This commit was merged in pull request #647.
This commit is contained in:
@@ -12,7 +12,6 @@
|
||||
|
||||
| ID | Release | Blocked by | Exempt | Item | L | E | I | R | S | Moves | Score |
|
||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||
| 460 | 0.14.0 | | | **Review the judge's fix for quoting the worker's task as evidence with every larv-review pass it fires, and adjust it to their findings.** | 2 | 2 | 3 | 5 | 2 | code health by 3, 1.1 by 5 | 7.2 |
|
||||
| 463 | 0.14.0 | | defect | **Show the judge the transcript's tail whatever the size of the records.** | 2 | 2 | 3 | 5 | 3 | 1.2 by 6, 1.5 by 4, 1.4 by 2 | 4.2 |
|
||||
| 449 | 0.14.0 | | | **Record do-epic's repo picks and sub-task summaries in the team's own spelling, such as `core-4` and `core-4: Bygg …`, as its config sets them.** | 2 | 2 | 2 | 4 | 3 | 1.6 by 6 | 2.0 |
|
||||
| 453 | 0.14.0 | | | **Make the issue types that do-epic and `todo-item add` file in Jira settings, since a Jira project such as TW has no Task type.** | 2 | 2 | 1 | 3 | 2 | 1.6 by 5 | 1.8 |
|
||||
@@ -78,18 +77,6 @@
|
||||
|
||||
## Details
|
||||
|
||||
### 460. Review the judge's fix for quoting the worker's task as evidence with every larv-review pass it fires, and adjust it to their findings.
|
||||
|
||||
The fix shipped without any larv-review pass, reviewer or comprehension check, at lilleman's request on 2026-11-19, so loop-claude could run unattended again: PR #641, commit "Let the judge quote the worker's task as evidence". Before it, the judge read the task above the transcript's tail but `quotes_checked` checked the evidence only against that tail. Once a session outgrew the tail, a verdict quoting the task, such as `Do the next chunk in 0.13.0`, was rejected three times running, and the loop exited after each merged chunk (items 448, 455 and 451). `Grounds` now carries the task, and the evidence must appear in the task, then the tail.
|
||||
|
||||
Run the passes the change fires: security, stability (with `~/.claude/rules/this-machine/cross-repo-review.md` where it applies), prose for the comments and docstrings it changed, and overrides if `rule-hook overrides` prints a line. Run the comprehension check where `larv-review` says one is due. Also weigh whether the evidence schema's description ("a verbatim quote of the one transcript passage") should name the task too, and whether `misquoted_evidence`'s message should say "the task or the transcript".
|
||||
|
||||
Touches:
|
||||
- `bin/agent_cycle/judge.py`: `Grounds` (small), `quotes_checked` (small), `judge_prompt` (small)
|
||||
- `bin/judge_replay/archived_prompt.py`: `grounds_of` (small)
|
||||
- `bin/agent_cycle/test_judge.py`
|
||||
- `bin/judge_replay/test_judge_replay.py`
|
||||
|
||||
### 463. Show the judge the transcript's tail whatever the size of the records.
|
||||
|
||||
`judge_prompt` in `bin/agent_cycle/judge.py` gives the transcript only what `JUDGE_PROMPT_CHARS = 400000` leaves after the premises, the records and the rules. In claude-config those now take about 519,000 to 523,000 characters, so `room` clamps to 0 and the judge reads the task above an empty transcript. Every judge prompt archived for claude-config since at least 2026-11-19 17:16 shows none:
|
||||
|
||||
Reference in New Issue
Block a user