Add AI integration testing suite#214
Open
gvdongen wants to merge 12 commits into
Open
Conversation
gvdongen
marked this pull request as ready for review
July 17, 2026 16:11
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds an end-to-end AI integration test suite for the Python SDK’s Restate AI integrations:
The suite runs the integrations against a real Restate test harness and focuses on the failure modes most likely to break during upstream Agent SDK upgrades: journal mismatches, replay instability, changed response types, tool execution, multi-turn session state, handoffs, and concurrent invocations.
What changed
ai-tests/with scripted and live-model scenarios for each integration.create_test_harness(...)fixtures.always_replay=Trueanddisable_retries=True.justrecipes per integration and for the full AI suite.Why
Keeping these integrations compatible with fast-moving Agent SDKs currently requires manual upgrades and example testing. This PR makes that process repeatable: bump an SDK, run the focused integration suite, and catch the common breakages before merging.
The tests are integration checks, not model evals. They verify that the SDK protocols remain compatible and deterministic under Restate replay.
Testing
just test-ai-scripted(without OpenAI and Google API key, orjust test-aiwith API keysThis currently runs the deterministic variants for all four integrations.