intern-agent

Use when inspecting AI assistant file-based long-term memory, session JSONL archives, soft consolidation, Dream updates, or assistant context isolation.

Use when running Agent golden-case evaluation, checking intent accuracy, tool-call accuracy, RAG grounding, job matching, interview follow-up policy, or resume rubric compliance.

Use when reading saved jobs, application status counts, manual follow-up notes, or the user's application tracking state.

Use when inspecting FastAPI routes, controllers, backend service boundaries, repository-backed endpoints, API surface, or route availability.

Use when inspecting or explaining Qingcheng AI chat complexity classification, prompt-template injection, SupervisorAgent routing, selected tool allowlists, or agent planning for a user message.

Use when changing or reviewing the Next.js frontend UI, Tailwind layout, chat/interview pages, resume/job/application screens, or frontend API wrappers.

Use when inspecting simulated interview Agent short-term session state, job-resume binding, question plan progress, answer signals, difficulty, follow-up strategy, or remaining focus.

Use when searching or explaining InternAgent job discovery, recommendation, match scoring, source labels, query expansion, city filters, or missing skills.

Use when answering or debugging AI assistant knowledge_search, Java/backend interview notes, Hybrid RAG retrieval, citations, sufficiency, or knowledge chunk references.

Use when checking InternAgent LLM provider abstraction, Gemma4/Ollama transport, provider health, generation reachability, model name, or timeout diagnostics.

Use when reading a user's default resume profile, resume parse status, resume score, rubric dimensions, risks, or skills for Agent context.

Use when starting, stopping, rebuilding, or diagnosing the InternAgent Docker Compose runtime, API health, nginx routing, frontend container, or local service recovery.

Use when creating, listing, testing, or debugging Qingcheng AI scheduled tasks, task inbox results, worker execution, natural-language reminder parsing, or Telegram task commands.

Use when configuring, testing, or explaining Qingcheng AI Telegram binding, AI-assistant chat bridging, proactive notification candidates, LLM send/skip decisions, cooldowns, quiet hours, or Telegram delivery failures.