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/hooks/src/lib.rs

@@ -2,6 +2,7 @@ mod config_rules;
 mod engine;
 pub(crate) mod events;
 mod legacy_notify;
+mod output_spill;
 mod registry;
 mod schema;
 mod types;