Adds generation_fork and generation_run to copy an agent preset and run a task on a new session.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:goecho/dsh-generation
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
English | 中文
A DeepSeek Harness plugin that forks agent presets and runs a task on the next generation.
It is make, not a compiler. Creator mode is already the compiler: it can inspect the runtime, edit files, and author presets. This plugin only records a lineage — copy a known-good preset, let the meta agent edit that copy with ordinary fs / bash, then start a new working session on it.
Compatible with DeepSeek Harness 0.1.5+ (dsh-v0.1.5-rc.2 and current master, session format v3). It needs Session.snapshotEvents(), async ctx.agents.create({ sessionId, parentAgent, meta, signal, setup }), Host-global ctx.tools.register, and dsh.bundle.patch. The shipped coding preset is ptc (formerly code). Do not add @deepseek-ai/* to this package — a second copy of those modules crashes tool dispatch.
Install
dsh plugin --profile web add github:goecho/dsh-generation
Then restart dsh --profile web so the host profile reloads. Pin a SHA from the commit history after you have read the source. The package is plain JavaScript, so git installs do not need a prepare build allowlist. Plugin 0.3.0 is the line that forks ptc instead of code and passes parentAgent so workers are runtime children.
Then open a Creator mode (cordis) session — or a copy of that preset whose composition still has a plugin row name: '@deepseek-ai/dsh-tool-cordis'.
dsh plugin add installs into the host profile, so the two tools are registered globally. This plugin then hides them from every non-Creator session (including user copies of standard / minimal / ptc) and from every agent with origin: subagent, including the workers generation_run starts. Execute still refuses a non-Creator caller.
This repository already has the dsh-plugin, dsh, and deepseek-harness GitHub topics.
Why
DeepSeek Harness splits composition into a Host plane (sandbox, model route, persistence) and an Agent plane (tools, persona, prompt). A session’s preset is locked once a turn has run, so you cannot hot-swap the working agent’s toolset without stranding logged tool calls.
The useful bootstrap is the same as a C compiler: each generation is a new binary. Stage N writes files for stage N+1; you do not patch the process that is currently compiling.
What it is not
- Not a replacement for Creator mode (
cordispreset) orcordis_define/cordis_run - Not a way to recompose the current session, or to give an in-process subagent a different preset
- Not a YAML/JS generator, scorer, or auto-promoter of the default creator
- Not a Host-plane kernel: it does not add services, session event types, or sandbox backends
- It does not depend on
@deepseek-ai/dsh-tools/@deepseek-ai/dsh-llm. Tools are registered as raw definitions so a second copy of those packages cannot split the host’s module identity.
Design
Four rules:
- The kernel stays assembly. No new Host services, no new
SessionEventtypes, no unlockingagent-preset-locked. - A generation is a new process of composition.
generation_runusesagents.create+agentPresets.mount(id), neverrecomposeon the meta session and nevercomposeFrom(in-process children inherit the parent preset). - This plugin is make. It does not write
agent.cordis.yml. Editing uses tools the creator preset already has. - A human is stage3.
forkandrungo throughtools/pre-executeask. Nothing is promoted to the default creator automatically. Lineage is the meta session log (tool/call/tool/result), not a second database.
meta session (cordis + this plugin)
→ generation_fork copy a preset to a new id
→ fs / bash edit the copy (not this plugin)
→ generation_run new agent, mount that id, run the task, dispose
→ summary back into the meta log
→ fork again or stop
Working generations should fork from standard, minimal, or ptc.
Tools
| Tool | Does | Does not |
|---|---|---|
generation_fork |
agentPresets.copy(from, id); writes purpose into the new preset.yml description; returns id and directory |
Accept composition YAML (authoring stays copy-only); overwrite an existing id |
generation_run |
After approval, create an agent, mount the preset, followup(task), wait until idle, cancel, or a 15-minute timeout, return sessionId, stopReason, tool names used, last assistant text, then dispose |
Run Creator mode as the worker; inherit the meta toolset; leave a half-created agent on failure |
generation_fork
| Argument | Required | Meaning |
|---|---|---|
from |
yes | Preset id to copy. Prefer standard, minimal, or ptc. |
id |
yes | New preset id (/^[a-z0-9][a-z0-9-]*$/). Must not already exist. |
purpose |
yes | One sentence written into the new preset.yml description. |
Returns { ok, id, from, purpose, path, compositionPath } where path is the preset directory.
generation_run
| Argument | Required | Meaning |
|---|---|---|
preset |
yes | Preset id to mount on the new working session. Must not be cordis. |
task |
yes | Self-contained follow-up for the worker. It does not see meta history. |
Refuses a worker whose composition still has a plugin row name: '@deepseek-ai/dsh-tool-cordis'. Inherits the meta session’s workspace cwd, records origin: subagent and parentSession so logs chain, sets parentAgent so the worker is a runtime child (not a scheduled root), and passes the parent tool AbortSignal into agents.create so cancelling the meta tool also aborts worker creation. It does not dump the full worker transcript into the meta context. Worker logs are read with snapshotEvents(). If the worker never goes idle, it is cancelled after 15 minutes (stopReason: "timeout"). Domain failures keep { ok: false } but render as ERROR: so the model notices.
Returns { ok, sessionId, presetId, stopReason, toolsUsed, lastAssistantText }.
Trust
Treat a Creator session that can fork and run generations as shell access. Mitigation in v1:
- Human approval on every fork and every run
- Worker preset cannot be
cordis, and cannot still carry a@deepseek-ai/dsh-tool-cordisplugin row - Edits belong under the new preset directory
- Model-written JavaScript is never auto-mounted via
cordis_run
Develop
npm test
There are no @deepseek-ai/* runtime dependencies. The tests mock ctx.tools / ctx.agentPresets / ctx.agents. GitHub Actions runs the same npm test on Node 22.
License
Links
More in this category
Tencent/WeKnora#dsh-weknora★ 37685
Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.
DayuanJiang/next-ai-draw-io#dsh-plugin★ 37029
Draws draw.io diagrams in DeepSeek Harness through the next-ai-drawio MCP server: the link in the reply opens a live preview in the right sidebar, you can edit the diagram by hand, and each AI change is a version you can restore. Node.js 18+; npx downloads the MCP server on first use.
superdesigndev/treg★ 8322
Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.
T-Auto/dsh-ops★ 5899
Provides bash, PowerShell 7, and high-performance Rust tools for DSH on Windows to reduce token usage.
sixtysevenlf/dsh-blender-plugin★ 2178
Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.
helloHub1212/dsh-windows-mcp★ 1612
Bridges the CursorTouch/Windows-MCP desktop automation server into DSH through the official MCP client bridge, registering its screenshot, UI tree snapshot, mouse and keyboard input, clipboard, process and registry tools as mcp__windows__* tools for the model, and adds a windows_mcp_doctor diagnostic tool. Computer Use is off by default and is switched on from the plugin panel.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.