---

description: "Claude-style Ultra mode for DSH: the top reasoning effort plus Claude's standing multi-agent orchestration." kind: "package-bundle"

dsh-claude-ultra

English | 中文

Summary

Adds Claude's Ultra mode to DSH. Ultra is a fifth tier on the Codex effort switcher's slider, above the model's own levels. Selecting it runs the session at the model's highest reasoning effort and keeps multi-agent orchestration standing, carrying the same instruction Claude Code carries when ultracode is on.

This package is the Host and browser half of the mode. The browser half reads the switcher's codexModelTiers client service, so dsh-codex-effort-switcher 0.2.0 or newer must be installed in the same profile. Without the switcher this package contributes no tier and the composer keeps its shipped picker.

Table of Contents

• Install
• Use
• How it works
• Claude source
• Compatibility
• Known Limitations and Deferred Work
• Develop and verify

---

Install

Build the package inside this directory; development dependencies and artifacts stay here. Use a Node.js version supported by DSH.

npm install --ignore-scripts --workspaces=false
npm run build
npm pack
dsh plugin --profile <profile> add "./dsh-claude-ultra-0.1.2.tgz"

Install into the profile you actually use. dsh plugin add appends the bundle row and runs pnpm inside the profile directory. A profile composes its bundle rows at boot, so restart the app afterwards; patchReload: live reloads patch and config edits, not a new bundle row.

dsh --profile web --dump-config should list dsh-codex-effort-switcher and dsh-claude-ultra and print no "incompatible" line. The card then shows a fifth cell labelled Ultra above Max.

Reinstalling the same version is a no-op for pnpm: after rebuilding, dsh plugin --profile web remove dsh-claude-ultra then add it again, or the profile keeps serving the previous lib/client.js.

Use

Click the model chip, choose a model that advertises a reasoning effort, and click the last cell. The trigger reads <model> Ultra, and the slider takes the violet top-tier treatment.

The next model request carries the mapped effort and a system-prompt section holding Claude's ultracode instruction plus the DSH agent-team usage notes. The mode stays active for later requests and for child agents. Choosing any lower level, in this card or through /model, makes the next assembly materialize Claude's exit text instead.

A prompt that contains the whole word ultracode opts that turn into orchestration even when the tier is not selected, which is Claude's keyword trigger. The matcher is Claude's: a prompt that starts with a slash command is ignored, as is a keyword inside quotes, backticks, brackets or braces, and one glued to a path separator or a file extension. That turn receives Claude's keyword reminder in its own section, beside the standing one when the tier is active.

The mode is durable: it is folded from the logged system/message into the claudeUltraMode session projection, so a reload or a resume restores the fifth cell without a new request.

How it works

1. The switcher appends the tier to its effort choices. available(model) is true when the model advertises a reasoning effort, and effort(model) maps max first, otherwise the highest advertised non-off level.
2. Applying the tier first calls the standard model-selection path with that mapped effort. The Host receives the same session.selectModel that /model uses; there is no second selection path.
3. The browser then calls /api/dsh-claude-ultra/arm with the session, provider, model, and mapped effort. The Host validates the route through llm.resolveModelInfo and llm.resolveCallConfig and stores an in-memory arm for that session.
4. The next system-prompt assembly matches the arm against the session's pending or last-used selection. A match materializes the entry text; a selection after an entry snapshot materializes the exit text; a child agent with no snapshot of its own inherits an active parent.
5. The system/message that carries the sections is logged. The claudeUltraMode projection folds that text, the model/selection events, and the newest typed prompt into { mode, dirty, keyword }, where mode is 'full', 'still', 'off', or null and keyword records whether that prompt carries the ultracode keyword. The tier's active face is "an entry mode and not dirty", so a lower selection turns the fifth cell off immediately while the next request still receives the exit text.
6. The agent/request listener consumes the arm after the request it armed, and a later selection, agent disposal, or session teardown cannot reuse a stale intent.

Why a system-prompt section

A section appended by the system-prompt/assemble waterfall is retained by the assembly and by the later runtime-context refresh, is model-visible, and is logged in the system message. A systemPrompt.context() contribution is optional by default and is dropped whenever a suppressor is active in the scope, which would leave the mode invisible to the model. The section survives unless some registered section sets complete: true; the shipped Standard preset does not.

No DSH package dependency

The Host half imports no @deepseek-ai/* module: it reads the services it needs off the injected context through the structural views in src/ports.ts. That is not only a packaging convenience — the published @deepseek-ai/dsh-llm, -session, -system-prompt, and -session-projection versions on npm (0.0.1-rc.1) do not match the running runtime (0.2.0-rc.2 from a checkout, 0.2.1-rc.5 from the desktop runtime), so installing them is not possible. zod is the only runtime dependency and it is inlined into lib/index.js.

Claude source

The reminder bodies are copied from the attachment table inside @anthropic-ai/claude-code 2.1.316's bin/claude.exe — the JavaScript bundle embedded in the Bun single-file executable. The table starts at byte offset 296490096; the effort scale and the ultracode alias are at 282594834 and 286520088.

Claude's ultracode is a session-scoped switch that sits beside the effort levels on the effort slider (effortSlider:toggleUltracode, bound to Tab) and maps to xhigh when it is passed as an effort value ({ ultracode: "xhigh" }). DSH models advertise their own levels, so this plugin takes the model's top level — max on DeepSeek-V41-Flash.

Verbatim, with one substitution: DSH has no Workflow tool, so the Workflow tool becomes the 'subagent' and 'subagent_fork' tools, and the workflow authoring reference becomes the DSH agent-team usage notes below. Everything else, including the em dashes and the closing sentences, is unchanged.

Claude attachment	Text used here
ultra_effort_enter (full)	Ultracode is on: optimize for the most exhaustive, correct answer — not the fastest or cheapest. Use the 'subagent' and 'subagent_fork' tools on every substantive task; token cost is not a constraint. See the Ultracode section and quality patterns in the DSH agent-team usage notes below. Solo only on conversational/trivial turns.
ultra_effort_enter (sparse)	Ultracode is still on — use the 'subagent' and 'subagent_fork' tools; see the Ultracode section of the DSH agent-team usage notes below.
ultra_effort_exit	Ultracode is off — the standard opt-in rule for multi-agent delegation applies again. Only delegate when the user has explicitly asked for sub-agents, delegation, or parallel agent work; a task that would merely benefit from parallelism does not count.
workflow_keyword_request	The user included the keyword "ultracode", opting this turn into multi-agent orchestration — use the 'subagent' and 'subagent_fork' tools to fulfill the request.
ultrathink_effort	Not emitted. Pinned in src/prompts.ts; it raises one turn's effort rather than switching a mode, and this plugin's effort entry point is the slider.

The exit text's second sentence restates the opt-in rule from Claude's Workflow tool description (ONLY call this tool when the user has explicitly opted into multi-agent orchestration…), which is the rule the first sentence refers to.

Compatibility

• Verified against DSH 0.2.1-rc.5 (the desktop runtime that serves a web profile) and the 0.2.0-rc.2 checkout.
• dsh-codex-effort-switcher 0.2.0 or newer, in the same profile.
• Web platform client bundles; the Host half is a normal bundle patch row.
• No DSH core changes and no new session event type: the mode rides the existing system/message, user/message, and model/selection events, so SESSION_FORMAT_VERSION is unchanged.

Known Limitations and Deferred Work

• The switcher is required. dsh-codex-effort-switcher must be in the same profile. The client half reads its codexModelTiers service through ctx.get rather than ctx.inject, because a pending inject is reported by the client boot audit as a failed plugin load and blanks the whole surface; a composition without the switcher therefore loads normally and simply contributes no tier.
• Reminder cadence. Claude emits the entry reminder on the first turn and then a sparse one every 10 user turns (Uxr()), and the exit reminder once. Here the entry reminder is re-emitted on every assembly (full first, then the still-on text) and the exit text is re-emitted while the mode is off. Claude's reminders are message attachments, so repeating them would grow its transcript; this section is rebuilt into each request's system prompt, where repeating costs no context. The text is Claude's; the frequency is the DSH-native equivalent.
• The ultrathink keyword is not wired. Claude raises one turn to xhigh when its prompt contains ultrathink. That is a per-turn effort override rather than a mode, and this plugin's effort entry point is the slider; the text is pinned in src/prompts.ts. The ultracode keyword is wired, and its matcher is a port of Claude's own.
• Default selection save. The standard session.selectModel path also saves the selection as the profile default where DSH does so, so selecting Ultra can leave the top level as the saved default for new sessions. The saved value carries the effort but not the mode, so a new session can start at that level without Ultra's instruction. This is the switcher's shared selection path, not a separate Ultra path.
• The arm is in memory until the first request. Selecting Ultra and reloading before sending a prompt loses the local cell. After the first request the logged system message restores it.
• Uninstall leaves history. Removing the plugin stops new Ultra sections and removes the fifth cell, but an existing session's logged system prompt still contains the mode text; resuming that session shows the old instruction.
• No fallback for a model without reasoning. The tier is hidden when a model advertises no non-off effort.
• complete: true sections win. A preset that registers a complete section replaces every other section after the waterfall, which would drop this one. The shipped Standard preset does not.
• Fork and concurrency. A fork taken before the first Ultra request has no mode; a fork after it inherits the projected state with the rest of the transcript. The arm is per session.

Develop and verify

npm run typecheck
npm test

npm test builds the Host bundle and the Node-loadable browser bundle and runs 95 assertions over the effort mapping, the arm store, the projection fold, the pinned prompt text, the reminder resolution, the arm route's every branch, and the browser tier. Each spec has a recorded negative proof.

.runtime/no-switcher.overlay.yml is a --patch overlay that disables the switcher, for reproducing the degradation path:

dsh --profile web --patch ".runtime/no-switcher.overlay.yml" --no-open --port 0

Published packages exclude development dependencies and evidence.

License

MIT