Files
OpenJarvis/tests
Andrew ParkandClaude Opus 4.7 7f432453e1 hybrid: track tool_calls per row across all paradigms
results-table.md caveat (3) flagged that tool_calls was missing from
results.jsonl for every paradigm and the legacy skillorchestra values
came from a defunct telemetry path. Wire the count back through the
canonical row-write path so future ablation cells populate it.

Definition per paradigm:
  - SWE-bench: sum of bash turns from each run_swe_agent_loop subloop
    (one tool call = one bash command the agent ran).
  - GAIA: native web_search invocations from the cloud backbone. Zero
    on one-shot GAIA paths and on paradigms whose GAIA path is pure
    text passing (minions w/o prefetch).

runner._run_one now reads meta["tool_calls"] into the top-level row;
summary.json picks up tool_calls_total. Existing n=100 rows stay "—"
(no rerun).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 13:32:04 -07:00
..
2026-04-20 15:33:51 -07:00
2026-03-12 17:29:39 +00:00
2026-04-17 15:22:17 -07:00
2026-03-31 19:25:29 +05:30
2026-04-17 15:22:17 -07:00
2026-03-12 17:29:39 +00:00