felixxia-oai fcd90d8f07 Enforce complete request budgets for Guardian reviews (#44281) ...

## Why

Review evidence can fit its own limits while exceeding the reviewer context window once history, tools, output format, and reminders are included. Tool continuations can also push an existing review over budget.

## What changed

- Select evidence after tools and turn context are resolved, reserving request overhead and a 256-token margin. Omit optional evidence while preserving required sections, and reject required evidence that cannot fit.
- Keep incoming evidence pending until budget selection succeeds so cancellation and compaction cannot record unselected input in reusable history.
- Check the assembled prompt before sampling, including retries and tool continuations. Retry budget failures with summary compaction once per model step, and retire reviewers whose budgets remain exhausted. Avoid history-resetting token-budget compaction for this recovery.
- Record section costs after budget selection.

## Testing

Add unit and integration coverage for required-evidence rejection, optional-evidence omission, reminder overhead, cancellation safety, incoming-review and tool-continuation compaction, and reviewer retirement after ineffective compaction.

GitOrigin-RevId: 2f7ef191b3f46032d295ad363eb7debf9d7a9684

2026-09-09 19:21:08 +00:00

..

common

Remove the unused legacy remote compaction implementation (#44273)

2026-09-09 18:40:53 +00:00

remote_env_windows

Apply remote platform semantics to exec safety checks (#42113)

2026-09-01 18:24:56 +00:00

suite

Enforce complete request budgets for Guardian reviews (#44281)

2026-09-09 19:21:08 +00:00

all.rs

[codex] Use expect in integration tests (#28441)

2026-06-15 21:53:47 -07:00

responses_headers.rs

Sanitize credentials from Git remote metadata (#40713)

2026-08-25 21:34:05 +00:00