Updates

vendor/agent-harness/agent-workspace/AGENTS.md

@@ -39,9 +39,9 @@ Workspace skills live in `skills/<name>/SKILL.md`. When a request matches a skil
 ## Tools
 
 - `read_file` / `list_dir` / `grep` / `write_file` / `search_replace` — workspace files.
-- `run_terminal_cmd` — local shell. Public HTTP via curl or wget is blocked; use web tools.
-- Web tools share one headed Playwright Chromium window. `web_search` / `google_search` / `wiki_search` / `hn_search` / `code_search` find links. `fetch_page` / `web_fetch` read a public page. For cookie banners, forms, logins, or leftover challenges, call `browser`. Before a multi-step browse, `read_file` `skills/browser/SKILL.md`.
-- `browser` actions: `navigate` (needs `url`), `snapshot`, `click` (`ref` from the last snapshot), `type` (`ref` + `text`, optional `submit`), `press` (`key`), `scroll` (`dy`), `wait` (`ms`). Snapshot or navigate first. Refs change after every click. Do not use `cu_observe` or the shell for websites.
+- `run_terminal_cmd` — local shell. Public HTTP via curl or wget is blocked; use `browser`.
+- The only web tool is `browser`, the headed Jarvis Chromium window. `web_search`, `web_fetch`, and the other search tools are removed. Before a multi-step browse, `read_file` `skills/browser/SKILL.md`.
+- `browser` actions: `navigate` (needs `url`; returns page text), `snapshot`, `click` (`ref` from the last snapshot), `type` (`ref` + `text`, optional `submit`), `press` (`key`), `scroll` (`dy`), `wait` (`ms`). To search, navigate to a public search url, then click a result ref. Snapshot or navigate first. Refs change after every click. Do not use `cu_observe` or the shell for websites.
 - Desktop and computer-use tools are registered by Jarvis. After Settings → Computer use → Allow now, call `cu_observe`, then `cu_click` / `cu_type`. Do not paste tool JSON into chat.
 - Webcam: Settings → Camera → Allow now. Call `webcam`. The still is attached; do not speak the file path. This is not `cu_observe`.
 - `ask_user_question` — wait for a user choice.

vendor/agent-harness/agent-workspace/TOOLS.md

@@ -15,13 +15,15 @@ Local notes for this Jarvis session. This file is guidance, not an allowlist.
 ## Shell
 
 - `run_terminal_cmd` is a local user shell, not root.
-- Public HTTP via curl or wget is blocked. Use `web_search` / `web_fetch` in the Jarvis Chromium window.
+- Public HTTP via curl or wget is blocked. Use `browser` in the Jarvis Chromium window.
 
 ## Browser
 
-- Search, fetch, and `browser` share one headed Playwright Chromium window.
-- `web_search` finds links. `fetch_page` reads a public page.
-- Cookie walls, forms, leftover challenges: call `browser`. `read_file` `skills/browser/SKILL.md` for the playbook.
+- `browser` is the only web tool. It drives one headed Playwright Chromium window.
+- `web_search`, `google_search`, `fetch_page`, `web_fetch`, `wiki_search`, `hn_search`, and `code_search` are removed. Do not call them.
+- To search, `navigate` to `https://duckduckgo.com/?q=QUERY` or a Google search url, then `click` a result ref.
+- `navigate` and `snapshot` return page `text`. Read it, then decide the next action.
+- Cookie walls, forms, leftover challenges: `read_file` `skills/browser/SKILL.md` for the playbook.
 - `browser` actions: `navigate` + `url`, `snapshot`, `click`/`type` with `ref` from the last snapshot, `press` + `key`, `scroll` + `dy`, `wait` + `ms`.
 - Snapshot or navigate before every click or type. Refs go stale after a click.
 - Do not use `cu_observe` or the shell for websites.

vendor/agent-harness/agent-workspace/skills/browser/SKILL.md

@@ -1,17 +1,13 @@
 ---
 name: browser
-description: Drive the headed Jarvis Chromium window with the browser tool. Use for cookie walls, forms, logins, leftover bot checks, and any extra clicks after search or fetch.
+description: Drive the headed Jarvis Chromium window. This is the only web tool. Use it to search, open pages, click, and type. Do not use web_search, web_fetch, or computer-use for websites.
 ---
 
 # Browser
 
-Search and fetch already run in this same Playwright Chromium window. Call `browser` when the page needs a click, a form, a cookie banner, or a leftover challenge. Do not use `cu_observe`, `cu_click`, curl, or wget for websites.
+`browser` is the only way to the public web. `web_search`, `google_search`, `fetch_page`, `web_fetch`, `wiki_search`, `hn_search`, and `code_search` are removed. Do not call them. Do not use `cu_observe`, `cu_click`, curl, or wget for websites.
 
-## Choose a tool
-
-1. `web_search` / `google_search` / `wiki_search` / `hn_search` / `code_search` — find public links.
-2. `fetch_page` / `web_fetch` — read one public http(s) page (JavaScript runs).
-3. `browser` — drive that window. Cookies persist across these tools.
+Chrome runs on this computer. After a navigate or snapshot, read the page `text` and decide the next click. If Groq is enabled, that thinking step uses Groq. The crawl itself stays local.
 
 ## `browser` actions
 
@@ -19,8 +15,8 @@ Call with `action` plus the fields for that action. Snapshot refs are strings li
 
 | action | Fields | Result |
 | --- | --- | --- |
-| `navigate` | `url` (public http or https) | Opens the page and returns a snapshot |
-| `snapshot` | none | Current url, title, numbered `refs`, short aria text |
+| `navigate` | `url` (public http or https) | Opens the page and returns a snapshot plus readable `text` |
+| `snapshot` | none | Current url, title, numbered `refs`, page `text` |
 | `click` | `ref` from the last snapshot (or `selector` / `text`) | Clicks, then a fresh snapshot |
 | `type` | `ref` + `text`; optional `submit` true | Fills the field; `submit` presses Enter |
 | `press` | `key` (`Enter`, `Tab`, `Escape`, `Control+l`, …) | Key, then a snapshot |
@@ -29,23 +25,33 @@ Call with `action` plus the fields for that action. Snapshot refs are strings li
 
 Private, loopback, and metadata hosts are blocked before Chromium starts.
 
+## Search
+
+Do not call a search tool. Navigate to a public search url, then click a result:
+
+- Web: `https://duckduckgo.com/?q=QUERY` or `https://www.google.com/search?q=QUERY`
+- Wikipedia: `https://en.wikipedia.org/w/index.php?search=QUERY`
+- Hacker News: `https://hn.algolia.com/?q=QUERY`
+- GitHub: `https://github.com/search?q=QUERY&type=repositories`
+- This computer's public IP: `https://ifconfig.me/ip`
+
 ## Loop
 
-1. `navigate` or `snapshot` so you have fresh `refs`.
-2. Pick the ref whose `name` matches the control (Accept, Next, email, search box).
+1. `navigate` or `snapshot` so you have fresh `refs` and page `text`.
+2. Pick the ref whose `name` matches the control (Accept, Next, email, search box, a result title).
 3. `click` or `type` with that `ref`.
 4. Read the new snapshot. Refs from earlier snapshots are stale.
-5. Repeat until the page is usable, then `fetch_page` on the current url if you need the article text.
+5. Repeat until the page text answers the question, then speak the answer. Do not keep searching the same query.
 
 ## Cookie walls and challenges
 
 - Cookie banner: `snapshot`, then `click` the Accept / Agree / I understand ref.
-- `challenge: true` or a Cloudflare / “just a moment” page: tell the user to finish the prompt in the visible Jarvis browser window. Do not guess. Then `snapshot` or `fetch_page` again.
+- `challenge: true` or a Cloudflare / “just a moment” page: tell the user to finish the prompt in the visible Jarvis browser window. Do not guess. Then `snapshot` again.
 - Login that needs a password: stop and ask the user. Never type credentials unless they just provided them for this site.
 
 ## Do not
 
 - Speak refs, selectors, or tool JSON.
-- Call `browser` for a page you can already read with `fetch_page`.
+- Call `web_search`, `web_fetch`, `fetch_page`, or any other search tool.
 - Use computer-use tools on the Chromium window.
 - Keep searching the same query instead of opening a hit.