fix: add deepseek-coder model to DeepSeek provider #7774
Conversation
- Added deepseek-coder model configuration with 8K max output tokens - Added test coverage for the new model - Fixes issue where users could not select deepseek-coder model Fixes #7773
dosubot
bot
added
size:S
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
| contextWindow: 128_000, | ||
| supportsImages: false, | ||
| supportsPromptCache: true, | ||
| inputPrice: 0.56, // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025 |
There was a problem hiding this comment.
Is this pricing accurate for the coder model? The comment says "Updated Sept 5, 2025" which seems to be a future date, and I'm using the same pricing as deepseek-chat. Should we verify the actual pricing from DeepSeek's platform to ensure billing accuracy?
| outputPrice: 1.68, // $1.68 per million tokens - Updated Sept 5, 2025 | ||
| cacheWritesPrice: 0.56, // $0.56 per million tokens (cache miss) - Updated Sept 5, 2025 | ||
| cacheReadsPrice: 0.07, // $0.07 per million tokens (cache hit) - Updated Sept 5, 2025 | ||
| description: `DeepSeek-Coder-V3 is specifically optimized for code generation, completion, and understanding tasks. It excels at programming challenges across multiple languages.`, |
There was a problem hiding this comment.
The description mentions "DeepSeek-Coder-V3" but the model ID is just "deepseek-coder". Should we verify if V3 is the actual version being accessed via the API? This could be important for users to know which specific version they're using.
| expect(model.info.contextWindow).toBe(128_000) | ||
| expect(model.info.supportsImages).toBe(false) | ||
| expect(model.info.supportsPromptCache).toBe(true) | ||
| }) |
There was a problem hiding this comment.
Good test coverage for the model configuration! Consider also adding an integration test that verifies the actual API handler behavior with the deepseek-coder model to ensure end-to-end functionality works as expected.
hannesrudolph
added
the
Issue/PR - Triage
|
@roomote-agent close this pr. |
|
Closing this PR as requested by @NaccOll |
This PR attempts to address Issue #7773. Feedback and guidance are welcome.
Problem
Users were unable to select the "deepseek-coder" model in the DeepSeek provider dropdown. Only "deepseek-chat" and "deepseek-reasoner" models were available.
Solution
deepseek-codermodel configuration to the DeepSeek models definitiondeepseek-chatmodel (8K max output, 128K context window)Testing
Fixes #7773
Important
Add
deepseek-codermodel to DeepSeek provider with test coverage and same specs asdeepseek-chat.deepseek-codermodel todeepSeekModelsindeepseek.tswith 8K max output and 128K context window.deepseek-chatmodel.deepseek.spec.tsto verifydeepseek-codermodel configuration.This description was created by
for 47509bc. You can customize this summary. It will automatically update as commits are pushed.