L/api docs#358
Merged
Merged
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
Resolve PR conflicts in chat service, MCP patch compatibility, and chat tests.
- Fix test_execute_emits_working_and_completed to assert 'input-required' instead of 'completed', matching the production code which emits TaskState.input_required for multi-turn A2A conversation support - Populate _visible_params in AgentTool.__init__ so tests that assert against it continue to work correctly Applied via @cursor push command
…/hud-evals/hud-python into feat/a2a-chat-orchestrator-clean
Feat/a2a chat orchestrator clean #HUD-935
add claude citations HUD-985
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Note
Medium Risk
Medium risk because it changes core agent execution to support multi-turn conversation inputs and citation propagation across providers, and modifies deploy/dev CLI behavior around env var syncing and MCP proxy tool forwarding.
Overview
Adds substantial new documentation for remote testing and REST API usage, plus a new guide for multi-turn chat scenarios (including A2A serving and examples) and updates nav/index pages to surface these docs.
Updates the Python SDK to better support chat-style, multi-turn agent runs by accepting conversation histories, mapping provider roles (notably Gemini’s
modelrole), and exportingChatfromhud.__init__. Introduces provider-normalizedcitationsinInferenceResult/Trace, extracts citations from OpenAI/Claude/Gemini responses, and (when enabled) threads tool outputs into provider-specific citation mechanisms;run()now submits{content, citations}when citations exist.Improves tooling and DX:
hud deploynow supports--no-env, persists a.envsync preference in.hud/deploy.json, and the build summary can show the environment name plus a quick-start task JSON. The Docker dev proxy now forwards hidden tools via a fallback client and cleans it up on shutdown, and dataset/task runners inject anEnv-Hud-Model-Nameheader for HUD hub connections.Written by Cursor Bugbot for commit 5d7843f. This will update automatically on new commits. Configure here.