@tangle-network/agent-bench 0.3.7 → 0.4.0

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.
Files changed (211) hide show
  1. package/CHANGELOG.md +11 -0
  2. package/HARNESS.md +43 -0
  3. package/README.md +7 -0
  4. package/dist/adapters.js +23 -23
  5. package/dist/benchmarks/_harness.d.ts +1 -1
  6. package/dist/benchmarks/_harness.js +1 -1
  7. package/dist/benchmarks/aec-bench.js +2 -2
  8. package/dist/benchmarks/agentbench.js +2 -2
  9. package/dist/benchmarks/appworld.js +2 -2
  10. package/dist/benchmarks/bfcl.js +2 -2
  11. package/dist/benchmarks/commit0.js +2 -2
  12. package/dist/benchmarks/crag.js +2 -2
  13. package/dist/benchmarks/dabstep.js +2 -2
  14. package/dist/benchmarks/enterpriseops-gym.js +2 -2
  15. package/dist/benchmarks/finresearchbench.js +2 -2
  16. package/dist/benchmarks/nomiracl.js +2 -2
  17. package/dist/benchmarks/open-rag-bench.js +2 -2
  18. package/dist/benchmarks/programbench.js +2 -2
  19. package/dist/benchmarks/ragbench.js +2 -2
  20. package/dist/benchmarks/swe-bench.js +2 -2
  21. package/dist/benchmarks/t2-ragbench.js +2 -2
  22. package/dist/benchmarks/tau-bench-shared.js +2 -2
  23. package/dist/benchmarks/tau2-bench.js +3 -3
  24. package/dist/benchmarks/tau3-banking.js +3 -3
  25. package/dist/benchmarks/terminal-bench.js +2 -2
  26. package/dist/benchmarks/toollm.js +2 -2
  27. package/dist/benchmarks/webarena-verified.js +2 -2
  28. package/dist/{chunk-CKUVRZ2T.js → chunk-3U5TXJZS.js} +2 -2
  29. package/dist/{chunk-YCGY7UIZ.js → chunk-7GRVHU22.js} +2 -2
  30. package/dist/{chunk-Z7ML6L77.js → chunk-HWST3SED.js} +2 -2
  31. package/dist/{chunk-SYDW647C.js → chunk-IA2FBTWC.js} +2 -2
  32. package/dist/{chunk-R67DFVLO.js → chunk-IFVINJ4B.js} +2 -2
  33. package/dist/{chunk-R36V2VP7.js → chunk-IZ5M6OAC.js} +2 -2
  34. package/dist/{chunk-ODT47UAY.js → chunk-K3BQGZCT.js} +2 -2
  35. package/dist/{chunk-IFAV6KEM.js → chunk-KP5KD6EN.js} +2 -2
  36. package/dist/{chunk-ZEWMTR5M.js → chunk-MQMRLGOG.js} +2 -2
  37. package/dist/{chunk-TSWPNOYM.js → chunk-NQG5XDSB.js} +2 -2
  38. package/dist/{chunk-7WSD27QQ.js → chunk-PB64GYIG.js} +2 -2
  39. package/dist/{chunk-HBSWHQNJ.js → chunk-RCYQEFNX.js} +3 -3
  40. package/dist/{chunk-J3KDJNX2.js → chunk-RH5F53JT.js} +2 -2
  41. package/dist/{chunk-UAIOHCUK.js → chunk-SFLA7OH3.js} +3 -3
  42. package/dist/{chunk-Y6O2OCUO.js → chunk-SHM6MRRF.js} +2 -2
  43. package/dist/{chunk-KDIKRJGB.js → chunk-SHYIRB7I.js} +2 -2
  44. package/dist/{chunk-HHXFIHXC.js → chunk-SVR2LKYI.js} +2 -2
  45. package/dist/{chunk-PWQVGAJB.js → chunk-V7AEBY6U.js} +21 -21
  46. package/dist/{chunk-LRRD7NAG.js → chunk-WSKWVEQB.js} +18 -2
  47. package/dist/chunk-WSKWVEQB.js.map +1 -0
  48. package/dist/{chunk-2PVVP7GN.js → chunk-XKEFIFIC.js} +2 -2
  49. package/dist/{chunk-JRWWGMK7.js → chunk-XYA4XSNU.js} +2 -2
  50. package/dist/{chunk-X5YKXC6V.js → chunk-YSMEKBTD.js} +2 -2
  51. package/dist/{chunk-2XU6OGEN.js → chunk-Z4TZ76N7.js} +2 -2
  52. package/dist/index.js +23 -23
  53. package/package.json +5 -5
  54. package/scripts/trata-hedge/README.md +6 -5
  55. package/scripts/verify-packed-consumer.mjs +1 -1
  56. package/src/benchmarks/_harness.ts +20 -2
  57. package/src/benchmarks/humaneval.test.mts +2 -2
  58. package/src/gate.ts +1 -1
  59. package/src/hev-eval.mts +5 -2
  60. package/src/hev-improve.mts +118 -73
  61. package/src/official-optimizer-config.mts +89 -0
  62. package/src/official-optimizer-config.test.mts +88 -0
  63. package/src/profiles.ts +2 -2
  64. package/src/quant-arena/README.md +144 -0
  65. package/src/quant-arena/backtest.test.mts +135 -0
  66. package/src/quant-arena/backtest.ts +218 -0
  67. package/src/quant-arena/data.test.mts +44 -0
  68. package/src/quant-arena/data.ts +141 -0
  69. package/src/quant-arena/driver.test.mts +253 -0
  70. package/src/quant-arena/driver.ts +219 -0
  71. package/src/quant-arena/fixtures/data/PROVENANCE.md +26 -0
  72. package/src/quant-arena/fixtures/data/holdout/IDX.csv +523 -0
  73. package/src/quant-arena/fixtures/data/holdout/S01.csv +523 -0
  74. package/src/quant-arena/fixtures/data/holdout/S02.csv +523 -0
  75. package/src/quant-arena/fixtures/data/holdout/S03.csv +523 -0
  76. package/src/quant-arena/fixtures/data/holdout/S04.csv +523 -0
  77. package/src/quant-arena/fixtures/data/holdout/S05.csv +523 -0
  78. package/src/quant-arena/fixtures/data/holdout/S06.csv +523 -0
  79. package/src/quant-arena/fixtures/data/holdout/S07.csv +523 -0
  80. package/src/quant-arena/fixtures/data/holdout/S08.csv +523 -0
  81. package/src/quant-arena/fixtures/data/holdout/S09.csv +523 -0
  82. package/src/quant-arena/fixtures/data/holdout/S10.csv +523 -0
  83. package/src/quant-arena/fixtures/data/insample/IDX.csv +2087 -0
  84. package/src/quant-arena/fixtures/data/insample/S01.csv +2087 -0
  85. package/src/quant-arena/fixtures/data/insample/S02.csv +2087 -0
  86. package/src/quant-arena/fixtures/data/insample/S03.csv +2087 -0
  87. package/src/quant-arena/fixtures/data/insample/S04.csv +2087 -0
  88. package/src/quant-arena/fixtures/data/insample/S05.csv +2087 -0
  89. package/src/quant-arena/fixtures/data/insample/S06.csv +2087 -0
  90. package/src/quant-arena/fixtures/data/insample/S07.csv +2087 -0
  91. package/src/quant-arena/fixtures/data/insample/S08.csv +2087 -0
  92. package/src/quant-arena/fixtures/data/insample/S09.csv +2087 -0
  93. package/src/quant-arena/fixtures/data/insample/S10.csv +2087 -0
  94. package/src/quant-arena/fixtures/demo-campaign/cost-ledger.jsonl +16 -0
  95. package/src/quant-arena/fixtures/demo-campaign/notebook.jsonl +5 -0
  96. package/src/quant-arena/fixtures/demo-campaign/rollout-manifest.json +171 -0
  97. package/src/quant-arena/fixtures/demo-campaign/strategies/cand-001-default-author/strategy.ts +119 -0
  98. package/src/quant-arena/fixtures/demo-campaign/strategies/cand-002-default-author/strategy.ts +119 -0
  99. package/src/quant-arena/fixtures/demo-campaign/strategies/cand-003-quant-researcher/strategy.ts +105 -0
  100. package/src/quant-arena/fixtures/demo-campaign/strategies/cand-004-quant-researcher/strategy.ts +102 -0
  101. package/src/quant-arena/fixtures/demo-campaign-v2/cost-ledger.jsonl +4 -0
  102. package/src/quant-arena/fixtures/demo-campaign-v2/notebook.jsonl +2 -0
  103. package/src/quant-arena/fixtures/demo-campaign-v2/rollout-manifest.json +84 -0
  104. package/src/quant-arena/fixtures/demo-campaign-v2/strategies/cand-001-quant-researcher/strategy.ts +117 -0
  105. package/src/quant-arena/holdout-certify.mts +206 -0
  106. package/src/quant-arena/holdout-certify.test.mts +82 -0
  107. package/src/quant-arena/leak-audit.test.mts +79 -0
  108. package/src/quant-arena/leak-audit.ts +95 -0
  109. package/src/quant-arena/make-fixtures.mts +161 -0
  110. package/src/quant-arena/multiplicity.test.mts +68 -0
  111. package/src/quant-arena/multiplicity.ts +87 -0
  112. package/src/quant-arena/nautilus-certify.ts +31 -0
  113. package/src/quant-arena/oms.ts +90 -0
  114. package/src/quant-arena/profiles/quant-researcher.profile.json +7 -0
  115. package/src/quant-arena/python/pyproject.toml +8 -0
  116. package/src/quant-arena/python/uv.lock +1297 -0
  117. package/src/quant-arena/python/vbt-worker.py +192 -0
  118. package/src/quant-arena/quant-loop.mts +813 -0
  119. package/src/quant-arena/quant-loop.test.mts +75 -0
  120. package/src/quant-arena/strategies/buy-hold-index/strategy.ts +11 -0
  121. package/src/quant-arena/strategies/equal-weight/strategy.ts +20 -0
  122. package/src/quant-arena/strategies/sma-crossover/strategy.ts +42 -0
  123. package/src/quant-arena/types.ts +133 -0
  124. package/src/quant-arena/vbt-client.ts +321 -0
  125. package/src/quant-arena/vbt-parity.test.mts +183 -0
  126. package/src/quant-arena/windows.test.mts +45 -0
  127. package/src/quant-arena/windows.ts +54 -0
  128. package/src/rollout-ledger/backfill-swe-arena.mts +606 -0
  129. package/src/rollout-ledger/backfill-swe-arena.test.mts +342 -0
  130. package/src/rollout-ledger/settle-capture.mts +442 -0
  131. package/src/rollout-ledger/settle-capture.test.mts +270 -0
  132. package/src/smoke-structural-rollout.mts +15 -9
  133. package/src/swe-arena/activation.mts +225 -0
  134. package/src/swe-arena/activation.test.mts +300 -0
  135. package/src/swe-arena/arms.ts +30 -14
  136. package/src/swe-arena/briefing.mts +217 -0
  137. package/src/swe-arena/briefing.test.mts +178 -0
  138. package/src/swe-arena/calibrate.ts +102 -1
  139. package/src/swe-arena/cell-evidence.mts +41 -9
  140. package/src/swe-arena/factory-command-container.ts +284 -0
  141. package/src/swe-arena/factory-judge-child.mts +228 -0
  142. package/src/swe-arena/factory.test.mts +643 -0
  143. package/src/swe-arena/fixtures/factory/agent-eval-309/calibration.md +51 -0
  144. package/src/swe-arena/fixtures/factory/agent-eval-309/manifest.json +29 -0
  145. package/src/swe-arena/fixtures/factory/agent-eval-309/spec.md +64 -0
  146. package/src/swe-arena/fixtures/factory/agent-runtime-232/calibration.md +48 -0
  147. package/src/swe-arena/fixtures/factory/agent-runtime-232/manifest.json +29 -0
  148. package/src/swe-arena/fixtures/factory/agent-runtime-232/spec.md +48 -0
  149. package/src/swe-arena/fixtures/factory/loops-28/calibration.md +47 -0
  150. package/src/swe-arena/fixtures/factory/loops-28/manifest.json +30 -0
  151. package/src/swe-arena/fixtures/factory/loops-28/spec.md +50 -0
  152. package/src/swe-arena/fixtures/run-report/README.md +43 -0
  153. package/src/swe-arena/fixtures/run-report/factory-agent-eval-309-FSUP0.json +173 -0
  154. package/src/swe-arena/fixtures/run-report/factory-agent-eval-309-FSUP0.md +100 -0
  155. package/src/swe-arena/fixtures/run-report/gen3-rollup.json +551 -0
  156. package/src/swe-arena/fixtures/run-report/gen3-rollup.md +64 -0
  157. package/src/swe-arena/fixtures.ts +135 -2
  158. package/src/swe-arena/gepa-seat.mts +877 -0
  159. package/src/swe-arena/gepa-seat.test.mts +1059 -0
  160. package/src/swe-arena/implementation-ref.test.mts +64 -0
  161. package/src/swe-arena/implementation-ref.ts +62 -0
  162. package/src/swe-arena/ledger-orphans.mts +77 -0
  163. package/src/swe-arena/ledger-orphans.test.mts +147 -0
  164. package/src/swe-arena/outer-loop.mts +710 -33
  165. package/src/swe-arena/premeasured-from-cells.mts +281 -0
  166. package/src/swe-arena/premeasured-from-cells.test.mts +180 -0
  167. package/src/swe-arena/proposer-fanout.mts +327 -31
  168. package/src/swe-arena/proposer-fanout.test.mts +246 -0
  169. package/src/swe-arena/proposer-provenance.mts +172 -0
  170. package/src/swe-arena/proposer-provenance.test.mts +106 -0
  171. package/src/swe-arena/run-experiment.mts +367 -1
  172. package/src/swe-arena/run-report.mts +75 -0
  173. package/src/swe-arena/run-supervisor.test.mts +5 -3
  174. package/src/swe-arena/score-split.mts +140 -0
  175. package/src/swe-arena/score-split.test.mts +123 -0
  176. package/src/swe-arena/scratch-worktree.test.mts +55 -0
  177. package/src/swe-arena/scratch-worktree.ts +34 -0
  178. package/src/swe-arena/types.ts +52 -0
  179. package/src/swe-code-improve.mts +24 -25
  180. package/src/swe-improve.mts +129 -96
  181. package/src/swe-local-proof.mts +6 -1
  182. package/src/swe-stream.mts +4 -2
  183. package/src/swe-structural.mts +245 -837
  184. package/src/tb-container-executor.test.mts +30 -6
  185. package/src/tb-supervisor-sidecar.mts +2 -1
  186. package/src/trata-gepa.mts +182 -245
  187. package/dist/chunk-LRRD7NAG.js.map +0 -1
  188. package/src/live-improve-campaign-mbpp.mts +0 -641
  189. package/src/live-improve-campaign.mts +0 -500
  190. /package/dist/{chunk-CKUVRZ2T.js.map → chunk-3U5TXJZS.js.map} +0 -0
  191. /package/dist/{chunk-YCGY7UIZ.js.map → chunk-7GRVHU22.js.map} +0 -0
  192. /package/dist/{chunk-Z7ML6L77.js.map → chunk-HWST3SED.js.map} +0 -0
  193. /package/dist/{chunk-SYDW647C.js.map → chunk-IA2FBTWC.js.map} +0 -0
  194. /package/dist/{chunk-R67DFVLO.js.map → chunk-IFVINJ4B.js.map} +0 -0
  195. /package/dist/{chunk-R36V2VP7.js.map → chunk-IZ5M6OAC.js.map} +0 -0
  196. /package/dist/{chunk-ODT47UAY.js.map → chunk-K3BQGZCT.js.map} +0 -0
  197. /package/dist/{chunk-IFAV6KEM.js.map → chunk-KP5KD6EN.js.map} +0 -0
  198. /package/dist/{chunk-ZEWMTR5M.js.map → chunk-MQMRLGOG.js.map} +0 -0
  199. /package/dist/{chunk-TSWPNOYM.js.map → chunk-NQG5XDSB.js.map} +0 -0
  200. /package/dist/{chunk-7WSD27QQ.js.map → chunk-PB64GYIG.js.map} +0 -0
  201. /package/dist/{chunk-HBSWHQNJ.js.map → chunk-RCYQEFNX.js.map} +0 -0
  202. /package/dist/{chunk-J3KDJNX2.js.map → chunk-RH5F53JT.js.map} +0 -0
  203. /package/dist/{chunk-UAIOHCUK.js.map → chunk-SFLA7OH3.js.map} +0 -0
  204. /package/dist/{chunk-Y6O2OCUO.js.map → chunk-SHM6MRRF.js.map} +0 -0
  205. /package/dist/{chunk-KDIKRJGB.js.map → chunk-SHYIRB7I.js.map} +0 -0
  206. /package/dist/{chunk-HHXFIHXC.js.map → chunk-SVR2LKYI.js.map} +0 -0
  207. /package/dist/{chunk-PWQVGAJB.js.map → chunk-V7AEBY6U.js.map} +0 -0
  208. /package/dist/{chunk-2PVVP7GN.js.map → chunk-XKEFIFIC.js.map} +0 -0
  209. /package/dist/{chunk-JRWWGMK7.js.map → chunk-XYA4XSNU.js.map} +0 -0
  210. /package/dist/{chunk-X5YKXC6V.js.map → chunk-YSMEKBTD.js.map} +0 -0
  211. /package/dist/{chunk-2XU6OGEN.js.map → chunk-Z4TZ76N7.js.map} +0 -0
@@ -0,0 +1,100 @@
1
+ # Run report — factory.agent-eval.309 [FSUP0]
2
+
3
+ ```
4
+ RUN-REPORT factory.agent-eval.309 [FSUP0]
5
+ steers=0 (spawn→wait→respawn only; no mid-task steering)
6
+ waves=4 sizes=[2,1,1,1] workers=5 settled=5 cancelled=0
7
+ concurrency max=2 utilization=0.663 idle=15.6min (48.3%) wall=32.2min
8
+ respawns=3 evidence→respawn=3 blind-respawn=0 depth=1
9
+ accepted=3 rejected=1 empty-pass=1
10
+ brain=$0.179577 total=$0.179577 judge.resolved=false score=0.4333 verify=unavailable — result.json absent or has no verify_pass
11
+ gaps(1): verifyPass: result.json absent or has no verify_pass
12
+ ```
13
+
14
+ - Cell dir: `/tmp/factory-gen0-live/rep-0/runs/factory.agent-eval.309/FSUP0`
15
+ - Supervisor: `sup-1-8f75ee`
16
+ - Generated: 2026-07-24T00:32:17.691Z
17
+
18
+ ## Orchestration
19
+
20
+ | Metric | Value |
21
+ |---|---|
22
+ | Workers spawned | 5 |
23
+ | Workers settled | 5 |
24
+ | Workers cancelled | 0 |
25
+ | **Steers (mid-task messages to live workers)** | **0** |
26
+ | Steers delivered | 0 |
27
+ | Outer-driver `supervisor_steer` calls | 0 |
28
+ | Spawn waves | 4 |
29
+ | Wave sizes | [2, 1, 1, 1] |
30
+ | Max concurrency | 2 |
31
+ | Respawns (spawns after first settle) | 3 |
32
+ | Repeated labels | none |
33
+ | Delegation depth | 1 |
34
+ | Time to first spawn | 13.9min |
35
+ | Supervisor wall | 32.2min |
36
+ | Idle (zero live workers) | 15.6min (48.3%) |
37
+ | Worker utilization (Σ worker wall ÷ supervisor wall) | 0.663 |
38
+
39
+ ### Steers per worker
40
+
41
+ | Worker | Queued | Delivered |
42
+ |---|---:|---:|
43
+ | `w-0` | 0 | 0 |
44
+ | `w-1` | 0 | 0 |
45
+ | `w-2` | 0 | 0 |
46
+ | `w-3` | 0 | 0 |
47
+ | `w-4` | 0 | 0 |
48
+
49
+ ## Decision quality
50
+
51
+ | Metric | Value |
52
+ |---|---|
53
+ | Settled by status | done=5 |
54
+ | Settled verdicts | none |
55
+ | Accepted (verify green + patch bytes) | 3 |
56
+ | Rejected (verify red) | 1 |
57
+ | Empty pass (green, no patch) | 1 |
58
+ | Evidence → respawn sequences | 3 |
59
+ | Respawn with no settled evidence in front | 0 |
60
+ | Review actions (steers + worker questions) | 0 |
61
+ | Worker evidence returned | 12153 bytes |
62
+
63
+ ## Economics
64
+
65
+ | Role | Tokens in | Tokens out | USD | Source |
66
+ |---|---:|---:|---:|---|
67
+ | brain | 228169 | 19398 | 0.179577 | journal metered events (n=17) |
68
+ | workers | 286763 | 69794 | 0 | journal settled spend + opencode sessions (n=5) |
69
+
70
+ - Total USD: 0.179577 (source: state.json result.spentUsd — brain-priced only; worker CLI inference is unpriced (see worker token counts))
71
+ - Cost per accepted patch: 0.059859
72
+ - Worker wall (n=5): min 70.4s / p50 3.9min / p90 9.3min / max 9.3min / Σ 21.2min
73
+
74
+ | Worker | Wall | Patch bytes | Verify passed |
75
+ |---|---:|---:|---|
76
+ | `w-0` | 9.3min | 21183 | false |
77
+ | `w-1` | 4.7min | 14573 | true |
78
+ | `w-2` | 70.4s | 0 | true |
79
+ | `w-3` | 3.9min | 21325 | true |
80
+ | `w-4` | 2.2min | 1016 | true |
81
+
82
+ ## Outcome
83
+
84
+ | Metric | Value |
85
+ |---|---|
86
+ | Supervisor status | completed |
87
+ | Supervisor verdict | delivered |
88
+ | Delivered | true |
89
+ | Judge resolved | false |
90
+ | Judge score | 0.4333 |
91
+ | Judge passed / total | 13 / 30 |
92
+ | Judge source | /tmp/factory-gen0-live/ledger.jsonl (ledger row) |
93
+ | Verify gate | pass=unavailable — result.json absent or has no verify_pass rc=unavailable — result.json absent or has no verify_rc |
94
+ | Patch | 5 file(s), +939/-0, test files touched: src/capability-headroom.test.ts, src/paired-arms.test.ts |
95
+
96
+ ## Gaps
97
+
98
+ - verifyPass: result.json absent or has no verify_pass
99
+
100
+ > Harness-session view of the same cell (model calls, stuck loops, tool errors): `npx --yes @tangle-network/traces@latest analyze --harness opencode --cwd <worker-clone-cwd>`
@@ -0,0 +1,551 @@
1
+ {
2
+ "schema": "swe-arena/run-report-rollup@1",
3
+ "cells": 51,
4
+ "steersTotal": 0,
5
+ "cellsWithSteers": 0,
6
+ "cellsWithUnavailableSteers": 9,
7
+ "wavesMean": 3.137,
8
+ "maxConcurrencyMax": 2,
9
+ "utilizationMean": 0.474,
10
+ "idlePctMean": 52.618,
11
+ "workersSpawnedTotal": 161,
12
+ "acceptedTotal": 35,
13
+ "usdTotal": 3.258497,
14
+ "resolvedCount": 17,
15
+ "perCell": [
16
+ {
17
+ "instanceId": "astropy__astropy-13033",
18
+ "arm": "R4",
19
+ "steers": 0,
20
+ "waves": 2,
21
+ "utilization": 0.803,
22
+ "idlePct": 19.7,
23
+ "resolved": false,
24
+ "usd": 0.049903
25
+ },
26
+ {
27
+ "instanceId": "django__django-11532",
28
+ "arm": "R4",
29
+ "steers": 0,
30
+ "waves": 2,
31
+ "utilization": 0.702,
32
+ "idlePct": 29.8,
33
+ "resolved": false,
34
+ "usd": 0.036822
35
+ },
36
+ {
37
+ "instanceId": "matplotlib__matplotlib-20826",
38
+ "arm": "R4",
39
+ "steers": 0,
40
+ "waves": 10,
41
+ "utilization": 0.801,
42
+ "idlePct": 19.9,
43
+ "resolved": false,
44
+ "usd": 0.224134
45
+ },
46
+ {
47
+ "instanceId": "pydata__xarray-4687",
48
+ "arm": "R4",
49
+ "steers": 0,
50
+ "waves": 5,
51
+ "utilization": 0.831,
52
+ "idlePct": 16.9,
53
+ "resolved": false,
54
+ "usd": 0.096077
55
+ },
56
+ {
57
+ "instanceId": "pytest-dev__pytest-6197",
58
+ "arm": "R4",
59
+ "steers": 0,
60
+ "waves": 14,
61
+ "utilization": 0.308,
62
+ "idlePct": 69.9,
63
+ "resolved": false,
64
+ "usd": 0.189169
65
+ },
66
+ {
67
+ "instanceId": "sphinx-doc__sphinx-9658",
68
+ "arm": "R4",
69
+ "steers": 0,
70
+ "waves": 4,
71
+ "utilization": 0.574,
72
+ "idlePct": 42.6,
73
+ "resolved": true,
74
+ "usd": 0.085226
75
+ },
76
+ {
77
+ "instanceId": "astropy__astropy-13033",
78
+ "arm": "R4",
79
+ "steers": 0,
80
+ "waves": 2,
81
+ "utilization": 0.833,
82
+ "idlePct": 16.7,
83
+ "resolved": false,
84
+ "usd": 0.033692
85
+ },
86
+ {
87
+ "instanceId": "django__django-11532",
88
+ "arm": "R4",
89
+ "steers": 0,
90
+ "waves": 2,
91
+ "utilization": 0.546,
92
+ "idlePct": 45.4,
93
+ "resolved": false,
94
+ "usd": 0.079202
95
+ },
96
+ {
97
+ "instanceId": "matplotlib__matplotlib-20826",
98
+ "arm": "R4",
99
+ "steers": 0,
100
+ "waves": 4,
101
+ "utilization": 0.749,
102
+ "idlePct": 25.1,
103
+ "resolved": false,
104
+ "usd": 0.107538
105
+ },
106
+ {
107
+ "instanceId": "pydata__xarray-4687",
108
+ "arm": "R4",
109
+ "steers": 0,
110
+ "waves": 2,
111
+ "utilization": 0.722,
112
+ "idlePct": 27.8,
113
+ "resolved": true,
114
+ "usd": 0.040083
115
+ },
116
+ {
117
+ "instanceId": "pytest-dev__pytest-6197",
118
+ "arm": "R4",
119
+ "steers": 0,
120
+ "waves": 4,
121
+ "utilization": 0.458,
122
+ "idlePct": 54.2,
123
+ "resolved": false,
124
+ "usd": 0.072682
125
+ },
126
+ {
127
+ "instanceId": "sphinx-doc__sphinx-9658",
128
+ "arm": "R4",
129
+ "steers": 0,
130
+ "waves": 5,
131
+ "utilization": 0.611,
132
+ "idlePct": 38.9,
133
+ "resolved": true,
134
+ "usd": 0.063746
135
+ },
136
+ {
137
+ "instanceId": "astropy__astropy-13033",
138
+ "arm": "R4",
139
+ "steers": 0,
140
+ "waves": 3,
141
+ "utilization": 0.817,
142
+ "idlePct": 18.3,
143
+ "resolved": true,
144
+ "usd": 0.064968
145
+ },
146
+ {
147
+ "instanceId": "django__django-11532",
148
+ "arm": "R4",
149
+ "steers": {
150
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-0/runs/django__django-11532/R4/ws/.loops/supervisor/sup-1-4b0be0"
151
+ },
152
+ "waves": 0,
153
+ "utilization": 0,
154
+ "idlePct": 100,
155
+ "resolved": false,
156
+ "usd": 0
157
+ },
158
+ {
159
+ "instanceId": "matplotlib__matplotlib-20826",
160
+ "arm": "R4",
161
+ "steers": {
162
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-0/runs/matplotlib__matplotlib-20826/R4/ws/.loops/supervisor/sup-1-2c15b1"
163
+ },
164
+ "waves": 0,
165
+ "utilization": 0,
166
+ "idlePct": 100,
167
+ "resolved": false,
168
+ "usd": 0
169
+ },
170
+ {
171
+ "instanceId": "pydata__xarray-4687",
172
+ "arm": "R4",
173
+ "steers": 0,
174
+ "waves": 2,
175
+ "utilization": 0.473,
176
+ "idlePct": 52.7,
177
+ "resolved": true,
178
+ "usd": 0.043101
179
+ },
180
+ {
181
+ "instanceId": "pytest-dev__pytest-6197",
182
+ "arm": "R4",
183
+ "steers": 0,
184
+ "waves": 13,
185
+ "utilization": 0.352,
186
+ "idlePct": 64.8,
187
+ "resolved": false,
188
+ "usd": 0.222542
189
+ },
190
+ {
191
+ "instanceId": "sphinx-doc__sphinx-9658",
192
+ "arm": "R4",
193
+ "steers": {
194
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-0/runs/sphinx-doc__sphinx-9658/R4/ws/.loops/supervisor/sup-1-cd137b"
195
+ },
196
+ "waves": 0,
197
+ "utilization": 0,
198
+ "idlePct": 100,
199
+ "resolved": false,
200
+ "usd": 0
201
+ },
202
+ {
203
+ "instanceId": "astropy__astropy-13033",
204
+ "arm": "R4",
205
+ "steers": 0,
206
+ "waves": 1,
207
+ "utilization": 0.321,
208
+ "idlePct": 67.9,
209
+ "resolved": false,
210
+ "usd": 0.014523
211
+ },
212
+ {
213
+ "instanceId": "django__django-11532",
214
+ "arm": "R4",
215
+ "steers": {
216
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-1/runs/django__django-11532/R4/ws/.loops/supervisor/sup-1-c84e92"
217
+ },
218
+ "waves": 0,
219
+ "utilization": 0,
220
+ "idlePct": 100,
221
+ "resolved": false,
222
+ "usd": 0
223
+ },
224
+ {
225
+ "instanceId": "matplotlib__matplotlib-20826",
226
+ "arm": "R4",
227
+ "steers": 0,
228
+ "waves": 2,
229
+ "utilization": 0.305,
230
+ "idlePct": 69.5,
231
+ "resolved": true,
232
+ "usd": 0.028989
233
+ },
234
+ {
235
+ "instanceId": "pydata__xarray-4687",
236
+ "arm": "R4",
237
+ "steers": 0,
238
+ "waves": 4,
239
+ "utilization": 0.648,
240
+ "idlePct": 35.2,
241
+ "resolved": true,
242
+ "usd": 0.081441
243
+ },
244
+ {
245
+ "instanceId": "pytest-dev__pytest-6197",
246
+ "arm": "R4",
247
+ "steers": {
248
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-1/runs/pytest-dev__pytest-6197/R4/ws/.loops/supervisor/sup-1-d7b670"
249
+ },
250
+ "waves": 0,
251
+ "utilization": 0,
252
+ "idlePct": 100,
253
+ "resolved": false,
254
+ "usd": 0
255
+ },
256
+ {
257
+ "instanceId": "sphinx-doc__sphinx-9658",
258
+ "arm": "R4",
259
+ "steers": {
260
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/31fc08bd3a/rep-1/runs/sphinx-doc__sphinx-9658/R4/ws/.loops/supervisor/sup-1-37e35d"
261
+ },
262
+ "waves": 0,
263
+ "utilization": 0,
264
+ "idlePct": 100,
265
+ "resolved": false,
266
+ "usd": 0
267
+ },
268
+ {
269
+ "instanceId": "astropy__astropy-13033",
270
+ "arm": "R4",
271
+ "steers": {
272
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/a7a2a982e5/rep-0/runs/astropy__astropy-13033/R4/ws/.loops/supervisor/sup-1-4b8aff"
273
+ },
274
+ "waves": 0,
275
+ "utilization": 0,
276
+ "idlePct": 100,
277
+ "resolved": false,
278
+ "usd": 0
279
+ },
280
+ {
281
+ "instanceId": "django__django-11532",
282
+ "arm": "R4",
283
+ "steers": 0,
284
+ "waves": 2,
285
+ "utilization": 0.447,
286
+ "idlePct": 55.3,
287
+ "resolved": true,
288
+ "usd": 0.042501
289
+ },
290
+ {
291
+ "instanceId": "matplotlib__matplotlib-20826",
292
+ "arm": "R4",
293
+ "steers": 0,
294
+ "waves": 2,
295
+ "utilization": 0.233,
296
+ "idlePct": 76.7,
297
+ "resolved": false,
298
+ "usd": 0.028501
299
+ },
300
+ {
301
+ "instanceId": "pydata__xarray-4687",
302
+ "arm": "R4",
303
+ "steers": 0,
304
+ "waves": 3,
305
+ "utilization": 0.847,
306
+ "idlePct": 15.3,
307
+ "resolved": true,
308
+ "usd": 0.070831
309
+ },
310
+ {
311
+ "instanceId": "pytest-dev__pytest-6197",
312
+ "arm": "R4",
313
+ "steers": 0,
314
+ "waves": 2,
315
+ "utilization": 0.14,
316
+ "idlePct": 86,
317
+ "resolved": false,
318
+ "usd": 0.029033
319
+ },
320
+ {
321
+ "instanceId": "sphinx-doc__sphinx-9658",
322
+ "arm": "R4",
323
+ "steers": {
324
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/a7a2a982e5/rep-0/runs/sphinx-doc__sphinx-9658/R4/ws/.loops/supervisor/sup-1-d97029"
325
+ },
326
+ "waves": 0,
327
+ "utilization": 0,
328
+ "idlePct": 100,
329
+ "resolved": false,
330
+ "usd": 0
331
+ },
332
+ {
333
+ "instanceId": "astropy__astropy-13033",
334
+ "arm": "R4",
335
+ "steers": 0,
336
+ "waves": 2,
337
+ "utilization": 0.482,
338
+ "idlePct": 51.8,
339
+ "resolved": false,
340
+ "usd": 0.037866
341
+ },
342
+ {
343
+ "instanceId": "django__django-11532",
344
+ "arm": "R4",
345
+ "steers": 0,
346
+ "waves": 3,
347
+ "utilization": 0.388,
348
+ "idlePct": 61.2,
349
+ "resolved": true,
350
+ "usd": 0.059868
351
+ },
352
+ {
353
+ "instanceId": "matplotlib__matplotlib-20826",
354
+ "arm": "R4",
355
+ "steers": {
356
+ "unavailable": "workers/ directory absent under /tmp/claude-1000/-home-drew-code-supervisor-lab/f06fd156-042a-4ef9-bd88-f2ec7f52b90c/scratchpad/hh/gen3/arm-runs/a7a2a982e5/rep-1/runs/matplotlib__matplotlib-20826/R4/ws/.loops/supervisor/sup-1-eab778"
357
+ },
358
+ "waves": 0,
359
+ "utilization": 0,
360
+ "idlePct": 100,
361
+ "resolved": false,
362
+ "usd": 0
363
+ },
364
+ {
365
+ "instanceId": "pydata__xarray-4687",
366
+ "arm": "R4",
367
+ "steers": 0,
368
+ "waves": 2,
369
+ "utilization": 0.714,
370
+ "idlePct": 28.6,
371
+ "resolved": true,
372
+ "usd": 0.044491
373
+ },
374
+ {
375
+ "instanceId": "pytest-dev__pytest-6197",
376
+ "arm": "R4",
377
+ "steers": 0,
378
+ "waves": 5,
379
+ "utilization": 0.566,
380
+ "idlePct": 43.4,
381
+ "resolved": false,
382
+ "usd": 0.108311
383
+ },
384
+ {
385
+ "instanceId": "sphinx-doc__sphinx-9658",
386
+ "arm": "R4",
387
+ "steers": 0,
388
+ "waves": 4,
389
+ "utilization": 0.359,
390
+ "idlePct": 64.1,
391
+ "resolved": true,
392
+ "usd": 0.060977
393
+ },
394
+ {
395
+ "instanceId": "astropy__astropy-13033",
396
+ "arm": "R4",
397
+ "steers": 0,
398
+ "waves": 2,
399
+ "utilization": 0.834,
400
+ "idlePct": 16.6,
401
+ "resolved": false,
402
+ "usd": 0.04263
403
+ },
404
+ {
405
+ "instanceId": "django__django-11532",
406
+ "arm": "R4",
407
+ "steers": 0,
408
+ "waves": 3,
409
+ "utilization": 0.394,
410
+ "idlePct": 60.6,
411
+ "resolved": false,
412
+ "usd": 0.068403
413
+ },
414
+ {
415
+ "instanceId": "matplotlib__matplotlib-20826",
416
+ "arm": "R4",
417
+ "steers": 0,
418
+ "waves": 5,
419
+ "utilization": 0.588,
420
+ "idlePct": 41.2,
421
+ "resolved": false,
422
+ "usd": 0.110963
423
+ },
424
+ {
425
+ "instanceId": "pydata__xarray-4687",
426
+ "arm": "R4",
427
+ "steers": 0,
428
+ "waves": 3,
429
+ "utilization": 0.82,
430
+ "idlePct": 18,
431
+ "resolved": true,
432
+ "usd": 0.084503
433
+ },
434
+ {
435
+ "instanceId": "pytest-dev__pytest-6197",
436
+ "arm": "R4",
437
+ "steers": 0,
438
+ "waves": 3,
439
+ "utilization": 0.281,
440
+ "idlePct": 71.9,
441
+ "resolved": false,
442
+ "usd": 0.079547
443
+ },
444
+ {
445
+ "instanceId": "sphinx-doc__sphinx-9658",
446
+ "arm": "R4",
447
+ "steers": 0,
448
+ "waves": 5,
449
+ "utilization": 0.649,
450
+ "idlePct": 35.1,
451
+ "resolved": true,
452
+ "usd": 0.068044
453
+ },
454
+ {
455
+ "instanceId": "astropy__astropy-13033",
456
+ "arm": "R4",
457
+ "steers": 0,
458
+ "waves": 4,
459
+ "utilization": 0.85,
460
+ "idlePct": 15,
461
+ "resolved": false,
462
+ "usd": 0.096642
463
+ },
464
+ {
465
+ "instanceId": "django__django-11532",
466
+ "arm": "R4",
467
+ "steers": 0,
468
+ "waves": 2,
469
+ "utilization": 0.244,
470
+ "idlePct": 75.6,
471
+ "resolved": false,
472
+ "usd": 0.047655
473
+ },
474
+ {
475
+ "instanceId": "matplotlib__matplotlib-20826",
476
+ "arm": "R4",
477
+ "steers": 0,
478
+ "waves": 7,
479
+ "utilization": 0.76,
480
+ "idlePct": 24,
481
+ "resolved": false,
482
+ "usd": 0.161885
483
+ },
484
+ {
485
+ "instanceId": "pydata__xarray-4687",
486
+ "arm": "R4",
487
+ "steers": 0,
488
+ "waves": 5,
489
+ "utilization": 0.528,
490
+ "idlePct": 47.2,
491
+ "resolved": true,
492
+ "usd": 0.084818
493
+ },
494
+ {
495
+ "instanceId": "pytest-dev__pytest-6197",
496
+ "arm": "R4",
497
+ "steers": 0,
498
+ "waves": 5,
499
+ "utilization": 0.263,
500
+ "idlePct": 73.7,
501
+ "resolved": true,
502
+ "usd": 0.122129
503
+ },
504
+ {
505
+ "instanceId": "sphinx-doc__sphinx-9658",
506
+ "arm": "R4",
507
+ "steers": 0,
508
+ "waves": 2,
509
+ "utilization": 0.514,
510
+ "idlePct": 48.6,
511
+ "resolved": true,
512
+ "usd": 0.0709
513
+ },
514
+ {
515
+ "instanceId": "astropy__astropy-13033",
516
+ "arm": "R4",
517
+ "steers": 0,
518
+ "waves": 3,
519
+ "utilization": 0.789,
520
+ "idlePct": 21.1,
521
+ "resolved": {
522
+ "unavailable": "judge.json absent"
523
+ },
524
+ "usd": 0.079491
525
+ },
526
+ {
527
+ "instanceId": "astropy__astropy-13033",
528
+ "arm": "R4",
529
+ "steers": 0,
530
+ "waves": 2,
531
+ "utilization": 0.846,
532
+ "idlePct": 15.4,
533
+ "resolved": {
534
+ "unavailable": "judge.json absent"
535
+ },
536
+ "usd": 0.040525
537
+ },
538
+ {
539
+ "instanceId": "astropy__astropy-13033",
540
+ "arm": "R4",
541
+ "steers": 0,
542
+ "waves": 3,
543
+ "utilization": 0.782,
544
+ "idlePct": 21.8,
545
+ "resolved": {
546
+ "unavailable": "judge.json absent"
547
+ },
548
+ "usd": 0.084145
549
+ }
550
+ ]
551
+ }