- Complete local development cycle: clone → repair → run/show/server on
workspace paths without HuggingFace round-trips
- Vision processing now defaults to safe chunking (one image at a time,
prevents OOM + hallucination)
- Resumable clone with --force-resume and deterministic temp cache naming
- Improved test infrastructure (umbrella marker convention)
- 161 Wet Umbrella tests passing including new Vision→Geo pipe integration tests
See CHANGELOG.md for complete details.
The /v1/models endpoint was not reading README front-matter when
detecting model frameworks, causing models from organizations like
lmstudio-community to be filtered out even when properly tagged as MLX.
This completes the implementation started in #31 by ensuring the web
API uses the same front-matter detection as the CLI.
- Import read_front_matter from operations.common
- Read front-matter before calling detect_framework()
- Pass fm parameter to align with CLI behavior
Fixes#41
Signed-off-by: Robert Clark <robert.clark@niftybean.com>
Major Features Added:
• Complete run command implementation with interactive/single-shot modes
• MLXRunner core engine ported from 1.x with modular architecture
• OpenAI-compatible server with SIGINT-robust supervisor mode
• Experimental push feature properly isolated behind environment variable
Key Improvements:
- Full feature parity with 1.1.1 stable releases
- Enhanced human output formatting across all commands
- Clean separation of stable (184 tests) vs experimental features
- Updated demo GIF showcasing improved 2.0 interface
Fixes:
- Pull operation cache pollution (Issue #30) with preflight access checks
- Test stability improvements across all environments
Architecture:
- Modular runner design with focused helper modules
- Thread-safe model loading and memory management
- stable testing across Python 3.9-3.13
Ready for use as comprehensive 1.x alternative.
The BROKE Cluster Team