feat(forge): Component-specific configuration (#7170)

Remove many env vars and use component-level configuration that could be loaded from file instead.

### Changed

- `BaseAgent` provides `serialize_configs` and `deserialize_configs` that can save and load all component configuration as json `str`. Deserialized components/values overwrite existing values, so not all values need to be present in the serialized config.
- Decoupled `forge/content_processing/text.py` from `Config`
- Kept `execute_local_commands` in `Config` because it's needed to know if OS info should be included in the prompt
- Updated docs to reflect changes
- Renamed `Config` to `AppConfig`

### Added

- Added `ConfigurableComponent` class for components and following configs:
  - `ActionHistoryConfiguration`
  - `CodeExecutorConfiguration`
  - `FileManagerConfiguration` - now file manager allows to have multiple agents using the same workspace
  - `GitOperationsConfiguration`
  - `ImageGeneratorConfiguration`
  - `WebSearchConfiguration`
  - `WebSeleniumConfiguration`
- `BaseConfig` in `forge` and moved `Config` (now inherits from `BaseConfig`) back to `autogpt`
- Required `config_class` attribute for the `ConfigurableComponent` class that should be set to configuration class for a component
`--component-config-file` CLI option and `COMPONENT_CONFIG_FILE` env var and field in `Config`. This option allows to load configuration from a specific file, CLI option takes precedence over env var.
- Added comments to config models

### Removed

- Unused `change_agent_id` method from `FileManagerComponent`
- Unused `allow_downloads` from `Config` and CLI options (it should be in web component config if needed)
- CLI option `--browser-name` (the option is inside `WebSeleniumConfiguration`)
- Unused `workspace_directory` from CLI options
- No longer needed variables from `Config` and docs
- Unused fields from `Config`: `image_size`, `audio_to_text_provider`, `huggingface_audio_to_text_model`
- Removed `files` and `workspace` class attributes from `FileManagerComponent`

autogpt/.env.template

@@ -15,8 +15,8 @@
 ##   This helps us to spot and solve problems earlier & faster. (Default: DISABLED)
 # TELEMETRY_OPT_IN=true
 
-## EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False)
+## COMPONENT_CONFIG_FILE - Path to the json config file (Default: None)
-# EXECUTE_LOCAL_COMMANDS=False
+# COMPONENT_CONFIG_FILE=
 
 ### Workspace ###
 
@@ -44,9 +44,6 @@
 
 ### Miscellaneous ###
 
-## USER_AGENT - Define the user-agent used by the requests library to browse website (string)
-# USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
-
 ## AUTHORISE COMMAND KEY - Key to authorise commands
 # AUTHORISE_COMMAND_KEY=y
 
@@ -96,38 +93,12 @@
 ## EMBEDDING_MODEL - Model to use for creating embeddings
 # EMBEDDING_MODEL=text-embedding-3-small
 
-################################################################################
-### SHELL EXECUTION
-################################################################################
-
-## SHELL_COMMAND_CONTROL - Whether to use "allowlist" or "denylist" to determine what shell commands can be executed (Default: denylist)
-# SHELL_COMMAND_CONTROL=denylist
-
-## ONLY if SHELL_COMMAND_CONTROL is set to denylist:
-## SHELL_DENYLIST - List of shell commands that ARE NOT allowed to be executed by AutoGPT (Default: sudo,su)
-# SHELL_DENYLIST=sudo,su
-
-## ONLY if SHELL_COMMAND_CONTROL is set to allowlist:
-## SHELL_ALLOWLIST - List of shell commands that ARE allowed to be executed by AutoGPT (Default: None)
-# SHELL_ALLOWLIST=
-
 ################################################################################
 ### IMAGE GENERATION PROVIDER
 ################################################################################
 
-### Common
-
-## IMAGE_PROVIDER - Image provider (Default: dalle)
-# IMAGE_PROVIDER=dalle
-
-## IMAGE_SIZE - Image size (Default: 256)
-# IMAGE_SIZE=256
-
 ### Huggingface (IMAGE_PROVIDER=huggingface)
 
-## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)
-# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4
-
 ## HUGGINGFACE_API_TOKEN - HuggingFace API token (Default: None)
 # HUGGINGFACE_API_TOKEN=
 
@@ -136,19 +107,6 @@
 ## SD_WEBUI_AUTH - Stable Diffusion Web UI username:password pair (Default: None)
 # SD_WEBUI_AUTH=
 
-## SD_WEBUI_URL - Stable Diffusion Web UI API URL (Default: http://localhost:7860)
-# SD_WEBUI_URL=http://localhost:7860
-
-################################################################################
-### AUDIO TO TEXT PROVIDER
-################################################################################
-
-## AUDIO_TO_TEXT_PROVIDER - Audio-to-text provider (Default: huggingface)
-# AUDIO_TO_TEXT_PROVIDER=huggingface
-
-## HUGGINGFACE_AUDIO_TO_TEXT_MODEL - The model for HuggingFace to use (Default: CompVis/stable-diffusion-v1-4)
-# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=CompVis/stable-diffusion-v1-4
-
 ################################################################################
 ### GITHUB
 ################################################################################
@@ -163,18 +121,6 @@
 ### WEB BROWSING
 ################################################################################
 
-## HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True)
-# HEADLESS_BROWSER=True
-
-## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome)
-# USE_WEB_BROWSER=chrome
-
-## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (Default: 3000)
-# BROWSE_CHUNK_MAX_LENGTH=3000
-
-## BROWSE_SPACY_LANGUAGE_MODEL - spaCy language model](https://spacy.io/usage/models) to use when creating chunks. (Default: en_core_web_sm)
-# BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm
-
 ## GOOGLE_API_KEY - Google API key (Default: None)
 # GOOGLE_API_KEY=
 
@@ -198,13 +144,6 @@
 ## ELEVENLABS_VOICE_ID - Eleven Labs voice ID (Example: None)
 # ELEVENLABS_VOICE_ID=
 
-################################################################################
-### CHAT MESSAGES
-################################################################################
-
-## CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)
-# CHAT_MESSAGES_ENABLED=False
-
 ################################################################################
 ### LOGGING
 ################################################################################

autogpt/README.md

@@ -68,10 +68,6 @@ Options:
                                   continuous mode
   --speak                         Enable Speak Mode
   --debug                         Enable Debug Mode
-  -b, --browser-name TEXT         Specifies which web-browser to use when
-                                  using selenium to scrape the web.
-  --allow-downloads               Dangerous: Allows AutoGPT to download files
-                                  natively.
   --skip-news                     Specifies whether to suppress the output of
                                   latest news on startup.
   --install-plugin-deps           Installs external dependencies for 3rd party
@@ -90,6 +86,7 @@ Options:
   --override-directives           If specified, --constraint, --resource and
                                   --best-practice will override the AI's
                                   directives instead of being appended to them
+  --component-config-file TEXT    Path to the json configuration file.
   --help                          Show this message and exit.
 ```
 </details>
@@ -111,10 +108,6 @@ Usage: python -m autogpt serve [OPTIONS]
 
 Options:
   --debug                     Enable Debug Mode
-  -b, --browser-name TEXT     Specifies which web-browser to use when using
-                              selenium to scrape the web.
-  --allow-downloads           Dangerous: Allows AutoGPT to download files
-                              natively.
   --install-plugin-deps       Installs external dependencies for 3rd party
                               plugins.
   --help                      Show this message and exit.

autogpt/autogpt/agent_factory/configurators.py

@@ -2,17 +2,17 @@ from typing import Optional
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config
 from forge.file_storage.base import FileStorage
 from forge.llm.providers import MultiProvider
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
+from autogpt.app.config import AppConfig
 
 
 def create_agent(
     agent_id: str,
     task: str,
-    app_config: Config,
+    app_config: AppConfig,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
     ai_profile: Optional[AIProfile] = None,
@@ -38,7 +38,7 @@ def create_agent(
 
 def configure_agent_with_state(
     state: AgentSettings,
-    app_config: Config,
+    app_config: AppConfig,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
 ) -> Agent:
@@ -51,7 +51,7 @@ def configure_agent_with_state(
 
 
 def _configure_agent(
-    app_config: Config,
+    app_config: AppConfig,
     llm_provider: MultiProvider,
     file_storage: FileStorage,
     agent_id: str = "",
@@ -80,7 +80,7 @@ def _configure_agent(
         settings=agent_state,
         llm_provider=llm_provider,
         file_storage=file_storage,
-        legacy_config=app_config,
+        app_config=app_config,
     )
 
 
@@ -89,7 +89,7 @@ def create_agent_state(
     task: str,
     ai_profile: AIProfile,
     directives: AIDirectives,
-    app_config: Config,
+    app_config: AppConfig,
 ) -> AgentSettings:
     return AgentSettings(
         agent_id=agent_id,

autogpt/autogpt/agent_factory/generators.py

@@ -6,7 +6,7 @@ from forge.file_storage.base import FileStorage
 
 if TYPE_CHECKING:
     from autogpt.agents.agent import Agent
-    from forge.config.config import Config
+    from autogpt.app.config import AppConfig
     from forge.llm.providers import MultiProvider
 
 from .configurators import _configure_agent
@@ -16,7 +16,7 @@ from .profile_generator import generate_agent_profile_for_task
 async def generate_agent_for_task(
     agent_id: str,
     task: str,
-    app_config: Config,
+    app_config: AppConfig,
     file_storage: FileStorage,
     llm_provider: MultiProvider,
 ) -> Agent:

autogpt/autogpt/agent_factory/profile_generator.py

@@ -3,7 +3,6 @@ import logging
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config
 from forge.llm.prompting import ChatPrompt, LanguageModelClassification, PromptStrategy
 from forge.llm.providers import MultiProvider
 from forge.llm.providers.schema import (
@@ -14,6 +13,8 @@ from forge.llm.providers.schema import (
 from forge.models.config import SystemConfiguration, UserConfigurable
 from forge.models.json_schema import JSONSchema
 
+from autogpt.app.config import AppConfig
+
 logger = logging.getLogger(__name__)
 
 
@@ -212,7 +213,7 @@ class AgentProfileGenerator(PromptStrategy):
 
 async def generate_agent_profile_for_task(
     task: str,
-    app_config: Config,
+    app_config: AppConfig,
     llm_provider: MultiProvider,
 ) -> tuple[AIProfile, AIDirectives]:
     """Generates an AIConfig object from the given string.

autogpt/autogpt/agents/README.md

@@ -26,10 +26,10 @@ class MyAgent(Agent):
         settings: AgentSettings,
         llm_provider: MultiProvider
         file_storage: FileStorage,
-        legacy_config: Config,
+        app_config: AppConfig,
     ):
         # Call the parent constructor to bring in the default components
-        super().__init__(settings, llm_provider, file_storage, legacy_config)
+        super().__init__(settings, llm_provider, file_storage, app_config)
         # Add your custom component
         self.my_component = MyComponent()
 ```

autogpt/autogpt/agents/agent.py

@@ -18,7 +18,11 @@ from forge.components.action_history import (
     ActionHistoryComponent,
     EpisodicActionHistory,
 )
-from forge.components.code_executor.code_executor import CodeExecutorComponent
+from forge.components.action_history.action_history import ActionHistoryConfiguration
+from forge.components.code_executor.code_executor import (
+    CodeExecutorComponent,
+    CodeExecutorConfiguration,
+)
 from forge.components.context.context import AgentContext, ContextComponent
 from forge.components.file_manager import FileManagerComponent
 from forge.components.git_operations import GitOperationsComponent
@@ -58,7 +62,7 @@ from .prompt_strategies.one_shot import (
 )
 
 if TYPE_CHECKING:
-    from forge.config.config import Config
+    from autogpt.app.config import AppConfig
 
 logger = logging.getLogger(__name__)
 
@@ -91,7 +95,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         settings: AgentSettings,
         llm_provider: MultiProvider,
         file_storage: FileStorage,
-        legacy_config: Config,
+        app_config: AppConfig,
     ):
         super().__init__(settings)
 
@@ -109,31 +113,35 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
         self.system = SystemComponent()
         self.history = ActionHistoryComponent(
             settings.history,
-            self.send_token_limit,
             lambda x: self.llm_provider.count_tokens(x, self.llm.name),
-            legacy_config,
             llm_provider,
+            ActionHistoryConfiguration(
+                model_name=app_config.fast_llm, max_tokens=self.send_token_limit
+            ),
         ).run_after(WatchdogComponent)
-        self.user_interaction = UserInteractionComponent(legacy_config)
+        if not app_config.noninteractive_mode:
-        self.file_manager = FileManagerComponent(settings, file_storage)
+            self.user_interaction = UserInteractionComponent()
+        self.file_manager = FileManagerComponent(file_storage, settings)
         self.code_executor = CodeExecutorComponent(
             self.file_manager.workspace,
-            settings,
+            CodeExecutorConfiguration(
-            legacy_config,
+                docker_container_name=f"{settings.agent_id}_sandbox"
+            ),
         )
-        self.git_ops = GitOperationsComponent(legacy_config)
+        self.git_ops = GitOperationsComponent()
-        self.image_gen = ImageGeneratorComponent(
+        self.image_gen = ImageGeneratorComponent(self.file_manager.workspace)
-            self.file_manager.workspace, legacy_config
+        self.web_search = WebSearchComponent()
+        self.web_selenium = WebSeleniumComponent(
+            llm_provider,
+            app_config.app_data_dir,
         )
-        self.web_search = WebSearchComponent(legacy_config)
-        self.web_selenium = WebSeleniumComponent(legacy_config, llm_provider, self.llm)
         self.context = ContextComponent(self.file_manager.workspace, settings.context)
         self.watchdog = WatchdogComponent(settings.config, settings.history).run_after(
             ContextComponent
         )
 
         self.event_history = settings.history
-        self.legacy_config = legacy_config
+        self.app_config = app_config
 
     async def propose_action(self) -> OneShotAgentActionProposal:
         """Proposes the next action to execute, based on the task and current state.
@@ -166,7 +174,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
             ai_profile=self.state.ai_profile,
             ai_directives=directives,
             commands=function_specs_from_commands(self.commands),
-            include_os_info=self.legacy_config.execute_local_commands,
+            include_os_info=self.code_executor.config.execute_local_commands,
         )
 
         logger.debug(f"Executing prompt:\n{dump_prompt(prompt)}")
@@ -277,7 +285,7 @@ class Agent(BaseAgent[OneShotAgentActionProposal], Configurable[AgentSettings]):
             command
             for command in self.commands
             if not any(
-                name in self.legacy_config.disabled_commands for name in command.names
+                name in self.app_config.disabled_commands for name in command.names
             )
         ]
 

autogpt/autogpt/app/agent_protocol_server.py

@@ -23,7 +23,6 @@ from forge.agent_protocol.models import (
     TaskRequestBody,
     TaskStepsListResponse,
 )
-from forge.config.config import Config
 from forge.file_storage import FileStorage
 from forge.llm.providers import ModelProviderBudget, MultiProvider
 from forge.models.action import ActionErrorResult, ActionSuccessResult
@@ -35,6 +34,7 @@ from sentry_sdk import set_user
 
 from autogpt.agent_factory.configurators import configure_agent_with_state, create_agent
 from autogpt.agents.agent_manager import AgentManager
+from autogpt.app.config import AppConfig
 from autogpt.app.utils import is_port_free
 
 logger = logging.getLogger(__name__)
@@ -45,7 +45,7 @@ class AgentProtocolServer:
 
     def __init__(
         self,
-        app_config: Config,
+        app_config: AppConfig,
         database: AgentDB,
         file_storage: FileStorage,
         llm_provider: MultiProvider,

autogpt/autogpt/app/cli.py

@@ -28,24 +28,6 @@ def cli(ctx: click.Context):
     help="Defines the number of times to run in continuous mode",
 )
 @click.option("--speak", is_flag=True, help="Enable Speak Mode")
-@click.option(
-    "-b",
-    "--browser-name",
-    help="Specifies which web-browser to use when using selenium to scrape the web.",
-)
-@click.option(
-    "--allow-downloads",
-    is_flag=True,
-    help="Dangerous: Allows AutoGPT to download files natively.",
-)
-@click.option(
-    # TODO: this is a hidden option for now, necessary for integration testing.
-    # We should make this public once we're ready to roll out agent specific workspaces.
-    "--workspace-directory",
-    "-w",
-    type=click.Path(file_okay=False),
-    hidden=True,
-)
 @click.option(
     "--install-plugin-deps",
     is_flag=True,
@@ -128,13 +110,15 @@ def cli(ctx: click.Context):
     ),
     type=click.Choice([i.value for i in LogFormatName]),
 )
+@click.option(
+    "--component-config-file",
+    help="Path to a json configuration file",
+    type=click.Path(exists=True, dir_okay=False, resolve_path=True),
+)
 def run(
     continuous: bool,
     continuous_limit: Optional[int],
     speak: bool,
-    browser_name: Optional[str],
-    allow_downloads: bool,
-    workspace_directory: Optional[Path],
     install_plugin_deps: bool,
     skip_news: bool,
     skip_reprompt: bool,
@@ -148,6 +132,7 @@ def run(
     log_level: Optional[str],
     log_format: Optional[str],
     log_file_format: Optional[str],
+    component_config_file: Optional[Path],
 ) -> None:
     """
     Sets up and runs an agent, based on the task specified by the user, or resumes an
@@ -165,10 +150,7 @@ def run(
         log_level=log_level,
         log_format=log_format,
         log_file_format=log_file_format,
-        browser_name=browser_name,
-        allow_downloads=allow_downloads,
         skip_news=skip_news,
-        workspace_directory=workspace_directory,
         install_plugin_deps=install_plugin_deps,
         override_ai_name=ai_name,
         override_ai_role=ai_role,
@@ -176,20 +158,11 @@ def run(
         constraints=list(constraint),
         best_practices=list(best_practice),
         override_directives=override_directives,
+        component_config_file=component_config_file,
     )
 
 
 @cli.command()
-@click.option(
-    "-b",
-    "--browser-name",
-    help="Specifies which web-browser to use when using selenium to scrape the web.",
-)
-@click.option(
-    "--allow-downloads",
-    is_flag=True,
-    help="Dangerous: Allows AutoGPT to download files natively.",
-)
 @click.option(
     "--install-plugin-deps",
     is_flag=True,
@@ -217,8 +190,6 @@ def run(
     type=click.Choice([i.value for i in LogFormatName]),
 )
 def serve(
-    browser_name: Optional[str],
-    allow_downloads: bool,
     install_plugin_deps: bool,
     debug: bool,
     log_level: Optional[str],
@@ -237,8 +208,6 @@ def serve(
         log_level=log_level,
         log_format=log_format,
         log_file_format=log_file_format,
-        browser_name=browser_name,
-        allow_downloads=allow_downloads,
         install_plugin_deps=install_plugin_deps,
     )
 

autogpt/autogpt/app/config.py

@@ -7,15 +7,13 @@ import re
 from pathlib import Path
 from typing import Any, Optional, Union
 
-from pydantic import SecretStr, validator
-
 import forge
-from forge.file_storage import FileStorageBackendName
+from forge.config.base import BaseConfig
 from forge.llm.providers import CHAT_MODELS, ModelName
 from forge.llm.providers.openai import OpenAICredentials, OpenAIModelName
 from forge.logging.config import LoggingConfig
-from forge.models.config import Configurable, SystemSettings, UserConfigurable
+from forge.models.config import Configurable, UserConfigurable
-from forge.speech.say import TTSConfig
+from pydantic import SecretStr, validator
 
 logger = logging.getLogger(__name__)
 
@@ -26,7 +24,7 @@ GPT_4_MODEL = OpenAIModelName.GPT4
 GPT_3_MODEL = OpenAIModelName.GPT3
 
 
-class Config(SystemSettings, arbitrary_types_allowed=True):
+class AppConfig(BaseConfig):
     name: str = "Auto-GPT configuration"
     description: str = "Default configuration for the Auto-GPT application."
 
@@ -40,14 +38,9 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
     authorise_key: str = UserConfigurable(default="y", from_env="AUTHORISE_COMMAND_KEY")
     exit_key: str = UserConfigurable(default="n", from_env="EXIT_KEY")
     noninteractive_mode: bool = False
-
-    # TTS configuration
     logging: LoggingConfig = LoggingConfig()
-    tts_config: TTSConfig = TTSConfig()
+    component_config_file: Optional[Path] = UserConfigurable(
-
+        default=None, from_env="COMPONENT_CONFIG_FILE"
-    # File storage
-    file_storage_backend: FileStorageBackendName = UserConfigurable(
-        default=FileStorageBackendName.LOCAL, from_env="FILE_STORAGE_BACKEND"
     )
 
     ##########################
@@ -69,9 +62,6 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
     embedding_model: str = UserConfigurable(
         default="text-embedding-3-small", from_env="EMBEDDING_MODEL"
     )
-    browse_spacy_language_model: str = UserConfigurable(
-        default="en_core_web_sm", from_env="BROWSE_SPACY_LANGUAGE_MODEL"
-    )
 
     # Run loop configuration
     continuous_mode: bool = False
@@ -91,56 +81,6 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
         default=True,
         from_env=lambda: os.getenv("RESTRICT_TO_WORKSPACE", "True") == "True",
     )
-    allow_downloads: bool = False
-
-    # Shell commands
-    shell_command_control: str = UserConfigurable(
-        default="denylist", from_env="SHELL_COMMAND_CONTROL"
-    )
-    execute_local_commands: bool = UserConfigurable(
-        default=False,
-        from_env=lambda: os.getenv("EXECUTE_LOCAL_COMMANDS", "False") == "True",
-    )
-    shell_denylist: list[str] = UserConfigurable(
-        default_factory=lambda: ["sudo", "su"],
-        from_env=lambda: _safe_split(
-            os.getenv("SHELL_DENYLIST", os.getenv("DENY_COMMANDS"))
-        ),
-    )
-    shell_allowlist: list[str] = UserConfigurable(
-        default_factory=list,
-        from_env=lambda: _safe_split(
-            os.getenv("SHELL_ALLOWLIST", os.getenv("ALLOW_COMMANDS"))
-        ),
-    )
-
-    # Text to image
-    image_provider: Optional[str] = UserConfigurable(from_env="IMAGE_PROVIDER")
-    huggingface_image_model: str = UserConfigurable(
-        default="CompVis/stable-diffusion-v1-4", from_env="HUGGINGFACE_IMAGE_MODEL"
-    )
-    sd_webui_url: Optional[str] = UserConfigurable(
-        default="http://localhost:7860", from_env="SD_WEBUI_URL"
-    )
-    image_size: int = UserConfigurable(default=256, from_env="IMAGE_SIZE")
-
-    # Audio to text
-    audio_to_text_provider: str = UserConfigurable(
-        default="huggingface", from_env="AUDIO_TO_TEXT_PROVIDER"
-    )
-    huggingface_audio_to_text_model: Optional[str] = UserConfigurable(
-        from_env="HUGGINGFACE_AUDIO_TO_TEXT_MODEL"
-    )
-
-    # Web browsing
-    selenium_web_browser: str = UserConfigurable("chrome", from_env="USE_WEB_BROWSER")
-    selenium_headless: bool = UserConfigurable(
-        default=True, from_env=lambda: os.getenv("HEADLESS_BROWSER", "True") == "True"
-    )
-    user_agent: str = UserConfigurable(
-        default="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",  # noqa: E501
-        from_env="USER_AGENT",
-    )
 
     ###############
     # Credentials #
@@ -151,24 +91,6 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
         default=AZURE_CONFIG_FILE, from_env="AZURE_CONFIG_FILE"
     )
 
-    # Github
-    github_api_key: Optional[str] = UserConfigurable(from_env="GITHUB_API_KEY")
-    github_username: Optional[str] = UserConfigurable(from_env="GITHUB_USERNAME")
-
-    # Google
-    google_api_key: Optional[str] = UserConfigurable(from_env="GOOGLE_API_KEY")
-    google_custom_search_engine_id: Optional[str] = UserConfigurable(
-        from_env="GOOGLE_CUSTOM_SEARCH_ENGINE_ID",
-    )
-
-    # Huggingface
-    huggingface_api_token: Optional[str] = UserConfigurable(
-        from_env="HUGGINGFACE_API_TOKEN"
-    )
-
-    # Stable Diffusion
-    sd_webui_auth: Optional[str] = UserConfigurable(from_env="SD_WEBUI_AUTH")
-
     @validator("openai_functions")
     def validate_openai_functions(cls, v: bool, values: dict[str, Any]):
         if v:
@@ -180,11 +102,11 @@ class Config(SystemSettings, arbitrary_types_allowed=True):
         return v
 
 
-class ConfigBuilder(Configurable[Config]):
+class ConfigBuilder(Configurable[AppConfig]):
-    default_settings = Config()
+    default_settings = AppConfig()
 
     @classmethod
-    def build_config_from_env(cls, project_root: Path = PROJECT_ROOT) -> Config:
+    def build_config_from_env(cls, project_root: Path = PROJECT_ROOT) -> AppConfig:
         """Initialize the Config class"""
 
         config = cls.build_agent_configuration()
@@ -206,14 +128,13 @@ class ConfigBuilder(Configurable[Config]):
         return config
 
 
-async def assert_config_has_required_llm_api_keys(config: Config) -> None:
+async def assert_config_has_required_llm_api_keys(config: AppConfig) -> None:
     """
     Check if API keys (if required) are set for the configured SMART_LLM and FAST_LLM.
     """
-    from pydantic import ValidationError
-
     from forge.llm.providers.anthropic import AnthropicModelName
     from forge.llm.providers.groq import GroqModelName
+    from pydantic import ValidationError
 
     if set((config.smart_llm, config.fast_llm)).intersection(AnthropicModelName):
         from forge.llm.providers.anthropic import AnthropicCredentials
@@ -243,9 +164,8 @@ async def assert_config_has_required_llm_api_keys(config: Config) -> None:
             )
 
     if set((config.smart_llm, config.fast_llm)).intersection(GroqModelName):
-        from groq import AuthenticationError
-
         from forge.llm.providers.groq import GroqProvider
+        from groq import AuthenticationError
 
         try:
             groq = GroqProvider()
@@ -268,9 +188,8 @@ async def assert_config_has_required_llm_api_keys(config: Config) -> None:
             raise ValueError("Groq is unavailable: invalid API key") from e
 
     if set((config.smart_llm, config.fast_llm)).intersection(OpenAIModelName):
-        from openai import AuthenticationError
-
         from forge.llm.providers.openai import OpenAIProvider
+        from openai import AuthenticationError
 
         try:
             openai = OpenAIProvider()

autogpt/autogpt/app/configurator.py

@@ -5,20 +5,18 @@ import logging
 from typing import Literal, Optional
 
 import click
-from colorama import Back, Style
-from forge.config.config import GPT_3_MODEL, Config
 from forge.llm.providers import ModelName, MultiProvider
 
+from autogpt.app.config import GPT_3_MODEL, AppConfig
+
 logger = logging.getLogger(__name__)
 
 
 async def apply_overrides_to_config(
-    config: Config,
+    config: AppConfig,
     continuous: bool = False,
     continuous_limit: Optional[int] = None,
     skip_reprompt: bool = False,
-    browser_name: Optional[str] = None,
-    allow_downloads: bool = False,
     skip_news: bool = False,
 ) -> None:
     """Updates the config object with the given arguments.
@@ -33,8 +31,6 @@ async def apply_overrides_to_config(
         log_level (int): The global log level for the application.
         log_format (str): The format for the log(s).
         log_file_format (str): Override the format for the log file.
-        browser_name (str): The name of the browser to use for scraping the web.
-        allow_downloads (bool): Whether to allow AutoGPT to download files natively.
         skips_news (bool): Whether to suppress the output of latest news on startup.
     """
     config.continuous_mode = False
@@ -61,23 +57,6 @@ async def apply_overrides_to_config(
     if skip_reprompt:
         config.skip_reprompt = True
 
-    if browser_name:
-        config.selenium_web_browser = browser_name
-
-    if allow_downloads:
-        logger.warning(
-            msg=f"{Back.LIGHTYELLOW_EX}"
-            "AutoGPT will now be able to download and save files to your machine."
-            f"{Back.RESET}"
-            " It is recommended that you monitor any files it downloads carefully.",
-        )
-        logger.warning(
-            msg=f"{Back.RED + Style.BRIGHT}"
-            "NEVER OPEN FILES YOU AREN'T SURE OF!"
-            f"{Style.RESET_ALL}",
-        )
-        config.allow_downloads = True
-
     if skip_news:
         config.skip_news = True
 

autogpt/autogpt/app/main.py

@@ -21,11 +21,6 @@ from forge.components.code_executor.code_executor import (
 )
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
-from forge.config.config import (
-    Config,
-    ConfigBuilder,
-    assert_config_has_required_llm_api_keys,
-)
 from forge.file_storage import FileStorageBackendName, get_storage
 from forge.llm.providers import MultiProvider
 from forge.logging.config import configure_logging
@@ -38,6 +33,11 @@ from forge.utils.exceptions import AgentTerminated, InvalidAgentResponseError
 from autogpt.agent_factory.configurators import configure_agent_with_state, create_agent
 from autogpt.agents.agent_manager import AgentManager
 from autogpt.agents.prompt_strategies.one_shot import AssistantThoughts
+from autogpt.app.config import (
+    AppConfig,
+    ConfigBuilder,
+    assert_config_has_required_llm_api_keys,
+)
 
 if TYPE_CHECKING:
     from autogpt.agents.agent import Agent
@@ -66,10 +66,7 @@ async def run_auto_gpt(
     log_level: Optional[str] = None,
     log_format: Optional[str] = None,
     log_file_format: Optional[str] = None,
-    browser_name: Optional[str] = None,
-    allow_downloads: bool = False,
     skip_news: bool = False,
-    workspace_directory: Optional[Path] = None,
     install_plugin_deps: bool = False,
     override_ai_name: Optional[str] = None,
     override_ai_role: Optional[str] = None,
@@ -77,6 +74,7 @@ async def run_auto_gpt(
     constraints: Optional[list[str]] = None,
     best_practices: Optional[list[str]] = None,
     override_directives: bool = False,
+    component_config_file: Optional[Path] = None,
 ):
     # Set up configuration
     config = ConfigBuilder.build_config_from_env()
@@ -109,8 +107,6 @@ async def run_auto_gpt(
         continuous=continuous,
         continuous_limit=continuous_limit,
         skip_reprompt=skip_reprompt,
-        browser_name=browser_name,
-        allow_downloads=allow_downloads,
         skip_news=skip_news,
     )
 
@@ -135,15 +131,12 @@ async def run_auto_gpt(
         print_python_version_info(logger)
         print_attribute("Smart LLM", config.smart_llm)
         print_attribute("Fast LLM", config.fast_llm)
-        print_attribute("Browser", config.selenium_web_browser)
         if config.continuous_mode:
             print_attribute("Continuous Mode", "ENABLED", title_color=Fore.YELLOW)
             if continuous_limit:
                 print_attribute("Continuous Limit", config.continuous_limit)
         if config.tts_config.speak_mode:
             print_attribute("Speak Mode", "ENABLED")
-        if config.allow_downloads:
-            print_attribute("Native Downloading", "ENABLED")
         if we_are_running_in_a_docker_container() or is_docker_available():
             print_attribute("Code Execution", "ENABLED")
         else:
@@ -330,6 +323,14 @@ async def run_auto_gpt(
         #     )
         # ).add_done_callback(update_agent_directives)
 
+    # Load component configuration from file
+    if _config_file := component_config_file or config.component_config_file:
+        try:
+            logger.info(f"Loading component configuration from {_config_file}")
+            agent.load_component_configs(_config_file.read_text())
+        except Exception as e:
+            logger.error(f"Could not load component configuration: {e}")
+
     #################
     # Run the Agent #
     #################
@@ -356,8 +357,6 @@ async def run_auto_gpt_server(
     log_level: Optional[str] = None,
     log_format: Optional[str] = None,
     log_file_format: Optional[str] = None,
-    browser_name: Optional[str] = None,
-    allow_downloads: bool = False,
     install_plugin_deps: bool = False,
 ):
     from .agent_protocol_server import AgentProtocolServer
@@ -387,8 +386,6 @@ async def run_auto_gpt_server(
 
     await apply_overrides_to_config(
         config=config,
-        browser_name=browser_name,
-        allow_downloads=allow_downloads,
     )
 
     llm_provider = _configure_llm_provider(config)
@@ -413,7 +410,7 @@ async def run_auto_gpt_server(
     )
 
 
-def _configure_llm_provider(config: Config) -> MultiProvider:
+def _configure_llm_provider(config: AppConfig) -> MultiProvider:
     multi_provider = MultiProvider()
     for model in [config.smart_llm, config.fast_llm]:
         # Ensure model providers for configured LLMs are available
@@ -453,15 +450,15 @@ async def run_interaction_loop(
         None
     """
     # These contain both application config and agent config, so grab them here.
-    legacy_config = agent.legacy_config
+    app_config = agent.app_config
     ai_profile = agent.state.ai_profile
     logger = logging.getLogger(__name__)
 
     cycle_budget = cycles_remaining = _get_cycle_budget(
-        legacy_config.continuous_mode, legacy_config.continuous_limit
+        app_config.continuous_mode, app_config.continuous_limit
     )
     spinner = Spinner(
-        "Thinking...", plain_output=legacy_config.logging.plain_console_output
+        "Thinking...", plain_output=app_config.logging.plain_console_output
     )
     stop_reason = None
 
@@ -539,7 +536,7 @@ async def run_interaction_loop(
         update_user(
             ai_profile,
             action_proposal,
-            speak_mode=legacy_config.tts_config.speak_mode,
+            speak_mode=app_config.tts_config.speak_mode,
         )
 
         ##################
@@ -548,7 +545,7 @@ async def run_interaction_loop(
         handle_stop_signal()
         if cycles_remaining == 1:  # Last cycle
             feedback_type, feedback, new_cycles_remaining = await get_user_feedback(
-                legacy_config,
+                app_config,
                 ai_profile,
             )
 
@@ -659,7 +656,7 @@ def update_user(
 
 
 async def get_user_feedback(
-    config: Config,
+    config: AppConfig,
     ai_profile: AIProfile,
 ) -> tuple[UserFeedback, str, int | None]:
     """Gets the user's feedback on the assistant's reply.

autogpt/autogpt/app/setup.py

@@ -4,9 +4,10 @@ from typing import Optional
 
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config
 from forge.logging.utils import print_attribute
 
+from autogpt.app.config import AppConfig
+
 from .input import clean_input
 
 logger = logging.getLogger(__name__)
@@ -46,7 +47,7 @@ def apply_overrides_to_ai_settings(
 async def interactively_revise_ai_settings(
     ai_profile: AIProfile,
     directives: AIDirectives,
-    app_config: Config,
+    app_config: AppConfig,
 ):
     """Interactively revise the AI settings.
 

autogpt/tests/conftest.py

@@ -6,7 +6,6 @@ from pathlib import Path
 
 import pytest
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config, ConfigBuilder
 from forge.file_storage.local import (
     FileStorage,
     FileStorageConfiguration,
@@ -16,6 +15,7 @@ from forge.llm.providers import MultiProvider
 from forge.logging.config import configure_logging
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
+from autogpt.app.config import AppConfig, ConfigBuilder
 from autogpt.app.main import _configure_llm_provider
 
 pytest_plugins = [
@@ -62,7 +62,7 @@ def config(
 
 
 @pytest.fixture(scope="session")
-def setup_logger(config: Config):
+def setup_logger():
     configure_logging(
         debug=True,
         log_dir=Path(__file__).parent / "logs",
@@ -71,12 +71,14 @@ def setup_logger(config: Config):
 
 
 @pytest.fixture
-def llm_provider(config: Config) -> MultiProvider:
+def llm_provider(config: AppConfig) -> MultiProvider:
     return _configure_llm_provider(config)
 
 
 @pytest.fixture
-def agent(config: Config, llm_provider: MultiProvider, storage: FileStorage) -> Agent:
+def agent(
+    config: AppConfig, llm_provider: MultiProvider, storage: FileStorage
+) -> Agent:
     ai_profile = AIProfile(
         ai_name="Base",
         ai_role="A base AI",
@@ -101,6 +103,6 @@ def agent(config: Config, llm_provider: MultiProvider, storage: FileStorage) ->
         settings=agent_settings,
         llm_provider=llm_provider,
         file_storage=storage,
-        legacy_config=config,
+        app_config=config,
     )
     return agent

autogpt/tests/integration/agent_factory.py

@@ -2,15 +2,15 @@ from pathlib import Path
 
 import pytest
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config
 from forge.file_storage import FileStorageBackendName, get_storage
 from forge.llm.providers import MultiProvider
 
 from autogpt.agents.agent import Agent, AgentConfiguration, AgentSettings
+from autogpt.app.config import AppConfig
 
 
 @pytest.fixture
-def dummy_agent(config: Config, llm_provider: MultiProvider):
+def dummy_agent(config: AppConfig, llm_provider: MultiProvider):
     ai_profile = AIProfile(
         ai_name="Dummy Agent",
         ai_role="Dummy Role",
@@ -44,7 +44,7 @@ def dummy_agent(config: Config, llm_provider: MultiProvider):
         settings=agent_settings,
         llm_provider=llm_provider,
         file_storage=file_storage,
-        legacy_config=config,
+        app_config=config,
     )
 
     return agent

autogpt/tests/integration/test_execute_code.py

@@ -5,19 +5,17 @@ from pathlib import Path
 
 import pytest
 from forge.components.code_executor.code_executor import (
-    ALLOWLIST_CONTROL,
     CodeExecutorComponent,
     is_docker_available,
     we_are_running_in_a_docker_container,
 )
+from forge.file_storage.base import FileStorage
 from forge.utils.exceptions import InvalidArgumentError, OperationNotAllowedError
 
-from autogpt.agents.agent import Agent
-
 
 @pytest.fixture
-def code_executor_component(agent: Agent):
+def code_executor_component(storage: FileStorage):
-    return agent.code_executor
+    return CodeExecutorComponent(storage)
 
 
 @pytest.fixture
@@ -26,10 +24,8 @@ def random_code(random_string) -> str:
 
 
 @pytest.fixture
-def python_test_file(agent: Agent, random_code: str):
+def python_test_file(storage: FileStorage, random_code: str):
-    temp_file = tempfile.NamedTemporaryFile(
+    temp_file = tempfile.NamedTemporaryFile(dir=storage.root, suffix=".py")
-        dir=agent.file_manager.workspace.root, suffix=".py"
-    )
     temp_file.write(str.encode(random_code))
     temp_file.flush()
 
@@ -38,10 +34,8 @@ def python_test_file(agent: Agent, random_code: str):
 
 
 @pytest.fixture
-def python_test_args_file(agent: Agent):
+def python_test_args_file(storage: FileStorage):
-    temp_file = tempfile.NamedTemporaryFile(
+    temp_file = tempfile.NamedTemporaryFile(dir=storage.root, suffix=".py")
-        dir=agent.file_manager.workspace.root, suffix=".py"
-    )
     temp_file.write(str.encode("import sys\nprint(sys.argv[1], sys.argv[2])"))
     temp_file.flush()
 
@@ -58,7 +52,6 @@ def test_execute_python_file(
     code_executor_component: CodeExecutorComponent,
     python_test_file: Path,
     random_string: str,
-    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -71,7 +64,6 @@ def test_execute_python_file_args(
     code_executor_component: CodeExecutorComponent,
     python_test_args_file: Path,
     random_string: str,
-    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -89,7 +81,6 @@ async def test_execute_python_code(
     code_executor_component: CodeExecutorComponent,
     random_code: str,
     random_string: str,
-    agent: Agent,
 ):
     if not (is_docker_available() or we_are_running_in_a_docker_container()):
         pytest.skip("Docker is not available")
@@ -98,16 +89,12 @@ async def test_execute_python_code(
     assert result.replace("\r", "") == f"Hello {random_string}!\n"
 
 
-def test_execute_python_file_invalid(
+def test_execute_python_file_invalid(code_executor_component: CodeExecutorComponent):
-    code_executor_component: CodeExecutorComponent, agent: Agent
-):
     with pytest.raises(InvalidArgumentError):
         code_executor_component.execute_python_file(Path("not_python.txt"))
 
 
-def test_execute_python_file_not_found(
+def test_execute_python_file_not_found(code_executor_component: CodeExecutorComponent):
-    code_executor_component: CodeExecutorComponent, agent: Agent
-):
     with pytest.raises(
         FileNotFoundError,
         match=r"python: can't open file '([a-zA-Z]:)?[/\\\-\w]*notexist.py': "
@@ -116,53 +103,41 @@ def test_execute_python_file_not_found(
         code_executor_component.execute_python_file(Path("notexist.py"))
 
 
-def test_execute_shell(
-    code_executor_component: CodeExecutorComponent, random_string: str, agent: Agent
-):
-    result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
-    assert f"Hello {random_string}!" in result
-
-
-def test_execute_shell_local_commands_not_allowed(
-    code_executor_component: CodeExecutorComponent, random_string: str, agent: Agent
-):
-    result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
-    assert f"Hello {random_string}!" in result
-
-
 def test_execute_shell_denylist_should_deny(
-    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str
 ):
-    agent.legacy_config.shell_denylist = ["echo"]
+    code_executor_component.config.shell_command_control = "denylist"
+    code_executor_component.config.shell_denylist = ["echo"]
 
     with pytest.raises(OperationNotAllowedError, match="not allowed"):
         code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
 
 
 def test_execute_shell_denylist_should_allow(
-    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str
 ):
-    agent.legacy_config.shell_denylist = ["cat"]
+    code_executor_component.config.shell_command_control = "denylist"
+    code_executor_component.config.shell_denylist = ["cat"]
 
     result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
     assert "Hello" in result and random_string in result
 
 
 def test_execute_shell_allowlist_should_deny(
-    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str
 ):
-    agent.legacy_config.shell_command_control = ALLOWLIST_CONTROL
+    code_executor_component.config.shell_command_control = "allowlist"
-    agent.legacy_config.shell_allowlist = ["cat"]
+    code_executor_component.config.shell_allowlist = ["cat"]
 
     with pytest.raises(OperationNotAllowedError, match="not allowed"):
         code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
 
 
 def test_execute_shell_allowlist_should_allow(
-    code_executor_component: CodeExecutorComponent, agent: Agent, random_string: str
+    code_executor_component: CodeExecutorComponent, random_string: str
 ):
-    agent.legacy_config.shell_command_control = ALLOWLIST_CONTROL
+    code_executor_component.config.shell_command_control = "allowlist"
-    agent.legacy_config.shell_allowlist = ["echo"]
+    code_executor_component.config.shell_allowlist = ["echo"]
 
     result = code_executor_component.execute_shell(f"echo 'Hello {random_string}!'")
     assert "Hello" in result and random_string in result

autogpt/tests/integration/test_image_gen.py

@@ -5,14 +5,27 @@ from unittest.mock import patch
 
 import pytest
 from forge.components.image_gen import ImageGeneratorComponent
+from forge.components.image_gen.image_gen import ImageGeneratorConfiguration
+from forge.file_storage.base import FileStorage
+from forge.llm.providers.openai import OpenAICredentials
 from PIL import Image
-
+from pydantic import SecretStr
-from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
-def image_gen_component(agent: Agent):
+def image_gen_component(storage: FileStorage):
-    return agent.image_gen
+    cred = OpenAICredentials.from_env()
+    return ImageGeneratorComponent(storage, openai_credentials=cred)
+
+
+@pytest.fixture
+def huggingface_image_gen_component(storage: FileStorage):
+    config = ImageGeneratorConfiguration(
+        image_provider="huggingface",
+        huggingface_api_token=SecretStr("1"),
+        huggingface_image_model="CompVis/stable-diffusion-v1-4",
+    )
+    return ImageGeneratorComponent(storage, config=config)
 
 
 @pytest.fixture(params=[256, 512, 1024])
@@ -25,16 +38,11 @@ def image_size(request):
 @pytest.mark.vcr
 def test_dalle(
     image_gen_component: ImageGeneratorComponent,
-    agent: Agent,
-    storage,
     image_size,
-    cached_openai_client,
 ):
     """Test DALL-E image generation."""
     generate_and_validate(
         image_gen_component,
-        agent,
-        storage,
         image_provider="dalle",
         image_size=image_size,
     )
@@ -51,16 +59,12 @@ def test_dalle(
 )
 def test_huggingface(
     image_gen_component: ImageGeneratorComponent,
-    agent: Agent,
-    storage,
     image_size,
     image_model,
 ):
     """Test HuggingFace image generation."""
     generate_and_validate(
         image_gen_component,
-        agent,
-        storage,
         image_provider="huggingface",
         image_size=image_size,
         hugging_face_image_model=image_model,
@@ -68,14 +72,10 @@ def test_huggingface(
 
 
 @pytest.mark.xfail(reason="SD WebUI call does not work.")
-def test_sd_webui(
+def test_sd_webui(image_gen_component: ImageGeneratorComponent, image_size):
-    image_gen_component: ImageGeneratorComponent, agent: Agent, storage, image_size
-):
     """Test SD WebUI image generation."""
     generate_and_validate(
         image_gen_component,
-        agent,
-        storage,
         image_provider="sd_webui",
         image_size=image_size,
     )
@@ -83,7 +83,7 @@ def test_sd_webui(
 
 @pytest.mark.xfail(reason="SD WebUI call does not work.")
 def test_sd_webui_negative_prompt(
-    image_gen_component: ImageGeneratorComponent, storage, image_size
+    image_gen_component: ImageGeneratorComponent, image_size
 ):
     gen_image = functools.partial(
         image_gen_component.generate_image_with_sd_webui,
@@ -114,17 +114,15 @@ def lst(txt):
 
 def generate_and_validate(
     image_gen_component: ImageGeneratorComponent,
-    agent: Agent,
-    storage,
     image_size,
     image_provider,
     hugging_face_image_model=None,
     **kwargs,
 ):
     """Generate an image and validate the output."""
-    agent.legacy_config.image_provider = image_provider
+    image_gen_component.config.image_provider = image_provider
     if hugging_face_image_model:
-        agent.legacy_config.huggingface_image_model = hugging_face_image_model
+        image_gen_component.config.huggingface_image_model = hugging_face_image_model
     prompt = "astronaut riding a horse"
 
     image_path = lst(image_gen_component.generate_image(prompt, image_size, **kwargs))
@@ -149,9 +147,7 @@ def generate_and_validate(
 )
 @pytest.mark.parametrize("delay", [10, 0])
 def test_huggingface_fail_request_with_delay(
-    image_gen_component: ImageGeneratorComponent,
+    huggingface_image_gen_component: ImageGeneratorComponent,
-    agent: Agent,
-    storage,
     image_size,
     image_model,
     return_text,
@@ -173,14 +169,12 @@ def test_huggingface_fail_request_with_delay(
             mock_post.return_value.ok = False
             mock_post.return_value.text = return_text
 
-        agent.legacy_config.image_provider = "huggingface"
+        huggingface_image_gen_component.config.huggingface_image_model = image_model
-        agent.legacy_config.huggingface_api_token = "mock-api-key"
-        agent.legacy_config.huggingface_image_model = image_model
         prompt = "astronaut riding a horse"
 
         with patch("time.sleep") as mock_sleep:
             # Verify request fails.
-            result = image_gen_component.generate_image(prompt, image_size)
+            result = huggingface_image_gen_component.generate_image(prompt, image_size)
             assert result == "Error creating image."
 
             # Verify retry was called with delay if delay is in return_text
@@ -191,10 +185,8 @@ def test_huggingface_fail_request_with_delay(
 
 
 def test_huggingface_fail_request_no_delay(
-    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
+    mocker, huggingface_image_gen_component: ImageGeneratorComponent
 ):
-    agent.legacy_config.huggingface_api_token = "1"
-
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 500
@@ -206,10 +198,9 @@ def test_huggingface_fail_request_no_delay(
     # Mock time.sleep
     mock_sleep = mocker.patch("time.sleep")
 
-    agent.legacy_config.image_provider = "huggingface"
+    result = huggingface_image_gen_component.generate_image(
-    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+        "astronaut riding a horse", 512
-
+    )
-    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."
 
@@ -218,10 +209,8 @@ def test_huggingface_fail_request_no_delay(
 
 
 def test_huggingface_fail_request_bad_json(
-    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
+    mocker, huggingface_image_gen_component: ImageGeneratorComponent
 ):
-    agent.legacy_config.huggingface_api_token = "1"
-
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 500
@@ -231,10 +220,9 @@ def test_huggingface_fail_request_bad_json(
     # Mock time.sleep
     mock_sleep = mocker.patch("time.sleep")
 
-    agent.legacy_config.image_provider = "huggingface"
+    result = huggingface_image_gen_component.generate_image(
-    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+        "astronaut riding a horse", 512
-
+    )
-    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."
 
@@ -243,17 +231,14 @@ def test_huggingface_fail_request_bad_json(
 
 
 def test_huggingface_fail_request_bad_image(
-    mocker, image_gen_component: ImageGeneratorComponent, agent: Agent
+    mocker, huggingface_image_gen_component: ImageGeneratorComponent
 ):
-    agent.legacy_config.huggingface_api_token = "1"
-
     # Mock requests.post
     mock_post = mocker.patch("requests.post")
     mock_post.return_value.status_code = 200
 
-    agent.legacy_config.image_provider = "huggingface"
+    result = huggingface_image_gen_component.generate_image(
-    agent.legacy_config.huggingface_image_model = "CompVis/stable-diffusion-v1-4"
+        "astronaut riding a horse", 512
-
+    )
-    result = image_gen_component.generate_image("astronaut riding a horse", 512)
 
     assert result == "Error creating image."

autogpt/tests/integration/test_setup.py

@@ -3,8 +3,8 @@ from unittest.mock import patch
 import pytest
 from forge.config.ai_directives import AIDirectives
 from forge.config.ai_profile import AIProfile
-from forge.config.config import Config
 
+from autogpt.app.config import AppConfig
 from autogpt.app.setup import (
     apply_overrides_to_ai_settings,
     interactively_revise_ai_settings,
@@ -39,7 +39,7 @@ async def test_apply_overrides_to_ai_settings():
 
 
 @pytest.mark.asyncio
-async def test_interactively_revise_ai_settings(config: Config):
+async def test_interactively_revise_ai_settings(config: AppConfig):
     ai_profile = AIProfile(ai_name="Test AI", ai_role="Test Role")
     directives = AIDirectives(
         resources=["Resource1"],

autogpt/tests/unit/test_config.py

@@ -8,15 +8,15 @@ from typing import Any
 from unittest import mock
 
 import pytest
-from forge.config.config import GPT_3_MODEL, GPT_4_MODEL, Config, ConfigBuilder
 from openai.pagination import AsyncPage
 from openai.types import Model
 from pydantic import SecretStr
 
+from autogpt.app.config import GPT_3_MODEL, GPT_4_MODEL, AppConfig, ConfigBuilder
 from autogpt.app.configurator import apply_overrides_to_config
 
 
-def test_initial_values(config: Config) -> None:
+def test_initial_values(config: AppConfig) -> None:
     """
     Test if the initial values of the config class attributes are set correctly.
     """
@@ -29,7 +29,7 @@ def test_initial_values(config: Config) -> None:
 @pytest.mark.asyncio
 @mock.patch("openai.resources.models.AsyncModels.list")
 async def test_fallback_to_gpt3_if_gpt4_not_available(
-    mock_list_models: Any, config: Config
+    mock_list_models: Any, config: AppConfig
 ) -> None:
     """
     Test if models update to gpt-3.5-turbo if gpt-4 is not available.
@@ -51,7 +51,7 @@ async def test_fallback_to_gpt3_if_gpt4_not_available(
     assert config.smart_llm == GPT_3_MODEL
 
 
-def test_missing_azure_config(config: Config) -> None:
+def test_missing_azure_config(config: AppConfig) -> None:
     assert config.openai_credentials is not None
 
     config_file = config.app_data_dir / "azure_config.yaml"
@@ -68,7 +68,7 @@ def test_missing_azure_config(config: Config) -> None:
 
 
 @pytest.fixture
-def config_with_azure(config: Config):
+def config_with_azure(config: AppConfig):
     config_file = config.app_data_dir / "azure_config.yaml"
     config_file.write_text(
         f"""
@@ -91,7 +91,7 @@ azure_model_map:
     del os.environ["AZURE_CONFIG_FILE"]
 
 
-def test_azure_config(config_with_azure: Config) -> None:
+def test_azure_config(config_with_azure: AppConfig) -> None:
     assert (credentials := config_with_azure.openai_credentials) is not None
     assert credentials.api_type == SecretStr("azure")
     assert credentials.api_version == SecretStr("2023-06-01-preview")

autogpt/tests/unit/test_git_commands.py

@@ -37,7 +37,7 @@ def test_clone_auto_gpt_repository(
 
     assert clone_result == expected_output
     mock_clone_from.assert_called_once_with(
-        url=f"{scheme}{agent.legacy_config.github_username}:{agent.legacy_config.github_api_key}@{repo}",  # noqa: E501
+        url=f"{scheme}{git_ops_component.config.github_username}:{git_ops_component.config.github_api_key}@{repo}",  # noqa: E501
         to_path=clone_path,
     )
 

autogpt/tests/unit/test_web_search.py

@@ -4,12 +4,15 @@ import pytest
 from forge.components.web.search import WebSearchComponent
 from forge.utils.exceptions import ConfigurationError
 from googleapiclient.errors import HttpError
+from pydantic import SecretStr
 
 from autogpt.agents.agent import Agent
 
 
 @pytest.fixture
 def web_search_component(agent: Agent):
+    agent.web_search.config.google_api_key = SecretStr("test")
+    agent.web_search.config.google_custom_search_engine_id = SecretStr("test")
     return agent.web_search
 
 

docs/content/AutoGPT/configuration/imagegen.md

@@ -1,63 +0,0 @@
-# 🖼 Image Generation configuration
-
-| Config variable  | Values                          |                      |
-| ---------------- | ------------------------------- | -------------------- |
-| `IMAGE_PROVIDER` | `dalle` `huggingface` `sdwebui` | **default: `dalle`** |
-
-## DALL-e
-
-In `.env`, make sure `IMAGE_PROVIDER` is commented (or set to `dalle`):
-
-```ini
-# IMAGE_PROVIDER=dalle    # this is the default
-```
-
-Further optional configuration:
-
-| Config variable  | Values             |                |
-| ---------------- | ------------------ | -------------- |
-| `IMAGE_SIZE`     | `256` `512` `1024` | default: `256` |
-
-## Hugging Face
-
-To use text-to-image models from Hugging Face, you need a Hugging Face API token.
-Link to the appropriate settings page: [Hugging Face > Settings > Tokens](https://huggingface.co/settings/tokens)
-
-Once you have an API token, uncomment and adjust these variables in your `.env`:
-
-```ini
-IMAGE_PROVIDER=huggingface
-HUGGINGFACE_API_TOKEN=your-huggingface-api-token
-```
-
-Further optional configuration:
-
-| Config variable           | Values                 |                                          |
-| ------------------------- | ---------------------- | ---------------------------------------- |
-| `HUGGINGFACE_IMAGE_MODEL` | see [available models] | default: `CompVis/stable-diffusion-v1-4` |
-
-[available models]: https://huggingface.co/models?pipeline_tag=text-to-image
-
-## Stable Diffusion WebUI
-
-It is possible to use your own self-hosted Stable Diffusion WebUI with AutoGPT:
-
-```ini
-IMAGE_PROVIDER=sdwebui
-```
-
-!!! note
-    Make sure you are running WebUI with `--api` enabled.
-
-Further optional configuration:
-
-| Config variable | Values                  |                                  |
-| --------------- | ----------------------- | -------------------------------- |
-| `SD_WEBUI_URL`  | URL to your WebUI       | default: `http://127.0.0.1:7860` |
-| `SD_WEBUI_AUTH` | `{username}:{password}` | *Note: do not copy the braces!*  |
-
-## Selenium
-
-```shell
-sudo Xvfb :10 -ac -screen 0 1024x768x24 & DISPLAY=:10 <YOUR_CLIENT>
-```

docs/content/AutoGPT/configuration/options.md

@@ -4,18 +4,14 @@ Configuration is controlled through the `Config` object. You can set configurati
 
 ## Environment Variables
 
-- `AUDIO_TO_TEXT_PROVIDER`: Audio To Text Provider. Only option currently is `huggingface`. Default: huggingface
 - `AUTHORISE_COMMAND_KEY`: Key response accepted when authorising commands. Default: y
 - `ANTHROPIC_API_KEY`: Set this if you want to use Anthropic models with AutoGPT
 - `AZURE_CONFIG_FILE`: Location of the Azure Config file relative to the AutoGPT root directory. Default: azure.yaml
-- `BROWSE_CHUNK_MAX_LENGTH`: When browsing website, define the length of chunks to summarize. Default: 3000
+- `COMPONENT_CONFIG_FILE`: Path to the component configuration file (json) for an agent. Optional
-- `BROWSE_SPACY_LANGUAGE_MODEL`: [spaCy language model](https://spacy.io/usage/models) to use when creating chunks. Default: en_core_web_sm
+- `DISABLED_COMMANDS`: Commands to disable. Use comma separated names of commands. See the list of commands from built-in components [here](../components/components.md). Default: None
-- `CHAT_MESSAGES_ENABLED`: Enable chat messages. Optional
-- `DISABLED_COMMANDS`: Commands to disable. Use comma separated names of commands. See the list of commands from built-in components [here](../../forge/components/built-in-components.md). Default: None
 - `ELEVENLABS_API_KEY`: ElevenLabs API Key. Optional.
 - `ELEVENLABS_VOICE_ID`: ElevenLabs Voice ID. Optional.
 - `EMBEDDING_MODEL`: LLM Model to use for embedding tasks. Default: `text-embedding-3-small`
-- `EXECUTE_LOCAL_COMMANDS`: If shell commands should be executed locally. Default: False
 - `EXIT_KEY`: Exit key accepted to exit. Default: n
 - `FAST_LLM`: LLM Model to use for most tasks. Default: `gpt-3.5-turbo-0125`
 - `GITHUB_API_KEY`: [Github API Key](https://github.com/settings/tokens). Optional.
@@ -23,26 +19,16 @@ Configuration is controlled through the `Config` object. You can set configurati
 - `GOOGLE_API_KEY`: Google API key. Optional.
 - `GOOGLE_CUSTOM_SEARCH_ENGINE_ID`: [Google custom search engine ID](https://programmablesearchengine.google.com/controlpanel/all). Optional.
 - `GROQ_API_KEY`: Set this if you want to use Groq models with AutoGPT
-- `HEADLESS_BROWSER`: Use a headless browser while AutoGPT uses a web browser. Setting to `False` will allow you to see AutoGPT operate the browser. Default: True
 - `HUGGINGFACE_API_TOKEN`: HuggingFace API, to be used for both image generation and audio to text. Optional.
-- `HUGGINGFACE_AUDIO_TO_TEXT_MODEL`: HuggingFace audio to text model. Default: CompVis/stable-diffusion-v1-4
 - `HUGGINGFACE_IMAGE_MODEL`: HuggingFace model to use for image generation. Default: CompVis/stable-diffusion-v1-4
-- `IMAGE_PROVIDER`: Image provider. Options are `dalle`, `huggingface`, and `sdwebui`. Default: dalle
-- `IMAGE_SIZE`: Default size of image to generate. Default: 256
 - `OPENAI_API_KEY`: *REQUIRED*- Your [OpenAI API Key](https://platform.openai.com/account/api-keys).
 - `OPENAI_ORGANIZATION`: Organization ID in OpenAI. Optional.
 - `PLAIN_OUTPUT`: Plain output, which disables the spinner. Default: False
 - `RESTRICT_TO_WORKSPACE`: The restrict file reading and writing to the workspace directory. Default: True
 - `SD_WEBUI_AUTH`: Stable Diffusion Web UI username:password pair. Optional.
-- `SD_WEBUI_URL`: Stable Diffusion Web UI URL. Default: http://localhost:7860
-- `SHELL_ALLOWLIST`: List of shell commands that ARE allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `allowlist`. Default: None
-- `SHELL_COMMAND_CONTROL`: Whether to use `allowlist` or `denylist` to determine what shell commands can be executed (Default: denylist)
-- `SHELL_DENYLIST`: List of shell commands that ARE NOT allowed to be executed by AutoGPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `denylist`. Default: sudo,su
 - `SMART_LLM`: LLM Model to use for "smart" tasks. Default: `gpt-4-turbo-preview`
 - `STREAMELEMENTS_VOICE`: StreamElements voice to use. Default: Brian
 - `TEMPERATURE`: Value of temperature given to OpenAI. Value from 0 to 2. Lower is more deterministic, higher is more random. See https://platform.openai.com/docs/api-reference/completions/create#completions/create-temperature
 - `TEXT_TO_SPEECH_PROVIDER`: Text to Speech Provider. Options are `gtts`, `macos`, `elevenlabs`, and `streamelements`. Default: gtts
-- `USER_AGENT`: User-Agent given when browsing websites. Default: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
 - `USE_AZURE`: Use Azure's LLM Default: False
-- `USE_WEB_BROWSER`: Which web browser to use. Options are `chrome`, `firefox`, `safari` or `edge` Default: chrome
 - `WIPE_REDIS_ON_START`: Wipes data / index on start. Default: True

docs/content/AutoGPT/configuration/search.md

@@ -2,36 +2,36 @@
 
 !!! note
     This section is optional. Use the official Google API if search attempts return
-    error 429. To use the `google_official_search` command, you need to set up your
+    error 429. To use the `google` command, you need to set up your
-    Google API key in your environment variables.
+    Google API key in your environment variables or pass it with configuration to the [`WebSearchComponent`](../../forge/components/built-in-components.md).
 
 Create your project:
 
 1. Go to the [Google Cloud Console](https://console.cloud.google.com/).
-2. If you don't already have an account, create one and log in
+1. If you don't already have an account, create one and log in
-3. Create a new project by clicking on the *Select a Project* dropdown at the top of the
+1. Create a new project by clicking on the *Select a Project* dropdown at the top of the
     page and clicking *New Project*
-4. Give it a name and click *Create*
+1. Give it a name and click *Create*
-5. Set up a custom search API and add to your .env file:
+1. Set up a custom search API and add to your .env file:
-    5. Go to the [APIs & Services Dashboard](https://console.cloud.google.com/apis/dashboard)
+    1. Go to the [APIs & Services Dashboard](https://console.cloud.google.com/apis/dashboard)
-    6. Click *Enable APIs and Services*
+    1. Click *Enable APIs and Services*
-    7. Search for *Custom Search API* and click on it
+    1. Search for *Custom Search API* and click on it
-    8. Click *Enable*
+    1. Click *Enable*
-    9. Go to the [Credentials](https://console.cloud.google.com/apis/credentials) page
+    1. Go to the [Credentials](https://console.cloud.google.com/apis/credentials) page
-    10. Click *Create Credentials*
+    1. Click *Create Credentials*
-    11. Choose *API Key*
+    1. Choose *API Key*
-    12. Copy the API key
+    1. Copy the API key
-    13. Set it as the `GOOGLE_API_KEY` in your `.env` file
+    1. Set it as the `GOOGLE_API_KEY` in your `.env` file
-14. [Enable](https://console.developers.google.com/apis/api/customsearch.googleapis.com)
+1. [Enable](https://console.developers.google.com/apis/api/customsearch.googleapis.com)
     the Custom Search API on your project. (Might need to wait few minutes to propagate.)
     Set up a custom search engine and add to your .env file:
-    15. Go to the [Custom Search Engine](https://cse.google.com/cse/all) page
+    1. Go to the [Custom Search Engine](https://cse.google.com/cse/all) page
-    16. Click *Add*
+    1. Click *Add*
-    17. Set up your search engine by following the prompts.
+    1. Set up your search engine by following the prompts.
         You can choose to search the entire web or specific sites
-    18. Once you've created your search engine, click on *Control Panel*
+    1. Once you've created your search engine, click on *Control Panel*
-    19. Click *Basics*
+    1. Click *Basics*
-    20. Copy the *Search engine ID*
+    1. Copy the *Search engine ID*
-    21. Set it as the `CUSTOM_SEARCH_ENGINE_ID` in your `.env` file
+    1. Set it as the `CUSTOM_SEARCH_ENGINE_ID` in your `.env` file
 
 _Remember that your free daily custom search quota allows only up to 100 searches. To increase this limit, you need to assign a billing account to the project to profit from up to 10K daily searches._

docs/content/AutoGPT/usage.md

@@ -60,10 +60,6 @@ Options:
   --debug                         Enable Debug Mode
   --gpt3only                      Enable GPT3.5 Only Mode
   --gpt4only                      Enable GPT4 Only Mode
-  -b, --browser-name TEXT         Specifies which web-browser to use when
-                                  using selenium to scrape the web.
-  --allow-downloads               Dangerous: Allows AutoGPT to download files
-                                  natively.
   --skip-news                     Specifies whether to suppress the output of
                                   latest news on startup.
   --install-plugin-deps           Installs external dependencies for 3rd party
@@ -82,6 +78,7 @@ Options:
   --override-directives           If specified, --constraint, --resource and
                                   --best-practice will override the AI's
                                   directives instead of being appended to them
+  --component-config-file TEXT    Path to the json configuration file.
   --help                          Show this message and exit.
 ```
 </details>
@@ -128,10 +125,6 @@ Options:
   --debug                     Enable Debug Mode
   --gpt3only                  Enable GPT3.5 Only Mode
   --gpt4only                  Enable GPT4 Only Mode
-  -b, --browser-name TEXT     Specifies which web-browser to use when using
-                              selenium to scrape the web.
-  --allow-downloads           Dangerous: Allows AutoGPT to download files
-                              natively.
   --install-plugin-deps       Installs external dependencies for 3rd party
                               plugins.
   --help                      Show this message and exit.

docs/content/forge/components/built-in-components.md

@@ -1,19 +1,26 @@
 # Built-in Components
 
 This page lists all [🧩 Components](./components.md) and [⚙️ Protocols](./protocols.md) they implement that are natively provided. They are used by the AutoGPT agent.
+Some components have additional configuration options listed in the table, see [Component configuration](./components.md/#ordering-components) to learn more.
+
+!!! note
+    If a configuration field uses environment variable, it still can be passed using configuration model. **Value from the configuration takes precedence over env var!** Env var will be only applied if value in the configuration is not set.
 
 ## `SystemComponent`
 
 Essential component to allow an agent to finish.
 
 **DirectiveProvider**
+
 - Constraints about API budget
   
 **MessageProvider**
+
 - Current time and date
 - Remaining API budget and warnings if budget is low
 
 **CommandProvider**
+
 - `finish` used when task is completed
 
 ## `UserInteractionComponent`
@@ -21,6 +28,7 @@ Essential component to allow an agent to finish.
 Adds ability to interact with user in CLI.
 
 **CommandProvider**
+
 - `ask_user` used to ask user for input
 
 ## `FileManagerComponent`
@@ -28,10 +36,19 @@ Adds ability to interact with user in CLI.
 Adds ability to read and write persistent files to local storage, Google Cloud Storage or Amazon's S3.
 Necessary for saving and loading agent's state (preserving session).
 
+| Config variable  | Details                                | Type  | Default                            |
+| ---------------- | -------------------------------------- | ----- | ---------------------------------- |
+| `files_path`     | Path to agent files, e.g. state        | `str` | `agents/{agent_id}/`[^1]           |
+| `workspace_path` | Path to files that agent has access to | `str` | `agents/{agent_id}/workspace/`[^1] |
+
+[^1] This option is set dynamically during component construction as opposed to by default inside the configuration model, `{agent_id}` is replaced with the agent's unique identifier.
+
 **DirectiveProvider**
+
 - Resource information that it's possible to read and write files
 
 **CommandProvider**
+
 - `read_file` used to read file
 - `write_file` used to write file
 - `list_folder` lists all files in a folder 
@@ -40,7 +57,16 @@ Necessary for saving and loading agent's state (preserving session).
 
 Lets the agent execute non-interactive Shell commands and Python code. Python execution works only if Docker is available.
 
+| Config variable          | Details                                              | Type                        | Default           |
+| ------------------------ | ---------------------------------------------------- | --------------------------- | ----------------- |
+| `execute_local_commands` | Enable shell command execution                       | `bool`                      | `False`           |
+| `shell_command_control`  | Controls which list is used                          | `"allowlist" \| "denylist"` | `"allowlist"`     |
+| `shell_allowlist`        | List of allowed shell commands                       | `List[str]`                 | `[]`              |
+| `shell_denylist`         | List of prohibited shell commands                    | `List[str]`                 | `[]`              |
+| `docker_container_name`  | Name of the Docker container used for code execution | `str`                       | `"agent_sandbox"` |
+
 **CommandProvider**
+
 - `execute_shell` execute shell command
 - `execute_shell_popen` execute shell command with popen
 - `execute_python_code` execute Python code
@@ -50,38 +76,84 @@ Lets the agent execute non-interactive Shell commands and Python code. Python ex
 
 Keeps track of agent's actions and their outcomes. Provides their summary to the prompt.
 
+| Config variable        | Details                                                 | Type        | Default            |
+| ---------------------- | ------------------------------------------------------- | ----------- | ------------------ |
+| `model_name`           | Name of the llm model used to compress the history      | `ModelName` | `"gpt-3.5-turbo"`  |
+| `max_tokens`           | Maximum number of tokens to use for the history summary | `int`       | `1024`             |
+| `spacy_language_model` | Language model used for summary chunking using spacy    | `str`       | `"en_core_web_sm"` |
+
 **MessageProvider**
+
 - Agent's progress summary
 
 **AfterParse**
+
 - Register agent's action
 
-**ExecutionFailuer**
+**ExecutionFailure**
+
 - Rewinds the agent's action, so it isn't saved
 
 **AfterExecute**
+
 - Saves the agent's action result in the history
 
 ## `GitOperationsComponent`
 
+Adds ability to iteract with git repositories and GitHub.
+
+| Config variable   | Details                                   | Type  | Default |
+| ----------------- | ----------------------------------------- | ----- | ------- |
+| `github_username` | GitHub username, *ENV:* `GITHUB_USERNAME` | `str` | `None`  |
+| `github_api_key`  | GitHub API key, *ENV:* `GITHUB_API_KEY`   | `str` | `None`  |
+
 **CommandProvider**
+
 - `clone_repository` used to clone a git repository
 
 ## `ImageGeneratorComponent`
 
-Adds ability to generate images using various providers, see [Image Generation configuration](./../configuration/imagegen.md) to learn more.
+Adds ability to generate images using various providers.
+
+### Hugging Face
+
+To use text-to-image models from Hugging Face, you need a Hugging Face API token.
+Link to the appropriate settings page: [Hugging Face > Settings > Tokens](https://huggingface.co/settings/tokens)
+
+### Stable Diffusion WebUI
+
+It is possible to use your own self-hosted Stable Diffusion WebUI with AutoGPT. **Make sure you are running WebUI with `--api` enabled.**
+
+| Config variable           | Details                                                       | Type                                    | Default                           |
+| ------------------------- | ------------------------------------------------------------- | --------------------------------------- | --------------------------------- |
+| `image_provider`          | Image generation provider                                     | `"dalle" \| "huggingface" \| "sdwebui"` | `"dalle"`                         |
+| `huggingface_image_model` | Hugging Face image model, see [available models]              | `str`                                   | `"CompVis/stable-diffusion-v1-4"` |
+| `huggingface_api_token`   | Hugging Face API token, *ENV:* `HUGGINGFACE_API_TOKEN`        | `str`                                   | `None`                            |
+| `sd_webui_url`            | URL to self-hosted Stable Diffusion WebUI                     | `str`                                   | `"http://localhost:7860"`         |
+| `sd_webui_auth`           | Basic auth for Stable Diffusion WebUI, *ENV:* `SD_WEBUI_AUTH` | `str` of format `{username}:{password}` | `None`                            |
+
+[available models]: https://huggingface.co/models?pipeline_tag=text-to-image
 
 **CommandProvider**
+
 - `generate_image` used to generate an image given a prompt
 
 ## `WebSearchComponent`
 
-Allows agent to search the web.
+Allows agent to search the web. Google credentials aren't required for DuckDuckGo. [Instructions how to set up Google API key](../../AutoGPT/configuration/search.md)
+
+| Config variable                  | Details                                                                 | Type  | Default |
+| -------------------------------- | ----------------------------------------------------------------------- | ----- | ------- |
+| `google_api_key`                 | Google API key, *ENV:* `GOOGLE_API_KEY`                                 | `str` | `None`  |
+| `google_custom_search_engine_id` | Google Custom Search Engine ID, *ENV:* `GOOGLE_CUSTOM_SEARCH_ENGINE_ID` | `str` | `None`  |
+| `duckduckgo_max_attempts`        | Maximum number of attempts to search using DuckDuckGo                   | `int` | `3`     |
 
 **DirectiveProvider**
+
 - Resource information that it's possible to search the web
 
 **CommandProvider**
+
 - `search_web` used to search the web using DuckDuckGo
 - `google` used to search the web using Google, requires API key
 
@@ -89,10 +161,20 @@ Allows agent to search the web.
 
 Allows agent to read websites using Selenium.
 
+| Config variable               | Details                                     | Type                                          | Default                                                                                                                      |
+| ----------------------------- | ------------------------------------------- | --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+| `model_name`                  | Name of the llm model used to read websites | `ModelName`                                   | `"gpt-3.5-turbo"`                                                                                                            |
+| `web_browser`                 | Web browser used by Selenium                | `"chrome" \| "firefox" \| "safari" \| "edge"` | `"chrome"`                                                                                                                   |
+| `headless`                    | Run browser in headless mode                | `bool`                                        | `True`                                                                                                                       |
+| `user_agent`                  | User agent used by the browser              | `str`                                         | `"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"` |
+| `browse_spacy_language_model` | Spacy language model used for chunking text | `str`                                         | `"en_core_web_sm"`                                                                                                           |
+
 **DirectiveProvider**
+
 - Resource information that it's possible to read websites
 
 **CommandProvider**
+
 - `read_website` used to read a specific url and look for specific topics or answer a question
 
 ## `ContextComponent`
@@ -100,9 +182,11 @@ Allows agent to read websites using Selenium.
 Adds ability to keep up-to-date file and folder content in the prompt.
 
 **MessageProvider**
+
 - Content of elements in the context
 
 **CommandProvider**
+
 - `open_file` used to open a file into context
 - `open_folder` used to open a folder into context
 - `close_context_item` remove an item from the context
@@ -112,4 +196,5 @@ Adds ability to keep up-to-date file and folder content in the prompt.
 Watches if agent is looping and switches to smart mode if necessary.
 
 **AfterParse**
+
 - Investigates what happened and switches to smart mode if necessary

docs/content/forge/components/creating-components.md

@@ -148,12 +148,12 @@ It gives an ability for the agent to ask user for input in the terminal.
         yield self.ask_user
     ```
 
-5. Since agent isn't always running in the terminal or interactive mode, we need to disable this component by setting `self._enabled` when it's not possible to ask for user input.
+5. Since agent isn't always running in the terminal or interactive mode, we need to disable this component by setting `self._enabled=False` when it's not possible to ask for user input.
 
     ```py
-    def __init__(self, config: Config):
+    def __init__(self, interactive_mode: bool):
         self.config = config
-        self._enabled = not config.noninteractive_mode
+        self._enabled = interactive_mode
     ```
 
 The final component should look like this:
@@ -164,10 +164,10 @@ class MyUserInteractionComponent(CommandProvider):
     """Provides commands to interact with the user."""
 
     # We pass config to check if we're in noninteractive mode
-    def __init__(self, config: Config):
+    def __init__(self, interactive_mode: bool):
         self.config = config
         # 5.
-        self._enabled = not config.noninteractive_mode
+        self._enabled = interactive_mode
 
     # 4.
     def get_commands(self) -> Iterator[Command]:
@@ -205,10 +205,10 @@ class MyAgent(Agent):
         settings: AgentSettings,
         llm_provider: MultiProvider,
         file_storage: FileStorage,
-        legacy_config: Config,
+        app_config: Config,
     ):
         # Call the parent constructor to bring in the default components
-        super().__init__(settings, llm_provider, file_storage, legacy_config)
+        super().__init__(settings, llm_provider, file_storage, app_config)
         # Disable the default user interaction component by overriding it
         self.user_interaction = MyUserInteractionComponent()
 ```
@@ -222,14 +222,14 @@ class MyAgent(Agent):
         settings: AgentSettings,
         llm_provider: MultiProvider,
         file_storage: FileStorage,
-        legacy_config: Config,
+        app_config: Config,
     ):
         # Call the parent constructor to bring in the default components
-        super().__init__(settings, llm_provider, file_storage, legacy_config)
+        super().__init__(settings, llm_provider, file_storage, app_config)
         # Disable the default user interaction component
         self.user_interaction = None
         # Add our own component
-        self.my_user_interaction = MyUserInteractionComponent(legacy_config)
+        self.my_user_interaction = MyUserInteractionComponent(app_config)
 ```
 
 ## Learn more

docs/content/forge/components/introduction.md

@@ -1,5 +1,11 @@
 # Component Agents
 
+!!! important
+    [Legacy plugins] no longer work with AutoGPT. They have been replaced by components,
+    although we're still working on a new system to load plug-in components.
+
+[Legacy plugins]: https://github.com/Significant-Gravitas/Auto-GPT-Plugins
+
 This guide explains the component-based architecture of AutoGPT agents. It's a new way of building agents that is more flexible and easier to extend. Components replace some agent's logic and plugins with a more modular and composable system.
 
 Agent is composed of *components*, and each *component* implements a range of *protocols* (interfaces), each one providing a specific functionality, e.g. additional commands or messages. Each *protocol* is handled in a specific order, defined by the agent. This allows for a clear separation of concerns and a more modular design.

docs/mkdocs.yml

@@ -15,7 +15,6 @@ nav:
               - Options: AutoGPT/configuration/options.md
               - Search: AutoGPT/configuration/search.md
               - Voice: AutoGPT/configuration/voice.md
-              - Image Generation: AutoGPT/configuration/imagegen.md
       - Usage: AutoGPT/usage.md
       - Help us improve AutoGPT:
           - Share your debug logs with us: AutoGPT/share-your-logs.md

forge/forge/agent/base.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import copy
 import inspect
+import json
 import logging
 from abc import ABCMeta, abstractmethod
 from typing import (
@@ -18,12 +19,13 @@ from typing import (
 )
 
 from colorama import Fore
-from pydantic import BaseModel, Field, validator
+from pydantic import BaseModel, Field, parse_raw_as, validator
 
 from forge.agent import protocols
 from forge.agent.components import (
     AgentComponent,
     ComponentEndpointError,
+    ConfigurableComponent,
     EndpointPipelineError,
 )
 from forge.config.ai_directives import AIDirectives
@@ -45,6 +47,11 @@ DEFAULT_TRIGGERING_PROMPT = (
 )
 
 
+# HACK: This is a workaround wrapper to de/serialize component configs until pydantic v2
+class ModelContainer(BaseModel):
+    models: dict[str, BaseModel]
+
+
 class BaseAgentConfiguration(SystemConfiguration):
     allow_fs_access: bool = UserConfigurable(default=False)
 
@@ -82,9 +89,6 @@ class BaseAgentConfiguration(SystemConfiguration):
     defaults to 75% of `llm.max_tokens`.
     """
 
-    summary_max_tlength: Optional[int] = None
-    # TODO: move to ActionHistoryConfiguration
-
     @validator("use_functions_api")
     def validate_openai_functions(cls, v: bool, values: dict[str, Any]):
         if v:
@@ -272,6 +276,30 @@ class BaseAgent(Generic[AnyProposal], metaclass=AgentMeta):
                 raise e
         return method_result
 
+    def dump_component_configs(self) -> str:
+        configs = {}
+        for component in self.components:
+            if isinstance(component, ConfigurableComponent):
+                config_type_name = component.config.__class__.__name__
+                configs[config_type_name] = component.config
+        data = ModelContainer(models=configs).json()
+        raw = parse_raw_as(dict[str, dict[str, Any]], data)
+        return json.dumps(raw["models"], indent=4)
+
+    def load_component_configs(self, serialized_configs: str):
+        configs_dict = parse_raw_as(dict[str, dict[str, Any]], serialized_configs)
+
+        for component in self.components:
+            if not isinstance(component, ConfigurableComponent):
+                continue
+            config_type = type(component.config)
+            config_type_name = config_type.__name__
+            if config_type_name in configs_dict:
+                # Parse the serialized data and update the existing config
+                updated_data = configs_dict[config_type_name]
+                data = {**component.config.dict(), **updated_data}
+                component.config = component.config.__class__(**data)
+
     def _collect_components(self):
         components = [
             getattr(self, attr)

forge/forge/agent/components.py

@@ -1,9 +1,14 @@
 from __future__ import annotations
 
 from abc import ABC
-from typing import Callable, TypeVar
+from typing import Callable, ClassVar, Generic, Optional, TypeVar
 
-T = TypeVar("T", bound="AgentComponent")
+from pydantic import BaseModel
+
+from forge.models.config import _update_user_config_from_env, deep_update
+
+AC = TypeVar("AC", bound="AgentComponent")
+BM = TypeVar("BM", bound=BaseModel)
 
 
 class AgentComponent(ABC):
@@ -24,7 +29,7 @@ class AgentComponent(ABC):
         """Return the reason this component is disabled."""
         return self._disabled_reason
 
-    def run_after(self: T, *components: type[AgentComponent] | AgentComponent) -> T:
+    def run_after(self: AC, *components: type[AgentComponent] | AgentComponent) -> AC:
         """Set the components that this component should run after."""
         for component in components:
             t = component if isinstance(component, type) else type(component)
@@ -33,6 +38,39 @@ class AgentComponent(ABC):
         return self
 
 
+class ConfigurableComponent(ABC, Generic[BM]):
+    """A component that can be configured with a Pydantic model."""
+
+    config_class: ClassVar[type[BM]]  # type: ignore
+
+    def __init__(self, configuration: Optional[BM]):
+        self._config: Optional[BM] = None
+        if configuration is not None:
+            self.config = configuration
+
+    def __init_subclass__(cls, **kwargs):
+        super().__init_subclass__(**kwargs)
+        if getattr(cls, "config_class", None) is None:
+            raise NotImplementedError(
+                f"ConfigurableComponent subclass {cls.__name__} "
+                "must define config_class class attribute."
+            )
+
+    @property
+    def config(self) -> BM:
+        if not hasattr(self, "_config") or self._config is None:
+            self.config = self.config_class()
+        return self._config  # type: ignore
+
+    @config.setter
+    def config(self, config: BM):
+        if not hasattr(self, "_config") or self._config is None:
+            # Load configuration from environment variables
+            updated = _update_user_config_from_env(config)
+            config = self.config_class(**deep_update(config.dict(), updated))
+        self._config = config
+
+
 class ComponentEndpointError(Exception):
     """Error of a single protocol method on a component."""
 

forge/forge/components/README.md

@@ -30,6 +30,48 @@ class MyAgent(BaseAgent):
         self.some_component = SomeComponent(self.hello_component)
 ```
 
+## Component configuration
+
+Each component can have its own configuration defined using a regular pydantic `BaseModel`.
+To ensure the configuration is loaded from the file correctly, the component must inherit from `ConfigurableComponent[T]` where `T` is the configuration model it uses.
+`ConfigurableComponent` provides a `config` attribute that holds the configuration instance.
+It's possible to either set the `config` attribute directly or pass the configuration instance to the component's constructor.
+Extra configuration (i.e. for components that are not part of the agent) can be passed and will be silently ignored. Extra config won't be applied even if the component is added later.
+To see the configuration of built-in components visit [Built-in Components](./built-in-components.md).
+
+```py
+from pydantic import BaseModel
+from forge.agent.components import ConfigurableComponent
+
+class MyConfig(BaseModel):
+    some_value: str
+
+class MyComponent(AgentComponent, ConfigurableComponent[MyConfig]):
+    def __init__(self, config: MyConfig):
+        super().__init__(config)
+        # This has the same effect as above:
+        # self.config = config
+
+    def get_some_value(self) -> str:
+        # Access the configuration like a regular model
+        return self.config.some_value
+```
+
+### Sensitive information
+
+While it's possible to pass sensitive data directly in code to the configuration it's recommended to use `UserConfigurable(from_env="ENV_VAR_NAME", exclude=True)` field for sensitive data like API keys.
+The data will be loaded from the environment variable but keep in mind that value passed in code takes precedence.
+All fields, even excluded ones (`exclude=True`) will be loaded when the configuration is loaded from the file.
+Exclusion allows you to skip them during *serialization*, non excluded `SecretStr` will be serialized literally as a `"**********"` string.
+
+```py
+from pydantic import BaseModel, SecretStr
+from forge.models.config import UserConfigurable
+
+class SensitiveConfig(BaseModel):
+    api_key: SecretStr = UserConfigurable(from_env="API_KEY", exclude=True)
+```
+
 ## Ordering components
 
 The execution order of components is important because some may depend on the results of the previous ones.
@@ -72,6 +114,7 @@ class MyAgent(Agent):
 ## Disabling components
 
 You can control which components are enabled by setting their `_enabled` attribute.
+Components are *enabled* by default.
 Either provide a `bool` value or a `Callable[[], bool]`, will be checked each time
 the component is about to be executed. This way you can dynamically enable or disable
 components based on some conditions.

forge/forge/components/action_history/action_history.py

@@ -1,38 +1,54 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Callable, Iterator, Optional
+from typing import Callable, Iterator, Optional
 
+from pydantic import BaseModel
+
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import AfterExecute, AfterParse, MessageProvider
 from forge.llm.prompting.utils import indent
 from forge.llm.providers import ChatMessage, MultiProvider
-
+from forge.llm.providers.multi import ModelName
-if TYPE_CHECKING:
+from forge.llm.providers.openai import OpenAIModelName
-    from forge.config.config import Config
 
 from .model import ActionResult, AnyProposal, Episode, EpisodicActionHistory
 
 
-class ActionHistoryComponent(MessageProvider, AfterParse[AnyProposal], AfterExecute):
+class ActionHistoryConfiguration(BaseModel):
+    model_name: ModelName = OpenAIModelName.GPT3
+    """Name of the llm model used to compress the history"""
+    max_tokens: int = 1024
+    """Maximum number of tokens to use up with generated history messages"""
+    spacy_language_model: str = "en_core_web_sm"
+    """Language model used for summary chunking using spacy"""
+
+
+class ActionHistoryComponent(
+    MessageProvider,
+    AfterParse[AnyProposal],
+    AfterExecute,
+    ConfigurableComponent[ActionHistoryConfiguration],
+):
     """Keeps track of the event history and provides a summary of the steps."""
 
+    config_class = ActionHistoryConfiguration
+
     def __init__(
         self,
         event_history: EpisodicActionHistory[AnyProposal],
-        max_tokens: int,
         count_tokens: Callable[[str], int],
-        legacy_config: Config,
         llm_provider: MultiProvider,
+        config: Optional[ActionHistoryConfiguration] = None,
     ) -> None:
+        ConfigurableComponent.__init__(self, config)
         self.event_history = event_history
-        self.max_tokens = max_tokens
         self.count_tokens = count_tokens
-        self.legacy_config = legacy_config
         self.llm_provider = llm_provider
 
     def get_messages(self) -> Iterator[ChatMessage]:
         if progress := self._compile_progress(
             self.event_history.episodes,
-            self.max_tokens,
+            self.config.max_tokens,
             self.count_tokens,
         ):
             yield ChatMessage.system(f"## Progress on your Task so far\n\n{progress}")
@@ -43,7 +59,7 @@ class ActionHistoryComponent(MessageProvider, AfterParse[AnyProposal], AfterExec
     async def after_execute(self, result: ActionResult) -> None:
         self.event_history.register_result(result)
         await self.event_history.handle_compression(
-            self.llm_provider, self.legacy_config
+            self.llm_provider, self.config.model_name, self.config.spacy_language_model
         )
 
     def _compile_progress(

forge/forge/components/action_history/model.py

@@ -8,11 +8,11 @@ from pydantic.generics import GenericModel
 
 from forge.content_processing.text import summarize_text
 from forge.llm.prompting.utils import format_numbered_list, indent
+from forge.llm.providers.multi import ModelName
 from forge.models.action import ActionResult, AnyProposal
 from forge.models.utils import ModelWithSummary
 
 if TYPE_CHECKING:
-    from forge.config.config import Config
     from forge.llm.providers import MultiProvider
 
 
@@ -108,7 +108,10 @@ class EpisodicActionHistory(GenericModel, Generic[AnyProposal]):
             self.cursor = len(self.episodes)
 
     async def handle_compression(
-        self, llm_provider: MultiProvider, app_config: Config
+        self,
+        llm_provider: MultiProvider,
+        model_name: ModelName,
+        spacy_model: str,
     ) -> None:
         """Compresses each episode in the action history using an LLM.
 
@@ -131,7 +134,8 @@ class EpisodicActionHistory(GenericModel, Generic[AnyProposal]):
                     episode.format(),
                     instruction=compress_instruction,
                     llm_provider=llm_provider,
-                    config=app_config,
+                    model_name=model_name,
+                    spacy_model=spacy_model,
                 )
                 for episode in episodes_to_summarize
             ]

forge/forge/components/code_executor/__init__.py

@@ -1,9 +1,4 @@
-from .code_executor import (
+from .code_executor import CodeExecutionError, CodeExecutorComponent
-    ALLOWLIST_CONTROL,
-    DENYLIST_CONTROL,
-    CodeExecutionError,
-    CodeExecutorComponent,
-)
 
 __all__ = [
     "ALLOWLIST_CONTROL",

forge/forge/components/code_executor/code_executor.py

@@ -5,16 +5,16 @@ import shlex
 import string
 import subprocess
 from pathlib import Path
-from typing import Iterator
+from typing import Iterator, Literal, Optional
 
 import docker
 from docker.errors import DockerException, ImageNotFound, NotFound
 from docker.models.containers import Container as DockerContainer
+from pydantic import BaseModel, Field
 
-from forge.agent import BaseAgentSettings
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider
 from forge.command import Command, command
-from forge.config.config import Config
 from forge.file_storage import FileStorage
 from forge.models.json_schema import JSONSchema
 from forge.utils.exceptions import (
@@ -25,9 +25,6 @@ from forge.utils.exceptions import (
 
 logger = logging.getLogger(__name__)
 
-ALLOWLIST_CONTROL = "allowlist"
-DENYLIST_CONTROL = "denylist"
-
 
 def we_are_running_in_a_docker_container() -> bool:
     """Check if we are running in a Docker container
@@ -56,15 +53,45 @@ class CodeExecutionError(CommandExecutionError):
     """The operation (an attempt to run arbitrary code) returned an error"""
 
 
-class CodeExecutorComponent(CommandProvider):
+class CodeExecutorConfiguration(BaseModel):
+    execute_local_commands: bool = False
+    """Enable shell command execution"""
+    shell_command_control: Literal["allowlist", "denylist"] = "allowlist"
+    """Controls which list is used"""
+    shell_allowlist: list[str] = Field(default_factory=list)
+    """List of allowed shell commands"""
+    shell_denylist: list[str] = Field(default_factory=list)
+    """List of prohibited shell commands"""
+    docker_container_name: str = "agent_sandbox"
+    """Name of the Docker container used for code execution"""
+
+
+class CodeExecutorComponent(
+    CommandProvider, ConfigurableComponent[CodeExecutorConfiguration]
+):
     """Provides commands to execute Python code and shell commands."""
 
+    config_class = CodeExecutorConfiguration
+
     def __init__(
-        self, workspace: FileStorage, state: BaseAgentSettings, config: Config
+        self,
+        workspace: FileStorage,
+        config: Optional[CodeExecutorConfiguration] = None,
     ):
+        ConfigurableComponent.__init__(self, config)
         self.workspace = workspace
-        self.state = state
+
-        self.legacy_config = config
+        # Change container name if it's empty or default to prevent different agents
+        # from using the same container
+        default_container_name = self.config.__fields__["docker_container_name"].default
+        if (
+            not self.config.docker_container_name
+            or self.config.docker_container_name == default_container_name
+        ):
+            random_suffix = "".join(random.choices(string.ascii_lowercase, k=8))
+            self.config.docker_container_name = (
+                f"{default_container_name}_{random_suffix}"
+            )
 
         if not we_are_running_in_a_docker_container() and not is_docker_available():
             logger.info(
@@ -72,7 +99,7 @@ class CodeExecutorComponent(CommandProvider):
                 "The code execution commands will not be available."
             )
 
-        if not self.legacy_config.execute_local_commands:
+        if not self.config.execute_local_commands:
             logger.info(
                 "Local shell commands are disabled. To enable them,"
                 " set EXECUTE_LOCAL_COMMANDS to 'True' in your config file."
@@ -83,7 +110,7 @@ class CodeExecutorComponent(CommandProvider):
             yield self.execute_python_code
             yield self.execute_python_file
 
-        if self.legacy_config.execute_local_commands:
+        if self.config.execute_local_commands:
             yield self.execute_shell
             yield self.execute_shell_popen
 
@@ -192,7 +219,7 @@ class CodeExecutorComponent(CommandProvider):
         logger.debug("App is not running in a Docker container")
         return self._run_python_code_in_docker(file_path, args)
 
-    def validate_command(self, command_line: str, config: Config) -> tuple[bool, bool]:
+    def validate_command(self, command_line: str) -> tuple[bool, bool]:
         """Check whether a command is allowed and whether it may be executed in a shell.
 
         If shell command control is enabled, we disallow executing in a shell, because
@@ -211,10 +238,10 @@ class CodeExecutorComponent(CommandProvider):
 
         command_name = shlex.split(command_line)[0]
 
-        if config.shell_command_control == ALLOWLIST_CONTROL:
+        if self.config.shell_command_control == "allowlist":
-            return command_name in config.shell_allowlist, False
+            return command_name in self.config.shell_allowlist, False
-        elif config.shell_command_control == DENYLIST_CONTROL:
+        elif self.config.shell_command_control == "denylist":
-            return command_name not in config.shell_denylist, False
+            return command_name not in self.config.shell_denylist, False
         else:
             return True, True
 
@@ -238,9 +265,7 @@ class CodeExecutorComponent(CommandProvider):
         Returns:
             str: The output of the command
         """
-        allow_execute, allow_shell = self.validate_command(
+        allow_execute, allow_shell = self.validate_command(command_line)
-            command_line, self.legacy_config
-        )
         if not allow_execute:
             logger.info(f"Command '{command_line}' not allowed")
             raise OperationNotAllowedError("This shell command is not allowed.")
@@ -287,9 +312,7 @@ class CodeExecutorComponent(CommandProvider):
         Returns:
             str: Description of the fact that the process started and its id
         """
-        allow_execute, allow_shell = self.validate_command(
+        allow_execute, allow_shell = self.validate_command(command_line)
-            command_line, self.legacy_config
-        )
         if not allow_execute:
             logger.info(f"Command '{command_line}' not allowed")
             raise OperationNotAllowedError("This shell command is not allowed.")
@@ -320,12 +343,10 @@ class CodeExecutorComponent(CommandProvider):
         """Run a Python script in a Docker container"""
         file_path = self.workspace.get_path(filename)
         try:
-            assert self.state.agent_id, "Need Agent ID to attach Docker container"
-
             client = docker.from_env()
             image_name = "python:3-alpine"
             container_is_fresh = False
-            container_name = f"{self.state.agent_id}_sandbox"
+            container_name = self.config.docker_container_name
             with self.workspace.mount() as local_path:
                 try:
                     container: DockerContainer = client.containers.get(

forge/forge/components/file_manager/file_manager.py

@@ -3,7 +3,10 @@ import os
 from pathlib import Path
 from typing import Iterator, Optional
 
+from pydantic import BaseModel
+
 from forge.agent import BaseAgentSettings
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider, DirectiveProvider
 from forge.command import Command, command
 from forge.file_storage.base import FileStorage
@@ -13,67 +16,89 @@ from forge.utils.file_operations import decode_textual_file
 logger = logging.getLogger(__name__)
 
 
-class FileManagerComponent(DirectiveProvider, CommandProvider):
+class FileManagerConfiguration(BaseModel):
+    storage_path: str
+    """Path to agent files, e.g. state"""
+    workspace_path: str
+    """Path to files that agent has access to"""
+
+    class Config:
+        # Prevent mutation of the configuration
+        # as this wouldn't be reflected in the file storage
+        allow_mutation = False
+
+
+class FileManagerComponent(
+    DirectiveProvider, CommandProvider, ConfigurableComponent[FileManagerConfiguration]
+):
     """
     Adds general file manager (e.g. Agent state),
     workspace manager (e.g. Agent output files) support and
     commands to perform operations on files and folders.
     """
 
-    files: FileStorage
+    config_class = FileManagerConfiguration
-    """Agent-related files, e.g. state, logs.
-    Use `workspace` to access the agent's workspace files."""
-
-    workspace: FileStorage
-    """Workspace that the agent has access to, e.g. for reading/writing files.
-    Use `files` to access agent-related files, e.g. state, logs."""
 
     STATE_FILE = "state.json"
     """The name of the file where the agent's state is stored."""
 
-    def __init__(self, state: BaseAgentSettings, file_storage: FileStorage):
+    def __init__(
-        self.state = state
+        self,
+        file_storage: FileStorage,
+        agent_state: BaseAgentSettings,
+        config: Optional[FileManagerConfiguration] = None,
+    ):
+        """Initialise the FileManagerComponent.
+        Either `agent_id` or `config` must be provided.
 
-        if not state.agent_id:
+        Args:
+            file_storage (FileStorage): The file storage instance to use.
+            state (BaseAgentSettings): The agent's state.
+            config (FileManagerConfiguration, optional): The configuration for
+            the file manager. Defaults to None.
+        """
+        if not agent_state.agent_id:
             raise ValueError("Agent must have an ID.")
 
-        self.files = file_storage.clone_with_subroot(f"agents/{state.agent_id}/")
+        self.agent_state = agent_state
-        self.workspace = file_storage.clone_with_subroot(
+
-            f"agents/{state.agent_id}/workspace"
+        if not config:
-        )
+            storage_path = f"agents/{self.agent_state.agent_id}/"
+            workspace_path = f"agents/{self.agent_state.agent_id}/workspace"
+            ConfigurableComponent.__init__(
+                self,
+                FileManagerConfiguration(
+                    storage_path=storage_path, workspace_path=workspace_path
+                ),
+            )
+        else:
+            ConfigurableComponent.__init__(self, config)
+
+        self.storage = file_storage.clone_with_subroot(self.config.storage_path)
+        """Agent-related files, e.g. state, logs.
+        Use `workspace` to access the agent's workspace files."""
+        self.workspace = file_storage.clone_with_subroot(self.config.workspace_path)
+        """Workspace that the agent has access to, e.g. for reading/writing files.
+        Use `storage` to access agent-related files, e.g. state, logs."""
         self._file_storage = file_storage
 
-    async def save_state(self, save_as: Optional[str] = None) -> None:
+    async def save_state(self, save_as_id: Optional[str] = None) -> None:
-        """Save the agent's state to the state file."""
+        """Save the agent's data and state."""
-        state: BaseAgentSettings = getattr(self, "state")
+        if save_as_id:
-        if save_as:
+            self._file_storage.make_dir(f"agents/{save_as_id}")
-            temp_id = state.agent_id
-            state.agent_id = save_as
-            self._file_storage.make_dir(f"agents/{save_as}")
             # Save state
             await self._file_storage.write_file(
-                f"agents/{save_as}/{self.STATE_FILE}", state.json()
+                f"agents/{save_as_id}/{self.STATE_FILE}", self.agent_state.json()
             )
             # Copy workspace
             self._file_storage.copy(
-                f"agents/{temp_id}/workspace",
+                self.config.workspace_path,
-                f"agents/{save_as}/workspace",
+                f"agents/{save_as_id}/workspace",
             )
-            state.agent_id = temp_id
         else:
-            await self.files.write_file(self.files.root / self.STATE_FILE, state.json())
+            await self.storage.write_file(
-
+                self.storage.root / self.STATE_FILE, self.agent_state.json()
-    def change_agent_id(self, new_id: str):
+            )
-        """Change the agent's ID and update the file storage accordingly."""
-        state: BaseAgentSettings = getattr(self, "state")
-        # Rename the agent's files and workspace
-        self._file_storage.rename(f"agents/{state.agent_id}", f"agents/{new_id}")
-        # Update the file storage objects
-        self.files = self._file_storage.clone_with_subroot(f"agents/{new_id}/")
-        self.workspace = self._file_storage.clone_with_subroot(
-            f"agents/{new_id}/workspace"
-        )
-        state.agent_id = new_id
 
     def get_resources(self) -> Iterator[str]:
         yield "The ability to read and write files."

forge/forge/components/git_operations/git_operations.py

@@ -1,23 +1,36 @@
 from pathlib import Path
-from typing import Iterator
+from typing import Iterator, Optional
 
 from git.repo import Repo
+from pydantic import BaseModel, SecretStr
 
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider
 from forge.command import Command, command
-from forge.config.config import Config
+from forge.models.config import UserConfigurable
 from forge.models.json_schema import JSONSchema
 from forge.utils.exceptions import CommandExecutionError
 from forge.utils.url_validator import validate_url
 
 
-class GitOperationsComponent(CommandProvider):
+class GitOperationsConfiguration(BaseModel):
+    github_username: Optional[str] = UserConfigurable(from_env="GITHUB_USERNAME")
+    github_api_key: Optional[SecretStr] = UserConfigurable(
+        from_env="GITHUB_API_KEY", exclude=True
+    )
+
+
+class GitOperationsComponent(
+    CommandProvider, ConfigurableComponent[GitOperationsConfiguration]
+):
     """Provides commands to perform Git operations."""
 
-    def __init__(self, config: Config):
+    config_class = GitOperationsConfiguration
-        self._enabled = bool(config.github_username and config.github_api_key)
+
+    def __init__(self, config: Optional[GitOperationsConfiguration] = None):
+        ConfigurableComponent.__init__(self, config)
+        self._enabled = bool(self.config.github_username and self.config.github_api_key)
         self._disabled_reason = "Configure github_username and github_api_key."
-        self.legacy_config = config
 
     def get_commands(self) -> Iterator[Command]:
         yield self.clone_repository
@@ -48,9 +61,13 @@ class GitOperationsComponent(CommandProvider):
             str: The result of the clone operation.
         """
         split_url = url.split("//")
-        auth_repo_url = (
+        api_key = (
-            f"//{self.legacy_config.github_username}:"
+            self.config.github_api_key.get_secret_value()
-            f"{self.legacy_config.github_api_key}@".join(split_url)
+            if self.config.github_api_key
+            else None
+        )
+        auth_repo_url = f"//{self.config.github_username}:" f"{api_key}@".join(
+            split_url
         )
         try:
             Repo.clone_from(url=auth_repo_url, to_path=clone_path)

forge/forge/components/image_gen/image_gen.py

@@ -1,5 +1,3 @@
-"""Commands to generate images based on text input"""
-
 import io
 import json
 import logging
@@ -7,35 +5,61 @@ import time
 import uuid
 from base64 import b64decode
 from pathlib import Path
-from typing import Iterator
+from typing import Iterator, Literal, Optional
 
 import requests
 from openai import OpenAI
 from PIL import Image
+from pydantic import BaseModel, SecretStr
 
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider
 from forge.command import Command, command
-from forge.config.config import Config
 from forge.file_storage import FileStorage
+from forge.llm.providers.openai import OpenAICredentials
+from forge.models.config import UserConfigurable
 from forge.models.json_schema import JSONSchema
 
 logger = logging.getLogger(__name__)
 
 
-class ImageGeneratorComponent(CommandProvider):
+class ImageGeneratorConfiguration(BaseModel):
+    image_provider: Literal["dalle", "huggingface", "sdwebui"] = "dalle"
+    huggingface_image_model: str = "CompVis/stable-diffusion-v1-4"
+    huggingface_api_token: Optional[SecretStr] = UserConfigurable(
+        from_env="HUGGINGFACE_API_TOKEN", exclude=True
+    )
+    sd_webui_url: str = "http://localhost:7860"
+    sd_webui_auth: Optional[SecretStr] = UserConfigurable(
+        from_env="SD_WEBUI_AUTH", exclude=True
+    )
+
+
+class ImageGeneratorComponent(
+    CommandProvider, ConfigurableComponent[ImageGeneratorConfiguration]
+):
     """A component that provides commands to generate images from text prompts."""
 
-    def __init__(self, workspace: FileStorage, config: Config):
+    config_class = ImageGeneratorConfiguration
-        self._enabled = bool(config.image_provider)
+
+    def __init__(
+        self,
+        workspace: FileStorage,
+        config: Optional[ImageGeneratorConfiguration] = None,
+        openai_credentials: Optional[OpenAICredentials] = None,
+    ):
+        """openai_credentials only needed for `dalle` provider."""
+        ConfigurableComponent.__init__(self, config)
+        self.openai_credentials = openai_credentials
+        self._enabled = bool(self.config.image_provider)
         self._disabled_reason = "No image provider set."
         self.workspace = workspace
-        self.legacy_config = config
 
     def get_commands(self) -> Iterator[Command]:
         if (
-            self.legacy_config.openai_credentials
+            self.openai_credentials
-            or self.legacy_config.huggingface_api_token
+            or self.config.huggingface_api_token
-            or self.legacy_config.sd_webui_auth
+            or self.config.sd_webui_auth
         ):
             yield self.generate_image
 
@@ -48,7 +72,7 @@ class ImageGeneratorComponent(CommandProvider):
             ),
             "size": JSONSchema(
                 type=JSONSchema.Type.INTEGER,
-                description="The size of the image",
+                description="The size of the image [256, 512, 1024]",
                 required=False,
             ),
         },
@@ -65,22 +89,21 @@ class ImageGeneratorComponent(CommandProvider):
             str: The filename of the image
         """
         filename = self.workspace.root / f"{str(uuid.uuid4())}.jpg"
-        cfg = self.legacy_config
 
-        if cfg.openai_credentials and (
+        if self.openai_credentials and (
-            cfg.image_provider == "dalle"
+            self.config.image_provider == "dalle"
-            or not (cfg.huggingface_api_token or cfg.sd_webui_url)
+            or not (self.config.huggingface_api_token or self.config.sd_webui_url)
         ):
             return self.generate_image_with_dalle(prompt, filename, size)
 
-        elif cfg.huggingface_api_token and (
+        elif self.config.huggingface_api_token and (
-            cfg.image_provider == "huggingface"
+            self.config.image_provider == "huggingface"
-            or not (cfg.openai_credentials or cfg.sd_webui_url)
+            or not (self.openai_credentials or self.config.sd_webui_url)
         ):
             return self.generate_image_with_hf(prompt, filename)
 
-        elif cfg.sd_webui_url and (
+        elif self.config.sd_webui_url and (
-            cfg.image_provider == "sdwebui" or cfg.sd_webui_auth
+            self.config.image_provider == "sdwebui" or self.config.sd_webui_auth
         ):
             return self.generate_image_with_sd_webui(prompt, filename, size)
 
@@ -96,13 +119,15 @@ class ImageGeneratorComponent(CommandProvider):
         Returns:
             str: The filename of the image
         """
-        API_URL = f"https://api-inference.huggingface.co/models/{self.legacy_config.huggingface_image_model}"  # noqa: E501
+        API_URL = f"https://api-inference.huggingface.co/models/{self.config.huggingface_image_model}"  # noqa: E501
-        if self.legacy_config.huggingface_api_token is None:
+        if self.config.huggingface_api_token is None:
             raise ValueError(
                 "You need to set your Hugging Face API token in the config file."
             )
         headers = {
-            "Authorization": f"Bearer {self.legacy_config.huggingface_api_token}",
+            "Authorization": (
+                f"Bearer {self.config.huggingface_api_token.get_secret_value()}"
+            ),
             "X-Use-Cache": "false",
         }
 
@@ -156,7 +181,7 @@ class ImageGeneratorComponent(CommandProvider):
         Returns:
             str: The filename of the image
         """
-        assert self.legacy_config.openai_credentials  # otherwise this tool is disabled
+        assert self.openai_credentials  # otherwise this tool is disabled
 
         # Check for supported image sizes
         if size not in [256, 512, 1024]:
@@ -169,7 +194,10 @@ class ImageGeneratorComponent(CommandProvider):
 
         # TODO: integrate in `forge.llm.providers`(?)
         response = OpenAI(
-            api_key=self.legacy_config.openai_credentials.api_key.get_secret_value()
+            api_key=self.openai_credentials.api_key.get_secret_value(),
+            organization=self.openai_credentials.organization.get_secret_value()
+            if self.openai_credentials.organization
+            else None,
         ).images.generate(
             prompt=prompt,
             n=1,
@@ -208,13 +236,13 @@ class ImageGeneratorComponent(CommandProvider):
         """
         # Create a session and set the basic auth if needed
         s = requests.Session()
-        if self.legacy_config.sd_webui_auth:
+        if self.config.sd_webui_auth:
-            username, password = self.legacy_config.sd_webui_auth.split(":")
+            username, password = self.config.sd_webui_auth.get_secret_value().split(":")
             s.auth = (username, password or "")
 
         # Generate the images
         response = requests.post(
-            f"{self.legacy_config.sd_webui_url}/sdapi/v1/txt2img",
+            f"{self.config.sd_webui_url}/sdapi/v1/txt2img",
             json={
                 "prompt": prompt,
                 "negative_prompt": negative_prompt,

forge/forge/components/user_interaction/user_interaction.py

@@ -4,7 +4,6 @@ import click
 
 from forge.agent.protocols import CommandProvider
 from forge.command import Command, command
-from forge.config.config import Config
 from forge.models.json_schema import JSONSchema
 from forge.utils.const import ASK_COMMAND
 
@@ -12,9 +11,6 @@ from forge.utils.const import ASK_COMMAND
 class UserInteractionComponent(CommandProvider):
     """Provides commands to interact with the user."""
 
-    def __init__(self, config: Config):
-        self._enabled = not config.noninteractive_mode
-
     def get_commands(self) -> Iterator[Command]:
         yield self.ask_user
 

forge/forge/components/watchdog/watchdog.py

@@ -22,7 +22,7 @@ class WatchdogComponent(AfterParse[AnyProposal]):
 
     def __init__(
         self,
-        config: "BaseAgentConfiguration",
+        config: BaseAgentConfiguration,
         event_history: EpisodicActionHistory[AnyProposal],
     ):
         self.config = config

forge/forge/components/web/search.py

@@ -1,30 +1,44 @@
 import json
 import logging
 import time
-from typing import Iterator
+from typing import Iterator, Optional
 
 from duckduckgo_search import DDGS
+from pydantic import BaseModel, SecretStr
 
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider, DirectiveProvider
 from forge.command import Command, command
-from forge.config.config import Config
+from forge.models.config import UserConfigurable
 from forge.models.json_schema import JSONSchema
 from forge.utils.exceptions import ConfigurationError
 
-DUCKDUCKGO_MAX_ATTEMPTS = 3
-
 logger = logging.getLogger(__name__)
 
 
-class WebSearchComponent(DirectiveProvider, CommandProvider):
+class WebSearchConfiguration(BaseModel):
+    google_api_key: Optional[SecretStr] = UserConfigurable(
+        from_env="GOOGLE_API_KEY", exclude=True
+    )
+    google_custom_search_engine_id: Optional[SecretStr] = UserConfigurable(
+        from_env="GOOGLE_CUSTOM_SEARCH_ENGINE_ID", exclude=True
+    )
+    duckduckgo_max_attempts: int = 3
+
+
+class WebSearchComponent(
+    DirectiveProvider, CommandProvider, ConfigurableComponent[WebSearchConfiguration]
+):
     """Provides commands to search the web."""
 
-    def __init__(self, config: Config):
+    config_class = WebSearchConfiguration
-        self.legacy_config = config
+
+    def __init__(self, config: Optional[WebSearchConfiguration] = None):
+        ConfigurableComponent.__init__(self, config)
 
         if (
-            not self.legacy_config.google_api_key
+            not self.config.google_api_key
-            or not self.legacy_config.google_custom_search_engine_id
+            or not self.config.google_custom_search_engine_id
         ):
             logger.info(
                 "Configure google_api_key and custom_search_engine_id "
@@ -37,10 +51,7 @@ class WebSearchComponent(DirectiveProvider, CommandProvider):
     def get_commands(self) -> Iterator[Command]:
         yield self.web_search
 
-        if (
+        if self.config.google_api_key and self.config.google_custom_search_engine_id:
-            self.legacy_config.google_api_key
-            and self.legacy_config.google_custom_search_engine_id
-        ):
             yield self.google
 
     @command(
@@ -74,7 +85,7 @@ class WebSearchComponent(DirectiveProvider, CommandProvider):
         search_results = []
         attempts = 0
 
-        while attempts < DUCKDUCKGO_MAX_ATTEMPTS:
+        while attempts < self.config.duckduckgo_max_attempts:
             if not query:
                 return json.dumps(search_results)
 
@@ -136,17 +147,25 @@ class WebSearchComponent(DirectiveProvider, CommandProvider):
         from googleapiclient.errors import HttpError
 
         try:
-            # Get the Google API key and Custom Search Engine ID from the config file
+            # Should be the case if this command is enabled:
-            api_key = self.legacy_config.google_api_key
+            assert self.config.google_api_key
-            custom_search_engine_id = self.legacy_config.google_custom_search_engine_id
+            assert self.config.google_custom_search_engine_id
 
             # Initialize the Custom Search API service
-            service = build("customsearch", "v1", developerKey=api_key)
+            service = build(
+                "customsearch",
+                "v1",
+                developerKey=self.config.google_api_key.get_secret_value(),
+            )
 
             # Send the search query and retrieve the results
             result = (
                 service.cse()
-                .list(q=query, cx=custom_search_engine_id, num=num_results)
+                .list(
+                    q=query,
+                    cx=self.config.google_custom_search_engine_id.get_secret_value(),
+                    num=num_results,
+                )
                 .execute()
             )
 

forge/forge/components/web/selenium.py

@@ -3,10 +3,11 @@ import logging
 import re
 from pathlib import Path
 from sys import platform
-from typing import Iterator, Type
+from typing import Iterator, Literal, Optional, Type
 from urllib.request import urlretrieve
 
 from bs4 import BeautifulSoup
+from pydantic import BaseModel
 from selenium.common.exceptions import WebDriverException
 from selenium.webdriver.chrome.options import Options as ChromeOptions
 from selenium.webdriver.chrome.service import Service as ChromeDriverService
@@ -27,12 +28,14 @@ from webdriver_manager.chrome import ChromeDriverManager
 from webdriver_manager.firefox import GeckoDriverManager
 from webdriver_manager.microsoft import EdgeChromiumDriverManager as EdgeDriverManager
 
+from forge.agent.components import ConfigurableComponent
 from forge.agent.protocols import CommandProvider, DirectiveProvider
 from forge.command import Command, command
-from forge.config.config import Config
 from forge.content_processing.html import extract_hyperlinks, format_hyperlinks
 from forge.content_processing.text import extract_information, summarize_text
-from forge.llm.providers import ChatModelInfo, MultiProvider
+from forge.llm.providers import MultiProvider
+from forge.llm.providers.multi import ModelName
+from forge.llm.providers.openai import OpenAIModelName
 from forge.models.json_schema import JSONSchema
 from forge.utils.exceptions import CommandExecutionError, TooMuchOutputError
 from forge.utils.url_validator import validate_url
@@ -51,18 +54,38 @@ class BrowsingError(CommandExecutionError):
     """An error occurred while trying to browse the page"""
 
 
-class WebSeleniumComponent(DirectiveProvider, CommandProvider):
+class WebSeleniumConfiguration(BaseModel):
+    model_name: ModelName = OpenAIModelName.GPT3
+    """Name of the llm model used to read websites"""
+    web_browser: Literal["chrome", "firefox", "safari", "edge"] = "chrome"
+    """Web browser used by Selenium"""
+    headless: bool = True
+    """Run browser in headless mode"""
+    user_agent: str = (
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"
+    )
+    """User agent used by the browser"""
+    browse_spacy_language_model: str = "en_core_web_sm"
+    """Spacy language model used for chunking text"""
+
+
+class WebSeleniumComponent(
+    DirectiveProvider, CommandProvider, ConfigurableComponent[WebSeleniumConfiguration]
+):
     """Provides commands to browse the web using Selenium."""
 
+    config_class = WebSeleniumConfiguration
+
     def __init__(
         self,
-        config: Config,
         llm_provider: MultiProvider,
-        model_info: ChatModelInfo,
+        data_dir: Path,
+        config: Optional[WebSeleniumConfiguration] = None,
     ):
-        self.legacy_config = config
+        ConfigurableComponent.__init__(self, config)
         self.llm_provider = llm_provider
-        self.model_info = model_info
+        self.data_dir = data_dir
 
     def get_resources(self) -> Iterator[str]:
         yield "Ability to read websites."
@@ -129,7 +152,7 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
         """
         driver = None
         try:
-            driver = await self.open_page_in_browser(url, self.legacy_config)
+            driver = await self.open_page_in_browser(url)
 
             text = self.scrape_text_with_selenium(driver)
             links = self.scrape_links_with_selenium(driver, url)
@@ -141,7 +164,7 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
             elif get_raw_content:
                 if (
                     output_tokens := self.llm_provider.count_tokens(
-                        text, self.model_info.name
+                        text, self.config.model_name
                     )
                 ) > MAX_RAW_CONTENT_LENGTH:
                     oversize_factor = round(output_tokens / MAX_RAW_CONTENT_LENGTH, 1)
@@ -228,7 +251,7 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
 
         return format_hyperlinks(hyperlinks)
 
-    async def open_page_in_browser(self, url: str, config: Config) -> WebDriver:
+    async def open_page_in_browser(self, url: str) -> WebDriver:
         """Open a browser window and load a web page using Selenium
 
         Params:
@@ -248,11 +271,11 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
             "safari": SafariOptions,
         }
 
-        options: BrowserOptions = options_available[config.selenium_web_browser]()
+        options: BrowserOptions = options_available[self.config.web_browser]()
-        options.add_argument(f"user-agent={config.user_agent}")
+        options.add_argument(f"user-agent={self.config.user_agent}")
 
         if isinstance(options, FirefoxOptions):
-            if config.selenium_headless:
+            if self.config.headless:
                 options.headless = True  # type: ignore
                 options.add_argument("--disable-gpu")
             driver = FirefoxDriver(
@@ -274,13 +297,11 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
                 options.add_argument("--remote-debugging-port=9222")
 
             options.add_argument("--no-sandbox")
-            if config.selenium_headless:
+            if self.config.headless:
                 options.add_argument("--headless=new")
                 options.add_argument("--disable-gpu")
 
-            self._sideload_chrome_extensions(
+            self._sideload_chrome_extensions(options, self.data_dir / "assets" / "crx")
-                options, config.app_data_dir / "assets" / "crx"
-            )
 
             if (chromium_driver_path := Path("/usr/bin/chromedriver")).exists():
                 chrome_service = ChromeDriverService(str(chromium_driver_path))
@@ -361,7 +382,8 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
                 text,
                 topics_of_interest=topics_of_interest,
                 llm_provider=self.llm_provider,
-                config=self.legacy_config,
+                model_name=self.config.model_name,
+                spacy_model=self.config.browse_spacy_language_model,
             )
             return "\n".join(f"* {i}" for i in information)
         else:
@@ -369,6 +391,7 @@ class WebSeleniumComponent(DirectiveProvider, CommandProvider):
                 text,
                 question=question,
                 llm_provider=self.llm_provider,
-                config=self.legacy_config,
+                model_name=self.config.model_name,
+                spacy_model=self.config.browse_spacy_language_model,
             )
             return result

forge/forge/config/__init__.py

@@ -3,12 +3,10 @@ This module contains configuration models and helpers for AutoGPT Forge.
 """
 from .ai_directives import AIDirectives
 from .ai_profile import AIProfile
-from .config import Config, ConfigBuilder, assert_config_has_required_llm_api_keys
+from .base import BaseConfig
 
 __all__ = [
-    "assert_config_has_required_llm_api_keys",
     "AIProfile",
     "AIDirectives",
-    "Config",
+    "BaseConfig",
-    "ConfigBuilder",
 ]

forge/forge/config/base.py

@@ -0,0 +1,16 @@
+from forge.file_storage import FileStorageBackendName
+from forge.models.config import SystemSettings, UserConfigurable
+from forge.speech.say import TTSConfig
+
+
+class BaseConfig(SystemSettings):
+    name: str = "Base configuration"
+    description: str = "Default configuration for forge agent."
+
+    # TTS configuration
+    tts_config: TTSConfig = TTSConfig()
+
+    # File storage
+    file_storage_backend: FileStorageBackendName = UserConfigurable(
+        default=FileStorageBackendName.LOCAL, from_env="FILE_STORAGE_BACKEND"
+    )

forge/forge/content_processing/text.py

@@ -3,16 +3,14 @@ from __future__ import annotations
 
 import logging
 import math
-from typing import TYPE_CHECKING, Iterator, Optional, TypeVar
+from typing import Iterator, Optional, TypeVar
 
 import spacy
 
-if TYPE_CHECKING:
-    from forge.config.config import Config
-
 from forge.json.parsing import extract_list_from_json
 from forge.llm.prompting import ChatPrompt
 from forge.llm.providers import ChatMessage, ModelTokenizer, MultiProvider
+from forge.llm.providers.multi import ModelName
 
 logger = logging.getLogger(__name__)
 
@@ -57,7 +55,8 @@ def chunk_content(
 async def summarize_text(
     text: str,
     llm_provider: MultiProvider,
-    config: Config,
+    model_name: ModelName,
+    spacy_model: str = "en_core_web_sm",
     question: Optional[str] = None,
     instruction: Optional[str] = None,
 ) -> tuple[str, list[tuple[str, str]]]:
@@ -82,7 +81,8 @@ async def summarize_text(
         text=text,
         instruction=instruction,
         llm_provider=llm_provider,
-        config=config,
+        model_name=model_name,
+        spacy_model=spacy_model,
     )
 
 
@@ -90,7 +90,8 @@ async def extract_information(
     source_text: str,
     topics_of_interest: list[str],
     llm_provider: MultiProvider,
-    config: Config,
+    model_name: ModelName,
+    spacy_model: str = "en_core_web_sm",
 ) -> list[str]:
     fmt_topics_list = "\n".join(f"* {topic}." for topic in topics_of_interest)
     instruction = (
@@ -106,7 +107,8 @@ async def extract_information(
         instruction=instruction,
         output_type=list[str],
         llm_provider=llm_provider,
-        config=config,
+        model_name=model_name,
+        spacy_model=spacy_model,
     )
 
 
@@ -114,7 +116,8 @@ async def _process_text(
     text: str,
     instruction: str,
     llm_provider: MultiProvider,
-    config: Config,
+    model_name: ModelName,
+    spacy_model: str = "en_core_web_sm",
     output_type: type[str | list[str]] = str,
 ) -> tuple[str, list[tuple[str, str]]] | list[str]:
     """Process text using the OpenAI API for summarization or information extraction
@@ -123,7 +126,8 @@ async def _process_text(
         text (str): The text to process.
         instruction (str): Additional instruction for processing.
         llm_provider: LLM provider to use.
-        config (Config): The global application config.
+        model_name: The name of the llm model to use.
+        spacy_model: The spaCy model to use for sentence splitting.
         output_type: `str` for summaries or `list[str]` for piece-wise info extraction.
 
     Returns:
@@ -133,13 +137,11 @@ async def _process_text(
     if not text.strip():
         raise ValueError("No content")
 
-    model = config.fast_llm
+    text_tlength = llm_provider.count_tokens(text, model_name)
-
-    text_tlength = llm_provider.count_tokens(text, model)
     logger.debug(f"Text length: {text_tlength} tokens")
 
     max_result_tokens = 500
-    max_chunk_length = llm_provider.get_token_limit(model) - max_result_tokens - 50
+    max_chunk_length = llm_provider.get_token_limit(model_name) - max_result_tokens - 50
     logger.debug(f"Max chunk length: {max_chunk_length} tokens")
 
     if text_tlength < max_chunk_length:
@@ -157,7 +159,7 @@ async def _process_text(
 
         response = await llm_provider.create_chat_completion(
             model_prompt=prompt.messages,
-            model_name=model,
+            model_name=model_name,
             temperature=0.5,
             max_output_tokens=max_result_tokens,
             completion_parser=lambda s: (
@@ -182,9 +184,9 @@ async def _process_text(
         chunks = list(
             split_text(
                 text,
-                config=config,
                 max_chunk_length=max_chunk_length,
-                tokenizer=llm_provider.get_tokenizer(model),
+                tokenizer=llm_provider.get_tokenizer(model_name),
+                spacy_model=spacy_model,
             )
         )
 
@@ -196,7 +198,8 @@ async def _process_text(
                 instruction=instruction,
                 output_type=output_type,
                 llm_provider=llm_provider,
-                config=config,
+                model_name=model_name,
+                spacy_model=spacy_model,
             )
             processed_results.extend(
                 chunk_result if output_type == list[str] else [chunk_result]
@@ -212,7 +215,8 @@ async def _process_text(
                     "Combine these partial summaries into one."
                 ),
                 llm_provider=llm_provider,
-                config=config,
+                model_name=model_name,
+                spacy_model=spacy_model,
             )
             return summary.strip(), [
                 (processed_results[i], chunks[i][0]) for i in range(0, len(chunks))
@@ -221,9 +225,9 @@ async def _process_text(
 
 def split_text(
     text: str,
-    config: Config,
     max_chunk_length: int,
     tokenizer: ModelTokenizer,
+    spacy_model: str = "en_core_web_sm",
     with_overlap: bool = True,
 ) -> Iterator[tuple[str, int]]:
     """
@@ -231,7 +235,7 @@ def split_text(
 
     Args:
         text (str): The text to split.
-        config (Config): Config object containing the Spacy model setting.
+        spacy_model (str): The spaCy model to use for sentence splitting.
         max_chunk_length (int, optional): The maximum length of a chunk.
         tokenizer (ModelTokenizer): Tokenizer to use for determining chunk length.
         with_overlap (bool, optional): Whether to allow overlap between chunks.
@@ -251,7 +255,7 @@ def split_text(
     n_chunks = math.ceil(text_length / max_chunk_length)
     target_chunk_length = math.ceil(text_length / n_chunks)
 
-    nlp: spacy.language.Language = spacy.load(config.browse_spacy_language_model)
+    nlp: spacy.language.Language = spacy.load(spacy_model)
     nlp.add_pipe("sentencizer")
     doc = nlp(text)
     sentences = [sentence.text.strip() for sentence in doc.sents]

forge/forge/models/config.py

@@ -16,6 +16,7 @@ def UserConfigurable(
     default_factory: Optional[Callable[[], T]] = None,
     from_env: Optional[str | Callable[[], T | None]] = None,
     description: str = "",
+    exclude: bool = False,
     **kwargs,
 ) -> T:
     # TODO: use this to auto-generate docs for the application configuration
@@ -25,6 +26,7 @@ def UserConfigurable(
         default_factory=default_factory,
         from_env=from_env,
         description=description,
+        exclude=exclude,
         **kwargs,
         user_configurable=True,
     )