Felipe Coury 8d3c6cc13d Preserve conversation context and separate next actions in recaps (#45090) ...

## Why

The 900-byte recap prompt limit leaves little room for completed progress, unresolved caveats, and recent corrections. Recaps need this context to distinguish completed work from pending requests.

## What changed

- Introduce a shared `RecapPrompt` with a 32 KiB ceiling for instructions and history, using an 8,192-token estimate. Instruct summaries to retain the broader goal, completed outcomes, and unresolved availability or validation caveats.
- Select up to eight answered exchanges plus a pending request, preserving adjacent steering and progress messages. Drop older whole exchanges before excerpting both ends of oversized messages, while retaining the newest answer and pending correction.
- Require a `summary` and nullable `next_action`, bounded to 700 and 200 characters respectively. Reject malformed or oversized responses and display an optional, separately styled `Next:` line.

## Testing

Add coverage for UTF-8 prompt bounds, exchange selection, pending corrections, excerpt boundaries, strict response parsing, and next-action rendering. Extend the recap generation integration test to verify bounded history and the structured response schema.

GitOrigin-RevId: 6c6a84bc602a168418c1952feb1d286ec0cb9e28

2026-09-12 18:16:17 +00:00

..

src

Preserve conversation context and separate next actions in recaps (#45090)

2026-09-12 18:16:17 +00:00

BUILD.bazel

…

Cargo.toml

Disable empty Cargo test targets (#21584)

2026-05-07 15:44:17 -07:00