[codex] Support model-defined reasoning efforts (#26444)

## Summary
- accept non-empty model-defined reasoning effort values while
preserving built-in effort behavior
- propagate the non-Copy effort type through core, app-server, TUI,
telemetry, and persistence call sites
- preserve string wire encoding and expose an open-string schema for
clients
- update model selection and shortcut behavior for model-advertised
effort values

## Root cause
`ReasoningEffort` gained a string-backed custom variant, so it could no
longer implement `Copy` or rely on derived closed-enum serialization.
Existing consumers still moved effort values from shared references and
assumed a fixed built-in value set.

## Validation
- `just fmt`
- Local tests and compilation were not run per request; relying on CI.
This commit is contained in:
Ahmed Ibrahim authored and GitHub committed 2026-06-04 13:36:24 -07:00
1 parent 4a70e0ac1b
commit 8ac304c299
97 files changed
+685 -581

No files matched your search

+1 -1
View File
@@ -75,7 +75,7 @@ fn apply_turn_context(metadata: &mut ThreadMetadata, turn_ctx: &TurnContextItem)
metadata.cwd = turn_ctx.cwd.clone();
}
metadata.model = Some(turn_ctx.model.clone());
metadata.reasoning_effort = turn_ctx.effort;
metadata.reasoning_effort = turn_ctx.effort.clone();
metadata.sandbox_policy =
serde_json::to_string(&turn_ctx.permission_profile()).unwrap_or_default();
metadata.approval_mode = enum_to_string(&turn_ctx.approval_policy);