* fix(vertex_ai): replace custom model names with actual Vertex AI model names in passthrough URLs (#19948)
When the passthrough URL already contains project and location, the code
was skipping the deployment lookup and forwarding the URL as-is to Vertex AI.
For custom model names like gcp/google/gemini-2.5-flash, Vertex AI returned
404 because it only knows the actual model name (gemini-2.5-flash).
The fix makes the deployment lookup always run, so the custom model name
gets replaced with the actual Vertex AI model name before forwarding.
* add _resolve_vertex_model_from_router
* fix: get_llm_provider
* Potential fix for code scanning alert no. 4020: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
The regex in get_vertex_model_id_from_url() was using [^/:]+
which stopped at the first slash, truncating model names like
'gcp/google/gemini-2.5-flash' to just 'gcp'. This caused
access_groups checks to fail for custom model names.
Changed the pattern to [^:]+ to allow slashes in model names,
only stopping at the colon before the action (e.g., :generateContent).
* Cleanup code for user cli auth, and make sure not to prompt user for team multiple times while polling
* Adding tests
* Cleanup normalize teams some more
When using langfuse_otel callback, empty traces were being sent to Langfuse
for requests that didn't result in actual LLM calls (e.g., auth operations,
health checks, failed requests). These traces contained only internal proxy
operations (auth, postgres, proxy_pre_call) with no useful LLM data.
Root cause: LangfuseOtelLogger extends OpenTelemetry, which sets itself as
the proxy's open_telemetry_logger. This caused create_litellm_proxy_request_started_span
to be called for every request, creating a parent span that was sent to Langfuse
even when no LLM call occurred.
Fix: Override create_litellm_proxy_request_started_span in LangfuseOtelLogger
to return None, preventing the creation of empty parent spans. This is consistent
with the existing overrides for async_service_success_hook and async_service_failure_hook
which already prevent service-level logs from being sent to Langfuse.
Fixes: Empty traces in Langfuse v3 when using langfuse_otel callback
Fixes issue where tool_result content blocks include explicit
'cache_control': null which breaks some Anthropic API channels.
Changes:
- Only include cache_control field when explicitly set and not None
- Prevents serialization of null values in tool_result text content
- Maintains backward compatibility with existing cache_control usage
Related issue: Anthropic tool_result conversion adds explicit null values
that cause compatibility issues with certain API implementations.
Co-Authored-By: Claude (claude-4.5-sonnet) <noreply@anthropic.com>
