This CL introduces logic to handle scenarios where a non-ADK agent transitions to the `TaskState.input_required` or `TaskState.auth_required` states. It intercepts these events and converts them into a synthetic ADK `FunctionCall` event.

PiperOrigin-RevId: 914877123

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 914934690

…same invocation

Currently, BaseToolset caches its tools per invocation_id. Because SkillToolset dynamically resolves additional tools from the state when a skill is loaded, the cache prevents new tools from being picked up in the same invocation right after a load_skill call. This change sets `_use_invocation_cache = False` in SkillToolset so that it correctly re-evaluates the state-dependent tools at each step of the LLM generation loop within an invocation, preventing "Tool not found" errors.

PiperOrigin-RevId: 914997555

…ling

This change removes support for the deprecated `--session_db_url`, `--artifact_storage_uri`, and `--verbosity` flags from the ADK CLI. It also simplifies the service URI handling in `cli_deploy.py` by always using the new `--session_service_uri`, `--artifact_service_uri`, and `--memory_service_uri` flags, regardless of the ADK version.

The deprecated flags has been more than 1 year

Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 915100881

This is related to google#5327.
`BaseToolset.get_auth_config()` returns `None` by default and removing its overrides in toolsets that don't need OAuth flows to list tools does the job.

No regressions in unit tests (`pytest tests/unittests/auth`):
```
================================================================= 181 passed, 508 warnings in 4.23s =================================================================
```

PiperOrigin-RevId: 915128706

This change enables the Google Cloud Telemetry exporter to use mTLS endpoints. It checks for the availability of client certificates and respects the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variables to determine whether to use the mTLS-specific endpoint and configure the session accordingly.

PiperOrigin-RevId: 915541335

…confusion from BaseToolset's invocation_cache

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 915578052

PiperOrigin-RevId: 915616175

This CL implements the  class in the integrations folder, used specifically for the Skill Registry API.

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 915627057

…unity alignment

- Restrict invoke and review triggers purely to explicit user comments.
- Enforce strict author association verification (OWNER, MEMBER, COLLABORATOR).
- Enforce strict targeting assertion to ensure pull requests act on the main branch.
- Synchronize prompt constraints and GitHub action tools with the community catalog.
- Refine action API key options to uniformly target secrets.GOOGLE_API_KEY.

Co-authored-by: Shangjie Chen <deanchen@google.com>
PiperOrigin-RevId: 915654346

PiperOrigin-RevId: 916015512

… double-escaping

PiperOrigin-RevId: 916037238

This ensures that adding README.md files to subdirectories (as discussed
for new folders and integrations) won't result in them being included in
the published package.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916075206

When judge_model_config is None, LlmRequest raises a ValidationError
because it requires a config. We now construct a default GenerateContentConfig
if one isn't provided.

Close google#5677

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916087055

…actions

This change introduces logic to identify events containing requests for tool confirmation or auth credentials. The compaction process will now stop before any such "Human-in-the-Loop" (HITL) events, ensuring that the full context of the interaction is preserved and not summarized away. This applies to both sliding window and token threshold compaction strategies.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916108771

`part_to_message_block` iterated `content` char-by-char when a tool
returned it as a plain string (e.g. `LoadSkillResourceTool`'s
`{"content": <file text>}`), producing `"H\ne\nl\nl\no"` instead of
`"Hello"`. Guard the list branch with `isinstance(..., list)` and add
a sibling branch that passes a scalar string through directly, matching
Anthropic's `content: str | list[ContentBlockParam]` shape.

Close google#5358

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916109239

Co-authored-by: Amaad Martin <amaadmartin@google.com>
PiperOrigin-RevId: 916112779

…ack as successful

Previously, an empty `candidates` list without `prompt_feedback` resulted in an `UNKNOWN_ERROR`. This change updates the logic to handle such cases as a successful completion with no generated content, which is valid for certain model interactions like tool-driven turns.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916115022

…rt ~8%

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916195791

…ntTool

AgentTool.run_async only extracted text parts from the inner agent's
response, silently dropping code_execution_result.output and
executable_code.code. Outer agents using an inner agent with a code
executor saw nothing.

Close google#5481

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916196604

Co-authored-by: Kathy Wu <wukathy@google.com>
PiperOrigin-RevId: 916198410

Adds @functools.lru_cache to find_context_parameter so the inspect.signature
+ typing.get_type_hints lookup runs once per function, not on every MCP
confirmation callback or declaration build. No public surface change.

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 916204929

… MCP session creation failure

Co-authored-by: Sasha Sobran <asobran@google.com>
PiperOrigin-RevId: 916220631

PiperOrigin-RevId: 916227202

* Implements live inference in evaluation_generator.py using Runner.run_live().
* Updates base_eval_service.py, local_eval_service.py to support live mode data structures and connection handling.

Testing: Added unit tests:
* test_generates_inferences_with_user_simulator_live
* test_live_session_manually_triggers_callbacks
* test_live_session_manually_triggers_callbacks_with_tools
* test_perform_inference_with_use_live
* test_perform_inference_single_eval_item_live
* test_perform_inference_single_eval_item_non_live
PiperOrigin-RevId: 916231029

The file_data.file_uri path silently fell back to application/octet-stream
when no MIME type could be determined, then passed it to LiteLLM which raised
a cryptic internal ValueError. The inline_data path already had fail-fast
behavior for unsupported types but the file_data path did not.

This change removes the _DEFAULT_MIME_TYPE fallback and raises ValueError early
with an actionable message for two cases: when no MIME type can be determined
from the URI, display_name, or explicit field, and when the resolved type is
application/octet-stream regardless of whether it was set by the caller or
arrived via a library default. Both cases cause the same downstream failure.

The logic order is also corrected so that providers which always produce a
text fallback (anthropic, non-Gemini Vertex AI) and OpenAI/Azure HTTP media
URLs are handled before the MIME type guard, keeping those paths unaffected.

Tests are updated to assert the new ValueError and a new test covers the
explicit application/octet-stream case.

Adds test_content_to_message_param_user_message_file_uri_explicit_octet_stream
to confirm that an upstream caller passing mime_type='application/octet-stream'
raises a clear ValueError, covering both branches of the combined guard.

Fixes: google#5022