wifi-densepose/rust-port/wifi-densepose-rs/crates/wifi-densepose-desktop/ui/node_modules/lru-cache
rUv 341d9e05a8
ruv-neural: publish 11 crates to crates.io — full implementation, no stubs
* Add temporal graph evolution & RuVector integration research

GOAP Agent 8 output: 1,528-line SOTA research document covering temporal
graph models (TGN, JODIE, DyRep), RuVector graph memory design, mincut
trajectory tracking with Kalman filtering, event detection pipelines,
compressed temporal storage, cross-room transition graphs, and a 5-phase
integration roadmap.

Part of RF Topological Sensing research swarm (10 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add transformer architectures for graph sensing research

GOAP Agent 4 output: 896-line SOTA document covering Graph Transformers
(Graphormer, SAN, GPS, TokenGT), Temporal Graph Transformers (TGN, TGAT,
DyRep), ViT for RF spectrograms, transformer-based mincut prediction,
positional encoding for RF graphs, foundation models for RF sensing, and
efficient edge deployment with INT8 quantization.

Part of RF Topological Sensing research swarm (10 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add attention mechanisms for RF sensing research

GOAP Agent 3 output: 1,110-line document covering GAT for RF graphs,
self-attention for CSI sequences, cross-attention multi-link fusion,
attention-weighted differentiable mincut, spatial node attention,
antenna-level subcarrier attention, and efficient attention variants
(linear, sparse, LSH, S4/Mamba). 8 ASCII architecture diagrams.

Part of RF Topological Sensing research swarm (10 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add sublinear mincut algorithms research

GOAP Agent 5 output: 698-line document covering classical mincut complexity,
sublinear approximation (sampling, sparsifiers), dynamic mincut with lazy
recomputation hybrid, streaming sketch algorithms, Benczur-Karger
sparsification, local partitioning (PageRank-guided cuts), randomized
methods reliability analysis, and Rust implementation with const-generic
RfGraph, zero-alloc Stoer-Wagner, SIMD batch updates.

Part of RF Topological Sensing research swarm (10 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add CSI edge weight computation research

GOAP Agent 2 output: ~700-line document covering CSI feature extraction,
coherence metrics (cross-correlation, mutual information, phasor coherence),
multipath stability scoring (MUSIC, ESPRIT, ISTA), temporal windowing
(EMA, Welford, Kalman), noise robustness (phase noise, AGC, clock drift),
edge weight normalization, and implementation architecture showing 32KB
memory for 120 edges within ESP32-S3 capability.

Part of RF Topological Sensing research swarm (10 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add contrastive learning for RF coherence research

GOAP Agent 7 output: 1,226-line document covering SimCLR/MoCo/BYOL for CSI,
AETHER-Topo dual-head extension, coherence boundary detection with multi-scale
analysis, delta-driven updates (2-12x efficiency), self-supervised pre-training
protocol, triplet networks for 5-state edge classification, and MERIDIAN
cross-environment transfer with EWC continual learning.

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add resolution and spatial granularity analysis research

GOAP Agent 9 output: 1,383-line document covering Fresnel zone analysis,
node density vs resolution (16-node/5m room → 30-60cm), Cramer-Rao lower
bounds with Fisher Information Matrix, graph cut resolution theory,
multi-frequency enhancement (6cm coherent dual-band limit), RF tomography
comparison, experimental validation protocols, and resolution scaling laws
(8.8cm theoretical limit).

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add RF graph theory and minimum cut foundations research

GOAP Agent 1 output: Graph-theoretic foundations covering max-flow/min-cut
for RF (Ford-Fulkerson, Stoer-Wagner, Karger), RF as dynamic graph with
CSI coherence weights, topological change detection via Fiedler vector and
Cheeger inequality, dynamic graph algorithms, comparison to classical RF
sensing, formal mathematical framework, and 9 open research questions.

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add ESP32 mesh hardware constraints research

GOAP Agent 6 output: ESP32 CSI capabilities (52/114 subcarriers), 16-node
mesh topology with 120 edges, TDM synchronized sensing (3ms slots),
computational budget (Stoer-Wagner uses 0.07% of one core), channel hopping,
power analysis (0.44W/node), dual-core firmware architecture, and edge vs
server computing with 100x data reduction on-device.

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add system architecture and prototype design research

GOAP Agent 10 output: End-to-end architecture with pipeline diagrams,
existing crate integration mapping, new rf_topology module design (DDD
aggregate roots), 100ms latency budget breakdown, 3-phase prototype plan
(4-node POC → 16-node room → 72-node multi-room), benchmark design with
8 metrics, ADR-044 draft, and Rust trait definitions (EdgeWeightComputer,
TopologyGraph, MinCutSolver, BoundaryInterpolator).

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add quantum sensing and quantum biomedical research documents

Agent 11: Quantum-level sensors (729 lines) — NV centers, SQUIDs, Rydberg
atoms, quantum illumination, quantum graph theory (walks, spectral, QAOA),
hybrid classical-quantum architecture, quantum ML (VQC, kernels, reservoir
computing), NISQ applications (D-Wave, VQE), hardware roadmap.

Agent 12: Quantum biomedical sensing (827 lines) — whole body biomagnetic
mapping, neural field imaging without electrodes, circulation sensing,
cellular EM signaling, non-contact diagnostics, coherence-based diagnostics
(disease as coherence breakdown), neural interfaces, multimodal observatory,
room-scale ambient health monitoring, graph-based biomedical analysis.

Part of RF Topological Sensing research swarm (12 agents).

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add research index synthesizing all 12 documents (14,322 lines)

Master index for RF Topological Sensing research compendium covering:
graph theory foundations, CSI edge weights, attention mechanisms,
transformers, sublinear algorithms, ESP32 hardware, contrastive learning,
temporal graphs, resolution analysis, system architecture, quantum sensors,
and quantum biomedical sensing. Includes key findings, proposed ADRs
(044, 045), and 5-phase implementation roadmap.

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add SOTA neural decoding landscape and 10 application domains research

- Doc 21: Comprehensive SOTA map (2023-2026) of brain sensors, decoders,
  and visualization systems with RuVector/mincut positioning analysis
- Doc 22: Ten application domains for brain state observatory including
  disease detection, BCI, cognitive monitoring, mental health diagnostics,
  neurofeedback, dream reconstruction, cognitive research, HCI, wearables,
  and brain network digital twins with strategic roadmap

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add NV diamond neural magnetometry research document (13/22)

Comprehensive 600+ line document covering NV center physics, neural
magnetic field sources, sensor architecture, SQUID comparison, signal
processing pipeline, RuVector integration, and development roadmap.

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add ruv-neural workspace Cargo.toml with 12 crate definitions

Workspace structure for the rUv Neural brain topology analysis system.
12 mix-and-match crates with shared dependencies including RuVector
integration, petgraph, rustfft, and WASM/ESP32 support.

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add ruv-neural crate ecosystem — 12 mix-and-match crates (WIP)

Initial implementation of the rUv Neural brain topology analysis system:
- ruv-neural-core: Core types, traits, errors, RVF format (compiles)
- ruv-neural-sensor: NV diamond, OPM, EEG sensor interfaces (in progress)
- ruv-neural-signal: DSP, filtering, spectral, connectivity (in progress)
- ruv-neural-graph: Brain connectivity graph construction (in progress)
- ruv-neural-mincut: Dynamic minimum cut topology analysis (in progress)
- ruv-neural-embed: RuVector graph embeddings (in progress)
- ruv-neural-memory: Persistent neural state memory + HNSW (compiles)
- ruv-neural-decoder: Cognitive state classification + BCI (in progress)
- ruv-neural-esp32: ESP32 edge sensor integration (compiles)
- ruv-neural-wasm: WebAssembly browser bindings (in progress)
- ruv-neural-viz: Visualization + ASCII rendering (in progress)
- ruv-neural-cli: CLI tool (in progress)

Agents still writing remaining modules. Next: fix compilation, tests, push.

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Fix ruv-neural crate compilation: all 12 crates build and 1200+ tests pass

- Fix node2vec.rs type inference error (Vec<_> → Vec<Vec<f64>>)
- Fix artifact.rs with full filter-based detection implementations
- Fix signal crate ConnectivityMetric re-export and trait method names
- Fix embed crate EmbeddingGenerator trait implementations
- Complete spectral, topology, and node2vec embedders with tests
- Complete preprocessing pipeline with sequential stage processing
- All workspace crates compile cleanly, 0 test failures

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* Add ruv-neural-cli README

https://claude.ai/code/session_01DGUAowNScGVp88bK2eiuRv

* fix: convert desktop icons from RGB to RGBA for Tauri build

Tauri's generate_context!() macro requires RGBA PNG icons. All 5 icon
files (32x32.png, 128x128.png, 128x128@2x.png, icon.icns, icon.ico)
were RGB-only, causing a proc macro panic on Linux builds.

Fixes #200

Co-Authored-By: claude-flow <ruv@ruv.net>

* Add Subcarrier Manifold and Vitals Oracle modules for 3D visualizations

- Implemented Subcarrier Manifold to visualize amplitude data as a 3D surface with height and age attributes.
- Created Vitals Oracle to represent vital signs using toroidal rings and particle trails, incorporating breathing and heart rate dynamics.
- Both modules utilize Three.js for rendering and include custom shaders for visual effects.

* feat: complete ruv-neural implementation — physics models, security, witness verification

Replace all stubs/mocks with production physics-based signal models:
- NV Diamond: ODMR Lorentzian dip, 1/f pink noise (Voss-McCartney), brain oscillations
- OPM: SERF-mode, 50/60Hz powerline harmonics, full cross-talk compensation
  via Gaussian elimination with partial pivoting
- EEG: 5 frequency bands, eye blink artifacts (Fp1/Fp2), muscle artifacts,
  impedance-based thermal noise floor
- ESP32 ADC: ring-buffer reader with calibration signal generator, i16 clamp

Security hardening (SEC-001 through SEC-005):
- RVF bounded allocation (16MB metadata, 256MB payload)
- sample_rate validation (>0, finite)
- Signal NaN/Inf rejection
- ADC resolution_bits overflow clamp
- HNSW HashSet visited tracking + bounds checks

Performance optimizations (PERF-001 through PERF-005):
- 67x fewer FFTs via pre-computed analytic signals
- VecDeque O(1) eviction in memory store
- Thread-local FFT planner caching
- BrainGraph::validate() for edge/weight integrity
- Eigenvalue convergence early termination

Ed25519 witness verification system:
- 41 capability attestations across all 12 crates
- SHA-256 digest + Ed25519 signature
- CLI commands: `witness --output` and `witness --verify`

README: ethics warning, hardware parts list (AliExpress), assembly instructions

Co-Authored-By: claude-flow <ruv@ruv.net>

* docs: add crates.io badges and install instructions to ruv-neural README

Add version badges linking to each published crate on crates.io,
cargo add instructions, and crate search link in the Crate Map table.

Co-Authored-By: claude-flow <ruv@ruv.net>

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-03-09 10:52:24 -04:00
..
LICENSE ruv-neural: publish 11 crates to crates.io — full implementation, no stubs 2026-03-09 10:52:24 -04:00
README.md ruv-neural: publish 11 crates to crates.io — full implementation, no stubs 2026-03-09 10:52:24 -04:00
index.js ruv-neural: publish 11 crates to crates.io — full implementation, no stubs 2026-03-09 10:52:24 -04:00
package.json ruv-neural: publish 11 crates to crates.io — full implementation, no stubs 2026-03-09 10:52:24 -04:00

README.md

lru cache

A cache object that deletes the least-recently-used items.

Build Status Coverage Status

Installation:

npm install lru-cache --save

Usage:

var LRU = require("lru-cache")
  , options = { max: 500
              , length: function (n, key) { return n * 2 + key.length }
              , dispose: function (key, n) { n.close() }
              , maxAge: 1000 * 60 * 60 }
  , cache = new LRU(options)
  , otherCache = new LRU(50) // sets just the max size

cache.set("key", "value")
cache.get("key") // "value"

// non-string keys ARE fully supported
// but note that it must be THE SAME object, not
// just a JSON-equivalent object.
var someObject = { a: 1 }
cache.set(someObject, 'a value')
// Object keys are not toString()-ed
cache.set('[object Object]', 'a different value')
assert.equal(cache.get(someObject), 'a value')
// A similar object with same keys/values won't work,
// because it's a different object identity
assert.equal(cache.get({ a: 1 }), undefined)

cache.reset()    // empty the cache

If you put more stuff in it, then items will fall out.

If you try to put an oversized thing in it, then it'll fall out right away.

Options

  • max The maximum size of the cache, checked by applying the length function to all values in the cache. Not setting this is kind of silly, since that's the whole purpose of this lib, but it defaults to Infinity. Setting it to a non-number or negative number will throw a TypeError. Setting it to 0 makes it be Infinity.
  • maxAge Maximum age in ms. Items are not pro-actively pruned out as they age, but if you try to get an item that is too old, it'll drop it and return undefined instead of giving it to you. Setting this to a negative value will make everything seem old! Setting it to a non-number will throw a TypeError.
  • length Function that is used to calculate the length of stored items. If you're storing strings or buffers, then you probably want to do something like function(n, key){return n.length}. The default is function(){return 1}, which is fine if you want to store max like-sized things. The item is passed as the first argument, and the key is passed as the second argumnet.
  • dispose Function that is called on items when they are dropped from the cache. This can be handy if you want to close file descriptors or do other cleanup tasks when items are no longer accessible. Called with key, value. It's called before actually removing the item from the internal cache, so if you want to immediately put it back in, you'll have to do that in a nextTick or setTimeout callback or it won't do anything.
  • stale By default, if you set a maxAge, it'll only actually pull stale items out of the cache when you get(key). (That is, it's not pre-emptively doing a setTimeout or anything.) If you set stale:true, it'll return the stale value before deleting it. If you don't set this, then it'll return undefined when you try to get a stale entry, as if it had already been deleted.
  • noDisposeOnSet By default, if you set a dispose() method, then it'll be called whenever a set() operation overwrites an existing key. If you set this option, dispose() will only be called when a key falls out of the cache, not when it is overwritten.
  • updateAgeOnGet When using time-expiring entries with maxAge, setting this to true will make each item's effective time update to the current time whenever it is retrieved from cache, causing it to not expire. (It can still fall out of cache based on recency of use, of course.)

API

  • set(key, value, maxAge)

  • get(key) => value

    Both of these will update the "recently used"-ness of the key. They do what you think. maxAge is optional and overrides the cache maxAge option if provided.

    If the key is not found, get() will return undefined.

    The key and val can be any value.

  • peek(key)

    Returns the key value (or undefined if not found) without updating the "recently used"-ness of the key.

    (If you find yourself using this a lot, you might be using the wrong sort of data structure, but there are some use cases where it's handy.)

  • del(key)

    Deletes a key out of the cache.

  • reset()

    Clear the cache entirely, throwing away all values.

  • has(key)

    Check if a key is in the cache, without updating the recent-ness or deleting it for being stale.

  • forEach(function(value,key,cache), [thisp])

    Just like Array.prototype.forEach. Iterates over all the keys in the cache, in order of recent-ness. (Ie, more recently used items are iterated over first.)

  • rforEach(function(value,key,cache), [thisp])

    The same as cache.forEach(...) but items are iterated over in reverse order. (ie, less recently used items are iterated over first.)

  • keys()

    Return an array of the keys in the cache.

  • values()

    Return an array of the values in the cache.

  • length

    Return total length of objects in cache taking into account length options function.

  • itemCount

    Return total quantity of objects currently in cache. Note, that stale (see options) items are returned as part of this item count.

  • dump()

    Return an array of the cache entries ready for serialization and usage with 'destinationCache.load(arr)`.

  • load(cacheEntriesArray)

    Loads another cache entries array, obtained with sourceCache.dump(), into the cache. The destination cache is reset before loading new entries

  • prune()

    Manually iterates over the entire cache proactively pruning old entries