Update to Kapa

{
  "description": "Set up a Kapa Google Drive source so documents in a Drive are ingested. Use when the user wants Kapa to answer from files in Google Drive or a shared drive.",
  "included_files": [],
  "name": "kapa-setup-google-drive",
  "skill_md_contents": "---\nname: kapa-setup-google-drive\ndescription: Set up a Kapa Google Drive source so documents in a Drive are ingested. Use when the user wants Kapa to answer from files in Google Drive or a shared drive.\n---\n\n# Set up Google Drive\n\nConnects through OAuth, so the user approves it in their browser.\n\nUnlike the other OAuth sources, the grant belongs to the **signed-in user, not\nthe source**, and configuring a source uses it up. Connect again for each\nGoogle Drive source, and never run two Google Drive setups at the same time.\n\n## 1. Create the source\n\n`create_google_drive_source` with `project` and `name`. Keep the returned id.\n\n## 2. Connect the Drive\n\n`connect_google_drive` takes no arguments and returns the URL the user\napproves at.\n\n**Open that URL in the user's browser** and ask them to approve it.\n\n## 3. Wait for the user, then check once\n\nThe approval happens in the browser, so there is nothing to poll. Ask the user\nto tell you when they have approved it, then call\n`check_google_drive_connection` **once**. It answers with the Google account\nthat approved, or nothing if they have not finished.\n\n## 4. Choose what to ingest\n\n`list_google_drive_folders` and `list_google_drive_files` show what the\nconnected account can see. Both answer with at most 20 results, so pass `name`\nto search rather than expecting the whole Drive back.\n\nAsk the user which folders or files to ingest, and use these tools to turn\ntheir answer into ids. There is no \"everything\" option: the source reads only\nthe folders and files you name.\n\n## 5. Configure it\n\n`configure_google_drive` with `source_google_drive` and the ids:\n\n- `folder_ids_include` and `file_ids_include` take what to read. They add up:\n  named files are read on top of the files in named folders.\n- `folder_ids_exclude` and `file_ids_exclude` drop things from a wider set.\n- Pass at least one folder or file to include. With none, the configuration\n  saves but ingests nothing.\n\nNo credential travels here. The connection supplies the token and the account\nemail, so never ask the user for either.\n\n## What gets ingested\n\nGoogle Docs, Sheets and Slides are read as documents. A file the connected\naccount cannot open is skipped.\n\n## When it ingests nothing\n\nThe approving account cannot see the folders you configured. Drive permissions\nbelong to the person who approved, so a folder shared with the team but not\nwith them is invisible. Have the user check their own access before changing\nthe configuration.\n\n## Finish the job\n\nSaving the configuration starts ingestion. There is no separate publish step.\n\nThen call `list_sources` with `project_id` to confirm what the project holds.\n\n## Shared Kapa workflow rules\n\nTools act as the connected user with that user's project permissions. Resolve the intended project and use only authorized data. Do not invent credentials, source IDs, filters, or tool results. Check the available tool schema before passing arguments.\n\nExplain and obtain approval for ingestion and its quota cost before saving a configuration that starts ingestion or calling `start_crawl`; existing explicit approval for that exact action is sufficient. Ask the user to choose source scope and filters. Validate credentials and discover accessible content before saving. Keep credentials out of visible results, logs, and exported artifacts. Use a secure credential input if the host provides one.\n\nFor a web source, preview the exact configuration and inspect the extracted article content before ingestion. Report queued, running, failed, and completed states accurately. If uncertain about Kapa behavior, use `search_kapa_docs` when available.\n"
}