Neo4j Knowledge Graph

MERGE (r:Repository {full_name: $full_name})
SET r.scanned_at = $now

UNWIND $files AS f
MERGE (file:File {repo: $repo, path: f.path})
SET file.language = f.language, file.size = f.size
WITH file
MERGE (r:Repository {full_name: $repo})
MERGE (r)-[:CONTAINS]->(file)

MERGE (pr:PullRequest {repo: $repo, number: $number})
SET pr.title = $title,
    pr.author = $author,
    pr.verdict = $verdict,
    pr.reviewed_at = $now

MERGE (d:Developer {login: $login})
WITH d
MATCH (pr:PullRequest {repo: $repo, number: $number})
MERGE (pr)-[:AUTHORED_BY]->(d)
WITH d
MERGE (r:Repository {full_name: $repo})
MERGE (d)-[:CONTRIBUTED_TO]->(r)

UNWIND $issue_nums AS issue_num
MERGE (i:Issue {repo: $repo, number: issue_num})
WITH i
MATCH (pr:PullRequest {repo: $repo, number: $pr_num})
MERGE (pr)-[:CLOSES]->(i)

MATCH (r:Repository {full_name: "alice/backend"})-[:CONTAINS]->(f:File)
WHERE f.language = "Python"
RETURN f.path, f.size
ORDER BY f.size DESC
LIMIT 10

MATCH (pr:PullRequest {repo: "alice/backend", number: 42})-[:TOUCHES]->(f:File)
RETURN f.path, f.language

MATCH (pr:PullRequest {repo: "alice/backend"})-[:AUTHORED_BY]->(d:Developer)
RETURN d.login, count(pr) AS pr_count
ORDER BY pr_count DESC
LIMIT 5

MATCH (d:Developer {login: "alice"})-[:CONTRIBUTED_TO]->(r:Repository)
RETURN r.full_name

MATCH (pr:PullRequest {repo: "alice/backend"})-[:CLOSES]->(i:Issue)
RETURN pr.number, pr.title, collect(i.number) AS closed_issues
ORDER BY pr.number DESC
LIMIT 10

-- Repository: unique by full_name
CREATE CONSTRAINT repo_full_name IF NOT EXISTS
FOR (r:Repository) REQUIRE r.full_name IS UNIQUE;

-- Developer: unique by login
CREATE CONSTRAINT dev_login IF NOT EXISTS
FOR (d:Developer) REQUIRE d.login IS UNIQUE;

-- PullRequest: unique by (repo, number)
CREATE CONSTRAINT pr_repo_number IF NOT EXISTS
FOR (pr:PullRequest) REQUIRE (pr.repo, pr.number) IS UNIQUE;

-- Issue: unique by (repo, number)
CREATE CONSTRAINT issue_repo_number IF NOT EXISTS
FOR (i:Issue) REQUIRE (i.repo, i.number) IS UNIQUE;

-- File: unique by (repo, path)
CREATE CONSTRAINT file_repo_path IF NOT EXISTS
FOR (f:File) REQUIRE (f.repo, f.path) IS UNIQUE;

-- Index on File.language for faster filtering
CREATE INDEX file_language IF NOT EXISTS
FOR (f:File) ON (f.language);

-- Index on PullRequest.verdict for analytics
CREATE INDEX pr_verdict IF NOT EXISTS
FOR (pr:PullRequest) ON (pr.verdict);

from app.services import graph_builder

experts = await graph_builder.get_file_experts(
    repo_full_name="alice/backend",
    file_paths=["app/auth/jwt_utils.py", "app/auth/dependencies.py"],
    top_k=5,
)
# [{"login": "alice", "touch_count": 12}, {"login": "bob", "touch_count": 8}, ...]

related = await graph_builder.get_related_prs(
    repo_full_name="alice/backend",
    file_paths=["app/auth/jwt_utils.py", "app/auth/dependencies.py"],
    exclude_pr=42,  # Don't include current PR
    top_k=5,
)
# [{"number": 38, "title": "Add JWT refresh", "author": "bob", "verdict": "APPROVE", "overlap": 2}, ...]

hotspots = await graph_builder.get_file_hotspots(
    repo_full_name="alice/backend",
    limit=10,
)
# [{"path": "app/main.py", "language": "Python", "pr_count": 45}, ...]

risky = await graph_builder.get_high_risk_files(
    repo_full_name="alice/backend",
    limit=8,
)
# [{"path": "app/auth/jwt_utils.py", "language": "Python", "risk_count": 7}, ...]

ownership = await graph_builder.get_code_ownership(
    repo_full_name="alice/backend",
    limit=10,
)
# [{"path": "app/main.py", "owner": "alice", "owner_touches": 28, "total_touches": 45}, ...]