anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Interrupted thinking-only message causes 400 error (patch part bypasses filter) #6574

New Issue
Closed
opened 2026-02-16 18:04:37 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 18:04:37 -05:00
Owner
Copy Link
Copy Source

Originally created by @grumpygordon on GitHub (Jan 17, 2026).

Originally assigned to: @rekram1-node on GitHub.

Interrupting (Esc) while assistant is in thinking mode (reasoning only, no text output yet) breaks the session.

Next request fails with:

messages.X: all messages must have non-empty content except for the optional final assistant message

Related to #3101 but different root cause.

Repro:

  1. Use thinking model (claude-opus with high variant)
  2. Interrupt while "Thinking:" is displayed, before any text
  3. Send another message → 400 error

Cause:
message-v2.ts:toModelMessage() line 483:

msg.parts.some((part) => part.type !== "step-start" && part.type !== "reasoning")

Aborted messages should be skipped if they only have step-start/reasoning. But the patch part (created on abort) passes this check, so the message gets included with only reasoning content. Anthropic rejects non-final assistant messages with only reasoning.

Fix:
Add patch to exclusion, or check for output-producing parts (text, tool) explicitly.

  • macOS, dev build
Originally created by @grumpygordon on GitHub (Jan 17, 2026). Originally assigned to: @rekram1-node on GitHub. Interrupting (Esc) while assistant is in thinking mode (reasoning only, no text output yet) breaks the session. Next request fails with: ``` messages.X: all messages must have non-empty content except for the optional final assistant message ``` Related to #3101 but different root cause. **Repro:** 1. Use thinking model (claude-opus with `high` variant) 2. Interrupt while "Thinking:" is displayed, before any text 3. Send another message → 400 error **Cause:** `message-v2.ts:toModelMessage()` line 483: ```typescript msg.parts.some((part) => part.type !== "step-start" && part.type !== "reasoning") ``` Aborted messages should be skipped if they only have step-start/reasoning. But the `patch` part (created on abort) passes this check, so the message gets included with only reasoning content. Anthropic rejects non-final assistant messages with only reasoning. **Fix:** Add `patch` to exclusion, or check for output-producing parts (`text`, `tool`) explicitly. - macOS, dev build
yindo closed this issue 2026-02-16 18:04:37 -05:00
yindo commented 2026-02-16 18:04:38 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 17, 2026):

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

  • #3101: Missing context after network interruption - Related issue mentioning the same error: 'all messages must have non-empty content except for the optional final assistant message'
  • #2655: AI_APICallError with the exact same error message about non-empty content (now closed)
  • #6446: Empty message content causes Anthropic API errors during compaction - Detailed analysis of how empty assistant messages with only tool calls/reasoning parts cause this error

The root cause appears to be similar: messages reaching the API with no text or output-producing content. Your specific case involves thinking-only content filtered out, while #6446 was about tool-only messages, but the underlying issue in toModelMessage() filtering logic seems related.

Feel free to ignore if your case is indeed the specific 'patch part' bypass issue described in your report.

@github-actions[bot] commented on GitHub (Jan 17, 2026): This issue might be a duplicate of existing issues. Please check: - #3101: Missing context after network interruption - Related issue mentioning the same error: 'all messages must have non-empty content except for the optional final assistant message' - #2655: AI_APICallError with the exact same error message about non-empty content (now closed) - #6446: Empty message content causes Anthropic API errors during compaction - Detailed analysis of how empty assistant messages with only tool calls/reasoning parts cause this error The root cause appears to be similar: messages reaching the API with no text or output-producing content. Your specific case involves thinking-only content filtered out, while #6446 was about tool-only messages, but the underlying issue in toModelMessage() filtering logic seems related. Feel free to ignore if your case is indeed the specific 'patch part' bypass issue described in your report.
yindo commented 2026-02-16 18:04:38 -05:00
Author
Owner
Copy Link
Copy Source

@grumpygordon commented on GitHub (Jan 17, 2026):

Sorry, created this accidentally with opencode, its my local build error...

@grumpygordon commented on GitHub (Jan 17, 2026): Sorry, created this accidentally with opencode, its my local build error...
yindo commented 2026-02-16 18:04:38 -05:00
Author
Owner
Copy Link
Copy Source

@dan-cooke commented on GitHub (Jan 27, 2026):

I'm also experiencing this all the time since the most recent update - if anyone stumbles upon here, you an fix it by Cmd + P > Fork and picking your most recent message

There is some bug with opencode that causes the context to be continuously empty, it seems to happen most frequently when you cancel an LLM output

@dan-cooke commented on GitHub (Jan 27, 2026): I'm also experiencing this all the time since the most recent update - if anyone stumbles upon here, you an fix it by Cmd + P > Fork and picking your most recent message There is some bug with opencode that causes the context to be continuously empty, it seems to happen most frequently when you cancel an LLM output
yindo commented 2026-02-16 18:04:38 -05:00
Author
Owner
Copy Link
Copy Source

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

Also experiencing this when interrupting thinking. Forking from a known good state is a good workaround

@madeleineostoja commented on GitHub (Feb 4, 2026): Also experiencing this when interrupting thinking. Forking from a known good state is a good workaround
yindo commented 2026-02-16 18:04:38 -05:00
Author
Owner
Copy Link
Copy Source

@ujjwaljainnn commented on GitHub (Feb 10, 2026):

Also experiencing this when interrupting thinking. Forking from a known good state is a good workaround

If you didn't have file changes, you can also just click on your last message and run the revert command

@ujjwaljainnn commented on GitHub (Feb 10, 2026): > Also experiencing this when interrupting thinking. Forking from a known good state is a good workaround If you didn't have file changes, you can also just click on your last message and run the revert command
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#6574
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?