docs(state): close n8n wip and seed drive docs sheets plan

WIP.drive-docs-sheets.md

@@ -0,0 +1,80 @@
+# WIP.drive-docs-sheets.md
+
+## Status
+Status: `proposed`
+Owner: `zap`
+Opened: `2026-03-12`
+
+## Purpose
+Evaluate whether the n8n Google Workspace action bus should expand beyond Gmail + Calendar into Drive / Docs / Sheets, or whether those surfaces should stay direct-tool-only for now.
+
+## Decision goal
+Produce a clear go / no-go per surface:
+- Google Drive
+- Google Docs
+- Google Sheets
+
+## Why this is a separate WIP
+Gmail + Calendar are now implemented, deployed, and smoke-tested. Drive / Docs / Sheets are a different decision because they can easily sprawl into broad CRUD coverage without the same immediate operator value.
+
+## Constraints carried forward
+- Keep `openclaw-action` as the narrow authenticated ingress.
+- Keep approval/history/state in n8n.
+- Use the host-side `gog` bridge for execution when appropriate.
+- Preserve the compact operator contract:
+  - `pending_compact`
+  - `history_compact`
+  - `operator.summary_line`
+  - `operator.execution_state`
+  - `operator.result_refs`
+- Keep approval defaults explicit by family.
+- Default to the smallest useful verb set.
+
+## Questions to answer
+### Drive
+Possible useful verbs:
+- `search_drive_files`
+- `list_drive_files`
+- `get_drive_file_metadata`
+- `move_drive_file`
+- `trash_drive_file`
+
+Questions:
+- Is Drive mainly a discovery/search surface here, or do we need mutating file-management actions?
+- Would direct `gog drive ...` usage be simpler than queueing through n8n for most cases?
+
+### Docs
+Possible useful verbs:
+- `create_doc`
+- `append_doc_text`
+- `replace_doc_text`
+- `get_doc_text`
+
+Questions:
+- Do we actually need approval-gated doc writes, or is docs work better done directly in a focused tool flow?
+- Is append/replace enough, or would structured range operations be needed too soon?
+
+### Sheets
+Possible useful verbs:
+- `read_sheet_range`
+- `append_sheet_rows`
+- `update_sheet_cells`
+- `create_sheet_tab`
+
+Questions:
+- Is Sheets the highest-leverage next action surface because it fits queueable structured writes?
+- If yes, what is the minimum safe starter set?
+
+## Initial recommendation
+- **Drive:** probably `no` for broad action-bus expansion right now; maybe `yes` for a tiny read/search surface later.
+- **Docs:** probably `no` for now unless a very specific document-drafting workflow appears.
+- **Sheets:** strongest `maybe yes` candidate because append/update flows map well to approval + audit history.
+
+## Success criteria
+- One-page recommendation covering Drive / Docs / Sheets.
+- Clear go / no-go per surface.
+- If any surface is greenlit, define only the minimum starter verbs.
+- If any surface is greenlit, specify approval defaults (`low` read-only vs `high` mutating) before implementation begins.
+
+## If implemented later
+Use a fresh implementation session and promote the chosen scope into `WIP.md` before coding.