@pellux/goodvibes-agent 1.0.12 → 1.0.14

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 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.
+- Keep connected-host operation model-visible without exposing host lifecycle, listener, non-Agent knowledge, hidden background work, or arbitrary host mutations.
+- Refresh package-facing docs and focused harness coverage for the updated connected-host capability map.
+
 ## 1.0.12 - 2026-06-03
 
 - Expose command browser, reasoning-effort picker, and live process output as model-visible confirmation-gated harness UI surfaces.

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. 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

@@ -389257,6 +389257,23 @@ function createSchema2(db) {
   `);
   db.run(`CREATE INDEX IF NOT EXISTS idx_knowledge_schedules_job_id ON knowledge_schedules(job_id)`);
 }
+function getKnowledgeSchemaStatements() {
+  const statements = [];
+  createSchema2({
+    run(sql) {
+      const normalized = sql.trim();
+      if (normalized.length > 0)
+        statements.push(normalized);
+    }
+  });
+  return statements;
+}
+function renderKnowledgeSchemaSql() {
+  return `${getKnowledgeSchemaStatements().map((statement) => statement.endsWith(";") ? statement : `${statement};`).join(`
+
+`)}
+`;
+}
 function rowObject(columns, values2) {
   return Object.fromEntries(columns.map((column, index) => [column, values2[index]]));
 }
@@ -702594,6 +702611,9 @@ var init_ingest = __esm(() => {
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/browser-history/index.js
 var init_browser_history = __esm(() => {
   init_ingest();
+  init_discover();
+  init_readers();
+  init_paths2();
 });
 
 // node_modules/graphql/jsutils/devAssert.mjs
@@ -720233,6 +720253,7 @@ var init_semantic = __esm(() => {
   init_llm();
   init_gap_repair();
   init_service4();
+  init_self_improvement();
 });
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/home-graph/helpers.js
@@ -724201,8 +724222,40 @@ var init_map_view = __esm(() => {
 });
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/home-graph/types.js
-var HOME_GRAPH_CAPABILITIES;
+var HOME_GRAPH_NODE_KINDS, HOME_GRAPH_RELATIONS, HOME_GRAPH_CAPABILITIES;
 var init_types6 = __esm(() => {
+  HOME_GRAPH_NODE_KINDS = [
+    "ha_home",
+    "ha_entity",
+    "ha_device",
+    "ha_area",
+    "ha_automation",
+    "ha_script",
+    "ha_scene",
+    "ha_label",
+    "ha_integration",
+    "ha_room",
+    "ha_device_passport",
+    "ha_maintenance_item",
+    "ha_troubleshooting_case",
+    "ha_purchase",
+    "ha_network_node"
+  ];
+  HOME_GRAPH_RELATIONS = [
+    "controls",
+    "located_in",
+    "belongs_to_device",
+    "has_manual",
+    "has_receipt",
+    "has_warranty",
+    "has_issue",
+    "fixed_by",
+    "uses_battery",
+    "connected_via",
+    "part_of_network",
+    "mentioned_by",
+    "source_for"
+  ];
   HOME_GRAPH_CAPABILITIES = [
     "knowledge-space-isolation",
     "snapshot-sync",
@@ -725609,6 +725662,7 @@ var init_service5 = __esm(() => {
 var init_home_graph = __esm(() => {
   init_service5();
   init_extension();
+  init_types6();
 });
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/store-refinement.js
@@ -727936,10 +727990,14 @@ var init_service6 = __esm(() => {
 var init_project_planning = __esm(() => {
   init_service6();
   init_helpers3();
+  init_readiness();
 });
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/persistence.js
-var init_persistence = () => {};
+var init_persistence = __esm(() => {
+  init_store_schema();
+  init_store_load();
+});
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/knowledge/projections.js
 class KnowledgeProjectionService {
@@ -731447,21 +731505,21 @@ var init_service7 = __esm(() => {
 var exports_knowledge = {};
 __export(exports_knowledge, {
   withKnowledgeSpace: () => withKnowledgeSpace,
-  uniqKnowledgeValues: () => uniq3,
-  stabilizeKnowledgeText: () => stableText2,
-  runKnowledgeSemanticSelfImprovement: () => runKnowledgeSemanticSelfImprovement2,
+  uniqKnowledgeValues: () => uniq2,
+  stabilizeKnowledgeText: () => stableText,
+  runKnowledgeSemanticSelfImprovement: () => runKnowledgeSemanticSelfImprovement,
   resolveProjectPlanningSpace: () => resolveProjectPlanningSpace,
-  resolveKnowledgeDbPathFromControlPlaneDir: () => resolveKnowledgeDbPathFromControlPlaneDir2,
+  resolveKnowledgeDbPathFromControlPlaneDir: () => resolveKnowledgeDbPathFromControlPlaneDir,
   renderPacket: () => renderPacket,
   renderKnowledgeSchemaSql: () => renderKnowledgeSchemaSql,
   renderKnowledgeMap: () => renderKnowledgeMap,
   readKnowledgeSearchText: () => readKnowledgeSearchText,
-  readBrowserKnowledgeProfile: () => readBrowserKnowledgeProfile2,
+  readBrowserKnowledgeProfile: () => readBrowserKnowledgeProfile,
   projectPlanningSourceId: () => projectPlanningSourceId,
   projectPlanningProjectIdFromPath: () => projectPlanningProjectIdFromPath,
   projectPlanningCanonicalUri: () => projectPlanningCanonicalUri,
   projectKnowledgeSpaceId: () => projectKnowledgeSpaceId,
-  parseKnowledgeJsonValue: () => parseJsonValue2,
+  parseKnowledgeJsonValue: () => parseJsonValue,
   normalizeProjectId: () => normalizeProjectId,
   normalizeKnowledgeSpaceId: () => normalizeKnowledgeSpaceId,
   normalizeHomeAssistantInstallationId: () => normalizeHomeAssistantInstallationId,
@@ -731469,12 +731527,12 @@ __export(exports_knowledge, {
   materializeGeneratedKnowledgeProjection: () => materializeGeneratedKnowledgeProjection,
   looksLikeRawPdfPayload: () => looksLikeRawPdfPayload,
   looksBinaryLikeText: () => looksBinaryLikeText,
-  loadKnowledgeStoreSnapshot: () => loadKnowledgeStoreSnapshot2,
+  loadKnowledgeStoreSnapshot: () => loadKnowledgeStoreSnapshot,
   listGeneratedKnowledgePages: () => listGeneratedKnowledgePages,
-  listBrowserKinds: () => listBrowserKinds2,
+  listBrowserKinds: () => listBrowserKinds,
   knowledgeSpaceMetadata: () => knowledgeSpaceMetadata,
   knowledgePageSourceWeight: () => knowledgePageSourceWeight,
-  knowledgeNowMs: () => nowMs2,
+  knowledgeNowMs: () => nowMs,
   knowledgeExtractionNeedsRefresh: () => knowledgeExtractionNeedsRefresh,
   isUsefulKnowledgePageSourceCandidate: () => isUsefulKnowledgePageSourceCandidate,
   isUsefulKnowledgePageSource: () => isUsefulKnowledgePageSource,
@@ -731494,12 +731552,12 @@ __export(exports_knowledge, {
   generatedKnowledgeSourceId: () => generatedKnowledgeSourceId,
   generatedKnowledgeCanonicalUri: () => generatedKnowledgeCanonicalUri,
   extractKnowledgeArtifact: () => extractKnowledgeArtifact,
-  evaluateProjectPlanningReadiness: () => evaluateProjectPlanningReadiness2,
-  discoverBrowserKnowledgeProfiles: () => discoverBrowserKnowledgeProfiles2,
+  evaluateProjectPlanningReadiness: () => evaluateProjectPlanningReadiness,
+  discoverBrowserKnowledgeProfiles: () => discoverBrowserKnowledgeProfiles,
   createWebKnowledgeGapRepairer: () => createWebKnowledgeGapRepairer,
   createProviderBackedKnowledgeSemanticLlm: () => createProviderBackedKnowledgeSemanticLlm,
   createMemoryApi: () => createMemoryApi,
-  createKnowledgeSchema: () => createSchema3,
+  createKnowledgeSchema: () => createSchema2,
   createKnowledgeApi: () => createKnowledgeApi,
   createDefaultKnowledgeConnectorRegistry: () => createDefaultKnowledgeConnectorRegistry,
   compareKnowledgePageSources: () => compareKnowledgePageSources,
@@ -733937,7 +733995,7 @@ var init_delivery_manager = __esm(() => {
 });
 
 // node_modules/@pellux/goodvibes-sdk/dist/platform/automation/scheduler-capacity.js
-function computeSchedulerCapacity(slotsTotal, runs, nowMs3 = Date.now()) {
+function computeSchedulerCapacity(slotsTotal, runs, nowMs2 = Date.now()) {
   let slotsInUse = 0;
   const queuedRuns = [];
   for (const run7 of runs) {
@@ -733947,7 +734005,7 @@ function computeSchedulerCapacity(slotsTotal, runs, nowMs3 = Date.now()) {
       queuedRuns.push(run7);
   }
   const queueDepth = queuedRuns.length;
-  const oldestQueuedAgeMs = queueDepth > 0 ? nowMs3 - Math.min(...queuedRuns.map((r5) => r5.queuedAt)) : null;
+  const oldestQueuedAgeMs = queueDepth > 0 ? nowMs2 - Math.min(...queuedRuns.map((r5) => r5.queuedAt)) : null;
   return { slotsTotal, slotsInUse, queueDepth, oldestQueuedAgeMs };
 }
 
@@ -816508,7 +816566,7 @@ var createStyledCell = (char, overrides = {}) => ({
 // src/version.ts
 import { readFileSync } from "fs";
 import { join } from "path";
-var _version = "1.0.12";
+var _version = "1.0.14";
 var _sdkVersion = "0.33.35";
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, "..", "package.json"), "utf-8"));
@@ -839370,7 +839428,7 @@ var WORK_PLAN_STATUSES = [
   "failed",
   "cancelled"
 ];
-function nowMs3() {
+function nowMs2() {
   return Date.now();
 }
 function isObject5(value) {
@@ -839476,7 +839534,7 @@ class WorkPlanStore {
     if (!normalizedTitle)
       throw new Error("Work plan item title is required.");
     const plan = this.readPlan();
-    const time4 = nowMs3();
+    const time4 = nowMs2();
     const item = {
       id: createItemId(),
       title: normalizedTitle,
@@ -839500,7 +839558,7 @@ class WorkPlanStore {
   updateItem(idOrPrefix, patch2) {
     const plan = this.readPlan();
     const item = this.resolveItem(plan, idOrPrefix);
-    const time4 = nowMs3();
+    const time4 = nowMs2();
     const nextStatus = patch2.status ?? item.status;
     const next = this.pruneItem({
       ...item,
@@ -839533,7 +839591,7 @@ class WorkPlanStore {
   removeItem(idOrPrefix) {
     const plan = this.readPlan();
     const item = this.resolveItem(plan, idOrPrefix);
-    const time4 = nowMs3();
+    const time4 = nowMs2();
     const remaining = plan.items.filter((candidate) => candidate.id !== item.id);
     this.writePlan({
       ...plan,
@@ -839553,7 +839611,7 @@ class WorkPlanStore {
       ...plan,
       items: remaining,
       activeItemId: remaining[0]?.id,
-      updatedAt: nowMs3()
+      updatedAt: nowMs2()
     });
     return removed;
   }
@@ -839592,7 +839650,7 @@ class WorkPlanStore {
     const parsed = JSON.parse(raw);
     if (!isObject5(parsed))
       return this.createEmptyPlan();
-    const time4 = nowMs3();
+    const time4 = nowMs2();
     const createdAt = typeof parsed.createdAt === "number" ? parsed.createdAt : time4;
     const updatedAt = typeof parsed.updatedAt === "number" ? parsed.updatedAt : createdAt;
     const items = Array.isArray(parsed.items) ? parsed.items.map((item) => normalizeItem(item, createdAt)).filter((item) => item !== null) : [];
@@ -839611,7 +839669,7 @@ class WorkPlanStore {
     };
   }
   createEmptyPlan() {
-    const time4 = nowMs3();
+    const time4 = nowMs2();
     return {
       id: createPlanId(this.options.projectId, this.options.projectRoot),
       projectId: this.options.projectId,
@@ -879550,6 +879608,52 @@ function connectedHostRouteFamilies() {
     }
   ];
 }
+function normalizeCapabilityQuery(value) {
+  return value.trim().toLowerCase();
+}
+function recordTextMatches(record2, query2) {
+  if (!query2)
+    return false;
+  const values2 = Object.values(record2).flatMap((value) => Array.isArray(value) ? value : [value]);
+  return values2.filter((value) => typeof value === "string" || typeof value === "number" || typeof value === "boolean").map((value) => String(value).toLowerCase()).some((value) => value === query2 || value.includes(query2));
+}
+function relatedConnectedHostRouteFamilies(capability) {
+  const modelTools = Array.isArray(capability.modelTools) ? capability.modelTools.filter((tool2) => typeof tool2 === "string") : [];
+  const capabilityId = typeof capability.id === "string" ? capability.id : "";
+  return connectedHostRouteFamilies().filter((family) => {
+    const familyTools = Array.isArray(family.modelTools) ? family.modelTools.filter((tool2) => typeof tool2 === "string") : [];
+    if (familyTools.some((tool2) => modelTools.includes(tool2)))
+      return true;
+    return capabilityId.length > 0 && recordTextMatches(family, capabilityId);
+  });
+}
+function describeConnectedHostCapability(toolRegistry, rawQuery) {
+  const query2 = normalizeCapabilityQuery(rawQuery);
+  if (!query2)
+    return null;
+  const allowedCapability = connectedHostCapabilityMap(toolRegistry).find((capability) => recordTextMatches(capability, query2));
+  if (allowedCapability) {
+    return {
+      status: "allowed",
+      capability: allowedCapability,
+      relatedRouteFamilies: relatedConnectedHostRouteFamilies(allowedCapability),
+      statusMode: 'Use agent_harness mode:"connected_host_status" for live read-only reachability, SDK compatibility, token posture, and Agent Knowledge route readiness.',
+      boundary: "Use only the listed first-class model tools, slash-command families, and workspace categories. Mutations still require explicit confirmation through those tools or command bridges."
+    };
+  }
+  const blockedCapability = blockedConnectedHostCapabilities().find((capability) => recordTextMatches(capability, query2));
+  if (blockedCapability) {
+    return {
+      status: "blocked",
+      capability: blockedCapability,
+      allowed: false,
+      available: false,
+      boundary: "This connected-host surface is intentionally not exposed to the model as an Agent operation.",
+      statusMode: 'Use agent_harness mode:"connected_host_status" only for read-only readiness diagnostics.'
+    };
+  }
+  return null;
+}
 function connectedHostSummary(context, toolRegistry) {
   const shellPaths3 = context.workspace.shellPaths;
   const homeDirectory = shellPaths3?.homeDirectory ?? context.platform.configManager.getHomeDirectory() ?? "";
@@ -880606,6 +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 = [
@@ -880636,8 +880758,10 @@ var AGENT_HARNESS_MODES = [
   "workspace_action",
   "run_workspace_action",
   "tools",
+  "tool",
   "connected_host",
-  "connected_host_status"
+  "connected_host_status",
+  "connected_host_capability"
 ];
 var KEY_COMBO_PARAMETER_SCHEMA = {
   type: "object",
@@ -880720,7 +880844,15 @@ 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",
@@ -881901,7 +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, 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(" "),
@@ -881940,8 +882072,8 @@ 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.',
-              connectedHost: 'Use mode:"connected_host" for the connected-host capability map and blocked boundaries.',
+              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.'
             },
             settingsPolicy: settingsPolicySummary(),
@@ -882079,8 +882211,18 @@ 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") {
+          const query2 = readString57(args2.capabilityId || args2.target || args2.query);
+          const capability = describeConnectedHostCapability(deps.toolRegistry, query2);
+          return capability ? output7(capability) : error52(`Unknown connected-host capability ${query2 || "<missing>"}. Use mode:"connected_host" to inspect allowed and blocked capability ids.`);
+        }
         if (args2.mode === "connected_host_status")
           return output7(await connectedHostStatusSummary(deps.commandContext, deps.toolRegistry));
         return error52(`Unhandled agent_harness mode: ${args2.mode}`);

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. 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/connected-host.md

@@ -54,7 +54,7 @@ Agent owns the operator assistant TUI, local profiles, local memory/notes/routin
 
 Agent does not own connected-host lifecycle. It does not provide commands to install, expose, start, stop, restart, or mutate the connected GoodVibes host.
 
-The model can inspect this boundary with `agent_harness` mode `connected_host`. That report includes the configured base URL, token presence, token path, allowed route families, first-class Agent tool capabilities, tool availability, and blocked capabilities. Allowed capabilities are limited to read-only operator briefing, explicit allowlisted approval/automation/schedule actions, isolated Agent Knowledge read/ingest, confirmed channel or notification delivery, confirmed reminder schedules, and configured media generation. Blocked capabilities include connected-host lifecycle, listener mutation, default or non-Agent knowledge fallback, hidden background Agent jobs, implicit delegated review, route/account creation, and arbitrary connected-host mutations.
+The model can inspect this boundary with `agent_harness` mode `connected_host`. That report includes the configured base URL, token presence, token path, allowed route families, first-class Agent tool capabilities, tool availability, and blocked capabilities. Allowed capabilities are limited to read-only operator briefing, explicit allowlisted approval/automation/schedule actions, isolated Agent Knowledge read/ingest, confirmed channel or notification delivery, confirmed reminder schedules, and configured media generation. Blocked capabilities include connected-host lifecycle, listener mutation, default or non-Agent knowledge fallback, hidden background Agent jobs, implicit delegated review, route/account creation, and arbitrary connected-host mutations. To inspect one surface without parsing the full report, use `connected_host_capability` with `capabilityId`, `target`, or `query`; it returns either the allowed capability with related route families or the blocked capability with the boundary reason.
 
 The model can inspect live connected-host readiness with `agent_harness` mode `connected_host_status`. That report uses the same read-only status probe as the CLI: it checks the connected-host status route, verifies the SDK version pin, checks the isolated Agent Knowledge status route when token and version posture allow it, reports endpoint bindings and token posture without printing token values, and returns actionable findings. It is diagnostic only and does not expose host start, stop, restart, install, listener, or account-management operations.
 

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, 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.
 
@@ -138,7 +138,7 @@ If the GoodVibes API is not on `http://127.0.0.1:3421`, pass `--runtime-url http
 
 Agent Knowledge is an Agent-owned product segment. Agent commands must not fall back to default knowledge or other product-specific knowledge spaces.
 
-Host lifecycle commands are not part of GoodVibes Agent. Use Agent Workspace -> Home -> Host compatibility, Doctor diagnostics, and Review health for diagnostics. CLI status/doctor/compat commands are scriptable mirrors for install checks. The model-visible `connected_host` harness report lists usable Agent route families, first-class tool capabilities, and blocked lifecycle/non-Agent surfaces. The model-visible `connected_host_status` report performs the live read-only connected-host status and isolated Agent Knowledge readiness checks, reports SDK compatibility, token posture, endpoint bindings, route readiness, and actionable findings, and still does not expose host start/stop/restart/install operations.
+Host lifecycle commands are not part of GoodVibes Agent. Use Agent Workspace -> Home -> Host compatibility, Doctor diagnostics, and Review health for diagnostics. CLI status/doctor/compat commands are scriptable mirrors for install checks. The model-visible `connected_host` harness report lists usable Agent route families, first-class tool capabilities, and blocked lifecycle/non-Agent surfaces. `connected_host_capability` inspects one allowed or blocked connected-host capability and returns the matching route families, first-class tools, and boundary reason. The model-visible `connected_host_status` report performs the live read-only connected-host status and isolated Agent Knowledge readiness checks, reports SDK compatibility, token posture, endpoint bindings, route readiness, and actionable findings, and still does not expose host start/stop/restart/install operations.
 
 ## Current Product Notes
 

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, 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; 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": "1.0.12",
+  "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-metadata.ts

@@ -356,6 +356,68 @@ export function connectedHostRouteFamilies(): readonly Record<string, unknown>[]
   ];
 }
 
+function normalizeCapabilityQuery(value: string): string {
+  return value.trim().toLowerCase();
+}
+
+function recordTextMatches(record: Record<string, unknown>, query: string): boolean {
+  if (!query) return false;
+  const values = Object.values(record).flatMap((value) => Array.isArray(value) ? value : [value]);
+  return values
+    .filter((value): value is string | number | boolean => (
+      typeof value === 'string' || typeof value === 'number' || typeof value === 'boolean'
+    ))
+    .map((value) => String(value).toLowerCase())
+    .some((value) => value === query || value.includes(query));
+}
+
+function relatedConnectedHostRouteFamilies(capability: Record<string, unknown>): readonly Record<string, unknown>[] {
+  const modelTools = Array.isArray(capability.modelTools)
+    ? capability.modelTools.filter((tool): tool is string => typeof tool === 'string')
+    : [];
+  const capabilityId = typeof capability.id === 'string' ? capability.id : '';
+  return connectedHostRouteFamilies().filter((family) => {
+    const familyTools = Array.isArray(family.modelTools)
+      ? family.modelTools.filter((tool): tool is string => typeof tool === 'string')
+      : [];
+    if (familyTools.some((tool) => modelTools.includes(tool))) return true;
+    return capabilityId.length > 0 && recordTextMatches(family, capabilityId);
+  });
+}
+
+export function describeConnectedHostCapability(
+  toolRegistry: ToolRegistry,
+  rawQuery: string,
+): Record<string, unknown> | null {
+  const query = normalizeCapabilityQuery(rawQuery);
+  if (!query) return null;
+
+  const allowedCapability = connectedHostCapabilityMap(toolRegistry).find((capability) => recordTextMatches(capability, query));
+  if (allowedCapability) {
+    return {
+      status: 'allowed',
+      capability: allowedCapability,
+      relatedRouteFamilies: relatedConnectedHostRouteFamilies(allowedCapability),
+      statusMode: 'Use agent_harness mode:"connected_host_status" for live read-only reachability, SDK compatibility, token posture, and Agent Knowledge route readiness.',
+      boundary: 'Use only the listed first-class model tools, slash-command families, and workspace categories. Mutations still require explicit confirmation through those tools or command bridges.',
+    };
+  }
+
+  const blockedCapability = blockedConnectedHostCapabilities().find((capability) => recordTextMatches(capability, query));
+  if (blockedCapability) {
+    return {
+      status: 'blocked',
+      capability: blockedCapability,
+      allowed: false,
+      available: false,
+      boundary: 'This connected-host surface is intentionally not exposed to the model as an Agent operation.',
+      statusMode: 'Use agent_harness mode:"connected_host_status" only for read-only readiness diagnostics.',
+    };
+  }
+
+  return null;
+}
+
 export function connectedHostSummary(context: CommandContext, toolRegistry: ToolRegistry): Record<string, unknown> {
   const shellPaths = context.workspace.shellPaths;
   const homeDirectory = shellPaths?.homeDirectory ?? context.platform.configManager.getHomeDirectory() ?? '';

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 +4,8 @@ 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;
 
 const KEY_COMBO_PARAMETER_SCHEMA = {
@@ -89,7 +90,15 @@ 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',

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

@@ -22,11 +22,12 @@ 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 {
   connectedHostSummary,
+  describeConnectedHostCapability,
   describeCommandPolicy,
   settingsPolicySummary,
 } from './agent-harness-metadata.ts';
@@ -58,6 +59,8 @@ interface AgentHarnessToolArgs {
   readonly key?: unknown;
   readonly value?: unknown;
   readonly target?: unknown;
+  readonly capabilityId?: unknown;
+  readonly toolName?: unknown;
   readonly category?: unknown;
   readonly prefix?: unknown;
   readonly includeHidden?: unknown;
@@ -513,7 +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, 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(' '),
@@ -551,8 +554,8 @@ 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.',
-              connectedHost: 'Use mode:"connected_host" for the connected-host capability map and blocked boundaries.',
+              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.',
             },
             settingsPolicy: settingsPolicySummary(),
@@ -690,7 +693,21 @@ 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);
+          const capability = describeConnectedHostCapability(deps.toolRegistry, query);
+          return capability
+            ? output(capability)
+            : error(`Unknown connected-host capability ${query || '<missing>'}. Use mode:"connected_host" to inspect allowed and blocked capability ids.`);
+        }
         if (args.mode === 'connected_host_status') return output(await connectedHostStatusSummary(deps.commandContext, deps.toolRegistry));
         return error(`Unhandled agent_harness mode: ${args.mode}`);
       } catch (err) {

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 = '1.0.12';
+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 {