loom-concurrency

# Concurrency ## Overview Cross-language concurrency reference organized by concept, not by language. Each concept lists the shared principle plus per-language gotcha callouts for Rust (tokio), Python (asyncio), TypeScript (event loop), and Go. The hard part is never the happy-path API; it's the failure modes — data races, deadlocks, latent OOM from unbounded queues, futures dropped mid-flight by cancellation, and memory-ordering bugs that only surface under load on weakly-ordered CPUs. ## Agent Delegation - **loom-senior-software-engineer** (Opus) — DEFAULT. Threading models, shared-state vs message-passing, race/TOCTOU analysis, lock ordering, memory ordering, distributed concurrency/consistency, saga patterns. - **loom-software-engineer** (Sonnet) — ONLY boilerplate async handlers or unit tests following an established pattern. ## Mental Model: Pick the Right Executor | Workload | Rust | Python | TS/JS | Go | | --- | --- | --- | --- | --- | | I/O-bound | tokio tasks | asyncio | async/Promises | goroutines | | CPU-bound | rayon / `spawn_blocking` | `ProcessPoolExecutor` | Worker threads | goroutines (real parallelism) | | Blocking call in async | `spawn_blocking` | `run_in_executor`/`to_thread` | Worker | fine (goroutines block cheaply) | **Runtime model determines everything:** - **Rust/tokio, Go** — genuinely multi-threaded; tasks run on a thread pool → shared mutable state needs real synchronization. - **Python asyncio** — single OS thread; the GIL means asyncio ...