add agent instruction docs

Author: anhnh2002

README.md

@@ -139,8 +139,8 @@ codewiki generate --create-branch --github-pages --verbose
 CodeWiki supports customization for language-specific projects and documentation styles:
 
 ```bash
-# C# project: only analyze .cs files, exclude tests
-codewiki generate --include "*.cs" --exclude "*Tests*,*Specs*"
+# C# project: only analyze .cs files, exclude test directories
+codewiki generate --include "*.cs" --exclude "Tests,Specs,*.test.cs"
 
 # Focus on specific modules with architecture-style docs
 codewiki generate --focus "src/core,src/api" --doc-type architecture
@@ -149,6 +149,21 @@ codewiki generate --focus "src/core,src/api" --doc-type architecture
 codewiki generate --instructions "Focus on public APIs and include usage examples"
 ```
 
+#### Pattern Behavior (Important!)
+
+- **`--include`**: When specified, **ONLY** these patterns are used (replaces defaults completely)
+  - Example: `--include "*.cs"` will analyze ONLY `.cs` files
+  - If omitted, all supported file types are analyzed
+  - Supports glob patterns: `*.py`, `src/**/*.ts`, `*.{js,jsx}`
+  
+- **`--exclude`**: When specified, patterns are **MERGED** with default ignore patterns
+  - Example: `--exclude "Tests,Specs"` will exclude these directories AND still exclude `.git`, `__pycache__`, `node_modules`, etc.
+  - Default patterns include: `.git`, `node_modules`, `__pycache__`, `*.pyc`, `bin/`, `dist/`, and many more
+  - Supports multiple formats:
+    - Exact names: `Tests`, `.env`, `config.local`
+    - Glob patterns: `*.test.js`, `*_test.py`, `*.min.*`
+    - Directory patterns: `build/`, `dist/`, `coverage/`
+
 #### Setting Persistent Defaults
 
 Save your preferred settings as defaults:
@@ -157,8 +172,8 @@ Save your preferred settings as defaults:
 # Set include patterns for C# projects
 codewiki config agent --include "*.cs"
 
-# Exclude test projects by default
-codewiki config agent --exclude "*Tests*,*Specs*,test_*"
+# Exclude test projects by default (merged with default excludes)
+codewiki config agent --exclude "Tests,Specs,*.test.cs"
 
 # Set focus modules
 codewiki config agent --focus "src/core,src/api"
@@ -173,13 +188,13 @@ codewiki config agent
 codewiki config agent --clear
 ```
 
-| Option | Description | Example |
-|--------|-------------|---------|
-| `--include` | File patterns to include | `*.cs`, `*.py,*.pyi` |
-| `--exclude` | Patterns to exclude | `*Tests*`, `*test*,*mock*` |
-| `--focus` | Modules to document in detail | `src/core,src/api` |
-| `--doc-type` | Documentation style | `api`, `architecture`, `user-guide`, `developer` |
-| `--instructions` | Custom agent instructions | Free-form text |
+| Option | Description | Behavior | Example |
+|--------|-------------|----------|---------|
+| `--include` | File patterns to include | **Replaces** defaults | `*.cs`, `*.py`, `src/**/*.ts` |
+| `--exclude` | Patterns to exclude | **Merges** with defaults | `Tests,Specs`, `*.test.js`, `build/` |
+| `--focus` | Modules to document in detail | Standalone option | `src/core,src/api` |
+| `--doc-type` | Documentation style | Standalone option | `api`, `architecture`, `user-guide`, `developer` |
+| `--instructions` | Custom agent instructions | Standalone option | Free-form text |
 
 ### Configuration Storage
 

codewiki/src/be/agent_orchestrator.py

@@ -42,8 +42,6 @@
 from codewiki.src.be.agent_tools.generate_sub_module_documentations import generate_sub_module_documentation_tool
 from codewiki.src.be.llm_services import create_fallback_models
 from codewiki.src.be.prompt_template import (
-    SYSTEM_PROMPT,
-    LEAF_SYSTEM_PROMPT,
     format_user_prompt,
     format_system_prompt,
     format_leaf_system_prompt,
@@ -64,12 +62,11 @@ class AgentOrchestrator:
     def __init__(self, config: Config):
         self.config = config
         self.fallback_models = create_fallback_models(config)
+        self.custom_instructions = config.get_prompt_addition() if config else None
 
     def create_agent(self, module_name: str, components: Dict[str, Any], 
                     core_component_ids: List[str]) -> Agent:
         """Create an appropriate agent based on module complexity."""
-        # Get custom instructions from config
-        custom_instructions = self.config.get_prompt_addition() if self.config else None
 
         if is_complex_module(components, core_component_ids):
             return Agent(
@@ -81,15 +78,15 @@ def create_agent(self, module_name: str, components: Dict[str, Any],
                     str_replace_editor_tool, 
                     generate_sub_module_documentation_tool
                 ],
-                system_prompt=format_system_prompt(module_name, custom_instructions),
+                system_prompt=format_system_prompt(module_name, self.custom_instructions),
             )
         else:
             return Agent(
                 self.fallback_models,
                 name=module_name,
                 deps_type=CodeWikiDeps,
                 tools=[read_code_components_tool, str_replace_editor_tool],
-                system_prompt=format_leaf_system_prompt(module_name, custom_instructions),
+                system_prompt=format_leaf_system_prompt(module_name, self.custom_instructions),
             )
 
     async def process_module(self, module_name: str, components: Dict[str, Node], 
@@ -115,7 +112,8 @@ async def process_module(self, module_name: str, components: Dict[str, Node],
             module_tree=module_tree,
             max_depth=self.config.max_depth,
             current_depth=1,
-            config=self.config
+            config=self.config,
+            custom_instructions=self.custom_instructions
         )
 
         # check if overview docs already exists

codewiki/src/be/agent_tools/deps.py

@@ -13,4 +13,5 @@ class CodeWikiDeps:
     module_tree: dict[str, any]
     max_depth: int
     current_depth: int
-    config: Config  # LLM configuration
+    config: Config  # LLM configuration
+    custom_instructions: str = None

codewiki/src/be/agent_tools/generate_sub_module_documentations.py

@@ -52,15 +52,15 @@ async def generate_sub_module_documentation(
                 model=fallback_models,
                 name=sub_module_name,
                 deps_type=CodeWikiDeps,
-                system_prompt=SYSTEM_PROMPT.format(module_name=sub_module_name),
+                system_prompt=SYSTEM_PROMPT.format(module_name=sub_module_name, custom_instructions=ctx.deps.custom_instructions),
                 tools=[read_code_components_tool, str_replace_editor_tool, generate_sub_module_documentation_tool],
             )
         else:
             sub_agent = Agent(
                 model=fallback_models,
                 name=sub_module_name,
                 deps_type=CodeWikiDeps,
-                system_prompt=LEAF_SYSTEM_PROMPT.format(module_name=sub_module_name),
+                system_prompt=LEAF_SYSTEM_PROMPT.format(module_name=sub_module_name, custom_instructions=ctx.deps.custom_instructions),
                 tools=[read_code_components_tool, str_replace_editor_tool],
             )
 

codewiki/src/be/dependency_analyzer/analysis/repo_analyzer.py

@@ -19,9 +19,11 @@ def __init__(
         include_patterns: Optional[List[str]] = None,
         exclude_patterns: Optional[List[str]] = None,
     ) -> None:
+        # Include patterns: if specified, use ONLY those patterns (replaces defaults)
         self.include_patterns = (
             include_patterns if include_patterns is not None else DEFAULT_INCLUDE_PATTERNS
         )
+        # Exclude patterns: if specified, MERGE with default ignore patterns
         self.exclude_patterns = (
             list(DEFAULT_IGNORE_PATTERNS) + exclude_patterns
             if exclude_patterns is not None

codewiki/src/fe/background_worker.py

@@ -16,7 +16,7 @@
 from dataclasses import asdict
 
 from codewiki.src.be.documentation_generator import DocumentationGenerator
-from codewiki.src.config import Config
+from codewiki.src.config import Config, MAIN_MODEL
 from .models import JobStatus
 from .cache_manager import CacheManager
 from .github_processor import GitHubRepoProcessor