code-review-graph 2.2.0__tar.gz → 2.2.2__tar.gz

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/.gitignore

@@ -32,11 +32,16 @@ env/
 .DS_Store
 Thumbs.db
 
-# Node (if any JS tooling)
+# Node
 node_modules/
 
+# VS Code extension build artifacts
+code-review-graph-vscode/dist/
+*.vsix
+
 # Claude Code
 .claude/
+.claude-plugin/
 
 # Coverage
 htmlcov/
@@ -49,26 +54,24 @@ htmlcov/
 # mypy
 .mypy_cache/
 
-# Medium article
-medium/
-
-# Superpowers brainstorm
-.superpowers/
-docs/superpowers/plans/
-docs/superpowers/specs/
-
-# Diagrams (PNGs + script tracked, excalidraw sources gitignored)
-diagrams/*.excalidraw
-diagrams/export_pngs.mjs
+# Excalidraw source files (PNGs are tracked, sources are not)
 *.excalidraw
+diagrams/export_pngs.mjs
 
-# Evaluation test repos (third-party checkouts)
+# Evaluation (generated output — test repos, results, reports)
 evaluate/test_repos/
+evaluate/results/
+evaluate/reports/
 
-# Draft/duplicate files
+# Superpowers brainstorm docs
+.superpowers/
+docs/superpowers/
+
+# Draft/duplicate assets
 docs/assets/marketing-diagram*
 
-# One-off audit/design docs
+# One-off docs (audits, analyses, plans, articles)
+medium/
 Quality-Audit-Report.docx
 accessibility-audit.md
 cross-audit-synthesis.md
@@ -76,3 +79,5 @@ design-critique.md
 design-handoff.md
 design-system-audit.md
 research-synthesis.md
+code-review-graph-analysis.md
+SCALING_AND_TOKEN_EFFICIENCY_PLAN.md

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-review-graph
-Version: 2.2.0
+Version: 2.2.2
 Summary: Persistent incremental knowledge graph for token-efficient, context-aware code reviews with Claude Code
 Project-URL: Homepage, https://code-review-graph.com
 Project-URL: Repository, https://github.com/tirth8205/code-review-graph

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/cli.py

@@ -429,9 +429,7 @@ def main() -> None:
     from .incremental import (
         find_project_root,
         find_repo_root,
-        full_build,
         get_db_path,
-        incremental_update,
         watch,
     )
 

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/graph.py

@@ -8,6 +8,7 @@ Supports impact-radius queries and subgraph extraction.
 from __future__ import annotations
 
 import json
+import logging
 import sqlite3
 import threading
 import time
@@ -15,15 +16,13 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Optional
 
-import logging
-
 import networkx as nx
 
 from .constants import BFS_ENGINE, MAX_IMPACT_DEPTH, MAX_IMPACT_NODES
 from .migrations import get_schema_version, run_migrations
+from .parser import EdgeInfo, NodeInfo
 
 logger = logging.getLogger(__name__)
-from .parser import EdgeInfo, NodeInfo
 
 # ---------------------------------------------------------------------------
 # Schema

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/parser.py

@@ -242,6 +242,8 @@ _TEST_FILE_PATTERNS = [
     re.compile(r".*_test\.dart$"),
     re.compile(r"test[_-].*\.[rR]$"),
     re.compile(r"tests/testthat/"),
+    re.compile(r".*Test\.kt$"),
+    re.compile(r".*Test\.java$"),
 ]
 
 _TEST_RUNNER_NAMES = frozenset({
@@ -249,20 +251,29 @@ _TEST_RUNNER_NAMES = frozenset({
     "beforeAll", "afterAll",
 })
 
+# Annotations/decorators that mark test methods (JUnit, TestNG, etc.)
+_TEST_ANNOTATIONS = frozenset({
+    "Test", "ParameterizedTest", "RepeatedTest", "TestFactory",
+    "org.junit.Test", "org.junit.jupiter.api.Test",
+})
+
 
 def _is_test_file(path: str) -> bool:
     return any(p.search(path) for p in _TEST_FILE_PATTERNS)
 
 
-def _is_test_function(name: str, file_path: str) -> bool:
-    """A function is a test if its name matches test patterns or it lives
-    in a test file and has a test-runner name (describe, it, test, etc.).
+def _is_test_function(
+    name: str, file_path: str, decorators: tuple[str, ...] = (),
+) -> bool:
+    """A function is a test if its name matches test patterns, it lives
+    in a test file and has a test-runner name, or it has a @Test annotation.
     """
     if any(p.search(name) for p in _TEST_PATTERNS):
         return True
-    # In test files, treat common JS/TS test-runner wrappers as tests
     if _is_test_file(file_path) and name in _TEST_RUNNER_NAMES:
         return True
+    if decorators and any(d in _TEST_ANNOTATIONS for d in decorators):
+        return True
     return False
 
 
@@ -1540,7 +1551,26 @@ class CodeParser:
         if not name:
             return False
 
-        is_test = _is_test_function(name, file_path)
+        # Extract annotations/decorators for test detection
+        decorators: tuple[str, ...] = ()
+        deco_list: list[str] = []
+        for sub in child.children:
+            # Java/Kotlin/C#: annotations inside a modifiers child
+            if sub.type == "modifiers":
+                for mod in sub.children:
+                    if mod.type in ("annotation", "marker_annotation"):
+                        text = mod.text.decode("utf-8", errors="replace")
+                        deco_list.append(text.lstrip("@").strip())
+        # Python: check parent decorated_definition for decorator siblings
+        if child.parent and child.parent.type == "decorated_definition":
+            for sib in child.parent.children:
+                if sib.type == "decorator":
+                    text = sib.text.decode("utf-8", errors="replace")
+                    deco_list.append(text.lstrip("@").strip())
+        if deco_list:
+            decorators = tuple(deco_list)
+
+        is_test = _is_test_function(name, file_path, decorators)
         kind = "Test" if is_test else "Function"
         qualified = self._qualify(name, file_path, enclosing_class)
         params = self._get_params(child, language, source)
@@ -2432,7 +2462,8 @@ class CodeParser:
             return None  # method child not found
 
         # Simple call: func_name(args)
-        if first.type == "identifier":
+        # Kotlin uses "simple_identifier" instead of "identifier".
+        if first.type in ("identifier", "simple_identifier"):
             return first.text.decode("utf-8", errors="replace")
 
         # Perl: function_call_expression / ambiguous_function_call_expression
@@ -2450,18 +2481,25 @@ class CodeParser:
             return None
 
         # Method call: obj.method(args)
+        # Kotlin uses "navigation_expression" for member access (obj.method).
         member_types = (
             "attribute", "member_expression",
             "field_expression", "selector_expression",
+            "navigation_expression",
         )
         if first.type in member_types:
             # Get the rightmost identifier (the method name)
+            # Kotlin navigation_expression uses navigation_suffix > simple_identifier.
             for child in reversed(first.children):
                 if child.type in (
                     "identifier", "property_identifier", "field_identifier",
-                    "field_name",
+                    "field_name", "simple_identifier",
                 ):
                     return child.text.decode("utf-8", errors="replace")
+                if child.type == "navigation_suffix":
+                    for sub in child.children:
+                        if sub.type == "simple_identifier":
+                            return sub.text.decode("utf-8", errors="replace")
             return first.text.decode("utf-8", errors="replace")
 
         # Scoped call (e.g., Rust path::func())

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/prompts.py

@@ -12,7 +12,8 @@ detail_level="minimal" first patterns with get_minimal_context entry point.
 
 from __future__ import annotations
 
-_TOKEN_EFFICIENCY_PREAMBLE = """\
+_TOKEN_EFFICIENCY_PREAMBLE = (  # nosec B105 — prompt template, not a password
+    """\
 ## Rules for Token-Efficient Graph Usage
 1. ALWAYS call `get_minimal_context` first with a task description.
 2. Use `detail_level="minimal"` on all tool calls unless the minimal output \
@@ -25,6 +26,7 @@ scans (list_communities with full members).
 6. When reviewing changes: detect_changes(detail_level="minimal") → only \
 expand on high-risk items.
 """
+)
 
 
 def review_changes_prompt(base: str = "HEAD~1") -> list[dict]:

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/skills.py

@@ -141,7 +141,7 @@ def install_platform_configs(
         existing: dict[str, Any] = {}
         if config_path.exists():
             try:
-                existing = json.loads(config_path.read_text())
+                existing = json.loads(config_path.read_text(encoding="utf-8"))
             except (json.JSONDecodeError, OSError):
                 logger.warning("Invalid JSON in %s, will overwrite.", config_path)
                 existing = {}
@@ -176,7 +176,7 @@ def install_platform_configs(
             print(f"  [dry-run] {plat['name']}: would write {config_path}")
         else:
             config_path.parent.mkdir(parents=True, exist_ok=True)
-            config_path.write_text(json.dumps(existing, indent=2) + "\n")
+            config_path.write_text(json.dumps(existing, indent=2) + "\n", encoding="utf-8")
             print(f"  {plat['name']}: configured {config_path}")
 
         configured.append(plat["name"])
@@ -325,7 +325,7 @@ def generate_skills(repo_root: Path, skills_dir: Path | None = None) -> Path:
             "---\n\n"
             f"{skill['body']}\n"
         )
-        path.write_text(content)
+        path.write_text(content, encoding="utf-8")
         logger.info("Wrote skill: %s", path)
 
     return skills_dir
@@ -345,13 +345,13 @@ def generate_hooks_config() -> dict[str, Any]:
             "PostToolUse": [
                 {
                     "matcher": "Edit|Write|Bash",
-                    "command": "code-review-graph update --quiet --skip-flows",
+                    "command": "code-review-graph update --skip-flows",
                     "timeout": 5000,
                 },
             ],
             "SessionStart": [
                 {
-                    "command": "code-review-graph status --json",
+                    "command": "code-review-graph status",
                     "timeout": 3000,
                 },
             ],
@@ -381,14 +381,14 @@ def install_hooks(repo_root: Path) -> None:
     existing: dict[str, Any] = {}
     if settings_path.exists():
         try:
-            existing = json.loads(settings_path.read_text())
+            existing = json.loads(settings_path.read_text(encoding="utf-8"))
         except (json.JSONDecodeError, OSError) as exc:
             logger.warning("Could not read existing %s: %s", settings_path, exc)
 
     hooks_config = generate_hooks_config()
     existing.update(hooks_config)
 
-    settings_path.write_text(json.dumps(existing, indent=2) + "\n")
+    settings_path.write_text(json.dumps(existing, indent=2) + "\n", encoding="utf-8")
     logger.info("Wrote hooks config: %s", settings_path)
 
 
@@ -445,7 +445,7 @@ def _inject_instructions(file_path: Path, marker: str, section: str) -> bool:
     """
     existing = ""
     if file_path.exists():
-        existing = file_path.read_text()
+        existing = file_path.read_text(encoding="utf-8")
 
     if marker in existing:
         logger.info("%s already contains instructions, skipping.", file_path.name)
@@ -453,7 +453,7 @@ def _inject_instructions(file_path: Path, marker: str, section: str) -> bool:
 
     separator = "\n" if existing and not existing.endswith("\n") else ""
     extra_newline = "\n" if existing else ""
-    file_path.write_text(existing + separator + extra_newline + section)
+    file_path.write_text(existing + separator + extra_newline + section, encoding="utf-8")
     logger.info("Appended MCP tools section to %s", file_path)
     return True
 

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/tools/context.py

@@ -91,21 +91,21 @@ def get_minimal_context(
         # 3. Top 3 communities
         communities: list[str] = []
         try:
-            rows = store.conn.execute(
+            rows = store._conn.execute(
                 "SELECT name FROM communities ORDER BY size DESC LIMIT 3"
             ).fetchall()
             communities = [r[0] for r in rows]
-        except Exception:
+        except Exception:  # nosec B110 — table may not exist yet
             pass
 
         # 4. Top 3 critical flows
         flows: list[str] = []
         try:
-            rows = store.conn.execute(
+            rows = store._conn.execute(
                 "SELECT name FROM flows ORDER BY criticality DESC LIMIT 3"
             ).fetchall()
             flows = [r[0] for r in rows]
-        except Exception:
+        except Exception:  # nosec B110 — table may not exist yet
             pass
 
         # 5. Suggest next tools based on task keywords

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/docs/FEATURES.md

@@ -1,6 +1,21 @@
 # Features
 
-## v2.1.0 (Current)
+## v2.2.1 (Current)
+- **24 MCP tools** (up from 22): Added `get_minimal_context` and `run_postprocess`.
+- **Parallel parsing**: `ProcessPoolExecutor` for 3-5x faster builds on large repos.
+- **Lazy post-processing**: `postprocess="full"|"minimal"|"none"` to skip expensive steps.
+- **SQLite-native BFS**: Recursive CTE replaces NetworkX for impact analysis (faster on large graphs).
+- **Token-efficient output**: `detail_level="minimal"` on 8 tools for 40-60% token reduction.
+- **`get_minimal_context`**: Ultra-compact entry point (~100 tokens) with task-based tool routing.
+- **Incremental flow/community updates**: Only re-trace affected flows, skip community re-detection when unaffected.
+- **Visualization aggregation**: Community/file/auto modes with drill-down for 5k+ node graphs.
+- **Token-efficiency benchmarks**: 5 workflow benchmarks in eval framework.
+- **Pre-computed summary tables**: DB schema v6 with `community_summaries`, `flow_snapshots`, `risk_index`.
+- **Configurable limits**: `CRG_MAX_IMPACT_NODES`, `CRG_MAX_IMPACT_DEPTH`, `CRG_DEPENDENT_HOPS`, etc.
+- **Multi-hop dependents**: N-hop dependent discovery (default 2) with 500-file cap.
+- **615 tests** across 22 test files.
+
+## v2.1.0
 - **22 MCP tools** (up from 9): 13 new tools for flows, communities, architecture, refactoring, wiki, multi-repo, and risk-scored change detection.
 - **5 MCP prompts**: `review_changes`, `architecture_map`, `debug_issue`, `onboard_developer`, `pre_merge_check` workflow templates.
 - **18 languages** (up from 15): Added Dart, R, Perl support.

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/docs/LLM-OPTIMIZED-REFERENCE.md

@@ -1,4 +1,4 @@
-# LLM-OPTIMIZED REFERENCE -- code-review-graph v2.1.0
+# LLM-OPTIMIZED REFERENCE -- code-review-graph v2.2.1
 
 Claude Code: Read ONLY the exact `<section>` you need. Never load the whole file.
 
@@ -7,15 +7,15 @@ Quick install: pip install code-review-graph
 Then: code-review-graph install && code-review-graph build
 First run: /code-review-graph:build-graph
 After that use only delta/pr commands.
-For v2 features: detect_changes_tool for risk-scored reviews, list_flows_tool for execution paths, list_communities_tool for architecture.
+ALWAYS start with get_minimal_context_tool(task="your task") — returns ~100 tokens with risk, communities, flows, and suggested next tools.
+Use detail_level="minimal" on all subsequent calls unless you need more detail.
 </section>
 
 <section name="review-delta">
-Always call get_impact_radius on changed files first.
-Then get_review_context (depth=2).
-Or use detect_changes_tool for risk-scored, priority-ordered review guidance.
-Generate review using ONLY changed nodes + 2-hop neighbors.
-Target: <800 tokens total context.
+1. Call get_minimal_context_tool(task="review changes") first.
+2. If risk is low: detect_changes_tool(detail_level="minimal") → report summary.
+3. If risk is medium/high: detect_changes_tool(detail_level="standard") → expand on high-risk items.
+Target: ≤5 tool calls, ≤800 tokens total context.
 </section>
 
 <section name="review-pr">
@@ -24,10 +24,11 @@ Never include full files unless explicitly asked.
 </section>
 
 <section name="commands">
-MCP tools (22): build_or_update_graph_tool, get_impact_radius_tool, query_graph_tool, get_review_context_tool, semantic_search_nodes_tool, embed_graph_tool, list_graph_stats_tool, get_docs_section_tool, find_large_functions_tool, list_flows_tool, get_flow_tool, get_affected_flows_tool, list_communities_tool, get_community_tool, get_architecture_overview_tool, detect_changes_tool, refactor_tool, apply_refactor_tool, generate_wiki_tool, get_wiki_page_tool, list_repos_tool, cross_repo_search_tool
+MCP tools (24): get_minimal_context_tool, build_or_update_graph_tool, run_postprocess_tool, get_impact_radius_tool, query_graph_tool, get_review_context_tool, semantic_search_nodes_tool, embed_graph_tool, list_graph_stats_tool, get_docs_section_tool, find_large_functions_tool, list_flows_tool, get_flow_tool, get_affected_flows_tool, list_communities_tool, get_community_tool, get_architecture_overview_tool, detect_changes_tool, refactor_tool, apply_refactor_tool, generate_wiki_tool, get_wiki_page_tool, list_repos_tool, cross_repo_search_tool
 MCP prompts (5): review_changes, architecture_map, debug_issue, onboard_developer, pre_merge_check
 Skills: build-graph, review-delta, review-pr
-CLI: code-review-graph [install|init|build|update|status|watch|visualize|serve|wiki|detect-changes|register|unregister|repos|eval]
+CLI: code-review-graph [install|init|build|update|status|watch|visualize|serve|wiki|detect-changes|postprocess|register|unregister|repos|eval]
+Token efficiency: All tools support detail_level="minimal" for compact output. Always call get_minimal_context_tool first.
 </section>
 
 <section name="legal">
@@ -48,7 +49,7 @@ Configure via CRG_EMBEDDING_MODEL env var or model parameter.
 </section>
 
 <section name="languages">
-Supported (18): Python, TypeScript/TSX, JavaScript, Vue, Go, Rust, Java, Scala, C#, Ruby, Kotlin, Swift, PHP, Solidity, C/C++, Dart, R, Perl
+Supported (19): Python, TypeScript/TSX, JavaScript, Vue, Go, Rust, Java, Scala, C#, Ruby, Kotlin, Swift, PHP, Solidity, C/C++, Dart, R, Perl, Lua
 Parser: Tree-sitter via tree-sitter-language-pack
 </section>
 

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "code-review-graph"
-version = "2.2.0"
+version = "2.2.2"
 description = "Persistent incremental knowledge graph for token-efficient, context-aware code reviews with Claude Code"
 readme = {file = "README.md", content-type = "text/markdown"}
 license = "MIT"

code_review_graph-2.2.0/.claude-plugin/marketplace.json

@@ -1,21 +0,0 @@
-{
-  "name": "code-review-graph",
-  "owner": {
-    "name": "Tirth Kanani",
-    "email": "tirthkanani18@gmail.com"
-  },
-  "metadata": {
-    "description": "Persistent incremental knowledge graph for token-efficient, context-aware code reviews with Claude Code",
-    "version": "2.1.0"
-  },
-  "plugins": [
-    {
-      "name": "code-review-graph",
-      "source": "./",
-      "description": "Persistent incremental knowledge graph for token-efficient, context-aware code reviews with Claude Code",
-      "version": "2.1.0",
-      "category": "development",
-      "keywords": ["code-review", "knowledge-graph", "incremental", "tree-sitter", "mcp", "claude-code"]
-    }
-  ]
-}

code_review_graph-2.2.0/.claude-plugin/plugin.json

@@ -1,21 +0,0 @@
-{
-  "name": "code-review-graph",
-  "description": "Persistent incremental knowledge graph for token-efficient, context-aware code reviews with Claude Code",
-  "version": "2.1.0",
-  "author": {
-    "name": "Tirth Kanani",
-    "email": "tirthkanani18@gmail.com",
-    "url": "https://github.com/tirth8205"
-  },
-  "homepage": "https://code-review-graph.com",
-  "repository": "https://github.com/tirth8205/code-review-graph",
-  "license": "MIT",
-  "keywords": ["code-review", "knowledge-graph", "incremental", "tree-sitter", "mcp", "claude-code"],
-  "mcpServers": {
-    "code-review-graph": {
-      "command": "uvx",
-      "args": ["code-review-graph", "serve"]
-    }
-  },
-  "skills": "./skills/"
-}

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/main.py

@@ -21,8 +21,6 @@ from .tools import (
     apply_refactor_func,
     build_or_update_graph,
     cross_repo_search_func,
-    get_minimal_context,
-    run_postprocess,
     detect_changes_func,
     embed_graph,
     find_large_functions,
@@ -33,6 +31,7 @@ from .tools import (
     get_docs_section,
     get_flow,
     get_impact_radius,
+    get_minimal_context,
     get_review_context,
     get_wiki_page_func,
     list_communities_func,
@@ -41,6 +40,7 @@ from .tools import (
     list_repos_func,
     query_graph,
     refactor_func,
+    run_postprocess,
     semantic_search_nodes,
 )
 

{code_review_graph-2.2.0 → code_review_graph-2.2.2}/code_review_graph/tools/__init__.py

@@ -46,9 +46,6 @@ from ._common import (
 # -- build ------------------------------------------------------------------
 from .build import build_or_update_graph, run_postprocess
 
-# -- context ----------------------------------------------------------------
-from .context import get_minimal_context
-
 # -- community_tools --------------------------------------------------------
 from .community_tools import (
     get_architecture_overview_func,
@@ -56,6 +53,9 @@ from .community_tools import (
     list_communities_func,
 )
 
+# -- context ----------------------------------------------------------------
+from .context import get_minimal_context
+
 # -- docs -------------------------------------------------------------------
 from .docs import embed_graph, generate_wiki_func, get_docs_section, get_wiki_page_func