know-cli 0.4.2__tar.gz → 0.5.0__tar.gz

{know_cli-0.4.2 → know_cli-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: know-cli
-Version: 0.4.2
+Version: 0.5.0
 Summary: Context Intelligence for AI Coding Agents — smart, token-budgeted code context
 Project-URL: Homepage, https://github.com/sushilk1991/know-cli
 Project-URL: Repository, https://github.com/sushilk1991/know-cli

{know_cli-0.4.2 → know_cli-0.5.0}/docs/arc.md

@@ -7,29 +7,29 @@
 
 ## 📁 Project Structure
 
+- **[src.know.daemon](src/know/daemon.py)** - Background daemon for maintaining hot indexes.
 - **[src.know.ai](src/know/ai.py)** - AI integration for intelligent code understanding with advanced token optimization.
 - **[src.know.diff](src/know/diff.py)** - Diff mode for tracking architectural changes safely using git worktrees.
 - **[src.know.knowledge_base](src/know/knowledge_base.py)** - Knowledge base: cross-session memory for AI agents.
 - **[src.know.index](src/know/index.py)** - Index management for incremental code scanning.
 - **[src.know.logger](src/know/logger.py)** - Logging configuration for know.
 - **[src.know.watcher](src/know/watcher.py)** - File system watcher for auto-updating documentation.
+- **[src.know.embeddings](src/know/embeddings.py)** - Centralized embedding model management.
 - **[src.know.models](src/know/models.py)** - Data models for know-cli.
 - **[src.know.token_counter](src/know/token_counter.py)** - Token counting for context budget management.
-- **[src.know.model_router](src/know/model_router.py)** - Smart model router for cost-optimized AI interactions.
 - **[src.know.stats](src/know/stats.py)** - Usage statistics tracker for know-cli.
 - **[src.know.semantic_search](src/know/semantic_search.py)** - Semantic code search using real embeddings and vector similarity.
 - **[src.know.__init__](src/know/__init__.py)** - know - Living documentation generator for codebases.
-- **[src.know.cli](src/know/cli.py)** - CLI entry point for know.
 - **[src.know.generator](src/know/generator.py)** - Documentation generator.
 - **[src.know.config](src/know/config.py)** - Configuration management for know.
-- ... and 8 more modules
+- ... and 18 more modules
 
 ## 📊 Statistics
 
-- **Files:** 23
-- **Modules:** 23
-- **Functions:** 57
-- **Classes:** 47
+- **Files:** 33
+- **Modules:** 33
+- **Functions:** 74
+- **Classes:** 55
 
 ---
 

{know_cli-0.4.2 → know_cli-0.5.0}/docs/architecture.md

@@ -2,33 +2,41 @@
 
 ```mermaid
 graph TB
+    daemon["daemon\n(9f, 2c)"]
     ai["ai\n(0f, 4c)"]
     diff["diff\n(0f, 1c)"]
     knowledge_base["knowledge_base\n(0f, 2c)"]
     index["index\n(1f, 1c)"]
     logger["logger\n(2f, 0c)"]
     watcher["watcher\n(0f, 2c)"]
+    embeddings["embeddings\n(3f, 0c)"]
     models["models\n(0f, 4c)"]
     token_counter["token_counter\n(4f, 0c)"]
-    model_router["model_router\n(0f, 2c)"]
-    stats["stats\n(0f, 2c)"]
+    stats["stats\n(0f, 1c)"]
     semantic_search["semantic_search\n(0f, 2c)"]
     __init__["__init__"]
-    cli["cli\n(35f, 0c)"]
     generator["generator\n(0f, 1c)"]
     config["config\n(1f, 6c)"]
     import_graph["import_graph\n(0f, 1c)"]
     exceptions["exceptions\n(0f, 8c)"]
     git_hooks["git_hooks\n(0f, 1c)"]
+    daemon_db["daemon_db\n(0f, 1c)"]
     mcp_server["mcp_server\n(5f, 0c)"]
-    scanner["scanner\n(1f, 1c)"]
 
+    daemon --> config
+    daemon --> daemon_db
+    daemon --> logger
+    daemon --> parsers
+    daemon --> scanner
+    daemon --> import_graph
     ai --> config
     diff --> config
     diff --> scanner
     knowledge_base --> logger
     knowledge_base --> config
+    knowledge_base --> daemon_db
     knowledge_base --> token_counter
+    knowledge_base --> embeddings
     index --> exceptions
     index --> logger
     index --> config
@@ -36,32 +44,20 @@ graph TB
     watcher --> config
     watcher --> scanner
     watcher --> generator
+    embeddings --> logger
     stats --> logger
     stats --> config
+    semantic_search --> embeddings
     semantic_search --> context_engine
-    __init__ --> cli
-    cli --> config
-    cli --> scanner
-    cli --> generator
-    cli --> watcher
-    cli --> ai
-    cli --> git_hooks
-    cli --> logger
-    cli --> exceptions
-    cli --> semantic_search
-    cli --> context_engine
-    cli --> import_graph
-    cli --> diff
-    cli --> knowledge_base
-    cli --> stats
-    cli --> model_router
-    cli --> mcp_server
     generator --> config
     generator --> scanner
     generator --> ai
     import_graph --> logger
     import_graph --> config
+    import_graph --> daemon_db
     git_hooks --> config
+    daemon_db --> logger
+    daemon_db --> token_counter
     mcp_server --> logger
     mcp_server --> config
     mcp_server --> context_engine
@@ -79,11 +75,48 @@ graph TB
     scanner --> index
     parsers --> exceptions
     parsers --> models
+    parsers --> logger
     context_engine --> token_counter
     context_engine --> logger
+    context_engine --> embeddings
     context_engine --> config
     context_engine --> scanner
     context_engine --> import_graph
+    hooks --> git_hooks
+    core --> config
+    core --> scanner
+    core --> generator
+    core --> ai
+    core --> watcher
+    core --> knowledge_base
+    search --> scanner
+    search --> agent
+    search --> context_engine
+    search --> import_graph
+    search --> semantic_search
+    search --> stats
+    search --> knowledge_base
+    stats --> scanner
+    stats --> knowledge_base
+    __init__ --> config
+    __init__ --> logger
+    __init__ --> exceptions
+    __init__ --> core
+    __init__ --> search
+    __init__ --> knowledge
+    __init__ --> stats
+    __init__ --> hooks
+    __init__ --> mcp
+    __init__ --> agent
+    __init__ --> diff
+    knowledge --> knowledge_base
+    knowledge --> stats
+    agent --> daemon_db
+    agent --> token_counter
+    agent --> daemon
+    agent --> import_graph
+    agent --> scanner
+    mcp --> mcp_server
 ```
 
 *Generated by know*

{know_cli-0.4.2 → know_cli-0.5.0}/docs/digest-llm.md

@@ -1,27 +1,27 @@
 # Codebase Digest
 
-- {'name': 'src.know.diff', 'path': 'src/know/diff.py', 'description': 'Diff mode for tracking architectural changes safely using git worktrees.', 'function_count': 0, 'class_count': 1}
-- {'name': 'src.know.index', 'path': 'src/know/index.py', 'description': 'Index management for incremental code scanning.', 'function_count': 1, 'class_count': 1}
-- {'name': 'src.know.knowledge_base', 'path': 'src/know/knowledge_base.py', 'description': 'Knowledge base: cross-session memory for AI agents.\n\nPersists codebase understanding in a project-local SQLite database.\nSupports semantic recall (fastembed) with text-match fallback.\nEach memory is p', 'function_count': 0, 'class_count': 2}
+- {'name': 'src.know.knowledge_base', 'path': 'src/know/knowledge_base.py', 'description': 'Knowledge base: cross-session memory for AI agents.\n\nThin wrapper around DaemonDB — the single source of truth for all\nproject data. Translates between integer display IDs (used by CLI)\nand text UUIDs', 'function_count': 0, 'class_count': 2}
+- {'name': 'src.know.daemon', 'path': 'src/know/daemon.py', 'description': 'Background daemon for maintaining hot indexes.\n\nLifecycle:\n- Auto-started on first CLI call (no explicit `know start` needed)\n- Listens on Unix socket at ~/.know/sockets/<project-hash>.sock\n- PID file', 'function_count': 9, 'class_count': 2}
 - {'name': 'src.know.logger', 'path': 'src/know/logger.py', 'description': 'Logging configuration for know.', 'function_count': 2, 'class_count': 0}
-- {'name': 'src.know.models', 'path': 'src/know/models.py', 'description': 'Data models for know-cli.', 'function_count': 0, 'class_count': 4}
-- {'name': 'src.know.token_counter', 'path': 'src/know/token_counter.py', 'description': "Token counting for context budget management.\n\nUses tiktoken when available for accurate counting, falls back to\na simple word-based estimation that's fast and dependency-free.\nRoughly approximates GP", 'function_count': 4, 'class_count': 0}
 - {'name': 'src.know.ai', 'path': 'src/know/ai.py', 'description': 'AI integration for intelligent code understanding with advanced token optimization.', 'function_count': 0, 'class_count': 4}
+- {'name': 'src.know.embeddings', 'path': 'src/know/embeddings.py', 'description': 'Centralized embedding model management.\n\nSingle process-wide cache for fastembed models. All consumers\n(context_engine, semantic_search, knowledge_base) use this instead\nof maintaining separate caches', 'function_count': 3, 'class_count': 0}
+- {'name': 'src.know.diff', 'path': 'src/know/diff.py', 'description': 'Diff mode for tracking architectural changes safely using git worktrees.', 'function_count': 0, 'class_count': 1}
+- {'name': 'src.know.models', 'path': 'src/know/models.py', 'description': 'Data models for know-cli.', 'function_count': 0, 'class_count': 4}
 - {'name': 'src.know.watcher', 'path': 'src/know/watcher.py', 'description': 'File system watcher for auto-updating documentation.', 'function_count': 0, 'class_count': 2}
+- {'name': 'src.know.token_counter', 'path': 'src/know/token_counter.py', 'description': "Token counting for context budget management.\n\nUses tiktoken (cl100k_base) for accurate counting. Applies a calibration\nfactor for Anthropic models since Claude uses a different tokenizer than\nOpenAI'", 'function_count': 4, 'class_count': 0}
 - {'name': 'src.know.__init__', 'path': 'src/know/__init__.py', 'description': 'know - Living documentation generator for codebases.', 'function_count': 0, 'class_count': 0}
-- {'name': 'src.know.model_router', 'path': 'src/know/model_router.py', 'description': 'Smart model router for cost-optimized AI interactions.\n\nRoutes tasks to the cheapest model that meets quality requirements,\nenabling significant cost savings while maintaining output quality.', 'function_count': 0, 'class_count': 2}
-- {'name': 'src.know.stats', 'path': 'src/know/stats.py', 'description': 'Usage statistics tracker for know-cli.\n\nTracks every query, search, and memory operation in a project-local\nSQLite database (`.know/stats.db`).  Powers the `know stats` command.', 'function_count': 0, 'class_count': 2}
+- {'name': 'src.know.stats', 'path': 'src/know/stats.py', 'description': 'Usage statistics tracker for know-cli.\n\nTracks every query, search, and memory operation in a project-local\nSQLite database (`.know/stats.db`).  Powers the `know stats` command.', 'function_count': 0, 'class_count': 1}
+- {'name': 'src.know.index', 'path': 'src/know/index.py', 'description': 'Index management for incremental code scanning.', 'function_count': 1, 'class_count': 1}
 - {'name': 'src.know.config', 'path': 'src/know/config.py', 'description': 'Configuration management for know.', 'function_count': 1, 'class_count': 6}
-- {'name': 'src.know.generator', 'path': 'src/know/generator.py', 'description': 'Documentation generator.', 'function_count': 0, 'class_count': 1}
-- {'name': 'src.know.import_graph', 'path': 'src/know/import_graph.py', 'description': "Import graph: tracks dependencies between project modules.\n\nStores import relationships as an adjacency list in index.db.\nProvides queries for 'what does X import?' and 'what imports X?'.", 'function_count': 0, 'class_count': 1}
 - {'name': 'src.know.exceptions', 'path': 'src/know/exceptions.py', 'description': 'Custom exceptions for know-cli.', 'function_count': 0, 'class_count': 8}
 - {'name': 'src.know.git_hooks', 'path': 'src/know/git_hooks.py', 'description': 'Git hook management.', 'function_count': 0, 'class_count': 1}
-- {'name': 'src.know.mcp_server', 'path': 'src/know/mcp_server.py', 'description': "MCP (Model Context Protocol) server for know-cli.\n\nExposes know-cli's context engine, search, memory, and graph features\nas MCP tools and resources.  Works with Claude Desktop, Cursor, and any\nMCP-com", 'function_count': 5, 'class_count': 0}
+- {'name': 'src.know.import_graph', 'path': 'src/know/import_graph.py', 'description': "Import graph: tracks dependencies between project modules.\n\nDelegates storage to DaemonDB (the single source of truth).\nProvides queries for 'what does X import?' and 'what imports X?'.\n\nUses fully-qu", 'function_count': 0, 'class_count': 1}
+- {'name': 'src.know.generator', 'path': 'src/know/generator.py', 'description': 'Documentation generator.', 'function_count': 0, 'class_count': 1}
+- {'name': 'src.know.daemon_db', 'path': 'src/know/daemon_db.py', 'description': 'Unified daemon database — SQLite with FTS5 for search.\n\nStores code chunks, import graph, and cross-session memories in a\nsingle database. FTS5 provides BM25 keyword search as the default;\nvector embe', 'function_count': 0, 'class_count': 1}
 - {'name': 'src.know.semantic_search', 'path': 'src/know/semantic_search.py', 'description': 'Semantic code search using real embeddings and vector similarity.\n\nSupports both file-level (v1) and function-level (v2) embeddings.\nFunction-level uses AST to split Python files into individual chunk', 'function_count': 0, 'class_count': 2}
 - {'name': 'src.know.scanner', 'path': 'src/know/scanner.py', 'description': 'Codebase scanner for AST analysis.', 'function_count': 1, 'class_count': 1}
-- {'name': 'src.know.parsers', 'path': 'src/know/parsers.py', 'description': 'Parser strategy pattern for language-specific parsing.', 'function_count': 0, 'class_count': 5}
 
-Files: 23
-Modules: 23
+Files: 33
+Modules: 33
 
 *Set ANTHROPIC_API_KEY for AI digests*

{know_cli-0.4.2 → know_cli-0.5.0}/docs/onboarding-new-devs.md

@@ -1,13 +1,13 @@
 # Onboarding: new team members
 
 ## Structure
+- {'name': 'src.know.daemon', 'path': 'src/know/daemon.py', 'description': 'Background daemon for maintaining hot indexes.\n\nLifecycle:\n- Auto-started on first CLI call (no explicit `know start` needed)\n- Listens on Unix socket at ~/.know/sockets/<project-hash>.sock\n- PID file', 'function_count': 9, 'class_count': 2}
 - {'name': 'src.know.ai', 'path': 'src/know/ai.py', 'description': 'AI integration for intelligent code understanding with advanced token optimization.', 'function_count': 0, 'class_count': 4}
 - {'name': 'src.know.diff', 'path': 'src/know/diff.py', 'description': 'Diff mode for tracking architectural changes safely using git worktrees.', 'function_count': 0, 'class_count': 1}
-- {'name': 'src.know.knowledge_base', 'path': 'src/know/knowledge_base.py', 'description': 'Knowledge base: cross-session memory for AI agents.\n\nPersists codebase understanding in a project-local SQLite database.\nSupports semantic recall (fastembed) with text-match fallback.\nEach memory is p', 'function_count': 0, 'class_count': 2}
+- {'name': 'src.know.knowledge_base', 'path': 'src/know/knowledge_base.py', 'description': 'Knowledge base: cross-session memory for AI agents.\n\nThin wrapper around DaemonDB — the single source of truth for all\nproject data. Translates between integer display IDs (used by CLI)\nand text UUIDs', 'function_count': 0, 'class_count': 2}
 - {'name': 'src.know.index', 'path': 'src/know/index.py', 'description': 'Index management for incremental code scanning.', 'function_count': 1, 'class_count': 1}
 - {'name': 'src.know.logger', 'path': 'src/know/logger.py', 'description': 'Logging configuration for know.', 'function_count': 2, 'class_count': 0}
 - {'name': 'src.know.watcher', 'path': 'src/know/watcher.py', 'description': 'File system watcher for auto-updating documentation.', 'function_count': 0, 'class_count': 2}
-- {'name': 'src.know.models', 'path': 'src/know/models.py', 'description': 'Data models for know-cli.', 'function_count': 0, 'class_count': 4}
-- {'name': 'src.know.token_counter', 'path': 'src/know/token_counter.py', 'description': "Token counting for context budget management.\n\nUses tiktoken when available for accurate counting, falls back to\na simple word-based estimation that's fast and dependency-free.\nRoughly approximates GP", 'function_count': 4, 'class_count': 0}
+- {'name': 'src.know.embeddings', 'path': 'src/know/embeddings.py', 'description': 'Centralized embedding model management.\n\nSingle process-wide cache for fastembed models. All consumers\n(context_engine, semantic_search, knowledge_base) use this instead\nof maintaining separate caches', 'function_count': 3, 'class_count': 0}
 
 *Set ANTHROPIC_API_KEY for AI-powered guides*