diff --git a/RESUME.md b/RESUME.md
index b51a541..6ee74b5 100644
--- a/RESUME.md
+++ b/RESUME.md
@@ -16,11 +16,21 @@ Last updated: 2026-05-22. Update this at the end of every session.
 - [x] ~~**Vaultwarden NFS cleanup**~~ — `/mnt/pve/unas/services/vaultwarden/` deleted 2026-05-22.
 - [x] ~~**apps/backrest rename**~~ — done 2026-05-22 (renamed from PVE host via ZFS subvolume path; idmapped LXC blocked it from inside CT 104).
 
+### MCP / AI stack
+- [ ] **Consolidate syncstack → MCP gateway** — `syncstack.py` cron is fragile; move LiteLLM model polling + LobeChat model-list sync into `mcp-gateway/server.py` alongside the existing plugin sync loop. Delete syncstack container + cron after.
+- [ ] **crawl4ai SSE StreamConsumed** — intermittent 502s on first request after gateway restart (race with in-flight requests from old code). Investigate if still present after a clean restart cycle; likely harmless but worth confirming.
+- [ ] **Generalize Pocket-ID import script** — current importer is hard-coded for Pocket-ID export layout; generalize to handle any v5 collection export format.
+
 ### Audits / housekeeping
 - [ ] **Zoraxy audit** — CT 108 routes: WS headers, ACME coverage, decommissioned routes, auth consistency (Tinyauth gaps). See `services/zoraxy.md`.
 - [ ] **Arcane OIDC secret** — rotation was done 2026-05-22 but Arcane has known issues with OIDC. Verify it still authenticates cleanly.
 - [ ] **AdGuard split-horizon DNS** — some internal services still resolve to public IPs instead of LAN IPs for internal clients. Needs rewrite rules audit in `services/adguard-dns.md`.
 
+## Recently completed (session continued ×2, 2026-05-22)
+
+- **crawl4ai MCP fixed**: was returning 404 on `/mcp` (streamable-HTTP). Current 0.8.6 image already has MCP over SSE at `/mcp/sse`. Added SSE transport support to `mcp-gateway/server.py`: per-request SSE round-trip with auto-initialize handshake; `transport: sse` in hardcoded SERVERS + config.json. Gateway health now shows crawl4ai ok; lobe-sync shows 27/27 servers.
+- **syncstack cron fixed**: missing `cd /opt/stacks/ai &&` prefix caused "no configuration file" every 15 min since ~May 18. Fixed. Manual run confirmed 60 models including 5 Claude models; LobeChat recreated.
+
 ## Recently completed (session continued, 2026-05-22)
 
 - **claude-max-bridge `/v1/responses` endpoint**: implemented OpenAI Responses API with `previous_response_id` chaining. Root cause of "session already in use": Claude CLI leaves session JSONL files in an un-resumable "dequeued" state after each `--print` run. Fix: maintain conversation history server-side as formatted text; inject into system prompt for continuations; always use `--no-session-persistence`. Also fixed: assistant turns in `--input-format stream-json` require `content` as array-of-blocks not string (JS error otherwise). Assistant content array format also fixed in `_parse_messages` / `_parse_responses_input`.