EchoBird Token Quota & Traffic Rate-Limiting Router

@edison7009/echobird · v1.2.5

A token budget and traffic rate-limiting middleware for DeepSeek Harness fleets. Implements sliding-window rate limiting, multi-tenant token quotas, and smooth queue backpressure.

Rate-LimiterToken-QuotaBudget-GuardTraffic-Shaper
GitHub Stars
30 K+
+12.4% this month
Monthly Downloads
115 K+
Monthly registry pulls
Reach Score
98.1/ 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 @edison7009/echobird

Architecture

EchoBird Quota Router protects autonomous agent infrastructure from runaway token costs and rate limit exhaustion. In multi-tenant enterprise environments, a single rogue agent looping uncontrollably can burn thousands of dollars and starve critical services. This plugin implements sliding-window rate limiting and distributed token buckets directly inside Cordis. Platform engineers enforce granular Requests Per Minute (RPM) and Tokens Per Day limits scoped by team, user, or project ID. Requests gracefully queue during bursts and safely halt before exceeding strict organizational budget ceilings.

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
Sliding-Window Precision Rate Limiting: Prevents edge-burst exploits typical of fixed windows
02
Multi-Tenant Quota Hierarchy: Inherits limits across Organization, Department, and User trees
03
Intelligent Burst Queue Smoothing: Buffers temporary traffic peaks, avoiding sudden HTTP 429 errors
04
Real-Time Cost Dashboards & Alerts: Configurable 80% soft alerts and 100% hard budget circuit breakers

Core Workflow

01

Ingress Metering & Auth

Inspects incoming inference calls, extracting tenant ID and estimating token usage.

02

Token Bucket Evaluation

Checks distributed Redis token buckets to evaluate remaining rate limits.

03

Queue Buffer & Backpressure

Buffers transient burst traffic in priority queues, smoothing out invocation spikes.

04

Quota Trip & Alerting

Blocks calls cleanly when budgets deplete, triggering enterprise webhook alerts.

Configuration Parameters Reference (YAML / JSON)

ParameterTypeDefaultDescription
defaultDailyBudgetUsdnumber50.0Default daily spend cap per tenant in USD
maxRPMnumber60Default Requests Per Minute (RPM) ceiling
redisEndpointstringredis://127.0.0.1:6379Redis connection URL for distributed state

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