@tangle-network/agent-eval 0.207.3 → 0.208.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +21 -0
- package/dist/adapters/http.d.ts +2 -2
- package/dist/{agent-profile-EpO0HURy.d.ts → agent-profile-CEhxR_I3.d.ts} +4 -4
- package/dist/{agent-profile-EpO0HURy.d.ts.map → agent-profile-CEhxR_I3.d.ts.map} +1 -1
- package/dist/analyst/index.d.ts +12 -12
- package/dist/analyst/index.js +5 -5
- package/dist/{analyze-runs-Q74o4Hfj.d.ts → analyze-runs-CTJyUplR.d.ts} +2 -2
- package/dist/{analyze-runs-Q74o4Hfj.d.ts.map → analyze-runs-CTJyUplR.d.ts.map} +1 -1
- package/dist/{benchmark-command-DtP94cOB.js → benchmark-command-BC265T1r.js} +6 -6
- package/dist/{benchmark-command-DtP94cOB.js.map → benchmark-command-BC265T1r.js.map} +1 -1
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +3 -3
- package/dist/campaign/index.d.ts +7 -7
- package/dist/campaign/index.js +7 -7
- package/dist/{campaign-BL591dWw.js → campaign-C5pjR-Qn.js} +8 -8
- package/dist/{campaign-BL591dWw.js.map → campaign-C5pjR-Qn.js.map} +1 -1
- package/dist/{chat-client-5LLl4Ctl.js → chat-client-CydfmLdO.js} +3 -2
- package/dist/chat-client-CydfmLdO.js.map +1 -0
- package/dist/{chat-json-call-Digk-pfF.js → chat-json-call-BJJdJ2uj.js} +2 -2
- package/dist/{chat-json-call-Digk-pfF.js.map → chat-json-call-BJJdJ2uj.js.map} +1 -1
- package/dist/cli.js +6 -6
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +6 -6
- package/dist/{default-registry-BthquIoC.js → default-registry-DX5R7_n9.js} +2 -2
- package/dist/{default-registry-BthquIoC.js.map → default-registry-DX5R7_n9.js.map} +1 -1
- package/dist/{default-registry-BHEfZHQd.d.ts → default-registry-DZFWY2_E.d.ts} +6 -6
- package/dist/{default-registry-BHEfZHQd.d.ts.map → default-registry-DZFWY2_E.d.ts.map} +1 -1
- package/dist/{define-agent-eval-CmItPfIq.js → define-agent-eval-BjKXcDQp.js} +3 -3
- package/dist/{define-agent-eval-CmItPfIq.js.map → define-agent-eval-BjKXcDQp.js.map} +1 -1
- package/dist/{define-agent-eval-B2YV-RDE.d.ts → define-agent-eval-C8zBSbsc.d.ts} +7 -7
- package/dist/{define-agent-eval-B2YV-RDE.d.ts.map → define-agent-eval-C8zBSbsc.d.ts.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -2
- package/dist/{dspy-rlm-engine-DCQKNQMn.js → dspy-rlm-engine-sHwdSxK3.js} +2 -2
- package/dist/{dspy-rlm-engine-DCQKNQMn.js.map → dspy-rlm-engine-sHwdSxK3.js.map} +1 -1
- package/dist/{engine-F_PvwesR.d.ts → engine-DProXJ7A.d.ts} +4 -4
- package/dist/{engine-F_PvwesR.d.ts.map → engine-DProXJ7A.d.ts.map} +1 -1
- package/dist/evaluation.d.ts +2 -2
- package/dist/{exact-types-BBMMYk3g.d.ts → exact-types-Cq6xXNVR.d.ts} +2 -2
- package/dist/{exact-types-BBMMYk3g.d.ts.map → exact-types-Cq6xXNVR.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +1 -1
- package/dist/{external-optimizer-process-CIV4EqiT.js → external-optimizer-process-D2Txd-7D.js} +2 -2
- package/dist/{external-optimizer-process-CIV4EqiT.js.map → external-optimizer-process-D2Txd-7D.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-BmKtH3T6.js → external-optimizer-subprocess-C0EsxEbI.js} +12 -4
- package/dist/{external-optimizer-subprocess-BmKtH3T6.js.map → external-optimizer-subprocess-C0EsxEbI.js.map} +1 -1
- package/dist/{feedback-trajectory-C6NJxXEa.d.ts → feedback-trajectory-C6Z8PRoF.d.ts} +3 -3
- package/dist/{feedback-trajectory-C6NJxXEa.d.ts.map → feedback-trajectory-C6Z8PRoF.d.ts.map} +1 -1
- package/dist/{index-CojsA_EE.d.ts → index-Bzto04CY.d.ts} +7 -7
- package/dist/{index-CojsA_EE.d.ts.map → index-Bzto04CY.d.ts.map} +1 -1
- package/dist/{index-DzYX3WBL.d.ts → index-DkucR0KJ.d.ts} +7 -7
- package/dist/{index-DzYX3WBL.d.ts.map → index-DkucR0KJ.d.ts.map} +1 -1
- package/dist/{index-DVDiJIhi.d.ts → index-nwNoS582.d.ts} +8 -8
- package/dist/{index-DVDiJIhi.d.ts.map → index-nwNoS582.d.ts.map} +1 -1
- package/dist/index.d.ts +19 -19
- package/dist/index.js +10 -10
- package/dist/{integrity-BWO6RPxv.d.ts → integrity-zloavsM_.d.ts} +2 -2
- package/dist/{integrity-BWO6RPxv.d.ts.map → integrity-zloavsM_.d.ts.map} +1 -1
- package/dist/{llm-client-DmCNzrc9.js → llm-client-v968tWw8.js} +76 -29
- package/dist/llm-client-v968tWw8.js.map +1 -0
- package/dist/{llm-judge-Fc3UIcPq.js → llm-judge-HLWASwUJ.js} +5 -5
- package/dist/{llm-judge-Fc3UIcPq.js.map → llm-judge-HLWASwUJ.js.map} +1 -1
- package/dist/{matrix-W1lbSx72.d.ts → matrix-Cqkk7eYI.d.ts} +2 -2
- package/dist/{matrix-W1lbSx72.d.ts.map → matrix-Cqkk7eYI.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +1 -1
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/openapi.json +1 -1
- package/dist/{prime-protocol-IoN4Qb6c.d.ts → prime-protocol-Csr9kcOM.d.ts} +2 -2
- package/dist/{prime-protocol-IoN4Qb6c.d.ts.map → prime-protocol-Csr9kcOM.d.ts.map} +1 -1
- package/dist/{produced-state-CywjstcW.js → produced-state-Bzlh09oj.js} +3 -3
- package/dist/{produced-state-CywjstcW.js.map → produced-state-Bzlh09oj.js.map} +1 -1
- package/dist/{registry-CT-hMSkR.d.ts → registry-DMkmhBQ5.d.ts} +4 -4
- package/dist/{registry-CT-hMSkR.d.ts.map → registry-DMkmhBQ5.d.ts.map} +1 -1
- package/dist/{researcher-zTpxNJBy.d.ts → researcher-CZFZjj-u.d.ts} +3 -3
- package/dist/{researcher-zTpxNJBy.d.ts.map → researcher-CZFZjj-u.d.ts.map} +1 -1
- package/dist/rl.d.ts +4 -4
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-mzeNuzr8.js → search-kernel-CIie6xig.js} +44 -2
- package/dist/search-kernel-CIie6xig.js.map +1 -0
- package/dist/{search-kernel-CZ8KJQRw.d.ts → search-kernel-uKdPVRAe.d.ts} +18 -3
- package/dist/search-kernel-uKdPVRAe.d.ts.map +1 -0
- package/dist/{search-summary-CDURlgZR.js → search-summary-BV5uehLd.js} +2 -2
- package/dist/{search-summary-CDURlgZR.js.map → search-summary-BV5uehLd.js.map} +1 -1
- package/dist/{semantic-concept-judge-BbiYuv7U.js → semantic-concept-judge-D1wH-YKc.js} +4 -4
- package/dist/{semantic-concept-judge-BbiYuv7U.js.map → semantic-concept-judge-D1wH-YKc.js.map} +1 -1
- package/dist/{series-convergence-DLy0bQMV.d.ts → series-convergence-hEfKdoi-.d.ts} +2 -2
- package/dist/{series-convergence-DLy0bQMV.d.ts.map → series-convergence-hEfKdoi-.d.ts.map} +1 -1
- package/dist/{server-CoBZO1fj.js → server-BZOt7eNC.js} +2 -2
- package/dist/{server-CoBZO1fj.js.map → server-BZOt7eNC.js.map} +1 -1
- package/dist/{skillopt-optimization-method-BSgM_cbI.js → skillopt-optimization-method-Dcnh5Pvr.js} +5 -5
- package/dist/{skillopt-optimization-method-BSgM_cbI.js.map → skillopt-optimization-method-Dcnh5Pvr.js.map} +1 -1
- package/dist/{statistical-heldout-COfgpWah.d.ts → statistical-heldout-DFKtp-Qm.d.ts} +2 -2
- package/dist/{statistical-heldout-COfgpWah.d.ts.map → statistical-heldout-DFKtp-Qm.d.ts.map} +1 -1
- package/dist/{store-tool-spans-BYIarVrG.d.ts → store-tool-spans-9YJNMP-z.d.ts} +5 -5
- package/dist/{store-tool-spans-BYIarVrG.d.ts.map → store-tool-spans-9YJNMP-z.d.ts.map} +1 -1
- package/dist/{systemone-review-DGTKkLMG.d.ts → systemone-review-Bt4JcxMc.d.ts} +2 -2
- package/dist/{systemone-review-DGTKkLMG.d.ts.map → systemone-review-Bt4JcxMc.d.ts.map} +1 -1
- package/dist/systemone.d.ts +3 -3
- package/dist/{tool-groups-B7_jUPHp.d.ts → tool-groups-j19pmOfP.d.ts} +3 -3
- package/dist/tool-groups-j19pmOfP.d.ts.map +1 -0
- package/dist/{trace-questions-Dd3AMf-U.d.ts → trace-questions-dRvmsbTk.d.ts} +3 -3
- package/dist/{trace-questions-Dd3AMf-U.d.ts.map → trace-questions-dRvmsbTk.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +1 -1
- package/dist/traces.d.ts +5 -5
- package/dist/{tree-CN8mlzUO.js → tree-CJOXbVcv.js} +2 -2
- package/dist/{tree-CN8mlzUO.js.map → tree-CJOXbVcv.js.map} +1 -1
- package/dist/{types-DZQpUJse.d.ts → types-BlSBUNRd.d.ts} +2 -2
- package/dist/{types-DZQpUJse.d.ts.map → types-BlSBUNRd.d.ts.map} +1 -1
- package/dist/{types-ZUy5HGY5.d.ts → types-CFCUZk0B.d.ts} +3 -3
- package/dist/{types-ZUy5HGY5.d.ts.map → types-CFCUZk0B.d.ts.map} +1 -1
- package/dist/{types-6VEehmEg.d.ts → types-DAPpAkd4.d.ts} +2 -2
- package/dist/{types-6VEehmEg.d.ts.map → types-DAPpAkd4.d.ts.map} +1 -1
- package/dist/{types-DLxe96rp.d.ts → types-Lub7o6bN.d.ts} +10 -3
- package/dist/{types-DLxe96rp.d.ts.map → types-Lub7o6bN.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +2 -2
- package/dist/wire/index.js +1 -1
- package/docs/changes/llm-call-pacing.md +56 -0
- package/docs/quickstart-external.md +268 -0
- package/docs/search-ledger.md +4 -1
- package/package.json +1 -1
- package/dist/chat-client-5LLl4Ctl.js.map +0 -1
- package/dist/llm-client-DmCNzrc9.js.map +0 -1
- package/dist/search-kernel-CZ8KJQRw.d.ts.map +0 -1
- package/dist/search-kernel-mzeNuzr8.js.map +0 -1
- package/dist/tool-groups-B7_jUPHp.d.ts.map +0 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,27 @@ All notable changes to `@tangle-network/agent-eval` and its sibling `agent-eval-
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
+
## [0.208.2] — 2026-10-06
|
|
8
|
+
|
|
9
|
+
- fix(analyst): re-pin the benchmark implementation digest after the bridge environment fix (#946)
|
|
10
|
+
|
|
11
|
+
## [0.208.1] — 2026-10-06
|
|
12
|
+
|
|
13
|
+
- fix(external-optimizer): give the bridge its interpreter's loader path, and name a killing signal (#944)
|
|
14
|
+
|
|
15
|
+
## [0.208.0] — 2026-10-06
|
|
16
|
+
|
|
17
|
+
- feat(search): searchClaimDecision returns the paired decision a claim made for a tested finalist (#942)
|
|
18
|
+
- test: give corpus and dataset tests unique temp directories (#941)
|
|
19
|
+
- ci: run workflows on self-hosted runners; publish only new versions from hosted (#940)
|
|
20
|
+
- docs: complete external agent campaign quickstart and RL import coverage (#939)
|
|
21
|
+
|
|
22
|
+
## [0.207.4] — 2026-10-05
|
|
23
|
+
|
|
24
|
+
- fix(llm): honor full retry delays and pace campaign calls (#934)
|
|
25
|
+
- fix(llm): report a caller abort that lands while the final answer is recorded (#936)
|
|
26
|
+
- fix(llm): end a call with the server's answer when the deadline cannot cover its retry wait (#935)
|
|
27
|
+
|
|
7
28
|
## [0.207.3] — 2026-10-04
|
|
8
29
|
|
|
9
30
|
- fix(supervisor-run): count a receipt as a native session only when its copy is complete and holds a session file (#932)
|
package/dist/adapters/http.d.ts
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { m as CostReceipt } from "../cost-ledger-DbQdN3nO.js";
|
|
2
|
-
import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-
|
|
3
|
-
import "../index-
|
|
2
|
+
import { R as Scenario, d as DispatchContext, f as DispatchFn } from "../types-CFCUZk0B.js";
|
|
3
|
+
import "../index-nwNoS582.js";
|
|
4
4
|
//#region src/adapters/http.d.ts
|
|
5
5
|
export interface HttpDispatchOptions<TScenario extends Scenario, _TArtifact> {
|
|
6
6
|
/** Static endpoint URL. Mutually exclusive with `resolveUrl`. */
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
import { b as CustomTokenPricing, g as CostReceiptInput } from "./cost-ledger-DbQdN3nO.js";
|
|
2
|
-
import { O as TraceAnalysisStore, c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef } from "./types-
|
|
3
|
-
import { C as ChatResponse, S as ChatRequest } from "./types-
|
|
4
|
-
import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-
|
|
2
|
+
import { O as TraceAnalysisStore, c as AnalystRunInputs, f as AnalystUsageReceipt, i as AnalystFinding, p as EvidenceRef } from "./types-DAPpAkd4.js";
|
|
3
|
+
import { C as ChatResponse, S as ChatRequest } from "./types-Lub7o6bN.js";
|
|
4
|
+
import { c as RegistryRunOpts, n as AnalystRegistry } from "./registry-DMkmhBQ5.js";
|
|
5
5
|
import { AgentProfile, AgentProfile as AgentProfile$1, HarnessType, HarnessType as HarnessType$1 } from "@tangle-network/agent-interface";
|
|
6
6
|
//#region src/campaign/external-optimizer-contracts.d.ts
|
|
7
7
|
interface ExternalOptimizerProcessLimits {
|
|
@@ -485,4 +485,4 @@ declare function agentProfileId(profile: AgentProfile): string;
|
|
|
485
485
|
declare function agentProfileHash(profile: AgentProfile): string;
|
|
486
486
|
//#endregion
|
|
487
487
|
export { runAnalystBenchmark as A, ExternalOptimizerModelBudget as B, AnalystEvidenceResolutionError as C, AnalystLatencyDistribution as D, AnalystIssueExpectation as E, ExternalOptimizerCallbackLimits as F, ExternalOptimizerProcessLimits as G, ExternalOptimizerModelCallRequest as H, ExternalOptimizerChatRequest as I, ExternalOptimizerWireCounts as J, ExternalOptimizerResumeMode as K, ExternalOptimizerEndpointFormat as L, scoreAnalystFindings as M, DEFAULT_EXTERNAL_OPTIMIZER_CALLBACK_LIMITS as N, RunAnalystBenchmarkOptions as O, DEFAULT_EXTERNAL_OPTIMIZER_PROCESS_LIMITS as P, resolveExternalOptimizerProcessLimits as Q, ExternalOptimizerEvaluationObservation as R, AnalystEvidenceResolution as S, AnalystFindingScore as T, ExternalOptimizerModelCallResult as U, ExternalOptimizerModelCall as V, ExternalOptimizerModelExecutionObservation as W, ExternalTextEvaluationRequest as X, ExternalTextCandidate as Y, resolveExternalOptimizerCallbackLimits as Z, 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, traceStoreEvidenceResolver as j, registryBenchmarkRunner as k, harnessAxisOf as l, AnalystBenchmarkLabelState as m, CODING_HARNESSES as n, agentProfileHash as o, AnalystBenchmarkError as p, ExternalOptimizerRunnerCommand as q, HARNESS_NATIVE_MODEL as r, agentProfileId as s, AgentProfile$1 as t, AnalystBenchmarkCase as u, AnalystBenchmarkResult as v, AnalystEvidenceResolver as w, AnalystEvidenceExpectation as x, AnalystBenchmarkRunner as y, ExternalOptimizerEvaluationRefusalReason as z };
|
|
488
|
-
//# sourceMappingURL=agent-profile-
|
|
488
|
+
//# sourceMappingURL=agent-profile-CEhxR_I3.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"agent-profile-
|
|
1
|
+
{"version":3,"file":"agent-profile-CEhxR_I3.d.ts","names":["_$___cost_ledger0.CostReceiptInput"],"sources":["../src/campaign/external-optimizer-contracts.ts","../src/analyst/benchmark-scoring.ts","../src/analyst/benchmark.ts","../src/agent-profile.ts"],"mappings":";;;;;;UAWiB;;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;;iBAUc,sCACd,OAAO,QAAQ,6CACf,iBACC;iBAmBa,uCACd,OAAO,QAAQ,8CACf,iBACC;KAkBE,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;;;;iBCtQc,qBACd,UAAU,KAAK,oEACf,mBAAmB,mBAClB;;;UCIc;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;iBAyDK,wBAAwB;EACtC;EACA,UAAU;EACV,aAAa,KAAK;;EAElB;IACE,uBAAuB;;;;;;;;;;cCpUd,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
CHANGED
|
@@ -1,16 +1,16 @@
|
|
|
1
1
|
import { b as CustomTokenPricing, c as CostLedgerHandle } from "../cost-ledger-DbQdN3nO.js";
|
|
2
|
-
import { B as TraceAnalystSpan, O as TraceAnalysisStore, _ as ProposalFinding, a as AnalystInputKind, b as makeFinding, c as AnalystRunInputs, d as AnalystSeverity, f as AnalystUsageReceipt, g as ExecutionProbeRequest, h as ExecutionProbeOutcome, i as AnalystFinding, l as AnalystRunResult, m as ExecutionProbe, n as AnalystContext, o as AnalystRequirements, p as EvidenceRef, r as AnalystCost, s as AnalystRunEvent, t as Analyst, u as AnalystRunSummary, v as ProposalFindingOrigin, x as makeProposalFinding, y as computeFindingId } from "../types-
|
|
3
|
-
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-
|
|
4
|
-
import { A as runAnalystBenchmark, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, M as scoreAnalystFindings, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, V as ExternalOptimizerModelCall, W as ExternalOptimizerModelExecutionObservation, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, j as traceStoreEvidenceResolver, k as registryBenchmarkRunner, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, q as ExternalOptimizerRunnerCommand, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner } from "../agent-profile-
|
|
5
|
-
import { a as ExactAnalystRunPolicySnapshot, c as ExactAnalystSnapshot, d as ExactExecutionComponentSnapshot, i as ExactAnalystRunEvent, l as ExactCapableAnalyst, n as ExactAnalystExecutionPlanSnapshot, o as ExactAnalystRunResult, r as ExactAnalystRunCompletion, s as ExactAnalystRunSummary, t as ExactAnalystBudgetSnapshot, u as ExactExecutionComponentIdentity } from "../exact-types-
|
|
6
|
-
import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-
|
|
7
|
-
import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-
|
|
8
|
-
import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-
|
|
9
|
-
import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-
|
|
10
|
-
import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-
|
|
11
|
-
import { A as ReplyRowDecoded, C as primeProtocolSha256, D as DecodedReply, E as runPrimeExchange, M as decodeReplyRows, O as ReplyContract, S as normalizePrimeUsage, T as projectPrimeTrajectory, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as extractPrimeJsonObject, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, j as ReplyRowRejection, k as ReplyEnvelope, l as PrimeRawUsage, m as PrimeRowDecoded, n as PrimeExchangeOutcome, o as PrimeProjectionSource, p as PrimeReplyContract, r as PrimeFailure, s as PrimePromptSpec, t as PrimeExchangeOptions, u as PrimeRejectedRow, v as buildPrimeRepairPrompt, w as primeReplyDefect, x as mergePrimeRawUsage, y as emptyPrimeRawUsage } from "../prime-protocol-
|
|
2
|
+
import { B as TraceAnalystSpan, O as TraceAnalysisStore, _ as ProposalFinding, a as AnalystInputKind, b as makeFinding, c as AnalystRunInputs, d as AnalystSeverity, f as AnalystUsageReceipt, g as ExecutionProbeRequest, h as ExecutionProbeOutcome, i as AnalystFinding, l as AnalystRunResult, m as ExecutionProbe, n as AnalystContext, o as AnalystRequirements, p as EvidenceRef, r as AnalystCost, s as AnalystRunEvent, t as Analyst, u as AnalystRunSummary, v as ProposalFindingOrigin, x as makeProposalFinding, y as computeFindingId } from "../types-DAPpAkd4.js";
|
|
3
|
+
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-Lub7o6bN.js";
|
|
4
|
+
import { A as runAnalystBenchmark, C as AnalystEvidenceResolutionError, D as AnalystLatencyDistribution, E as AnalystIssueExpectation, M as scoreAnalystFindings, O as RunAnalystBenchmarkOptions, S as AnalystEvidenceResolution, T as AnalystFindingScore, V as ExternalOptimizerModelCall, W as ExternalOptimizerModelExecutionObservation, _ as AnalystBenchmarkProvenance, b as AnalystBenchmarkSummary, d as AnalystBenchmarkDatasetRef, f as AnalystBenchmarkDescriptor, g as AnalystBenchmarkOutput, h as AnalystBenchmarkObservation, j as traceStoreEvidenceResolver, k as registryBenchmarkRunner, m as AnalystBenchmarkLabelState, p as AnalystBenchmarkError, q as ExternalOptimizerRunnerCommand, t as AgentProfile, u as AnalystBenchmarkCase, v as AnalystBenchmarkResult, w as AnalystEvidenceResolver, x as AnalystEvidenceExpectation, y as AnalystBenchmarkRunner } from "../agent-profile-CEhxR_I3.js";
|
|
5
|
+
import { a as ExactAnalystRunPolicySnapshot, c as ExactAnalystSnapshot, d as ExactExecutionComponentSnapshot, i as ExactAnalystRunEvent, l as ExactCapableAnalyst, n as ExactAnalystExecutionPlanSnapshot, o as ExactAnalystRunResult, r as ExactAnalystRunCompletion, s as ExactAnalystRunSummary, t as ExactAnalystBudgetSnapshot, u as ExactExecutionComponentIdentity } from "../exact-types-Cq6xXNVR.js";
|
|
6
|
+
import { a as ExactAnalystBudgetPolicy, c as RegistryRunOpts, i as BudgetPolicy, n as AnalystRegistry, o as ExactAnalystRunExecutionError, r as AnalystRegistryOptions, s as ExactRegistryRunOpts, t as AnalystHooks } from "../registry-DMkmhBQ5.js";
|
|
7
|
+
import { a as createTraceAnalyst, c as BehavioralAnalystOptions, i as TraceAnalystDefinition, l as behavioralAnalyst, n as buildDefaultAnalystRegistry, o as renderPriorFindings, r as CreateTraceAnalystOptions, s as runTraceAnalyst, t as DefaultAnalystRegistryOptions, u as deriveEfficiencyFindings } from "../default-registry-DZFWY2_E.js";
|
|
8
|
+
import { a as TraceAnalystLimits, c as RawAnalystEvidence, d as evidenceRefsFromRawFinding, f as parseRawFinding, i as TraceAnalysisEngineResult, l as RawAnalystFinding, n as TraceAnalysisEngine, o as resolveTraceAnalystLimits, r as TraceAnalysisEngineRequest, s as RAW_FINDING_SCHEMA_PROMPT, t as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, u as RawAnalystFindingSchema } from "../engine-DProXJ7A.js";
|
|
9
|
+
import { n as buildTraceToolsForGroup, t as TraceToolGroupName } from "../tool-groups-j19pmOfP.js";
|
|
10
|
+
import { A as SemanticConceptJudgeInput, C as DspyRlmTraceEngineOptions, E as createChatTraceEngine, S as renderFindingSubject, T as ChatTraceEngineOptions, _ as FindingSubject, a as FAILURE_MODE_KIND_SPEC, b as findingSubjectGrammarPromptFor, c as emitControlIntegrityFindings, d as FindingsStore, f as PersistedFinding, g as FINDING_SUBJECT_SYNTAX, h as FINDING_SUBJECT_KINDS, i as IMPROVEMENT_KIND_SPEC, j as SemanticConceptJudgeOptions, l as DiffPolicy, m as diffFindings, n as KNOWLEDGE_POISONING_KIND_SPEC, o as CONTROL_INTEGRITY_ANALYST, p as defaultIsMaterial, r as KNOWLEDGE_GAP_KIND_SPEC, s as ControlIntegrityAnalyst, t as DEFAULT_TRACE_ANALYST_KINDS, u as FindingsDiff, v as FindingSubjectKind, w as createDspyRlmTraceEngine, x as parseFindingSubject, y as KIND_EXPECTED_SUBJECTS } from "../index-DkucR0KJ.js";
|
|
11
|
+
import { A as ReplyRowDecoded, C as primeProtocolSha256, D as DecodedReply, E as runPrimeExchange, M as decodeReplyRows, O as ReplyContract, S as normalizePrimeUsage, T as projectPrimeTrajectory, _ as buildPrimePrompt, a as PrimeProjectionOutcome, b as extractPrimeJsonObject, c as PrimeProtocolIdentity, d as PrimeRepairPromptSpec, f as PrimeRepairState, g as analystUsageReceiptFromPrimeUsage, h as PrimeTurnRecord, i as PrimeProjectionDelivery, j as ReplyRowRejection, k as ReplyEnvelope, l as PrimeRawUsage, m as PrimeRowDecoded, n as PrimeExchangeOutcome, o as PrimeProjectionSource, p as PrimeReplyContract, r as PrimeFailure, s as PrimePromptSpec, t as PrimeExchangeOptions, u as PrimeRejectedRow, v as buildPrimeRepairPrompt, w as primeReplyDefect, x as mergePrimeRawUsage, y as emptyPrimeRawUsage } from "../prime-protocol-Csr9kcOM.js";
|
|
12
12
|
import { i as nodeHttpPrimeBridgeTransport, n as PrimeBridgeTransportRequest, r as PrimeBridgeTransportResult, t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
|
|
13
|
-
import { a as askTraceQuestions, i as VerifiedTraceFinding, n as TraceQuestionOutcome, o as citedSpansOnly, r as TraceQuestionSpec, t as AskTraceQuestionsOptions } from "../trace-questions-
|
|
13
|
+
import { a as askTraceQuestions, i as VerifiedTraceFinding, n as TraceQuestionOutcome, o as citedSpansOnly, r as TraceQuestionSpec, t as AskTraceQuestionsOptions } from "../trace-questions-dRvmsbTk.js";
|
|
14
14
|
import { z } from "zod";
|
|
15
15
|
//#region src/analyst/adapters.d.ts
|
|
16
16
|
interface SemanticConceptJudgeAdapterOpts {
|
|
@@ -1188,7 +1188,7 @@ export declare const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "f83f8df7818f921
|
|
|
1188
1188
|
export declare const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
|
|
1189
1189
|
export declare const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
|
|
1190
1190
|
export declare const ANALYST_BENCHMARK_IMPLEMENTATION_FILES: readonly string[];
|
|
1191
|
-
export declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "
|
|
1191
|
+
export declare const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "3a994853640a80394e766f6b1992e16a41a490b3ea834752e06223c590f84d65";
|
|
1192
1192
|
export declare function analystBenchmarkImplementationDigest(): string;
|
|
1193
1193
|
export declare function analystBenchmarkDependencyLockDigest(): string;
|
|
1194
1194
|
//#endregion
|
package/dist/analyst/index.js
CHANGED
|
@@ -2,13 +2,13 @@ import { i as CostLedger } from "../cost-ledger-_IbkejCF.js";
|
|
|
2
2
|
import { n as isProposalFinding, t as assertProposalFindings } from "../proposal-findings-CXblsskH.js";
|
|
3
3
|
import { B as FINDING_SUBJECT_KINDS, F as evidenceRefsFromRawFinding, G as renderFindingSubject, H as KIND_EXPECTED_SUBJECTS, I as parseRawFinding, K as DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS, L as parseTraceSpanEvidenceUri, N as RAW_FINDING_SCHEMA_PROMPT, P as RawAnalystFindingSchema, R as coerceJson, U as findingSubjectGrammarPromptFor, V as FINDING_SUBJECT_SYNTAX, W as parseFindingSubject, i as buildTraceToolsForGroup, n as renderPriorFindings, q as resolveTraceAnalystLimits, r as runTraceAnalyst, t as createTraceAnalyst, z as stripCodeFences } from "../kind-factory-Cn1lbsAd.js";
|
|
4
4
|
import { i as validateUsageSettlementTimeout, n as settleUsageReceiptFromCostLedger } from "../usage-receipt-Cx3xNeyB.js";
|
|
5
|
-
import { a as KNOWLEDGE_POISONING_KIND_SPEC, c as FAILURE_MODE_KIND_SPEC, d as emitControlIntegrityFindings, f as behavioralAnalyst, i as DEFAULT_TRACE_ANALYST_KINDS, l as CONTROL_INTEGRITY_ANALYST, n as AnalystRegistry, o as KNOWLEDGE_GAP_KIND_SPEC, p as deriveEfficiencyFindings, r as ExactAnalystRunExecutionError, s as IMPROVEMENT_KIND_SPEC, t as buildDefaultAnalystRegistry, u as ControlIntegrityAnalyst } from "../default-registry-
|
|
5
|
+
import { a as KNOWLEDGE_POISONING_KIND_SPEC, c as FAILURE_MODE_KIND_SPEC, d as emitControlIntegrityFindings, f as behavioralAnalyst, i as DEFAULT_TRACE_ANALYST_KINDS, l as CONTROL_INTEGRITY_ANALYST, n as AnalystRegistry, o as KNOWLEDGE_GAP_KIND_SPEC, p as deriveEfficiencyFindings, r as ExactAnalystRunExecutionError, s as IMPROVEMENT_KIND_SPEC, t as buildDefaultAnalystRegistry, u as ControlIntegrityAnalyst } from "../default-registry-DX5R7_n9.js";
|
|
6
6
|
import { i as makeProposalFinding, n as computeFindingId, r as makeFinding } from "../types-CW5b90JH.js";
|
|
7
|
-
import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-
|
|
8
|
-
import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, o as createChatTraceEngine, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-
|
|
9
|
-
import { t as createChatClient } from "../chat-client-
|
|
7
|
+
import { t as createDspyRlmTraceEngine } from "../dspy-rlm-engine-sHwdSxK3.js";
|
|
8
|
+
import { a as diffFindings, i as defaultIsMaterial, n as runSemanticConceptJudge, o as createChatTraceEngine, r as FindingsStore, t as SEMANTIC_CONCEPT_JUDGE_VERSION } from "../semantic-concept-judge-D1wH-YKc.js";
|
|
9
|
+
import { t as createChatClient } from "../chat-client-CydfmLdO.js";
|
|
10
10
|
import { a as scoreAnalystFindings, i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver, t as registryBenchmarkRunner } from "../benchmark-BywPeAUo.js";
|
|
11
|
-
import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-
|
|
11
|
+
import { $ as ANALYST_BENCHMARK_MANIFEST_FILE, A as readAnalystInstructionsOverride, B as parseVerificationOutcome, C as emptyPublicBenchmarkRunner, D as summarizeCodeTraceCalibration, E as renderCodeTraceCalibrationMarkdown, F as publicBenchmarkRlmInstructions, G as ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256, H as ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES, I as publicBenchmarkSystemPrompt, J as ANALYST_BENCHMARK_IMPLEMENTATION_SHA256, K as ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM, L as DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES, M as MAX_INCORRECT_BLOCKS, N as MAX_INCORRECT_BLOCK_STEPS, O as analystInstructionsOverrideFromText, P as publicBenchmarkProtocolSha256, Q as ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE, R as appendVerificationArtifactsToOtlp, S as adaptPublicBenchmarkFindings, T as readAnalystBenchmarkArtifact, U as ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256, V as ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM, W as ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256, X as analystBenchmarkImplementationDigest, Y as analystBenchmarkDependencyLockDigest, Z as ANALYST_BENCHMARK_COST_LEDGER_FILE, _ as publicDirectAnalystDefinition, a as primeCodeTraceAnalystDefinition, at as codeTraceBenchCase, b as analystDefinitionAsymmetries, c as preparePublicAnalystBenchmark, ct as agentRxPredictionsToFindings, d as selectPublicBenchmarkRows, dt as normalizeBenchmarkLabel, et as ANALYST_BENCHMARK_OBSERVATIONS_FILE, f as createPublicBenchmarkRlmRunner, g as createPublicBenchmarkDirectRunner, h as runReplVariableAnalystDefinition, i as primeAnalystProtocolSha256, it as summarizeAgentRxCalibration, j as CODE_TRACE_BENCH_ANALYST_PROMPT, k as effectiveAnalystProtocolSha256, l as publicBenchmarkDistributions, lt as normalizeAgentRxCategory, m as rlmEngineLimits, n as renderAnalystBenchmarkMarkdown, nt as AGENT_RX_UPSTREAM_REVISION, o as runInlineAnalystDefinition, ot as codeTracerPredictionsToFindings, p as publicRlmAnalystDefinition, q as ANALYST_BENCHMARK_IMPLEMENTATION_FILES, r as createPrimeBenchmarkRunner, rt as renderAgentRxCalibrationMarkdown, s as loadPublicBenchmarkRows, st as agentRxBenchmarkCase, t as runAnalystBenchmarkCommand, tt as compareAnalystRunners, u as publicBenchmarkSelectionReport, ut as roundAgentRxStep, v as runChunkedAnalystDefinition, w as expandCodeTraceFailureBlocks, x as analystDefinitionProtocolSha256, y as AnalystExpressivenessError, z as loadCodeTraceVerificationArtifacts } from "../benchmark-command-BC265T1r.js";
|
|
12
12
|
import { a as extractPrimeJsonObject, c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, i as emptyPrimeRawUsage, l as primeReplyDefect, n as buildPrimePrompt, o as mergePrimeRawUsage, r as buildPrimeRepairPrompt, s as normalizePrimeUsage, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "../prime-protocol-DcAK9pC8.js";
|
|
13
13
|
import { t as nodeHttpPrimeBridgeTransport } from "../prime-bridge-transport-Z3cpKGoV.js";
|
|
14
14
|
import { existsSync, readFileSync, readdirSync, statSync } from "node:fs";
|
|
@@ -3,7 +3,7 @@ import { a as RunRecord, u as RunTerminalOutcome } from "./run-record-DF-fuu31.j
|
|
|
3
3
|
import { r as ContinuousAgreement } from "./judge-calibration-DFtEMlde.js";
|
|
4
4
|
import { r as DatasetScenario } from "./dataset-DQqhOCPt.js";
|
|
5
5
|
import { i as ParetoFigureSpec, t as GainDistributionBin } from "./summary-report-DvvesgR_.js";
|
|
6
|
-
import { n as AnalystRegistry } from "./registry-
|
|
6
|
+
import { n as AnalystRegistry } from "./registry-DMkmhBQ5.js";
|
|
7
7
|
//#region src/contract/insight-report.d.ts
|
|
8
8
|
interface InsightReport {
|
|
9
9
|
/** Number of runs analyzed. */
|
|
@@ -484,4 +484,4 @@ declare function summarizeExecution(opts: SummarizeExecutionOptions): ExecutionR
|
|
|
484
484
|
declare function analyzeRuns(opts: AnalyzeRunsOptions): Promise<InsightReport>;
|
|
485
485
|
//#endregion
|
|
486
486
|
export { ReleaseSummary as _, summarizeExecution as a, ExecutionInsight as c, InsightReport as d, InterRaterInsight as f, Recommendation as g, OutcomeCorrelationInsight as h, analyzeRuns as i, FailureClassTally as l, LiftInsight as m, ExecutionReport as n, CostProvenanceSummary as o, JudgeInsight as p, SummarizeExecutionOptions as r, ExecutionErrorOutcomeCell as s, AnalyzeRunsOptions as t, FailureClusterInsight as u, ScalarDistribution as v, TokenUsageInsight as y };
|
|
487
|
-
//# sourceMappingURL=analyze-runs-
|
|
487
|
+
//# sourceMappingURL=analyze-runs-CTJyUplR.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"analyze-runs-
|
|
1
|
+
{"version":3,"file":"analyze-runs-CTJyUplR.d.ts","names":[],"sources":["../src/contract/insight-report.ts","../src/contract/analyze-runs.ts"],"mappings":";;;;;;;UAqCiB;;EAEf;;;;EAKA,WAAW;;EAGX,WAAW;;;EAIX,cAAc,eAAe;;EAG7B;IACE,MAAM;IACN,QAAQ;;;;;IAKR,aAAa;;;;;IAKb;MAAa;MAAe;;;;;;EAM9B,QAAQ,eAAe;;;;EAKvB,aAAa;;;;EAKb,OAAO;;;EAIP,kBAAkB;;;EAIlB,gBAAgB;;;;;EAMhB,qBAAqB;;;;;EAMrB,SAAS;;;;;;EAOT,wBAAwB;;;;EAKxB,iBAAiB;;;EAIjB,iBAAiB;;UAGF;EACf;IAAY;IAAW;;EACvB;IAAa;IAAW;;;;EAGxB;IAAc;IAAW;;EACzB;IAAc;;EACd;;UAGe;;EAEf,YAAY;;EAEZ,SAAS;;;EAGT,YAAY;;;EAGZ;IACE;IACA,YAAY;IACZ,SAAS;IACT;;;EAGF,QAAQ;IAAQ;IAAe;;;;;EAI/B;IACE;IACA;IACA;;;;;EAKF;IACE;;;IAGA;;IAEA;;IAEA;;IAEA;;IAEA;;;;;IAKA,mBAAmB,OAAO,oBAAoB;;;;EAIhD;IACE;IACA;IACA;IACA;IACA;;;UAIa;;EAEf;;EAEA;;EAEA;;UAGe;EACf,OAAO;EACP,QAAQ;EACR,WAAW;EACX,QAAQ;EACR,YAAY;EACZ;IACE;IACA;IACA;IACA;IACA;;;;UAOa;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,WAAW;;;;;EAKX,WAAW;IAAQ;IAAe;;;UAGnB;;EAEf;;EAEA;;;EAGA,cAAc;;;EAGd;;;EAGA;;;EAGA;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,SAAS;;EAET,mBAAmB;IACjB;IACA,SAAS;MAAQ;MAAe;;IAChC;;;UAIa;EACf;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;;;;;;EAWA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe;;EAEf,UAAU;IACR;IACA;;IAEA;;IAEA;;IAEA;;EAEF;;;;;UAMe;;EAEf,cAAc;;EAEd;;EAEA;;UAGe;;EAEf;;;EAGA;EACA,UAAU;IAAQ;IAAe;IAAgB;;;UAGlC;;;EAGf;;EAEA;;EAEA;;EAEA;;EAEA;IACE;IACA;IACA;;;UAIa;;;EAGf;EACA,MAAM;IACJ;IACA;IACA;;;;EAIF;;UAGQ;;EAER;;EAEA;;;;EAIA;;EAEA;EACA;;KAGU,eACP;EACC;;EAEA;;EAEA;;EAEA;;EAEA;MAED;EACC;;EAEA;EACA;EACA;EACA;;UAGW;;EAEf;EACA;;EAEA;;;;EAIA,SAAS,eAAe;;;EAGxB;;EAEA;;EAEA;;UAGe;EACf;EACA;EACA;EACA;;EAEA;;;;UC/Xe;;EAEf,MAAM;;;EAGN;;;;;EAKA;EACA;;;EAGA,8BAA8B;;;EAG9B,kBAAkB;;;EAGlB,UAAU;;;;EAIV;IACE;IACA,cAAc;;;;;EAKhB,cAAc;IAAQ;IAAe;IAAe;;;EAEpD;;;;EAIA;;;;;;;;;EASA,eAAe;;;EAGf;;UAGe;EACf,MAAM;EACN;;UAGe;EACf,WAAW;EACX,gBAAgB;;;iBAIF,mBAAmB,MAAM,4BAA4B;iBAgB/C,YAAY,MAAM,qBAAqB,QAAQ"}
|
|
@@ -5,17 +5,17 @@ import { a as resolveModelPricing } from "./metrics-DOMpkoeb.js";
|
|
|
5
5
|
import { a as CostLedgerPersistenceError, i as CostLedger, n as CostCallConflictError, o as CostReceiptCaptureError, r as CostCeilingReachedError, s as CostReservationExceededError, t as CostAccountingIncompleteError } from "./cost-ledger-_IbkejCF.js";
|
|
6
6
|
import { d as withLedgerFileLock, f as writeLedgerFileAtomically } from "./journal-DvKCvjty.js";
|
|
7
7
|
import "./ledger-core/index.js";
|
|
8
|
-
import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-
|
|
8
|
+
import { S as fsCampaignStorage, i as startExternalOptimizerModelProxy, r as runWithCleanup, x as createRunCostLedger, y as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-C0EsxEbI.js";
|
|
9
9
|
import { f as redactText } from "./redact-Dk1ZdJEm.js";
|
|
10
10
|
import { t as acquireSingleRunLock } from "./single-run-lock-fVu3MZWH.js";
|
|
11
|
-
import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-
|
|
11
|
+
import { a as callLlmJson, r as LlmResponseError, t as LlmCallError } from "./llm-client-v968tWw8.js";
|
|
12
12
|
import { F as evidenceRefsFromRawFinding, N as RAW_FINDING_SCHEMA_PROMPT, P as RawAnalystFindingSchema, _ as TRACE_ANALYSIS_LIMITS, r as runTraceAnalyst } from "./kind-factory-Cn1lbsAd.js";
|
|
13
13
|
import { r as usageReceiptFromCostLedger } from "./usage-receipt-Cx3xNeyB.js";
|
|
14
14
|
import { r as makeFinding } from "./types-CW5b90JH.js";
|
|
15
|
-
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-
|
|
15
|
+
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-sHwdSxK3.js";
|
|
16
16
|
import { i as otlpTextToTraceAnalysisStore, r as createOtlpBufferTraceStore, t as DEFAULT_MAX_TRACE_FILE_BYTES } from "./store-otlp-BA7G1Du-.js";
|
|
17
17
|
import { i as summarizeAnalystBenchmarkRunner, n as runAnalystBenchmark, r as traceStoreEvidenceResolver } from "./benchmark-BywPeAUo.js";
|
|
18
|
-
import "./external-optimizer-process-
|
|
18
|
+
import "./external-optimizer-process-D2Txd-7D.js";
|
|
19
19
|
import { t as assertEqualDeclarativeTerms } from "./equal-terms-Blx9Zk5I.js";
|
|
20
20
|
import { c as primeProtocolSha256, d as runPrimeExchange, f as decodeReplyRows, n as buildPrimePrompt, t as analystUsageReceiptFromPrimeUsage, u as projectPrimeTrajectory } from "./prime-protocol-DcAK9pC8.js";
|
|
21
21
|
import { t as nodeHttpPrimeBridgeTransport } from "./prime-bridge-transport-Z3cpKGoV.js";
|
|
@@ -1537,7 +1537,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
|
1537
1537
|
"src/trace/redact.ts",
|
|
1538
1538
|
"src/verdict-cache.ts"
|
|
1539
1539
|
]);
|
|
1540
|
-
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "
|
|
1540
|
+
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "3a994853640a80394e766f6b1992e16a41a490b3ea834752e06223c590f84d65";
|
|
1541
1541
|
function analystBenchmarkImplementationDigest() {
|
|
1542
1542
|
return ANALYST_BENCHMARK_IMPLEMENTATION_SHA256;
|
|
1543
1543
|
}
|
|
@@ -6324,4 +6324,4 @@ function shellQuote(value) {
|
|
|
6324
6324
|
//#endregion
|
|
6325
6325
|
export { ANALYST_BENCHMARK_MANIFEST_FILE as $, readAnalystInstructionsOverride as A, parseVerificationOutcome as B, emptyPublicBenchmarkRunner as C, summarizeCodeTraceCalibration as D, renderCodeTraceCalibrationMarkdown as E, publicBenchmarkRlmInstructions as F, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as G, ANALYST_BENCHMARK_DEPENDENCY_LOCK_FILES as H, publicBenchmarkSystemPrompt as I, ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 as J, ANALYST_BENCHMARK_IMPLEMENTATION_DIGEST_ALGORITHM as K, DEFAULT_MAX_VERIFICATION_ARTIFACT_BYTES as L, MAX_INCORRECT_BLOCKS as M, MAX_INCORRECT_BLOCK_STEPS as N, analystInstructionsOverrideFromText as O, publicBenchmarkProtocolSha256 as P, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as Q, appendVerificationArtifactsToOtlp as R, adaptPublicBenchmarkFindings as S, readAnalystBenchmarkArtifact as T, ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 as U, ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM as V, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as W, analystBenchmarkImplementationDigest as X, analystBenchmarkDependencyLockDigest as Y, ANALYST_BENCHMARK_COST_LEDGER_FILE as Z, publicDirectAnalystDefinition as _, primeCodeTraceAnalystDefinition as a, codeTraceBenchCase as at, analystDefinitionAsymmetries as b, preparePublicAnalystBenchmark as c, agentRxPredictionsToFindings as ct, selectPublicBenchmarkRows as d, normalizeBenchmarkLabel as dt, ANALYST_BENCHMARK_OBSERVATIONS_FILE as et, createPublicBenchmarkRlmRunner as f, createPublicBenchmarkDirectRunner as g, runReplVariableAnalystDefinition as h, primeAnalystProtocolSha256 as i, summarizeAgentRxCalibration as it, CODE_TRACE_BENCH_ANALYST_PROMPT as j, effectiveAnalystProtocolSha256 as k, publicBenchmarkDistributions as l, normalizeAgentRxCategory as lt, rlmEngineLimits as m, renderAnalystBenchmarkMarkdown as n, AGENT_RX_UPSTREAM_REVISION as nt, runInlineAnalystDefinition as o, codeTracerPredictionsToFindings as ot, publicRlmAnalystDefinition as p, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as q, createPrimeBenchmarkRunner as r, renderAgentRxCalibrationMarkdown as rt, loadPublicBenchmarkRows as s, agentRxBenchmarkCase as st, runAnalystBenchmarkCommand as t, compareAnalystRunners as tt, publicBenchmarkSelectionReport as u, roundAgentRxStep as ut, runChunkedAnalystDefinition as v, expandCodeTraceFailureBlocks as w, analystDefinitionProtocolSha256 as x, AnalystExpressivenessError as y, loadCodeTraceVerificationArtifacts as z };
|
|
6326
6326
|
|
|
6327
|
-
//# sourceMappingURL=benchmark-command-
|
|
6327
|
+
//# sourceMappingURL=benchmark-command-BC265T1r.js.map
|