iPolloWork Human-in-the-Loop Workbench & Governance Hub

@devin-axis/ipollowork · v1.3.0

An enterprise Human-in-the-Loop (HITL) developer workbench for DeepSeek Harness. Features interactive code diff review, approval gates for critical commands, and web terminal management.

Human-in-the-LoopHITLCode-ReviewGovernance
GitHub Stars
34 K+
+12.4% this month
Monthly Downloads
129 K+
Monthly registry pulls
Reach Score
98.4/ 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 @devin-axis/ipollowork

Architecture

iPolloWork Workbench restores ultimate human agency over autonomous agent actions. While fully autonomous coding agents deliver remarkable productivity, irrevocable actions—such as dropping tables or altering firewall rules—demand deterministic human oversight. This plugin integrates Human-in-the-Loop (HITL) checkpoints into the Cordis lifecycle. Agents pause gracefully at critical junctures to prompt engineers with structured multi-choice options or request explicit command authorizations. A responsive browser interface provides live file diff reviews and terminal access for instant intervention.

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
Non-Destructive HITL Pause: Safely suspends agent loops awaiting human sign-off without data loss
02
Interactive Visual Diff Viewer: Line-by-line syntax-highlighted diffs of proposed file modifications
03
Multi-Channel Bot Integration: Sends interactive approval cards directly to Slack, Feishu, and Teams
04
Live Web Terminal Takeover: One-click terminal access for developers to debug sandboxes directly

Core Workflow

01

Critical Policy Detection

Agent proposes high-risk shell commands or structural edits, hitting governance gates.

02

Structured Human Prompt

Pushes actionable notification cards with visual diffs and choices to Slack/Feishu.

03

Engineer Review & Feedback

Engineer inspects diffs in the web UI, clicking Approve, Reject, or typing guidance.

04

Atomic Resume & Execution

Bus receives authorization signal, injecting feedback to advance downstream steps.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
approvalTimeoutMinutesnumber30Timeout in minutes awaiting human response
notificationWebhookstring-Notification webhook URL for approval cards
requireApprovalForGitPushbooleantrueRequire human sign-off before Git pushes

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