Skip to content

Blog

Releasesv0.19.6

v0.19.6 — cheaper skill-card injection

This is the release note as published, not a rewrite of it. Release notes are published in the language they were written in.

The self-evolution flywheel's card-reading loop (injecting learned reasoning cards into the agent's context) was kept opt-in mostly because injection cost +~349% tokens on short tasks. This release cuts that ~7–9×.

Changed

  • Skill-card injection is ~7–9× cheaper. Three levers, measured over two runs on the hard suite:
    • inject the single best card (CHIMERA_SKILL_CARDS_K=1, was 3),
    • a relevance gate (CHIMERA_SKILL_CARDS_MIN_OVERLAP=2) — a task with no strong match (< 2 shared query terms) injects nothing, so it pays no tokens and gets no misleading card,
    • a shorter render (CHIMERA_SKILL_CARDS_MAX_LINES=3). Overhead dropped from +~349% to ~+37–48%, now under the registered +50% flip gate. These are the new defaults (they only apply when card reading is opted in).

Honest note

The M19-A1 default (reading cards automatically) still stays OFF — the cost blocker is removed, but the accuracy lift isn't statistically significant at n=12 (it swung +16.7pp → −8.3pp between identical free-model runs). Flipping it now waits on a larger paired A/B, not on code. See bench/skillcard/RESULTS.md.

Gate: 1460 passed / 3 skipped, mypy + ruff green.

Upgrade: `pip install --upgrade 'chimera-agent[full]'`

Read the release on GitHub