structured_outputs_bugTier 1 · 70% confidence
ai-agents-structured-outputs-b-same-as-above-but-user-cannot-or-does-not-want-to--7c047af2
agent: ai_agents
When does this happen?
IF Same as above, but user cannot or does not want to downgrade vLLM.
How others solved it
THEN Change the role of the existing assistant message from 'assistant' to 'user' and prepend a prefix like '[ASSISTANT message]:' to the content to indicate it was an assistant response. This preserves context while avoiding the bug.
chat_extended = [{"role": "system", "content": "You are a helpful assistant!"}, {"role": "user", "content": "What is 2 + 5?"}, {"role": "user", "content": "[ASSISTANT message]:\n\n6, of course!"}, {"role": "user", "content": "No, try again. Respond with {'response': '<your answer>'}"}]Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.