nisse

Merge pull request 'Keep runs with different tuning apart in the report, and raise max_turns to 40' (#52 ) from report-keeps-tuning-apart into main

CI #142:Commit f2c48d8b16 pushed by dongar

main

2026-09-27 22:44:41 +00:00

1m13s

Keep runs with different tuning apart in the report, and raise max_turns to 40

CI #141:Commit f881a18ca4 pushed by dev-agent

#52

2026-09-27 22:27:16 +00:00

1m11s

Merge pull request 'Render one assistant message per turn, and make the request timeout a setting' (#51 ) from fix-transcript-and-timeout into main

CI #140:Commit a77c84c128 pushed by dev-agent

main

2026-09-27 22:26:05 +00:00

1m11s

Keep runs with different tuning apart in the report, and raise max_turns to 40

CI #139:Commit 570da5784e pushed by dev-agent

#52

2026-09-27 22:21:16 +00:00

1m15s

Render one assistant message per turn, and make the request timeout a setting

CI #138:Commit d49435d4e5 pushed by dev-agent

#51

2026-09-27 22:16:50 +00:00

1m16s

Merge pull request 'Record rate-limit waits in benchmark runs, and leave them out of time' (#50 ) from record-rate-limit-retries into main

CI #137:Commit f41cbb00cf pushed by dev-agent

main

2026-09-27 21:25:10 +00:00

1m7s

Record rate-limit waits in benchmark runs, and leave them out of time

CI #136:Commit 4e45dfe06a pushed by dev-agent

#50

2026-09-27 20:58:35 +00:00

1m17s

Merge pull request 'Benchmark seven new RTX 4090 models, and local-fast on the 4090' (#49 ) from bench-4090 into main

CI #135:Commit a716d5ec8d pushed by dev-agent

main

2026-09-27 20:33:54 +00:00

1m8s

Merge pull request 'Point the example config at Opus 5.5, with Haiku as consultant' (#48 ) from example-opus-5-5 into main

CI #134:Commit 1cc8df8dab pushed by dev-agent

main

2026-09-27 20:32:46 +00:00

1m7s

Benchmark seven new RTX 4090 models, and local-fast on the 4090

CI #133:Commit 82f171c2f5 pushed by dev-agent

#49

2026-09-27 18:45:36 +00:00

1m16s

Point the example config at Opus 5.5, with Haiku as consultant

CI #132:Commit 3cb70c0656 pushed by dev-agent

#48

2026-09-25 20:24:03 +00:00

1m13s

Merge pull request 'Add an executor benchmark that keeps its results' (#47 ) from benchmark into main

CI #131:Commit 8a8d8dc27f pushed by dongar

main

2026-09-25 02:25:15 +00:00

1m15s

Add the local baseline: qwen3-8b-awq and qwen3-14b, 5 runs per task

CI #130:Commit 0cccfe1e94 pushed by dev-agent

#47

2026-09-25 01:26:32 +00:00

1m14s

Add an executor benchmark that keeps its results

CI #129:Commit 50b46821d7 pushed by dev-agent

#47

2026-09-25 00:36:40 +00:00

1m11s

Merge pull request 'Enforce the tool-call contract, asking servers only where it works' (#45 ) from enforce-tool-calls into main

CI #128:Commit b2bbf70b7b pushed by dongar

main

2026-09-25 00:06:45 +00:00

53s

Enforce the tool-call contract, asking servers only where it works

CI #127:Commit b934c46714 pushed by dev-agent

#45

2026-09-24 22:55:48 +00:00

56s

Merge pull request 'Fit every model request to its context window' (#44 ) from context-budget into main

CI #126:Commit 389b71a5d1 pushed by dongar

main

2026-09-24 13:42:18 +00:00

57s

Fit every model request to its context window

CI #125:Commit 494715efa9 pushed by dev-agent

#44

2026-09-24 00:27:29 +00:00

56s

Merge pull request 'Move configuration to YAML, and make the tuning knobs configurable' (#43 ) from yaml-config into main

CI #124:Commit 31851b7396 pushed by dongar

main

2026-09-23 23:50:43 +00:00

51s

Show which config key refers to each example secret

CI #123:Commit e1034a2cb7 pushed by dev-agent

#43

2026-09-23 23:45:58 +00:00

49s

Pass the capability matrix's models as a pytest option

CI #122:Commit 58b439088f pushed by dev-agent

#43

2026-09-23 23:33:41 +00:00

51s

Make the config file the only home for settings

CI #121:Commit 15d69799bf pushed by dev-agent

#43

2026-09-23 23:26:50 +00:00

51s

Move configuration to a YAML file, and make the tuning knobs configurable

CI #120:Commit df449c7e34 pushed by dev-agent

#43

2026-09-23 23:15:01 +00:00

52s

Merge pull request 'Add the operator kill switch, stop (A4)' (#41 ) from stop-command into main

CI #119:Commit 4a9354ae3b pushed by dongar

main

2026-09-23 22:51:41 +00:00

51s

Add the operator kill switch, stop (A4)

CI #118:Commit abb7fa0216 pushed by dev-agent

#41

2026-09-23 22:48:23 +00:00

49s

Merge pull request 'Gate ops writes on approved step sequences' (#39 ) from ops-gating into main

CI #117:Commit d2fe3d5642 pushed by dongar

main

2026-09-23 22:27:23 +00:00

1m8s

Wait a grace period before switching away from a waiting item

CI #116:Commit 019fa24517 pushed by dev-agent

#39

2026-09-23 22:17:43 +00:00

57s

Let the agent also switch on its own when the active item closes

CI #115:Commit a91252cb77 pushed by dev-agent

#39

2026-09-23 22:10:43 +00:00

57s

Give calls outside any work item an agent-level scope

CI #114:Commit 5b163f0c2e pushed by dev-agent

#39

2026-09-23 21:58:01 +00:00

50s

Let the model choose which ready work item to switch to

CI #113:Commit 854bddc680 pushed by dev-agent

#39

2026-09-23 21:55:14 +00:00

52s