Repository navigation
Add the agent sample and regression harness - #111
Merged
Merged
Conversation
A runnable agent against the in-process test server, using Azure AI Foundry (Entra ID) or any OpenAI-compatible endpoint, with a chat mode and an eval mode that reports pass rate, tool calls, rejected queries and tokens. AgentLoopTests runs the full tool loop in CI with a scripted chat client. Adds Linq2GraphQL.Client.AI to the release filter and documents agent mode in the README.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Slice 6 of agent mode (see
docs/design/agent-mode.md).Sample (
test/Linq2GraphQL.Agent.Sample)Agent:ServerUrlis set.DefaultAzureCredential(no keys), or any OpenAI-compatible endpoint such as Ollama.chatmode (default) andeval [questions.json], which reports PASS/FAIL, tool calls, rejected queries, tokens and duration, and writeseval-*.json.--verboseprints each tool call.LINQ2GRAPHQL_environment variables; nothing secret in the repo.CI loop test
AgentLoopTests: a scriptedIChatClientplays the model and Microsoft.Extensions.AI function invocation runs the real tools against the test server (explore → query → answer, and fixing a rejected paged query).Other
Linq2GraphQL.Client.AIadded toLinq2GraphQL.Release.slnf, so it publishes with the next release.Build: 0 warnings. Tests: 294 passed.