chore: raise default agent concurrency

CHANGELOG.md

@@ -6,6 +6,7 @@ Docs: https://docs.clawd.bot
 
 ### Changes
 - Repo: remove the Peekaboo git submodule now that the SPM release is used.
+- Gateway: raise default lane concurrency for main and sub-agent runs.
 
 ### Fixes
 - Web search: infer Perplexity base URL from API key source (direct vs OpenRouter).

docs/concepts/queue.md

@@ -12,7 +12,7 @@ We serialize inbound auto-reply runs (all channels) through a tiny in-process qu
 - Serializing avoids competing for shared resources (session files, logs, CLI stdin) and reduces the chance of upstream rate limits.
 
 ## How it works
-- A lane-aware FIFO queue drains each lane with a configurable concurrency cap (default 1).
+- A lane-aware FIFO queue drains each lane with a configurable concurrency cap (default 1 for unconfigured lanes; main defaults to 4, subagent to 8).
 - `runEmbeddedPiAgent` enqueues by **session key** (lane `session:<key>`) to guarantee only one active run per session.
 - Each session run is then queued into a **global lane** (`main` by default) so overall parallelism is capped by `agents.defaults.maxConcurrent`.
 - When verbose logging is enabled, queued runs emit a short notice if they waited more than ~2s before starting.

docs/gateway/configuration.md

@@ -1840,7 +1840,7 @@ Example:
 
 `agents.defaults.subagents` configures sub-agent defaults:
 - `model`: default model for spawned sub-agents (string or `{ primary, fallbacks }`). If omitted, sub-agents inherit the caller’s model unless overridden per agent or per call.
-- `maxConcurrent`: max concurrent sub-agent runs (default 1)
+- `maxConcurrent`: max concurrent sub-agent runs (default 8)
 - `archiveAfterMinutes`: auto-archive sub-agent sessions after N minutes (default 60; set `0` to disable)
 - Per-subagent tool policy: `tools.subagents.tools.allow` / `tools.subagents.tools.deny` (deny wins)
 
@@ -1974,7 +1974,7 @@ Notes:
 
 `agents.defaults.maxConcurrent` sets the maximum number of embedded agent runs that can
 execute in parallel across sessions. Each session is still serialized (one run
-per session key at a time). Default: 1.
+per session key at a time). Default: 4.
 
 ### `agents.defaults.sandbox`
 

docs/tools/subagents.md

@@ -118,7 +118,7 @@ Override via config:
 
 Sub-agents use a dedicated in-process queue lane:
 - Lane name: `subagent`
-- Concurrency: `agents.defaults.subagents.maxConcurrent` (default `1`)
+- Concurrency: `agents.defaults.subagents.maxConcurrent` (default `8`)
 
 ## Stopping
 

src/gateway/server-lanes.ts

@@ -3,6 +3,6 @@ import { setCommandLaneConcurrency } from "../process/command-queue.js";
 
 export function applyGatewayLaneConcurrency(cfg: ReturnType<typeof loadConfig>) {
   setCommandLaneConcurrency("cron", cfg.cron?.maxConcurrentRuns ?? 1);
-  setCommandLaneConcurrency("main", cfg.agents?.defaults?.maxConcurrent ?? 1);
+  setCommandLaneConcurrency("main", cfg.agents?.defaults?.maxConcurrent ?? 4);
-  setCommandLaneConcurrency("subagent", cfg.agents?.defaults?.subagents?.maxConcurrent ?? 1);
+  setCommandLaneConcurrency("subagent", cfg.agents?.defaults?.subagents?.maxConcurrent ?? 8);
 }

src/gateway/server-reload-handlers.ts

@@ -127,10 +127,10 @@ export function createGatewayReloadHandlers(params: {
     }
 
     setCommandLaneConcurrency("cron", nextConfig.cron?.maxConcurrentRuns ?? 1);
-    setCommandLaneConcurrency("main", nextConfig.agents?.defaults?.maxConcurrent ?? 1);
+    setCommandLaneConcurrency("main", nextConfig.agents?.defaults?.maxConcurrent ?? 4);
     setCommandLaneConcurrency(
       "subagent",
-      nextConfig.agents?.defaults?.subagents?.maxConcurrent ?? 1,
+      nextConfig.agents?.defaults?.subagents?.maxConcurrent ?? 8,
     );
 
     if (plan.hotReasons.length > 0) {