File item 463: show the judge the transcript's tail whatever the size of the records
CI / tests (pull_request) Successful in 3m21s

This commit was merged in pull request #649.
This commit is contained in:
Lilleman
2026-11-19 23:59:38 +01:00
parent 5108ab97b9
commit ecc69835b8
+16 -1
View File
@@ -6,13 +6,14 @@
`Bar = 0.1`
`Next ID = 463`
`Next ID = 464`
## Items
| 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 |
| 452 | 0.14.0 | | | **Make do-epic's view of the Jira workflow settings: the statuses at which an issue unblocks the issues it blocks, and the moves the team's own automation makes, so do-epic makes none of those.** | 3 | 2 | 2 | 5 | 5 | 1.6 by 7, 1.5 by 3 | 2.1 |
| 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 |
@@ -90,6 +91,20 @@ Touches:
- `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:
- The 0.13.0 chunks of items 448, 455 and 451 each stopped after the judge failed three times.
- The chunk of items 458 and 459 drew four `unfinished` verdicts after it had merged, each quoting only the task.
The judge sees neither a merge nor a worker's question, so every chunk here loops until a human ends it. Item 460's fix, letting the judge quote the task, treated a symptom of this.
Keep the transcript's tail a floor of the budget. Where the head leaves less, cut the records or stop with a message that names their size, rather than send a blind prompt. The constant's comment sizes the budget for a 200,000-token context, so raise it only where the judge's model has room. Item 298 cuts the records for cost; this item only guarantees the transcript room. Write first the test that fails today: a brief whose records exceed the budget still shows the transcript's last message.
Touches:
- `bin/agent_cycle/judge.py`: `JUDGE_PROMPT_CHARS` (small), `judge_prompt` (small)
- `bin/agent_cycle/test_judge.py`: `JudgePrompt`
### 452. Make do-epic's view of the Jira workflow settings: the statuses at which an issue unblocks the issues it blocks, and the moves the team's own automation makes, so do-epic makes none of those.
do-epic counts an issue as done only where Jira's status category is done, and moves a finished chunk's issue to done itself, by `jira-finish-transition`. On a team whose CI moves issues through the workflow, both are wrong. On TW, CI moves an issue to Code Review when its pull request opens, to Release Ready when it merges, and to Done when it is deployed. So do-epic would move an issue to Done before it is deployed, and would hold every blocked issue until the blocker is deployed, though the team wants blocked work to start once the blocker's pull request merges.