feat: add DeepSeek AI provider#3
Open
ZgrK wants to merge 2 commits intoBatuhanK:mainfrom
Open
Conversation
Adds DeepSeek as a new AI provider alongside Kimi, Copilot, ZAI, and Codex. Uses official @ai-sdk/deepseek so reasoning_content is handled correctly and requests hit /chat/completions (DeepSeek does not implement OpenAI's /responses endpoint). Models: deepseek-v4-flash, deepseek-v4-pro. - Wire provider through AgentManager (active + title model) and LlmApiServer - Persist deepseekApiKey in SettingsStore - Crawl deepseek key from opencode auth.json - Settings UI: provider/model selector entries, API key input, crawl preview
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
@ai-sdk/deepseeksoreasoning_contentis handled correctly and requests hit/chat/completions(DeepSeek does not implement OpenAI's/responsesendpoint, so naive@ai-sdk/openaiwith custom baseURL hits 404)deepseek-v4-flash,deepseek-v4-proChanges
AgentManager(active + title model) andLlmApiServerdeepseekApiKeyinSettingsStore(keyai_deepseek_key)~/.local/share/opencode/auth.jsonTest plan
deepseek-v4-flashand run a chat — verify response streams (noAI_NoOutputGeneratedError)deepseek-v4-prowith a reasoning prompt — verify completion/v1/completeworks withdeepseekprovider active