14 Commits

Author SHA1 Message Date
Shangjie Chen 556eedc958 fix(samples): update burgers test case in task sub agent
Change-Id: I91fa7b7199484eb75464158b4db502b322bcab50
2026-04-17 10:54:53 -07:00
Bo Yang 745d861395 fix(tools): Resolve string annotations in FunctionTool to fix type conversion
When from __future__ import annotations is used, type hints are stored as strings. This caused is_list_of_basemodel to fail in FunctionTool, preventing dictionaries from being automatically converted back to Pydantic models when passed to tools. Used get_type_hints to evaluate them.

Also updated 10_burgers.json test trace to reflect the successful execution after this fix.

Change-Id: I92a708dd17ef76fc222779cd28e4a2d551325ce8
2026-04-16 22:08:11 -07:00
Bo Yang 8414f1fcea fix(test): Prevent function ID mismatch in multi-agent test replay
Use a FIFO queue for function name lookups to handle multiple calls in a trace, and remove hardcoded agent names to support all task agents. Also extract duplicate post-processing logic into a shared function.

Change-Id: Ia1062c6a6ba87a0d49c3982936121ac02f2bb352
2026-04-16 19:48:55 -07:00
Bo Yang 887bb6c600 feat(agent_samples): Update intake agent instruction and add wrong_name test
Change-Id: Id1bf62307d30137151931befc4c2355eda671648
2026-04-16 14:51:20 -07:00
Bo Yang 5de4cc3f03 test(cli): Avoid AdkEvent construction during event comparison
Compare events using raw dicts instead of constructing AdkEvent objects to avoid validation overhead and potential issues. Also sort longRunningToolIds to ensure order-independent comparison.

Change-Id: Ia17ea5bd0caaa1dd1b38cbef66e10d38d5666893
2026-04-11 00:44:39 -07:00
Bo Yang 3ad14489cc fix(agents): Fix missing branch field for events in standalone agents
The is_parallel flag was ignored in Context.run_node when falling back to non-workflow mode. Now it propagates to NodeRunner so that events generated by the node correctly create a sub-branch.

Change-Id: I4f58a7fb58f998a831c48b3c0b39f18dbb828bae
2026-04-11 00:28:02 -07:00
Bo Yang 7ff410b247 test(samples): Update agent_in_workflow tests to cover approval, decline, and error cases
Change-Id: I277ed131120edb2ec61f1134553b3eaa886d734b
2026-04-10 11:08:56 -07:00
Bo Yang ed8add2e9b test(cli): Make JSON test files deterministic and sequential
Sort keys when saving rebuilt JSON test files and re-assign sequential event IDs to avoid gaps from filtered events. Also applied these changes to all existing test files in the contributing folder.

Change-Id: Ib126228f016db1d28030eee4f7d9d8cbc604e038
2026-04-10 11:08:42 -07:00
Bo Yang c97d39982f feat(workflow): Refine branch propagation for parallelism
Only add branch segments when parallelism occurs. Handle joins by using the common prefix of incoming branches.

Change-Id: If75f57e2dd69f2ddf71ade818e9c19d2a6e32c53
2026-04-10 11:08:02 -07:00
Bo Yang 4476854455 feat(events): make run_id calculated and remove from JSON dump
Change-Id: Ida7d49b36bf6f590796f5c22ca26e5dc121352a5
2026-04-09 09:44:59 -07:00
Bo Yang 1f898f833d refactor: update agent workflow to use tool confirmation. Currently tests fail due to interruption not supported in llm agent as a node in a workflow.
Change-Id: I9d41ac107d61e38629d39899cb4893780eba003e
2026-04-06 14:42:49 -07:00
Bo Yang d66d0f7d0a feat: add support for agent transfers, CLI argument handling, and set_model_response filtering in test runner
Change-Id: Ibc2efe19b010c7059beec44091abbf2df1b9826f
2026-04-05 22:54:31 -07:00
Bo Yang 6f173041b3 feat: implement task mode support in V1 LLM agent wrapper and add integration test samples
Change-Id: Icd026eb74ec37d1685db6835ef549b6efe76547e
2026-04-05 15:03:13 -07:00
Wei (Jack) Sun 1c64a41b53 feat: ADK 2.0 alpha
Introduces two major capabilities:
- Workflow runtime: graph-based execution engine for composing
  deterministic execution flows for agentic apps, with support for
  routing, fan-out/fan-in, loops, retry, state management, dynamic
  nodes, human-in-the-loop, and nested workflows
- Task API: structured agent-to-agent delegation with multi-turn
  task mode, single-turn controlled output, mixed delegation
  patterns, human-in-the-loop, and task agents as workflow nodes

Co-Authored-By: Bo Yang <ybo@google.com>
Co-Authored-By: George Weale <gweale@google.com>
Co-Authored-By: Sean Zhou <seanzhougoogle@google.com>
Co-Authored-By: Shangjie Chen <deanchen@google.com>
Co-Authored-By: Swapnil Agarwal <swapnilag@google.com>
Co-Authored-By: Wei Sun <weisun@google.com>
Co-Authored-By: Xuan Yang <xygoogle@google.com>
Co-Authored-By: Yifan Wang <wanyif@google.com>
Change-Id: I35932c50cfe29ff68559e3781713dbb5eb7b3382
2026-03-17 23:24:58 -07:00