diff --git a/reme/config/benchmark.yaml b/reme/config/benchmark.yaml index d9d51c3e..3f239c80 100644 --- a/reme/config/benchmark.yaml +++ b/reme/config/benchmark.yaml @@ -327,7 +327,7 @@ jobs: frontmatter_read: backend: base - description: "Read a file's frontmatter as a dict." + description: "Read a file's frontmatter, one key: value per line." parameters: type: object properties: diff --git a/reme/steps/file_io/frontmatter_read.py b/reme/steps/file_io/frontmatter_read.py index d557b8ff..0f41338d 100644 --- a/reme/steps/file_io/frontmatter_read.py +++ b/reme/steps/file_io/frontmatter_read.py @@ -1,9 +1,11 @@ -"""``frontmatter_read_step`` — return the frontmatter dict of a markdown file. +"""``frontmatter_read_step`` — surface a markdown file's frontmatter. Cheap structured read — frontmatter only, no body. Use ``body:read`` for the post-frontmatter content slice, or whole-file ``read`` when -you want both at once. Returns ``{exists: false}`` when the target -doesn't exist; otherwise ``{exists: true, frontmatter: {...}}``. +you want both at once. The answer is textual — ``- key: value`` per +line — because MCP callers only ever see ``answer``; the parsed +mapping itself is returned in ``metadata["frontmatter"]`` (and +``exists: false`` in metadata when the target doesn't exist). ``path`` is a path relative to the workspace. """ @@ -20,25 +22,22 @@ from ...components import R def _render_value(value) -> str: - """Flatten one frontmatter value onto a single answer line.""" - if isinstance(value, (list, tuple)): - rendered = ", ".join(str(item) for item in value) - elif isinstance(value, dict): - rendered = json.dumps(value, ensure_ascii=False, sort_keys=True) - else: - rendered = str(value) - return " ".join(rendered.split()) + """Render one frontmatter key or value on a single answer line. - -def _render_frontmatter(meta: dict) -> list[str]: - """Render each frontmatter key on its own ``- key: value`` line. - - ``frontmatter_read`` is served straight to the LLM, so the answer has to - carry the frontmatter itself; a key count alone leaves the caller with - nothing to act on. Values are flattened to one line each so a multi-line - description cannot break the line-per-key layout. + ``frontmatter_read`` is served straight to the LLM, so the answer has + to carry the frontmatter itself. Collections keep their JSON shape so + list boundaries, empty collections, and nested structure stay visible; + ``default=str`` covers YAML-only types such as dates, and skipping key + sort keeps mixed-type mapping keys loadable. Bare strings are the one + exception — quoting every scalar would drown the answer in noise — but + their line breaks are escaped so the one-key-per-line layout survives. """ - return [f"- {key}: {_render_value(value)}" for key, value in meta.items()] + if isinstance(value, str): + return value.replace("\r", "\\r").replace("\n", "\\n") + try: + return json.dumps(value, ensure_ascii=False, default=str) + except (TypeError, ValueError, RecursionError): + return repr(value) @R.register("frontmatter_read_step") @@ -87,7 +86,7 @@ class FrontmatterReadStep(BaseStep): return self.context.response.success = True header = f"Read frontmatter from {probed} ({len(meta)} key(s))" - rendered = _render_frontmatter(meta) + rendered = [f"- {_render_value(key)}: {_render_value(value)}" for key, value in meta.items()] self.context.response.answer = f"{header}:\n" + "\n".join(rendered) if rendered else f"{header}: (no keys)" self.context.response.metadata.update({"path": path, "exists": True, "frontmatter": meta, **resolved}) self.logger.info(f"[{self.name}] path={path} keys={len(meta)}") diff --git a/tests/unit/test_frontmatter_steps.py b/tests/unit/test_frontmatter_steps.py index af0e279a..b71a2dbd 100644 --- a/tests/unit/test_frontmatter_steps.py +++ b/tests/unit/test_frontmatter_steps.py @@ -12,6 +12,7 @@ probed path in not-found errors instead of the caller's raw input. import os import tempfile +from datetime import date from pathlib import Path import pytest @@ -207,14 +208,14 @@ async def test_read_answer_carries_the_frontmatter_itself(): store = await _make_store() resp = await _run(FrontmatterReadStep, store, path="notes/post") assert resp.success is True - assert resp.answer == "Read frontmatter from notes/post.md (2 key(s)):\n- name: n\n- tags: a" + assert resp.answer == 'Read frontmatter from notes/post.md (2 key(s)):\n- name: n\n- tags: ["a"]' assert resp.metadata["frontmatter"] == {"name": "n", "tags": ["a"]} await store.close() @pytest.mark.asyncio -async def test_read_answer_flattens_values_and_reports_empty(): - """Multi-line, list and nested values stay on one line each; empty says so.""" +async def test_read_answer_preserves_value_structure_and_reports_empty(): + """Multi-line values stay on one line each; lists keep their shape; empty says so.""" with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp): _seed( Path(tmp), @@ -225,15 +226,74 @@ async def test_read_answer_flattens_values_and_reports_empty(): store = await _make_store() resp = await _run(FrontmatterReadStep, store, path="notes/rich.md") + assert resp.success is True assert resp.answer == ( "Read frontmatter from notes/rich.md (4 key(s)):\n" "- name: Cobalt\n" "- description: line one line two\n" - "- tags: a, b\n" + '- tags: ["a", "b"]\n' '- nested: {"x": 1}' ) + assert resp.metadata["frontmatter"] == { + "name": "Cobalt", + "description": "line one line two", + "tags": ["a", "b"], + "nested": {"x": 1}, + } resp = await _run(FrontmatterReadStep, store, path="notes/empty.md") + assert resp.success is True assert resp.answer == "Read frontmatter from notes/empty.md (0 key(s)): (no keys)" assert resp.metadata["frontmatter"] == {} await store.close() + + +@pytest.mark.asyncio +async def test_read_answer_tolerates_rich_yaml_types(): + """Rendering must never turn a parseable frontmatter into a failed job. + + Regression test for the review findings: YAML dates (``datetime.date``) + crashed ``json.dumps``, mixed mapping keys crashed ``sort_keys``, and + comma-joined lists / collapsed whitespace lost value boundaries. All of + these stay successful reads with the structured ``metadata`` untouched. + """ + rich = ( + "---\n" + "created: 2026-10-12\n" + "schedule:\n" + " 1: one\n" + " label: two\n" + "tags: []\n" + "aliases:\n" + ' - "a, b"\n' + " - c\n" + 'command: "echo a b"\n' + "description: |-\n" + " line one\n" + " line two\n" + "---\n" + "body\n" + ) + with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp): + _seed(Path(tmp), "notes/types.md", rich) + store = await _make_store() + resp = await _run(FrontmatterReadStep, store, path="notes/types.md") + assert resp.success is True + assert resp.answer == ( + "Read frontmatter from notes/types.md (6 key(s)):\n" + '- created: "2026-10-12"\n' + '- schedule: {"1": "one", "label": "two"}\n' + "- tags: []\n" + '- aliases: ["a, b", "c"]\n' + "- command: echo a b\n" + "- description: line one\\nline two" + ) + assert resp.metadata["frontmatter"] == { + "created": date(2026, 10, 12), + "schedule": {1: "one", "label": "two"}, + "tags": [], + "aliases": ["a, b", "c"], + "command": "echo a b", + "description": "line one\nline two", + } + await store.close()