Add body_after_prefix auto-compact token limit scope (#22870)

## Why

`model_auto_compact_token_limit` has only been able to budget the full
active context. That makes it hard to set a small "growth since
compaction" budget for sessions that preserve a large carried window
prefix: the preserved prefix can consume the whole budget and force
immediate repeated compaction.

This PR adds an opt-in `body_after_prefix` scope so callers can apply
`model_auto_compact_token_limit` to sampled output and later growth
after the current carried prefix, while still forcing compaction before
the full model context window is exhausted.

## What changed

- Adds `AutoCompactTokenLimitScope` with the existing `total` behavior
as the default and a new `body_after_prefix` mode:
[`config_types.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/protocol/src/config_types.rs#L24-L37).
- Threads `model_auto_compact_token_limit_scope` through config loading,
`Config`, `core-api`, and app-server v2 schema/TypeScript generation.
- Records the first observed input-token count for a `body_after_prefix`
compaction window and uses it as the baseline when deciding whether the
scoped auto-compaction budget is exhausted:
[`turn.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/src/session/turn.rs#L743-L781).
- Keeps a hard context-window cap in `body_after_prefix`, so scoped
budgeting cannot let the active context overrun the usable window.

## Verification

Added compact-suite coverage for the two key behaviors:
`body_after_prefix` does not re-compact just because the carried prefix
is larger than the scoped budget, and it still compacts when the total
active context reaches the configured context window:
[`compact.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/tests/suite/compact.rs#L3003-L3128).

codex-rs/core/src/state/session_tests.rs

@@ -1,5 +1,6 @@
 use super::*;
 use crate::session::tests::make_session_configuration_for_tests;
+use crate::state::AutoCompactWindowSnapshot;
 use codex_protocol::protocol::CreditsSnapshot;
 use codex_protocol::protocol::RateLimitWindow;
 use pretty_assertions::assert_eq;
@@ -61,6 +62,24 @@ async fn set_rate_limits_defaults_limit_id_to_codex_when_missing() {
     );
 }
 
+#[tokio::test]
+async fn replace_history_clears_auto_compact_window_prefill_without_advancing() {
+    let session_configuration = make_session_configuration_for_tests().await;
+    let mut state = SessionState::new(session_configuration);
+
+    state.start_next_auto_compact_window();
+    state.set_auto_compact_window_estimated_prefill(/*tokens*/ 100);
+    state.replace_history(Vec::new(), /*reference_context_item*/ None);
+
+    assert_eq!(
+        state.auto_compact_window_snapshot(),
+        AutoCompactWindowSnapshot {
+            ordinal: 2,
+            prefill_input_tokens: None,
+        }
+    );
+}
+
 #[tokio::test]
 async fn set_rate_limits_defaults_to_codex_when_limit_id_missing_after_other_bucket() {
     let session_configuration = make_session_configuration_for_tests().await;