feat(gateway): complete openclaw phase1 queue parity v2

README.md

@@ -804,27 +804,39 @@ Per-session FIFO queue policy for concurrent gateway requests (`agent.send`).
 ```yaml
 server:
   queue:
-    mode: collect      # collect | steer | interrupt
+    mode: collect      # collect | followup | steer | steer_backlog | interrupt
     cap: 50            # max pending requests per session lane
     overflow: drop_old # drop_old | drop_new
+    debounce_ms: 0     # delay before running next queued item
+    summarize_overflow: true
     overrides:
       channels:
         ws:
-          mode: steer
+          mode: followup
           cap: 10
       sessions:
         ws:vip-user:
           mode: interrupt
           overflow: drop_new
+          debounce_ms: 100
 ```
 
 Notes:
 - `collect` keeps all queued requests (subject to `cap`).
-- `steer` and `interrupt` keep only the latest pending request while one is active.
+- `followup` keeps at most one pending item while a request is active; newer followups replace older pending items.
+- `steer` and `steer_backlog` replace pending backlog with the newest request while one is active.
+- `interrupt` uses steer-backlog queueing behavior; active work still requires `agent.cancel` for best-effort cancellation.
 - `interrupt` currently does not force-stop already running work; use `agent.cancel` for active cancellation.
+- `debounce_ms` delays the next queued execution, helping collapse bursty same-session traffic.
+- `summarize_overflow` enables richer overflow error messages and payload metadata.
 - On overflow, `drop_old` evicts the oldest pending request, `drop_new` rejects the new request.
 - Override precedence: exact `sessions` match first, then `channels`.
 
+Runtime session controls from chat commands:
+- `/queue` shows effective session queue policy.
+- `/queue set <mode|cap|overflow|debounce_ms|summarize_overflow> <value>` sets a per-session override.
+- `/queue reset` clears per-session queue overrides.
+
 ## Gateway Request Body Limit
 
 Cap inbound HTTP POST body size (webhooks and Gmail push) to reduce memory-DoS risk.