chore: improve automated example coverage and local service handling#3297
Merged
chore: improve automated example coverage and local service handling#3297
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request improves the reliability and coverage of automated example validation by making examples easier to run in non-interactive Codex workflows, reducing avoidable environment-specific failures, and adding focused local smoke tests for integrations that previously required more manual setup.
The examples runner now supports default optional dependency extras, unbuffered module execution, temporary local Redis startup for the Redis memory example, prerequisite-based Dapr skipping, and clearer guidance to run example batches outside the Codex sandbox when examples need nested sandboxes or local services. This keeps full-suite example runs closer to real usage while avoiding failures caused only by missing local daemons or sandbox restrictions.
It also adds or hardens local verification paths for integration examples: the SSE MCP example can fall back to a bundled local SSE server instead of relying on a remote service, the MCP Manager FastAPI example has a separate smoke test that exercises app/server integration without complicating the app itself, and the Temporal sandbox extension now includes a minimal local SandboxAgent workflow that uses the real model API, defaults to OpenAI tracing, and allows tracing mode selection.
The Daytona USAspending text-to-SQL example is adjusted for automated runs by failing early on missing credentials, emitting clearer progress, using a deterministic auto-mode prompt, avoiding long memory generation during automation, and ignoring generated runtime state. The financial research example prompt and verifier guidance are also updated so automated runs avoid claims about unreleased quarterly results and judge the synthesized demo output appropriately. No released SDK APIs or persisted runtime schemas are changed.