feat: AI chat conclusion + survey completion & management (#95)

* fix: increase assistant chat input height from 1 to 3 rows

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add Anthropic prompt caching to assistant chat

Cache the static system prompt and conversation history prefix across
turns, reducing input token costs by ~80% on multi-turn conversations.
RAG context is intentionally uncached since it changes per query.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add Microsoft Learn MCP integration + refine assistant system prompt

- Integrate Microsoft Learn MCP server via Anthropic's MCP connector
  for real-time documentation lookups (docs search, fetch, code samples)
- Refine system prompt: clear persona, structured answer guidelines,
  when to use RAG flows vs Microsoft Learn, guardrails against fabrication
- Add ENABLE_MCP_MICROSOFT_LEARN config toggle (default: True)
- Fix bugs from prior edit: wrong MCP URL, broken indentation, undefined
  usage/token variables, NOT_GIVEN for disabled MCP params
- Log MCP tool usage and cache performance

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: AI chat session conclusion + survey completion & management

AI Assistant - Conclude Session:
- 3-step modal: select outcome (resolved/escalated/paused), add notes, AI-generated summary
- AI generates structured ticket notes from conversation transcript (PSA-ready format)
- Copy to clipboard for pasting into ticketing systems
- "Resume in New Chat" for paused sessions (pre-loads context into new chat)
- Backend: POST /chats/{id}/conclude endpoint, conclusion_summary/outcome/concluded_at fields
- Migration 048: add conclusion fields to assistant_chats

Survey Completion Flow:
- Email-to-self option after submission (branded HTML email with formatted responses)
- Finish button navigates to /survey/thank-you page
- Thank you page with close-window message and feedback email callout
- Already-submitted state updated with same messaging
- Backend: POST /survey/email-copy public endpoint

Survey Admin Management:
- Read/unread indicators (cyan dot, bold name, auto-mark on expand)
- Unread count stat card
- Per-row context menu: mark read/unread, archive/unarchive, delete
- Bulk actions bar: select all, mark read/unread, archive, delete
- Show Archived toggle to filter archived responses
- Backend: 7 new admin endpoints (read, unread, archive, unarchive, delete, bulk)
- Migration 049: add is_read, archived_at to survey_responses

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: initialize VerifyEmailPage state from token to avoid setState in effect

Moves the no-token error case from useEffect into initial state to satisfy
the react-hooks/set-state-in-effect ESLint rule.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

backend/app/api/endpoints/survey.py

@@ -14,7 +14,7 @@ from app.core.email import EmailService
 from app.core.rate_limit import limiter
 from app.models.survey_invite import SurveyInvite
 from app.models.survey_response import SurveyResponse
-from app.schemas.survey import SurveyInviteStatus, SurveySubmission, SurveySubmissionResponse
+from app.schemas.survey import SurveyEmailCopyRequest, SurveyInviteStatus, SurveySubmission, SurveySubmissionResponse
 
 logger = logging.getLogger(__name__)
 
@@ -88,3 +88,79 @@ async def submit_survey(
     await db.commit()
 
     return SurveySubmissionResponse(id=str(response.id))
+
+
+# Question metadata for formatting email copy
+_QUESTION_LABELS = {
+    "prereqs": "Q1. Before you start troubleshooting, what info do you need?",
+    "verify_fix": "Q2. After you apply a fix, how do you verify it actually worked?",
+    "steps_at_a_time": "Q3. How many steps do you prefer to see at once?",
+    "first_step": "Q4. \"Internet is down.\" What's your FIRST move?",
+    "junior_mistake": "Q5. Most common mistake junior engineers make?",
+    "pivot": "Q6. When do you stop pursuing one theory and pivot?",
+    "scenario_approach": "Q7. First 3 diagnostic steps for this ticket.",
+    "scenario_deeper": "Q8. Server pings fine, you can RDP in. What next?",
+    "doc_pct": "Q9. Percentage of steps you actually document?",
+    "go_to_commands": "Q10. Top 3 go-to PowerShell commands?",
+    "secret_weapon": "Q11. Secret weapon command/tool/technique?",
+    "gotcha": "Q12. Issue where the obvious diagnosis was WRONG?",
+    "hard_rules": "Q13. Which rules do you follow?",
+    "prioritization": "Q14. Rank factors by diagnostic priority.",
+    "detail_level": "Q15. How specific should AI suggestions be?",
+    "ai_personality": "Q16. What makes an AI feel like a useful colleague?",
+}
+
+_QUESTION_ORDER = [
+    "prereqs", "verify_fix", "steps_at_a_time", "first_step", "junior_mistake",
+    "pivot", "scenario_approach", "scenario_deeper", "doc_pct", "go_to_commands",
+    "secret_weapon", "gotcha", "hard_rules", "prioritization", "detail_level", "ai_personality",
+]
+
+
+@router.post("/survey/email-copy")
+@limiter.limit("5/hour")
+async def email_survey_copy(
+    request: Request,
+    data: SurveyEmailCopyRequest,
+    db: Annotated[AsyncSession, Depends(get_db)],
+):
+    """Email a copy of survey responses to the respondent."""
+    from uuid import UUID as _UUID
+
+    try:
+        resp_id = _UUID(data.response_id)
+    except ValueError:
+        raise HTTPException(status_code=400, detail="Invalid response ID")
+
+    result = await db.execute(
+        select(SurveyResponse).where(SurveyResponse.id == resp_id)
+    )
+    response = result.scalar_one_or_none()
+    if not response:
+        raise HTTPException(status_code=404, detail="Response not found")
+
+    # Build formatted responses for the email
+    answers = response.responses or {}
+    formatted_lines = []
+    for qid in _QUESTION_ORDER:
+        label = _QUESTION_LABELS.get(qid, qid)
+        val = answers.get(qid)
+        if isinstance(val, list):
+            answer_str = ", ".join(str(v) for v in val)
+        elif val is not None:
+            answer_str = str(val)
+        else:
+            answer_str = "(no answer)"
+        formatted_lines.append(f"{label}\n{answer_str}")
+
+    try:
+        await EmailService.send_survey_copy_email(
+            to_email=data.email,
+            respondent_name=response.respondent_name,
+            formatted_responses="\n\n".join(formatted_lines),
+        )
+    except Exception:
+        logger.exception("Failed to send survey copy email to %s", data.email)
+        raise HTTPException(status_code=502, detail="Failed to send email. Please try again.")
+
+    return {"message": "Email sent"}