* fix: Update formatting of the Bidi-streaming dev guide part 1
fix: Update formatting of the Bidi-streaming dev guide part 1
* fix: update mkdocs.yml for the streaming doc updates
fix: update mkdocs.yml for the streaming doc updates
---------
Co-authored-by: Kristopher Overholt <koverholt@gmail.com>
* fix: missing links and formatting on streaming index.md
fix: missing links and formatting on streaming index.md
* fix: missing links and formatting on streaming/index.md
fix: missing links and formatting on streaming/index.md
* feat: modifying the Evaluate docs with the new features.
New features added:
1. Evaluation Configuration: users can now configure custom threshold for the metrics used for each eval run, allowing more control for the evaluation criteria
2. Evaluation Case view & edit: Each eval case added can now be viewed and edited. Right now we only support edit of text responses from Agent. This allows users to customize the response to fit their needs
3. New tracing: We have a new tab which contains all traces grouped by user messages. Each trace row is clickable and hoverable. Upon hover the corresponding message will be highlighted in the chat window. Upon click, the bottom panel will show up that contains Event detail, Request, Response, and Graph that corresponds to that trace row
* fix: modified the Step 2, and added the Trace View section
fix: modified the Step 2, and added the Trace View section
* fix: added gif animations
fix: added gif animations
* fix: inserted the gif animations
fix: inserted the gif animations
* fix: added an explanation for the blue rows
fix: added an explanation for the blue rows
* doc: Update quickstart-streaming.md
doc: remove the model name as it changes very often and it's causing confusion. instead, point them to the right source so they can figure it out.
* doc: Update quickstart-streaming.md
* doc: Update quickstart-streaming.md
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.
Updated the Markdown link to point directly to the relevant section (output_key) within the LLM Agent documentation, instead of linking to the top of the page.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
I've added a new section to `docs/sessions/state.md` detailing the recommended method of updating session state. This method ensures changes are properly tracked.
I also refined the existing "A Warning About Direct State Modification" section to more precisely define which types of direct state modification are discouraged and to ensure it doesn't conflict with the newly added documentation for context-based state updates.
Examples for both Python and Java are provided for the new method. This addresses issue #267 by ensuring all recommended state modification paths are documented.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
* fix: remove as_dict() usage from final session state logging
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit removes the invalid `.as_dict()` call.
* fix: remove .as_dict() usage from final session state logging
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit like the previous one removes another occurence of the `.as_dict()` call.
---------
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
- #254 docs/sessions/session.md -> …part of session object's identification.
In the session object identification description, it was unclear (for first time readers), what exactly is id, and app_name and how they are different. Added some examples according to my own understanding. Please change accordingly if you feel so. Thanks.
- #252 Multiple files: quickstart-streaming.md, quickstart.md, mcp-tools.md
add an option in the CLI to enable or disable the reload feature. So users(esp. windows) can disable this if they come across the '_make_subprocess_transport NotImplementedError' bug on windows.
- #179 docs/agents/models.md -> Add Windows Encoding Note for LiteLLM
When using ADK agents with LiteLlm on Windows, users might encounter a UnicodeDecodeError: 'charmap' codec can't decode byte... error. This often happens when litellm (used by LiteLlm) tries to read cached files (like model pricing information) using the default Windows encoding (cp1252) instead of UTF-8.
- #170 docs/tools/mcp-tools.md fix: update ADK setup link and add .env file location note in MCPTools.
Also resolved the issue: #169
Removed the incorrect instruction to copy code into a non-existent `main.py` file. Now it only mentions `__init__.py`, matching the ADK streaming guide and avoiding confusion during setup.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
* Update authentication.md
Fix an example code that refers to undefined variables.
* Update authentication.md
use client_id and client_secret stored in auth_credential.
* Update authentication.md
Add missing imports
* Update authentication.md
Update for the latest auth lib.
---------
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
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit replaces it with direct usage of the dictionary and adds a comment.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
sitalakshmi