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 stay under request size limit." 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
Updates the Yutori agent loop and action schema for both Python and TypeScript templates, changing the API payload and browser-control behaviors. Risk is moderate since it affects runtime automation flows (tool invocation, input timing, and message history trimming) but is isolated to scaffolding/templates.

Overview
Upgrades the Yutori computer-use templates (Python + TypeScript) from n1-latest to n1.5-latest, including updated request wiring (tool_set: browser_tools_core-20260403 and explicit disable_tools to keep the template computer-use only).

Updates the action schema/handlers to match n1.5: adds support for new actions (e.g. mouse_move, mouse_down/mouse_up, middle_click, hold_key, go_forward), changes key_press to use key, drops n1-only typing flags, and threads optional modifier into Kernel hold_keys for clicks/scrolls.

Adds request-size protection in both loops by deep-copying and trimming older screenshot parts when the serialized message payload exceeds ~9.5MB (keeping the most recent screenshots), and reduces post-action screenshot delay from 300ms to 150ms. Documentation and template display strings are updated to reflect n1.5 and the supported/disabled tool set.

^{Reviewed by Cursor Bugbot for commit 7bb49ec. 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.}

[masnwilliams]

reviewed — n1.5 contract changes look clean and python/typescript halves stay in lockstep. trim helpers verified end-to-end on a synthetic 20-step × 600KB history (16MB → 8.8MB, last 6 screenshots byte-identical, caller list unchanged). one real bug worth fixing before ship:

Bugs

• pkg/templates/python/yutori/tools/computer.py:259,280 and pkg/templates/typescript/yutori/tools/computer.ts:281,312 — duration for wait and hold_key is treated as milliseconds, but per yutori's reference impl (yutori-ai/frontend-visualqa/src/frontend_visualqa/actions.py lines 469, 506) it's seconds — passed straight to asyncio.sleep, clamped to 100 seconds. defaults are fine because they're pre-computed in ms (1000, 2000), but any model-supplied duration is interpreted 1000× too short (wait { duration: 2 } → 2ms instead of 2s, hold_key { duration: 0.5 } → 0.5ms instead of 500ms). need to multiply by 1000 before sleeping / before passing to kernel press_key.duration.

Nits

• pkg/templates/python/yutori/loop.py:203 and pkg/templates/typescript/yutori/loop.ts:147 — placeholder text is "Screenshot omitted to stay under request size limit.", but PR description quotes "[screenshot omitted to fit request size]". wording mismatch only.
• pkg/templates/python/yutori/README.md:6 and pkg/templates/typescript/yutori/README.md:6 — vendor benchmark + pricing numbers will stale fast. consider scoping with "at launch" or dropping.
• pkg/templates/typescript/yutori/loop.ts:112 — @ts-expect-error on extra_body becomes a build failure the day the OpenAI SDK adds the field. @ts-ignore or a cast is more future-proof.

[dprevoznik]

@masnwilliams fixed the nits you had! still working