[codex] Remove auto-compaction opt-out (#29815)

## Summary

- remove the default-on `auto_compaction` feature flag and generated
config schema entries
- restore unconditional pre-turn, model-switch/hash, and mid-turn
automatic compaction
- expose `new_context` whenever token-budget tooling is enabled
- remove the disabled-auto-compaction integration coverage introduced by
#28260

## Motivation

Roll back the internal auto-compaction escape hatch added in #28260.
Automatic compaction should no longer be suppressible with `--disable
auto_compaction`; existing manual `/compact` behavior remains unchanged.

## Testing

- `just write-config-schema`
- `just test -p codex-features` — 53 passed
- `just test -p codex-core 'suite::compact::'` — 36 passed
- `just test -p codex-core
suite::token_budget::new_context_tool_starts_new_window_before_follow_up`
— 1 passed
- `just fix -p codex-core -p codex-features`
- `just fmt`
- `just test -p codex-core` — 2,778 passed, 59 failed, 16 skipped;
failures were outside the changed compaction paths and were dominated by
missing first-party test binaries and shell-snapshot timeouts

codex-rs/features/src/lib.rs

@@ -235,8 +235,6 @@ 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.
@@ -1347,12 +1345,6 @@ 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",