Voyager Web Automator & Playwright Testing Suite

@nagi-ovo/voyager · v2.2.0

A Playwright-powered autonomous web browsing and E2E testing framework for DeepSeek Harness. Equips agents with full DOM interaction, multi-tab orchestration, visual regression, and form submission.

Browser-AutomationPlaywrightE2E-TestingRPA
GitHub Stars
59 K+
+12.4% this month
Monthly Downloads
267 K+
Monthly registry pulls
Reach Score
99.4/ 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 @nagi-ovo/voyager

Architecture

Voyager Suite bridges intelligent agents with real-world dynamic web applications. Complex enterprise portals, multi-factor authenticated dashboards, and drag-and-drop interfaces defy plain HTTP scrapers. This plugin integrates Playwright browser automation into DeepSeek Harness. Agents inspect active DOM accessibility trees, synthesize resilient ARIA locators, execute complex multi-step user workflows, and record reproducible test artifacts with trace logs and video playback.

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
Industrial Playwright Engine: Robust automation across Chromium, Firefox, and WebKit
02
Semantic ARIA Locators: Prioritizes accessible selectors that resist frontend markup refactoring
03
Full-Motion Trace Archival: Records step-by-step videos, network har logs, and console traces
04
Multi-Tab Context Management: Smoothly handles popups, OAuth login windows, and iframes

Core Workflow

01

Browser Sandbox Launch

Launches isolated Chromium processes with pristine storage and session states.

02

Actionable Element Binding

Analyzes the accessibility tree to synthesize robust semantic locators.

03

Humanlike Interaction

Executes clicks, keyboard strokes, drag operations, and file uploads.

04

State Assertion & Tracing

Captures screenshots, asserts network response codes, and archives zip traces.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
headlessbooleantrueLaunch browser in headless execution mode
recordVideobooleanfalseCapture full video recordings of sessions
viewportWidthnumber1280Default browser viewport width in pixels

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