Merge pull request #55 from vamplabAI/agents-config-definitions

Agents from Config

Author: EvilFreelancer

.gitignore

@@ -2,6 +2,7 @@
 
 # БЕЗОПАСНОСТЬ - API КЛЮЧИ И КОНФИДЕНЦИАЛЬНЫЕ ДАННЫЕ
 config.yaml
+agents.yaml
 *.env
 .env*
 venv/

agents.yaml.example

@@ -0,0 +1,130 @@
+# Example Custom Agents Configuration
+# =====================================
+# This file demonstrates how to define custom agents for SGR Deep Research
+
+# Notes:
+# ------
+# 1. Agent names must be unique or will be overridden
+# 2. All tools must be registered in the tool registry
+# 3. LLM, Search, Prompts, Execution, MCP settings are optional and inherit from global config
+# 4. Agents override global settings by providing their own values
+
+agents:
+  # Example 1: Simple custom research agent with overrides
+  custom_research_agent:
+    base_class: "sgr_deep_research.core.SGRAgent"
+    # Optional: Override LLM settings for this agent
+    llm:
+      model: "gpt-4o"
+      temperature: 0.3
+      max_tokens: 16000
+      # api_key: "your-custom-api-key"  # Optional: use different API key
+      # base_url: "https://api.openai.com/v1"  # Optional: use different endpoint
+      # proxy: "http://127.0.0.1:8080"  # Optional: use proxy
+
+    # Optional: Override search settings
+    search:
+      max_results: 15
+      max_pages: 8
+      content_limit: 2000
+
+    # Optional: Execution configuration
+    execution:
+      max_steps: 8
+      max_iterations: 15
+      max_clarifications: 5
+      max_searches: 6
+      mcp_context_limit: 20000
+      logs_dir: "logs/custom_agent"
+      reports_dir: "reports/custom_agent"
+
+    # Optional: MCP configuration
+    mcp:
+      mcpServers:
+        deepwiki:
+          url: "https://mcp.deepwiki.com/mcp"
+
+    # Tools this agent can use (must be registered in tool registry)
+    tools:
+      - "WebSearchTool"
+      - "ExtractPageContentTool"
+      - "CreateReportTool"
+      - "ClarificationTool"
+      - "GeneratePlanTool"
+      - "AdaptPlanTool"
+      - "FinalAnswerTool"
+
+  # Example 2: Minimal agent with defaults
+  simple_agent:
+    base_class: "SGRToolCallingResearchAgent"
+
+    # Only override what's needed
+    llm:
+      model: "gpt-4o-mini"
+
+    tools:
+      - "WebSearchTool"
+      - "FinalAnswerTool"
+
+  # Example 3: Fast research agent optimized for speed
+  fast_research_agent:
+    base_class: "SGRToolCallingAgent"
+
+    llm:
+      model: "gpt-4o-mini"
+      temperature: 0.1
+      max_tokens: 4000
+
+    execution:
+      max_steps: 4
+      max_iterations: 8
+      max_clarifications: 2
+      max_searches: 3
+
+    tools:
+      - "WebSearchTool"
+      - "CreateReportTool"
+      - "FinalAnswerTool"
+      - "ReasoningTool"
+
+  # Example 4: Specialized technical analyst with custom prompts
+  technical_analyst:
+    base_class: "SGRAgent"
+
+    llm:
+      model: "gpt-4o"
+      temperature: 0.2
+
+    prompts:
+      system_prompt: "You are a highly specialized technical analyst."
+
+    execution:
+      max_steps: 10
+      max_iterations: 20
+      max_clarifications: 3
+      max_searches: 8
+
+    tools:
+      - "WebSearchTool"
+      - "ExtractPageContentTool"
+      - "CreateReportTool"
+      - "ClarificationTool"
+      - "FinalAnswerTool"
+
+  # Example 5: Agent using inline prompts instead of files
+  inline_prompt_agent:
+    base_class: "SGRResearchAgent"
+
+    prompts:
+      system_prompt_str: |
+        You are a helpful research assistant.
+        Your goal is to provide accurate and concise information.
+      initial_user_request_str: |
+        User request: {user_request}
+        Please analyze and respond.
+      clarification_response_str: |
+        I need clarification on: {clarification_needed}
+
+    tools:
+      - "WebSearchTool"
+      - "FinalAnswerTool"

benchmark/run_simpleqa_bench.py

@@ -14,7 +14,7 @@
     grading_answer,
     save_result,
 )
-from sgr_deep_research.settings import get_config
+from sgr_deep_research.core.agent_config import GlobalConfig
 
 project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 config_path = os.path.join(project_root, "config.yaml")
@@ -29,8 +29,8 @@
 
 
 async def benchmark_agent(question, answer, model_config) -> Dict[str, Any]:
-    system_conf = get_config()
-    agent = BenchmarkAgent(task=question, max_iterations=system_conf.execution.max_steps)
+    system_conf = GlobalConfig()
+    agent = BenchmarkAgent(task=question, max_iterations=system_conf.execution.max_iterations)
 
     try:
         await agent.execute()

config.yaml.example

@@ -1,58 +1,62 @@
-# SGR Research Agent - Configuration Template
-# Production-ready configuration for Schema-Guided Reasoning
-# Copy this file to config.yaml and fill in your API keys
-
-# OpenAI API Configuration
-openai:
-  api_key: "your-openai-api-key-here"  # Required: Your OpenAI API key
-  base_url: "https://api.openai.com/v1"  # Optional: Alternative URL (e.g., for proxy LiteLLM/vLLM)
-  model: "gpt-4o-mini"                 # Model to use
-  max_tokens: 8000                     # Maximum number of tokens
-  temperature: 0.4                     # Generation temperature (0.0-1.0)
-  proxy: ""                            # Example: "socks5://127.0.0.1:1081" or "http://127.0.0.1:8080" or leave empty for no proxy
-
-# Tavily Search Configuration
-tavily:
-  api_key: "your-tavily-api-key-here"  # Required: Your Tavily API key
-  api_base_url: "https://api.tavily.com"  # Tavily API base URL
-
-# Search Settings
+# SGR Deep Research Agent - Configuration Template
+# Copy this file to config.yaml and fill in your data
+
+# LLM Configuration
+llm:
+  api_key: "your-openai-api-key-here"  # Your OpenAI API key
+  base_url: "https://api.openai.com/v1"  # API base URL
+  model: "gpt-4o-mini"  # Model name
+  max_tokens: 8000  # Max output tokens
+  temperature: 0.4  # Temperature (0.0-1.0)
+  # proxy: "socks5://127.0.0.1:1081"  # Optional proxy (socks5:// or http://)
+
+# Search Configuration (Tavily)
 search:
-  max_results: 10                      # Maximum number of search results
-
-# Scraping Settings
-scraping:
-  enabled: false                       # Enable full text scraping of found pages
-  max_pages: 5                         # Maximum pages to scrape per search
-  content_limit: 1500                  # Character limit for full content per source
+  tavily_api_key: "your-tavily-api-key-here"  # Tavily API key (get at tavily.com)
+  tavily_api_base_url: "https://api.tavily.com"  # Tavily API URL
+  max_results: 10  # Max search results
+  max_pages: 5  # Max pages to scrape
+  content_limit: 1500  # Content char limit per source
 
 # Execution Settings
 execution:
-  max_steps: 6                         # Maximum number of execution steps
-  reports_dir: "reports"               # Directory for saving reports
-  logs_dir: "logs"                     # Directory for saving reports
-
-# Prompts Settings
-prompts:
-  prompts_dir: "prompts"               # Directory with prompts
-  system_prompt_file: "system_prompt.txt"  # System prompt file
-
-# Logging Settings
-logging:
-  config_file: "logging_config.yaml"  # Logging configuration file path
-
+  max_steps: 6  # Max execution steps
+  max_clarifications: 3  # Max clarification requests
+  max_iterations: 10  # Max iterations per step
+  max_searches: 4  # Max search operations
+  mcp_context_limit: 15000  # Max context length from MCP server response
+  logs_dir: "logs"  # Directory for saving agent execution logs
+  reports_dir: "reports"  # Directory for saving agent reports
+
+# Prompts Configuration
+# prompts:
+#   # Option 1: Use file paths (absolute or relative to project root)
+#   system_prompt_file: "path/to/your/system_prompt.txt"
+#   initial_user_request_file: "path/to/your/initial_user_request.txt"
+#   clarification_response_file: "path/to/your/clarification_response.txt"
+
+#  # Option 2: Provide prompts directly as strings
+#   system_prompt_str: "Your custom system prompt here..."
+#   initial_user_request_str: "Your custom initial request template..."
+#   clarification_response_str: "Your custom clarification template..."
+
+  # Note: If both file and string are provided, string takes precedence
+
+# MCP (Model Context Protocol) Configuration
 mcp:
-
-  # Limit on the result of MCP tool invocation.
-  # A balanced constant value: not too large to avoid filling the entire context window with potentially unimportant data,
-  # yet not too small to ensure critical information from a single MCP fits through
-  context_limit: 15000
-
-  # https://gofastmcp.com/clients/transports#mcp-json-configuration-transport
-  transport_config:
-    mcpServers:
-      deepwiki:
-        url: "https://mcp.deepwiki.com/mcp"
-
-      context7:
-        url: "https://mcp.context7.com/mcp"
+  mcpServers:
+    deepwiki:
+      url: "https://mcp.deepwiki.com/mcp"
+
+    # Add more MCP servers here:
+    # your_server:
+    #   url: "https://your-mcp-server.com/mcp"
+    #   headers:
+    #     Authorization: "Bearer your-token"
+
+
+# Note: The 'agents' field is optional and can be loaded from either:
+# - This config.yaml file
+# - Any separate file by GlobalConfig.definitions_from_yaml method
+# See examples in agents.yaml.example for agent configuration options
+agents: {}

docs/WIKI.md

@@ -57,7 +57,12 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
 ```bash
 # 1. Setup configuration
 cp config.yaml.example config.yaml
-# Edit config.yaml with your API keys
+# Edit config.yaml with your configuration
+
+#Optional:
+touch agents.yaml
+# Add your agents definitions based on config.yaml and agents.yaml.example
+
 
 # 2. Change to src directory and install dependencies
 uv sync
@@ -71,7 +76,11 @@ uv run python sgr_deep_research
 ```bash
 # 1. Setup configuration
 cp config.yaml.example config.yaml
-# Edit config.yaml with your API keys
+# Edit config.yaml with your configuration
+
+#Optional:
+touch agents.yaml
+# Add your agents definitions based on config.yaml and agents.yaml.example
 
 # 2. Go to the services folder
 cd services
@@ -511,9 +520,9 @@ execution:
 
 # Prompts Settings
 prompts:
-  prompts_dir: "prompts"               # Directory with prompts
-  tool_function_prompt_file: "tool_function_prompt.txt"  # Tool function prompt file
-  system_prompt_file: "system_prompt.txt"  # System prompt file
+  system_prompt_file: "prompts/system_prompt.txt"  # Path to system prompt file
+  initial_user_request_file: "prompts/initial_user_request.txt"  # Path to initial user request file
+  clarification_response_file: "prompts/clarification_response.txt"  # Path to clarification response file
 ```
 
 ### Server Configuration

logging_config.yaml

@@ -10,18 +10,20 @@ formatters:
     format: '%(asctime)s - %(name)s - %(lineno)d - %(levelname)s - %(message)s'
 
 handlers:
-  console:
-    class: logging.StreamHandler
-    level: INFO
-    formatter: standard
-    stream: ext://sys.stdout
 
   console_error:
     class: logging.StreamHandler
     level: ERROR
     formatter: standard
     stream: ext://sys.stderr
 
+
+  console:
+    class: logging.StreamHandler
+    level: INFO
+    formatter: standard
+    stream: ext://sys.stdout
+
   file:
     class: logging.handlers.RotatingFileHandler
     level: DEBUG

pyproject.toml

@@ -46,7 +46,6 @@ dependencies = [
     "youtube-transcript-api>=0.6.0",
     # Configuration and utilities - конфигурация и утилиты
     "PyYAML>=6.0",
-    "envyaml>=1.10.0",
     "python-dateutil>=2.8.0",
     "pydantic-settings>=2.10.1",
     "fastapi>=0.116.1",

services/api_service/requirements.txt

@@ -59,8 +59,6 @@ email-validator==2.3.0
     # via
     #   jambo
     #   pydantic
-envyaml==1.10.211231
-    # via sgr-deep-research (pyproject.toml)
 exceptiongroup==1.3.0
     # via fastmcp
 fastapi==0.119.0
@@ -188,7 +186,6 @@ pytz==2025.2
 pyyaml==6.0.3
     # via
     #   sgr-deep-research (pyproject.toml)
-    #   envyaml
     #   jsonschema-path
 referencing==0.36.2
     # via
@@ -247,6 +244,8 @@ trafilatura==2.0.0
     # via sgr-deep-research (pyproject.toml)
 typing-extensions==4.15.0
     # via
+    #   anyio
+    #   exceptiongroup
     #   fastapi
     #   openai
     #   openapi-core

services/docker-compose.yml

@@ -11,6 +11,7 @@ services:
     volumes:
       - ../sgr_deep_research:/app/sgr_deep_research:ro
       - ../config.yaml:/app/config.yaml:ro
+      - ../agents.yaml:/app/agents.yaml:ro
       - ../logging_config.yaml:/app/logging_config.yaml:ro
       -  ./logs:/app/logs
       -  ./reports:/app/reports

sgr_deep_research/__init__.py

@@ -6,9 +6,8 @@
 
 from sgr_deep_research.api import *  # noqa: F403
 from sgr_deep_research.core import *  # noqa: F403
-from sgr_deep_research.services import *  # noqa: F403
 
-__version__ = "0.2.5"
+__version__ = "0.4.0"
 __author__ = "sgr-deep-research-team"