Balance Whale Cloud Billing & Budget Telemetry Widget

@meteornox/balance-whale-widget · v1.0.4

A lightweight cloud billing and token expenditure monitor for DeepSeek Harness. Features multi-provider balance tracking, burn-rate telemetry, and automated low-balance safeguards.

Billing-MonitorBudget-WidgetCost-ControlBurn-Rate
GitHub Stars
17 K+
+12.4% this month
Monthly Downloads
68 K+
Monthly registry pulls
Reach Score
97.1/ 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 @meteornox/balance-whale-widget

Architecture

Balance Whale eliminates cloud billing anxiety for AI engineers. Running unattended agent evaluations or data synthesis pipelines overnight often results in shocking bills or sudden API service cuts due to account exhaustion. This plugin integrates lightweight billing telemetry directly into DeepSeek Harness. Querying real-time balance endpoints across DeepSeek, Anthropic, and OpenRouter, it calculates live burn rates (dollars per hour) and projects monthly costs. When balances cross critical thresholds, it dispatches proactive warnings or halts non-essential workers automatically.

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
Unified Multi-Vendor Balance Hub: Consolidates balances across DeepSeek, Claude, and OpenAI
02
Real-Time Hourly Burn Rates: Pinpoints exactly how much cash active test jobs are consuming per hour
03
Custom Low-Balance Warning Gates: Dispatches notifications before unexpected service freezes hit
04
Minimal Footprint: Lightweight polling routines consuming <5MB memory with zero CPU overhead

Core Workflow

01

Multi-Provider Balance Probe

Silently polls official account balance APIs across configured LLM providers.

02

Burn-Rate Projection

Combines active token burn rates to linearly project end-of-month expenditure.

03

Micro-Widget Rendering

Renders non-intrusive live telemetry badges on web workbenches and terminal headers.

04

Low-Balance Safety Trip

Dispatches urgent threshold alerts and cleanly halts non-essential test batches.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
warningThresholdUsdnumber10.0Low balance warning threshold in USD
pollIntervalMinutesnumber15Balance polling interval in minutes
haltOnDepletionbooleantrueAuto-halt non-critical jobs on low balance

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