mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-11 02:07:15 +01:00
Krzysztof kuhy Rudnicki
c5cd63fb80
Some checks are pending
Counting transcript records reports 1.00 tool calls per message no matter what the model did: the harness writes one JSONL record per tool_use block, all sharing message.id. A hand-rolled per-record count read the real 1.9% batching rate as 0.0%, which nearly shipped as a headline finding. Group by message.id instead, and report it, so the number comes from a tested code path with the window handled by find_transcripts rather than an ad-hoc timestamp. Three snapshot fields give next week's run a baseline. Axes was at the 12-attribute cap, so the counters live in their own Batching dataclass with the two ratios as properties. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NiSSDu4gKbp9GGxTTtXvYW |
||
|---|---|---|
| .. | ||
| explanations | ||
| superpowers | ||
| DOCS-agent-harness-evaluation-2026-08-18.md | ||
| DOCS-app-split-recipes.md | ||
| DOCS-device-owner-research.md | ||
| DOCS-dns-filtering-parked.md | ||
| DOCS-kcov-under-report.md | ||
| DOCS-python-split-recipes.md | ||
| DOCS-restructure-live-state.md | ||
| DOCS-shared-checkout-safety.md | ||
| DOCS-shell-split-harness.md | ||
| DOCS-shell-split-recipes.md | ||
| DOCS-shell-split-verification.md | ||
| DOCS-syncyomi-restore-runbook.md | ||
| mcp-shortlist.html | ||