[codex] Add internal auto-compaction opt-out (#28260)

## Summary

- add a default-on `auto_compaction` feature flag as an internal escape
hatch
- skip pre-turn, model-switch/hash, and mid-turn automatic compaction
when the flag is disabled
- preserve manual `/compact` behavior and surface the existing
context-window error when the provider runs out of room
- add integration coverage for disabled pre-turn and mid-turn compaction

## Motivation

Long-running SPO optimization rollouts need the option to preserve their
full context and fail on context exhaustion instead of entering another
compaction window. This deliberately uses the existing feature-flag
mechanism rather than adding a dedicated public config or app-server
API.

Disable it with:

```sh
codex --disable auto_compaction
```

## Testing

- `just test -p codex-features` — 51 passed
- `just test -p codex-core auto_compaction_feature_disabled` — 2 passed
- `just fix -p codex-core -p codex-features`
- `just write-config-schema`
- `just test -p codex-core` — the new compaction tests passed; the
overall local run had 54 unrelated environment failures, primarily
missing first-party test binaries and shell-snapshot timeouts

codex-rs/features/src/lib.rs

@@ -231,6 +231,8 @@ pub enum Feature {
     RealtimeConversation,
     /// Prevent idle system sleep while a turn is actively running.
     PreventIdleSleep,
+    /// Enable automatic context compaction before or during a turn.
+    AutoCompaction,
     /// Enable remote compaction v2 over the normal Responses API.
     RemoteCompactionV2,
     /// Use Agent Identity for ChatGPT-authenticated sessions.
@@ -1335,6 +1337,12 @@ pub const FEATURES: &[FeatureSpec] = &[
         stage: Stage::Removed,
         default_enabled: false,
     },
+    FeatureSpec {
+        id: Feature::AutoCompaction,
+        key: "auto_compaction",
+        stage: Stage::Stable,
+        default_enabled: true,
+    },
     FeatureSpec {
         id: Feature::RemoteCompactionV2,
         key: "remote_compaction_v2",