Kimi K2.5 can't enable thinking (reasoning_content missing #8501

Closed
opened 2026-02-16 18:10:08 -05:00 by yindo · 4 comments
Owner

Originally created by @3dot141 on GitHub (Feb 4, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

What happened?

When using Kimi K2.5 via the OpenAI-compatible provider, enabling thinking does not return reasoning_content. As a result, the model behaves like non-thinking mode even when the feature should be available.

Expected behavior

Kimi K2.5 should support thinking and return interleaved reasoning content (reasoning_content) when enabled.

Steps to reproduce

  1. Configure a Kimi K2.5 model through the OpenAI-compatible provider.
  2. Enable thinking / reasoning in the request.
  3. Observe that no reasoning content is returned.

Environment

  • opencode version: v1.1.51
  • model: kimi-k2.5 / k2p5

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @3dot141 on GitHub (Feb 4, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description ### What happened? When using Kimi K2.5 via the OpenAI-compatible provider, enabling thinking does not return `reasoning_content`. As a result, the model behaves like non-thinking mode even when the feature should be available. ### Expected behavior Kimi K2.5 should support thinking and return interleaved reasoning content (`reasoning_content`) when enabled. ### Steps to reproduce 1. Configure a Kimi K2.5 model through the OpenAI-compatible provider. 2. Enable thinking / reasoning in the request. 3. Observe that no reasoning content is returned. ### Environment - opencode version: v1.1.51 - model: kimi-k2.5 / k2p5 ### Plugins _No response_ ### OpenCode version _No response_ ### Steps to reproduce _No response_ ### Screenshot and/or share link _No response_ ### Operating System _No response_ ### Terminal _No response_
yindo added the bugzen labels 2026-02-16 18:10:08 -05:00
yindo closed this issue 2026-02-16 18:10:08 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Feb 4, 2026):

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

  • #11446: New Kimi 2.5 model is giving error "Extra inputs are not permitted, field: 'reasoning_content', value: []" - Reports the exact same reasoning_content error when using Kimi K2.5
  • #11917: Kimi K2.5 model ID 'k2p5' bypasses reasoning variants exclusion - Related issue about Kimi K2.5 reasoning support configuration (CLOSED)

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Feb 4, 2026): This issue might be a duplicate of existing issues. Please check: - #11446: New Kimi 2.5 model is giving error "Extra inputs are not permitted, field: 'reasoning_content', value: []" - Reports the exact same reasoning_content error when using Kimi K2.5 - #11917: Kimi K2.5 model ID 'k2p5' bypasses reasoning variants exclusion - Related issue about Kimi K2.5 reasoning support configuration (CLOSED) Feel free to ignore if none of these address your specific case.
Author
Owner

@leosongwei commented on GitHub (Feb 4, 2026):

chould be this? https://github.com/vllm-project/vllm/issues/33616

@leosongwei commented on GitHub (Feb 4, 2026): chould be this? https://github.com/vllm-project/vllm/issues/33616
Author
Owner

@docg1701 commented on GitHub (Feb 4, 2026):

It works fine with opencode-ai@1.1.49 but is broken since 1.1.50. I just checked. Kimi K2.5 got really dumb and non-thinking. Can't make it max/high variants with ctrl+t (which is missing past 1.1.49 in TUI).

To fix this:
add "autoupdate": false in ~/.config/opencode/opencode.json
Then,
npm install -g opencode-ai@1.1.49

$ cat ~/.config/opencode/opencode.json 
{
  "$schema": "https://opencode.ai/config.json",
    "tui": {
      "scroll_speed": 3,
      "scroll_acceleration": {
        "enabled": true
      }
   },
  "autoupdate": false,
  "mcp": {
    "context7": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@upstash/context7-mcp",
        "--api-key",
        "ctx7sk-d860989a-2d42-48d6-9da8-4990ba4fd697"
      ],
      "enabled": true
    }
  }
}
@docg1701 commented on GitHub (Feb 4, 2026): It works fine with opencode-ai@1.1.49 but is broken since 1.1.50. I just checked. Kimi K2.5 got really dumb and non-thinking. Can't make it max/high variants with ctrl+t (which is missing past 1.1.49 in TUI). To fix this: add "autoupdate": false in ~/.config/opencode/opencode.json Then, npm install -g opencode-ai@1.1.49 ```bash $ cat ~/.config/opencode/opencode.json { "$schema": "https://opencode.ai/config.json", "tui": { "scroll_speed": 3, "scroll_acceleration": { "enabled": true } }, "autoupdate": false, "mcp": { "context7": { "type": "local", "command": [ "npx", "-y", "@upstash/context7-mcp", "--api-key", "ctx7sk-d860989a-2d42-48d6-9da8-4990ba4fd697" ], "enabled": true } } } ```
Author
Owner

@rekram1-node commented on GitHub (Feb 4, 2026):

The kimi-for-coding provider has thinking off by default, I merged a fix to make it think by default in next release (consistent w/ other providers)

The high/max actually makes no difference in thinking u just need to explicitly turn it on for that provider. I merged a "fix" from some external contributor who cited claims from kimi team directly.

It caused this issue, but @monotykamary fixed it. you can fix temporarily using this:

 "provider": {
    "kimi-for-coding": {
      "models": {
        "k2p5": {
          "options": {
             "thinking": {
                "type": "enabled",
                "budgetTokens": 16000 // this is required for ai sdk even tho it doesnt do anything in actuality
              }
          }
        }
      }
    }
  }
@rekram1-node commented on GitHub (Feb 4, 2026): The kimi-for-coding provider has thinking off by default, I merged a fix to make it think by default in next release (consistent w/ other providers) The high/max actually makes no difference in thinking u just need to explicitly turn it on for that provider. I merged a "fix" from some external contributor who cited claims from kimi team directly. It caused this issue, but @monotykamary fixed it. you can fix temporarily using this: ``` "provider": { "kimi-for-coding": { "models": { "k2p5": { "options": { "thinking": { "type": "enabled", "budgetTokens": 16000 // this is required for ai sdk even tho it doesnt do anything in actuality } } } } } } ````
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#8501