Artifact comment actions are respelled: read replaces comments, watch with on false replaces unwatch, and old names now error.
Finding fe546477ccfcf6f4
The artifact comments/watch tool now steers users toward a new action vocabulary. Use read instead of comments, watch with on:false instead of unwatch, watch with no url instead of status, and watch with replies:true instead of resume_replies. Using an old action name now produces a validation error explaining the new spelling.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
The usage page doesn't count usage that a credit covers, so that usage shows as \$0.00 there. While the credit covers your pilot, watch the **List price** column of the **Spend by channel** table at [`claude.ai/analytics/claude-tag`](https…claude-tag/overview see the edit
When the request exhausts all retries on a transient error, `attempt` equals one more than that effective limit: 11 by default, and never more than 16 unless the watchdog is set. A lower value indicates a non-retryable error such as a `400…monitoring-usage see the edit
Local-command connectors run inside the sandbox with the same network limits as Claude's code and a per-connector writable directory. Environment variables for local connectors are saved unencrypted in a configuration file readable by your…claude-science/custom-connectors see the edit
| `.mcp.json` | MCP servers bundled with this plugin. A JSON object keyed by server name: `{"mcpServers": {"<name>": {"type": "http", "url": "...", "oauth": true}}}`. A remote entry uses `type` (`http` or `sse`), not `transport`, and suppo…third-party/claude-desktop/extensions see the edit
Anthropic's documentation has since written up read, on MCP, plugins, skills, and hooks.