Agent Observability Fault Tolerance
Design and review agent runtime observability and model/provider fault tolerance. Use when adding metrics, traces, cost tracking, audit alignment, structured runtime events, model fallback, structured output repair, refusal handling, provider timeouts, or local execution tree diagnostics.
Bff Transport Boundary
Design and review Backend-for-Frontend transport boundaries. Use when implementing or changing request parsing, response mapping, streaming proxy behavior, CORS, header allowlists, authentication boundaries, timeouts, cancellation, error envelopes, or upstream orchestration.
Node Engineering
Guide robust Node.js and TypeScript engineering. Use when working on Node services, scripts, CLIs, tests, streams, async workflows, module boundaries, environment configuration, logging, caching, profiling, or graceful shutdown.
Distributed Step Lock
Design and review distributed locks for agent step transitions. Use when preventing concurrent workers, duplicate resumes, retries, compensation, or external requests from mutating the same task or step state at the same time.
Retry Budget Policy
Design and review retry budgets for agent steps, tools, providers, and transport calls. Use when classifying retryable errors, enforcing max attempts, respecting Retry-After, applying backoff and jitter, handling timeouts, or preventing retries for permission, validation, business, or user-cancelled failures.
Tool Renderer Contract
Design and review structured tool-result rendering. Use when rendering tool calls, tool messages, structured tool outputs, status cards, fallback JSON/text displays, parser boundaries, display status mappings, or unknown tool results.
Frontend Ui Engineering
Build production-quality frontend interfaces. Use when creating or modifying UI components, layouts, interaction states, responsive behavior, accessibility, visual polish, or user-facing workflows.
Observability And Instrumentation
Add or review observability. Use when adding logs, metrics, traces, audit events, health checks, alerts, or production diagnostics for features, background jobs, APIs, tools, and integrations.
Compensation Saga Runtime
Design and review compensation and Saga runtime behavior for agent workflows. Use when handling multi-step side effects, rollback plans, irreversible actions, compensation ordering, manual escalation, cancellation cleanup, or audit-linked recovery flows.
Frontend Streaming Contract
Design and review frontend streaming contracts. Use when handling server-sent events, WebSocket messages, async iterables, stream parsers, reducer state, terminal states, progress timelines, cancellation, retries, or UI updates driven by runtime events.
Agent Task State Machine
Design and review generic agent task and step state machines. Use when adding business-level task progress, step lifecycle tracking, task events, persistence, streaming timelines, resumable task state, or cross-layer task status APIs.
Langgraph Runtime Boundary Review
Review LangGraph native runtime boundaries before building custom agent runtime infrastructure. Use when deciding whether queueing, workers, checkpointers, stores, interrupts, resume flows, retries, task semantics, audit, locks, or cost tracking should be native runtime responsibilities or custom application runtime responsibilities.
Code Review And Quality
Conduct multi-axis code review. Use before merging code written by an agent or human, when assessing diffs for correctness, maintainability, security, tests, observability, and contract risk.
Langgraph Backend Contract
Design and review LangGraph backend contracts. Use when creating or changing graph state, nodes, edges, reducers, commands, sends, checkpoints, runtime events, provider adapters, tool adapters, prompts, terminal states, or resumable workflows.
Type Boundary Contract
Design and review type contracts across package, service, frontend, backend, tool, event, and transport boundaries. Use when defining schemas, discriminated unions, runtime parsers, error envelopes, schemaVersion fields, or duplicated transport/domain types.
Security And Hardening
Harden software against security risk. Use when handling user input, authentication, authorization, sessions, secrets, file uploads, external integrations, webhooks, browser data, storage, or privileged actions.
Context Budget Governance
Design and review context budget governance for agent prompts and model calls. Use when assembling long conversation context, tool results, retrieved evidence, memory, task state, system rules, multimodal observations, or compressed summaries under a token budget.
Test Driven Development
Drive implementation with tests. Use when fixing bugs, changing behavior, adding logic, modifying contracts, or proving that agent-written code works and remains safe across regressions.
Idempotency Audit Contract
Design and review idempotency and audit contracts for agent runtimes. Use when preventing duplicate side effects, propagating idempotency keys, persisting operation history, redacting sensitive payloads, auditing tool decisions, or reconstructing task execution after retries and resumes.
Performance Optimization
Optimize application performance with evidence. Use when latency, throughput, memory, bundle size, rendering speed, Core Web Vitals, query time, startup time, or resource usage matters.
Incremental Implementation
Deliver changes in small verifiable increments. Use when implementing a multi-file feature, refactor, migration, bug fix, or any task that is large enough to become risky if completed in one pass.
Api And Interface Design
Guide stable API and interface design. Use when creating or changing public module boundaries, REST or GraphQL endpoints, event contracts, SDK methods, data transfer objects, error envelopes, or cross-team interfaces.
Debugging And Error Recovery
Guide systematic root-cause debugging. Use when tests fail, builds break, runtime behavior is unexpected, logs show errors, or repeated fixes are not resolving the same issue.
Chat Gun React Agent
🤖A production-oriented full-stack Agent Chat system built with React, TypeScript, LangGraph JS, Qwen/OpenAI-compatible models, native tools, optional MCP, HITL, streaming events, multimodal input, and deep research workflows.