القائمة
Use when inspecting AI assistant file-based long-term memory, session JSONL archives, soft consolidation, Dream updates, or assistant context isolation.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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.
| name | assistant-memory-tool |
| description | Use when inspecting AI assistant file-based long-term memory, session JSONL archives, soft consolidation, Dream updates, or assistant context isolation. |
AI assistant memory follows the file workspace design implemented in backend/app/services/ai_assistant_file_memory.py, while PostgreSQL chat_sessions remains the business source of truth.
Runtime path:
runtime/ai_assistant_memory/users/<user_id>/
sessions/<session_id>.jsonl
memory/history.jsonl
USER.md
MEMORY.md
SOUL.md
Use this skill to inspect the memory boundary:
interview_sessions.report.agent_state.memory/history.jsonl; it does not overwrite raw sessions/*.jsonl.Legacy assistant_memories scripts still exist for older audit data, but the current AI assistant runtime context comes from runtime/ai_assistant_memory.
Inspect legacy database memories if needed:
docker compose exec api python /app/skills/assistant-memory-tool/scripts/inspect_memory.py --email admin@example.com --assistant-type ai_assistant
Export older database memory snapshots if needed:
docker compose exec api python /app/skills/assistant-memory-tool/scripts/export_memory_md.py --email admin@example.com --assistant-type ai_assistant
Inspect current file memory from the host or container:
Get-ChildItem runtime\ai_assistant_memory\users -Recurse
When reporting current runtime memory, summarize file names, item counts, and whether consolidation happened. Do not print full private messages, raw prompts, API keys, or complete resume text.
Explain memory as lightweight context, not authoritative fact. The authoritative records remain PostgreSQL users, resumes, jobs, applications, chat_sessions, and interview_sessions. Mention explicitly that the two assistants are isolated: AI assistant file memory is not interview memory.
python skills/assistant-memory-tool/scripts/inspect_memory.py --self-test
python skills/assistant-memory-tool/scripts/export_memory_md.py --self-test
docker compose exec api pytest tests/memory/test_ai_assistant_file_memory.py tests/interview/test_interview_short_memory.py -q