knowledge-rag 3.3.1__tar.gz → 3.3.2__tar.gz

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: knowledge-rag
-Version: 3.3.1
+Version: 3.3.2
 Summary: Local RAG System for Claude Code — Hybrid search + Cross-encoder Reranking + 12 MCP Tools. Zero external servers.
 Project-URL: Homepage, https://github.com/lyonzin/knowledge-rag
 Project-URL: Repository, https://github.com/lyonzin/knowledge-rag
@@ -38,7 +38,7 @@ Description-Content-Type: text/markdown
 
 <div align="center">
 
-![Version](https://img.shields.io/badge/version-3.3.1-blue.svg)
+![Version](https://img.shields.io/badge/version-3.3.2-blue.svg)
 ![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-green.svg)
 ![License](https://img.shields.io/badge/license-MIT-yellow.svg)
 ![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)
@@ -1163,7 +1163,7 @@ pip install rank-bm25
 
 ### "ModuleNotFoundError: No module named 'mcp_server'"
 
-This occurs when Claude Code doesn't set the working directory correctly. Use the `cmd /c "cd /d ... && python"` wrapper in your MCP config (see [Installation](#configure-mcp-for-claude-code)).
+This occurs when Claude Code doesn't set the working directory correctly. Use the `cmd /c "cd /d ... && python"` wrapper in your MCP config (see [Installation](#installation)).
 
 ### Dimension mismatch after upgrade
 
@@ -1195,6 +1195,15 @@ With ~200 documents, expect ~300-500MB RAM. The embedding model (~50MB) and rera
 
 ## Changelog
 
+### v3.3.2 (2026-04-06)
+
+- **FIX**: Full type validation on all YAML config values — wrong types warn and fall back to defaults
+- **FIX**: Bounds validation for chunk_size, chunk_overlap, default_results, max_results, embedding_dim
+- **FIX**: `keyword_routes` with string values instead of lists detected and removed with warning
+- **FIX**: `reranker_enabled: "yes"` (string) corrected to boolean with warning
+- **FIX**: Synced version strings across all source files
+- **FIX**: Broken README anchor, duplicate keyword, error handling in `knowledge-rag init`
+
 ### v3.3.1 (2026-04-06)
 
 - **FIX**: YAML null values (`category_mappings:` without value) no longer crash the server — falls back to defaults

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/README.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-![Version](https://img.shields.io/badge/version-3.3.1-blue.svg)
+![Version](https://img.shields.io/badge/version-3.3.2-blue.svg)
 ![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-green.svg)
 ![License](https://img.shields.io/badge/license-MIT-yellow.svg)
 ![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)
@@ -1127,7 +1127,7 @@ pip install rank-bm25
 
 ### "ModuleNotFoundError: No module named 'mcp_server'"
 
-This occurs when Claude Code doesn't set the working directory correctly. Use the `cmd /c "cd /d ... && python"` wrapper in your MCP config (see [Installation](#configure-mcp-for-claude-code)).
+This occurs when Claude Code doesn't set the working directory correctly. Use the `cmd /c "cd /d ... && python"` wrapper in your MCP config (see [Installation](#installation)).
 
 ### Dimension mismatch after upgrade
 
@@ -1159,6 +1159,15 @@ With ~200 documents, expect ~300-500MB RAM. The embedding model (~50MB) and rera
 
 ## Changelog
 
+### v3.3.2 (2026-04-06)
+
+- **FIX**: Full type validation on all YAML config values — wrong types warn and fall back to defaults
+- **FIX**: Bounds validation for chunk_size, chunk_overlap, default_results, max_results, embedding_dim
+- **FIX**: `keyword_routes` with string values instead of lists detected and removed with warning
+- **FIX**: `reranker_enabled: "yes"` (string) corrected to boolean with warning
+- **FIX**: Synced version strings across all source files
+- **FIX**: Broken README anchor, duplicate keyword, error handling in `knowledge-rag init`
+
 ### v3.3.1 (2026-04-06)
 
 - **FIX**: YAML null values (`category_mappings:` without value) no longer crash the server — falls back to defaults

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/mcp_server/__init__.py

@@ -1,6 +1,6 @@
 """Knowledge RAG MCP Server - Local Retrieval-Augmented Generation System"""
 
-__version__ = "3.2.3"
+__version__ = "3.3.2"
 __author__ = "Ailton Rocha (Lyon.)"
 
 from .config import Config

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/mcp_server/config.py

@@ -1,4 +1,4 @@
-"""Configuration for Knowledge RAG System v3.1 — YAML-configurable"""
+"""Configuration for Knowledge RAG System v3.3.2 — YAML-configurable"""
 
 import os
 from dataclasses import dataclass, field
@@ -73,7 +73,19 @@ def _get(section: str, key: str, default):
     if not isinstance(s, dict):
         return default
     val = s.get(key)
-    return val if val is not None else default
+    if val is None:
+        return default
+    # Skip type check when default is None (caller handles validation)
+    if default is None:
+        return val
+    # YAML parses "yes"/"no" as bool, but explicit string "yes" stays str
+    if not isinstance(val, type(default)):
+        print(
+            f"[WARN] config.yaml: {section}.{key} has wrong type "
+            f"(expected {type(default).__name__}, got {type(val).__name__}), using default"
+        )
+        return default
+    return val
 
 
 def _get_top(key: str, default):
@@ -81,7 +93,8 @@ def _get_top(key: str, default):
     val = _yaml.get(key)
     if val is None:
         return default
-    if not isinstance(val, type(default)):
+    if not isinstance(val, dict):
+        print(f"[WARN] config.yaml: {key} has wrong type (expected dict, got {type(val).__name__}), using default")
         return default
     return val
 
@@ -155,7 +168,6 @@ _DEFAULT_KEYWORD_ROUTES = {
         "deserialization",
         "ysoserial",
         "upload bypass",
-        "reverse shell",
         "web shell",
         "hash cracking",
         "hashcat",
@@ -431,7 +443,41 @@ class Config:
     max_results: int = field(default_factory=lambda: _get("search", "max_results", 20))
 
     def __post_init__(self):
-        """Ensure directories exist"""
+        """Validate config values and ensure directories exist."""
+        # Bounds validation
+        if not isinstance(self.chunk_size, int) or self.chunk_size < 100:
+            print(f"[WARN] chunk_size={self.chunk_size} invalid, using 1000")
+            self.chunk_size = 1000
+        if not isinstance(self.chunk_overlap, int) or self.chunk_overlap < 0:
+            print(f"[WARN] chunk_overlap={self.chunk_overlap} invalid, using 200")
+            self.chunk_overlap = 200
+        if self.chunk_overlap >= self.chunk_size:
+            print(
+                f"[WARN] chunk_overlap ({self.chunk_overlap}) >= chunk_size ({self.chunk_size}), using {self.chunk_size // 5}"
+            )
+            self.chunk_overlap = self.chunk_size // 5
+        if not isinstance(self.default_results, int) or self.default_results < 1:
+            self.default_results = 5
+        if not isinstance(self.max_results, int) or self.max_results < 1:
+            self.max_results = 20
+        if not isinstance(self.embedding_dim, int) or self.embedding_dim < 1:
+            self.embedding_dim = 384
+        if not isinstance(self.reranker_enabled, bool):
+            print(f"[WARN] reranker_enabled={self.reranker_enabled!r} invalid, using True")
+            self.reranker_enabled = True
+        if not isinstance(self.reranker_top_k_multiplier, int) or self.reranker_top_k_multiplier < 1:
+            self.reranker_top_k_multiplier = 3
+        if not isinstance(self.supported_formats, list) or not self.supported_formats:
+            print("[WARN] supported_formats is empty or invalid, using defaults")
+            self.supported_formats = [".md", ".txt", ".pdf", ".py", ".json", ".docx", ".xlsx", ".pptx", ".csv"]
+
+        # Validate keyword_routes values are lists (not strings)
+        for cat, keywords in list(self.keyword_routes.items()):
+            if not isinstance(keywords, list):
+                print(f"[WARN] keyword_routes.{cat} is not a list, removing")
+                del self.keyword_routes[cat]
+
+        # Ensure directories exist
         self.data_dir.mkdir(parents=True, exist_ok=True)
         self.chroma_dir.mkdir(parents=True, exist_ok=True)
         self.documents_dir.mkdir(parents=True, exist_ok=True)

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/mcp_server/server.py

@@ -19,8 +19,8 @@ Features:
     - CRUD operations via MCP tools (add, update, remove docs)
 
 Autor:   Lyon (Ailton Rocha)
-Versao:  3.0.0
-Data:    2026-03-19
+Versao:  3.3.2
+Data:    2026-04-06
 """
 
 import hashlib
@@ -1836,32 +1836,37 @@ def _handle_init():
 
     cwd = Path.cwd()
 
-    # Copy config.example.yaml
-    src = data_dir / "config.example.yaml"
-    if src.exists():
-        dst = cwd / "config.example.yaml"
-        shutil.copy2(src, dst)
-        print(f"[OK] {dst}")
-
-    # Copy presets
-    presets_dir = cwd / "presets"
-    presets_dir.mkdir(exist_ok=True)
-    for f in data_dir.glob("*.yaml"):
-        if f.name == "config.example.yaml":
-            continue
-        dst = presets_dir / f.name
-        shutil.copy2(f, dst)
-        print(f"[OK] {dst}")
-
-    # Create documents dir
-    docs_dir = cwd / "documents"
-    docs_dir.mkdir(exist_ok=True)
-    print(f"[OK] {docs_dir}/")
-
-    print("\nDone. Quick start:")
-    print("  cp presets/general.yaml config.yaml     # or cybersecurity, developer, research")
-    print("  # Add your documents to documents/")
-    print("  # Restart Claude Code")
+    try:
+        # Copy config.example.yaml
+        src = data_dir / "config.example.yaml"
+        if src.exists():
+            dst = cwd / "config.example.yaml"
+            shutil.copy2(src, dst)
+            print(f"[OK] {dst}")
+
+        # Copy presets
+        presets_dir = cwd / "presets"
+        presets_dir.mkdir(exist_ok=True)
+        for f in data_dir.glob("*.yaml"):
+            if f.name == "config.example.yaml":
+                continue
+            dst = presets_dir / f.name
+            shutil.copy2(f, dst)
+            print(f"[OK] {dst}")
+
+        # Create documents dir
+        docs_dir = cwd / "documents"
+        docs_dir.mkdir(exist_ok=True)
+        print(f"[OK] {docs_dir}/")
+
+        print("\nDone. Quick start:")
+        print("  cp presets/general.yaml config.yaml     # or cybersecurity, developer, research")
+        print("  # Add your documents to documents/")
+        print("  # Restart Claude Code")
+    except PermissionError:
+        print("[ERROR] Permission denied. Run from a writable directory.")
+    except OSError as e:
+        print(f"[ERROR] Failed to write files: {e}")
 
 
 def main():

{knowledge_rag-3.3.1 → knowledge_rag-3.3.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "knowledge-rag"
-version = "3.3.1"
+version = "3.3.2"
 description = "Local RAG System for Claude Code — Hybrid search + Cross-encoder Reranking + 12 MCP Tools. Zero external servers."
 readme = "README.md"
 license = {text = "MIT"}