Install Codeflash Github action

[misrasaurabh1]

• This Pull Request sets up the codeflash.yml file which will run on every new Pull Request that modifies the source code for pydantic_ai_slim/pydantic_ai and is covered by the tests/test_examples.py.
• We modified the test file to add benchmark to selectively trace and benchmark the examples.
• We have installed codeflash as a dev dependency, and setup the codeflash config in the pyproject.toml file.

Actions Required to make this work-

• Install the Codeflash Github app from this link to this repo. This is required for our github-bot to comment and create suggestions on the github repo.
• Create a new CODEFLASH_API_KEY after signing up to Codeflash from our website. The onboarding will ask you to create an API Key and show instructions on how to save the api key on your repo secrets.

Then, after this PR is merged in it will start generating new optimizations 🎉

[hyperlint-ai]

PR Change Summary

Set up Codeflash GitHub action with necessary configurations and added guidance for development and testing.

• Installed Codeflash as a dev dependency and configured it in the pyproject.toml file.
• Added CLAUDE.md for development guidance and project architecture.
• Updated several documentation files to reflect new features and integrations.
• Modified API documentation to include new providers and configuration options.

Modified Files

• docs/ag-ui.md
• docs/api/messages.md
• docs/api/providers.md
• docs/mcp/client.md
• docs/mcp/server.md
• docs/models/index.md
• docs/models/openai.md
• docs/output.md

Added Files

• CLAUDE.md

---

How can I customize these reviews?

Check out the Hyperlint AI Reviewer docs for more information on how to customize the review.

If you just want to ignore it on this PR, you can add the hyperlint-ignore label to the PR. Future changes won't trigger a Hyperlint review.

Note specifically for link checks, we only check the first 30 links in a file and we cache the results for several hours (for instance, if you just added a page, you might experience this). Our recommendation is to add hyperlint-ignore to the PR to ignore the link check for this PR.

[DouweM]

Is this fixture coming directly from codeflash?

[KRRT7]

Yes.

This fixture is provided by codeflash & adapts based on the testing environment: it uses CodeFlash's internal benchmarking when Codeflash mechanisms are active, falls back to pytest-benchmark when available in standard pytest, or acts as a no-op otherwise to preserve normal test behavior.