anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 18:25:32 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

[MiniMax M2] Agent stop at the middle of the work #2719

New Issue
Closed
opened 2026-02-16 17:36:57 -05:00 by yindo · 27 comments
yindo commented 2026-02-16 17:36:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @lst97 on GitHub (Nov 9, 2025).

Originally assigned to: @rekram1-node on GitHub.

Description

1. Incorrect Side Panel Title (Context Header)

The title/header of the right-hand side panel, which appears to contain session context, metadata, and task lists, is displaying an outdated or generic title.

  • Problem: The header currently reads "New session - 2025-11-07T07:33:05.124Z".
  • Context: The title should be updated to reflect the actual status or the user's current task within the agent's environment.

2. Agent Stops in the Middle of the Work (Incomplete Execution)

The interaction flow suggests the AI agent (MiniMax) failed to complete its intended action after a code modification step and is now waiting for user input, indicating a premature halt or failure in the execution pipeline.

Have to manually keep response "Please continue"

OpenCode version

1.0.49

Steps to reproduce

No response

Screenshot and/or share link

Image

Operating System

masOS 26.2 beta

Terminal

Ghostty

Originally created by @lst97 on GitHub (Nov 9, 2025). Originally assigned to: @rekram1-node on GitHub. ### Description ~~1. Incorrect Side Panel Title (Context Header)~~ The title/header of the right-hand side panel, which appears to contain session context, metadata, and task lists, is displaying an outdated or generic title. * **Problem:** The header currently reads **"New session - 2025-11-07T07:33:05.124Z"**. * **Context:** The title should be updated to reflect the actual status or the user's current task within the agent's environment. --- ### **2. Agent Stops in the Middle of the Work (Incomplete Execution)** The interaction flow suggests the AI agent (MiniMax) failed to complete its intended action after a code modification step and is now waiting for user input, indicating a premature halt or failure in the execution pipeline. Have to manually keep response "Please continue" ### OpenCode version 1.0.49 ### Steps to reproduce _No response_ ### Screenshot and/or share link <img width="1498" height="646" alt="Image" src="https://github.com/user-attachments/assets/ebad1825-55b3-4ae8-b9b3-5ef5dab8b3f7" /> ### Operating System masOS 26.2 beta ### Terminal Ghostty
yindo added the bug label 2026-02-16 17:36:57 -05:00
yindo closed this issue 2026-02-16 17:36:57 -05:00
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Nov 9, 2025):

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

  • #4073: Both issues describe agents stopping/hanging during execution and not completing their intended work. Issue #4073 specifically mentions agents hanging during tasks with ESC becoming unresponsive, which seems very similar to your MiniMax M2 agent stopping in the middle of work.

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

@github-actions[bot] commented on GitHub (Nov 9, 2025): This issue might be a duplicate of existing issues. Please check: - #4073: Both issues describe agents stopping/hanging during execution and not completing their intended work. Issue #4073 specifically mentions agents hanging during tasks with ESC becoming unresponsive, which seems very similar to your MiniMax M2 agent stopping in the middle of work. Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Nov 9, 2025):

@lst97 do u not have any openrouter credits? When u select a model we use a tiny cheap one for title gen that your provider has if u are using openrouter this would be haiku 4.5

seems like it is failing for u tho

@rekram1-node commented on GitHub (Nov 9, 2025): @lst97 do u not have any openrouter credits? When u select a model we use a tiny cheap one for title gen that your provider has if u are using openrouter this would be haiku 4.5 seems like it is failing for u tho
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@lst97 commented on GitHub (Nov 9, 2025):

@rekram1-node Ah i see, thank you for your response :)

@lst97 commented on GitHub (Nov 9, 2025): @rekram1-node Ah i see, thank you for your response :)
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Nov 9, 2025):

@lst97 for now id recommend setting “small_model” in your global opencode.json

choose any model from the following output: “opencode models”

ofc choose a model u have access to, it can even be a free one like:

opencode/big-pickle

@rekram1-node commented on GitHub (Nov 9, 2025): @lst97 for now id recommend setting “small_model” in your global opencode.json choose any model from the following output: “opencode models” ofc choose a model u have access to, it can even be a free one like: opencode/big-pickle
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@lst97 commented on GitHub (Nov 10, 2025):

For the Issue 2, it may not be the issue with opencode.

According to the official announcement: After 24:00 UTC on November 7, the RPM for free users will be reduced. If you are running high-concurrency task, we recommend switching to the MiniMax-M2-Stable in advance or adjusting your task concurrency to ensure uninterrupted execution.

However it's better to display a message if it's the case.

ref: https://x.com/MiniMax__AI/status/1986815058249408541

@lst97 commented on GitHub (Nov 10, 2025): For the Issue 2, it may not be the issue with opencode. According to the official announcement: After 24:00 UTC on November 7, the RPM for free users will be reduced. If you are running high-concurrency task, we recommend switching to the MiniMax-M2-Stable in advance or adjusting your task concurrency to ensure uninterrupted execution. However it's better to display a message if it's the case. ref: https://x.com/MiniMax__AI/status/1986815058249408541
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@bennyzen commented on GitHub (Nov 10, 2025):

I'm currently on the new MiniMax Coding Plan and it keeps happening all the time. Execution stops and I need to say something like 'resume' to get it going again.

@bennyzen commented on GitHub (Nov 10, 2025): I'm currently on the new MiniMax Coding Plan and it keeps happening all the time. Execution stops and I need to say something like 'resume' to get it going again.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@bennyzen commented on GitHub (Nov 11, 2025):

Needless to say, but in its current state v1.0.55, opencode is almost unusable with MiniMax M2. it halts after nearly every turn.

@bennyzen commented on GitHub (Nov 11, 2025): Needless to say, but in its current state v1.0.55, opencode is almost unusable with MiniMax M2. it halts after nearly every turn.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Nov 11, 2025):

@bennyzen if the model stops working, that's a model / prompting thing typically unless u are seeing an error? Otherwise the model is saying it is done

@rekram1-node commented on GitHub (Nov 11, 2025): @bennyzen if the model stops working, that's a model / prompting thing typically unless u are seeing an error? Otherwise the model is saying it is done
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@lst97 commented on GitHub (Nov 12, 2025):

https://github.com/MiniMax-AI/MiniMax-M2/issues/37

@lst97 commented on GitHub (Nov 12, 2025): https://github.com/MiniMax-AI/MiniMax-M2/issues/37
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@bennyzen commented on GitHub (Nov 12, 2025):

@rekram1-node not that sure about that, as other coding agents don't show that behavior with MiniMax M2.

@bennyzen commented on GitHub (Nov 12, 2025): @rekram1-node not that sure about that, as other coding agents don't show that behavior with MiniMax M2.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@ditfetzt commented on GitHub (Dec 1, 2025):

I can confirm the same issue and it only happens in Opencode for me. Other harnesses work just fine.

@ditfetzt commented on GitHub (Dec 1, 2025): I can confirm the same issue and it only happens in Opencode for me. Other harnesses work just fine.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 1, 2025):

@bennyzen @lst97 what version of oc are u running openrouter fixed some stuff and we updated the package that we use with the newest fixes

@rekram1-node commented on GitHub (Dec 1, 2025): @bennyzen @lst97 what version of oc are u running openrouter fixed some stuff and we updated the package that we use with the newest fixes
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@lst97 commented on GitHub (Dec 2, 2025):

@rekram1-node Thank you for the response, I have updated to 1.0.216 and have some simple testing. The result is positive. looks like the issue has been fixed. I will conduct some more testing during this week and will close the issue if the issues fixed. Thanks 💯

UPDATE:

I am not using openrouter for the M2 model but by modify the opencode.json:

"provider": {
    "minimax": {
      "npm": "@ai-sdk/anthropic",
      "options": {
        "baseURL": "https://api.minimax.io/anthropic/v1",
        "apiKey": "*"
      },
      "models": {
        "MiniMax-M2": {
          "name": "MiniMax-M2"
        }
      }
    }
  }

I just realized that a offical MiniMax provider added in the auth login in OC, and I will test this provider instead in the coming week.

@lst97 commented on GitHub (Dec 2, 2025): @rekram1-node Thank you for the response, I have updated to 1.0.216 and have some simple testing. The result is positive. looks like the issue has been fixed. I will conduct some more testing during this week and will close the issue if the issues fixed. Thanks 💯 UPDATE: I am not using openrouter for the M2 model but by modify the opencode.json: ```json "provider": { "minimax": { "npm": "@ai-sdk/anthropic", "options": { "baseURL": "https://api.minimax.io/anthropic/v1", "apiKey": "*" }, "models": { "MiniMax-M2": { "name": "MiniMax-M2" } } } } ``` I just realized that a offical MiniMax provider added in the auth login in OC, and I will test this provider instead in the coming week.
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@lst97 commented on GitHub (Dec 2, 2025):

I still have the same issue appeared. OC 1.0.216 auth login selected to MiniMax

Image
@lst97 commented on GitHub (Dec 2, 2025): I still have the same issue appeared. OC 1.0.216 auth login selected to MiniMax <img width="1668" height="533" alt="Image" src="https://github.com/user-attachments/assets/a3286bdd-ec10-427e-919b-9a26ddbbce42" />
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@gtaswin commented on GitHub (Dec 2, 2025):

+1 Same Issue
Version : 1.0.126
Model: minimax/MiniMax-M2

I have tried all 3 methods,
opencode auth login -> MiniMax provider
opencode auth login -> Others
Added Minimax providers in opencode.json config

In All 3 methods Minimax agent stopped in the middle of the work

@gtaswin commented on GitHub (Dec 2, 2025): +1 Same Issue Version : 1.0.126 Model: minimax/MiniMax-M2 I have tried all 3 methods, opencode auth login -> MiniMax provider opencode auth login -> Others Added Minimax providers in opencode.json config In All 3 methods Minimax agent stopped in the middle of the work
yindo commented 2026-02-16 17:36:57 -05:00
Author
Owner
Copy Link
Copy Source

@hicder commented on GitHub (Dec 2, 2025):

I wonder if it's due to maxed out context window. From my shared link: https://opencode.ai/s/adJ4a7bx
looks like input token is 232117, which is larger than the context window of this model

@hicder commented on GitHub (Dec 2, 2025): I wonder if it's due to maxed out context window. From my shared link: https://opencode.ai/s/adJ4a7bx looks like input token is 232117, which is larger than the context window of this model
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@legout commented on GitHub (Dec 3, 2025):

Same here. Hope this could be fixed soon.

Thanks!

@legout commented on GitHub (Dec 3, 2025): Same here. Hope this could be fixed soon. Thanks!
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@0dragosh commented on GitHub (Dec 3, 2025):

I’m encountering the same issue with Gemini 3 Pro (from Google APIs directly). #4953
I think it’s more likely an issue within Opencode and not much to do with the specific model.

This issue has more traction so I figured we’d consolidate here. Is there anything in particular I can do to debug?

@0dragosh commented on GitHub (Dec 3, 2025): I’m encountering the same issue with Gemini 3 Pro (from Google APIs directly). #4953 I think it’s more likely an issue within Opencode and not much to do with the specific model. This issue has more traction so I figured we’d consolidate here. Is there anything in particular I can do to debug?
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 3, 2025):

@0dragosh it has to do with interleavened thinking models, but for anything regarding OpenRouter then it is an issue w/ their API or their sdk. I have been talking with them about several issues and they are still addressing some.

As for minimax outside of openrouter, that's separate and ill have to make an account to check it out

@rekram1-node commented on GitHub (Dec 3, 2025): @0dragosh it has to do with interleavened thinking models, but for anything regarding OpenRouter then it is an issue w/ their API or their sdk. I have been talking with them about several issues and they are still addressing some. As for minimax outside of openrouter, that's separate and ill have to make an account to check it out
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@0dragosh commented on GitHub (Dec 4, 2025):

@0dragosh it has to do with interleavened thinking models, but for anything regarding OpenRouter then it is an issue w/ their API or their sdk. I have been talking with them about several issues and they are still addressing some.

As for minimax outside of openrouter, that's separate and ill have to make an account to check it out

Appreciate the insight! For me it happens with Gemini 3 Pro from Google APIs directly (not OpenRouter).

@0dragosh commented on GitHub (Dec 4, 2025): > @0dragosh it has to do with interleavened thinking models, but for anything regarding OpenRouter then it is an issue w/ their API or their sdk. I have been talking with them about several issues and they are still addressing some. > > As for minimax outside of openrouter, that's separate and ill have to make an account to check it out Appreciate the insight! For me it happens with Gemini 3 Pro from Google APIs directly (not OpenRouter).
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@hicdercpl commented on GitHub (Dec 4, 2025):

I think this PR https://github.com/sst/opencode/pull/4933 seems to fix this issue, but not sure why it's closed.

@hicdercpl commented on GitHub (Dec 4, 2025): I think this PR https://github.com/sst/opencode/pull/4933 seems to fix this issue, but not sure why it's closed.
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 9, 2025):

Can anyone send me example sessions of this happening? I have a minimax coding plan setup. Trying to get this stop behavior mentioned but minimax through the minimax provider seems to work great?

Maybe if anyone can replicate the issue they are describing, try sending me your session:
opencode export > session.json

OR send me steps to replicate this issue?

Also please tell me:

  • are you on minimax or minimax china
  • did you set the provider in your opencode.json or are you using the default (using the default works for me you shouldn't need custom config here)
@rekram1-node commented on GitHub (Dec 9, 2025): Can anyone send me example sessions of this happening? I have a minimax coding plan setup. Trying to get this stop behavior mentioned but minimax through the minimax provider seems to work great? Maybe if anyone can replicate the issue they are describing, try sending me your session: `opencode export > session.json` OR send me steps to replicate this issue? Also please tell me: - are you on minimax or minimax china - did you set the provider in your opencode.json or are you using the default (using the default works for me you shouldn't need custom config here)
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 9, 2025):

Okay I managed to replicate, setup a proxy to validate and in fact the minimax provider IS telling us the response is done. I still don't think this is an opencode bug, we are doing exactly what their api / model is saying...

Artifacts for evidence:

Share link of the conversation (note the model says it's about to do something, then stops after a read):
https://docs.dev.opencode.ai/s/djgvEIGD

Here is a gist containing a conversation where the model stops (both request & response) as well as a basic conversation where I just send "hello"

In both cases their api is responding with the same stop reason, it seems like they aren't correctly doing a tool-calls stop reason?

Stopped randomly excerpt:

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"input_tokens":42131,"output_tokens":355}}

event: message_stop
data: {"type":"message_stop"}

Hello excerpt:

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"input_tokens":13613,"output_tokens":104}}

event: message_stop
data: {"type":"message_stop"}

Here is my gist w/ full payloads for each:
https://gist.github.com/rekram1-node/96907df65c6385d534151f6d35ae8fcd

@rekram1-node commented on GitHub (Dec 9, 2025): Okay I managed to replicate, setup a proxy to validate and in fact the minimax provider IS telling us the response is done. I still don't think this is an opencode bug, we are doing exactly what their api / model is saying... Artifacts for evidence: Share link of the conversation (note the model says it's about to do something, then stops after a read): https://docs.dev.opencode.ai/s/djgvEIGD Here is a gist containing a conversation where the model stops (both request & response) as well as a basic conversation where I just send "hello" In both cases their api is responding with the same stop reason, it seems like they aren't correctly doing a tool-calls stop reason? Stopped randomly excerpt: ``` event: message_delta data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"input_tokens":42131,"output_tokens":355}} event: message_stop data: {"type":"message_stop"} ``` Hello excerpt: ``` event: message_delta data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"input_tokens":13613,"output_tokens":104}} event: message_stop data: {"type":"message_stop"} ``` Here is my gist w/ full payloads for each: https://gist.github.com/rekram1-node/96907df65c6385d534151f6d35ae8fcd
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 10, 2025):

Okay I presented it to their team and in fact the issue is on their end, they said they will be addressing it soon.

So not an opencode bug

@rekram1-node commented on GitHub (Dec 10, 2025): Okay I presented it to their team and in fact the issue is on their end, they said they will be addressing it soon. So not an opencode bug
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 11, 2025):

Okay they said they fixed it, doing some testing myself to see if the issue persists. If I cannot replicate I will be closing this but please comment if you continue having issues & we will reopen and continue discussion w/ their team.

@rekram1-node commented on GitHub (Dec 11, 2025): Okay they said they fixed it, doing some testing myself to see if the issue persists. If I cannot replicate I will be closing this but please comment if you continue having issues & we will reopen and continue discussion w/ their team.
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 11, 2025):

Tested quite a bit, couldn't get it to stop randomly!

Now anyone who is using Minimax through other providers, lmk if you hit snags but it should function properly through openrouter & minimax providers

@rekram1-node commented on GitHub (Dec 11, 2025): Tested quite a bit, couldn't get it to stop randomly! Now anyone who is using Minimax through other providers, lmk if you hit snags but it should function properly through openrouter & minimax providers
yindo commented 2026-02-16 17:36:58 -05:00
Author
Owner
Copy Link
Copy Source

@legout commented on GitHub (Dec 11, 2025):

You rock!! Thanks

@legout commented on GitHub (Dec 11, 2025): You rock!! Thanks
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 bug
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#2719
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?