Bjornmelin

World-class pytest engineer for Python: write/refactor tests, fix flakiness, design fixtures/markers, add coverage, speed up suites (collection/runtime), and optimize CI (GitHub Actions sharding, xdist parallelism, caching). Use when asked about pytest best practices, pytest 9.x features (subtests, strict mode, TOML config), pytest plugins (xdist/cov/asyncio/mock/httpx), or test performance/CI tuning.

Architect-level guidance, workflows, and scripts for building agentic coding systems with OpenAI Codex. Use for Codex SDK (@openai/codex-sdk) threads + streaming JSONL events; Codex CLI automation (codex exec, output schema, JSONL, resume); MCP server usage (codex mcp-server) and dynamic tool integration; multi-agent orchestration with OpenAI Agents SDK (handoffs, gating, tracing); durable state, caching, and memory using SQLite; safe-by-default sandbox/approval patterns and execpolicy rules.

Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep, callOptionsSchema/prepareCall, dynamic tool selection, tool loops, or agent workflows (sequential, routing, evaluator-optimizer, orchestrator-worker). Triggers: ToolLoopAgent, agent loop, stopWhen, stepCountIs, prepareStep, callOptionsSchema, prepareCall, hasToolCall, InferAgentUIMessage, agent workflows.

Expert guidance for AI SDK Core: text generation, structured data, tool calling (tool/dynamicTool), MCP integration (createMCPClient, Experimental_StdioMCPTransport), embeddings/reranking, provider setup, middleware, telemetry, and error handling. Use when building with generateText/streamText, generateObject/streamObject, tools (needsApproval, strict, inputExamples, activeTools, toolChoice, experimental_context), embeddings (embed/embedMany/rerank), or MCP tools/resources/prompts/elicitation.

World-class Vitest QA/test engineer for TypeScript + Next.js (local + CI performance focused)

Expert guidance for Vercel's Streamdown library - a streaming-optimized react-markdown replacement for AI applications. Use when: (1) Rendering AI-generated markdown from useChat/streamText, (2) Building chat UIs with streaming responses, (3) Migrating from react-markdown to streaming-friendly rendering, (4) Configuring code blocks (Shiki), math (KaTeX), diagrams (Mermaid), (5) Handling incomplete markdown during AI streaming (remend preprocessor), (6) Customizing markdown styling with Tailwind/CSS variables, (7) Securing AI output with rehype-harden (link/image protocols). Triggers: Streamdown, streaming markdown, AI chat markdown, react-markdown replacement, AI Elements Response, incomplete markdown, remend, Shiki themes, Mermaid diagrams, KaTeX math, rehype-harden, isAnimating, markdown streaming.

Architect-level development, audit, and migration of multi-agent systems using LangGraph (v1+) and LangChain (v1+). Use when building or refactoring supervisor/subagent architectures, orchestrator-worker workflows, routing/hand-offs, agentic RAG, memory (short + long-term), state + context engineering, guardrails + human-in-the-loop, MCP tool integration, observability (LangSmith/OpenTelemetry), deployment, and performance/cost optimization — or when migrating off deprecated patterns like `langgraph.prebuilt.create_react_agent` and libraries like `langgraph-supervisor(-py)`, LlamaIndex agents, CrewAI, Agno, or OpenAI Agents.