chore(release): v0.3.2

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HBbjgS5A55RVavoyjJC4FX

CHANGELOG.md

@@ -5,6 +5,22 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.2] — 2026-07-23
+
+### Fixed
+
+- **Frontmatter and index-label values are emitted verbatim; only
+  `source_query` is whitespace-collapsed.** Earlier releases collapsed every
+  whitespace run in every frontmatter value and index link label to a single
+  space. §5 of `ingest-spec.md` mandates that collapse for `source_query`
+  alone — where a multi-line SQL `SELECT` must render on one line — while
+  every other value is validated single-line at manifest load and passed
+  through unchanged: validation, not repair. A `title` carrying an internal
+  whitespace run now survives byte-for-byte at both the `title` frontmatter
+  and the index link label, instead of being silently altered. Output bytes
+  change only for values that contained a collapsible whitespace run; the
+  shipped golden fixtures and both consumers are unaffected.
+
 ## [0.3.1] — 2026-07-19
 
 ### Fixed

CLAUDE.md

@@ -11,7 +11,8 @@ one boundary rule:
   `ingest-{id}.md` → index generation; zero model calls). This repo
   IMPLEMENTS the spec; commons keeps authorship. Spec changes the library
   needs go via commons, never edited locally. The library ships the §11
-  golden fixtures (byte-exact) that are missing today.
+  golden fixtures (byte-exact) for the three door-A source types
+  (`ingest-golden-{file,sql,http}/`, shipped in `9dd86b1`).
 - **Door B — bundle inbox:** converts dropped files to OKF concepts. All
   file-type→text extraction lives HERE (the guard is text-only). v1 core:
   `md`, `txt`, `csv`, `json`, `html` (stdlib). `pdf`/`docx`/`xlsx` only via

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "llm-ingestion-okf"
-version = "0.3.1"
+version = "0.3.2"
 description = "Shared OKF (Open Knowledge Format) ingestion library: spec-based connectors, bundle inbox, and external-bundle import, with security delegated to llm-ingestion-guard."
 readme = "README.md"
 license = "MIT"

src/llm_ingestion_okf/__init__.py

@@ -35,7 +35,7 @@ from .manifest import (
 )
 from .materialize import IngestResult, materialize_bundle
 
-__version__ = "0.3.1"
+__version__ = "0.3.2"
 
 __all__ = [
     "Extraction",

src/llm_ingestion_okf/connectors.py

@@ -35,7 +35,14 @@ def safe_resolve(root: Path, relative: str) -> Path:
     a naive startswith would not).
     """
     real_root = os.path.realpath(root)
-    candidate = os.path.realpath(os.path.join(real_root, relative))
+    try:
+        candidate = os.path.realpath(os.path.join(real_root, relative))
+    except ValueError as exc:
+        # An embedded NUL makes the path syscalls reject the string before
+        # any boundary check can run. SourceError promises a typed failure,
+        # so a target that cannot be resolved at all fails closed under the
+        # boundary code rather than leaking an untyped ValueError.
+        raise SourceError(f"path is not resolvable: {relative!r}", code="path_escape") from exc
     try:
         within = os.path.commonpath([real_root, candidate]) == real_root
     except ValueError:

src/llm_ingestion_okf/errors.py

@@ -55,7 +55,8 @@ class SourceError(IngestError):
     OSError and never silent truncation.
 
     Codes:
-    - `path_escape` — a path resolves outside its root directory
+    - `path_escape` — a path resolves outside its root directory, or cannot
+      be resolved at all (e.g. an embedded NUL byte)
     - `source_root_missing` — the file-source root is not a directory
     - `source_file_missing` — the query does not resolve to a file
     - `csv_no_header` — the CSV has no header row

src/llm_ingestion_okf/materialize.py

@@ -49,11 +49,22 @@ class IngestResult:
     stamp: str
 
 
+def _collapse_whitespace(value: str) -> str:
+    # §5 mandates whitespace-run collapse for ONE field only: `source_query`
+    # (ingest-spec.md:140-141), where a legitimately multi-line SQL SELECT
+    # must render on one line. Every other value is validated single-line at
+    # manifest load and emitted verbatim — validation, not repair — so
+    # operator-supplied bytes (e.g. a title's internal double space) survive.
+    return " ".join(value.split())
+
+
 def _render_frontmatter(frontmatter: dict[str, str]) -> str:
-    # Line-oriented `key: value`; values are single-lined (whitespace runs,
+    # Line-oriented `key: value`, insertion order. Only `source_query` is
-    # including newlines, collapse to one space — §5) because parsing is
+    # collapsed; all other values pass through verbatim.
-    # line-oriented and stops at the first `---` line. Insertion order.
+    return "\n".join(
-    return "\n".join(f"{key}: {' '.join(value.split())}" for key, value in frontmatter.items())
+        f"{key}: {_collapse_whitespace(value) if key == 'source_query' else value}"
+        for key, value in frontmatter.items()
+    )
 
 
 def _parse_frontmatter(path: Path) -> dict[str, str]:

tests/test_error_codes.py

@@ -157,6 +157,17 @@ def test_path_escape(tmp_path: Path) -> None:
     assert code_of(excinfo) == "path_escape"
 
 
+def test_path_escape_covers_embedded_null(tmp_path: Path) -> None:
+    # A NUL byte makes the OS path syscalls raise ValueError before any
+    # boundary check runs. SourceError promises "always typed, never a
+    # leaked OSError" — an untyped ValueError breaks that contract, so a
+    # malformed target must fail closed under the same code as any other
+    # target that cannot resolve inside the root.
+    with pytest.raises(SourceError) as excinfo:
+        safe_resolve(tmp_path, "bad\x00.md")
+    assert code_of(excinfo) == "path_escape"
+
+
 def test_source_root_missing(tmp_path: Path) -> None:
     with pytest.raises(SourceError) as excinfo:
         read_csv(tmp_path / "nope", "a.csv", max_rows=1)

tests/test_materialize.py

@@ -124,6 +124,73 @@ def test_file_source_concept_file_exact_bytes(file_setup: tuple[Path, Path]) ->
     assert (bundle / "ingest-orders.md").read_bytes() == expected.encode("utf-8")
 
 
+def test_title_renders_identically_in_frontmatter_and_index(tmp_path: Path) -> None:
+    # §4: the title "becomes the `title` frontmatter AND the index link
+    # label" — one value, two sites, so the two MUST agree. The frontmatter
+    # renderer single-lines its values; the index label was written raw, so
+    # a title carrying a whitespace run diverged between the two.
+    src = tmp_path / "src"
+    manifest_path = write_manifest(
+        src,
+        file_manifest_data(
+            [
+                {
+                    "id": "orders",
+                    "title": "Energiforbruk  2024",
+                    "query": "orders.csv",
+                    "okf_type": "dataset",
+                    "max_rows": 100,
+                }
+            ]
+        ),
+    )
+    (src / "data").mkdir()
+    (src / "data" / "orders.csv").write_text("a,b\n1,x\n", encoding="utf-8", newline="")
+    bundle = tmp_path / "bundle"
+
+    materialize_bundle(manifest_path, bundle, ingested_at=INGESTED_AT)
+
+    concept = (bundle / "ingest-orders.md").read_text(encoding="utf-8")
+    index = (bundle / "index.md").read_text(encoding="utf-8")
+    frontmatter_title = next(
+        line.partition(":")[2].strip() for line in concept.splitlines() if line.startswith("title:")
+    )
+    index_label = index.partition("- [")[2].partition("]")[0]
+    assert frontmatter_title == index_label
+
+
+def test_title_emitted_verbatim_not_collapsed(tmp_path: Path) -> None:
+    # §5 mandates whitespace-run collapse ONLY for `source_query`
+    # (ingest-spec.md:140-141). `title` is validated single-line at manifest
+    # load and emitted verbatim — validation, not repair — so an internal
+    # whitespace run survives at BOTH the frontmatter and the index-label site.
+    src = tmp_path / "src"
+    manifest_path = write_manifest(
+        src,
+        file_manifest_data(
+            [
+                {
+                    "id": "orders",
+                    "title": "Energiforbruk  2024",
+                    "query": "orders.csv",
+                    "okf_type": "dataset",
+                    "max_rows": 100,
+                }
+            ]
+        ),
+    )
+    (src / "data").mkdir()
+    (src / "data" / "orders.csv").write_text("a,b\n1,x\n", encoding="utf-8", newline="")
+    bundle = tmp_path / "bundle"
+
+    materialize_bundle(manifest_path, bundle, ingested_at=INGESTED_AT)
+
+    concept = (bundle / "ingest-orders.md").read_text(encoding="utf-8")
+    index = (bundle / "index.md").read_text(encoding="utf-8")
+    assert "title: Energiforbruk  2024\n" in concept
+    assert "- [Energiforbruk  2024](ingest-orders.md)" in index
+
+
 def test_result_lists_written_concept_files(file_setup: tuple[Path, Path]) -> None:
     manifest_path, bundle = file_setup
     result = materialize_bundle(manifest_path, bundle, INGESTED_AT)

uv.lock

@@ -166,7 +166,7 @@ wheels = [
 
 [[package]]
 name = "llm-ingestion-okf"
-version = "0.3.1"
+version = "0.3.2"
 source = { editable = "." }
 
 [package.dev-dependencies]