feat: wire multi-agent config and routing

Co-authored-by: Mark Pors <1078320+pors@users.noreply.github.com>

CHANGELOG.md

@@ -15,6 +15,7 @@
 - Deps: bump Pi to 0.40.0 and drop pi-ai patch (upstream 429 fix). (#543) — thanks @mcinteerj
 - Security: per-agent mention patterns and group elevated directives now require explicit mention to avoid cross-agent toggles.
 - Config: support inline env vars in config (`env.*` / `env.vars`) and document env precedence.
+- Config: migrate routing/agent config into agents.list/agents.defaults and messages/tools/audio with default agent selection and per-agent identity config.
 - Agent: enable adaptive context pruning by default for tool-result trimming.
 - Doctor: check config/state permissions and offer to tighten them. — thanks @steipete
 - Doctor/Daemon: audit supervisor configs, add --repair/--force flows, surface service config audits in daemon status, and document user vs system services. — thanks @steipete
@@ -109,8 +110,8 @@
   - New default: DM pairing (`dmPolicy="pairing"` / `discord.dm.policy="pairing"` / `slack.dm.policy="pairing"`).
   - To keep old “open to everyone” behavior: set `dmPolicy="open"` and include `"*"` in the relevant `allowFrom` (Discord/Slack: `discord.dm.allowFrom` / `slack.dm.allowFrom`).
   - Approve requests via `clawdbot pairing list --provider <provider>` + `clawdbot pairing approve --provider <provider> <code>`.
-- Sandbox: default `agent.sandbox.scope` to `"agent"` (one container/workspace per agent). Use `"session"` for per-session isolation; `"shared"` disables cross-session isolation.
-- Timestamps in agent envelopes are now UTC (compact `YYYY-MM-DDTHH:mmZ`); removed `messages.timestampPrefix`. Add `agent.userTimezone` to tell the model the user’s local time (system prompt only).
+- Sandbox: default `agents.defaults.sandbox.scope` to `"agent"` (one container/workspace per agent). Use `"session"` for per-session isolation; `"shared"` disables cross-session isolation.
+- Timestamps in agent envelopes are now UTC (compact `YYYY-MM-DDTHH:mmZ`); removed `messages.timestampPrefix`. Add `agents.defaults.userTimezone` to tell the model the user’s local time (system prompt only).
 - Model config schema changes (auth profiles + model lists); doctor auto-migrates and the gateway rewrites legacy configs on startup.
 - Commands: gate all slash commands to authorized senders; add `/compact` to manually compact session context.
 - Groups: `whatsapp.groups`, `telegram.groups`, and `imessage.groups` now act as allowlists when set. Add `"*"` to keep allow-all behavior.
@@ -136,7 +137,7 @@
 ## 2026.1.5
 
 ### Highlights
-- Models: add image-specific model config (`agent.imageModel` + fallbacks) and scan support.
+- Models: add image-specific model config (`agents.defaults.imageModel` + fallbacks) and scan support.
 - Agent tools: new `image` tool routed to the image model (when configured).
 - Config: default model shorthands (`opus`, `sonnet`, `gpt`, `gpt-mini`, `gemini`, `gemini-flash`).
 - Docs: document built-in model shorthands + precedence (user config wins).
@@ -161,7 +162,7 @@
 - Agent tools: OpenAI-compatible tool JSON Schemas (fix `browser`, normalize union schemas).
 - Onboarding: when running from source, auto-build missing Control UI assets (`bun run ui:build`).
 - Discord/Slack: route reaction + system notifications to the correct session (no main-session bleed).
-- Agent tools: honor `agent.tools` allow/deny policy even when sandbox is off.
+- Agent tools: honor `tools.allow` / `tools.deny` policy even when sandbox is off.
 - Discord: avoid duplicate replies when OpenAI emits repeated `message_end` events.
 - Commands: unify /status (inline) and command auth across providers; group bypass for authorized control commands; remove Discord /clawd slash handler.
 - CLI: run `clawdbot agent` via the Gateway by default; use `--local` to force embedded mode.

README.md

@@ -284,7 +284,7 @@ Runbook: [iOS connect](https://docs.clawd.bot/ios).
 
 ## Agent workspace + skills
 
-- Workspace root: `~/clawd` (configurable via `agent.workspace`).
+- Workspace root: `~/clawd` (configurable via `agents.defaults.workspace`).
 - Injected prompt files: `AGENTS.md`, `SOUL.md`, `TOOLS.md`.
 - Skills: `~/clawd/skills/<skill>/SKILL.md`.
 
@@ -305,7 +305,7 @@ Minimal `~/.clawdbot/clawdbot.json` (model + defaults):
 ## Security model (important)
 
 - **Default:** tools run on the host for the **main** session, so the agent has full access when it’s just you.
-- **Group/channel safety:** set `agent.sandbox.mode: "non-main"` to run **non‑main sessions** (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
+- **Group/channel safety:** set `agents.defaults.sandbox.mode: "non-main"` to run **non‑main sessions** (groups/channels) inside per‑session Docker sandboxes; bash then runs in Docker for those sessions.
 - **Sandbox defaults:** allowlist `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`; denylist `browser`, `canvas`, `nodes`, `cron`, `discord`, `gateway`.
 
 Details: [Security guide](https://docs.clawd.bot/security) · [Docker + sandboxing](https://docs.clawd.bot/docker) · [Sandbox config](https://docs.clawd.bot/configuration)

apps/macos/Sources/Clawdbot/ClawdbotConfigFile.swift

@@ -81,22 +81,33 @@ enum ClawdbotConfigFile {
 
     static func agentWorkspace() -> String? {
         let root = self.loadDict()
-        let agent = root["agent"] as? [String: Any]
-        return agent?["workspace"] as? String
+        let agents = root["agents"] as? [String: Any]
+        let defaults = agents?["defaults"] as? [String: Any]
+        return defaults?["workspace"] as? String
     }
 
     static func setAgentWorkspace(_ workspace: String?) {
         var root = self.loadDict()
-        var agent = root["agent"] as? [String: Any] ?? [:]
+        var agents = root["agents"] as? [String: Any] ?? [:]
+        var defaults = agents["defaults"] as? [String: Any] ?? [:]
         let trimmed = workspace?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         if trimmed.isEmpty {
-            agent.removeValue(forKey: "workspace")
+            defaults.removeValue(forKey: "workspace")
         } else {
-            agent["workspace"] = trimmed
+            defaults["workspace"] = trimmed
+        }
+        if defaults.isEmpty {
+            agents.removeValue(forKey: "defaults")
+        } else {
+            agents["defaults"] = defaults
+        }
+        if agents.isEmpty {
+            root.removeValue(forKey: "agents")
+        } else {
+            root["agents"] = agents
         }
-        root["agent"] = agent
         self.saveDict(root)
-        self.logger.debug("agent workspace updated set=\(!trimmed.isEmpty)")
+        self.logger.debug("agents.defaults.workspace updated set=\(!trimmed.isEmpty)")
     }
 
     static func gatewayPassword() -> String? {

apps/macos/Sources/Clawdbot/ConfigSettings.swift

@@ -387,13 +387,20 @@ struct ConfigSettings: View {
 
     private func loadConfig() async {
         let parsed = await ConfigStore.load()
-        let agent = parsed["agent"] as? [String: Any]
-        let heartbeatMinutes = agent?["heartbeatMinutes"] as? Int
-        let heartbeatBody = agent?["heartbeatBody"] as? String
+        let agents = parsed["agents"] as? [String: Any]
+        let defaults = agents?["defaults"] as? [String: Any]
+        let heartbeat = defaults?["heartbeat"] as? [String: Any]
+        let heartbeatEvery = heartbeat?["every"] as? String
+        let heartbeatBody = heartbeat?["prompt"] as? String
         let browser = parsed["browser"] as? [String: Any]
         let talk = parsed["talk"] as? [String: Any]
 
-        let loadedModel = (agent?["model"] as? String) ?? ""
+        let loadedModel: String = {
+            if let raw = defaults?["model"] as? String { return raw }
+            if let modelDict = defaults?["model"] as? [String: Any],
+               let primary = modelDict["primary"] as? String { return primary }
+            return ""
+        }()
         if !loadedModel.isEmpty {
             self.configModel = loadedModel
             self.customModel = loadedModel
@@ -402,7 +409,13 @@ struct ConfigSettings: View {
             self.customModel = SessionLoader.fallbackModel
         }
 
-        if let heartbeatMinutes { self.heartbeatMinutes = heartbeatMinutes }
+        if let heartbeatEvery {
+            let digits = heartbeatEvery.trimmingCharacters(in: .whitespacesAndNewlines)
+                .prefix { $0.isNumber }
+            if let minutes = Int(digits) {
+                self.heartbeatMinutes = minutes
+            }
+        }
         if let heartbeatBody, !heartbeatBody.isEmpty { self.heartbeatBody = heartbeatBody }
 
         if let browser {
@@ -480,25 +493,49 @@ struct ConfigSettings: View {
     @MainActor
     private static func buildAndSaveConfig(_ draft: ConfigDraft) async -> String? {
         var root = await ConfigStore.load()
-        var agent = root["agent"] as? [String: Any] ?? [:]
+        var agents = root["agents"] as? [String: Any] ?? [:]
+        var defaults = agents["defaults"] as? [String: Any] ?? [:]
         var browser = root["browser"] as? [String: Any] ?? [:]
         var talk = root["talk"] as? [String: Any] ?? [:]
 
         let chosenModel = (draft.configModel == "__custom__" ? draft.customModel : draft.configModel)
             .trimmingCharacters(in: .whitespacesAndNewlines)
         let trimmedModel = chosenModel
-        if !trimmedModel.isEmpty { agent["model"] = trimmedModel }
+        if !trimmedModel.isEmpty {
+            var model = defaults["model"] as? [String: Any] ?? [:]
+            model["primary"] = trimmedModel
+            defaults["model"] = model
+
+            var models = defaults["models"] as? [String: Any] ?? [:]
+            if models[trimmedModel] == nil {
+                models[trimmedModel] = [:]
+            }
+            defaults["models"] = models
+        }
 
         if let heartbeatMinutes = draft.heartbeatMinutes {
-            agent["heartbeatMinutes"] = heartbeatMinutes
+            var heartbeat = defaults["heartbeat"] as? [String: Any] ?? [:]
+            heartbeat["every"] = "\(heartbeatMinutes)m"
+            defaults["heartbeat"] = heartbeat
         }
 
         let trimmedBody = draft.heartbeatBody.trimmingCharacters(in: .whitespacesAndNewlines)
         if !trimmedBody.isEmpty {
-            agent["heartbeatBody"] = trimmedBody
+            var heartbeat = defaults["heartbeat"] as? [String: Any] ?? [:]
+            heartbeat["prompt"] = trimmedBody
+            defaults["heartbeat"] = heartbeat
         }
 
-        root["agent"] = agent
+        if defaults.isEmpty {
+            agents.removeValue(forKey: "defaults")
+        } else {
+            agents["defaults"] = defaults
+        }
+        if agents.isEmpty {
+            root.removeValue(forKey: "agents")
+        } else {
+            root["agents"] = agents
+        }
 
         browser["enabled"] = draft.browserEnabled
         let trimmedUrl = draft.browserControlUrl.trimmingCharacters(in: .whitespacesAndNewlines)

apps/macos/Sources/Clawdbot/OnboardingView+Pages.swift

@@ -607,7 +607,7 @@ extension OnboardingView {
                                     let saved = await self.saveAgentWorkspace(AgentWorkspace.displayPath(for: url))
                                     if saved {
                                         self.workspaceStatus =
-                                            "Saved to ~/.clawdbot/clawdbot.json (agent.workspace)"
+                                            "Saved to ~/.clawdbot/clawdbot.json (agents.defaults.workspace)"
                                     }
                                 }
                             }

apps/macos/Sources/Clawdbot/OnboardingView+Workspace.swift

@@ -69,8 +69,9 @@ extension OnboardingView {
 
     private func loadAgentWorkspace() async -> String? {
         let root = await ConfigStore.load()
-        let agent = root["agent"] as? [String: Any]
-        return agent?["workspace"] as? String
+        let agents = root["agents"] as? [String: Any]
+        let defaults = agents?["defaults"] as? [String: Any]
+        return defaults?["workspace"] as? String
     }
 
     @discardableResult
@@ -86,17 +87,23 @@ extension OnboardingView {
     @MainActor
     private static func buildAndSaveWorkspace(_ workspace: String?) async -> (Bool, String?) {
         var root = await ConfigStore.load()
-        var agent = root["agent"] as? [String: Any] ?? [:]
+        var agents = root["agents"] as? [String: Any] ?? [:]
+        var defaults = agents["defaults"] as? [String: Any] ?? [:]
         let trimmed = workspace?.trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
         if trimmed.isEmpty {
-            agent.removeValue(forKey: "workspace")
+            defaults.removeValue(forKey: "workspace")
         } else {
-            agent["workspace"] = trimmed
+            defaults["workspace"] = trimmed
         }
-        if agent.isEmpty {
-            root.removeValue(forKey: "agent")
+        if defaults.isEmpty {
+            agents.removeValue(forKey: "defaults")
         } else {
-            root["agent"] = agent
+            agents["defaults"] = defaults
+        }
+        if agents.isEmpty {
+            root.removeValue(forKey: "agents")
+        } else {
+            root["agents"] = agents
         }
         do {
             try await ConfigStore.save(root)

docs/automation/gmail-pubsub.md

@@ -63,7 +63,7 @@ If you want a fixed channel, set `provider` + `to`. Otherwise `provider: "last"`
 uses the last delivery route (falls back to WhatsApp).
 
 To force a cheaper model for Gmail runs, set `model` in the mapping
-(`provider/model` or alias). If you enforce `agent.models`, include it there.
+(`provider/model` or alias). If you enforce `agents.defaults.models`, include it there.
 
 To customize payload handling further, add `hooks.mappings` or a JS/TS transform module
 under `hooks.transformsDir` (see [`docs/webhook.md`](https://docs.clawd.bot/automation/webhook)).

docs/automation/webhook.md

@@ -134,7 +134,7 @@ curl -X POST http://127.0.0.1:18789/hooks/agent \
   -d '{"message":"Summarize inbox","name":"Email","model":"openai/gpt-5.2-mini"}'
 ```
 
-If you enforce `agent.models`, make sure the override model is included there.
+If you enforce `agents.defaults.models`, make sure the override model is included there.
 
 ```bash
 curl -X POST http://127.0.0.1:18789/hooks/gmail \

docs/cli/index.md

@@ -488,10 +488,10 @@ Options:
 Always includes the auth overview and OAuth expiry status for profiles in the auth store.
 
 ### `models set <model>`
-Set `agent.model.primary`.
+Set `agents.defaults.model.primary`.
 
 ### `models set-image <model>`
-Set `agent.imageModel.primary`.
+Set `agents.defaults.imageModel.primary`.
 
 ### `models aliases list|add|remove`
 Options:

docs/concepts/agent-loop.md

@@ -42,7 +42,7 @@ Short, exact flow of one agent run.
 
 ## Timeouts
 - `agent.wait` default: 30s (just the wait). `timeoutMs` param overrides.
-- Agent runtime: `agent.timeoutSeconds` default 600s; enforced in `runEmbeddedPiAgent` abort timer.
+- Agent runtime: `agents.defaults.timeoutSeconds` default 600s; enforced in `runEmbeddedPiAgent` abort timer.
 
 ## Where things can end early
 - Agent timeout (abort)

docs/concepts/agent-workspace.md

@@ -15,7 +15,7 @@ sessions.
 **Important:** the workspace is the **default cwd**, not a hard sandbox. Tools
 resolve relative paths against the workspace, but absolute paths can still reach
 elsewhere on the host unless sandboxing is enabled. If you need isolation, use
-[`agent.sandbox`](/gateway/sandboxing) (and/or per‑agent sandbox config).
+[`agents.defaults.sandbox`](/gateway/sandboxing) (and/or per‑agent sandbox config).
 When sandboxing is enabled and `workspaceAccess` is not `"rw"`, tools operate
 inside a sandbox workspace under `~/.clawdbot/sandboxes`, not your host workspace.
 
@@ -53,7 +53,7 @@ only one workspace is active at a time.
 **Recommendation:** keep a single active workspace. If you no longer use the
 legacy folders, archive or move them to Trash (for example `trash ~/clawdis`).
 If you intentionally keep multiple workspaces, make sure
-`agent.workspace` points to the active one.
+`agents.defaults.workspace` points to the active one.
 
 `clawdbot doctor` warns when it detects legacy workspace directories.
 
@@ -207,7 +207,7 @@ Suggested `.gitignore` starter:
 ## Moving the workspace to a new machine
 
 1. Clone the repo to the desired path (default `~/clawd`).
-2. Set `agent.workspace` to that path in `~/.clawdbot/clawdbot.json`.
+2. Set `agents.defaults.workspace` to that path in `~/.clawdbot/clawdbot.json`.
 3. Run `clawdbot setup --workspace <path>` to seed any missing files.
 4. If you need sessions, copy `~/.clawdbot/agents/<agentId>/sessions/` from the
    old machine separately.
@@ -216,5 +216,5 @@ Suggested `.gitignore` starter:
 
 - Multi-agent routing can use different workspaces per agent. See
   `docs/provider-routing.md` for routing configuration.
-- If `agent.sandbox` is enabled, non-main sessions can use per-session sandbox
-  workspaces under `agent.sandbox.workspaceRoot`.
+- If `agents.defaults.sandbox` is enabled, non-main sessions can use per-session sandbox
+  workspaces under `agents.defaults.sandbox.workspaceRoot`.

docs/concepts/agent.md

@@ -9,19 +9,19 @@ CLAWDBOT runs a single embedded agent runtime derived from **p-mono**.
 
 ## Workspace (required)
 
-CLAWDBOT uses a single agent workspace directory (`agent.workspace`) as the agent’s **only** working directory (`cwd`) for tools and context.
+CLAWDBOT uses a single agent workspace directory (`agents.defaults.workspace`) as the agent’s **only** working directory (`cwd`) for tools and context.
 
 Recommended: use `clawdbot setup` to create `~/.clawdbot/clawdbot.json` if missing and initialize the workspace files.
 
 Full workspace layout + backup guide: [`docs/agent-workspace.md`](/concepts/agent-workspace)
 
-If `agent.sandbox` is enabled, non-main sessions can override this with
-per-session workspaces under `agent.sandbox.workspaceRoot` (see
+If `agents.defaults.sandbox` is enabled, non-main sessions can override this with
+per-session workspaces under `agents.defaults.sandbox.workspaceRoot` (see
 [`docs/configuration.md`](/gateway/configuration)).
 
 ## Bootstrap files (injected)
 
-Inside `agent.workspace`, CLAWDBOT expects these user-editable files:
+Inside `agents.defaults.workspace`, CLAWDBOT expects these user-editable files:
 - `AGENTS.md` — operating instructions + “memory”
 - `SOUL.md` — persona, boundaries, tone
 - `TOOLS.md` — user-maintained tool notes (e.g. `imsg`, `sag`, conventions)
@@ -84,9 +84,9 @@ current turn ends, then a new agent turn starts with the queued payloads. See
 [`docs/queue.md`](/concepts/queue) for mode + debounce/cap behavior.
 
 Block streaming sends completed assistant blocks as soon as they finish; disable
-via `agent.blockStreamingDefault: "off"` if you only want the final response.
-Tune the boundary via `agent.blockStreamingBreak` (`text_end` vs `message_end`; defaults to text_end).
-Control soft block chunking with `agent.blockStreamingChunk` (defaults to
+via `agents.defaults.blockStreamingDefault: "off"` if you only want the final response.
+Tune the boundary via `agents.defaults.blockStreamingBreak` (`text_end` vs `message_end`; defaults to text_end).
+Control soft block chunking with `agents.defaults.blockStreamingChunk` (defaults to
 800–1200 chars; prefers paragraph breaks, then newlines; sentences last).
 Verbose tool summaries are emitted at tool start (no debounce); Control UI
 streams tool output via agent events when available.
@@ -95,7 +95,7 @@ More details: [Streaming + chunking](/concepts/streaming).
 ## Configuration (minimal)
 
 At minimum, set:
-- `agent.workspace`
+- `agents.defaults.workspace`
 - `whatsapp.allowFrom` (strongly recommended)
 
 ---

docs/concepts/group-messages.md

@@ -7,7 +7,7 @@ read_when:
 
 Goal: let Clawd sit in WhatsApp groups, wake up only when pinged, and keep that thread separate from the personal DM session.
 
-Note: `routing.groupChat.mentionPatterns` is now used by Telegram/Discord/Slack/iMessage as well; this doc focuses on WhatsApp-specific behavior. For multi-agent setups, you can override per agent with `routing.agents.<agentId>.mentionPatterns`.
+Note: `agents.list[].groupChat.mentionPatterns` is now used by Telegram/Discord/Slack/iMessage as well; this doc focuses on WhatsApp-specific behavior. For multi-agent setups, set `agents.list[].groupChat.mentionPatterns` per agent (or use `messages.groupChat.mentionPatterns` as a global fallback).
 
 ## What’s implemented (2025-12-03)
 - Activation modes: `mention` (default) or `always`. `mention` requires a ping (real WhatsApp @-mentions via `mentionedJids`, regex patterns, or the bot’s E.164 anywhere in the text). `always` wakes the agent on every message but it should reply only when it can add meaningful value; otherwise it returns the silent token `NO_REPLY`. Defaults can be set in config (`whatsapp.groups`) and overridden per group via `/activation`. When `whatsapp.groups` is set, it also acts as a group allowlist (include `"*"` to allow all).
@@ -28,16 +28,21 @@ Add a `groupChat` block to `~/.clawdbot/clawdbot.json` so display-name pings wor
       "*": { "requireMention": true }
     }
   },
-  "routing": {
-    "groupChat": {
-      "historyLimit": 50,
-      "mentionPatterns": [
-        "@?clawd",
-        "@?clawd\\s*uk",
-        "@?clawdbot",
-        "\\+?447700900123"
-      ]
-    }
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "groupChat": {
+          "historyLimit": 50,
+          "mentionPatterns": [
+            "@?clawd",
+            "@?clawd\\s*uk",
+            "@?clawdbot",
+            "\\+?447700900123"
+          ]
+        }
+      }
+    ]
   }
 }
 ```
@@ -70,4 +75,4 @@ Only the owner number (from `whatsapp.allowFrom`, or the bot’s own E.164 when
 - Heartbeats are intentionally skipped for groups to avoid noisy broadcasts.
 - Echo suppression uses the combined batch string; if you send identical text twice without mentions, only the first will get a response.
 - Session store entries will appear as `agent:<agentId>:whatsapp:group:<jid>` in the session store (`~/.clawdbot/agents/<agentId>/sessions/sessions.json` by default); a missing entry just means the group hasn’t triggered a run yet.
-- Typing indicators in groups follow `agent.typingMode` (default: `message` when unmentioned).
+- Typing indicators in groups follow `agents.defaults.typingMode` (default: `message` when unmentioned).

docs/concepts/groups.md

@@ -88,11 +88,16 @@ Group messages require a mention unless overridden per group. Defaults live per
       "123": { requireMention: false }
     }
   },
-  routing: {
-    groupChat: {
-      mentionPatterns: ["@clawd", "clawdbot", "\\+15555550123"],
-      historyLimit: 50
-    }
+  agents: {
+    list: [
+      {
+        id: "main",
+        groupChat: {
+          mentionPatterns: ["@clawd", "clawdbot", "\\+15555550123"],
+          historyLimit: 50
+        }
+      }
+    ]
   }
 }
 ```
@@ -100,7 +105,7 @@ Group messages require a mention unless overridden per group. Defaults live per
 Notes:
 - `mentionPatterns` are case-insensitive regexes.
 - Surfaces that provide explicit mentions still pass; patterns are a fallback.
-- Per-agent override: `routing.agents.<agentId>.mentionPatterns` (useful when multiple agents share a group).
+- Per-agent override: `agents.list[].groupChat.mentionPatterns` (useful when multiple agents share a group).
 - Mention gating is only enforced when mention detection is possible (native mentions or `mentionPatterns` are configured).
 - Discord defaults live in `discord.guilds."*"` (overridable per guild/channel).
 

docs/concepts/model-failover.md

@@ -9,7 +9,7 @@ read_when:
 
 Clawdbot handles failures in two stages:
 1) **Auth profile rotation** within the current provider.
-2) **Model fallback** to the next model in `agent.model.fallbacks`.
+2) **Model fallback** to the next model in `agents.defaults.model.fallbacks`.
 
 This doc explains the runtime rules and the data that backs them.
 
@@ -82,14 +82,14 @@ State is stored in `auth-profiles.json` under `usageStats`:
 ## Model fallback
 
 If all profiles for a provider fail, Clawdbot moves to the next model in
-`agent.model.fallbacks`. This applies to auth failures, rate limits, and
+`agents.defaults.model.fallbacks`. This applies to auth failures, rate limits, and
 timeouts that exhausted profile rotation.
 
 ## Related config
 
 See [`docs/configuration.md`](/gateway/configuration) for:
 - `auth.profiles` / `auth.order`
-- `agent.model.primary` / `agent.model.fallbacks`
-- `agent.imageModel` routing
+- `agents.defaults.model.primary` / `agents.defaults.model.fallbacks`
+- `agents.defaults.imageModel` routing
 
 See [`docs/models.md`](/concepts/models) for the broader model selection and fallback overview.

docs/concepts/models.md

@@ -14,20 +14,20 @@ rotation, cooldowns, and how that interacts with fallbacks.
 
 Clawdbot selects models in this order:
 
-1) **Primary** model (`agent.model.primary` or `agent.model`).
-2) **Fallbacks** in `agent.model.fallbacks` (in order).
+1) **Primary** model (`agents.defaults.model.primary` or `agents.defaults.model`).
+2) **Fallbacks** in `agents.defaults.model.fallbacks` (in order).
 3) **Provider auth failover** happens inside a provider before moving to the
    next model.
 
 Related:
-- `agent.models` is the allowlist/catalog of models Clawdbot can use (plus aliases).
-- `agent.imageModel` is used **only when** the primary model can’t accept images.
+- `agents.defaults.models` is the allowlist/catalog of models Clawdbot can use (plus aliases).
+- `agents.defaults.imageModel` is used **only when** the primary model can’t accept images.
 
 ## Config keys (overview)
 
-- `agent.model.primary` and `agent.model.fallbacks`
-- `agent.imageModel.primary` and `agent.imageModel.fallbacks`
-- `agent.models` (allowlist + aliases + provider params)
+- `agents.defaults.model.primary` and `agents.defaults.model.fallbacks`
+- `agents.defaults.imageModel.primary` and `agents.defaults.imageModel.fallbacks`
+- `agents.defaults.models` (allowlist + aliases + provider params)
 - `models.providers` (custom providers written into `models.json`)
 
 Model refs are normalized to lowercase. Provider aliases like `z.ai/*` normalize
@@ -35,7 +35,7 @@ to `zai/*`.
 
 ## “Model is not allowed” (and why replies stop)
 
-If `agent.models` is set, it becomes the **allowlist** for `/model` and for
+If `agents.defaults.models` is set, it becomes the **allowlist** for `/model` and for
 session overrides. When a user selects a model that isn’t in that allowlist,
 Clawdbot returns:
 
@@ -46,8 +46,8 @@ Model "provider/model" is not allowed. Use /model to list available models.
 This happens **before** a normal reply is generated, so the message can feel
 like it “didn’t respond.” The fix is to either:
 
-- Add the model to `agent.models`, or
-- Clear the allowlist (remove `agent.models`), or
+- Add the model to `agents.defaults.models`, or
+- Clear the allowlist (remove `agents.defaults.models`), or
 - Pick a model from `/model list`.
 
 Example allowlist config:
@@ -123,8 +123,8 @@ Key flags:
 - `--max-age-days <days>`: skip older models
 - `--provider <name>`: provider prefix filter
 - `--max-candidates <n>`: fallback list size
-- `--set-default`: set `agent.model.primary` to the first selection
-- `--set-image`: set `agent.imageModel.primary` to the first image selection
+- `--set-default`: set `agents.defaults.model.primary` to the first selection
+- `--set-image`: set `agents.defaults.imageModel.primary` to the first image selection
 
 Probing requires an OpenRouter API key (from auth profiles or
 `OPENROUTER_API_KEY`). Without a key, use `--no-probe` to list candidates only.

docs/concepts/multi-agent.md

@@ -32,7 +32,7 @@ reach other host locations unless sandboxing is enabled. See
 - Config: `~/.clawdbot/clawdbot.json` (or `CLAWDBOT_CONFIG_PATH`)
 - State dir: `~/.clawdbot` (or `CLAWDBOT_STATE_DIR`)
 - Workspace: `~/clawd` (or `~/clawd-<agentId>`)
-- Agent dir: `~/.clawdbot/agents/<agentId>/agent` (or `routing.agents.<agentId>.agentDir`)
+- Agent dir: `~/.clawdbot/agents/<agentId>/agent` (or `agents.list[].agentDir`)
 - Sessions: `~/.clawdbot/agents/<agentId>/sessions`
 
 ### Single-agent mode (default)
@@ -52,7 +52,7 @@ Use the agent wizard to add a new isolated agent:
 clawdbot agents add work
 ```
 
-Then add `routing.bindings` (or let the wizard do it) to route inbound messages.
+Then add `bindings` (or let the wizard do it) to route inbound messages.
 
 Verify with:
 
@@ -79,7 +79,7 @@ Bindings are **deterministic** and **most-specific wins**:
 3. `teamId` (Slack)
 4. `accountId` match for a provider
 5. provider-level match (`accountId: "*"`)
-6. fallback to `routing.defaultAgentId` (default: `main`)
+6. fallback to default agent (`agents.list[].default`, else first list entry, default: `main`)
 
 ## Multiple accounts / phone numbers
 
@@ -100,39 +100,42 @@ multiple phone numbers without mixing sessions.
 
 ```js
 {
-  routing: {
-    defaultAgentId: "home",
-
-    agents: {
-      home: {
+  agents: {
+    list: [
+      {
+        id: "home",
+        default: true,
         name: "Home",
         workspace: "~/clawd-home",
         agentDir: "~/.clawdbot/agents/home/agent",
       },
-      work: {
+      {
+        id: "work",
         name: "Work",
         workspace: "~/clawd-work",
         agentDir: "~/.clawdbot/agents/work/agent",
       },
-    },
-
-    // Deterministic routing: first match wins (most-specific first).
-    bindings: [
-      { agentId: "home", match: { provider: "whatsapp", accountId: "personal" } },
-      { agentId: "work", match: { provider: "whatsapp", accountId: "biz" } },
-
-      // Optional per-peer override (example: send a specific group to work agent).
-      {
-        agentId: "work",
-        match: {
-          provider: "whatsapp",
-          accountId: "personal",
-          peer: { kind: "group", id: "1203630...@g.us" },
-        },
-      },
     ],
+  },
 
-    // Off by default: agent-to-agent messaging must be explicitly enabled + allowlisted.
+  // Deterministic routing: first match wins (most-specific first).
+  bindings: [
+    { agentId: "home", match: { provider: "whatsapp", accountId: "personal" } },
+    { agentId: "work", match: { provider: "whatsapp", accountId: "biz" } },
+
+    // Optional per-peer override (example: send a specific group to work agent).
+    {
+      agentId: "work",
+      match: {
+        provider: "whatsapp",
+        accountId: "personal",
+        peer: { kind: "group", id: "1203630...@g.us" },
+      },
+    },
+  ],
+
+  // Off by default: agent-to-agent messaging must be explicitly enabled + allowlisted.
+  tools: {
     agentToAgent: {
       enabled: false,
       allow: ["home", "work"],
@@ -160,16 +163,18 @@ Starting with v2026.1.6, each agent can have its own sandbox and tool restrictio
 
 ```js
 {
-  routing: {
-    agents: {
-      personal: {
+  agents: {
+    list: [
+      {
+        id: "personal",
         workspace: "~/clawd-personal",
         sandbox: {
           mode: "off",  // No sandbox for personal agent
         },
         // No tool restrictions - all tools available
       },
-      family: {
+      {
+        id: "family",
         workspace: "~/clawd-family",
         sandbox: {
           mode: "all",     // Always sandboxed
@@ -184,7 +189,7 @@ Starting with v2026.1.6, each agent can have its own sandbox and tool restrictio
           deny: ["bash", "write", "edit"],    // Deny others
         },
       },
-    },
+    ],
   },
 }
 ```
@@ -194,8 +199,8 @@ Starting with v2026.1.6, each agent can have its own sandbox and tool restrictio
 - **Resource control**: Sandbox specific agents while keeping others on host
 - **Flexible policies**: Different permissions per agent
 
-Note: `agent.elevated` is **global** and sender-based; it is not configurable per agent.
-If you need per-agent boundaries, use `routing.agents[id].tools` to deny `bash`.
-For group targeting, you can set `routing.agents[id].mentionPatterns` so @mentions map cleanly to the intended agent.
+Note: `tools.elevated` is **global** and sender-based; it is not configurable per agent.
+If you need per-agent boundaries, use `agents.list[].tools` to deny `bash`.
+For group targeting, use `agents.list[].groupChat.mentionPatterns` so @mentions map cleanly to the intended agent.
 
 See [Multi-Agent Sandbox & Tools](/multi-agent-sandbox-tools) for detailed examples.

docs/concepts/provider-routing.md

@@ -42,35 +42,33 @@ Examples:
 
 Routing picks **one agent** for each inbound message:
 
-1. **Exact peer match** (`routing.bindings` with `peer.kind` + `peer.id`).
+1. **Exact peer match** (`bindings` with `peer.kind` + `peer.id`).
 2. **Guild match** (Discord) via `guildId`.
 3. **Team match** (Slack) via `teamId`.
 4. **Account match** (`accountId` on the provider).
 5. **Provider match** (any account on that provider).
-6. **Default agent** (`routing.defaultAgentId`, fallback to `main`).
+6. **Default agent** (`agents.list[].default`, else first list entry, fallback to `main`).
 
 The matched agent determines which workspace and session store are used.
 
 ## Config overview
 
-- `routing.defaultAgentId`: default agent when no binding matches.
-- `routing.agents`: named agent definitions (workspace, model, etc.).
-- `routing.bindings`: map inbound providers/accounts/peers to agents.
+- `agents.list`: named agent definitions (workspace, model, etc.).
+- `bindings`: map inbound providers/accounts/peers to agents.
 
 Example:
 
 ```json5
 {
-  routing: {
-    defaultAgentId: "main",
-    agents: {
-      support: { name: "Support", workspace: "~/clawd-support" }
-    },
-    bindings: [
-      { match: { provider: "slack", teamId: "T123" }, agentId: "support" },
-      { match: { provider: "telegram", peer: { kind: "group", id: "-100123" } }, agentId: "support" }
+  agents: {
+    list: [
+      { id: "support", name: "Support", workspace: "~/clawd-support" }
     ]
-  }
+  },
+  bindings: [
+    { match: { provider: "slack", teamId: "T123" }, agentId: "support" },
+    { match: { provider: "telegram", peer: { kind: "group", id: "-100123" } }, agentId: "support" }
+  ]
 }
 ```
 

docs/concepts/queue.md

@@ -14,7 +14,7 @@ We now serialize command-based auto-replies (WhatsApp Web listener) through a ti
 ## How it works
 - A lane-aware FIFO queue drains each lane synchronously.
 - `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 `agent.maxConcurrent`.
+- 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 commands emit a short notice if they waited more than ~2s before starting.
 - Typing indicators (`onReplyStart`) still fire immediately on enqueue so user experience is unchanged while we wait our turn.
 
@@ -30,16 +30,16 @@ Inbound messages can steer the current run, wait for a followup turn, or do both
 Steer-backlog means you can get a followup response after the steered run, so
 streaming surfaces can look like duplicates. Prefer `collect`/`steer` if you want
 one response per inbound message.
-Send `/queue collect` as a standalone command (per-session) or set `routing.queue.byProvider.discord: "collect"`.
+Send `/queue collect` as a standalone command (per-session) or set `messages.queue.byProvider.discord: "collect"`.
 
 Defaults (when unset in config):
 - All surfaces → `collect`
 
-Configure globally or per provider via `routing.queue`:
+Configure globally or per provider via `messages.queue`:
 
 ```json5
 {
-  routing: {
+  messages: {
     queue: {
       mode: "collect",
       debounceMs: 1000,
@@ -67,7 +67,7 @@ Defaults: `debounceMs: 1000`, `cap: 20`, `drop: summarize`.
 
 ## Scope and guarantees
 - Applies only to config-driven command replies; plain text replies are unaffected.
-- Default lane (`main`) is process-wide for inbound + main heartbeats; set `agent.maxConcurrent` to allow multiple sessions in parallel.
+- Default lane (`main`) is process-wide for inbound + main heartbeats; set `agents.defaults.maxConcurrent` to allow multiple sessions in parallel.
 - Additional lanes may exist (e.g. `cron`) so background jobs can run in parallel without blocking inbound replies.
 - Per-session lanes guarantee that only one agent run touches a given session at a time.
 - No external dependencies or background worker threads; pure TypeScript + promises.

docs/concepts/session-pruning.md

@@ -2,7 +2,7 @@
 summary: "Session pruning: tool-result trimming to reduce context bloat"
 read_when:
   - You want to reduce LLM context growth from tool outputs
-  - You are tuning agent.contextPruning
+  - You are tuning agents.defaults.contextPruning
 ---
 # Session Pruning
 
@@ -23,7 +23,7 @@ Session pruning trims **old tool results** from the in-memory context right befo
 Pruning uses an estimated context window (chars ≈ tokens × 4). The window size is resolved in this order:
 1) Model definition `contextWindow` (from the model registry).
 2) `models.providers.*.models[].contextWindow` override.
-3) `agent.contextTokens`.
+3) `agents.defaults.contextTokens`.
 4) Default `200000` tokens.
 
 ## Modes

docs/concepts/session-tool.md

@@ -132,19 +132,19 @@ Parameters:
 - `cleanup?` (`delete|keep`, default `keep`)
 
 Allowlist:
-- `routing.agents.<agentId>.subagents.allowAgents`: list of agent ids allowed via `agentId` (`["*"]` to allow any). Default: only the requester agent.
+- `agents.list[].subagents.allowAgents`: list of agent ids allowed via `agentId` (`["*"]` to allow any). Default: only the requester agent.
 
 Discovery:
 - Use `agents_list` to discover which agent ids are allowed for `sessions_spawn`.
 
 Behavior:
 - Starts a new `agent:<agentId>:subagent:<uuid>` session with `deliver: false`.
-- Sub-agents default to the full tool set **minus session tools** (configurable via `agent.subagents.tools`).
+- Sub-agents default to the full tool set **minus session tools** (configurable via `tools.subagents.tools`).
 - Sub-agents are not allowed to call `sessions_spawn` (no sub-agent → sub-agent spawning).
 - Always non-blocking: returns `{ status: "accepted", runId, childSessionKey }` immediately.
 - After completion, Clawdbot runs a sub-agent **announce step** and posts the result to the requester chat provider.
 - Reply exactly `ANNOUNCE_SKIP` during the announce step to stay silent.
-- Sub-agent sessions are auto-archived after `agent.subagents.archiveAfterMinutes` (default: 60).
+- Sub-agent sessions are auto-archived after `agents.defaults.subagents.archiveAfterMinutes` (default: 60).
 - Announce replies include a stats line (runtime, tokens, sessionKey/sessionId, transcript path, and optional cost).
 
 ## Sandbox Session Visibility
@@ -155,10 +155,12 @@ Config:
 
 ```json5
 {
-  agent: {
-    sandbox: {
-      // default: "spawned"
-      sessionToolsVisibility: "spawned" // or "all"
+  agents: {
+    defaults: {
+      sandbox: {
+        // default: "spawned"
+        sessionToolsVisibility: "spawned" // or "all"
+      }
     }
   }
 }

docs/concepts/streaming.md

@@ -32,9 +32,9 @@ Legend:
 - `provider send`: actual outbound messages (block replies).
 
 **Controls:**
-- `agent.blockStreamingDefault`: `"on"`/`"off"` (default on).
-- `agent.blockStreamingBreak`: `"text_end"` or `"message_end"`.
-- `agent.blockStreamingChunk`: `{ minChars, maxChars, breakPreference? }`.
+- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default on).
+- `agents.defaults.blockStreamingBreak`: `"text_end"` or `"message_end"`.
+- `agents.defaults.blockStreamingChunk`: `{ minChars, maxChars, breakPreference? }`.
 - Provider hard cap: `*.textChunkLimit` (e.g., `whatsapp.textChunkLimit`).
 - Discord soft cap: `discord.maxLinesPerMessage` (default 17) splits tall replies to avoid UI clipping.
 

docs/concepts/system-prompt.md

@@ -17,7 +17,7 @@ The prompt is intentionally compact and uses fixed sections:
 - **Tooling**: current tool list + short descriptions.
 - **Skills**: tells the model how to load skill instructions on demand.
 - **Clawdbot Self-Update**: how to run `config.apply` and `update.run`.
-- **Workspace**: working directory (`agent.workspace`).
+- **Workspace**: working directory (`agents.defaults.workspace`).
 - **Workspace Files (injected)**: indicates bootstrap files are included below.
 - **Time**: UTC default + the user’s local time (already converted).
 - **Reply Tags**: optional reply tag syntax for supported providers.
@@ -43,9 +43,9 @@ Large files are truncated with a marker. Missing files inject a short missing-fi
 The Time line is compact and explicit:
 
 - Assume timestamps are **UTC** unless stated.
-- The listed **user time** is already converted to `agent.userTimezone` (if set).
+- The listed **user time** is already converted to `agents.defaults.userTimezone` (if set).
 
-Use `agent.userTimezone` in `~/.clawdbot/clawdbot.json` to change the user time zone.
+Use `agents.defaults.userTimezone` in `~/.clawdbot/clawdbot.json` to change the user time zone.
 
 ## Skills
 

docs/concepts/timezone.md

@@ -26,7 +26,7 @@ These are typically UTC ISO strings (Discord) or UTC epoch strings (Slack). We d
 
 ## User timezone for the system prompt
 
-Set `agent.userTimezone` to tell the model the user's local time zone. If it is
+Set `agents.defaults.userTimezone` to tell the model the user's local time zone. If it is
 unset, Clawdbot resolves the **host timezone at runtime** (no config write).
 
 ```json5

docs/concepts/typing-indicators.md

@@ -6,18 +6,18 @@ read_when:
 # Typing indicators
 
 Typing indicators are sent to the chat provider while a run is active. Use
-`agent.typingMode` to control **when** typing starts and `typingIntervalSeconds`
+`agents.defaults.typingMode` to control **when** typing starts and `typingIntervalSeconds`
 to control **how often** it refreshes.
 
 ## Defaults
-When `agent.typingMode` is **unset**, Clawdbot keeps the legacy behavior:
+When `agents.defaults.typingMode` is **unset**, Clawdbot keeps the legacy behavior:
 - **Direct chats**: typing starts immediately once the model loop begins.
 - **Group chats with a mention**: typing starts immediately.
 - **Group chats without a mention**: typing starts only when message text begins streaming.
 - **Heartbeat runs**: typing is disabled.
 
 ## Modes
-Set `agent.typingMode` to one of:
+Set `agents.defaults.typingMode` to one of:
 - `never` — no typing indicator, ever.
 - `instant` — start typing **as soon as the model loop begins**, even if the run
   later returns only the silent reply token.

docs/experiments/research/memory.md

@@ -8,7 +8,7 @@ read_when:
 
 # Workspace Memory v2 (offline): research notes
 
-Target: Clawd-style workspace (`agent.workspace`, default `~/clawd`) where “memory” is stored as one Markdown file per day (`memory/YYYY-MM-DD.md`) plus a small set of stable files (e.g. `memory.md`, `SOUL.md`).
+Target: Clawd-style workspace (`agents.defaults.workspace`, default `~/clawd`) where “memory” is stored as one Markdown file per day (`memory/YYYY-MM-DD.md`) plus a small set of stable files (e.g. `memory.md`, `SOUL.md`).
 
 This doc proposes an **offline-first** memory architecture that keeps Markdown as the canonical, reviewable source of truth, but adds **structured recall** (search, entity summaries, confidence updates) via a derived index.
 
@@ -159,7 +159,7 @@ Recommendation: **deep integration in Clawdbot**, but keep a separable core libr
 
 ### Why integrate into Clawdbot?
 - Clawdbot already knows:
-  - the workspace path (`agent.workspace`)
+  - the workspace path (`agents.defaults.workspace`)
   - the session model + heartbeats
   - logging + troubleshooting patterns
 - You want the agent itself to call the tools:

docs/gateway/background-process.md

@@ -32,9 +32,9 @@ Environment overrides:
 - `PI_BASH_JOB_TTL_MS`: TTL for finished sessions (ms, bounded to 1m–3h)
 
 Config (preferred):
-- `agent.bash.backgroundMs` (default 10000)
-- `agent.bash.timeoutSec` (default 1800)
-- `agent.bash.cleanupMs` (default 1800000)
+- `tools.bash.backgroundMs` (default 10000)
+- `tools.bash.timeoutSec` (default 1800)
+- `tools.bash.cleanupMs` (default 1800000)
 
 ## process tool
 

docs/gateway/configuration-examples.md

@@ -189,52 +189,71 @@ Save to `~/.clawdbot/clawdbot.json` and you can DM the bot from that number.
   },
 
   // Agent runtime
-  agent: {
-    workspace: "~/clawd",
-    userTimezone: "America/Chicago",
-    model: {
-      primary: "anthropic/claude-sonnet-4-5",
-      fallbacks: ["anthropic/claude-opus-4-5", "openai/gpt-5.2"]
-    },
-    imageModel: {
-      primary: "openrouter/anthropic/claude-sonnet-4-5"
-    },
-    models: {
-      "anthropic/claude-opus-4-5": { alias: "opus" },
-      "anthropic/claude-sonnet-4-5": { alias: "sonnet" },
-      "openai/gpt-5.2": { alias: "gpt" }
-    },
-    thinkingDefault: "low",
-    verboseDefault: "off",
-    elevatedDefault: "on",
-    blockStreamingDefault: "on",
-    blockStreamingBreak: "text_end",
-    blockStreamingChunk: {
-      minChars: 800,
-      maxChars: 1200,
-      breakPreference: "paragraph"
-    },
-    timeoutSeconds: 600,
-    mediaMaxMb: 5,
-    typingIntervalSeconds: 5,
-    maxConcurrent: 3,
-    tools: {
-      allow: ["bash", "process", "read", "write", "edit"],
-      deny: ["browser", "canvas"]
-    },
+  agents: {
+    defaults: {
+      workspace: "~/clawd",
+      userTimezone: "America/Chicago",
+      model: {
+        primary: "anthropic/claude-sonnet-4-5",
+        fallbacks: ["anthropic/claude-opus-4-5", "openai/gpt-5.2"]
+      },
+      imageModel: {
+        primary: "openrouter/anthropic/claude-sonnet-4-5"
+      },
+      models: {
+        "anthropic/claude-opus-4-5": { alias: "opus" },
+        "anthropic/claude-sonnet-4-5": { alias: "sonnet" },
+        "openai/gpt-5.2": { alias: "gpt" }
+      },
+      thinkingDefault: "low",
+      verboseDefault: "off",
+      elevatedDefault: "on",
+      blockStreamingDefault: "on",
+      blockStreamingBreak: "text_end",
+      blockStreamingChunk: {
+        minChars: 800,
+        maxChars: 1200,
+        breakPreference: "paragraph"
+      },
+      timeoutSeconds: 600,
+      mediaMaxMb: 5,
+      typingIntervalSeconds: 5,
+      maxConcurrent: 3,
+      heartbeat: {
+        every: "30m",
+        model: "anthropic/claude-sonnet-4-5",
+        target: "last",
+        to: "+15555550123",
+        prompt: "HEARTBEAT",
+        ackMaxChars: 30
+      },
+      sandbox: {
+        mode: "non-main",
+        perSession: true,
+        workspaceRoot: "~/.clawdbot/sandboxes",
+        docker: {
+          image: "clawdbot-sandbox:bookworm-slim",
+          workdir: "/workspace",
+          readOnlyRoot: true,
+          tmpfs: ["/tmp", "/var/tmp", "/run"],
+          network: "none",
+          user: "1000:1000"
+        },
+        browser: {
+          enabled: false
+        }
+      }
+    }
+  },
+
+  tools: {
+    allow: ["bash", "process", "read", "write", "edit"],
+    deny: ["browser", "canvas"],
     bash: {
       backgroundMs: 10000,
       timeoutSec: 1800,
       cleanupMs: 1800000
     },
-    heartbeat: {
-      every: "30m",
-      model: "anthropic/claude-sonnet-4-5",
-      target: "last",
-      to: "+15555550123",
-      prompt: "HEARTBEAT",
-      ackMaxChars: 30
-    },
     elevated: {
       enabled: true,
       allowFrom: {
@@ -246,22 +265,6 @@ Save to `~/.clawdbot/clawdbot.json` and you can DM the bot from that number.
         imessage: ["user@example.com"],
         webchat: ["session:demo"]
       }
-    },
-    sandbox: {
-      mode: "non-main",
-      perSession: true,
-      workspaceRoot: "~/.clawdbot/sandboxes",
-      docker: {
-        image: "clawdbot-sandbox:bookworm-slim",
-        workdir: "/workspace",
-        readOnlyRoot: true,
-        tmpfs: ["/tmp", "/var/tmp", "/run"],
-        network: "none",
-        user: "1000:1000"
-      },
-      browser: {
-        enabled: false
-      }
     }
   },
 

docs/gateway/configuration.md

@@ -9,11 +9,11 @@ CLAWDBOT reads an optional **JSON5** config from `~/.clawdbot/clawdbot.json` (co
 
 If the file is missing, CLAWDBOT uses safe-ish defaults (embedded Pi agent + per-sender sessions + workspace `~/clawd`). You usually only need a config to:
 - restrict who can trigger the bot (`whatsapp.allowFrom`, `telegram.allowFrom`, etc.)
-- control group allowlists + mention behavior (`whatsapp.groups`, `telegram.groups`, `discord.guilds`, `routing.groupChat`)
+- control group allowlists + mention behavior (`whatsapp.groups`, `telegram.groups`, `discord.guilds`, `agents.list[].groupChat`)
 - customize message prefixes (`messages`)
-- set the agent's workspace (`agent.workspace`)
-- tune the embedded agent (`agent`) and session behavior (`session`)
-- set the agent's identity (`identity`)
+- set the agent's workspace (`agents.defaults.workspace` or `agents.list[].workspace`)
+- tune the embedded agent defaults (`agents.defaults`) and session behavior (`session`)
+- set per-agent identity (`agents.list[].identity`)
 
 > **New to configuration?** Check out the [Configuration Examples](/gateway/configuration-examples) guide for complete examples with detailed explanations!
 
@@ -39,7 +39,7 @@ Example (via `gateway call`):
 
 ```bash
 clawdbot gateway call config.apply --params '{
-  "raw": "{\\n  agent: { workspace: \\"~/clawd\\" }\\n}\\n",
+  "raw": "{\\n  agents: { defaults: { workspace: \\"~/clawd\\" } }\\n}\\n",
   "sessionKey": "agent:main:whatsapp:dm:+15555550123",
   "restartDelayMs": 1000
 }'
@@ -49,7 +49,7 @@ clawdbot gateway call config.apply --params '{
 
 ```json5
 {
-  agent: { workspace: "~/clawd" },
+  agents: { defaults: { workspace: "~/clawd" } },
   whatsapp: { allowFrom: ["+15555550123"] }
 }
 ```
@@ -65,16 +65,19 @@ To prevent the bot from responding to WhatsApp @-mentions in groups (only respon
 
 ```json5
 {
-  agent: { workspace: "~/clawd" },
+  agents: {
+    defaults: { workspace: "~/clawd" },
+    list: [
+      {
+        id: "main",
+        groupChat: { mentionPatterns: ["@clawd", "reisponde"] }
+      }
+    ]
+  },
   whatsapp: {
     // Allowlist is DMs only; including your own number enables self-chat mode.
     allowFrom: ["+15555550123"],
     groups: { "*": { requireMention: true } }
-  },
-  routing: {
-    groupChat: {
-      mentionPatterns: ["@clawd", "reisponde"]
-    }
   }
 }
 ```
@@ -175,17 +178,21 @@ rotation order used for failover.
 }
 ```
 
-### `identity`
+### `agents.list[].identity`
 
-Optional agent identity used for defaults and UX. This is written by the macOS onboarding assistant.
+Optional per-agent identity used for defaults and UX. This is written by the macOS onboarding assistant.
 
 If set, CLAWDBOT derives defaults (only when you haven’t set them explicitly):
-- `messages.ackReaction` from `identity.emoji` (falls back to 👀)
-- `routing.groupChat.mentionPatterns` from `identity.name` (so “@Samantha” works in groups across Telegram/Slack/Discord/iMessage/WhatsApp)
+- `messages.ackReaction` from the **active agent**’s `identity.emoji` (falls back to 👀)
+- `agents.list[].groupChat.mentionPatterns` from the agent’s `identity.name`/`identity.emoji` (so “@Samantha” works in groups across Telegram/Slack/Discord/iMessage/WhatsApp)
 
 ```json5
 {
-  identity: { name: "Samantha", theme: "helpful sloth", emoji: "🦥" }
+  agents: {
+    list: [
+      { id: "main", identity: { name: "Samantha", theme: "helpful sloth", emoji: "🦥" } }
+    ]
+  }
 }
 ```
 
@@ -311,25 +318,26 @@ Notes:
 - `default` is used when `accountId` is omitted (CLI + routing).
 - Env tokens only apply to the **default** account.
 - Base provider settings (group policy, mention gating, etc.) apply to all accounts unless overridden per account.
-- Use `routing.bindings[].match.accountId` to route each account to a different agent.
+- Use `bindings[].match.accountId` to route each account to a different agents.defaults.
 
-### `routing.groupChat`
+### Group chat mention gating (`agents.list[].groupChat` + `messages.groupChat`)
 
 Group messages default to **require mention** (either metadata mention or regex patterns). Applies to WhatsApp, Telegram, Discord, and iMessage group chats.
 
 **Mention types:**
 - **Metadata mentions**: Native platform @-mentions (e.g., WhatsApp tap-to-mention). Ignored in WhatsApp self-chat mode (see `whatsapp.allowFrom`).
-- **Text patterns**: Regex patterns defined in `mentionPatterns`. Always checked regardless of self-chat mode.
+- **Text patterns**: Regex patterns defined in `agents.list[].groupChat.mentionPatterns`. Always checked regardless of self-chat mode.
 - Mention gating is enforced only when mention detection is possible (native mentions or at least one `mentionPattern`).
- - Per-agent override: `routing.agents.<agentId>.mentionPatterns` (useful when multiple agents share a group).
 
 ```json5
 {
-  routing: {
-    groupChat: {
-      mentionPatterns: ["@clawd", "clawdbot", "clawd"],
-      historyLimit: 50
-    }
+  messages: {
+    groupChat: { historyLimit: 50 }
+  },
+  agents: {
+    list: [
+      { id: "main", groupChat: { mentionPatterns: ["@clawd", "clawdbot", "clawd"] } }
+    ]
   }
 }
 ```
@@ -337,11 +345,11 @@ Group messages default to **require mention** (either metadata mention or regex
 Per-agent override (takes precedence when set, even `[]`):
 ```json5
 {
-  routing: {
-    agents: {
-      work: { mentionPatterns: ["@workbot", "\\+15555550123"] },
-      personal: { mentionPatterns: ["@homebot", "\\+15555550999"] }
-    }
+  agents: {
+    list: [
+      { id: "work", groupChat: { mentionPatterns: ["@workbot", "\\+15555550123"] } },
+      { id: "personal", groupChat: { mentionPatterns: ["@homebot", "\\+15555550999"] } }
+    ]
   }
 }
 ```
@@ -356,11 +364,16 @@ To respond **only** to specific text triggers (ignoring native @-mentions):
     allowFrom: ["+15555550123"],
     groups: { "*": { requireMention: true } }
   },
-  routing: {
-    groupChat: {
-      // Only these text patterns will trigger responses
-      mentionPatterns: ["reisponde", "@clawd"]
-    }
+  agents: {
+    list: [
+      {
+        id: "main",
+        groupChat: {
+          // Only these text patterns will trigger responses
+          mentionPatterns: ["reisponde", "@clawd"]
+        }
+      }
+    ]
   }
 }
 ```
@@ -410,17 +423,22 @@ Notes:
 - Discord/Slack use channel allowlists (`discord.guilds.*.channels`, `slack.channels`).
 - Group DMs (Discord/Slack) are still controlled by `dm.groupEnabled` + `dm.groupChannels`.
 
-### Multi-agent routing (`routing.agents` + `routing.bindings`)
+### Multi-agent routing (`agents.list` + `bindings`)
 
-Run multiple isolated agents (separate workspace, `agentDir`, sessions) inside one Gateway. Inbound messages are routed to an agent via bindings.
+Run multiple isolated agents (separate workspace, `agentDir`, sessions) inside one Gateway.
+Inbound messages are routed to an agent via bindings.
 
-- `routing.defaultAgentId`: fallback when no binding matches (default: `main`).
-- `routing.agents.<agentId>`: per-agent overrides.
+- `agents.list[]`: per-agent overrides.
+  - `id`: stable agent id (required).
+  - `default`: optional; when multiple are set, the first wins and a warning is logged.
+    If none are set, the **first entry** in the list is the default agent.
   - `name`: display name for the agent.
-  - `workspace`: default `~/clawd-<agentId>` (for `main`, falls back to legacy `agent.workspace`).
+  - `workspace`: default `~/clawd-<agentId>` (for `main`, falls back to `agents.defaults.workspace`).
   - `agentDir`: default `~/.clawdbot/agents/<agentId>/agent`.
-  - `model`: per-agent default model (provider/model), overrides `agent.model` for that agent.
-  - `sandbox`: per-agent sandbox config (overrides `agent.sandbox`).
+  - `model`: per-agent default model (provider/model), overrides `agents.defaults.model` for that agent.
+  - `identity`: per-agent name/theme/emoji (used for mention patterns + ack reactions).
+  - `groupChat`: per-agent mention-gating (`mentionPatterns`).
+  - `sandbox`: per-agent sandbox config (overrides `agents.defaults.sandbox`).
     - `mode`: `"off"` | `"non-main"` | `"all"`
     - `workspaceAccess`: `"none"` | `"ro"` | `"rw"`
     - `scope`: `"session"` | `"agent"` | `"shared"`
@@ -428,13 +446,13 @@ Run multiple isolated agents (separate workspace, `agentDir`, sessions) inside o
     - `docker`: per-agent docker overrides (e.g. `image`, `network`, `env`, `setupCommand`, limits; ignored when `scope: "shared"`)
     - `browser`: per-agent sandboxed browser overrides (ignored when `scope: "shared"`)
     - `prune`: per-agent sandbox pruning overrides (ignored when `scope: "shared"`)
-    - `tools`: per-agent sandbox tool policy (deny wins; overrides `agent.sandbox.tools`)
   - `subagents`: per-agent sub-agent defaults.
     - `allowAgents`: allowlist of agent ids for `sessions_spawn` from this agent (`["*"]` = allow any; default: only same agent)
-  - `tools`: per-agent tool restrictions (overrides `agent.tools`; applied before sandbox tool policy).
+  - `tools`: per-agent tool restrictions (applied before sandbox tool policy).
     - `allow`: array of allowed tool names
     - `deny`: array of denied tool names (deny wins)
-- `routing.bindings[]`: routes inbound messages to an `agentId`.
+- `agents.defaults`: shared agent defaults (model, workspace, sandbox, etc.).
+- `bindings[]`: routes inbound messages to an `agentId`.
   - `match.provider` (required)
   - `match.accountId` (optional; `*` = any account; omitted = default account)
   - `match.peer` (optional; `{ kind: dm|group|channel, id }`)
@@ -446,9 +464,9 @@ Deterministic match order:
 3) `match.teamId`
 4) `match.accountId` (exact, no peer/guild/team)
 5) `match.accountId: "*"` (provider-wide, no peer/guild/team)
-6) `routing.defaultAgentId`
+6) default agent (`agents.list[].default`, else first list entry, else `"main"`)
 
-Within each match tier, the first matching entry in `routing.bindings` wins.
+Within each match tier, the first matching entry in `bindings` wins.
 
 #### Per-agent access profiles (multi-agent)
 
@@ -464,13 +482,14 @@ additional examples.
 Full access (no sandbox):
 ```json5
 {
-  routing: {
-    agents: {
-      personal: {
+  agents: {
+    list: [
+      {
+        id: "personal",
         workspace: "~/clawd-personal",
         sandbox: { mode: "off" }
       }
-    }
+    ]
   }
 }
 ```
@@ -478,9 +497,10 @@ Full access (no sandbox):
 Read-only tools + read-only workspace:
 ```json5
 {
-  routing: {
-    agents: {
-      family: {
+  agents: {
+    list: [
+      {
+        id: "family",
         workspace: "~/clawd-family",
         sandbox: {
           mode: "all",
@@ -492,7 +512,7 @@ Read-only tools + read-only workspace:
           deny: ["write", "edit", "bash", "process", "browser"]
         }
       }
-    }
+    ]
   }
 }
 ```
@@ -500,9 +520,10 @@ Read-only tools + read-only workspace:
 No filesystem access (messaging/session tools enabled):
 ```json5
 {
-  routing: {
-    agents: {
-      public: {
+  agents: {
+    list: [
+      {
+        id: "public",
         workspace: "~/clawd-public",
         sandbox: {
           mode: "all",
@@ -514,7 +535,7 @@ No filesystem access (messaging/session tools enabled):
           deny: ["read", "write", "edit", "bash", "process", "browser", "canvas", "nodes", "cron", "gateway", "image"]
         }
       }
-    }
+    ]
   }
 }
 ```
@@ -523,17 +544,16 @@ Example: two WhatsApp accounts → two agents:
 
 ```json5
 {
-  routing: {
-    defaultAgentId: "home",
-    agents: {
-      home: { workspace: "~/clawd-home" },
-      work: { workspace: "~/clawd-work" },
-    },
-    bindings: [
-      { agentId: "home", match: { provider: "whatsapp", accountId: "personal" } },
-      { agentId: "work", match: { provider: "whatsapp", accountId: "biz" } },
-    ],
+  agents: {
+    list: [
+      { id: "home", default: true, workspace: "~/clawd-home" },
+      { id: "work", workspace: "~/clawd-work" }
+    ]
   },
+  bindings: [
+    { agentId: "home", match: { provider: "whatsapp", accountId: "personal" } },
+    { agentId: "work", match: { provider: "whatsapp", accountId: "biz" } }
+  ],
   whatsapp: {
     accounts: {
       personal: {},
@@ -543,13 +563,13 @@ Example: two WhatsApp accounts → two agents:
 }
 ```
 
-### `routing.agentToAgent` (optional)
+### `tools.agentToAgent` (optional)
 
 Agent-to-agent messaging is opt-in:
 
 ```json5
 {
-  routing: {
+  tools: {
     agentToAgent: {
       enabled: false,
       allow: ["home", "work"]
@@ -558,13 +578,13 @@ Agent-to-agent messaging is opt-in:
 }
 ```
 
-### `routing.queue`
+### `messages.queue`
 
 Controls how inbound messages behave when an agent run is already active.
 
 ```json5
 {
-  routing: {
+  messages: {
     queue: {
       mode: "collect", // steer | followup | collect | steer-backlog (steer+backlog ok) | interrupt (queue=steer legacy)
       debounceMs: 1000,
@@ -859,7 +879,7 @@ Example wrapper:
 exec ssh -T mac-mini "imsg rpc"
 ```
 
-### `agent.workspace`
+### `agents.defaults.workspace`
 
 Sets the **single global workspace directory** used by the agent for file operations.
 
@@ -867,14 +887,14 @@ Default: `~/clawd`.
 
 ```json5
 {
-  agent: { workspace: "~/clawd" }
+  agents: { defaults: { workspace: "~/clawd" } }
 }
 ```
 
-If `agent.sandbox` is enabled, non-main sessions can override this with their
-own per-scope workspaces under `agent.sandbox.workspaceRoot`.
+If `agents.defaults.sandbox` is enabled, non-main sessions can override this with their
+own per-scope workspaces under `agents.defaults.sandbox.workspaceRoot`.
 
-### `agent.skipBootstrap`
+### `agents.defaults.skipBootstrap`
 
 Disables automatic creation of the workspace bootstrap files (`AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, and `BOOTSTRAP.md`).
 
@@ -882,18 +902,18 @@ Use this for pre-seeded deployments where your workspace files come from a repo.
 
 ```json5
 {
-  agent: { skipBootstrap: true }
+  agents: { defaults: { skipBootstrap: true } }
 }
 ```
 
-### `agent.userTimezone`
+### `agents.defaults.userTimezone`
 
 Sets the user’s timezone for **system prompt context** (not for timestamps in
 message envelopes). If unset, Clawdbot uses the host timezone at runtime.
 
 ```json5
 {
-  agent: { userTimezone: "America/Chicago" }
+  agents: { defaults: { userTimezone: "America/Chicago" } }
 }
 ```
 
@@ -917,7 +937,7 @@ streaming, final replies) across providers unless already present.
 
 `ackReaction` sends a best-effort emoji reaction to acknowledge inbound messages
 on providers that support reactions (Slack/Discord/Telegram). Defaults to the
-configured `identity.emoji` when set, otherwise `"👀"`. Set it to `""` to disable.
+active agent’s `identity.emoji` when set, otherwise `"👀"`. Set it to `""` to disable.
 
 `ackReactionScope` controls when reactions fire:
 - `group-mentions` (default): only when a group/room requires mentions **and** the bot was mentioned
@@ -947,22 +967,22 @@ Defaults for Talk mode (macOS/iOS/Android). Voice IDs fall back to `ELEVENLABS_V
 }
 ```
 
-### `agent`
+### `agents.defaults`
 
 Controls the embedded agent runtime (model/thinking/verbose/timeouts).
-`agent.models` defines the configured model catalog (and acts as the allowlist for `/model`).
-`agent.model.primary` sets the default model; `agent.model.fallbacks` are global failovers.
-`agent.imageModel` is optional and is **only used if the primary model lacks image input**.
-Each `agent.models` entry can include:
+`agents.defaults.models` defines the configured model catalog (and acts as the allowlist for `/model`).
+`agents.defaults.model.primary` sets the default model; `agents.defaults.model.fallbacks` are global failovers.
+`agents.defaults.imageModel` is optional and is **only used if the primary model lacks image input**.
+Each `agents.defaults.models` entry can include:
 - `alias` (optional model shortcut, e.g. `/opus`).
 - `params` (optional provider-specific API params passed through to the model request).
 
 Z.AI GLM-4.x models automatically enable thinking mode unless you:
 - set `--thinking off`, or
-- define `agent.models["zai/<model>"].params.thinking` yourself.
+- define `agents.defaults.models["zai/<model>"].params.thinking` yourself.
 
 Clawdbot also ships a few built-in alias shorthands. Defaults only apply when the model
-is already present in `agent.models`:
+is already present in `agents.defaults.models`:
 
 - `opus` -> `anthropic/claude-opus-4-5`
 - `sonnet` -> `anthropic/claude-sonnet-4-5`
@@ -975,61 +995,63 @@ If you configure the same alias name (case-insensitive) yourself, your value win
 
 ```json5
 {
-  agent: {
-    models: {
-      "anthropic/claude-opus-4-5": { alias: "Opus" },
-      "anthropic/claude-sonnet-4-1": { alias: "Sonnet" },
-      "openrouter/deepseek/deepseek-r1:free": {},
-      "zai/glm-4.7": {
-        alias: "GLM",
-        params: {
-          thinking: {
-            type: "enabled",
-            clear_thinking: false
+  agents: {
+    defaults: {
+      models: {
+        "anthropic/claude-opus-4-5": { alias: "Opus" },
+        "anthropic/claude-sonnet-4-1": { alias: "Sonnet" },
+        "openrouter/deepseek/deepseek-r1:free": {},
+        "zai/glm-4.7": {
+          alias: "GLM",
+          params: {
+            thinking: {
+              type: "enabled",
+              clear_thinking: false
+            }
           }
         }
-      }
-    },
-    model: {
-      primary: "anthropic/claude-opus-4-5",
-      fallbacks: [
-        "openrouter/deepseek/deepseek-r1:free",
-        "openrouter/meta-llama/llama-3.3-70b-instruct:free"
-      ]
-    },
-    imageModel: {
-      primary: "openrouter/qwen/qwen-2.5-vl-72b-instruct:free",
-      fallbacks: [
-        "openrouter/google/gemini-2.0-flash-vision:free"
-      ]
-    },
-    thinkingDefault: "low",
-    verboseDefault: "off",
-    elevatedDefault: "on",
-    timeoutSeconds: 600,
-    mediaMaxMb: 5,
-    heartbeat: {
-      every: "30m",
-      target: "last"
-    },
-    maxConcurrent: 3,
-    subagents: {
-      maxConcurrent: 1,
-      archiveAfterMinutes: 60
-    },
-    bash: {
-      backgroundMs: 10000,
-      timeoutSec: 1800,
-      cleanupMs: 1800000
-    },
-    contextTokens: 200000
+      },
+      model: {
+        primary: "anthropic/claude-opus-4-5",
+        fallbacks: [
+          "openrouter/deepseek/deepseek-r1:free",
+          "openrouter/meta-llama/llama-3.3-70b-instruct:free"
+        ]
+      },
+      imageModel: {
+        primary: "openrouter/qwen/qwen-2.5-vl-72b-instruct:free",
+        fallbacks: [
+          "openrouter/google/gemini-2.0-flash-vision:free"
+        ]
+      },
+      thinkingDefault: "low",
+      verboseDefault: "off",
+      elevatedDefault: "on",
+      timeoutSeconds: 600,
+      mediaMaxMb: 5,
+      heartbeat: {
+        every: "30m",
+        target: "last"
+      },
+      maxConcurrent: 3,
+      subagents: {
+        maxConcurrent: 1,
+        archiveAfterMinutes: 60
+      },
+      bash: {
+        backgroundMs: 10000,
+        timeoutSec: 1800,
+        cleanupMs: 1800000
+      },
+      contextTokens: 200000
+    }
   }
 }
 ```
 
-#### `agent.contextPruning` (tool-result pruning)
+#### `agents.defaults.contextPruning` (tool-result pruning)
 
-`agent.contextPruning` prunes **old tool results** from the in-memory context right before a request is sent to the LLM.
+`agents.defaults.contextPruning` prunes **old tool results** from the in-memory context right before a request is sent to the LLM.
 It does **not** modify the session history on disk (`*.jsonl` remains complete).
 
 This is intended to reduce token usage for chatty agents that accumulate large tool outputs over time.
@@ -1061,22 +1083,14 @@ Notes / current limitations:
 Default (adaptive):
 ```json5
 {
-  agent: {
-    contextPruning: {
-      mode: "adaptive"
-    }
-  }
+  agents: { defaults: { contextPruning: { mode: "adaptive" } } }
 }
 ```
 
 To disable:
 ```json5
 {
-  agent: {
-    contextPruning: {
-      mode: "off"
-    }
-  }
+  agents: { defaults: { contextPruning: { mode: "off" } } }
 }
 ```
 
@@ -1091,28 +1105,26 @@ Defaults (when `mode` is `"adaptive"` or `"aggressive"`):
 Example (aggressive, minimal):
 ```json5
 {
-  agent: {
-    contextPruning: {
-      mode: "aggressive"
-    }
-  }
+  agents: { defaults: { contextPruning: { mode: "aggressive" } } }
 }
 ```
 
 Example (adaptive tuned):
 ```json5
 {
-  agent: {
-    contextPruning: {
-      mode: "adaptive",
-      keepLastAssistants: 3,
-      softTrimRatio: 0.3,
-      hardClearRatio: 0.5,
-      minPrunableToolChars: 50000,
-      softTrim: { maxChars: 4000, headChars: 1500, tailChars: 1500 },
-      hardClear: { enabled: true, placeholder: "[Old tool result content cleared]" },
-      // Optional: restrict pruning to specific tools (deny wins; supports "*" wildcards)
-      tools: { deny: ["browser", "canvas"] },
+  agents: {
+    defaults: {
+      contextPruning: {
+        mode: "adaptive",
+        keepLastAssistants: 3,
+        softTrimRatio: 0.3,
+        hardClearRatio: 0.5,
+        minPrunableToolChars: 50000,
+        softTrim: { maxChars: 4000, headChars: 1500, tailChars: 1500 },
+        hardClear: { enabled: true, placeholder: "[Old tool result content cleared]" },
+        // Optional: restrict pruning to specific tools (deny wins; supports "*" wildcards)
+        tools: { deny: ["browser", "canvas"] },
+      }
     }
   }
 }
@@ -1121,36 +1133,34 @@ Example (adaptive tuned):
 See [/concepts/session-pruning](/concepts/session-pruning) for behavior details.
 
 Block streaming:
-- `agent.blockStreamingDefault`: `"on"`/`"off"` (default on).
-- `agent.blockStreamingBreak`: `"text_end"` or `"message_end"` (default: text_end).
-- `agent.blockStreamingChunk`: soft chunking for streamed blocks. Defaults to
+- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default on).
+- `agents.defaults.blockStreamingBreak`: `"text_end"` or `"message_end"` (default: text_end).
+- `agents.defaults.blockStreamingChunk`: soft chunking for streamed blocks. Defaults to
   800–1200 chars, prefers paragraph breaks (`\n\n`), then newlines, then sentences.
   Example:
   ```json5
   {
-    agent: {
-      blockStreamingChunk: { minChars: 800, maxChars: 1200 }
-    }
+    agents: { defaults: { blockStreamingChunk: { minChars: 800, maxChars: 1200 } } }
   }
   ```
 See [/concepts/streaming](/concepts/streaming) for behavior + chunking details.
 
 Typing indicators:
-- `agent.typingMode`: `"never" | "instant" | "thinking" | "message"`. Defaults to
+- `agents.defaults.typingMode`: `"never" | "instant" | "thinking" | "message"`. Defaults to
   `instant` for direct chats / mentions and `message` for unmentioned group chats.
 - `session.typingMode`: per-session override for the mode.
-- `agent.typingIntervalSeconds`: how often the typing signal is refreshed (default: 6s).
+- `agents.defaults.typingIntervalSeconds`: how often the typing signal is refreshed (default: 6s).
 - `session.typingIntervalSeconds`: per-session override for the refresh interval.
 See [/concepts/typing-indicators](/concepts/typing-indicators) for behavior details.
 
-`agent.model.primary` should be set as `provider/model` (e.g. `anthropic/claude-opus-4-5`).
-Aliases come from `agent.models.*.alias` (e.g. `Opus`).
+`agents.defaults.model.primary` should be set as `provider/model` (e.g. `anthropic/claude-opus-4-5`).
+Aliases come from `agents.defaults.models.*.alias` (e.g. `Opus`).
 If you omit the provider, CLAWDBOT currently assumes `anthropic` as a temporary
 deprecation fallback.
 Z.AI models are available as `zai/<model>` (e.g. `zai/glm-4.7`) and require
 `ZAI_API_KEY` (or legacy `Z_AI_API_KEY`) in the environment.
 
-`agent.heartbeat` configures periodic heartbeat runs:
+`agents.defaults.heartbeat` configures periodic heartbeat runs:
 - `every`: duration string (`ms`, `s`, `m`, `h`); default unit minutes. Default:
   `30m`. Set `0m` to disable.
 - `model`: optional override model for heartbeat runs (`provider/model`).
@@ -1162,31 +1172,27 @@ Z.AI models are available as `zai/<model>` (e.g. `zai/glm-4.7`) and require
 Heartbeats run full agent turns. Shorter intervals burn more tokens; be mindful
 of `every`, keep `HEARTBEAT.md` tiny, and/or choose a cheaper `model`.
 
-`agent.bash` configures background bash defaults:
+`tools.bash` configures background bash defaults:
 - `backgroundMs`: time before auto-background (ms, default 10000)
 - `timeoutSec`: auto-kill after this runtime (seconds, default 1800)
 - `cleanupMs`: how long to keep finished sessions in memory (ms, default 1800000)
 
-`agent.subagents` configures sub-agent defaults:
+`agents.defaults.subagents` configures sub-agent defaults:
 - `maxConcurrent`: max concurrent sub-agent runs (default 1)
 - `archiveAfterMinutes`: auto-archive sub-agent sessions after N minutes (default 60; set `0` to disable)
-- `tools.allow` / `tools.deny`: per-subagent tool allow/deny policy (deny wins)
+- Per-subagent tool policy: `tools.subagents.tools.allow` / `tools.subagents.tools.deny` (deny wins)
 
-`agent.tools` configures a global tool allow/deny policy (deny wins).
+`tools.allow` / `tools.deny` configure a global tool allow/deny policy (deny wins).
 This is applied even when the Docker sandbox is **off**.
 
 Example (disable browser/canvas everywhere):
 ```json5
 {
-  agent: {
-    tools: {
-      deny: ["browser", "canvas"]
-    }
-  }
+  tools: { deny: ["browser", "canvas"] }
 }
 ```
 
-`agent.elevated` controls elevated (host) bash access:
+`tools.elevated` controls elevated (host) bash access:
 - `enabled`: allow elevated mode (default true)
 - `allowFrom`: per-provider allowlists (empty = disabled)
   - `whatsapp`: E.164 numbers
@@ -1199,7 +1205,7 @@ Example (disable browser/canvas everywhere):
 Example:
 ```json5
 {
-  agent: {
+  tools: {
     elevated: {
       enabled: true,
       allowFrom: {
@@ -1212,16 +1218,16 @@ Example:
 ```
 
 Notes:
-- `agent.elevated` is **global** (not per-agent). Availability is based on sender allowlists.
+- `tools.elevated` is **global** (not per-agent). Availability is based on sender allowlists.
 - `/elevated on|off` stores state per session key; inline directives apply to a single message.
 - Elevated `bash` runs on the host and bypasses sandboxing.
 - Tool policy still applies; if `bash` is denied, elevated cannot be used.
 
-`agent.maxConcurrent` sets the maximum number of embedded agent runs that can
+`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.
 
-### `agent.sandbox`
+### `agents.defaults.sandbox`
 
 Optional **Docker sandboxing** for the embedded agent. Intended for non-main
 sessions so they cannot access your host system.
@@ -1236,7 +1242,8 @@ Defaults (if enabled):
   - `"ro"`: keep the sandbox workspace at `/workspace`, and mount the agent workspace read-only at `/agent` (disables `write`/`edit`)
   - `"rw"`: mount the agent workspace read/write at `/workspace`
 - auto-prune: idle > 24h OR age > 7d
-- tools: allow only `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn` (deny wins)
+- tool policy: allow only `bash`, `process`, `read`, `write`, `edit`, `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn` (deny wins)
+  - configure via `tools.sandbox.tools`, override per-agent via `agents.list[].tools.sandbox.tools`
 - optional sandboxed browser (Chromium + CDP, noVNC observer)
 - hardening knobs: `network`, `user`, `pidsLimit`, `memory`, `cpus`, `ulimits`, `seccompProfile`, `apparmorProfile`
 
@@ -1248,54 +1255,60 @@ Legacy: `perSession` is still supported (`true` → `scope: "session"`,
 
 ```json5
 {
-  agent: {
-    sandbox: {
-      mode: "non-main", // off | non-main | all
-      scope: "agent", // session | agent | shared (agent is default)
-      workspaceAccess: "none", // none | ro | rw
-      workspaceRoot: "~/.clawdbot/sandboxes",
-      docker: {
-        image: "clawdbot-sandbox:bookworm-slim",
-        containerPrefix: "clawdbot-sbx-",
-        workdir: "/workspace",
-        readOnlyRoot: true,
-        tmpfs: ["/tmp", "/var/tmp", "/run"],
-        network: "none",
-        user: "1000:1000",
-        capDrop: ["ALL"],
-        env: { LANG: "C.UTF-8" },
-        setupCommand: "apt-get update && apt-get install -y git curl jq",
-        // Per-agent override (multi-agent): routing.agents.<agentId>.sandbox.docker.*
-        pidsLimit: 256,
-        memory: "1g",
-        memorySwap: "2g",
-        cpus: 1,
-        ulimits: {
-          nofile: { soft: 1024, hard: 2048 },
-          nproc: 256
+  agents: {
+    defaults: {
+      sandbox: {
+        mode: "non-main", // off | non-main | all
+        scope: "agent", // session | agent | shared (agent is default)
+        workspaceAccess: "none", // none | ro | rw
+        workspaceRoot: "~/.clawdbot/sandboxes",
+        docker: {
+          image: "clawdbot-sandbox:bookworm-slim",
+          containerPrefix: "clawdbot-sbx-",
+          workdir: "/workspace",
+          readOnlyRoot: true,
+          tmpfs: ["/tmp", "/var/tmp", "/run"],
+          network: "none",
+          user: "1000:1000",
+          capDrop: ["ALL"],
+          env: { LANG: "C.UTF-8" },
+          setupCommand: "apt-get update && apt-get install -y git curl jq",
+          // Per-agent override (multi-agent): agents.list[].sandbox.docker.*
+          pidsLimit: 256,
+          memory: "1g",
+          memorySwap: "2g",
+          cpus: 1,
+          ulimits: {
+            nofile: { soft: 1024, hard: 2048 },
+            nproc: 256
+          },
+          seccompProfile: "/path/to/seccomp.json",
+          apparmorProfile: "clawdbot-sandbox",
+          dns: ["1.1.1.1", "8.8.8.8"],
+          extraHosts: ["internal.service:10.0.0.5"]
         },
-        seccompProfile: "/path/to/seccomp.json",
-        apparmorProfile: "clawdbot-sandbox",
-        dns: ["1.1.1.1", "8.8.8.8"],
-        extraHosts: ["internal.service:10.0.0.5"]
-      },
-      browser: {
-        enabled: false,
-        image: "clawdbot-sandbox-browser:bookworm-slim",
-        containerPrefix: "clawdbot-sbx-browser-",
-        cdpPort: 9222,
-        vncPort: 5900,
-        noVncPort: 6080,
-        headless: false,
-        enableNoVnc: true
-      },
+        browser: {
+          enabled: false,
+          image: "clawdbot-sandbox-browser:bookworm-slim",
+          containerPrefix: "clawdbot-sbx-browser-",
+          cdpPort: 9222,
+          vncPort: 5900,
+          noVncPort: 6080,
+          headless: false,
+          enableNoVnc: true
+        },
+        prune: {
+          idleHours: 24,  // 0 disables idle pruning
+          maxAgeDays: 7   // 0 disables max-age pruning
+        }
+      }
+    }
+  },
+  tools: {
+    sandbox: {
       tools: {
         allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn"],
         deny: ["browser", "canvas", "nodes", "cron", "discord", "gateway"]
-      },
-      prune: {
-        idleHours: 24,  // 0 disables idle pruning
-        maxAgeDays: 7   // 0 disables max-age pruning
       }
     }
   }
@@ -1307,7 +1320,7 @@ Build the default sandbox image once with:
 scripts/sandbox-setup.sh
 ```
 
-Note: sandbox containers default to `network: "none"`; set `agent.sandbox.docker.network`
+Note: sandbox containers default to `network: "none"`; set `agents.defaults.sandbox.docker.network`
 to `"bridge"` (or your custom network) if the agent needs outbound access.
 
 Note: inbound attachments are staged into the active workspace at `media/inbound/*`. With `workspaceAccess: "rw"`, that means files are written into the agent workspace.
@@ -1317,7 +1330,7 @@ Build the optional browser image with:
 scripts/sandbox-browser-setup.sh
 ```
 
-When `agent.sandbox.browser.enabled=true`, the browser tool uses a sandboxed
+When `agents.defaults.sandbox.browser.enabled=true`, the browser tool uses a sandboxed
 Chromium instance (CDP). If noVNC is enabled (default when headless=false),
 the noVNC URL is injected into the system prompt so the agent can reference it.
 This does not require `browser.enabled` in the main config; the sandbox control
@@ -1335,14 +1348,16 @@ When `models.providers` is present, Clawdbot writes/merges a `models.json` into
 - default behavior: **merge** (keeps existing providers, overrides on name)
 - set `models.mode: "replace"` to overwrite the file contents
 
-Select the model via `agent.model.primary` (provider/model).
+Select the model via `agents.defaults.model.primary` (provider/model).
 
 ```json5
 {
-  agent: {
-    model: { primary: "custom-proxy/llama-3.1-8b" },
-    models: {
-      "custom-proxy/llama-3.1-8b": {}
+  agents: {
+    defaults: {
+      model: { primary: "custom-proxy/llama-3.1-8b" },
+      models: {
+        "custom-proxy/llama-3.1-8b": {}
+      }
     }
   },
   models: {
@@ -1376,9 +1391,11 @@ in your environment and reference the model by provider/model.
 
 ```json5
 {
-  agent: {
-    model: "zai/glm-4.7",
-    allowedModels: ["zai/glm-4.7"]
+  agents: {
+    defaults: {
+      model: { primary: "zai/glm-4.7" },
+      models: { "zai/glm-4.7": {} }
+    }
   }
 }
 ```
@@ -1401,11 +1418,13 @@ via **LM Studio** using the **Responses API**.
 
 ```json5
 {
-  agent: {
-    model: { primary: "lmstudio/minimax-m2.1-gs32" },
-    models: {
-      "anthropic/claude-opus-4-5": { alias: "Opus" },
-      "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" }
+  agents: {
+    defaults: {
+      model: { primary: "lmstudio/minimax-m2.1-gs32" },
+      models: {
+        "anthropic/claude-opus-4-5": { alias: "Opus" },
+        "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" }
+      }
     }
   },
   models: {
@@ -1475,7 +1494,7 @@ Controls session scoping, idle expiry, reset triggers, and where the session sto
 
 Fields:
 - `mainKey`: direct-chat bucket key (default: `"main"`). Useful when you want to “rename” the primary DM thread without changing `agentId`.
-  - Sandbox note: `agent.sandbox.mode: "non-main"` uses this key to detect the main session. Any session key that does not match `mainKey` (groups/channels) is sandboxed.
+  - Sandbox note: `agents.defaults.sandbox.mode: "non-main"` uses this key to detect the main session. Any session key that does not match `mainKey` (groups/channels) is sandboxed.
 - `agentToAgent.maxPingPongTurns`: max reply-back turns between requester/target (0–5, default 5).
 - `sendPolicy.default`: `allow` or `deny` fallback when no rule matches.
 - `sendPolicy.rules[]`: match by `provider`, `chatType` (`direct|group|room`), or `keyPrefix` (e.g. `cron:`). First deny wins; otherwise allow.
@@ -1684,7 +1703,7 @@ Hot-applied (no full gateway restart):
 - `hooks` (webhook auth/path/mappings) + `hooks.gmail` (Gmail watcher restarted)
 - `browser` (browser control server restart)
 - `cron` (cron service restart + concurrency update)
-- `agent.heartbeat` (heartbeat runner restart)
+- `agents.defaults.heartbeat` (heartbeat runner restart)
 - `web` (WhatsApp web provider restart)
 - `telegram`, `discord`, `signal`, `imessage` (provider restarts)
 - `agent`, `models`, `routing`, `messages`, `session`, `whatsapp`, `logging`, `skills`, `ui`, `talk`, `identity`, `wizard` (dynamic reads)
@@ -1701,7 +1720,7 @@ Requires full Gateway restart:
 To run multiple gateways on one host, isolate per-instance state + config and use unique ports:
 - `CLAWDBOT_CONFIG_PATH` (per-instance config)
 - `CLAWDBOT_STATE_DIR` (sessions/creds)
-- `agent.workspace` (memories)
+- `agents.defaults.workspace` (memories)
 - `gateway.port` (unique per instance)
 
 Convenience flags (CLI):
@@ -1771,7 +1790,7 @@ Mapping notes:
 - `transform` can point to a JS/TS module that returns a hook action.
 - `deliver: true` sends the final reply to a provider; `provider` defaults to `last` (falls back to WhatsApp).
 - If there is no prior delivery route, set `provider` + `to` explicitly (required for Telegram/Discord/Slack/Signal/iMessage).
-- `model` overrides the LLM for this hook run (`provider/model` or alias; must be allowed if `agent.models` is set).
+- `model` overrides the LLM for this hook run (`provider/model` or alias; must be allowed if `agents.defaults.models` is set).
 
 Gmail helper config (used by `clawdbot hooks gmail setup` / `run`):
 
@@ -1886,7 +1905,7 @@ clawdbot dns setup --apply
 
 ## Template variables
 
-Template placeholders are expanded in `routing.transcribeAudio.command` (and any future templated command fields).
+Template placeholders are expanded in `audio.transcription.command` (and any future templated command fields).
 
 | Variable | Description |
 |----------|-------------|

docs/gateway/doctor.md

@@ -94,8 +94,18 @@ legacy config format, so stale configs are repaired without manual intervention.
 
 Current migrations:
 - `routing.allowFrom` → `whatsapp.allowFrom`
+- `routing.groupChat.requireMention` → `whatsapp/telegram/imessage.groups."*".requireMention`
+- `routing.groupChat.historyLimit` → `messages.groupChat.historyLimit`
+- `routing.groupChat.mentionPatterns` → `messages.groupChat.mentionPatterns`
+- `routing.queue` → `messages.queue`
+- `routing.bindings` → top-level `bindings`
+- `routing.agents`/`routing.defaultAgentId` → `agents.list` + `agents.list[].default`
+- `routing.agentToAgent` → `tools.agentToAgent`
+- `routing.transcribeAudio` → `audio.transcription`
+- `identity` → `agents.list[].identity`
+- `agent.*` → `agents.defaults` + `tools.*` (tools/elevated/bash/sandbox/subagents)
 - `agent.model`/`allowedModels`/`modelAliases`/`modelFallbacks`/`imageModelFallbacks`
-  → `agent.models` + `agent.model.primary/fallbacks` + `agent.imageModel.primary/fallbacks`
+  → `agents.defaults.models` + `agents.defaults.model.primary/fallbacks` + `agents.defaults.imageModel.primary/fallbacks`
 
 ### 3) Legacy state migrations (disk layout)
 Doctor can migrate older on-disk layouts into the current structure:

docs/gateway/health.md

@@ -22,7 +22,7 @@ Short guide to verify the WhatsApp Web / Baileys stack without guessing.
 ## When something fails
 - `logged out` or status 409–515 → relink with `clawdbot providers logout` then `clawdbot providers login`.
 - Gateway unreachable → start it: `clawdbot gateway --port 18789` (use `--force` if the port is busy).
-- No inbound messages → confirm linked phone is online and the sender is allowed (`whatsapp.allowFrom`); for group chats, ensure allowlist + mention rules match (`whatsapp.groups`, `routing.groupChat.mentionPatterns`).
+- No inbound messages → confirm linked phone is online and the sender is allowed (`whatsapp.allowFrom`); for group chats, ensure allowlist + mention rules match (`whatsapp.groups`, `agents.list[].groupChat.mentionPatterns`).
 
 ## Dedicated "health" command
 `clawdbot health --json` asks the running Gateway for its health snapshot (no direct Baileys socket from the CLI). It reports linked creds, auth age, Baileys connect result/status code, session-store summary, and a probe duration. It exits non-zero if the Gateway is unreachable or the probe fails/timeouts. Use `--timeout <ms>` to override the 10s default.

docs/gateway/heartbeat.md

@@ -10,8 +10,8 @@ surface anything that needs attention without spamming you.
 
 ## Defaults
 
-- Interval: `30m` (set `agent.heartbeat.every`; use `0m` to disable).
-- Prompt body (configurable via `agent.heartbeat.prompt`):
+- Interval: `30m` (set `agents.defaults.heartbeat.every`; use `0m` to disable).
+- Prompt body (configurable via `agents.defaults.heartbeat.prompt`):
   `Read HEARTBEAT.md if exists. Consider outstanding tasks. Checkup sometimes on your human during (user local) day time.`
 - The heartbeat prompt is sent **verbatim** as the user message. The system
   prompt includes a “Heartbeat” section and the run is flagged internally.
@@ -33,14 +33,16 @@ and logged; a message that is only `HEARTBEAT_OK` is dropped.
 
 ```json5
 {
-  agent: {
-    heartbeat: {
-      every: "30m",           // default: 30m (0m disables)
-      model: "anthropic/claude-opus-4-5",
-      target: "last",         // last | whatsapp | telegram | discord | slack | signal | imessage | none
-      to: "+15551234567",     // optional provider-specific override
-      prompt: "Read HEARTBEAT.md if exists. Consider outstanding tasks. Checkup sometimes on your human during (user local) day time.",
-      ackMaxChars: 30          // max chars allowed after HEARTBEAT_OK
+  agents: {
+    defaults: {
+      heartbeat: {
+        every: "30m",           // default: 30m (0m disables)
+        model: "anthropic/claude-opus-4-5",
+        target: "last",         // last | whatsapp | telegram | discord | slack | signal | imessage | none
+        to: "+15551234567",     // optional provider-specific override
+        prompt: "Read HEARTBEAT.md if exists. Consider outstanding tasks. Checkup sometimes on your human during (user local) day time.",
+        ackMaxChars: 30          // max chars allowed after HEARTBEAT_OK
+      }
     }
   }
 }

docs/gateway/index.md

@@ -68,7 +68,7 @@ Defaults (can be overridden via env/flags/config):
 - `bridge.port=19002` (derived: `gateway.port+1`)
 - `browser.controlUrl=http://127.0.0.1:19003` (derived: `gateway.port+2`)
 - `canvasHost.port=19005` (derived: `gateway.port+4`)
-- `agent.workspace` default becomes `~/clawd-dev` when you run `setup`/`onboard` under `--dev`.
+- `agents.defaults.workspace` default becomes `~/clawd-dev` when you run `setup`/`onboard` under `--dev`.
 
 Derived ports (rules of thumb):
 - Base port = `gateway.port` (or `CLAWDBOT_GATEWAY_PORT` / `--port`)
@@ -81,7 +81,7 @@ Checklist per instance:
 - unique `gateway.port`
 - unique `CLAWDBOT_CONFIG_PATH`
 - unique `CLAWDBOT_STATE_DIR`
-- unique `agent.workspace`
+- unique `agents.defaults.workspace`
 - separate WhatsApp numbers (if using WA)
 
 Example:

docs/gateway/sandboxing.md

@@ -1,15 +1,15 @@
 ---
 summary: "How Clawdbot sandboxing works: modes, scopes, workspace access, and images"
 title: Sandboxing
-read_when: "You want a dedicated explanation of sandboxing or need to tune agent.sandbox."
+read_when: "You want a dedicated explanation of sandboxing or need to tune agents.defaults.sandbox."
 status: active
 ---
 
 # Sandboxing
 
 Clawdbot can run **tools inside Docker containers** to reduce blast radius.
-This is **optional** and controlled by configuration (`agent.sandbox` or
-`routing.agents[id].sandbox`). If sandboxing is off, tools run on the host.
+This is **optional** and controlled by configuration (`agents.defaults.sandbox` or
+`agents.list[].sandbox`). If sandboxing is off, tools run on the host.
 The Gateway stays on the host; tool execution runs in an isolated sandbox
 when enabled.
 
@@ -18,16 +18,16 @@ and process access when the model does something dumb.
 
 ## What gets sandboxed
 - Tool execution (`bash`, `read`, `write`, `edit`, `process`, etc.).
-- Optional sandboxed browser (`agent.sandbox.browser`).
+- Optional sandboxed browser (`agents.defaults.sandbox.browser`).
 
 Not sandboxed:
 - The Gateway process itself.
-- Any tool explicitly allowed to run on the host (e.g. `agent.elevated`).
+- Any tool explicitly allowed to run on the host (e.g. `tools.elevated`).
   - **Elevated bash runs on the host and bypasses sandboxing.**
-  - If sandboxing is off, `agent.elevated` does not change execution (already on host). See [Elevated Mode](/tools/elevated).
+  - If sandboxing is off, `tools.elevated` does not change execution (already on host). See [Elevated Mode](/tools/elevated).
 
 ## Modes
-`agent.sandbox.mode` controls **when** sandboxing is used:
+`agents.defaults.sandbox.mode` controls **when** sandboxing is used:
 - `"off"`: no sandboxing.
 - `"non-main"`: sandbox only **non-main** sessions (default if you want normal chats on host).
 - `"all"`: every session runs in a sandbox.
@@ -35,13 +35,13 @@ Note: `"non-main"` is based on `session.mainKey` (default `"main"`), not agent i
 Group/channel sessions use their own keys, so they count as non-main and will be sandboxed.
 
 ## Scope
-`agent.sandbox.scope` controls **how many containers** are created:
+`agents.defaults.sandbox.scope` controls **how many containers** are created:
 - `"session"` (default): one container per session.
 - `"agent"`: one container per agent.
 - `"shared"`: one container shared by all sandboxed sessions.
 
 ## Workspace access
-`agent.sandbox.workspaceAccess` controls **what the sandbox can see**:
+`agents.defaults.sandbox.workspaceAccess` controls **what the sandbox can see**:
 - `"none"` (default): tools see a sandbox workspace under `~/.clawdbot/sandboxes`.
 - `"ro"`: mounts the agent workspace read-only at `/agent` (disables `write`/`edit`).
 - `"rw"`: mounts the agent workspace read/write at `/workspace`.
@@ -66,7 +66,7 @@ scripts/sandbox-browser-setup.sh
 ```
 
 By default, sandbox containers run with **no network**.
-Override with `agent.sandbox.docker.network`.
+Override with `agents.defaults.sandbox.docker.network`.
 
 Docker installs and the containerized gateway live here:
 [Docker](/install/docker)
@@ -75,28 +75,30 @@ Docker installs and the containerized gateway live here:
 Tool allow/deny policies still apply before sandbox rules. If a tool is denied
 globally or per-agent, sandboxing doesn’t bring it back.
 
-`agent.elevated` is an explicit escape hatch that runs `bash` on the host.
+`tools.elevated` is an explicit escape hatch that runs `bash` on the host.
 Keep it locked down.
 
 ## Multi-agent overrides
 Each agent can override sandbox + tools:
-`routing.agents[id].sandbox` and `routing.agents[id].tools`.
+`agents.list[].sandbox` and `agents.list[].tools` (plus `agents.list[].tools.sandbox.tools` for sandbox tool policy).
 See [Multi-Agent Sandbox & Tools](/multi-agent-sandbox-tools) for precedence.
 
 ## Minimal enable example
 ```json5
 {
-  agent: {
-    sandbox: {
-      mode: "non-main",
-      scope: "session",
-      workspaceAccess: "none"
+  agents: {
+    defaults: {
+      sandbox: {
+        mode: "non-main",
+        scope: "session",
+        workspaceAccess: "none"
+      }
     }
   }
 }
 ```
 
 ## Related docs
-- [Sandbox Configuration](/gateway/configuration#agent-sandbox)
+- [Sandbox Configuration](/gateway/configuration#agentsdefaults-sandbox)
 - [Multi-Agent Sandbox & Tools](/multi-agent-sandbox-tools)
 - [Security](/gateway/security)

docs/gateway/security.md

@@ -127,10 +127,13 @@ Keep config + state private on the gateway host:
       "*": { "requireMention": true }
     }
   },
-  "routing": {
-    "groupChat": {
-      "mentionPatterns": ["@clawd", "@mybot"]
-    }
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "groupChat": { "mentionPatterns": ["@clawd", "@mybot"] }
+      }
+    ]
   }
 }
 ```
@@ -146,7 +149,7 @@ Consider running your AI on a separate phone number from your personal one:
 ### 4. Read-Only Mode (Today, via sandbox + tools)
 
 You can already build a read-only profile by combining:
-- `sandbox.workspaceAccess: "ro"` (or `"none"` for no workspace access)
+- `agents.defaults.sandbox.workspaceAccess: "ro"` (or `"none"` for no workspace access)
 - tool allow/deny lists that block `write`, `edit`, `bash`, `process`, etc.
 
 We may add a single `readOnlyMode` flag later to simplify this configuration.
@@ -158,18 +161,18 @@ Dedicated doc: [Sandboxing](/gateway/sandboxing)
 Two complementary approaches:
 
 - **Run the full Gateway in Docker** (container boundary): [Docker](/install/docker)
-- **Tool sandbox** (`agent.sandbox`, host gateway + Docker-isolated tools): [Sandboxing](/gateway/sandboxing)
+- **Tool sandbox** (`agents.defaults.sandbox`, host gateway + Docker-isolated tools): [Sandboxing](/gateway/sandboxing)
 
-Note: to prevent cross-agent access, keep `sandbox.scope` at `"agent"` (default)
+Note: to prevent cross-agent access, keep `agents.defaults.sandbox.scope` at `"agent"` (default)
 or `"session"` for stricter per-session isolation. `scope: "shared"` uses a
 single container/workspace.
 
 Also consider agent workspace access inside the sandbox:
-- `agent.sandbox.workspaceAccess: "none"` (default) keeps the agent workspace off-limits; tools run against a sandbox workspace under `~/.clawdbot/sandboxes`
-- `workspaceAccess: "ro"` mounts the agent workspace read-only at `/agent` (disables `write`/`edit`)
-- `workspaceAccess: "rw"` mounts the agent workspace read/write at `/workspace`
+- `agents.defaults.sandbox.workspaceAccess: "none"` (default) keeps the agent workspace off-limits; tools run against a sandbox workspace under `~/.clawdbot/sandboxes`
+- `agents.defaults.sandbox.workspaceAccess: "ro"` mounts the agent workspace read-only at `/agent` (disables `write`/`edit`)
+- `agents.defaults.sandbox.workspaceAccess: "rw"` mounts the agent workspace read/write at `/workspace`
 
-Important: `agent.elevated` is a **global**, sender-based escape hatch that runs bash on the host. Keep `agent.elevated.allowFrom` tight and don’t enable it for strangers. See [Elevated Mode](/tools/elevated).
+Important: `tools.elevated` is a **global**, sender-based escape hatch that runs bash on the host. Keep `tools.elevated.allowFrom` tight and don’t enable it for strangers. See [Elevated Mode](/tools/elevated).
 
 ## Per-agent access profiles (multi-agent)
 
@@ -187,13 +190,14 @@ Common use cases:
 
 ```json5
 {
-  routing: {
-    agents: {
-      personal: {
+  agents: {
+    list: [
+      {
+        id: "personal",
         workspace: "~/clawd-personal",
         sandbox: { mode: "off" }
       }
-    }
+    ]
   }
 }
 ```
@@ -202,9 +206,10 @@ Common use cases:
 
 ```json5
 {
-  routing: {
-    agents: {
-      family: {
+  agents: {
+    list: [
+      {
+        id: "family",
         workspace: "~/clawd-family",
         sandbox: {
           mode: "all",
@@ -216,7 +221,7 @@ Common use cases:
           deny: ["write", "edit", "bash", "process", "browser"]
         }
       }
-    }
+    ]
   }
 }
 ```
@@ -225,9 +230,10 @@ Common use cases:
 
 ```json5
 {
-  routing: {
-    agents: {
-      public: {
+  agents: {
+    list: [
+      {
+        id: "public",
         workspace: "~/clawd-public",
         sandbox: {
           mode: "all",
@@ -239,7 +245,7 @@ Common use cases:
           deny: ["read", "write", "edit", "bash", "process", "browser", "canvas", "nodes", "cron", "gateway", "image"]
         }
       }
-    }
+    ]
   }
 }
 ```

docs/gateway/troubleshooting.md

@@ -127,12 +127,12 @@ or state drift because only one workspace is active.
 Symptoms: `pwd` or file tools show `~/.clawdbot/sandboxes/...` even though you
 expected the host workspace.
 
-**Why:** `agent.sandbox.mode: "non-main"` keys off `session.mainKey` (default `"main"`).
+**Why:** `agents.defaults.sandbox.mode: "non-main"` keys off `session.mainKey` (default `"main"`).
 Group/channel sessions use their own keys, so they are treated as non-main and
 get sandbox workspaces.
 
 **Fix options:**
-- If you want host workspaces for an agent: set `routing.agents.<id>.sandbox.mode: "off"`.
+- If you want host workspaces for an agent: set `agents.list[].sandbox.mode: "off"`.
 - If you want host workspace access inside sandbox: set `workspaceAccess: "rw"` for that agent.
 
 ### "Agent was aborted"
@@ -157,8 +157,8 @@ Look for `AllowFrom: ...` in the output.
 **Check 2:** For group chats, is mention required?
 ```bash
 # The message must match mentionPatterns or explicit mentions; defaults live in provider groups/guilds.
-# Multi-agent: `routing.agents.<agentId>.mentionPatterns` overrides global patterns.
-grep -n "routing\\|groupChat\\|mentionPatterns\\|whatsapp\\.groups\\|telegram\\.groups\\|imessage\\.groups\\|discord\\.guilds" \
+# Multi-agent: `agents.list[].groupChat.mentionPatterns` overrides global patterns.
+grep -n "agents\\|groupChat\\|mentionPatterns\\|whatsapp\\.groups\\|telegram\\.groups\\|imessage\\.groups\\|discord\\.guilds" \
   "${CLAWDBOT_CONFIG_PATH:-$HOME/.clawdbot/clawdbot.json}"
 ```
 

docs/install/docker.md

@@ -109,12 +109,12 @@ Deep dive: [Sandboxing](/gateway/sandboxing)
 
 ### What it does
 
-When `agent.sandbox` is enabled, **non-main sessions** run tools inside a Docker
+When `agents.defaults.sandbox` is enabled, **non-main sessions** run tools inside a Docker
 container. The gateway stays on your host, but the tool execution is isolated:
 - scope: `"agent"` by default (one container + workspace per agent)
 - scope: `"session"` for per-session isolation
 - per-scope workspace folder mounted at `/workspace`
-- optional agent workspace access (`agent.sandbox.workspaceAccess`)
+- optional agent workspace access (`agents.defaults.sandbox.workspaceAccess`)
 - allow/deny tool policy (deny wins)
 - inbound media is copied into the active sandbox workspace (`media/inbound/*`) so tools can read it (with `workspaceAccess: "rw"`, this lands in the agent workspace)
 
@@ -124,7 +124,7 @@ one container and one workspace.
 ### Per-agent sandbox profiles (multi-agent)
 
 If you use multi-agent routing, each agent can override sandbox + tool settings:
-`routing.agents[id].sandbox` and `routing.agents[id].tools`. This lets you run
+`agents.list[].sandbox` and `agents.list[].tools` (plus `agents.list[].tools.sandbox.tools`). This lets you run
 mixed access levels in one gateway:
 - Full access (personal agent)
 - Read-only tools + read-only workspace (family/work agent)
@@ -149,54 +149,60 @@ precedence, and troubleshooting.
 
 ```json5
 {
-  agent: {
-    sandbox: {
-      mode: "non-main", // off | non-main | all
-      scope: "agent", // session | agent | shared (agent is default)
-      workspaceAccess: "none", // none | ro | rw
-      workspaceRoot: "~/.clawdbot/sandboxes",
-      docker: {
-        image: "clawdbot-sandbox:bookworm-slim",
-        workdir: "/workspace",
-        readOnlyRoot: true,
-        tmpfs: ["/tmp", "/var/tmp", "/run"],
-        network: "none",
-        user: "1000:1000",
-        capDrop: ["ALL"],
-        env: { LANG: "C.UTF-8" },
-        setupCommand: "apt-get update && apt-get install -y git curl jq",
-        pidsLimit: 256,
-        memory: "1g",
-        memorySwap: "2g",
-        cpus: 1,
-        ulimits: {
-          nofile: { soft: 1024, hard: 2048 },
-          nproc: 256
+  agents: {
+    defaults: {
+      sandbox: {
+        mode: "non-main", // off | non-main | all
+        scope: "agent", // session | agent | shared (agent is default)
+        workspaceAccess: "none", // none | ro | rw
+        workspaceRoot: "~/.clawdbot/sandboxes",
+        docker: {
+          image: "clawdbot-sandbox:bookworm-slim",
+          workdir: "/workspace",
+          readOnlyRoot: true,
+          tmpfs: ["/tmp", "/var/tmp", "/run"],
+          network: "none",
+          user: "1000:1000",
+          capDrop: ["ALL"],
+          env: { LANG: "C.UTF-8" },
+          setupCommand: "apt-get update && apt-get install -y git curl jq",
+          pidsLimit: 256,
+          memory: "1g",
+          memorySwap: "2g",
+          cpus: 1,
+          ulimits: {
+            nofile: { soft: 1024, hard: 2048 },
+            nproc: 256
+          },
+          seccompProfile: "/path/to/seccomp.json",
+          apparmorProfile: "clawdbot-sandbox",
+          dns: ["1.1.1.1", "8.8.8.8"],
+          extraHosts: ["internal.service:10.0.0.5"]
         },
-        seccompProfile: "/path/to/seccomp.json",
-        apparmorProfile: "clawdbot-sandbox",
-        dns: ["1.1.1.1", "8.8.8.8"],
-        extraHosts: ["internal.service:10.0.0.5"]
-      },
+        prune: {
+          idleHours: 24, // 0 disables idle pruning
+          maxAgeDays: 7  // 0 disables max-age pruning
+        }
+      }
+    }
+  },
+  tools: {
+    sandbox: {
       tools: {
         allow: ["bash", "process", "read", "write", "edit", "sessions_list", "sessions_history", "sessions_send", "sessions_spawn"],
         deny: ["browser", "canvas", "nodes", "cron", "discord", "gateway"]
-      },
-      prune: {
-        idleHours: 24, // 0 disables idle pruning
-        maxAgeDays: 7  // 0 disables max-age pruning
       }
     }
   }
 }
 ```
 
-Hardening knobs live under `agent.sandbox.docker`:
+Hardening knobs live under `agents.defaults.sandbox.docker`:
 `network`, `user`, `pidsLimit`, `memory`, `memorySwap`, `cpus`, `ulimits`,
 `seccompProfile`, `apparmorProfile`, `dns`, `extraHosts`.
 
-Multi-agent: override `agent.sandbox.{docker,browser,prune}.*` per agent via `routing.agents.<agentId>.sandbox.{docker,browser,prune}.*`
-(ignored when `agent.sandbox.scope` / `routing.agents.<agentId>.sandbox.scope` is `"shared"`).
+Multi-agent: override `agents.defaults.sandbox.{docker,browser,prune}.*` per agent via `agents.list[].sandbox.{docker,browser,prune}.*`
+(ignored when `agents.defaults.sandbox.scope` / `agents.list[].sandbox.scope` is `"shared"`).
 
 ### Build the default sandbox image
 
@@ -217,7 +223,7 @@ This builds `clawdbot-sandbox-common:bookworm-slim`. To use it:
 
 ```json5
 {
-  agent: { sandbox: { docker: { image: "clawdbot-sandbox-common:bookworm-slim" } } }
+  agents: { defaults: { sandbox: { docker: { image: "clawdbot-sandbox-common:bookworm-slim" } } } }
 }
 ```
 
@@ -235,16 +241,18 @@ an optional noVNC observer (headful via Xvfb).
 
 Notes:
 - Headful (Xvfb) reduces bot blocking vs headless.
-- Headless can still be used by setting `agent.sandbox.browser.headless=true`.
+- Headless can still be used by setting `agents.defaults.sandbox.browser.headless=true`.
 - No full desktop environment (GNOME) is needed; Xvfb provides the display.
 
 Use config:
 
 ```json5
 {
-  agent: {
-    sandbox: {
-      browser: { enabled: true }
+  agents: {
+    defaults: {
+      sandbox: {
+        browser: { enabled: true }
+      }
     }
   }
 }
@@ -254,8 +262,10 @@ Custom browser image:
 
 ```json5
 {
-  agent: {
-    sandbox: { browser: { image: "my-clawdbot-browser" } }
+  agents: {
+    defaults: {
+      sandbox: { browser: { image: "my-clawdbot-browser" } }
+    }
   }
 }
 ```
@@ -266,7 +276,7 @@ When enabled, the agent receives:
 
 Remember: if you use an allowlist for tools, add `browser` (and remove it from
 deny) or the tool remains blocked.
-Prune rules (`agent.sandbox.prune`) apply to browser containers too.
+Prune rules (`agents.defaults.sandbox.prune`) apply to browser containers too.
 
 ### Custom sandbox image
 
@@ -278,8 +288,10 @@ docker build -t my-clawdbot-sbx -f Dockerfile.sandbox .
 
 ```json5
 {
-  agent: {
-    sandbox: { docker: { image: "my-clawdbot-sbx" } }
+  agents: {
+    defaults: {
+      sandbox: { docker: { image: "my-clawdbot-sbx" } }
+    }
   }
 }
 ```
@@ -310,7 +322,7 @@ Example:
 
 ## Troubleshooting
 
-- Image missing: build with [`scripts/sandbox-setup.sh`](https://github.com/clawdbot/clawdbot/blob/main/scripts/sandbox-setup.sh) or set `agent.sandbox.docker.image`.
+- Image missing: build with [`scripts/sandbox-setup.sh`](https://github.com/clawdbot/clawdbot/blob/main/scripts/sandbox-setup.sh) or set `agents.defaults.sandbox.docker.image`.
 - Container not running: it will auto-create per session on demand.
 - Permission errors in sandbox: set `docker.user` to a UID:GID that matches your
   mounted workspace ownership (or chown the workspace folder).

docs/multi-agent-sandbox-tools.md

@@ -10,8 +10,8 @@ status: active
 ## Overview
 
 Each agent in a multi-agent setup can now have its own:
-- **Sandbox configuration** (`mode`, `scope`, `workspaceRoot`, `workspaceAccess`, `tools`)
-- **Tool restrictions** (`allow`, `deny`)
+- **Sandbox configuration** (`agents.list[].sandbox` overrides `agents.defaults.sandbox`)
+- **Tool restrictions** (`tools.allow` / `tools.deny`, plus `agents.list[].tools`)
 
 This allows you to run multiple agents with different security profiles:
 - Personal assistant with full access
@@ -28,18 +28,17 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
 
 ```json
 {
-  "routing": {
-    "defaultAgentId": "main",
-    "agents": {
-      "main": {
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "default": true,
         "name": "Personal Assistant",
         "workspace": "~/clawd",
-        "sandbox": {
-          "mode": "off"
-        }
-        // No tool restrictions - all tools available
+        "sandbox": { "mode": "off" }
       },
-      "family": {
+      {
+        "id": "family",
         "name": "Family Bot",
         "workspace": "~/clawd-family",
         "sandbox": {
@@ -51,21 +50,21 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
           "deny": ["bash", "write", "edit", "process", "browser"]
         }
       }
-    },
-    "bindings": [
-      {
-        "agentId": "family",
-        "match": {
-          "provider": "whatsapp",
-          "accountId": "*",
-          "peer": {
-            "kind": "group",
-            "id": "120363424282127706@g.us"
-          }
+    ]
+  },
+  "bindings": [
+    {
+      "agentId": "family",
+      "match": {
+        "provider": "whatsapp",
+        "accountId": "*",
+        "peer": {
+          "kind": "group",
+          "id": "120363424282127706@g.us"
         }
       }
-    ]
-  }
+    }
+  ]
 }
 ```
 
@@ -79,13 +78,15 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
 
 ```json
 {
-  "routing": {
-    "agents": {
-      "personal": {
+  "agents": {
+    "list": [
+      {
+        "id": "personal",
         "workspace": "~/clawd-personal",
         "sandbox": { "mode": "off" }
       },
-      "work": {
+      {
+        "id": "work",
         "workspace": "~/clawd-work",
         "sandbox": {
           "mode": "all",
@@ -97,7 +98,7 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
           "deny": ["browser", "gateway", "discord"]
         }
       }
-    }
+    ]
   }
 }
 ```
@@ -108,21 +109,23 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
 
 ```json
 {
-  "agent": {
-    "sandbox": {
-      "mode": "non-main",  // Global default
-      "scope": "session"
-    }
-  },
-  "routing": {
-    "agents": {
-      "main": {
+  "agents": {
+    "defaults": {
+      "sandbox": {
+        "mode": "non-main",  // Global default
+        "scope": "session"
+      }
+    },
+    "list": [
+      {
+        "id": "main",
         "workspace": "~/clawd",
         "sandbox": {
           "mode": "off"  // Override: main never sandboxed
         }
       },
-      "public": {
+      {
+        "id": "public",
         "workspace": "~/clawd-public",
         "sandbox": {
           "mode": "all",  // Override: public always sandboxed
@@ -133,7 +136,7 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
           "deny": ["bash", "write", "edit"]
         }
       }
-    }
+    ]
   }
 }
 ```
@@ -142,40 +145,40 @@ For how sandboxing behaves at runtime, see [Sandboxing](/gateway/sandboxing).
 
 ## Configuration Precedence
 
-When both global (`agent.*`) and agent-specific (`routing.agents[id].*`) configs exist:
+When both global (`agents.defaults.*`) and agent-specific (`agents.list[].*`) configs exist:
 
 ### Sandbox Config
 Agent-specific settings override global:
 ```
-routing.agents[id].sandbox.mode > agent.sandbox.mode
-routing.agents[id].sandbox.scope > agent.sandbox.scope
-routing.agents[id].sandbox.workspaceRoot > agent.sandbox.workspaceRoot
-routing.agents[id].sandbox.workspaceAccess > agent.sandbox.workspaceAccess
-routing.agents[id].sandbox.docker.* > agent.sandbox.docker.*
-routing.agents[id].sandbox.browser.* > agent.sandbox.browser.*
-routing.agents[id].sandbox.prune.* > agent.sandbox.prune.*
+agents.list[].sandbox.mode > agents.defaults.sandbox.mode
+agents.list[].sandbox.scope > agents.defaults.sandbox.scope
+agents.list[].sandbox.workspaceRoot > agents.defaults.sandbox.workspaceRoot
+agents.list[].sandbox.workspaceAccess > agents.defaults.sandbox.workspaceAccess
+agents.list[].sandbox.docker.* > agents.defaults.sandbox.docker.*
+agents.list[].sandbox.browser.* > agents.defaults.sandbox.browser.*
+agents.list[].sandbox.prune.* > agents.defaults.sandbox.prune.*
 ```
 
 **Notes:**
-- `routing.agents[id].sandbox.{docker,browser,prune}.*` overrides `agent.sandbox.{docker,browser,prune}.*` for that agent (ignored when sandbox scope resolves to `"shared"`).
+- `agents.list[].sandbox.{docker,browser,prune}.*` overrides `agents.defaults.sandbox.{docker,browser,prune}.*` for that agent (ignored when sandbox scope resolves to `"shared"`).
 
 ### Tool Restrictions
 The filtering order is:
-1. **Global tool policy** (`agent.tools`)
-2. **Agent-specific tool policy** (`routing.agents[id].tools`)
-3. **Sandbox tool policy** (`agent.sandbox.tools` or `routing.agents[id].sandbox.tools`)
-4. **Subagent tool policy** (if applicable)
+1. **Global tool policy** (`tools.allow` / `tools.deny`)
+2. **Agent-specific tool policy** (`agents.list[].tools`)
+3. **Sandbox tool policy** (`tools.sandbox.tools` or `agents.list[].tools.sandbox.tools`)
+4. **Subagent tool policy** (`tools.subagents.tools`, if applicable)
 
 Each level can further restrict tools, but cannot grant back denied tools from earlier levels.
-If `routing.agents[id].sandbox.tools` is set, it replaces `agent.sandbox.tools` for that agent.
+If `agents.list[].tools.sandbox.tools` is set, it replaces `tools.sandbox.tools` for that agent.
 
 ### Elevated Mode (global)
-`agent.elevated` is **global** and **sender-based** (per-provider allowlist). It is **not** configurable per agent.
+`tools.elevated` is **global** and **sender-based** (per-provider allowlist). It is **not** configurable per agent.
 
 Mitigation patterns:
-- Deny `bash` for untrusted agents (`routing.agents[id].tools.deny: ["bash"]`)
+- Deny `bash` for untrusted agents (`agents.list[].tools.deny: ["bash"]`)
 - Avoid allowlisting senders that route to restricted agents
-- Disable elevated globally (`agent.elevated.enabled: false`) if you only want sandboxed execution
+- Disable elevated globally (`tools.elevated.enabled: false`) if you only want sandboxed execution
 
 ---
 
@@ -184,10 +187,16 @@ Mitigation patterns:
 **Before (single agent):**
 ```json
 {
-  "agent": {
-    "workspace": "~/clawd",
+  "agents": {
+    "defaults": {
+      "workspace": "~/clawd",
+      "sandbox": {
+        "mode": "non-main"
+      }
+    }
+  },
+  "tools": {
     "sandbox": {
-      "mode": "non-main",
       "tools": {
         "allow": ["read", "write", "bash"],
         "deny": []
@@ -200,21 +209,20 @@ Mitigation patterns:
 **After (multi-agent with different profiles):**
 ```json
 {
-  "routing": {
-    "defaultAgentId": "main",
-    "agents": {
-      "main": {
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "default": true,
         "workspace": "~/clawd",
-        "sandbox": {
-          "mode": "off"
-        }
+        "sandbox": { "mode": "off" }
       }
-    }
+    ]
   }
 }
 ```
 
-The global `agent.workspace` and `agent.sandbox` are still supported for backward compatibility, but we recommend using `routing.agents` for clarity in multi-agent setups.
+Legacy `agent.*` configs are migrated by `clawdbot doctor`; prefer `agents.defaults` + `agents.list` going forward.
 
 ---
 
@@ -254,10 +262,10 @@ The global `agent.workspace` and `agent.sandbox` are still supported for backwar
 
 ## Common Pitfall: "non-main"
 
-`sandbox.mode: "non-main"` is based on `session.mainKey` (default `"main"`),
+`agents.defaults.sandbox.mode: "non-main"` is based on `session.mainKey` (default `"main"`),
 not the agent id. Group/channel sessions always get their own keys, so they
 are treated as non-main and will be sandboxed. If you want an agent to never
-sandbox, set `routing.agents.<id>.sandbox.mode: "off"`.
+sandbox, set `agents.list[].sandbox.mode: "off"`.
 
 ---
 
@@ -289,8 +297,8 @@ After configuring multi-agent sandbox and tools:
 ## Troubleshooting
 
 ### Agent not sandboxed despite `mode: "all"`
-- Check if there's a global `agent.sandbox.mode` that overrides it
-- Agent-specific config takes precedence, so set `routing.agents[id].sandbox.mode: "all"`
+- Check if there's a global `agents.defaults.sandbox.mode` that overrides it
+- Agent-specific config takes precedence, so set `agents.list[].sandbox.mode: "all"`
 
 ### Tools still available despite deny list
 - Check tool filtering order: global → agent → sandbox → subagent
@@ -306,5 +314,5 @@ After configuring multi-agent sandbox and tools:
 ## See Also
 
 - [Multi-Agent Routing](/concepts/multi-agent)
-- [Sandbox Configuration](/gateway/configuration#agent-sandbox)
+- [Sandbox Configuration](/gateway/configuration#agentsdefaults-sandbox)
 - [Session Management](/concepts/session)

docs/nodes/audio.md

@@ -6,7 +6,7 @@ read_when:
 # Audio / Voice Notes — 2025-12-05
 
 ## What works
-- **Optional transcription**: If `routing.transcribeAudio.command` is set in `~/.clawdbot/clawdbot.json`, CLAWDBOT will:
+- **Optional transcription**: If `audio.transcription.command` is set in `~/.clawdbot/clawdbot.json`, CLAWDBOT will:
   1) Download inbound audio to a temp path when WhatsApp only provides a URL.
   2) Run the configured CLI (templated with `{{MediaPath}}`), expecting transcript on stdout.
   3) Replace `Body` with the transcript, set `{{Transcript}}`, and prepend the original media path plus a `Transcript:` section in the command prompt so models see both.
@@ -17,8 +17,8 @@ read_when:
 Requires `OPENAI_API_KEY` in env and `openai` CLI installed:
 ```json5
 {
-  routing: {
-    transcribeAudio: {
+  audio: {
+    transcription: {
       command: [
         "openai",
         "api",

docs/nodes/images.md

@@ -20,7 +20,7 @@ CLAWDBOT is now **web-only** (Baileys). This document captures the current media
 ## Web Provider Behavior
 - Input: local file path **or** HTTP(S) URL.
 - Flow: load into a Buffer, detect media kind, and build the correct payload:
-  - **Images:** resize & recompress to JPEG (max side 2048px) targeting `agent.mediaMaxMb` (default 5 MB), capped at 6 MB.
+  - **Images:** resize & recompress to JPEG (max side 2048px) targeting `agents.defaults.mediaMaxMb` (default 5 MB), capped at 6 MB.
   - **Audio/Voice/Video:** pass-through up to 16 MB; audio is sent as a voice note (`ptt: true`).
   - **Documents:** anything else, up to 100 MB, with filename preserved when available.
 - WhatsApp GIF-style playback: send an MP4 with `gifPlayback: true` (CLI: `--gif-playback`) so mobile clients loop inline.

docs/providers/discord.md

@@ -136,8 +136,8 @@ Example “single server, only allow me, only allow #help”:
 
 Notes:
 - `requireMention: true` means the bot only replies when mentioned (recommended for shared channels).
-- `routing.groupChat.mentionPatterns` also count as mentions for guild messages.
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
+- `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`) also count as mentions for guild messages.
+- Multi-agent override: set per-agent patterns on `agents.list[].groupChat.mentionPatterns`.
 - If `channels` is present, any channel not listed is denied by default.
 
 ### 6) Verify it works

docs/providers/imessage.md

@@ -66,8 +66,8 @@ DMs:
 Groups:
 - `imessage.groupPolicy = open | allowlist | disabled`.
 - `imessage.groupAllowFrom` controls who can trigger in groups when `allowlist` is set.
-- Mention gating uses `routing.groupChat.mentionPatterns` (iMessage has no native mention metadata).
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
+- Mention gating uses `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`) because iMessage has no native mention metadata.
+- Multi-agent override: set per-agent patterns on `agents.list[].groupChat.mentionPatterns`.
 
 ## How it works (behavior)
 - `imsg` streams message events; the gateway normalizes them into the shared provider envelope.
@@ -112,5 +112,5 @@ Provider options:
 - `imessage.textChunkLimit`: outbound chunk size (chars).
 
 Related global options:
-- `routing.groupChat.mentionPatterns`.
+- `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`).
 - `messages.responsePrefix`.

docs/providers/signal.md

@@ -92,6 +92,6 @@ Provider options:
 - `signal.mediaMaxMb`: inbound/outbound media cap (MB).
 
 Related global options:
-- `routing.groupChat.mentionPatterns` (Signal does not support native mentions).
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
+- `agents.list[].groupChat.mentionPatterns` (Signal does not support native mentions).
+- `messages.groupChat.mentionPatterns` (global fallback).
 - `messages.responsePrefix`.

docs/providers/slack.md

@@ -248,8 +248,8 @@ Slack tool actions can be gated with `slack.actions.*`:
 | emojiList | enabled | Custom emoji list |
 
 ## Notes
-- Mention gating is controlled via `slack.channels` (set `requireMention` to `true`); `routing.groupChat.mentionPatterns` also count as mentions.
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
+- Mention gating is controlled via `slack.channels` (set `requireMention` to `true`); `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`) also count as mentions.
+- Multi-agent override: set per-agent patterns on `agents.list[].groupChat.mentionPatterns`.
 - Reaction notifications follow `slack.reactionNotifications` (use `reactionAllowlist` with mode `allowlist`).
 - Bot-authored messages are ignored by default; enable via `slack.allowBots` or `slack.channels.<id>.allowBots`.
 - For the Slack tool, reaction removal semantics are in [/tools/reactions](/tools/reactions).

docs/providers/telegram.md

@@ -64,10 +64,10 @@ group messages, so use admin if you need full visibility.
 
 ## How it works (behavior)
 - Inbound messages are normalized into the shared provider envelope with reply context and media placeholders.
-- Group replies require a mention by default (native @mention or `routing.groupChat.mentionPatterns`).
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
+- Group replies require a mention by default (native @mention or `agents.list[].groupChat.mentionPatterns` / `messages.groupChat.mentionPatterns`).
+- Multi-agent override: set per-agent patterns on `agents.list[].groupChat.mentionPatterns`.
 - Replies always route back to the same Telegram chat.
-- Long-polling uses grammY runner with per-chat sequencing; overall concurrency is capped by `agent.maxConcurrent`.
+- Long-polling uses grammY runner with per-chat sequencing; overall concurrency is capped by `agents.defaults.maxConcurrent`.
 
 ## Formatting (Telegram HTML)
 - Outbound Telegram text uses `parse_mode: "HTML"` (Telegram’s supported tag subset).
@@ -81,7 +81,7 @@ group messages, so use admin if you need full visibility.
 
 ## Group activation modes
 
-By default, the bot only responds to mentions in groups (`@botname` or patterns in `routing.groupChat.mentionPatterns`). To change this behavior:
+By default, the bot only responds to mentions in groups (`@botname` or patterns in `agents.list[].groupChat.mentionPatterns`). To change this behavior:
 
 ### Via config (recommended)
 
@@ -280,7 +280,7 @@ Provider options:
 - `telegram.actions.sendMessage`: gate Telegram tool message sends.
 
 Related global options:
-- `routing.groupChat.mentionPatterns` (mention gating patterns).
-- `routing.agents.<agentId>.mentionPatterns` overrides for multi-agent setups.
+- `agents.list[].groupChat.mentionPatterns` (mention gating patterns).
+- `messages.groupChat.mentionPatterns` (global fallback).
 - `commands.native`, `commands.text`, `commands.useAccessGroups` (command behavior).
 - `messages.responsePrefix`, `messages.ackReaction`, `messages.ackReactionScope`.

docs/providers/whatsapp.md

@@ -148,7 +148,7 @@ Behavior:
 
 ## Limits
 - Outbound text is chunked to `whatsapp.textChunkLimit` (default 4000).
-- Media items are capped by `agent.mediaMaxMb` (default 5 MB).
+- Media items are capped by `agents.defaults.mediaMaxMb` (default 5 MB).
 
 ## Outbound send (text + media)
 - Uses active web listener; error if gateway not running.
@@ -164,13 +164,13 @@ Behavior:
 
 ## Media limits + optimization
 - Default cap: 5 MB (per media item).
-- Override: `agent.mediaMaxMb`.
+- Override: `agents.defaults.mediaMaxMb`.
 - Images are auto-optimized to JPEG under cap (resize + quality sweep).
 - Oversize media => error; media reply falls back to text warning.
 
 ## Heartbeats
 - **Gateway heartbeat** logs connection health (`web.heartbeatSeconds`, default 60s).
-- **Agent heartbeat** is global (`agent.heartbeat.*`) and runs in the main session.
+- **Agent heartbeat** is global (`agents.defaults.heartbeat.*`) and runs in the main session.
   - Uses the configured heartbeat prompt (default: `Read HEARTBEAT.md if exists. Consider outstanding tasks. Checkup sometimes on your human during (user local) day time.`) + `HEARTBEAT_OK` skip behavior.
   - Delivery defaults to the last used provider (or configured target).
 
@@ -189,16 +189,15 @@ Behavior:
 - `whatsapp.groupPolicy` (group policy).
 - `whatsapp.groups` (group allowlist + mention gating defaults; use `"*"` to allow all)
 - `whatsapp.actions.reactions` (gate WhatsApp tool reactions).
-- `routing.groupChat.mentionPatterns`
-- Multi-agent override: `routing.agents.<agentId>.mentionPatterns` takes precedence.
-- `routing.groupChat.historyLimit`
+- `agents.list[].groupChat.mentionPatterns` (or `messages.groupChat.mentionPatterns`)
+- `messages.groupChat.historyLimit`
 - `messages.messagePrefix` (inbound prefix)
 - `messages.responsePrefix` (outbound prefix)
-- `agent.mediaMaxMb`
-- `agent.heartbeat.every`
-- `agent.heartbeat.model` (optional override)
-- `agent.heartbeat.target`
-- `agent.heartbeat.to`
+- `agents.defaults.mediaMaxMb`
+- `agents.defaults.heartbeat.every`
+- `agents.defaults.heartbeat.model` (optional override)
+- `agents.defaults.heartbeat.target`
+- `agents.defaults.heartbeat.to`
 - `session.*` (scope, idle, store, mainKey)
 - `web.enabled` (disable provider startup when false)
 - `web.heartbeatSeconds`

docs/reference/AGENTS.default.md

@@ -8,7 +8,7 @@ read_when:
 
 ## First run (recommended)
 
-Clawdbot uses a dedicated workspace directory for the agent. Default: `~/clawd` (configurable via `agent.workspace`).
+Clawdbot uses a dedicated workspace directory for the agent. Default: `~/clawd` (configurable via `agents.defaults.workspace`).
 
 1) Create the workspace (if it doesn’t already exist):
 
@@ -30,13 +30,11 @@ cp docs/reference/templates/TOOLS.md ~/clawd/TOOLS.md
 cp docs/reference/AGENTS.default.md ~/clawd/AGENTS.md
 ```
 
-4) Optional: choose a different workspace by setting `agent.workspace` (supports `~`):
+4) Optional: choose a different workspace by setting `agents.defaults.workspace` (supports `~`):
 
 ```json5
 {
-  agent: {
-    workspace: "~/clawd"
-  }
+  agents: { defaults: { workspace: "~/clawd" } }
 }
 ```
 

docs/start/clawd.md

@@ -18,7 +18,7 @@ You’re putting an agent in a position to:
 Start conservative:
 - Always set `whatsapp.allowFrom` (never run open-to-the-world on your personal Mac).
 - Use a dedicated WhatsApp number for the assistant.
-- Heartbeats now default to every 30 minutes. Disable until you trust the setup by setting `agent.heartbeat.every: "0m"`.
+- Heartbeats now default to every 30 minutes. Disable until you trust the setup by setting `agents.defaults.heartbeat.every: "0m"`.
 
 ## Prerequisites
 
@@ -103,7 +103,7 @@ clawdbot setup
 
 Full workspace layout + backup guide: [`docs/agent-workspace.md`](/concepts/agent-workspace)
 
-Optional: choose a different workspace with `agent.workspace` (supports `~`).
+Optional: choose a different workspace with `agents.defaults.workspace` (supports `~`).
 
 ```json5
 {
@@ -173,9 +173,9 @@ Example:
 
 By default, CLAWDBOT runs a heartbeat every 30 minutes with the prompt:
 `Read HEARTBEAT.md if exists. Consider outstanding tasks. Checkup sometimes on your human during (user local) day time.`
-Set `agent.heartbeat.every: "0m"` to disable.
+Set `agents.defaults.heartbeat.every: "0m"` to disable.
 
-- If the agent replies with `HEARTBEAT_OK` (optionally with short padding; see `agent.heartbeat.ackMaxChars`), CLAWDBOT suppresses outbound delivery for that heartbeat.
+- If the agent replies with `HEARTBEAT_OK` (optionally with short padding; see `agents.defaults.heartbeat.ackMaxChars`), CLAWDBOT suppresses outbound delivery for that heartbeat.
 - Heartbeats run full agent turns — shorter intervals burn more tokens.
 
 ```json5

docs/start/faq.md

@@ -115,14 +115,14 @@ Everything lives under `$CLAWDBOT_STATE_DIR` (default: `~/.clawdbot`):
 
 Legacy single‑agent path: `~/.clawdbot/agent/*` (migrated by `clawdbot doctor`).
 
-Your **workspace** (AGENTS.md, memory files, skills, etc.) is separate and configured via `agent.workspace` (default: `~/clawd`).
+Your **workspace** (AGENTS.md, memory files, skills, etc.) is separate and configured via `agents.defaults.workspace` (default: `~/clawd`).
 
 ### Can agents work outside the workspace?
 
 Yes. The workspace is the **default cwd** and memory anchor, not a hard sandbox.
 Relative paths resolve inside the workspace, but absolute paths can access other
 host locations unless sandboxing is enabled. If you need isolation, use
-[`agent.sandbox`](/gateway/sandboxing) or per‑agent sandbox settings. If you
+[`agents.defaults.sandbox`](/gateway/sandboxing) or per‑agent sandbox settings. If you
 want a repo to be the default working directory, point that agent’s
 `workspace` to the repo root. The Clawdbot repo is just source code; keep the
 workspace separate unless you intentionally want the agent to work inside it.
@@ -259,7 +259,7 @@ Direct chats collapse to the main session by default. Groups/channels have their
 Clawdbot’s default model is whatever you set as:
 
 ```
-agent.model.primary
+agents.defaults.model.primary
 ```
 
 Models are referenced as `provider/model` (example: `anthropic/claude-opus-4-5`). If you omit the provider, Clawdbot currently assumes `anthropic` as a temporary deprecation fallback — but you should still **explicitly** set `provider/model`.
@@ -282,7 +282,7 @@ You can list available models with `/model`, `/model list`, or `/model status`.
 
 ### Why do I see “Model … is not allowed” and then no reply?
 
-If `agent.models` is set, it becomes the **allowlist** for `/model` and any
+If `agents.defaults.models` is set, it becomes the **allowlist** for `/model` and any
 session overrides. Choosing a model that isn’t in that list returns:
 
 ```
@@ -290,11 +290,11 @@ Model "provider/model" is not allowed. Use /model to list available models.
 ```
 
 That error is returned **instead of** a normal reply. Fix: add the model to
-`agent.models`, remove the allowlist, or pick a model from `/model list`.
+`agents.defaults.models`, remove the allowlist, or pick a model from `/model list`.
 
 ### Are opus / sonnet / gpt built‑in shortcuts?
 
-Yes. Clawdbot ships a few default shorthands (only applied when the model exists in `agent.models`):
+Yes. Clawdbot ships a few default shorthands (only applied when the model exists in `agents.defaults.models`):
 
 - `opus` → `anthropic/claude-opus-4-5`
 - `sonnet` → `anthropic/claude-sonnet-4-5`
@@ -307,7 +307,7 @@ If you set your own alias with the same name, your value wins.
 
 ### How do I define/override model shortcuts (aliases)?
 
-Aliases come from `agent.models.<modelId>.alias`. Example:
+Aliases come from `agents.defaults.models.<modelId>.alias`. Example:
 
 ```json5
 {
@@ -359,7 +359,7 @@ If you reference a provider/model but the required provider key is missing, you
 Failover happens in two stages:
 
 1) **Auth profile rotation** within the same provider.
-2) **Model fallback** to the next model in `agent.model.fallbacks`.
+2) **Model fallback** to the next model in `agents.defaults.model.fallbacks`.
 
 Cooldowns apply to failing profiles (exponential backoff), so Clawdbot can keep responding even when a provider is rate‑limited or temporarily failing.
 
@@ -387,7 +387,7 @@ It means the system attempted to use the auth profile ID `anthropic:default`, bu
 
 If your model config includes Google Gemini as a fallback (or you switched to a Gemini shorthand), Clawdbot will try it during model fallback. If you haven’t configured Google credentials, you’ll see `No API key found for provider "google"`.
 
-Fix: either provide Google auth, or remove/avoid Google models in `agent.model.fallbacks` / aliases so fallback doesn’t route there.
+Fix: either provide Google auth, or remove/avoid Google models in `agents.defaults.model.fallbacks` / aliases so fallback doesn’t route there.
 
 ## Auth profiles: what they are and how to manage them
 
@@ -506,7 +506,7 @@ Yes, but you must isolate:
 
 - `CLAWDBOT_CONFIG_PATH` (per‑instance config)
 - `CLAWDBOT_STATE_DIR` (per‑instance state)
-- `agent.workspace` (workspace isolation)
+- `agents.defaults.workspace` (workspace isolation)
 - `gateway.port` (unique ports)
 
 There are convenience CLI flags like `--dev` and `--profile <name>` that shift state dirs and ports.
@@ -619,7 +619,7 @@ You can add options like `debounce:2s cap:25 drop:summarize` for followup modes.
 ### “All models failed” — what should I check first?
 
 - **Credentials** present for the provider(s) being tried (auth profiles + env vars).
-- **Model routing**: confirm `agent.model.primary` and fallbacks are models you can access.
+- **Model routing**: confirm `agents.defaults.model.primary` and fallbacks are models you can access.
 - **Gateway logs** in `/tmp/clawdbot/…` for the exact provider error.
 - **`/model status`** to see current configured models + shorthands.
 
@@ -658,7 +658,7 @@ clawdbot providers login
 
 **Q: “What’s the default model for Anthropic with an API key?”**
 
-**A:** In Clawdbot, credentials and model selection are separate. Setting `ANTHROPIC_API_KEY` (or storing an Anthropic API key in auth profiles) enables authentication, but the actual default model is whatever you configure in `agent.model.primary` (for example, `anthropic/claude-sonnet-4-5` or `anthropic/claude-opus-4-5`). If you see `No credentials found for profile "anthropic:default"`, it means the Gateway couldn’t find Anthropic credentials in the expected `auth-profiles.json` for the agent that’s running.
+**A:** In Clawdbot, credentials and model selection are separate. Setting `ANTHROPIC_API_KEY` (or storing an Anthropic API key in auth profiles) enables authentication, but the actual default model is whatever you configure in `agents.defaults.model.primary` (for example, `anthropic/claude-sonnet-4-5` or `anthropic/claude-opus-4-5`). If you see `No credentials found for profile "anthropic:default"`, it means the Gateway couldn’t find Anthropic credentials in the expected `auth-profiles.json` for the agent that’s running.
 
 ---
 

docs/start/getting-started.md

@@ -19,7 +19,7 @@ Recommended path: use the **CLI onboarding wizard** (`clawdbot onboard`). It set
 
 If you want the deeper reference pages, jump to: [Wizard](/start/wizard), [Setup](/start/setup), [Pairing](/start/pairing), [Security](/gateway/security).
 
-Sandboxing note: `agent.sandbox.mode: "non-main"` uses `session.mainKey` (default `"main"`),
+Sandboxing note: `agents.defaults.sandbox.mode: "non-main"` uses `session.mainKey` (default `"main"`),
 so group/channel sessions are sandboxed. If you want the main agent to always
 run on host, set an explicit per-agent override:
 

docs/start/wizard.md

@@ -71,12 +71,12 @@ Tip: `--json` does **not** imply non-interactive mode. Use `--non-interactive` (
 
 2) **Model/Auth**
    - **Anthropic OAuth (Claude CLI)**: on macOS the wizard checks Keychain item "Claude Code-credentials" (choose "Always Allow" so launchd starts don't block); on Linux/Windows it reuses `~/.claude/.credentials.json` if present.
-- **Anthropic token (paste setup-token)**: run `claude setup-token` in your terminal, then paste the token (you can name it; blank = default).
-- **OpenAI Codex OAuth (Codex CLI)**: if `~/.codex/auth.json` exists, the wizard can reuse it.
-- **OpenAI Codex OAuth**: browser flow; paste the `code#state`.
-  - Sets `agent.model` to `openai-codex/gpt-5.2` when model is unset or `openai/*`.
-- **OpenAI API key**: uses `OPENAI_API_KEY` if present or prompts for a key, then saves it to `~/.clawdbot/.env` so launchd can read it.
-- **API key**: stores the key for you.
+   - **Anthropic token (paste setup-token)**: run `claude setup-token` in your terminal, then paste the token (you can name it; blank = default).
+   - **OpenAI Codex OAuth (Codex CLI)**: if `~/.codex/auth.json` exists, the wizard can reuse it.
+   - **OpenAI Codex OAuth**: browser flow; paste the `code#state`.
+     - Sets `agents.defaults.model` to `openai-codex/gpt-5.2` when model is unset or `openai/*`.
+   - **OpenAI API key**: uses `OPENAI_API_KEY` if present or prompts for a key, then saves it to `~/.clawdbot/.env` so launchd can read it.
+   - **API key**: stores the key for you.
    - **Minimax M2.1 (LM Studio)**: config is auto‑written for the LM Studio endpoint.
    - **Skip**: no auth configured yet.
    - Wizard runs a model check and warns if the configured model is unknown or missing auth.
@@ -144,14 +144,14 @@ Use `clawdbot agents add <name>` to create a separate agent with its own workspa
 sessions, and auth profiles. Running without `--workspace` launches the wizard.
 
 What it sets:
-- `routing.agents.<agentId>.name`
-- `routing.agents.<agentId>.workspace`
-- `routing.agents.<agentId>.agentDir`
+- `agents.list[].name`
+- `agents.list[].workspace`
+- `agents.list[].agentDir`
 
 Notes:
 - Default workspaces follow `~/clawd-<agentId>`.
-- Add `routing.bindings` to route inbound messages (the wizard can do this).
- - Non-interactive flags: `--model`, `--agent-dir`, `--bind`, `--non-interactive`.
+- Add `bindings` to route inbound messages (the wizard can do this).
+- Non-interactive flags: `--model`, `--agent-dir`, `--bind`, `--non-interactive`.
 
 ## Non‑interactive mode
 
@@ -213,8 +213,8 @@ Notes:
 ## What the wizard writes
 
 Typical fields in `~/.clawdbot/clawdbot.json`:
-- `agent.workspace`
-- `agent.model` / `models.providers` (if Minimax chosen)
+- `agents.defaults.workspace`
+- `agents.defaults.model` / `models.providers` (if Minimax chosen)
 - `gateway.*` (mode, bind, auth, tailscale)
 - `telegram.botToken`, `discord.token`, `signal.*`, `imessage.*`
 - `skills.install.nodeManager`
@@ -224,7 +224,7 @@ Typical fields in `~/.clawdbot/clawdbot.json`:
 - `wizard.lastRunCommand`
 - `wizard.lastRunMode`
 
-`clawdbot agents add` writes `routing.agents.<agentId>` and optional `routing.bindings`.
+`clawdbot agents add` writes `agents.list[]` and optional `bindings`.
 
 WhatsApp credentials go under `~/.clawdbot/credentials/whatsapp/<accountId>/`.
 Sessions are stored under `~/.clawdbot/agents/<agentId>/sessions/`.

docs/tools/elevated.md

@@ -12,7 +12,7 @@ read_when:
 - Only `on|off` are accepted; anything else returns a hint and does not change state.
 
 ## What it controls (and what it doesn’t)
-- **Global availability gate**: `agent.elevated` is global (not per-agent). If disabled or sender not allowlisted, elevated is unavailable everywhere.
+- **Global availability gate**: `tools.elevated` is global (not per-agent). If disabled or sender not allowlisted, elevated is unavailable everywhere.
 - **Per-session state**: `/elevated on|off` sets the elevated level for the current session key.
 - **Inline directive**: `/elevated on` inside a message applies to that message only.
 - **Groups**: In group chats, elevated directives are only honored when the agent is mentioned. Command-only messages that bypass mention requirements are treated as mentioned.
@@ -31,7 +31,7 @@ Note:
 ## Resolution order
 1. Inline directive on the message (applies only to that message).
 2. Session override (set by sending a directive-only message).
-3. Global default (`agent.elevatedDefault` in config).
+3. Global default (`agents.defaults.elevatedDefault` in config).
 
 ## Setting a session default
 - Send a message that is **only** the directive (whitespace allowed), e.g. `/elevated on`.
@@ -40,10 +40,10 @@ Note:
 - Send `/elevated` (or `/elevated:`) with no argument to see the current elevated level.
 
 ## Availability + allowlists
-- Feature gate: `agent.elevated.enabled` (default can be off via config even if the code supports it).
-- Sender allowlist: `agent.elevated.allowFrom` with per-provider allowlists (e.g. `discord`, `whatsapp`).
+- Feature gate: `tools.elevated.enabled` (default can be off via config even if the code supports it).
+- Sender allowlist: `tools.elevated.allowFrom` with per-provider allowlists (e.g. `discord`, `whatsapp`).
 - Both must pass; otherwise elevated is treated as unavailable.
-- Discord fallback: if `agent.elevated.allowFrom.discord` is omitted, the `discord.dm.allowFrom` list is used as a fallback. Set `agent.elevated.allowFrom.discord` (even `[]`) to override.
+- Discord fallback: if `tools.elevated.allowFrom.discord` is omitted, the `discord.dm.allowFrom` list is used as a fallback. Set `tools.elevated.allowFrom.discord` (even `[]`) to override.
 
 ## Logging + status
 - Elevated bash calls are logged at info level.

docs/tools/index.md

@@ -13,16 +13,12 @@ and the agent should rely on them directly.
 
 ## Disabling tools
 
-You can globally allow/deny tools via `agent.tools` in `clawdbot.json`
+You can globally allow/deny tools via `tools.allow` / `tools.deny` in `clawdbot.json`
 (deny wins). This prevents disallowed tools from being sent to providers.
 
 ```json5
 {
-  agent: {
-    tools: {
-      deny: ["browser"]
-    }
-  }
+  tools: { deny: ["browser"] }
 }
 ```
 
@@ -43,7 +39,7 @@ Notes:
 - Returns `status: "running"` with a `sessionId` when backgrounded.
 - Use `process` to poll/log/write/kill/clear background sessions.
 - If `process` is disallowed, `bash` runs synchronously and ignores `yieldMs`/`background`.
-- `elevated` is gated by `agent.elevated` (global sender allowlist) and runs on the host.
+- `elevated` is gated by `tools.elevated` (global sender allowlist) and runs on the host.
 - `elevated` only changes behavior when the agent is sandboxed (otherwise it’s a no-op).
 
 ### `process`
@@ -145,7 +141,7 @@ Core parameters:
 - `maxBytesMb` (optional size cap)
 
 Notes:
-- Only available when `agent.imageModel` is configured (primary or fallbacks).
+- Only available when `agents.defaults.imageModel` is configured (primary or fallbacks).
 - Uses the image model directly (independent of the main chat model).
 
 ### `message`
@@ -219,7 +215,7 @@ Notes:
 List agent ids that the current session may target with `sessions_spawn`.
 
 Notes:
-- Result is restricted to per-agent allowlists (`routing.agents.<agentId>.subagents.allowAgents`).
+- Result is restricted to per-agent allowlists (`agents.list[].subagents.allowAgents`).
 - When `["*"]` is configured, the tool includes all configured agents and marks `allowAny: true`.
 
 ## Parameters (common)

docs/tools/slash-commands.md

@@ -46,7 +46,7 @@ Text + native (when enabled):
 - `/verbose on|off` (alias: `/v`)
 - `/reasoning on|off|stream` (alias: `/reason`; `stream` = Telegram draft only)
 - `/elevated on|off` (alias: `/elev`)
-- `/model <name>` (or `/<alias>` from `agent.models.*.alias`)
+- `/model <name>` (or `/<alias>` from `agents.defaults.models.*.alias`)
 - `/queue <mode>` (plus options like `debounce:2s cap:25 drop:summarize`; send `/queue` to see current settings)
 
 Text-only:

docs/tools/subagents.md

@@ -30,13 +30,13 @@ Tool params:
 - `cleanup?` (`delete|keep`, default `keep`)
 
 Allowlist:
-- `routing.agents.<agentId>.subagents.allowAgents`: list of agent ids that can be targeted via `agentId` (`["*"]` to allow any). Default: only the requester agent.
+- `agents.list[].subagents.allowAgents`: list of agent ids that can be targeted via `agentId` (`["*"]` to allow any). Default: only the requester agent.
 
 Discovery:
 - Use `agents_list` to see which agent ids are currently allowed for `sessions_spawn`.
 
 Auto-archive:
-- Sub-agent sessions are automatically archived after `agent.subagents.archiveAfterMinutes` (default: 60).
+- Sub-agent sessions are automatically archived after `agents.defaults.subagents.archiveAfterMinutes` (default: 60).
 - Archive uses `sessions.delete` and renames the transcript to `*.deleted.<timestamp>` (same folder).
 - `cleanup: "delete"` archives immediately after announce (still keeps the transcript via rename).
 - Auto-archive is best-effort; pending timers are lost if the gateway restarts.
@@ -67,9 +67,15 @@ Override via config:
 
 ```json5
 {
-  agent: {
+  agents: {
+    defaults: {
+      subagents: {
+        maxConcurrent: 1
+      }
+    }
+  },
+  tools: {
     subagents: {
-      maxConcurrent: 1,
       tools: {
         // deny wins
         deny: ["gateway", "cron"],
@@ -85,7 +91,7 @@ Override via config:
 
 Sub-agents use a dedicated in-process queue lane:
 - Lane name: `subagent`
-- Concurrency: `agent.subagents.maxConcurrent` (default `1`)
+- Concurrency: `agents.defaults.subagents.maxConcurrent` (default `1`)
 
 ## Limitations
 

docs/tools/thinking.md

@@ -17,7 +17,7 @@ read_when:
 ## Resolution order
 1. Inline directive on the message (applies only to that message).
 2. Session override (set by sending a directive-only message).
-3. Global default (`agent.thinkingDefault` in config).
+3. Global default (`agents.defaults.thinkingDefault` in config).
 4. Fallback: low for reasoning-capable models; off otherwise.
 
 ## Setting a session default

scripts/e2e/onboard-docker.sh

@@ -231,8 +231,10 @@ const cfg = JSON5.parse(fs.readFileSync(process.env.CONFIG_PATH, "utf-8"));
 const expectedWorkspace = process.env.WORKSPACE_DIR;
 const errors = [];
 
-if (cfg?.agent?.workspace !== expectedWorkspace) {
-  errors.push(`agent.workspace mismatch (got ${cfg?.agent?.workspace ?? "unset"})`);
+if (cfg?.agents?.defaults?.workspace !== expectedWorkspace) {
+  errors.push(
+    `agents.defaults.workspace mismatch (got ${cfg?.agents?.defaults?.workspace ?? "unset"})`,
+  );
 }
 if (cfg?.gateway?.mode !== "local") {
   errors.push(`gateway.mode mismatch (got ${cfg?.gateway?.mode ?? "unset"})`);

scripts/sandbox-common-setup.sh

@@ -59,7 +59,7 @@ EOF
 
 cat <<NOTE
 Built ${TARGET_IMAGE}.
-To use it, set agent.sandbox.docker.image to "${TARGET_IMAGE}" and restart.
+To use it, set agents.defaults.sandbox.docker.image to "${TARGET_IMAGE}" and restart.
 If you want a clean re-create, remove old sandbox containers:
   docker rm -f \$(docker ps -aq --filter label=clawdbot.sandbox=1)
 NOTE

src/agents/agent-scope.test.ts

@@ -11,10 +11,8 @@ describe("resolveAgentConfig", () => {
 
   it("should return undefined when agent id does not exist", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          main: { workspace: "~/clawd" },
-        },
+      agents: {
+        list: [{ id: "main", workspace: "~/clawd" }],
       },
     };
     const result = resolveAgentConfig(cfg, "nonexistent");
@@ -23,15 +21,16 @@ describe("resolveAgentConfig", () => {
 
   it("should return basic agent config", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             name: "Main Agent",
             workspace: "~/clawd",
             agentDir: "~/.clawdbot/agents/main",
             model: "anthropic/claude-opus-4",
           },
-        },
+        ],
       },
     };
     const result = resolveAgentConfig(cfg, "main");
@@ -40,6 +39,9 @@ describe("resolveAgentConfig", () => {
       workspace: "~/clawd",
       agentDir: "~/.clawdbot/agents/main",
       model: "anthropic/claude-opus-4",
+      identity: undefined,
+      groupChat: undefined,
+      subagents: undefined,
       sandbox: undefined,
       tools: undefined,
     });
@@ -47,9 +49,10 @@ describe("resolveAgentConfig", () => {
 
   it("should return agent-specific sandbox config", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          work: {
+      agents: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             sandbox: {
               mode: "all",
@@ -57,13 +60,9 @@ describe("resolveAgentConfig", () => {
               perSession: false,
               workspaceAccess: "ro",
               workspaceRoot: "~/sandboxes",
-              tools: {
-                allow: ["read"],
-                deny: ["bash"],
-              },
             },
           },
-        },
+        ],
       },
     };
     const result = resolveAgentConfig(cfg, "work");
@@ -73,25 +72,22 @@ describe("resolveAgentConfig", () => {
       perSession: false,
       workspaceAccess: "ro",
       workspaceRoot: "~/sandboxes",
-      tools: {
-        allow: ["read"],
-        deny: ["bash"],
-      },
     });
   });
 
   it("should return agent-specific tools config", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          restricted: {
+      agents: {
+        list: [
+          {
+            id: "restricted",
             workspace: "~/clawd-restricted",
             tools: {
               allow: ["read"],
               deny: ["bash", "write", "edit"],
             },
           },
-        },
+        ],
       },
     };
     const result = resolveAgentConfig(cfg, "restricted");
@@ -103,9 +99,10 @@ describe("resolveAgentConfig", () => {
 
   it("should return both sandbox and tools config", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          family: {
+      agents: {
+        list: [
+          {
+            id: "family",
             workspace: "~/clawd-family",
             sandbox: {
               mode: "all",
@@ -116,7 +113,7 @@ describe("resolveAgentConfig", () => {
               deny: ["bash"],
             },
           },
-        },
+        ],
       },
     };
     const result = resolveAgentConfig(cfg, "family");
@@ -126,10 +123,8 @@ describe("resolveAgentConfig", () => {
 
   it("should normalize agent id", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          main: { workspace: "~/clawd" },
-        },
+      agents: {
+        list: [{ id: "main", workspace: "~/clawd" }],
       },
     };
     // Should normalize to "main" (default)

src/agents/agent-scope.ts

@@ -11,6 +11,24 @@ import {
 import { resolveUserPath } from "../utils.js";
 import { DEFAULT_AGENT_WORKSPACE_DIR } from "./workspace.js";
 
+type AgentEntry = NonNullable<
+  NonNullable<ClawdbotConfig["agents"]>["list"]
+>[number];
+
+type ResolvedAgentConfig = {
+  name?: string;
+  workspace?: string;
+  agentDir?: string;
+  model?: string;
+  identity?: AgentEntry["identity"];
+  groupChat?: AgentEntry["groupChat"];
+  subagents?: AgentEntry["subagents"];
+  sandbox?: AgentEntry["sandbox"];
+  tools?: AgentEntry["tools"];
+};
+
+let defaultAgentWarned = false;
+
 export function resolveAgentIdFromSessionKey(
   sessionKey?: string | null,
 ): string {
@@ -18,46 +36,51 @@ export function resolveAgentIdFromSessionKey(
   return normalizeAgentId(parsed?.agentId ?? DEFAULT_AGENT_ID);
 }
 
+function listAgents(cfg: ClawdbotConfig): AgentEntry[] {
+  const list = cfg.agents?.list;
+  if (!Array.isArray(list)) return [];
+  return list.filter((entry): entry is AgentEntry =>
+    Boolean(entry && typeof entry === "object"),
+  );
+}
+
+export function resolveDefaultAgentId(cfg: ClawdbotConfig): string {
+  const agents = listAgents(cfg);
+  if (agents.length === 0) return DEFAULT_AGENT_ID;
+  const defaults = agents.filter((agent) => agent?.default);
+  if (defaults.length > 1 && !defaultAgentWarned) {
+    defaultAgentWarned = true;
+    console.warn(
+      "Multiple agents marked default=true; using the first entry as default.",
+    );
+  }
+  const chosen = (defaults[0] ?? agents[0])?.id?.trim();
+  return normalizeAgentId(chosen || DEFAULT_AGENT_ID);
+}
+
+function resolveAgentEntry(
+  cfg: ClawdbotConfig,
+  agentId: string,
+): AgentEntry | undefined {
+  const id = normalizeAgentId(agentId);
+  return listAgents(cfg).find((entry) => normalizeAgentId(entry.id) === id);
+}
+
 export function resolveAgentConfig(
   cfg: ClawdbotConfig,
   agentId: string,
-):
-  | {
-      name?: string;
-      workspace?: string;
-      agentDir?: string;
-      model?: string;
-      subagents?: {
-        allowAgents?: string[];
-      };
-      sandbox?: {
-        mode?: "off" | "non-main" | "all";
-        workspaceAccess?: "none" | "ro" | "rw";
-        scope?: "session" | "agent" | "shared";
-        perSession?: boolean;
-        workspaceRoot?: string;
-        tools?: {
-          allow?: string[];
-          deny?: string[];
-        };
-      };
-      tools?: {
-        allow?: string[];
-        deny?: string[];
-      };
-    }
-  | undefined {
+): ResolvedAgentConfig | undefined {
   const id = normalizeAgentId(agentId);
-  const agents = cfg.routing?.agents;
-  if (!agents || typeof agents !== "object") return undefined;
-  const entry = agents[id];
-  if (!entry || typeof entry !== "object") return undefined;
+  const entry = resolveAgentEntry(cfg, id);
+  if (!entry) return undefined;
   return {
     name: typeof entry.name === "string" ? entry.name : undefined,
     workspace:
       typeof entry.workspace === "string" ? entry.workspace : undefined,
     agentDir: typeof entry.agentDir === "string" ? entry.agentDir : undefined,
     model: typeof entry.model === "string" ? entry.model : undefined,
+    identity: entry.identity,
+    groupChat: entry.groupChat,
     subagents:
       typeof entry.subagents === "object" && entry.subagents
         ? entry.subagents
@@ -71,9 +94,10 @@ export function resolveAgentWorkspaceDir(cfg: ClawdbotConfig, agentId: string) {
   const id = normalizeAgentId(agentId);
   const configured = resolveAgentConfig(cfg, id)?.workspace?.trim();
   if (configured) return resolveUserPath(configured);
-  if (id === DEFAULT_AGENT_ID) {
-    const legacy = cfg.agent?.workspace?.trim();
-    if (legacy) return resolveUserPath(legacy);
+  const defaultAgentId = resolveDefaultAgentId(cfg);
+  if (id === defaultAgentId) {
+    const fallback = cfg.agents?.defaults?.workspace?.trim();
+    if (fallback) return resolveUserPath(fallback);
     return DEFAULT_AGENT_WORKSPACE_DIR;
   }
   return path.join(os.homedir(), `clawd-${id}`);

src/agents/auth-profiles.ts

@@ -925,7 +925,10 @@ export function resolveAuthProfileOrder(params: {
 
     // Still put preferredProfile first if specified
     if (preferredProfile && ordered.includes(preferredProfile)) {
-      return [preferredProfile, ...ordered.filter((e) => e !== preferredProfile)];
+      return [
+        preferredProfile,
+        ...ordered.filter((e) => e !== preferredProfile),
+      ];
     }
     return ordered;
   }

src/agents/claude-cli-runner.ts

@@ -108,7 +108,7 @@ function formatUserTime(date: Date, timeZone: string): string | undefined {
 }
 
 function buildModelAliasLines(cfg?: ClawdbotConfig) {
-  const models = cfg?.agent?.models ?? {};
+  const models = cfg?.agents?.defaults?.models ?? {};
   const entries: Array<{ alias: string; model: string }> = [];
   for (const [keyRaw, entryRaw] of Object.entries(models)) {
     const model = String(keyRaw ?? "").trim();
@@ -134,7 +134,9 @@ function buildSystemPrompt(params: {
   contextFiles?: EmbeddedContextFile[];
   modelDisplay: string;
 }) {
-  const userTimezone = resolveUserTimezone(params.config?.agent?.userTimezone);
+  const userTimezone = resolveUserTimezone(
+    params.config?.agents?.defaults?.userTimezone,
+  );
   const userTime = formatUserTime(new Date(), userTimezone);
   return buildAgentSystemPrompt({
     workspaceDir: params.workspaceDir,
@@ -143,7 +145,7 @@ function buildSystemPrompt(params: {
     ownerNumbers: params.ownerNumbers,
     reasoningTagHint: false,
     heartbeatPrompt: resolveHeartbeatPrompt(
-      params.config?.agent?.heartbeat?.prompt,
+      params.config?.agents?.defaults?.heartbeat?.prompt,
     ),
     runtimeInfo: {
       host: "clawdbot",

src/agents/clawdbot-gateway-tool.test.ts

@@ -46,7 +46,7 @@ describe("gateway tool", () => {
     expect(tool).toBeDefined();
     if (!tool) throw new Error("missing gateway tool");
 
-    const raw = '{\n  agent: { workspace: "~/clawd" }\n}\n';
+    const raw = '{\n  agents: { defaults: { workspace: "~/clawd" } }\n}\n';
     await tool.execute("call2", {
       action: "config.apply",
       raw,

src/agents/clawdbot-tools.agents.test.ts

@@ -52,18 +52,20 @@ describe("agents_list", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             name: "Main",
             subagents: {
               allowAgents: ["research"],
             },
           },
-          research: {
+          {
+            id: "research",
             name: "Research",
           },
-        },
+        ],
       },
     };
 
@@ -87,20 +89,23 @@ describe("agents_list", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["*"],
             },
           },
-          research: {
+          {
+            id: "research",
             name: "Research",
           },
-          coder: {
+          {
+            id: "coder",
             name: "Coder",
           },
-        },
+        ],
       },
     };
 
@@ -131,14 +136,15 @@ describe("agents_list", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["research"],
             },
           },
-        },
+        ],
       },
     };
 

src/agents/clawdbot-tools.subagents.test.ts

@@ -314,14 +314,15 @@ describe("subagents", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["beta"],
             },
           },
-        },
+        ],
       },
     };
 
@@ -365,14 +366,15 @@ describe("subagents", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["*"],
             },
           },
-        },
+        ],
       },
     };
 
@@ -416,14 +418,15 @@ describe("subagents", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["Research"],
             },
           },
-        },
+        ],
       },
     };
 
@@ -467,14 +470,15 @@ describe("subagents", () => {
         mainKey: "main",
         scope: "per-sender",
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             subagents: {
               allowAgents: ["alpha"],
             },
           },
-        },
+        ],
       },
     };
 

src/agents/model-fallback.ts

@@ -34,7 +34,7 @@ function buildAllowedModelKeys(
   defaultProvider: string,
 ): Set<string> | null {
   const rawAllowlist = (() => {
-    const modelMap = cfg?.agent?.models ?? {};
+    const modelMap = cfg?.agents?.defaults?.models ?? {};
     return Object.keys(modelMap);
   })();
   if (rawAllowlist.length === 0) return null;
@@ -85,7 +85,7 @@ function resolveImageFallbackCandidates(params: {
   if (params.modelOverride?.trim()) {
     addRaw(params.modelOverride, false);
   } else {
-    const imageModel = params.cfg?.agent?.imageModel as
+    const imageModel = params.cfg?.agents?.defaults?.imageModel as
       | { primary?: string }
       | string
       | undefined;
@@ -95,7 +95,7 @@ function resolveImageFallbackCandidates(params: {
   }
 
   const imageFallbacks = (() => {
-    const imageModel = params.cfg?.agent?.imageModel as
+    const imageModel = params.cfg?.agents?.defaults?.imageModel as
       | { fallbacks?: string[] }
       | string
       | undefined;
@@ -142,7 +142,7 @@ function resolveFallbackCandidates(params: {
   addCandidate({ provider, model }, false);
 
   const modelFallbacks = (() => {
-    const model = params.cfg?.agent?.model as
+    const model = params.cfg?.agents?.defaults?.model as
       | { fallbacks?: string[] }
       | string
       | undefined;
@@ -253,7 +253,7 @@ export async function runWithImageModelFallback<T>(params: {
   });
   if (candidates.length === 0) {
     throw new Error(
-      "No image model configured. Set agent.imageModel.primary or agent.imageModel.fallbacks.",
+      "No image model configured. Set agents.defaults.imageModel.primary or agents.defaults.imageModel.fallbacks.",
     );
   }
 

src/agents/model-selection.test.ts

@@ -18,9 +18,11 @@ const catalog = [
 describe("buildAllowedModelSet", () => {
   it("always allows the configured default model", () => {
     const cfg = {
-      agent: {
-        models: {
-          "openai/gpt-4": { alias: "gpt4" },
+      agents: {
+        defaults: {
+          models: {
+            "openai/gpt-4": { alias: "gpt4" },
+          },
         },
       },
     } as ClawdbotConfig;
@@ -41,7 +43,7 @@ describe("buildAllowedModelSet", () => {
 
   it("includes the default model when no allowlist is set", () => {
     const cfg = {
-      agent: {},
+      agents: { defaults: {} },
     } as ClawdbotConfig;
 
     const allowed = buildAllowedModelSet({

src/agents/model-selection.ts

@@ -65,7 +65,7 @@ export function buildModelAliasIndex(params: {
   const byAlias = new Map<string, { alias: string; ref: ModelRef }>();
   const byKey = new Map<string, string[]>();
 
-  const rawModels = params.cfg.agent?.models ?? {};
+  const rawModels = params.cfg.agents?.defaults?.models ?? {};
   for (const [keyRaw, entryRaw] of Object.entries(rawModels)) {
     const parsed = parseModelRef(String(keyRaw ?? ""), params.defaultProvider);
     if (!parsed) continue;
@@ -109,7 +109,7 @@ export function resolveConfiguredModelRef(params: {
   defaultModel: string;
 }): ModelRef {
   const rawModel = (() => {
-    const raw = params.cfg.agent?.model as
+    const raw = params.cfg.agents?.defaults?.model as
       | { primary?: string }
       | string
       | undefined;
@@ -128,7 +128,7 @@ export function resolveConfiguredModelRef(params: {
       aliasIndex,
     });
     if (resolved) return resolved.ref;
-    // TODO(steipete): drop this fallback once provider-less agent.model is fully deprecated.
+    // TODO(steipete): drop this fallback once provider-less agents.defaults.model is fully deprecated.
     return { provider: "anthropic", model: trimmed };
   }
   return { provider: params.defaultProvider, model: params.defaultModel };
@@ -145,7 +145,7 @@ export function buildAllowedModelSet(params: {
   allowedKeys: Set<string>;
 } {
   const rawAllowlist = (() => {
-    const modelMap = params.cfg.agent?.models ?? {};
+    const modelMap = params.cfg.agents?.defaults?.models ?? {};
     return Object.keys(modelMap);
   })();
   const allowAny = rawAllowlist.length === 0;
@@ -203,7 +203,7 @@ export function resolveThinkingDefault(params: {
   model: string;
   catalog?: ModelCatalogEntry[];
 }): ThinkLevel {
-  const configured = params.cfg.agent?.thinkingDefault;
+  const configured = params.cfg.agents?.defaults?.thinkingDefault;
   if (configured) return configured;
   const candidate = params.catalog?.find(
     (entry) => entry.provider === params.provider && entry.id === params.model,

src/agents/pi-embedded-runner-extraparams.test.ts

@@ -110,12 +110,14 @@ describe("resolveExtraParams", () => {
     it("respects explicit thinking config from user (disable thinking)", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                params: {
-                  thinking: {
-                    type: "disabled",
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  params: {
+                    thinking: {
+                      type: "disabled",
+                    },
                   },
                 },
               },
@@ -136,12 +138,14 @@ describe("resolveExtraParams", () => {
     it("preserves other params while adding thinking config", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                params: {
-                  temperature: 0.7,
-                  max_tokens: 4096,
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  params: {
+                    temperature: 0.7,
+                    max_tokens: 4096,
+                  },
                 },
               },
             },
@@ -164,13 +168,15 @@ describe("resolveExtraParams", () => {
     it("does not override explicit thinking config even if partial", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                params: {
-                  thinking: {
-                    type: "enabled",
-                    // User explicitly omitted clear_thinking
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  params: {
+                    thinking: {
+                      type: "enabled",
+                      // User explicitly omitted clear_thinking
+                    },
                   },
                 },
               },
@@ -214,12 +220,14 @@ describe("resolveExtraParams", () => {
     it("passes through params for non-GLM models without modification", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "openai/gpt-4": {
-                params: {
-                  logprobs: true,
-                  top_logprobs: 5,
+          agents: {
+            defaults: {
+              models: {
+                "openai/gpt-4": {
+                  params: {
+                    logprobs: true,
+                    top_logprobs: 5,
+                  },
                 },
               },
             },
@@ -264,7 +272,7 @@ describe("resolveExtraParams", () => {
 
     it("handles config with empty models gracefully", () => {
       const result = resolveExtraParams({
-        cfg: { agent: { models: {} } },
+        cfg: { agents: { defaults: { models: {} } } },
         provider: "zai",
         modelId: "glm-4.7",
       });
@@ -280,12 +288,14 @@ describe("resolveExtraParams", () => {
     it("model alias lookup uses exact provider/model key", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                alias: "smart",
-                params: {
-                  custom_param: "value",
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  alias: "smart",
+                  params: {
+                    custom_param: "value",
+                  },
                 },
               },
             },
@@ -307,11 +317,13 @@ describe("resolveExtraParams", () => {
     it("treats thinking: null as explicit config (no auto-enable)", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                params: {
-                  thinking: null,
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  params: {
+                    thinking: null,
+                  },
                 },
               },
             },
@@ -374,11 +386,13 @@ describe("resolveExtraParams", () => {
     it("thinkLevel: 'off' still passes through explicit config", () => {
       const result = resolveExtraParams({
         cfg: {
-          agent: {
-            models: {
-              "zai/glm-4.7": {
-                params: {
-                  custom_param: "value",
+          agents: {
+            defaults: {
+              models: {
+                "zai/glm-4.7": {
+                  params: {
+                    custom_param: "value",
+                  },
                 },
               },
             },

src/agents/pi-embedded-runner.ts

@@ -105,7 +105,7 @@ import { loadWorkspaceBootstrapFiles } from "./workspace.js";
  * - GLM-4.5/4.6: Interleaved thinking (clear_thinking: true) - reasoning cleared each turn
  *
  * Users can override via config:
- *   agent.models["zai/glm-4.7"].params.thinking = { type: "disabled" }
+ *   agents.defaults.models["zai/glm-4.7"].params.thinking = { type: "disabled" }
  *
  * Or disable via runtime flag: --thinking off
  *
@@ -119,7 +119,7 @@ export function resolveExtraParams(params: {
   thinkLevel?: string;
 }): Record<string, unknown> | undefined {
   const modelKey = `${params.provider}/${params.modelId}`;
-  const modelConfig = params.cfg?.agent?.models?.[modelKey];
+  const modelConfig = params.cfg?.agents?.defaults?.models?.[modelKey];
   let extraParams = modelConfig?.params ? { ...modelConfig.params } : undefined;
 
   // Auto-enable thinking for ZAI GLM-4.x models when not explicitly configured
@@ -200,10 +200,10 @@ function resolveContextWindowTokens(params: {
   if (fromModelsConfig) return fromModelsConfig;
 
   const fromAgentConfig =
-    typeof params.cfg?.agent?.contextTokens === "number" &&
-    Number.isFinite(params.cfg.agent.contextTokens) &&
-    params.cfg.agent.contextTokens > 0
-      ? Math.floor(params.cfg.agent.contextTokens)
+    typeof params.cfg?.agents?.defaults?.contextTokens === "number" &&
+    Number.isFinite(params.cfg.agents.defaults.contextTokens) &&
+    params.cfg.agents.defaults.contextTokens > 0
+      ? Math.floor(params.cfg.agents.defaults.contextTokens)
       : undefined;
   if (fromAgentConfig) return fromAgentConfig;
 
@@ -217,7 +217,7 @@ function buildContextPruningExtension(params: {
   modelId: string;
   model: Model<Api> | undefined;
 }): { additionalExtensionPaths?: string[] } {
-  const raw = params.cfg?.agent?.contextPruning;
+  const raw = params.cfg?.agents?.defaults?.contextPruning;
   if (raw?.mode !== "adaptive" && raw?.mode !== "aggressive") return {};
 
   const settings = computeEffectiveSettings(raw);
@@ -254,7 +254,7 @@ export type EmbeddedPiRunMeta = {
 };
 
 function buildModelAliasLines(cfg?: ClawdbotConfig) {
-  const models = cfg?.agent?.models ?? {};
+  const models = cfg?.agents?.defaults?.models ?? {};
   const entries: Array<{ alias: string; model: string }> = [];
   for (const [keyRaw, entryRaw] of Object.entries(models)) {
     const model = String(keyRaw ?? "").trim();
@@ -844,7 +844,7 @@ export async function compactEmbeddedPiSession(params: {
         const contextFiles = buildBootstrapContextFiles(bootstrapFiles);
         const tools = createClawdbotCodingTools({
           bash: {
-            ...params.config?.agent?.bash,
+            ...params.config?.tools?.bash,
             elevated: params.bashElevated,
           },
           sandbox,
@@ -865,7 +865,7 @@ export async function compactEmbeddedPiSession(params: {
         const sandboxInfo = buildEmbeddedSandboxInfo(sandbox);
         const reasoningTagHint = provider === "ollama";
         const userTimezone = resolveUserTimezone(
-          params.config?.agent?.userTimezone,
+          params.config?.agents?.defaults?.userTimezone,
         );
         const userTime = formatUserTime(new Date(), userTimezone);
         const appendPrompt = buildEmbeddedSystemPrompt({
@@ -875,7 +875,7 @@ export async function compactEmbeddedPiSession(params: {
           ownerNumbers: params.ownerNumbers,
           reasoningTagHint,
           heartbeatPrompt: resolveHeartbeatPrompt(
-            params.config?.agent?.heartbeat?.prompt,
+            params.config?.agents?.defaults?.heartbeat?.prompt,
           ),
           runtimeInfo,
           sandboxInfo,
@@ -1157,7 +1157,7 @@ export async function runEmbeddedPiAgent(params: {
           // `createClawdbotCodingTools()` normalizes schemas so the session can pass them through unchanged.
           const tools = createClawdbotCodingTools({
             bash: {
-              ...params.config?.agent?.bash,
+              ...params.config?.tools?.bash,
               elevated: params.bashElevated,
             },
             sandbox,
@@ -1178,7 +1178,7 @@ export async function runEmbeddedPiAgent(params: {
           const sandboxInfo = buildEmbeddedSandboxInfo(sandbox);
           const reasoningTagHint = provider === "ollama";
           const userTimezone = resolveUserTimezone(
-            params.config?.agent?.userTimezone,
+            params.config?.agents?.defaults?.userTimezone,
           );
           const userTime = formatUserTime(new Date(), userTimezone);
           const appendPrompt = buildEmbeddedSystemPrompt({
@@ -1188,7 +1188,7 @@ export async function runEmbeddedPiAgent(params: {
             ownerNumbers: params.ownerNumbers,
             reasoningTagHint,
             heartbeatPrompt: resolveHeartbeatPrompt(
-              params.config?.agent?.heartbeat?.prompt,
+              params.config?.agents?.defaults?.heartbeat?.prompt,
             ),
             runtimeInfo,
             sandboxInfo,
@@ -1444,7 +1444,8 @@ export async function runEmbeddedPiAgent(params: {
           }
 
           const fallbackConfigured =
-            (params.config?.agent?.model?.fallbacks?.length ?? 0) > 0;
+            (params.config?.agents?.defaults?.model?.fallbacks?.length ?? 0) >
+            0;
           const authFailure = isAuthAssistantError(lastAssistant);
           const rateLimitFailure = isRateLimitAssistantError(lastAssistant);
 

src/agents/pi-tools-agent-config.test.ts

@@ -6,18 +6,17 @@ import type { SandboxDockerConfig } from "./sandbox.js";
 describe("Agent-specific tool filtering", () => {
   it("should apply global tool policy when no agent-specific policy exists", () => {
     const cfg: ClawdbotConfig = {
-      agent: {
-        tools: {
-          allow: ["read", "write"],
-          deny: ["bash"],
-        },
+      tools: {
+        allow: ["read", "write"],
+        deny: ["bash"],
       },
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             workspace: "~/clawd",
           },
-        },
+        ],
       },
     };
 
@@ -36,22 +35,21 @@ describe("Agent-specific tool filtering", () => {
 
   it("should apply agent-specific tool policy", () => {
     const cfg: ClawdbotConfig = {
-      agent: {
-        tools: {
-          allow: ["read", "write", "bash"],
-          deny: [],
-        },
+      tools: {
+        allow: ["read", "write", "bash"],
+        deny: [],
       },
-      routing: {
-        agents: {
-          restricted: {
+      agents: {
+        list: [
+          {
+            id: "restricted",
             workspace: "~/clawd-restricted",
             tools: {
               allow: ["read"], // Agent override: only read
               deny: ["bash", "write", "edit"],
             },
           },
-        },
+        ],
       },
     };
 
@@ -71,20 +69,22 @@ describe("Agent-specific tool filtering", () => {
 
   it("should allow different tool policies for different agents", () => {
     const cfg: ClawdbotConfig = {
-      routing: {
-        agents: {
-          main: {
+      agents: {
+        list: [
+          {
+            id: "main",
             workspace: "~/clawd",
             // No tools restriction - all tools available
           },
-          family: {
+          {
+            id: "family",
             workspace: "~/clawd-family",
             tools: {
               allow: ["read"],
               deny: ["bash", "write", "edit", "process"],
             },
           },
-        },
+        ],
       },
     };
 
@@ -116,20 +116,19 @@ describe("Agent-specific tool filtering", () => {
 
   it("should prefer agent-specific tool policy over global", () => {
     const cfg: ClawdbotConfig = {
-      agent: {
-        tools: {
-          deny: ["browser"], // Global deny
-        },
+      tools: {
+        deny: ["browser"], // Global deny
       },
-      routing: {
-        agents: {
-          work: {
+      agents: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             tools: {
               deny: ["bash", "process"], // Agent deny (override)
             },
           },
-        },
+        ],
       },
     };
 
@@ -149,19 +148,16 @@ describe("Agent-specific tool filtering", () => {
 
   it("should work with sandbox tools filtering", () => {
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-          tools: {
-            allow: ["read", "write", "bash"], // Sandbox allows these
-            deny: [],
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
           },
         },
-      },
-      routing: {
-        agents: {
-          restricted: {
+        list: [
+          {
+            id: "restricted",
             workspace: "~/clawd-restricted",
             sandbox: {
               mode: "all",
@@ -172,6 +168,14 @@ describe("Agent-specific tool filtering", () => {
               deny: ["bash", "write"],
             },
           },
+        ],
+      },
+      tools: {
+        sandbox: {
+          tools: {
+            allow: ["read", "write", "bash"], // Sandbox allows these
+            deny: [],
+          },
         },
       },
     };
@@ -216,10 +220,8 @@ describe("Agent-specific tool filtering", () => {
 
   it("should run bash synchronously when process is denied", async () => {
     const cfg: ClawdbotConfig = {
-      agent: {
-        tools: {
-          deny: ["process"],
-        },
+      tools: {
+        deny: ["process"],
       },
     };
 

src/agents/pi-tools.test.ts

@@ -171,7 +171,7 @@ describe("createClawdbotCodingTools", () => {
       sessionKey: "agent:main:subagent:test",
       // Intentionally partial config; only fields used by pi-tools are provided.
       config: {
-        agent: {
+        tools: {
           subagents: {
             tools: {
               // Policy matching is case-insensitive
@@ -325,7 +325,7 @@ describe("createClawdbotCodingTools", () => {
 
   it("filters tools by agent tool policy even without sandbox", () => {
     const tools = createClawdbotCodingTools({
-      config: { agent: { tools: { deny: ["browser"] } } },
+      config: { tools: { deny: ["browser"] } },
     });
     // NOTE: bash is capitalized to bypass Anthropic OAuth blocking
     expect(tools.some((tool) => tool.name === "Bash")).toBe(true);

src/agents/pi-tools.ts

@@ -429,7 +429,7 @@ const DEFAULT_SUBAGENT_TOOL_DENY = [
 ];
 
 function resolveSubagentToolPolicy(cfg?: ClawdbotConfig): SandboxToolPolicy {
-  const configured = cfg?.agent?.subagents?.tools;
+  const configured = cfg?.tools?.subagents?.tools;
   const deny = [
     ...DEFAULT_SUBAGENT_TOOL_DENY,
     ...(Array.isArray(configured?.deny) ? configured.deny : []),
@@ -466,7 +466,7 @@ function resolveEffectiveToolPolicy(params: {
       ? resolveAgentConfig(params.config, agentId)
       : undefined;
   const hasAgentTools = agentConfig?.tools !== undefined;
-  const globalTools = params.config?.agent?.tools;
+  const globalTools = params.config?.tools;
   return {
     agentId,
     policy: hasAgentTools ? agentConfig?.tools : globalTools,

src/agents/sandbox-agent-config.test.ts

@@ -56,18 +56,19 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-        },
-      },
-      routing: {
-        agents: {
-          main: {
-            workspace: "~/clawd",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
           },
         },
+        list: [
+          {
+            id: "main",
+            workspace: "~/clawd",
+          },
+        ],
       },
     };
 
@@ -85,18 +86,19 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-          docker: {
-            setupCommand: "echo global",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
+            docker: {
+              setupCommand: "echo global",
+            },
           },
         },
-      },
-      routing: {
-        agents: {
-          work: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             sandbox: {
               mode: "all",
@@ -106,7 +108,7 @@ describe("Agent-specific sandbox config", () => {
               },
             },
           },
-        },
+        ],
       },
     };
 
@@ -133,18 +135,19 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "shared",
-          docker: {
-            setupCommand: "echo global",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "shared",
+            docker: {
+              setupCommand: "echo global",
+            },
           },
         },
-      },
-      routing: {
-        agents: {
-          work: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             sandbox: {
               mode: "all",
@@ -154,7 +157,7 @@ describe("Agent-specific sandbox config", () => {
               },
             },
           },
-        },
+        ],
       },
     };
 
@@ -182,19 +185,20 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-          docker: {
-            image: "global-image",
-            network: "none",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
+            docker: {
+              image: "global-image",
+              network: "none",
+            },
           },
         },
-      },
-      routing: {
-        agents: {
-          work: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             sandbox: {
               mode: "all",
@@ -205,7 +209,7 @@ describe("Agent-specific sandbox config", () => {
               },
             },
           },
-        },
+        ],
       },
     };
 
@@ -224,21 +228,22 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all", // Global default
-          scope: "agent",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all", // Global default
+            scope: "agent",
+          },
         },
-      },
-      routing: {
-        agents: {
-          main: {
+        list: [
+          {
+            id: "main",
             workspace: "~/clawd",
             sandbox: {
               mode: "off", // Agent override
             },
           },
-        },
+        ],
       },
     };
 
@@ -256,21 +261,22 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "off", // Global default
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "off", // Global default
+          },
         },
-      },
-      routing: {
-        agents: {
-          family: {
+        list: [
+          {
+            id: "family",
             workspace: "~/clawd-family",
             sandbox: {
               mode: "all", // Agent override
               scope: "agent",
             },
           },
-        },
+        ],
       },
     };
 
@@ -288,22 +294,23 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "session", // Global default
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "session", // Global default
+          },
         },
-      },
-      routing: {
-        agents: {
-          work: {
+        list: [
+          {
+            id: "work",
             workspace: "~/clawd-work",
             sandbox: {
               mode: "all",
               scope: "agent", // Agent override
             },
           },
-        },
+        ],
       },
     };
 
@@ -322,16 +329,17 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-          workspaceRoot: "~/.clawdbot/sandboxes", // Global default
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
+            workspaceRoot: "~/.clawdbot/sandboxes", // Global default
+          },
         },
-      },
-      routing: {
-        agents: {
-          isolated: {
+        list: [
+          {
+            id: "isolated",
             workspace: "~/clawd-isolated",
             sandbox: {
               mode: "all",
@@ -339,7 +347,7 @@ describe("Agent-specific sandbox config", () => {
               workspaceRoot: "/tmp/isolated-sandboxes", // Agent override
             },
           },
-        },
+        ],
       },
     };
 
@@ -359,28 +367,30 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "non-main",
-          scope: "session",
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "non-main",
+            scope: "session",
+          },
         },
-      },
-      routing: {
-        agents: {
-          main: {
+        list: [
+          {
+            id: "main",
             workspace: "~/clawd",
             sandbox: {
               mode: "off", // main: no sandbox
             },
           },
-          family: {
+          {
+            id: "family",
             workspace: "~/clawd-family",
             sandbox: {
               mode: "all", // family: always sandbox
               scope: "agent",
             },
           },
-        },
+        ],
       },
     };
 
@@ -406,29 +416,38 @@ describe("Agent-specific sandbox config", () => {
     const { resolveSandboxContext } = await import("./sandbox.js");
 
     const cfg: ClawdbotConfig = {
-      agent: {
-        sandbox: {
-          mode: "all",
-          scope: "agent",
-          tools: {
-            allow: ["read"],
-            deny: ["bash"],
+      agents: {
+        defaults: {
+          sandbox: {
+            mode: "all",
+            scope: "agent",
           },
         },
-      },
-      routing: {
-        agents: {
-          restricted: {
+        list: [
+          {
+            id: "restricted",
             workspace: "~/clawd-restricted",
             sandbox: {
               mode: "all",
               scope: "agent",
-              tools: {
-                allow: ["read", "write"],
-                deny: ["edit"],
+            },
+            tools: {
+              sandbox: {
+                tools: {
+                  allow: ["read", "write"],
+                  deny: ["edit"],
+                },
               },
             },
           },
+        ],
+      },
+      tools: {
+        sandbox: {
+          tools: {
+            allow: ["read"],
+            deny: ["bash"],
+          },
         },
       },
     };

src/agents/sandbox.ts

@@ -22,7 +22,10 @@ import {
 import { normalizeAgentId } from "../routing/session-key.js";
 import { defaultRuntime } from "../runtime.js";
 import { resolveUserPath } from "../utils.js";
-import { resolveAgentIdFromSessionKey } from "./agent-scope.js";
+import {
+  resolveAgentConfig,
+  resolveAgentIdFromSessionKey,
+} from "./agent-scope.js";
 import { syncSkillsToWorkspace } from "./skills.js";
 import {
   DEFAULT_AGENT_WORKSPACE_DIR,
@@ -345,15 +348,14 @@ export function resolveSandboxConfigForAgent(
   cfg?: ClawdbotConfig,
   agentId?: string,
 ): SandboxConfig {
-  const agent = cfg?.agent?.sandbox;
+  const agent = cfg?.agents?.defaults?.sandbox;
 
   // Agent-specific sandbox config overrides global
   let agentSandbox: typeof agent | undefined;
-  if (agentId && cfg?.routing?.agents) {
-    const agentConfig = cfg.routing.agents[agentId];
-    if (agentConfig && typeof agentConfig === "object") {
-      agentSandbox = agentConfig.sandbox;
-    }
+  const agentConfig =
+    cfg && agentId ? resolveAgentConfig(cfg, agentId) : undefined;
+  if (agentConfig?.sandbox) {
+    agentSandbox = agentConfig.sandbox;
   }
 
   const scope = resolveSandboxScope({
@@ -382,9 +384,13 @@ export function resolveSandboxConfigForAgent(
     }),
     tools: {
       allow:
-        agentSandbox?.tools?.allow ?? agent?.tools?.allow ?? DEFAULT_TOOL_ALLOW,
+        agentConfig?.tools?.sandbox?.tools?.allow ??
+        cfg?.tools?.sandbox?.tools?.allow ??
+        DEFAULT_TOOL_ALLOW,
       deny:
-        agentSandbox?.tools?.deny ?? agent?.tools?.deny ?? DEFAULT_TOOL_DENY,
+        agentConfig?.tools?.sandbox?.tools?.deny ??
+        cfg?.tools?.sandbox?.tools?.deny ??
+        DEFAULT_TOOL_DENY,
     },
     prune: resolveSandboxPruneConfig({
       scope,
@@ -1059,7 +1065,7 @@ export async function resolveSandboxContext(params: {
     await ensureSandboxWorkspace(
       sandboxWorkspaceDir,
       agentWorkspaceDir,
-      params.config?.agent?.skipBootstrap,
+      params.config?.agents?.defaults?.skipBootstrap,
     );
     if (cfg.workspaceAccess === "none") {
       try {
@@ -1133,7 +1139,7 @@ export async function ensureSandboxWorkspaceForSession(params: {
     await ensureSandboxWorkspace(
       sandboxWorkspaceDir,
       agentWorkspaceDir,
-      params.config?.agent?.skipBootstrap,
+      params.config?.agents?.defaults?.skipBootstrap,
     );
     if (cfg.workspaceAccess === "none") {
       try {

src/agents/subagent-registry.ts

@@ -24,7 +24,7 @@ let listenerStarted = false;
 
 function resolveArchiveAfterMs() {
   const cfg = loadConfig();
-  const minutes = cfg.agent?.subagents?.archiveAfterMinutes ?? 60;
+  const minutes = cfg.agents?.defaults?.subagents?.archiveAfterMinutes ?? 60;
   if (!Number.isFinite(minutes) || minutes <= 0) return undefined;
   return Math.max(1, Math.floor(minutes)) * 60_000;
 }

src/agents/timeout.ts

@@ -8,7 +8,7 @@ const normalizeNumber = (value: unknown): number | undefined =>
     : undefined;
 
 export function resolveAgentTimeoutSeconds(cfg?: ClawdbotConfig): number {
-  const raw = normalizeNumber(cfg?.agent?.timeoutSeconds);
+  const raw = normalizeNumber(cfg?.agents?.defaults?.timeoutSeconds);
   const seconds = raw ?? DEFAULT_AGENT_TIMEOUT_SECONDS;
   return Math.max(seconds, 1);
 }

src/agents/tools/agents-list-tool.ts

@@ -55,19 +55,17 @@ export function createAgentsListTool(opts?: {
           .map((value) => normalizeAgentId(value)),
       );
 
-      const configuredAgents = cfg.routing?.agents ?? {};
-      const configuredIds = Object.keys(configuredAgents).map((key) =>
-        normalizeAgentId(key),
+      const configuredAgents = Array.isArray(cfg.agents?.list)
+        ? cfg.agents?.list
+        : [];
+      const configuredIds = configuredAgents.map((entry) =>
+        normalizeAgentId(entry.id),
       );
       const configuredNameMap = new Map<string, string>();
-      for (const [key, value] of Object.entries(configuredAgents)) {
-        if (!value || typeof value !== "object") continue;
-        const name =
-          typeof (value as { name?: unknown }).name === "string"
-            ? ((value as { name?: string }).name?.trim() ?? "")
-            : "";
+      for (const entry of configuredAgents) {
+        const name = entry?.name?.trim() ?? "";
         if (!name) continue;
-        configuredNameMap.set(normalizeAgentId(key), name);
+        configuredNameMap.set(normalizeAgentId(entry.id), name);
       }
 
       const allowed = new Set<string>();

src/agents/tools/image-tool.ts

@@ -23,7 +23,7 @@ import type { AnyAgentTool } from "./common.js";
 const DEFAULT_PROMPT = "Describe the image.";
 
 function ensureImageToolConfigured(cfg?: ClawdbotConfig): boolean {
-  const imageModel = cfg?.agent?.imageModel as
+  const imageModel = cfg?.agents?.defaults?.imageModel as
     | { primary?: string; fallbacks?: string[] }
     | string
     | undefined;
@@ -45,7 +45,7 @@ function pickMaxBytes(
   ) {
     return Math.floor(maxBytesMb * 1024 * 1024);
   }
-  const configured = cfg?.agent?.mediaMaxMb;
+  const configured = cfg?.agents?.defaults?.mediaMaxMb;
   if (
     typeof configured === "number" &&
     Number.isFinite(configured) &&
@@ -141,7 +141,7 @@ export function createImageTool(options?: {
     label: "Image",
     name: "image",
     description:
-      "Analyze an image with the configured image model (agent.imageModel). Provide a prompt and image path or URL.",
+      "Analyze an image with the configured image model (agents.defaults.imageModel). Provide a prompt and image path or URL.",
     parameters: Type.Object({
       prompt: Type.Optional(Type.String()),
       image: Type.String(),

src/agents/tools/sessions-history-tool.ts

@@ -25,7 +25,7 @@ const SessionsHistoryToolSchema = Type.Object({
 function resolveSandboxSessionToolsVisibility(
   cfg: ReturnType<typeof loadConfig>,
 ) {
-  return cfg.agent?.sandbox?.sessionToolsVisibility ?? "spawned";
+  return cfg.agents?.defaults?.sandbox?.sessionToolsVisibility ?? "spawned";
 }
 
 async function isSpawnedSessionAllowed(params: {
@@ -97,7 +97,7 @@ export function createSessionsHistoryTool(opts?: {
         }
       }
 
-      const routingA2A = cfg.routing?.agentToAgent;
+      const routingA2A = cfg.tools?.agentToAgent;
       const a2aEnabled = routingA2A?.enabled === true;
       const allowPatterns = Array.isArray(routingA2A?.allow)
         ? routingA2A.allow
@@ -126,14 +126,13 @@ export function createSessionsHistoryTool(opts?: {
           return jsonResult({
             status: "forbidden",
             error:
-              "Agent-to-agent history is disabled. Set routing.agentToAgent.enabled=true to allow cross-agent access.",
+              "Agent-to-agent history is disabled. Set tools.agentToAgent.enabled=true to allow cross-agent access.",
           });
         }
         if (!matchesAllow(requesterAgentId) || !matchesAllow(targetAgentId)) {
           return jsonResult({
             status: "forbidden",
-            error:
-              "Agent-to-agent history denied by routing.agentToAgent.allow.",
+            error: "Agent-to-agent history denied by tools.agentToAgent.allow.",
           });
         }
       }

src/agents/tools/sessions-list-tool.gating.test.ts

@@ -13,7 +13,7 @@ vi.mock("../../config/config.js", async (importOriginal) => {
     loadConfig: () =>
       ({
         session: { scope: "per-sender", mainKey: "main" },
-        routing: { agentToAgent: { enabled: false } },
+        tools: { agentToAgent: { enabled: false } },
       }) as never,
   };
 });
@@ -32,7 +32,7 @@ describe("sessions_list gating", () => {
     });
   });
 
-  it("filters out other agents when routing.agentToAgent.enabled is false", async () => {
+  it("filters out other agents when tools.agentToAgent.enabled is false", async () => {
     const tool = createSessionsListTool({ agentSessionKey: "agent:main:main" });
     const result = await tool.execute("call1", {});
     expect(result.details).toMatchObject({

src/agents/tools/sessions-list-tool.ts

@@ -53,7 +53,7 @@ const SessionsListToolSchema = Type.Object({
 function resolveSandboxSessionToolsVisibility(
   cfg: ReturnType<typeof loadConfig>,
 ) {
-  return cfg.agent?.sandbox?.sessionToolsVisibility ?? "spawned";
+  return cfg.agents?.defaults?.sandbox?.sessionToolsVisibility ?? "spawned";
 }
 
 export function createSessionsListTool(opts?: {
@@ -126,7 +126,7 @@ export function createSessionsListTool(opts?: {
 
       const sessions = Array.isArray(list?.sessions) ? list.sessions : [];
       const storePath = typeof list?.path === "string" ? list.path : undefined;
-      const routingA2A = cfg.routing?.agentToAgent;
+      const routingA2A = cfg.tools?.agentToAgent;
       const a2aEnabled = routingA2A?.enabled === true;
       const allowPatterns = Array.isArray(routingA2A?.allow)
         ? routingA2A.allow

src/agents/tools/sessions-send-tool.gating.test.ts

@@ -13,7 +13,7 @@ vi.mock("../../config/config.js", async (importOriginal) => {
     loadConfig: () =>
       ({
         session: { scope: "per-sender", mainKey: "main" },
-        routing: { agentToAgent: { enabled: false } },
+        tools: { agentToAgent: { enabled: false } },
       }) as never,
   };
 });
@@ -25,7 +25,7 @@ describe("sessions_send gating", () => {
     callGatewayMock.mockReset();
   });
 
-  it("blocks cross-agent sends when routing.agentToAgent.enabled is false", async () => {
+  it("blocks cross-agent sends when tools.agentToAgent.enabled is false", async () => {
     const tool = createSessionsSendTool({
       agentSessionKey: "agent:main:main",
       agentProvider: "whatsapp",

src/agents/tools/sessions-send-tool.ts

@@ -54,7 +54,7 @@ export function createSessionsSendTool(opts?: {
       const cfg = loadConfig();
       const { mainKey, alias } = resolveMainSessionAlias(cfg);
       const visibility =
-        cfg.agent?.sandbox?.sessionToolsVisibility ?? "spawned";
+        cfg.agents?.defaults?.sandbox?.sessionToolsVisibility ?? "spawned";
       const requesterInternalKey =
         typeof opts?.agentSessionKey === "string" && opts.agentSessionKey.trim()
           ? resolveInternalSessionKey({
@@ -126,7 +126,7 @@ export function createSessionsSendTool(opts?: {
         mainKey,
       });
 
-      const routingA2A = cfg.routing?.agentToAgent;
+      const routingA2A = cfg.tools?.agentToAgent;
       const a2aEnabled = routingA2A?.enabled === true;
       const allowPatterns = Array.isArray(routingA2A?.allow)
         ? routingA2A.allow
@@ -156,7 +156,7 @@ export function createSessionsSendTool(opts?: {
             runId: crypto.randomUUID(),
             status: "forbidden",
             error:
-              "Agent-to-agent messaging is disabled. Set routing.agentToAgent.enabled=true to allow cross-agent sends.",
+              "Agent-to-agent messaging is disabled. Set tools.agentToAgent.enabled=true to allow cross-agent sends.",
             sessionKey: displayKey,
           });
         }
@@ -165,7 +165,7 @@ export function createSessionsSendTool(opts?: {
             runId: crypto.randomUUID(),
             status: "forbidden",
             error:
-              "Agent-to-agent messaging denied by routing.agentToAgent.allow.",
+              "Agent-to-agent messaging denied by tools.agentToAgent.allow.",
             sessionKey: displayKey,
           });
         }

src/auto-reply/reply.block-streaming.test.ts

@@ -85,9 +85,11 @@ describe("block streaming", () => {
           onBlockReply,
         },
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -140,9 +142,11 @@ describe("block streaming", () => {
           onBlockReply,
         },
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           telegram: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -185,9 +189,11 @@ describe("block streaming", () => {
           onBlockReply,
         },
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -239,9 +245,11 @@ describe("block streaming", () => {
           blockReplyTimeoutMs: 10,
         },
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           telegram: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },

src/auto-reply/reply.directive.test.ts

@@ -78,11 +78,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": { alias: " help " },
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": { alias: " help " },
+              },
             },
           },
           whatsapp: { allowFrom: ["*"] },
@@ -108,9 +110,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -138,11 +142,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
-          routing: {
+          messages: {
             queue: {
               mode: "collect",
               debounceMs: 1500,
@@ -174,10 +180,12 @@ describe("directive behavior", () => {
         { Body: "/think", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
-            thinkingDefault: "high",
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              thinkingDefault: "high",
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -198,9 +206,11 @@ describe("directive behavior", () => {
         { Body: "/think", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -232,9 +242,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -270,9 +282,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: path.join(home, "sessions.json") },
@@ -303,9 +317,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -330,9 +346,11 @@ describe("directive behavior", () => {
         { Body: "/verbose on", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -352,10 +370,12 @@ describe("directive behavior", () => {
         { Body: "/think", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
-            thinkingDefault: "high",
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              thinkingDefault: "high",
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -376,9 +396,11 @@ describe("directive behavior", () => {
         { Body: "/think", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -399,10 +421,12 @@ describe("directive behavior", () => {
         { Body: "/verbose", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
-            verboseDefault: "on",
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              verboseDefault: "on",
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -423,9 +447,11 @@ describe("directive behavior", () => {
         { Body: "/reasoning", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           session: { store: path.join(home, "sessions.json") },
         },
@@ -452,10 +478,14 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
-            elevatedDefault: "on",
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              elevatedDefault: "on",
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1222"] },
             },
@@ -486,13 +516,17 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+              sandbox: { mode: "off" },
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1222"] },
             },
-            sandbox: { mode: "off" },
           },
           whatsapp: { allowFrom: ["+1222"] },
           session: { store: path.join(home, "sessions.json") },
@@ -520,9 +554,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1222"] },
             },
@@ -552,9 +590,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1222"] },
             },
@@ -585,9 +627,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1222"] },
             },
@@ -613,9 +659,11 @@ describe("directive behavior", () => {
         { Body: "/queue interrupt", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: storePath },
@@ -644,9 +692,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: storePath },
@@ -677,9 +727,11 @@ describe("directive behavior", () => {
         { Body: "/queue interrupt", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: storePath },
@@ -690,9 +742,11 @@ describe("directive behavior", () => {
         { Body: "/queue reset", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: { allowFrom: ["*"] },
           session: { store: storePath },
@@ -749,9 +803,11 @@ describe("directive behavior", () => {
         ctx,
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -810,9 +866,11 @@ describe("directive behavior", () => {
         { Body: "/verbose on", From: ctx.From, To: ctx.To },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -825,9 +883,11 @@ describe("directive behavior", () => {
         ctx,
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -853,12 +913,14 @@ describe("directive behavior", () => {
         { Body: "/model", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           session: { store: storePath },
@@ -883,12 +945,14 @@ describe("directive behavior", () => {
         { Body: "/model status", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           session: { store: storePath },
@@ -913,12 +977,14 @@ describe("directive behavior", () => {
         { Body: "/model list", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           session: { store: storePath },
@@ -943,12 +1009,14 @@ describe("directive behavior", () => {
         { Body: "/model", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           session: { store: storePath },
@@ -972,11 +1040,13 @@ describe("directive behavior", () => {
         { Body: "/model list", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+              },
             },
           },
           session: { store: storePath },
@@ -999,12 +1069,14 @@ describe("directive behavior", () => {
         { Body: "/model openai/gpt-4.1-mini", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           session: { store: storePath },
@@ -1030,12 +1102,14 @@ describe("directive behavior", () => {
         { Body: "/model Opus", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "openai/gpt-4.1-mini" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "openai/gpt-4.1-mini": {},
-              "anthropic/claude-opus-4-5": { alias: "Opus" },
+          agents: {
+            defaults: {
+              model: { primary: "openai/gpt-4.1-mini" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "openai/gpt-4.1-mini": {},
+                "anthropic/claude-opus-4-5": { alias: "Opus" },
+              },
             },
           },
           session: { store: storePath },
@@ -1081,12 +1155,14 @@ describe("directive behavior", () => {
         { Body: "/model Opus@anthropic:work", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "openai/gpt-4.1-mini" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "openai/gpt-4.1-mini": {},
-              "anthropic/claude-opus-4-5": { alias: "Opus" },
+          agents: {
+            defaults: {
+              model: { primary: "openai/gpt-4.1-mini" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "openai/gpt-4.1-mini": {},
+                "anthropic/claude-opus-4-5": { alias: "Opus" },
+              },
             },
           },
           session: { store: storePath },
@@ -1112,12 +1188,14 @@ describe("directive behavior", () => {
         { Body: "/model Opus", From: "+1222", To: "+1222" },
         {},
         {
-          agent: {
-            model: { primary: "openai/gpt-4.1-mini" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "openai/gpt-4.1-mini": {},
-              "anthropic/claude-opus-4-5": { alias: "Opus" },
+          agents: {
+            defaults: {
+              model: { primary: "openai/gpt-4.1-mini" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "openai/gpt-4.1-mini": {},
+                "anthropic/claude-opus-4-5": { alias: "Opus" },
+              },
             },
           },
           session: { store: storePath },
@@ -1151,12 +1229,14 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: { primary: "anthropic/claude-opus-4-5" },
-            workspace: path.join(home, "clawd"),
-            models: {
-              "anthropic/claude-opus-4-5": {},
-              "openai/gpt-4.1-mini": {},
+          agents: {
+            defaults: {
+              model: { primary: "anthropic/claude-opus-4-5" },
+              workspace: path.join(home, "clawd"),
+              models: {
+                "anthropic/claude-opus-4-5": {},
+                "openai/gpt-4.1-mini": {},
+              },
             },
           },
           whatsapp: {
@@ -1204,9 +1284,11 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -1242,9 +1324,13 @@ describe("directive behavior", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: path.join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: path.join(home, "clawd"),
+            },
+          },
+          tools: {
             elevated: {
               allowFrom: { whatsapp: ["+1004"] },
             },

src/auto-reply/reply.heartbeat-typing.test.ts

@@ -57,9 +57,11 @@ async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
 
 function makeCfg(home: string) {
   return {
-    agent: {
-      model: "anthropic/claude-opus-4-5",
-      workspace: join(home, "clawd"),
+    agents: {
+      defaults: {
+        model: "anthropic/claude-opus-4-5",
+        workspace: join(home, "clawd"),
+      },
     },
     whatsapp: {
       allowFrom: ["*"],

src/auto-reply/reply.media-note.test.ts

@@ -53,9 +53,11 @@ async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
 
 function makeCfg(home: string) {
   return {
-    agent: {
-      model: "anthropic/claude-opus-4-5",
-      workspace: path.join(home, "clawd"),
+    agents: {
+      defaults: {
+        model: "anthropic/claude-opus-4-5",
+        workspace: path.join(home, "clawd"),
+      },
     },
     whatsapp: { allowFrom: ["*"] },
     session: { store: path.join(home, "sessions.json") },

src/auto-reply/reply.queue.test.ts

@@ -50,13 +50,15 @@ async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
 
 function makeCfg(home: string, queue?: Record<string, unknown>) {
   return {
-    agent: {
-      model: "anthropic/claude-opus-4-5",
-      workspace: path.join(home, "clawd"),
+    agents: {
+      defaults: {
+        model: "anthropic/claude-opus-4-5",
+        workspace: path.join(home, "clawd"),
+      },
     },
     whatsapp: { allowFrom: ["*"] },
     session: { store: path.join(home, "sessions.json") },
-    routing: queue ? { queue } : undefined,
+    messages: queue ? { queue } : undefined,
   };
 }
 

src/auto-reply/reply.triggers.test.ts

@@ -25,13 +25,18 @@ const usageMocks = vi.hoisted(() => ({
 
 vi.mock("../infra/provider-usage.js", () => usageMocks);
 
+import { resolveAgentWorkspaceDir } from "../agents/agent-scope.js";
 import {
   abortEmbeddedPiRun,
   compactEmbeddedPiSession,
   runEmbeddedPiAgent,
 } from "../agents/pi-embedded.js";
 import { ensureSandboxWorkspaceForSession } from "../agents/sandbox.js";
-import { loadSessionStore, resolveSessionKey } from "../config/sessions.js";
+import {
+  loadSessionStore,
+  resolveAgentIdFromSessionKey,
+  resolveSessionKey,
+} from "../config/sessions.js";
 import { getReplyFromConfig } from "./reply.js";
 import { HEARTBEAT_TOKEN } from "./tokens.js";
 
@@ -61,9 +66,11 @@ async function withTempHome<T>(fn: (home: string) => Promise<T>): Promise<T> {
 
 function makeCfg(home: string) {
   return {
-    agent: {
-      model: "anthropic/claude-opus-4-5",
-      workspace: join(home, "clawd"),
+    agents: {
+      defaults: {
+        model: "anthropic/claude-opus-4-5",
+        workspace: join(home, "clawd"),
+      },
     },
     whatsapp: {
       allowFrom: ["*"],
@@ -345,9 +352,11 @@ describe("trigger handling", () => {
   it("allows owner to set send policy", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
         },
         whatsapp: {
           allowFrom: ["+1000"],
@@ -381,9 +390,13 @@ describe("trigger handling", () => {
   it("allows approved sender to toggle elevated mode", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -420,9 +433,13 @@ describe("trigger handling", () => {
   it("rejects elevated toggles when disabled", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             enabled: false,
             allowFrom: { whatsapp: ["+1000"] },
@@ -467,9 +484,13 @@ describe("trigger handling", () => {
         },
       });
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -510,9 +531,13 @@ describe("trigger handling", () => {
         },
       });
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -545,9 +570,13 @@ describe("trigger handling", () => {
   it("allows elevated directive in groups when mentioned", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -589,9 +618,13 @@ describe("trigger handling", () => {
   it("allows elevated directive in direct chats without mentions", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -635,9 +668,13 @@ describe("trigger handling", () => {
         },
       });
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { whatsapp: ["+1000"] },
           },
@@ -668,9 +705,11 @@ describe("trigger handling", () => {
   it("falls back to discord dm allowFrom for elevated approval", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
         },
         discord: {
           dm: {
@@ -708,9 +747,13 @@ describe("trigger handling", () => {
   it("treats explicit discord elevated allowlist as override", async () => {
     await withTempHome(async (home) => {
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+          },
+        },
+        tools: {
           elevated: {
             allowFrom: { discord: [] },
           },
@@ -799,9 +842,12 @@ describe("trigger handling", () => {
       });
 
       const cfg = makeCfg(home);
-      cfg.agent = {
-        ...cfg.agent,
-        heartbeat: { model: "anthropic/claude-haiku-4-5-20251001" },
+      cfg.agents = {
+        ...cfg.agents,
+        defaults: {
+          ...cfg.agents?.defaults,
+          heartbeat: { model: "anthropic/claude-haiku-4-5-20251001" },
+        },
       };
 
       await getReplyFromConfig(
@@ -941,15 +987,17 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
             groups: { "*": { requireMention: false } },
           },
-          routing: {
+          messages: {
             groupChat: {},
           },
           session: { store: join(home, "sessions.json") },
@@ -985,9 +1033,11 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -1024,9 +1074,11 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -1056,9 +1108,11 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["+1999"],
@@ -1083,9 +1137,11 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["+1999"],
@@ -1124,9 +1180,11 @@ describe("trigger handling", () => {
         },
         {},
         {
-          agent: {
-            model: "anthropic/claude-opus-4-5",
-            workspace: join(home, "clawd"),
+          agents: {
+            defaults: {
+              model: "anthropic/claude-opus-4-5",
+              workspace: join(home, "clawd"),
+            },
           },
           whatsapp: {
             allowFrom: ["*"],
@@ -1229,12 +1287,14 @@ describe("trigger handling", () => {
       });
 
       const cfg = {
-        agent: {
-          model: "anthropic/claude-opus-4-5",
-          workspace: join(home, "clawd"),
-          sandbox: {
-            mode: "non-main" as const,
-            workspaceRoot: join(home, "sandboxes"),
+        agents: {
+          defaults: {
+            model: "anthropic/claude-opus-4-5",
+            workspace: join(home, "clawd"),
+            sandbox: {
+              mode: "non-main" as const,
+              workspaceRoot: join(home, "sandboxes"),
+            },
           },
         },
         whatsapp: {
@@ -1272,10 +1332,11 @@ describe("trigger handling", () => {
         ctx,
         cfg.session?.mainKey,
       );
+      const agentId = resolveAgentIdFromSessionKey(sessionKey);
       const sandbox = await ensureSandboxWorkspaceForSession({
         config: cfg,
         sessionKey,
-        workspaceDir: cfg.agent.workspace,
+        workspaceDir: resolveAgentWorkspaceDir(cfg, agentId),
       });
       expect(sandbox).not.toBeNull();
       if (!sandbox) {

src/auto-reply/reply.ts

@@ -212,7 +212,7 @@ export async function getReplyFromConfig(
 ): Promise<ReplyPayload | ReplyPayload[] | undefined> {
   const cfg = configOverride ?? loadConfig();
   const agentId = resolveAgentIdFromSessionKey(ctx.SessionKey);
-  const agentCfg = cfg.agent;
+  const agentCfg = cfg.agents?.defaults;
   const sessionCfg = cfg.session;
   const { defaultProvider, defaultModel, aliasIndex } = resolveDefaultModel({
     cfg,
@@ -239,7 +239,7 @@ export async function getReplyFromConfig(
     resolveAgentWorkspaceDir(cfg, agentId) ?? DEFAULT_AGENT_WORKSPACE_DIR;
   const workspace = await ensureAgentWorkspace({
     dir: workspaceDirRaw,
-    ensureBootstrapFiles: !cfg.agent?.skipBootstrap,
+    ensureBootstrapFiles: !agentCfg?.skipBootstrap,
   });
   const workspaceDir = workspace.dir;
   const agentDir = resolveAgentDir(cfg, agentId);
@@ -257,7 +257,7 @@ export async function getReplyFromConfig(
   opts?.onTypingController?.(typing);
 
   let transcribedText: string | undefined;
-  if (cfg.routing?.transcribeAudio && isAudio(ctx.MediaType)) {
+  if (cfg.audio?.transcription && isAudio(ctx.MediaType)) {
     const transcribed = await transcribeInboundAudio(cfg, ctx, defaultRuntime);
     if (transcribed?.text) {
       transcribedText = transcribed.text;
@@ -329,7 +329,7 @@ export async function getReplyFromConfig(
       cmd.textAliases.map((a) => a.replace(/^\//, "").toLowerCase()),
     ),
   );
-  const configuredAliases = Object.values(cfg.agent?.models ?? {})
+  const configuredAliases = Object.values(cfg.agents?.defaults?.models ?? {})
     .map((entry) => entry.alias?.trim())
     .filter((alias): alias is string => Boolean(alias))
     .filter((alias) => !reservedCommands.has(alias.toLowerCase()));
@@ -391,7 +391,7 @@ export async function getReplyFromConfig(
     sessionCtx.Provider?.trim().toLowerCase() ??
     ctx.Provider?.trim().toLowerCase() ??
     "";
-  const elevatedConfig = agentCfg?.elevated;
+  const elevatedConfig = cfg.tools?.elevated;
   const discordElevatedFallback =
     messageProviderKey === "discord" ? cfg.discord?.dm?.allowFrom : undefined;
   const elevatedEnabled = elevatedConfig?.enabled !== false;

src/auto-reply/reply/block-streaming.ts

@@ -34,7 +34,7 @@ export function resolveBlockStreamingChunking(
 } {
   const providerKey = normalizeChunkProvider(provider);
   const textLimit = resolveTextChunkLimit(cfg, providerKey);
-  const chunkCfg = cfg?.agent?.blockStreamingChunk;
+  const chunkCfg = cfg?.agents?.defaults?.blockStreamingChunk;
   const maxRequested = Math.max(
     1,
     Math.floor(chunkCfg?.maxChars ?? DEFAULT_BLOCK_STREAM_MAX),

src/auto-reply/reply/commands.ts

@@ -163,18 +163,19 @@ export async function buildStatusReply(params: {
     ? (normalizeGroupActivation(sessionEntry?.groupActivation) ??
       defaultGroupActivation())
     : undefined;
+  const agentDefaults = cfg.agents?.defaults ?? {};
   const statusText = buildStatusMessage({
     config: cfg,
     agent: {
-      ...cfg.agent,
+      ...agentDefaults,
       model: {
-        ...cfg.agent?.model,
+        ...agentDefaults.model,
         primary: `${provider}/${model}`,
       },
       contextTokens,
-      thinkingDefault: cfg.agent?.thinkingDefault,
-      verboseDefault: cfg.agent?.verboseDefault,
-      elevatedDefault: cfg.agent?.elevatedDefault,
+      thinkingDefault: agentDefaults.thinkingDefault,
+      verboseDefault: agentDefaults.verboseDefault,
+      elevatedDefault: agentDefaults.elevatedDefault,
     },
     sessionEntry,
     sessionKey,

src/auto-reply/reply/directive-handling.ts

@@ -23,6 +23,7 @@ import {
   resolveConfiguredModelRef,
   resolveModelRefFromString,
 } from "../../agents/model-selection.js";
+import { resolveSandboxConfigForAgent } from "../../agents/sandbox.js";
 import type { ClawdbotConfig } from "../../config/config.js";
 import {
   resolveAgentIdFromSessionKey,
@@ -363,16 +364,16 @@ export async function handleDirectiveOnly(params: {
     currentElevatedLevel,
   } = params;
   const runtimeIsSandboxed = (() => {
-    const sandboxMode = params.cfg.agent?.sandbox?.mode ?? "off";
-    if (sandboxMode === "off") return false;
     const sessionKey = params.sessionKey?.trim();
     if (!sessionKey) return false;
     const agentId = resolveAgentIdFromSessionKey(sessionKey);
+    const sandboxCfg = resolveSandboxConfigForAgent(params.cfg, agentId);
+    if (sandboxCfg.mode === "off") return false;
     const mainKey = resolveAgentMainSessionKey({
       cfg: params.cfg,
       agentId,
     });
-    if (sandboxMode === "all") return true;
+    if (sandboxCfg.mode === "all") return true;
     return sessionKey !== mainKey;
   })();
   const shouldHintDirectRuntime =
@@ -394,7 +395,9 @@ export async function handleDirectiveOnly(params: {
           provider: string;
           id: string;
         }> = [];
-        for (const raw of Object.keys(params.cfg.agent?.models ?? {})) {
+        for (const raw of Object.keys(
+          params.cfg.agents?.defaults?.models ?? {},
+        )) {
           const resolved = resolveModelRefFromString({
             raw: String(raw),
             defaultProvider,
@@ -851,7 +854,7 @@ export async function persistInlineDirectives(params: {
   model: string;
   initialModelLabel: string;
   formatModelSwitchEvent: (label: string, alias?: string) => string;
-  agentCfg: ClawdbotConfig["agent"] | undefined;
+  agentCfg: NonNullable<ClawdbotConfig["agents"]>["defaults"] | undefined;
 }): Promise<{ provider: string; model: string; contextTokens: number }> {
   const {
     directives,
@@ -1007,13 +1010,16 @@ export function resolveDefaultModel(params: {
     agentModelOverride && agentModelOverride.length > 0
       ? {
           ...params.cfg,
-          agent: {
-            ...params.cfg.agent,
-            model: {
-              ...(typeof params.cfg.agent?.model === "object"
-                ? params.cfg.agent.model
-                : undefined),
-              primary: agentModelOverride,
+          agents: {
+            ...params.cfg.agents,
+            defaults: {
+              ...params.cfg.agents?.defaults,
+              model: {
+                ...(typeof params.cfg.agents?.defaults?.model === "object"
+                  ? params.cfg.agents.defaults.model
+                  : undefined),
+                primary: agentModelOverride,
+              },
             },
           },
         }

src/auto-reply/reply/mentions.test.ts

@@ -9,7 +9,7 @@ import {
 describe("mention helpers", () => {
   it("builds regexes and skips invalid patterns", () => {
     const regexes = buildMentionRegexes({
-      routing: {
+      messages: {
         groupChat: { mentionPatterns: ["\\bclawd\\b", "(invalid"] },
       },
     });
@@ -23,7 +23,7 @@ describe("mention helpers", () => {
 
   it("matches patterns case-insensitively", () => {
     const regexes = buildMentionRegexes({
-      routing: { groupChat: { mentionPatterns: ["\\bclawd\\b"] } },
+      messages: { groupChat: { mentionPatterns: ["\\bclawd\\b"] } },
     });
     expect(matchesMentionPatterns("CLAWD: hi", regexes)).toBe(true);
   });
@@ -31,11 +31,16 @@ describe("mention helpers", () => {
   it("uses per-agent mention patterns when configured", () => {
     const regexes = buildMentionRegexes(
       {
-        routing: {
+        messages: {
           groupChat: { mentionPatterns: ["\\bglobal\\b"] },
-          agents: {
-            work: { mentionPatterns: ["\\bworkbot\\b"] },
-          },
+        },
+        agents: {
+          list: [
+            {
+              id: "work",
+              groupChat: { mentionPatterns: ["\\bworkbot\\b"] },
+            },
+          ],
         },
       },
       "work",

src/auto-reply/reply/mentions.ts

@@ -1,23 +1,62 @@
+import { resolveAgentConfig } from "../../agents/agent-scope.js";
 import type { ClawdbotConfig } from "../../config/config.js";
 import type { MsgContext } from "../templating.js";
 
+function escapeRegExp(text: string): string {
+  return text.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+
+function deriveMentionPatterns(identity?: { name?: string; emoji?: string }) {
+  const patterns: string[] = [];
+  const name = identity?.name?.trim();
+  if (name) {
+    const parts = name.split(/\s+/).filter(Boolean).map(escapeRegExp);
+    const re = parts.length ? parts.join(String.raw`\s+`) : escapeRegExp(name);
+    patterns.push(String.raw`\b@?${re}\b`);
+  }
+  const emoji = identity?.emoji?.trim();
+  if (emoji) {
+    patterns.push(escapeRegExp(emoji));
+  }
+  return patterns;
+}
+
+const BACKSPACE_CHAR = "\u0008";
+
+function normalizeMentionPattern(pattern: string): string {
+  if (!pattern.includes(BACKSPACE_CHAR)) return pattern;
+  return pattern.split(BACKSPACE_CHAR).join("\\b");
+}
+
+function normalizeMentionPatterns(patterns: string[]): string[] {
+  return patterns.map(normalizeMentionPattern);
+}
+
 function resolveMentionPatterns(
   cfg: ClawdbotConfig | undefined,
   agentId?: string,
 ): string[] {
   if (!cfg) return [];
-  const agentConfig = agentId ? cfg.routing?.agents?.[agentId] : undefined;
-  if (agentConfig && Object.hasOwn(agentConfig, "mentionPatterns")) {
-    return agentConfig.mentionPatterns ?? [];
+  const agentConfig = agentId ? resolveAgentConfig(cfg, agentId) : undefined;
+  const agentGroupChat = agentConfig?.groupChat;
+  if (agentGroupChat && Object.hasOwn(agentGroupChat, "mentionPatterns")) {
+    return agentGroupChat.mentionPatterns ?? [];
   }
-  return cfg.routing?.groupChat?.mentionPatterns ?? [];
+  const globalGroupChat = cfg.messages?.groupChat;
+  if (globalGroupChat && Object.hasOwn(globalGroupChat, "mentionPatterns")) {
+    return globalGroupChat.mentionPatterns ?? [];
+  }
+  const derived = deriveMentionPatterns(agentConfig?.identity);
+  return derived.length > 0 ? derived : [];
 }
 
 export function buildMentionRegexes(
   cfg: ClawdbotConfig | undefined,
   agentId?: string,
 ): RegExp[] {
-  const patterns = resolveMentionPatterns(cfg, agentId);
+  const patterns = normalizeMentionPatterns(
+    resolveMentionPatterns(cfg, agentId),
+  );
   return patterns
     .map((pattern) => {
       try {
@@ -66,7 +105,9 @@ export function stripMentions(
   agentId?: string,
 ): string {
   let result = text;
-  const patterns = resolveMentionPatterns(cfg, agentId);
+  const patterns = normalizeMentionPatterns(
+    resolveMentionPatterns(cfg, agentId),
+  );
   for (const p of patterns) {
     try {
       const re = new RegExp(p, "gi");

src/auto-reply/reply/model-selection.ts

@@ -33,7 +33,9 @@ type ModelSelectionState = {
 
 export async function createModelSelectionState(params: {
   cfg: ClawdbotConfig;
-  agentCfg: ClawdbotConfig["agent"] | undefined;
+  agentCfg:
+    | NonNullable<NonNullable<ClawdbotConfig["agents"]>["defaults"]>
+    | undefined;
   sessionEntry?: SessionEntry;
   sessionStore?: Record<string, SessionEntry>;
   sessionKey?: string;
@@ -201,7 +203,9 @@ export function resolveModelDirectiveSelection(params: {
 }
 
 export function resolveContextTokens(params: {
-  agentCfg: ClawdbotConfig["agent"] | undefined;
+  agentCfg:
+    | NonNullable<NonNullable<ClawdbotConfig["agents"]>["defaults"]>
+    | undefined;
   model: string;
 }): number {
   return (

src/auto-reply/reply/queue.ts

@@ -553,7 +553,7 @@ export function resolveQueueSettings(params: {
   inlineOptions?: Partial<QueueSettings>;
 }): QueueSettings {
   const providerKey = params.provider?.trim().toLowerCase();
-  const queueCfg = params.cfg.routing?.queue;
+  const queueCfg = params.cfg.messages?.queue;
   const providerModeRaw =
     providerKey && queueCfg?.byProvider
       ? (queueCfg.byProvider as Record<string, string | undefined>)[providerKey]

src/auto-reply/status.ts

@@ -35,7 +35,9 @@ import type {
   VerboseLevel,
 } from "./thinking.js";
 
-type AgentConfig = NonNullable<ClawdbotConfig["agent"]>;
+type AgentConfig = Partial<
+  NonNullable<NonNullable<ClawdbotConfig["agents"]>["defaults"]>
+>;
 
 export const formatTokenCount = formatTokenCountShared;
 
@@ -188,7 +190,11 @@ export function buildStatusMessage(args: StatusArgs): string {
   const now = args.now ?? Date.now();
   const entry = args.sessionEntry;
   const resolved = resolveConfiguredModelRef({
-    cfg: { agent: args.agent ?? {} },
+    cfg: {
+      agents: {
+        defaults: args.agent ?? {},
+      },
+    } as ClawdbotConfig,
     defaultProvider: DEFAULT_PROVIDER,
     defaultModel: DEFAULT_MODEL,
   });

src/auto-reply/transcription.test.ts

@@ -37,8 +37,8 @@ describe("transcribeInboundAudio", () => {
     vi.stubGlobal("fetch", fetchMock);
 
     const cfg = {
-      routing: {
-        transcribeAudio: {
+      audio: {
+        transcription: {
           command: ["echo", "{{MediaPath}}"],
           timeoutSeconds: 5,
         },
@@ -64,7 +64,7 @@ describe("transcribeInboundAudio", () => {
   it("returns undefined when no transcription command", async () => {
     const { transcribeInboundAudio } = await import("./transcription.js");
     const res = await transcribeInboundAudio(
-      { routing: {} } as never,
+      { audio: {} } as never,
       {} as never,
       runtime as never,
     );