Validate common AI tool-call arguments to enable pydantic-ai retries

[zozo123]

Malformed model-generated arguments currently bypass validation in the Common AI toolsets. Missing or mistyped arguments can therefore reach tool implementations and fail with KeyError or TypeError instead of producing the bounded retry that pydantic-ai supports.

Invalid payloads are now rejected at validation; pydantic-ai then regenerates a new tool call — the original malformed payload is never re-executed.

Concretely: if the model calls the query tool but omits the required sql argument, the call previously crashed the run with KeyError: 'sql'; it now raises a ValidationError that pydantic-ai turns into one bounded retry, and the model regenerates the call with sql supplied.

This change derives each tool's argument validator from the same JSON Schema advertised to the model and applies it to SQLToolset, DataFusionToolset, and HookToolset. Hook introspection keeps optional and union parameters accurate, leaves unsupported annotations permissive, drops unexpected arguments for fixed signatures, and preserves additional arguments for methods that accept **kwargs.

Validation:

• 1,043 Common AI unit tests passed
• provider mypy passed
• pre-commit and manual prek checks passed

---

Was generative AI tooling used to co-author this PR?

• Yes — Claude Code (Fable 5) and Codex (GPT-5)

Generated-by: Claude Code (Fable 5) and Codex (GPT-5) following the guidelines

[SameerMesiah97]

I think the title is a bit misleading. It appears that the malformed payload is not retried, but rather rejected during validation, allowing Pydantic AI to regenerate a new tool call. "Retry malformed tool calls" initially reads as though the original invalid payload is executed again, whereas the retry is actually another model generation. It might be worth clarifying this in the title and PR description.

This looks fine to me logically (and the tests are solid) but this will need someone who is more familiar with this provider to deeply vet the validation logic. I see a lot of small changes scattered throughout the diff that I am not sure of how to ascertain the impact of.

CI needs to be triggered too.

[zozo123]

Thanks @SameerMesiah97 — good catch on the title. Renamed to "Validate common AI tool-call arguments to enable pydantic-ai retries" and added a line to the description making explicit that the malformed payload is rejected at validation and pydantic-ai regenerates a fresh tool call (the original is never re-executed). Also replied inline on the nested-object question.