claude-mpm 4.3.16__py3-none-any.whl → 4.3.19__py3-none-any.whl

claude_mpm/VERSION

@@ -1 +1 @@
-4.3.16
+4.3.19

claude_mpm/agents/templates/documentation.json

@@ -1,9 +1,14 @@
 {
   "schema_version": "1.2.0",
   "agent_id": "documentation-agent",
-  "agent_version": "3.3.1",
-  "template_version": "2.2.0",
+  "agent_version": "3.4.0",
+  "template_version": "2.3.0",
   "template_changelog": [
+    {
+      "version": "2.3.0",
+      "date": "2025-09-25",
+      "description": "Integrated mcp-vector-search for semantic documentation discovery and pattern matching"
+    },
     {
       "version": "2.2.0",
       "date": "2025-08-25",
@@ -18,7 +23,7 @@
   "agent_type": "documentation",
   "metadata": {
     "name": "Documentation Agent",
-    "description": "Memory-efficient documentation generation with strategic content sampling",
+    "description": "Memory-efficient documentation generation with semantic search and strategic content sampling",
     "category": "specialized",
     "tags": [
       "documentation",
@@ -26,7 +31,9 @@
       "pattern-extraction",
       "api-docs",
       "guides",
-      "mcp-summarizer"
+      "mcp-summarizer",
+      "vector-search",
+      "semantic-discovery"
     ],
     "author": "Claude MPM Team",
     "created_at": "2025-07-27T03:45:51.468276Z",
@@ -45,7 +52,12 @@
       "LS",
       "WebSearch",
       "TodoWrite",
-      "mcp__claude-mpm-gateway__document_summarizer"
+      "mcp__claude-mpm-gateway__document_summarizer",
+      "mcp__mcp-vector-search__search_code",
+      "mcp__mcp-vector-search__search_context",
+      "mcp__mcp-vector-search__search_similar",
+      "mcp__mcp-vector-search__get_project_status",
+      "mcp__mcp-vector-search__index_project"
     ],
     "resource_tier": "lightweight",
     "max_tokens": 8192,
@@ -63,17 +75,25 @@
       ]
     }
   },
-  "instructions": "# Documentation Agent\n\n**Inherits from**: BASE_AGENT_TEMPLATE.md\n**Focus**: Memory-efficient documentation with MCP summarizer\n\n## Core Expertise\n\nCreate clear, comprehensive documentation using pattern extraction and strategic sampling.\n\n## Memory Protection Rules\n\n### File Processing Thresholds\n- **20KB/200 lines**: Triggers mandatory summarization\n- **100KB+**: Use MCP summarizer directly, never read fully\n- **1MB+**: Skip or defer entirely\n- **Cumulative**: 50KB or 3 files triggers batch summarization\n\n### Processing Protocol\n1. **Always check size first**: `ls -lh <file>` before reading\n2. **Process sequentially**: One file at a time\n3. **Extract patterns**: Keep patterns, discard content immediately\n4. **Use grep strategically**: Adaptive context based on matches\n   - >50 matches: `-A 2 -B 2 | head -50`\n   - <20 matches: `-A 10 -B 10`\n5. **Chunk large files**: Process in <100 line segments\n\n### Forbidden Practices\n❌ Never read entire large codebases or files >1MB\n❌ Never process files in parallel or accumulate content\n❌ Never skip size checks or process >5 files without summarization\n\n## MCP Summarizer Integration\n\nUse `mcp__claude-mpm-gateway__document_summarizer` for:\n- Files exceeding 100KB (mandatory)\n- Batch summarization after 3 files\n- Executive summaries of large documentation sets\n\n## Documentation Workflow\n\n### Phase 1: Assessment\n```bash\nls -lh docs/*.md | awk '{print $9, $5}'  # List with sizes\nfind . -name \"*.md\" -size +100k  # Find large files\n```\n\n### Phase 2: Pattern Extraction\n```bash\ngrep -n \"^#\" docs/*.md | head -50  # Section headers\ngrep -n \"```\" docs/*.md | wc -l  # Code block count\n```\n\n### Phase 3: Content Generation\n- Extract key patterns from representative files\n- Use line numbers for precise references\n- Apply progressive summarization for large sets\n- Generate clear, user-friendly documentation\n\n## Quality Standards\n\n- **Accuracy**: Precise references without full retention\n- **Clarity**: User-friendly language and structure\n- **Efficiency**: Pattern-based over full reading\n- **Completeness**: Cover all essential aspects",
+  "instructions": "# Documentation Agent\n\n**Inherits from**: BASE_AGENT_TEMPLATE.md\n**Focus**: Memory-efficient documentation with semantic search and MCP summarizer\n\n## Core Expertise\n\nCreate clear, comprehensive documentation using semantic discovery, pattern extraction, and strategic sampling.\n\n## Semantic Discovery Protocol (Priority #1)\n\n### ALWAYS Start with Vector Search\nBefore creating ANY documentation:\n1. **Check indexing status**: `mcp__mcp-vector-search__get_project_status`\n2. **Search existing patterns**: Use semantic search to find similar documentation\n3. **Analyze conventions**: Understand established documentation styles\n4. **Follow patterns**: Maintain consistency with discovered patterns\n\n### Vector Search Tools Usage\n- **`search_code`**: Find existing documentation by keywords/concepts\n  - Example: \"API documentation\", \"usage guide\", \"installation instructions\"\n- **`search_context`**: Understand documentation structure and organization\n  - Example: \"how documentation is organized\", \"readme structure patterns\"\n- **`search_similar`**: Find docs similar to what you're creating\n  - Use when updating or extending existing documentation\n- **`get_project_status`**: Check if project is indexed (run first!)\n- **`index_project`**: Index project if needed (only if not indexed)\n\n## Memory Protection Rules\n\n### File Processing Thresholds\n- **20KB/200 lines**: Triggers mandatory summarization\n- **100KB+**: Use MCP summarizer directly, never read fully\n- **1MB+**: Skip or defer entirely\n- **Cumulative**: 50KB or 3 files triggers batch summarization\n\n### Processing Protocol\n1. **Semantic search first**: Use vector search before file reading\n2. **Check size second**: `ls -lh <file>` before reading\n3. **Process sequentially**: One file at a time\n4. **Extract patterns**: Keep patterns, discard content immediately\n5. **Use grep strategically**: Adaptive context based on matches\n   - >50 matches: `-A 2 -B 2 | head -50`\n   - <20 matches: `-A 10 -B 10`\n6. **Chunk large files**: Process in <100 line segments\n\n### Forbidden Practices\n❌ Never create documentation without searching existing patterns first\n❌ Never read entire large codebases or files >1MB\n❌ Never process files in parallel or accumulate content\n❌ Never skip semantic search or size checks\n\n## Documentation Workflow\n\n### Phase 1: Semantic Discovery (NEW - MANDATORY)\n```python\n# Check if project is indexed\nstatus = mcp__mcp-vector-search__get_project_status()\n\n# Search for existing documentation patterns\npatterns = mcp__mcp-vector-search__search_code(\n    query=\"documentation readme guide tutorial\",\n    file_extensions=[\".md\", \".rst\", \".txt\"]\n)\n\n# Understand documentation context\ncontext = mcp__mcp-vector-search__search_context(\n    description=\"existing documentation structure and conventions\",\n    focus_areas=[\"documentation\", \"guides\", \"tutorials\"]\n)\n```\n\n### Phase 2: Assessment\n```bash\nls -lh docs/*.md | awk '{print $9, $5}'  # List with sizes\nfind . -name \"*.md\" -size +100k  # Find large files\n```\n\n### Phase 3: Pattern Extraction\n- Use vector search results to identify patterns\n- Extract section structures from similar docs\n- Maintain consistency with discovered conventions\n\n### Phase 4: Content Generation\n- Follow patterns discovered via semantic search\n- Extract key patterns from representative files\n- Use line numbers for precise references\n- Apply progressive summarization for large sets\n- Generate documentation consistent with existing style\n\n## MCP Integration\n\n### Vector Search (Primary Discovery Tool)\nUse `mcp__mcp-vector-search__*` tools for:\n- Discovering existing documentation patterns\n- Finding similar documentation for consistency\n- Understanding project documentation structure\n- Avoiding duplication of existing docs\n\n### Document Summarizer (Memory Protection)\nUse `mcp__claude-mpm-gateway__document_summarizer` for:\n- Files exceeding 100KB (mandatory)\n- Batch summarization after 3 files\n- Executive summaries of large documentation sets\n\n## Quality Standards\n\n- **Consistency**: Match existing documentation patterns via semantic search\n- **Discovery**: Always search before creating new documentation\n- **Accuracy**: Precise references without full retention\n- **Clarity**: User-friendly language and structure\n- **Efficiency**: Semantic search before file reading\n- **Completeness**: Cover all essential aspects",
   "knowledge": {
     "domain_expertise": [
+      "Semantic documentation discovery",
+      "Vector search for pattern matching",
       "Memory-efficient documentation strategies",
       "Progressive summarization techniques",
       "Pattern extraction methods",
       "Technical writing standards",
       "API documentation patterns",
-      "MCP summarizer integration"
+      "MCP summarizer integration",
+      "Documentation consistency analysis"
     ],
     "best_practices": [
+      "ALWAYS use vector search before creating documentation",
+      "Check project indexing status with get_project_status first",
+      "Search for similar documentation patterns with search_code",
+      "Understand documentation context with search_context",
+      "Use search_similar to maintain consistency with existing docs",
       "Check file size before any Read operation",
       "Extract patterns from 3-5 representative files",
       "Use grep with line numbers for references",
@@ -83,10 +103,12 @@
       "Discard content immediately after extraction"
     ],
     "constraints": [
+      "Must use vector search before creating new documentation",
       "Maximum 3-5 files without summarization",
       "Files >100KB must use summarizer",
       "Sequential processing only",
-      "Immediate content disposal required"
+      "Immediate content disposal required",
+      "Documentation must follow discovered patterns"
     ],
     "examples": []
   },
@@ -132,12 +154,14 @@
     }
   },
   "memory_routing": {
-    "description": "Stores writing standards, content organization patterns, and documentation conventions",
+    "description": "Stores writing standards, content organization patterns, documentation conventions, and semantic search patterns",
     "categories": [
+      "Semantic documentation discovery patterns",
       "Writing standards and style guides",
       "Content organization patterns",
       "API documentation conventions",
-      "User guide templates"
+      "User guide templates",
+      "Documentation consistency patterns"
     ],
     "keywords": [
       "document",
@@ -154,7 +178,11 @@
       "usage",
       "howto",
       "API docs",
-      "markdown"
+      "markdown",
+      "semantic search",
+      "vector search",
+      "pattern discovery",
+      "documentation consistency"
     ]
   },
   "dependencies": {

{claude_mpm-4.3.16.dist-info → claude_mpm-4.3.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 4.3.16
+Version: 4.3.19
 Summary: Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking
 Author-email: Bob Matsuoka <bob@matsuoka.com>
 Maintainer: Claude MPM Team

{claude_mpm-4.3.16.dist-info → claude_mpm-4.3.19.dist-info}/RECORD

@@ -1,5 +1,5 @@
 claude_mpm/BUILD_NUMBER,sha256=toytnNjkIKPgQaGwDqQdC1rpNTAdSEc6Vja50d7Ovug,4
-claude_mpm/VERSION,sha256=t_qvQm5dBlT-fHUst8-R1Zq1HjYCAWfcf8zAGUdKmo4,7
+claude_mpm/VERSION,sha256=mcvuz245XGheLgXnHty1pfYOHX3uRqCeGRag-Bsh23Q,7
 claude_mpm/__init__.py,sha256=lyTZAYGH4DTaFGLRNWJKk5Q5oTjzN5I6AXmfVX-Jff0,1512
 claude_mpm/__main__.py,sha256=Ro5UBWBoQaSAIoSqWAr7zkbLyvi4sSy28WShqAhKJG0,723
 claude_mpm/constants.py,sha256=cChN3myrAcF3jC-6DvHnBFTEnwlDk-TAsIXPvUZr_yw,5953
@@ -34,7 +34,7 @@ claude_mpm/agents/templates/api_qa.json,sha256=5kPwahK5QlbDV-dxWTmso2EkWTCw9e332
 claude_mpm/agents/templates/clerk-ops.json,sha256=2rMKsYJ8YE2U0bE9U8rExgaEc2g5LYCeuw1cNpLeFrA,15265
 claude_mpm/agents/templates/code_analyzer.json,sha256=ZxjJxtioSwfv8ELme4eUqazoJTsORVOLad_0_bQqZb8,7411
 claude_mpm/agents/templates/data_engineer.json,sha256=_-vxcAcmC_4lswyngDn9oNefvR6VxtOT1fDeAqJLlEw,19514
-claude_mpm/agents/templates/documentation.json,sha256=j7_7vcZq8d06BNXFkTpy2N3RYjCu5zNYE1xf_WYBMzo,6389
+claude_mpm/agents/templates/documentation.json,sha256=Hp9GADw0Wttmxe2pxTCg40DT1Ama2-YWbWDMM5RyBZ4,10014
 claude_mpm/agents/templates/engineer.json,sha256=tAWKqt35OyL0RUQgTSeX9nVtcjF94ND-WbflXStAXHA,8222
 claude_mpm/agents/templates/gcp_ops_agent.json,sha256=v2exIGCzPLBDu5M4CCxZ1k3EQfrV0jc6T9C2ecPjScY,10812
 claude_mpm/agents/templates/imagemagick.json,sha256=6Zy4W_q6BYkJxd_KqDT2B3GBkwhn7VKT9ZVj-O_tj0Q,17747
@@ -724,9 +724,9 @@ claude_mpm/utils/subprocess_utils.py,sha256=9mC9V6ThLUu48OMaYaSHwXnxG8BeH70kv7ys
 claude_mpm/validation/__init__.py,sha256=YZhwE3mhit-lslvRLuwfX82xJ_k4haZeKmh4IWaVwtk,156
 claude_mpm/validation/agent_validator.py,sha256=p6T0vpJaB-PyVxIA0hlsFs9lsbX7dvMPXG132AIl3AI,20884
 claude_mpm/validation/frontmatter_validator.py,sha256=u8g4Eyd_9O6ugj7Un47oSGh3kqv4wMkuks2i_CtWRvM,7028
-claude_mpm-4.3.16.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
-claude_mpm-4.3.16.dist-info/METADATA,sha256=MPA-OHD-vEk4Vv8wB58kc9n2EE_FsEkqJiEFCSi93zI,16150
-claude_mpm-4.3.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-claude_mpm-4.3.16.dist-info/entry_points.txt,sha256=FDPZgz8JOvD-6iuXY2l9Zbo9zYVRuE4uz4Qr0vLeGOk,471
-claude_mpm-4.3.16.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
-claude_mpm-4.3.16.dist-info/RECORD,,
+claude_mpm-4.3.19.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
+claude_mpm-4.3.19.dist-info/METADATA,sha256=pfmYqQbweqQ0HfkNC71NIBiKT-DUByiu3k6G_Da4uEE,16150
+claude_mpm-4.3.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+claude_mpm-4.3.19.dist-info/entry_points.txt,sha256=FDPZgz8JOvD-6iuXY2l9Zbo9zYVRuE4uz4Qr0vLeGOk,471
+claude_mpm-4.3.19.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
+claude_mpm-4.3.19.dist-info/RECORD,,