agentlas 1.0.45 → 1.0.47

package/CHANGELOG.md

@@ -1,5 +1,35 @@
 # Changelog
 
+## 1.0.47 — 2026-08-14
+
+Antigravity and the shared runtime contracts now reach the independent
+Terminal surface.
+
+- `agy` is recognized as a first-class runtime in capabilities, detection,
+  resolution, permissions, and the interactive shell.
+- Terminal model and runtime choices use the same runtime contract as Desktop,
+  including honest no-runtime stops and project-scoped execution.
+- Workforce capture, local Core transport, graph commands, and the native host
+  preserve the synchronized Agentlas architecture without copying Desktop-only
+  SaaS state into Terminal.
+
+Verification: the local smoke suite passed 100 cases with 0 failures. The npm
+publication gate remains the authority for whether this tag is visible in the
+registry.
+
+## 1.0.46 — 2026-08-11
+
+Pick from a list instead of retyping a slug.
+
+- `/search` in the shell now shows its results as a list you move through with the
+  arrow keys; Enter installs the one you chose. `/graph` does the same and runs the
+  graph you pick. Escape cancels either.
+- Search results say what the listing actually means for you — "callable without
+  installing" or "install to use" — rather than repeating the server's own enum.
+- Commands now know which surface you are standing on, so the next step they print is
+  one you can actually type there. Inside the shell, `search` ends with `/install <slug>`
+  instead of `agentlas install <slug>`, which the shell would have refused.
+
 ## 1.0.45 — 2026-08-11
 
 The command surface was rebuilt from one catalog, and failures stopped printing JSON.

package/README.md

@@ -9,7 +9,7 @@
  ╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝   ╚══════╝╚═╝  ╚═╝╚══════╝
 ```
 
-**Agentlas Terminal CLI** — Independent AI agent runtime installed via `npm install -g agentlas` and launched with `agentlas`. Run exact installed agents, teams, and parallel sessions directly from your shell without keeping Desktop open. When Desktop is installed, Terminal reads the same local project, agent, and runtime state. Bring your own model — use your existing Claude Code, Codex, or Gemini CLI subscriptions or BYOK API keys.
+**Agentlas Terminal CLI** — Independent AI agent runtime installed via `npm install -g agentlas` and launched with `agentlas`. Run exact installed agents, teams, and parallel sessions directly from your shell without keeping Desktop open. When Desktop is installed, Terminal reads the same local project, agent, and runtime state. Bring your own model — use Antigravity (`agy`), Claude Code, Codex, legacy Gemini CLI, or BYOK API keys.
 
 Use this existing independent Terminal as the command-line runtime: inspect owner-private packages with `agentlas cloud list`, restore one with `agentlas cloud restore <slug>`, or install an eligible public package with `agentlas install <slug>`.
 
@@ -24,10 +24,10 @@ Agent Trust is our product principle: agent packages are treated as portable, ow
 | Category | Requirement |
 | --- | --- |
 | **Node.js** | **Node 22+ recommended.** `package.json` specifies `engines: ">=20"`, but if native optional dependency `better-sqlite3` build fails, the launcher falls back strictly to `node:sqlite` in Node 22+. Node 20 works when `better-sqlite3` native build succeeds. |
-| **Agent CLI** | Requires at least one supported runtime CLI (`claude`, `codex`, or `gemini`) in your `PATH`. Halts honestly with `no_runtime` if none are found (no fake model responses). |
+| **Agent CLI** | Requires at least one supported runtime CLI: `agy` (Antigravity, preferred), `claude`, `codex`, or legacy `gemini` in your `PATH`. Halts honestly with `no_runtime` if none are found (no fake model responses). |
 | **OS** | macOS is verified by the current local release gate. Linux is covered by the public adapter/CI contract. A Windows launcher is provided, but this release does not claim independent end-to-end Windows verification. |
 
-*Note: `kimi`, `grok`, and `cursor-agent` are detected by diagnostics (`doctor`) but not yet executable (`has no v2 streaming driver yet`). Supported active runtimes are `claude-code`, `codex`, and `gemini`.*
+*Note: `kimi`, `grok`, and `cursor-agent` are detected by diagnostics (`doctor`) but not yet executable (`has no v2 streaming driver yet`). Supported active runtimes are `claude-code`, `codex`, `agy` (Antigravity), and legacy `gemini`.*
 
 ## Installation
 
@@ -143,7 +143,7 @@ agentlas netadmin <sub>           # Local network administration (init|status|re
 agentlas version | help
 ```
 
-Common flags across subcommands: `-p|--print`, `--runtime claude-code|codex|gemini`, `--permission read|write|full`.
+Common flags across subcommands: `-p|--print`, `--runtime claude-code|codex|agy|gemini`, `--permission read|write|full`.
 
 ### Typo Guard & Desktop Surface Redirection
 
@@ -183,7 +183,7 @@ Executing `agentlas` with no arguments resolves the current folder to an Agentla
 | `/agents` · `/list` | List installed agents |
 | `/mcp` | List active MCP servers |
 | `/doctor` | Run runtime & database diagnostics |
-| `/runtime <kind>` | Set runtime for new sessions (`claude-code` \| `codex` \| `gemini`) |
+| `/runtime <kind>` | Set runtime for new sessions (`claude-code` \| `codex` \| `agy` (Antigravity) \| legacy `gemini`) |
 | `/permission <level>` | Set permission level for new sessions (`read` \| `write` \| `full`) |
 | `/quit` · `/exit` | Exit REPL |
 
@@ -276,8 +276,8 @@ agentlas doctor      # Checks database, PATH runtimes, active CLI drivers, and c
 agentlas --where     # Outputs JSON diagnostic of launcher, engine, DB paths, driver, and Node version
 ```
 
-- **`no_runtime: no agent CLI found`**: Install `claude`, `codex`, or `gemini` CLI and add to `PATH`. Note that `kimi`/`grok`/`cursor-agent` are detected by `doctor` but do not yet have streaming execution drivers.
-- **`runtime '<kind>' has no v2 streaming driver yet`**: Specified `--runtime` is not supported for active execution. Supported values: `claude-code`, `codex`, `gemini`.
+- **`no_runtime: no agent CLI found`**: Connect Antigravity and put `agy` on `PATH` first, or install `claude`/`codex`; `gemini` remains available as a legacy CLI. Note that `kimi`/`grok`/`cursor-agent` are detected by `doctor` but do not yet have streaming execution drivers.
+- **`runtime '<kind>' has no v2 streaming driver yet`**: Specified `--runtime` is not supported for active execution. Supported values: `claude-code`, `codex`, `agy` (Antigravity), `gemini` (legacy).
 - **`Node vX — Node 22+ (node:sqlite) is required when better-sqlite3 is unavailable`**: `better-sqlite3` native build failed on Node 20/21. Upgrade to Node 22+ or install build tools for native compilation.
 - **`storm`/`context`/`hep` halting due to missing runtime**: Agentlas OS core runtime is missing. Install Agentlas OS or set `HEPHAESTUS_BIN=<path>`.
 - **`'xxx' is not an agentlas command`**: Typo guard intercepted an unrecognized command. Use `agentlas run -p "xxx"` to run it as a prompt.

package/engine/agentlas-capabilities.cjs

@@ -15,6 +15,7 @@ const RUNTIME_CAPS = {
   "claude-code": { code: true, image: false, label: "claude" },
   codex: { code: true, image: true, label: "codex" }, // Imagen
   gemini: { code: true, image: true, label: "gemini" }, // nano-banana
+  agy: { code: true, image: true, label: "antigravity" },
   grok: { code: true, image: true, label: "grok" }, // Grok Imagine (generate_image/generate_video, 구독 키리스)
   anthropic: { code: true, image: false, label: "anthropic" },
   openai: { code: true, image: true, label: "openai" }, // gpt-image
@@ -25,7 +26,7 @@ const RUNTIME_CAPS = {
 
 // NOTE: grok은 CAPS(멀티모달 능력 인지)만 등록 — 터미널 스폰 러너(RUNTIME_BIN)가 아직 없어
 // CLI_KINDS에 넣으면 repl의 which(RUNTIME_BIN[k]) 탐지가 깨진다. 러너 추가 시 함께 확장할 것.
-const CLI_KINDS = ["claude-code", "codex", "gemini"];
+const CLI_KINDS = ["claude-code", "codex", "agy", "gemini"];
 
 function capsFor(spec) {
   return RUNTIME_CAPS[spec] || { code: true, image: false, label: spec || "?" };
@@ -115,7 +116,7 @@ function clearImageJudgments() {
 function autoRuntimeFor(agent, { installedKinds, activeSpec }) {
   if (needsImage(agent)) {
     if (capsFor(activeSpec).image) return activeSpec;
-    for (const k of ["gemini", "codex"]) if ((installedKinds || []).includes(k)) return k;
+    for (const k of ["agy", "gemini", "codex"]) if ((installedKinds || []).includes(k)) return k;
   }
   return activeSpec;
 }

package/engine/agentlas-core-harness.cjs

@@ -17,6 +17,10 @@ const CORE_RUNTIME_MARKERS = [
   ["schemas", "workforce-work-order.schema.json"],
   ["schemas", "workforce-selection.schema.json"],
 ];
+const CONTEXT_MAP_V3_RUNTIME_MARKERS = [
+  ["agentlas_cloud", "project_bootstrap.py"],
+  ["schemas", "context-index-policy.schema.json"],
+];
 
 const PY_BOOTSTRAP =
   "import os, runpy, sys; " +
@@ -116,6 +120,18 @@ function resolveCoreRuntimeRoot(explicitRoot, requiredMarkers = [], options = {}
   return resolveCoreRuntimeRootFromCandidates(runtimeRoots(explicitRoot), requiredMarkers, options);
 }
 
+// Context Map is a versioned Core capability. Every Terminal caller that
+// injects a slice must use the same marker and minimum-version gate as the
+// explicit `agentlas context` command; otherwise a stale runtime can silently
+// supply a pre-v3 map to prompts, memory, or Workforce.
+function resolveContextMapCoreRoot(explicitRoot) {
+  return resolveCoreRuntimeRoot(
+    explicitRoot,
+    CONTEXT_MAP_V3_RUNTIME_MARKERS,
+    { minVersion: CONTEXT_MAP_MIN_CORE_VERSION },
+  );
+}
+
 function pythonCandidates() {
   return [...new Set([
     process.env.HEPHAESTUS_PYTHON,
@@ -262,10 +278,12 @@ module.exports = {
   HARNESS_ID,
   HARNESS_MODE,
   CONTEXT_MAP_MIN_CORE_VERSION,
+  CONTEXT_MAP_V3_RUNTIME_MARKERS,
   PY_BOOTSTRAP,
   readCoreRuntimeVersion,
   resolveCoreRuntimeRootFromCandidates,
   resolveCoreRuntimeRoot,
+  resolveContextMapCoreRoot,
   resolvePython,
   spawnCoreModule,
   parseJsonOutput,

package/engine/agentlas-i18n.cjs

@@ -62,9 +62,9 @@ const STRINGS = {
     "noKey": "No %s API key. Add one in the app (Settings → BYOK), or switch with /runtime.",
     "runtimeSet": "runtime → %s",
     "runtimeNotInstalled": "%s CLI is not installed.",
-    "runtimeUnknown": "Unknown runtime: %s (claude-code|codex|gemini)",
-    "runtimeUnavailable": "No runtime is available. Install a CLI (claude/codex/gemini) or configure an API key/Ollama in the app.",
-    "runtimeUsage": "usage: /runtime claude-code|codex|gemini|anthropic|openai|google|ollama|upstage",
+    "runtimeUnknown": "Unknown runtime: %s (claude-code|codex|agy|gemini)",
+    "runtimeUnavailable": "No runtime is available. Install a CLI (claude/codex/agy; legacy gemini is supported) or configure an API key/Ollama in the app.",
+    "runtimeUsage": "usage: /runtime claude-code|codex|agy|gemini|anthropic|openai|google|ollama|upstage",
     "modelOnlyApi": "/model only applies to BYOK/Ollama (api) runtimes.",
     "modelSet": "model → %s",
     "modelCurrent": "current model: %s",
@@ -166,7 +166,7 @@ const STRINGS = {
     "help.team": "view/assign each agent's LLM (auto-routed by capability)",
     "help.agent": "switch to another agent",
     "help.firms": "list companies / switch to one",
-    "help.runtime": "switch runtime (claude-code|codex|gemini|anthropic|openai|google|ollama|upstage)",
+    "help.runtime": "switch runtime (claude-code|codex|agy|legacy gemini|anthropic|openai|google|ollama|upstage)",
     "help.model": "set the model (claude/codex/gemini alias or BYOK/Ollama id)",
     "help.effort": "set reasoning effort (low|medium|high|max|off|auto)",
     "help.permission": "what it may do (read|write|full)",
@@ -311,9 +311,9 @@ const STRINGS = {
     "noKey": "%s API 키가 없습니다. 앱 설정 → BYOK에서 등록하거나 /runtime으로 전환하세요.",
     "runtimeSet": "런타임 → %s",
     "runtimeNotInstalled": "%s CLI가 설치돼 있지 않습니다.",
-    "runtimeUnknown": "알 수 없는 런타임: %s (claude-code|codex|gemini)",
-    "runtimeUnavailable": "사용 가능한 런타임이 없습니다. CLI(claude/codex/gemini)를 설치하거나 앱에서 API 키/Ollama를 설정하세요.",
-    "runtimeUsage": "사용법: /runtime claude-code|codex|gemini|anthropic|openai|google|ollama|upstage",
+    "runtimeUnknown": "알 수 없는 런타임: %s (claude-code|codex|agy|gemini)",
+    "runtimeUnavailable": "사용 가능한 런타임이 없습니다. CLI(claude/codex/agy, 레거시 gemini 지원)를 설치하거나 앱에서 API 키/Ollama를 설정하세요.",
+    "runtimeUsage": "사용법: /runtime claude-code|codex|agy|gemini|anthropic|openai|google|ollama|upstage",
     "modelOnlyApi": "/model은 BYOK/Ollama(api) 런타임에서만 적용됩니다.",
     "modelSet": "모델 → %s",
     "modelCurrent": "현재 모델: %s",
@@ -414,7 +414,7 @@ const STRINGS = {
     "help.team": "에이전트별 LLM 보기/지정 (능력 기반 자동)",
     "help.agent": "다른 에이전트로 전환",
     "help.firms": "회사 목록 / 전환",
-    "help.runtime": "런타임 전환 (claude-code|codex|gemini|anthropic|openai|google|ollama|upstage)",
+    "help.runtime": "런타임 전환 (claude-code|codex|agy|레거시 gemini|anthropic|openai|google|ollama|upstage)",
     "help.model": "모델 지정 (claude/codex/gemini 별칭 또는 BYOK/Ollama id)",
     "help.effort": "추론 강도 지정 (low|medium|high|max|off|auto)",
     "help.permission": "허용 범위 (read|write|full)",

package/engine/agentlas-input.cjs

@@ -270,7 +270,7 @@ const SLASH_COMMAND_META = [
   { command: "/agent", description: "Switch to another agent", category: "Routing", usage: "/agent <name>", detail: "Switch the current conversation to an installed agent." },
   { command: "/firms", description: "List installed companies", category: "Routing", usage: "/firms", detail: "Show company CEOs available in this terminal." },
   { command: "/firm", description: "Switch to a company CEO", category: "Routing", usage: "/firm <name>", detail: "Switch the current conversation to a company CEO agent." },
-  { command: "/runtime", description: "Switch runtime: claude-code, codex, gemini, BYOK, or Ollama", category: "Settings", usage: "/runtime codex", detail: "Change the engine Agentlas uses for subsequent turns." },
+  { command: "/runtime", description: "Switch runtime: claude-code, codex, agy, legacy gemini, BYOK, or Ollama", category: "Settings", usage: "/runtime agy", detail: "Change the engine Agentlas uses for subsequent turns." },
   { command: "/model", description: "Pin a model or return to auto allocation", category: "Settings", usage: "/model <id|auto>", detail: "An id is an explicit session pin; auto lets the higher-level allocator choose a provider-compatible tier." },
   { command: "/effort", description: "Pin reasoning effort or return to auto", category: "Settings", usage: "/effort low|medium|high|max|off|auto", detail: "A level is an explicit pin; auto lets the higher-level allocator choose per task; off is an explicit no-effort pin." },
   { command: "/permission", description: "Set read/write/full permission", category: "Settings", usage: "/permission full", detail: "No argument shows what read, write, and full mean.", aliases: ["/perm"] },
@@ -306,7 +306,7 @@ const SLASH_COMMAND_META = [
   { command: "/exit", description: "Quit Agentlas", category: "Session", usage: "/exit", detail: "Close the terminal session.", aliases: ["/quit"] },
 ];
 const SLASH_COMMANDS = SLASH_COMMAND_META.flatMap((entry) => [entry.command].concat(entry.aliases || []));
-const RUNTIME_SPECS = ["claude-code", "codex", "gemini", "anthropic", "openai", "google", "ollama", "upstage"];
+const RUNTIME_SPECS = ["claude-code", "codex", "agy", "gemini", "anthropic", "openai", "google", "ollama", "upstage"];
 const PERM_LEVELS = ["read", "write", "full"];
 
 const HELP_KEY_BY_COMMAND = {

package/engine/agentlas-native-host.cjs

@@ -700,6 +700,118 @@ function geminiArgs({ prompt, systemPrompt, permission, model, mcpServers, mcpAl
   ];
 }
 
+function agyPermissionArgs(permission) {
+  const level = permissions.normalize(permission);
+  if (level === "full") return ["--dangerously-skip-permissions"];
+  return [
+    "--mode", level === "write" ? "accept-edits" : "plan",
+    "--sandbox",
+  ];
+}
+
+function agyArgs({ prompt, systemPrompt, permission, model, addDirectories = [] }) {
+  const body = systemPrompt ? `${systemPrompt}\n\n---\n\n${prompt}` : prompt;
+  return [
+    ...(model ? ["--model", model] : []),
+    ...[...new Set(addDirectories.filter(Boolean))].flatMap((dir) => ["--add-dir", dir]),
+    ...agyPermissionArgs(permission),
+    "--output-format", "stream-json",
+    "--print-timeout", "30m",
+    "--prompt", body,
+  ];
+}
+
+const AGY_WINDOWS_ARGV_PROMPT_LIMIT = 6_000;
+
+function agyPromptBootstrap(promptFile) {
+  return `Read the complete Agentlas request from ${JSON.stringify(promptFile)}, follow it exactly, and do not reveal the file path.`;
+}
+
+/**
+ * Windows npm CLI shims pass through cmd.exe's much smaller command-line
+ * ceiling. Move only oversized agy prompts into a private one-shot file and
+ * keep argv limited to a short bootstrap. The caller owns cleanup and must run
+ * it on every process terminal path (close, spawn error, timeout, and abort).
+ */
+function prepareAgyLaunch(request, options = {}) {
+  const body = request.systemPrompt
+    ? `${request.systemPrompt}\n\n---\n\n${request.prompt}`
+    : request.prompt;
+  const platform = options.platform || process.platform;
+  const promptLimit = Number.isFinite(options.promptLimit)
+    ? Math.max(1, Math.trunc(options.promptLimit))
+    : AGY_WINDOWS_ARGV_PROMPT_LIMIT;
+  if (platform !== "win32" || body.length <= promptLimit) {
+    return { args: agyArgs(request), promptFile: null, cleanup: () => {} };
+  }
+
+  let directory = null;
+  try {
+    directory = fs.mkdtempSync(path.join(os.tmpdir(), "agentlas-agy-prompt-"));
+    try { fs.chmodSync(directory, 0o700); } catch { /* Windows/best-effort */ }
+    const promptFile = path.join(directory, "request.txt");
+    fs.writeFileSync(promptFile, body, { encoding: "utf8", mode: 0o600, flag: "wx" });
+    try { fs.chmodSync(promptFile, 0o600); } catch { /* Windows/best-effort */ }
+    let cleaned = false;
+    return {
+      args: agyArgs({
+        ...request,
+        systemPrompt: "",
+        prompt: agyPromptBootstrap(promptFile),
+        addDirectories: [directory, ...(request.addDirectories || [])],
+      }),
+      promptFile,
+      cleanup: () => {
+        if (cleaned) return;
+        cleaned = true;
+        try { fs.rmSync(directory, { recursive: true, force: true }); } catch { /* OS temp cleanup fallback */ }
+      },
+    };
+  } catch (error) {
+    if (directory) {
+      try { fs.rmSync(directory, { recursive: true, force: true }); } catch { /* best-effort */ }
+    }
+    throw error;
+  }
+}
+
+function handleAgyLine(line, st, ui) {
+  let obj;
+  try { obj = JSON.parse(line); } catch { return; }
+  if (obj.event === "result") {
+    if (st.geminiStreaming) { ui.streamEnd(); st.geminiStreaming = false; }
+    if (obj.result && typeof obj.result.response === "string") st.finalText = obj.result.response;
+    if (obj.result?.status && !["success", "completed", "done"].includes(String(obj.result.status).toLowerCase())) {
+      st.error = `agy ${obj.result.status}`;
+      st.errorKind = "exit";
+      st.errorSource = "marker";
+    }
+    return;
+  }
+  if (obj.event !== "step_update" || !obj.step_update) {
+    if (obj.event) ui.status(`agy: ${obj.event}`);
+    return;
+  }
+  const step = obj.step_update;
+  if (step.usage) {
+    st.usage = {
+      input_tokens: step.usage.input_tokens,
+      output_tokens: step.usage.output_tokens,
+      ...(step.usage.duration_ms != null ? { duration_ms: step.usage.duration_ms } : {}),
+    };
+  }
+  if (step.step_type === "agent_response") {
+    const delta = typeof step.text_delta === "string" ? step.text_delta : "";
+    if (!delta) return;
+    if (!st.geminiStreaming) { ui.streamStart(); st.geminiStreaming = true; }
+    ui.streamDelta(delta);
+    st.text += delta;
+    return;
+  }
+  if (st.geminiStreaming) { ui.streamEnd(); st.geminiStreaming = false; }
+  ui.status(`agy: ${step.step_type || "step"}${step.state ? ` (${step.state})` : ""}`);
+}
+
 // gemini 툴명 → 친숙한 표시명 (claude/codex 표기와 통일)
 const GEMINI_TOOL_NAMES = {
   run_shell_command: "Bash",
@@ -829,6 +941,7 @@ function runNativeTurn(req) {
   let args;
   let lineHandler;
   let plainStream = false;
+  let launchCleanup = () => {};
   try {
     if (kind === "claude-code") {
       args = claudeArgs(launchReq);
@@ -840,17 +953,10 @@ function runNativeTurn(req) {
       args = geminiArgs(launchReq);
       lineHandler = (l) => handleGeminiLine(l, st, ui);
     } else if (kind === "agy") {
-      /*
-       * Antigravity CLI — stream-json이 없다(실측 1.1.10). 평문 stdout을 그대로 텍스트로.
-       * ★--prompt는 값 플래그가 아니라 --print의 별칭이다(실측: 프롬프트가 조용히 유실됐던
-       * 사고) — 프롬프트는 반드시 위치 인자로 넘긴다. 시스템 프롬프트는 본문에 앞세운다.
-       */
-      const agyPrompt = launchReq.systemPrompt
-        ? `${launchReq.systemPrompt}\n\n---\n\n${launchReq.prompt}`
-        : launchReq.prompt;
-      args = ["--print", agyPrompt, ...(launchReq.model ? ["--model", launchReq.model] : [])];
-      plainStream = true;
-      lineHandler = null;
+      const prepared = prepareAgyLaunch(launchReq);
+      args = prepared.args;
+      launchCleanup = prepared.cleanup;
+      lineHandler = (l) => handleAgyLine(l, st, ui);
     } else {
       return Promise.resolve({ text: "", session: st.session, error: `unknown runtime: ${kind}`, errorKind: "unsupported", errorSource: "marker" });
     }
@@ -885,6 +991,7 @@ function runNativeTurn(req) {
         try { req.onSpawn(child); } catch { /* observer 실패가 턴을 죽이면 안 됨 */ }
       }
     } catch (e) {
+      launchCleanup();
       ui.error(uiText(ui, "runtime.failed", kind, e.message));
       return resolve({ text: "", session: st.session, error: e.message });
     }
@@ -911,6 +1018,7 @@ function runNativeTurn(req) {
       removeLineReader();
       child.stderr?.removeListener("data", onStderr);
       if (req.signal) req.signal.removeEventListener?.("abort", onAbort);
+      launchCleanup();
     };
     const finish = (result) => {
       if (settled) return;
@@ -1212,6 +1320,11 @@ module.exports = {
   codexPermissionArgs,
   geminiArgs,
   geminiPermissionArgs,
+  agyArgs,
+  agyPermissionArgs,
+  agyPromptBootstrap,
+  prepareAgyLaunch,
+  handleAgyLine,
   claudeMcpIsolationArgs,
   geminiMcpIsolationArgs,
   prepareCodexRuntimeEnv,

package/engine/agentlas-onboard.cjs

@@ -133,11 +133,12 @@ async function runOnboard({ ui, rl, helpers, persist }) {
   // Step 2 — default runtime
   ui.line("");
   printIndented(ui.t("wiz.runtimeQ"), c.bold);
-  const cliKinds = ["claude-code", "codex", "gemini"];
+  const cliKinds = ["claude-code", "codex", "agy", "gemini"];
   const rtOpts = [{ value: "auto", label: ui.t("wiz.runtimeAuto") }];
   for (const k of cliKinds) {
     const has = !!H.which(H.RUNTIME_BIN[k]);
-    rtOpts.push({ value: k, label: `${k}  (${has ? ui.t("wiz.runtimeInstalled") : ui.t("wiz.runtimeMissing")})` });
+    const runtimeLabel = k === "agy" ? "agy · Antigravity" : k === "gemini" ? "gemini · legacy" : k;
+    rtOpts.push({ value: k, label: `${runtimeLabel}  (${has ? ui.t("wiz.runtimeInstalled") : ui.t("wiz.runtimeMissing")})` });
   }
   rtOpts.forEach((o, i) => optionLine(i + 1, o.label, i === 0));
   const ri = await pickNum(rtOpts.length);
@@ -149,6 +150,7 @@ async function runOnboard({ ui, rl, helpers, persist }) {
     const installHint = {
       "claude-code": "npm i -g @anthropic-ai/claude-code",
       codex: "npm i -g @openai/codex",
+      agy: "Install Antigravity from https://antigravity.google/ and put agy on PATH",
       gemini: "npm i -g @google/gemini-cli",
     }[runtime];
     if (!H.which(H.RUNTIME_BIN[runtime])) {
@@ -156,7 +158,10 @@ async function runOnboard({ ui, rl, helpers, persist }) {
     } else {
       try {
         const { runtimeAuthEvidence } = require("./runtimes/auth-evidence.cjs");
-        if (runtimeAuthEvidence(runtime).status === "none") {
+        // Antigravity and legacy Gemini currently share Google's local OAuth
+        // evidence root, but remain distinct executable/runtime selections.
+        const evidenceKind = runtime === "agy" ? "gemini" : runtime;
+        if (runtimeAuthEvidence(evidenceKind).status === "none") {
           printIndented(ui.t("wiz.runtimeLoginHint", H.RUNTIME_BIN[runtime]), c.dim);
         }
       } catch { /* evidence unavailable — say nothing rather than guess */ }

package/engine/agentlas-permissions.cjs

@@ -9,6 +9,10 @@
 
 const LEVELS = ["read", "write", "full"];
 
+function isLevel(value) {
+  return LEVELS.includes(String(value || "").trim().toLowerCase());
+}
+
 const COPY = {
   en: {
     read: {
@@ -94,4 +98,4 @@ function createCycleController(options = {}) {
   };
 }
 
-module.exports = { LEVELS, normalize, persistent, next, copy, createCycleController };
+module.exports = { LEVELS, isLevel, normalize, persistent, next, copy, createCycleController };