fix(core): count websocket stream failures - #50955

I checked the failure-accounting cases on head c0fd5c4 more closely.

The regressions pin three different outcomes:

• five idle-timeout failures cause the sixth request to stay on HTTP, with only five WebSocket opens
• five response-parser failures do the same
• five user interruptions do not increment the breaker; the sixth request still uses WebSocket successfully

That distinction looks important. The breaker is counting actual failed exchanges, not simply every non-terminal stream exit, and interruption does not poison the transport.

The existing reader-loss coverage also continues to protect against double-counting.

Exact-head check and test workflows are green. I did not run this against a live provider WebSocket, but the state-machine boundary itself looks directly exercised here.

Automated PR Cleanup

Thank you for contributing to opencode.

Due to the high volume of PRs from users and AI agents, we periodically close older PRs using automated criteria so maintainers can focus review time on the most active and community-supported contributions.

This PR was closed because it matched the following cleanup criteria:

• The PR was created more than 1 month ago
• The PR had fewer than 2 positive reactions
• Positive reactions are counted as thumbs-up, heart, celebration, or rocket reactions on the PR

PRs created within the last month are not affected by this cleanup.

If you believe this PR was closed incorrectly, or if you are still actively working on it, please leave a comment explaining why it should be reopened. A maintainer can review and reopen it if appropriate.

Thanks again for taking the time to contribute.