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.

Fix lint, formatting, and integration tests

swati510cf1221006c71
diff --git a/packages/cli/src/repowise/cli/commands/doctor_cmd.py b/packages/cli/src/repowise/cli/commands/doctor_cmd.py
index 5a26f96c6..87fa57a33 100644
--- a/packages/cli/src/repowise/cli/commands/doctor_cmd.py
+++ b/packages/cli/src/repowise/cli/commands/doctor_cmd.py
@@ -152,7 +152,6 @@ def doctor_command(path: str | None, repair: bool) -> None:
list_pages,
)
from repowise.core.persistence.vector_store import (
- InMemoryVectorStore,
LanceDBVectorStore,
)
from repowise.core.providers.embedding.base import MockEmbedder
@@ -202,14 +201,18 @@ def doctor_command(path: str | None, repair: bool) -> None:
)
vec_ok = not missing_from_vector and not orphaned_vector
- vec_detail = "in sync" if vec_ok else (
- f"{len(missing_from_vector)} missing, {len(orphaned_vector)} orphaned"
+ vec_detail = (
+ "in sync"
+ if vec_ok
+ else (f"{len(missing_from_vector)} missing, {len(orphaned_vector)} orphaned")
)
checks.append(_check("SQL ↔ Vector Store", vec_ok, vec_detail))
fts_ok = not missing_from_fts and not orphaned_fts
- fts_detail = "in sync" if fts_ok else (
- f"{len(missing_from_fts)} missing, {len(orphaned_fts)} orphaned"
+ fts_detail = (
+ "in sync"
+ if fts_ok
+ else (f"{len(missing_from_fts)} missing, {len(orphaned_fts)} orphaned")
)
checks.append(_check("SQL ↔ FTS Index", fts_ok, fts_detail))
except Exception:
@@ -241,7 +244,6 @@ def doctor_command(path: str | None, repair: bool) -> None:
create_engine,
create_session_factory,
get_session,
- list_pages,
)
url = get_db_url_for_repo(repo_path)
@@ -256,9 +258,10 @@ def doctor_command(path: str | None, repair: bool) -> None:
if missing_from_fts:
# Fetch full page data for missing pages
async with get_session(sf) as session:
- from repowise.core.persistence.models import Page
from sqlalchemy import select
+ from repowise.core.persistence.models import Page
+
rows = await session.execute(
select(Page).where(Page.page_id.in_(list(missing_from_fts)))
)
@@ -276,28 +279,20 @@ def doctor_command(path: str | None, repair: bool) -> None:
from repowise.core.persistence.vector_store import LanceDBVectorStore
from repowise.core.providers.embedding.base import MockEmbedder
- import os
-
- # Resolve embedder — try real embedder, fall back to mock
- embedder_name = os.environ.get("REPOWISE_EMBEDDER", "mock").lower()
- if embedder_name == "mock":
- embedder = MockEmbedder()
- else:
- # Use mock for repair to avoid API costs; user can re-run
- # repowise reindex for real embeddings
- embedder = MockEmbedder()
+ # Use mock embedder for repair to avoid API costs;
+ # user can re-run `repowise reindex` for real embeddings
+ embedder = MockEmbedder()
vs = LanceDBVectorStore(str(lance_dir), embedder=embedder)
if missing_from_vector:
async with get_session(sf) as session:
- from repowise.core.persistence.models import Page
from sqlalchemy import select
+ from repowise.core.persistence.models import Page
+
rows = await session.execute(
- select(Page).where(
- Page.page_id.in_(list(missing_from_vector))
- )
+ select(Page).where(Page.page_id.in_(list(missing_from_vector)))
)
for page in rows.scalars().all():
await vs.embed_and_upsert(
diff --git a/packages/cli/src/repowise/cli/commands/update_cmd.py b/packages/cli/src/repowise/cli/commands/update_cmd.py
index 954897754..5835b42e9 100644
--- a/packages/cli/src/repowise/cli/commands/update_cmd.py
+++ b/packages/cli/src/repowise/cli/commands/update_cmd.py
@@ -24,7 +24,12 @@ from repowise.cli.helpers import (
@click.option("--provider", "provider_name", default=None, help="LLM provider name.")
@click.option("--model", default=None, help="Model identifier override.")
@click.option("--since", default=None, help="Base git ref to diff from (overrides state).")
[email protected]("--cascade-budget", type=int, default=None, help="Max pages to regenerate (auto-scaled if unset).")
+ "--cascade-budget",
+ type=int,
+ default=None,
+ help="Max pages to regenerate (auto-scaled if unset).",
+)
@click.option(
"--dry-run", is_flag=True, default=False, help="Show affected pages without regenerating."
)
diff --git a/packages/core/src/repowise/core/generation/page_generator.py b/packages/core/src/repowise/core/generation/page_generator.py
index 5f8a0ca0e..5438b46fb 100644
--- a/packages/core/src/repowise/core/generation/page_generator.py
+++ b/packages/core/src/repowise/core/generation/page_generator.py
@@ -959,14 +959,64 @@ def _is_significant_file(
# Common words that appear in backticks but are not code symbols.
_BACKTICK_SKIP = frozenset(
{
- "True", "False", "None", "null", "undefined", "self", "cls", "this",
- "str", "int", "float", "bool", "list", "dict", "set", "tuple",
- "bytes", "object", "type", "Any", "Optional", "Union",
- "async", "await", "return", "yield", "import", "from",
- "class", "def", "if", "else", "for", "while", "try", "except",
- "raise", "with", "pass", "break", "continue", "lambda",
- "in", "not", "and", "or", "is", "del", "assert", "finally",
- "elif", "as", "pip", "npm", "go", "rust", "python", "node",
+ "True",
+ "False",
+ "None",
+ "null",
+ "undefined",
+ "self",
+ "cls",
+ "this",
+ "str",
+ "int",
+ "float",
+ "bool",
+ "list",
+ "dict",
+ "set",
+ "tuple",
+ "bytes",
+ "object",
+ "type",
+ "Any",
+ "Optional",
+ "Union",
+ "async",
+ "await",
+ "return",
+ "yield",
+ "import",
+ "from",
+ "class",
+ "def",
+ "if",
+ "else",
+ "for",
+ "while",
+ "try",
+ "except",
+ "raise",
+ "with",
+ "pass",
+ "break",
+ "continue",
+ "lambda",
+ "in",
+ "not",
+ "and",
+ "or",
+ "is",
+ "del",
+ "assert",
+ "finally",
+ "elif",
+ "as",
+ "pip",
+ "npm",
+ "go",
+ "rust",
+ "python",
+ "node",
}
)
diff --git a/packages/core/src/repowise/core/generation/report.py b/packages/core/src/repowise/core/generation/report.py
index bac973d56..1bda65051 100644
--- a/packages/core/src/repowise/core/generation/report.py
+++ b/packages/core/src/repowise/core/generation/report.py
@@ -36,9 +36,7 @@ class GenerationReport:
elapsed: float = 0.0,
) -> GenerationReport:
by_type = dict(Counter(p.page_type for p in pages))
- hal_count = sum(
- 1 for p in pages if p.metadata.get("hallucination_warnings")
- )
+ hal_count = sum(1 for p in pages if p.metadata.get("hallucination_warnings"))
return cls(
pages_by_type=by_type,
total_input_tokens=sum(p.input_tokens for p in pages),
@@ -62,8 +60,7 @@ class GenerationReport:
) -> float:
"""Estimated USD cost. Rates are per 1M tokens (Sonnet 4 defaults)."""
return (
- self.total_input_tokens * input_rate
- + self.total_output_tokens * output_rate
+ self.total_input_tokens * input_rate + self.total_output_tokens * output_rate
) / 1_000_000
diff --git a/packages/core/src/repowise/core/ingestion/graph.py b/packages/core/src/repowise/core/ingestion/graph.py
index 19a50f9c7..c6c8b4bc6 100644
--- a/packages/core/src/repowise/core/ingestion/graph.py
+++ b/packages/core/src/repowise/core/ingestion/graph.py
@@ -431,8 +431,6 @@ class GraphBuilder:
def _add_conftest_edges(self, path_set: set[str]) -> int:
"""conftest.py → test files in the same or child directories."""
- import re as _re
-
count = 0
conftest_paths = [p for p in path_set if Path(p).name == "conftest.py"]
@@ -446,15 +444,14 @@ class GraphBuilder:
if not node.get("is_test", False):
continue
# Test file must be in the same or a child directory
- if p.startswith(prefix) or (prefix == "" and "/" not in p):
- if self._add_edge_if_new(p, conf):
- count += 1
+ if (
+ p.startswith(prefix) or (prefix == "" and "/" not in p)
+ ) and self._add_edge_if_new(p, conf):
+ count += 1
return count
def _add_django_edges(self, path_set: set[str]) -> int:
"""Django conventions: admin→models, urls→views in the same directory."""
- import re as _re
-
count = 0
by_dir: dict[str, dict[str, str]] = {} # dir → {stem: path}
for p in path_set:
@@ -462,47 +459,60 @@ class GraphBuilder:
d = pp.parent.as_posix()
by_dir.setdefault(d, {})[pp.stem] = p
- for d, stems in by_dir.items():
+ for _d, stems in by_dir.items():
# admin.py → models.py
- if "admin" in stems and "models" in stems:
- if self._add_edge_if_new(stems["admin"], stems["models"]):
- count += 1
+ if (
+ "admin" in stems
+ and "models" in stems
+ and self._add_edge_if_new(stems["admin"], stems["models"])
+ ):
+ count += 1
# urls.py → views.py
- if "urls" in stems and "views" in stems:
- if self._add_edge_if_new(stems["urls"], stems["views"]):
- count += 1
+ if (
+ "urls" in stems
+ and "views" in stems
+ and self._add_edge_if_new(stems["urls"], stems["views"])
+ ):
+ count += 1
# forms.py → models.py
- if "forms" in stems and "models" in stems:
- if self._add_edge_if_new(stems["forms"], stems["models"]):
- count += 1
+ if (
+ "forms" in stems
+ and "models" in stems
+ and self._add_edge_if_new(stems["forms"], stems["models"])
+ ):
+ count += 1
# serializers.py → models.py
- if "serializers" in stems and "models" in stems:
- if self._add_edge_if_new(stems["serializers"], stems["models"]):
- count += 1
+ if (
+ "serializers" in stems
+ and "models" in stems
+ and self._add_edge_if_new(stems["serializers"], stems["models"])
+ ):
+ count += 1
return count
def _add_fastapi_edges(self, path_set: set[str]) -> int:
"""Detect include_router() calls and link app files to router modules."""
- import re as _re
+ import re
count = 0
# Build a map from imported variable names to source file paths
- # by scanning imports across all parsed files
var_to_file: dict[str, str] = {}
+ stem_map = {Path(p).stem.lower(): p for p in path_set}
for path, parsed in self._parsed_files.items():
for imp in parsed.imports:
for name in imp.imported_names:
if name.lower().endswith("router") or name.lower().endswith("app"):
resolved = self._resolve_import(
- imp.module_path, path, path_set,
- {Path(p).stem.lower(): p for p in path_set},
+ imp.module_path,
+ path,
+ path_set,
+ stem_map,
parsed.file_info.language,
)
if resolved and resolved in path_set:
var_to_file[name] = resolved
- # Scan source for include_router / add_api_route patterns
- router_re = _re.compile(r"(?:include_router|add_api_route)\s*\(\s*(\w+)")
+ router_re = re.compile(r"(?:include_router|add_api_route)\s*\(\s*(\w+)")
for path, parsed in self._parsed_files.items():
if parsed.file_info.language != "python":
continue
@@ -513,30 +523,32 @@ class GraphBuilder:
for match in router_re.finditer(source):
var_name = match.group(1)
target = var_to_file.get(var_name)
- if target and target in path_set:
- if self._add_edge_if_new(path, target):
- count += 1
+ if target and target in path_set and self._add_edge_if_new(path, target):
+ count += 1
return count
def _add_flask_edges(self, path_set: set[str]) -> int:
"""Detect register_blueprint() calls and link app files to blueprint modules."""
- import re as _re
+ import re
count = 0
var_to_file: dict[str, str] = {}
+ stem_map = {Path(p).stem.lower(): p for p in path_set}
for path, parsed in self._parsed_files.items():
for imp in parsed.imports:
for name in imp.imported_names:
if "blueprint" in name.lower() or name.lower().endswith("bp"):
resolved = self._resolve_import(
- imp.module_path, path, path_set,
- {Path(p).stem.lower(): p for p in path_set},
+ imp.module_path,
+ path,
+ path_set,
+ stem_map,
parsed.file_info.language,
)
if resolved and resolved in path_set:
var_to_file[name] = resolved
- bp_re = _re.compile(r"register_blueprint\s*\(\s*(\w+)")
+ bp_re = re.compile(r"register_blueprint\s*\(\s*(\w+)")
for path, parsed in self._parsed_files.items():
if parsed.file_info.language != "python":
continue
@@ -547,9 +559,8 @@ class GraphBuilder:
for match in bp_re.finditer(source):
var_name = match.group(1)
target = var_to_file.get(var_name)
- if target and target in path_set:
- if self._add_edge_if_new(path, target):
- count += 1
+ if target and target in path_set and self._add_edge_if_new(path, target):
+ count += 1
return count
def pagerank(self, alpha: float = 0.85) -> dict[str, float]:
diff --git a/tests/integration/test_cli.py b/tests/integration/test_cli.py
index a4963a5fd..8c47da76d 100644
--- a/tests/integration/test_cli.py
+++ b/tests/integration/test_cli.py
@@ -52,7 +52,7 @@ class TestInitFullMock:
assert result.exit_code == 0, result.output
assert (work_repo / ".repowise" / "wiki.db").exists()
assert (work_repo / ".repowise" / "state.json").exists()
- assert "Done!" in result.output
+ assert "init complete" in result.output
class TestInitIdempotent:
diff --git a/tests/integration/test_mcp.py b/tests/integration/test_mcp.py
index 018ef9910..e85d31224 100644
--- a/tests/integration/test_mcp.py
+++ b/tests/integration/test_mcp.py
@@ -423,7 +423,7 @@ async def test_mcp_dead_code_and_freshness_flow(mcp_env):
# Dead code
dead = await get_dead_code()
assert dead["summary"]["total_findings"] == 1
- assert dead["findings"][0]["symbol_name"] == "deprecated_verify"
+ assert dead["tiers"]["high"]["findings"][0]["symbol_name"] == "deprecated_verify"
# Freshness via get_context (all pages have confidence 0.9)
ctx = await get_context(["src/auth/login.py"], include=["freshness"])
diff --git a/tests/integration/test_provider_live.py b/tests/integration/test_provider_live.py
index 9ccbe1600..2be4fb0f2 100644
--- a/tests/integration/test_provider_live.py
+++ b/tests/integration/test_provider_live.py
@@ -50,8 +50,17 @@ async def test_openai_live(model):
GEMINI_KEY = os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY", "")
+_has_google_genai = True
+try:
+ import google.genai # noqa: F401
+except ImportError:
+ _has_google_genai = False
[email protected](not GEMINI_KEY, reason="GEMINI_API_KEY not set")
+
+ not GEMINI_KEY or not _has_google_genai,
+ reason="GEMINI_API_KEY not set or google-genai not installed",
+)
@pytest.mark.parametrize(
"model",
[