- Introduced a local read-only Debug API accessible at `http://127.0.0.1:17821` for diagnostics and agent interactions.
- Updated CLI commands to include `gpu-rent debug` for launching the Debug API.
- Enhanced documentation to reflect the new Debug API features and usage.
- Modified configuration to include `DEBUG_LOCAL_PORT` for easier customization.
- Added tests to ensure Debug API links are correctly generated in access card outputs.
Scan ru-6 by Nova availability zones (a/b/c). First boot uses FLAVOR_SIZE_PRESET=cheap; reruns stay on the disk segment.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Removed references to llamacpp from configuration files, scripts, and documentation, streamlining the LLM setup process to focus solely on Ollama.
- Updated environment variables and paths to eliminate llamacpp-related entries, ensuring clarity in the configuration.
- Adjusted CLI commands and help messages to reflect the removal of llamacpp, enhancing user experience and reducing confusion.
- Revised documentation to provide clear guidance on using Ollama exclusively, including updates to setup instructions and runtime options.
- Reduced default values for IDLE_MINUTES from 60 to 30 and IDLE_GRACE_MINUTES from 90 to 45 across configuration files and documentation.
- Updated related documentation to reflect the new default idle time settings, ensuring consistency in user guidance and system behavior.
- Added a new configuration option `UP_STOP_ON_FAIL` to control whether the GPU should be stopped automatically if the `up` command fails, enhancing user control over resource management.
- Updated the CLI to include a `--keep-on-fail` flag, allowing users to prevent GPU shutdown during installation errors.
- Enhanced the installation scripts and documentation to reflect these changes, providing clearer guidance on the new behavior and configuration options.
- Improved error handling in the CLI to ensure proper cleanup of resources in case of failure, preventing unexpected billing for unused GPU resources.
- Added new environment variables in `env.example` and `gpu-rent.vars.example` for fine-tuning LLM settings, including CUDA build options and model version pinning.
- Updated `llm.md` documentation to include detailed descriptions of new configuration options and usage cases for LLM setups.
- Enhanced the `provision.py` script to forward new environment variables during remote installations, improving the installation process for LLM components.
- Modified the `install_llamacpp.sh` script to support conditional CUDA builds and asset URL overrides, ensuring better compatibility with various environments.
- Improved logging in the installation scripts to provide clearer feedback during the setup process.
- Introduced support for Hugging Face API integration, allowing fallback model resolution when Civitai fails.
- Updated configuration to include `HF_TOKEN` and `HF_TOKEN_PATH` for authentication.
- Enhanced model capture logic to differentiate between Civitai and Hugging Face sources.
- Improved error handling for model downloads, providing clearer messages for authentication issues.
- Updated documentation to reflect new environment variables and usage instructions for Hugging Face integration.
- Added tests to validate the new fallback mechanism and ensure robust model resolution.
- Increased default values for IDLE_MINUTES from 30 to 60 and IDLE_GRACE_MINUTES from 45 to 90 across configuration files and documentation.
- Updated related documentation to reflect the new default idle time settings, ensuring consistency in user guidance and system behavior.
- Added support for balance tracking using `SELECTEL_API_TOKEN` in the configuration.
- Introduced new balance notification logic in the local watchdog, alerting users on balance changes based on defined thresholds.
- Updated documentation to include instructions for setting up balance notifications and the required environment variables.
- Enhanced the `ready` and `session` modules to initialize balance state and handle notifications during GPU operations.
- Refactored the CLI and related components to support the new balance monitoring features, ensuring a seamless user experience.
- Updated `env.example` and `gpu-rent.vars.example` to include new variables for LLM runtime and SwarmUI options.
- Refactored CLI commands to support interactive selection of LLM runtime and workload type (SwarmUI, LLM, or both).
- Improved access link generation to handle cases where SwarmUI is disabled, providing clearer user feedback.
- Enhanced provisioning logic to conditionally bootstrap SwarmUI based on user configuration, allowing for LLM-only setups.
- Updated documentation across multiple files to reflect changes in LLM integration, CLI usage, and configuration management.
- Added `ollama-models.yaml` to .gitignore and implemented logic to copy it in gpu-rent.ps1 and gpu-rent.sh.
- Enhanced env.example to include new variables for LLM runtime options and local watchdog configuration.
- Updated CLI commands to support LLM options during setup and execution, including new flags for Ollama and llama.cpp.
- Improved documentation in cli.md and README.md to reflect changes in LLM integration and local watchdog functionality.
- Adjusted architecture and decisions documentation to clarify the role of LLMs and local watchdog in the system.
- Updated .gitignore to include gpu-rent.vars.
- Modified env.example to introduce the UPDATE_GIT variable for controlling git updates during execution.
- Implemented Import-GpuRentVars function in gpu-rent.ps1 to load environment variables from gpu-rent.vars.
- Enhanced gpu-rent.sh to support loading variables from gpu-rent.vars and added logic for handling default and extra arguments.
- Updated CLI documentation to reflect the new gpu-rent.vars file and its usage in configuration.
- Improved bootstrap and provisioning logic to conditionally perform git updates based on the new configuration.
- Added functions to generate SSH user data in cloud-config format and encode it in Base64 for server creation.
- Updated the `create_gpu_server` function to include public key handling for SSH access.
- Adjusted the default boot volume size from 40GB to 30GB in `os_client.py`.
- Enhanced the `cmd_up` function to manage SSH key injection and server state more effectively.
- Improved logging for SSH connection attempts and error handling in `wait_ssh` to provide clearer feedback on authentication issues.
- Added optional SSH security-group CIDR configuration in `env.example` to allow broader access if needed.
- Improved `guess_operator_cidr` function to support multiple IP retrieval services and allow overriding CIDR via environment variable.
- Refactored security group management to ensure idempotency and proper logging of security group rules.
- Introduced helper function `_get_volume_or_none` for better volume management and error handling.
- Updated `wait_ssh` function to enhance SSH connection handling with improved timeout settings and logging.
- Added state reset logic in `cmd_up` to handle scenarios where the server is not found in the cloud.
- Introduced SCAN_POOLS configuration to specify pools for GPU flavor scanning.
- Updated the `flavors` command to scan specified pools and list available GPU flavors based on `FLAVOR_PREFERENCE`.
- Revised CLI documentation to reflect changes in the `flavors` command behavior.
- Enhanced decision documentation to include details about GPU pool scanning.
- Updated setup instructions to guide users on selecting appropriate GPU pools.
- Updated the project structure to store configuration files (.env, models.yaml, extensions.yaml) in the project root instead of the user's home directory.
- Enhanced the setup process to automatically copy example files to the project root on first run.
- Implemented a migration function to transfer legacy configuration files from the user's home directory to the new project structure.
- Revised documentation to reflect changes in file locations and setup instructions.
- Improved code readability and maintainability by refactoring path management functions.
Leonid Pershin
