LiteLLM's StreamHandlers output to stderr by default. In cloud environments like GCP, stderr output is treated as ERROR severity regardless of actual log level, causing INFO-level logs to be incorrectly classified as errors.
This change redirects LiteLLM loggers to stdout in two places:
- In `lite_llm.py`: Immediately after litellm import
- In `logs.py`: When `setup_adk_logger()` is called (with guard to check if litellm is imported)
Close#3824
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843393874
LiteLLM's `ollama_chat` provider does not accept array-based content in messages. This change flattens multipart content by joining text parts or JSON-serializing non-text parts before sending the request to the LiteLLM completion API. This ensures compatibility with Ollama's chat endpoint.
Close#3727
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843382361
The `_to_litellm_response_format` function now adapts the output format based on the provided model. Gemini models continue to use the "response_schema" key, while OpenAI-compatible models (including Azure OpenAI and Anthropic) now use the "json_schema" key as per LiteLLM's documentation for JSON mode. The schema name is also included in the "json_schema" format.
Close#3713Close#3890
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843326850
Explicitly resolve the GCP project from arguments or environment variables before calling `spanner.Client`. This avoids redundant calls to `google.auth.default()` that newer versions of the Spanner library might make.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843320305
Performance: Switched to BigQuery Storage Write API with async batching, reducing agent latency.
Multimodal: Native support for GCS offloading (ObjectRef) for images, video, and large text.
Reliability: Added connection pooling, retries, and a "rescue flush" for safe shutdown on Cloud Run.
Observability: Fixed distributed tracing hierarchy with ContextVars support.
PiperOrigin-RevId: 843062561
This change introduces an add_session_to_memory method to both CallbackContext and ToolContext, allowing agents and tools to explicitly trigger the saving of the current session to the memory service. This enables more fine-grained control over when session data is persisted for memory generation. A ValueError is raised if the memory service is not configured.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 843021899
When users instantiate LlmAgent directly (not subclassed), the origin inference incorrectly detected ADK's internal google/adk/agents/ path as a mismatch.
Use metadata from AgentLoader when available
Skip inference for google.adk.* module
Close#3143
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 842774292
Add using the execute sql query return result as list of dictionaries.
In each dictionary the key is the column name and the value is the value of
the that column in a given row.
PiperOrigin-RevId: 840909555
This change introduces a `verify` parameter to `RestApiTool` and `OpenAPIToolset`. This parameter allows users to configure how SSL certificates are verified when making API calls using the `requests` library. Options include providing a path to a CA bundle, disabling verification, or using a custom `ssl.SSLContext`. New methods `configure_verify` and `configure_verify_all` are added to update this setting after initialization. This is useful for environments with TLS-intercepting proxies.
Fixes: https://github.com/google/adk-python/issues/3720
Co-authored-by: Xuan Yang <xygoogle@google.com>
PiperOrigin-RevId: 840809727
The RemoteA2aAgent now extracts a "task_id" from the custom metadata of the last agent event in the session, alongside the existing "context_id". This task_id is then included in the A2AMessage sent to the remote A2A service.
Close#3765
PiperOrigin-RevId: 840375992
When converting `types.Content` with a `function_response` to LiteLLM's `ChatCompletionToolMessage`, if the response is already a string, use it directly. Otherwise, serialize the response to JSON. This prevents double-serialization of string payloads
Close#3676
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 840013822
This change refactors how session, memory, and artifact services are created in the fast_api server, using the shared service_factory.
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839997110
This change introduces `Gemma3Ollama`, a new LLM model class for running Gemma 3 models locally via Ollama, leveraging LiteLLM. The function calling logic previously in the `Gemma` class has been refactored into a `GemmaFunctionCallingMixin` and is now used by both `Gemma` and `Gemma3Ollama`. A new sample application, `hello_world_gemma3_ollama`, is added to demonstrate using `Gemma3Ollama` with an agent. Unit tests for `Gemma3Ollama` are also included.
Merge: https://github.com/google/adk-python/pull/3120
Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 839996879
George Weale
Xuan Yang
Google Team Member
Xiang (Sean) Zhou
hoonji
davidkl97
Doug Reid