v0.100.0 removed a critical user capability: hard 90% clamp nullifies user-defined compaction threshold

What version of Codex CLI is running?

101

What subscription do you have?

pro

Which model were you using?

gpt-5.3-codex

What platform is your computer?

Linux 6.8.0-94-generic x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

_No response_

What issue are you seeing?

v0.100.0 removed a critical user capability by introducing a hard clamp:
effective_auto_compact_limit = min(user_config_limit, context_window * 90%).

When context_window exists, higher user-defined model_auto_compact_token_limit values are silently ignored.
For default users this change adds almost no practical value (they were already on ~90% behavior), while for advanced users it removes intentional threshold control and causes earlier forced compaction.

What steps can reproduce the bug?

1. Install and run rust-v0.99.0 (baseline).
2. Set config:

• model_context_window = 100
• model_auto_compact_token_limit = 200

1. Start a new session/thread and send prompts until token usage is >90 but <200.
2. Observe on v0.99.0: no auto-compaction at 90; high configured limit is respected.
3. Upgrade to rust-v0.100.0 (or v0.101.0) with the same config and repeat.
4. Observe on v0.100.0+: auto-compaction triggers around 90% anyway.

Code snippet:

# ~/.codex/config.toml
model_context_window = 100
model_auto_compact_token_limit = 200

Thread ID:
N/A (local CLI regression; reproducible without a backend thread id)

What is the expected behavior?

If user sets model_auto_compact_token_limit, Codex should respect that explicit configured value (as pre-v0.100.0 behavior did), instead of silently clamping it to 90% of context window.

Additional information

• Commit introducing clamp behavior:

https://github.com/openai/codex/commit/40de788c4d703b504ba13dd74b50f36863afc698

• Clamp implementation:

https://github.com/openai/codex/blob/40de788c4d703b504ba13dd74b50f36863afc698/codex-rs/protocol/src/openai_models.rs#L259-L267

• Validation test added in same commit:

https://github.com/openai/codex/blob/40de788c4d703b504ba13dd74b50f36863afc698/codex-rs/core/tests/suite/compact.rs#L2556-L2612