update yutori template to n1.5

[dprevoznik]

Summary

Updates the Yutori CUA template (TS + Python) from n1-latest to n1.5-latest, plus speed and request-size improvements.

This is more than a model-name swap — n1.5 changes several action signatures, adds new actions, and introduces a tool-set selector. The template is computer-use only (no Playwright page exposed to the model), so we explicitly exclude the DOM/Playwright "expanded" tools.

Loop / API changes

• bump model id from n1-latest to n1.5-latest
• send extra_body.tool_set: "browser_tools_core-20260403" to select the coordinate-based tool set (the default, but pinned for stability)
• send extra_body.disable_tools: ["extract_elements", "find", "set_element_value", "execute_js"] as defense-in-depth — these are the expanded tools that need a Playwright page

Action / handler changes

• rename hover → mouse_move
• key_press: parameter key_comb → key
• type: drop press_enter_after / clear_before_typing (n1.5 emits separate key_press actions instead)
• new actions: middle_click, mouse_down, mouse_up, hold_key, go_forward
• click actions: optional modifier parameter wired into Kernel's hold_keys for shift/ctrl-clicks
• wait: optional duration parameter honored
• hold_key: optional duration parameter honored via pressKey's duration

Request-size trimming

Mirrors the official yutori-sdk-python payload.py algorithm to keep the per-request payload under the API ceiling on long sessions:

• MAX_REQUEST_BYTES = 9_500_000, KEEP_RECENT_SCREENSHOTS = 6 (Yutori's published defaults)
• size-triggered (not count-triggered) — only kicks in when the estimated request exceeds the threshold
• two-phase strip: drop images outside the protected window first; if still too large, walk into the protected window but always preserve the latest screenshot
• dual-list pattern: the caller's full conversation_messages is preserved (deep-copied before mutation); only the trimmed copy is sent to the API
• when an image_url block is stripped from a tool result with no remaining text, a "[screenshot omitted to fit request size]" placeholder is inserted so the message stays valid

Latency

• post-action SCREENSHOT_DELAY halved from 300ms → 150ms (the settle wait after click/type/scroll before grabbing the next screenshot)
• ACTION_DELAY (the focus-settling wait inside goto_url's ctrl+L → type → Enter flow) left at 300ms — halving it risks silent input misrouting if the address bar hasn't taken focus yet

Files

• pkg/create/templates.go — display name + description
• pkg/templates/{typescript,python}/yutori/{loop,index|main,tools/computer,README}.* — implementation, trim helpers, types, docs

Test plan

• make build and make test pass
• scaffold the template (kernel create -t yutori -l {typescript,python}) and deploy end-to-end against n1.5-latest in the Default project
• smoke test: navigate + interact on example.com (both TS and Python)
• verify key_press Enter works on in-page search forms (DuckDuckGo, Google) and Wikipedia
• verify scroll action works on results pages
• verify goto_url (ctrl+L address-bar flow) still works post-delay changes
• confirm trim helpers preserve the full caller history while shrinking only the request copy (verified with synthetic 20-step × 600KB history: 12.9MB → 9.2MB, last 6 screenshots byte-identical, tool_call_ids intact)

---

Note

Medium Risk
Medium risk because it changes the model version and the tool/action contract (new/renamed actions, new request parameters), which can alter automation behavior. Also adds request-trimming logic that could affect model context in long runs if mis-tuned.

Overview
Updates the Yutori CUA templates to use n1.5-latest (and renames the template to Yutori n1.5 Computer Use) across both TypeScript and Python.

Aligns the sampling loops and tool adapters with n1.5 by pinning tool_set to browser_tools_core-20260403, explicitly disabling DOM/Playwright “expanded” tools via disable_tools, and updating action schemas/handlers (e.g., hover→mouse_move, key_comb→key, new actions like mouse_down/up, hold_key, go_forward, plus modifier support for clicks/scroll).

Adds request-size protection by trimming older screenshot image_url parts from the messages sent to the API (while preserving full local history) and reduces per-step screenshot settle delay from 300ms to 150ms; READMEs are updated accordingly.

^{Reviewed by Cursor Bugbot for commit d2affba. Bugbot is set up for automated code reviews on this repo. Configure here.}

[firetiger-agent]

Firetiger deploy monitoring skipped

This PR didn't match the auto-monitor filter configured on your GitHub connection:

Any PR that changes the kernel API. Monitor changes to API endpoints (packages/api/cmd/api/) and Temporal workflows (packages/api/lib/temporal) in the kernel repo

Reason: PR updates a Yutori template with model changes and action signature updates, but does not modify kernel API endpoints (packages/api/cmd/api/) or Temporal workflows (packages/api/lib/temporal) in the codebase.

To monitor this PR anyway, reply with @firetiger monitor this.

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit d2affba. Configure here.}

[cursor]

Python hold_key duration guard inconsistent with other handlers

Low Severity

The Python _handle_hold_key uses action.get("duration") or 1000 to default the duration, but this lets negative values pass through to press_key. Every other duration handler in both the Python and TypeScript templates — _handle_wait, handleHoldKey, and handleWait — uses an explicit duration > 0 guard. A negative duration from the model would cause the Kernel SDK to receive a negative millisecond value.

Additional Locations (1)

• pkg/templates/python/yutori/tools/computer.py#L279-L280

 

^{Reviewed by Cursor Bugbot for commit d2affba. Configure here.}