dsh-plugin-codemode
适用于 DeepSeek Harness 的 Pi-style Code Mode：通过 QuickJS-WASM 沙箱进行程序化工具调用
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Yum-wu/dsh-plugin-codemode#40041897163d9a904cb63269331e82feb769ab1cPlugin Codemode 以 dsh-plugin-codemode 发布，当前版本为 0.1.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | 中文说明
Pi-style Code Mode (Programmatic Tool Calling) for DeepSeek Harness (DSH).
Turn verbose O(N) multi-turn ReAct loops into a single O(1) JavaScript orchestration script executed in an isolated memory sandbox.
Tested against all 17 real markdown documents in the repository's docs/ folder (including a 131 KB operational ledger, totaling 215,011 raw characters). The task: scan all documents, filter by keywords (JEV, Polymarket, Architecture), extract titles & line metrics, and return a sorted Top-5 summary JSON.
| Metric | Traditional ReAct Loop | Code Mode (Sandbox Orchestration) | Measured Improvement |
|---|---|---|---|
| Data Loaded into Context | 215,011 chars | 676 chars | 99.7% Reduction (318:1 distillation) |
| Estimated Input Tokens | ~67,191 tokens | ~211 tokens | 99.7% Saved (67k tokens spared) |
| Agent / LLM Turns | 19 round trips | 1 turn | 94.7% Fewer Turns (18 turns eliminated) |
| Local I/O & Compute Time | 3.94 ms | 2.76 ms | Parity (sub-3ms execution) |
| End-to-End Elapsed Time | ~47.5 s (at 2.5s / LLM turn) | ~2.5 s | 19× Faster (94.7% latency drop) |
| Computation Accuracy | Prone to LLM counting hallucinations | Native JS Array.filter().sort() | 100% Deterministic & Accurate |
Reproduce locally:
node tests/benchmark-codemode-vs-react.mjs
Modern LLM agents suffer from tool explosion and context pollution:
"Put deterministic things in code, non-deterministic in LLM." — Hacker News Community Consensus on Code Mode
Inspired by Pi 1.0 (Earendil)'s Code Mode architecture and Cloudflare's production agent rewrite:
With Code Mode, the agent writes a concise JavaScript async function. The script executes inside an isolated sandbox, concurrently calls registered host and MCP tools, filters out unnecessary data in memory, and only returns the final distilled result to the conversation context.
┌──────────────────────────────────────────────────────────┐
│ DeepSeek Harness (DSH) │
│ │
│ ┌──────────────────────┐ ┌──────────────────────┐ │
│ │ LLM Conversation │ │ ctx.tools / MCP │ │
│ │ (Main Context) │ │ (read, pwsh, mcp..) │ │
│ └──────────┬───────────┘ └──────────▲───────────┘ │
│ │ script │ │
│ ▼ │ invoke │
│ ┌─────────────────────────────────────────┴──────────┐ │
│ │ dsh-plugin-codemode (Cordis Extension) │ │
│ │ │ │
│ │ ┌──────────────────────────────────────────────┐ │ │
│ │ │ Dual-Engine Sandbox (Isolated Context) │ │ │
│ │ │ │ │ │
│ │ │ • V8 VM Sandbox (Default): native speed, │ │ │
│ │ │ zero memory caps, unconstrained concurrency│ │ │
│ │ │ • QuickJS-WASM: WebAssembly memory sandbox │ │ │
│ │ │ │ │ │
│ │ │ - Proxy bridge: tools.<name>(args) │ │ │
│ │ │ - Supports Promise.all concurrency │ │ │
│ │ │ - Hard timeout guard (default 60s) │ │ │
│ │ │ - Recursion & leak prevention │ │ │
│ │ └──────────────────────────────────────────────┘ │ │
│ └──────────────────────────┬─────────────────────────┘ │
│ │ distilled output only │
│ ▼ │
│ ┌────────────────────────────────────────────────────┐ │
│ │ Return to LLM: [Logs] + [Return Value] │ │
│ └────────────────────────────────────────────────────┘ │
└──────────────────────────────────────────────────────────┘
engine: 'vm', Default): Aligns with DSH's official PTC workflow architecture. Zero overhead, handles multi-megabyte payloads, native microsecond performance.engine: 'quickjs'): Strict WebAssembly memory isolation, zero Node/OS footprint.read, edit, pwsh, glob) and MCP tools (mcp__github__*, mcp__cua*, mcp__tavily__*) via tools.<tool_name>(args).tools.list(): Returns the full array of registered tool names in memory.tools.help('namePattern'): Inspects parameters and JSON Schemas on-demand inside the sandbox, cutting system prompt bloat by over 90%.codemode inside codemode.// Scan 10 files simultaneously and extract matching headers
const files = await tools.glob({ path: 'src', pattern: '**/*.ts' });
const results = await Promise.all(files.slice(0, 10).map(async (file) => {
const code = await tools.read({ file_path: file });
const exportedFns = code.match(/export (?:async )?function \w+/g) || [];
return { file, count: exportedFns.length, functions: exportedFns };
}));
// Sort by number of exports and return top 3
return results.sort((a, b) => b.count - a.count).slice(0, 3);
// Discover tools dynamically without polluting the prompt with 140+ tool schemas
const available = tools.list();
console.log(`Discovered ${available.length} active tools`);
// Inspect parameters on-demand only when needed
const issueHelp = tools.help('github__list_issues');
console.log(issueHelp);
// Fetch latest issues via GitHub MCP and summarize in memory
const issues = await tools.mcp__github__list_issues({ owner: 'deepseek-ai', repo: 'deepseek-harness' });
const topIssues = issues.slice(0, 3).map(i => ({
number: i.number,
title: i.title,
author: i.user?.login
}));
return topIssues;
dsh plugin add (Recommended)dsh plugin add dsh-plugin-codemode
The package declares dsh.bundle.patch (cordis.patch.yml), so the host row is inserted
into your profile automatically — nothing to hand-edit. Restart DSH and the codemode
tool appears.
In your DSH profile directory (e.g. ~/.dsh/profiles/web):
pnpm add dsh-plugin-codemode
# or: npm install dsh-plugin-codemode
Then add the row yourself to ~/.dsh/profiles/web/cordis.patch.yml:
- insert:
- id: plugin-codemode
name: 'dsh-plugin-codemode'
config: # 全部可选;省略即用默认值
toolName: 'codemode'
engine: 'vm' # 'vm' (default) or 'quickjs'
maxResultChars: 50000
timeoutMs: 60000
injectGuidance: true
git clone https://github.com/Yum-wu/dsh-plugin-codemode.git
cd dsh-plugin-codemode
npm install
npm run build
Link into your DSH web profile (~/.dsh/profiles/web/package.json):
{
"dependencies": {
"dsh-plugin-codemode": "link:C:/Users/Yum/Desktop/dsh-plugin-codemode"
}
}
Then add the row from Option B.
Restart the DSH service from your desktop management console. The agent will immediately receive the codemode tool declaration and execution guidance.
| Option | Type | Default | Description |
|---|---|---|---|
toolName | string | 'codemode' | Name of the tool declared to the LLM. |
engine | 'vm' | 'quickjs' | 'vm' | Execution engine: high-throughput V8 VM or WASM sandbox. |
maxResultChars | number | 50000 | Maximum length of distilled output returned to context. |
timeoutMs | number | 60000 | Hard deadline per script before auto-termination. |
injectGuidance | boolean | true | Injects Code Mode orchestration tips into system prompt. |
autoReasoning | boolean | false | Enables Auto Reasoning Effort takeover. Must be turned on explicitly — see below. |
Set reasoningEffort to the sentinel auto in your model config and turn on
autoReasoning: true in this plugin's config; the plugin then projects a legal tier based on
task complexity onto the model's real effort ladder before the request goes out.
# cordis.patch.yml
- id: agent-default-model
name: "@deepseek-ai/dsh-agent-default-model"
config:
provider: opencodex
model: google-antigravity/gemini-3.8-flash
reasoningEffort: auto # <- sentinel
- id: plugin-codemode
name: 'dsh-plugin-codemode'
config:
autoReasoning: true # <- without this the plugin never intervenes
Both are required: auto alone is handed to the host and raises UNSUPPORTED_REASONING_EFFORT;
autoReasoning alone does nothing unless the incoming tier really is auto (a manually picked
tier, or one already stored in the session header, is always left untouched).
| Aspect | Detail |
|---|---|
| Hook | cordis agent/request waterfall, registered {global, prepend}; the return value goes straight into llm.prepareCall. |
Why not llm/stream | Its options is deepFreezed for agent-loop requests, and cordis next(x) ignores arguments — the tier cannot be changed there. |
| Ladder source | ctx.llm.resolveModelInfo(provider, model).reasoning.efforts — never hardcoded. |
| Scoring | Deterministic 1-10 keyword tiers (auto-reasoning.ts): concurrency/deadlock/risk = 9, derivation/refactor = 7, routine dev = 5, lookup = 2. |
| Fallback | No ladder or a failing resolveModelInfo -> omit reasoningEffort so the model default applies. auto is never handed back to the host. |
| Visibility | Read-only route GET /api/codemode.auto-effort?sessionId=<id> on the host's shared /api channel (same-origin auth applies); the composer-dock pill polls it every 3s. |
| Session isolation | Decisions are archived per sessionId (LRU, cap 50, AUTO_DECISION_CAP). agent/request is a global waterfall, so a single module-level slot made every conversation's pill show the same "most recent" record. The session id comes from payload.agent.id, falling back to ctx.get('agents').currentInitiator() — the real host dispatches agent/request with {turn, step, signal} only, so the initiator boundary is the path that resolves in practice (lastAgentSource reports which one fired). |
Auto in the model pickerThe picker's effort menu is built verbatim from the model's declared reasoningEfforts,
so auto has to be listed there for the entry to exist at all:
- id: google-antigravity/gemini-3.8-flash
reasoningEfforts:
auto: auto # <- adds the "auto" entry to the picker
low: low
medium: medium
high: high
Verified on dsh-0.2.0-rc.2 (2026-10-04): with auto: auto declared, the picker offers
Auto, selecting it sends reasoningEffort: 'auto' to agent/request, and the plugin
replaces it before the request leaves. The pill turns green/amber/red/purple per projected tier.
⚠️
autois not a DSH effort key (the legal escalation set isoff/minimal/low/medium/high/xhigh/max), so it is only meaningful as a picker sentinel that this plugin always rewrites. Never leaveautoas the value actually handed tollm.prepareCall— the plugin's fallback path omits the field rather than doing that.
| Level | Scenario | Action | Recovery Time | Impact |
|---|---|---|---|---|
| Level 1 (Soft Disable) | Unstable model behavior | Add disabled: true to plugin-codemode in cordis.patch.yml and restart DSH. | < 15 seconds | Unregisters codemode, reverts to standard single-turn tools. |
| Level 2 (Runtime Fallback) | Script syntax or runtime error | Automatic: plugin catches errors and prompts model to fallback to native step-by-step tools. | 0 seconds (instant) | Session is never interrupted; graceful degradation. |
| Level 3 (Physical Clean) | Complete uninstall | Remove from cordis.patch.yml and package.json, delete directory. | < 15 seconds | 0 runtime traces, 0 configuration residues. |
npm test
Runs the test suite (21 cases) verifying:
Promise.all multi-tool execution.prepend ordering, fallback paths).currentInitiator() fallback.MIT © Yum-wu