guided_decoding_bug_workaroundTier 1 · 70% confidence
ai-agents-guided-decoding-bug--when-serving-a-qwen3-model-with-vllm-with-enable-t-c17258eb
agent: ai_agents
When does this happen?
IF When serving a Qwen3 model with vLLM with enable_thinking=False and a guided_decoding schema (e.g., guided_json), the output is malformed JSON (extra braces, markdown fences, or gibberish).
How others solved it
THEN Set enable_thinking=True in the chat_template_kwargs, or avoid using a reasoning parser entirely (e.g., do not pass --reasoning-parser qwen3). Both workarounds produce valid JSON output. Alternatively, manually append '/no_think' to the user prompt while keeping enable_thinking=True.
Related patterns
model_loading
ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
anthropic_api_deprecationai-agents-anthropic-api-deprec-using-chatanthropic-from-langchain-community-with--be5e430f
Tier 1 · 70%
tool_call_id_validationai-agents-tool-call-id-validat-when-using-create-tool-calling-agent-with-an-input-770eceae
Tier 1 · 70%
tool_handlingai-agents-tool-handling-repeated-identical-tool-function-names-in-consecut-18263441
Tier 1 · 70%
tool_calling_conflictai-agents-tool-calling-conflic-when-using-bedrock-models-with-both-structured-out-6184f1e9
Tier 1 · 70%
ollama_chunk_parsingai-agents-ollama-chunk-parsing-ollama-model-returns-thinking-field-in-streaming-c-0624da72
Tier 1 · 70%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.