chore(sync): mirror docs from openclaw/openclaw@7686136419

2026-05-02 10:17:13 +00:00 · 2026-05-02 10:17:13 +00:00 · c04137973a
commit c04137973a
parent b09e6327a4
3 changed files with 145 additions and 2 deletions
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@ -1,5 +1,5 @@
 {
  "repository": "openclaw/openclaw",
-  "sha": "0e8bd8e75c4c4fa15af809083355df0fe5fa4029",
-  "syncedAt": "2026-05-02T10:09:08.612Z"
+  "sha": "76861364197f58aee54c2d2ba25041f9829c721c",
+  "syncedAt": "2026-05-02T10:15:14.460Z"
 }
--- a/docs/concepts/parallel-specialist-lanes.md
+++ b/docs/concepts/parallel-specialist-lanes.md
@ -0,0 +1,127 @@
+---
+summary: "Run parallel specialist agents without clogging shared model and tool capacity"
+title: "Parallel specialist lanes"
+sidebarTitle: "Specialist lanes"
+read_when:
+  - You route group chats to dedicated agents
+  - You want parallel work without one long task blocking every chat
+  - You are designing a multi-agent operations setup
+status: active
+---
+
+Parallel specialist lanes let one Gateway route different chats or rooms to
+different agents, while keeping the user experience fast. The trick is to treat
+parallelism as a scarce-resource design problem, not just as "more agents".
+
+## First principles
+
+A specialist lane only improves throughput when it reduces contention for the
+real bottlenecks:
+
+- **Session locks**: only one run should mutate a given session at a time.
+- **Global model capacity**: all visible chat runs still share provider limits.
+- **Tool capacity**: shell, browser, network, and repository work can be slower
+  than the model turn itself.
+- **Context budget**: long transcripts make every future turn slower and less
+  focused.
+- **Ownership ambiguity**: duplicate agents doing the same job waste capacity.
+
+OpenClaw already serializes runs per session and caps global parallelism through
+the [command queue](/concepts/queue). Specialist lanes add policy on top:
+which agent owns which work, what stays in chat, and what becomes background
+work.
+
+## Recommended rollout
+
+### Phase 1: lane contracts + background heavy work
+
+Give every lane a written contract in its workspace and system prompt:
+
+- **Purpose**: the work this lane owns.
+- **Non-goals**: work it should hand off instead of attempting.
+- **Chat budget**: quick answers stay in chat; long tasks should acknowledge
+  briefly, then run in a background sub-agent or task.
+- **Handoff rule**: when another lane owns the work, say where it should go and
+  provide a compact handoff summary.
+- **Tool-risk rule**: prefer the smallest tool surface that can do the job.
+
+This is the cheapest phase and fixes most clogging: one coding job no longer
+turns the research lane into molasses, and each chat keeps its own context clean.
+
+### Phase 2: priority and concurrency controls
+
+Tune queue and model capacity around the business value of each lane:
+
+```json5
+{
+  agents: {
+    defaults: {
+      maxConcurrent: 4,
+      subagents: { maxConcurrent: 8 },
+    },
+  },
+  messages: {
+    queue: {
+      mode: "collect",
+      debounceMs: 1000,
+      cap: 20,
+      drop: "summarize",
+    },
+  },
+}
+```
+
+Use direct/personal chats and production-ops agents for high-priority work. Let
+research, drafting, and batch coding move to background tasks when the system is
+busy.
+
+### Phase 3: coordinator / traffic controller
+
+Add a small coordinator pattern once multiple lanes are active:
+
+- Track active lane tasks and owners.
+- Detect duplicate requests across groups.
+- Route handoff summaries between lanes.
+- Surface only blockers, completed results, and decisions the human must make.
+
+Do not start here. A coordinator without lane contracts just coordinates chaos.
+
+## Minimal lane contract template
+
+```md
+# Lane contract
+
+## Owns
+
+- <job this lane is responsible for>
+
+## Does not own
+
+- <work to hand off>
+
+## Chat budget
+
+- Answer quick questions directly.
+- For multi-step, slow, or tool-heavy work: acknowledge briefly, spawn/background
+  the work, then return the result when complete.
+
+## Handoff
+
+If another lane owns the request, reply with:
+
+- target lane
+- objective
+- relevant context
+- exact next action
+
+## Tool posture
+
+Use the smallest tool surface that can complete the task. Avoid broad shell or
+network work unless this lane explicitly owns it.
+```
+
+## Related
+
+- [Multi-agent routing](/concepts/multi-agent)
+- [Command queue](/concepts/queue)
+- [Sub-agents](/tools/subagents)
--- a/docs/docs.json
+++ b/docs/docs.json
@ -1167,6 +1167,7 @@
                "group": "Multi-agent",
                "pages": [
                  "concepts/multi-agent",
+                  "concepts/parallel-specialist-lanes",
                  "concepts/presence",
                  "concepts/delegate-architecture"
                ]
@ -2647,6 +2648,7 @@
                "group": "Multi-agent",
                "pages": [
                  "zh-TW/concepts/multi-agent",
+                  "zh-TW/concepts/parallel-specialist-lanes",
                  "zh-TW/concepts/presence",
                  "zh-TW/concepts/delegate-architecture"
                ]
@ -3512,6 +3514,7 @@
                "group": "Multi-agent",
                "pages": [
                  "ja-JP/concepts/multi-agent",
+                  "ja-JP/concepts/parallel-specialist-lanes",
                  "ja-JP/concepts/presence",
                  "ja-JP/concepts/delegate-architecture"
                ]
@ -4377,6 +4380,7 @@
                "group": "Multi-agent",
                "pages": [
                  "es/concepts/multi-agent",
+                  "es/concepts/parallel-specialist-lanes",
                  "es/concepts/presence",
                  "es/concepts/delegate-architecture"
                ]
@ -5242,6 +5246,7 @@
                "group": "Multi-agent",
                "pages": [
                  "pt-BR/concepts/multi-agent",
+                  "pt-BR/concepts/parallel-specialist-lanes",
                  "pt-BR/concepts/presence",
                  "pt-BR/concepts/delegate-architecture"
                ]
@ -6107,6 +6112,7 @@
                "group": "Multi-agent",
                "pages": [
                  "ko/concepts/multi-agent",
+                  "ko/concepts/parallel-specialist-lanes",
                  "ko/concepts/presence",
                  "ko/concepts/delegate-architecture"
                ]
@ -6972,6 +6978,7 @@
                "group": "Multi-agent",
                "pages": [
                  "de/concepts/multi-agent",
+                  "de/concepts/parallel-specialist-lanes",
                  "de/concepts/presence",
                  "de/concepts/delegate-architecture"
                ]
@ -7837,6 +7844,7 @@
                "group": "Multi-agent",
                "pages": [
                  "fr/concepts/multi-agent",
+                  "fr/concepts/parallel-specialist-lanes",
                  "fr/concepts/presence",
                  "fr/concepts/delegate-architecture"
                ]
@ -8702,6 +8710,7 @@
                "group": "Multi-agent",
                "pages": [
                  "ar/concepts/multi-agent",
+                  "ar/concepts/parallel-specialist-lanes",
                  "ar/concepts/presence",
                  "ar/concepts/delegate-architecture"
                ]
@ -9567,6 +9576,7 @@
                "group": "Multi-agent",
                "pages": [
                  "it/concepts/multi-agent",
+                  "it/concepts/parallel-specialist-lanes",
                  "it/concepts/presence",
                  "it/concepts/delegate-architecture"
                ]
@ -10432,6 +10442,7 @@
                "group": "Multi-agent",
                "pages": [
                  "vi/concepts/multi-agent",
+                  "vi/concepts/parallel-specialist-lanes",
                  "vi/concepts/presence",
                  "vi/concepts/delegate-architecture"
                ]
@ -11297,6 +11308,7 @@
                "group": "Multi-agent",
                "pages": [
                  "nl/concepts/multi-agent",
+                  "nl/concepts/parallel-specialist-lanes",
                  "nl/concepts/presence",
                  "nl/concepts/delegate-architecture"
                ]
@ -12162,6 +12174,7 @@
                "group": "Multi-agent",
                "pages": [
                  "tr/concepts/multi-agent",
+                  "tr/concepts/parallel-specialist-lanes",
                  "tr/concepts/presence",
                  "tr/concepts/delegate-architecture"
                ]
@ -13027,6 +13040,7 @@
                "group": "Multi-agent",
                "pages": [
                  "uk/concepts/multi-agent",
+                  "uk/concepts/parallel-specialist-lanes",
                  "uk/concepts/presence",
                  "uk/concepts/delegate-architecture"
                ]
@ -13892,6 +13906,7 @@
                "group": "Multi-agent",
                "pages": [
                  "id/concepts/multi-agent",
+                  "id/concepts/parallel-specialist-lanes",
                  "id/concepts/presence",
                  "id/concepts/delegate-architecture"
                ]
@ -14757,6 +14772,7 @@
                "group": "Multi-agent",
                "pages": [
                  "pl/concepts/multi-agent",
+                  "pl/concepts/parallel-specialist-lanes",
                  "pl/concepts/presence",
                  "pl/concepts/delegate-architecture"
                ]