mirror of
https://relay.ngit.dev/npub15qydau2hjma6ngxkl2cyar74wzyjshvl65za5k5rl69264ar2exs5cyejr/ngit-grasp.git
synced 2026-10-05 15:08:24 +00:00
DanConwayDev
ff388ce184
Persistent DNS, TLS, and protocol failures were recorded in the relay naughty list, but reconnect eligibility and every scheduling path ignored that state and continued announcing and launching retries after normal health backoff. Consult the existing tracker both when deciding reconnect eligibility and at the shared connection-scheduling boundary before mutating lifecycle state or reserving worker capacity. This preserves the required first dial, suppresses all subsequent scheduling paths while the entry is live, and restores eligibility through the existing expiry behavior. Add a scenario test with a deterministic broken WebSocket endpoint that proves only the classification dial reaches it across multiple reconnect ticks and no reconnect intent is emitted. Update the defensive-measures documentation to describe the enforced behavior. This deliberately does not change error classification, expiry duration, Git-domain throttling, or transient relay backoff. Correctness assumes canonical relay URLs are used consistently by reconnect selection, the scheduler, and naughty-list recording. Validated with nix develop -c cargo test (617 library tests and all integration/doc tests green before the eligibility refinement), the full sync target after refinement (79 passed and 1 ignored), focused health tests (16 passed), and git diff --check.