docs(gateway): split configuration-reference by extracting agent-defaults cluster into config-agents

docs/channels/groups.md

@@ -138,7 +138,7 @@ Want “groups can only see folder X” instead of “no host access”? Keep `w
 
 Related:
 
-- Configuration keys and defaults: [Gateway configuration](/gateway/configuration-reference#agentsdefaultssandbox)
+- Configuration keys and defaults: [Gateway configuration](/gateway/config-agents#agentsdefaultssandbox)
 - Debugging why a tool is blocked: [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated)
 - Bind mounts details: [Sandboxing](/gateway/sandboxing#custom-bind-mounts)
 

docs/cli/agents.md

@@ -37,7 +37,7 @@ Use routing bindings to pin inbound channel traffic to a specific agent.
 If you also want different visible skills per agent, configure
 `agents.defaults.skills` and `agents.list[].skills` in `openclaw.json`. See
 [Skills config](/tools/skills-config) and
-[Configuration Reference](/gateway/configuration-reference#agents-defaults-skills).
+[Configuration Reference](/gateway/config-agents#agents-defaults-skills).
 
 List bindings:
 

docs/cli/sessions.md

@@ -110,7 +110,7 @@ openclaw sessions cleanup --json
 
 Related:
 
-- Session config: [Configuration reference](/gateway/configuration-reference#session)
+- Session config: [Configuration reference](/gateway/config-agents#session)
 
 ## Related
 

docs/concepts/messages.md

@@ -149,7 +149,7 @@ Outbound message formatting is centralized in `messages`:
 - `messages.responsePrefix`, `channels.<channel>.responsePrefix`, and `channels.<channel>.accounts.<id>.responsePrefix` (outbound prefix cascade), plus `channels.whatsapp.messagePrefix` (WhatsApp inbound prefix)
 - Reply threading via `replyToMode` and per-channel defaults
 
-Details: [Configuration](/gateway/configuration-reference#messages) and channel docs.
+Details: [Configuration](/gateway/config-agents#messages) and channel docs.
 
 ## Silent replies
 

docs/concepts/model-providers.md

@@ -630,5 +630,5 @@ See also: [/gateway/configuration](/gateway/configuration) for full configuratio
 
 - [Models](/concepts/models) — model configuration and aliases
 - [Model Failover](/concepts/model-failover) — fallback chains and retry behavior
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults) — model config keys
+- [Configuration Reference](/gateway/config-agents#agent-defaults) — model config keys
 - [Providers](/providers) — per-provider setup guides

docs/concepts/models.md

@@ -288,4 +288,4 @@ This applies whenever OpenClaw regenerates `models.json`, including command-driv
 - [Image Generation](/tools/image-generation) — image model configuration
 - [Music Generation](/tools/music-generation) — music model configuration
 - [Video Generation](/tools/video-generation) — video model configuration
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults) — model config keys
+- [Configuration Reference](/gateway/config-agents#agent-defaults) — model config keys

docs/docs.json

@@ -1366,6 +1366,7 @@
                     "pages": [
                       "gateway/configuration",
                       "gateway/configuration-reference",
+                      "gateway/config-agents",
                       "gateway/configuration-examples",
                       "gateway/authentication",
                       "auth-credential-semantics",

docs/gateway/configuration.md

@@ -221,7 +221,7 @@ is skipped when a candidate contains redacted secret placeholders such as `***`.
     - Omit `agents.list[].skills` to inherit the defaults.
     - Set `agents.list[].skills: []` for no skills.
     - See [Skills](/tools/skills), [Skills config](/tools/skills-config), and
-      the [Configuration Reference](/gateway/configuration-reference#agents-defaults-skills).
+      the [Configuration Reference](/gateway/config-agents#agents-defaults-skills).
 
   </Accordion>
 
@@ -279,7 +279,7 @@ is skipped when a candidate contains redacted secret placeholders such as `***`.
     - `dmScope`: `main` (shared) | `per-peer` | `per-channel-peer` | `per-account-channel-peer`
     - `threadBindings`: global defaults for thread-bound session routing (Discord supports `/focus`, `/unfocus`, `/agents`, `/session idle`, and `/session max-age`).
     - See [Session Management](/concepts/session) for scoping, identity links, and send policy.
-    - See [full reference](/gateway/configuration-reference#session) for all fields.
+    - See [full reference](/gateway/config-agents#session) for all fields.
 
   </Accordion>
 
@@ -301,7 +301,7 @@ is skipped when a candidate contains redacted secret placeholders such as `***`.
 
     Build the image first: `scripts/sandbox-setup.sh`
 
-    See [Sandboxing](/gateway/sandboxing) for the full guide and [full reference](/gateway/configuration-reference#agentsdefaultssandbox) for all options.
+    See [Sandboxing](/gateway/sandboxing) for the full guide and [full reference](/gateway/config-agents#agentsdefaultssandbox) for all options.
 
   </Accordion>
 
@@ -459,7 +459,7 @@ is skipped when a candidate contains redacted secret placeholders such as `***`.
     }
     ```
 
-    See [Multi-Agent](/concepts/multi-agent) and [full reference](/gateway/configuration-reference#multi-agent-routing) for binding rules and per-agent access profiles.
+    See [Multi-Agent](/concepts/multi-agent) and [full reference](/gateway/config-agents#multi-agent-routing) for binding rules and per-agent access profiles.
 
   </Accordion>
 

docs/gateway/sandboxing.md

@@ -480,7 +480,7 @@ See [Multi-Agent Sandbox & Tools](/tools/multi-agent-sandbox-tools) for preceden
 ## Related docs
 
 - [OpenShell](/gateway/openshell) -- managed sandbox backend setup, workspace modes, and config reference
-- [Sandbox Configuration](/gateway/configuration-reference#agentsdefaultssandbox)
+- [Sandbox Configuration](/gateway/config-agents#agentsdefaultssandbox)
 - [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?"
 - [Multi-Agent Sandbox & Tools](/tools/multi-agent-sandbox-tools) -- per-agent overrides and precedence
 - [Security](/gateway/security)

docs/help/faq.md

@@ -1308,7 +1308,7 @@ Quick answers plus deeper troubleshooting for real-world setups (local dev, VPS,
 
     Setup walkthrough + example config: [Groups: personal DMs + public groups](/channels/groups#pattern-personal-dms-public-groups-single-agent)
 
-    Key config reference: [Gateway configuration](/gateway/configuration-reference#agentsdefaultssandbox)
+    Key config reference: [Gateway configuration](/gateway/config-agents#agentsdefaultssandbox)
 
   </Accordion>
 

docs/providers/alibaba.md

@@ -108,7 +108,7 @@ Reference image/video mode currently requires **remote http(s) URLs**. Local fil
   <Card title="Qwen" href="/providers/qwen" icon="microchip">
     Qwen provider setup and DashScope integration.
   </Card>
-  <Card title="Configuration reference" href="/gateway/configuration-reference#agent-defaults" icon="gear">
+  <Card title="Configuration reference" href="/gateway/config-agents#agent-defaults" icon="gear">
     Agent defaults and model configuration.
   </Card>
 </CardGroup>

docs/providers/comfy.md

@@ -346,7 +346,7 @@ The `image` and `video` sections also support:
   <Card title="Provider Directory" href="/providers/index" icon="layers">
     Overview of all providers and model refs.
   </Card>
-  <Card title="Configuration reference" href="/gateway/configuration-reference#agent-defaults" icon="gear">
+  <Card title="Configuration reference" href="/gateway/config-agents#agent-defaults" icon="gear">
     Full config reference including agent defaults.
   </Card>
 </CardGroup>

docs/providers/fal.md

@@ -137,7 +137,7 @@ models, including any recently added entries.
   <Card title="Video generation" href="/tools/video-generation" icon="video">
     Shared video tool parameters and provider selection.
   </Card>
-  <Card title="Configuration reference" href="/gateway/configuration-reference#agent-defaults" icon="gear">
+  <Card title="Configuration reference" href="/gateway/config-agents#agent-defaults" icon="gear">
     Agent defaults including image and video model selection.
   </Card>
 </CardGroup>

docs/providers/runway.md

@@ -85,7 +85,7 @@ Video-to-video currently requires `runway/gen4_aleph` specifically.
   <Card title="Video generation" href="/tools/video-generation" icon="video">
     Shared tool parameters, provider selection, and async behavior.
   </Card>
-  <Card title="Configuration reference" href="/gateway/configuration-reference#agent-defaults" icon="gear">
+  <Card title="Configuration reference" href="/gateway/config-agents#agent-defaults" icon="gear">
     Agent default settings including video generation model.
   </Card>
 </CardGroup>

docs/providers/vydra.md

@@ -166,7 +166,7 @@ Vydra's apex host (`https://vydra.ai/api/v1`) currently redirects to `www`. Some
   <Card title="Video generation" href="/tools/video-generation" icon="video">
     Shared video tool parameters and provider selection.
   </Card>
-  <Card title="Configuration reference" href="/gateway/configuration-reference#agent-defaults" icon="gear">
+  <Card title="Configuration reference" href="/gateway/config-agents#agent-defaults" icon="gear">
     Agent defaults and model configuration.
   </Card>
 </CardGroup>

docs/reference/memory-config.md

@@ -436,7 +436,7 @@ runtime environment.
 ### Scope
 
 Controls which sessions can receive QMD search results. Same schema as
-[`session.sendPolicy`](/gateway/configuration-reference#session):
+[`session.sendPolicy`](/gateway/config-agents#session):
 
 ```json5
 {

docs/tools/image-generation.md

@@ -305,5 +305,5 @@ cross-provider `image_generate` contract.
 - [OpenAI](/providers/openai) — OpenAI Images provider setup
 - [Vydra](/providers/vydra) — Vydra image, video, and speech setup
 - [xAI](/providers/xai) — Grok image, video, search, code execution, and TTS setup
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults) — `imageGenerationModel` config
+- [Configuration Reference](/gateway/config-agents#agent-defaults) — `imageGenerationModel` config
 - [Models](/concepts/models) — model configuration and failover

docs/tools/multi-agent-sandbox-tools.md

@@ -369,5 +369,5 @@ After configuring multi-agent sandbox and tools:
 - [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?"
 - [Elevated Mode](/tools/elevated)
 - [Multi-Agent Routing](/concepts/multi-agent)
-- [Sandbox Configuration](/gateway/configuration-reference#agentsdefaultssandbox)
+- [Sandbox Configuration](/gateway/config-agents#agentsdefaultssandbox)
 - [Session Management](/concepts/session)

docs/tools/music-generation.md

@@ -283,7 +283,7 @@ sections are configured.
 ## Related
 
 - [Background Tasks](/automation/tasks) - task tracking for detached `music_generate` runs
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults) - `musicGenerationModel` config
+- [Configuration Reference](/gateway/config-agents#agent-defaults) - `musicGenerationModel` config
 - [ComfyUI](/providers/comfy)
 - [Google (Gemini)](/providers/google)
 - [MiniMax](/providers/minimax)

docs/tools/pdf.md

@@ -188,4 +188,4 @@ Page-filtered fallback model:
 ## Related
 
 - [Tools Overview](/tools) — all available agent tools
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults) — pdfMaxBytesMb and pdfMaxPages config
+- [Configuration Reference](/gateway/config-agents#agent-defaults) — pdfMaxBytesMb and pdfMaxPages config

docs/tools/video-generation.md

@@ -437,5 +437,5 @@ openclaw config set agents.defaults.videoGenerationModel.primary "qwen/wan2.6-t2
 - [Together AI](/providers/together)
 - [Vydra](/providers/vydra)
 - [xAI](/providers/xai)
-- [Configuration Reference](/gateway/configuration-reference#agent-defaults)
+- [Configuration Reference](/gateway/config-agents#agent-defaults)
 - [Models](/concepts/models)