-
Notifications
You must be signed in to change notification settings - Fork 9
app-malt: A2A Compatibility #6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Draft
Kolleida
wants to merge
17
commits into
agentx-adapt
Choose a base branch
from
malt_a2a
base: agentx-adapt
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Conversation
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
- Query A2A endpoint for LLM answer instead of using dedicated LLM agent classes (convert main to async).
code for querying into separate file (for reuse later). Support parsing both synchronous message and task objects (defaults to last text artifact, then last text message).
(app-malt) -> now an async generator that yields the eval result objects (JSON) - Does not write to file by default anymore. - Makes it easier to process results for serving in web server. - Utils for creating the QA prompts (no Langchain) -> could be reused elsewhere.
…ver endpoint. Can handle both regular and streaming responses (with text and JSON structured output).
fail). - Each query evaluation result now also includes agent info -> lay groundwork for multiple agent evaluation at once. - Support for passing HTTP kwargs (e.g. headers) when calling each agent.
code was using raw relative path to find graph topology data, causing errors when scripts not executed from app-malt directory.
- Rename agent_utils.py -> agent_client.py and move to netarena. - App-malt now skips queries when agent cannot respond due to network errors.
- Move old LLM calling and prompting code to separate folder. - .gitignore should now properly ignore misc folders outside repo root.
results as eval artifacts (MALT agent). - Now do not need to specify agent endpoints separately in scenario.toml (just listing them in participants is good enough). - Add card-url option in compliance with Agentbeats format.
… truth code execution, improving isolation and preventing namespace pollution. Update test data with more diverse queries.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Overview
app-malt/green_agents/. Details can be found in here.netarena) for shared code across apps.uvfor dependency management.