fix(provider): overhaul openai-subscription retry policy (#32)

Statusless errors like service_unavailable_error/server_is_overloaded
failed fatally because retriability was an exact-match allowlist.
Classification now defaults to retrying and excludes permanent errors
by heuristic instead.

- retry budget 10m -> 24h, time-driven only (MAX_RETRIES removed)
- backoff cap 30s -> 60s; per-attempt 10m guard on send/credentials
- honor x-ratelimit-reset-* on 429 over Retry-After: pace waits at
  10m and retry until reset + 10m grace, clamped to the 24h budget
- cap all server delay hints at 10m
- reopen_stream keeps request_context in place so a cancelled reopen
  stays retryable from the first-event timeout path

Author: danielkov

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "kit"
-version = "0.1.95"
+version = "0.1.96"
 edition = "2024"
 rust-version = "1.94.0"
 publish = false
@@ -85,6 +85,7 @@ windows-sys = { version = "=0.61.2", features = [
 [dev-dependencies]
 jsonwebtoken = { version = "=11.0.0", default-features = false, features = ["aws_lc_rs", "use_pem"] }
 tempfile = "=3.27.0"
+tokio = { version = "=1.53.1", features = ["test-util"] }
 
 [patch.crates-io]
 agentkit-acp = { git = "https://github.com/danielkov/agentkit.git", rev = "4299f31ec1455ea8ee4c46b4dce8e5bec4fdc597" }