@pellux/goodvibes-agent 1.0.11 → 1.0.12

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 Product-facing release notes for GoodVibes Agent.
 
+## 1.0.12 - 2026-06-03
+
+- Expose command browser, reasoning-effort picker, and live process output as model-visible confirmation-gated harness UI surfaces.
+- Allow confirmed run_workspace_action execution for local memory, note, persona, skill, and routine create editors through agent_local_registry with required-field validation.
+- Refresh package-facing docs for current 1.0.x harness parity and keep coverage aligned with the completed user-facing and model-facing surface map.
+
 ## 1.0.11 - 2026-06-03
 
 - Model-visible harness parity now opens conversation search, prompt history search, slash-command mode, file picker, and nearest-block actions through confirmation-gated visible shell routes.

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, list built-in panels and their workspace routes, inspect modal/overlay/picker UI surfaces, list top-level CLI mirrors, inspect fixed shortcuts and configurable keybindings, list slash commands, inspect command policy metadata, inspect model tool definitions, inspect or change Agent settings with confirmation, run concrete workspace or slash-command mirrors 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, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, bookmarks, model/provider 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; `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`; 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. The `connected_host` report includes route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and availability for the first-class Agent tools. 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, list built-in panels and their workspace routes, inspect modal/overlay/picker UI surfaces, list top-level CLI mirrors, inspect fixed shortcuts and configurable keybindings, list slash commands, inspect command policy metadata, inspect model tool definitions, inspect or change Agent settings with confirmation, run concrete workspace or slash-command mirrors 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; `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`; 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. 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

@@ -816508,7 +816508,7 @@ var createStyledCell = (char, overrides = {}) => ({
 // src/version.ts
 import { readFileSync } from "fs";
 import { join } from "path";
-var _version = "1.0.11";
+var _version = "1.0.12";
 var _sdkVersion = "0.33.35";
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, "..", "package.json"), "utf-8"));
@@ -880492,7 +880492,7 @@ function localRegistryArgsFromEditor(editor, fields, id) {
   if (editor.kind === "memory")
     return { domain: "memory", action: editor.mode === "update" ? "update" : "create", id, cls: read("cls"), scope: read("scope"), summary: read("summary"), detail: read("detail"), tags: splitList5(read("tags")), confidence: read("confidence"), provenance: editor.recordId ? "agent-harness-local-operation" : "agent-harness-note-promotion" };
   if (editor.kind === "note")
-    return { domain: "note", action: "update", id, title: read("title"), body: read("body"), sourceUrl: read("sourceUrl"), tags: splitList5(read("tags")), provenance: "agent-harness-local-operation" };
+    return { domain: "note", action: editor.mode === "update" ? "update" : "create", id, title: read("title"), body: read("body"), sourceUrl: read("sourceUrl"), tags: splitList5(read("tags")), provenance: editor.recordId ? "agent-harness-local-operation" : "agent-harness-note-promotion" };
   if (editor.kind === "persona")
     return { domain: "persona", action: editor.mode === "update" ? "update" : "create", id, name: read("name"), description: read("description"), body: read("body"), tags: splitList5(read("tags")), triggers: splitList5(read("triggers")), activate: read("activate"), provenance: editor.recordId ? "agent-harness-local-operation" : "agent-harness-note-promotion" };
   if (editor.kind === "skill")
@@ -880530,6 +880530,27 @@ function describeLocalWorkspaceModelExecution(action2) {
     return { tool: "agent_knowledge_ingest", sourceKind: "url", requiresRecordId: true, selectedRecordDomain: "note" };
   return { tool: "agent_local_registry", selectedRecordDomain: "note", action: "create", requiresRecordId: true };
 }
+async function runLocalWorkspaceEditorAction(deps, editor, args2) {
+  const fields = readFieldMap2(args2.fields);
+  const missing = missingRequiredFields(editor, fields);
+  if (missing.length > 0) {
+    return output6({
+      status: "missing_required_fields",
+      missing,
+      editor: describeEditor(editor)
+    });
+  }
+  const confirmationError2 = requireConfirmed(args2, "Workspace local registry editor action");
+  if (confirmationError2)
+    return error51(confirmationError2);
+  if (editor.kind !== "memory" && editor.kind !== "note" && editor.kind !== "persona" && editor.kind !== "skill" && editor.kind !== "routine") {
+    return output6({
+      status: "model_tool_required",
+      editor: describeEditor(editor)
+    });
+  }
+  return executeTool(deps.toolRegistry, "agent_local_registry", localRegistryArgsFromEditor(editor, fields, editor.recordId));
+}
 async function runLocalWorkspaceAction(deps, action2, args2) {
   if (action2.kind === "local-selection")
     return output6({ status: "local_selection", action: action2.id, modelExecution: describeLocalWorkspaceModelExecution(action2) });
@@ -881084,6 +881105,33 @@ var UI_SURFACES = [
       return opened(surface, { target: "main" });
     }
   },
+  {
+    id: "reasoning-effort-picker",
+    label: "Reasoning Effort Picker",
+    kind: "picker",
+    summary: "Interactive reasoning-effort selector for the current main chat model when that model exposes effort levels.",
+    command: "/effort",
+    preferredModelRoute: "Use settings/get_setting/set_setting for provider.reasoningEffort when a concrete level is known, or run_workspace_action setup-effort with confirmation.",
+    available: (context) => typeof context.openReasoningEffortPicker === "function",
+    open: (context) => {
+      const surface = findSurfaceById("reasoning-effort-picker");
+      if (!context.openReasoningEffortPicker)
+        return routeUnavailable(surface);
+      const result2 = context.openReasoningEffortPicker();
+      return result2.opened ? opened(surface, {
+        model: result2.model,
+        levels: result2.levels ?? []
+      }) : {
+        status: "not_opened",
+        surface: surface.id,
+        kind: surface.kind,
+        model: result2.model,
+        levels: result2.levels ?? [],
+        reason: result2.reason ?? "unsupported",
+        note: "The current model does not expose configurable reasoning effort levels."
+      };
+    }
+  },
   {
     id: "tts-provider-picker",
     label: "TTS Provider Picker",
@@ -881198,6 +881246,35 @@ var UI_SURFACES = [
       return opened(surface);
     }
   },
+  {
+    id: "live-tail",
+    label: "Live Process Output",
+    kind: "modal",
+    summary: "Visible live-output tail for a running process, opened by the same shell route as Enter from the runtime activity monitor.",
+    command: "F2, Enter",
+    preferredModelRoute: "Use this only for visible supervision of a running process output stream; use first-class model tools or confirmed commands for actual operations.",
+    parameters: ["target", "query", "prefix", "key"],
+    available: (context) => typeof context.openLiveTail === "function",
+    open: (context, args2) => {
+      const surface = findSurfaceById("live-tail");
+      if (!context.openLiveTail)
+        return routeUnavailable(surface);
+      const target = surfaceInputText(args2);
+      const result2 = context.openLiveTail(target);
+      return result2.opened ? opened(surface, {
+        target: target ?? "selected",
+        processId: result2.processId,
+        label: result2.label
+      }) : {
+        status: "not_opened",
+        surface: surface.id,
+        kind: surface.kind,
+        target: target ?? "selected",
+        reason: result2.reason ?? "not_found",
+        note: result2.reason === "no_processes" ? "There are no running shell processes to tail." : "No running shell process matched the requested target."
+      };
+    }
+  },
   {
     id: "conversation-search",
     label: "Conversation Search",
@@ -881258,6 +881335,27 @@ var UI_SURFACES = [
       };
     }
   },
+  {
+    id: "command-browser",
+    label: "Command Browser",
+    kind: "picker",
+    summary: "Registry-driven searchable slash-command browser opened by /commands and /help.",
+    command: "/commands",
+    preferredModelRoute: "Use commands/command for model-readable slash-command discovery and run_command for confirmed command execution.",
+    available: (context) => typeof context.executeCommand === "function",
+    open: async (context) => {
+      const surface = findSurfaceById("command-browser");
+      if (!context.executeCommand)
+        return routeUnavailable(surface);
+      const handled = await context.executeCommand("commands", []);
+      return handled ? opened(surface, { command: "/commands" }) : {
+        status: "not_opened",
+        surface: surface.id,
+        kind: surface.kind,
+        note: "The slash-command registry did not handle /commands in the current runtime."
+      };
+    }
+  },
   {
     id: "file-picker",
     label: "File Picker",
@@ -881553,15 +881651,15 @@ function describeWorkspaceAction(category, action2, options = {}) {
 }
 function localEditorModelExecution(editorKind) {
   if (editorKind === "memory")
-    return 'Use agent_local_registry with domain:"memory" for create/update/review/stale/delete.';
+    return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"memory"; agent_local_registry also supports list/search/get/review/stale/delete.';
   if (editorKind === "note")
-    return 'Use agent_local_registry with domain:"note" for create/update/review/stale/delete.';
+    return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"note"; agent_local_registry also supports list/search/get/review/stale/delete.';
   if (editorKind === "persona")
-    return 'Use agent_local_registry with domain:"persona" for create/update/use/clear_active/review/stale/delete.';
+    return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"persona"; agent_local_registry also supports list/search/get/use/clear_active/review/stale/delete.';
   if (editorKind === "skill")
-    return 'Use agent_local_registry with domain:"skill" for create/update/enable/disable/review/stale/delete.';
+    return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"skill"; agent_local_registry also supports list/search/get/enable/disable/review/stale/delete.';
   if (editorKind === "routine")
-    return 'Use agent_local_registry with domain:"routine" for create/update/enable/disable/start/review/stale/delete.';
+    return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"routine"; agent_local_registry also supports list/search/get/enable/disable/start/review/stale/delete.';
   if (editorKind === "learned-behavior")
     return "run_workspace_action can create the learned behavior from fields.";
   if (editorKind === "profile")
@@ -881715,6 +881813,9 @@ async function runWorkspaceEditorAction(deps, action2, editor, args2) {
     });
   }
   if (!isAgentWorkspaceCommandEditorKind(editor.kind)) {
+    if (editor.kind === "memory" || editor.kind === "note" || editor.kind === "persona" || editor.kind === "skill" || editor.kind === "routine") {
+      return runLocalWorkspaceEditorAction(deps, editor, args2);
+    }
     return output7({
       status: "model_tool_required",
       action: action2.id,
@@ -900010,6 +900111,40 @@ function wireShellUiOpeners(options) {
       render();
     });
   };
+  commandContext.openReasoningEffortPicker = () => {
+    const currentModel = providerRegistry.getCurrentModel();
+    const validLevels = currentModel.reasoningEffort ?? [];
+    if (validLevels.length === 0) {
+      return { opened: false, model: currentModel.displayName, levels: [], reason: "unsupported" };
+    }
+    const current = String(runtime3.reasoningEffort || configManager.get("provider.reasoningEffort") || "medium");
+    const descriptions = {
+      ...EFFORT_DESCRIPTIONS,
+      medium: "Balanced speed and quality (default)"
+    };
+    input.openSelection("Reasoning Effort", validLevels.map((level) => ({
+      id: level,
+      label: level,
+      detail: level === current ? `current - ${descriptions[level] ?? level}` : descriptions[level] ?? level
+    })), { preSelectId: current, allowSearch: false }, (result2) => {
+      if (!result2)
+        return;
+      const level = result2.item.id;
+      runtime3.reasoningEffort = level;
+      configManager.set("provider.reasoningEffort", level);
+      commandContext.print([
+        "Reasoning effort set",
+        `  level ${level}`
+      ].join(`
+`));
+      render();
+    });
+    return {
+      opened: true,
+      model: currentModel.displayName,
+      levels: validLevels
+    };
+  };
   commandContext.openSelection = (title, items, opts, callback) => {
     input.openSelection(title, items, opts, callback);
   };
@@ -900031,6 +900166,23 @@ function wireShellUiOpeners(options) {
     input.processModal.open();
     render();
   };
+  commandContext.openLiveTail = (target) => {
+    input.processModal.refresh();
+    const entries = input.processModal.entries;
+    if (entries.length === 0) {
+      return { opened: false, reason: "no_processes" };
+    }
+    const normalizedTarget = target?.trim().toLowerCase() ?? "";
+    const entry = normalizedTarget.length > 0 ? entries.find((candidate) => candidate.id.toLowerCase() === normalizedTarget || candidate.label.toLowerCase().includes(normalizedTarget)) : input.processModal.getSelected() ?? entries[0];
+    if (!entry) {
+      return { opened: false, reason: "not_found" };
+    }
+    input.modalOpened("liveTail");
+    input.processModal.close();
+    input.liveTailModal.open(entry);
+    render();
+    return { opened: true, processId: entry.id, label: entry.label };
+  };
   commandContext.openConversationSearch = (query2) => {
     input.searchManager.open();
     const searchQuery = query2?.trim() ?? "";

package/docs/README.md

@@ -22,7 +22,7 @@ Important baseline constraints:
 - Agent depends on `@pellux/goodvibes-sdk@0.33.35`.
 - Agent connects to a GoodVibes host owned outside this product.
 - Agent does not start, stop, restart, install, uninstall, or own the connected GoodVibes host.
-- User-facing Agent workspace actions, built-in panels, modal/overlay/picker UI surfaces, named operator surfaces, top-level CLI mirrors, fixed shortcuts, configurable keybindings, slash commands, command policy metadata, model tools, settings, local registries, connected-host capability boundaries, and live connected-host readiness are model-visible through Agent-owned tools. Mutations and visible UI routing remain explicit and confirmation-gated.
+- User-facing Agent workspace actions, built-in panels, modal/overlay/picker UI surfaces, named operator surfaces, top-level CLI mirrors, fixed shortcuts, configurable keybindings, slash commands, command policy metadata, model tools, settings, local registries, connected-host capability boundaries, and live connected-host readiness are model-visible through Agent-owned tools. Visible UI routing includes the command browser, reasoning-effort picker, live process output, runtime activity, settings, workspaces, and pickers the user can open. Local memory, note, persona, skill, and routine create editors can also run through confirmed workspace actions. Mutations and visible UI routing remain explicit and confirmation-gated.
 - Agent Knowledge uses only `/api/goodvibes-agent/knowledge/*`; there is no default knowledge or non-Agent product fallback.
 - Agent supports isolated Agent homes with `GOODVIBES_AGENT_HOME=<path>` and named profile homes with `goodvibes-agent profiles create <name> --template <starter> --yes` plus `--agent-profile <name>`.
 - Agent supports connected-host URL overrides with `--runtime-url http://host:port` or `GOODVIBES_AGENT_RUNTIME_URL=http://host:port`; these only change the Agent connection target.

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, built-in panel discovery/routing, modal/overlay/picker UI surface discovery/routing, top-level CLI mirror discovery, fixed shortcut and configurable keybinding discovery, keybinding mutation with confirmation, slash-command discovery, command policy metadata, command execution with confirmation, model tool discovery, settings inspection/mutation, connected-host capability inventory, 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, conversation search, prompt-history search, slash-command mode, file picker, block actions, context, runtime activity, bookmarks, model/provider 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; 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. 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. 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, built-in panel discovery/routing, modal/overlay/picker UI surface discovery/routing, top-level CLI mirror discovery, fixed shortcut and configurable keybinding discovery, keybinding mutation with confirmation, slash-command discovery, command policy metadata, command execution with confirmation, model tool discovery, settings inspection/mutation, connected-host capability inventory, 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; 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. 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

@@ -52,7 +52,7 @@ The main Agent model has an Agent-owned harness bridge rather than generic SDK s
 
 `agent_harness` discovery modes are read-only. `summary` reports the model access map; `panels` and `panel` return the built-in panel catalog, current open/focused state, and each panel's matching Agent workspace route; `ui_surfaces` and `ui_surface` return modal, overlay, picker, and workspace entrypoints with shell-opener availability and preferred model routes; `cli_commands` and `cli_command` return top-level package CLI mirror metadata, parser output, blocked command tokens, and preferred in-process model routes; `shortcuts` returns fixed runtime/editor shortcuts plus configurable keybindings; `keybindings` and `keybinding` return the live resolved keybinding table, default bindings, custom state, and config path; `commands` and `command` return slash-command descriptions plus effect/confirmation/preferred-tool/boundary policy metadata; `workspace_actions` lists Agent workspace actions and can inline editor field schemas with `includeParameters:true`; `workspace_action` returns one action with its editor schema; `tools` can inline model tool JSON schemas with `includeParameters:true`; `settings` returns setting descriptors plus setting policy; `connected_host` returns the connected-host route families, allowed capabilities, blocked capabilities, and first-class tool availability; 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 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, file picker, block actions, bookmarks, context inspector, runtime activity monitor, 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.
+`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.
 
 `set_keybinding` and `reset_keybinding` are confirmation-gated control modes. They write the same Agent `keybindings.json` file exposed by `/keybindings`, reload the runtime keybinding manager, and leave fixed runtime/editor shortcuts read-only.
 
@@ -62,7 +62,7 @@ CLI mirror modes are catalog and parser inspection only. When the user asks the
 
 Setting writes, setting resets, keybinding writes/resets, UI surface routing, slash-command invocation, workspace-action invocation, local record deletion, channel sends, notifications, reminders, media generation, and connected-host operator mutations require explicit user request and confirmation. Secret-backed settings are stored through the secret manager, and connected-host lifecycle/listener settings remain read-only in Agent.
 
-Selection-based local workspace actions use the same bridge. `agent_harness` reports the required model tool for each local action; for actions that depend on the TUI selection, call `run_workspace_action` with the selected local `recordId`. Note promotion actions can prefill and create memory, personas, skills, routines, or isolated Agent Knowledge URL ingests through the matching first-class model tool. Profile creation schemas include the current runtime starter-template inventory, and routine schedule schemas prefill the selected routine when `recordId` or a `routineId` field matches a local routine.
+Selection-based local workspace actions use the same bridge. `agent_harness` reports the required model tool for each local action; for actions that depend on the TUI selection, call `run_workspace_action` with the selected local `recordId`. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted `fields` through `run_workspace_action`; the harness validates required fields, requires `confirm:true` and `explicitUserRequest`, and dispatches through `agent_local_registry`. Note promotion actions can prefill and create memory, personas, skills, routines, or isolated Agent Knowledge URL ingests through the matching first-class model tool. Profile creation schemas include the current runtime starter-template inventory, and routine schedule schemas prefill the selected routine when `recordId` or a `routineId` field matches a local routine.
 
 Use first-class Agent tools before falling back to slash-command mirrors. Slash-command execution is for harness parity and scriptable mirrors, not for bypassing Agent product boundaries.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pellux/goodvibes-agent",
-  "version": "1.0.11",
+  "version": "1.0.12",
   "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/input/command-registry.ts

@@ -90,6 +90,12 @@ export interface CommandShellUiOpeners {
   openModelPickerWithTarget?: (target: import('./model-picker.ts').ModelPickerTarget) => boolean;
   openProviderModelPickerWithTarget?: (target: import('./model-picker.ts').ModelPickerTarget) => boolean;
   openProviderPicker?: () => void;
+  openReasoningEffortPicker?: () => {
+    opened: boolean;
+    model?: string;
+    levels?: readonly string[];
+    reason?: 'unsupported';
+  };
   openContextInspector?: () => void;
   openBookmarkModal?: () => void;
   openProcessModal?: () => void;
@@ -98,6 +104,12 @@ export interface CommandShellUiOpeners {
   openSlashCommandMode?: (query?: string) => boolean;
   openFilePicker?: (options?: { injectMode?: boolean; query?: string }) => boolean;
   openBlockActions?: () => boolean;
+  openLiveTail?: (target?: string) => {
+    opened: boolean;
+    processId?: string;
+    label?: string;
+    reason?: 'no_processes' | 'not_found';
+  };
   jumpToBookmark?: (key: string) => void;
   scrollToLine?: (line: number) => void;
   openHelpOverlay?: () => void;

package/src/shell/ui-openers.ts

@@ -4,6 +4,7 @@ import type { ConversationManager } from '../core/conversation';
 import type { CommandContext } from '../input/command-registry.ts';
 import type { InputHandler } from '../input/handler.ts';
 import type { PanelManager } from '../panels/panel-manager.ts';
+import { EFFORT_DESCRIPTIONS } from '@pellux/goodvibes-sdk/platform/providers';
 import type { ProviderRegistry } from '@pellux/goodvibes-sdk/platform/providers';
 import type { MutableRuntimeState } from '@/runtime/index.ts';
 import type { FeatureFlagManager } from '@/runtime/index.ts';
@@ -229,6 +230,45 @@ export function wireShellUiOpeners(options: WireShellUiOpenersOptions): void {
     });
   };
 
+  commandContext.openReasoningEffortPicker = () => {
+    const currentModel = providerRegistry.getCurrentModel();
+    const validLevels = currentModel.reasoningEffort ?? [];
+    if (validLevels.length === 0) {
+      return { opened: false, model: currentModel.displayName, levels: [], reason: 'unsupported' };
+    }
+
+    const current = String(runtime.reasoningEffort || configManager.get('provider.reasoningEffort') || 'medium');
+    const descriptions: Record<string, string> = {
+      ...EFFORT_DESCRIPTIONS,
+      medium: 'Balanced speed and quality (default)',
+    };
+    input.openSelection(
+      'Reasoning Effort',
+      validLevels.map((level) => ({
+        id: level,
+        label: level,
+        detail: level === current ? `current - ${descriptions[level] ?? level}` : (descriptions[level] ?? level),
+      })),
+      { preSelectId: current, allowSearch: false },
+      (result) => {
+        if (!result) return;
+        const level = result.item.id as 'instant' | 'low' | 'medium' | 'high';
+        runtime.reasoningEffort = level;
+        configManager.set('provider.reasoningEffort', level);
+        commandContext.print([
+          'Reasoning effort set',
+          `  level ${level}`,
+        ].join('\n'));
+        render();
+      },
+    );
+    return {
+      opened: true,
+      model: currentModel.displayName,
+      levels: validLevels,
+    };
+  };
+
   commandContext.openSelection = (title, items, opts, callback) => {
     input.openSelection(title, items, opts, callback);
   };
@@ -255,6 +295,32 @@ export function wireShellUiOpeners(options: WireShellUiOpenersOptions): void {
     render();
   };
 
+  commandContext.openLiveTail = (target?: string) => {
+    input.processModal.refresh();
+    const entries = input.processModal.entries;
+    if (entries.length === 0) {
+      return { opened: false, reason: 'no_processes' };
+    }
+
+    const normalizedTarget = target?.trim().toLowerCase() ?? '';
+    const entry = normalizedTarget.length > 0
+      ? entries.find((candidate) => (
+        candidate.id.toLowerCase() === normalizedTarget
+        || candidate.label.toLowerCase().includes(normalizedTarget)
+      ))
+      : input.processModal.getSelected() ?? entries[0];
+
+    if (!entry) {
+      return { opened: false, reason: 'not_found' };
+    }
+
+    input.modalOpened('liveTail');
+    input.processModal.close();
+    input.liveTailModal.open(entry);
+    render();
+    return { opened: true, processId: entry.id, label: entry.label };
+  };
+
   commandContext.openConversationSearch = (query?: string) => {
     input.searchManager.open();
     const searchQuery = query?.trim() ?? '';

package/src/tools/agent-harness-local-operations.ts

@@ -172,7 +172,7 @@ function editorForOperation(context: CommandContext, operation: AgentWorkspaceLo
 function localRegistryArgsFromEditor(editor: AgentWorkspaceLocalEditor, fields: Readonly<Record<string, string>>, id?: string): Record<string, unknown> {
   const read = fieldReader(editor, fields);
   if (editor.kind === 'memory') return { domain: 'memory', action: editor.mode === 'update' ? 'update' : 'create', id, cls: read('cls'), scope: read('scope'), summary: read('summary'), detail: read('detail'), tags: splitList(read('tags')), confidence: read('confidence'), provenance: editor.recordId ? 'agent-harness-local-operation' : 'agent-harness-note-promotion' };
-  if (editor.kind === 'note') return { domain: 'note', action: 'update', id, title: read('title'), body: read('body'), sourceUrl: read('sourceUrl'), tags: splitList(read('tags')), provenance: 'agent-harness-local-operation' };
+  if (editor.kind === 'note') return { domain: 'note', action: editor.mode === 'update' ? 'update' : 'create', id, title: read('title'), body: read('body'), sourceUrl: read('sourceUrl'), tags: splitList(read('tags')), provenance: editor.recordId ? 'agent-harness-local-operation' : 'agent-harness-note-promotion' };
   if (editor.kind === 'persona') return { domain: 'persona', action: editor.mode === 'update' ? 'update' : 'create', id, name: read('name'), description: read('description'), body: read('body'), tags: splitList(read('tags')), triggers: splitList(read('triggers')), activate: read('activate'), provenance: editor.recordId ? 'agent-harness-local-operation' : 'agent-harness-note-promotion' };
   if (editor.kind === 'skill') return { domain: 'skill', action: editor.mode === 'update' ? 'update' : 'create', id, name: read('name'), description: read('description'), procedure: read('procedure'), tags: splitList(read('tags')), triggers: splitList(read('triggers')), requiresEnv: splitList(read('requiresEnv')), requiresCommands: splitList(read('requiresCommands')), enabled: isAffirmative(read('enabled')), provenance: editor.recordId ? 'agent-harness-local-operation' : 'agent-harness-note-promotion' };
   return { domain: 'routine', action: editor.mode === 'update' ? 'update' : 'create', id, name: read('name'), description: read('description'), steps: read('steps'), tags: splitList(read('tags')), triggers: splitList(read('triggers')), requiresEnv: splitList(read('requiresEnv')), requiresCommands: splitList(read('requiresCommands')), enabled: isAffirmative(read('enabled')), provenance: editor.recordId ? 'agent-harness-local-operation' : 'agent-harness-note-promotion' };
@@ -206,6 +206,41 @@ export function describeLocalWorkspaceModelExecution(action: AgentWorkspaceActio
   return { tool: 'agent_local_registry', selectedRecordDomain: 'note', action: 'create', requiresRecordId: true };
 }
 
+export async function runLocalWorkspaceEditorAction(
+  deps: AgentHarnessLocalOperationDeps,
+  editor: AgentWorkspaceLocalEditor,
+  args: AgentHarnessLocalOperationArgs,
+): Promise<HarnessResult> {
+  const fields = readFieldMap(args.fields);
+  const missing = missingRequiredFields(editor, fields);
+  if (missing.length > 0) {
+    return output({
+      status: 'missing_required_fields',
+      missing,
+      editor: describeEditor(editor),
+    });
+  }
+  const confirmationError = requireConfirmed(args, 'Workspace local registry editor action');
+  if (confirmationError) return error(confirmationError);
+  if (
+    editor.kind !== 'memory'
+    && editor.kind !== 'note'
+    && editor.kind !== 'persona'
+    && editor.kind !== 'skill'
+    && editor.kind !== 'routine'
+  ) {
+    return output({
+      status: 'model_tool_required',
+      editor: describeEditor(editor),
+    });
+  }
+  return executeTool(
+    deps.toolRegistry,
+    'agent_local_registry',
+    localRegistryArgsFromEditor(editor, fields, editor.recordId),
+  );
+}
+
 export async function runLocalWorkspaceAction(
   deps: AgentHarnessLocalOperationDeps,
   action: AgentWorkspaceAction,

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

@@ -21,7 +21,7 @@ import { blockedHarnessCliCommandTokens, describeHarnessCliCommand, listHarnessC
 import { describeHarnessKeybinding, listHarnessKeybindings, listHarnessShortcuts, resetHarnessKeybinding, setHarnessKeybinding, totalHarnessKeybindings, totalHarnessShortcuts } from './agent-harness-keybinding-metadata.ts';
 import { describeHarnessPanel, listHarnessPanels, openHarnessPanel, totalHarnessPanels } from './agent-harness-panel-metadata.ts';
 import { connectedHostStatusSummary } from './agent-harness-connected-host-status.ts';
-import { describeLocalWorkspaceModelExecution, runLocalWorkspaceAction } from './agent-harness-local-operations.ts';
+import { describeLocalWorkspaceModelExecution, runLocalWorkspaceAction, runLocalWorkspaceEditorAction } from './agent-harness-local-operations.ts';
 import { listHarnessModelTools } from './agent-harness-model-tool-catalog.ts';
 import { AGENT_HARNESS_MODES, AGENT_HARNESS_PARAMETER_PROPERTIES } from './agent-harness-tool-schema.ts';
 import { describeHarnessUiSurface, listHarnessUiSurfaces, openHarnessUiSurface, totalHarnessUiSurfaces } from './agent-harness-ui-surface-metadata.ts';
@@ -238,11 +238,11 @@ function describeWorkspaceAction(
 }
 
 function localEditorModelExecution(editorKind: AgentWorkspaceEditorKind): string {
-  if (editorKind === 'memory') return 'Use agent_local_registry with domain:"memory" for create/update/review/stale/delete.';
-  if (editorKind === 'note') return 'Use agent_local_registry with domain:"note" for create/update/review/stale/delete.';
-  if (editorKind === 'persona') return 'Use agent_local_registry with domain:"persona" for create/update/use/clear_active/review/stale/delete.';
-  if (editorKind === 'skill') return 'Use agent_local_registry with domain:"skill" for create/update/enable/disable/review/stale/delete.';
-  if (editorKind === 'routine') return 'Use agent_local_registry with domain:"routine" for create/update/enable/disable/start/review/stale/delete.';
+  if (editorKind === 'memory') return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"memory"; agent_local_registry also supports list/search/get/review/stale/delete.';
+  if (editorKind === 'note') return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"note"; agent_local_registry also supports list/search/get/review/stale/delete.';
+  if (editorKind === 'persona') return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"persona"; agent_local_registry also supports list/search/get/use/clear_active/review/stale/delete.';
+  if (editorKind === 'skill') return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"skill"; agent_local_registry also supports list/search/get/enable/disable/review/stale/delete.';
+  if (editorKind === 'routine') return 'run_workspace_action can execute this editor from fields through agent_local_registry domain:"routine"; agent_local_registry also supports list/search/get/enable/disable/start/review/stale/delete.';
   if (editorKind === 'learned-behavior') return 'run_workspace_action can create the learned behavior from fields.';
   if (editorKind === 'profile') return 'run_workspace_action dispatches the matching /agent-profile create command.';
   return 'Use the command field, editor schema, or a first-class Agent model tool when available.';
@@ -409,6 +409,15 @@ async function runWorkspaceEditorAction(
   }
 
   if (!isAgentWorkspaceCommandEditorKind(editor.kind)) {
+    if (
+      editor.kind === 'memory'
+      || editor.kind === 'note'
+      || editor.kind === 'persona'
+      || editor.kind === 'skill'
+      || editor.kind === 'routine'
+    ) {
+      return runLocalWorkspaceEditorAction(deps, editor, args);
+    }
     return output({
       status: 'model_tool_required',
       action: action.id,

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

@@ -312,6 +312,34 @@ const UI_SURFACES: readonly UiSurfaceDefinition[] = [
       return opened(surface, { target: 'main' });
     },
   },
+  {
+    id: 'reasoning-effort-picker',
+    label: 'Reasoning Effort Picker',
+    kind: 'picker',
+    summary: 'Interactive reasoning-effort selector for the current main chat model when that model exposes effort levels.',
+    command: '/effort',
+    preferredModelRoute: 'Use settings/get_setting/set_setting for provider.reasoningEffort when a concrete level is known, or run_workspace_action setup-effort with confirmation.',
+    available: (context) => typeof context.openReasoningEffortPicker === 'function',
+    open: (context) => {
+      const surface = findSurfaceById('reasoning-effort-picker')!;
+      if (!context.openReasoningEffortPicker) return routeUnavailable(surface);
+      const result = context.openReasoningEffortPicker();
+      return result.opened
+        ? opened(surface, {
+          model: result.model,
+          levels: result.levels ?? [],
+        })
+        : {
+          status: 'not_opened',
+          surface: surface.id,
+          kind: surface.kind,
+          model: result.model,
+          levels: result.levels ?? [],
+          reason: result.reason ?? 'unsupported',
+          note: 'The current model does not expose configurable reasoning effort levels.',
+        };
+    },
+  },
   {
     id: 'tts-provider-picker',
     label: 'TTS Provider Picker',
@@ -421,6 +449,38 @@ const UI_SURFACES: readonly UiSurfaceDefinition[] = [
       return opened(surface);
     },
   },
+  {
+    id: 'live-tail',
+    label: 'Live Process Output',
+    kind: 'modal',
+    summary: 'Visible live-output tail for a running process, opened by the same shell route as Enter from the runtime activity monitor.',
+    command: 'F2, Enter',
+    preferredModelRoute: 'Use this only for visible supervision of a running process output stream; use first-class model tools or confirmed commands for actual operations.',
+    parameters: ['target', 'query', 'prefix', 'key'],
+    available: (context) => typeof context.openLiveTail === 'function',
+    open: (context, args) => {
+      const surface = findSurfaceById('live-tail')!;
+      if (!context.openLiveTail) return routeUnavailable(surface);
+      const target = surfaceInputText(args);
+      const result = context.openLiveTail(target);
+      return result.opened
+        ? opened(surface, {
+          target: target ?? 'selected',
+          processId: result.processId,
+          label: result.label,
+        })
+        : {
+          status: 'not_opened',
+          surface: surface.id,
+          kind: surface.kind,
+          target: target ?? 'selected',
+          reason: result.reason ?? 'not_found',
+          note: result.reason === 'no_processes'
+            ? 'There are no running shell processes to tail.'
+            : 'No running shell process matched the requested target.',
+        };
+    },
+  },
   {
     id: 'conversation-search',
     label: 'Conversation Search',
@@ -480,6 +540,28 @@ const UI_SURFACES: readonly UiSurfaceDefinition[] = [
         };
     },
   },
+  {
+    id: 'command-browser',
+    label: 'Command Browser',
+    kind: 'picker',
+    summary: 'Registry-driven searchable slash-command browser opened by /commands and /help.',
+    command: '/commands',
+    preferredModelRoute: 'Use commands/command for model-readable slash-command discovery and run_command for confirmed command execution.',
+    available: (context) => typeof context.executeCommand === 'function',
+    open: async (context) => {
+      const surface = findSurfaceById('command-browser')!;
+      if (!context.executeCommand) return routeUnavailable(surface);
+      const handled = await context.executeCommand('commands', []);
+      return handled
+        ? opened(surface, { command: '/commands' })
+        : {
+          status: 'not_opened',
+          surface: surface.id,
+          kind: surface.kind,
+          note: 'The slash-command registry did not handle /commands in the current runtime.',
+        };
+    },
+  },
   {
     id: 'file-picker',
     label: 'File Picker',

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 = '1.0.11';
+let _version = '1.0.12';
 let _sdkVersion = '0.33.35';
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, '..', 'package.json'), 'utf-8')) as {