Andrew ParkandClaude Opus 4.7 08e37e294a fix: SWE cloud-loop silent termination + ablation sweep bench label ...

mini_swe_agent.py adds recovery nudges so the agent doesn't exit silently
when the cloud model produces an empty turn:
- _loop_cloud_openai: finish_reason='length' with empty content/tool_calls
  → re-prompt instead of breaking. Hit gpt-5-mini on SWE n=100 (caused 0-score
  exits with empty final_summary).
- _loop_cloud_gemini: MALFORMED_FUNCTION_CALL / MAX_TOKENS with empty parts
  → same recovery. Hit gemini-2.5-flash on SWE n=100 (24/100 tasks).
Also: proper Gemini Schema-shaped bash tool params, gpt-5-family handling,
missing is_gpt5_family import. 5 regression tests cover both recovery paths
and natural-stop sanity guards.

scripts/ablation/run_sweep.py parse_cell anchors on the n100 suffix and
walks left, so advisors-*-gaia-n100 cells report GAIA as bench instead of
'qwen27b'. Old logic only handled cloud-only/skillorchestra-qwen prefixes
explicitly.

Companion working-tree changes shipped here: Gemini price entries,
baseline_cloud module registration, swebench dataset variant note,
swebench_harness Modal cgroup-v2 patch (file write swallows
FileNotFoundError on cgroup paths so Modal v2 sandboxes don't die).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-17 18:36:57 -07:00

..

make_report.py

feat: wire native web_search into GAIA cells across paradigms

2026-05-17 17:55:18 -07:00

run_sweep.py

fix: SWE cloud-loop silent termination + ablation sweep bench label

2026-05-17 18:36:57 -07:00