akvaithiandClaude Opus 5.5
84b8995d7b
- `lightcraft_denoise::remote`: protocol v1 over TCP (JSON lines + byte-shuffled, deflated half-float tiles), a `Remote` client (connection pool, four slots, greeting checks the model's SHA-256 and tile size, gives up after three failed tiles) and `serve` (shared token compared in constant time, size caps including payloads that inflate past their tile, connection limit, timeouts). - Engine: with LIGHTCRAFT_DENOISE_URL / LIGHTCRAFT_DENOISE_TOKEN set, the loaded model greets the server on first use and adds its slots to this computer's tiles at once; a tile goes to a free server slot, else runs here, and a tile the server fails runs here too. `denoise.status` → `device.remote` says where. - `lightcraft-cli denoise-serve` serves the installed, selected model on this computer's card (checked against the CPU, as in the app) or CPU. - docs/denoise.md: setup, safety (unencrypted: VPN/LAN only) and the protocol. Tested: protocol round trips, refusals (token, model, tile size, hostile payloads), fallback and give-up; the engine model with a live, a mismatched and a dead server; the CLI binary serving a synthetic model end to end. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
lightcraft-denoise
L1 pure-Rust AI RAW denoise primitives and CPU inference. No weights are bundled. See user workflow and limitations.
lightcraft-denoise-core provides metadata, Bayer helpers and cache formats,
re-exported here. manifest and known validate opt-in models; onnx reads a bounded operator subset
into net; cpu executes it and reference supplies scalar checks. bayer, tiles
and run pack sensor data and blend overlapping tiles while preserving clipped
highlights. product reads/writes the disposable .lcdn cache. runtime supplies
the installation self-test. Synthetic networks are generated in Rust for tests.
Run cargo test -p lightcraft-denoise --features runtime. The CPU backend is optional;
featureless and web builds keep the model metadata and cache format without faer/GEMM.
The rawnind-model feature enables the otherwise empty download catalog and requires
an explicit release-policy decision. Real-model tests are ignored by default and
require an explicitly supplied local model. The GPU twin is lightcraft-gpu::nn;
model management, background jobs and export integration live in lightcraft-engine.