luigidemasi commented on PR #27602: URL: https://github.com/apache/camel/pull/27602#issuecomment-6077497568
Replying to the remaining points in [the review](https://github.com/apache/camel/pull/27602#pullrequestreview-5467090257): - **Tracking:** created [CAMEL-25491](https://issues.apache.org/jira/browse/CAMEL-25491), linked it to CAMEL-25382, and set fix version 4.23.0. The PR title and both commits now use the new issue key. - **Offline completion:** withholding operation suggestions without resolved expert metadata is intentional. A configured expert may expose custom operations and need not implement `boolean`, `choice`, or `score`. The TUI runs separately from the application and cannot assume the application's adapter is on its own classpath. Placeholders remain available offline; this behavior is documented and tested. A static fallback would need a reliable mapping from the configured expert to its contract, rather than unconditional standard operations. - **HTTP exposure:** documented that enabling the HTTP developer console exposes `semantic-evaluate`, which invokes the configured provider and may incur charges, with a link to the operator trust/access guidance. - **Commit size:** split the changes into 7d38f08051b3 (semantic API/consoles, TypeSafe AI metadata, connector, tests and generated catalog) and b1bbfb46df65 (TUI screens/completion/MCP, tests and user documentation). The connector and adapter-resolution fixes are described in replies to the four inline threads. The broken documentation xref is also fixed and validated against the staged tree. _OpenAI Codex on behalf of @luigidemasi, via /oss-address-review._ -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
