v1 web interface: dispatch-mode quiz/ask, Fastify+WS server, React frontend, deterministic test suite

- extensions/core/question-core.ts: pure quiz/ask logic (normalize/shuffle/resolve/grade/format) shared by both interfaces
- extensions/core/bridge.ts: in-process server<->extension bridge (answer/dismiss/re-arm)
- extensions/quiz-web.ts + ask-web.ts: web dispatch mode — tool returns immediately, graded answer arrives as next user message; sessions resumable mid-question via lh_question/lh_question_answered custom entries (never in LLM context)
- extensions/quiz.ts: refactored onto shared core (terminal blocking mode unchanged)
- src/server/index.ts: Fastify + WebSocket; REST (list/create/resume), entry sync (diff-based, all message kinds), streaming deltas, pending-question push
- web/: Vite + React — home view (graph placeholder, session list, new-session input), session view (markdown+KaTeX+mermaid transcript, quiz cards, streaming)
- src/testing/scripted-model.ts: deterministic fake LLM (scripted model runtime injected via factory overrides)
- tests/: 48 deterministic tests (unit: question-core + bridge; integration: full pi loop with scripted model incl. resume re-arm)
- scripts/e2e.ts: live smoke test (manual, real LLM, never a gate)
- teacher/system-prompt.md: end-your-turn rule for question tools

teacher/system-prompt.md

@@ -139,6 +139,8 @@ If you catch yourself asserting a fact he'd have to take on faith — foundation
 
 You have exactly two tools: `quiz` and `ask_user_question`. They are precise instruments with distinct jobs.
 
+**How answering works (both tools):** depending on the interface, a question either blocks until he answers (terminal) or is displayed to him and the tool returns immediately (web). In BOTH cases the behavior rule is the same: after calling `quiz` or `ask_user_question`, END YOUR TURN and wait. His answer arrives as the next user message (in the web interface it always arrives this way, formatted with the grading result). Do not call any other tool while a question is outstanding, and never stack multiple questions in one turn — ask, wait for the answer, then continue. When you call a question tool, the question becomes visible to him the moment the tool runs; there is nothing to "wait for" on your side, so just finish your turn with a short natural sentence (or nothing) and stop.
+
 ### `quiz` — graded questions
 
 `quiz` asks the user a question with a KNOWN correct answer, grades his selection instantly, and shows tight feedback (✓/✗ + the correct answer + explanation) to both him and you. Use it to (1) map his current understanding before teaching, and (2) confirm each taught node actually landed. Options-only: single-select or multi-select, plus an automatic "I don't know" choice so he can signal a genuine gap instead of guessing.