History

Gud Boi b95e7c796e .data: reconnect after websocket reader close errors A Binance Ping racing local socket closure makes trio-websocket's reader send a Pong while wsproto is LOCAL_CLOSING. That reader nursery error escapes proxy_msgs(), then tears down brokerd and pikerd instead of restoring quote delivery. Classify NoBsWs.recon_errors around the entire websocket context, with collapse_eg() outside it so a singleton reader exit group reaches the reconnect handler. Invalidate the stale connected event and socket reference before retrying. Keep retry sleep unshielded so parent cancellation stops recovery promptly. Deats, - Add real loopback websocket coverage: TCP, handshake, Ping, reader dispatch and wsproto's actual Pong validation. - Control only the first client Ping's protocol-state ordering, withholding its Close frame to prevent a peer response racing the deterministic LOCAL_CLOSING reproducer. - Require fresh data on a replacement connection, plus exactly one connection when cancelling at the reader or retry boundary. - Use RuntimeError for the unexpected-failure control: LocalProtocolError is now a recoverable connection failure. - Preserve the original unexpected exception with bare raise, and assert its identity in the test. Log recoverable errors with the websocket URL and the underlying traceback. This is a local follow-up, not another downstream cherry-pick. The earlier wrapper suppressed escaped communication failures; `97eb8347` deliberately re-raised them. Retain that outer error visibility rather than restoring suppression without recovery. The isolated baseline reproduces the live Pong failure; all 13 selected Binance/websocket cases pass with this fix. Human live qualification remains separate from these loopback regressions. Follow-up-to: `97eb834799` Original-equivalent: `d50ab6124c` Related-history: `3d83b61f3f` Prompt-IO: ai/prompt-io/opencode/20261028T160846Z_7242dcb9_websocket_close.md (this patch was generated in some part by `opencode` using `gpt-6.1-sol` (`openai`))		2026-10-28 12:48:06 -04:00
..
claude-code	Add `ai/` integration docs w/ `/commit-msg` usage	2026-03-05 15:30:34 -05:00
prompt-io	.data: reconnect after websocket reader close errors	2026-10-28 12:48:06 -04:00
README.md	Add `ai/` integration docs w/ `/commit-msg` usage	2026-03-05 15:30:34 -05:00
ib-recovery-candidate.md	Document bounded IB recovery and downstream replay	2026-10-23 11:36:29 -04:00

README.md

AI Tooling Integrations

Documentation and usage guides for AI-assisted development tools integrated with this repo.

Each subdirectory corresponds to a specific AI tool or frontend and contains usage docs for the custom skills/prompts/workflows configured for it.

Originally introduced in PR #69; track new integration ideas and proposals in issue #79.

Integrations

Tool	Directory	Status
Claude Code	`claude-code/`	active

Adding a New Integration

Create a subdirectory named after the tool (use lowercase + hyphens), then add:

A README.md covering setup, available skills/commands, and usage examples
Any tool-specific config or prompt files

ai/
├── README.md                  # <- you are here
├── claude-code/
│   └── README.md
├── opencode/                  # future
│   └── README.md
└── <your-tool>/
    └── README.md

Conventions

Skill/command names use hyphen-case (commit-msg, not commit_msg)
Each integration doc should describe what the skill does, how to invoke it, and any output artifacts it produces
Keep docs concise; link to the actual skill source files (under .claude/skills/, etc.) rather than duplicating content