Expand agent participant configuration with logging, debugging, and web search#896
Conversation
Display agent-specific information when viewing agent participant stats: - Agent configuration (API type, model, prompt context) - Summary of API calls (total, successful, failed counts) - Detailed log entries for each LLM call with: - Status, timestamp, and duration - Stage where the call was made - Expandable prompt and response details This helps experimenters debug and monitor agent participant behavior in real-time as logs stream in via Firestore. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix empty agentId causing Firestore path error in getAgentParticipantPrompt
When agent participants are created without a persona, agentId is empty string
which caused .doc('') to crash. Now returns null to use default prompts.
- Fix Gemini API not parsing JSON responses for agent participants
Added missing addParsedModelResponse() call that OpenAI/Claude APIs had.
This was preventing profile and survey stage responses from being processed.
- Add debug logging to agent participant and chat flows
Logs prefixed with [AgentParticipant], [AgentChat], [ChatTrigger] to help
trace issues in Firebase Functions console.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add useWebSearch option to agent model settings for Gemini and Claude - Hide web search option in UI for OpenAI/Ollama (not supported) - Fix Claude API to extract text from correct content block when web search is used - Fix dialog overlay z-index to appear above cohort-list header - Add chat settings support for quick-add agent participants 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
|
I'd signed it but needed to resync, if you check now you should you should see I've signed |
|
I see that the CLA check is failing for Claude 😆 |
|
This pull request has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. If this PR is still relevant, please leave a comment or remove the |
Hiya! I found agent participants weren't completing stages as intended and had their responses incorrectly parsed in group chats so have vibe-coded a fix. Code was written by Claude - I did my best to guide it towards making the minimum changes necessary and not introduce any breaking changes.
As part of the PR I've included a way to view agent participant API logs in the UI and have expanded the agent participant config UI component. Here's a video showing the result:
Summary
This PR enhances agent participant functionality with three main improvements:
Changes
Agent Log Viewer
Agent Participant Bug Fixes
Expanded Agent Configuration
agent-participant-configuration-dialogcomponentBackend Changes
useWebSearchtoAgentModelSettingsinterfacegoogleSearchtoolweb_search_20250305tool integrationTesting
I've created a few experiments with 'group chat', 'set your profile', and 'survey' stages, and have tested them against each combination of (Google/Anthropic/OpenAI, w/wo web search), with between one and four agent participants. The parsing errors have disappeared, the API log viewer seems to work, and the new agent participant settings worked as intended.
I haven't included automated tests as the contrib guidelines didn't ask for them, however if you have something in mind please say.
Known Limitations