No reasoning at all through Github Copilot provider

[Coruscant11]

Description

Validate thinking in VSCode

Attempt to get thinking in opencode

opencode.jsonc

{
  "$schema": "https://opencode.ai/config.json",
  "theme": "aura",
  "autoupdate": true,
  "provider": {
    "github-copilot": {
      "models": {
        "[Custom] Opus 4.5 Thinking": {
          "id": "claude-opus-4.5",
          "reasoning": true,
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 32000,
            },
          }
        },
      }
    }
  }
}

A conversation example:

opencode export

{
  "info": {
    "id": "ses_4753afc9affenaSxWVHstiDVAN",
    "version": "1.1.1",
    "projectID": "e53faf218247b17967230b742668df6addde9727",
    "directory": "/home/jcarlens/Development/sesm",
    "title": "Checking assistant reasoning",
    "time": {
      "created": 1767559725925,
      "updated": 1767559730475
    },
    "summary": {
      "additions": 0,
      "deletions": 0,
      "files": 0
    }
  },
  "messages": [
    {
      "info": {
        "id": "msg_b8ac50368001zOrnH6Xk5rnVK3",
        "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
        "role": "user",
        "time": {
          "created": 1767559725933
        },
        "summary": {
          "title": "Asking about reasoning",
          "diffs": []
        },
        "agent": "build",
        "model": {
          "providerID": "github-copilot",
          "modelID": "[Custom] Opus 4.5 Thinking"
        }
      },
      "parts": [
        {
          "id": "prt_b8ac50368002yxYgBf1OX3yO1R",
          "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
          "messageID": "msg_b8ac50368001zOrnH6Xk5rnVK3",
          "type": "text",
          "text": "Are you reasoning?"
        }
      ]
    },
    {
      "info": {
        "id": "msg_b8ac503730018iRxad0NY14TX9",
        "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
        "role": "assistant",
        "time": {
          "created": 1767559725939,
          "completed": 1767559730467
        },
        "parentID": "msg_b8ac50368001zOrnH6Xk5rnVK3",
        "modelID": "[Custom] Opus 4.5 Thinking",
        "providerID": "github-copilot",
        "mode": "build",
        "agent": "build",
        "path": {
          "cwd": "/home/jcarlens/Development/sesm",
          "root": "/home/jcarlens/Development/sesm"
        },
        "cost": 0,
        "tokens": {
          "input": 327,
          "output": 77,
          "reasoning": 0,
          "cache": {
            "read": 10534,
            "write": 0
          }
        },
        "finish": "stop"
      },
      "parts": [
        {
          "id": "prt_b8ac5101b001lc4JrFFJfRMDvj",
          "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
          "messageID": "msg_b8ac503730018iRxad0NY14TX9",
          "type": "step-start",
          "snapshot": "e0066eb511d26f679f2ba4739f14047f10f435aa"
        },
        {
          "id": "prt_b8ac5101c001ZUyiAP75JVK2pe",
          "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
          "messageID": "msg_b8ac503730018iRxad0NY14TX9",
          "type": "text",
          "text": "No, I'm not using an extended reasoning or \"thinking\" mode. I'm a standard Claude model responding directly to your messages. I process your input and generate responses, but I don't have a separate visible chain-of-thought or reasoning trace that I'm working through before answering.\n\nIs there something specific you'd like help with in your project?",
          "time": {
            "start": 1767559730442,
            "end": 1767559730442
          }
        },
        {
          "id": "prt_b8ac5150c001FbC86cMHHQDIoA",
          "sessionID": "ses_4753afc9affenaSxWVHstiDVAN",
          "messageID": "msg_b8ac503730018iRxad0NY14TX9",
          "type": "step-finish",
          "reason": "stop",
          "snapshot": "e0066eb511d26f679f2ba4739f14047f10f435aa",
          "cost": 0,
          "tokens": {
            "input": 327,
            "output": 77,
            "reasoning": 0,
            "cache": {
              "read": 10534,
              "write": 0
            }
          }
        }
      ]
    }
  ]
}

I also tried to put any value in the reasoning, nothing seems to break the API. Maybe the options are ignored?

Thanks for your hardwork!

Plugins

No response

OpenCode version

1.1.1

Steps to reproduce

1. Connect to github copilot provider
2. Either use built-in Opus 4.5 with any built-in variants, or try to configure a custom model
3. Ask anything to see a chain of thougth

Screenshot and/or share link

No response

Operating System

Ubuntu 24.04

Terminal

Ghostty

[Coruscant11]

Note: I did the same kind of exercice with GPT 5.2 (with the reasoning effort settings), same issue.

[Coruscant11]

I tried to run mitmproxy to see VSCode requests body.
Here is a snippet:

{
  "messages": [
    {
      "role": "system",
      "content": "You are an expert AI...",
      "copilot_cache_control": {
        "type": "ephemeral"
      }
    }
  ],
  "model": "claude-opus-4.5",
  "temperature": 0,
  "top_p": 1,
  "max_tokens": 16000,
  "tools": [],
  "n": 1,
  "stream": true,
  "thinking_budget": 15999
}

I removed some useless details.
It seems like it defines a thinking_budget field in the root of the JSON payload the the /completions endpoint. Interesting.

[Coruscant11]

GPT 5.2 through copilot:

{
  "model": "gpt-5.2",
  "input": [
    {
      "role": "system",
      "content": []
    }
  ],
  "stream": true,
  "tools": [],
  "max_output_tokens": 64000,
  "store": false,
  "truncation": "disabled",
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "include": [
    "reasoning.encrypted_content"
  ]

We can see the reasoning and include at the root too.
From what I understood, this is because it uses the Responses API. While opencode use the completions one for my test prompts. OpenCode is apparently using Respones API only for codex according to my opencode thread.

[NicolaiOksen]

I'm seeing the same issue. Would love to be able to configure thinking/reasoning for Copilot models.

[jbuckmccready]

This is a critical bug if wanting to use copilot provider as there is a huge difference for models like gpt 5.2 with reasoning on/off.

[pushad]

Also would like to know if this is getting implemented.

[dreambit]

same for me

[iamim]

Would be very helpful to have it since Anthropic subscription is not an option anymore.

[hazrid93]

so is it actually reasoning but we dont see the thinking block or its not reasoning at all?

[Coruscant11]

@hazrid93 no reasoning at all.