anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-23 02:36:57 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

MiniMax M2 <think> tags #2662

New Issue
Open
opened 2026-02-16 17:36:42 -05:00 by yindo · 13 comments
yindo commented 2026-02-16 17:36:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @pskwr on GitHub (Nov 7, 2025).

Originally assigned to: @rekram1-node on GitHub.

Question

Does opencode support rendering tags in the UI like for example Claude Code?

Opencode:
Image

Claude Code:
Image

Originally created by @pskwr on GitHub (Nov 7, 2025). Originally assigned to: @rekram1-node on GitHub. ### Question Does opencode support rendering <think> tags in the UI like for example Claude Code? Opencode: <img width="721" height="402" alt="Image" src="https://github.com/user-attachments/assets/c299b75a-a5db-4c44-aa18-10c7eee2e20d" /> Claude Code: <img width="791" height="170" alt="Image" src="https://github.com/user-attachments/assets/73d505c4-b3ed-4b48-82c4-7cfd8e9ca55a" />
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Nov 7, 2025):

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

  • #3555: Deals specifically with MiniMax-M2 reasoning content and tags not being properly handled in OpenAI-compatible mode (closed)
  • #1528: General feature request for better support of thinking tags in local models with UI separation

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

@github-actions[bot] commented on GitHub (Nov 7, 2025): This issue might be a duplicate of existing issues. Please check: - #3555: Deals specifically with MiniMax-M2 reasoning content and <think> tags not being properly handled in OpenAI-compatible mode (closed) - #1528: General feature request for better support of thinking tags in local models with UI separation Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@aaronnewsome commented on GitHub (Nov 7, 2025):

I'm using Minimax M2 on both their official API and locally hosted with llama.cpp. Both rendering the reasoning blocks properly in opencode, no think tags appear in the response texts. I set reasoning true in opencode.json

"models": {
        "minimax-m2": {
          "name": "minimax-m2",
          "tool_call": true,
          "reasoning": true,
          "cost": {
            "input": 0.10,
            "output": 1.20
          },
          "options": {
            "num_ctx": 131072,
            "temperature": 1.0,
            "top_p": 0.95,
            "top_k": 40
          }
        },

CORRECTION: I am using OpenCode with Minimax-M2 locally hosted only, not the official API. Using Minimax M2 official API with Claude Code.

@aaronnewsome commented on GitHub (Nov 7, 2025): I'm using Minimax M2 on <strike>both their official API and</strike> locally hosted with llama.cpp. Both rendering the reasoning blocks properly in opencode, no think tags appear in the response texts. I set reasoning true in opencode.json ``` "models": { "minimax-m2": { "name": "minimax-m2", "tool_call": true, "reasoning": true, "cost": { "input": 0.10, "output": 1.20 }, "options": { "num_ctx": 131072, "temperature": 1.0, "top_p": 0.95, "top_k": 40 } }, ``` CORRECTION: I am using OpenCode with Minimax-M2 locally hosted only, not the official API. Using Minimax M2 official API with Claude Code.
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@no1wudi commented on GitHub (Nov 7, 2025):

I'm using offical antropic API, opencode can't get correct title, but no "think" tags.

Image
@no1wudi commented on GitHub (Nov 7, 2025): I'm using offical antropic API, opencode can't get correct title, but no "think" tags. <img width="962" height="400" alt="Image" src="https://github.com/user-attachments/assets/60f0a3e3-a88b-4ddb-a98d-4aadeb7e377c" />
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@WAY29 commented on GitHub (Nov 18, 2025):

meet same error in unoffical codex relay... anyone can help?

@WAY29 commented on GitHub (Nov 18, 2025): meet same error in unoffical codex relay... anyone can help?
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Nov 18, 2025):

what is codex relay?

@rekram1-node commented on GitHub (Nov 18, 2025): what is codex relay?
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@WAY29 commented on GitHub (Nov 18, 2025):

what is codex relay?

Oh, it means third-party intermediary website. It work well with the Codex CLI, but encountered some issues in OpenCode (can't render think blocks).

@WAY29 commented on GitHub (Nov 18, 2025): > what is codex relay? Oh, it means third-party intermediary website. It work well with the Codex CLI, but encountered some issues in OpenCode (can't render think blocks).
yindo commented 2026-02-16 17:36:42 -05:00
Author
Owner
Copy Link
Copy Source

@otarkhan commented on GitHub (Dec 5, 2025):

I'm using Minimax M2 on both their official API and locally hosted with llama.cpp. Both rendering the reasoning blocks properly in opencode, no think tags appear in the response texts. I set reasoning true in opencode.json

"models": {
        "minimax-m2": {
          "name": "minimax-m2",
          "tool_call": true,
          "reasoning": true,
          "cost": {
            "input": 0.10,
            "output": 1.20
          },
          "options": {
            "num_ctx": 131072,
            "temperature": 1.0,
            "top_p": 0.95,
            "top_k": 40
          }
        },

CORRECTION: I am using OpenCode with Minimax-M2 locally hosted only, not the official API. Using Minimax M2 official API with Claude Code.

@aaronnewsome Does tool calling work with OpenCode + local MiniMax-M2? I tested them but OpenCode doesn't parse/understand MiniMax's way of tool call (XML)

@otarkhan commented on GitHub (Dec 5, 2025): > I'm using Minimax M2 on both their official API and locally hosted with llama.cpp. Both rendering the reasoning blocks properly in opencode, no think tags appear in the response texts. I set reasoning true in opencode.json > > ``` > "models": { > "minimax-m2": { > "name": "minimax-m2", > "tool_call": true, > "reasoning": true, > "cost": { > "input": 0.10, > "output": 1.20 > }, > "options": { > "num_ctx": 131072, > "temperature": 1.0, > "top_p": 0.95, > "top_k": 40 > } > }, > ``` > > CORRECTION: I am using OpenCode with Minimax-M2 locally hosted only, not the official API. Using Minimax M2 official API with Claude Code. @aaronnewsome Does tool calling work with OpenCode + local MiniMax-M2? I tested them but OpenCode doesn't parse/understand MiniMax's way of tool call (XML)
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@aaronnewsome commented on GitHub (Dec 5, 2025):

I use OpenCode heavily with Minimax-M2 hosted locally. Over many weeks of heavy daily usage, I see no major issues and it runs very stable, much better than GLM 4.5. When someone says it doesn't work, my first two questions are, what are you serving it with and what chat template are you using. Details of my setup are here

https://github.com/ggml-org/llama.cpp/pull/16932#issuecomment-3583382087

@aaronnewsome commented on GitHub (Dec 5, 2025): I use OpenCode heavily with Minimax-M2 hosted locally. Over many weeks of heavy daily usage, I see no major issues and it runs very stable, much better than GLM 4.5. When someone says it doesn't work, my first two questions are, what are you serving it with and what chat template are you using. Details of my setup are here [https://github.com/ggml-org/llama.cpp/pull/16932#issuecomment-3583382087](https://github.com/ggml-org/llama.cpp/pull/16932#issuecomment-3583382087)
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@druellan commented on GitHub (Dec 6, 2025):

I'm using Minmax through nVidia NIM and I can see the tags showing as <think> and I think I saw them as _think_ one time. Seems to me there is a escaping/encode issue with some providers.

Image

V1.0.134 - Windows 10 - Windows Terminal

@druellan commented on GitHub (Dec 6, 2025): I'm using Minmax through nVidia NIM and I can see the tags showing as `<think>` and I think I saw them as `_think_` one time. Seems to me there is a escaping/encode issue with some providers. <img width="655" height="478" alt="Image" src="https://github.com/user-attachments/assets/24a7a883-17ec-4870-8559-431d3a1dcdfa" /> V1.0.134 - Windows 10 - Windows Terminal
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@letsrock85 commented on GitHub (Dec 25, 2025):

Image

Same issue. I suspect providers like OpenRouter run extra post-processing & parsing layers behind the scenes, which is why their outputs stay intact - unlike what I see when running the same model locally vLLM

@letsrock85 commented on GitHub (Dec 25, 2025): <img width="2117" height="1191" alt="Image" src="https://github.com/user-attachments/assets/8050ca35-c84b-4f19-aa5e-c841d4923d36" /> Same issue. I suspect providers like OpenRouter run extra post-processing & parsing layers behind the scenes, which is why their outputs stay intact - unlike what I see when running the same model locally vLLM
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 25, 2025):

the think tags are being sent as assistant messages not reasoning thats why opencode renders them as such

@rekram1-node commented on GitHub (Dec 25, 2025): the think tags are being sent as assistant messages not reasoning thats why opencode renders them as such
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@h14h commented on GitHub (Dec 30, 2025):

I'm trying to use MiniMax-M2.1 via the Fireworks API (using the default opencode auth setup) and running into this same issue. And not only are the <think> tags coming through as plaintext, but so are <minimax:tool_call> tags, which renders the model unusable.

AFAIK Fireworks does not have any equivalent to the reasoning_split flag that the official MiniMax API supports to ensure OpenAI SDK compatibility.

If feasible, it'd be awesome if OpenCode offered special support interleaved thinking models via the OpenAI-compatible API. The Fireworks-hosted M2.1 deployment is super appealing as a smart, inexpensive, high-TPS model, and I would love to not have to wait on Fireworks (or any other competing model provider) to figure out how to make these interleaved thinking models truly OpenAI compatible.

@h14h commented on GitHub (Dec 30, 2025): I'm trying to use MiniMax-M2.1 via the Fireworks API (using the default opencode auth setup) and running into this same issue. And not only are the `<think>` tags coming through as plaintext, but so are `<minimax:tool_call>` tags, which renders the model unusable. AFAIK Fireworks does not have any equivalent to the `reasoning_split` flag that the official [MiniMax API](https://platform.minimax.io/docs/api-reference/text-openai-api) supports to ensure OpenAI SDK compatibility. If feasible, it'd be awesome if OpenCode offered special support interleaved thinking models via the OpenAI-compatible API. The Fireworks-hosted M2.1 deployment is super appealing as a smart, inexpensive, high-TPS model, and I would love to not have to wait on Fireworks (or any other competing model provider) to figure out how to make these interleaved thinking models truly OpenAI compatible.
yindo commented 2026-02-16 17:36:43 -05:00
Author
Owner
Copy Link
Copy Source

@snipeship commented on GitHub (Jan 25, 2026):

@rekram1-node I think this issue can be closed

@snipeship commented on GitHub (Jan 25, 2026): @rekram1-node I think this issue can be closed
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#2662
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?