docs: close Drive/Docs/Sheets evaluation and complete Google Workspace tasks

WIP.drive-docs-sheets.md

@@ -1,80 +1,77 @@
 # WIP.drive-docs-sheets.md
 
 ## Status
-Status: `proposed`
+Status: `closed`
 Owner: `zap`
 Opened: `2026-03-12`
+Decision: `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
+## Decision
 
-## 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.
+**All three surfaces: NO - defer for now**
 
-## 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.
+### Rationale
 
-## Questions to answer
-### Drive
-Possible useful verbs:
-- `search_drive_files`
-- `list_drive_files`
-- `get_drive_file_metadata`
-- `move_drive_file`
-- `trash_drive_file`
+The Gmail + Calendar integration succeeded because they map cleanly to the approval/queue pattern:
 
-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?
+- **Discrete actions:** One-shot operations (send draft, create event)
+- **Clear audit value:** Each action is a standalone event worth recording
+- **Low iteration cost:** No back-and-forth editing required
+- **Operator clarity:** "Send this email" / "Create this event" are clear human decisions
 
-### Docs
-Possible useful verbs:
-- `create_doc`
-- `append_doc_text`
-- `replace_doc_text`
-- `get_doc_text`
+Drive / Docs / Sheets don't fit this pattern as naturally:
 
-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?
+#### Drive
+- Read/search operations are discovery tools, not approval-worthy events
+- File management (move, trash) is edge case and rare in automation flows
+- Direct `gog drive ...` usage is simpler for most cases
+- **Verdict:** Overkill to queue through n8n for standard file ops
 
-### Sheets
-Possible useful verbs:
-- `read_sheet_range`
-- `append_sheet_rows`
-- `update_sheet_cells`
-- `create_sheet_tab`
+#### Docs
+- Document editing is inherently iterative - you need to see, tweak, see again
+- Approval gating for "create this doc" is fine, but then what?
+- The real value is in the editing loop, not the initial create action
+- Document work belongs in focused tool flows, not a one-shot queue
+- **Verdict:** Wrong pattern for the action bus
 
-Questions:
-- Is Sheets the highest-leverage next action surface because it fits queueable structured writes?
-- If yes, what is the minimum safe starter set?
+#### Sheets
+- Strongest candidate (structured writes map well to approval)
+- But without a clear use case, this is premature optimization
+- Append/update flows are useful *if* you have a structured data pipeline
+- We don't have that yet, so building it now is YAGNI
+- **Verdict:** Highest-priority "if needed later" item, but not today
 
-## 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.
+## When to revisit
 
-## 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.
+Revisit each surface only when a concrete use case appears:
 
-## If implemented later
-Use a fresh implementation session and promote the chosen scope into `WIP.md` before coding.
+- **Drive:** If you need approval-gated file moves/trash for an automation workflow
+- **Docs:** If you have a "draft document → review → approve → publish" pattern that fits queueing
+- **Sheets:** If you need structured data logging/metrics with an audit trail
+
+## Recommendation preserved
+
+Keep the action bus focused on the patterns that work:
+- Notification routing (already implemented)
+- Gmail actions (already implemented)
+- Calendar actions (already implemented)
+- Future surface additions should pass the same "discrete, approval-worthy, low-iteration" test
+
+## Evidence referenced
+- `WIP.md` — Gmail + Calendar completion record
+- `skills/n8n-webhook/references/openclaw-action.md` — current action contract
+- `skills/n8n-webhook/assets/openclaw-action.workflow.json` — live workflow
+
+## Success criteria met
+- ✅ One-page recommendation covering Drive / Docs / Sheets
+- ✅ Clear go / no-go per surface
+- ✅ No implementation scope added
+- ✅ Preserved the compact operator contract for future use
+
+## Next actions
+- Update `memory/2026-03-12.md` with this decision
+- Close out the Google Workspace n8n work in `memory/tasks.json`
+- Consider syncing `feat/n8n-action-bus-v2` to the LAN Gitea repo for backup/review