Answer product-owner round 1: 0 🔴, 1 🟡 (0 misread); the failure names the shortfall in e062f71d, and item 298 records claude-config's judge room

This commit is contained in:
Lilleman
2026-11-20 01:24:24 +01:00
parent e062f71d47
commit b76a3bcf24
+2
View File
@@ -531,6 +531,8 @@ Found by review of PR #317. The black-box test, `bin/loop_claude/test_black_box.
153 `Judge cost:` entries total $109.76, a median of about $0.76 a verdict at every rung, and the cost follows the size of the records, not the transcript: about 76k characters in log and 188k in claude-config. In 224 of 251 recent verdicts (89%) the evidence sits in the worker's final message. A missed interrupt is the costly error, so the bar is zero changed interrupts and zero new rejections across the replay. The judge is about 4.5% of dollars, so the saving is small; each cycle also gets faster.
On 2026-11-20, with docs/decisions.md read once, claude-config's records take 285,754 characters. With a short task they leave the transcript about 107,500 of the judge's 400,000 characters, some 57,500 above the 50,000 it must read. The decision log grows about 4,000 characters a day, so the judge stops on claude-config, naming the shortfall, in about two weeks unless this item ships first.
Touches:
- `bin/agent_cycle/judge.py`: `Brief`, `judge_prompt`, `JUDGE_PROMPT_CHARS`
- `bin/chunk_driver/project/records.py`: `read_records`