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

codex-rs/Cargo.lock

@@ -2868,6 +2868,7 @@ dependencies = [
  "codex-plugin",
  "codex-protocol",
  "codex-utils-absolute-path",
+ "codex-utils-output-truncation",
  "futures",
  "pretty_assertions",
  "regex",
@@ -2876,6 +2877,8 @@ dependencies = [
  "serde_json",
  "tempfile",
  "tokio",
+ "tracing",
+ "uuid",
 ]
 
 [[package]]