Abhinav dca105cf99 Spill large hook outputs from context (#21069) ...

## Why

Large hook outputs can enter model-visible context through hook-specific
paths such as `additionalContext` and `Stop` continuation prompts.
Without a dedicated cap, one hook can inject a large blob directly into
conversation history instead of leaving a bounded preview for the model
and preserving the full text elsewhere.

## What

- spill hook text once it exceeds a fixed `2_500`-token budget,
preserving the full output on disk and leaving a head/tail preview plus
saved path in context
- add shared hook-output spilling under
`CODEX_HOME/hook_outputs/<thread_id>/<uuid>.txt`
- apply the cap to both `additionalContext`, `feedback_message`, and
`Stop` continuation fragments

dca105cf99 · 2026-05-05 05:03:18 +00:00

History

..

schema/generated

Support MCP tools in hooks (#18385)

2026-04-23 07:33:57 +00:00

src

Spill large hook outputs from context (#21069)

2026-05-05 05:03:18 +00:00

BUILD.bazel

start of hooks engine (#13276)

2026-03-10 04:11:31 +00:00

Cargo.toml

Spill large hook outputs from context (#21069)

2026-05-05 05:03:18 +00:00