Keep response streams alive through connection failures

[copyberry]

Keep response streams alive through connection failures

What changed

• Classify HTTP connection failures separately from other network errors without exposing request URLs.
• For sampling requests, retry connection failures with exponential delays from 5 to 60 seconds and show a Reconnecting... waiting for network stream error.
• Preserve the normal stream retry budget while waiting for the provider to become reachable. Keep the existing bounded retry behavior for other retryable errors.

Testing

• Verify connection errors are classified without leaking URL contents.
• Verify a turn recovers after its provider becomes reachable and still applies the configured retry limit to a subsequent incomplete stream.