@tangle-network/agent-eval 0.118.1 → 0.118.2

package/CHANGELOG.md

@@ -4,6 +4,13 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
 
 ---
 
+## [0.118.2] — 2026-07-13 — interoperable contracts and trace accounting
+
+### Fixed
+
+- Every caller-supplied cost-ledger API now uses the public structural `CostLedgerHandle`, so types remain assignable when TypeScript resolves them through separate package entrypoints.
+- Trace writers emit an exact context-input total from known non-overlapping input and cache categories; behavioral analysis uses that value and leaves ambiguous third-party prompt totals unchanged.
+
 ## [0.118.1] — 2026-07-13 — parsed OTLP intake
 
 ### Added

package/dist/analyst/index.d.ts

@@ -939,6 +939,13 @@ declare class CostLedger {
     private ensureCostLimitPersisted;
     private appendEvent;
 }
+/** Public callback surface for a shared cost ledger.
+ *
+ * Declaration bundles may expose this type through multiple package subpaths.
+ * Keeping callback contracts structural lets those subpaths compose while the
+ * concrete {@link CostLedger} retains its private durable state.
+ */
+type CostLedgerHandle = Pick<CostLedger, keyof CostLedger>;
 
 /**
  * LLM client with graceful degrade.
@@ -1181,7 +1188,7 @@ interface SemanticConceptJudgeOptions {
     maxHtmlChars?: number;
     /** LlmClient config (baseUrl, apiKey, authHeader, …). */
     llm?: LlmClientOptions;
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
     signal?: AbortSignal;
     /**
@@ -1256,7 +1263,7 @@ interface JudgeInput {
     turns: TurnResult[];
     artifacts: CollectedArtifacts;
     /** Shared ledger for paid built-in judges. Direct calls default to an uncapped ledger. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
     costTags?: Record<string, string>;
     signal?: AbortSignal;
@@ -2941,7 +2948,7 @@ interface StructureFindingsOptions {
     baseUrl: string;
     apiKey?: string;
     /** Optional ledger for direct use. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
     maxTokens?: number;
     /** Max reask attempts after a zero/invalid extraction. Default 1. */

package/dist/analyst/index.js

@@ -10,13 +10,13 @@ import {
   diffFindings,
   emitSkillUsageFindings,
   runSemanticConceptJudge
-} from "../chunk-BFW56GTT.js";
+} from "../chunk-DRSFTBKU.js";
 import {
   behavioralAnalyst,
   buildDefaultAnalystRegistry,
   createChatClient,
   deriveEfficiencyFindings
-} from "../chunk-33JA4TFA.js";
+} from "../chunk-J23QK2U5.js";
 import "../chunk-HHWE3POT.js";
 import "../chunk-3YYRZDON.js";
 import {
@@ -65,16 +65,16 @@ import {
   structureFindings,
   validatePolicyEdit,
   validatePolicyEditCandidateRecord
-} from "../chunk-OIIMMLRB.js";
+} from "../chunk-DZBCDDIE.js";
 import "../chunk-NJC7U437.js";
-import "../chunk-VCTY3W6J.js";
+import "../chunk-MLHRFWQK.js";
 import "../chunk-VI2UW6B6.js";
-import "../chunk-QKEGNI5B.js";
+import "../chunk-BUBU3YHT.js";
 import "../chunk-PC4UYEBM.js";
 import "../chunk-XJYR7XFV.js";
 import "../chunk-VSMTAMNK.js";
 import "../chunk-ONWEPEDO.js";
-import "../chunk-WDHBCA3M.js";
+import "../chunk-NW4AQBXD.js";
 import "../chunk-PZ5AY32C.js";
 
 // src/analyst/adapters.ts

package/dist/benchmarks/index.js

@@ -16,27 +16,27 @@ import {
   routing_exports,
   runBenchmarkAdapter,
   summarizeBenchmarkCampaign
-} from "../chunk-JSDVRFAP.js";
-import "../chunk-Q442S5AS.js";
-import "../chunk-YLMUS4MM.js";
-import "../chunk-IDZTTFRR.js";
+} from "../chunk-KK2O4VWA.js";
+import "../chunk-GCT3DQWU.js";
+import "../chunk-I42AAGHL.js";
+import "../chunk-EGNRE7VA.js";
 import "../chunk-3YYRZDON.js";
-import "../chunk-OIIMMLRB.js";
+import "../chunk-DZBCDDIE.js";
 import "../chunk-ARU2PZFM.js";
 import "../chunk-NJC7U437.js";
 import "../chunk-PJQFMIOX.js";
-import "../chunk-VCTY3W6J.js";
+import "../chunk-MLHRFWQK.js";
 import "../chunk-VI2UW6B6.js";
-import "../chunk-3EHHMC6E.js";
+import "../chunk-63KG3ASG.js";
 import "../chunk-GGE4NNQT.js";
-import "../chunk-QKEGNI5B.js";
+import "../chunk-BUBU3YHT.js";
 import "../chunk-PC4UYEBM.js";
 import "../chunk-S3UZOQ5Y.js";
 import "../chunk-MA6HLL3S.js";
 import "../chunk-XJYR7XFV.js";
 import "../chunk-VSMTAMNK.js";
 import "../chunk-ONWEPEDO.js";
-import "../chunk-WDHBCA3M.js";
+import "../chunk-NW4AQBXD.js";
 import "../chunk-PZ5AY32C.js";
 export {
   BENCHMARK_SPLIT_SEED,

package/dist/campaign/index.d.ts

@@ -888,6 +888,13 @@ declare class CostLedger {
     private ensureCostLimitPersisted;
     private appendEvent;
 }
+/** Public callback surface for a shared cost ledger.
+ *
+ * Declaration bundles may expose this type through multiple package subpaths.
+ * Keeping callback contracts structural lets those subpaths compose while the
+ * concrete {@link CostLedger} retains its private durable state.
+ */
+type CostLedgerHandle = Pick<CostLedger, keyof CostLedger>;
 
 /**
  * RawProviderSink — first-class persistence for the actual HTTP-level
@@ -1469,7 +1476,7 @@ interface JudgeConfig<TArtifact, TScenario extends Scenario = Scenario> {
         scenario: TScenario;
         signal: AbortSignal;
         /** Shared run spend account and receipt attribution phase. */
-        costLedger?: CostLedger;
+        costLedger?: CostLedgerHandle;
         costPhase?: string;
         costTags?: Record<string, string>;
     }): JudgeScore | Promise<JudgeScore>;
@@ -1656,7 +1663,7 @@ interface ProposeContext<TFindings = unknown> {
      *  reflection may ignore it. See {@link ParetoParent}. */
     paretoParents?: ParetoParent[];
     /** Shared run spend account and receipt attribution phase. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
     /** FIREWALL (non-negotiable): the held-out judge is write-only — its verdicts
      *  score the chosen output and gate promotion, and are NEVER an input to
@@ -1740,7 +1747,7 @@ interface GateContext<TArtifact, TScenario extends Scenario> {
         baseline: number;
     };
     /** Shared run spend account and receipt attribution phase. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
     signal: AbortSignal;
 }
@@ -2064,7 +2071,7 @@ interface LlmJudgeOptions<TArtifact, TScenario extends Scenario = Scenario> {
         scenario: TScenario;
     }) => string;
     /** Strict runtime contract; its JSON Schema is sent to the provider. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     responseSchema?: {
         name: string;
         schema: z.ZodObject;
@@ -2094,7 +2101,7 @@ interface ReferenceEquivalenceJudgeOptions {
     /** Used only by the direct-call adapter. */
     signal?: AbortSignal;
     /** Optional receipt destination for direct calls; campaigns supply their own. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
 }
 /** Build the campaign-native expected-answer judge. */
 declare function createReferenceEquivalenceJudge(options: ReferenceEquivalenceJudgeOptions): JudgeConfig<string, ReferenceEquivalenceScenario>;
@@ -2844,7 +2851,7 @@ interface RunCampaignOptions<TScenario extends Scenario, TArtifact> {
     costCeiling?: number;
     /** Shared spend account. Improvement loops pass one ledger through every
      *  campaign so the ceiling and returned total are run-wide. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     /** Attribution label for receipts recorded by this campaign. */
     costPhase?: string;
     /** Max concurrent cells. Default 2. */
@@ -4106,7 +4113,7 @@ interface RunOptimizationBaseOptions<TScenario extends Scenario, TArtifact> exte
         }>;
         history: GenerationRecord[];
         /** Shared run spend account and receipt attribution phase. */
-        costLedger?: CostLedger;
+        costLedger?: CostLedgerHandle;
         costPhase?: string;
     }) => Promise<unknown[]>;
 }
@@ -5148,14 +5155,14 @@ interface ProposePatchesArgs {
     /** How many candidate patches to propose. */
     count: number;
     signal: AbortSignal;
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     costPhase?: string;
 }
 interface SkillOptProposerOptions {
     llm: LlmClientOptions;
     model: string;
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     /** What the skill document governs — orients the prompt. */
     target: string;
     /** Default ops-per-patch cap when used as a bare `SurfaceProposer`. The
@@ -5444,7 +5451,7 @@ interface GepaProposerOptions {
     /** Model that performs the reflection. */
     model: string;
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     /** What is being optimized — appears in the reflection prompt for orientation. */
     target: string;
     /** Surface-specific mutation levers offered to the model. */
@@ -5509,7 +5516,7 @@ interface HaloProposerOptions {
     /** Model used to APPLY halo's findings to the prompt surface. Default = `model`. */
     applyModel?: string;
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     analysisMaximumCharge?: MaximumCharge;
     analysisReceipt?: (report: string) => CostReceiptInput;
     applyMaxTokens?: number;
@@ -5646,7 +5653,7 @@ interface LlmPolicyEditProposerOptions {
     llm: LlmClientOptions;
     model: string;
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     /** Plain-language description of the JSON surface being improved. */
     target: string;
     /** PolicyEdit target surface every authored edit must retain. */
@@ -5721,7 +5728,7 @@ declare function projectPolicyEditHistory(history: readonly GenerationRecord[],
 
 interface MemoryCurationProposerOptions {
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     /** Top-K lessons retained in the surface memory block. Default 12. */
     maxEntries?: number;
     /** Heading rendered above the lessons inside the block. Default below. */
@@ -5931,7 +5938,7 @@ interface TraceAnalystProposerOptions {
      *  Keep this EQUAL to haloProposer's `applyModel` for an apples-to-apples run. */
     applyModel?: string;
     /** Optional ledger for direct proposer use. Campaign context takes precedence. */
-    costLedger?: CostLedger;
+    costLedger?: CostLedgerHandle;
     analysisMaximumCharge?: MaximumCharge;
     analysisReceipt?: (report: string) => CostReceiptInput;
     applyMaxTokens?: number;
@@ -7314,4 +7321,4 @@ declare function verifyCodeSurface(surface: CodeSurface, worktreeDir?: string):
  *  identity against the checkout at `worktreeRef`. */
 declare function resolveWorktreePath(surface: CodeSurface, worktreeDir?: string): string;
 
-export { type AcceptedEdit, type AceProposerOptions, type AnalystArtifact, type AnalystScenario, type AnalyzeCrossSurfaceInteractionsInput, type ApplySkillPatchResult, type AxisEvidence, type AxisVerdict, type BuildAnalystSurfaceDispatchOptions, type BuildEvidenceVectorOptions, type BuildLoopProvenanceArgs, type CampaignAggregates, type CampaignArtifactWriter, type CampaignBreakdown, type CampaignCellResult, type CampaignCostMeter, type CampaignResult, type CampaignRunPlan, type CampaignRunPlanCell, type CampaignStorage, type CampaignTokenUsage, type CampaignTraceWriter, type CodeSurface, type CodeSurfaceVerification, type CompareProposersOptions, type CompositeProposerOptions, type CrossSurfaceAdditionDecision, type CrossSurfaceAdditionRejectionReason, type CrossSurfaceAttemptCompleteness, type CrossSurfaceBestSingleSelection, type CrossSurfaceBootstrapPolicy, type CrossSurfaceCandidate, type CrossSurfaceCandidateComparison, type CrossSurfaceCandidateEvidence, type CrossSurfaceCandidateOutcome, type CrossSurfaceCandidateSummary, type CrossSurfaceComponent, type CrossSurfaceComponentEvidence, type CrossSurfaceCompositionStep, type CrossSurfaceDistribution, type CrossSurfaceEligibility, type CrossSurfaceEvidenceBreakdown, type CrossSurfaceIneligibilityReason, type CrossSurfaceInteractionAwareSelection, type CrossSurfaceInteractionEffect, type CrossSurfaceInteractionPath, type CrossSurfaceInteractionReport, type CrossSurfaceInteractionTask, type CrossSurfaceNaiveStackSelection, type CrossSurfacePairCompatibility, type CrossSurfacePairEvidence, type CrossSurfacePairIncompatibilityReason, type CrossSurfacePairwiseEntry, type CrossSurfaceRankedSingle, type CrossSurfaceRelativeCost, type CrossSurfaceSelectionPolicy, type CrossSurfaceSelections, type CrossSurfaceTaskRow, DEFAULT_POLICY_EDIT_HISTORY_LIMITS, type DefaultProductionGateOptions, type DimensionRegression, type DiscriminationScore, type DispatchContext, type DispatchFn, type EmitLoopProvenanceArgs, type EmitLoopProvenanceResult, type EvalFixture, type EvalFixtureFile, type EvalFixtureLoadOptions, type EvalFixtureRunPlan, type EvalFixtureScenario, type EvalFixtureValidationMode, type EvidenceVector, type EvolutionaryProposerOptions, type FailureModeRecallJudgeOptions, type FapoAttributionSignals, type FapoEntryConfig, type FapoFailureCluster, type FapoOptimizationLevel, type FapoProposerOptions, type FapoReviewInput, type FapoReviewIssue, type FapoReviewResult, type FapoScopeContract, FileSearchLedger, FsLabeledScenarioStore, type FsLabeledScenarioStoreOptions, type Gate, type GateContext, type GateDecision, type GateResult, type GenerationCandidate, type GenerationRecord, type GepaProposerConstraints, type GepaProposerOptions, type GitWorktreeAdapterOptions, type Governor, type GovernorContext, type GovernorOp, type HaloProposerOptions, type HeldOutGateOptions, type HeldoutSignificance, type HeldoutSignificanceOptions, type HeuristicGovernorOptions, type JsonPolicyEditTargetSurface, type JsonPrimitive, type JsonValue, type JudgeAggregate, type JudgeConfig, type JudgeDimension, type JudgeScore, type LabelTrust, type LabeledScenarioRecord, type LabeledScenarioSampleArgs, type LabeledScenarioSource, type LabeledScenarioStore, LabeledScenarioStoreError, type LabeledScenarioWrite, Lineage, type LineageEdge, type LineageGraph, type LineageNode, type LineageNodeInput, type LineageStore, type LlmJudgeDimension, type LlmJudgeOptions, type LlmPolicyEditProposerOptions, type LoadEvalFixtureScenariosOptions, type LoopProvenanceBackend, type LoopProvenanceCandidate, type LoopProvenanceRecord, type MemoryCurationProposerOptions, type MutableSurface, type Mutator, type NeutralizationGateOptions, type ObjectiveSource, type OpenAutoPrOptions, type OpenAutoPrResult, type OpenSearchLedgerOptions, type OptimizationProposer, type OptimizerConfig, type OptimizerEntryConfig, POLICY_EDIT_CANDIDATE_RECORD_SCHEMA, type PairedHoldout, type ParameterCandidate, type ParameterChange, type ParameterSweepProposerOptions, type ParetoParent, type ParetoSignificanceGateOptions, type PlanCampaignRunOptions, type PlanEvalFixtureRunOptions, type PlaybackContext, type PlaybackDriver, type PlaybackStep, type PolicyEditAuthorScenarioRow, type PolicyEditCandidateRecord, type PolicyEditCandidateSummary, type PolicyEditFindingInput, type PolicyEditFindingSource, type PolicyEditHistoryCandidateContext, type PolicyEditHistoryGenerationContext, type PolicyEditHistoryProjectionOptions, type PolicyEditObjective, type PolicyEditOutcomeContext, type PolicyEditProposerOptions, type PowerPreflight, type PowerPreflightOptions, type ProfileDispatchFn, ProfileMatrixError, type ProfileSummary, type PromotionObjective, type PromotionPolicy, type ProposeContext, type ProposePatchesArgs, type ProposedCandidate, type ProposerComparison, type ProposerEntry, type ProposerPairwise, type ProposerScore, type RedactionStatus, type ReferenceEquivalenceJudgeOptions, type ReferenceEquivalenceScenario, type RejectedEdit, type RolloutArgumentDiff, type RolloutArgumentDiffOptions, type RolloutCall, type RunCampaignOptions, type RunEvalOptions, type RunImprovementLoopOptions, type RunImprovementLoopResult, type RunLineageLoopOptions, type RunLineageLoopResult, type RunLineageLoopSeed, type RunLineageOptions, type RunLineageResult, type RunLineageSeed, type RunLineageStepResult, type RunOptimizationOptions, type RunOptimizationResult, type RunProfileMatrixOptions, type RunProfileMatrixResult, type RunSkillOptOptions, type RunSkillOptResult, SEARCH_LEDGER_SCHEMA, type Scenario, type ScenarioAggregate, type ScenarioRollup, type ScenarioSignal, type ScoreboardRenderOptions, type ScoreboardRow, type ScoreboardSummary, type ScoredRollout, type ScoredSurfaceOutcome, type SearchAccountingAudit, type SearchArtifactRef, type SearchAttemptAccounting, type SearchCandidateDecidedEvent, type SearchCandidateLineage, type SearchCandidateRegisteredEvent, type SearchCandidateSlot, type SearchCandidateSlotClosedEvent, type SearchCandidateSurface, type SearchCompletedEvent, type SearchCostAccounting, type SearchFailureReason, type SearchLedger, type SearchLedgerAppendResult, SearchLedgerConflictError, type SearchLedgerEntry, SearchLedgerError, type SearchLedgerEvent, type SearchLedgerHash, SearchLedgerIntegrityError, type SearchLedgerReplay, type SearchModelIdentity, type SearchOperationKind, type SearchOperationRecordedEvent, type SearchPlan, type SearchPlannedEvent, type SearchPlannedOperation, type SearchPlannedTask, type SearchSourceRef, type SearchSurfaceEffect, type SearchSurfaceEvidence, type SearchSurfaceKind, type SearchTaskAttemptedEvent, type SearchTaskOutcome, type SearchTokenAccounting, type SelectPolicyEditAuthorRowsOptions, type SequentialDecideFn, type SequentialDecideOptions, type SequentialDecision, type SequentialObservation, type SequentialPairedGate, type SequentialPairedGateOptions, type SerializedJsonBudget, type SessionScript, type SingleRunLock, type SingleRunLockOptions, type SkillOptEpochRecord, type SkillOptEvidence, type SkillOptProposer, type SkillOptProposerOptions, type SkillPatch, type SkillPatchOp, SkillPatchParseError, type SkillPatchRejection, type SurfaceProposer, type SurfaceScore, type TraceAnalystProposerOptions, type TraceSpan, type TransientFailureOptions, type UngroundedLiteralReport, type UserStory, type UserStoryVerdict, type Worktree, type WorktreeAdapter, WorktreeAdapterError, aceProposer, acquireSingleRunLock, analyzeCrossSurfaceInteractions, applySkillPatch, assertCodeSurfaceIdentity, assertPolicyEditAuthorContextBudget, buildAnalystSurfaceDispatch, buildEvidenceVector, buildLoopProvenanceRecord, callbackGovernor, campaignBreakdown, campaignMeanComposite, classifyUngroundedLiterals, codeSurfaceIdentityMaterial, compareProposers, composeGate, compositeProposer, countSentenceEdits, createReferenceEquivalenceJudge, createRunCostLedger, defaultProductionGate, defaultRenderDiff, detectScale, dimensionRegressions, discoverEvalFixtures, emitLoopProvenance, evolutionaryProposer, extractFapoAttributionSignals, extractH2Sections, failureModeRecallJudge, fapoEscalationEntry, fapoProposer, fsCampaignStorage, fsLineageStore, gepaParetoEntry, gepaProposer, gepaReflectionEntry, gitWorktreeAdapter, haloProposer, heldOutGate, heldoutSignificance, heuristicGovernor, inMemoryCampaignStorage, isProposedCandidate, isTransientTransportFailure, labelTrustRank, lineageNodeId, llmJudge, llmPolicyEditProposer, loadEvalFixture, loadEvalFixtureScenarios, loopProvenanceSpans, makePlaybackDispatch, memLineageStore, memoryCurationProposer, neutralizationGate, neutralizeText, openAutoPr, openSearchLedger, pairHoldout, parameterSweepProposer, paretoPolicy, paretoSignificanceGate, parseSkillPatchResponse, patchEditCount, planCampaignRun, planEvalFixtureRun, policyEditProposer, powerPreflight, projectPolicyEditHistory, provenanceRecordPath, provenanceSpansPath, renderScoreboardMarkdown, resolveRunDir, resolveWorktreePath, rolloutArgumentDiff, runCampaign, runEval, runImprovementLoop, runLineage, runLineageLoop, runOptimization, runProfileMatrix, runSkillOpt, scoreDiscrimination, scoreUserStory, scoreboardSummary, selectDiscriminative, selectPolicyEditAuthorRows, sequentialDecide, sequentialPairedGate, skillOptEntry, skillOptProposer, surfaceContentHash, surfaceHash, tangleTracesRoot, traceAnalystProposer, userStoryScoreboard, validatePolicyEditCandidateRecord, validateSearchLedgerEvent, verifyCodeSurface };
+export { type AcceptedEdit, type AceProposerOptions, type AnalystArtifact, type AnalystScenario, type AnalyzeCrossSurfaceInteractionsInput, type ApplySkillPatchResult, type AxisEvidence, type AxisVerdict, type BuildAnalystSurfaceDispatchOptions, type BuildEvidenceVectorOptions, type BuildLoopProvenanceArgs, type CampaignAggregates, type CampaignArtifactWriter, type CampaignBreakdown, type CampaignCellResult, type CampaignCostMeter, type CampaignResult, type CampaignRunPlan, type CampaignRunPlanCell, type CampaignStorage, type CampaignTokenUsage, type CampaignTraceWriter, type CodeSurface, type CodeSurfaceVerification, type CompareProposersOptions, type CompositeProposerOptions, type CostLedgerHandle, type CrossSurfaceAdditionDecision, type CrossSurfaceAdditionRejectionReason, type CrossSurfaceAttemptCompleteness, type CrossSurfaceBestSingleSelection, type CrossSurfaceBootstrapPolicy, type CrossSurfaceCandidate, type CrossSurfaceCandidateComparison, type CrossSurfaceCandidateEvidence, type CrossSurfaceCandidateOutcome, type CrossSurfaceCandidateSummary, type CrossSurfaceComponent, type CrossSurfaceComponentEvidence, type CrossSurfaceCompositionStep, type CrossSurfaceDistribution, type CrossSurfaceEligibility, type CrossSurfaceEvidenceBreakdown, type CrossSurfaceIneligibilityReason, type CrossSurfaceInteractionAwareSelection, type CrossSurfaceInteractionEffect, type CrossSurfaceInteractionPath, type CrossSurfaceInteractionReport, type CrossSurfaceInteractionTask, type CrossSurfaceNaiveStackSelection, type CrossSurfacePairCompatibility, type CrossSurfacePairEvidence, type CrossSurfacePairIncompatibilityReason, type CrossSurfacePairwiseEntry, type CrossSurfaceRankedSingle, type CrossSurfaceRelativeCost, type CrossSurfaceSelectionPolicy, type CrossSurfaceSelections, type CrossSurfaceTaskRow, DEFAULT_POLICY_EDIT_HISTORY_LIMITS, type DefaultProductionGateOptions, type DimensionRegression, type DiscriminationScore, type DispatchContext, type DispatchFn, type EmitLoopProvenanceArgs, type EmitLoopProvenanceResult, type EvalFixture, type EvalFixtureFile, type EvalFixtureLoadOptions, type EvalFixtureRunPlan, type EvalFixtureScenario, type EvalFixtureValidationMode, type EvidenceVector, type EvolutionaryProposerOptions, type FailureModeRecallJudgeOptions, type FapoAttributionSignals, type FapoEntryConfig, type FapoFailureCluster, type FapoOptimizationLevel, type FapoProposerOptions, type FapoReviewInput, type FapoReviewIssue, type FapoReviewResult, type FapoScopeContract, FileSearchLedger, FsLabeledScenarioStore, type FsLabeledScenarioStoreOptions, type Gate, type GateContext, type GateDecision, type GateResult, type GenerationCandidate, type GenerationRecord, type GepaProposerConstraints, type GepaProposerOptions, type GitWorktreeAdapterOptions, type Governor, type GovernorContext, type GovernorOp, type HaloProposerOptions, type HeldOutGateOptions, type HeldoutSignificance, type HeldoutSignificanceOptions, type HeuristicGovernorOptions, type JsonPolicyEditTargetSurface, type JsonPrimitive, type JsonValue, type JudgeAggregate, type JudgeConfig, type JudgeDimension, type JudgeScore, type LabelTrust, type LabeledScenarioRecord, type LabeledScenarioSampleArgs, type LabeledScenarioSource, type LabeledScenarioStore, LabeledScenarioStoreError, type LabeledScenarioWrite, Lineage, type LineageEdge, type LineageGraph, type LineageNode, type LineageNodeInput, type LineageStore, type LlmJudgeDimension, type LlmJudgeOptions, type LlmPolicyEditProposerOptions, type LoadEvalFixtureScenariosOptions, type LoopProvenanceBackend, type LoopProvenanceCandidate, type LoopProvenanceRecord, type MemoryCurationProposerOptions, type MutableSurface, type Mutator, type NeutralizationGateOptions, type ObjectiveSource, type OpenAutoPrOptions, type OpenAutoPrResult, type OpenSearchLedgerOptions, type OptimizationProposer, type OptimizerConfig, type OptimizerEntryConfig, POLICY_EDIT_CANDIDATE_RECORD_SCHEMA, type PairedHoldout, type ParameterCandidate, type ParameterChange, type ParameterSweepProposerOptions, type ParetoParent, type ParetoSignificanceGateOptions, type PlanCampaignRunOptions, type PlanEvalFixtureRunOptions, type PlaybackContext, type PlaybackDriver, type PlaybackStep, type PolicyEditAuthorScenarioRow, type PolicyEditCandidateRecord, type PolicyEditCandidateSummary, type PolicyEditFindingInput, type PolicyEditFindingSource, type PolicyEditHistoryCandidateContext, type PolicyEditHistoryGenerationContext, type PolicyEditHistoryProjectionOptions, type PolicyEditObjective, type PolicyEditOutcomeContext, type PolicyEditProposerOptions, type PowerPreflight, type PowerPreflightOptions, type ProfileDispatchFn, ProfileMatrixError, type ProfileSummary, type PromotionObjective, type PromotionPolicy, type ProposeContext, type ProposePatchesArgs, type ProposedCandidate, type ProposerComparison, type ProposerEntry, type ProposerPairwise, type ProposerScore, type RedactionStatus, type ReferenceEquivalenceJudgeOptions, type ReferenceEquivalenceScenario, type RejectedEdit, type RolloutArgumentDiff, type RolloutArgumentDiffOptions, type RolloutCall, type RunCampaignOptions, type RunEvalOptions, type RunImprovementLoopOptions, type RunImprovementLoopResult, type RunLineageLoopOptions, type RunLineageLoopResult, type RunLineageLoopSeed, type RunLineageOptions, type RunLineageResult, type RunLineageSeed, type RunLineageStepResult, type RunOptimizationOptions, type RunOptimizationResult, type RunProfileMatrixOptions, type RunProfileMatrixResult, type RunSkillOptOptions, type RunSkillOptResult, SEARCH_LEDGER_SCHEMA, type Scenario, type ScenarioAggregate, type ScenarioRollup, type ScenarioSignal, type ScoreboardRenderOptions, type ScoreboardRow, type ScoreboardSummary, type ScoredRollout, type ScoredSurfaceOutcome, type SearchAccountingAudit, type SearchArtifactRef, type SearchAttemptAccounting, type SearchCandidateDecidedEvent, type SearchCandidateLineage, type SearchCandidateRegisteredEvent, type SearchCandidateSlot, type SearchCandidateSlotClosedEvent, type SearchCandidateSurface, type SearchCompletedEvent, type SearchCostAccounting, type SearchFailureReason, type SearchLedger, type SearchLedgerAppendResult, SearchLedgerConflictError, type SearchLedgerEntry, SearchLedgerError, type SearchLedgerEvent, type SearchLedgerHash, SearchLedgerIntegrityError, type SearchLedgerReplay, type SearchModelIdentity, type SearchOperationKind, type SearchOperationRecordedEvent, type SearchPlan, type SearchPlannedEvent, type SearchPlannedOperation, type SearchPlannedTask, type SearchSourceRef, type SearchSurfaceEffect, type SearchSurfaceEvidence, type SearchSurfaceKind, type SearchTaskAttemptedEvent, type SearchTaskOutcome, type SearchTokenAccounting, type SelectPolicyEditAuthorRowsOptions, type SequentialDecideFn, type SequentialDecideOptions, type SequentialDecision, type SequentialObservation, type SequentialPairedGate, type SequentialPairedGateOptions, type SerializedJsonBudget, type SessionScript, type SingleRunLock, type SingleRunLockOptions, type SkillOptEpochRecord, type SkillOptEvidence, type SkillOptProposer, type SkillOptProposerOptions, type SkillPatch, type SkillPatchOp, SkillPatchParseError, type SkillPatchRejection, type SurfaceProposer, type SurfaceScore, type TraceAnalystProposerOptions, type TraceSpan, type TransientFailureOptions, type UngroundedLiteralReport, type UserStory, type UserStoryVerdict, type Worktree, type WorktreeAdapter, WorktreeAdapterError, aceProposer, acquireSingleRunLock, analyzeCrossSurfaceInteractions, applySkillPatch, assertCodeSurfaceIdentity, assertPolicyEditAuthorContextBudget, buildAnalystSurfaceDispatch, buildEvidenceVector, buildLoopProvenanceRecord, callbackGovernor, campaignBreakdown, campaignMeanComposite, classifyUngroundedLiterals, codeSurfaceIdentityMaterial, compareProposers, composeGate, compositeProposer, countSentenceEdits, createReferenceEquivalenceJudge, createRunCostLedger, defaultProductionGate, defaultRenderDiff, detectScale, dimensionRegressions, discoverEvalFixtures, emitLoopProvenance, evolutionaryProposer, extractFapoAttributionSignals, extractH2Sections, failureModeRecallJudge, fapoEscalationEntry, fapoProposer, fsCampaignStorage, fsLineageStore, gepaParetoEntry, gepaProposer, gepaReflectionEntry, gitWorktreeAdapter, haloProposer, heldOutGate, heldoutSignificance, heuristicGovernor, inMemoryCampaignStorage, isProposedCandidate, isTransientTransportFailure, labelTrustRank, lineageNodeId, llmJudge, llmPolicyEditProposer, loadEvalFixture, loadEvalFixtureScenarios, loopProvenanceSpans, makePlaybackDispatch, memLineageStore, memoryCurationProposer, neutralizationGate, neutralizeText, openAutoPr, openSearchLedger, pairHoldout, parameterSweepProposer, paretoPolicy, paretoSignificanceGate, parseSkillPatchResponse, patchEditCount, planCampaignRun, planEvalFixtureRun, policyEditProposer, powerPreflight, projectPolicyEditHistory, provenanceRecordPath, provenanceSpansPath, renderScoreboardMarkdown, resolveRunDir, resolveWorktreePath, rolloutArgumentDiff, runCampaign, runEval, runImprovementLoop, runLineage, runLineageLoop, runOptimization, runProfileMatrix, runSkillOpt, scoreDiscrimination, scoreUserStory, scoreboardSummary, selectDiscriminative, selectPolicyEditAuthorRows, sequentialDecide, sequentialPairedGate, skillOptEntry, skillOptProposer, surfaceContentHash, surfaceHash, tangleTracesRoot, traceAnalystProposer, userStoryScoreboard, validatePolicyEditCandidateRecord, validateSearchLedgerEvent, verifyCodeSurface };

package/dist/campaign/index.js

@@ -66,7 +66,7 @@ import {
   userStoryScoreboard,
   validateSearchLedgerEvent,
   verifyCodeSurface
-} from "../chunk-Q442S5AS.js";
+} from "../chunk-GCT3DQWU.js";
 import {
   assertCodeSurfaceIdentity,
   buildEvidenceVector,
@@ -103,7 +103,7 @@ import {
   runOptimization,
   surfaceContentHash,
   surfaceHash
-} from "../chunk-YLMUS4MM.js";
+} from "../chunk-I42AAGHL.js";
 import {
   SearchLedgerConflictError,
   SearchLedgerError,
@@ -115,27 +115,27 @@ import {
   resolveRunDir,
   runCampaign,
   tangleTracesRoot
-} from "../chunk-IDZTTFRR.js";
+} from "../chunk-EGNRE7VA.js";
 import "../chunk-3YYRZDON.js";
 import {
   POLICY_EDIT_CANDIDATE_RECORD_SCHEMA,
   validatePolicyEditCandidateRecord
-} from "../chunk-OIIMMLRB.js";
+} from "../chunk-DZBCDDIE.js";
 import "../chunk-ARU2PZFM.js";
 import "../chunk-NJC7U437.js";
 import "../chunk-PJQFMIOX.js";
-import "../chunk-VCTY3W6J.js";
+import "../chunk-MLHRFWQK.js";
 import "../chunk-VI2UW6B6.js";
-import "../chunk-3EHHMC6E.js";
+import "../chunk-63KG3ASG.js";
 import "../chunk-GGE4NNQT.js";
-import "../chunk-QKEGNI5B.js";
+import "../chunk-BUBU3YHT.js";
 import "../chunk-PC4UYEBM.js";
 import "../chunk-S3UZOQ5Y.js";
 import "../chunk-MA6HLL3S.js";
 import "../chunk-XJYR7XFV.js";
 import "../chunk-VSMTAMNK.js";
 import "../chunk-ONWEPEDO.js";
-import "../chunk-WDHBCA3M.js";
+import "../chunk-NW4AQBXD.js";
 import "../chunk-PZ5AY32C.js";
 export {
   DEFAULT_POLICY_EDIT_HISTORY_LIMITS,

package/dist/{chunk-3EHHMC6E.js → chunk-63KG3ASG.js}

@@ -2,7 +2,7 @@ import {
   OtlpFileTraceStore,
   TraceFileMissingError,
   buildTraceAnalystTools
-} from "./chunk-QKEGNI5B.js";
+} from "./chunk-BUBU3YHT.js";
 
 // src/trace-analyst/prompts.ts
 var TRACE_ANALYST_ACTOR_DESCRIPTION = `You answer questions about an OTLP-shaped JSONL trace dataset using the trace tools provided in the \`traces\` namespace.
@@ -198,4 +198,4 @@ export {
   TRACE_ANALYST_SUBAGENT_DESCRIPTION,
   analyzeTraces
 };
-//# sourceMappingURL=chunk-3EHHMC6E.js.map
+//# sourceMappingURL=chunk-63KG3ASG.js.map

package/dist/{chunk-FTUMG2U7.js → chunk-6JQE3YVE.js}

@@ -1,14 +1,14 @@
 import {
   recordAggregateMeasurements,
   summarizeExecutionMeasurements
-} from "./chunk-KSDQVPLR.js";
+} from "./chunk-TVXPJJ7H.js";
 import {
   extractUsage,
   extractUsageFromSse
 } from "./chunk-PXE2VKMX.js";
 import {
   analyzeTraces
-} from "./chunk-3EHHMC6E.js";
+} from "./chunk-63KG3ASG.js";
 import {
   LLM_MODEL_ATTR_KEYS,
   applyToolSpanOtlpAttributes,
@@ -17,7 +17,7 @@ import {
   projectOtlpFlatLine,
   spanEpochMillis,
   traceSpanKindToOpenInferenceKind
-} from "./chunk-QKEGNI5B.js";
+} from "./chunk-BUBU3YHT.js";
 import {
   defaultProviderRedactor,
   providerFromBaseUrl
@@ -33,16 +33,13 @@ import {
   ReplayError
 } from "./chunk-ONWEPEDO.js";
 import {
-  LLM_CACHED_TOKENS,
-  LLM_CACHE_WRITE_TOKENS,
-  LLM_COST_USD,
   LLM_INPUT_TOKENS,
   LLM_MODEL_NAME,
   LLM_OUTPUT_TOKENS,
-  LLM_REASONING_TOKENS,
   OPENINFERENCE_SPAN_KIND,
-  TOOL_NAME
-} from "./chunk-WDHBCA3M.js";
+  TOOL_NAME,
+  applyLlmSpanOtlpAttributes
+} from "./chunk-NW4AQBXD.js";
 
 // src/trace-analyst/hook.ts
 var DEFAULT_QUESTION = "Summarise what happened in this run. Surface any failure modes, surprising findings, or evidence that the run's verdict is wrong.";
@@ -1179,16 +1176,7 @@ function flattenSpanAttributes(span) {
   }
   base[OPENINFERENCE_SPAN_KIND] = traceSpanKindToOpenInferenceKind(span.kind);
   if (span.kind === "llm") {
-    base[LLM_MODEL_NAME] = span.model;
-    if (span.inputTokens !== void 0) base[LLM_INPUT_TOKENS] = span.inputTokens;
-    if (span.outputTokens !== void 0) base[LLM_OUTPUT_TOKENS] = span.outputTokens;
-    if (span.reasoningTokens !== void 0) base[LLM_REASONING_TOKENS] = span.reasoningTokens;
-    if (span.cachedTokens !== void 0) base[LLM_CACHED_TOKENS] = span.cachedTokens;
-    if (span.cacheWriteTokens !== void 0) {
-      base[LLM_CACHE_WRITE_TOKENS] = span.cacheWriteTokens;
-    }
-    if (span.costUsd !== void 0) base[LLM_COST_USD] = span.costUsd;
-    if (span.finishReason) base["llm.finish_reason"] = span.finishReason;
+    applyLlmSpanOtlpAttributes(base, span);
   } else if (span.kind === "tool") {
     applyToolSpanOtlpAttributes(base, span);
   } else if (span.kind === "retrieval") {
@@ -1411,15 +1399,7 @@ function toOtlpSpan(span) {
     }
   }
   attrs[OPENINFERENCE_SPAN_KIND] = traceSpanKindToOpenInferenceKind(span.kind);
-  if (span.model) attrs[LLM_MODEL_NAME] = span.model;
-  if (span.inputTokens !== void 0) attrs[LLM_INPUT_TOKENS] = span.inputTokens;
-  if (span.outputTokens !== void 0) attrs[LLM_OUTPUT_TOKENS] = span.outputTokens;
-  if (span.reasoningTokens !== void 0) attrs[LLM_REASONING_TOKENS] = span.reasoningTokens;
-  if (span.cachedTokens !== void 0) attrs[LLM_CACHED_TOKENS] = span.cachedTokens;
-  if (span.cacheWriteTokens !== void 0) {
-    attrs[LLM_CACHE_WRITE_TOKENS] = span.cacheWriteTokens;
-  }
-  if (span.costUsd !== void 0) attrs[LLM_COST_USD] = span.costUsd;
+  applyLlmSpanOtlpAttributes(attrs, span);
   if (span.tool) applyToolSpanOtlpAttributes(attrs, span.tool);
   return {
     traceId: padTraceId(span.traceId),
@@ -1667,16 +1647,7 @@ function spanToAttributes(span, events) {
     [OPENINFERENCE_SPAN_KIND]: traceSpanKindToOpenInferenceKind(span.kind)
   };
   if (span.kind === "llm") {
-    attrs[LLM_MODEL_NAME] = span.model;
-    if (span.inputTokens !== void 0) attrs[LLM_INPUT_TOKENS] = span.inputTokens;
-    if (span.outputTokens !== void 0) attrs[LLM_OUTPUT_TOKENS] = span.outputTokens;
-    if (span.reasoningTokens !== void 0) attrs[LLM_REASONING_TOKENS] = span.reasoningTokens;
-    if (span.cachedTokens !== void 0) attrs[LLM_CACHED_TOKENS] = span.cachedTokens;
-    if (span.cacheWriteTokens !== void 0) {
-      attrs[LLM_CACHE_WRITE_TOKENS] = span.cacheWriteTokens;
-    }
-    if (span.costUsd !== void 0) attrs[LLM_COST_USD] = span.costUsd;
-    if (span.finishReason) attrs["llm.finish_reason"] = span.finishReason;
+    applyLlmSpanOtlpAttributes(attrs, span);
     if (Array.isArray(span.messages)) {
       attrs["llm.input_messages"] = JSON.stringify(span.messages.slice(-6));
     }
@@ -1926,4 +1897,4 @@ export {
   createReplayFetch,
   iterateRawCalls
 };
-//# sourceMappingURL=chunk-FTUMG2U7.js.map
+//# sourceMappingURL=chunk-6JQE3YVE.js.map