fix(codex): update model selector#2740
Conversation
Greptile SummaryUpdates the Codex plugin model selector to replace three deprecated models (
Confidence Score: 5/5Straightforward model list update; the old models are replaced with current OpenAI offerings and the change is confined to display metadata only. The three new model IDs match what the official OpenAI Codex models page documents as recommended models. The description field is already optional in modelOptionSchema. No runtime logic, authentication, or data-flow is affected — only the set of selectable model strings shown to the user changes. No files require special attention; the single changed file is self-contained model metadata.
|
| Filename | Overview |
|---|---|
| packages/plugins/src/agents/impl/codex/index.ts | Replaces three deprecated Codex model entries (codex-mini-latest, o4-mini, o3) with three current models (gpt-5.5, gpt-5.4-mini, gpt-5.3-codex-spark); adds description fields; all model IDs and schema fields are valid. |
Flowchart
%%{init: {'theme': 'neutral'}}%%
flowchart TD
A[User opens Codex model selector] --> B{Select model}
B --> C["gpt-5.5\n(intelligence: 5, speed: 3)\nComplex coding & agentic workflows"]
B --> D["gpt-5.4-mini\n(intelligence: 4, speed: 5)\nLighter tasks & subagents"]
B --> E["gpt-5.3-codex-spark\n(intelligence: 4, speed: 5)\nNear-instant iteration (research preview)"]
C --> F[Passed as -m flag to Codex CLI]
D --> F
E --> F
%%{init: {'theme': 'base', 'themeVariables': {"darkMode": true, "background": "#0d1117", "primaryColor": "#21262d", "primaryTextColor": "#e6edf3", "primaryBorderColor": "#8b949e", "lineColor": "#8b949e", "textColor": "#e6edf3", "edgeLabelBackground": "#161b22", "actorBkg": "#21262d", "actorBorder": "#8b949e", "actorTextColor": "#e6edf3", "actorLineColor": "#8b949e", "signalColor": "#8b949e", "signalTextColor": "#e6edf3", "noteBkgColor": "#373320", "noteBorderColor": "#d4a72c", "noteTextColor": "#f0e6c0", "labelBoxBkgColor": "#21262d", "labelBoxBorderColor": "#8b949e", "labelTextColor": "#e6edf3", "loopTextColor": "#e6edf3", "activationBkgColor": "#30363d", "activationBorderColor": "#8b949e"}}}%%
flowchart TD
A[User opens Codex model selector] --> B{Select model}
B --> C["gpt-5.5\n(intelligence: 5, speed: 3)\nComplex coding & agentic workflows"]
B --> D["gpt-5.4-mini\n(intelligence: 4, speed: 5)\nLighter tasks & subagents"]
B --> E["gpt-5.3-codex-spark\n(intelligence: 4, speed: 5)\nNear-instant iteration (research preview)"]
C --> F[Passed as -m flag to Codex CLI]
D --> F
E --> F
Prompt To Fix All With AI
Fix the following 1 code review issue. Work through them one at a time, proposing concise fixes.
---
### Issue 1 of 1
packages/plugins/src/agents/impl/codex/index.ts:48-52
`gpt-5.3-codex-spark` and `gpt-5.4-mini` are assigned identical `intelligence: 4, speed: 5` ratings. The official Codex models page describes `gpt-5.3-codex-spark` as a research-preview model optimized for near-instant iteration, while `gpt-5.4-mini` is the stable fast model. Differentiating the ratings (e.g. lower intelligence for the older research-preview model) would give users clearer signal in the selector UI.
```suggestion
'gpt-5.3-codex-spark': {
name: 'GPT-5.3 Codex Spark',
description: 'Research-preview Codex model optimized for near-instant iteration.',
modelFeatures: { intelligence: 3, speed: 5 },
},
```
Reviews (1): Last reviewed commit: "test(codex): remove model selector cover..." | Re-trigger Greptile
Description
Screenshot/Recording (if applicable)
https://cap.link/65tkx6y8n2e4pzg
Checklist
messages and, when possible, the PR title