@pellux/goodvibes-agent 1.0.26 → 1.0.27

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 Product-facing release notes for GoodVibes Agent.
 
+## 1.0.27 - 2026-06-03
+
+- Classify every built-in slash command with concrete model-visible effect and boundary policy metadata instead of generic unknown policy fallback.
+- Document that built-in slash-command inspection returns concrete effect and boundary policy metadata.
+- Add focused harness coverage so registered built-in slash commands cannot silently regress to unknown model policy.
+
 ## 1.0.26 - 2026-06-03
 
 - Route confirmed agent_harness panel-close and panel-close-all keybinding runs through the same Agent workspace dismiss bridge as the user shortcut before falling back to legacy panels.

package/README.md

@@ -66,7 +66,7 @@ Use the workspace as the primary product surface:
 
 Inside the Agent workspace, press `/` to search every workspace action by name, category, command, or detail. This is the primary discovery path for product actions; slash commands and CLI subcommands remain power-user/scriptable mirrors.
 
-The model has the same harness map through `agent_harness`: it can list Agent workspace actions, inspect or run one workspace action by `actionId`, `command`, `target`, or `query`, list built-in panels and inspect one panel by `panelId`, `target`, or `query`, inspect modal/overlay/picker UI surfaces by `surfaceId`, `target`, or `query`, list top-level CLI mirrors and inspect one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, inspect fixed shortcuts and configurable keybindings by `actionId`, `target`, `key`, or `query`, run shell-safe keybinding equivalents with confirmation, list slash commands, inspect or run one slash command by `command`, `commandName`, `target`, or `query` with parsed arguments and policy metadata, inspect model tool definitions or one model tool schema, inspect or change Agent settings by `key`, `target`, or `query` with confirmation, and report connected-host capability and live readiness posture. CLI mirror modes are read-only catalog and parser inspection; inside the main conversation, the model uses the returned preferred model tool, workspace action, setting mode, or confirmed slash-command mirror instead of launching hidden nested CLI processes. Panel modes expose catalog/open state and route visible panel/workspace changes through the current Agent shell bridge with confirmation. UI surface modes expose help, shortcuts, command browser, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, live process output, bookmarks, model/provider/reasoning-effort pickers, TTS provider/voice pickers, session/profile pickers, the panel-picker compatibility route, security/knowledge/subscription operator surfaces, settings, MCP workspace, onboarding, and Agent workspace entrypoints; `open_ui_surface` is confirmation-gated and only performs visible shell navigation. Shortcut modes expose fixed runtime/editor controls plus the live resolved keybinding table; each keybinding descriptor reports its model operation route, `run_keybinding` executes only supported shell-safe equivalents with confirmation, and prompt-editor-only or terminal-selection shortcuts remain explicit direct user interaction. `set_keybinding` and `reset_keybinding` write the same `keybindings.json` file the user edits and require confirmation. Workspace action discovery can inline editor field schemas with `includeParameters:true`; single-action lookup and execution use the same user-facing search fields, return or preserve lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates; CLI mirror, panel, UI surface, keybinding, slash-command, model tool, setting, and connected-host capability lookup use their catalog search fields and refuse ambiguous route, schema, capability, or mutation requests with candidates; confirmed slash-command execution uses the same slash-command lookup and refuses ambiguous requests before any handler runs; profile editors use the current starter-template inventory, and routine schedule editors can prefill a selected local routine from `recordId`. Selection-based local workspace actions accept a local `recordId` so the model can use the same note promotion and local registry flows as the TUI. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted fields through `run_workspace_action` and `agent_local_registry` with confirmation. The `connected_host` report includes route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and availability for the first-class Agent tools; `connected_host_capability` inspects one allowed or blocked capability by id, target, or query with its route families and boundary. The `connected_host_status` report performs a read-only live check of the connected-host status route and the isolated Agent Knowledge status route, reports SDK compatibility, token posture, endpoint bindings, route readiness, and actionable findings, and still refuses connected-host lifecycle control. The model uses those first-class tools for product workflows where they exist, such as Agent Knowledge, local memory/notes/personas/skills/routines, channel sends, notifications, reminders, media generation, work plans, and connected-host operator actions.
+The model has the same harness map through `agent_harness`: it can list Agent workspace actions, inspect or run one workspace action by `actionId`, `command`, `target`, or `query`, list built-in panels and inspect one panel by `panelId`, `target`, or `query`, inspect modal/overlay/picker UI surfaces by `surfaceId`, `target`, or `query`, list top-level CLI mirrors and inspect one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, inspect fixed shortcuts and configurable keybindings by `actionId`, `target`, `key`, or `query`, run shell-safe keybinding equivalents with confirmation, list slash commands, inspect or run one slash command by `command`, `commandName`, `target`, or `query` with parsed arguments and concrete built-in effect/boundary policy metadata, inspect model tool definitions or one model tool schema, inspect or change Agent settings by `key`, `target`, or `query` with confirmation, and report connected-host capability and live readiness posture. CLI mirror modes are read-only catalog and parser inspection; inside the main conversation, the model uses the returned preferred model tool, workspace action, setting mode, or confirmed slash-command mirror instead of launching hidden nested CLI processes. Panel modes expose catalog/open state and route visible panel/workspace changes through the current Agent shell bridge with confirmation. UI surface modes expose help, shortcuts, command browser, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, live process output, bookmarks, model/provider/reasoning-effort pickers, TTS provider/voice pickers, session/profile pickers, the panel-picker compatibility route, security/knowledge/subscription operator surfaces, settings, MCP workspace, onboarding, and Agent workspace entrypoints; `open_ui_surface` is confirmation-gated and only performs visible shell navigation. Shortcut modes expose fixed runtime/editor controls plus the live resolved keybinding table; each keybinding descriptor reports its model operation route, `run_keybinding` executes only supported shell-safe equivalents with confirmation, and prompt-editor-only or terminal-selection shortcuts remain explicit direct user interaction. `set_keybinding` and `reset_keybinding` write the same `keybindings.json` file the user edits and require confirmation. Workspace action discovery can inline editor field schemas with `includeParameters:true`; single-action lookup and execution use the same user-facing search fields, return or preserve lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates; CLI mirror, panel, UI surface, keybinding, slash-command, model tool, setting, and connected-host capability lookup use their catalog search fields and refuse ambiguous route, schema, capability, or mutation requests with candidates; confirmed slash-command execution uses the same slash-command lookup and refuses ambiguous requests before any handler runs; profile editors use the current starter-template inventory, and routine schedule editors can prefill a selected local routine from `recordId`. Selection-based local workspace actions accept a local `recordId` so the model can use the same note promotion and local registry flows as the TUI. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted fields through `run_workspace_action` and `agent_local_registry` with confirmation. The `connected_host` report includes route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and availability for the first-class Agent tools; `connected_host_capability` inspects one allowed or blocked capability by id, target, or query with its route families and boundary. The `connected_host_status` report performs a read-only live check of the connected-host status route and the isolated Agent Knowledge status route, reports SDK compatibility, token posture, endpoint bindings, route readiness, and actionable findings, and still refuses connected-host lifecycle control. The model uses those first-class tools for product workflows where they exist, such as Agent Knowledge, local memory/notes/personas/skills/routines, channel sends, notifications, reminders, media generation, work plans, and connected-host operator actions.
 
 The setup workspace surfaces discovered Agent-local persona, skill, and routine markdown files so day-one setup can import useful behavior instead of starting from blank records. It can also create one initial scratchpad note, local persona, skill, and routine directly during first-run setup; those records stay in Agent-local registries and never write to default knowledge or non-Agent segments.
 

package/dist/package/main.js

@@ -816566,7 +816566,7 @@ var createStyledCell = (char, overrides = {}) => ({
 // src/version.ts
 import { readFileSync } from "fs";
 import { join } from "path";
-var _version = "1.0.26";
+var _version = "1.0.27";
 var _sdkVersion = "0.33.35";
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, "..", "package.json"), "utf-8"));
@@ -879380,7 +879380,119 @@ function actionSearchStatus(host) {
 function describeCommandPolicy(commandName) {
   const root = commandName.replace(/^\//, "").trim().toLowerCase();
   const confirmation = 'agent_harness mode:"run_command" requires confirm:true and explicitUserRequest for every slash command invocation.';
-  if (root === "memory" || root === "memories" || root === "note" || root === "notes" || root === "persona" || root === "personas" || root === "skill" || root === "skills" || root === "routine" || root === "routines") {
+  if (root === "agent" || root === "agent-workspace" || root === "workspace") {
+    return {
+      effect: "ui-navigation",
+      confirmation,
+      preferredModelTool: "agent_harness workspace/workspace_categories/workspace_actions/workspace_action/run_workspace_action",
+      boundary: "Agent workspace navigation is visible shell routing. Use workspace action modes for concrete model-readable operation."
+    };
+  }
+  if (root === "setup" || root === "welcome") {
+    return {
+      effect: "ui-navigation",
+      confirmation,
+      preferredModelTool: "agent_harness workspace_actions/workspace_action/open_ui_surface",
+      boundary: "Setup opens the visible Agent onboarding or setup workspace. Model-side changes should use setting modes or workspace actions."
+    };
+  }
+  if (root === "commands" || root === "help" || root === "shortcuts") {
+    return {
+      effect: "ui-navigation",
+      confirmation,
+      preferredModelTool: root === "shortcuts" ? "agent_harness shortcuts/keybindings/keybinding" : "agent_harness commands/command",
+      boundary: "Discovery commands open visible help surfaces. The model should inspect the matching harness catalog directly before invoking commands."
+    };
+  }
+  if (root === "keybindings") {
+    return {
+      effect: "read-only",
+      confirmation,
+      preferredModelTool: "agent_harness shortcuts/keybindings/keybinding/run_keybinding/set_keybinding/reset_keybinding",
+      boundary: "Keybinding inspection is read-only. Keybinding execution or edits require explicit confirmation through agent_harness keybinding modes."
+    };
+  }
+  if (root === "settings" || root === "config") {
+    return {
+      effect: "mixed",
+      confirmation,
+      preferredModelTool: "agent_harness settings/get_setting/set_setting/reset_setting",
+      boundary: "Model-writable settings can be changed through agent_harness. Connected-host lifecycle/listener settings remain read-only."
+    };
+  }
+  if (root === "model" || root === "effort") {
+    return {
+      effect: "mixed",
+      confirmation,
+      preferredModelTool: "agent_harness settings/get_setting/set_setting/open_ui_surface",
+      boundary: "Model and reasoning-effort changes affect the current Agent chat route. Prefer settings modes for concrete values and UI surface routing for visible pickers."
+    };
+  }
+  if (root === "provider" || root === "providers") {
+    return {
+      effect: "mixed",
+      confirmation,
+      preferredModelTool: "agent_harness settings/get_setting/set_setting/open_ui_surface",
+      boundary: "Provider selection and custom provider files belong to Agent provider configuration. Adding, removing, or switching providers requires explicit user intent."
+    };
+  }
+  if (root === "refresh-models") {
+    return {
+      effect: "external-network",
+      confirmation,
+      preferredModelTool: "agent_harness settings/tools",
+      boundary: "Model catalog refresh may call provider discovery routes and update local provider metadata. Do not run it without explicit user request."
+    };
+  }
+  if (root === "pin" || root === "unpin") {
+    return {
+      effect: "local-state",
+      confirmation,
+      preferredModelTool: "agent_harness run_command",
+      boundary: "Pinned model changes mutate local Agent provider preferences only and require an explicit model id."
+    };
+  }
+  if (root === "mode") {
+    return {
+      effect: "local-state",
+      confirmation,
+      preferredModelTool: "agent_harness settings/get_setting/set_setting",
+      boundary: "Interaction-mode changes affect the current Agent operator notification posture and should be explicit."
+    };
+  }
+  if (root === "brief") {
+    return {
+      effect: "read-only",
+      confirmation,
+      preferredModelTool: "agent_operator_briefing",
+      boundary: "Briefing reads current Agent operator posture and next actions without mutating connected-host state."
+    };
+  }
+  if (root === "health" || root === "compat" || root === "context" || root === "accounts" || root === "security") {
+    return {
+      effect: "read-only",
+      confirmation,
+      preferredModelTool: root === "compat" ? "agent_harness connected_host_status" : "agent_harness connected_host_status/settings/tools/open_ui_surface",
+      boundary: "Diagnostics and review commands inspect Agent, provider, MCP, security, and connected-host readiness without taking lifecycle ownership."
+    };
+  }
+  if (root === "trust" || root === "auth" || root === "bundle") {
+    return {
+      effect: "mixed",
+      confirmation,
+      preferredModelTool: "agent_harness run_command",
+      boundary: "Review subcommands are read-only; bundle export/import or auth/trust bundle export writes local files and requires explicit confirmation."
+    };
+  }
+  if (root === "mcp" || root === "voice" || root === "subscription" || root === "secrets" || root === "secret") {
+    return {
+      effect: "mixed",
+      confirmation,
+      preferredModelTool: root === "secrets" || root === "secret" ? "agent_harness settings/get_setting/set_setting/reset_setting" : "agent_harness workspace_actions/settings/open_ui_surface",
+      boundary: "Harness-owned configuration, secret, voice, subscription, and MCP commands can expose credentials or external account state. Mutations require explicit user intent and should prefer secret refs over raw values."
+    };
+  }
+  if (root === "memory" || root === "memories" || root === "note" || root === "persona" || root === "personas" || root === "skill" || root === "skills" || root === "routine" || root === "routines") {
     return {
       effect: "local-state",
       confirmation,
@@ -879388,20 +879500,20 @@ function describeCommandPolicy(commandName) {
       boundary: "Agent-local library records only unless the invoked command explicitly promotes to a connected schedule or Agent Knowledge source."
     };
   }
-  if (root === "knowledge") {
+  if (root === "notes") {
     return {
-      effect: "mixed",
+      effect: "ui-navigation",
       confirmation,
-      preferredModelTool: "agent_knowledge or agent_knowledge_ingest",
-      boundary: "Agent Knowledge only. Do not use default knowledge or non-Agent knowledge spaces."
+      preferredModelTool: "agent_harness workspace_actions/workspace_action/run_workspace_action or agent_local_registry",
+      boundary: "Notes workspace routing is visible navigation; note record mutations should use Agent-local registry or workspace action modes."
     };
   }
-  if (root === "settings") {
+  if (root === "knowledge") {
     return {
       effect: "mixed",
       confirmation,
-      preferredModelTool: "agent_harness settings/get_setting/set_setting/reset_setting",
-      boundary: "Model-writable settings can be changed through agent_harness. Connected-host lifecycle/listener settings remain read-only."
+      preferredModelTool: "agent_knowledge or agent_knowledge_ingest",
+      boundary: "Agent Knowledge only. Do not use default knowledge or non-Agent knowledge spaces."
     };
   }
   if (root === "approval" || root === "approvals" || root === "automation") {
@@ -879428,7 +879540,7 @@ function describeCommandPolicy(commandName) {
       boundary: "External delivery requires an explicit target and direct user authorization."
     };
   }
-  if (root === "media" || root === "image") {
+  if (root === "media") {
     return {
       effect: "external-network",
       confirmation,
@@ -879436,6 +879548,22 @@ function describeCommandPolicy(commandName) {
       boundary: "Media generation uses configured Agent media providers and writes normal artifacts only."
     };
   }
+  if (root === "image") {
+    return {
+      effect: "external-network",
+      confirmation,
+      preferredModelTool: "agent_harness open_ui_surface",
+      boundary: "Image attachment reads a local image and submits a model turn with image content. Use only for explicit user-supplied files."
+    };
+  }
+  if (root === "tts") {
+    return {
+      effect: "external-network",
+      confirmation,
+      preferredModelTool: "agent_harness settings/open_ui_surface",
+      boundary: "Live TTS submits a normal prompt and may call model and speech providers; stopping playback is local runtime control."
+    };
+  }
   if (root === "workplan" || root === "plan" || root === "task" || root === "tasks") {
     return {
       effect: "local-state",
@@ -879451,26 +879579,50 @@ function describeCommandPolicy(commandName) {
       boundary: "Delegation is explicit user-directed work only; no hidden background review or separate Agent job should be created implicitly."
     };
   }
-  if (root === "session" || root === "conversation" || root === "clear" || root === "quit" || root === "exit") {
+  if (root === "session" || root === "conversation" || root === "clear" || root === "reset" || root === "compact" || root === "quit" || root === "exit" || root === "save" || root === "load" || root === "sessions" || root === "title" || root === "undo" || root === "redo" || root === "retry") {
     return {
       effect: "session-lifecycle",
       confirmation,
       boundary: "Session and conversation commands operate on the visible harness session lifecycle."
     };
   }
-  if (root === "agent-workspace" || root === "workspace" || root === "help" || root === "shortcuts") {
+  if (root === "export") {
+    return {
+      effect: "local-state",
+      confirmation,
+      boundary: "Conversation export writes a local workspace file and requires an explicit output intent."
+    };
+  }
+  if (root === "bookmarks" || root === "expand" || root === "collapse" || root === "next-error" || root === "prev-error") {
     return {
       effect: "ui-navigation",
       confirmation,
-      preferredModelTool: "agent_harness workspace/workspace_actions/workspace_action/run_workspace_action",
-      boundary: "Navigation and discovery commands should be inspected through agent_harness when possible."
+      preferredModelTool: root === "bookmarks" ? "agent_harness open_ui_surface" : undefined,
+      boundary: "Conversation display navigation mutates only the visible transcript view or scroll position."
     };
   }
-  if (root === "profile" || root === "agent-profile" || root === "provider" || root === "providers" || root === "auth" || root === "secret" || root === "secrets" || root === "mcp" || root === "voice" || root === "subscription") {
+  if (root === "paste") {
+    return {
+      effect: "local-state",
+      confirmation,
+      preferredModelTool: "agent_harness run_keybinding",
+      boundary: "Paste reads the local clipboard and mutates the visible prompt or image attachment state."
+    };
+  }
+  if (root === "profile" || root === "agent-profile") {
     return {
       effect: "mixed",
       confirmation,
-      boundary: "Harness-owned configuration, auth, provider, MCP, and profile commands are available through the command bridge with explicit confirmation."
+      preferredModelTool: "agent_harness workspace_actions/workspace_action/run_workspace_action",
+      boundary: "Agent profile commands manage isolated Agent runtime profiles and starter templates. Mutations require explicit confirmation."
+    };
+  }
+  if (root === "qrcode") {
+    return {
+      effect: "read-only",
+      confirmation,
+      preferredModelTool: "agent_harness run_command",
+      boundary: "Pairing details are displayed for explicit operator use; the Agent does not manage connected-host listener lifecycle."
     };
   }
   return {

package/docs/getting-started.md

@@ -44,7 +44,7 @@ After setup has been applied once, the TUI opens directly into the Agent operato
 
 Press `/` inside the Agent workspace to search every workspace action by name, category, command, or detail. Use that finder before reaching for shell commands; CLI subcommands are scriptable mirrors of these TUI workflows.
 
-The model can inspect and use the same harness surface through Agent-owned tools. `agent_harness` exposes workspace action discovery, single workspace-action inspection and execution by action id, command, or lookup text, built-in panel discovery/routing by panel id or lookup text, modal/overlay/picker UI surface discovery/routing by surface id or lookup text, top-level CLI mirror discovery and single-mirror lookup by command string, command token, or lookup text, fixed shortcut and configurable keybinding discovery, keybinding inspection/mutation by action id or lookup text, confirmation-gated shell-safe keybinding execution, slash-command discovery, single slash-command inspection by typed command or lookup text, command policy metadata, single slash-command execution by typed command or lookup text with confirmation, model tool discovery and single-tool schema inspection, settings inspection/mutation by key or lookup text, connected-host capability inventory, single connected-host capability inspection, and live connected-host readiness posture. CLI mirror modes are read-only catalog/parser inspection and point the model to the matching in-process tool, workspace action, setting mode, or slash-command mirror. Panel modes expose catalog/open state and route visible panel/workspace changes through the current Agent shell bridge with confirmation. UI surface modes expose help, shortcuts, command browser, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, live process output, bookmarks, model/provider/reasoning-effort pickers, TTS provider/voice pickers, session/profile pickers, the panel-picker compatibility route, security/knowledge/subscription operator surfaces, settings, MCP workspace, onboarding, and Agent workspace entrypoints; `open_ui_surface` is confirmation-gated and only performs visible shell navigation. Shortcut modes expose the fixed runtime/editor shortcuts and the live keybindings table; keybinding descriptors include a model operation route, `run_keybinding` executes supported shell-safe equivalents only with confirmation, prompt-editor-only or terminal-selection shortcuts remain direct user interaction, and confirmed keybinding edits write the same `keybindings.json` file the user edits and reload the runtime manager. Workspace action discovery can include editor field schemas with `includeParameters:true`, including starter-template defaults for profile creation and selected-routine defaults for routine schedule promotion when `recordId` is supplied; single-action lookup and execution use the same user-facing search fields, return lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates. Single-CLI-mirror, single-panel, single-surface, single-keybinding, single-slash-command, single-tool, single-setting, and single-connected-host-capability lookup use their catalog search fields, return lookup metadata where the result carries it, and refuse ambiguous route, schema, capability, or mutation requests with candidates; confirmed slash-command execution uses the same slash-command lookup and refuses ambiguous requests before any handler runs. Selection-based local workspace actions accept a local `recordId`, so the model can use the same note promotion and local registry flows as the TUI. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted fields through `run_workspace_action` and `agent_local_registry` with confirmation. First-class model tools cover the main product workflows directly: Agent Knowledge, Agent Knowledge ingest, Agent-local memory/notes/personas/skills/routines, operator actions, notifications, channel sends, reminders, generated media, and work plans.
+The model can inspect and use the same harness surface through Agent-owned tools. `agent_harness` exposes workspace action discovery, single workspace-action inspection and execution by action id, command, or lookup text, built-in panel discovery/routing by panel id or lookup text, modal/overlay/picker UI surface discovery/routing by surface id or lookup text, top-level CLI mirror discovery and single-mirror lookup by command string, command token, or lookup text, fixed shortcut and configurable keybinding discovery, keybinding inspection/mutation by action id or lookup text, confirmation-gated shell-safe keybinding execution, slash-command discovery, single slash-command inspection by typed command or lookup text, concrete built-in command effect/boundary policy metadata, single slash-command execution by typed command or lookup text with confirmation, model tool discovery and single-tool schema inspection, settings inspection/mutation by key or lookup text, connected-host capability inventory, single connected-host capability inspection, and live connected-host readiness posture. CLI mirror modes are read-only catalog/parser inspection and point the model to the matching in-process tool, workspace action, setting mode, or slash-command mirror. Panel modes expose catalog/open state and route visible panel/workspace changes through the current Agent shell bridge with confirmation. UI surface modes expose help, shortcuts, command browser, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, live process output, bookmarks, model/provider/reasoning-effort pickers, TTS provider/voice pickers, session/profile pickers, the panel-picker compatibility route, security/knowledge/subscription operator surfaces, settings, MCP workspace, onboarding, and Agent workspace entrypoints; `open_ui_surface` is confirmation-gated and only performs visible shell navigation. Shortcut modes expose the fixed runtime/editor shortcuts and the live keybindings table; keybinding descriptors include a model operation route, `run_keybinding` executes supported shell-safe equivalents only with confirmation, prompt-editor-only or terminal-selection shortcuts remain direct user interaction, and confirmed keybinding edits write the same `keybindings.json` file the user edits and reload the runtime manager. Workspace action discovery can include editor field schemas with `includeParameters:true`, including starter-template defaults for profile creation and selected-routine defaults for routine schedule promotion when `recordId` is supplied; single-action lookup and execution use the same user-facing search fields, return lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates. Single-CLI-mirror, single-panel, single-surface, single-keybinding, single-slash-command, single-tool, single-setting, and single-connected-host-capability lookup use their catalog search fields, return lookup metadata where the result carries it, and refuse ambiguous route, schema, capability, or mutation requests with candidates; confirmed slash-command execution uses the same slash-command lookup and refuses ambiguous requests before any handler runs. Selection-based local workspace actions accept a local `recordId`, so the model can use the same note promotion and local registry flows as the TUI. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted fields through `run_workspace_action` and `agent_local_registry` with confirmation. First-class model tools cover the main product workflows directly: Agent Knowledge, Agent Knowledge ingest, Agent-local memory/notes/personas/skills/routines, operator actions, notifications, channel sends, reminders, generated media, and work plans.
 
 Use the Artifacts area for concrete files and generated output: attach images to prompts, export conversations or saved sessions, ingest local source files and URL lists into Agent Knowledge, import bookmarks or browser history, inspect source records, and generate media artifacts from confirmed prompts.
 

package/docs/tools-and-commands.md

@@ -50,7 +50,7 @@ The main Agent model has an Agent-owned harness bridge rather than generic SDK s
 - `agent_work_plan`: keep the visible Agent-local work plan current from the conversation.
 - `agent_channel_send`, `agent_notify`, `agent_reminder_schedule`, and `agent_media_generate`: perform confirmed external delivery, notification, reminder, or media actions when the user explicitly asks.
 
-`agent_harness` discovery modes are read-only. `summary` reports the model access map; `panels` lists the built-in panel catalog, and `panel` resolves one panel by `panelId`, `target`, or `query` with current open/focused state plus its matching Agent workspace route; `ui_surfaces` lists modal, overlay, picker, and workspace entrypoints, and `ui_surface` resolves one by `surfaceId`, `target`, or `query` with shell-opener availability and preferred model routes; `cli_commands` lists top-level package CLI mirror metadata, and `cli_command` resolves one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, returning parser output for concrete invocations, blocked command tokens, lookup metadata, and preferred in-process model routes; `shortcuts` returns fixed runtime/editor shortcuts plus configurable keybindings; `keybindings` lists the live resolved keybinding table, and `keybinding`, `run_keybinding`, `set_keybinding`, and `reset_keybinding` resolve one action by `actionId`, `target`, `key`, or `query` with default bindings, custom state, config path, lookup metadata, and model-operation route metadata; `commands` lists slash-command descriptions; `command` returns one slash-command detail by `command`, `commandName`, `target`, or `query`, including parsed arguments plus effect/confirmation/preferred-tool/boundary policy metadata, and refuses ambiguous command lookup with candidate commands; `run_command` executes one confirmed slash command using the same `command`, `commandName`, `target`, or `query` resolver and refuses ambiguous command lookup before any handler runs; `workspace_actions` lists Agent workspace actions and can inline editor field schemas with `includeParameters:true`; `workspace_action` and `run_workspace_action` resolve one action by `actionId`, `command`, `target`, or `query`, using the same user-facing action-search fields; inspection returns lookup metadata plus editor schema, and execution refuses ambiguous requests with candidate actions before any effect; `tools` lists model tool definitions and can inline JSON schemas with `includeParameters:true`; `tool` returns one model tool schema by `toolName`, `target`, or `query` and refuses ambiguous schema lookup with candidate tools; `settings` returns setting descriptors plus setting policy; `get_setting`, `set_setting`, and `reset_setting` resolve one setting by `key`, `target`, or `query`, return lookup metadata on success, and refuse ambiguous matches with candidate settings; `connected_host` returns the connected-host route families, allowed capabilities, blocked capabilities, and first-class tool availability; `connected_host_capability` returns one allowed or blocked connected-host capability by `capabilityId`, `target`, or `query` with related route families and boundary text and refuses ambiguous capability lookup with candidates; and `connected_host_status` performs a live read-only check of the connected-host status and Agent Knowledge status routes and reports endpoint bindings, token posture, SDK compatibility, route readiness, and findings without printing token values.
+`agent_harness` discovery modes are read-only. `summary` reports the model access map; `panels` lists the built-in panel catalog, and `panel` resolves one panel by `panelId`, `target`, or `query` with current open/focused state plus its matching Agent workspace route; `ui_surfaces` lists modal, overlay, picker, and workspace entrypoints, and `ui_surface` resolves one by `surfaceId`, `target`, or `query` with shell-opener availability and preferred model routes; `cli_commands` lists top-level package CLI mirror metadata, and `cli_command` resolves one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, returning parser output for concrete invocations, blocked command tokens, lookup metadata, and preferred in-process model routes; `shortcuts` returns fixed runtime/editor shortcuts plus configurable keybindings; `keybindings` lists the live resolved keybinding table, and `keybinding`, `run_keybinding`, `set_keybinding`, and `reset_keybinding` resolve one action by `actionId`, `target`, `key`, or `query` with default bindings, custom state, config path, lookup metadata, and model-operation route metadata; `commands` lists slash-command descriptions; `command` returns one slash-command detail by `command`, `commandName`, `target`, or `query`, including parsed arguments plus concrete built-in effect/confirmation/preferred-tool/boundary policy metadata, and refuses ambiguous command lookup with candidate commands; `run_command` executes one confirmed slash command using the same `command`, `commandName`, `target`, or `query` resolver and refuses ambiguous command lookup before any handler runs; `workspace_actions` lists Agent workspace actions and can inline editor field schemas with `includeParameters:true`; `workspace_action` and `run_workspace_action` resolve one action by `actionId`, `command`, `target`, or `query`, using the same user-facing action-search fields; inspection returns lookup metadata plus editor schema, and execution refuses ambiguous requests with candidate actions before any effect; `tools` lists model tool definitions and can inline JSON schemas with `includeParameters:true`; `tool` returns one model tool schema by `toolName`, `target`, or `query` and refuses ambiguous schema lookup with candidate tools; `settings` returns setting descriptors plus setting policy; `get_setting`, `set_setting`, and `reset_setting` resolve one setting by `key`, `target`, or `query`, return lookup metadata on success, and refuse ambiguous matches with candidate settings; `connected_host` returns the connected-host route families, allowed capabilities, blocked capabilities, and first-class tool availability; `connected_host_capability` returns one allowed or blocked connected-host capability by `capabilityId`, `target`, or `query` with related route families and boundary text and refuses ambiguous capability lookup with candidates; and `connected_host_status` performs a live read-only check of the connected-host status and Agent Knowledge status routes and reports endpoint bindings, token posture, SDK compatibility, route readiness, and findings without printing token values.
 
 `open_ui_surface` is a confirmation-gated visible navigation mode for the same shell surfaces the user can open: Agent workspace, settings, MCP workspace, model/provider/reasoning-effort pickers, TTS provider/voice pickers, session/profile pickers, the panel-picker compatibility route, security/knowledge/subscription operator surfaces, conversation search, prompt-history search, slash-command mode, command browser, file picker, block actions, bookmarks, context inspector, runtime activity monitor, live process output, help, shortcuts, and onboarding. It does not perform hidden operations; use first-class model tools, settings modes, workspace actions, or confirmed slash-command mirrors for actual state changes. Ambiguous UI surface lookup text is refused with candidate surfaces instead of routed.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pellux/goodvibes-agent",
-  "version": "1.0.26",
+  "version": "1.0.27",
   "private": false,
   "description": "GoodVibes personal operator assistant TUI with a proactive Agent product brain, isolated Agent Knowledge, local profiles, routines, skills, personas, and explicit build delegation.",
   "type": "module",

package/src/tools/agent-harness-metadata.ts

@@ -16,11 +16,122 @@ export type ConnectedHostCapabilityResolution =
 export function describeCommandPolicy(commandName: string): CommandExecutionPolicy {
   const root = commandName.replace(/^\//, '').trim().toLowerCase();
   const confirmation = 'agent_harness mode:"run_command" requires confirm:true and explicitUserRequest for every slash command invocation.';
+  if (root === 'agent' || root === 'agent-workspace' || root === 'workspace') {
+    return {
+      effect: 'ui-navigation',
+      confirmation,
+      preferredModelTool: 'agent_harness workspace/workspace_categories/workspace_actions/workspace_action/run_workspace_action',
+      boundary: 'Agent workspace navigation is visible shell routing. Use workspace action modes for concrete model-readable operation.',
+    };
+  }
+  if (root === 'setup' || root === 'welcome') {
+    return {
+      effect: 'ui-navigation',
+      confirmation,
+      preferredModelTool: 'agent_harness workspace_actions/workspace_action/open_ui_surface',
+      boundary: 'Setup opens the visible Agent onboarding or setup workspace. Model-side changes should use setting modes or workspace actions.',
+    };
+  }
+  if (root === 'commands' || root === 'help' || root === 'shortcuts') {
+    return {
+      effect: 'ui-navigation',
+      confirmation,
+      preferredModelTool: root === 'shortcuts' ? 'agent_harness shortcuts/keybindings/keybinding' : 'agent_harness commands/command',
+      boundary: 'Discovery commands open visible help surfaces. The model should inspect the matching harness catalog directly before invoking commands.',
+    };
+  }
+  if (root === 'keybindings') {
+    return {
+      effect: 'read-only',
+      confirmation,
+      preferredModelTool: 'agent_harness shortcuts/keybindings/keybinding/run_keybinding/set_keybinding/reset_keybinding',
+      boundary: 'Keybinding inspection is read-only. Keybinding execution or edits require explicit confirmation through agent_harness keybinding modes.',
+    };
+  }
+  if (root === 'settings' || root === 'config') {
+    return {
+      effect: 'mixed',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/get_setting/set_setting/reset_setting',
+      boundary: 'Model-writable settings can be changed through agent_harness. Connected-host lifecycle/listener settings remain read-only.',
+    };
+  }
+  if (root === 'model' || root === 'effort') {
+    return {
+      effect: 'mixed',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/get_setting/set_setting/open_ui_surface',
+      boundary: 'Model and reasoning-effort changes affect the current Agent chat route. Prefer settings modes for concrete values and UI surface routing for visible pickers.',
+    };
+  }
+  if (root === 'provider' || root === 'providers') {
+    return {
+      effect: 'mixed',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/get_setting/set_setting/open_ui_surface',
+      boundary: 'Provider selection and custom provider files belong to Agent provider configuration. Adding, removing, or switching providers requires explicit user intent.',
+    };
+  }
+  if (root === 'refresh-models') {
+    return {
+      effect: 'external-network',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/tools',
+      boundary: 'Model catalog refresh may call provider discovery routes and update local provider metadata. Do not run it without explicit user request.',
+    };
+  }
+  if (root === 'pin' || root === 'unpin') {
+    return {
+      effect: 'local-state',
+      confirmation,
+      preferredModelTool: 'agent_harness run_command',
+      boundary: 'Pinned model changes mutate local Agent provider preferences only and require an explicit model id.',
+    };
+  }
+  if (root === 'mode') {
+    return {
+      effect: 'local-state',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/get_setting/set_setting',
+      boundary: 'Interaction-mode changes affect the current Agent operator notification posture and should be explicit.',
+    };
+  }
+  if (root === 'brief') {
+    return {
+      effect: 'read-only',
+      confirmation,
+      preferredModelTool: 'agent_operator_briefing',
+      boundary: 'Briefing reads current Agent operator posture and next actions without mutating connected-host state.',
+    };
+  }
+  if (root === 'health' || root === 'compat' || root === 'context' || root === 'accounts' || root === 'security') {
+    return {
+      effect: 'read-only',
+      confirmation,
+      preferredModelTool: root === 'compat' ? 'agent_harness connected_host_status' : 'agent_harness connected_host_status/settings/tools/open_ui_surface',
+      boundary: 'Diagnostics and review commands inspect Agent, provider, MCP, security, and connected-host readiness without taking lifecycle ownership.',
+    };
+  }
+  if (root === 'trust' || root === 'auth' || root === 'bundle') {
+    return {
+      effect: 'mixed',
+      confirmation,
+      preferredModelTool: 'agent_harness run_command',
+      boundary: 'Review subcommands are read-only; bundle export/import or auth/trust bundle export writes local files and requires explicit confirmation.',
+    };
+  }
+  if (root === 'mcp' || root === 'voice' || root === 'subscription' || root === 'secrets' || root === 'secret') {
+    return {
+      effect: 'mixed',
+      confirmation,
+      preferredModelTool: root === 'secrets' || root === 'secret' ? 'agent_harness settings/get_setting/set_setting/reset_setting' : 'agent_harness workspace_actions/settings/open_ui_surface',
+      boundary: 'Harness-owned configuration, secret, voice, subscription, and MCP commands can expose credentials or external account state. Mutations require explicit user intent and should prefer secret refs over raw values.',
+    };
+  }
   if (
     root === 'memory'
     || root === 'memories'
     || root === 'note'
-    || root === 'notes'
     || root === 'persona'
     || root === 'personas'
     || root === 'skill'
@@ -35,20 +146,20 @@ export function describeCommandPolicy(commandName: string): CommandExecutionPoli
       boundary: 'Agent-local library records only unless the invoked command explicitly promotes to a connected schedule or Agent Knowledge source.',
     };
   }
-  if (root === 'knowledge') {
+  if (root === 'notes') {
     return {
-      effect: 'mixed',
+      effect: 'ui-navigation',
       confirmation,
-      preferredModelTool: 'agent_knowledge or agent_knowledge_ingest',
-      boundary: 'Agent Knowledge only. Do not use default knowledge or non-Agent knowledge spaces.',
+      preferredModelTool: 'agent_harness workspace_actions/workspace_action/run_workspace_action or agent_local_registry',
+      boundary: 'Notes workspace routing is visible navigation; note record mutations should use Agent-local registry or workspace action modes.',
     };
   }
-  if (root === 'settings') {
+  if (root === 'knowledge') {
     return {
       effect: 'mixed',
       confirmation,
-      preferredModelTool: 'agent_harness settings/get_setting/set_setting/reset_setting',
-      boundary: 'Model-writable settings can be changed through agent_harness. Connected-host lifecycle/listener settings remain read-only.',
+      preferredModelTool: 'agent_knowledge or agent_knowledge_ingest',
+      boundary: 'Agent Knowledge only. Do not use default knowledge or non-Agent knowledge spaces.',
     };
   }
   if (root === 'approval' || root === 'approvals' || root === 'automation') {
@@ -75,7 +186,7 @@ export function describeCommandPolicy(commandName: string): CommandExecutionPoli
       boundary: 'External delivery requires an explicit target and direct user authorization.',
     };
   }
-  if (root === 'media' || root === 'image') {
+  if (root === 'media') {
     return {
       effect: 'external-network',
       confirmation,
@@ -83,6 +194,22 @@ export function describeCommandPolicy(commandName: string): CommandExecutionPoli
       boundary: 'Media generation uses configured Agent media providers and writes normal artifacts only.',
     };
   }
+  if (root === 'image') {
+    return {
+      effect: 'external-network',
+      confirmation,
+      preferredModelTool: 'agent_harness open_ui_surface',
+      boundary: 'Image attachment reads a local image and submits a model turn with image content. Use only for explicit user-supplied files.',
+    };
+  }
+  if (root === 'tts') {
+    return {
+      effect: 'external-network',
+      confirmation,
+      preferredModelTool: 'agent_harness settings/open_ui_surface',
+      boundary: 'Live TTS submits a normal prompt and may call model and speech providers; stopping playback is local runtime control.',
+    };
+  }
   if (root === 'workplan' || root === 'plan' || root === 'task' || root === 'tasks') {
     return {
       effect: 'local-state',
@@ -98,37 +225,65 @@ export function describeCommandPolicy(commandName: string): CommandExecutionPoli
       boundary: 'Delegation is explicit user-directed work only; no hidden background review or separate Agent job should be created implicitly.',
     };
   }
-  if (root === 'session' || root === 'conversation' || root === 'clear' || root === 'quit' || root === 'exit') {
+  if (
+    root === 'session'
+    || root === 'conversation'
+    || root === 'clear'
+    || root === 'reset'
+    || root === 'compact'
+    || root === 'quit'
+    || root === 'exit'
+    || root === 'save'
+    || root === 'load'
+    || root === 'sessions'
+    || root === 'title'
+    || root === 'undo'
+    || root === 'redo'
+    || root === 'retry'
+  ) {
     return {
       effect: 'session-lifecycle',
       confirmation,
       boundary: 'Session and conversation commands operate on the visible harness session lifecycle.',
     };
   }
-  if (root === 'agent-workspace' || root === 'workspace' || root === 'help' || root === 'shortcuts') {
+  if (root === 'export') {
+    return {
+      effect: 'local-state',
+      confirmation,
+      boundary: 'Conversation export writes a local workspace file and requires an explicit output intent.',
+    };
+  }
+  if (root === 'bookmarks' || root === 'expand' || root === 'collapse' || root === 'next-error' || root === 'prev-error') {
     return {
       effect: 'ui-navigation',
       confirmation,
-      preferredModelTool: 'agent_harness workspace/workspace_actions/workspace_action/run_workspace_action',
-      boundary: 'Navigation and discovery commands should be inspected through agent_harness when possible.',
+      preferredModelTool: root === 'bookmarks' ? 'agent_harness open_ui_surface' : undefined,
+      boundary: 'Conversation display navigation mutates only the visible transcript view or scroll position.',
     };
   }
-  if (
-    root === 'profile'
-    || root === 'agent-profile'
-    || root === 'provider'
-    || root === 'providers'
-    || root === 'auth'
-    || root === 'secret'
-    || root === 'secrets'
-    || root === 'mcp'
-    || root === 'voice'
-    || root === 'subscription'
-  ) {
+  if (root === 'paste') {
+    return {
+      effect: 'local-state',
+      confirmation,
+      preferredModelTool: 'agent_harness run_keybinding',
+      boundary: 'Paste reads the local clipboard and mutates the visible prompt or image attachment state.',
+    };
+  }
+  if (root === 'profile' || root === 'agent-profile') {
     return {
       effect: 'mixed',
       confirmation,
-      boundary: 'Harness-owned configuration, auth, provider, MCP, and profile commands are available through the command bridge with explicit confirmation.',
+      preferredModelTool: 'agent_harness workspace_actions/workspace_action/run_workspace_action',
+      boundary: 'Agent profile commands manage isolated Agent runtime profiles and starter templates. Mutations require explicit confirmation.',
+    };
+  }
+  if (root === 'qrcode') {
+    return {
+      effect: 'read-only',
+      confirmation,
+      preferredModelTool: 'agent_harness run_command',
+      boundary: 'Pairing details are displayed for explicit operator use; the Agent does not manage connected-host listener lifecycle.',
     };
   }
   return {

package/src/version.ts

@@ -6,7 +6,7 @@ import { join } from 'node:path';
 // The prebuild script updates the fallback value before compilation.
 // Uses import.meta.dir (Bun) to locate package.json relative to this file,
 // which is correct regardless of the process working directory.
-let _version = '1.0.26';
+let _version = '1.0.27';
 let _sdkVersion = '0.33.35';
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, '..', 'package.json'), 'utf-8')) as {