CodeScope Codebase Graph Analysis

pip install codegraph-ai

# Create Python virtural environment
python -m venv .venv

source .venv/bin/activate

# Point to a pre-built database (skip indexing)
export CODESCOPE_DB_DIR="/path/to/.linux_db"

# Offline mode for HuggingFace models
export HF_HUB_OFFLINE="1"

# Fallback when HuggingFace is unreachable (e.g., network issues in China)
# Use HF mirror or ModelScope for sentence-transformers models:
export HF_ENDPOINT="https://hf-mirror.com"
# https://www.modelscope.cn/models/sentence-transformers/all-MiniLM-L6-v2

codegraph status --db $CODESCOPE_DB_DIR

codegraph init --repo . --lang auto --commits 500

codegraph ingest --repo . --db $CODESCOPE_DB_DIR --commits 500
codegraph ingest --repo . --db $CODESCOPE_DB_DIR --backfill-limit 200   # add MODIFIES edges only

codegraph status --db $CODESCOPE_DB_DIR
codegraph analyze --db $CODESCOPE_DB_DIR --output report.md

import os
os.environ['HF_HUB_OFFLINE'] = '1'  # required

from codegraph.core import CodeScope
cs = CodeScope(os.environ['CODESCOPE_DB_DIR'])

# Cypher query
rows = list(cs.conn.execute('''
    MATCH (caller:Function)-[:CALLS]->(f:Function {name: "free_irq"})
    RETURN caller.name, caller.file_path LIMIT 10
'''))
for r in rows:
    print(r)

cs.close()  # always close when done

# Get all composition relationships (A strongly owns B)
list(cs.conn.execute('MATCH (c1:Class)-[:COMPOSES]->(c2:Class) RETURN c1.name, c2.name'))

# Get all aggregation relationships (A optionally holds B)
list(cs.conn.execute('MATCH (c1:Class)-[:AGGREGATES]->(c2:Class) RETURN c1.name, c2.name'))

# How many objects does a class directly own?
list(cs.conn.execute(
    'MATCH (c:Class {name: "Llama"})-[:COMPOSES]->(t:Class) RETURN t.name'
))

# Full dependency graph for a class (composition + aggregation + inheritance)
list(cs.conn.execute(
    'MATCH (c:Class {name: "GPUModelRunner"})-[r:COMPOSES|AGGREGATES]->(t:Class) '
    'RETURN type(r), t.name'
))

inherits  = list(cs.conn.execute('MATCH (c1:Class)-[:INHERITS]->(c2:Class) RETURN c1.name, c2.name'))
composes  = list(cs.conn.execute('MATCH (c1:Class)-[:COMPOSES]->(c2:Class) RETURN c1.name, c2.name'))
aggregates = list(cs.conn.execute('MATCH (c1:Class)-[:AGGREGATES]->(c2:Class) RETURN c1.name, c2.name'))

print('classDiagram')
for src, tgt in inherits:   print(f'    {tgt} <|-- {src}')   # parent <|-- child
for src, tgt in composes:   print(f'    {src} *-- {tgt}')    # owner *-- owned
for src, tgt in aggregates: print(f'    {src} o-- {tgt}')    # holder o-- optional

from codegraph.analyzer import generate_report
report = generate_report(cs)  # full architecture analysis as markdown

codegraph analyze --output reports/analysis.md

codegraph init --repo /path/to/java-project --lang java --commits 500

codegraph init --repo /path/to/java-project --lang auto

# Find all classes that extend a specific class
list(cs.conn.execute("""
    MATCH (c:Class)-[:INHERITS]->(p:Class {name: 'FileSystem'})
    RETURN c.name, c.file_path
"""))

# Find all methods in a specific class
list(cs.conn.execute("""
    MATCH (c:Class {name: 'DefaultParser'})-[:HAS_METHOD]->(f:Function)
    RETURN f.name, f.signature
"""))

# Find constructor call chains
list(cs.conn.execute("""
    MATCH (f:Function)-[:CALLS]->(init:Function {name: '<init>'})
    WHERE init.class_name = 'Configuration'
    RETURN f.name, f.file_path LIMIT 10
"""))

# Analyze a specific GitHub issue against the indexed code graph
result = cs.analyze_issue("owner", "repo", 1234, topk=10)
print(result.format_report())

# Analyze top-k bug issues and get aggregated hotspot data
results = cs.analyze_top_bugs("owner", "repo", k=10, label="bug")
for r in results:
    print(f"#{r.issue.number}: {r.issue.title}")
    for c in r.candidates[:3]:
        print(f"  {c.function_name} ({c.file_path}) score={c.score:.2f}")

# Fetch and parse a single issue (no graph needed)
codegraph fetch-issue owner repo 1234

# Fetch top-k bugs from a repo
codegraph fetch-bugs owner repo --top 10 --label bug

# Analyze a single bug against the code graph
codegraph analyze-bug owner repo 1234 --db .codegraph --topk 10

# Batch analyze top bugs
codegraph analyze-bugs owner repo --db .codegraph --top 10 --label bug

from codegraph.issue_fetcher import fetch_and_parse_issue
from codegraph.bug_locator import (
    resolve_paths_to_files,
    find_semantic_matches,
    trace_callers,
    rank_root_causes,
    analyze_bug,
)

# Fetch and parse (with caching)
issue = fetch_and_parse_issue("owner", "repo", 1234)
print(issue.extracted_paths)   # file paths found in body
print(issue.extracted_funcs)   # function names from stack traces
print(issue.linked_commits)    # merge commit SHAs from linked PRs

# Match paths to graph nodes
path_matches = resolve_paths_to_files(cs, issue.extracted_paths)

# Semantic search using issue description
semantic_matches = find_semantic_matches(cs, f"{issue.title}\n{issue.body}")

# Trace callers of mentioned functions
caller_traces = trace_callers(cs, issue.extracted_funcs, max_hops=2)

# Combine into ranked candidates
candidates = rank_root_causes(path_matches, semantic_matches, caller_traces, issue.extracted_funcs)

from codegraph.issue_cache import clear_cache
clear_cache(owner="openclaw", repo="openclaw")  # clear specific repo
clear_cache()  # clear all

# Phase 1: Analyze PRs, detect conflicts, write to graph DB (full rebuild)
# Pipeline: cross-PR analysis → single-PR risk scoring → report + labels
codegraph pr-review prepare --db .codegraph

# Filter by author during prepare:
codegraph pr-review prepare --db .codegraph --author someone

# Override auto-detected GitHub repo (owner/repo):
codegraph pr-review prepare --db .codegraph --repo owner/repo

# Skip per-PR risk scoring (conflict-only, faster):
codegraph pr-review prepare --db .codegraph --skip-single-pr

# Phase 2: Apply labels and post conflict comments from graph DB
codegraph pr-review label --db .codegraph

# Label with dry-run (preview without API calls):
codegraph pr-review label --db .codegraph --dry-run

from codegraph.pr_api import PRReview

# Full pipeline in 2 lines
with PRReview(db=".codegraph") as pr:
    pr.prepare()                # fetch PRs → graph DB → scoring → report
    pr.label(dry_run=True)      # preview labels without API calls

# Query after prepare (works across sessions once DB has data)
with PRReview(db=".codegraph") as pr:
    # Conflicts
    pr.conflict_prs_of("100")           # → ["101", "102"]

    # Risk
    pr.risk("100")                      # → {"number": "100", "risk_level": "HIGH", ...}

    # Classification
    pr.auto_merge_candidates()          # → [{"number": "200", ...}, ...]
    pr.conflicting_groups()             # → [["100", "101"], ["103"]]

    # All PRs in DB
    pr.all_prs()                        # → [{"number": "100", ...}, ...]

    # Functions changed by a specific PR (added / modified / deleted)
    import json
    cs = pr._open_cs()
    rows = list(cs.conn.execute(
        f"MATCH (pr:PR {{id: {json.dumps('439')}}})-[c:CHANGES]->(f:Function) "
        f"RETURN c.info AS change_type, f.name, f.file_path "
        f"ORDER BY c.info, f.name"
    ))
    for change_type, name, path in rows:
        print(f"  [{change_type}] {name} ({path})")
    # change_type: 'hunk' (modified), 'new' (added), 'deleted', 'related' (newly calls)

from codegraph.pr_analysis import GitHubClient, GraphAnalyzer, PRScorer, CrossPRAnalyzer
gh = GitHubClient(repo='owner/repo')
scorer = PRScorer(GraphAnalyzer(cs, repo_dir), repo_dir, gh)
result = scorer.analyze(gh.pr_to_entry(pr), output_dir='/tmp')  # risk_score, risk_level, peak_blast...

cross = CrossPRAnalyzer(cs, repo_dir, gh)
cross.prepare(pr_ids)  # index PR nodes into graph
cross.connected_components()  # {root: [pr_ids]} — detects conflicts
cross.update_pr_labels(assignments)  # persist labels to graph DB

# Load PR results from graph DB (no GitHub API needed)
all_results, components = cross.load_from_graph()

# Build and apply labels from analysis results
from codegraph.pr_labeler import build_label_assignments, apply_labels
assignments = build_label_assignments(all_results, components)
apply_labels(assignments, repo='owner/repo', create_labels=True)