ddmitry/adversarial-review
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(runner): изменена модель с haiku на sonnet

Browse Source 
- Зачем:
  - Sonnet обеспечивает лучшее соотношение цена/качество для runner subagent.
- Что:
  - AGENTS.md: обновлено описание runner subagent (model: haiku → sonnet).
  - SKILL.md: обновлены все ссылки на модель runner в Agent tool и документации.
  - docs/DESIGN.md: обновлено описание модели в §12.5 и §12.6.
- Проверка:
  - git diff HEAD~1 -- AGENTS.md SKILL.md docs/DESIGN.md.
This commit is contained in:
ddadmin
2026-04-26 00:26:49 +03:00
parent 9cff0c7986
commit 983a7a04ff
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+1 -1
View File
@@ -31,7 +31,7 @@ The skill runs in two processes:
**Main orchestrator** (`SKILL.md`, main Claude thread): mode detection, REVIEW_ID, REPO_ROOT capture, review-material prep (Steps 1-3), review display (Step 5), code fixes (Step 6), final summary (Step 8), cleanup (Step 9), and round counting.
**Runner subagent** (`references/runner.md`, dispatched via Claude Code's Agent tool with `model: haiku`): builds the launch prompt with per-attempt session marker, invokes `codex exec` (or resume or fresh-exec), runs strict checks on the result, captures the session id via two-tier lookup (primary JSONL `thread_id`, secondary rollout content-match), retries once on infrastructure failure, returns a small JSON summary.
**Runner subagent** (`references/runner.md`, dispatched via Claude Code's Agent tool with `model: sonnet`): builds the launch prompt with per-attempt session marker, invokes `codex exec` (or resume or fresh-exec), runs strict checks on the result, captures the session id via two-tier lookup (primary JSONL `thread_id`, secondary rollout content-match), retries once on infrastructure failure, returns a small JSON summary.
**Why the split:** Every codex-exec invocation produces stdout JSONL, a stderr file, and a rollout file under `~/.codex/sessions/`. Keeping these inside the subagent means the main thread's context never sees them — only the final review markdown (~5K) flows back. This eliminates the ~48M-token cache-read residue observed before the split.