browsentic 0.4.6 → 0.4.9

package/dist/cli.js

@@ -28508,6 +28508,28 @@ var hoverElement = defineAction({
   }
 });
 
+// ../lib/actions/page/inject-code.ts
+var MAX_CODE_LENGTH = 32768;
+var injectCode = defineAction({
+  name: "page.injectCode",
+  description: "Install a small toolkit of JavaScript functions into the page, to be called later with page.runCode. Reach for it only when the ordinary tools are the wrong shape: a step sequence you are about to repeat three or more times with different inputs (create 20 tags, delete every row), or a capability no tool covers (seek a video, read a canvas, drive a bespoke editor API). The user reviews and approves the code before it runs \u2014 one approval covers every later page.runCode call and survives page reloads, so batch work needs no further prompts. The toolkit is bound to the tab and origin it was approved on; navigating to another site voids it. Installing goes through Chrome\u2019s debugger, so the browser shows a \u201CBrowsentic is debugging this browser\u201D bar for the moment it takes, it cannot install on a tab that has DevTools open, and it is unavailable on Firefox \u2014 the calls afterwards are cheap and show nothing. For a one-off click or fill, the ordinary tools are always the better choice.",
+  input: external_exports.object({
+    purpose: external_exports.string().min(1).max(200).describe(
+      "One plain sentence saying what this toolkit does and why it is needed \u2014 shown to the user on the approval prompt, so write it for them, not for the page."
+    ),
+    code: external_exports.string().min(1).max(MAX_CODE_LENGTH).describe(
+      "JavaScript source that assigns each entry point onto the provided `tools` object: `tools.addTag = async (name) => {\u2026}`. It runs once in the page\u2019s main world after the user approves it, so it can use the page\u2019s DOM, globals and same-origin fetch, but nothing of the extension. Keep it pure of data: anything that varies per call arrives as arguments through page.runCode, and secrets never belong in it. Async functions are awaited; return values must be JSON-serializable."
+    ),
+    call: external_exports.object({
+      function: external_exports.string().min(1).describe("Name of a function the code assigns onto `tools`."),
+      args: external_exports.array(external_exports.unknown()).default([]).describe("Arguments for that first call, JSON values only.")
+    }).optional().describe("Call one of the new functions immediately after installing, saving a round trip when the first use is already known.")
+  }),
+  execute() {
+    throw new ActionError("page.injectCode is resolved by the Browsentic extension, not in the page", "UNSUPPORTED");
+  }
+});
+
 // ../lib/actions/page/list-downloads.ts
 var listDownloads = defineAction({
   name: "page.listDownloads",
@@ -28636,12 +28658,9 @@ var CURSOR_PATHS = [
 ];
 var CURSOR2 = `url("data:image/svg+xml,${encodeURIComponent(cursorSvg())}") 14 14, crosshair`;
 var DEFAULT_HINT = "Click the element you mean";
-var picking = false;
-function lensIsUp() {
-  return picking;
-}
+var dismissCurrent = null;
 function pickWithLens({ hint, timeoutMs }) {
-  picking = true;
+  dismissCurrent?.();
   const host = document.createElement("div");
   host.id = HOST_ID;
   host.style.cssText = "all: initial; position: static;";
@@ -28656,6 +28675,8 @@ function pickWithLens({ hint, timeoutMs }) {
   const chip = root.querySelector(".chip");
   let hovered = null;
   return new Promise((resolve) => {
+    const dismiss = () => settle2({ cancelled: true });
+    dismissCurrent = dismiss;
     const timer = setTimeout(() => settle2({ timedOut: true }), timeoutMs);
     const mute = (event) => {
       event.stopPropagation();
@@ -28720,7 +28741,7 @@ function pickWithLens({ hint, timeoutMs }) {
       }
       host.remove();
       cursor.remove();
-      picking = false;
+      if (dismissCurrent === dismiss) dismissCurrent = null;
       resolve(outcome);
     }
   });
@@ -28799,18 +28820,16 @@ function styles() {
 
 // ../lib/actions/page/pick-element.ts
 var MAX_CONTENT = 2e4;
+var PICK_DEFAULT_TIMEOUT_MS = 6e4;
 var pickElement = defineAction({
   name: "page.pickElement",
-  description: "Ask the user to point at an element \u2014 A-Eye. Their cursor becomes a lens, whatever they hover is outlined, and the element they click comes back with its selector, its role and its rendered text. Use it when a target is genuinely ambiguous \u2014 several things share a label, or the user said \u201Cthis one\u201D about something you cannot see \u2014 and pointing is faster than describing. It takes over the page and waits for a person, so never call it to explore, and never call it twice in a row.",
+  description: "Ask the user to point at an element \u2014 A-Eye. Their cursor becomes a lens, whatever they hover is outlined, and the element they click comes back with its selector, its role, its rendered text and a screenshot of it exactly as they saw it. Use it when a target is genuinely ambiguous \u2014 several things share a label, or the user said \u201Cthis one\u201D about something you cannot see \u2014 and pointing is faster than describing. It takes over the page and waits for a person, so never call it to explore; a new call dismisses a pick already waiting.",
   input: external_exports.object({
     hint: external_exports.string().max(120).optional().describe("One line shown over the page saying what to point at, e.g. \u201CPoint at the price you mean\u201D"),
     maxContentLength: external_exports.number().int().positive().max(MAX_CONTENT).default(2e3).describe('Characters of the element\u2019s rendered text to return; past that it is cut and "truncated" comes back true'),
-    timeoutMs: external_exports.number().int().min(5e3).max(3e5).default(6e4).describe("How long to wait for the user to click before giving up")
+    timeoutMs: external_exports.number().int().min(5e3).max(3e5).default(PICK_DEFAULT_TIMEOUT_MS).describe("How long to wait for the user to click before giving up")
   }),
   async execute({ hint, maxContentLength, timeoutMs }) {
-    if (lensIsUp()) {
-      throw new ActionError("A-Eye is already waiting for the user to point at something", "ACTION_FAILED");
-    }
     const outcome = await pickWithLens({ hint, timeoutMs });
     if ("timedOut" in outcome) {
       throw new ActionError(
@@ -28824,12 +28843,18 @@ var pickElement = defineAction({
     const element = outcome.picked;
     const rendered2 = element instanceof HTMLElement ? element.innerText : element.textContent ?? "";
     const content = rendered2.replace(/\n{3,}/g, "\n\n").trim() || accessibleText(element);
+    const rect = element.getBoundingClientRect();
     return {
       element: describeElement(element),
       content: content.slice(0, maxContentLength),
       truncated: content.length > maxContentLength,
       url: location.href,
-      title: document.title
+      title: document.title,
+      capture: {
+        region: { x: rect.x, y: rect.y, w: rect.width, h: rect.height },
+        viewport: { w: window.innerWidth, h: window.innerHeight },
+        dpr: window.devicePixelRatio || 1
+      }
     };
   }
 });
@@ -29141,6 +29166,64 @@ function renderDiagram2(tree) {
   return lines.join("\n");
 }
 
+// ../lib/actions/page/toolkit.ts
+var TOOLKIT_ATTRIBUTE = "data-browsentic-toolkit";
+var TOOLKIT_CALL_EVENT = "browsentic:toolkit:call";
+var TOOLKIT_RESULT_EVENT = "browsentic:toolkit:result";
+var TOOLKIT_MISSING = "TOOLKIT_MISSING";
+var CODE_ERROR = "CODE_ERROR";
+function callToolkit(fn, args, timeoutMs) {
+  if (!document.documentElement.hasAttribute(TOOLKIT_ATTRIBUTE)) {
+    throw new ActionError("No toolkit is installed in this page.", TOOLKIT_MISSING);
+  }
+  const callId = crypto.randomUUID();
+  return new Promise((resolve, reject) => {
+    const onResult = (event) => {
+      const reply = parseReply(event.detail);
+      if (reply?.id !== callId) return;
+      stop2();
+      if (reply.ok) resolve(reply.value ?? null);
+      else reject(new ActionError(reply.error ?? "The function threw.", CODE_ERROR));
+    };
+    const timer = setTimeout(() => {
+      stop2();
+      reject(new ActionError(`\u201C${fn}\u201D did not finish within ${timeoutMs}ms.`, "TIMEOUT"));
+    }, timeoutMs);
+    function stop2() {
+      clearTimeout(timer);
+      window.removeEventListener(TOOLKIT_RESULT_EVENT, onResult);
+    }
+    window.addEventListener(TOOLKIT_RESULT_EVENT, onResult);
+    window.dispatchEvent(
+      new CustomEvent(TOOLKIT_CALL_EVENT, { detail: JSON.stringify({ id: callId, fn, args }) })
+    );
+  });
+}
+function parseReply(detail) {
+  if (typeof detail !== "string") return null;
+  try {
+    return JSON.parse(detail);
+  } catch {
+    return null;
+  }
+}
+
+// ../lib/actions/page/run-code.ts
+var runCode = defineAction({
+  name: "page.runCode",
+  description: "Call one function from the toolkit page.injectCode installed in this tab, with fresh arguments. This is the cheap, repeatable half of the pair: the user approved the code once, so every call runs without another prompt, and a page reload re-installs the approved toolkit on its own. It refuses if nothing is installed here, or if the tab has moved to a different site than the one the code was approved on \u2014 inject again in either case. The function\u2019s return value comes back as JSON.",
+  input: external_exports.object({
+    function: external_exports.string().min(1).describe("Name of a function the installed toolkit assigned onto `tools`."),
+    args: external_exports.array(external_exports.unknown()).default([]).describe(
+      "Arguments passed to the function, in order. JSON values only \u2014 this is where per-call data like a tag name belongs."
+    ),
+    timeoutMs: external_exports.number().int().min(100).max(12e4).default(1e4).describe("How long the call may run before it is abandoned. Raise it for functions that wait on the page.")
+  }),
+  async execute({ function: fn, args, timeoutMs }) {
+    return { function: fn, returned: await callToolkit(fn, args, timeoutMs) };
+  }
+});
+
 // ../lib/actions/page/screenshot.ts
 var screenshot = defineAction({
   name: "page.screenshot",
@@ -29846,6 +29929,8 @@ var actions = new Map(
     pressKey,
     submitForm,
     waitForElement,
+    injectCode,
+    runCode,
     findProgress,
     findSearch,
     readTheme,
@@ -29895,7 +29980,8 @@ var AGENTS = {
     vendor: "Anthropic",
     bin: "claude",
     install: "npm i -g @anthropic-ai/claude-code",
-    docs: "https://claude.com/claude-code"
+    docs: "https://claude.com/claude-code",
+    models: ["claude-fable-5", "claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"]
   },
   codex: {
     kind: "codex",
@@ -29903,7 +29989,8 @@ var AGENTS = {
     vendor: "OpenAI",
     bin: "codex",
     install: "npm i -g @openai/codex",
-    docs: "https://developers.openai.com/codex/cli"
+    docs: "https://developers.openai.com/codex/cli",
+    models: ["gpt-5.6-terra", "gpt-5.1-codex-max", "gpt-5.1-codex", "gpt-5.1-codex-mini"]
   },
   antigravity: {
     kind: "antigravity",
@@ -29911,7 +29998,8 @@ var AGENTS = {
     vendor: "Google",
     bin: "agy",
     install: "https://antigravity.google/docs/cli/install",
-    docs: "https://antigravity.google/docs/cli"
+    docs: "https://antigravity.google/docs/cli",
+    models: ["gemini-3-pro", "gemini-3-flash"]
   }
 };
 var AGENT_LIST = AGENT_KINDS.map((kind) => AGENTS[kind]);
@@ -29925,11 +30013,13 @@ var SAVE_SITE_MAP_ACTION = `${RESERVED_PREFIX}saveSiteMap`;
 var START_RECORDING_ACTION = `${RESERVED_PREFIX}startRecording`;
 var STOP_RECORDING_ACTION = `${RESERVED_PREFIX}stopRecording`;
 var READ_SITEMAP_ACTION = `${RESERVED_PREFIX}readSitemap`;
+var FOCUS_SHOT_ACTION = `${RESERVED_PREFIX}focusShot`;
 var RESERVED_ACTIONS = [
   SAVE_SITE_MAP_ACTION,
   START_RECORDING_ACTION,
   STOP_RECORDING_ACTION,
-  READ_SITEMAP_ACTION
+  READ_SITEMAP_ACTION,
+  FOCUS_SHOT_ACTION
 ];
 
 // ../lib/actions/tool-names.ts
@@ -30243,6 +30333,15 @@ var claudeRunner = {
     };
   },
   reader() {
+    let generated = 0;
+    const report = (usage, sink) => {
+      if (!usage) return;
+      generated += usage.output_tokens ?? 0;
+      sink.usage({
+        contextTokens: (usage.input_tokens ?? 0) + (usage.cache_read_input_tokens ?? 0) + (usage.cache_creation_input_tokens ?? 0) + (usage.output_tokens ?? 0),
+        outputTokens: generated
+      });
+    };
     return (line, sink) => {
       const message = parseJsonLine(line);
       if (!message) return;
@@ -30266,10 +30365,14 @@ var claudeRunner = {
           }
           return;
         }
+        case "assistant":
+          if (!message.parent_tool_use_id) report(message.message?.usage, sink);
+          return;
         case "result":
           if (message.is_error) {
             return sink.fail("AGENT_FAILED", message.result || message.subtype || "Claude Code reported an error");
           }
+          if (!generated) report(message.usage, sink);
           return sink.done(message.stop_reason || "end_turn");
       }
     };
@@ -30580,6 +30683,17 @@ var codexRunner = {
             return finish(msg.message, sink);
           case "web_search_begin":
             return sink.tool(randomUUID3(), WEB_TOOL);
+          case "token_count": {
+            const last = msg.info?.last_token_usage ?? msg.info?.total_token_usage;
+            const total = msg.info?.total_token_usage ?? last;
+            if (last) {
+              sink.usage({
+                contextTokens: (last.input_tokens ?? 0) + (last.output_tokens ?? 0),
+                outputTokens: total?.output_tokens ?? 0
+              });
+            }
+            return;
+          }
           case "task_complete":
             return sink.done("end_turn");
           case "error":
@@ -30603,8 +30717,16 @@ var codexRunner = {
           if (kind === "web_search") return sink.tool(item?.id ?? randomUUID3(), WEB_TOOL);
           return;
         }
-        case "turn.completed":
+        case "turn.completed": {
+          const usage = frame.usage;
+          if (usage) {
+            sink.usage({
+              contextTokens: (usage.input_tokens ?? 0) + (usage.output_tokens ?? 0),
+              outputTokens: usage.output_tokens ?? 0
+            });
+          }
           return sink.done("end_turn");
+        }
         case "turn.failed":
           return sink.fail("AGENT_FAILED", frame.error?.message || "Codex could not finish the turn");
         case "error":
@@ -31181,6 +31303,26 @@ var DEFAULT_RULES = [
     title: "Saves a file from the page to disk",
     reason: "That writes a file the page chose into the user\u2019s download folder."
   },
+  {
+    // The most powerful thing an agent can ask for, and the one gate that has to show
+    // its work: the panel puts the source behind a Review button, because "allow this
+    // action?" is not a question anyone can answer about code they have not read. It
+    // confirms rather than denies because a reviewed function is how twenty repetitions
+    // stop being twenty round trips — and `unattended: deny` keeps an external MCP
+    // client, which has nobody to show the code to, from installing any at all.
+    id: "code-injection",
+    when: "injectsCode",
+    effect: "confirm",
+    title: "Runs code it wrote in the page",
+    reason: "That installs JavaScript the agent wrote into the page, with your logged-in session."
+  },
+  {
+    id: "external-code-execution",
+    when: "runsCodeOutsideThePanel",
+    effect: "deny",
+    title: "Calls injected code from outside the panel",
+    reason: "Code installed by page.injectCode was reviewed and approved for the side-panel conversation that asked for it. It is not available to an MCP client."
+  },
   {
     id: "leaves-pinned-tab",
     when: "leavesPinnedTab",
@@ -31707,6 +31849,7 @@ function invokeTimeoutFor(action, input2) {
   const declared = input2?.timeoutMs;
   if (typeof declared === "number" && declared > 0) return declared + 1e4;
   if (action === awaitMonitor.name) return AWAIT_DEFAULT_TIMEOUT_MS + 1e4;
+  if (action === pickElement.name) return PICK_DEFAULT_TIMEOUT_MS + 1e4;
   return REQUEST_TIMEOUT_MS;
 }
 
@@ -33455,6 +33598,12 @@ var Server = class extends Protocol {
 // server.ts
 var STATUS_TOOL = toolNameFor(`${RESERVED_PREFIX}status`);
 var SCREENSHOT_TOOL = "page_screenshot";
+var PICK_TOOL = "page_pickElement";
+var FOCUS_SHOT_TOOL = {
+  name: toolNameFor(FOCUS_SHOT_ACTION),
+  description: "Show the screenshot of the element the user pointed at with A-Eye, taken at the instant they picked it. Only answers when the current instruction arrived with a pick attached.",
+  inputSchema: { type: "object", properties: {}, additionalProperties: false }
+};
 var RESOURCES = [
   {
     uri: "browsentic://page/current",
@@ -33568,7 +33717,7 @@ function createMcpServer(bridge, version2, opts = {}) {
           description: "Report whether the Browsentic browser extension is connected, its version, and the active tab. Use this first if a page tool fails.",
           inputSchema: { type: "object", properties: {}, additionalProperties: false }
         },
-        ...opts.agentRun ? [SAVE_SITE_MAP_TOOL] : []
+        ...opts.agentRun ? [SAVE_SITE_MAP_TOOL, FOCUS_SHOT_TOOL] : []
       ]
     };
   });
@@ -33577,6 +33726,8 @@ function createMcpServer(bridge, version2, opts = {}) {
     const action = actionNameFor(params.name);
     const result = await bridge.invoke(action, params.arguments ?? {});
     if (params.name === SCREENSHOT_TOOL) return renderScreenshot(result);
+    if (params.name === FOCUS_SHOT_TOOL.name) return renderFocusShot(result);
+    if (params.name === PICK_TOOL) return renderPick(result, shouldFence(action, policy) ? tag2 : void 0);
     return render(result, shouldFence(action, policy) ? tag2 : void 0);
   });
   server.setRequestHandler(ListResourcesRequestSchema, async () => ({ resources: [...RESOURCES] }));
@@ -33654,6 +33805,38 @@ function renderScreenshot(result) {
     ]
   };
 }
+function renderPick(result, fenceWith) {
+  if (!result.ok) return render(result, fenceWith);
+  const { shot, ...rest } = result.data;
+  if (typeof shot?.dataUrl !== "string") return render(result, fenceWith);
+  const [mimeType, base643] = splitDataUrl(shot.dataUrl);
+  const rendered2 = render({ ok: true, data: rest }, fenceWith);
+  return {
+    content: [
+      ...rendered2.content,
+      { type: "image", data: base643, mimeType },
+      {
+        type: "text",
+        text: `${IMAGE_NOTE} This is the picked element photographed at the instant the user clicked it.`
+      }
+    ]
+  };
+}
+function renderFocusShot(result) {
+  if (!result.ok) return render(result);
+  const dataUrl = result.data?.dataUrl;
+  if (typeof dataUrl !== "string") return render(result);
+  const [mimeType, base643] = splitDataUrl(dataUrl);
+  return {
+    content: [
+      { type: "image", data: base643, mimeType },
+      {
+        type: "text",
+        text: `${IMAGE_NOTE} This is the element the user pointed at with A-Eye, as it stood when they picked it.`
+      }
+    ]
+  };
+}
 function splitDataUrl(dataUrl) {
   const match = /^data:([^;,]+);base64,(.*)$/s.exec(dataUrl);
   return match ? [match[1], match[2]] : ["image/png", ""];
@@ -33679,7 +33862,7 @@ function text2(uri, mimeType, body) {
 // package.json
 var package_default = {
   name: "browsentic",
-  version: "0.4.6",
+  version: "0.4.9",
   description: "Hand your real, logged-in browser to the AI agent you already run. Installs the browser extension, runs the local daemon, and speaks MCP.",
   type: "module",
   license: "MIT",