[BUG]: Empty content error when switching from Cerebras GLM to Claude Opus

[srs-adamr]

Problem

When switching from Cerebras GLM 4.7 to Claude Opus 4.5 in the same session, I get this error:

messages.1: all messages must have non-empty content except for the optional final assistant message

This makes it impossible to switch between models during development sessions.

Steps to Reproduce

1. Start a session with build agent (Cerebras GLM 4.7)
2. Send a few messages
3. Switch to plan agent (Claude Opus 4.5 with extended thinking)
4. Try to send a message
5. Error occurs

Environment

• OpenCode version: 1.1.49
• Provider: Cerebras (GLM 4.7) → Anthropic (Opus 4.5)
• OS: macOS

Related Issues

• Error: Invalid signature in thinking block #6418 - Invalid signature in thinking block (different error but related to model switching)
• AI_APICallError: messages.157: all messages must have non-empty content except for the optional final assistant message #2655 - Empty message content (closed, PR fix: only keep aborted messages if they have sufficient parts #2651 merged)
• Interrupted thinking-only message causes 400 error (patch part bypasses filter) #9042 - Interrupted thinking-only message (closed)
• Empty message content causes Anthropic API errors during compaction #6446 - Empty message content during compaction (closed)

Notes

• PR fix: ensure switching anthropic models mid convo on copilot works without errors, fix issue with reasoning opaque not being picked up for gemini models #11569 was merged before v1.1.49 release but doesn't seem to fix this specific case
• PR fix: strip incompatible thinking blocks when switching to Claude (improved) #11882 is open but has failing tests
• This is a critical blocker for workflows that require switching between GLM and Claude models

[github-actions]

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

• TypeError: undefined is not an object (evaluating 'agent.name') in createUserMessage #11798: TypeError: undefined is not an object (evaluating 'agent.name') in createUserMessage - related to message creation during model/agent switching
• AI_APICallError: messages.157: all messages must have non-empty content except for the optional final assistant message #2655: Empty message content (closed, PR fix: only keep aborted messages if they have sufficient parts #2651 merged) - similar error signature

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

[srs-adamr]

Correction: This is NOT a duplicate of #6418.

After deeper analysis, this is a different error with a different root cause:

Issue	Error	Root Cause	Fix
#6418	Invalid signature in thinking block	GLM thinking blocks have incompatible signatures	PR #11569 (merged)
This issue	all messages must have non-empty content	GLM reasoning parts stripped, leaving empty message	PR #11882 (OPEN)

The Failure Path

1. Use Cerebras GLM 4.7 (produces reasoning/thinking parts)
2. Switch to Claude Opus (Anthropic provider)
3. Empty content filter runs BEFORE GLM reasoning is processed
4. GLM reasoning handler strips reasoning parts → message now has empty array
5. Claude API rejects: "non-empty content"

Why PR #6383 (in v1.1.49) doesn't fix this

PR #6383 filters messages with only step-start parts. But GLM reasoning parts are NOT step-start parts - they pass the filter, then get stripped later, leaving empty content.

Required Fix

PR #11882 handles this by:

1. Converting GLM thinking blocks to text (preserving content)
2. Filtering empty content AFTER processing (not before)

PR #11882 is currently OPEN with failing tests and merge conflicts.

Environment

• OpenCode: v1.1.49
• Provider: Cerebras → Anthropic (NOT GitHub Copilot)
• Models: cerebras/zai-glm-4.7 → anthropic/claude-opus-4-5