diff --git a/HANDOFF.md b/HANDOFF.md
index b442570..699dd41 100644
--- a/HANDOFF.md
+++ b/HANDOFF.md
@@ -4,12 +4,13 @@
 Immediate baton-pass for the next fresh implementation session.
 
 ## Current objective
-Operator/polish pass is complete. Next fresh session should decide whether Drive / Docs / Sheets need action-bus verbs at all, while preserving the approval/history contract that now exists for Gmail + Calendar.
+The Gmail + Calendar n8n action-bus WIP is complete and live. Next fresh session should review `WIP.drive-docs-sheets.md` and decide whether Drive / Docs / Sheets need action-bus verbs at all, while preserving the approval/history contract that now exists for Gmail + Calendar.
 
 ## Use these state files first
-1. `WIP.md` — full standing plan and checkpoints
-2. `memory/2026-03-12.md` — detailed execution history and evidence
-3. `memory/tasks.json` — task status tracking
+1. `WIP.md` — completed Google Workspace + n8n implementation record
+2. `WIP.drive-docs-sheets.md` — proposed next-phase decision WIP
+3. `memory/2026-03-12.md` — detailed execution history and evidence
+4. `memory/tasks.json` — task status tracking
 
 ## What is already true
 - `openclaw-action` is live in n8n and active.
@@ -59,9 +60,10 @@ Operator/polish pass is complete. Next fresh session should decide whether Drive
 - Added docs/test payloads/validator coverage for the expanded calendar contract.
 
 ## Highest-priority next actions
-1. Decide whether Drive / Docs / Sheets need action-bus verbs or should stay direct-tool only.
-2. If new Google actions are added, keep approval defaults explicit by family (`notification`, `gmail`, `calendar`, `manual`).
+1. Review `WIP.drive-docs-sheets.md` and make a go / no-go call per surface: Drive, Docs, Sheets.
+2. If any new Google actions are added, keep approval defaults explicit by family (`notification`, `gmail`, `calendar`, `manual`, and any new family names).
 3. Preserve compact operator reporting (`pending_compact`, `history_compact`, `summary_line`, `result_refs`) for any new approval-backed actions.
+4. Keep the live deployment habit: after implementation, sync the live workflow and run a safe smoke test instead of trusting static validation alone.
 
 ## Success criteria for the next session
 - Clear go/no-go decision on expanding beyond Gmail + Calendar.
diff --git a/WIP.drive-docs-sheets.md b/WIP.drive-docs-sheets.md
new file mode 100644
index 0000000..41a3813
--- /dev/null
+++ b/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.
diff --git a/WIP.md b/WIP.md
index 5627566..f88090a 100644
--- a/WIP.md
+++ b/WIP.md
@@ -7,9 +7,10 @@ Google Workspace + n8n integration
 Use OpenClaw as the brain, n8n as the orchestration layer, and Google Workspace as a real execution surface for Gmail/Calendar workflows.
 
 ## Current status
-Status: `in-progress`
+Status: `completed`
 Owner: `zap`
 Started: `2026-03-12`
+Completed: `2026-03-12`
 
 ### Architecture decision
 - Keep `openclaw-action` as the narrow authenticated ingress into n8n.
@@ -39,6 +40,7 @@ Started: `2026-03-12`
 
 ### n8n action bus
 - [x] Live `openclaw-action` workflow exists and is active.
+- [x] Live workflow re-synced from the current workspace asset after implementation completed.
 - [x] Core actions verified live:
   - `append_log`
   - `get_logs`
@@ -268,8 +270,32 @@ Targeted verification evidence:
   - `test-verify-email-draft-cycle.json` → request id `verify-email-draft-cycle-001`
   - `test-verify-calendar-event-cycle.json` → request id `verify-calendar-event-cycle-001`
 
+## Live deploy + smoke verification (2026-03-12 21:36Z)
+- Live workflow id: `Jwi54VWMdlLqYnRo`
+- Synced the active n8n workflow in place from the current `skills/n8n-webhook/assets/openclaw-action.workflow.json` asset while preserving:
+  - webhook credential binding
+  - webhook registration id
+  - active state
+- First live sync revealed the old minimal router was still running; re-synced from the current full code-node asset and re-activated successfully.
+- Safe smoke calls succeeded against the production webhook:
+  - `append_log` → `ok: true`
+  - `get_logs` → `ok: true`
+  - `list_email_drafts` → `status: queued_for_approval`
+  - `list_upcoming_events` → `status: queued_for_approval`
+  - `approval_queue_list` → `ok: true`, with `pending_compact` + `history_compact` present
+  - `fetch_and_normalize_url` against local n8n `/healthz` → `ok: true`, HTTP `200`
+  - unknown action → expected HTTP `400` / `unknown_action`
+- Smoke-created approval items were rejected and cleaned up:
+  - `approval-mmnzm1ev-yjk46sd1`
+  - `approval-mmnzm1gi-l7yszi92`
+  - `approval-mmnzmw80-kb8szya2`
+  - `approval-mmnzmw9w-c25hlml4`
+- Remaining pending queue items after cleanup were pre-existing and left untouched:
+  - `approval-mmnvgv1o-h06r397e`
+  - `approval-mmnulm6r-mfaj7ea8`
+
 ## Next-session handoff
-For the next fresh implementation session, start from `HANDOFF.md` + `WIP.md` rather than from old chat context.
+This WIP is complete. For the next fresh implementation session, review `HANDOFF.md` plus the proposed next-phase file `WIP.drive-docs-sheets.md`.
 
 Immediate target:
 - decide whether Drive / Docs / Sheets actually need action-bus verbs or can remain direct-tool workflows for now
diff --git a/memory/2026-03-12.md b/memory/2026-03-12.md
index ae9a20b..bcbbc01 100644
--- a/memory/2026-03-12.md
+++ b/memory/2026-03-12.md
@@ -199,6 +199,32 @@
     - `gog calendar delete primary example-calendar-event-id --account will@example.com --json --no-input --force --send-updates none --dry-run`
   - `python3 -m py_compile skills/n8n-webhook/scripts/resolve-approval-with-gog.py` passed.
 
+## Live deploy + smoke verification
+- Re-synced the active n8n workflow `Jwi54VWMdlLqYnRo` from the current `openclaw-action.workflow.json` asset while preserving the bound webhook credential + webhook id.
+- First sync exposed that the live workflow had still been on the older minimal router; re-synced again from the current full asset and re-activated successfully.
+- Safe production-webhook smoke calls succeeded:
+  - `append_log` → ok
+  - `get_logs` → ok
+  - `list_email_drafts` → queued_for_approval
+  - `list_upcoming_events` → queued_for_approval
+  - `approval_queue_list` → ok with `pending_compact` + `history_compact`
+  - `fetch_and_normalize_url` against local `/healthz` → ok / HTTP 200
+  - unknown action → expected HTTP 400 / `unknown_action`
+- Smoke-created pending approvals were rejected/cleaned:
+  - `approval-mmnzm1ev-yjk46sd1`
+  - `approval-mmnzm1gi-l7yszi92`
+  - `approval-mmnzmw80-kb8szya2`
+  - `approval-mmnzmw9w-c25hlml4`
+- Remaining pending items after cleanup were older pre-existing queue items and were intentionally left alone.
+
+## Subagent monitoring thresholds
+- Added an explicit operating rule for fresh implementation runs:
+  - first routine check at ~5 minutes if still running
+  - inspect child history at ~10 minutes
+  - narrow pass feels suspiciously long at ~12 minutes and should be actively intervened by ~15 minutes absent crisp progress
+  - medium bounded pass feels suspiciously long at ~20 minutes and should be actively intervened by ~25 minutes absent crisp progress
+- Also recorded the fallback rule: if the run is looping, not updating `WIP.md`, or returns an unusable result, finish the pass directly in the main session after one inspection.
+
 ## Operator/polish pass 3 (fresh subagent implementation, locally verified)
 - Added explicit approval families + defaults across the n8n action bus:
   - notification → required/high