Added Kimi API key invocation and the new model Kimi-k2.5 #10850

Activity

1. anyiba

   added

   bugSomething isn't workingSomething isn't working

   on Jan 27, 2026
2. github-actions

   assigned

   rekram1-node

   on Jan 27, 2026
3. github-actions

   added

   windows

   on Jan 27, 2026
4. github-actions commented on Jan 27, 2026

   

   github-actionsBot

   on Jan 27, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • [FEATURE]: kimi k2.5 integration #10811: [FEATURE]: kimi k2.5 integration - Feature request for kimi k2.5 integration
   • Kimi-K2 via OpenRouter fails with tool call tokens inside thinking block #8851: Kimi-K2 via OpenRouter fails with tool call tokens inside thinking block - Related to tool call issues with thinking/reasoning content
   • Logic behind mapping <think> tags to reasoning_content #9433: Logic behind mapping tags to reasoning_content - Related to reasoning_content handling in thinking mode
   • Missing Kimi model options: K2 turbo and K2 thinking turbo for coding #7314: Missing Kimi model options: K2 turbo and K2 thinking turbo for coding - Related to Kimi model configuration

   Feel free to ignore if none of these address your specific case.
5. kassieclaire commented on Jan 27, 2026

   

   kassieclaire

   on Jan 27, 2026

   More actions

   Are you using DCP? There might be an issue related to pruning tool use context that includes thinking for K2.5
6. mcowger commented on Jan 27, 2026

   

   mcowger

   on Jan 27, 2026

   More actions

   I have this an dont use DCP
7. kassieclaire commented on Jan 27, 2026

   

   kassieclaire

   on Jan 27, 2026

   More actions

   Do you have any custom settings related to the Kimi-K2.5 model in your configuration, and which provider are you using?
8. qingchunnh commented on Jan 28, 2026

   

   qingchunnh

   on Jan 28, 2026

   More actions

   I'm using OpenRouter's API. I solved a similar problem through #6040, so this might help you.
9. jackjoliet commented on Feb 11, 2026

   

   jackjoliet

   on Feb 11, 2026

   Last edited by jackjoliet

   More actions

   Might be a different stack, but I was facing the same issue with ai-sdk. Here's what solved it for me

   // reasoning_content — Kimi's API requires this field on every assistant
   // tool-call message when thinking mode is enabled.
   const kimiProvider = createOpenAICompatible({
     name: 'moonshot',
     baseURL: 'https://api.moonshot.ai/v1',
     apiKey: KIMI_API_KEY,
     includeUsage: true,
     transformRequestBody: (body: Record<string, unknown>) => {
       const messages = body.messages
       if (!Array.isArray(messages)) return body
       for (const msg of messages) {
         if (
           msg.role === 'assistant' &&
           Array.isArray(msg.tool_calls) &&
           msg.tool_calls.length > 0 &&
           !msg.reasoning_content
         ) {
           msg.reasoning_content = '.'
         }
       }
       return body
     },
   })
   
10. github-actions commented on Apr 13, 2026

    

    github-actionsBot

    on Apr 13, 2026 – with GitHub Actions

    Contributor

    More actions

    To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.
11. github-actions

    closed this as completedon Apr 13, 2026