mainly because http://github.com/robots.txt disallows `/*/raw/` path. using GCS HTTP URIs is more reliable with Gemini model.
PiperOrigin-RevId: 811409688
this is to allow turning on debug log for debugging if some unexpected behavior observed during running cache analysis experiments.
PiperOrigin-RevId: 811189954
This is to avoid serialization issue for some fields that are not json serializable.
meanwhile restructure the debug logs in context cache manager for better debugging potential issues.
PiperOrigin-RevId: 811182492
Static instructions:
Always added to system instructions for context caching
Dynamic instructions:
Added to system instructions when no static instruction exists (for backward compatibility), OR inserted before last batch of continuous user content when static instructions exist
PiperOrigin-RevId: 809170679
1. add a context cache config in app level which will apply to all agents in the app
2. pass on cache config through invocation context to llm_reqeust
3. store cache metadata in llm_response
4. lookup old cache metadata from latest event for reusing old cache
5. create new cache if old cache cannot be reused
PiperOrigin-RevId: 809158578
a. dump the discussion content to a tmp file first to avoid github redaction of environment variable
b. instruct the agent to use get_discussion_and_comments only when discussion content json is not available.
PiperOrigin-RevId: 805581573
original tests assert too strict time boundary, now we only assert the parallel execution time should be less than sequential execution time
PiperOrigin-RevId: 800563929
VertexAiCodeExecutor and ContainerCodeExecutor request additional dependencies, lazy load them so that when users import other names, they won't get impacted if they don't had those additional dependencies installed.
Original codes swallow the exception and log a debug log is wrong and awkward, should follow the same style as what we did in https://github.com/google/adk-python/blob/main/src/google/adk/tools/retrieval/__init__.py
PiperOrigin-RevId: 796969332
This is to address the name conflict issue of tools returned by different toolset. Mainly it's to give each toolset a namespace.
We have a flag `add_tool_name_prefix` to decide whether to apply this behavior
We have a `tool_name_prefix` to let client specify a custom prefix, if not set , toolset name will be used as prefix.
PiperOrigin-RevId: 794306796
The issue was caused by a breaking change in Python 3.13's inspect.cleandoc() function that made it more conservative about whitespace handling:
Root Cause:
- Python 3.12-: inspect.cleandoc() used line.lstrip() - strips all whitespace (spaces, tabs, etc.)
- Python 3.13+: inspect.cleandoc() uses line.lstrip(' ') - strips only space characters
PiperOrigin-RevId: 793921360
1. Allow developers to specify output schema and tools together.
2. If both are specified, do the following:
2.1 Do not set output schema on the model config
2.2 Add a special tool called set_model_response(result)
2.3 `result` has the same schema as the requested output_schema
2.4 Instruct the model to use set_model_response() to output its final result, rather than output text directly.
2.5 When the set_model_response() is called, ADK will extract its content and put it in a text part, so the client would treat it as the model response.
PiperOrigin-RevId: 792686011
original codes try to eagerly import VertexAiRagRetrieval while it doesn't want to raise error if client try to import other names in this package and dependencies of VertexAiRagRetrieval is missing. so it swallow the import error which doesn't make sense, given vertex sdk is a must have for VertexAiRagRetrieval, we should fail fast.
this fix achieve the same purpose but fail fast if client try to import VertexAiRagRetrieval from this package and miss certain dependencies (e.g. vertex sdk)
PiperOrigin-RevId: 791759776
1. given we are running parallel functions in one event loop (one thread) , we should use async lock instead of thread lock
2. test three kind of functions:
a. sync function
b. async function that doesn't yield
c. async function that yield
PiperOrigin-RevId: 791255012
1. if a function has no return type annotation, we should treat it as returning any type
2. we use empty schema (with `type` as None) to indicate no type constraints and this is already supported by model server
PiperOrigin-RevId: 789808104
The test test_token_exchange_not_supported was slow because of an incorrect monkeypatch target. The test was patching google.adk.auth.auth_handler.AUTHLIB_AVAILABLE, but the actual OAuth2 exchange logic uses a different AUTHLIB_AVAILABLE variable in google.adk.auth.exchanger.oauth2_credential_exchanger.
What was happening:
Test set auth_handler.AUTHLIB_AVAILABLE = False
AuthHandler.exchange_auth_token() called OAuth2CredentialExchanger.exchange()
But oauth2_credential_exchanger.AUTHLIB_AVAILABLE was still True
The exchanger attempted real OAuth2 token exchange with client.fetch_token()
This made actual network calls to OAuth2 endpoints, causing timeouts and delays
PiperOrigin-RevId: 788576949
Mainly it's due to GenAI sdk changed their header of genai SDK versions, we have UT to verify that ADK or ADK users won't override their headers. Updated the header accordingly in the UT.
PiperOrigin-RevId: 786334741
1. credential service may be accessed by callbacks
2. plan to add load_credential and save_credential method in CallbackContext (see cl/782158513) given customer has requirement to access credential service themselves. (see https://github.com/google/adk-python/issues/1816)
It's backward compatible given CallbackContext is parent class of ToolContext
PiperOrigin-RevId: 783480378
This is to support model path like :
projects/265104255505/locations/us-central1/publishers/google/models/gemini-2.0-flash-001"
PiperOrigin-RevId: 783413351
1) raise explicit error if the response event contains responses against multiple function call events
2) merge all function responses for the corresponding function call event
PiperOrigin-RevId: 782154577
According to a2a protocol task artifact is a different concept from adk artifact.
if a task is completed the final result should be in task artifact.
PiperOrigin-RevId: 782154265
