Reuven
bcecd1d904
fix(ruvllm): apply security and performance optimizations to MoE routing
...
HIGH severity security fixes:
- router: Change new() from panic to Result<Self, &'static str>
- router: Change with_default_affinity() to return Result
- precision_allocator: Change new() to return Result, add new_unchecked()
- sram_mapper: Change assign_tier() from assert! to returning bool
MEDIUM severity security fixes:
- router: Add NaN/Inf validation in apply_cache_bonus_inplace()
- router: Handle NaN in select_top_k(), treat as NEG_INFINITY
- affinity: Add NaN handling in top_k_by_affinity() with deterministic tie-breaking
- affinity: Add NaN handling in least_affinity() for eviction decisions
- sram_mapper: Fix division by zero in priority_score() when last_access=0
P0 performance optimizations:
- router: Add apply_cache_bonus_inplace() to avoid allocation in hot path
- router: Use select_nth_unstable_by for partial sort when k << n (O(n) vs O(n log n))
All 103 tests pass (84 unit + 19 integration).
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 15:25:36 -04:00
Reuven
830fa5c4ed
feat(ruvllm): implement ADR-092 MoE Memory-Aware Routing
...
Implements memory-aware expert routing with cache residency bonus:
## New moe/ Module (5 files, ~4,300 lines)
- router.rs: MemoryAwareRouter with cache bonus (0.15 default)
- INV-6 compliant (deterministic tie-breaking)
- PagingRequest generation for non-resident experts
- affinity.rs: EMA-based expert affinity tracking
- INV-2 compliant (monotonic decay without activation)
- top_k_by_affinity() for prefetch predictions
- precision_allocator.rs: Hot/warm/cold precision assignment
- Frequency-based percentile thresholds
- GGUF format mapping (Q4_K_M, Q3_K, Q2_K)
- sram_mapper.rs: Hardware memory hierarchy config
- Presets: RPi5, Mobile, Desktop, WasmBrowser
- Tier assignment (SRAM/DRAM/Storage)
- metrics.rs: MoE routing metrics tracking
- Cache hit rate, paging latency, prefetch accuracy
## Extended bitnet/expert_cache.rs
- suggest_eviction_with_affinity(): Combined LRU/LFU + affinity
- prefetch_by_affinity(): Affinity-based expert prefetching
- hot_experts(): List currently cached experts
## Tests (131 total)
- 86 MoE unit tests
- 19 integration tests (GATE-1 through GATE-4 validation)
- 26 ExpertCache tests
## Benchmarks (9 suites)
- Routing overhead: ~22 ns (target: ≤15 μs) ✅
- Cache hit rate simulation
- Affinity update, precision allocation
Target: ≥70% cache hit rate vs 34% baseline
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 15:00:59 -04:00
Reuven
9f80f7298f
feat(ruvector-cnn): implement ADR-091 INT8 CNN quantization
...
Complete implementation of INT8 quantization for ruvector-cnn:
Phase 1 - Core Infrastructure:
- QuantizationParams, QuantizationScheme, QuantizationMode
- QuantizedTensor<i8> with quantize/dequantize methods
- CalibrationMethod (MinMax, Percentile, MSE, Entropy)
- 34 unit tests passing
Phase 2 - INT8 Kernels:
- Scalar reference: conv2d, depthwise_conv2d, matmul, requantize
- AVX2 SIMD: _mm256_maddubs_epi16 for 2-4x speedup
- ARM NEON: vmull_s8, vpadalq_s16 for 2-3x speedup
- WASM SIMD128: i8x16 operations for 1.5-2x speedup
Phase 3 - Graph Rewrite Passes:
- GR-1: BatchNorm fusion into Conv weights
- GR-2: Zero-point correction pre-computation
- GR-3: Q/DQ node insertion at FP32/INT8 boundaries
- GR-4: ReLU/HardSwish fusion with LUT
Phase 4 - Quantized Layers:
- QuantizedConv2d with per-channel quantization
- QuantizedDepthwiseConv2d for MobileNet
- QuantizedLinear for FC layers
- QuantizedMaxPool2d/AvgPool2d
- QuantizedResidualAdd with scale alignment
Phase 6 - Tests & Benchmarks:
- quality_validation.rs: cosine similarity ≥0.995
- acceptance_gates.rs: 7 ADR-091 gates
- kernel_equivalence.rs: SIMD vs scalar validation
- int8_bench.rs: Criterion benchmarks
Performance targets:
- 2.5x latency improvement (MobileNetV3)
- 4x memory reduction
- <1% accuracy degradation
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 14:45:52 -04:00
github-actions[bot]
b376344cff
chore: Update NAPI-RS binaries for all platforms
...
Built from commit e9f32ff9a8🤖 Generated by GitHub Actions
2026-03-12 18:11:09 +00:00
Reuven
e9f32ff9a8
Merge branch 'feat/adr-090-ultra-low-bit-qat'
2026-03-12 14:04:51 -04:00
Reuven
f7942f91c1
refactor(ruvllm): remove unused NEON helper function
...
Remove neon_process_4_groups_ultra() which was superseded by the
optimized 8-group batching implementation with prefetching.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 13:59:16 -04:00
Reuven
9a7d458d81
perf(ruvllm): optimize pi-quantization SIMD kernels
...
- Add AVX-512 dequantization kernel (16-wide SIMD, target >12 GB/s)
- Add AVX2 quantization kernel (8-wide SIMD) for forward pass
- Add AVX2 2-bit quantization kernel
- Optimize NEON kernel with prefetching and 8-group batching
- Add inline assembly prefetch (prfm pldl1keep)
- Update benchmarks with new throughput tests
- All 77 tests pass (pi_quant: 35, simd_equivalence: 19, hadamard: 23)
Performance optimizations target ADR-090 requirements:
- Quantize throughput: >1 GB/s (was 467 MiB/s)
- NEON dequant: >10 GB/s (was 2.54 GiB/s)
- AVX-512 dequant: >12 GB/s (new)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 13:57:04 -04:00
Reuven
8403d563df
feat(ruvllm): implement ADR-090 Ultra-Low-Bit QAT & Pi-Quantization
...
Phase 1-4 implementation of ADR-090 with 114 tests passing.
## Core Quantization (src/quantize/)
- pi_quant.rs: PiQuantizer with π/k step sizes, Pi3BitBlock, Pi2BitBlock
- pi_quant_simd.rs: NEON/AVX2/scalar dequantization kernels (2.1x speedup)
- hadamard.rs: Fast Walsh-Hadamard O(n log n), INV-4 orthogonality verified
- incoherence.rs: IncoherenceTransform for QuIP-style decorrelation
- quip.rs: Q2_QuIP variant combining incoherence + 2-bit K-quant
- security.rs: WeightIntegrity, GGUF validation, bounds checking
## QAT Infrastructure (src/qat/)
- config.rs: QatConfig, SteVariant, QuantGranularity with builder pattern
- ste.rs: Straight-through estimator (Standard, Clipped, LSQ, EWGS)
- differentiable_quant.rs: DifferentiableQuantizer trait, PiQuantDifferentiable
- calibration.rs: CalibrationEngine with mixed-domain support
- distillation.rs: Teacher-student composite loss (L_task + L_KD + L_reasoning)
- reasoning_loss.rs: Chain-of-thought fidelity preservation
- training_loop.rs: QatTrainer orchestrator with checkpointing
- lora_qat.rs: Memory-efficient LoRA-QAT (50 MB vs 114 GB for full QAT)
## WASM Integration (ruvllm-wasm/)
- pi_quant_wasm.rs: PiQuantWasm with SIMD128 kernel, JSON serialization
- quant_bench_wasm.rs: QuantBenchWasm for in-browser benchmarking
- Feature flags: pi-quant, qat
## Tests (114 passing)
- pi_quant_tests.rs (35): Round-trip, block packing, bounds checking
- hadamard_tests.rs (23): Orthogonality, invertibility, energy preservation
- ste_tests.rs (24): Gradient correctness, PyTorch reference comparison
- simd_equivalence_tests.rs (19): SIMD ≈ scalar within 1 ULP (INV-8)
- acceptance_gates.rs (13): G1-G5 quality and security gates
## Benchmarks (benches/pi_quant_bench.rs)
- Hadamard 4096: 5.3 μs (target <50 μs) ✓
- NEON dequant: 2.54 GiB/s (2.1x over scalar)
- QAT backward: 7.3 Gelem/s
## Invariants Verified
- INV-1: STE gradient flow
- INV-2: Scale positivity (α > 0)
- INV-3: Step size constraint (π/k)
- INV-4: Hadamard orthogonality
- INV-5: Calibration provenance
- INV-8: SIMD ≈ scalar (≤1 ULP)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 12:36:36 -04:00
github-actions[bot]
1745d9054d
chore: Update NAPI-RS binaries for all platforms
...
Built from commit f091d45575🤖 Generated by GitHub Actions
2026-03-12 14:53:46 +00:00
Reuven
f091d45575
docs(adr): add governance improvements to ADR-090/091, create ADR-092, add implementation checklists
...
ADR-090 (Ultra-Low-Bit QAT):
- Changed status to "Accepted (Staged Implementation)"
- Added decision statement choosing LoRA-QAT as first path
- Added staged implementation phases (4 phases, explicit gates)
- Added validation plan defining "better" (MSE, spectral, cosine, outlier retention)
- Added reasoning preservation metrics (PPL, GSM8K, HumanEval, tool use, long context)
- Added system invariants (INV-1 through INV-8)
- Added acceptance gates (G1-G6) with rollback triggers
- Restructured success criteria into correctness/performance/quality/rollout
ADR-091 (INT8 CNN Quantization):
- Changed status to "Accepted"
- Added decision statement with acceptance benchmark
- Added system invariants (INV-1 through INV-8)
- Added operator coverage table (11 operators)
- Added graph rewrite passes section (4 passes)
- Added deployment policy matrix
- Added acceptance gates (7 gates) with rollback conditions
ADR-092 (MoE Memory-Aware Routing):
- Split from ADR-090 as routing affects scheduling/cache, not representation
- Added decision statement with acceptance benchmark (≥70% cache hit rate)
- Added system invariants (INV-1 through INV-6)
- Added acceptance gates (G1-G5) with rollback conditions
- Added domain analysis with bounded context
Implementation Checklists:
- ADR-090: 6 phases, ~28 files, 16 new + 12 extended
- ADR-091: 6 phases, acceptance gate verification commands
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 10:47:00 -04:00
github-actions[bot]
e6a5c710dc
chore: Update NAPI-RS binaries for all platforms
...
Built from commit cbd6b1402f🤖 Generated by GitHub Actions
2026-03-12 14:35:32 +00:00
github-actions[bot]
9ca5c30e83
chore: Update NAPI-RS binaries for all platforms
...
Built from commit a36fdc80cf🤖 Generated by GitHub Actions
2026-03-12 14:29:24 +00:00
Reuven
cbd6b1402f
docs(adr): add ADR-091 INT8 CNN Quantization DDD Architecture
...
Formalizes INT8 quantization for ruvector-cnn with DDD bounded contexts:
- Quantization Core: params, tensors, scale computation
- Calibration: statistics, histograms, MinMax/Percentile methods
- Inference: QuantizedConv2d, fused BatchNorm, INT8 ReLU
- SIMD Kernels: AVX2, NEON, WASM INT8 implementations
- Observability: benchmarks, accuracy validation
Targets 2-4x speedup over FP32 with <1% accuracy loss.
Related to ADR-090 (ultra-low-bit QAT for LLMs).
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 10:28:54 -04:00
github-actions[bot]
3dbcfe3864
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 3ed78842dd🤖 Generated by GitHub Actions
2026-03-12 14:27:36 +00:00
Reuven
a36fdc80cf
docs(cnn): add INT8 quantization design document
...
Add comprehensive design doc for INT8 quantization implementation
in ruvector-cnn, including calibration strategies and SIMD optimization.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-12 10:22:35 -04:00
rUv
3ed78842dd
docs(research): add ultra-low-bit quantization & edge deployment research ( #255 )
...
* docs(research): add ultra-low-bit quantization & edge deployment research
Comprehensive research collection on 2-bit/3-bit quantization for ruvLLM:
- 01: Ultra-low-bit quantization survey (ICLR'26, QuIP, BitNet, I-quants)
- 02: Quantization-aware training (QAT) with reasoning preservation
- 03: QuIP 2-bit framework analysis (incoherence processing, E8 lattice)
- 04: MoE memory-aware routing for edge SRAM budgets
- 05: ruvLLM quantization architecture deep review and gap analysis
- 06: Rust implementation plan for 2-bit QAT pipeline (14-week roadmap)
- 07: Novel 3-int pi-constant quantization using irrational scaling
Key findings: ruvLLM has strong foundations (BitNet, K-quants, GGUF, KV cache)
but needs QAT training loop and differentiable quantization primitives.
Pi-constant scaling provides ~0.5 bit effective precision gain at 3-bit.
https://claude.ai/code/session_01E4pmfETYzknb1xq2dzCCaj
* docs(adr): add ADR-090 ultra-low-bit QAT & pi-quantization DDD architecture
Comprehensive architecture decision record for implementing 2-bit/3-bit
quantization-aware training in ruvLLM using Domain-Driven Design:
- 5 bounded contexts: Quantization Core, Training, MoE Routing, WASM Runtime, Observability
- Pi-constant quantization with irrational scaling (pi/k step sizes)
- QAT training loop with STE variants and LoRA-QAT lightweight path
- QuIP incoherence via fast Walsh-Hadamard (O(n log n))
- Memory-aware MoE routing with expert precision allocation
- WASM SIMD128 kernels reusing existing tl1_wasm.rs LUT pattern
- Security: weight integrity, GGUF validation, WASM sandbox
- Benchmarking: criterion suite with throughput/quality targets
- 14-week timeline, maps to 18 existing files for extension
Placed in docs/adr/ddd/ per DDD architectural pattern organization.
https://claude.ai/code/session_01E4pmfETYzknb1xq2dzCCaj
---------
Co-authored-by: Claude <noreply@anthropic.com>
2026-03-12 10:21:30 -04:00
github-actions[bot]
260b870312
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 014bf98ea2🤖 Generated by GitHub Actions
2026-03-11 23:36:01 +00:00
Reuven
014bf98ea2
feat(demo): add Self-Learning tab with 6 interactive training demos
...
- Live Classifier: Train custom classes with labeled examples, test classification
- Few-Shot Learning: 3-class system (A/B/C) with drag-drop training
- Incremental Learning: Positive/negative examples with prototype visualization
- Feedback Learning: Track predictions and accuracy over time
- Memory Bank: View stored embeddings, export/import as JSON
- Camera Training: Train using webcam with single/auto-capture modes
All demos use real CNN embeddings (512-dim) with prototypical networks
for classification. Includes cosine similarity scoring and confidence bars.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 19:31:23 -04:00
github-actions[bot]
18a5f5a006
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 3691699569🤖 Generated by GitHub Actions
2026-03-11 23:03:28 +00:00
Reuven
3691699569
fix(demo): improve motion detection sensitivity and reliability
...
- Wait for video to be fully ready before processing
- Add camera warmup delay
- Increase sensitivity (10x amplification, lower threshold)
- Center crop video for consistent detection
- Add better error handling and logging
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 18:58:45 -04:00
github-actions[bot]
79520fff4f
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 4f49ec2d42🤖 Generated by GitHub Actions
2026-03-11 22:31:17 +00:00
Reuven
4f49ec2d42
feat(demo): add interactive demos and self-learning examples
...
Interactive Demos:
- Similarity Search: Click image to find similar ones
- Motion Detection: Real-time scene change via embeddings
- A/B Comparison: Side-by-side image comparison
- Batch Processor: Process up to 20 images at once
- Embedding Explorer: Visualize 512-dim features with stats
- Anomaly Detection: Find outlier images in a set
Self-Learning Code Examples:
- Self-Learning System: Adaptive classifier with feedback loop
- Incremental Learning: Online learning without forgetting
- Few-Shot Learning: Learn from 1-5 examples per class
- Image Retrieval: Searchable image database
- Content Moderation: Flag similar inappropriate content
- Visual Recommendations: Recommend similar items
- Video Keyframes: Extract unique frames
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 18:26:30 -04:00
github-actions[bot]
9aaaf03786
chore: Update NAPI-RS binaries for all platforms
...
Built from commit da6c7e260a🤖 Generated by GitHub Actions
2026-03-11 22:15:23 +00:00
github-actions[bot]
22262d2ba2
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 72c1f225f7🤖 Generated by GitHub Actions
2026-03-11 22:13:38 +00:00
Reuven
da6c7e260a
fix(pose): force WebGL backend for TensorFlow.js compatibility
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 18:10:59 -04:00
Reuven
72c1f225f7
feat(demo): add real-time pose estimation with MoveNet
...
- Add new Pose Estimation tab with 17-keypoint body tracking
- Integrate TensorFlow.js MoveNet (SinglePose Lightning model)
- Real-time skeleton visualization with colored keypoints
- Pose embedding (34-dim) with similarity comparison
- Reference pose capture for pose matching
- Toggle skeleton visibility
- Add pose tracking and gesture control code examples
- Update badges and examples grid
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 18:09:07 -04:00
github-actions[bot]
641a7d355f
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 1799da243f🤖 Generated by GitHub Actions
2026-03-11 22:06:34 +00:00
github-actions[bot]
9ce3d478f0
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 15fcb8d556🤖 Generated by GitHub Actions
2026-03-11 22:03:38 +00:00
github-actions[bot]
9aeb9c942f
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 10b03c75c6🤖 Generated by GitHub Actions
2026-03-11 22:02:36 +00:00
Reuven
1799da243f
feat: add real-time CNN processing with live webcam
...
- Real-time embedding extraction at ~30+ FPS
- Live FPS and latency display
- Reference image comparison with similarity score
- Live embedding visualization
- Center-crop to square for consistent input
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 18:02:13 -04:00
github-actions[bot]
35ee504c64
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 4bf6bf706b🤖 Generated by GitHub Actions
2026-03-11 22:02:00 +00:00
Reuven
15fcb8d556
fix: host WASM files locally + add console debugging
...
- Host ruvector_cnn_wasm.js and .wasm in docs/cnn/
- Add detailed console.log for debugging WASM init
- Remove CDN dependency for reliability
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 17:59:13 -04:00
github-actions[bot]
8007dc398a
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 955793a301🤖 Generated by GitHub Actions
2026-03-11 21:58:01 +00:00
Reuven
4bf6bf706b
fix: correct WASM API usage in CNN demo
...
- Use object format for init: { module_or_path: url }
- Use WasmCnnEmbedder (not CnnEmbedder)
- Use snake_case methods: embedding_dim, cosine_similarity
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 17:57:25 -04:00
github-actions[bot]
81e4d73602
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 0625e2c46c🤖 Generated by GitHub Actions
2026-03-11 21:56:46 +00:00
github-actions[bot]
6072a61d79
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 27b1931130🤖 Generated by GitHub Actions
2026-03-11 21:56:23 +00:00
Reuven
955793a301
fix: add .nojekyll to disable Jekyll processing
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 17:53:19 -04:00
Reuven
0625e2c46c
refactor: move CNN demo to docs/cnn/ for shorter URL
...
URL: https://ruvnet.github.io/ruvector/cnn/
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 17:52:13 -04:00
Reuven
27b1931130
fix: add docs/index.html for GitHub Pages landing
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-11 17:51:50 -04:00
rUv
10b03c75c6
feat: add interactive CNN browser demo for GitHub Pages ( #253 )
...
- Single-file HTML demo with modern dark theme UI
- Drag & drop image upload + camera capture
- Real-time embedding extraction and visualization
- Similarity matrix comparing multiple images
- Performance metrics display (~5ms per image)
- Falls back to demo mode if WASM fails to load
- ADR-089 documenting the approach
Deploy to: https://ruvnet.github.io/ruvector/demo/cnn/
Co-authored-by: Reuven <cohen@ruv-mac-mini.local>
2026-03-11 17:50:42 -04:00
github-actions[bot]
1caaa1b2fa
chore: Update NAPI-RS binaries for all platforms
...
Built from commit e743785c7d🤖 Generated by GitHub Actions
2026-03-11 21:46:44 +00:00
rUv
e743785c7d
feat(ruvector-cnn): CNN contrastive learning + SIMD optimization fixes ( #252 )
...
* feat: add CNN contrastive learning crate with SIMD optimization
- Add ruvector-cnn crate with SIMD-optimized convolutions and contrastive losses
- Implement InfoNCE (SimCLR) and TripletLoss for contrastive learning
- Add MobileNet-V3 inspired backbone architecture
- Include AVX2, NEON, WASM SIMD support with scalar fallback
- Add WASM bindings (ruvector-cnn-wasm) for browser/Node.js
- Add npm package with TypeScript definitions
- Include comprehensive research docs and ADR-088
- 36 tests passing
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: add npm package JavaScript wrapper and TypeScript definitions
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ruvector-cnn): implement real SIMD and fix stubbed code
## SIMD Implementations (was using scalar fallbacks)
- AVX2: conv_3x3_avx2, conv_3x3_avx2_fma, depthwise_conv_3x3_avx2
- AVX2: global_avg_pool_avx2, max_pool_2x2_avx2
- WASM: conv_3x3_wasm, depthwise_conv_3x3_wasm
All now use real SIMD intrinsics processing 8 (AVX2) or 4 (WASM)
channels simultaneously with scalar fallback for remainders.
## Backbone Fixes
- Deprecated MobileNetV3Small/Large (use unified MobileNetV3 instead)
- Implemented actual block processing in forward() methods
- Fixed hardcoded channel counts in global_avg_pool calls
## Dead Code Fixes
- Added #[allow(dead_code)] for momentum field (used in training)
- Added #[allow(dead_code)] for rng field (feature-gated)
- Added #[cfg(feature = "augmentation")] for rand::Rng import
- Commented out undefined "parallel" feature reference
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat(ruvector-cnn): add Winograd F(2,3) and π-calibrated INT8 quantization
- Add Winograd F(2,3) transforms for 2.25x faster 3x3 convolutions
- Implement π-calibrated INT8 quantization with anti-resonance offsets
- Apply 4x loop unrolling with 4 accumulators to AVX2 convolutions
- Update README with practical intro, capabilities table, benchmarks
- Update npm README with simpler language and examples
- Add CNN image embeddings to root README capabilities
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat: publish @ruvector/cnn v0.1.0 WASM npm package
- Add unsafe blocks for WASM SIMD intrinsics (v128_load/v128_store)
- Disable wasm-opt to avoid SIMD validation issues
- Build and include WASM bindings in npm package
- Update npm package.json with all WASM files
- Published to npm as @ruvector/cnn@0.1.0
Co-Authored-By: claude-flow <ruv@ruv.net>
---------
Co-authored-by: Reuven <cohen@ruv-mac-mini.local>
2026-03-11 17:41:53 -04:00
github-actions[bot]
aa57b9a7c2
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 7ace64061d🤖 Generated by GitHub Actions
2026-03-10 20:05:41 +00:00
rUv
7ace64061d
fix: auto-generate embedding and witness_hash for page creation
...
CreatePageRequest previously required embedding and witness_hash
fields, causing 422 errors when clients (including MCP SSE) omitted
them. Now matches ShareRequest behavior: #[serde(default)] on
embedding, witness_hash, tags, and evidence_links. Server
auto-generates 128-dim embedding via ruvllm and SHAKE-256 witness
hash when not provided.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-10 20:01:10 +00:00
github-actions[bot]
c1522bad91
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 82b3431853🤖 Generated by GitHub Actions
2026-03-10 19:25:22 +00:00
rUv
82b3431853
feat: make SSE the default MCP connection method on pi.ruv.io
...
Restructure Guide modal MCP tab to lead with SSE (one command, no
install) and demote npx/Cargo to an optional "Local install" step.
Update main page terminal section to show SSE first.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-10 19:20:45 +00:00
github-actions[bot]
0122f35a1a
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 296749aafb🤖 Generated by GitHub Actions
2026-03-10 19:12:11 +00:00
rUv
296749aafb
docs: add SSE transport documentation to pi.ruv.io landing page
...
Add remote MCP SSE connection instructions to the Guide modal (MCP tab)
and the main page terminal section. Users can now connect via
`claude mcp add pi-brain --transport sse https://pi.ruv.io/sse `
without any local install.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-10 19:06:25 +00:00
github-actions[bot]
48c3812e4e
chore: Update NAPI-RS binaries for all platforms
...
Built from commit d11dde6dbd🤖 Generated by GitHub Actions
2026-03-10 15:02:35 +00:00
rUv
d11dde6dbd
fix: prevent .mcp.json overwrites by removing empty mcpServers from settings ( #250 )
...
Stop writing empty mcpServers: {} to settings.json which could trigger
Claude Code to regenerate .mcp.json, stripping user-added fields like
autoStart. Doctor --fix now cleans up stale empty mcpServers entries.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-10 14:55:40 +00:00
