Skip to content

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

refactor(generation): validate evidence files in one place (#1251)

Sergei Iakhnitskii38dd5543b45a
diff --git a/packages/core/src/repowise/core/generation/models.py b/packages/core/src/repowise/core/generation/models.py
index 8a112450e..7317ca6fb 100644
--- a/packages/core/src/repowise/core/generation/models.py
+++ b/packages/core/src/repowise/core/generation/models.py
@@ -68,6 +68,40 @@ def _source_evidence_page_keys() -> set[str]:
}
+def _normalize_evidence_files(
+ raw_files: Mapping[str, Any], *, label: str
+) -> dict[str, tuple[str, ...]]:
+ """Validate a page-key -> paths mapping, framing errors with *label*.
+
+ Shared by ``from_repo_config`` (label ``generation_context.files``, the key
+ the user wrote) and ``__post_init__`` (label ``source_evidence_files``, the
+ internal field for direct construction). The two labels are the whole point
+ of the parameter: the same rules, reported against the surface the caller
+ touched.
+
+ Sharing one validator also unifies key normalization: both paths now
+ ``str(...).strip()`` a key before the membership check. ``from_repo_config``
+ always did; direct construction did not, so a padded key like
+ ``" repo_overview "`` is now trimmed and accepted where it used to raise.
+ """
+ valid_page_keys = _source_evidence_page_keys()
+ result: dict[str, tuple[str, ...]] = {}
+ for raw_page_key, raw_paths in raw_files.items():
+ page_key = str(raw_page_key).strip()
+ if page_key not in valid_page_keys:
+ raise ValueError(
+ f"{label} keys must name repo_overview or a "
+ "model-written onboarding slot; project_overview is configured "
+ "as repo_overview"
+ )
+ if not isinstance(raw_paths, (list, tuple)) or not all(
+ isinstance(path, str) and path.strip() for path in raw_paths
+ ):
+ raise ValueError(f"{label}.{page_key} must be a list of file paths")
+ result[page_key] = tuple(path.strip() for path in raw_paths)
+ return result
+
+
class _FrozenEvidenceFiles(Mapping[str, tuple[str, ...]]):
"""Small immutable mapping that preserves the frozen config contract.
@@ -322,24 +356,9 @@ class GenerationConfig:
raw_files = raw_evidence.get("files", {})
if not isinstance(raw_files, Mapping):
raise ValueError("generation_context.files must be a mapping")
- valid_page_keys = _source_evidence_page_keys()
- evidence_files: dict[str, tuple[str, ...]] = {}
- for raw_page_key, raw_paths in raw_files.items():
- page_key = str(raw_page_key).strip()
- if page_key not in valid_page_keys:
- raise ValueError(
- "generation_context.files keys must name repo_overview or a "
- "model-written onboarding slot; project_overview is configured "
- "as repo_overview"
- )
- if not isinstance(raw_paths, (list, tuple)) or not all(
- isinstance(path, str) and path.strip() for path in raw_paths
- ):
- raise ValueError(
- f"generation_context.files.{page_key} must be a list of file paths"
- )
- evidence_files[page_key] = tuple(path.strip() for path in raw_paths)
- values["source_evidence_files"] = evidence_files
+ values["source_evidence_files"] = _normalize_evidence_files(
+ raw_files, label="generation_context.files"
+ )
values.update(overrides)
return cls(**values)
@@ -361,20 +380,9 @@ class GenerationConfig:
raise ValueError("source_evidence_token_budget must be a non-negative integer")
if not isinstance(self.source_evidence_files, Mapping):
raise ValueError("source_evidence_files must be a mapping")
- valid_page_keys = _source_evidence_page_keys()
- evidence_files: dict[str, tuple[str, ...]] = {}
- for page_key, paths in self.source_evidence_files.items():
- if page_key not in valid_page_keys:
- raise ValueError(
- "source_evidence_files keys must name repo_overview or a "
- "model-written onboarding slot; project_overview is configured "
- "as repo_overview"
- )
- if not isinstance(paths, (list, tuple)) or not all(
- isinstance(path, str) and path.strip() for path in paths
- ):
- raise ValueError(f"source_evidence_files.{page_key} must be a list of file paths")
- evidence_files[page_key] = tuple(path.strip() for path in paths)
+ evidence_files = _normalize_evidence_files(
+ self.source_evidence_files, label="source_evidence_files"
+ )
object.__setattr__(
self,
"source_evidence_files",
diff --git a/tests/unit/generation/test_models.py b/tests/unit/generation/test_models.py
index 3247e8d94..5e4bd60f6 100644
--- a/tests/unit/generation/test_models.py
+++ b/tests/unit/generation/test_models.py
@@ -279,6 +279,24 @@ def test_direct_generation_config_rejects_an_unconsumed_evidence_key() -> None:
)
+def test_direct_generation_config_frames_evidence_errors_with_the_field_name() -> None:
+ # Direct construction reports against the internal field, not the config
+ # key from_repo_config uses -- the two framings are deliberate, so pin both.
+ with pytest.raises(ValueError, match=r"^source_evidence_files keys must name"):
+ GenerationConfig(source_evidence_files={"module_page": ("README.md",)})
+ with pytest.raises(ValueError, match=r"^source_evidence_files\.repo_overview must be a list"):
+ GenerationConfig(source_evidence_files={"repo_overview": "README.md"})
+
+
+def test_direct_generation_config_normalizes_evidence_keys_like_the_config_loader() -> None:
+ # Sharing one validator also aligns key normalization: direct construction
+ # now strips keys before the membership check, as from_repo_config always
+ # did. A padded key is accepted and stored trimmed, not rejected.
+ config = GenerationConfig(source_evidence_files={" repo_overview ": ("README.md",)})
+
+ assert config.source_evidence_files == {"repo_overview": ("README.md",)}
+
+
@pytest.mark.parametrize("value", [0, -1, True, 1.5, "not-a-number"])
def test_generation_config_rejects_invalid_repo_max_tokens(value):
with pytest.raises(ValueError, match="positive integer"):