@alan-ai-hq/agent-manager-linux-arm64 0.1.166 → 0.1.167

package/alan-holder.cjs

@@ -22957,7 +22957,7 @@ You are a product UI designer and frontend interaction specialist. When identify
 
 ## Taste Skill (premium frontends)
 
-For any UI or design work, read and follow the \`uiux\` skill in \`.agents/skills/\` before writing UI. Its internal procedures retain the mandatory design graph, design-system audit, reuse, skeleton-loading, and surface-rework gates; its bundled references cover visual redesigns and premium frontends. Sync bundled upstream material with \`scripts/sync-taste-skills.sh\`.
+For any UI or design work, read and follow the \`uiux\` skill in \`.agents/skills/\` before writing UI. Its internal procedures retain the mandatory design-system audit, reuse, skeleton-loading, and surface-rework gates; its bundled references cover visual redesigns and premium frontends. Sync bundled upstream material with \`scripts/sync-taste-skills.sh\`.
 
 ## How to approach the work
 
@@ -24801,7 +24801,7 @@ var init_chunk_AF3IPGDT = __esm({
   }
 });
 
-// ../agent-core/dist/chunk-ZCTKXKYY.js
+// ../agent-core/dist/chunk-WYNUYKKN.js
 function readCapReset(text2) {
   const epoch = EPOCH_RESET.exec(text2);
   if (epoch) return { resetsAt: new Date(Number(epoch[1]) * 1e3).toISOString() };
@@ -24842,7 +24842,8 @@ function prefixStatus(text2) {
   return match ? Number(match[1]) : void 0;
 }
 function errorType(outer, inner) {
-  const type = asString(inner.type) || asString(outer.type);
+  const flatCode = asString(outer.error);
+  const type = asString(inner.type) || asString(outer.type) || (ERROR_CODE_SHAPE.test(flatCode) ? flatCode : "");
   return type && type !== "error" ? type : void 0;
 }
 function readProviderErrorDetail(text2) {
@@ -24927,7 +24928,8 @@ function statusKind(status) {
 }
 function mapProviderApiError(errorCode, apiStatus) {
   if (apiStatus === 403) return "access_denied";
-  if (apiStatus === 402) return "payment_required";
+  if (apiStatus === 402)
+    return GATEWAY_402_KINDS.get(errorCode?.trim().toLowerCase() ?? "") ?? "payment_required";
   if (apiStatus === 401) return "auth_invalid";
   const code = errorCode?.trim().toLowerCase();
   const byCode = code ? CODE_RULES.find((rule) => rule.pattern.test(code))?.kind : void 0;
@@ -24941,8 +24943,8 @@ function classifyProviderApiError(input2) {
   if (fromText && TEXT_REFINES[structured]?.has(fromText.errorKind)) return fromText;
   return specForErrorKind(structured);
 }
-function withPaymentRemedy(classified, message) {
-  if (classified.errorKind !== "payment_required") return classified;
+function withPaymentRemedy(classified, message, status) {
+  if (classified.errorKind !== "payment_required" && status !== 402) return classified;
   const remedy = message.replace(STATUS_LEAD, "").trim();
   return remedy ? { ...classified, message: remedy.slice(0, 300) } : classified;
 }
@@ -24955,7 +24957,7 @@ function classifyProviderError(text2, hints = {}) {
     ...status === void 0 ? {} : { status },
     text: detail.message
   }) ?? classifyProviderTerminalText(text2);
-  if (classified) return withPaymentRemedy(classified, detail.message);
+  if (classified) return withPaymentRemedy(classified, detail.message, status);
   const message = detail.message.slice(0, 200);
   return message ? { message, errorKind: "unknown_cli_error", recoveryClass: "unknown" } : specForErrorKind("unknown_cli_error");
 }
@@ -25007,9 +25009,9 @@ function createCliProblem(observed, options) {
     ...classified.resetsAt ? { resetsAt: classified.resetsAt } : {}
   });
 }
-var import_crypto, EPOCH_RESET, WORDED_RESET, CODEX_RESET, ERROR_SPECS, AGENT_ERROR_KINDS, AGENT_SIGN_IN_BY_HARNESS, STATUS_PREFIX, TEXT_RULES, CODEX_TIMEOUT_MESSAGE, CODEX_EXPIRED_MESSAGE, COMMAND_NOT_FOUND, CODE_RULES, TEXT_REFINES, STATUS_LEAD, CLI_PROBLEM_CODE_BY_ERROR_KIND, KEY_REJECTION_KINDS;
-var init_chunk_ZCTKXKYY = __esm({
-  "../agent-core/dist/chunk-ZCTKXKYY.js"() {
+var import_crypto, EPOCH_RESET, WORDED_RESET, CODEX_RESET, ERROR_SPECS, AGENT_ERROR_KINDS, AGENT_SIGN_IN_BY_HARNESS, STATUS_PREFIX, ERROR_CODE_SHAPE, TEXT_RULES, CODEX_TIMEOUT_MESSAGE, CODEX_EXPIRED_MESSAGE, COMMAND_NOT_FOUND, CODE_RULES, GATEWAY_402_KINDS, TEXT_REFINES, STATUS_LEAD, CLI_PROBLEM_CODE_BY_ERROR_KIND, KEY_REJECTION_KINDS;
+var init_chunk_WYNUYKKN = __esm({
+  "../agent-core/dist/chunk-WYNUYKKN.js"() {
     "use strict";
     init_chunk_YXWJW7I5();
     import_crypto = require("crypto");
@@ -25050,6 +25052,10 @@ var init_chunk_ZCTKXKYY = __esm({
         message: "The account behind this model has no active plan or credits. Ask an admin to check billing, or switch to a model from your own provider, then retry.",
         recoveryClass: "user_fixable"
       },
+      managed_models_paused: {
+        message: "Alan-managed models are paused by Alan. Switch to a model from your own provider to keep working.",
+        recoveryClass: "user_fixable"
+      },
       quota_exceeded: {
         message: "API quota exceeded. Wait for it to reset or check your billing, then retry.",
         recoveryClass: "user_fixable"
@@ -25136,6 +25142,7 @@ var init_chunk_ZCTKXKYY = __esm({
       ["command_code_cli", { name: "Command Code" }]
     ]);
     STATUS_PREFIX = /\b(?:api error|status|http)[:\s]+(\d{3})\b/i;
+    ERROR_CODE_SHAPE = /^[a-z][a-z0-9_]*$/;
     TEXT_RULES = [
       { kind: "auth_expired", pattern: /\bcodex cli connection expired\b|\breconnect openai codex\b/ },
       { kind: "provider_timeout", pattern: /\bcodex connection to openai timed out\b/ },
@@ -25163,6 +25170,7 @@ var init_chunk_ZCTKXKYY = __esm({
         kind: "quota_exceeded",
         pattern: /\bcredit balance is too low\b|\binsufficient_quota\b/
       },
+      { kind: "managed_models_paused", pattern: /\balan-managed models are paused\b/ },
       { kind: "subscription_required", pattern: /creditserror|\bno payment method\b/ },
       { kind: "model_mismatch", pattern: /datapolicyerror|\brequires explicit opt in\b/ },
       // A cancelled turn can leave history the provider refuses on every later request: empty
@@ -25233,11 +25241,16 @@ var init_chunk_ZCTKXKYY = __esm({
         kind: "context_length"
       }
     ];
+    GATEWAY_402_KINDS = /* @__PURE__ */ new Map([
+      ["quota_exceeded", "quota_exceeded"],
+      ["managed_models_paused", "managed_models_paused"]
+    ]);
     TEXT_REFINES = {
       rate_limited: /* @__PURE__ */ new Set(["usage_limit", "quota_exceeded"]),
+      payment_required: /* @__PURE__ */ new Set(["usage_limit", "managed_models_paused"]),
       auth_invalid: /* @__PURE__ */ new Set(["auth_expired", "not_logged_in", "not_authenticated"])
     };
-    STATUS_LEAD = /^(?:api error|status|http)[:\s]+\d{3}\b[:\s]*/i;
+    STATUS_LEAD = /^(?:(?:api error|status|http)[:\s]+\d{3}\b|payment required:)[:\s]*/i;
     CLI_PROBLEM_CODE_BY_ERROR_KIND = {
       model_mismatch: "cli.model.unavailable",
       auth_invalid: "cli.auth.invalid",
@@ -25247,6 +25260,7 @@ var init_chunk_ZCTKXKYY = __esm({
       auth_expired: "cli.auth.expired",
       subscription_required: "cli.entitlement.required",
       payment_required: "cli.entitlement.required",
+      managed_models_paused: "cli.model.unavailable",
       quota_exceeded: "cli.quota_exceeded",
       usage_limit: "cli.quota_exceeded",
       context_length: "cli.context_exhausted",
@@ -26096,7 +26110,7 @@ var init_chunk_KVTSAS2T = __esm({
   }
 });
 
-// ../agent-core/dist/chunk-4LDW3FJB.js
+// ../agent-core/dist/chunk-U4RQE7JS.js
 function detectImageMimeType(buffer) {
   if (buffer.length >= 8 && buffer.subarray(0, 8).equals(PNG_SIGNATURE)) return "image/png";
   if (buffer.length >= 3 && buffer[0] === 255 && buffer[1] === 216 && buffer[2] === 255) {
@@ -26537,11 +26551,11 @@ function silentStartError(name, timeoutMs) {
   };
 }
 var import_crypto4, import_fs5, import_path4, PNG_SIGNATURE, IMAGE_MIME_BY_EXT, VIDEO_MIME_BY_EXT, IMAGE_EXTENSIONS, VIDEO_EXTENSIONS, MAX_IMAGE_BYTES, MAX_VIDEO_BYTES, MAX_TURN_MEDIA_DATA_CHARS, MTIME_SLACK_MS, AGENT_BROWSER_MENTION, AGENT_BROWSER_CAPTURE_COMMAND, LocalMediaReader, SessionOpenRefusal, JsonRpcError, ACP_PROTOCOL_VERSION, ACP_ERROR, STDERR_TAIL_LINES, RESULT_EXIT_GRACE_MS, PerTurnSession;
-var init_chunk_4LDW3FJB = __esm({
-  "../agent-core/dist/chunk-4LDW3FJB.js"() {
+var init_chunk_U4RQE7JS = __esm({
+  "../agent-core/dist/chunk-U4RQE7JS.js"() {
     "use strict";
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
     init_chunk_YXWJW7I5();
     import_crypto4 = require("crypto");
@@ -26923,15 +26937,15 @@ var init_chunk_4LDW3FJB = __esm({
 var init_dist = __esm({
   "../agent-core/dist/index.js"() {
     "use strict";
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
     init_chunk_YXWJW7I5();
   }
 });
 
-// ../agent-core/dist/chunk-DLVRNIY5.js
+// ../agent-core/dist/chunk-7FJ7QKFN.js
 function repositories(input2, context) {
   const problems = new Map(input2.problems.map((problem) => [problem.path, problem]));
   const listed = context?.repositories ?? [];
@@ -27538,24 +27552,51 @@ function cloudExecutionSection(spec) {
       "If a required delivery step is blocked, complete remaining independent work and report the precise blocker and what remains unfinished. Never describe local-only work as fully delivered."
     );
   }
-  const skills = spec.promptContext?.availableSkills ?? [];
   lines.push(
     "## Installed skills",
     "Use a matching installed skill when it helps the request. Read its SKILL.md before acting; the index is discovery metadata, not instructions. Follow repository instructions and project skills within the cloud workflow boundaries above."
   );
-  if (skills.length === 0) {
+  const skills = spec.promptContext?.availableSkills;
+  if (skills === void 0) {
+    lines.push(
+      "No installed skill inventory was supplied. Inspect the provider's skill index; do not assume a named package is installed."
+    );
+  } else if (skills.length === 0) {
     lines.push(
-      skills.length === 0 && spec.promptContext?.availableSkills !== void 0 ? "No verified installed packages were found. Do not assume a named skill is available." : "No installed skill inventory was supplied. Inspect the provider's skill index; do not assume a named package is installed."
+      "No other installed skills were found. Do not assume a named skill is available unless your skill index lists it."
     );
   } else {
-    for (const skill of skills) {
-      lines.push(
-        `- ${JSON.stringify(skill.name)}: ${JSON.stringify(skill.description)} \u2014 ${JSON.stringify(`${skill.packageDirectory}/SKILL.md`)}`
-      );
-    }
+    lines.push(...installedSkillLines(skills));
   }
   return lines.join("\n");
 }
+function truncate2(text2, max) {
+  return text2.length > max ? `${text2.slice(0, max - 1)}\u2026` : text2;
+}
+function byListingPriority(left, right) {
+  const platform = Number(right.name.startsWith("alan-")) - Number(left.name.startsWith("alan-"));
+  return platform !== 0 ? platform : left.name.localeCompare(right.name);
+}
+function overflowLine(omitted) {
+  const folders = [...new Set(omitted.map((skill) => (0, import_path5.dirname)(skill.packageDirectory)))].sort();
+  return `${omitted.length} more installed skills are not listed. Each is a folder holding a SKILL.md under ${folders.map((folder) => JSON.stringify(folder)).join(" or ")}; look there before assuming a named skill is unavailable.`;
+}
+function installedSkillLines(skills) {
+  const ordered = [...skills].sort(byListingPriority);
+  const lines = [];
+  let used = 0;
+  for (const [index, skill] of ordered.entries()) {
+    const description = truncate2(skill.description, INSTALLED_SKILL_DESCRIPTION_MAX_CHARS);
+    const line = `- ${JSON.stringify(skill.name)}: ${JSON.stringify(description)} \u2014 ${JSON.stringify(`${skill.packageDirectory}/SKILL.md`)}`;
+    if (used + line.length + 1 > INSTALLED_SKILLS_MAX_CHARS) {
+      lines.push(overflowLine(ordered.slice(index)));
+      break;
+    }
+    lines.push(line);
+    used += line.length + 1;
+  }
+  return lines;
+}
 function promptParts(input2) {
   const { spec } = input2;
   const overlay = teamOverlay(spec);
@@ -27633,12 +27674,13 @@ function buildTurnText(input2) {
 ${body}` : body;
   return spec.mode === "plan" ? planModePrefix(prefixed) : prefixed;
 }
-var startCommandStateSchema, repositorySnapshotSchema, environmentSnapshotSchema, agentContextSnapshotSchema, BRANCH_REASONS, SLACK_SURFACE_INSTRUCTIONS, PLAIN_SCALAR, COMMAND_PREVIEW_CHARS, MAX_PARSED_ATTACHMENTS, MAX_PARSED_ATTACHMENT_CHARS, MAX_METADATA_CHARS, UNAVAILABLE, READ_ONLY_MODES, AGENT_MODES;
-var init_chunk_DLVRNIY5 = __esm({
-  "../agent-core/dist/chunk-DLVRNIY5.js"() {
+var import_path5, startCommandStateSchema, repositorySnapshotSchema, environmentSnapshotSchema, agentContextSnapshotSchema, BRANCH_REASONS, SLACK_SURFACE_INSTRUCTIONS, PLAIN_SCALAR, COMMAND_PREVIEW_CHARS, MAX_PARSED_ATTACHMENTS, MAX_PARSED_ATTACHMENT_CHARS, MAX_METADATA_CHARS, UNAVAILABLE, READ_ONLY_MODES, AGENT_MODES, INSTALLED_SKILLS_MAX_CHARS, INSTALLED_SKILL_DESCRIPTION_MAX_CHARS;
+var init_chunk_7FJ7QKFN = __esm({
+  "../agent-core/dist/chunk-7FJ7QKFN.js"() {
     "use strict";
     init_runtime_v2();
     init_zod();
+    import_path5 = require("path");
     init_agent2();
     startCommandStateSchema = external_exports.discriminatedUnion("state", [
       external_exports.object({ state: external_exports.literal("not_configured") }),
@@ -27738,6 +27780,8 @@ var init_chunk_DLVRNIY5 = __esm({
       "ask",
       "review"
     ]);
+    INSTALLED_SKILLS_MAX_CHARS = 8e3;
+    INSTALLED_SKILL_DESCRIPTION_MAX_CHARS = 200;
   }
 });
 
@@ -27831,8 +27875,8 @@ function canonicalizeManagedMcpToolName(toolName) {
   return flattened ? `mcp__${MANAGED_MCP_SERVER_NAME}__${flattened[1]}` : toolName;
 }
 async function writeSecretFile(name, contents) {
-  const dir = await (0, import_promises13.mkdtemp)((0, import_path5.join)((0, import_os2.tmpdir)(), "alan-mcp-"));
-  const path = (0, import_path5.join)(dir, name);
+  const dir = await (0, import_promises13.mkdtemp)((0, import_path6.join)((0, import_os2.tmpdir)(), "alan-mcp-"));
+  const path = (0, import_path6.join)(dir, name);
   const remove = async () => {
     await (0, import_promises13.rm)(dir, { recursive: true, force: true });
   };
@@ -27844,7 +27888,7 @@ async function writeSecretFile(name, contents) {
   }
   return { path, remove, [Symbol.asyncDispose]: remove };
 }
-var import_crypto5, import_crypto6, import_promises13, import_os2, import_path5, OPENCODE_CODE_MODE_ENV, OPENCODE_CODE_MODE_TOOL, CODE_MODE_CALLS_META, MANAGED_MCP_SERVER_NAME, RUN_SCOPED_SERVER, NAMESPACED_RUN_TOOL, FLATTENED_RUN_TOOL;
+var import_crypto5, import_crypto6, import_promises13, import_os2, import_path6, OPENCODE_CODE_MODE_ENV, OPENCODE_CODE_MODE_TOOL, CODE_MODE_CALLS_META, MANAGED_MCP_SERVER_NAME, RUN_SCOPED_SERVER, NAMESPACED_RUN_TOOL, FLATTENED_RUN_TOOL;
 var init_chunk_OSECDZA5 = __esm({
   "../agent-core/dist/chunk-OSECDZA5.js"() {
     "use strict";
@@ -27855,7 +27899,7 @@ var init_chunk_OSECDZA5 = __esm({
     init_runtime_v2();
     import_promises13 = require("fs/promises");
     import_os2 = require("os");
-    import_path5 = require("path");
+    import_path6 = require("path");
     OPENCODE_CODE_MODE_ENV = "OPENCODE_EXPERIMENTAL_CODE_MODE";
     OPENCODE_CODE_MODE_TOOL = "execute";
     CODE_MODE_CALLS_META = "alanToolCalls";
@@ -28101,16 +28145,16 @@ function classifyAcpError(error62) {
   return classifyAcpText(acpErrorText(error62));
 }
 function within(root, path) {
-  const rel = (0, import_path6.relative)(root, path);
-  return rel === "" || !rel.startsWith(`..${import_path6.sep}`) && rel !== ".." && !(0, import_path6.isAbsolute)(rel);
+  const rel = (0, import_path7.relative)(root, path);
+  return rel === "" || !rel.startsWith(`..${import_path7.sep}`) && rel !== ".." && !(0, import_path7.isAbsolute)(rel);
 }
 async function resolveReal(path) {
   try {
     return await (0, import_promises14.realpath)(path);
   } catch {
-    const parent = (0, import_path6.dirname)(path);
+    const parent = (0, import_path7.dirname)(path);
     if (parent === path) return path;
-    return (0, import_path6.join)(await resolveReal(parent), (0, import_path6.basename)(path));
+    return (0, import_path7.join)(await resolveReal(parent), (0, import_path7.basename)(path));
   }
 }
 function sliceLines(text2, params) {
@@ -28125,7 +28169,7 @@ function createWorkspaceFs(roots, writable) {
   const realRoots = Promise.all(roots.map((root) => resolveReal(root)));
   const confined = async (params) => {
     const path = asString(params.path);
-    if (!(0, import_path6.isAbsolute)(path)) throw new FsDenied(`fs path must be absolute: ${path || "(empty)"}`);
+    if (!(0, import_path7.isAbsolute)(path)) throw new FsDenied(`fs path must be absolute: ${path || "(empty)"}`);
     const real = await resolveReal(path);
     if (!(await realRoots).some((root) => within(root, real))) {
       throw new FsDenied(`${path} is outside the session's workspace`);
@@ -28754,19 +28798,19 @@ async function acpTurnInput(run, context) {
     ...encoded.length ? { images: encoded, imagePaths: images.map((image) => image.path) } : {}
   };
 }
-var import_promises14, import_path6, import_crypto7, import_promises15, CURSOR_ASK_QUESTION, copilotAcpProfile, cursorAcpProfile, MODEL_REJECTED, MAX_READ_BYTES, FsDenied, ENV_REFERENCE, AcpBackgroundTasks, CURSOR_CREATE_PLAN, STATUSES, READ_KINDS, ALLOW_KINDS, REJECT_KINDS, CANCELLED_PERMISSION, STOP_REASONS, CHUNKS, ECHOES, AcpTurn, STDERR_TAIL_LINES2, MAX_BETWEEN_UPDATES, AcpSession, DEFAULTS, CLIENT_INFO, TASK_BACKGROUNDED, TASK_COMPLETED, SESSION_NOTIFICATION, KILLED_STATUSES, SUCCESS_STATUSES, SUBAGENT_ID, grokTaskDialect, grokAcpProfile, kimiAcpProfile, ACP_PROFILES, ACP_MODES;
+var import_promises14, import_path7, import_crypto7, import_promises15, CURSOR_ASK_QUESTION, copilotAcpProfile, cursorAcpProfile, MODEL_REJECTED, MAX_READ_BYTES, FsDenied, ENV_REFERENCE, AcpBackgroundTasks, CURSOR_CREATE_PLAN, STATUSES, READ_KINDS, ALLOW_KINDS, REJECT_KINDS, CANCELLED_PERMISSION, STOP_REASONS, CHUNKS, ECHOES, AcpTurn, STDERR_TAIL_LINES2, MAX_BETWEEN_UPDATES, AcpSession, DEFAULTS, CLIENT_INFO, TASK_BACKGROUNDED, TASK_COMPLETED, SESSION_NOTIFICATION, KILLED_STATUSES, SUCCESS_STATUSES, SUBAGENT_ID, grokTaskDialect, grokAcpProfile, kimiAcpProfile, ACP_PROFILES, ACP_MODES;
 var init_acp2 = __esm({
   "../agent-core/dist/providers/acp.js"() {
     "use strict";
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     import_promises14 = require("fs/promises");
-    import_path6 = require("path");
+    import_path7 = require("path");
     init_effort();
     init_acp();
     import_crypto7 = require("crypto");
@@ -29637,7 +29681,7 @@ var init_acp3 = __esm({
 var init_classify = __esm({
   "../agent-core/dist/classify.js"() {
     "use strict";
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_YXWJW7I5();
   }
 });
@@ -30352,7 +30396,7 @@ function alanCodeEngineBinary(platform) {
   return platform === "win32" ? "opencode.exe" : "opencode";
 }
 function packagedAlanCodeEnginePath(bundle, platform) {
-  return (0, import_path7.join)((0, import_path7.dirname)(bundle), "..", "engine", alanCodeEngineBinary(platform));
+  return (0, import_path8.join)((0, import_path8.dirname)(bundle), "..", "engine", alanCodeEngineBinary(platform));
 }
 function isRunnableFile(path, platform) {
   try {
@@ -30554,13 +30598,13 @@ export const AlanEnginePlugin = async () => ({
 `;
 }
 function alanCodeEngineRoot(home) {
-  return (0, import_path8.join)(home, ".alan", "alan-code", "engine");
+  return (0, import_path9.join)(home, ".alan", "alan-code", "engine");
 }
 function alanCodeEngineDirectories(root) {
   return {
-    XDG_DATA_HOME: (0, import_path8.join)(root, "share"),
-    XDG_STATE_HOME: (0, import_path8.join)(root, "state"),
-    XDG_CACHE_HOME: (0, import_path8.join)(root, "cache")
+    XDG_DATA_HOME: (0, import_path9.join)(root, "share"),
+    XDG_STATE_HOME: (0, import_path9.join)(root, "state"),
+    XDG_CACHE_HOME: (0, import_path9.join)(root, "cache")
   };
 }
 function bearerToken(authorization) {
@@ -30576,8 +30620,8 @@ function alanCodeEngineEnv(input2) {
   };
 }
 function openCodeGlobalConfigDirectory(env, home) {
-  const configHome = env.XDG_CONFIG_HOME?.trim() || (0, import_path8.join)(home, ".config");
-  return (0, import_path8.join)(configHome, "opencode");
+  const configHome = env.XDG_CONFIG_HOME?.trim() || (0, import_path9.join)(home, ".config");
+  return (0, import_path9.join)(configHome, "opencode");
 }
 function stripJsonc(text2) {
   let out = "";
@@ -30636,7 +30680,7 @@ function parseJsonc(text2) {
 async function inheritedMcpServerNames(configDirectory) {
   const names = /* @__PURE__ */ new Set();
   for (const file2 of ["config.json", "opencode.json", "opencode.jsonc"]) {
-    const text2 = await (0, import_promises16.readFile)((0, import_path8.join)(configDirectory, file2), "utf8").catch(() => null);
+    const text2 = await (0, import_promises16.readFile)((0, import_path9.join)(configDirectory, file2), "utf8").catch(() => null);
     if (text2 === null) continue;
     const parsed = parseJsonc(text2);
     const mcp = parsed !== null && typeof parsed === "object" ? parsed.mcp : void 0;
@@ -30648,7 +30692,7 @@ async function inheritedMcpServerNames(configDirectory) {
 }
 async function writePlugin(directory, apiOrigin) {
   const origin = (0, import_crypto8.createHash)("sha256").update(apiOrigin).digest("hex").slice(0, 12);
-  const target = (0, import_path8.join)(directory, `engine-plugin-v${ALAN_CODE_ENGINE_PLUGIN_VERSION}-${origin}.mjs`);
+  const target = (0, import_path9.join)(directory, `engine-plugin-v${ALAN_CODE_ENGINE_PLUGIN_VERSION}-${origin}.mjs`);
   const temporary = `${target}.${(0, import_crypto8.randomUUID)()}.tmp`;
   await (0, import_promises16.mkdir)(directory, { recursive: true, mode: 448 });
   await (0, import_promises16.writeFile)(temporary, alanCodeEnginePluginSource(apiOrigin), { mode: 384 });
@@ -30661,7 +30705,7 @@ async function prepareAlanCodeProfile(input2) {
     directories.map((directory) => (0, import_promises16.mkdir)(directory, { recursive: true, mode: 448 }))
   );
   const [pluginUrl, models, inheritedMcpServers] = await Promise.all([
-    writePlugin((0, import_path8.join)(input2.engineRoot, "plugin"), input2.access.apiOrigin),
+    writePlugin((0, import_path9.join)(input2.engineRoot, "plugin"), input2.access.apiOrigin),
     (input2.loadModels ?? fetchAlanCodeModels)(input2.access),
     input2.globalConfigDirectory === void 0 ? Promise.resolve([]) : inheritedMcpServerNames(input2.globalConfigDirectory)
   ]);
@@ -30683,7 +30727,7 @@ function alanCodeSystemPrompt(alanSystemPrompt) {
 
 ${instructions}` : ALAN_CODE_TOOL_NAMING_PROMPT;
 }
-var import_http3, import_https, import_fs6, import_path7, import_crypto8, import_promises16, import_path8, import_url, ALAN_CODE_BASELINE_PROMPT, ALAN_CODE_ENGINE_PROVIDER_ID, DEFAULT_CONTEXT_WINDOW, DEFAULT_MAX_OUTPUT_TOKENS, ALAN_CODE_API_KEY_ENV, ALAN_CODE_CONVERSATION_ID_ENV, ALAN_CODE_PROXY_PATH, ALAN_CODE_WEBSEARCH_PATH, ALAN_CODE_CATALOG_PATH, ALAN_CODE_CHUNK_TIMEOUT_MS, CATALOG_TIMEOUT_MS, MAX_CATALOG_BYTES, ACTIVATION_WAIT_MS, ACTIVATION_POLL_MS, CatalogResponseError, ALAN_CODE_ENGINE_PATH_ENV, ALAN_CODE_ENGINE_COMMAND, ALAN_CODE_ENGINE_NAME, WINDOWS_RUNNABLE_EXTENSION, ALAN_CODE_ENGINE_PLUGIN_VERSION, ALAN_CODE_TOOL_NAMING_PROMPT;
+var import_http3, import_https, import_fs6, import_path8, import_crypto8, import_promises16, import_path9, import_url, ALAN_CODE_BASELINE_PROMPT, ALAN_CODE_ENGINE_PROVIDER_ID, DEFAULT_CONTEXT_WINDOW, DEFAULT_MAX_OUTPUT_TOKENS, ALAN_CODE_API_KEY_ENV, ALAN_CODE_CONVERSATION_ID_ENV, ALAN_CODE_PROXY_PATH, ALAN_CODE_WEBSEARCH_PATH, ALAN_CODE_CATALOG_PATH, ALAN_CODE_CHUNK_TIMEOUT_MS, CATALOG_TIMEOUT_MS, MAX_CATALOG_BYTES, ACTIVATION_WAIT_MS, ACTIVATION_POLL_MS, CatalogResponseError, ALAN_CODE_ENGINE_PATH_ENV, ALAN_CODE_ENGINE_COMMAND, ALAN_CODE_ENGINE_NAME, WINDOWS_RUNNABLE_EXTENSION, ALAN_CODE_ENGINE_PLUGIN_VERSION, ALAN_CODE_TOOL_NAMING_PROMPT;
 var init_alan_code = __esm({
   "../agent-core/dist/providers/alan-code.js"() {
     "use strict";
@@ -30695,11 +30739,11 @@ var init_alan_code = __esm({
     init_runtime_v2();
     init_models();
     import_fs6 = require("fs");
-    import_path7 = require("path");
+    import_path8 = require("path");
     init_runtime_v2();
     import_crypto8 = require("crypto");
     import_promises16 = require("fs/promises");
-    import_path8 = require("path");
+    import_path9 = require("path");
     import_url = require("url");
     ALAN_CODE_BASELINE_PROMPT = "You are alan-code, an interactive CLI coding agent that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nDo not invent URLs. Use verified URLs or ones supplied by the user or project.\n\nIf the user asks for help or wants to give feedback, inform them of the following:\n- `--harness-help` / harness help: learn how to run alan-code\n- For product feedback or bugs, report through the Alan / Supatest issue channels used by this repository\n\nWhen the user directly asks about alan-code capabilities (for example \"can alan-code\u2026\", \"does the harness have\u2026\") or asks in second person about your abilities, answer from the tools and instructions available in this session. If a docs/fetch tool is available and project docs URLs are known, use them; otherwise inspect local README / AGENTS.md rather than inventing product claims.\n\n# Personality\n\nYour default personality and tone is concise, direct, and friendly. You communicate efficiently, always keeping the user clearly informed about ongoing actions without unnecessary detail. You always prioritize actionable guidance, clearly stating assumptions, environment prerequisites, and next steps. Unless explicitly asked, you avoid excessively verbose explanations about your work.\n\n# Tone and style\n\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, so the user understands what you are doing (especially important for commands that change their system).\nRemember that your output will be displayed on a command line interface. Your responses can use GitHub-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, do not lecture about why. Offer helpful alternatives if possible; otherwise keep the response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid emojis in all communication unless asked.\nIMPORTANT: Minimize output tokens while staying helpful, correct, and accurate. Only address the specific query or task. Avoid tangential information unless it is critical to completing the request. If you can answer in 1-3 sentences or a short paragraph, do that.\nAnswer the user's question directly. One-word answers are best when they suffice. Avoid text before/after your response such as \"The answer is <answer>.\", \"Here is the content of the file\u2026\", \"Based on the information provided\u2026\", or \"Here is what I will do next\u2026\". Examples of appropriate verbosity:\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use tools to inspect the project, then answer]\nnpm run dev\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [lists files and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [searches for similar tests, reads relevant files concurrently, edits/writes tests]\n</example>\n\n# Responsiveness\n\n## Preamble messages\n\nBefore making tool calls, send a brief preamble to the user explaining what you're about to do. When sending preamble messages, follow these principles and examples:\n\n- **Logically group related actions**: if you're about to run several related commands, describe them together in one preamble rather than sending a separate note for each.\n- **Keep it concise**: be no more than 1-2 sentences, focused on immediate, tangible next steps. (8\u201312 words for quick updates).\n- **Build on prior context**: if this is not your first tool call, use the preamble message to connect the dots with what's been done so far and create a sense of momentum and clarity for the user to understand your next actions.\n- **Keep your tone light, friendly and curious**: add small touches of personality in preambles feel collaborative and engaging.\n- **Exception**: Avoid adding a preamble for every trivial read (e.g., `cat` a single file) unless it's part of a larger grouped action.\n\nExamples:\n\n- \"I've explored the repo; now checking the API route definitions.\"\n- \"Next, I'll patch the config and update the related tests.\"\n- \"I'm about to scaffold the CLI commands and helper functions.\"\n- \"Ok cool, so I've wrapped my head around the repo. Now digging into the API routes.\"\n- \"Config's looking tidy. Next up is patching helpers to keep things in sync.\"\n- \"Finished poking at the DB gateway. I will now chase down error handling.\"\n- \"Alright, build pipeline order is interesting. Checking how it reports failures.\"\n- \"Spotted a clever caching util; now hunting where it gets used.\"\n\n# Planning\n\nIf a planning tool is available, use it when it helps track complex work. Keep the plan brief and update it as work progresses.\n\nNote that plans are not for padding out simple work with filler steps or stating the obvious. The content of your plan should not involve doing anything that you aren't capable of doing (i.e. don't try to test things that you can't test). Do not use plans for simple or single-step queries that you can just do or answer immediately.\n\nWhen a planning tool displays the plan, summarize only what changed or what comes next.\n\nKeep any active plan aligned with the work completed and remaining.\n\nUse a plan when:\n\n- The task is non-trivial and will require multiple actions over a long time horizon.\n- There are logical phases or dependencies where sequencing matters.\n- The work has ambiguity that benefits from outlining high-level goals.\n- You want intermediate checkpoints for feedback and validation.\n- When the user asked you to do more than one thing in a single prompt\n- The user has asked you to use the plan tool (aka \"TODOs\")\n- You generate additional steps while working, and plan to do them before yielding to the user\n\n## Examples\n\n**High-quality plans**\n\nExample 1:\n\n1. Add CLI entry with file args\n2. Parse Markdown via CommonMark library\n3. Apply semantic HTML template\n4. Handle code blocks, images, links\n5. Add error handling for invalid files\n\nExample 2:\n\n1. Define CSS variables for colors\n2. Add toggle with localStorage state\n3. Refactor components to use variables\n4. Verify all views for readability\n5. Add smooth theme-change transition\n\nExample 3:\n\n1. Set up Node.js + WebSocket server\n2. Add join/leave broadcast events\n3. Implement messaging with timestamps\n4. Add usernames + mention highlighting\n5. Persist messages in lightweight DB\n6. Add typing indicators + unread count\n\n**Low-quality plans**\n\nExample 1:\n\n1. Create CLI tool\n2. Add Markdown parser\n3. Convert to HTML\n\nExample 2:\n\n1. Add dark mode toggle\n2. Save preference\n3. Make styles look good\n\nExample 3:\n\n1. Create single-file HTML game\n2. Run quick sanity check\n3. Summarize usage instructions\n\nIf you need to write a plan, only write high quality plans, not low quality ones.\n\n## Plan mode and clarification (harness specifics)\n\n- When the session is in plan mode, inspect without making changes and produce a concrete plan. Outside plan mode, proceed with authorized work and ask for approval only when the action requires it.\n- Prefer the durable plan file path over relying on chat memory after compaction.\n- When requirements are ambiguous, ask a targeted question using an available user-input tool instead of guessing.\n- An execution checklist is not a substitute for a durable plan when the task requires one.\n\n# Task execution\n\nYou are a coding agent. Please keep going until the query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability, using the tools available to you, before coming back to the user. Do NOT guess or make up an answer.\n\nYou MUST adhere to the following criteria when solving queries:\n\n- Working on the repo(s) in the current environment is allowed, even if they are proprietary.\n- Analyzing code for vulnerabilities is allowed.\n- Showing user code and tool call details is allowed.\n- Use the editing tools available in the current host to modify files. Do not assume a particular tool name.\n\nIf completing the user's task requires writing or modifying files, your code and final answer should follow these coding guidelines, though user instructions (i.e. AGENTS.md) may override these guidelines:\n\n- Fix the problem at the root cause rather than applying surface-level patches, when possible.\n- Avoid unneeded complexity in your solution.\n- Do not attempt to fix unrelated bugs or broken tests. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)\n- Update documentation as necessary.\n- Keep changes consistent with the style of the existing codebase. Changes should be minimal and focused on the task.\n- Use `git log` and `git blame` to search the history of the codebase if additional context is required.\n- NEVER add copyright or license headers unless specifically requested.\n- Do not waste tokens by re-reading files after editing them. The tool call will fail if it didn't work. The same goes for making folders, deleting folders, etc.\n- Do not `git commit` your changes or create new git branches unless explicitly requested.\n- Add comments when they explain a non-obvious invariant or reason for a decision.\n- Do not use one-letter variable names unless explicitly requested.\n- NEVER output inline citations like \"\u3010F:README.md\u2020L5-L14\u3011\" in your outputs. The CLI is not able to render these so they will just be broken in the UI. Instead, if you output valid filepaths, users will be able to click on them to open the files in their editor.\n\n# Validating your work\n\nIf the codebase has tests or the ability to build or run, consider using them to verify that your work is complete.\n\nWhen testing, your philosophy should be to start as specific as possible to the code you changed so that you can catch issues efficiently, then make your way to broader tests as you build confidence. If there's no test for the code you changed, and if the adjacent patterns in the codebases show that there's a logical place for you to add a test, you may do so. However, do not add tests to codebases with no tests.\n\nSimilarly, once you're confident in correctness, you can suggest or use formatting commands to ensure that your code is well formatted. If there are issues you can iterate up to 3 times to get formatting right, but if you still can't manage it's better to save the user time and present them a correct solution where you call out the formatting in your final message. If the codebase does not have a formatter configured, do not add one.\n\nFor all of testing, running, building, and formatting, do not attempt to fix unrelated bugs. It is not your responsibility to fix them. (You may mention them to the user in your final message though.)\n\nBe mindful of whether to run validation commands proactively. In the absence of behavioral guidance:\n\n- When running in a non-interactive mode where edits are auto-approved (print/headless, or the `allow edits` permission mode), proactively run tests, lint and do whatever you need to ensure you've completed the task.\n- In plan mode, stay read-only. Otherwise, run focused checks after changes when the host permits them.\n- When working on test-related tasks, such as adding tests, fixing tests, or reproducing a bug to verify behavior, you may proactively run tests regardless of permission mode. Use your judgement to decide whether this is a test-related task.\n\n# Ambition vs. precision\n\nFor tasks that have no prior context (i.e. the user is starting something brand new), you should feel free to be ambitious and demonstrate creativity with your implementation.\n\nIf you're operating in an existing codebase, you should make sure you do exactly what the user asks with surgical precision. Treat the surrounding codebase with respect, and don't overstep (i.e. changing filenames or variables unnecessarily). You should balance being sufficiently ambitious and proactive when completing tasks of this nature.\n\nYou should use judicious initiative to decide on the right level of detail and complexity to deliver based on the user's needs. This means showing good judgment that you're capable of doing the right extras without gold-plating. This might be demonstrated by high-value, creative touches when scope of the task is vague; while being surgical and targeted when scope is tightly specified.\n\n# Sharing progress updates\n\nFor especially longer tasks that you work on (i.e. requiring many tool calls, or a plan with multiple steps), you should provide progress updates back to the user at reasonable intervals. These updates should be structured as a concise sentence or two (no more than 8-10 words long) recapping progress so far in plain language: this update demonstrates your understanding of what needs to be done, progress so far (i.e. files explores, subtasks complete), and where you're going next.\n\nBefore doing large chunks of work that may incur latency as experienced by the user (i.e. writing a new file), you should send a concise message to the user with an update indicating what you're about to do to ensure they know what you're spending time on. Don't start editing or writing large files before informing the user what you are doing and why.\n\nThe messages you send before tool calls should describe what is immediately about to be done next in very concise language. If there was previous work done, this preamble message should also include a note about the work done so far to bring the user along.\n\n# Presenting your work and final message\n\nYour final message should read naturally, like an update from a concise teammate. For casual conversation, brainstorming tasks, or quick questions from the user, respond in a friendly, conversational tone. You should ask questions, suggest ideas, and adapt to the user's style. If you've finished a large amount of work, when describing what you've done to the user, you should follow the final answer formatting guidelines to communicate substantive changes. You don't need to add structured formatting for one-word answers, greetings, or purely conversational exchanges.\n\nYou can skip heavy formatting for single, simple actions or confirmations. In these cases, respond in plain sentences with any relevant next step or quick option. Reserve multi-section structured responses for results that need grouping or explanation.\n\nThe user is working on the same computer as you, and has access to your work. As such there's no need to show the full contents of large files you have already written unless the user explicitly asks for them. Similarly, if you've created or modified files, there's no need to tell users to \"save the file\" or \"copy the code into a file\"\u2014just reference the file path.\n\nComplete authorized next steps, including relevant tests. Ask before a consequential action that needs approval, and briefly report anything you could not verify.\n\nBrevity is very important as a default. You should be very concise (i.e. no more than 10 lines), but can relax this requirement for tasks where additional detail and comprehensiveness is important for the user's understanding.\n\n## Final answer structure and style guidelines\n\nYou are producing plain text that will later be styled by the CLI. Follow these rules exactly. Formatting should make results easy to scan, but not feel mechanical. Use judgment to decide how much structure adds value.\n\n**Section Headers**\n\n- Use only when they improve clarity \u2014 they are not mandatory for every answer.\n- Choose descriptive names that fit the content\n- Keep headers short (1\u20133 words) and in `**Title Case**`. Always start headers with `**` and end with `**`\n- Use the blank lines required by the renderer for headings and lists.\n- Section headers should only be used where they genuinely improve scanability; avoid fragmenting the answer.\n\n**Bullets**\n\n- Use `-` followed by a space for every bullet.\n- Merge related points when possible; avoid a bullet for every trivial detail.\n- Keep bullets to one line unless breaking for clarity is unavoidable.\n- Group into short lists (4\u20136 bullets) ordered by importance.\n- Use consistent keyword phrasing and formatting across sections.\n\n**Monospace**\n\n- Wrap all commands, file paths, env vars, and code identifiers in backticks (`` `...` ``).\n- Apply to inline examples and to bullet keywords if the keyword itself is a literal file/command.\n- Never mix monospace and bold markers; choose one based on whether it's a keyword (`**`) or inline code/path (`` ` ``).\n\n**File References**\n\nWhen referencing files in your response, make sure to include the relevant start line and always follow the below rules:\n\n- Use inline code to make file paths clickable.\n- Each reference should have a stand alone path. Even if it's the same file.\n- Accepted: absolute, workspace\u2011relative, a/ or b/ diff prefixes, or bare filename/suffix.\n- Line/column (1\u2011based, optional): :line[:column] or #Lline[Ccolumn] (column defaults to 1).\n- Do not use URIs like file://, vscode://, or https://.\n- Do not provide range of lines\n- Examples: src/app.ts, src/app.ts:42, b/server/index.js#L10, C:\\repo\\project\\main.rs:12:5\n\n**Structure**\n\n- Place related bullets together; don't mix unrelated concepts in the same section.\n- Order sections from general \u2192 specific \u2192 supporting info.\n- For subsections (e.g., \"Binaries\" under \"Rust Workspace\"), introduce with a bolded keyword bullet, then list items under it.\n- Match structure to complexity:\n  - Multi-part or detailed results \u2192 use clear headers and grouped bullets.\n  - Simple results \u2192 minimal headers, possibly just a short list or paragraph.\n\n**Tone**\n\n- Keep the voice collaborative and natural, like a coding partner handing off work.\n- Be concise and factual \u2014 no filler or conversational commentary and avoid unnecessary repetition\n- Use present tense and active voice (e.g., \"Runs tests\" not \"This will run tests\").\n- Keep descriptions self-contained; don't refer to \"above\" or \"below\".\n- Use parallel structure in lists for consistency.\n\n**Don't**\n\n- Don't use literal words \"bold\" or \"monospace\" in the content.\n- Don't nest bullets or create deep hierarchies.\n- Don't output ANSI escape codes directly \u2014 the CLI renderer applies them.\n- Don't cram unrelated keywords into a single bullet; split for clarity.\n- Don't let keyword lists run long \u2014 wrap or reformat for scanability.\n\nGenerally, ensure your final answers adapt their shape and depth to the request. For example, answers to code explanations should have a precise, structured explanation with code references that answer the question directly. For tasks with a simple implementation, lead with the outcome and supplement only with what's needed for clarity. Larger changes can be presented as a logical walkthrough of your approach, grouping related steps, explaining rationale where it adds value, and highlighting next actions to accelerate the user. Your answers should provide the right level of detail while being easily scannable.\n\nFor casual greetings, acknowledgements, or other one-off conversational messages that are not delivering substantive information or structured results, respond naturally without section headers or bullet formatting.\n\n# Professional objectivity\n\nPrioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving. Be direct and objective without unnecessary praise or emotional validation. Disagree when needed. When uncertain, investigate before confirming the user's assumptions.\n\n# Proactiveness\n\nProactively complete work that follows from the user's request. Avoid unrelated actions that would surprise the user. Strike a balance between:\n\n1. Doing the right thing when asked, including follow-up actions\n2. Not surprising the user with unrequested actions\n   For example, if the user asks how to approach something, answer first; do not immediately jump into edits.\n\n# Following conventions\n\nWhen changing files, first understand the file's conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n\n- NEVER assume a library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses it (neighboring files, package.json, cargo.toml, go.mod, etc.).\n- When creating a new component, first look at existing components for framework choice, naming, typing, and other conventions.\n- When editing code, first look at surrounding context (especially imports) to understand chosen frameworks/libraries, then make the change idiomatically.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Doing tasks\n\nThe user will primarily request software engineering tasks: bugs, features, refactors, explanations, and more. Recommended steps:\n\n- Use available search/read tools extensively to understand the codebase and the query (in parallel when independent).\n- Implement the solution with the tools available to you.\n- Prefer editing existing files. Create documentation when the task or project instructions require it.\n- Verify when possible with tests. NEVER assume a specific test framework or script \u2014 check README / AGENTS.md or search the repo.\n- Run lint and typecheck commands (for example npm run lint, npm run typecheck, ruff, pnpm lint) if they were provided to you \u2014 see Validating your work for when to run them proactively vs. when to hold off. If you cannot find the correct command, ask the user, and if they supply it, proactively suggest writing it to AGENTS.md so you know next time.\n\n- Tool results and user messages may include <system-reminder> tags. Those tags contain useful reminders. They are NOT part of the user's provided input or the tool result.\n\n# Tool usage policy\n\n- Prefer specialized file tools over shell for reading, editing, writing, listing, and searching when those tools are available. Use the `grep`, `glob`, and `list` tools instead of bash for search and listing \u2014 they are ripgrep-backed and return structured, length-capped results. Use shell for real system commands (git, package managers, builds, tests, process control).\n- When doing broad codebase exploration, use the available search tools and delegate only when the task benefits from independent work.\n- You can call multiple tools in one response. When multiple independent pieces of information are needed, batch tool calls for performance. When making multiple bash tool calls, send a single message with multiple tool calls so they can run in parallel (for example git status and git diff together).\n- Match edit old-text exactly, including whitespace.\n- If a tool call is denied by policy, adapt: use an allowed approach or ask the user. Do not retry the same blocked call in a loop.\n\n## Shell commands\n\nWhen using the shell, you must adhere to the following guidelines:\n\n- When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep` and `find`. (If the `rg` command is not found, then use alternatives.) Reach for the shell only when the `grep`/`glob` tools cannot express the query \u2014 for example counting matches, or piping results into another command.\n- Search narrow first: use `rg -l` or `rg -c` to find which files match, then read only those files. Do not dump full match bodies across a repo into context.\n- Never pipe a large file into your context. Do not `cat` a big file; use the `read` tool with an offset/limit, or `sed -n 'START,ENDp'` for a specific range.\n- Do not use python scripts to attempt to output larger chunks of a file.\n\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames and directory structure.\n\n# AGENTS.md spec\n\n- Repos often contain AGENTS.md files. These files can appear anywhere within the repository.\n- These files are a way for humans to give you (the agent) instructions or tips for working within the container.\n- Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.\n- Instructions in AGENTS.md files:\n  - The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.\n  - For every file you touch in the final change, you must obey instructions in any AGENTS.md file whose scope includes that file.\n  - Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the file states otherwise.\n  - More-deeply-nested AGENTS.md files take precedence in the case of conflicting instructions.\n  - Direct system/developer/user instructions (as part of a prompt) take precedence over AGENTS.md instructions.\n- The contents of the AGENTS.md file at the root of the repo and the project directory are loaded into your context automatically and don't need to be re-read. AGENTS.md files in subdirectories are NOT loaded automatically: when working in a subdirectory, or a directory outside the CWD, check for any AGENTS.md files that may be applicable.\n\n# Permissions and safety\n\n- Never commit secrets or keys.\n- Never create a git commit unless the user explicitly asks.\n- Do not run destructive commands (mass delete, force-push, hard reset) unless the user clearly requested them.\n";
     ALAN_CODE_ENGINE_PROVIDER_ID = "alan";
@@ -31071,7 +31115,7 @@ function notice(kind, message) {
 function promptParts2(input2) {
   const files = (input2.imagePaths ?? []).map((path, index) => ({
     type: "file",
-    mime: input2.images?.[index]?.mimeType ?? IMAGE_TYPES[(0, import_path10.extname)(path).toLowerCase()] ?? "application/octet-stream",
+    mime: input2.images?.[index]?.mimeType ?? IMAGE_TYPES[(0, import_path11.extname)(path).toLowerCase()] ?? "application/octet-stream",
     filename: path.split(/[\\/]/).at(-1) ?? path,
     url: (0, import_url2.pathToFileURL)(path).href
   }));
@@ -31194,7 +31238,7 @@ async function canonicalDirectory(directory) {
   try {
     return await (0, import_promises17.realpath)(directory);
   } catch {
-    return (0, import_path9.resolve)(directory);
+    return (0, import_path10.resolve)(directory);
   }
 }
 async function openSession(session, client, spec, log) {
@@ -31294,9 +31338,9 @@ function createOpenCodeDriver(options = {}) {
       const spec = { ...planned, env: launchEnv(planned, authorization) };
       const password = options.password?.() ?? (0, import_crypto10.randomBytes)(24).toString("base64url");
       try {
-        const data = spec.env.XDG_DATA_HOME ?? (0, import_path9.join)(spec.env.HOME ?? spec.env.USERPROFILE ?? spec.cwd, ".local", "share");
+        const data = spec.env.XDG_DATA_HOME ?? (0, import_path10.join)(spec.env.HOME ?? spec.env.USERPROFILE ?? spec.cwd, ".local", "share");
         const session = await withStartupLock(
-          (0, import_path9.join)(data, "opencode", ".alan-startup.lock"),
+          (0, import_path10.join)(data, "opencode", ".alan-startup.lock"),
           resolved.clock,
           () => openWithRetries(spec, password, resolved)
         );
@@ -31394,15 +31438,15 @@ function openCodeTurnInput(run, context) {
     ...context.attachments.length ? { readableFiles: context.attachments.map((attachment) => attachment.path) } : {}
   };
 }
-var import_crypto9, import_http4, import_crypto10, import_promises17, import_path9, import_path10, import_url2, import_path11, import_crypto11, IDLE_SOCKET_MS2, OpenCodeHttpError, BASE62, messageIdClock, OpenCodeClient, OPENCODE_CONFIG_ENV, OPENCODE_ENGINE, TEXT_PARTS, STEP_PARTS, STOPPED_BY_USER, OpenCodeSubagents, NAMED_KINDS, OPENCODE_ABORTED_ERROR, PROVIDER_EVENT_META, TASK_TOOL_NAME, TASK_RESULT_TAG, TASK_ERROR_TAG, PERMISSION_DENIED, FILE_OPERATIONS, NO_USAGE, PartReader, NOTHING, NON_INTERACTIVE_PERMISSIONS, CONTENT_FILTER_FINISHES, TRUNCATED_FINISHES, OUTPUT_PARTS, OpenCodeTurn, LISTENING, OUTPUT_TAIL_LINES, IMAGE_TYPES, OpenCodeSession, OPENCODE_MIN_VERSION, OPENCODE_REQUIREMENT, OPENCODE_TESTED_LINE, OPENCODE_SUPPORTED_MAJOR, DEFAULTS2, STORE_LOCKED, NON_INTERACTIVE_RULES, TITLE_LENGTH, MAX_VARIANT_LENGTH;
+var import_crypto9, import_http4, import_crypto10, import_promises17, import_path10, import_path11, import_url2, import_path12, import_crypto11, IDLE_SOCKET_MS2, OpenCodeHttpError, BASE62, messageIdClock, OpenCodeClient, OPENCODE_CONFIG_ENV, OPENCODE_ENGINE, TEXT_PARTS, STEP_PARTS, STOPPED_BY_USER, OpenCodeSubagents, NAMED_KINDS, OPENCODE_ABORTED_ERROR, PROVIDER_EVENT_META, TASK_TOOL_NAME, TASK_RESULT_TAG, TASK_ERROR_TAG, PERMISSION_DENIED, FILE_OPERATIONS, NO_USAGE, PartReader, NOTHING, NON_INTERACTIVE_PERMISSIONS, CONTENT_FILTER_FINISHES, TRUNCATED_FINISHES, OUTPUT_PARTS, OpenCodeTurn, LISTENING, OUTPUT_TAIL_LINES, IMAGE_TYPES, OpenCodeSession, OPENCODE_MIN_VERSION, OPENCODE_REQUIREMENT, OPENCODE_TESTED_LINE, OPENCODE_SUPPORTED_MAJOR, DEFAULTS2, STORE_LOCKED, NON_INTERACTIVE_RULES, TITLE_LENGTH, MAX_VARIANT_LENGTH;
 var init_opencode = __esm({
   "../agent-core/dist/providers/opencode.js"() {
     "use strict";
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     import_crypto9 = require("crypto");
@@ -31410,12 +31454,12 @@ var init_opencode = __esm({
     init_runtime_v2();
     import_crypto10 = require("crypto");
     import_promises17 = require("fs/promises");
-    import_path9 = require("path");
-    init_agent2();
     import_path10 = require("path");
+    init_agent2();
+    import_path11 = require("path");
     import_url2 = require("url");
     init_acp();
-    import_path11 = require("path");
+    import_path12 = require("path");
     init_acp();
     init_constants();
     import_crypto11 = require("crypto");
@@ -32053,7 +32097,7 @@ var init_opencode = __esm({
         this.#readOnly = readOnly;
         this.#memory = memory;
         this.#engine = engine;
-        this.#readableFiles = new Set(readableFiles.map((path) => (0, import_path11.normalize)(path)));
+        this.#readableFiles = new Set(readableFiles.map((path) => (0, import_path12.normalize)(path)));
       }
       get childSessionIds() {
         return [...this.#children.keys()];
@@ -32293,7 +32337,7 @@ var init_opencode = __esm({
       #opensAttachment(kind, properties) {
         if (kind !== "external_directory") return false;
         const filepath = asString(asRecord(properties.metadata)?.filepath);
-        return (0, import_path11.isAbsolute)(filepath) && this.#readableFiles.has((0, import_path11.normalize)(filepath));
+        return (0, import_path12.isAbsolute)(filepath) && this.#readableFiles.has((0, import_path12.normalize)(filepath));
       }
       #question(properties) {
         const requestId = asString(properties.id).trim();
@@ -33066,6 +33110,14 @@ function modelArgs(input2) {
     effort: option("--effort", effort)
   };
 }
+function skillListingArgs(input2) {
+  const chars = input2.skillListingMaxDescChars;
+  const ownSettings = (input2.extraArgs ?? []).some(
+    (arg) => arg === "--settings" || arg.startsWith("--settings=")
+  );
+  if (chars === void 0 || !input2.capabilities.supportsPluginDir || ownSettings) return [];
+  return ["--settings", JSON.stringify({ skillListingMaxDescChars: chars })];
+}
 function buildClaudeArgs(input2) {
   const { capabilities } = input2;
   const disallowed = input2.disallowedTools?.length ? input2.disallowedTools.join(",") : void 0;
@@ -33090,6 +33142,7 @@ function buildClaudeArgs(input2) {
     // Without it the whole answer lands in one frame at turn end.
     ...capabilities.supportsPartialMessages ? ["--include-partial-messages"] : [],
     ...capabilities.supportsPluginDir ? (input2.pluginDirs ?? []).flatMap((dir) => ["--plugin-dir", dir]) : [],
+    ...skillListingArgs(input2),
     ...option("--resume", input2.resumeId),
     "--chrome",
     ...input2.extraArgs ?? []
@@ -33977,7 +34030,7 @@ function createClaudeDriver(options = {}) {
   };
 }
 function claudeHomeFor(env, homeDir) {
-  return env.CLAUDE_CONFIG_DIR || (0, import_path12.join)(env.HOME || homeDir, ".claude");
+  return env.CLAUDE_CONFIG_DIR || (0, import_path13.join)(env.HOME || homeDir, ".claude");
 }
 function encodeProjectDir(cwd) {
   return cwd.replace(/[^a-zA-Z0-9]/g, "-");
@@ -33998,14 +34051,14 @@ function projectDirs(projectsRoot) {
 }
 function claudeSessionLogExists(query) {
   if (!query.sessionId || !query.cwd) return false;
-  const projectsRoot = (0, import_path12.join)(query.claudeHome, "projects");
+  const projectsRoot = (0, import_path13.join)(query.claudeHome, "projects");
   const fileName = `${query.sessionId}.jsonl`;
   const here = new Set([query.cwd, realCwd(query.cwd)].map(encodeProjectDir));
   for (const dir of here) {
-    if ((0, import_fs8.existsSync)((0, import_path12.join)(projectsRoot, dir, fileName))) return true;
+    if ((0, import_fs8.existsSync)((0, import_path13.join)(projectsRoot, dir, fileName))) return true;
   }
   return projectDirs(projectsRoot).some(
-    (dir) => !here.has(dir) && (0, import_fs8.existsSync)((0, import_path12.join)(projectsRoot, dir, fileName))
+    (dir) => !here.has(dir) && (0, import_fs8.existsSync)((0, import_path13.join)(projectsRoot, dir, fileName))
   );
 }
 function envDigest3(env) {
@@ -34034,6 +34087,7 @@ function planClaudeSession(run, context) {
     ...prompts.systemPrompt === void 0 ? {} : { systemPrompt: prompts.systemPrompt },
     ...prompts.systemPromptAppend === void 0 ? {} : { appendSystemPrompt: prompts.systemPromptAppend },
     ...context.pluginDirs?.length ? { pluginDirs: context.pluginDirs } : {},
+    ...run.sandboxId || run.cloudEnvironmentId ? { skillListingMaxDescChars: CLOUD_SKILL_LISTING_MAX_DESCRIPTION_CHARS } : {},
     ...context.managedMcp === void 0 ? {} : {
       mcp: {
         alanMcpUrl: context.managedMcp.url,
@@ -34078,16 +34132,16 @@ async function claudeTurnInput(run, context) {
   );
   return { turnId: run.runId, text: text2, ...encoded.length ? { images: encoded } : {} };
 }
-var import_crypto12, import_fs8, import_path12, import_crypto13, import_promises18, EDIT_TOOLS, ThoughtBlocks, UNDERSTOOD_SYSTEM_SUBTYPES, CLAUDE_MCP_STATUS, RATE_LIMIT_WARN_AT, CLAUDE_GRAMMAR_NAME, SUBAGENT_TOOL_NAMES, controlResponseSchema, STOPPED_STATUSES, TaskRecords, TERMINAL_BACKGROUND_STATUSES, NON_TERMINAL_BACKGROUND_STATUSES, ASYNC_LAUNCH_ACK, BackgroundTasks, FAILED_STATUSES, STOPPED_BY_USER_TEXT, ClaudeTurn, STDERR_TAIL_LINES3, MAX_EARLY_LINES, UNSUPPORTED_STOP, OUTPUT_CLOSED_REASON, ClaudeSession, DEFAULTS3, READ_ONLY_DISALLOWED_TOOLS, DEFAULT_MCP_TIMEOUT_MS;
+var import_crypto12, import_fs8, import_path13, import_crypto13, import_promises18, EDIT_TOOLS, ThoughtBlocks, UNDERSTOOD_SYSTEM_SUBTYPES, CLAUDE_MCP_STATUS, RATE_LIMIT_WARN_AT, CLAUDE_GRAMMAR_NAME, SUBAGENT_TOOL_NAMES, controlResponseSchema, STOPPED_STATUSES, TaskRecords, TERMINAL_BACKGROUND_STATUSES, NON_TERMINAL_BACKGROUND_STATUSES, ASYNC_LAUNCH_ACK, BackgroundTasks, FAILED_STATUSES, STOPPED_BY_USER_TEXT, ClaudeTurn, STDERR_TAIL_LINES3, MAX_EARLY_LINES, UNSUPPORTED_STOP, OUTPUT_CLOSED_REASON, ClaudeSession, DEFAULTS3, READ_ONLY_DISALLOWED_TOOLS, DEFAULT_MCP_TIMEOUT_MS, CLOUD_SKILL_LISTING_MAX_DESCRIPTION_CHARS;
 var init_claude = __esm({
   "../agent-core/dist/providers/claude.js"() {
     "use strict";
     init_chunk_VUWLTOVK();
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     init_effort();
@@ -34099,7 +34153,7 @@ var init_claude = __esm({
     init_constants();
     init_agent2();
     import_fs8 = require("fs");
-    import_path12 = require("path");
+    import_path13 = require("path");
     import_crypto13 = require("crypto");
     import_promises18 = require("fs/promises");
     init_agent2();
@@ -35067,6 +35121,7 @@ var init_claude = __esm({
       "NotebookEdit"
     ];
     DEFAULT_MCP_TIMEOUT_MS = 5e3;
+    CLOUD_SKILL_LISTING_MAX_DESCRIPTION_CHARS = 250;
   }
 });
 
@@ -35224,7 +35279,7 @@ function codexExecArgs(input2) {
   ];
 }
 function codexHomeOf(env) {
-  return env.CODEX_HOME || (0, import_path13.join)(env.HOME ?? "", ".codex");
+  return env.CODEX_HOME || (0, import_path14.join)(env.HOME ?? "", ".codex");
 }
 function namesNewestFirst(dir, isDir) {
   try {
@@ -35240,15 +35295,15 @@ function findCodexRollout(codexHome, sessionId) {
       const name = namesNewestFirst(dir, false).find(
         (file2) => file2.startsWith("rollout-") && file2.endsWith(suffix)
       );
-      return name ? (0, import_path13.join)(dir, name) : void 0;
+      return name ? (0, import_path14.join)(dir, name) : void 0;
     }
     for (const child of namesNewestFirst(dir, true)) {
-      const found = walk((0, import_path13.join)(dir, child), depth - 1);
+      const found = walk((0, import_path14.join)(dir, child), depth - 1);
       if (found) return found;
     }
     return void 0;
   };
-  return sessionId ? walk((0, import_path13.join)(codexHome, "sessions"), 3) : void 0;
+  return sessionId ? walk((0, import_path14.join)(codexHome, "sessions"), 3) : void 0;
 }
 function codexRolloutExists(codexHome, sessionId) {
   return Promise.resolve(findCodexRollout(codexHome, sessionId) !== void 0);
@@ -36426,20 +36481,20 @@ function codexTurnInput(run, context) {
     ...images.length ? { imagePaths: images.map((image) => image.path) } : {}
   };
 }
-var import_fs9, import_path13, import_crypto14, import_crypto15, import_crypto16, import_crypto17, TokenRefresher, MCP_STARTUP_TIMEOUT_SEC, FIELD_TYPES, YES_NO, ACCEPT_DECLINE, MAX_INLINE_GENERATED_IMAGE_BYTES, PNG_SIGNATURE2, JPEG_NON_FRAME_MARKERS, IMAGE_GEN_CALL, PROMPT_LITERAL, RELOCATE_EVERY_MS, CodexImageGenerationFold, CodexRolloutImages, CodexRateLimits, USER_INPUT_METHOD, PERMISSIONS_METHOD, ELICITATION_METHOD, COMMAND_OR_FILE, LEGACY, DECISIONS, COORDINATION_TOOLS, SETTLED_AGENT, STATUS, CHANGE_OPERATIONS, SILENT_ON_START, IGNORED_ITEMS, PLAN_STATUS, CodexTurnTokens, CODEX_MCP_STATUS, WORKER_LIFECYCLE, INFO_KINDS, SILENT, CodexTurn, STDERR_TAIL_LINES4, MAX_BETWEEN_UPDATES2, UNSUPPORTED_REQUEST, DECLINED_ELICITATION, IMAGE_CATCH_UP_MS, IMAGE_POLL_MS, CodexSession, CODEX_MIN_VERSION, CODEX_REQUIREMENT, CODEX_TESTED_LINE, DEFAULTS4, CLIENT_INFO2, STATUS2, EXITED_WITHOUT_RESPONSE, CodexExecTurn, DEFAULTS22, CodexExecSession;
+var import_fs9, import_path14, import_crypto14, import_crypto15, import_crypto16, import_crypto17, TokenRefresher, MCP_STARTUP_TIMEOUT_SEC, FIELD_TYPES, YES_NO, ACCEPT_DECLINE, MAX_INLINE_GENERATED_IMAGE_BYTES, PNG_SIGNATURE2, JPEG_NON_FRAME_MARKERS, IMAGE_GEN_CALL, PROMPT_LITERAL, RELOCATE_EVERY_MS, CodexImageGenerationFold, CodexRolloutImages, CodexRateLimits, USER_INPUT_METHOD, PERMISSIONS_METHOD, ELICITATION_METHOD, COMMAND_OR_FILE, LEGACY, DECISIONS, COORDINATION_TOOLS, SETTLED_AGENT, STATUS, CHANGE_OPERATIONS, SILENT_ON_START, IGNORED_ITEMS, PLAN_STATUS, CodexTurnTokens, CODEX_MCP_STATUS, WORKER_LIFECYCLE, INFO_KINDS, SILENT, CodexTurn, STDERR_TAIL_LINES4, MAX_BETWEEN_UPDATES2, UNSUPPORTED_REQUEST, DECLINED_ELICITATION, IMAGE_CATCH_UP_MS, IMAGE_POLL_MS, CodexSession, CODEX_MIN_VERSION, CODEX_REQUIREMENT, CODEX_TESTED_LINE, DEFAULTS4, CLIENT_INFO2, STATUS2, EXITED_WITHOUT_RESPONSE, CodexExecTurn, DEFAULTS22, CodexExecSession;
 var init_codex = __esm({
   "../agent-core/dist/providers/codex.js"() {
     "use strict";
     init_chunk_VUWLTOVK();
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     import_fs9 = require("fs");
-    import_path13 = require("path");
+    import_path14 = require("path");
     init_effort();
     import_crypto14 = require("crypto");
     import_crypto15 = require("crypto");
@@ -38122,11 +38177,11 @@ var import_crypto18, import_promises19, FACTORY_API_VERSION, FACTORY_PROTOCOL_VE
 var init_droid = __esm({
   "../agent-core/dist/providers/droid.js"() {
     "use strict";
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     init_runtime_v2();
@@ -38613,7 +38668,7 @@ var init_opencode2 = __esm({
 // ../agent-core/dist/providers/antigravity.js
 function settingsPath(env) {
   const home = env.HOME?.trim() || env.USERPROFILE?.trim();
-  return home ? (0, import_path14.resolve)(home, ".gemini", "antigravity-cli", "settings.json") : void 0;
+  return home ? (0, import_path15.resolve)(home, ".gemini", "antigravity-cli", "settings.json") : void 0;
 }
 async function readSettings(path) {
   let raw;
@@ -38636,7 +38691,7 @@ async function selectAntigravityApiKeyMode(env) {
   const settings2 = await readSettings(path);
   if (settings2 === "malformed") return "malformed";
   if (settings2.modelProvider === "gemini") return "already_selected";
-  await (0, import_promises20.mkdir)((0, import_path14.dirname)(path), { recursive: true });
+  await (0, import_promises20.mkdir)((0, import_path15.dirname)(path), { recursive: true });
   await (0, import_promises20.writeFile)(path, JSON.stringify({ ...settings2, modelProvider: "gemini" }), { mode: 384 });
   return "selected";
 }
@@ -38680,21 +38735,21 @@ function antigravityArgs(input2, capabilities, prompt) {
   ];
 }
 function workspaceRoot(cwd) {
-  for (let current = (0, import_path15.resolve)(cwd); ; current = (0, import_path15.dirname)(current)) {
-    if ((0, import_fs10.existsSync)((0, import_path15.join)(current, ".git"))) return current;
-    if ((0, import_path15.dirname)(current) === current) return (0, import_path15.resolve)(cwd);
+  for (let current = (0, import_path16.resolve)(cwd); ; current = (0, import_path16.dirname)(current)) {
+    if ((0, import_fs10.existsSync)((0, import_path16.join)(current, ".git"))) return current;
+    if ((0, import_path16.dirname)(current) === current) return (0, import_path16.resolve)(cwd);
   }
 }
 function instructionPaths(cwd) {
   const root = workspaceRoot(cwd);
   const paths = [];
-  for (let current = (0, import_path15.resolve)(cwd); ; current = (0, import_path15.dirname)(current)) {
-    const path = (0, import_path15.join)(current, INSTRUCTIONS_FILE);
+  for (let current = (0, import_path16.resolve)(cwd); ; current = (0, import_path16.dirname)(current)) {
+    const path = (0, import_path16.join)(current, INSTRUCTIONS_FILE);
     try {
       if ((0, import_fs10.existsSync)(path) && (0, import_fs10.statSync)(path).isFile()) paths.unshift(path);
     } catch {
     }
-    if (current === root || (0, import_path15.dirname)(current) === current) return paths;
+    if (current === root || (0, import_path16.dirname)(current) === current) return paths;
   }
 }
 function antigravityWorkspaceInstructions(cwd, maxChars = MAX_INSTRUCTION_CHARS) {
@@ -38948,7 +39003,7 @@ function normalizeAntigravityFrame(event) {
 }
 function antigravityBrainRoot(env) {
   const home = env.HOME?.trim() || env.USERPROFILE?.trim();
-  return home ? (0, import_path16.resolve)(home, ".gemini", "antigravity-cli", "brain") : void 0;
+  return home ? (0, import_path17.resolve)(home, ".gemini", "antigravity-cli", "brain") : void 0;
 }
 function parseEntry(text2) {
   try {
@@ -38986,14 +39041,14 @@ function childTranscriptPath(root, frame) {
   try {
     const url2 = new URL(logUri);
     if (url2.protocol !== "file:") return void 0;
-    path = (0, import_path16.resolve)((0, import_url3.fileURLToPath)(url2));
+    path = (0, import_path17.resolve)((0, import_url3.fileURLToPath)(url2));
   } catch {
     return void 0;
   }
-  const fromRoot = (0, import_path16.relative)(root, path);
-  if (!fromRoot || (0, import_path16.isAbsolute)(fromRoot) || fromRoot.split(import_path16.sep).includes("..")) return void 0;
+  const fromRoot = (0, import_path17.relative)(root, path);
+  if (!fromRoot || (0, import_path17.isAbsolute)(fromRoot) || fromRoot.split(import_path17.sep).includes("..")) return void 0;
   const expected = [conversationId, ...LOG_DIRS, TRANSCRIPT_FILE];
-  const segments = fromRoot.split(import_path16.sep);
+  const segments = fromRoot.split(import_path17.sep);
   const matches = segments.length === expected.length && segments.every((segment, index) => segment === expected[index]);
   return matches ? path : void 0;
 }
@@ -39255,24 +39310,24 @@ function antigravityTurnInput(run, context) {
   });
   return { turnId: run.runId, text: appendImagePathReferences(text2, images) };
 }
-var import_promises20, import_path14, import_fs10, import_path15, import_path16, import_url3, import_crypto19, NO_ANTIGRAVITY_CAPABILITIES, INSTRUCTIONS_FILE, MAX_INSTRUCTION_CHARS, SHORTENED_NOTE, DIFF_BLOCK_START, DIFF_BLOCK_END, HUNK_HEADER, TRANSCRIPT_FILE, FULL_TRANSCRIPT_FILE, LOG_DIRS, TOOL_RESULT_TYPES, BrainTranscript, AntigravityTranscripts, ANTIGRAVITY_GRAMMAR_NAME, AntigravityGrammar, ignored, HANDLERS, SUCCESSFUL_STATUSES, SESSION_START_TYPES, RESULT_TYPES, SUBAGENT_START_TYPES, RESUME_FORKED, EXITED_WITHOUT_RESULT, AntigravityTurn, DEFAULTS6, AntigravitySession, WINDOWS_LINE_MARGIN;
+var import_promises20, import_path15, import_fs10, import_path16, import_path17, import_url3, import_crypto19, NO_ANTIGRAVITY_CAPABILITIES, INSTRUCTIONS_FILE, MAX_INSTRUCTION_CHARS, SHORTENED_NOTE, DIFF_BLOCK_START, DIFF_BLOCK_END, HUNK_HEADER, TRANSCRIPT_FILE, FULL_TRANSCRIPT_FILE, LOG_DIRS, TOOL_RESULT_TYPES, BrainTranscript, AntigravityTranscripts, ANTIGRAVITY_GRAMMAR_NAME, AntigravityGrammar, ignored, HANDLERS, SUCCESSFUL_STATUSES, SESSION_START_TYPES, RESULT_TYPES, SUBAGENT_START_TYPES, RESUME_FORKED, EXITED_WITHOUT_RESULT, AntigravityTurn, DEFAULTS6, AntigravitySession, WINDOWS_LINE_MARGIN;
 var init_antigravity = __esm({
   "../agent-core/dist/providers/antigravity.js"() {
     "use strict";
     init_chunk_VUWLTOVK();
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_YXWJW7I5();
     import_promises20 = require("fs/promises");
-    import_path14 = require("path");
+    import_path15 = require("path");
     init_type_guards();
     import_fs10 = require("fs");
-    import_path15 = require("path");
-    init_effort();
     import_path16 = require("path");
+    init_effort();
+    import_path17 = require("path");
     import_url3 = require("url");
     import_crypto19 = require("crypto");
     init_agent2();
@@ -39312,7 +39367,7 @@ var init_antigravity = __esm({
       #full;
       constructor(path) {
         this.#cursor = new TranscriptCursor(path);
-        this.#fullPath = (0, import_path16.resolve)((0, import_path16.dirname)(path), FULL_TRANSCRIPT_FILE);
+        this.#fullPath = (0, import_path17.resolve)((0, import_path17.dirname)(path), FULL_TRANSCRIPT_FILE);
       }
       skipExisting() {
         this.#cursor.read();
@@ -39360,7 +39415,7 @@ var init_antigravity = __esm({
       /** A conversation this turn did not resume was created by it, so it is read whole. */
       trackParent(conversationId) {
         if (this.#parent?.conversationId === conversationId) return;
-        const path = (0, import_path16.resolve)(this.#root, conversationId, ...LOG_DIRS, TRANSCRIPT_FILE);
+        const path = (0, import_path17.resolve)(this.#root, conversationId, ...LOG_DIRS, TRANSCRIPT_FILE);
         this.#parent = { conversationId, transcript: new BrainTranscript(path) };
       }
       /** A launcher keeps the first valid transcript it names; later frames change nothing. */
@@ -39791,7 +39846,7 @@ function parseConfig(raw) {
   }
 }
 async function writeCommandCodeProjectMcp(cwd, mcp) {
-  const path = (0, import_path17.join)(cwd, ".mcp.json");
+  const path = (0, import_path18.join)(cwd, ".mcp.json");
   const original = await (0, import_promises21.readFile)(path, "utf8").catch(() => null);
   const config2 = parseConfig(original);
   const next = {
@@ -39986,19 +40041,19 @@ function commandCodeTurnInput(run, context) {
   });
   return { turnId: run.runId, text: appendImagePathReferences(text2, images) };
 }
-var import_promises21, import_path17, import_crypto20, COMMAND_CODE_GRAMMAR_NAME, SILENT3, CommandCodeGrammar, SHELL_TOOL, STOP_TOOLS, REPORTED_STATUS, SHELL_STATUS, SWEEP_INTERVAL_MS, CommandCodeBackgroundTasks, EXITED_WITHOUT_RESULT2, CommandCodeTurn, COMMAND_CODE_MAX_TURNS, DEFAULTS7, CommandCodeSession;
+var import_promises21, import_path18, import_crypto20, COMMAND_CODE_GRAMMAR_NAME, SILENT3, CommandCodeGrammar, SHELL_TOOL, STOP_TOOLS, REPORTED_STATUS, SHELL_STATUS, SWEEP_INTERVAL_MS, CommandCodeBackgroundTasks, EXITED_WITHOUT_RESULT2, CommandCodeTurn, COMMAND_CODE_MAX_TURNS, DEFAULTS7, CommandCodeSession;
 var init_command_code = __esm({
   "../agent-core/dist/providers/command-code.js"() {
     "use strict";
-    init_chunk_4LDW3FJB();
+    init_chunk_U4RQE7JS();
     init_chunk_AF3IPGDT();
-    init_chunk_ZCTKXKYY();
+    init_chunk_WYNUYKKN();
     init_chunk_KVTSAS2T();
-    init_chunk_DLVRNIY5();
+    init_chunk_7FJ7QKFN();
     init_chunk_OSECDZA5();
     init_chunk_YXWJW7I5();
     import_promises21 = require("fs/promises");
-    import_path17 = require("path");
+    import_path18 = require("path");
     init_agent2();
     init_runtime_v2();
     init_acp();
@@ -49798,13 +49853,14 @@ function decodeUtf8(bytes, path) {
     throw new SkillPackageError("INVALID_FRONTMATTER", `${path} must be valid UTF-8`, path);
   }
 }
+var MARKDOWN_LINK_TARGET = /\]\(<?([^\s)>\]]+)>?(?=[\s)])/g;
 function collectDiagnostics(skillMarkdown, license, packagePaths) {
   if (!skillMarkdown)
     return [];
   const diagnostics = [];
   const markdown = decodeUtf8(skillMarkdown, "SKILL.md");
   const references = /* @__PURE__ */ new Set();
-  for (const match of markdown.matchAll(/\]\(<?([^\s)>]+)>?(?:\s+[^)]*)?\)/g)) {
+  for (const match of markdown.matchAll(MARKDOWN_LINK_TARGET)) {
     const reference = normalizePackageReference(match[1]);
     if (reference && looksLikeFileReference(reference))
       references.add(reference);
@@ -50005,22 +50061,21 @@ async function resolveSkillInvocations(layout, invocations, baked = "any") {
   }
   return missing.length === 0 ? { kind: "resolved", skills: resolved } : { kind: "missing", names: missing };
 }
-async function availableSkillIndex(layout) {
+async function nativeCandidates(layout) {
+  const nativeDir = layout.nativeDir;
+  if (nativeDir === null) return [];
+  const entries = await (0, import_promises27.readdir)(nativeDir, { withFileTypes: true }).catch(() => []);
+  return entries.filter((entry) => entry.isDirectory() || entry.isSymbolicLink()).map((entry) => ({ directory: (0, import_node_path13.join)(nativeDir, entry.name) }));
+}
+async function availableSkillIndex(layout, sources = { synced: true, native: true }) {
   const found = /* @__PURE__ */ new Map();
-  const candidates2 = [];
-  for (const skill of await readInstalledSkills(layout)) {
-    candidates2.push({
-      directory: packageDirectory(layout, skill.versionId),
-      contentHash: skill.contentHash
-    });
-  }
-  if (layout.nativeDir !== null) {
-    const entries = await (0, import_promises27.readdir)(layout.nativeDir, { withFileTypes: true }).catch(() => []);
-    for (const entry of entries) {
-      if (entry.isDirectory() || entry.isSymbolicLink())
-        candidates2.push({ directory: (0, import_node_path13.join)(layout.nativeDir, entry.name) });
-    }
-  }
+  const installed = await readInstalledSkills(layout);
+  const synced = sources.synced ? installed.map((skill) => ({
+    directory: packageDirectory(layout, skill.versionId),
+    contentHash: skill.contentHash
+  })) : [];
+  const shadowed = new Set(sources.synced ? [] : installed.map((skill) => skill.slug));
+  const candidates2 = [...synced, ...sources.native ? await nativeCandidates(layout) : []];
   const bounded = candidates2.slice(0, 2e3);
   for (let start = 0; start < bounded.length; start += INDEX_CONCURRENCY) {
     const batch = bounded.slice(start, start + INDEX_CONCURRENCY);
@@ -50028,7 +50083,8 @@ async function availableSkillIndex(layout) {
       batch.map((candidate) => inspectIndexedSkill(candidate.directory, candidate.contentHash))
     );
     for (const skill of inspected) {
-      if (skill !== null && !found.has(skill.name)) found.set(skill.name, skill);
+      if (skill !== null && !found.has(skill.name) && !shadowed.has(skill.name))
+        found.set(skill.name, skill);
     }
   }
   return [...found.values()].sort((a, b) => a.name.localeCompare(b.name));
@@ -50650,7 +50706,7 @@ var import_promises33 = require("fs/promises");
 var import_node_path21 = require("path");
 
 // ../agent-core/dist/prompt.js
-init_chunk_DLVRNIY5();
+init_chunk_7FJ7QKFN();
 
 // src/holder/agent-context.ts
 async function readText2(path) {
@@ -51113,13 +51169,38 @@ async function admitDefaultWorkspace(spec, context, skills) {
     );
   }
 }
+async function selfListedSkills(spec, context) {
+  const pointed = context.skills !== void 0 && installedSkillFolders(context.skills) !== null;
+  switch (spec.backendKind) {
+    case "claude_cli":
+      return {
+        synced: pointed && await (context.discovery?.claudeLoadsPlugins() ?? false),
+        native: false
+      };
+    case "codex_app_server":
+      return {
+        synced: pointed && context.discovery?.codexLinksSyncedSkills === true,
+        native: true
+      };
+    case ALAN_CODE_BACKEND:
+    case "opencode_serve":
+      return { synced: pointed, native: true };
+    default:
+      return { synced: false, native: false };
+  }
+}
 async function withInstalledCloudSkills(spec, context) {
   if (!spec.sandboxId && !spec.cloudEnvironmentId || context.skills === void 0) return spec;
+  const listed = await selfListedSkills(spec, context);
+  if (listed.synced && listed.native) return spec;
   return {
     ...spec,
     promptContext: {
       ...spec.promptContext,
-      availableSkills: await availableSkillIndex(context.skills)
+      availableSkills: await availableSkillIndex(context.skills, {
+        synced: !listed.synced,
+        native: !listed.native
+      })
     }
   };
 }
@@ -51172,7 +51253,8 @@ function createHolderWorkspace(machine, clock, log) {
           platform
         });
         return approved.roots();
-      }
+      },
+      ...machine.skillDiscovery === void 0 ? {} : { discovery: machine.skillDiscovery }
     },
     ...machine.refreshesFirstCheckout === true ? {
       refreshFirstCheckout: createCheckoutRefresh({
@@ -52036,6 +52118,9 @@ var SECRET_VARIABLES = /* @__PURE__ */ new Set([
   ENROLLMENT_CODE_VARIABLE
 ]);
 var ALAN_CODE_ENGINE_VARIABLE = "ALAN_CODE_ENGINE_PATH";
+function codexSkillsDir(config2) {
+  return config2.gitGatewayUrl === null ? null : (0, import_node_path32.join)(config2.codexHome, "skills");
+}
 function loadRuntimeConfig(env = process.env) {
   const parsed = envSchema.safeParse(env);
   if (!parsed.success) {
@@ -52292,6 +52377,7 @@ async function runHold(argv) {
       [ALAN_MCP_URL_ENV]: access3.managedMcp.url,
       [ALAN_MCP_CREDENTIAL_FILE_ENV]: credentialPath
     };
+    const flags = createFlagProbe();
     await runHolder({
       launch: launch.value,
       driver: createProviderDrivers({
@@ -52310,7 +52396,11 @@ async function runHold(argv) {
         env: cliEnvironment,
         stateDir: paths.stateDir,
         // Only a cloud sandbox's runtime has a git gateway.
-        refreshesFirstCheckout: config2.gitGatewayUrl !== null
+        refreshesFirstCheckout: config2.gitGatewayUrl !== null,
+        skillDiscovery: {
+          codexLinksSyncedSkills: codexSkillsDir(config2) !== null,
+          claudeLoadsPlugins: () => flags.supportsFlag("claude", "--plugin-dir", cliEnvironment)
+        }
       }
     });
   } catch (_) {