DSH Web Workshop Visual Canvas & Agent Workbench

@zhu1090093659/dsh-web-ui · v1.3.5

A real-time developer workbench and visual debugging canvas for DeepSeek Harness. Features live agent trajectory playback, tool call tracing, state inspection, and live variable manipulation.

Visual-WorkbenchDebuggerTrajectory-PlaybackWebUI
GitHub Stars
46 K+
+12.4% this month
Monthly Downloads
189 K+
Monthly registry pulls
Reach Score
99.0/ 100
Top Tier Ecosystem
Runtime
Cordis v3+
Node 18+ / Bun / Deno

Installation & Integration

CLI one-click launch, package managers, and Cordis integration

bash
manager:
$ pnpm add @zhu1090093659/dsh-web-ui

Architecture

DSH Web Workshop demystifies autonomous agent execution with a responsive developer GUI. When complex multi-step workflows deviate or fail silently, scanning tens of thousands of lines of terminal text is grueling and inefficient. This plugin launches an embedded local web server delivering an interactive observability canvas. Developers inspect step-by-step agent trajectories, audit tool arguments, inspect file diffs in real time, and inject variable overrides at logical breakpoints to steer autonomous behaviors interactively.

Architectural Principles & Constraints

01
Strict Type Isolation

Guaranteed by TypeScript compile-time contracts, inter-plugin event bus calls enjoy zero-drift safety.

02
Sub-Millisecond Hot Reload

Supports dynamic runtime mounting and graceful unloading without restarting the primary host process.

03
Deterministic State Machine

Embeds multi-phase execution lifecycle guards, preventing context loss during long-horizon reasoning.

04
Zero Native Build Dependencies

Designed for lightweight cross-platform environments, booting instantly across Node.js, Bun, and Deno.

Core Features

01
Zero-Friction Plug & Play: Spins up alongside agent daemons with instant browser access
02
Interactive Trajectory Scrubber: Step backwards and forwards through reasoning history
03
Live Visual File Diff Inspector: Clear syntax-highlighted diffs of every file modified in sandbox
04
Interactive Pause & Override: Pause execution at critical junctures to inject human corrections

Core Workflow

01

Workbench Server Spinup

Spins up local HTTP/WebSocket servers hosting the reactive debugging frontend.

02

Bus Telemetry Tap

Taps the Cordis event pipeline, broadcasting token streams and tool events to the UI.

03

Visual State Tree Render

Visualizes agent reasoning, tool dispatches, and environmental feedback as a DAG.

04

Intervention & Live Editing

Allows engineers to pause sessions, alter context variables, and resume execution.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
portnumber3210Local HTTP port for developer workbench
autoOpenBrowserbooleantrueAutomatically open browser window on launch
maxLogHistorynumber500Maximum trace logs retained in memory

Use Cases

Enterprise Production Agent

Relies on microkernel lifecycle guards and fault-tolerant state machines for continuous reliability.

SWE-bench Benchmark Evaluation

Native integration with SWE-bench workflows, automatically capturing diffs and verification metrics.

Autonomous Code Refactoring

Separates reasoning from tool actions to independently locate and refactor multi-file codebases.

Cross-Tool Workflow Automation

Safely orchestrates events across sandboxes to seamlessly link enterprise developer tooling.

Best Practices

01
Sandbox Permission Guard

Strictly isolate sub-process calls and network scope; deploy within Docker containers in production.

02
Exponential Backoff Retries

Configure adaptive exponential retries with strict timeouts to mitigate upstream model rate limits.

03
Session State Checkpointing

Persist state machine snapshots to survive hardware interruptions and resume instantly without loss.

04
Full Trajectory Audit Logs

Enable full trace logging, aggregating reasoning thought streams and tool I/O into your observability hub.

FAQ

Q1:How to handle timeouts in long-running autonomous tasks?

Increase the timeout parameter inside your YAML configuration and dispatch periodic heartbeat signals across the Cordis event bus. For long-running tool execution and model reasoning, configure persistent session snapshotting so suspended tasks can safely resume their exact context after interruptions, preventing the kernel from recycling active agent sessions prematurely.

Q2:How to capture and stream the model reasoning thought process?

The harness runtime natively provides end-to-end streaming hooks while its state machine automatically intercepts and strips <think> reasoning tags from model responses. Subscribe directly to the onThink event listener to consume live reasoning token streams in real-time, delivering typewriter animation to the user interface while persisting full trajectories for audit compliance.

Q3:How to resolve dependency conflicts across multiple plugins?

Cordis microkernel uses directed acyclic graph topological sorting to dynamically resolve plugin dependencies. When shared services or runtime versions conflict, assign distinct isolated namespaces at the application entrypoint. Leveraging context injection alongside lazy activation ensures dependencies load strictly on-demand when tools are triggered, maintaining system stability and preventing memory bloat.

Q4:How to enforce permissions and sandbox isolation in production?

Combine isolated container sandboxing with fine-grained capability checks to prevent plugins from accessing sensitive files or unauthorized external networks. Enforce explicit runtime system call whitelisting through the microkernel, executing all third-party tool scripts inside isolated ephemeral containers to block arbitrary code execution and eliminate security privilege escalation risks entirely.

Recommended Ecosystem Plugins

Explore related Cordis extensions designed to work synergistically