Skip to content

Commit 43c16a5

Browse files
GoodbyePlanetclaude
andcommitted
chore: Fix ruff formatting and lint errors
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1 parent 77740da commit 43c16a5

31 files changed

Lines changed: 1010 additions & 596 deletions

.github/workflows/ci.yml

Lines changed: 3 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -2,22 +2,19 @@ name: CI
22

33
on:
44
push:
5-
branches: [main]
5+
branches: [ main ]
66
pull_request:
7-
branches: [main]
7+
branches: [ main ]
88

99
jobs:
1010
lint:
1111
name: Lint
1212
runs-on: ubuntu-latest
1313
steps:
1414
- uses: actions/checkout@v4
15-
1615
- uses: astral-sh/setup-uv@v5
17-
1816
- name: Check formatting
1917
run: uvx ruff format --check .
20-
2118
- name: Lint
2219
run: uvx ruff check .
2320

@@ -26,13 +23,10 @@ jobs:
2623
runs-on: ubuntu-latest
2724
steps:
2825
- uses: actions/checkout@v4
29-
3026
- uses: astral-sh/setup-uv@v5
3127
with:
3228
enable-cache: true
33-
3429
- name: Install dependencies
3530
run: uv sync --frozen --all-groups
36-
3731
- name: Run tests
38-
run: uv run pytest --tb=short -q
32+
run: uv run pytest --tb=short -q

server/config.py

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -18,8 +18,8 @@ def __init__(
1818
) -> None:
1919
self.name = name
2020
self.github_repo = github_repo # e.g. "myorg/catalog-service"
21-
self.github_ref = github_ref # branch, tag, or commit SHA
22-
self.root = root # optional path prefix within the repo
21+
self.github_ref = github_ref # branch, tag, or commit SHA
22+
self.root = root # optional path prefix within the repo
2323
self.exclude = exclude
2424

2525

@@ -34,7 +34,9 @@ class Settings(BaseSettings):
3434

3535
qdrant_url: str = Field(default="http://localhost:6333", alias="QDRANT_URL")
3636
qdrant_collection: str = Field(default="code_symbols", alias="QDRANT_COLLECTION")
37-
qdrant_commits_collection: str = Field(default="git_commits", alias="QDRANT_COMMITS_COLLECTION")
37+
qdrant_commits_collection: str = Field(
38+
default="git_commits", alias="QDRANT_COMMITS_COLLECTION"
39+
)
3840
git_history_max_commits: int = Field(default=500, alias="GIT_HISTORY_MAX_COMMITS")
3941

4042
mcp_transport: Literal["streamable-http", "sse", "stdio"] = Field(

server/embeddings/bm25.py

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,9 @@ async def embed_query(self, text: str) -> SparseVector:
3131
[embedding] = await loop.run_in_executor(
3232
None, lambda: list(self._model.query_embed(prepared))
3333
)
34-
return SparseVector(indices=embedding.indices.tolist(), values=embedding.values.tolist())
34+
return SparseVector(
35+
indices=embedding.indices.tolist(), values=embedding.values.tolist()
36+
)
3537

3638

3739
def get_sparse_embedding_provider() -> BM25SparseProvider:

server/embeddings/code_tokenizer.py

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -9,8 +9,8 @@ def split_code_identifiers(text: str) -> str:
99
Both the original tokens and their subword splits are returned so BM25
1010
matches exact identifiers (PlaceOrderRequest) AND partial queries (place order).
1111
"""
12-
expanded = re.sub(r'([a-z0-9])([A-Z])', r'\1 \2', text)
13-
expanded = re.sub(r'([A-Z]+)([A-Z][a-z])', r'\1 \2', expanded)
14-
expanded = expanded.replace('_', ' ')
15-
expanded = expanded.replace('-', ' ')
12+
expanded = re.sub(r"([a-z0-9])([A-Z])", r"\1 \2", text)
13+
expanded = re.sub(r"([A-Z]+)([A-Z][a-z])", r"\1 \2", expanded)
14+
expanded = expanded.replace("_", " ")
15+
expanded = expanded.replace("-", " ")
1616
return text + "\n" + expanded

server/indexer/git_history.py

Lines changed: 73 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,11 @@
1010
from server.config import settings
1111
from server.embeddings.base import EmbeddingProvider
1212
from server.embeddings.jina import get_embedding_provider
13-
from server.indexer.github_source import GitHubCommit, fetch_commits_with_diffs, list_commits
13+
from server.indexer.github_source import (
14+
GitHubCommit,
15+
fetch_commits_with_diffs,
16+
list_commits,
17+
)
1418
from server.indexer.pipeline import ProgressEvent
1519
from server.store.commit_store import CommitStore
1620

@@ -78,25 +82,34 @@ async def index_service(
7882

7983
async with httpx.AsyncClient() as http_client:
8084
commits = await list_commits(
81-
settings.github_token, svc.github_repo, svc.github_ref,
82-
root=svc.root, max_commits=settings.git_history_max_commits,
85+
settings.github_token,
86+
svc.github_repo,
87+
svc.github_ref,
88+
root=svc.root,
89+
max_commits=settings.git_history_max_commits,
8390
client=http_client,
8491
)
8592

8693
if progress_callback:
87-
await progress_callback(ProgressEvent(
88-
phase="discovery",
89-
current=len(commits),
90-
total=len(commits),
91-
percentage=100.0,
92-
service=service_name,
93-
))
94+
await progress_callback(
95+
ProgressEvent(
96+
phase="discovery",
97+
current=len(commits),
98+
total=len(commits),
99+
percentage=100.0,
100+
service=service_name,
101+
)
102+
)
94103

95104
existing_shas = set() if force else await self._store.get_indexed_shas(svc.name)
96105
new_commits = [c for c in commits if c.sha not in existing_shas]
97106
skipped = len(commits) - len(new_commits)
98107

99-
shas_without_diffs = set(await self._store.get_commits_without_diffs(svc.name)) if not force else set()
108+
shas_without_diffs = (
109+
set(await self._store.get_commits_without_diffs(svc.name))
110+
if not force
111+
else set()
112+
)
100113
commits_needing_diffs = [c for c in commits if c.sha in shas_without_diffs]
101114

102115
if not new_commits and not commits_needing_diffs:
@@ -105,41 +118,55 @@ async def index_service(
105118
diff_updated = 0
106119

107120
if new_commits:
108-
logger.info("Fetching diffs for %d new commits in %s", len(new_commits), service_name)
121+
logger.info(
122+
"Fetching diffs for %d new commits in %s",
123+
len(new_commits),
124+
service_name,
125+
)
109126
new_commits = await fetch_commits_with_diffs(
110127
settings.github_token, svc.github_repo, new_commits
111128
)
112129
texts = [_build_embedding_text(c, svc.name) for c in new_commits]
113130
try:
114131
vectors = await self._embedder.embed_batch(texts)
115132
except Exception as exc:
116-
logger.error("Embedding failed for %s git history: %s", service_name, exc)
133+
logger.error(
134+
"Embedding failed for %s git history: %s", service_name, exc
135+
)
117136
return {"error": 1, "new": 0, "skipped": skipped, "diff_updated": 0}
118137

119138
if progress_callback:
120-
await progress_callback(ProgressEvent(
121-
phase="embedding",
122-
current=len(new_commits),
123-
total=len(new_commits),
124-
percentage=100.0,
125-
service=service_name,
126-
))
139+
await progress_callback(
140+
ProgressEvent(
141+
phase="embedding",
142+
current=len(new_commits),
143+
total=len(new_commits),
144+
percentage=100.0,
145+
service=service_name,
146+
)
147+
)
127148

128149
payloads = [_commit_to_payload(c, svc.name) for c in new_commits]
129150
await self._store.upsert_commits(svc.name, payloads, vectors)
130151
logger.info("Indexed %d new commits for %s", len(new_commits), service_name)
131152

132153
if progress_callback:
133-
await progress_callback(ProgressEvent(
134-
phase="upserting",
135-
current=len(new_commits),
136-
total=len(new_commits),
137-
percentage=100.0,
138-
service=service_name,
139-
))
154+
await progress_callback(
155+
ProgressEvent(
156+
phase="upserting",
157+
current=len(new_commits),
158+
total=len(new_commits),
159+
percentage=100.0,
160+
service=service_name,
161+
)
162+
)
140163

141164
if commits_needing_diffs:
142-
logger.info("Fetching diffs for %d existing commits in %s", len(commits_needing_diffs), service_name)
165+
logger.info(
166+
"Fetching diffs for %d existing commits in %s",
167+
len(commits_needing_diffs),
168+
service_name,
169+
)
143170
commits_needing_diffs = await fetch_commits_with_diffs(
144171
settings.github_token, svc.github_repo, commits_needing_diffs
145172
)
@@ -148,15 +175,21 @@ async def index_service(
148175
diff_updated = len(commits_needing_diffs)
149176

150177
if progress_callback:
151-
await progress_callback(ProgressEvent(
152-
phase="upserting",
153-
current=diff_updated,
154-
total=diff_updated,
155-
percentage=100.0,
156-
service=service_name,
157-
))
158-
159-
return {"new": len(new_commits), "skipped": skipped, "diff_updated": diff_updated}
178+
await progress_callback(
179+
ProgressEvent(
180+
phase="upserting",
181+
current=diff_updated,
182+
total=diff_updated,
183+
percentage=100.0,
184+
service=service_name,
185+
)
186+
)
187+
188+
return {
189+
"new": len(new_commits),
190+
"skipped": skipped,
191+
"diff_updated": diff_updated,
192+
}
160193

161194
async def index_all(
162195
self,
@@ -167,5 +200,7 @@ async def index_all(
167200
results: dict[str, Any] = {}
168201
for svc in services:
169202
logger.info("Indexing git history for: %s", svc.name)
170-
results[svc.name] = await self.index_service(svc.name, force=force, progress_callback=progress_callback)
203+
results[svc.name] = await self.index_service(
204+
svc.name, force=force, progress_callback=progress_callback
205+
)
171206
return results

0 commit comments

Comments
 (0)