qector-architecturelisted

QECTOR architecture overview: the Rust core / Python layer FFI boundary, the module map, the threading and memory models, the layering of services, and the bit-determinism guarantee. Load for any question about the engine's internals, where a class lives, how the GIL interacts with the decode call, or why batch decode is reproducible across worker counts.
GuillaumeLessard/qector-claude-plugin · ★ 1 · AI & Automation · score 62

Install: claude install-skill GuillaumeLessard/qector-claude-plugin

# QECTOR Architecture Overview Source of authority: v1.0.0 reference manual, chapter 26. ## Module map (Table 26.1) | Area | Rust modules | Responsibility | | ------------ | ---------------------------------------------------------------------- | ---------------------------------------------------- | | Matching | `blossom.rs`, `mwpm.rs`, `sparse_blossom.rs`, `fusion_mwpm.rs` | Exact and near-optimal MWPM | | Union-Find | `uf_core.rs`, `fast_uf.rs`, `decoder.rs`, `batch.rs`, `cpu_batch.rs` | Graphlike approximate decoding, single and batch | | BP-OSD | `bp_osd.rs`, `gf2.rs`, `ambig_cluster.rs` | Belief propagation and ordered statistics | | GPU | `cuda_*.rs`, `opencl_batch.rs`, `cuda_kernels.cu` | Bit-identical batch kernels | | Temporal | `space_time_decoder.rs`, `streaming.rs`, `sliding_window.rs` | Multi-round and windowed decoding | | Routing | `auto_decoder.rs`, `cascade_decoder.rs`, `two_stage_decoder.rs` | Dispatch, escalation, sector coupling | | GNN / ML | `gnn_*.rs`, `neural_predecoder.rs`, `hybrid_decoder.rs` | Learned predecoders and hybrids | | Services | `mcp_server.rs`, `grpc_server.rs`, `metrics.rs`, `str