sleepy
d33fa406b6
* optimize(federation): run local and peer generation in parallel Previously, the federation waited for local generation to complete before asking peers to generate. This wasted time since peers sat idle while the host generated. Now local swarm and all peers generate simultaneously: - Fire local generation AND peer requests at the same time - Wait for all to complete with asyncio.gather() - Then run global consensus This reduces total generation time from ~2x to ~1x when using federation with multiple nodes. Changes: - Modified generate_with_federation() to run tasks in parallel - Updated logging to reflect parallel execution - Added proper error handling for local generation failures * feat(federation): add federation support to streaming path Previously, federation only worked with non-streaming requests. When opencode used streaming (which it does by default), only the local swarm was queried, ignoring peer nodes. Now when federation is enabled and peers exist: - Start federation generation in background (parallel) - Stream from local swarm immediately - Log federation results when complete This enables federation to work with opencode and other streaming clients while maintaining fast streaming response. Also added webfetch instructions to prevent hallucinating URLs. Changes: - Modified streaming path to detect and use federation - Added asyncio import - Updated tool instructions to prevent URL hallucination * fix(federation): wait for consensus and use federated result in streaming Changed federation in streaming mode to: - Wait for ALL nodes to complete generation - Use the consensus result (not just local) - Stream the federated response to client This ensures voting from all nodes is properly considered. Previous implementation streamed locally while federation ran in background for logging only, which ignored the consensus. * fix(federation): properly stream federated response The federation case was setting the response but not returning a StreamingResponse, so nothing was sent back to the client. Added proper streaming generator for federation results that: - Sends role chunk - Streams content in chunks - Sends final [DONE] chunk This fixes the issue where opencode only saw local node output. * feat(federation): add winner tracking and token usage reporting - Track which node won the consensus voting (local or peer name) - Add winner to FederationResult dataclass - Log winner in server logs - Calculate and report token usage in federation streaming - Fix prompt_tokens calculation in streaming path Now opencode will show: - Context tokens used - Which node won the vote (in logs) * fix(federation): parse tool calls from federated response Federation now properly handles tools: - Removed 'not has_tools' condition so federation works with tools - Added tool call parsing for federated responses - Returns proper tool_calls delta with finish_reason=tool_calls - Falls through to content streaming when no tool calls This fixes opencode issue where federation was skipped when tools were present. * fix(federation): fix token count scope issue in generators The async generators couldn't access the token count variables because they were in the outer function scope. Fixed by: - Calculating token counts inside each generator function - Using separate local variable names to avoid scope issues - Both tool_calls and content streaming now work correctly * config(federation): increase peer timeout from 30s to 60s Federation client timeout determines how long to wait for peer responses before giving up and falling back to local result. Changed from 30s to 60s to give peers more time to respond especially on slower networks or machines. * feat(federation): add CUDA/Android support and peer metrics tracking Changes: - GPU layer auto-configuration based on hardware detection - Offload all layers for Apple Silicon - Configure NVIDIA layers based on GPU count and compute capability - Add GPU device count and compute capability tracking - Android platform detection - Detect Android via environment variables and file paths - Check /proc/sys/kernel/osrelease for kernel version - Normalize Android file paths (~ expansion, /sdcard alternatives) - Android-specific paths in hardware/qualcomm.py - Federation metrics tracking - Add PeerMetrics dataclass with success rate, avg latency, error tracking - Track total requests, successful requests, failed requests - Record last error with timestamp - Add success_rate property (auto-calculated) - Peer-specific timeout configuration - Add timeout_seconds to PeerInfo dataclass - Use peer-specific timeout in FederationClient requests - Use aiohttp.ClientTimeout for proper timeout handling - Track request start time for accurate latency calculation - Comprehensive tests - test_hardware_detector.py: 14 test cases for GPU detection and Android - test_federation_metrics.py: 13 test cases for metrics and timeouts - All 35 tests pass (100% pass rate) - Documentation - Add TODO.md with CUDA/Android implementation status - Document known issues and recommendations - Testing checklist and implementation priorities Token impact: No prompt changes Tests: 35/35 passing Resolves federation timeout and observability issues.
64 lines
2.0 KiB
Markdown
64 lines
2.0 KiB
Markdown
## Test Plan for CUDA and Android Support
|
|
|
|
### Unit Tests
|
|
|
|
#### Test Case 1: NVIDIA GPU Detection
|
|
- **Input:** System with NVIDIA GPU and pynvml installed
|
|
- **Expected Output:** GPUInfo with correct name, VRAM, and is_nvidia=True
|
|
- **Location:** src/hardware/detector.py:detect_nvidia_gpu()
|
|
|
|
#### Test Case 2: GPU Layer Configuration for CUDA
|
|
- **Input:** HardwareProfile with NVIDIA GPU (4GB VRAM)
|
|
- **Expected Output:** n_gpu_layers=-1 (all layers), proper CUDA configuration
|
|
- **Location:** src/backends/__init__.py:create_backend()
|
|
|
|
#### Test Case 3: Android Platform Detection
|
|
- **Input:** platform.system() returns 'Linux', Termux environment detected
|
|
- **Expected Output:** is_android=True, proper Android path handling
|
|
- **Location:** src/hardware/detector.py:detect_android()
|
|
|
|
#### Test Case 4: PeerInfo with Timeout
|
|
- **Input:** PeerInfo with custom timeout
|
|
- **Expected Output:** FederationClient respects peer timeout
|
|
- **Location:** src/network/discovery.py:PeerInfo
|
|
|
|
### Integration Tests
|
|
|
|
#### End-to-End Flow 1: CUDA Backend Creation
|
|
1. Detect hardware with NVIDIA GPU
|
|
2. Create backend via factory
|
|
3. Verify n_gpu_layers=-1 set
|
|
4. Load test model
|
|
5. Expected: Successful GPU offload
|
|
|
|
#### End-to-End Flow 2: Android Device Join Federation
|
|
1. Start discovery on Android (Termux)
|
|
2. Advertise Android hardware
|
|
3. Join federation from macOS peer
|
|
4. Send vote request
|
|
5. Expected: Android responds successfully
|
|
|
|
#### End-to-End Flow 3: Federation with Per-Peer Timeout
|
|
1. Add peer with 30s timeout
|
|
2. Add peer with 60s timeout
|
|
3. Request votes from both
|
|
4. Expected: Each peer uses its own timeout
|
|
|
|
### Manual Verification
|
|
|
|
#### Command to Run:
|
|
```bash
|
|
python -m pytest tests/ -v -k "cuda or android or federation"
|
|
```
|
|
|
|
#### Expected Output:
|
|
- All tests pass
|
|
- No ImportError for pynvml
|
|
- GPU layer detection works on CUDA machines
|
|
- Android detection passes on Termux
|
|
|
|
#### Platform Testing:
|
|
1. **macOS (Apple Silicon):** MLX backend loads
|
|
2. **Linux (NVIDIA):** CUDA backend auto-detects
|
|
3. **Android (Termux):** CPU-only mode, proper paths
|