@pellux/goodvibes-agent 1.0.13 → 1.0.14

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 Product-facing release notes for GoodVibes Agent.
 
+## 1.0.14 - 2026-06-03
+
+- Add agent_harness mode tool to inspect one first-class model tool schema by toolName, target, or query.
+- Keep broad tools discovery lightweight while making individual model tool parameters, side effects, concurrency, and streaming/progress support directly inspectable.
+- Refresh package-facing docs and focused harness coverage for the updated model tool discovery surface.
+
 ## 1.0.13 - 2026-06-03
 
 - Add connected_host_capability to inspect one allowed or blocked connected-host capability by id, target, or query with related route families and boundary text.

package/README.md

@@ -7,7 +7,7 @@ GoodVibes Agent is the personal operator assistant TUI for GoodVibes. It is buil
 
 The Agent product connects to a GoodVibes host owned outside this package. It does not install, start, stop, restart, or own that host.
 
-Most work happens in the interactive TUI. The installed CLI exists to launch that TUI and provide scriptable mirrors for workflows that are already reachable from the workspace. The main Agent model can inspect the same harness surface through Agent-owned tools: 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, settings, model tools, local registries, connected-host capability boundaries, and live connected-host readiness are all discoverable from the conversation without exposing connected-host lifecycle control.
+Most work happens in the interactive TUI. The installed CLI exists to launch that TUI and provide scriptable mirrors for workflows that are already reachable from the workspace. The main Agent model can inspect the same harness surface through Agent-owned tools: 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, settings, model tools and individual model tool schemas, local registries, connected-host capability boundaries, and live connected-host readiness are all discoverable from the conversation without exposing connected-host lifecycle control.
 
 ## Install
 
@@ -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, 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; `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, 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 or one model tool schema, 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; `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 = "1.0.13";
+var _version = "1.0.14";
 var _sdkVersion = "0.33.35";
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, "..", "package.json"), "utf-8"));
@@ -847775,13 +847775,13 @@ init_state3();
 
 // src/input/commands/recall-shared.ts
 var VALID_CLASSES = ["decision", "constraint", "incident", "pattern", "fact", "risk", "runbook", "architecture", "ownership"];
-var VALID_SCOPES2 = ["session", "project", "team"];
+var VALID_SCOPES = ["session", "project", "team"];
 var VALID_REVIEW_STATES = ["fresh", "reviewed", "stale", "contradicted"];
 function isValidClass(s4) {
   return VALID_CLASSES.includes(s4);
 }
 function isValidScope(s4) {
-  return VALID_SCOPES2.includes(s4);
+  return VALID_SCOPES.includes(s4);
 }
 function isValidReviewState(s4) {
   return VALID_REVIEW_STATES.includes(s4);
@@ -847824,7 +847824,7 @@ function handleRecallSearch(args2, context) {
     if (isValidScope(scope))
       filter.scope = scope;
     else {
-      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES.join(", ")}.`);
       return;
     }
   }
@@ -847999,7 +847999,7 @@ function handleRecallList(args2, context) {
   if (scopeIdx !== -1 && args2[scopeIdx + 1]) {
     const scope = args2[scopeIdx + 1];
     if (!isValidScope(scope)) {
-      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES.join(", ")}.`);
       return;
     }
     filter.scope = scope;
@@ -848049,7 +848049,7 @@ async function handleRecallAdd(args2, context) {
   const tags = tagsRaw ? tagsRaw.split(",").map((token) => token.trim()).filter(Boolean) : [];
   const scope = scopeRaw && isValidScope(scopeRaw) ? scopeRaw : "project";
   if (scopeRaw && !isValidScope(scopeRaw)) {
-    context.print(`[memory] Invalid scope "${scopeRaw}". Valid values ${VALID_SCOPES2.join(", ")}.`);
+    context.print(`[memory] Invalid scope "${scopeRaw}". Valid values ${VALID_SCOPES.join(", ")}.`);
     return;
   }
   const provenance = [];
@@ -848183,7 +848183,7 @@ function handleRecallExport(args2, context) {
   if (scopeIdx !== -1 && commandArgs[scopeIdx + 1]) {
     const scope = commandArgs[scopeIdx + 1];
     if (!isValidScope(scope)) {
-      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES.join(", ")}.`);
       return;
     }
     filter.scope = scope;
@@ -848262,7 +848262,7 @@ function handleRecallHandoffExport(args2, context) {
   const scopeIdx = commandArgs.indexOf("--scope");
   const scopeRaw = scopeIdx !== -1 ? commandArgs[scopeIdx + 1] : "team";
   if (!scopeRaw || !isValidScope(scopeRaw)) {
-    context.print(`[memory] Unknown scope "${scopeRaw ?? ""}". Valid values ${VALID_SCOPES2.join(", ")}.`);
+    context.print(`[memory] Unknown scope "${scopeRaw ?? ""}". Valid values ${VALID_SCOPES.join(", ")}.`);
     return;
   }
   const bundle = memory.exportBundle({ scope: scopeRaw });
@@ -848378,7 +848378,7 @@ function handleRecallPromote(args2, context) {
   const id = parsed.rest[0];
   const scope = parsed.rest[1];
   if (!id || !scope || !isValidScope(scope)) {
-    context.print(`[memory] Usage: /memory promote <id> <${VALID_SCOPES2.join("|")}> --yes`);
+    context.print(`[memory] Usage: /memory promote <id> <${VALID_SCOPES.join("|")}> --yes`);
     return;
   }
   if (!parsed.yes) {
@@ -862223,7 +862223,7 @@ import { mkdirSync as mkdirSync64, readFileSync as readFileSync86, writeFileSync
 import { dirname as dirname63, resolve as resolve39 } from "path";
 init_state3();
 var VALID_CLASSES2 = ["decision", "constraint", "incident", "pattern", "fact", "risk", "runbook", "architecture", "ownership"];
-var VALID_SCOPES4 = ["session", "project", "team"];
+var VALID_SCOPES3 = ["session", "project", "team"];
 var VALID_REVIEW_STATES3 = ["fresh", "reviewed", "stale", "contradicted"];
 var VALID_PROVENANCE_KINDS = ["session", "turn", "task", "event", "file"];
 var VALUE_OPTIONS = new Set([
@@ -862323,7 +862323,7 @@ function isMemoryClass2(value) {
   return VALID_CLASSES2.includes(value);
 }
 function isMemoryScope2(value) {
-  return VALID_SCOPES4.includes(value);
+  return VALID_SCOPES3.includes(value);
 }
 function isReviewState(value) {
   return VALID_REVIEW_STATES3.includes(value);
@@ -862338,7 +862338,7 @@ function requireClass(value) {
 }
 function requireScope(value) {
   if (!value || !isMemoryScope2(value))
-    throw new Error(`Invalid memory scope "${value ?? ""}". Valid values ${VALID_SCOPES4.join(", ")}`);
+    throw new Error(`Invalid memory scope "${value ?? ""}". Valid values ${VALID_SCOPES3.join(", ")}`);
   return value;
 }
 function optionalScope(value) {
@@ -880710,6 +880710,24 @@ function listHarnessModelTools(toolRegistry, args2) {
     ...includeParameters ? { parameters: tool2.parameters } : {}
   }));
 }
+function describeHarnessModelTool(toolRegistry, args2) {
+  const query2 = readString55(args2.toolName || args2.target || args2.query).toLowerCase();
+  if (!query2)
+    return null;
+  const tool2 = toolRegistry.getToolDefinitions().find((candidate) => candidate.name.toLowerCase() === query2 || candidate.name.toLowerCase().includes(query2));
+  if (!tool2)
+    return null;
+  return {
+    name: tool2.name,
+    description: tool2.description,
+    sideEffects: tool2.sideEffects ?? [],
+    concurrency: tool2.concurrency ?? "parallel",
+    supportsProgress: tool2.supportsProgress ?? false,
+    supportsStreamingOutput: tool2.supportsStreamingOutput ?? false,
+    parameters: tool2.parameters,
+    policy: "This is a first-class model tool definition. Use the returned JSON schema directly; mutating or external side-effect tools still require the explicit confirmation arguments defined by that tool."
+  };
+}
 
 // src/tools/agent-harness-tool-schema.ts
 var AGENT_HARNESS_MODES = [
@@ -880740,6 +880758,7 @@ var AGENT_HARNESS_MODES = [
   "workspace_action",
   "run_workspace_action",
   "tools",
+  "tool",
   "connected_host",
   "connected_host_status",
   "connected_host_capability"
@@ -880825,12 +880844,16 @@ var AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   target: {
     type: "string",
-    description: "Optional UI target, such as a model-picker target or settings target key."
+    description: "Optional lookup target, such as a model-picker target, settings key, model tool name, or connected-host capability id."
   },
   capabilityId: {
     type: "string",
     description: "Connected-host allowed or blocked capability id for mode connected_host_capability, such as agent-knowledge-read or connected-host-lifecycle."
   },
+  toolName: {
+    type: "string",
+    description: "First-class model tool name for mode tool, such as agent_harness or agent_local_registry."
+  },
   category: {
     type: "string",
     description: "Setting category filter such as provider, behavior, tools, ui, tts, permissions, automation, or surfaces."
@@ -882010,7 +882033,7 @@ function createAgentHarnessTool(deps) {
       name: "agent_harness",
       description: [
         "Discover and operate the GoodVibes Agent harness from the main conversation.",
-        "Use this tool to inspect Agent workspace actions, built-in panels, top-level CLI mirrors, UI surfaces, keybindings, slash commands with policy metadata, model tools, connected-host capabilities or one connected-host capability detail, and Agent settings, or to invoke a workspace action/command through the same in-process command registry the user uses in the TUI.",
+        "Use this tool to inspect Agent workspace actions, built-in panels, top-level CLI mirrors, UI surfaces, keybindings, slash commands with policy metadata, model tools or one model tool schema, connected-host capabilities or one connected-host capability detail, and Agent settings, or to invoke a workspace action/command through the same in-process command registry the user uses in the TUI.",
         "Discovery modes are read-only. Setting/keybinding writes, resets, UI routing, slash command invocation, and workspace action invocation require confirm:true plus explicitUserRequest.",
         "This tool preserves Agent product boundaries: connected-host lifecycle and listener posture stay externally owned, connected-host mode reports allowed and blocked route families, and secret-backed settings store raw values through the secret manager while config receives only a secret reference."
       ].join(" "),
@@ -882049,7 +882072,7 @@ function createAgentHarnessTool(deps) {
               slashCommands: 'Use mode:"commands" and mode:"command" to inspect; use mode:"run_command" with confirm:true plus explicitUserRequest to execute.',
               workspace: 'Use mode:"workspace_actions" to list and mode:"workspace_action" for editor schemas; set includeParameters:true on workspace_actions to inline editor schemas.',
               settings: 'Use mode:"settings", mode:"get_setting", mode:"set_setting", and mode:"reset_setting".',
-              tools: 'Use mode:"tools" with includeParameters:true to inspect first-class model tool schemas.',
+              tools: 'Use mode:"tools" to list first-class model tools, or mode:"tool" with toolName, target, or query to inspect one schema.',
               connectedHost: 'Use mode:"connected_host" for the connected-host capability map and blocked boundaries. Use mode:"connected_host_capability" with capabilityId, target, or query for one allowed or blocked capability.',
               connectedHostStatus: 'Use mode:"connected_host_status" for live read-only host reachability, SDK compatibility, token posture, and Agent Knowledge route readiness.'
             },
@@ -882188,6 +882211,11 @@ function createAgentHarnessTool(deps) {
           const tools3 = listHarnessModelTools(deps.toolRegistry, args2);
           return output7({ tools: tools3, returned: tools3.length, total: deps.toolRegistry.getToolDefinitions().length });
         }
+        if (args2.mode === "tool") {
+          const query2 = readString57(args2.toolName || args2.target || args2.query);
+          const tool2 = describeHarnessModelTool(deps.toolRegistry, args2);
+          return tool2 ? output7(tool2) : error52(`Unknown model tool ${query2 || "<missing>"}. Use mode:"tools" to inspect available model tools.`);
+        }
         if (args2.mode === "connected_host")
           return output7(connectedHostSummary(deps.commandContext, deps.toolRegistry));
         if (args2.mode === "connected_host_capability") {

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, single connected-host capability inspection, 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.
+- 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 and individual model tool schemas, settings, local registries, connected-host capability boundaries, single connected-host capability inspection, 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, 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; 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.
+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 and single-tool schema inspection, settings inspection/mutation, 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; 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

@@ -43,14 +43,14 @@ Host-management and coding-first commands that would imply connected-host lifecy
 
 The main Agent model has an Agent-owned harness bridge rather than generic SDK settings/context control. Use these model tools as the supported parity layer:
 
-- `agent_harness`: inspect workspace categories/actions, inspect built-in panels, inspect modal/overlay/picker UI surfaces and named operator surfaces, inspect top-level CLI mirrors, inspect fixed shortcuts and configurable keybindings, inspect slash commands and command policy metadata, run concrete workspace or slash-command mirrors with confirmation, inspect model tools, inspect or change Agent settings/keybindings, inspect connected-host capability boundaries or one connected-host capability, and inspect live connected-host readiness.
+- `agent_harness`: inspect workspace categories/actions, inspect built-in panels, inspect modal/overlay/picker UI surfaces and named operator surfaces, inspect top-level CLI mirrors, inspect fixed shortcuts and configurable keybindings, inspect slash commands and command policy metadata, run concrete workspace or slash-command mirrors with confirmation, inspect model tools or one model tool schema, inspect or change Agent settings/keybindings, inspect connected-host capability boundaries or one connected-host capability, and inspect live connected-host readiness.
 - `agent_local_registry`: inspect and maintain Agent-local memory, notes, personas, skills, skill bundles, and routines. Deleting local records requires `confirm:true` and `explicitUserRequest`.
 - `agent_knowledge` and `agent_knowledge_ingest`: ask/search and ingest into the isolated Agent Knowledge segment.
 - `agent_operator_briefing` and `agent_operator_action`: inspect connected work/approval/automation posture, or run exact confirmed approval/automation actions.
 - `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` 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; `connected_host_capability` returns one allowed or blocked connected-host capability by `capabilityId`, `target`, or `query` with related route families and boundary text; 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` 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` lists model tool definitions and can inline JSON schemas with `includeParameters:true`; `tool` returns one model tool schema by `toolName`, `target`, or `query`; `settings` returns setting descriptors plus setting policy; `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 `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.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pellux/goodvibes-agent",
-  "version": "1.0.13",
+  "version": "1.0.14",
   "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-model-tool-catalog.ts

@@ -2,6 +2,8 @@ import type { ToolRegistry } from '@pellux/goodvibes-sdk/platform/tools';
 
 export interface AgentHarnessModelToolCatalogArgs {
   readonly query?: unknown;
+  readonly toolName?: unknown;
+  readonly target?: unknown;
   readonly includeParameters?: unknown;
   readonly limit?: unknown;
 }
@@ -34,3 +36,21 @@ export function listHarnessModelTools(toolRegistry: ToolRegistry, args: AgentHar
       ...(includeParameters ? { parameters: tool.parameters } : {}),
     }));
 }
+
+export function describeHarnessModelTool(toolRegistry: ToolRegistry, args: AgentHarnessModelToolCatalogArgs): Record<string, unknown> | null {
+  const query = readString(args.toolName || args.target || args.query).toLowerCase();
+  if (!query) return null;
+  const tool = toolRegistry.getToolDefinitions()
+    .find((candidate) => candidate.name.toLowerCase() === query || candidate.name.toLowerCase().includes(query));
+  if (!tool) return null;
+  return {
+    name: tool.name,
+    description: tool.description,
+    sideEffects: tool.sideEffects ?? [],
+    concurrency: tool.concurrency ?? 'parallel',
+    supportsProgress: tool.supportsProgress ?? false,
+    supportsStreamingOutput: tool.supportsStreamingOutput ?? false,
+    parameters: tool.parameters,
+    policy: 'This is a first-class model tool definition. Use the returned JSON schema directly; mutating or external side-effect tools still require the explicit confirmation arguments defined by that tool.',
+  };
+}

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

@@ -4,7 +4,7 @@ export const AGENT_HARNESS_MODES = [
   'shortcuts', 'keybindings', 'keybinding', 'set_keybinding', 'reset_keybinding',
   'commands', 'command', 'run_command', 'settings', 'get_setting', 'set_setting',
   'reset_setting', 'workspace', 'workspace_categories', 'workspace_actions',
-  'workspace_action', 'run_workspace_action', 'tools', 'connected_host', 'connected_host_status',
+  'workspace_action', 'run_workspace_action', 'tools', 'tool', 'connected_host', 'connected_host_status',
   'connected_host_capability',
 ] as const;
 
@@ -90,12 +90,16 @@ export const AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   target: {
     type: 'string',
-    description: 'Optional UI target, such as a model-picker target or settings target key.',
+    description: 'Optional lookup target, such as a model-picker target, settings key, model tool name, or connected-host capability id.',
   },
   capabilityId: {
     type: 'string',
     description: 'Connected-host allowed or blocked capability id for mode connected_host_capability, such as agent-knowledge-read or connected-host-lifecycle.',
   },
+  toolName: {
+    type: 'string',
+    description: 'First-class model tool name for mode tool, such as agent_harness or agent_local_registry.',
+  },
   category: {
     type: 'string',
     description: 'Setting category filter such as provider, behavior, tools, ui, tts, permissions, automation, or surfaces.',

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

@@ -22,7 +22,7 @@ import { describeHarnessKeybinding, listHarnessKeybindings, listHarnessShortcuts
 import { describeHarnessPanel, listHarnessPanels, openHarnessPanel, totalHarnessPanels } from './agent-harness-panel-metadata.ts';
 import { connectedHostStatusSummary } from './agent-harness-connected-host-status.ts';
 import { describeLocalWorkspaceModelExecution, runLocalWorkspaceAction, runLocalWorkspaceEditorAction } from './agent-harness-local-operations.ts';
-import { listHarnessModelTools } from './agent-harness-model-tool-catalog.ts';
+import { describeHarnessModelTool, 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';
 import {
@@ -60,6 +60,7 @@ interface AgentHarnessToolArgs {
   readonly value?: unknown;
   readonly target?: unknown;
   readonly capabilityId?: unknown;
+  readonly toolName?: unknown;
   readonly category?: unknown;
   readonly prefix?: unknown;
   readonly includeHidden?: unknown;
@@ -515,7 +516,7 @@ export function createAgentHarnessTool(deps: AgentHarnessToolDeps): Tool {
       name: 'agent_harness',
       description: [
         'Discover and operate the GoodVibes Agent harness from the main conversation.',
-        'Use this tool to inspect Agent workspace actions, built-in panels, top-level CLI mirrors, UI surfaces, keybindings, slash commands with policy metadata, model tools, connected-host capabilities or one connected-host capability detail, and Agent settings, or to invoke a workspace action/command through the same in-process command registry the user uses in the TUI.',
+        'Use this tool to inspect Agent workspace actions, built-in panels, top-level CLI mirrors, UI surfaces, keybindings, slash commands with policy metadata, model tools or one model tool schema, connected-host capabilities or one connected-host capability detail, and Agent settings, or to invoke a workspace action/command through the same in-process command registry the user uses in the TUI.',
         'Discovery modes are read-only. Setting/keybinding writes, resets, UI routing, slash command invocation, and workspace action invocation require confirm:true plus explicitUserRequest.',
         'This tool preserves Agent product boundaries: connected-host lifecycle and listener posture stay externally owned, connected-host mode reports allowed and blocked route families, and secret-backed settings store raw values through the secret manager while config receives only a secret reference.',
       ].join(' '),
@@ -553,7 +554,7 @@ export function createAgentHarnessTool(deps: AgentHarnessToolDeps): Tool {
               slashCommands: 'Use mode:"commands" and mode:"command" to inspect; use mode:"run_command" with confirm:true plus explicitUserRequest to execute.',
               workspace: 'Use mode:"workspace_actions" to list and mode:"workspace_action" for editor schemas; set includeParameters:true on workspace_actions to inline editor schemas.',
               settings: 'Use mode:"settings", mode:"get_setting", mode:"set_setting", and mode:"reset_setting".',
-              tools: 'Use mode:"tools" with includeParameters:true to inspect first-class model tool schemas.',
+              tools: 'Use mode:"tools" to list first-class model tools, or mode:"tool" with toolName, target, or query to inspect one schema.',
               connectedHost: 'Use mode:"connected_host" for the connected-host capability map and blocked boundaries. Use mode:"connected_host_capability" with capabilityId, target, or query for one allowed or blocked capability.',
               connectedHostStatus: 'Use mode:"connected_host_status" for live read-only host reachability, SDK compatibility, token posture, and Agent Knowledge route readiness.',
             },
@@ -692,6 +693,13 @@ export function createAgentHarnessTool(deps: AgentHarnessToolDeps): Tool {
           const tools = listHarnessModelTools(deps.toolRegistry, args);
           return output({ tools, returned: tools.length, total: deps.toolRegistry.getToolDefinitions().length });
         }
+        if (args.mode === 'tool') {
+          const query = readString(args.toolName || args.target || args.query);
+          const tool = describeHarnessModelTool(deps.toolRegistry, args);
+          return tool
+            ? output(tool)
+            : error(`Unknown model tool ${query || '<missing>'}. Use mode:"tools" to inspect available model tools.`);
+        }
         if (args.mode === 'connected_host') return output(connectedHostSummary(deps.commandContext, deps.toolRegistry));
         if (args.mode === 'connected_host_capability') {
           const query = readString(args.capabilityId || args.target || args.query);

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 = '1.0.13';
+let _version = '1.0.14';
 let _sdkVersion = '0.33.35';
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, '..', 'package.json'), 'utf-8')) as {