In the human-in-the-loop example, the long_running_function_response
variable could be overwritten with `None` by a subsequent event that
did not contain a function response. This would cause the logic that
depends on the response to fail.
Fixes#375
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* fix: updated adk version to 1.10.0
fix: updated adk version to 1.10.0, and confirmed the demos work properly.
* fix: add session resumption
fix: add session resumption
* fix: adding session resumption to the docs.
fix: adding session resumption to the docs.
* fix: applied `await` on the `session_service.create_session()` call
* added license to the code
---------
Co-authored-by: Sita Lakshmi Sangameswaran <sitalakshmi@google.com>
* fix: update state key references
* update docs to include info on state injection in instructions
* update java snippet
* add docs on InstructionProvider
* add tooltip on direct state modification
---------
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
* fix: change call_agent to call_agent_async
* added await in storyflow where missing
* updated callbacks and storyflow with await and user comment
* fixed more
* added licencse header
---------
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
Co-authored-by: Lavi Nigam <lavinigam@google.com>
The LRO (Long-Running Operation) and HTIL (Human-in-the-Loop) tools were failing to execute properly due to an unhandled promise.
The `session_service.create_session` method is asynchronous but was not being awaited, causing race conditions. This change adds the required `await` to ensure proper execution flow.
Additionally, the related documentation has been updated to reflect the corrected code.
The loop agents example snippet did not have imports, which could break the code when copied directly and executed.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
* fix: Added SSL CERT setting and code snippets
fix: Added SSL CERT setting and code snippets
* fix: update the model name to -exp
fix: update the model name to -exp
* fix: changed model names on the troubleshooting tips
fix: changed model names on the troubleshooting tips
* fix(tutorial): Correct say_hello tool logic, update LLM models, and ensure async session creation
This commit addresses several issues and updates within the ADK agent team tutorial (adk_tutorial.ipynb) and its corresponding documentation (agent-team.md).
Notebook Updates (adk-tutorial.ipynb):
- Ensured all `SessionService.create_session` calls are `await`ed for proper asynchronous operation throughout the notebook.
- Updated Anthropic model to `claude-sonnet-4-20250514` and OpenAI model to `gpt-4.1`, with commented alternatives for flexibility.
- Added LiteLLM documentation links for model references.
- Resolved the 'Hello None' issue in Step 3 by modifying the `say_hello` tool to correctly handle optional name arguments and prevent the `Default value is not supported` warning with Gemini models.
- Tested and confirmed notebook compatibility with `google-adk==1.0.0`.
Page Update (agent-team.md):
- Synchronized `agent-team.md` with all notebook changes to ensure documentation accuracy and reflect the latest updates.
* fix(tutorial): Refine CLI/Web UI agent team tutorial and update content
This commit introduces several fixes and improvements to the Python file-based version of the ADK agent team tutorial, aligning it for use with `adk web`, `adk run`, and `adk api_server`.
Key changes to the `adk-tutorial` Python files:
- Validated and ensured all tutorial steps are compatible with `google-adk==1.0.0`.
- Synchronized Python file content with the latest changes from the main Colab notebook version.
- Corrected `step2_anthropic.py`: agent name, description, and instruction strings now accurately reflect Anthropic context (previously used GPT-related strings).
- Updated model identifiers: `anthropic/claude-sonnet-4-20250514` in `step2_anthropic.py` and `openai/gpt-4.1` in `step2_gpt4.py`.
- Performed general cleanup and refactoring in `step3_agent_team.py`.
- Added example queries directly within the agent Python files for Steps 1, 2, 3, 5, and 6 to facilitate easier testing by users.
- Removed `step4_state_personalization.py` as its demonstration of session state manipulation (especially direct InMemorySessionService updates) is better suited for an interactive notebook environment.
README.md Updates:
- Added a note explaining the removal of Step 4 and directing users to the interactive notebook version for that specific content.
- Included references to the newly added sample queries in the agent Python files, guiding users on how to test the agent's functionalities.
Correct `adk run` and `adk api_server` commands by removing script-specific references. Adjust documentation link titles and URLs to point to updated sections for clarity and accuracy.
Co-authored-by: Kristopher Overholt <koverholt@gmail.com>
* feat: Add shop agent notebook
This is a supplemental notebook sample for upcoming video created with Sita.
* fix: add mermaid code for the diagram
add mermaid code for the diagram
---------
Co-authored-by: Sita Lakshmi Sangameswaran <sitalakshmi@google.com>
* feat: Improve workflow agent examples (Loop, Parallel, Sequence)
This commit enhances the examples for LoopAgent, ParallelAgent, and SequenceAgent to provide clearer usage patterns, demonstrate key features, and improve developer experience.
Agent-Specific Fixes & Enhancements:
LoopAgent:
Adds an example demonstrating CheckCondition usage, showing both max_iterations and custom condition-based termination.
Fixesgoogle/adk-docs#67, google/adk-docs#148, google/adk-python#315
ParallelAgent:
Adds an example showing how to merge outputs from parallel branches using a subsequent SequentialAgent and agent states.
Demonstrates state/output control after parallel execution.
Fixesgoogle/adk-docs#142
SequenceAgent:
Clarifies the example to show explicit use of agent states within instructions for passing outputs between sequential steps.
Fixesgoogle/adk-docs#150
General Example Improvements (Applied across all three):
Updated examples to use InMemoryRunner.
Adopted new, clearer instruction prompt templates.
Included runner.run_async calls in standalone .py files to demonstrate programmatic execution outside adk web.
Enhanced InMemoryRunner print output for better visibility of individual agent outputs during execution.
Added commented-out asyncio.run() calls in .py files for environments requiring explicit async loop management.
Included multiple example queries in .py files for testing.
Added "Part of agent.py -->" comment for easy copy-pasting into agent.py for use with adk web.
Added copyright and license headers for each file.
* fix: instructions for LoopAgent is cleaned up and removed backticks. Changed the init to include initial state in the ---8<
* feat(LoopAgent): add exit_loop tool for controlled exit
Introduces the `exit_loop` tool, enabling the agent to programmatically trigger an exit from its processing loop based on internal logic or tool usage.
fix(LoopAgent): correct state f-string formatting
Resolves runtime errors caused by incorrect f-string formatting when state variables were used within the agent's execution flow.
chore: Temporarily comment out session/runner setup
Comments out initialization code related to session, runner, and agent interaction for debugging/refactoring purposes. This section should be revisited.
* fix: tutorial section overhaul and bug fixes
- Tutorial section is moved out of getting started and is a seperate section
- Fixed a sentence in getting-started page that still showed “google search”
- Given we will have more tutorials as part of docs, now we have sub-sections with the tutorial name
- For weather agent team - fixed issues pointed out in #118#135
- It now includes code for asynio in the notebook
- It also now has .py file to run it through adk web
- Step 2 is now optional and not connected to other steps. So user can follow other steps if they choose to
- There is disclaimer at the top - for different method to run the code
- The text on the page is now synced with notebook
- Collab and social link are updated with new changes in folder.
* added a redirect in the redirect_maps
* adding license headers in the code for tutorial for .py files
Mandy Chan