Add opt-in compaction after final responses (#46541)

## What changed

Add `model_post_turn_compact_threshold_percent` to trigger compaction after a final response when context usage reaches the configured percentage of the usable window or an existing auto-compaction limit. Accept values from `0` to `100`; omitted or zero disables the feature.

Skip post-turn compaction when input is pending, the turn is cancelled, or token-budget mode is enabled. Disable it for approval reviewers to avoid delaying approval completion, and record a distinct `PostTurn` analytics phase.

Buffer local post-turn summaries until compaction succeeds and require a nonempty assistant summary before replacing history. Log compaction failures without failing the completed turn, while still propagating interruptions and turn aborts.

GitOrigin-RevId: b616994175829bd83b5d7974f95dabb042a39a89

codex-rs/thread-manager-sample/src/main.rs

@@ -196,6 +196,7 @@ fn new_config(model: Option<String>, arg0_paths: Arg0DispatchPaths) -> anyhow::R
         model_context_window: None,
         model_auto_compact_token_limit: None,
         model_auto_compact_token_limit_scope: AutoCompactTokenLimitScope::Total,
+        model_post_turn_compact_threshold_percent: 0,
         model_provider_id,
         model_provider,
         personality: None,