jeffusion ec2029a942 feat(review): add token-aware context control with tokenlens ...

Replace hardcoded char-count context limits with token-based budgets using
tokenlens (data from models.dev). TokenCounter provides 3-tier context window
lookup: dynamic catalog (refreshed every 24h) → static tokenlens → 128k default.

- specialist-agent: token budget from model context window instead of MAX_CONTEXT_CHARS=100k
- critic-agent/reflexion-agent: tokenCounter.clip() instead of diff.slice(0, 3000/2000)
- diff-extractor: raw diff clipping at 30k tokens
- engine.ts: refreshCatalog() at startup, stopRefresh() at shutdown

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

2026-03-24 12:30:13 +08:00

1.5 KiB

Raw Blame History

View Raw