B,iBAAiB,aAAa,uCAAuC;EACrE,SAAS;;iBAGW,oBAAoB,QACxC,SAAS,2BAA2B,UACnC,QAAQ;;;;;;;;cCnQE,2BAA2B;UAOvB;;;EAGf,MAAM;;EAEN,qBAAqB;;;EAGrB;;;;;;EAMA;;;;;;;cAQW;;;;;;;;;;;;;;;;;;;iBAoBG,kBAAkB,MAAM,kBAAkB;;;;;;;;iBAwD1C,cACd,SAAS,KAAK;EACX,SAAS;EAAa;;;;;;;;;iBAiBX,eAAe,SAAS;;;;;;;;;;;iBAmDxB,iBAAiB,SAAS"}
+{"version":3,"file":"agent-profile-BO8ruI6R.d.ts","names":["_$___cost_ledger0.CostReceiptInput"],"sources":["../src/campaign/external-optimizer-contracts.ts","../src/analyst/benchmark.ts","../src/agent-profile.ts"],"mappings":";;;;UAciB;;EAEf;;EAEA;;EAEA;;cAGW,2CAA2C,SAAS;UAOhD;;EAEf;;EAEA;;cAGW,4CAA4C,SAAS;UAMjD;EACf;EACA;EACA,MAAM,OAAO;;EAEb,SAAS,QAAQ;;KAGP;KAEA,iCAAiC;UAE5B;EACf,WAAW;EACX;;KAqDG,aAAa,KAAK,eAAc,6BACjC,IACA,0BAA0B,gBACf,aAAa,OACtB,+BACc,WAAW,IAAI,aAAa,EAAE,SAC1C;;KAGI,+BAA+B,aACzC,KAAK;EAA0B;;KAGrB;;UAMK;;WAEN;;WAEA,SAAS;;WAET,iBAAiB;WACjB,QAAQ;;;KAIP;WAEG;;WAEA,UAAU;;;;;;;WAOV,SAPUA;;WASV;;WAGA;;WAEA;;WAEA,SATkCA;;WAWlC;;;;;;;;;;;;KAaH,8BACV,SAAS,sCACN,QAAQ;;KAGD;WAEG;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;WAGA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;KAGH;;;;;;KAUA;WAEG;WACA;WACA,WAAW;WACX;;WAGA;WACA;WACA,WAAW;WACX;WACA;;WAEA;WACA;;WAGA;WACA;WACA,QAAQ;WACR,YAAY;WACZ;WACA;;UAGE;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;;;;EAUA;;;;;;EAMA,UAAU;;EAEV;;;UAIe;;EAEf;;EAEA;;UCpQe;EACf;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA,oBAAoB;EACpB;;EAEA,4BAA4B;;KAGlB;UAEK,qBAAqB;EACpC;;EAEA;;EAEA,YAAY;EACZ,OAAO;EACP,yBAAyB;;EAEzB,2BAA2B;EAC3B;EACA,WAAW;;UAGI;EACf;EACA;EACA;EACA;EACA;EACA,mBAAmB;EACnB;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;EACA;;UAGe;EACf,UAAU;EACV;EACA;;UAGe;EACf;EACA;EACA,oBAAoB;EACpB,QAAQ;;EAER;;KAGU,wBAAwB,qBAAqB;EACvD;EACA,WAAW;EACX,UAAU;EACV,SAAS;gBACK;;;;;iBAMA,2BAA2B,QACzC,WAAW,OAAO,WAAW,qBAC5B,wBAAwB;UAoBV;EACf,mBAAmB;EACnB,QAAQ;EACR,WAAW;;;;;EAKX;;EAEA,QAAQ;;UAGO;EACf;EACA;EACA;EACA;;UAGe,uBAAuB;EACtC;EACA,QACE,OAAO,QACP;IAAW;IAAgB;IAAoB,SAAS;MACvD,yBAAyB,QAAQ;;UAGrB;EACf;EACA;EACA;EACA,YAAY;EACZ;EACA;EACA;EACA;EACA,mBAAmB;EACnB,OAAO;EACP,qBAAqB;EACrB;EACA,eAAe;EACf,QAAQ;EACR,iBAAiB;EACjB,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;EACA,WAAW;EACX;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,UAAU;EACV;EACA,cAAc;EACd,WAAW;;UAGI,mCAAmC;EAClD;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf,YAAY;EACZ,cAAc;EACd,WAAW;;UAGI,2BAA2B;EAC1C,gBAAgB,qBAAqB;EACrC,kBAAkB,uBAAuB;EACzC;EACA;EACA;EACA,kBAAkB,wBAAwB;EAC1C,YAAY;;EAEZ,+BAA+B;EAC/B,iBAAiB,aAAa,uCAAuC;EACrE,SAAS;;iBAGW,oBAAoB,QACxC,SAAS,2BAA2B,UACnC,QAAQ;;;;;;;;cCnQE,2BAA2B;UAOvB;;;EAGf,MAAM;;EAEN,qBAAqB;;;EAGrB;;;;;;EAMA;;;;;;;cAQW;;;;;;;;;;;;;;;;;;;iBAoBG,kBAAkB,MAAM,kBAAkB;;;;;;;;iBAwD1C,cACd,SAAS,KAAK;EACX,SAAS;EAAa;;;;;;;;;iBAiBX,eAAe,SAAS;;;;;;;;;;;iBAmDxB,iBAAiB,SAAS"}

package/dist/analyst/index.d.ts

@@ -1,20 +1,20 @@
 import { m as CustomTokenPricing, o as CostLedgerHandle } from "../cost-ledger-Czro9wmo.js";
-import { A as FindingParseOutcome, B as FindingConditions, C as CalibrationInterval, D as FindingLayer, E as FindingEvidenceUnit, F as independentUnitCount, H as TREATMENT_LAYERS, I as lineageRoots, L as parseAnalystFinding, M as FindingScope, N as FindingScopeReading, O as FindingMeasure, P as ProposalFindingSchema, R as readFindingScope, S as makeProposalFinding, T as FindingCalibration, U as TreatmentLayer, V as FindingTreatment, X as TraceAnalysisStore, _ as ExecutionProbeRequest, a as AnalystFindingSchemaVersion, b as computeFindingId, c as AnalystRunEvent, d as AnalystRunSummary, f as AnalystSeverity, g as ExecutionProbeOutcome, h as ExecutionProbe, i as AnalystFinding, j as FindingReaderLabel, k as FindingMethod, l as AnalystRunInputs, m as EvidenceRef, n as AnalystContext, o as AnalystInputKind, p as AnalystUsageReceipt, r as AnalystCost, s as AnalystRequirements, st as TraceAnalystSpan, t as Analyst, u as AnalystRunResult, v as ProposalFinding, w as FINDING_LAYERS, x as makeFinding, y as ProposalFindingOrigin, z as BootstrapInterval } from "../types-B9s9Xo5_.js";
-import { A as createChatClient, C as ChatResponse, D as MockTransportOpts, E as CustomTransportOpts, O as OpenAiCompatibleTransportOpts, S as ChatRequest, T as CreateChatClientOpts, b as ChatCallOpts, k as SandboxSdkTransportOpts, w as ChatTransport, x as ChatClient } from "../types-0KglnQ9o.js";
-import { cn as NominalAgreementOptions } from "../index-C3t17kHu.js";
-import { A as traceStoreEvidenceResolver, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, G as ExternalOptimizerRunnerCommand, H as ExternalOptimizerModelExecutionObservation, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, k as runAnalystBenchmark, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner, z as ExternalOptimizerModelCall } from "../agent-profile-CPv4tENR.js";
-import { C as BehavioralWindowPolicy, S as BehavioralTraceWindow, _ as BehavioralTraceEventMap, a as createTraceAnalyst, b as BehavioralTraceQuestionsOptions, c as BehavioralAnalystOptions, d as pinBehavioralFailureClass, f as BEHAVIORAL_TRACE_QUESTIONS, g as BehavioralTraceEvent, h as BehavioralTraceAnswer, i as TraceAnalystDefinition, l as assertFailureClasses, m as BehavioralQuestionCalibration, n as buildDefaultAnalystRegistry, o as runTraceAnalyst, p as BEHAVIORAL_TRACE_QUESTIONS_VERSION, r as CreateTraceAnalystOptions, s as BEHAVIORAL_FAILURE_CLASS, t as DefaultAnalystRegistryOptions, u as behavioralAnalyst, v as BehavioralTraceLayer, w as behavioralTraceQuestionDigest, x as BehavioralTraceSupport, y as BehavioralTraceQuestionId } from "../default-registry-BbXr18AT.js";
-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-CaLLU1Pz.js";
+import { A as FindingParseOutcome, B as FindingTreatment, C as CalibrationInterval, D as FindingLayer, E as FindingEvidenceUnit, F as independentUnitCount, H as TreatmentLayer, I as lineageRoots, L as parseAnalystFinding, M as FindingScope, N as FindingScopeReading, O as FindingMeasure, P as ProposalFindingSchema, R as readFindingScope, S as makeProposalFinding, T as FindingCalibration, V as TREATMENT_LAYERS, Y as TraceAnalysisStore, _ as ExecutionProbeRequest, a as AnalystFindingSchemaVersion, b as computeFindingId, c as AnalystRunEvent, d as AnalystRunSummary, f as AnalystSeverity, g as ExecutionProbeOutcome, h as ExecutionProbe, i as AnalystFinding, j as FindingReaderLabel, k as FindingMethod, l as AnalystRunInputs, m as EvidenceRef, n as AnalystContext, o as AnalystInputKind, ot as TraceAnalystSpan, p as AnalystUsageReceipt, r as AnalystCost, s as AnalystRequirements, t as Analyst, u as AnalystRunResult, v as ProposalFinding, w as FINDING_LAYERS, x as makeFinding, y as ProposalFindingOrigin, z as FindingConditions } from "../types-kBMNdo1X.js";
+import { A as ChatResponse, D as ChatCallOpts, F as OpenAiCompatibleTransportOpts, I as SandboxSdkTransportOpts, L as createChatClient, M as CreateChatClientOpts, N as CustomTransportOpts, O as ChatClient, P as MockTransportOpts, j as ChatTransport, k as ChatRequest, t as BootstrapInterval } from "../cluster-Cd0MRbr9.js";
+import { Ft as NominalAgreementOptions } from "../index-DNXFzSpc.js";
+import { A as traceStoreEvidenceResolver, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, G as ExternalOptimizerRunnerCommand, H as ExternalOptimizerModelExecutionObservation, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, k as runAnalystBenchmark, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner, z as ExternalOptimizerModelCall } from "../agent-profile-BO8ruI6R.js";
+import { C as BehavioralWindowPolicy, S as BehavioralTraceWindow, _ as BehavioralTraceEventMap, a as createTraceAnalyst, b as BehavioralTraceQuestionsOptions, c as BehavioralAnalystOptions, d as pinBehavioralFailureClass, f as BEHAVIORAL_TRACE_QUESTIONS, g as BehavioralTraceEvent, h as BehavioralTraceAnswer, i as TraceAnalystDefinition, l as assertFailureClasses, m as BehavioralQuestionCalibration, n as buildDefaultAnalystRegistry, o as runTraceAnalyst, p as BEHAVIORAL_TRACE_QUESTIONS_VERSION, r as CreateTraceAnalystOptions, s as BEHAVIORAL_FAILURE_CLASS, t as DefaultAnalystRegistryOptions, u as behavioralAnalyst, v as BehavioralTraceLayer, w as behavioralTraceQuestionDigest, x as BehavioralTraceSupport, y as BehavioralTraceQuestionId } from "../default-registry-aPvwtzEM.js";
+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-VAFjtOQN.js";
 import { g as SystemOneState } from "../systemone-protocol-C4t7JH4Y.js";
-import { B as DiffPolicy, F as FindingsTimeStep, H as FindingsStore, I as LedgerFinding, L as diffFindingsOverTime, M as FindingsLedgerOutcome, N as FindingsLedgerRead, P as FindingsQuery, R as openFindingsLedger, U as PersistedFinding, V as FindingsDiff, W as diffFindings, j as FindingsLedger, r as SystemOneEvaluatorOptions, z as queryFindings } from "../systemone-CpDppX8s.js";
-import { a as RAW_FINDING_SCHEMA_PROMPT, c as RawAnalystFindingSchema, i as TraceAnalystLimits, l as evidenceRefsFromRawFinding, n as TraceAnalysisEngineRequest, o as RawAnalystEvidence, r as TraceAnalysisEngineResult, s as RawAnalystFinding, t as TraceAnalysisEngine, u as parseRawFinding } from "../engine-rfV8Ff8V.js";
-import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-BQsjZD9F.js";
-import { a as BudgetPolicy, c as RegistryRunOpts, i as AnalystRegistryOptions, n as ExactAnalystRunExecutionError, o as ExactAnalystBudgetPolicy, r as AnalystHooks, s as ExactRegistryRunOpts, t as AnalystRegistry } from "../registry-Ck7w-rr5.js";
-import { T as SemanticConceptJudgeOptions, _ as DspyRlmTraceEngineOptions, a as FAILURE_MODE_KIND_SPEC, b as createChatTraceEngine, c as emitControlIntegrityFindings, d as FindingSubject, f as FindingSubjectKind, g as renderFindingSubject, h as parseFindingSubject, i as IMPROVEMENT_KIND_SPEC, l as FINDING_SUBJECT_KINDS, m as findingSubjectGrammarPromptFor, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as KIND_EXPECTED_SUBJECTS, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FINDING_SUBJECT_SYNTAX, v as createDspyRlmTraceEngine, y as ChatTraceEngineOptions } from "../index-AmfM3usI.js";
-import { C as runPrimeExchange, D as ReplyRowDecoded, E as ReplyEnvelope, O as ReplyRowRejection, S as projectPrimeTrajectory, T as ReplyContract, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as normalizePrimeUsage, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, 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 DecodedReply, x as primeProtocolSha256, y as mergePrimeRawUsage } from "../prime-protocol-DKRk4l4U.js";
+import { B as DiffPolicy, F as FindingsTimeStep, H as FindingsStore, I as LedgerFinding, L as diffFindingsOverTime, M as FindingsLedgerOutcome, N as FindingsLedgerRead, P as FindingsQuery, R as openFindingsLedger, U as PersistedFinding, V as FindingsDiff, W as diffFindings, j as FindingsLedger, r as SystemOneEvaluatorOptions, z as queryFindings } from "../systemone-DVk-Crtu.js";
+import { a as RAW_FINDING_SCHEMA_PROMPT, c as RawAnalystFindingSchema, i as TraceAnalystLimits, l as evidenceRefsFromRawFinding, n as TraceAnalysisEngineRequest, o as RawAnalystEvidence, r as TraceAnalysisEngineResult, s as RawAnalystFinding, t as TraceAnalysisEngine, u as parseRawFinding } from "../engine-BF8naBn7.js";
+import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-R5RO9OHn.js";
+import { a as BudgetPolicy, c as RegistryRunOpts, i as AnalystRegistryOptions, n as ExactAnalystRunExecutionError, o as ExactAnalystBudgetPolicy, r as AnalystHooks, s as ExactRegistryRunOpts, t as AnalystRegistry } from "../registry-BAcEbzKm.js";
+import { T as SemanticConceptJudgeOptions, _ as DspyRlmTraceEngineOptions, a as FAILURE_MODE_KIND_SPEC, b as createChatTraceEngine, c as emitControlIntegrityFindings, d as FindingSubject, f as FindingSubjectKind, g as renderFindingSubject, h as parseFindingSubject, i as IMPROVEMENT_KIND_SPEC, l as FINDING_SUBJECT_KINDS, m as findingSubjectGrammarPromptFor, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as KIND_EXPECTED_SUBJECTS, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FINDING_SUBJECT_SYNTAX, v as createDspyRlmTraceEngine, y as ChatTraceEngineOptions } from "../index-CM12lr9E.js";
+import { C as runPrimeExchange, D as ReplyRowDecoded, E as ReplyEnvelope, O as ReplyRowRejection, S as projectPrimeTrajectory, T as ReplyContract, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as normalizePrimeUsage, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, 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 DecodedReply, x as primeProtocolSha256, y as mergePrimeRawUsage } from "../prime-protocol-D1NkJRuD.js";
 import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-Cfqir_Im.js";
-import { b as SupervisorRunSources } from "../types-DNB9hIXa.js";
-import { a as askTraceQuestions, i as VerifiedTraceFinding, n as TraceQuestionOutcome, r as TraceQuestionSpec, t as AskTraceQuestionsOptions } from "../trace-questions-CpTrtEcm.js";
+import { b as SupervisorRunSources } from "../types-DUVhW5V1.js";
+import { a as askTraceQuestions, i as VerifiedTraceFinding, n as TraceQuestionOutcome, r as TraceQuestionSpec, t as AskTraceQuestionsOptions } from "../trace-questions-BY6taxnl.js";
 import { z } from "zod";
 interface SemanticConceptJudgeAdapterOpts {
   id?: string;

package/dist/analyst/index.js

@@ -1,21 +1,20 @@
 import { n as assertConsistentFindingConditions, o as mergeFindingComposition, r as findingCompositionKey, t as TREATMENT_LAYERS } from "../finding-composition-Belh_qU3.js";
-import { c as clusterBootstrap } from "../mean-D1d6gedE.js";
-import { i as nominalAgreement } from "../agreement-irr-DXcXEt4I.js";
-import { i as rocAuc, n as diffFindings, r as createChatTraceEngine, t as FindingsStore } from "../findings-store-BnYN57-h.js";
+import { G as nominalAgreement, V as rocAuc, gt as clusterBootstrap } from "../statistics-CvvC-MPv.js";
 import { t as FileLedgerJournal } from "../journal-CTX5uK-n.js";
 import { r as merkleRoot } from "../ledger-core-24IxvmVY.js";
-import { A as spanningWindow, C as UNKNOWN_LINEAGE, D as mostSevere, E as mergeEvidenceUnits, O as parseAnalystFinding, S as ProposalFindingSchema, T as lineageRoots, b as AnalystFindingSchema, k as readFindingScope, w as independentUnitCount, x as FINDING_LAYERS } from "../external-optimizer-subprocess-BtJk8UcU.js";
+import { A as spanningWindow, C as UNKNOWN_LINEAGE, D as mostSevere, E as mergeEvidenceUnits, O as parseAnalystFinding, S as ProposalFindingSchema, T as lineageRoots, b as AnalystFindingSchema, k as readFindingScope, w as independentUnitCount, x as FINDING_LAYERS } from "../external-optimizer-subprocess-_C_2yriN.js";
 import { a as makeProposalFinding, i as makeFinding, r as computeFindingId } from "../types-CL1_N7AZ.js";
-import { t as assertProposalFindings } from "../proposal-findings-BfzzZ_lN.js";
-import { A as RawAnalystFindingSchema, B as parseFindingSubject, F as stripCodeFences, I as FINDING_SUBJECT_KINDS, L as FINDING_SUBJECT_SYNTAX, M as parseRawFinding, N as parseTraceSpanEvidenceUri, R as KIND_EXPECTED_SUBJECTS, V as renderFindingSubject, j as evidenceRefsFromRawFinding, k as RAW_FINDING_SCHEMA_PROMPT, n as runTraceAnalyst, r as buildTraceToolsForGroup, t as createTraceAnalyst, z as findingSubjectGrammarPromptFor } from "../kind-factory-Cfz8DUCc.js";
-import { _ as behavioralTraceSupportSchema, a as KNOWLEDGE_POISONING_KIND_SPEC, b as behavioralTraceQuestionDigest, c as FAILURE_MODE_KIND_SPEC, d as emitControlIntegrityFindings, f as BEHAVIORAL_FAILURE_CLASS, g as validBehavioralCalibration, h as pinBehavioralFailureClass, i as DEFAULT_TRACE_ANALYST_KINDS, l as CONTROL_INTEGRITY_ANALYST, m as behavioralAnalyst, n as AnalystRegistry, o as KNOWLEDGE_GAP_KIND_SPEC, p as assertFailureClasses, r as ExactAnalystRunExecutionError, s as IMPROVEMENT_KIND_SPEC, t as buildDefaultAnalystRegistry, u as ControlIntegrityAnalyst, v as BEHAVIORAL_TRACE_QUESTIONS, y as BEHAVIORAL_TRACE_QUESTIONS_VERSION } from "../default-registry-BB9_jzyH.js";
-import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-CqQc0R2l.js";
-import { m as validDecisionIdentity, o as systemOneAnalyst, t as DECISION_POINT_AUC_BAR } from "../decision-point-CNyoKOkz.js";
-import { t as createChatClient } from "../chat-client-D0me8iwq.js";
-import { A as agentRxBenchmarkCase, C as ANALYST_BENCHMARK_COST_LEDGER_FILE, D as AGENT_RX_UPSTREAM_REVISION, E as ANALYST_BENCHMARK_OBSERVATIONS_FILE, F as runAnalystBenchmark, I as traceStoreEvidenceResolver, M as normalizeAgentRxCategory, N as externalId, O as codeTraceBenchCase, P as positiveStep, S as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, T as ANALYST_BENCHMARK_MANIFEST_FILE, _ as readAnalystBenchmarkArtifact, a as runInlineAnalystDefinition, b as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, c as publicRlmAnalystDefinition, d as publicDirectAnalystDefinition, f as runChunkedAnalystDefinition, g as expandCodeTraceFailureBlocks, h as analystDefinitionProtocolSha256, i as primeCodeTraceAnalystDefinition, j as agentRxPredictionsToFindings, k as codeTracerPredictionsToFindings, l as runReplVariableAnalystDefinition, m as analystDefinitionAsymmetries, n as createPrimeBenchmarkRunner, o as loadPublicBenchmarkRows, p as AnalystExpressivenessError, r as primeAnalystProtocolSha256, s as createPublicBenchmarkRlmRunner, t as runAnalystBenchmarkCommand, u as createPublicBenchmarkDirectRunner, v as CODE_TRACE_BENCH_ANALYST_PROMPT, w as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, x as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, y as publicBenchmarkProtocolSha256 } from "../benchmark-command-DSJQeYom.js";
+import { t as assertProposalFindings } from "../proposal-findings-DWs94yT8.js";
+import { A as RawAnalystFindingSchema, B as parseFindingSubject, F as stripCodeFences, I as FINDING_SUBJECT_KINDS, L as FINDING_SUBJECT_SYNTAX, M as parseRawFinding, N as parseTraceSpanEvidenceUri, R as KIND_EXPECTED_SUBJECTS, V as renderFindingSubject, j as evidenceRefsFromRawFinding, k as RAW_FINDING_SCHEMA_PROMPT, n as runTraceAnalyst, r as buildTraceToolsForGroup, t as createTraceAnalyst, z as findingSubjectGrammarPromptFor } from "../kind-factory-CV0FNCMM.js";
+import { _ as behavioralTraceSupportSchema, a as KNOWLEDGE_POISONING_KIND_SPEC, b as behavioralTraceQuestionDigest, c as FAILURE_MODE_KIND_SPEC, d as emitControlIntegrityFindings, f as BEHAVIORAL_FAILURE_CLASS, g as validBehavioralCalibration, h as pinBehavioralFailureClass, i as DEFAULT_TRACE_ANALYST_KINDS, l as CONTROL_INTEGRITY_ANALYST, m as behavioralAnalyst, n as AnalystRegistry, o as KNOWLEDGE_GAP_KIND_SPEC, p as assertFailureClasses, r as ExactAnalystRunExecutionError, s as IMPROVEMENT_KIND_SPEC, t as buildDefaultAnalystRegistry, u as ControlIntegrityAnalyst, v as BEHAVIORAL_TRACE_QUESTIONS, y as BEHAVIORAL_TRACE_QUESTIONS_VERSION } from "../default-registry-CdFbxPnr.js";
+import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-cWyn8G1a.js";
+import { n as diffFindings, r as createChatTraceEngine, t as FindingsStore } from "../findings-store-BSuaV3dN.js";
+import { m as validDecisionIdentity, o as systemOneAnalyst, t as DECISION_POINT_AUC_BAR } from "../decision-point-Di2LATNH.js";
+import { t as createChatClient } from "../chat-client-Zz97O3NB.js";
+import { A as agentRxBenchmarkCase, C as ANALYST_BENCHMARK_COST_LEDGER_FILE, D as AGENT_RX_UPSTREAM_REVISION, E as ANALYST_BENCHMARK_OBSERVATIONS_FILE, F as runAnalystBenchmark, I as traceStoreEvidenceResolver, M as normalizeAgentRxCategory, N as externalId, O as codeTraceBenchCase, P as positiveStep, S as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, T as ANALYST_BENCHMARK_MANIFEST_FILE, _ as readAnalystBenchmarkArtifact, a as runInlineAnalystDefinition, b as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, c as publicRlmAnalystDefinition, d as publicDirectAnalystDefinition, f as runChunkedAnalystDefinition, g as expandCodeTraceFailureBlocks, h as analystDefinitionProtocolSha256, i as primeCodeTraceAnalystDefinition, j as agentRxPredictionsToFindings, k as codeTracerPredictionsToFindings, l as runReplVariableAnalystDefinition, m as analystDefinitionAsymmetries, n as createPrimeBenchmarkRunner, o as loadPublicBenchmarkRows, p as AnalystExpressivenessError, r as primeAnalystProtocolSha256, s as createPublicBenchmarkRlmRunner, t as runAnalystBenchmarkCommand, u as createPublicBenchmarkDirectRunner, v as CODE_TRACE_BENCH_ANALYST_PROMPT, w as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, x as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, y as publicBenchmarkProtocolSha256 } from "../benchmark-command-CoNndRCk.js";
 import { a as normalizePrimeUsage, c as runPrimeExchange, i as mergePrimeRawUsage, n as buildPrimePrompt, o as primeProtocolSha256, r as buildPrimeRepairPrompt, s as projectPrimeTrajectory, t as analystUsageReceiptFromPrimeUsage } from "../prime-protocol-CrhpXRz9.js";
 import { t as nodeHttpPrimeBridgeTransport } from "../prime-bridge-transport-Csd5SQg7.js";
-import { t as clusterBootstrapMean } from "../cluster-bootstrap-BteuR1hg.js";
+import { t as clusterBootstrapMean } from "../cluster-bootstrap-B0MTOBRU.js";
 import { z } from "zod";
 import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
 import { join } from "node:path";