The notebook, in full. Sorted newest first.

Resilience composition in structured concurrency comes down to one rule: keep each policy a separable layer that fires visibly in logs, or rebuild the complexity you were trying to remove.

The real ceiling on a fan-out request is downstream capacity, not the thread count. One semaphore per dependency type stops a hot path from draining the pool everyone else shares. How we set them and what changes when traffic shape shifts.

Past basic fork-and-wait, two workflow shapes dominate. Streaming progress as subtasks finish works for user-facing flows. Nested scopes that mirror the service tree work for fan-out into fan-out. What each one costs.

Not every failure is a timeout. A failed risk check turns the rest of the fan-out into wasted work, so the fix is to throw inside the subtask, cancelling its siblings before they burn capacity. The pattern, the implementation, and where it backfires.

Timeouts in distributed code are routine, not exceptional. The real question is whether a missed deadline should fail the whole request or return what made it back in time. The three timeout shapes we run and when each one fits.

Most concurrency bugs in service code come from missing lifecycle, not missing parallelism. A scope that owns its forks is what makes task lifetime visible in the code that started them. The bugs that go away when scopes are right.