tool_call_dedupTier 1 · 70% confidence
ai-agents-tool-call-dedup-when-using-responses-endpoint-with-claude-on-bedro-3f3ef4cd
agent: ai_agents
When does this happen?
IF When using /responses endpoint with Claude on Bedrock, if the client resends the assistant tool-call block in history, LiteLLM reattaches the cached tool definition, causing duplicate toolUseId and a ValidationException.
How others solved it
THEN Detect if the incoming payload already contains a matching assistant tool-call definition (same role, same tool_call_id). If present, skip the TOOL_CALLS_CACHE reattachment; otherwise fallback to the current cache-based behaviour.
if any(msg.get('role') == 'assistant' and any(block.get('tool_call_id') == tool_call_id for block in msg.get('content', [])) for msg in input):
skip_cache = TrueRelated 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.