### Background
The current implementation of AgentServer doesn't allow for a single pin to be connected to multiple nodes, this will be problematic when you have a single output node that needs to be propagated into many nodes. Or multiple nodes that possibly feed the data into a single pin (first come first serve).
This infra change is also part of the preparation for changing the `block` interface to return a stream of output instead of a single output. Treating blocks as streams requires this capability.
### Changes 🏗️
* Update block run interface from returning `(output_name, output_data)` to `Generator[(output_name, output_data)]`
* Removed `agent` term in the API, replace it with `graph` for consistency.
* Reintroduced `AgentNodeExecutionInputOutput`. `AgentNodeExecution` input & output will be a list of `AgentNodeExecutionInputOutput` which describes the input & output data of its execution. Making an execution has 1-many relation to its input output data.
* Propagating the relation and block interface change into the execution engine.
### Background
Agent execution should be able to be triggered in a recurring manner.
This PR introduced an ExecutionScheduling service, a process responsible for managing the execution schedule and triggering its execution based on a predefined cron expression.
### Changes 🏗️
* Added `scheduler.py` / `ExecutionScheduler` implementation.
* Added scheduler test.
* Added `AgentExecutionSchedule` table and its logical model & prisma queries.
* Moved `add_execution` from API server to `execution_manager`
### Background
This PR adds support on IPC on autogpt_server.
To make this happen, there are a couple of refactoring efforts being made (will be described in the `Changes` section).
Currently, there are three independent processes:
```
AgentServer ----> ExecutionManager
|
--> ExecutionScheduler
```
### Changes 🏗️
* Added Pyro5 for IPC support.
* Introduced `AppService`: a class to construct an independent process that can expose a method to other running processes (this is analogous to a microservice).
* Introduced `AppProcess`: used by `AppService` a class for creating a child process that can be executed in the background.
* Adapting existing codebase to user `AppService`.
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`
When an agent is resumed from a mid-cycle state (having made a proposal but not executed it yet), we need to use the previously determined `current_episode.action` proposal instead of calling `agent.propose_action()` again.
* Rename `assert_config_has_openai_api_key` to `assert_config_has_required_llm_api_keys`
* Make OpenAI credential check conditional (only if an OpenAI model is selected in the config)
* Implement checks for Groq and Anthropic credentials
* Use API calls for Groq and OpenAI credential checks to make sure the keys are valid
Revert some changes to fix forge agent and enable components support.
- Rename forge `Agent` to `ProtocolAgent`
- Bring back and update `forge/app.py` and `forge/agent/forge_agent.py`
- `ForgeAgent` inherits from `BaseAgent`, supports component execution and runs the same pipelines as autogpt Agent
- Update forge version from 0.1.0 to 0.2.0
- Update code comments
### Background
This PR implements the main logic of the block execution engine for AutoGPT-Server.
An integration test is added to test the behavior.
*What you can do now with this PR*:
You can manually create a graph, by using the existing blocks as nodes (or write your own). Then execute the graph with an input.
*What you can't do yet*:
Listen to the graph execution result/update (you can follow the `AgentNodeExecution` table result, though).
### Changes 🏗️
* Split `data.py` (model file) into three modules:
* `execution`: a model for node execution.
* `graph`: a model for graph structure.
* `block`: a model for agent block/component.
* Implemented executor main logic
* Simplify db structure:
* Remove `AgentBlockInputOutput` in favor of `inputSchema` & `outputSchema` using serialized json/dict structure.
* Remove `id` on `AgentBlock` in favor of using name (class name of the block) as its identifier.
* Added `constantInput` column for `AgentNode` for hard-coded input/block configuration. Hence, removing`executionStateData` on `AgentNodeExecution`.
* Rename AgentNodeLink input/output to source/sink to avoid confusion
* Change multithreading to multiprocessing, to allow the use of multiple `prisma` asynchronous client.
Frontend broke in #7171 because of changes to the request models in `forge.agent_protocol`. This PR unbreaks it.
Changes:
- Make `input` required on `TaskRequestBody` and `StepRequestBody`
- Amend `toJson()` on `TaskRequestBody` and `StepRequestBody` to omit attributes with `null` value
### Background
Introduced initial database schema for AutoGPT server.
It currently consists of 7 tables:
* `AgentGraph`: This model describes the Agent Graph/Flow (Multi Agent System).
* `AgentNode`: This model describes a single node in the Agent Graph/Flow (Multi Agent System).
* `AgentNodeLink`: This model describes the link between two AgentNodes.
* `AgentNodeExecution`: This model describes the execution of an AgentNode.
* `AgentBlock`: This model describes a component that will be executed by the AgentNode (all the details required, like name, code, input/output).
* `AgentBlockInputOutput`: This model describes the output (produced event) or input (consumed event) of an AgentBlock.
* `FileDefinition`: This model describe a file that can be used as input/output of an AgentNodeExecution.
### Changes 🏗️
* Add Prisma
* Add sqlite3
* Initialize database.
* Update instructions to set up OpenAI / GPT-4 access
* Add instructions to set up Anthropic access
* Add instructions to set up Groq access
* Remove GPT-specific `--gpt3only`, `--gpt4only` CLI flags and related logic
* Remove duplicate config instructions from docker setup page, replace it by a link to the standard setup instructions
