chore: sync model developers data#1706
Conversation
Greptile SummaryThis automated PR syncs the
Confidence Score: 3/5The sync is safe to merge for most model entries, but the "Nano Banana 2" display name for gemini-3.1-flash-image-preview would be visible to end-users and should be corrected before merging. All model data updates look technically consistent (proper JSON structure, valid cost/limit values), but the upstream source contains a clearly bogus display name for gemini-3.1-flash-image-preview that would be rendered in the UI. A downstream name validation step or review gate in the sync workflow would have caught this. frontend/src/features/models/data/providers.json — specifically lines 7110 and 7142 where "Nano Banana 2" appears as both the name and display_name for gemini-3.1-flash-image-preview. Important Files Changed
Flowchart%%{init: {'theme': 'neutral'}}%%
flowchart TD
A[Weekly Sync Workflow] -->|fetch| B[PublicProviderConf all.json]
B -->|automated diff| C[providers.json patch]
C --> D{Change Types}
D --> E[New models added\nGemini 3.5 Flash, Qwen3.7 Max, etc.]
D --> F[Legacy preview models removed\ngemini-2.5-flash-preview-05-20, etc.]
D --> G[Capability / cost / limit updates\nGemma 4 IT, Grok 4.3, etc.]
D --> H[⚠️ Bogus name ingested\ngemini-3.1-flash-image-preview\nname = 'Nano Banana 2']
H -->|displayed in UI| I[Model picker shows\n'Nano Banana 2']
Reviews (1): Last reviewed commit: "chore: sync model developers data" | Re-trigger Greptile |
| @@ -7067,14 +7132,14 @@ | |||
| }, | |||
| "open_weights": false, | |||
| "limit": { | |||
| "context": 131072, | |||
| "output": 32768 | |||
| "context": 65536, | |||
| "output": 65536 | |||
| }, | |||
| "cost": { | |||
| "input": 0.5, | |||
| "output": 60 | |||
| }, | |||
| "display_name": "Gemini 3.1 Flash Image (Preview)", | |||
| "display_name": "Nano Banana 2", | |||
There was a problem hiding this comment.
Bogus model name "Nano Banana 2" from upstream source
The model gemini-3.1-flash-image-preview has both name and display_name set to "Nano Banana 2" in the upstream source (PublicProviderConf). This appears to be a placeholder or test entry in that dataset. As-is, this string will be displayed to end-users in the model selection UI as if it were a real model name.
Co-authored-by: looplj <231043908+looplj@users.noreply.github.com>
Automated sync of model developers data from upstream source.
Source: https://raw.githubusercontent.com/ThinkInAIXYZ/PublicProviderConf/refs/heads/dev/dist/all.json
This PR was automatically created by the weekly sync workflow.