Chat template is passed
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 35/100
Research direction
Start by reproducing the Multi-tool-search agent request with LiteLLM 1.80.0, Google ADK, and the listed Nebius models. Inspect the intercepted HTTP request and the chat-template configuration to determine why the service reports an untrusted template when none is present. Done means the request is accepted and the agent works with both tested models.
Written by the indexing model from the issue text.
Description
when running Multi-tool-search agent,
Error code: 400 - {'detail': 'Invalid request. Please check the parameters and try again. Details: Chat template is passed with request, but
--trust-request-chat-template is not set. Refused request with untrusted chat template.'}
Investigation:
We intercepted the actual HTTP request being sent and confirmed that NO chat_template parameter is present in the request body. The request only contains:
{
"messages": [{"role": "user", "content": "..."}],
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct"
}
Environment
- LiteLLM version: 1.80.0
- Google ADK (Agent Development Kit)
- Nebius API Base: https://api.studio.nebius.ai/v1
- Models tested:
- meta-llama/Meta-Llama-3.1-8B-Instruct
- meta-llama/Meta-Llama-3.1-8B-Instruct-fast
- Dominant language
- Jupyter Notebook
- Stars
- 47
- Forks
- 9
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from Astrodevil/ADK-Agent-Examples
-
Difficulty 5/5 Over a week Newbie friendliness 1/100
All issues in Astrodevil/ADK-Agent-Examples
Similar issues
-
bug follow-up-work-in-progress from-review-extraction llm-providers python severity:should-fix
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
area/evaluation bug
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
[Bug]: OLLAMA_KEEP_ALIVE="5m" / "24h" crashes Ollama embedding and vision models with ValueError Open
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
infiniflow/ragflow#20223 · 1 reaction ·
-
[Bug]: llms-anthropic 0.12.0 rejects claude-opus-5-5 during metadata lookup and agent initialization Open
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
run-llama/llama_index#23222 ·
-
Bedrock adapter reports a context-window-truncated tool-call completion as a normal stop, not length Open
Difficulty 2/5 1-3 hours Newbie friendliness 88/100