anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-21 17:56:33 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

[PR #8958] fix: strip incompatible thinking blocks when switching to Claude #12924

New Issue
Open
opened 2026-02-16 18:17:48 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 18:17:48 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/anomalyco/opencode/pull/8958

State: open
Merged: No

Fixes #6418

Problem

When switching from models like GLM 4.7 or MiniMax to Claude with extended thinking enabled, users get API errors:

messages.X.content.0: Invalid 'signature' in 'thinking' block

or

messages.X.content.0.type: Expected 'thinking' or 'redacted_thinking', but found 'text'

This happens because:

  1. Other models produce thinking blocks with signatures that are incompatible with Claude's signature validation
  2. Claude requires the last assistant message to start with a valid thinking block when thinking is enabled
  3. reasoning parts from other models don't have the signature format Claude expects

Solution

In normalizeMessages(), when the target model is Claude:

  1. Convert thinking blocks with signatures to wrapped text - Preserves the reasoning content while removing the invalid signature. Wrapped in <assistant_thinking> tags.
  2. Convert reasoning parts to text - Same approach, wrapped in <assistant_reasoning> tags.
  3. Track which messages had thinking blocks converted - Using a Set to avoid incorrectly removing messages that we already handled.
  4. Only remove last assistant message if safe - Only when it doesn't start with valid thinking, has no tool calls, AND didn't have converted thinking blocks.

This approach preserves tool_use/tool_result pairing while still handling the signature validation issues.

Changes

  • packages/opencode/src/provider/transform.ts: Added thinking block conversion logic in Claude-specific section
  • packages/opencode/test/provider/thinking-blocks.test.ts: New test file with comprehensive coverage
  • packages/opencode/test/provider/transform.test.ts: Updated existing test expectation

Testing

  1. Start a session with GLM 4.7 or MiniMax (models that generate thinking/reasoning)
  2. Send a few messages, including one that triggers tool use
  3. Switch to Claude with extended thinking enabled
  4. Send a message - should no longer get signature errors
  5. Tool results should still work correctly

Related

  • Supersedes #6748 (similar approach but that PR has been stale)
  • Related to #7779 (GLM 4.7 thinking format issues)
**Original Pull Request:** https://github.com/anomalyco/opencode/pull/8958 **State:** open **Merged:** No --- Fixes #6418 ## Problem When switching from models like GLM 4.7 or MiniMax to Claude with extended thinking enabled, users get API errors: ``` messages.X.content.0: Invalid 'signature' in 'thinking' block ``` or ``` messages.X.content.0.type: Expected 'thinking' or 'redacted_thinking', but found 'text' ``` This happens because: 1. Other models produce `thinking` blocks with signatures that are **incompatible** with Claude's signature validation 2. Claude requires the last assistant message to **start with a valid thinking block** when thinking is enabled 3. `reasoning` parts from other models don't have the signature format Claude expects ## Solution In `normalizeMessages()`, when the target model is Claude: 1. **Convert thinking blocks with signatures to wrapped text** - Preserves the reasoning content while removing the invalid signature. Wrapped in `<assistant_thinking>` tags. 2. **Convert reasoning parts to text** - Same approach, wrapped in `<assistant_reasoning>` tags. 3. **Track which messages had thinking blocks converted** - Using a Set to avoid incorrectly removing messages that we already handled. 4. **Only remove last assistant message if safe** - Only when it doesn't start with valid thinking, has no tool calls, AND didn't have converted thinking blocks. This approach preserves tool_use/tool_result pairing while still handling the signature validation issues. ## Changes - `packages/opencode/src/provider/transform.ts`: Added thinking block conversion logic in Claude-specific section - `packages/opencode/test/provider/thinking-blocks.test.ts`: New test file with comprehensive coverage - `packages/opencode/test/provider/transform.test.ts`: Updated existing test expectation ## Testing 1. Start a session with GLM 4.7 or MiniMax (models that generate thinking/reasoning) 2. Send a few messages, including one that triggers tool use 3. Switch to Claude with extended thinking enabled 4. Send a message - should no longer get signature errors 5. Tool results should still work correctly ## Related - Supersedes #6748 (similar approach but that PR has been stale) - Related to #7779 (GLM 4.7 thinking format issues)
yindo added the pull-request label 2026-02-16 18:17:48 -05:00
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 pull-request
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#12924
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?