mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
[codex] Treat max as a first-class reasoning effort (#30467)
## Why The Bedrock GPT-5.6 catalog advertises `max`, but Codex treated it as an opaque custom effort. That made the reasoning picker render it as lowercase `max` while known efforts use productized labels. Making `max` a known effort aligns catalog data, parsing, and UI presentation without changing the `max` wire value or persisted representation. ## What changed - Add first-class `ReasoningEffort::Max` parsing and serialization. - Use the typed effort in the Bedrock catalog and render it as `Max` in the TUI. - Preserve forward-compatible custom-effort coverage with a genuinely unknown `future` value. ### Before <img width="559" height="124" alt="Screenshot 2026-06-28 at 12 08 47 PM" src="https://github.com/user-attachments/assets/7c43cf4f-020b-4605-9239-0a9c97eb7364" /> ### After <img width="558" height="107" alt="Screenshot 2026-06-28 at 12 09 10 PM" src="https://github.com/user-attachments/assets/b9cc5ded-c940-43b4-b024-bba25abe0a17" />
This commit is contained in:
1 parent
ccdfb4f342
commit
80f54d1266
10 files changed
+26
-20
No files matched your search
@@ -70,7 +70,7 @@ fn gpt_5_6_bedrock_model(bedrock_slug: &str, display_name: &str, priority: i32)
|
||||
model
|
||||
.supported_reasoning_levels
|
||||
.push(ReasoningEffortPreset {
|
||||
effort: ReasoningEffort::Custom("max".to_string()),
|
||||
effort: ReasoningEffort::Max,
|
||||
description: "Maximum reasoning depth for the hardest problems".to_string(),
|
||||
});
|
||||
model
|
||||
@@ -148,7 +148,7 @@ mod tests {
|
||||
expected
|
||||
.supported_reasoning_levels
|
||||
.push(ReasoningEffortPreset {
|
||||
effort: ReasoningEffort::Custom("max".to_string()),
|
||||
effort: ReasoningEffort::Max,
|
||||
description: "Maximum reasoning depth for the hardest problems".to_string(),
|
||||
});
|
||||
|
||||
|
||||
Reference in new issue
Block a user