core/core-agent-ide
8
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix misleading 'maximize' high effort description on xhigh models (#7874)

Browse source 
## Notes
- switch misleading High reasoning effort descriptions from "Maximizes
reasoning depth" to "Higher reasoning depth" across models with xhigh
reasoning. Affects GPT-5.1 Codex Max and Robin
- refresh model list fixtures and chatwidget snapshots to match new copy

## Revision
- R2: Change 'Higher' to 'Greater'
- R1: Initial

## Testing

<img width="583" height="142" alt="image"
src="https://github.com/user-attachments/assets/1ddd8971-7841-4cb3-b9ba-91095a7435d2"
/>

<img width="838" height="142" alt="image"
src="https://github.com/user-attachments/assets/79aaedbf-7624-4695-b822-93dea7d6a800"
/>
This commit is contained in:
Victor Vannara 2025-12-11 16:38:52 -08:00 • committed by GitHub
parent 43e6e75317
commit 95f7d37ec6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 13 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
codex-rs/app-server/tests/suite/v2/model_list.rs
View file

@ -64,7 +64,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex problems".to_string(),
description: "Greater reasoning depth for complex problems".to_string(),
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::XHigh,
@ -138,7 +138,7 @@ async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
},
ReasoningEffortOption {
reasoning_effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems"
description: "Greater reasoning depth for complex or ambiguous problems"
.to_string(),
},
ReasoningEffortOption {

4
codex-rs/core/src/openai_models/model_presets.rs
View file

@ -28,7 +28,7 @@ static PRESETS: Lazy<Vec<ModelPreset>> = Lazy::new(|| {
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex problems".to_string(),
description: "Greater reasoning depth for complex problems".to_string(),
},
ReasoningEffortPreset {
effort: ReasoningEffort::XHigh,
@ -110,7 +110,7 @@ static PRESETS: Lazy<Vec<ModelPreset>> = Lazy::new(|| {
},
ReasoningEffortPreset {
effort: ReasoningEffort::High,
description: "Maximizes reasoning depth for complex or ambiguous problems".to_string(),
description: "Greater reasoning depth for complex or ambiguous problems".to_string(),
},
ReasoningEffortPreset {
effort: ReasoningEffort::XHigh,

4
codex-rs/core/tests/suite/list_models.rs
View file

@ -79,7 +79,7 @@ fn gpt_5_1_codex_max() -> ModelPreset {
),
effort(
ReasoningEffort::High,
"Maximizes reasoning depth for complex problems",
"Greater reasoning depth for complex problems",
),
effort(
ReasoningEffort::XHigh,
@ -162,7 +162,7 @@ fn gpt_5_2() -> ModelPreset {
),
effort(
ReasoningEffort::High,
"Maximizes reasoning depth for complex or ambiguous problems",
"Greater reasoning depth for complex or ambiguous problems",
),
effort(
ReasoningEffort::XHigh,

2
codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__model_reasoning_selection_popup.snap
View file

@ -6,7 +6,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday tasks
› 3. High (current) Maximizes reasoning depth for complex problems
› 3. High (current) Greater reasoning depth for complex problems
4. Extra high Extra high reasoning depth for complex problems
Press enter to confirm or esc to go back

2
codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__model_reasoning_selection_popup_extra_high_warning.snap
View file

@ -8,7 +8,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday
tasks
3. High Maximizes reasoning depth for complex problems
3. High Greater reasoning depth for complex problems
› 4. Extra high (current) Extra high reasoning depth for complex problems
⚠ Extra high reasoning effort can quickly consume
Plus plan rate limits.

2
codex-rs/tui/src/chatwidget/tests.rs
View file

@ -1930,7 +1930,7 @@ fn single_reasoning_option_skips_selection() {
let single_effort = vec![ReasoningEffortPreset {
effort: ReasoningEffortConfig::High,
description: "Maximizes reasoning depth for complex or ambiguous problems".to_string(),
description: "Greater reasoning depth for complex or ambiguous problems".to_string(),
}];
let preset = ModelPreset {
id: "model-with-single-reasoning".to_string(),

2
codex-rs/tui2/src/chatwidget/snapshots/codex_tui2__chatwidget__tests__model_reasoning_selection_popup.snap
View file

@ -6,7 +6,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday tasks
› 3. High (current) Maximizes reasoning depth for complex problems
› 3. High (current) Greater reasoning depth for complex problems
4. Extra high Extra high reasoning depth for complex problems
Press enter to confirm or esc to go back

2
codex-rs/tui2/src/chatwidget/snapshots/codex_tui2__chatwidget__tests__model_reasoning_selection_popup_extra_high_warning.snap
View file

@ -7,7 +7,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday
tasks
3. High Maximizes reasoning depth for complex problems
3. High Greater reasoning depth for complex problems
› 4. Extra high (current) Extra high reasoning depth for complex problems
⚠ Extra high reasoning effort can quickly consume
Plus plan rate limits.

2
codex-rs/tui2/src/chatwidget/snapshots/codex_tui__chatwidget__tests__model_reasoning_selection_popup.snap
View file

@ -6,7 +6,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday tasks
› 3. High (current) Maximizes reasoning depth for complex problems
› 3. High (current) Greater reasoning depth for complex problems
4. Extra high Extra high reasoning depth for complex problems
Press enter to confirm or esc to go back

2
codex-rs/tui2/src/chatwidget/snapshots/codex_tui__chatwidget__tests__model_reasoning_selection_popup_extra_high_warning.snap
View file

@ -8,7 +8,7 @@ expression: popup
1. Low Fast responses with lighter reasoning
2. Medium (default) Balances speed and reasoning depth for everyday
tasks
3. High Maximizes reasoning depth for complex problems
3. High Greater reasoning depth for complex problems
› 4. Extra high (current) Extra high reasoning depth for complex problems
⚠ Extra high reasoning effort can quickly consume
Plus plan rate limits.