* feat(preset): declare Agent compositions in profile YAML * fix(preset): share scope binding cleanup and refresh module graph * fix(preset): use host syntax colors in the YAML editor * fix(preset): write new profile declarations as block YAML * fix(preset): align eager activation with browser and worker surfaces * fix(ui-agent-preset): retain the existing preset card layout * fix(preset): keep rows waiting for a Host service mounted and re-audit after settlement A preset row whose Host provider was still activating at declaration time was reported as waiting for a missing service, and the registry recorded the definition as broken for the rest of the process. Split the mount audit into failed and pending rows: failures and root-realm leaks still reject the mount, while pending rows stay mounted and every read and binding re-audits them after the Host Loader tree settles. Remove the accidental self-dependency of @deepseek-ai/dsh-web-app and its lockfile self-link. Archive the copy-only preset authoring note, which the declarative-preset note fully supersedes, and update the ralph note's restore recipe to the profile-patch mechanism. * chore(lint): re-key and prune the unknown-cast baseline after the master merge * refactor(web-app): ship each Agent preset as its own bundle patch file `dsh.bundle.patch` accepts an ordered file list, so the four shipped preset declarations move out of the 1000-line web patch into `presets/<id>.patch.yml`, one insert per file, applied after the host patch. The host patch keeps the preset registry row. Gates and test scaffolds that read the web layer resolve every patch file through `bundlePatchPaths` instead of one hardcoded path. * refactor(preset): drop the save notice injected into live Agents The notice duplicated the save result the Web editor already shows, and after the producer-owned message sources it would have needed its own persisted source kind. Saving now only persists and reports the activation diagnostic; the persistence catalog is unchanged from master. * docs: regenerate the module graph after dropping the registry's llm dependency * test(ui-agent-preset): cover the guide dialog's keyboard handling on the declarative section * fix(preset): address the remaining review comments Apply the lowercase id rule only when creating a declaration, so presets declared with other ids stay editable. Export `isBuiltInPreset` from the display fold and key the client card groups on it. Remove the dead `error` and `retry` locale keys, the JSDoc orphaned by the `trust` removal, the `trust` fields in the plugin-inventory test fixtures, and the stale `dsh-agent-presets` package name in comments and READMEs. * refactor(preset): make the Web preset page view-and-select only Remove the child-plugin YAML editor, the `agent_preset` tool and the registry's read/save Remote methods. Presets are declared and changed only by bundle patches; the settings page keeps the roster, the new-task default and the mode help, and its question icon explains that and offers to start a Creator-mode task. The `editing-cordis-compositions` skill and the Creator persona describe the bundle-based path, and the authored skill-load Session and Web snapshots are refreshed for it. * docs(skill): make the composition skill self-sufficient for preset authoring State where the shipped declarations live, list every declaration field, inline a complete minimal bundle and an override example, and name the verification calls, so Creator mode no longer reads DSH package sources to infer the format. Refresh the authored skill-load Session for the new text. * test(tools): drop the removed agent_preset tool from the catalog expectation
description, kind
| description | kind |
|---|---|
| The experimental group map: publicly installable pre-stable prototypes. | package-group |
packages/experimental
English | 中文
Summary
The experimental group contains prototype capabilities whose contracts can change and carry no support promise. All current packages publish under their @deepseek-ai/dsh-experimental-* names, including the opt-in Agent Teams composition, Auto review, Cua Driver providers, browser-use backends, cross-realm Inspector, CPython PTC backend, and browser-worker preview libraries. Released products outside this group must not depend on experimental packages.
Table of Contents
Packages
| Package | Role | ctx key |
|---|---|---|
speech-to-text |
Named speech recognition providers | ctx.speechToText |
speech-to-text-sensevoice |
Managed local SenseVoice inference | — |
api-speech-to-text |
Authenticated transient transcription Remote | ctx.speechController |
client-ui-voice-input |
Microphone capture and guarded draft insertion | — |
voice-input-bundle |
Default-disabled optional voice input composition | — |
agent-team-profile |
Agent Teams collaboration, tools, and Web UI bundle | — |
agent-team |
Named teammates with durable messages and a shared task board | ctx.agentTeams |
client-ui-agent-team |
Team roster, task board, and teammate navigation for Web | — |
auto-review |
Explicit Web layer for same-model review before each native or PTC inner tool call | — |
ptc-runtime-python |
CPython subprocess backend for the PTC execution seam | ctx.ptcRuntime |
computer-use-cua-driver-mcp |
Use an installed Cua Driver through MCP | ctx.computerUse |
computer-use-cua-driver-native |
Embed the Cua Driver native npm runtime | ctx.computerUse |
browser-use-playwright-mcp |
Playwright browser tools over MCP | ctx.browserUse |
browser-use-chrome-devtools-mcp |
Chrome DevTools inspection and browser control over MCP | ctx.browserUse |
browser-use-stagehand-native |
Stagehand browser operations with explicitly configured native models | ctx.browserUse |
browser-use-runtime |
Session-owned browser resources shared by experimental providers | — |
inspector |
Cross-realm CDP hub for Host debugging, Client Runtime inspection, network capture, and Cordis trees | ctx.inspector |
tool-agent-team |
Nine tools that let the model create, message, and coordinate teammates | registers scoped tools on ctx.tools |
webworker-packer |
Builds the gzip-compressed VFS image consumed by the browser worker preview | library and CLI — no ctx key |
webworker-runtime |
Runs the harness plugin tree inside a dedicated browser worker | library and worker entry — no ctx key |
Related documentation
- Experimental publication decision — public defaults and private exceptions.
- Computer use — desktop provider choices.
- Browser use — browser provider choices and Session ownership.
- Agent Teams subsystem — durable Team types and the
ctx.agentTeamsservice API. - Experimental subtree rules — what experimental status does and does not relax.
Dev Note
Working context for maintainers — click to expand
None.