@tangle-network/agent-bench 0.3.7 → 0.4.0

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.4.0
+
+- Add the resumable SWE improvement loop backed by the official GEPA engine.
+- Isolate every concurrent candidate in its own Git worktree and authorize the exact candidate before execution.
+- Include the complete Runtime, Bench, and installed SWE judge implementations in resume identity.
+- Consume `@tangle-network/agent-runtime` 0.105.x, `@tangle-network/agent-eval` 0.126.6, and `@tangle-network/agent-knowledge` 5.0.1.
+
+## 0.3.8
+
+- Resolve package-owned fixtures and scripts from both source and compiled installs, and prove ToolLLM fixture loading from the packed package.
+
 ## 0.3.7
 
 - Declare the public executable search path for Pier candidate entrypoints so the exact process contract can replay them against `@tangle-network/agent-runtime@0.102.0`.

package/HARNESS.md

@@ -71,6 +71,48 @@ this codebase. `agent-lab/runs/RUNS.md` is the index mapping artifacts → verdi
 findings gist. **Set `OUT=runs/<date>/<name>.json` (in agent-lab) on every run — never `/tmp`**
 (a reboot erases ramdisk; ~20 runs nearly died there once).
 
+## Run observability — never hand-grep a journal again
+
+Every supervisor cell writes `run-report.json` + `run-report.md` next to its artifacts, and
+appends a headline block to the run log, automatically: `outer-loop.mts` and both
+`run-experiment.mts` paths call `writeRunReportSafe` after each cell and `reportRound` at
+the gate. Source: `swe-arena/run-report.mts` (pure `computeRunReport` + an I/O collector).
+
+What it answers, all deterministic, all from artifacts already on disk (`journal.jsonl`,
+`workers/*.ndjson`, `workers/*.inbox.ndjson`, `state.json`, `result.json`, `judge.json`,
+the ledger, `driver.log`, the delivered patch, the opencode session store):
+
+- **orchestration** — workers spawned/settled/cancelled, **steer count with a per-worker
+  breakdown**, spawn waves + sizes, max concurrency, respawns, repeated labels, delegation
+  depth, time-to-first-spawn, supervisor wall, idle wall (zero live workers), worker
+  utilization (Σ worker wall ÷ supervisor wall).
+- **decision quality** — settled by status/verdict, accepted vs rejected vs empty-pass,
+  evidence→respawn sequences vs blind respawns, review actions, evidence bytes returned.
+- **economics** — tokens + USD by role (brain from journal `metered`; workers from journal
+  `settled` spend plus the opencode session join), per-worker rows, cost per accepted patch,
+  worker wall distribution.
+- **outcome** — supervisor status/verdict/delivered, judge verdict + score (from `judge.json`
+  or the matching ledger row, with provenance), verify gate, patch file/line/test-touch stats.
+
+Every metric is UNAVAILABLE-aware: a missing artifact yields `{"unavailable": "<reason>"}`
+and renders as `unavailable — <reason>`, never `0`. A supervisor that steered nobody and a
+supervisor whose worker logs were lost are visually different, because they have driven
+opposite conclusions about the same architecture.
+
+Standalone / backfill (use `--report-dir` when the run directory must stay READ-ONLY):
+```
+tsx src/swe-arena/run-report.mts <cellDir> [--patch p.diff] [--ledger ledger.jsonl] [--log run.log] [--report-dir out/]
+tsx src/swe-arena/run-report.mts --round <outDir> [--report-dir out/]
+```
+
+Relationship to the published `traces` CLI (`npx @tangle-network/traces analyze`): traces
+covers the HARNESS-SESSION layer — per-session model calls, token/cost tables, latency
+distributions, stuck-loop detection, tool-error rates, skill/subagent adoption — reading the
+opencode/claude-code/codex session stores. It has no supervision-tree reader: no journal
+parsing, no steer/wave/concurrency/utilization/delegation-depth metric, no accepted-vs-rejected
+worker accounting. The two are complementary; run-report prints the traces command for the
+same cell rather than re-deriving session-level facts.
+
 ## Data flow (the whole experiment in one line)
 `rollout (worker → answer) → adapter.judge (valid?) → CORPUS RunRecord (k attempts, output+valid each) → corpus-replay --selector (pick WITHOUT the judge) → corpus-report CI → gate verdict`
 The expensive part (rollouts) produces a **reusable corpus**; selection + stats are free
@@ -135,6 +177,7 @@ the gate + measurement tools:
   commit0-env-run.mts  the HARD domain through `runBenchmark` (the optimization suite)
   terminal-compare.ts  Terminal-Bench compare (own main)
   pnpm verify:pier  zero-model failure/pass Pier controls through a separate verifier
+  swe-arena/run-report.mts  deterministic per-cell run report (steers, waves, idle, cost by role) + round rollup
 unit tests (the only fully-green, cred-free runnable surface besides offline replay):
   node --test --import tsx src/{selector,refine-loop}.test.mts
   tsx src/gate.test.mts   # offline plumbing test (no creds)

package/README.md

@@ -26,6 +26,13 @@ pnpm install                                              # tsx + link parent
 
 The judge needs only Docker; workers need a model key (Tangle router `TANGLE_API_KEY`, or a direct provider).
 
+Live optimizer scripts require explicit token prices so cost records cannot be guessed.
+Use the `REFLECT_` prefix for the general benchmark scripts and `GEPA_OPTIMIZER_` for the SWE arena seat.
+For either prefix, set `INPUT_USD_PER_MILLION`, `CACHED_INPUT_USD_PER_MILLION`, `CACHE_WRITE_USD_PER_MILLION`, and `OUTPUT_USD_PER_MILLION`.
+The SWE arena seat reads its model from `GEPA_OPTIMIZER_MODEL`, its URL from `GEPA_OPTIMIZER_BASE_URL`, and its key from `GEPA_OPTIMIZER_API_KEY`.
+It falls back to the configured driver model, `ROUTER_BASE`, and `TANGLE_API_KEY`.
+Missing prices fail before an optimizer model call.
+
 Retain every official per-test log and report before the temporary evaluator directory is removed:
 
 ```ts

package/dist/adapters.js

@@ -1,40 +1,40 @@
 import {
   ADAPTERS,
   resolveAdapter
-} from "./chunk-PWQVGAJB.js";
-import "./chunk-2PVVP7GN.js";
+} from "./chunk-V7AEBY6U.js";
+import "./chunk-XKEFIFIC.js";
 import "./chunk-VQRS7VUC.js";
-import "./chunk-Z7ML6L77.js";
-import "./chunk-R67DFVLO.js";
+import "./chunk-HWST3SED.js";
+import "./chunk-IFVINJ4B.js";
 import "./chunk-SEVJPLZC.js";
-import "./chunk-CKUVRZ2T.js";
-import "./chunk-Y6O2OCUO.js";
-import "./chunk-HBSWHQNJ.js";
-import "./chunk-UAIOHCUK.js";
-import "./chunk-R36V2VP7.js";
-import "./chunk-JRWWGMK7.js";
+import "./chunk-3U5TXJZS.js";
+import "./chunk-SHM6MRRF.js";
+import "./chunk-RCYQEFNX.js";
+import "./chunk-SFLA7OH3.js";
+import "./chunk-IZ5M6OAC.js";
+import "./chunk-XYA4XSNU.js";
 import "./chunk-INNOYXCP.js";
 import "./chunk-PA2ZKHJC.js";
 import "./chunk-5H5XV76F.js";
 import "./chunk-TBKU5XQI.js";
-import "./chunk-TSWPNOYM.js";
-import "./chunk-KDIKRJGB.js";
-import "./chunk-ZEWMTR5M.js";
+import "./chunk-NQG5XDSB.js";
+import "./chunk-SHYIRB7I.js";
+import "./chunk-MQMRLGOG.js";
 import "./chunk-PUIRNYI7.js";
 import "./chunk-C7T7WEK2.js";
 import "./chunk-JTHWEDEW.js";
-import "./chunk-2XU6OGEN.js";
-import "./chunk-HHXFIHXC.js";
+import "./chunk-Z4TZ76N7.js";
+import "./chunk-SVR2LKYI.js";
 import "./chunk-X3BTXCJ4.js";
-import "./chunk-J3KDJNX2.js";
-import "./chunk-X5YKXC6V.js";
-import "./chunk-YCGY7UIZ.js";
+import "./chunk-RH5F53JT.js";
+import "./chunk-YSMEKBTD.js";
+import "./chunk-7GRVHU22.js";
 import "./chunk-UPAMRDX4.js";
-import "./chunk-ODT47UAY.js";
-import "./chunk-7WSD27QQ.js";
-import "./chunk-SYDW647C.js";
-import "./chunk-IFAV6KEM.js";
-import "./chunk-LRRD7NAG.js";
+import "./chunk-K3BQGZCT.js";
+import "./chunk-PB64GYIG.js";
+import "./chunk-IA2FBTWC.js";
+import "./chunk-KP5KD6EN.js";
+import "./chunk-WSKWVEQB.js";
 import "./chunk-53UPUNBZ.js";
 export {
   ADAPTERS,

package/dist/benchmarks/_harness.d.ts

@@ -19,7 +19,7 @@ import '@tangle-network/agent-runtime/loops';
  * nonzero throws with the captured stderr — never a fabricated score.
  */
 
-/** Repo root for the bench package (…/bench), so `.venv` and `fixtures` resolve. */
+/** Package root for agent-bench, so `.venv`, scripts, and fixtures resolve. */
 declare const benchRoot: string;
 /** Resolve the shared interpreter without requiring an installed package to contain a venv. */
 declare function resolveBenchPython(env?: Readonly<{

package/dist/benchmarks/_harness.js

@@ -13,7 +13,7 @@ import {
   venvBin,
   venvPython,
   venvPythonAt
-} from "../chunk-LRRD7NAG.js";
+} from "../chunk-WSKWVEQB.js";
 export {
   StagedJudgeError,
   benchRoot,

package/dist/benchmarks/aec-bench.js

@@ -1,7 +1,7 @@
 import {
   createAecBenchAdapter
-} from "../chunk-ODT47UAY.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-K3BQGZCT.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createAecBenchAdapter
 };

package/dist/benchmarks/agentbench.js

@@ -1,8 +1,8 @@
 import {
   agentbenchAnswerOutput,
   createAgentBenchAdapter
-} from "../chunk-7WSD27QQ.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-PB64GYIG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   agentbenchAnswerOutput,
   createAgentBenchAdapter

package/dist/benchmarks/appworld.js

@@ -3,8 +3,8 @@ import {
   appworldToolLoopClient,
   createAppWorldAdapter,
   createAppWorldReactAdapter
-} from "../chunk-SYDW647C.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-IA2FBTWC.js";
+import "../chunk-WSKWVEQB.js";
 export {
   appworldSolutionOutput,
   appworldToolLoopClient,

package/dist/benchmarks/bfcl.js

@@ -1,8 +1,8 @@
 import {
   bfclOutput,
   createBfclAdapter
-} from "../chunk-IFAV6KEM.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-KP5KD6EN.js";
+import "../chunk-WSKWVEQB.js";
 export {
   bfclOutput,
   createBfclAdapter

package/dist/benchmarks/commit0.js

@@ -1,8 +1,8 @@
 import {
   commit0DiffOutput,
   createCommit0Adapter
-} from "../chunk-2XU6OGEN.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-Z4TZ76N7.js";
+import "../chunk-WSKWVEQB.js";
 export {
   commit0DiffOutput,
   createCommit0Adapter

package/dist/benchmarks/crag.js

@@ -1,8 +1,8 @@
 import {
   createCragAdapter
-} from "../chunk-HHXFIHXC.js";
+} from "../chunk-SVR2LKYI.js";
 import "../chunk-X3BTXCJ4.js";
-import "../chunk-LRRD7NAG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createCragAdapter
 };

package/dist/benchmarks/dabstep.js

@@ -1,8 +1,8 @@
 import {
   createDabstepAdapter,
   dabstepAnswerOutput
-} from "../chunk-J3KDJNX2.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-RH5F53JT.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createDabstepAdapter,
   dabstepAnswerOutput

package/dist/benchmarks/enterpriseops-gym.js

@@ -1,8 +1,8 @@
 import {
   createEnterpriseOpsGymAdapter,
   enterpriseOpsTranscriptOutput
-} from "../chunk-X5YKXC6V.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-YSMEKBTD.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createEnterpriseOpsGymAdapter,
   enterpriseOpsTranscriptOutput

package/dist/benchmarks/finresearchbench.js

@@ -1,7 +1,7 @@
 import {
   createFinResearchBenchAdapter
-} from "../chunk-YCGY7UIZ.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-7GRVHU22.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createFinResearchBenchAdapter
 };

package/dist/benchmarks/nomiracl.js

@@ -1,8 +1,8 @@
 import {
   createNoMiraclAdapter
-} from "../chunk-TSWPNOYM.js";
+} from "../chunk-NQG5XDSB.js";
 import "../chunk-X3BTXCJ4.js";
-import "../chunk-LRRD7NAG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createNoMiraclAdapter
 };

package/dist/benchmarks/open-rag-bench.js

@@ -1,8 +1,8 @@
 import {
   createOpenRagBenchAdapter
-} from "../chunk-KDIKRJGB.js";
+} from "../chunk-SHYIRB7I.js";
 import "../chunk-X3BTXCJ4.js";
-import "../chunk-LRRD7NAG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createOpenRagBenchAdapter
 };

package/dist/benchmarks/programbench.js

@@ -1,8 +1,8 @@
 import {
   createProgrambenchAdapter,
   programbenchSubmissionOutput
-} from "../chunk-ZEWMTR5M.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-MQMRLGOG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createProgrambenchAdapter,
   programbenchSubmissionOutput

package/dist/benchmarks/ragbench.js

@@ -1,8 +1,8 @@
 import {
   createRagBenchAdapter
-} from "../chunk-R67DFVLO.js";
+} from "../chunk-IFVINJ4B.js";
 import "../chunk-X3BTXCJ4.js";
-import "../chunk-LRRD7NAG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createRagBenchAdapter
 };

package/dist/benchmarks/swe-bench.js

@@ -3,8 +3,8 @@ import {
   scoreSweReport,
   sweEvaluationArgv,
   swePatchOutput
-} from "../chunk-CKUVRZ2T.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-3U5TXJZS.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createSweBenchAdapter,
   scoreSweReport,

package/dist/benchmarks/t2-ragbench.js

@@ -1,8 +1,8 @@
 import {
   createT2RagBenchAdapter
-} from "../chunk-Y6O2OCUO.js";
+} from "../chunk-SHM6MRRF.js";
 import "../chunk-X3BTXCJ4.js";
-import "../chunk-LRRD7NAG.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createT2RagBenchAdapter
 };

package/dist/benchmarks/tau-bench-shared.js

@@ -1,8 +1,8 @@
 import {
   createTauBenchAdapter,
   tauResultsOutput
-} from "../chunk-R36V2VP7.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-IZ5M6OAC.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createTauBenchAdapter,
   tauResultsOutput

package/dist/benchmarks/tau2-bench.js

@@ -1,9 +1,9 @@
 import {
   createTau2BenchAdapter,
   tau2ResultsOutput
-} from "../chunk-HBSWHQNJ.js";
-import "../chunk-R36V2VP7.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-RCYQEFNX.js";
+import "../chunk-IZ5M6OAC.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createTau2BenchAdapter,
   tau2ResultsOutput

package/dist/benchmarks/tau3-banking.js

@@ -1,8 +1,8 @@
 import {
   createTau3BankingAdapter
-} from "../chunk-UAIOHCUK.js";
-import "../chunk-R36V2VP7.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-SFLA7OH3.js";
+import "../chunk-IZ5M6OAC.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createTau3BankingAdapter
 };

package/dist/benchmarks/terminal-bench.js

@@ -1,7 +1,7 @@
 import {
   createTerminalBenchAdapter
-} from "../chunk-JRWWGMK7.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-XYA4XSNU.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createTerminalBenchAdapter
 };

package/dist/benchmarks/toollm.js

@@ -1,8 +1,8 @@
 import {
   createToolLlmAdapter,
   toollmOutput
-} from "../chunk-2PVVP7GN.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-XKEFIFIC.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createToolLlmAdapter,
   toollmOutput

package/dist/benchmarks/webarena-verified.js

@@ -1,8 +1,8 @@
 import {
   createWebArenaVerifiedAdapter,
   webarenaOutputDirOutput
-} from "../chunk-Z7ML6L77.js";
-import "../chunk-LRRD7NAG.js";
+} from "../chunk-HWST3SED.js";
+import "../chunk-WSKWVEQB.js";
 export {
   createWebArenaVerifiedAdapter,
   webarenaOutputDirOutput

package/dist/{chunk-CKUVRZ2T.js → chunk-3U5TXJZS.js}

@@ -5,7 +5,7 @@ import {
   runVenvPython,
   safeRunId,
   stageFile
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/swe-bench.ts
 import { join } from "path";
@@ -248,4 +248,4 @@ export {
   sweEvaluationArgv,
   createSweBenchAdapter
 };
-//# sourceMappingURL=chunk-CKUVRZ2T.js.map
+//# sourceMappingURL=chunk-3U5TXJZS.js.map

package/dist/{chunk-YCGY7UIZ.js → chunk-7GRVHU22.js}

@@ -1,6 +1,6 @@
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/finresearchbench.ts
 import { readFile, stat } from "fs/promises";
@@ -205,4 +205,4 @@ function createFinResearchBenchAdapter() {
 export {
   createFinResearchBenchAdapter
 };
-//# sourceMappingURL=chunk-YCGY7UIZ.js.map
+//# sourceMappingURL=chunk-7GRVHU22.js.map

package/dist/{chunk-Z7ML6L77.js → chunk-HWST3SED.js}

@@ -1,7 +1,7 @@
 import {
   benchRoot,
   runVenvPython
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/webarena-verified.ts
 import { access, readFile, stat } from "fs/promises";
@@ -159,4 +159,4 @@ export {
   webarenaOutputDirOutput,
   createWebArenaVerifiedAdapter
 };
-//# sourceMappingURL=chunk-Z7ML6L77.js.map
+//# sourceMappingURL=chunk-HWST3SED.js.map

package/dist/{chunk-SYDW647C.js → chunk-IA2FBTWC.js}

@@ -3,7 +3,7 @@ import {
   preflightVenvImports,
   runVenvScriptStdin,
   venvPython
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/appworld.ts
 import { spawn } from "child_process";
@@ -315,4 +315,4 @@ export {
   appworldToolLoopClient,
   createAppWorldReactAdapter
 };
-//# sourceMappingURL=chunk-SYDW647C.js.map
+//# sourceMappingURL=chunk-IA2FBTWC.js.map

package/dist/{chunk-R67DFVLO.js → chunk-IFVINJ4B.js}

@@ -14,7 +14,7 @@ import {
 } from "./chunk-X3BTXCJ4.js";
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/ragbench.ts
 import { readFile } from "fs/promises";
@@ -139,4 +139,4 @@ function createRagBenchAdapter() {
 export {
   createRagBenchAdapter
 };
-//# sourceMappingURL=chunk-R67DFVLO.js.map
+//# sourceMappingURL=chunk-IFVINJ4B.js.map

package/dist/{chunk-R36V2VP7.js → chunk-IZ5M6OAC.js}

@@ -1,6 +1,6 @@
 import {
   runVenvPython
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/tau-bench-shared.ts
 import { readFile, stat } from "fs/promises";
@@ -166,4 +166,4 @@ export {
   tauResultsOutput,
   createTauBenchAdapter
 };
-//# sourceMappingURL=chunk-R36V2VP7.js.map
+//# sourceMappingURL=chunk-IZ5M6OAC.js.map

package/dist/{chunk-ODT47UAY.js → chunk-K3BQGZCT.js}

@@ -5,7 +5,7 @@ import {
   runStagedJudge,
   stageFile,
   venvPython
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/aec-bench.ts
 import { readFile } from "fs/promises";
@@ -218,4 +218,4 @@ Fix: ensure network access to raw.githubusercontent.com, or set AEC_FIXTURES=1 t
 export {
   createAecBenchAdapter
 };
-//# sourceMappingURL=chunk-ODT47UAY.js.map
+//# sourceMappingURL=chunk-K3BQGZCT.js.map

package/dist/{chunk-IFAV6KEM.js → chunk-KP5KD6EN.js}

@@ -1,6 +1,6 @@
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/bfcl.ts
 import { readFile, stat } from "fs/promises";
@@ -273,4 +273,4 @@ export {
   bfclOutput,
   createBfclAdapter
 };
-//# sourceMappingURL=chunk-IFAV6KEM.js.map
+//# sourceMappingURL=chunk-KP5KD6EN.js.map

package/dist/{chunk-ZEWMTR5M.js → chunk-MQMRLGOG.js}

@@ -2,7 +2,7 @@ import {
   benchRoot,
   preflightVenvImports,
   runVenvScriptStdin
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/programbench.ts
 import { join } from "path";
@@ -133,4 +133,4 @@ export {
   programbenchSubmissionOutput,
   createProgrambenchAdapter
 };
-//# sourceMappingURL=chunk-ZEWMTR5M.js.map
+//# sourceMappingURL=chunk-MQMRLGOG.js.map

package/dist/{chunk-TSWPNOYM.js → chunk-NQG5XDSB.js}

@@ -10,7 +10,7 @@ import {
 } from "./chunk-X3BTXCJ4.js";
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/nomiracl.ts
 import { readFile } from "fs/promises";
@@ -144,4 +144,4 @@ function createNoMiraclAdapter() {
 export {
   createNoMiraclAdapter
 };
-//# sourceMappingURL=chunk-TSWPNOYM.js.map
+//# sourceMappingURL=chunk-NQG5XDSB.js.map

package/dist/{chunk-7WSD27QQ.js → chunk-PB64GYIG.js}

@@ -1,6 +1,6 @@
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/agentbench.ts
 import { readFile } from "fs/promises";
@@ -115,4 +115,4 @@ export {
   agentbenchAnswerOutput,
   createAgentBenchAdapter
 };
-//# sourceMappingURL=chunk-7WSD27QQ.js.map
+//# sourceMappingURL=chunk-PB64GYIG.js.map

package/dist/{chunk-HBSWHQNJ.js → chunk-RCYQEFNX.js}

@@ -1,10 +1,10 @@
 import {
   createTauBenchAdapter,
   tauResultsOutput
-} from "./chunk-R36V2VP7.js";
+} from "./chunk-IZ5M6OAC.js";
 import {
   benchRoot
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/tau2-bench.ts
 import { join } from "path";
@@ -27,4 +27,4 @@ export {
   tau2ResultsOutput,
   createTau2BenchAdapter
 };
-//# sourceMappingURL=chunk-HBSWHQNJ.js.map
+//# sourceMappingURL=chunk-RCYQEFNX.js.map

package/dist/{chunk-J3KDJNX2.js → chunk-RH5F53JT.js}

@@ -2,7 +2,7 @@ import {
   benchRoot,
   runVenvPython,
   runVenvScriptStdin
-} from "./chunk-LRRD7NAG.js";
+} from "./chunk-WSKWVEQB.js";
 
 // src/benchmarks/dabstep.ts
 import { join } from "path";
@@ -179,4 +179,4 @@ export {
   dabstepAnswerOutput,
   createDabstepAdapter
 };
-//# sourceMappingURL=chunk-J3KDJNX2.js.map
+//# sourceMappingURL=chunk-RH5F53JT.js.map