@tangle-network/agent-eval 0.213.0 → 0.215.0

package/dist/{types-Dv9sYwBB.d.ts → types-CMnPcbW5.d.ts}

@@ -4,7 +4,7 @@ import { _ as ProposalFinding } from "./types-KEkKkETv.js";
 import { M as LlmCallMetadata } from "./types-Lub7o6bN.js";
 import { t as SeriesDistribution } from "./descriptive-B2iPaT9J.js";
 import { A as SearchLedgerHash, G as SearchSplit, I as SearchNodeStatus, L as SearchOpenedEvent, N as SearchNodeDecision, O as SearchLedgerEntry, P as SearchNodeRef, Q as SearchTaskOutcome, R as SearchOperationKind, U as SearchReservation, Z as SearchTask, b as SearchClosedEvent, d as SearchCellCancelledEvent, i as SearchArtifactRef, l as SearchCandidateSurface, o as SearchAudit, p as SearchCellStage, t as NodeEstimate, w as SearchEdgeRecordedEvent, z as SearchOperationRecordedEvent } from "./search-ledger-types-p2xKfiDJ.js";
-import { p as LedgerProjector } from "./index-Bj96W0jZ.js";
+import { w as LedgerProjector } from "./index-DHKEAv3s.js";
 import { i as RolloutSearchLineage } from "./mint-CDy-brUR.js";
 //#region src/campaign/search-state.d.ts
 /** Deterministic node id: identical content in one search is one node. */
@@ -1015,4 +1015,4 @@ interface CampaignResult<TArtifact = unknown, TScenario extends Scenario = Scena
 }
 //#endregion
 export { SearchNode as $, LabeledScenarioWrite as A, ScoredSurfaceOutcome as B, JudgeDimension as C, LabeledScenarioSampleArgs as D, LabeledScenarioRecord as E, ProposeContext as F, labelTrustRank as G, SurfaceProposer as H, ProposedCandidate as I, renderSearchSummary as J, SearchProposerView as K, RedactionStatus as L, OptimizerConfig as M, ParetoParent as N, LabeledScenarioSource as O, ProposalTrackContext as P, SearchDecisionRecord as Q, Scenario as R, JudgeConfig as S, LabelTrust as T, TraceSpan as U, SessionScript as V, isProposedCandidate as W, SearchCell as X, searchProposerView as Y, SearchCompletion as Z, GateDecision as _, CampaignResult as a, SearchUnitScore as at, GenerationRecord as b, CampaignTraceWriter as c, searchTaskSetDigest as ct, DispatchContext as d, SearchOperation as et, DispatchFn as f, GateContribution as g, GateContext as h, CampaignCostMeter as i, SearchStateView as it, MutableSurface as j, LabeledScenarioStore as k, CodeSurface as l, searchUnitScores as lt, GateCheckStatus as m, CampaignArtifactWriter as n, SearchSpend as nt, CampaignScenarioIdentity as o, searchCellId as ot, Gate as p, SearchSummaryOptions as q, CampaignCellResult as r, SearchState as rt, CampaignTokenUsage as s, searchNodeId as st, CampaignAggregates as t, SearchScoredCell as tt, ComponentSurface as u, GateResult as v, JudgeScore as w, JudgeAggregate as x, GenerationCandidate as y, ScenarioAggregate as z };
-//# sourceMappingURL=types-Dv9sYwBB.d.ts.map
+//# sourceMappingURL=types-CMnPcbW5.d.ts.map

package/dist/{types-Dv9sYwBB.d.ts.map → types-CMnPcbW5.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-Dv9sYwBB.d.ts","names":[],"sources":["../src/campaign/search-state.ts","../src/campaign/search-summary.ts","../src/campaign/types.ts"],"mappings":";;;;;;;;;;iBAwDgB,aAAa,kBAAkB;;iBAK/B,aACd,kBACA,gBACA,gBACA,OAAO,aACP;;iBAMc,oBAAoB,gBAAgB,eAAe;UAkBlD;EACf;EACA,UAAU;EACV,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;UAKe;EACf;EACA;EACA;EACA;;;UAIe;EACf;EACA;;EAEA;EACA;;;;;;;;iBASc,iBAAiB,gBAAgB,qBAAqB;UAoBrD;EACf;;EAEA;EACA,gBAAgB;EAChB,UAAU;EACV,mBAAmB;;;EAGnB;;EAEA;;;;EAIA,kBAAkB;EAClB;EACA;EACA,QAAQ;EACR;;EAEA;EACA,oBAAoB;EACpB;EACA,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA,OAAO;EACP;EACA,OAAO;EACP;EACA,aAAa;EACb;EACA;EACA,SAAS;;EAET;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA;EACA;;UAGe;EACf;EACA,eAAe;EACf,aAAa;EACb;;EAEA,SAAS;;;EAGT,WAAW;;;EAGX,oBAAoB;;EAEpB;;EAEA;;UAGe;EACf;EACA;;;;;;;cA6BW,uBAAuB,gBAAgB,mBAAmB;WAC5D;UACD;UACA;UACA;UACA;UACA;UACA;mBACS;mBACA;mBACA;mBACA;mBACA;mBACA;mBACA;mBACA;UACT;UACA;;mBAES;;UAET;mBACS;EAEjB,YAAY;EAgCZ,MAAM,OAAO,mBAAmB;EA6BhC,YAAY;;EAKZ,KAAK;UAIG;UAgCA;UA6CA;UAsBA;UA8BA;UA8CA;UAsHA;UAmEA;UA4EA;UAoBA;UAmDA;UAaA;;;UA2EA;;EASR;;;UAmBQ;;;UAkBA;;;;;;;;;;;UAoBA;;;EAsBR;IAAgB;IAA4B;;;EAa5C,cAAc;;EAKd,cAAc;;EAKd;IAAc;IAAkB,WAAW;;;EAK3C;;EAKA,aAAa;;EAcb,SAAS,iBAAiB;;EAM1B;;EAKA,YAAY;;EAKZ,oBAAoB;;EAKpB,SAAS,iBAAiB;;EAK1B;;EAKA,SAAS,iBAAiB;;EAM1B,YAAY;;EAMZ,cAAc,sBAAsB;;EAMpC,gBAAgB,gBAAgB,OAAO,cAAc;;;;;;;cAiB1C;WACF;WACA,QAAQ;WACR,QAAQ;WACR;IAAQ;IAAkB,WAAW;;;WAErC;WACA,OAAO;WACP,YAAY;;;;;;;WAOZ;IAAU;IAA4B;;mBAC9B;mBACA;EAEjB,YAAY,OAAO,aAAa;;MAgB5B;EAIJ,KAAK,iBAAiB;EAItB,QAAQ;;EAKR;;EAKA,SAAS;EAKT,gBAAgB;EAIhB,KAAK,iBAAiB;;EAKtB,SAAS;EAKT,KAAK,iBAAiB;;EAKtB,MAAM;IAAU;MAAyB;EAKzC,UAAU,sBAAsB;;;EAMhC,YAAY,gBAAgB,OAAO,cAAc;;EAKjD,WAAW,gBAAgB,OAAO,cAAc;;EAKhD,QAAQ,aAAa,uBAAuB;UAmCpC;;;;;;UCluCO;WACN;WACA;;;EAGT,YAAY,0BAA0B;;EAEtC,WAAW,0BAA0B;;;iBAIvB,mBAAmB,OAAO,kBAAkB;UAW3C;;;;;;;;EAQf,OAAO;;EAEP;;;;;;;;;;;iBAYc,oBAAoB,OAAO,iBAAiB,SAAS;;;;;UCtCpD;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;;;;EAOV;;;;EAIA,eAAe,eAAe;IAAQ;IAAe;;;;;EAIrD;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;;;EAMA,cAAc,SAAS;;;;iBAKT,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;;;;WAIjC,gBAAgB;;;;;WAKhB;;;;WAIA,UAAU;IAAgB;IAAgB,UAAU;;;;WAGpD,QAAQ;;;;WAIR;;;WAGA,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB,gBAAgB;;;;WAIhB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;;UAMX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;;EAEA;IAAY;IAAsB;;EAClC;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;;;EAIA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;;;EAMA,cAAc;;UAGC;EACf;EACA;EACA;;;EAGA,cAAc;;UAGC;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;;;EAIA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;;;EAIA,cAAc,SAAS;;UAGR;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
+{"version":3,"file":"types-CMnPcbW5.d.ts","names":[],"sources":["../src/campaign/search-state.ts","../src/campaign/search-summary.ts","../src/campaign/types.ts"],"mappings":";;;;;;;;;;iBAwDgB,aAAa,kBAAkB;;iBAK/B,aACd,kBACA,gBACA,gBACA,OAAO,aACP;;iBAMc,oBAAoB,gBAAgB,eAAe;UAkBlD;EACf;EACA,UAAU;EACV,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;UAKe;EACf;EACA;EACA;EACA;;;UAIe;EACf;EACA;;EAEA;EACA;;;;;;;;iBASc,iBAAiB,gBAAgB,qBAAqB;UAoBrD;EACf;;EAEA;EACA,gBAAgB;EAChB,UAAU;EACV,mBAAmB;;;EAGnB;;EAEA;;;;EAIA,kBAAkB;EAClB;EACA;EACA,QAAQ;EACR;;EAEA;EACA,oBAAoB;EACpB;EACA,OAAO;EACP;EACA;;UAGe;EACf;EACA;EACA;EACA;EACA,OAAO;EACP;EACA,OAAO;EACP;EACA,aAAa;EACb;EACA;EACA,SAAS;;EAET;;EAEA;EACA,WAAW;;EAEX;;EAEA;EACA;EACA;EACA;;UAGe;EACf;EACA,eAAe;EACf,aAAa;EACb;;EAEA,SAAS;;;EAGT,WAAW;;;EAGX,oBAAoB;;EAEpB;;EAEA;;UAGe;EACf;EACA;;;;;;;cA6BW,uBAAuB,gBAAgB,mBAAmB;WAC5D;UACD;UACA;UACA;UACA;UACA;UACA;mBACS;mBACA;mBACA;mBACA;mBACA;mBACA;mBACA;mBACA;UACT;UACA;;mBAES;;UAET;mBACS;EAEjB,YAAY;EAgCZ,MAAM,OAAO,mBAAmB;EA6BhC,YAAY;;EAKZ,KAAK;UAIG;UAgCA;UA6CA;UAsBA;UA8BA;UA8CA;UAsHA;UAmEA;UA4EA;UAoBA;UAmDA;UAaA;;;UA2EA;;EASR;;;UAmBQ;;;UAkBA;;;;;;;;;;;UAoBA;;;EAsBR;IAAgB;IAA4B;;;EAa5C,cAAc;;EAKd,cAAc;;EAKd;IAAc;IAAkB,WAAW;;;EAK3C;;EAKA,aAAa;;EAcb,SAAS,iBAAiB;;EAM1B;;EAKA,YAAY;;EAKZ,oBAAoB;;EAKpB,SAAS,iBAAiB;;EAK1B;;EAKA,SAAS,iBAAiB;;EAM1B,YAAY;;EAMZ,cAAc,sBAAsB;;EAMpC,gBAAgB,gBAAgB,OAAO,cAAc;;;;;;;cAiB1C;WACF;WACA,QAAQ;WACR,QAAQ;WACR;IAAQ;IAAkB,WAAW;;;WAErC;WACA,OAAO;WACP,YAAY;;;;;;;WAOZ;IAAU;IAA4B;;mBAC9B;mBACA;EAEjB,YAAY,OAAO,aAAa;;MAgB5B;EAIJ,KAAK,iBAAiB;EAItB,QAAQ;;EAKR;;EAKA,SAAS;EAKT,gBAAgB;EAIhB,KAAK,iBAAiB;;EAKtB,SAAS;EAKT,KAAK,iBAAiB;;EAKtB,MAAM;IAAU;MAAyB;EAKzC,UAAU,sBAAsB;;;EAMhC,YAAY,gBAAgB,OAAO,cAAc;;EAKjD,WAAW,gBAAgB,OAAO,cAAc;;EAKhD,QAAQ,aAAa,uBAAuB;UAmCpC;;;;;;UCluCO;WACN;WACA;;;EAGT,YAAY,0BAA0B;;EAEtC,WAAW,0BAA0B;;;iBAIvB,mBAAmB,OAAO,kBAAkB;UAW3C;;;;;;;;EAQf,OAAO;;EAEP;;;;;;;;;;;iBAYc,oBAAoB,OAAO,iBAAiB,SAAS;;;;;UCtCpD;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;;;;EAOV;;;;EAIA,eAAe,eAAe;IAAQ;IAAe;;;;;EAIrD;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;;;EAMA,cAAc,SAAS;;;;iBAKT,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;;;;WAIjC,gBAAgB;;;;;WAKhB;;;;WAIA,UAAU;IAAgB;IAAgB,UAAU;;;;WAGpD,QAAQ;;;;WAIR;;;WAGA,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB,gBAAgB;;;;WAIhB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;;UAMX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;;EAEA;IAAY;IAAsB;;EAClC;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;;;EAIA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;;;;;EAMA,cAAc;;UAGC;EACf;EACA;EACA;;;EAGA,cAAc;;UAGC;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;;;EAIA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;;;EAIA,cAAc,SAAS;;UAGR;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}

package/dist/{types-tWFY6bON.d.ts → types-Dj0Qv2qi.d.ts}

@@ -1,5 +1,5 @@
 import { c as RunSplitTag } from "./run-record-p2AYTrCn.js";
-import { R as Scenario, d as DispatchContext } from "./types-Dv9sYwBB.js";
+import { R as Scenario, d as DispatchContext } from "./types-CMnPcbW5.js";
 //#region src/benchmarks/types.d.ts
 type BenchmarkTaskKind = 'retrieval' | 'rag-answer' | 'hallucination' | 'kb-improvement' | 'routing' | 'custom';
 type BenchmarkFamily = 'beir' | 'mteb-retrieval' | 'msmarco' | 'trec-dl' | 'miracl' | 'lotte' | 'bright' | 'crag' | 'hotpotqa' | 'kilt' | 'ragtruth' | 'faithbench' | 'first-party' | 'custom';
@@ -99,4 +99,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
 declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
 //#endregion
 export { BenchmarkFamily as a, BenchmarkSource as c, BenchmarkEvaluation as i, BenchmarkTaskKind as l, BenchmarkAdapter as n, BenchmarkResponder as o, BenchmarkDatasetItem as r, BenchmarkScenario as s, BENCHMARK_SPLIT_SEED as t, deterministicSplit as u };
-//# sourceMappingURL=types-tWFY6bON.d.ts.map
+//# sourceMappingURL=types-Dj0Qv2qi.d.ts.map

package/dist/{types-tWFY6bON.d.ts.map → types-Dj0Qv2qi.d.ts.map}

@@ -1 +1 @@
-{"version":3,"file":"types-tWFY6bON.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;;;;EAKA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
+{"version":3,"file":"types-Dj0Qv2qi.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;;;;EAKA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}

package/docs/public-api.md

@@ -7,11 +7,11 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
 | measure | count |
 | --- | --- |
 | export subpaths | 33 |
-| published value exports (subpath x symbol) | 1584 |
-| distinct symbols | 1393 |
+| published value exports (subpath x symbol) | 1612 |
+| distinct symbols | 1413 |
 | production | 1104 |
-| planned | 268 |
-| none | 212 |
+| planned | 284 |
+| none | 224 |
 
 Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
 
@@ -90,11 +90,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `.`
 
-358 value exports — 291 production, 36 planned, 31 none.
+366 value exports — 291 production, 43 planned, 32 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `acquisitionPlansForKnowledgeGaps` | production | agent-builder:src/lib/.server/eval/loops/data-acquisition-engine.ts |
+| `addCalibrationVerdicts` | planned | doc: docs/concepts.md |
 | `admitPolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
 | `AgentEvalError` | production | agent-runtime:src/errors.ts |
@@ -117,6 +118,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertCapabilityHeadroom` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `assertCrossFamily` | production | agent-builder:frontier/judges/artifact-head-to-head.ts |
 | `assertCrossFamilyServed` | planned | doc: docs/building-doctrine.md |
+| `assertJudgeMayGate` | planned | doc: docs/concepts.md |
 | `assertNoHiddenLeak` | planned | doc: docs/design/statistics-decisions.md |
 | `assertNoJudgeVerdict` | production | this package: src/analyst/policy-edit.ts:6 |
 | `assertProductBenchmarkRun` | production | creative-agent:eval/research-package.ts |
@@ -151,7 +153,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `canonicalJson` | production | agent-knowledge:src/benchmarks/memory-recovery.ts |
 | `capabilityHeadroom` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `captureFetchToRawSink` | production | creative-agent:eval/canonical-runner.ts |
-| `certificationEvidenceDigest` | production | this package: src/completion-verifier.ts:38 |
+| `certificationEvidenceDigest` | production | this package: src/completion-verifier.ts:37 |
 | `checkCanaries` | production | blueprint-agent:scripts/experiments/lib/contamination-preflight.ts |
 | `checkServedModel` | production | this package: src/integrity/preflight.ts:33 |
 | `checkTraceContracts` | production | creative-agent:eval/lib/trace-contracts.ts |
@@ -202,6 +204,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `DECISION_PAIRED_DELTA_STATISTIC` | production | this package: src/campaign/estimate-node.ts:19 |
 | `DEFAULT_BOUNDED_PROCESS_TIMEOUT_MS` | production | this package: src/command-runner.ts:28 |
 | `DEFAULT_FAILURE_REASON_RULES` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
+| `DEFAULT_JUDGE_GATE_POLICY` | none | — |
 | `DEFAULT_RED_TEAM_CORPUS` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
 | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
 | `DEFAULT_TRACE_ANALYST_KINDS` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
@@ -236,7 +239,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
 | `extractErrorCount` | production | blueprint-agent:scripts/experiments/lib/error-count-extractor.ts |
 | `extractProducedState` | production | agent-app:src/eval/index.ts |
-| `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:12 |
+| `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:13 |
 | `extractUsageFromSse` | production | this package: src/trace/capture-fetch.ts:8 |
 | `FAILURE_BLAME` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
 | `FAILURE_CLASSES` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
@@ -288,6 +291,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `judgeAgreementView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
 | `JudgeError` | production | agent-runtime:src/errors.ts |
 | `judgeFamily` | production | agent-builder:frontier/judges/llm.ts |
+| `judgeGateDecision` | planned | doc: docs/concepts.md |
+| `JudgeGateRefusedError` | planned | doc: docs/concepts.md |
 | `judgeSpans` | production | this package: src/builder-eval/three-layer-eval.ts:25 |
 | `knowledgeReadinessTracePayload` | production | agent-dev-container:products/intelligence/api/src/routes/project-engines.ts |
 | `leaderboard` | production | blueprint-agent:scripts/experiments/lib/cross-harness-leaderboard.ts |
@@ -309,6 +314,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `mcnemar` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `mcnemarPower` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
 | `mcnemarRequiredN` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
+| `measureJudgeAgreement` | planned | doc: docs/concepts.md |
 | `minimumPairsForPairedDeltaTest` | production | agent-dev-container:products/intelligence/api/src/routes/optimizations.ts |
 | `mintRolloutRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
 | `MODEL_PRICING` | production | supervisor-lab:archive/bench/profile-arena.ts |
@@ -373,6 +379,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `redTeamDataset` | production | creative-agent:eval/red-team.ts |
 | `redTeamReport` | production | creative-agent:eval/red-team.ts |
 | `regexMatches` | none | only this package's tests: src/oracle.test.ts:2 |
+| `registerCalibrationSet` | planned | doc: docs/concepts.md |
 | `renderPreferenceMemoryMarkdown` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
 | `repeatedActionDetector` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
 | `requiredPairedSampleSize` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
@@ -409,6 +416,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `ServedCrossFamilyError` | none | only this package's tests: src/integrity/served-model.test.ts:2 |
 | `servedModelAcceptable` | production | this package: src/integrity/preflight.ts:33 |
 | `shareAllowed` | production | agent-dev-container:products/intelligence/api/src/lib/search-blobs.ts |
+| `snapshotFromJudgeAgreement` | planned | doc: docs/concepts.md |
 | `spanRecordsToTraceAnalysisStore` | production | agent-dev-container:products/intelligence/api/src/lib/pg-trace-analyst-store.ts |
 | `spearmanR` | production | this package: scripts/synthetic-search-ledger.ts:71 |
 | `stripFencedJson` | production | agent-builder:src/lib/.server/eval/router-llm-client.ts |
@@ -824,7 +832,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./contract`
 
-62 value exports — 41 production, 15 planned, 6 none.
+63 value exports — 41 production, 15 planned, 7 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -848,6 +856,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `fromKimiCodeSession` | planned | doc: docs/code-agent-intake.md |
 | `fromOpenCodeSession` | planned | doc: docs/code-agent-intake.md |
 | `fromOtelSpans` | production | agent-dev-container:packages/intelligence-kernel/src/deterministic.ts |
+| `fromPiGraphSession` | none | only this package's tests: tests/contract-code-agent-intake.test.ts:6 |
 | `fromPiSession` | planned | doc: docs/code-agent-intake.md |
 | `fromRunRecordDir` | production | this package: src/contract/eval-reporting-suite.ts:25 |
 | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
@@ -859,7 +868,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `makeProposalFinding` | production | agent-lab:projects/playproof/code-surface.ts |
 | `measuredComparisonFromAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
 | `measuredComparisonFromCandidateExperiment` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
-| `observeCodeAgentSession` | production | this package: src/contract/intake/code-agent-session.ts:13 |
+| `observeCodeAgentSession` | production | this package: src/contract/intake/code-agent-session.ts:14 |
 | `observeCodeAgentStore` | none | only this package's tests: tests/contract-code-agent-store.test.ts:5 |
 | `paretoPolicy` | planned | named in discovery-lab (bind not in the import graph) |
 | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
@@ -946,7 +955,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `eProcess` | production | this package: src/campaign/gates/sequential.ts:37 |
 | `evaluateCondition` | planned | named in agent-dev-container (bind not in the import graph) |
 | `evaluateHaltRule` | production | this package: src/experiment/define.ts:20 |
-| `evaluateHypothesis` | none | only this package's tests: tests/tier2.test.ts:8 |
+| `evaluateHypothesis` | none | only this package's tests: tests/tier2.test.ts:4 |
 | `evaluateIdentityGate` | production | this package: src/experiment/define.ts:20 |
 | `evaluateOracleDeterminismGate` | production | this package: src/experiment/define.ts:20 |
 | `evaluatePopulationReproducibilityGate` | production | this package: src/experiment/define.ts:20 |
@@ -1066,7 +1075,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./ledger-core`
 
-20 value exports — 19 production, 1 planned, 0 none.
+28 value exports — 19 production, 1 planned, 8 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1079,6 +1088,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `LEDGER_HASH_PATTERN` | production | blueprint-agent:scripts/experiments/lib/causal-analytics.ts |
 | `LedgerCanonicalizationError` | planned | named in blueprint-agent (bind not in the import graph) |
 | `MemoryLedgerJournal` | production | this package: src/campaign/search-ledger.ts:23 |
+| `MERKLE_EMPTY_ROOT` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `merkleConsistencyProof` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `merkleInclusionProof` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `merkleLeafHash` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `merkleRoot` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `merkleSalt` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
 | `probeAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
 | `projectorSnapshotPathFor` | production | this package: src/ledger-core/journal.ts:48 |
 | `readProjectorSnapshotFile` | production | this package: src/ledger-core/journal.ts:48 |
@@ -1088,6 +1103,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `tryAcquireAtomicFileLock` | production | discovery-lab:runner/evidence-review.mjs |
 | `tryWithLedgerFileLock` | production | discovery-lab:experiments/diu-campaign-v1/launch-wave-cloud.mjs |
 | `verifyEntriesAgainstTrustedHead` | production | this package: src/ledger-core/journal.ts:55 |
+| `verifyMerkleConsistency` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
+| `verifyMerkleInclusion` | none | only this package's tests: src/ledger-core/merkle.test.ts:4 |
 | `withLedgerFileLock` | production | this package: src/analyst/benchmark-response-cache.ts:6 |
 | `writeLedgerFileAtomically` | production | discovery-lab:experiments/diu-campaign-v1/launch-wave-cloud.mjs |
 
@@ -1103,10 +1120,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./meta-eval`
 
-35 value exports — 27 production, 7 planned, 1 none.
+43 value exports — 27 production, 14 planned, 2 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
+| `addCalibrationVerdicts` | planned | doc: docs/concepts.md |
+| `assertJudgeMayGate` | planned | doc: docs/concepts.md |
 | `auditEvaluator` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-factory.ts |
 | `auditProbabilityPolicy` | planned | doc: docs/changes/probability-policy-audit.md |
 | `brierScore` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
@@ -1118,6 +1137,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `clusterBootstrapMean` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
 | `continuousAgreement` | production | agent-builder:frontier/judges/eval-validity.ts |
 | `correlationStudy` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
+| `DEFAULT_JUDGE_GATE_POLICY` | none | — |
 | `definePlant` | production | discovery-lab:experiments/e1-checker/score.mjs |
 | `evalHealthStamp` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `evaluatorAdmissionPolicySchema` | production | agent-dev-container:products/intelligence/api/src/lib/measurement-factory.ts |
@@ -1125,8 +1145,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `fileSentinelStore` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `FileSystemOutcomeStore` | production | ph0ny:products/builder/api/src/eval/outcomes.ts |
 | `InMemoryOutcomeStore` | planned | consumer tests: ph0ny:products/builder/api/src/eval/outcomes-correlate.test.ts |
-| `inMemorySentinelStore` | none | only this package's tests: tests/judge-sentinel.test.ts:7 |
+| `inMemorySentinelStore` | none | only this package's tests: src/meta-eval/judge-gate.test.ts:2 |
+| `judgeGateDecision` | planned | doc: docs/concepts.md |
+| `JudgeGateRefusedError` | planned | doc: docs/concepts.md |
 | `judgeSentinelReport` | production | creative-agent:eval/lib/judge-sentinel.ts |
+| `measureJudgeAgreement` | planned | doc: docs/concepts.md |
 | `multiclassBrierScore` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
 | `OutcomeStoreError` | planned | doc: docs/outcome-validity.md |
 | `perturbEvidence` | planned | doc: docs/plants.md |
@@ -1134,11 +1157,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `plantByPerturbation` | planned | doc: docs/plants.md |
 | `positionalBias` | production | ph0ny:products/builder/api/src/eval/judge-bias.ts |
 | `rankedProbabilityScore` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
+| `registerCalibrationSet` | planned | doc: docs/concepts.md |
 | `rubricPredictiveValidity` | production | physim:apps/server/src/scripts/agent-eval/validate-rubrics.ts |
 | `seedPlants` | production | discovery-lab:experiments/e1-checker/score.mjs |
 | `selfPreference` | production | ph0ny:products/builder/api/src/eval/judge-bias.ts |
 | `snapshotFromAgreement` | production | physim:apps/server/src/scripts/agent-eval/judge-sentinel.ts |
 | `snapshotFromCalibration` | production | gtm-agent:eval/calibrate-judges.ts |
+| `snapshotFromJudgeAgreement` | planned | doc: docs/concepts.md |
 | `snapshotFromSentinelSet` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `validateSentinelSnapshot` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `verbosityBias` | production | blueprint-agent:scripts/experiments/calibration/judge-agreement.ts |
@@ -1341,7 +1366,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./rollout`
 
-68 value exports — 45 production, 13 planned, 10 none.
+69 value exports — 45 production, 13 planned, 11 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1354,13 +1379,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `ATIF_SCHEMA_VERSION` | none | only this package's tests: src/rollout/interchange/harbor.test.ts:6 |
 | `buildDatasetCard` | production | this package: src/rollout/release/hf-dataset.ts:25 |
 | `buildHfDataset` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
-| `claudeProjectSlug` | none | only this package's tests: src/rollout/readers/claude-jsonl.test.ts:5 |
+| `claudeProjectSlug` | none | only this package's tests: src/rollout/readers/claude-jsonl.test.ts:11 |
 | `DEFAULT_CLAUDE_PROJECTS_DIR` | planned | named in discovery-lab (bind not in the import graph) |
 | `DEFAULT_OPENCODE_DB` | planned | named in discovery-lab (bind not in the import graph) |
 | `defaultRolloutScrubber` | production | supervisor-lab:archive/bench/vertical-rollout-package.ts |
 | `emptyScrubCounts` | production | this package: src/rollout/release/hf-dataset.ts:34 |
 | `findClaudeTranscripts` | planned | doc: docs/rollout.md |
-| `findOpencodeSessionsByDirectory` | none | only this package's tests: src/rollout/readers/opencode-sqlite.test.ts:6 |
+| `findOpencodeSessionsByDirectory` | none | only this package's tests: src/rollout/readers/opencode-sqlite.test.ts:7 |
 | `FORMAT_FILES` | production | this package: src/rollout/release/hf-dataset.ts:25 |
 | `FORMAT_GATE_DISPOSITION` | production | this package: src/rollout/release/card.ts:12 |
 | `fromHarborTrajectory` | planned | doc: docs/rollout.md |
@@ -1379,11 +1404,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `mintRolloutRows` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
 | `observedScore` | production | this package: src/rl/reward-hacking.ts:40 |
 | `observedSplitScore` | production | starter-foundry:src/lib/held-out-gate.ts |
-| `openOpencodeDb` | production | super-agent:evals/conversation-application.ts |
 | `parseClaudeTranscript` | planned | doc: docs/rollout.md |
 | `parseRolloutReleaseArgs` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
 | `planPushCommand` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
 | `readClaudeTranscript` | production | blueprint-agent:scripts/experiments/lib/vb-climb-coder.ts |
+| `readOpencodeSession` | none | only this package's tests: src/rollout/readers/opencode-sqlite.test.ts:7 |
 | `readOpencodeSessionMessages` | production | super-agent:evals/conversation-application.ts |
 | `readRolloutJournal` | none | only this package's tests: src/rollout/ledger.test.ts:6 |
 | `readRolloutLedger` | production | this package: src/rollout/release/hf-dataset.ts:23 |
@@ -1410,6 +1435,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `toVerifiersRolloutOutputs` | production | this package: src/rollout/release/hf-dataset.ts:22 |
 | `trainingReward` | production | supervisor-lab:archive/bench/vertical-gate-proof.ts |
 | `trainingScore` | production | this package: src/eval-trace-store.ts:20 |
+| `transcriptFromSession` | production | this package: src/supervisor-run/claude-code-reader.ts:67 |
 | `unmintableReasons` | production | supervisor-lab:archive/bench/mint-audit.ts |
 | `validateRolloutLine` | production | this package: src/supervisor-run/integrity-tree.ts:1 |
 | `writeRolloutLedger` | production | blueprint-agent:scripts/experiments/lib/vb-climb.ts |
@@ -1507,12 +1533,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./systemone`
 
-18 value exports — 10 production, 8 planned, 0 none.
+20 value exports — 10 production, 10 planned, 0 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `asAnalyst` | production | this package: src/systemone.ts:5 |
 | `asJudge` | production | this package: src/systemone.ts:5 |
+| `assessSystemOneDomainMatch` | planned | doc: docs/systemone-integrations.md |
 | `assessSystemOneReview` | planned | doc: docs/changes/systemone-provider-neutral.md |
 | `createEvaluator` | production | blueprint-agent:scripts/experiments/app-grade/drive.ts |
 | `normalizedSystemOneScore` | planned | doc: docs/changes/systemone-provider-neutral.md |
@@ -1521,6 +1548,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `parseSystemOneRecordedRequest` | planned | example: examples/systemone-replay.ts:7 |
 | `parseSystemOneRequest` | production | discovery-lab:experiments/diu-campaign-v1/jev-review.mjs |
 | `parseSystemOneResult` | production | discovery-lab:experiments/decision-bench-v1/score.mjs |
+| `prepareSystemOneDomainMatch` | planned | doc: docs/systemone-integrations.md |
 | `prepareSystemOneReview` | production | this package: src/rl/claim-integrity.ts:47 |
 | `systemOneAnalyst` | planned | example: examples/systemone-behavior-review.ts:3 |
 | `systemOneConfidence` | planned | doc: docs/changes/systemone-provider-neutral.md |
@@ -1716,7 +1744,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `emptyRedactionReport` | production | agent-runtime:src/candidate-execution/protected-redaction.ts |
 | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
 | `extractOtlpAttributes` | production | this package: src/trace-analyst/store-otlp.ts:40 |
-| `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:12 |
+| `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:13 |
 | `extractUsageFromResponse` | none | only this package's tests: src/trace/extract-usage.test.ts:2 |
 | `extractUsageFromSse` | production | this package: src/trace/capture-fetch.ts:8 |
 | `FAILURE_CLASSES` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |

package/docs/systemone-integrations.md

@@ -16,6 +16,7 @@ asJudge and asAnalyst adapt the same operation to existing consumers.
 | Next verification | Choose a test, retrieval or review that resolves uncertainty | Existing graph checkpoints and awaited boundaries, not new permissions. |
 | Candidate selection | Choose among generated plans or artifacts | Existing matrix/graph, exact checks first, semantic assessment second. |
 | Configuration experiments | Compare questions, context, models and thresholds | examples/systemone-decision-benchmark.ts using runAgentMatrix and cost receipts. |
+| Domain classification | Match bounded evidence to a product intent and caller-owned categories | prepareSystemOneDomainMatch plus assessSystemOneDomainMatch; positive matches require a qualified category and exact source. |
 
 These are compositions, not ten new frameworks. Product triage and the benchmark recipe are concrete
 adoption work; other rows reuse existing APIs or identify application policies to configure. An API

package/docs/systemone.md

@@ -62,6 +62,40 @@ add their own limits: Clef requires non-null `instructions`, 1–64 questions wi
 exact answer names and choice-label unions. Runtime JSON must be validated; its
 labels cannot become compile-time literals automatically.
 
+## DomainMatch
+
+`prepareSystemOneDomainMatch` builds a frozen three-question classification for products that need
+relevance, a caller-owned category, and an exact source segment. `assessSystemOneDomainMatch`
+revalidates the retained answer and returns `match`, `no_match`, or `uncertain` without another
+model call. It does not choose a domain taxonomy, threshold, credential, endpoint, or effect.
+
+```ts
+const prepared = prepareSystemOneDomainMatch({
+  version: 'health-v1',
+  model: selectedModel,
+  intent: 'Find personal health correspondence, not general wellness marketing.',
+  categories: { lab_result: 'A medical laboratory result', appointment: 'An appointment' },
+  evidence: [{ id: 'email-1', text: emailText }],
+  coverage: 'complete',
+  thresholds: {
+    matchAtLeast: 0.8,
+    noMatchAtLeast: 0.8,
+    categoryAtLeast: 0.7,
+    sourceAtLeast: 0.7,
+    minimumMargin: 0.2,
+  },
+})
+const observation = await evaluate(prepared.request, { signal, idempotencyKey })
+const decision = assessSystemOneDomainMatch(prepared, observation.value)
+```
+
+A positive match requires the match, category, and source questions to pass their thresholds and
+margins. Missing evidence stays unresolved; partial evidence can support a match but cannot refute
+one. The report retains native probabilities and an exact host-supplied evidence segment. Those
+probabilities are not calibrated domain confidence, and a result never authorizes storage, hiding,
+sending, deletion, or another effect. Re-assessing the same prepared input and retained answer is
+an offline replay, not new inference.
+
 ## Providers, rounding and confidence
 
 The wire format is the same for every provider; how each reports its numbers is not. A

package/docs/verified-labels-flywheel.md

@@ -22,7 +22,7 @@ Derived from what the run2 replay batch actually consumed (its enumeration exclu
 | Claude Code transcripts `~/.claude/projects` | 474 projects, 7,579 session JSONLs, 4.6 GB | no image; `cwd` + `gitBranch` + harness `version` per message | yes — full tool calls + results | **no** — Bash `toolUseResult` records `stdout`/`stderr`/`interrupted` only, no exit code field | no (host env unpinned, no rc) |
 | Codex sessions `~/.codex/sessions` | 4,332 rollout files, 113 GB | no image; `session_meta` has `cwd` + git `commit_hash`/`branch`/`repository_url` + `cli_version` | yes | shell events carry exit codes in payloads (format varies by version) | no (host env unpinned) |
 | traces CLI normalized envelope (`~/code/traces`, 18 harness adapters: claude, codex, amp, gemini, opencode, pi, copilot, factory, forge, qwen, …) | imports the two stores above | `cwd` filter exists; **no image/sandbox field in the envelope** | yes | adapter-dependent | no — the schema itself cannot express environment identity |
-| Sandbox sessions (agent-dev-container `PersistedSession`) | remote fleet; none stored on this host | runtime knows the image — `runtime.ready` event carries `image?` + `sandboxId` + backend — but `PersistedSession` persists only `workspaceRoot` + free-form `metadata`; `image?` is optional even on the event | yes (message store) | via tool parts, not normalized | **almost** — the image is in hand at runtime and dropped at persistence time |
+| Sandbox sessions (agent-container `PersistedSession`) | remote fleet; none stored on this host | runtime knows the image — `runtime.ready` event carries `image?` + `sandboxId` + backend — but `PersistedSession` persists only `workspaceRoot` + free-form `metadata`; `image?` is optional even on the event | yes (message store) | via tool parts, not normalized | **almost** — the image is in hand at runtime and dropped at persistence time |
 | mini-SWE / CodeTraceBench benchmark trajectories (`~/bench-cache/ctb-20260801`) | 133 labeled, 22 replayable | yes — `mswebench/*` images + cwd | yes | yes — `<returncode>N</returncode>` in every observation | **yes — the only eligible class; run2 proved 16/22 reproduce** |
 
 Conclusion: today only benchmark-imported trajectories are replay-eligible.
@@ -31,7 +31,7 @@ The sandbox class is one persistence field away from eligibility — the runtime
 
 ## Phase-2 capture changes (ranked by unlock per line of code)
 
-1. **Persist the sandbox image at session start** (agent-dev-container): copy `runtime.ready`'s `image` (as a digest, not a tag) + `sandboxId` into `PersistedSession` as first-class fields, and make `image` required on the event.
+1. **Persist the sandbox image at session start** (agent-container): copy `runtime.ready`'s `image` (as a digest, not a tag) + `sandboxId` into `PersistedSession` as first-class fields, and make `image` required on the event.
    This single change makes every future fleet sandbox session satisfy requirements 1–2 — the highest-leverage line in the flywheel.
 2. **Add environment identity to the traces envelope** (traces repo): an optional `environment: { image?, imageDigest?, cwd, gitCommit? }` block on the normalized session, populated by adapters where known.
    Without it, eligible sandbox sessions lose their eligibility at import time.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.213.0",
+  "version": "0.215.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {