pi-browser-harness 0.11.0 → 0.12.0

package/src/domains/files.ts

@@ -104,7 +104,7 @@ export const uploadFileTool = defineBrowserTool({
   description: "Set files on a file <input> via CDP, with a JS-DataTransfer fallback for stubborn pages. PREFERRED: pass `ref` from browser_snapshot; fallback: a CSS `selector`.",
   promptSnippet: "Upload a file to a file input by ref (preferred) or selector",
   promptGuidelines: [
-    "PREFER `ref` from browser_snapshot over a CSS selector — survives re-renders. (File inputs are often hidden; snapshot still surfaces them.)",
+    "File inputs are often hidden; browser_snapshot still surfaces them.",
     "File path must be absolute and readable.",
   ],
   parameters: UploadArgs,
@@ -145,22 +145,70 @@ export const uploadFileTool = defineBrowserTool({
   },
 });
 
+// Chrome stores the override in its default browser context, so it outlives this client and
+// silently redirects the user's own downloads. Track it, so session teardown can undo it.
+// The flag only records what THIS process set: the daemon is shared by every pi process on the
+// machine and the CDP primitive is last-writer-wins, so another session may have reset or
+// re-pointed it since. A crashed or killed session never reaches teardown, so the override can
+// also outlive the process that set it.
+let activeDownloadOverride: string | undefined;
+
+// Shutdown must not block on a browser that is already gone: a pending restore against a
+// disconnected daemon would otherwise trigger the one-shot reconnect (and Chrome's consent
+// prompt) that 0.11.1 confined to explicit tool calls, and wait up to the connect timeout.
+const SHUTDOWN_RESTORE_TIMEOUT_MS = 2_000;
+
+export const restoreDownloadBehavior = async (client: BrowserClient): Promise<Result<void, ToolErr>> => {
+  const pending = activeDownloadOverride;
+  if (pending === undefined) return ok(undefined);
+  if (!client.status().alive) {
+    return err({ kind: "not_connected", message: `browser not connected; downloads may keep going to ${pending} until Chrome restarts` });
+  }
+  const r = await cdpCallBrowser(client, "Browser.setDownloadBehavior", { behavior: "default" }, { timeoutMs: SHUTDOWN_RESTORE_TIMEOUT_MS });
+  if (!r.success) {
+    return err({ ...r.error, message: `${r.error.message} (downloads may keep going to ${pending})` });
+  }
+  activeDownloadOverride = undefined;
+  return ok(undefined);
+};
+
 const DownloadArgs = Type.Object({
-  downloadPath: Type.String({ description: "Absolute path to a writable directory where downloads should be saved" }),
+  downloadPath: Type.Optional(
+    Type.String({ description: "Absolute path to a writable directory where downloads should be saved" }),
+  ),
+  restore: Type.Optional(
+    Type.Boolean({
+      description:
+        "Undo a previous browser_download: reset Chrome's download behavior back to the user's own default.",
+    }),
+  ),
 });
 
 export const downloadTool = defineBrowserTool({
   name: "browser_download",
   label: "Browser Download",
-  description: "Configure Chrome's download behavior: set the save directory and disable the save-as prompt.",
+  description:
+    "Configure Chrome's download behavior: set the save directory and disable the save-as prompt, or restore the user's default. Restored automatically when this session shuts down cleanly.",
   promptSnippet: "Configure download directory",
   promptGuidelines: [
     "Pass an absolute path to an existing writable directory.",
-    "Affects all subsequent downloads on this browser.",
+    "The override applies to the user's own downloads too, not just yours, and only a clean session shutdown undoes it. Call browser_download({restore:true}) as soon as you are done.",
   ],
   parameters: DownloadArgs,
   concurrency: "serialized",
   async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
+    if (args.restore === true) {
+      if (args.downloadPath !== undefined) {
+        return err({ kind: "invalid_state", message: "Pass either downloadPath or restore, not both" });
+      }
+      const r = await cdpCallBrowser(client, "Browser.setDownloadBehavior", { behavior: "default" });
+      if (!r.success) return r;
+      activeDownloadOverride = undefined;
+      return ok({ text: "Downloads restored to Chrome's default location", details: { restored: true } });
+    }
+    if (args.downloadPath === undefined) {
+      return err({ kind: "invalid_state", message: "Provide downloadPath to set a directory, or restore:true to undo" });
+    }
     try {
       await mkdir(args.downloadPath, { recursive: true });
     } catch (e) {
@@ -187,6 +235,7 @@ export const downloadTool = defineBrowserTool({
       eventsEnabled: true,
     });
     if (!r.success) return r;
+    activeDownloadOverride = args.downloadPath;
     return ok({
       text: `Downloads will save to: ${args.downloadPath}`,
       details: { downloadPath: args.downloadPath },

package/src/domains/form-batch.ts

@@ -28,7 +28,6 @@ export const fillFormTool = defineBrowserTool({
   promptSnippet: "Fill many form fields at once by ref — React-safe, self-confirming",
   promptGuidelines: [
     "Preferred for forms: snapshot once, then fill all fields in a single browser_fill_form call.",
-    "Each field: { ref, value }. value is a string for text/select/contenteditable, boolean for checkbox/radio.",
     "The result summarizes how many fields filled cleanly and flags any value mismatches or per-field errors.",
     "Re-run browser_snapshot afterwards to verify the form state if needed.",
   ],

package/src/domains/form.ts

@@ -27,15 +27,12 @@ export const fillTool = defineBrowserTool({
     "Fill a form field (input/textarea/contenteditable), or tick a checkbox/radio by passing 'true'/'false'. PREFERRED: pass `ref` (e.g. 'e7') from browser_snapshot — survives re-renders. Fallback: a CSS `selector`. Writes through the native value setter and fires bubbling 'input'/'change' events, so React/Vue/Angular controlled components and rich-text editors update correctly — unlike browser_type. Refuses a disabled field rather than writing a value the page will ignore. Returns the field's value after writing, plus a compact diff of page changes.",
   promptSnippet: "Fill a form field by ref (preferred) or selector (works with React/Vue controlled inputs)",
   promptGuidelines: [
-    "PREFER `ref` from browser_snapshot (the '[eN]' handle) over a guessed CSS selector — refs survive re-renders and don't require you to invent a selector.",
     "Pass the desired value; no browser_click is needed first.",
     "For a checkbox or radio pass 'true' or 'false' — it toggles `checked`, not the submit value. browser_set_checked does the same thing with a boolean.",
-    "A disabled field is refused: the error says so, rather than reporting a write the page never accepted.",
-    "A 'ref is stale' error means the page changed — re-run browser_snapshot to get fresh refs.",
     "Use browser_type instead only for keystroke-sensitive widgets (autocomplete, masked/segmented inputs).",
     "Fill sets the value but does not focus or submit. To submit a tag/autocomplete input, follow with browser_dispatch_key({ ref, key: 'Enter' }) — not browser_press_key, which targets the focused element and may miss this field.",
     "For a custom (div-based) dropdown, browser_fill won't validate against its option list — open it, run browser_snapshot, then browser_click the option's ref.",
-    "The result reports the field's value after writing and an appended page-changes diff — confirm both match what you intended before moving on.",
+    "Confirm the field value browser_fill returns matches what you intended.",
   ],
   parameters: FillArgs,
   concurrency: "serialized",
@@ -118,8 +115,6 @@ export const focusTool = defineBrowserTool({
     "Focus an element via the DOM .focus() method — deterministic, no coordinate accuracy needed. PREFERRED: pass `ref` from browser_snapshot; fallback: a CSS `selector`. Use before browser_type when a click might miss the field.",
   promptSnippet: "Focus an element by ref (preferred) or selector",
   promptGuidelines: [
-    "PREFER `ref` from browser_snapshot over a CSS selector — survives re-renders.",
-    "Use before browser_type to guarantee the right field is focused without relying on click coordinates.",
     "For simply setting a value, prefer browser_fill (it doesn't need a separate focus step).",
   ],
   parameters: FocusArgs,
@@ -196,10 +191,8 @@ export const selectOptionTool = defineBrowserTool({
     "Select an option in a native <select> element by value, visible label, or index. PREFERRED: pass `ref` from browser_snapshot; fallback: a CSS `selector`. Sets the selection and fires bubbling 'input'/'change' events so framework listeners update. On no match, returns the available options.",
   promptSnippet: "Select an option in a native <select> by ref (preferred) or selector",
   promptGuidelines: [
-    "PREFER `ref` from browser_snapshot over a CSS selector — survives re-renders.",
     "Provide exactly one of value, label, or index to choose the option.",
     "For custom (non-native) dropdowns built from divs, click to open then browser_click the option instead.",
-    "If no option matches, the error details list the available options so you can retry.",
   ],
   parameters: SelectOptionArgs,
   concurrency: "serialized",
@@ -263,7 +256,6 @@ export const setCheckedTool = defineBrowserTool({
     "Set a checkbox or radio to a desired checked state by ref. Only acts if the current state differs, fires change, and reports the final state. Get the ref from browser_snapshot's [eN].",
   promptSnippet: "Set a checkbox/radio checked state by ref",
   promptGuidelines: [
-    "checked:true ticks the box, checked:false unticks it. Idempotent — no-op if already in the desired state.",
     "For radios, set checked:true on the option you want; the group deselects the others.",
   ],
   parameters: SetCheckedArgs,

package/src/domains/headers.ts

@@ -0,0 +1,89 @@
+import { Type } from "typebox";
+import type { BrowserClient } from "../client";
+import { type Result, err, ok } from "../util/result";
+import { defineBrowserTool, type ToolErr, type ToolOk } from "../util/tool";
+import { cdpCall } from "./cdp-call";
+
+const HeaderValue = Type.String({
+  maxLength: 8192,
+  pattern: "^[^\\r\\n]*$",
+});
+
+const SetHeadersArgs = Type.Object({
+  headers: Type.Record(Type.String(), HeaderValue, {
+    minProperties: 1,
+    maxProperties: 64,
+    description: "Extra HTTP request headers for the current owned tab. Names must be valid HTTP tokens.",
+  }),
+});
+
+const HEADER_NAME = /^[!#$%&'*+\-.^_`|~0-9A-Za-z]+$/;
+
+const currentOwnedTarget = (
+  client: BrowserClient,
+): Result<{ readonly targetId: string }, ToolErr> => {
+  const current = client.current();
+  if (current === undefined || current === null) {
+    return err({ kind: "invalid_state", message: "No tab attached." });
+  }
+  if (!client.owns(current.targetId)) {
+    return err({
+      kind: "invalid_state",
+      message: `Current tab ${current.targetId} is not owned by this harness session.`,
+    });
+  }
+  return ok({ targetId: current.targetId });
+};
+
+export const setHeadersTool = defineBrowserTool({
+  name: "browser_set_headers",
+  label: "Browser Set Headers",
+  description:
+    "Set extra HTTP request headers on the current owned tab. Headers persist for subsequent document, subresource, fetch, and XHR requests until cleared or the tab closes.",
+  promptSnippet: "Set extra request headers on the current owned tab",
+  promptGuidelines: [
+    "If no tab is attached yet, call browser_new_tab without a URL first.",
+    "Call before navigation when a site requires routing or environment headers.",
+    "Call browser_clear_headers before switching tabs or navigating this tab to another origin.",
+    "Header values are never echoed in tool output.",
+  ],
+  parameters: SetHeadersArgs,
+  concurrency: "serialized",
+  async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
+    const target = currentOwnedTarget(client);
+    if (!target.success) return target;
+    const invalidName = Object.keys(args.headers).find((name) => !HEADER_NAME.test(name));
+    if (invalidName !== undefined) {
+      return err({ kind: "invalid_state", message: `Invalid HTTP header name: ${JSON.stringify(invalidName)}` });
+    }
+    const result = await cdpCall(client, "Network.setExtraHTTPHeaders", { headers: args.headers });
+    if (!result.success) return result;
+    const headerNames = Object.keys(args.headers).sort();
+    return ok({
+      text: `Set ${headerNames.length} extra HTTP header(s) on tab ${target.data.targetId}: ${headerNames.join(", ")}. Values are hidden. Clear them before switching tabs or navigating to another origin.`,
+      details: { targetId: target.data.targetId, headerNames, count: headerNames.length },
+    });
+  },
+});
+
+export const clearHeadersTool = defineBrowserTool({
+  name: "browser_clear_headers",
+  label: "Browser Clear Headers",
+  description: "Clear all extra HTTP request headers previously set on the current owned tab.",
+  promptSnippet: "Clear extra request headers from the current owned tab",
+  promptGuidelines: [
+    "Call after finishing an environment-specific workflow, before switching tabs, or before navigating to another origin.",
+  ],
+  parameters: Type.Object({}),
+  concurrency: "serialized",
+  async handler(_args, { client }): Promise<Result<ToolOk, ToolErr>> {
+    const target = currentOwnedTarget(client);
+    if (!target.success) return target;
+    const result = await cdpCall(client, "Network.setExtraHTTPHeaders", { headers: {} });
+    if (!result.success) return result;
+    return ok({
+      text: `Cleared extra HTTP headers from tab ${target.data.targetId}.`,
+      details: { targetId: target.data.targetId },
+    });
+  },
+});

package/src/domains/history.ts

@@ -18,7 +18,7 @@ export const goBackTool = defineBrowserTool({
   label: "Browser Go Back",
   description: "Navigate back one page in history.",
   promptSnippet: "Go back one page",
-  promptGuidelines: ["Use to return to the previous page after navigating."],
+  promptGuidelines: [],
   parameters: Type.Object({}),
   concurrency: "serialized",
   async handler(_a, { client }): Promise<Result<ToolOk, ToolErr>> {
@@ -38,7 +38,7 @@ export const goForwardTool = defineBrowserTool({
   label: "Browser Go Forward",
   description: "Navigate forward one page in history.",
   promptSnippet: "Go forward one page",
-  promptGuidelines: ["Use to undo a browser_go_back."],
+  promptGuidelines: [],
   parameters: Type.Object({}),
   concurrency: "serialized",
   async handler(_a, { client }): Promise<Result<ToolOk, ToolErr>> {
@@ -58,7 +58,7 @@ export const reloadTool = defineBrowserTool({
   label: "Browser Reload",
   description: "Reload the current page.",
   promptSnippet: "Reload the page",
-  promptGuidelines: ["Use to refresh the page, e.g. after server-side changes."],
+  promptGuidelines: [],
   parameters: Type.Object({}),
   concurrency: "serialized",
   async handler(_a, { client }): Promise<Result<ToolOk, ToolErr>> {

package/src/domains/js.ts

@@ -1,5 +1,6 @@
 import { readFile } from "node:fs/promises";
 import { resolve, isAbsolute } from "node:path";
+import { isPathWithin } from "../util/paths";
 import { tmpdir } from "node:os";
 import { createRequire } from "node:module";
 import { Type } from "typebox";
@@ -35,8 +36,6 @@ export const executeJsTool = defineBrowserTool({
     "DEFAULT for extracting a specific value: `document.querySelector('.price').innerText`, `input.value`, `el.getAttribute('aria-label')`, etc.",
     "For click coordinates not already in browser_snapshot: `JSON.stringify(document.querySelector('SELECTOR').getBoundingClientRect())` — beats a screenshot every time.",
     "For 'is this element visible / enabled / checked / focused', a one-liner here beats a screenshot every time.",
-    "DO NOT call browser_screenshot to read a value or check element state. Use this tool.",
-    "`return foo` is auto-wrapped in an IIFE — both `foo` and `(() => foo)()` work.",
     "For iframes, first run `Object.values(document.querySelectorAll('iframe'))` to find the iframe, then pass its targetId.",
     "Result must be JSON-serializable (Runtime.evaluate returnByValue=true).",
   ],
@@ -121,10 +120,7 @@ const allowedRoots = (): ReadonlyArray<string> => {
   return [tmpdir(), process.cwd(), ...(env !== undefined ? [env] : [])].map((d) => resolve(d));
 };
 
-const isPathAllowed = (p: string): boolean => {
-  const abs = resolve(p);
-  return allowedRoots().some((root) => abs === root || abs.startsWith(`${root}/`));
-};
+const isPathAllowed = (p: string): boolean => allowedRoots().some((root) => isPathWithin(root, p));
 
 const MAX_SOURCE_BYTES = 1_000_000;
 
@@ -140,9 +136,7 @@ export const runScriptTool = defineBrowserTool({
     "Execute a temporary JavaScript script with full Node.js + browser-daemon access. Path must be inside tmpdir, cwd, or BH_SCRIPT_DIR. Mandatory timeout. The script is full RCE on the harness's process — only invoke scripts you wrote and reviewed.",
   promptSnippet: "Run a temporary script with daemon + Node access (security-bounded)",
   promptGuidelines: [
-    "Write the script with the write tool first; pass its absolute path.",
-    "Path must be inside tmpdir, cwd, or BH_SCRIPT_DIR — otherwise rejected.",
-    "Default timeout is 60s; pass timeoutMs to extend (max 600s).",
+    "Write the script with the write tool first; pass its absolute path. Use the OS temp directory rather than hardcoding /tmp.",
     "Script bindings: params, daemon, require, signal, onUpdate, ctx, console, fetch, JSON, Buffer, setTimeout, clearTimeout.",
     "Script MUST return { content: [{ type: 'text', text: '...' }], details?: {...} }. Throw on errors.",
   ],

package/src/domains/keyboard.ts

@@ -31,7 +31,6 @@ export const typeTool = defineBrowserTool({
   description: "Type text into the currently focused element. Use browser_click first to focus an input field.",
   promptSnippet: "Type text into the focused element",
   promptGuidelines: [
-    "Use browser_type to enter text. Click on an input field with browser_click first to focus it.",
     "For special keys (Enter, Tab, Escape, arrows), use browser_press_key instead.",
   ],
   parameters: TypeArgs,
@@ -84,9 +83,7 @@ export const pressKeyTool = defineBrowserTool({
   promptSnippet: "Press a key (Enter, Tab, Escape, arrows, or any character)",
   promptGuidelines: [
     "Use browser_press_key for keyboard shortcuts and navigation keys.",
-    "Special key names: Enter, Tab, Backspace, Escape, Delete, ArrowLeft, ArrowUp, ArrowRight, ArrowDown, Home, End, PageUp, PageDown.",
-    "Use Space as ' ' (a single space character).",
-    "Modifiers: 1=Alt, 2=Ctrl, 4=Meta(Cmd), 8=Shift. Combine with bitwise OR: Ctrl+Shift = 2|8 = 10.",
+    "browser_press_key modifiers combine with bitwise OR: Ctrl+Shift = 2|8 = 10.",
   ],
   parameters: PressKeyArgs,
   concurrency: "serialized",
@@ -138,11 +135,9 @@ export const dispatchKeyTool = defineBrowserTool({
     "Dispatch a DOM KeyboardEvent on a specific element via JS injection. PREFERRED: pass `ref` from browser_snapshot; fallback: a CSS `selector`. Use for React/Vue components that listen to synthetic events more reliably than CDP input.",
   promptSnippet: "Dispatch a DOM KeyboardEvent on an element by ref (preferred) or selector",
   promptGuidelines: [
-    "PREFER `ref` from browser_snapshot over a CSS selector — survives re-renders.",
-    "Dispatches a synthetic DOM KeyboardEvent — for React/Vue synthetic event listeners. Does NOT insert text (use browser_type or browser_press_key for actual typing).",
+    "Does NOT insert text (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 event carries keyCode/which (e.g. 13 for Enter) for legacy handlers, but is untrusted (isTrusted === false) — a few libraries may still ignore it.",
-    "eventType defaults to 'keydown'.",
   ],
   parameters: DispatchKeyArgs,
   concurrency: "serialized",

package/src/domains/navigate.ts

@@ -22,8 +22,6 @@ export const navigateTool = defineBrowserTool({
     "Navigate to a URL. Creates a new tab on first call (when no real tabs exist). Otherwise navigates the current tab in place.",
   promptSnippet: "Navigate to a URL",
   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.",
   ],
@@ -80,7 +78,6 @@ export const openUrlsTool = defineBrowserTool({
   promptGuidelines: [
     "Use after browser_web_search to open citations in parallel.",
     "After opening, use browser_list_tabs / browser_switch_tab to navigate, then browser_snapshot to inspect each tab.",
-    "Use browser_wait_for_load on a tab before extracting data from SPAs.",
   ],
   parameters: OpenUrlsArgs,
   concurrency: "serialized",

package/src/domains/network.ts

@@ -24,7 +24,6 @@ export const httpGetTool = defineBrowserTool({
     "Fetch a URL outside the browser (faster than browser_navigate for APIs and static pages). Timeout covers headers AND body read.",
   promptSnippet: "HTTP GET (outside browser; for APIs/static pages)",
   promptGuidelines: [
-    "Faster than navigate+execute_js for JSON/HTML APIs.",
     "No JS rendering — for SPAs use browser_navigate.",
   ],
   parameters: HttpGetArgs,
@@ -224,8 +223,7 @@ export const networkRequestsTool = defineBrowserTool({
   promptSnippet: "Inspect recent network requests on the current page",
   promptGuidelines: [
     "Buffer is reset on tab switch — only requests on the current tab since attach are visible.",
-    'urlPattern is a substring; wrap in slashes for regex (e.g. "/\\\\.json$/").',
-    "includeResponseBodies:true costs an extra CDP call per matched request — use only when you need payloads.",
+    "Pass includeResponseBodies:true to browser_network_requests only when you need payloads.",
     "If bufferOverflowed:true in the result, older events were dropped (capacity 500 records/tab).",
   ],
   parameters: NetworkRequestsArgs,

package/src/domains/page.ts

@@ -28,10 +28,7 @@ export const pageInfoTool = defineBrowserTool({
     "Get current page state: URL, title, viewport size, scroll position, page dimensions. If a JS dialog is open, returns dialog info instead.",
   promptSnippet: "Get current page URL, title, viewport, and scroll position",
   promptGuidelines: [
-    "Use browser_page_info to quickly check what page you're on and whether a JS dialog is blocking interaction.",
-    "If browser_page_info returns a dialog, use browser_handle_dialog before any other browser actions.",
-    "JS dialogs freeze the page's JS thread, so no other interaction works until the dialog is handled.",
-    "browser_page_info auto-detects alert, confirm, prompt, and beforeunload dialogs.",
+    "If browser_page_info returns a dialog, call browser_handle_dialog before any other browser actions: dialogs freeze the page's JS thread.",
   ],
   parameters: Type.Object({}),
   concurrency: "parallel",
@@ -87,7 +84,6 @@ export const waitForLoadTool = defineBrowserTool({
   promptSnippet: "Wait for the page to finish loading",
   promptGuidelines: [
     "Call after browser_navigate / browser_open_urls before extracting data.",
-    "Returns when readyState becomes 'complete' OR the timeout elapses.",
   ],
   parameters: WaitForLoadArgs,
   concurrency: "serialized",
@@ -122,8 +118,6 @@ export const waitForTool = defineBrowserTool({
   promptSnippet: "Wait for an element or text to appear (or an element to disappear)",
   promptGuidelines: [
     "Use before browser_fill / browser_click on dynamic pages so you act after the element renders.",
-    "Provide selector (default: wait until present; gone:true: wait until absent) or text.",
-    "Returns a typed timeout error if the condition isn't met within the timeout.",
   ],
   parameters: WaitForArgs,
   concurrency: "parallel",

package/src/domains/readpage/read-page.ts

@@ -157,7 +157,6 @@ export const readPageTool = defineBrowserTool({
     "Read a page as clean article text — main content with nav/ads/boilerplate stripped. Pass a url (opened in an isolated tab, read, then closed) or a targetId of an owned tab. Reader-mode counterpart to browser_web_search.",
   promptSnippet: "Read a page's main content as clean text",
   promptGuidelines: [
-    "Pass url to read an arbitrary page (opened + closed in its own tab, never disturbing your current tab), or targetId to read an already-open owned tab.",
     "Returns readable main-article text — use this over browser_snapshot/browser_execute_js when you want an article's content for reading or research.",
     "Boilerplate-heavy or structure-less pages fall back to bounded body text rather than erroring.",
   ],

package/src/domains/screenshot.ts

@@ -20,10 +20,6 @@ export const screenshotTool = defineBrowserTool({
     "Capture the page as a JPEG/PNG image. NOT a default exploration tool. Use ONLY when (a) you need to verify visual properties (layout, color, spacing, rendered text legibility), or (b) browser_snapshot and browser_execute_js cannot answer your question. For understanding what's on the page use browser_snapshot. For specific element values use browser_execute_js. For click coordinates use the @(x,y) hints in browser_snapshot's outline.",
   promptSnippet: "Capture a screenshot — visual verification only",
   promptGuidelines: [
-    "DO NOT use as a default exploration tool. browser_snapshot is the default for understanding page structure — far cheaper and more reliable.",
-    "DO NOT use to find click coordinates. browser_snapshot already includes @(x,y) for every interactive element. If a target isn't there, use browser_execute_js with element.getBoundingClientRect().",
-    "DO use to verify visual rendering after an action: did the modal animate in correctly, did the chart render, are colors right, did the layout reflow as expected.",
-    "DO use as a debugging fallback when browser_execute_js or browser_snapshot return surprising results and you suspect the rendered page differs from the DOM.",
     "format='jpeg' with quality 60-90 keeps screenshots small for photo-heavy pages. Use maxDim if the page is huge.",
   ],
   parameters: ScreenshotArgs,

package/src/domains/scroll.ts

@@ -20,7 +20,6 @@ export const scrollTool = defineBrowserTool({
     "Scroll the page at given coordinates. deltaY follows W3C wheel-event convention: positive = scroll down, negative = scroll up. Default scrolls down (deltaY = 300).",
   promptSnippet: "Scroll the page (deltaY positive=down, negative=up)",
   promptGuidelines: [
-    "Default behavior scrolls down 300px (deltaY=300). Pass a negative deltaY to scroll up.",
     "Pass x/y to target a specific scrollable region (e.g., a div with overflow); otherwise scrolls the page at viewport center.",
   ],
   parameters: ScrollArgs,

package/src/domains/search/web-search.ts

@@ -77,7 +77,6 @@ export const webSearchTool = defineBrowserTool({
     "Search the web and return ranked results (title, url, snippet, rank). Scrapes a Google results page in the real Chrome — no API key. Returns links only; use browser_read_page to read a result's content.",
   promptSnippet: "Search the web for a query",
   promptGuidelines: [
-    "Returns ranked {title, url, snippet, rank} — links only, no page content. Follow up with browser_read_page.",
     "On a CAPTCHA / bot wall the call fails with kind:'invalid_state' and details.reason:'captcha' (plus serpUrl) — surface it to the user; do not retry in a tight loop.",
     "On zero results it fails with details.reason:'no_results' — rephrase the query and try again.",
     "Runs in its own isolated tab and never disturbs the user's current tab.",

package/src/domains/setup.ts

@@ -15,8 +15,6 @@ export const setupTool = defineBrowserTool({
     "Call when browser tools fail with 'Browser harness not initialized'. Idempotent.",
   promptSnippet: "Initialize browser connection",
   promptGuidelines: [
-    "Call browser_setup when you get a 'Browser harness not initialized' error from any browser tool.",
-    "This tool is idempotent — calling it when already connected is harmless.",
     "After browser_setup succeeds, retry the browser tool that failed.",
   ],
   parameters: SetupArgs,

package/src/domains/snapshot.ts

@@ -98,10 +98,7 @@ export const snapshotTool = defineBrowserTool({
     "DEFAULT tool for understanding what is on the page. Returns the structured accessibility tree (roles, names, states, hierarchy). Every interactive element gets a stable ref shown as [eN] plus click coordinates @(x,y). Pass the ref to browser_click/browser_fill/etc. — refs survive re-renders, coordinates don't. Use this BEFORE deciding whether you need a screenshot. Pair with browser_execute_js for surgical reads of specific element values.",
   promptSnippet: "Get accessibility-tree snapshot with stable element refs (default for page inspection)",
   promptGuidelines: [
-    "DEFAULT — use this whenever you need to know what's on a page, what's clickable, or how the page is structured.",
-    "Refs come for free: every interactive element shows '[eN]' in the outline. Pass eN as `ref` to browser_click/browser_fill/browser_select_option/browser_focus/browser_upload_file — refs survive re-renders, so prefer them over the '@(x,y)' coordinates (a fallback).",
-    "DO NOT call browser_screenshot just to understand the page. This tool already gives you structure, labels, states, refs, and click targets.",
-    "Re-run after a navigation or a major re-render to get fresh refs; a 'ref is stale' error from an interaction tool means you need a new snapshot.",
+    "Re-run browser_snapshot after a navigation or a major re-render to get fresh refs.",
     "Pass includeScreenshot:true ONLY if you also need to verify visual rendering (rare).",
     "format:'json' returns the raw slim structure (with `ref` and `box` per node) for programmatic use; default 'outline' is human/LLM-readable.",
   ],

package/src/domains/tabs.ts

@@ -19,10 +19,7 @@ export const listTabsTool = defineBrowserTool({
   description: "List browser tabs. Defaults to tabs this harness session opened (scope:'owned'). Pass scope:'all' to see the user's other tabs too.",
   promptSnippet: "List browser tabs",
   promptGuidelines: [
-    "Defaults to scope:'owned' — only tabs this session created. Pass scope:'all' to inspect the user's other tabs.",
-    "browser_switch_tab and browser_close_tab refuse non-owned tabs; use browser_new_tab to open one this session controls.",
     "Each tab shows its full 32-char hex targetId — use the exact value with browser_switch_tab.",
-    "Internal tabs (chrome://) included by default; pass includeInternal=false to exclude them.",
   ],
   parameters: ListTabsArgs,
   concurrency: "parallel",
@@ -83,7 +80,6 @@ export const switchTabTool = defineBrowserTool({
   promptGuidelines: [
     "Get a targetId via browser_list_tabs first.",
     "Accepts exact targetId or a unique prefix of at least 8 hex characters.",
-    "Refuses tabs not owned by this session — use browser_new_tab to open a controllable tab instead.",
   ],
   parameters: SwitchTabArgs,
   concurrency: "serialized",
@@ -138,10 +134,7 @@ export const newTabTool = defineBrowserTool({
   label: "Browser New Tab",
   description: "Open a new tab in the harness's dedicated Chrome window and switch to it. Optionally navigate to a URL.",
   promptSnippet: "Open a new tab",
-  promptGuidelines: [
-    "All tabs opened by this tool live in a single dedicated Chrome window separate from the user's main browsing.",
-    "Pass url to navigate immediately.",
-  ],
+  promptGuidelines: [],
   parameters: NewTabArgs,
   concurrency: "serialized",
   async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> {
@@ -166,7 +159,6 @@ export const closeTabTool = defineBrowserTool({
   description: "Close a tab the harness owns. Refuses tabs not opened by this session.",
   promptSnippet: "Close an owned tab",
   promptGuidelines: [
-    "Only closes tabs this session opened (visible in browser_list_tabs default scope).",
     "Accepts exact targetId or a unique hex prefix (>=8 chars).",
   ],
   parameters: CloseTabArgs,

package/src/domains/viewport.ts

@@ -17,7 +17,6 @@ export const viewportResizeTool = defineBrowserTool({
   description: "Override the viewport size and device pixel ratio for responsive testing.",
   promptSnippet: "Resize the viewport (responsive testing)",
   promptGuidelines: [
-    "Width/height in CSS pixels (e.g., 375x667 for iPhone SE).",
     "Pass deviceScaleFactor=2 to simulate retina displays.",
   ],
   parameters: ViewportArgs,

package/src/index.ts

@@ -4,9 +4,10 @@ import { getBrowserSystemPrompt } from "./prompt";
 import { registerSetupCommand } from "./setup";
 import { registerProfileCommand } from "./profile/command";
 import { readPin } from "./profile/store";
-import { type BrowserState, defaultState, persistState, restoreState } from "./state";
+import { type BrowserState, createStatePersister, defaultState, restoreState } from "./state";
 import { registerAllTools } from "./registry";
 import { cleanupTempDirs } from "./util/truncate";
+import { restoreDownloadBehavior } from "./domains/files";
 import { createDaemonTransport } from "./daemon/transport";
 import { setDebugClicks } from "./util/debug";
 import { asBoolean, asString } from "./util/guards";
@@ -16,6 +17,7 @@ export default function browserHarnessExtension(pi: ExtensionAPI): void {
   const namespace = flagNs ?? `pi-${Math.random().toString(36).slice(2, 10)}`;
 
   let state: BrowserState = defaultState(namespace);
+  const persister = createStatePersister(pi);
   let client: BrowserClient | null = null;
   let toolsRegistered = false;
 
@@ -83,6 +85,7 @@ export default function browserHarnessExtension(pi: ExtensionAPI): void {
 
   pi.on("session_start", async (_event, ctx) => {
     state = restoreState(ctx, state.namespace);
+    persister.markPersisted(state);
     setDebugClicks(asBoolean(pi.getFlag("browser-debug-clicks")) ?? false);
 
     // Re-read the on-disk profile pin every session start: another pi session may have changed it since this client was created.
@@ -112,7 +115,7 @@ export default function browserHarnessExtension(pi: ExtensionAPI): void {
               ? { harnessWindowId: snap.harnessWindowId }
               : {}),
           };
-          try { persistState(pi, state); } catch {}
+          try { persister.persist(state); } catch {}
         },
       });
     } else {
@@ -130,6 +133,11 @@ export default function browserHarnessExtension(pi: ExtensionAPI): void {
   pi.on("session_shutdown", async () => {
     if (client) {
       try {
+        // Warn but keep going: detach and tab cleanup still have to run, and a throw here would skip both.
+        const restored = await restoreDownloadBehavior(client);
+        if (!restored.success) {
+          console.warn(`[pi-browser-harness] ${restored.error.message}`);
+        }
         await client.detach();
         await client.closeOwnedTabs();
       } catch (e) {
@@ -137,23 +145,19 @@ export default function browserHarnessExtension(pi: ExtensionAPI): void {
       }
       // Do NOT stop the client or null it out: the surviving daemon connection is what eliminates the per-session "Allow Remote Debugging" prompt.
     }
-    persistState(pi, state);
+    persister.persist(state);
     await cleanupTempDirs();
   });
 
+  // The branch already holds the restored snapshot: re-appending it only grows the session file.
   pi.on("session_tree", async (_event, ctx) => {
     state = restoreState(ctx, client?.namespace);
-    persistState(pi, state);
+    persister.markPersisted(state);
   });
 
   pi.on("before_agent_start", async (event) => {
-    if (!client || !client.status().alive) {
-      return {
-        systemPrompt:
-          event.systemPrompt +
-          `\n\n## Browser Control\n\nBrowser tools (browser_*) are available but the browser is not connected. Run /browser-setup.`,
-      };
-    }
-    return { systemPrompt: event.systemPrompt + getBrowserSystemPrompt() };
+    return {
+      systemPrompt: event.systemPrompt + getBrowserSystemPrompt(client?.status().alive ?? false),
+    };
   });
 }