Draft Proposal: Adding agentserver library#49572
Draft
johnoliver wants to merge 5 commits into
Draft
Conversation
Contributor
|
Thank you for your contribution @johnoliver! We will review the pull request and get back to you soon. |
…lient Add two new Agent Server samples and supporting API changes: - azure-agentserver-translator-sample: an Agent Server that translates input text to Italian via Azure OpenAI, demonstrating both the synchronous completions path and a token-by-token streaming path. - azure-ai-agents-sdk-client-sample: end-to-end client sample that deploys a hosted agent to Azure AI Foundry and invokes it through the com.azure:azure-ai-agents SDK, with idempotent deployment and printed managed-identity RBAC guidance. azure-agentserver-api changes supporting the translator sample: - AgentServerCreateResponse.inputText() now handles the structured input[] message shape (Foundry chat playground / multi-turn), not just a plain text input, returning the most recent user message. - ResponseEventStream gains streamChatCompletion / streamDeltas helpers that forward chat-completion chunks as output_text delta events. - Added serialization tests for the new inputText shapes. Register both modules in the agentserver parent pom. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This pull request introduces the initial implementation of the Azure Agent Server API module for Java, providing the foundational API and data structures for building agent servers compatible with the OpenAI Responses API and Azure AI Foundry. The changes include a new Maven module with its dependencies, key protocol data types, and a comprehensive README for the Java Agent Server Adapter.
Key changes:
Documentation and Developer Experience
README.mdfor the Java Agent Server Adapter, including project structure, build instructions, sample usage, Docker integration, Azure AI Foundry deployment, and TLS proxy certificate handling for the Azure hosting environment.New Maven Module and Dependencies
azure-agentserver-apiMaven module with apom.xmlthat declares dependencies on SLF4J, Jackson, OpenAI Java SDK, Azure SDKs, Netty (for networking), OpenTelemetry, and test libraries. This sets up the foundational library for agent server development.Core API Data Types
AgentReferenceandAgentReferenceTyperecords/enums to represent agent identity and reference types in the Foundry protocol, with Jackson annotations for robust JSON serialization/deserialization. [1] [2]AgentServerCreateResponse, a record representing incoming create-response requests, including custom Jackson deserialization logic to handle both standard and legacy Foundry request formats, and to inject missing type discriminators for input items. This ensures compatibility and resilience when parsing requests from various clients.All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines