@@ -2,6 +2,24 @@ # Changelog
 
 All notable changes to pi-browser-harness will be documented in this file.
 
+## 0.3.1 — 2026-05-02
+
+### Bug fixes
+
+- **`browser_list_tabs`** now shows full 32-character targetIds instead of truncated `BE9DD1DC…` prefixes. The `browser_list_tabs` → `browser_switch_tab` round-trip is repaired.
+- **`browser_switch_tab`** now supports prefix matching: pass a unique hex prefix (≥8 chars) and it resolves to the full targetId automatically. Ambiguous prefixes return a clear error listing all matching tabs.
+- **`browser_download`** auto-creates the download directory with `mkdir -p` if it doesn't exist. Previously it required a pre-existing writable directory.
+- **`ensureAlive()`** now probes the page session with `Runtime.evaluate("1")` after the transport health check. If the page target has crashed (e.g. localhost server died), it reattaches automatically instead of returning a cryptic `session_not_found` error on the next tool call.
+
+### Docs & metadata
+
+- **`browser_dispatch_key`** prompt guidelines now explicitly note it dispatches a synthetic DOM `KeyboardEvent` and does NOT type text. Point users to `browser_type` / `browser_press_key` for actual text input.
+- **`browser_navigate`** prompt guidelines now warn that Google and strict-anti-bot sites may reject CDP navigation. `browser_http_get` is the recommended workaround.
+- **`browser_get_network_log`** prompt snippet updated with explicit workaround (`browser_execute_js` with `PerformanceObserver`).
+- **`sharp`** added to `optionalDependencies` so `npm install` attempts it (enables `browser_screenshot` `maxDim` auto-resize).
+- **`SKILL.md`** script bindings section updated to document the actual daemon API: `daemon.evaluateJs()`, `daemon.pageInfo()`, `daemon.listTabs()`, `daemon.session().call()`. Example script updated to match.
+- **`SKILL.md`** troubleshooting section now covers `sharp`/`maxDim` and Google anti-bot navigation.
+
 ## 0.3.0 — 2026-05-02
 
 ### Internal rewrite

@@ -1,6 +1,6 @@
 {
   "name": "pi-browser-harness",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Browser control extension for pi — navigate, click, type, screenshot, and extract data from real Chrome via CDP",
   "keywords": [
     "pi-package",
@@ -61,6 +61,9 @@ "prepublishOnly": "tsc --noEmit"
   },
   "publishConfig": {
     "access": "public"
+  },
+  "optionalDependencies": {
+    "sharp": "^0.33.0"
   },
   "dependencies": {
     "ws": "^8.20.0"

@@ -130,7 +130,18 @@ - Don't try to call browser_* tools from within a script — sequence them as separate tool calls.
 
 **Script bindings:**
 - `params` — the arguments passed to browser_run_script
-- `daemon` — browser daemon (daemon.cdp(), daemon.evaluateJS(), daemon.getPageInfo(), etc.)
+- `daemon` — browser daemon with these methods:
+  - `daemon.evaluateJs(expression)` — run JS in the current page
+  - `daemon.pageInfo()` — get current page info or dialog
+  - `daemon.listTabs()` — returns `{ success, data: [{ targetId, url, title }] }`
+  - `daemon.switchTab(targetId)` — switch to a tab by full targetId
+  - `daemon.newTab(url?)` — open and switch to a new tab
+  - `daemon.current()` — returns `{ targetId, url?, title? }`
+  - `daemon.session(targetId)` — returns a session object for raw CDP:
+    - `session.call(method, params?)` — CDP command on the page target
+    - `session.callOnTarget(method, params, sessionId)` — CDP on a specific session
+    - `session.callBrowser(method, params?)` — CDP on the browser target
+    - `session.takeDialog()` — get/dismiss pending dialog
 - `require` — Node.js require() (use 'fs', 'path', 'crypto', etc.)
 - `signal` — AbortSignal for cancellation
 - `onUpdate` — progress callback: onUpdate({ content: [{ type: 'text', text: '...' }] })
@@ -140,9 +151,9 @@
 **Example — a script that extracts structured data:**
 ```javascript
 // /tmp/extract-products.js
-const info = await daemon.getPageInfo();
-if ("dialog" in info) throw new Error("Dialog is blocking: " + info.dialog.message);
-const data = await daemon.evaluateJS(`
+const info = await daemon.pageInfo();
+if (info && "dialog" in info) throw new Error("Dialog is blocking: " + info.dialog.message);
+const data = await daemon.evaluateJs(`
   JSON.stringify(Array.from(document.querySelectorAll('${params.rowSelector}')).map(el => ({
     title: el.querySelector('${params.titleSelector}')?.textContent?.trim(),
     price: el.querySelector('${params.priceSelector}')?.textContent?.trim(),
@@ -196,6 +207,8 @@ - **"DevToolsActivePort not found"**: Open chrome://inspect/#remote-debugging, tick checkbox, click Allow
 - **Stale session**: Run `/browser-reload-daemon` to restart the daemon
 - **Dialog blocking**: Run browser_page_info to detect it, then browser_handle_dialog
 - **Status check**: Run `/browser-status` to see daemon health and current page
+- **Screenshot maxDim not working**: Install sharp (`npm install sharp`) for auto-resize support
+- **Google navigation fails**: Google's anti-bot detection may reject CDP navigation; use `browser_http_get` to fetch search results instead
 
 ## Architecture
 

@@ -108,12 +108,26 @@ return start();
     }
     if (Date.now() - lastHealth < HEALTH_TTL_MS) return ok(undefined);
     const probe = await transport.request("Target.getTargets", {}, { sessionId: null, timeoutMs: 2_000 });
-    if (probe.success) {
-      lastHealth = Date.now();
-      return ok(undefined);
+    if (!probe.success) {
+      await stop();
+      return start();
     }
-    await stop();
-    return start();
+    lastHealth = Date.now();
+    // Verify the page session is still responsive (handles the case where the
+    // browser transport is alive but the page target crashed, e.g. localhost died).
+    const jsProbe = await session.call("Runtime.evaluate", {
+      expression: "1", returnByValue: true,
+    }, { timeoutMs: 2_000 });
+    if (!jsProbe.success && jsProbe.error.kind === "session_not_found") {
+      const reattached = await session.attachFirstPage();
+      if (reattached.success) {
+        pageCache = null;
+        return ok(undefined);
+      }
+      await stop();
+      return start();
+    }
+    return ok(undefined);
   };
 
   const evaluateJs = async (expression: string, sessionId?: string): Promise<Result<unknown, CdpError>> => {

@@ -1,4 +1,4 @@
-import { access, constants, stat, readFile, writeFile } from "node:fs/promises";
+import { mkdir, access, constants, stat, readFile, writeFile } from "node:fs/promises";
 import { basename } from "node:path";
 import { Type } from "typebox";
 import type { BrowserClient } from "../client";
@@ -135,6 +135,14 @@ "Affects all subsequent downloads on this browser.",
   ],
   parameters: DownloadArgs,
   async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
+    try {
+      await mkdir(args.downloadPath, { recursive: true });
+    } catch (e) {
+      return err({
+        kind: "io_error",
+        message: `Cannot create download directory: ${args.downloadPath} (${e instanceof Error ? e.message : String(e)})`,
+      });
+    }
     try {
       const s = await stat(args.downloadPath);
       if (!s.isDirectory()) {

@@ -91,6 +91,7 @@ description:
     "Dispatch a DOM KeyboardEvent on a specific element via JS injection. Use for React/Vue components that listen to synthetic events more reliably than CDP input.",
   promptSnippet: "Dispatch a DOM KeyboardEvent on a specific element",
   promptGuidelines: [
+    "Dispatches a synthetic DOM KeyboardEvent — for React/Vue synthetic event listeners. Does NOT insert text into inputs (use browser_type or browser_press_key for actual typing).",
     "Try browser_press_key first; only use browser_dispatch_key when the page ignores raw CDP key events.",
     "The selector must match exactly one or more elements; zero matches is reported as an error.",
     "eventType defaults to 'keydown'.",

@@ -22,6 +22,7 @@ promptGuidelines: [
     "Use browser_navigate to go to URLs.",
     "Use browser_wait_for_load after browser_navigate to wait for the page to finish loading.",
     "For extracting data from a page you already navigated to, use browser_execute_js or browser_http_get (faster for APIs).",
+    "Note: Google and some sites with strict anti-bot detection may reject CDP navigation. Use browser_http_get for search results.",
   ],
   parameters: NavigateArgs,
   renderCall: (a) => new Text(`🌐 Navigate to ${a.url}`, 0, 0),

@@ -61,7 +61,7 @@ name: "browser_get_network_log",
   label: "Browser Get Network Log",
   description:
     "Read buffered Network.* CDP events. NOTE: in v0.3 the event stream is consumed internally by the session manager; this tool is a placeholder. Use browser_execute_js with PerformanceObserver as a workaround.",
-  promptSnippet: "Get buffered network events (DEPRECATED in v0.3 — see description)",
+  promptSnippet: "Get buffered network events (DEPRECATED in v0.3 — use browser_execute_js with PerformanceObserver instead)",
   promptGuidelines: [
     "v0.3 routes CDP events through an internal AsyncIterable; a synchronous drain API isn't exposed yet.",
     "For now, use browser_execute_js with PerformanceObserver, performance.getEntries(), or fetch interceptors.",

@@ -12,14 +12,15 @@ label: "Browser List Tabs",
   description: "List all open browser tabs (page targets).",
   promptSnippet: "List browser tabs",
   promptGuidelines: [
-    "Use to find a targetId for browser_switch_tab.",
+    "Use to find a full targetId for browser_switch_tab.",
     "Internal tabs (chrome://) included by default; pass includeInternal=false to exclude them.",
+    "Each tab shows its full 32-char hex targetId — use the exact value with browser_switch_tab.",
   ],
   parameters: ListTabsArgs,
   async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
     const r = await client.listTabs(args.includeInternal ?? true);
     if (!r.success) return err({ kind: "cdp_error", message: r.error.message });
-    const lines = r.data.map((t, i) => `  [${i}] ${t.targetId.slice(0, 8)}… ${t.url}\n      ${t.title}`);
+    const lines = r.data.map((t, i) => `  [${i}] ${t.targetId} ${t.url}\n      ${t.title}`);
     return ok({
       text: `Tabs (${r.data.length}):\n${lines.join("\n")}`,
       details: { tabs: r.data },
@@ -56,12 +57,43 @@ name: "browser_switch_tab",
   label: "Browser Switch Tab",
   description: "Switch to and attach to a different tab by targetId.",
   promptSnippet: "Switch tabs",
-  promptGuidelines: ["Get a targetId via browser_list_tabs first."],
+  promptGuidelines: [
+    "Get a targetId via browser_list_tabs first.",
+    "Accepts exact targetId or a unique prefix of at least 8 hex characters.",
+  ],
   parameters: SwitchTabArgs,
   async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
-    const r = await client.switchTab(args.targetId);
+    // Try exact match first
+    let r = await client.switchTab(args.targetId);
+    if (r.success) {
+      return ok({ text: `Switched to ${args.targetId}`, details: { targetId: args.targetId } });
+    }
+    // If exact match failed and input looks like a short prefix (≥8 hex chars), try prefix resolution
+    const isHexPrefix = /^[0-9A-Fa-f]{8,}$/.test(args.targetId);
+    if (!isHexPrefix) {
+      return err({ kind: "cdp_error", message: r.error.message });
+    }
+    const tabs = await client.listTabs(true);
+    if (!tabs.success) return err({ kind: "cdp_error", message: r.error.message });
+    const matches = tabs.data.filter((t) => t.targetId.startsWith(args.targetId));
+    if (matches.length === 0) {
+      return err({ kind: "cdp_error", message: `No tab found with prefix "${args.targetId}"` });
+    }
+    if (matches.length > 1) {
+      const ids = matches.map((t) => t.targetId).join(", ");
+      return err({
+        kind: "invalid_state",
+        message: `Ambiguous prefix "${args.targetId}" matches ${matches.length} tabs: ${ids}`,
+        details: { matches: matches.map((t) => ({ targetId: t.targetId, url: t.url })) },
+      });
+    }
+    const resolved = matches[0]!.targetId;
+    r = await client.switchTab(resolved);
     if (!r.success) return err({ kind: "cdp_error", message: r.error.message });
-    return ok({ text: `Switched to ${args.targetId}`, details: { targetId: args.targetId } });
+    return ok({
+      text: `Switched to ${resolved} (resolved from prefix "${args.targetId}")`,
+      details: { targetId: resolved, resolvedPrefix: args.targetId },
+    });
   },
 });