@pellux/goodvibes-agent 1.0.21 → 1.0.23

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 Product-facing release notes for GoodVibes Agent.
 
+## 1.0.23 - 2026-06-03
+
+- Return ambiguous agent_harness slash-command detail lookups with candidate commands instead of collapsing broad descriptive matches to unknown.
+- Keep exact slash command, alias, typed command, target, and unique descriptive lookup behavior unchanged.
+- Refresh package-facing docs and focused harness coverage for no-guess slash-command lookup parity.
+
+## 1.0.22 - 2026-06-03
+
+- Refuse ambiguous agent_harness model-tool schema lookup with candidate tools instead of selecting the first partial match.
+- Refuse ambiguous connected-host capability lookup with candidate capabilities while preserving exact and unique lookup behavior.
+- Refresh model-visible harness parameter descriptions, preferred route hints, package docs, and focused harness coverage for no-guess single-item lookup parity.
+
 ## 1.0.21 - 2026-06-03
 
 - Resolve agent_harness run_workspace_action by actionId, command, target, or query using the same lookup contract as workspace_action inspection.

package/README.md

@@ -66,7 +66,7 @@ Use the workspace as the primary product surface:
 
 Inside the Agent workspace, press `/` to search every workspace action by name, category, command, or detail. This is the primary discovery path for product actions; slash commands and CLI subcommands remain power-user/scriptable mirrors.
 
-The model has the same harness map through `agent_harness`: it can list Agent workspace actions, inspect or run one workspace action by `actionId`, `command`, `target`, or `query`, list built-in panels and inspect one panel by `panelId`, `target`, or `query`, inspect modal/overlay/picker UI surfaces by `surfaceId`, `target`, or `query`, list top-level CLI mirrors and inspect one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, inspect fixed shortcuts and configurable keybindings by `actionId`, `target`, `key`, or `query`, run shell-safe keybinding equivalents with confirmation, list slash commands, inspect one slash command by `command`, `commandName`, `target`, or `query` with parsed arguments and policy metadata, inspect model tool definitions or one model tool schema, inspect or change Agent settings by `key`, `target`, or `query` with confirmation, run concrete 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; each keybinding descriptor reports its model operation route, `run_keybinding` executes only supported shell-safe equivalents with confirmation, and prompt-editor-only or terminal-selection shortcuts remain explicit direct user interaction. `set_keybinding` and `reset_keybinding` write the same `keybindings.json` file the user edits and require confirmation. Workspace action discovery can inline editor field schemas with `includeParameters:true`; single-action lookup and execution use the same user-facing search fields, return or preserve lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates; CLI mirror, panel, UI surface, keybinding, and setting lookup use their catalog search fields and refuse ambiguous route or mutation requests with candidates; profile editors use the current starter-template inventory, and routine schedule editors can prefill a selected local routine from `recordId`. Selection-based local workspace actions accept a local `recordId` so the model can use the same note promotion and local registry flows as the TUI. Direct local create editors for memory, notes, personas, skills, and routines can execute from submitted fields through `run_workspace_action` and `agent_local_registry` with confirmation. The `connected_host` report includes route families, allowed capabilities, blocked lifecycle/non-Agent surfaces, and availability for the first-class Agent tools; `connected_host_capability` inspects one allowed or blocked capability by id, target, or query with its route families and boundary. The `connected_host_status` report performs a read-only live check of the connected-host status route and the isolated Agent Knowledge status route, reports SDK compatibility, token posture, endpoint bindings, route readiness, and actionable findings, and still refuses connected-host lifecycle control. The model uses those first-class tools for product workflows where they exist, such as Agent Knowledge, local memory/notes/personas/skills/routines, channel sends, notifications, reminders, media generation, work plans, and connected-host operator actions.
+The model has the same harness map through `agent_harness`: it can list Agent workspace actions, inspect or run one workspace action by `actionId`, `command`, `target`, or `query`, list built-in panels and inspect one panel by `panelId`, `target`, or `query`, inspect modal/overlay/picker UI surfaces by `surfaceId`, `target`, or `query`, list top-level CLI mirrors and inspect one mirror by `cliCommand`, `command`, `commandName`, `target`, or `query`, inspect fixed shortcuts and configurable keybindings by `actionId`, `target`, `key`, or `query`, run shell-safe keybinding equivalents with confirmation, list slash commands, inspect one slash command by `command`, `commandName`, `target`, or `query` with parsed arguments and policy metadata, inspect model tool definitions or one model tool schema, inspect or change Agent settings by `key`, `target`, or `query` with confirmation, run concrete 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; each keybinding descriptor reports its model operation route, `run_keybinding` executes only supported shell-safe equivalents with confirmation, and prompt-editor-only or terminal-selection shortcuts remain explicit direct user interaction. `set_keybinding` and `reset_keybinding` write the same `keybindings.json` file the user edits and require confirmation. Workspace action discovery can inline editor field schemas with `includeParameters:true`; single-action lookup and execution use the same user-facing search fields, return or preserve lookup metadata where the action result carries descriptors, and refuse ambiguous run requests with candidates; CLI mirror, panel, UI surface, keybinding, slash-command, model tool, setting, and connected-host capability lookup use their catalog search fields and refuse ambiguous route, schema, capability, or mutation requests with candidates; 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 = "1.0.21";
+var _version = "1.0.23";
 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_SCOPES = ["session", "project", "team"];
+var VALID_SCOPES2 = ["session", "project", "team"];
 var VALID_REVIEW_STATES = ["fresh", "reviewed", "stale", "contradicted"];
 function isValidClass(s4) {
   return VALID_CLASSES.includes(s4);
 }
 function isValidScope(s4) {
-  return VALID_SCOPES.includes(s4);
+  return VALID_SCOPES2.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 ${VALID_SCOPES.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
       return;
     }
   }
@@ -847999,7 +847999,7 @@ function handleRecallList(args2, context) {
   if (scopeIdx !== -1 && args2[scopeIdx + 1]) {
     const scope = args2[scopeIdx + 1];
     if (!isValidScope(scope)) {
-      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
       return;
     }
     filter.scope = scope;
@@ -848049,7 +848049,7 @@ async function handleRecallAdd(args2, context) {
   const tags = tagsRaw ? tagsRaw.split(",").map((token) => token.trim()).filter(Boolean) : [];
   const scope = scopeRaw && isValidScope(scopeRaw) ? scopeRaw : "project";
   if (scopeRaw && !isValidScope(scopeRaw)) {
-    context.print(`[memory] Invalid scope "${scopeRaw}". Valid values ${VALID_SCOPES.join(", ")}.`);
+    context.print(`[memory] Invalid scope "${scopeRaw}". Valid values ${VALID_SCOPES2.join(", ")}.`);
     return;
   }
   const provenance = [];
@@ -848183,7 +848183,7 @@ function handleRecallExport(args2, context) {
   if (scopeIdx !== -1 && commandArgs[scopeIdx + 1]) {
     const scope = commandArgs[scopeIdx + 1];
     if (!isValidScope(scope)) {
-      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES.join(", ")}.`);
+      context.print(`[memory] Unknown scope "${scope}". Valid values ${VALID_SCOPES2.join(", ")}.`);
       return;
     }
     filter.scope = scope;
@@ -848262,7 +848262,7 @@ function handleRecallHandoffExport(args2, context) {
   const scopeIdx = commandArgs.indexOf("--scope");
   const scopeRaw = scopeIdx !== -1 ? commandArgs[scopeIdx + 1] : "team";
   if (!scopeRaw || !isValidScope(scopeRaw)) {
-    context.print(`[memory] Unknown scope "${scopeRaw ?? ""}". Valid values ${VALID_SCOPES.join(", ")}.`);
+    context.print(`[memory] Unknown scope "${scopeRaw ?? ""}". Valid values ${VALID_SCOPES2.join(", ")}.`);
     return;
   }
   const bundle = memory.exportBundle({ scope: scopeRaw });
@@ -848378,7 +848378,7 @@ function handleRecallPromote(args2, context) {
   const id = parsed.rest[0];
   const scope = parsed.rest[1];
   if (!id || !scope || !isValidScope(scope)) {
-    context.print(`[memory] Usage: /memory promote <id> <${VALID_SCOPES.join("|")}> --yes`);
+    context.print(`[memory] Usage: /memory promote <id> <${VALID_SCOPES2.join("|")}> --yes`);
     return;
   }
   if (!parsed.yes) {
@@ -862311,7 +862311,7 @@ import { mkdirSync as mkdirSync64, readFileSync as readFileSync86, writeFileSync
 import { dirname as dirname63, resolve as resolve39 } from "path";
 init_state3();
 var VALID_CLASSES2 = ["decision", "constraint", "incident", "pattern", "fact", "risk", "runbook", "architecture", "ownership"];
-var VALID_SCOPES3 = ["session", "project", "team"];
+var VALID_SCOPES4 = ["session", "project", "team"];
 var VALID_REVIEW_STATES3 = ["fresh", "reviewed", "stale", "contradicted"];
 var VALID_PROVENANCE_KINDS = ["session", "turn", "task", "event", "file"];
 var VALUE_OPTIONS = new Set([
@@ -862411,7 +862411,7 @@ function isMemoryClass2(value) {
   return VALID_CLASSES2.includes(value);
 }
 function isMemoryScope2(value) {
-  return VALID_SCOPES3.includes(value);
+  return VALID_SCOPES4.includes(value);
 }
 function isReviewState(value) {
   return VALID_REVIEW_STATES3.includes(value);
@@ -862426,7 +862426,7 @@ function requireClass(value) {
 }
 function requireScope(value) {
   if (!value || !isMemoryScope2(value))
-    throw new Error(`Invalid memory scope "${value ?? ""}". Valid values ${VALID_SCOPES3.join(", ")}`);
+    throw new Error(`Invalid memory scope "${value ?? ""}". Valid values ${VALID_SCOPES4.join(", ")}`);
   return value;
 }
 function optionalScope(value) {
@@ -879461,7 +879461,7 @@ function describeCommandPolicy(commandName) {
     return {
       effect: "ui-navigation",
       confirmation,
-      preferredModelTool: "agent_harness workspace/workspace_actions/workspace_action",
+      preferredModelTool: "agent_harness workspace/workspace_actions/workspace_action/run_workspace_action",
       boundary: "Navigation and discovery commands should be inspected through agent_harness when possible."
     };
   }
@@ -879512,7 +879512,7 @@ function describeCliCommandPolicy(commandName) {
     return {
       effect: root === "tui" || root === "onboarding" ? "ui-navigation" : "read-only",
       confirmation,
-      preferredModelTool: root === "onboarding" || root === "tui" ? "agent_harness workspace/workspace_actions" : "agent_harness cli_commands/cli_command",
+      preferredModelTool: root === "onboarding" || root === "tui" ? "agent_harness workspace/workspace_actions/workspace_action/run_workspace_action" : "agent_harness cli_commands/cli_command",
       boundary: "Top-level CLI launch, setup, help, version, and completion commands are package entrypoint surfaces; use in-process workspace and slash-command bridges from the model when operating inside the TUI."
     };
   }
@@ -879535,7 +879535,7 @@ function describeCliCommandPolicy(commandName) {
     return {
       effect: "local-state",
       confirmation,
-      preferredModelTool: root === "profiles" ? "agent_harness workspace_actions/run_workspace_action" : "agent_local_registry",
+      preferredModelTool: root === "profiles" ? "agent_harness workspace_actions/workspace_action/run_workspace_action" : "agent_local_registry",
       boundary: "Local library/profile/session/bundle CLI commands operate on Agent-local data. Mutations require explicit user intent and should use first-class Agent-local tools where available."
     };
   }
@@ -879715,31 +879715,52 @@ function relatedConnectedHostRouteFamilies(capability) {
     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) {
+function describeConnectedHostCapabilityCandidates(entries) {
+  return entries.slice(0, 8).map((entry) => ({
+    status: entry.status,
+    capabilityId: typeof entry.capability.id === "string" ? entry.capability.id : "",
+    purpose: typeof entry.capability.purpose === "string" ? entry.capability.purpose : undefined,
+    reason: typeof entry.capability.reason === "string" ? entry.capability.reason : undefined
+  }));
+}
+function connectedHostCapabilityDetail(entry) {
+  if (entry.status === "allowed") {
     return {
       status: "allowed",
-      capability: allowedCapability,
-      relatedRouteFamilies: relatedConnectedHostRouteFamilies(allowedCapability),
+      capability: entry.capability,
+      relatedRouteFamilies: relatedConnectedHostRouteFamilies(entry.capability),
       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 {
+    status: "blocked",
+    capability: entry.capability,
+    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.'
+  };
+}
+function describeConnectedHostCapability(toolRegistry, rawQuery) {
+  const query2 = normalizeCapabilityQuery(rawQuery);
+  if (!query2)
+    return null;
+  const entries = [
+    ...connectedHostCapabilityMap(toolRegistry).map((capability) => ({ status: "allowed", capability })),
+    ...blockedConnectedHostCapabilities().map((capability) => ({ status: "blocked", capability }))
+  ];
+  const exact = entries.find((entry) => entry.capability.id === rawQuery);
+  if (exact)
+    return { status: "found", detail: connectedHostCapabilityDetail(exact) };
+  const insensitive = entries.find((entry) => typeof entry.capability.id === "string" && entry.capability.id.toLowerCase() === query2);
+  if (insensitive)
+    return { status: "found", detail: connectedHostCapabilityDetail(insensitive) };
+  const searched = entries.filter((entry) => recordTextMatches(entry.capability, query2));
+  if (searched.length === 1)
+    return { status: "found", detail: connectedHostCapabilityDetail(searched[0]) };
+  if (searched.length > 1)
+    return { status: "ambiguous", input: rawQuery, candidates: describeConnectedHostCapabilityCandidates(searched) };
   return null;
 }
 function connectedHostSummary(context, toolRegistry) {
@@ -880019,6 +880040,15 @@ function describeCommand(command8, lookup) {
     policy: describeCommandPolicy(command8.name)
   };
 }
+function describeCommandCandidate(command8) {
+  return {
+    name: command8.name,
+    slash: `/${command8.name}`,
+    aliases: command8.aliases ?? [],
+    description: command8.description,
+    usage: command8.usage ?? ""
+  };
+}
 function commandDetailLookupFromArgs(args2) {
   const rawCommand = readString51(args2.command);
   if (rawCommand) {
@@ -880055,6 +880085,7 @@ function resolveCommandDetail(commandRegistry, args2) {
   const direct = commandRegistry.get(lookup.parsedName);
   if (direct) {
     return {
+      status: "found",
       command: direct,
       lookup: {
         ...lookup,
@@ -880065,19 +880096,33 @@ function resolveCommandDetail(commandRegistry, args2) {
   const normalized = lookup.parsedName.toLowerCase();
   for (const command8 of commandRegistry.list()) {
     if (command8.name.toLowerCase() === normalized) {
-      return { command: command8, lookup: { ...lookup, resolvedBy: "case-insensitive-name" } };
+      return { status: "found", command: command8, lookup: { ...lookup, resolvedBy: "case-insensitive-name" } };
     }
     if ((command8.aliases ?? []).some((alias) => alias.toLowerCase() === normalized)) {
-      return { command: command8, lookup: { ...lookup, resolvedBy: "case-insensitive-alias" } };
+      return { status: "found", command: command8, lookup: { ...lookup, resolvedBy: "case-insensitive-alias" } };
     }
   }
   const descriptionMatches = commandRegistry.list().filter((command8) => commandMatches(command8, lookup.input));
   if (descriptionMatches.length === 1) {
-    return { command: descriptionMatches[0], lookup: { ...lookup, resolvedBy: "description" } };
+    return { status: "found", command: descriptionMatches[0], lookup: { ...lookup, resolvedBy: "description" } };
+  }
+  if (descriptionMatches.length > 1) {
+    return {
+      status: "ambiguous",
+      input: lookup.input,
+      candidates: descriptionMatches.map(describeCommandCandidate).slice(0, 8)
+    };
   }
   const prefixMatches = commandRegistry.fuzzyMatch(lookup.parsedName).filter((entry) => entry.score >= 80);
   if (prefixMatches.length === 1) {
-    return { command: prefixMatches[0].command, lookup: { ...lookup, resolvedBy: "prefix" } };
+    return { status: "found", command: prefixMatches[0].command, lookup: { ...lookup, resolvedBy: "prefix" } };
+  }
+  if (prefixMatches.length > 1) {
+    return {
+      status: "ambiguous",
+      input: lookup.input,
+      candidates: prefixMatches.map((entry) => describeCommandCandidate(entry.command)).slice(0, 8)
+    };
   }
   return null;
 }
@@ -880088,7 +880133,11 @@ function listHarnessCommands(commandRegistry, args2) {
 }
 function describeHarnessCommand(commandRegistry, args2) {
   const detail = resolveCommandDetail(commandRegistry, args2);
-  return detail ? describeCommand(detail.command, detail.lookup) : null;
+  if (detail?.status === "found")
+    return describeCommand(detail.command, detail.lookup);
+  if (detail?.status === "ambiguous")
+    return { status: "ambiguous", input: detail.input, candidates: detail.candidates };
+  return null;
 }
 
 // src/tools/agent-harness-keybinding-metadata.ts
@@ -881327,37 +881376,77 @@ function readLimit9(value, fallback) {
     return fallback;
   return Math.max(1, Math.min(500, Math.trunc(parsed)));
 }
-function listHarnessModelTools(toolRegistry, args2) {
-  const query2 = readString56(args2.query).toLowerCase();
-  const includeParameters = args2.includeParameters === true;
-  const limit3 = readLimit9(args2.limit, 200);
-  return toolRegistry.getToolDefinitions().filter((tool2) => !query2 || [tool2.name, tool2.description, ...tool2.sideEffects ?? []].join(`
-`).toLowerCase().includes(query2)).sort((a4, b3) => a4.name.localeCompare(b3.name)).slice(0, limit3).map((tool2) => ({
+function modelToolSearchText(tool2) {
+  return [
+    tool2.name,
+    tool2.description,
+    ...tool2.sideEffects ?? []
+  ].join(`
+`).toLowerCase();
+}
+function modelToolLookupFromArgs(args2) {
+  const toolName = readString56(args2.toolName);
+  if (toolName)
+    return { source: "toolName", input: toolName };
+  const target = readString56(args2.target);
+  if (target)
+    return { source: "target", input: target };
+  const query2 = readString56(args2.query);
+  return query2 ? { source: "query", input: query2 } : null;
+}
+function describeModelTool(tool2, options = {}) {
+  return {
     name: tool2.name,
     description: tool2.description,
     sideEffects: tool2.sideEffects ?? [],
     concurrency: tool2.concurrency ?? "parallel",
     supportsProgress: tool2.supportsProgress ?? false,
     supportsStreamingOutput: tool2.supportsStreamingOutput ?? false,
-    ...includeParameters ? { parameters: tool2.parameters } : {}
+    ...options.lookup ? { lookup: options.lookup } : {},
+    ...options.includeParameters ? { parameters: tool2.parameters } : {}
+  };
+}
+function describeModelToolCandidates(tools3) {
+  return tools3.slice(0, 8).map((tool2) => ({
+    toolName: tool2.name,
+    description: tool2.description,
+    sideEffects: tool2.sideEffects ?? []
   }));
 }
+function listHarnessModelTools(toolRegistry, args2) {
+  const query2 = readString56(args2.query).toLowerCase();
+  const includeParameters = args2.includeParameters === true;
+  const limit3 = readLimit9(args2.limit, 200);
+  return toolRegistry.getToolDefinitions().filter((tool2) => !query2 || modelToolSearchText(tool2).includes(query2)).sort((a4, b3) => a4.name.localeCompare(b3.name)).slice(0, limit3).map((tool2) => describeModelTool(tool2, { includeParameters }));
+}
 function describeHarnessModelTool(toolRegistry, args2) {
-  const query2 = readString56(args2.toolName || args2.target || args2.query).toLowerCase();
-  if (!query2)
+  const lookup = modelToolLookupFromArgs(args2);
+  if (!lookup)
     return null;
-  const tool2 = toolRegistry.getToolDefinitions().find((candidate) => candidate.name.toLowerCase() === query2 || candidate.name.toLowerCase().includes(query2));
-  if (!tool2)
+  const tools3 = toolRegistry.getToolDefinitions().sort((a4, b3) => a4.name.localeCompare(b3.name));
+  const normalized = lookup.input.toLowerCase();
+  const exact = tools3.find((tool2) => tool2.name === lookup.input);
+  const found = exact ? { tool: exact, resolvedBy: "name" } : (() => {
+    const insensitive = tools3.find((tool2) => tool2.name.toLowerCase() === normalized);
+    if (insensitive)
+      return { tool: insensitive, resolvedBy: "case-insensitive-name" };
+    const searched = tools3.filter((tool2) => modelToolSearchText(tool2).includes(normalized));
+    if (searched.length === 1)
+      return { tool: searched[0], resolvedBy: "search" };
+    if (searched.length > 1)
+      return { candidates: searched };
     return null;
+  })();
+  if (!found)
+    return null;
+  if ("candidates" in found)
+    return { status: "ambiguous", input: lookup.input, candidates: describeModelToolCandidates(found.candidates) };
   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."
+    status: "found",
+    tool: {
+      ...describeModelTool(found.tool, { includeParameters: true, lookup: { ...lookup, resolvedBy: found.resolvedBy } }),
+      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."
+    }
   };
 }
 
@@ -881410,7 +881499,7 @@ var AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   query: {
     type: "string",
-    description: "Search text for command, CLI mirror, panel, UI surface, keybinding, workspace action, setting, or tool catalogs; also slash-command, CLI mirror, setting, panel, UI surface, or keybinding lookup for single-item modes."
+    description: "Search text for slash-command, CLI mirror, panel, UI surface, keybinding, workspace action, model tool, setting, or connected-host capability catalogs; also lookup text for the matching single-item modes."
   },
   command: {
     type: "string",
@@ -881477,7 +881566,7 @@ var AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   target: {
     type: "string",
-    description: "Optional lookup target, such as a model-picker target, top-level CLI mirror/search text, panel id/search text, UI surface id/search text, workspace action id/search text, slash command root or invocation, setting key/search text, keybinding action/search text, model tool name, or connected-host capability id."
+    description: "Optional lookup target, such as a model-picker target, top-level CLI mirror/search text, panel id/search text, UI surface id/search text, workspace action id/search text, slash command root or invocation, setting key/search text, keybinding action/search text, model tool name/search text, or connected-host capability id/search text."
   },
   capabilityId: {
     type: "string",
@@ -881514,11 +881603,11 @@ var AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   confirm: {
     type: "boolean",
-    description: "Required true for set_setting, reset_setting, run_keybinding, run_command, open_panel, open_ui_surface, and mutating run_workspace_action calls after an explicit user request."
+    description: "Required true for set_setting, reset_setting, run_keybinding, run_command, open_panel, open_ui_surface, and executable or mutating run_workspace_action calls after an explicit user request."
   },
   explicitUserRequest: {
     type: "string",
-    description: "Exact user request or faithful short summary authorizing a setting mutation, keybinding action, or harness UI/command invocation."
+    description: "Exact user request or faithful short summary authorizing a setting mutation, keybinding change/action, harness UI routing, slash-command invocation, or workspace-action invocation."
   }
 };
 
@@ -882947,15 +883036,23 @@ function createAgentHarnessTool(deps) {
         }
         if (args2.mode === "tool") {
           const query2 = readString58(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.`);
+          const resolved = describeHarnessModelTool(deps.toolRegistry, args2);
+          if (resolved?.status === "found")
+            return output7(resolved.tool);
+          if (resolved?.status === "ambiguous")
+            return error52(`Ambiguous model tool ${resolved.input}. Candidates: ${JSON.stringify(resolved.candidates)}`);
+          return 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 = readString58(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.`);
+          const resolved = describeConnectedHostCapability(deps.toolRegistry, query2);
+          if (resolved?.status === "found")
+            return output7(resolved.detail);
+          if (resolved?.status === "ambiguous")
+            return error52(`Ambiguous connected-host capability ${resolved.input}. Candidates: ${JSON.stringify(resolved.candidates)}`);
+          return 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));

package/docs/getting-started.md

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

package/docs/tools-and-commands.md

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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pellux/goodvibes-agent",
-  "version": "1.0.21",
+  "version": "1.0.23",
   "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-command-catalog.ts

@@ -19,6 +19,10 @@ interface CommandDetailLookup {
   readonly resolvedBy: 'name' | 'alias' | 'case-insensitive-name' | 'case-insensitive-alias' | 'description' | 'prefix';
 }
 
+type CommandDetailResolution =
+  | { readonly status: 'found'; readonly command: SlashCommand; readonly lookup: CommandDetailLookup }
+  | { readonly status: 'ambiguous'; readonly input: string; readonly candidates: readonly Record<string, unknown>[] };
+
 function readString(value: unknown): string {
   return typeof value === 'string' ? value.trim() : '';
 }
@@ -67,6 +71,16 @@ function describeCommand(command: SlashCommand, lookup?: CommandDetailLookup): R
   };
 }
 
+function describeCommandCandidate(command: SlashCommand): Record<string, unknown> {
+  return {
+    name: command.name,
+    slash: `/${command.name}`,
+    aliases: command.aliases ?? [],
+    description: command.description,
+    usage: command.usage ?? '',
+  };
+}
+
 function commandDetailLookupFromArgs(args: AgentHarnessCommandCatalogArgs): Omit<CommandDetailLookup, 'resolvedBy'> | null {
   const rawCommand = readString(args.command);
   if (rawCommand) {
@@ -97,12 +111,13 @@ function commandDetailLookupFromArgs(args: AgentHarnessCommandCatalogArgs): Omit
   return null;
 }
 
-function resolveCommandDetail(commandRegistry: CommandRegistry, args: AgentHarnessCommandCatalogArgs): { readonly command: SlashCommand; readonly lookup: CommandDetailLookup } | null {
+function resolveCommandDetail(commandRegistry: CommandRegistry, args: AgentHarnessCommandCatalogArgs): CommandDetailResolution | null {
   const lookup = commandDetailLookupFromArgs(args);
   if (!lookup?.parsedName) return null;
   const direct = commandRegistry.get(lookup.parsedName);
   if (direct) {
     return {
+      status: 'found',
       command: direct,
       lookup: {
         ...lookup,
@@ -114,21 +129,35 @@ function resolveCommandDetail(commandRegistry: CommandRegistry, args: AgentHarne
   const normalized = lookup.parsedName.toLowerCase();
   for (const command of commandRegistry.list()) {
     if (command.name.toLowerCase() === normalized) {
-      return { command, lookup: { ...lookup, resolvedBy: 'case-insensitive-name' } };
+      return { status: 'found', command, lookup: { ...lookup, resolvedBy: 'case-insensitive-name' } };
     }
     if ((command.aliases ?? []).some((alias) => alias.toLowerCase() === normalized)) {
-      return { command, lookup: { ...lookup, resolvedBy: 'case-insensitive-alias' } };
+      return { status: 'found', command, lookup: { ...lookup, resolvedBy: 'case-insensitive-alias' } };
     }
   }
 
   const descriptionMatches = commandRegistry.list().filter((command) => commandMatches(command, lookup.input));
   if (descriptionMatches.length === 1) {
-    return { command: descriptionMatches[0]!, lookup: { ...lookup, resolvedBy: 'description' } };
+    return { status: 'found', command: descriptionMatches[0]!, lookup: { ...lookup, resolvedBy: 'description' } };
+  }
+  if (descriptionMatches.length > 1) {
+    return {
+      status: 'ambiguous',
+      input: lookup.input,
+      candidates: descriptionMatches.map(describeCommandCandidate).slice(0, 8),
+    };
   }
 
   const prefixMatches = commandRegistry.fuzzyMatch(lookup.parsedName).filter((entry) => entry.score >= 80);
   if (prefixMatches.length === 1) {
-    return { command: prefixMatches[0]!.command, lookup: { ...lookup, resolvedBy: 'prefix' } };
+    return { status: 'found', command: prefixMatches[0]!.command, lookup: { ...lookup, resolvedBy: 'prefix' } };
+  }
+  if (prefixMatches.length > 1) {
+    return {
+      status: 'ambiguous',
+      input: lookup.input,
+      candidates: prefixMatches.map((entry) => describeCommandCandidate(entry.command)).slice(0, 8),
+    };
   }
   return null;
 }
@@ -145,5 +174,7 @@ export function listHarnessCommands(commandRegistry: CommandRegistry, args: Agen
 
 export function describeHarnessCommand(commandRegistry: CommandRegistry, args: AgentHarnessCommandCatalogArgs): Record<string, unknown> | null {
   const detail = resolveCommandDetail(commandRegistry, args);
-  return detail ? describeCommand(detail.command, detail.lookup) : null;
+  if (detail?.status === 'found') return describeCommand(detail.command, detail.lookup);
+  if (detail?.status === 'ambiguous') return { status: 'ambiguous', input: detail.input, candidates: detail.candidates };
+  return null;
 }

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

@@ -9,6 +9,10 @@ export interface CommandExecutionPolicy {
   readonly boundary: string;
 }
 
+export type ConnectedHostCapabilityResolution =
+  | { readonly status: 'found'; readonly detail: Record<string, unknown> }
+  | { readonly status: 'ambiguous'; readonly input: string; readonly candidates: readonly Record<string, unknown>[] };
+
 export function describeCommandPolicy(commandName: string): CommandExecutionPolicy {
   const root = commandName.replace(/^\//, '').trim().toLowerCase();
   const confirmation = 'agent_harness mode:"run_command" requires confirm:true and explicitUserRequest for every slash command invocation.';
@@ -105,7 +109,7 @@ export function describeCommandPolicy(commandName: string): CommandExecutionPoli
     return {
       effect: 'ui-navigation',
       confirmation,
-      preferredModelTool: 'agent_harness workspace/workspace_actions/workspace_action',
+      preferredModelTool: 'agent_harness workspace/workspace_actions/workspace_action/run_workspace_action',
       boundary: 'Navigation and discovery commands should be inspected through agent_harness when possible.',
     };
   }
@@ -168,7 +172,7 @@ export function describeCliCommandPolicy(commandName: string): CommandExecutionP
     return {
       effect: root === 'tui' || root === 'onboarding' ? 'ui-navigation' : 'read-only',
       confirmation,
-      preferredModelTool: root === 'onboarding' || root === 'tui' ? 'agent_harness workspace/workspace_actions' : 'agent_harness cli_commands/cli_command',
+      preferredModelTool: root === 'onboarding' || root === 'tui' ? 'agent_harness workspace/workspace_actions/workspace_action/run_workspace_action' : 'agent_harness cli_commands/cli_command',
       boundary: 'Top-level CLI launch, setup, help, version, and completion commands are package entrypoint surfaces; use in-process workspace and slash-command bridges from the model when operating inside the TUI.',
     };
   }
@@ -191,7 +195,7 @@ export function describeCliCommandPolicy(commandName: string): CommandExecutionP
     return {
       effect: 'local-state',
       confirmation,
-      preferredModelTool: root === 'profiles' ? 'agent_harness workspace_actions/run_workspace_action' : 'agent_local_registry',
+      preferredModelTool: root === 'profiles' ? 'agent_harness workspace_actions/workspace_action/run_workspace_action' : 'agent_local_registry',
       boundary: 'Local library/profile/session/bundle CLI commands operate on Agent-local data. Mutations require explicit user intent and should use first-class Agent-local tools where available.',
     };
   }
@@ -385,35 +389,55 @@ function relatedConnectedHostRouteFamilies(capability: Record<string, unknown>):
   });
 }
 
-export function describeConnectedHostCapability(
-  toolRegistry: ToolRegistry,
-  rawQuery: string,
-): Record<string, unknown> | null {
-  const query = normalizeCapabilityQuery(rawQuery);
-  if (!query) return null;
+function describeConnectedHostCapabilityCandidates(
+  entries: readonly { readonly status: 'allowed' | 'blocked'; readonly capability: Record<string, unknown> }[],
+): readonly Record<string, unknown>[] {
+  return entries.slice(0, 8).map((entry) => ({
+    status: entry.status,
+    capabilityId: typeof entry.capability.id === 'string' ? entry.capability.id : '',
+    purpose: typeof entry.capability.purpose === 'string' ? entry.capability.purpose : undefined,
+    reason: typeof entry.capability.reason === 'string' ? entry.capability.reason : undefined,
+  }));
+}
 
-  const allowedCapability = connectedHostCapabilityMap(toolRegistry).find((capability) => recordTextMatches(capability, query));
-  if (allowedCapability) {
+function connectedHostCapabilityDetail(entry: { readonly status: 'allowed' | 'blocked'; readonly capability: Record<string, unknown> }): Record<string, unknown> {
+  if (entry.status === 'allowed') {
     return {
       status: 'allowed',
-      capability: allowedCapability,
-      relatedRouteFamilies: relatedConnectedHostRouteFamilies(allowedCapability),
+      capability: entry.capability,
+      relatedRouteFamilies: relatedConnectedHostRouteFamilies(entry.capability),
       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.',
     };
   }
+  return {
+    status: 'blocked',
+    capability: entry.capability,
+    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.',
+  };
+}
 
-  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.',
-    };
-  }
+export function describeConnectedHostCapability(
+  toolRegistry: ToolRegistry,
+  rawQuery: string,
+): ConnectedHostCapabilityResolution | null {
+  const query = normalizeCapabilityQuery(rawQuery);
+  if (!query) return null;
+
+  const entries = [
+    ...connectedHostCapabilityMap(toolRegistry).map((capability) => ({ status: 'allowed' as const, capability })),
+    ...blockedConnectedHostCapabilities().map((capability) => ({ status: 'blocked' as const, capability })),
+  ];
+  const exact = entries.find((entry) => entry.capability.id === rawQuery);
+  if (exact) return { status: 'found', detail: connectedHostCapabilityDetail(exact) };
+  const insensitive = entries.find((entry) => typeof entry.capability.id === 'string' && entry.capability.id.toLowerCase() === query);
+  if (insensitive) return { status: 'found', detail: connectedHostCapabilityDetail(insensitive) };
+  const searched = entries.filter((entry) => recordTextMatches(entry.capability, query));
+  if (searched.length === 1) return { status: 'found', detail: connectedHostCapabilityDetail(searched[0]!) };
+  if (searched.length > 1) return { status: 'ambiguous', input: rawQuery, candidates: describeConnectedHostCapabilityCandidates(searched) };
 
   return null;
 }

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

@@ -8,6 +8,13 @@ export interface AgentHarnessModelToolCatalogArgs {
   readonly limit?: unknown;
 }
 
+type HarnessModelToolDefinition = ReturnType<ToolRegistry['getToolDefinitions']>[number];
+type ModelToolLookupSource = 'toolName' | 'target' | 'query';
+
+export type HarnessModelToolResolution =
+  | { readonly status: 'found'; readonly tool: Record<string, unknown> }
+  | { readonly status: 'ambiguous'; readonly input: string; readonly candidates: readonly Record<string, unknown>[] };
+
 function readString(value: unknown): string {
   return typeof value === 'string' ? value.trim() : '';
 }
@@ -18,39 +25,78 @@ function readLimit(value: unknown, fallback: number): number {
   return Math.max(1, Math.min(500, Math.trunc(parsed)));
 }
 
+function modelToolSearchText(tool: HarnessModelToolDefinition): string {
+  return [
+    tool.name,
+    tool.description,
+    ...(tool.sideEffects ?? []),
+  ].join('\n').toLowerCase();
+}
+
+function modelToolLookupFromArgs(args: AgentHarnessModelToolCatalogArgs): { readonly source: ModelToolLookupSource; readonly input: string } | null {
+  const toolName = readString(args.toolName);
+  if (toolName) return { source: 'toolName', input: toolName };
+  const target = readString(args.target);
+  if (target) return { source: 'target', input: target };
+  const query = readString(args.query);
+  return query ? { source: 'query', input: query } : null;
+}
+
+function describeModelTool(tool: HarnessModelToolDefinition, options: { readonly includeParameters?: boolean; readonly lookup?: Record<string, unknown> } = {}): Record<string, unknown> {
+  return {
+    name: tool.name,
+    description: tool.description,
+    sideEffects: tool.sideEffects ?? [],
+    concurrency: tool.concurrency ?? 'parallel',
+    supportsProgress: tool.supportsProgress ?? false,
+    supportsStreamingOutput: tool.supportsStreamingOutput ?? false,
+    ...(options.lookup ? { lookup: options.lookup } : {}),
+    ...(options.includeParameters ? { parameters: tool.parameters } : {}),
+  };
+}
+
+function describeModelToolCandidates(tools: readonly HarnessModelToolDefinition[]): readonly Record<string, unknown>[] {
+  return tools.slice(0, 8).map((tool) => ({
+    toolName: tool.name,
+    description: tool.description,
+    sideEffects: tool.sideEffects ?? [],
+  }));
+}
+
 export function listHarnessModelTools(toolRegistry: ToolRegistry, args: AgentHarnessModelToolCatalogArgs): readonly Record<string, unknown>[] {
   const query = readString(args.query).toLowerCase();
   const includeParameters = args.includeParameters === true;
   const limit = readLimit(args.limit, 200);
   return toolRegistry.getToolDefinitions()
-    .filter((tool) => !query || [tool.name, tool.description, ...(tool.sideEffects ?? [])].join('\n').toLowerCase().includes(query))
+    .filter((tool) => !query || modelToolSearchText(tool).includes(query))
     .sort((a, b) => a.name.localeCompare(b.name))
     .slice(0, limit)
-    .map((tool) => ({
-      name: tool.name,
-      description: tool.description,
-      sideEffects: tool.sideEffects ?? [],
-      concurrency: tool.concurrency ?? 'parallel',
-      supportsProgress: tool.supportsProgress ?? false,
-      supportsStreamingOutput: tool.supportsStreamingOutput ?? false,
-      ...(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;
+    .map((tool) => describeModelTool(tool, { includeParameters }));
+}
+
+export function describeHarnessModelTool(toolRegistry: ToolRegistry, args: AgentHarnessModelToolCatalogArgs): HarnessModelToolResolution | null {
+  const lookup = modelToolLookupFromArgs(args);
+  if (!lookup) return null;
+  const tools = toolRegistry.getToolDefinitions().sort((a, b) => a.name.localeCompare(b.name));
+  const normalized = lookup.input.toLowerCase();
+  const exact = tools.find((tool) => tool.name === lookup.input);
+  const found = exact
+    ? { tool: exact, resolvedBy: 'name' }
+    : (() => {
+        const insensitive = tools.find((tool) => tool.name.toLowerCase() === normalized);
+        if (insensitive) return { tool: insensitive, resolvedBy: 'case-insensitive-name' };
+        const searched = tools.filter((tool) => modelToolSearchText(tool).includes(normalized));
+        if (searched.length === 1) return { tool: searched[0]!, resolvedBy: 'search' };
+        if (searched.length > 1) return { candidates: searched };
+        return null;
+      })();
+  if (!found) return null;
+  if ('candidates' in found) return { status: 'ambiguous', input: lookup.input, candidates: describeModelToolCandidates(found.candidates) };
   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.',
+    status: 'found',
+    tool: {
+      ...describeModelTool(found.tool, { includeParameters: true, lookup: { ...lookup, resolvedBy: found.resolvedBy } }),
+      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

@@ -23,7 +23,7 @@ export const AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   query: {
     type: 'string',
-    description: 'Search text for command, CLI mirror, panel, UI surface, keybinding, workspace action, setting, or tool catalogs; also slash-command, CLI mirror, setting, panel, UI surface, or keybinding lookup for single-item modes.',
+    description: 'Search text for slash-command, CLI mirror, panel, UI surface, keybinding, workspace action, model tool, setting, or connected-host capability catalogs; also lookup text for the matching single-item modes.',
   },
   command: {
     type: 'string',
@@ -90,7 +90,7 @@ export const AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   target: {
     type: 'string',
-    description: 'Optional lookup target, such as a model-picker target, top-level CLI mirror/search text, panel id/search text, UI surface id/search text, workspace action id/search text, slash command root or invocation, setting key/search text, keybinding action/search text, model tool name, or connected-host capability id.',
+    description: 'Optional lookup target, such as a model-picker target, top-level CLI mirror/search text, panel id/search text, UI surface id/search text, workspace action id/search text, slash command root or invocation, setting key/search text, keybinding action/search text, model tool name/search text, or connected-host capability id/search text.',
   },
   capabilityId: {
     type: 'string',
@@ -127,10 +127,10 @@ export const AGENT_HARNESS_PARAMETER_PROPERTIES = {
   },
   confirm: {
     type: 'boolean',
-    description: 'Required true for set_setting, reset_setting, run_keybinding, run_command, open_panel, open_ui_surface, and mutating run_workspace_action calls after an explicit user request.',
+    description: 'Required true for set_setting, reset_setting, run_keybinding, run_command, open_panel, open_ui_surface, and executable or mutating run_workspace_action calls after an explicit user request.',
   },
   explicitUserRequest: {
     type: 'string',
-    description: 'Exact user request or faithful short summary authorizing a setting mutation, keybinding action, or harness UI/command invocation.',
+    description: 'Exact user request or faithful short summary authorizing a setting mutation, keybinding change/action, harness UI routing, slash-command invocation, or workspace-action invocation.',
   },
 } as const;

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

@@ -756,18 +756,18 @@ export function createAgentHarnessTool(deps: AgentHarnessToolDeps): Tool {
         }
         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.`);
+          const resolved = describeHarnessModelTool(deps.toolRegistry, args);
+          if (resolved?.status === 'found') return output(resolved.tool);
+          if (resolved?.status === 'ambiguous') return error(`Ambiguous model tool ${resolved.input}. Candidates: ${JSON.stringify(resolved.candidates)}`);
+          return 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.`);
+          const resolved = describeConnectedHostCapability(deps.toolRegistry, query);
+          if (resolved?.status === 'found') return output(resolved.detail);
+          if (resolved?.status === 'ambiguous') return error(`Ambiguous connected-host capability ${resolved.input}. Candidates: ${JSON.stringify(resolved.candidates)}`);
+          return 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}`);

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 = '1.0.21';
+let _version = '1.0.23';
 let _sdkVersion = '0.33.35';
 try {
   const pkg = JSON.parse(readFileSync(join(import.meta.dir, '..', 'package.json'), 'utf-8')) as {