feat(p25): 反饋環深化 — caller-level quality 趨勢追蹤 + ROI 月報整合

Operation Ollama-First v5.0 / Phase 25 — 反饋環自主學習深化

services/feedback_quality_tracker.py (180+ 行)
- 純 SQL 統計，零 LLM 成本
- 4 個閾值常數（demote 👎×5/avg<2.5 / promote 👍×10/avg>=4.5）
- compute_caller_quality_trend(days=7) — 取近 N 日各 caller 反饋
- get_caller_recommendations() — 給 token 日報/ROI 月報用
  • 規則 1: 👎 ≥ 5 次 → review
  • 規則 2: avg < 2.5 + 樣本足 → review
  • 規則 3: 👍 ≥ 10 + avg ≥ 4.5 → promote（建議關閉 Gemini fallback）
- should_demote_caller(caller) — 自動降權判斷（戰役預設不啟用）
- render_quality_summary() — 給訊息用 emoji 摘要

ROI 月報整合（services/roi_report_service.py）：
- 加 Section 「💬 Caller 反饋趨勢（30 日）」TOP 10 by 最低 avg
- 加 Section 「🔮 智能建議」最多 3 條（review / promote）
- 失敗 swallow 不影響月報主流程

訊息範例:
  💬 Caller 反饋趨勢（30 日）
    ⚠️ openclaw_qa: avg 1.85/5 (👍2 👎8 n=12)
    ➖ hermes_analyst: avg 3.10/5 (👍5 👎3 n=10)
    ✅ ppt_gemini: avg 4.75/5 (👍12 👎0 n=15)
  🔮 智能建議
    ⚠️ openclaw_qa: 近 30 日 👎 反饋 8 次 (avg 1.85/5) — 建議統帥檢視 prompt 或切換 model
    ✅ ppt_gemini: 近 30 日 👍 反饋 12 次 — 可考慮關閉 Gemini fallback 純走 Ollama

tests/test_feedback_quality_tracker.py (10 tests 全綠)
- 4 閾值常數 / DB fail 安全 / 空 trends 容錯
- demote 規則（👎 多次）/ promote 規則（👍 多次）/ neutral 不觸發
- should_demote_caller 樣本不足保護
- trend 分類（positive/negative/neutral/no_data）正確

依 ADR-032 RAG 自主學習迴圈 + ADR-033 護欄 #1
不直接改 caller 行為（避循環自動修正失控），只產出建議給統帥審視。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/test_feedback_quality_tracker.py

@@ -0,0 +1,166 @@
+"""
+tests/test_feedback_quality_tracker.py
+─────────────────────────────────────────────────────────────────
+Operation Ollama-First v5.0 / Phase 25 — 反饋環深化驗證
+"""
+
+from datetime import datetime, timedelta
+from unittest.mock import MagicMock
+
+import pytest
+
+
+def test_constants_defined():
+    """4 個閾值常數應存在"""
+    from services.feedback_quality_tracker import (
+        DEMOTE_THUMBS_DOWN_THRESHOLD, DEMOTE_AVG_SCORE_THRESHOLD,
+        PROMOTE_THUMBS_UP_THRESHOLD, PROMOTE_AVG_SCORE_THRESHOLD,
+    )
+    assert DEMOTE_THUMBS_DOWN_THRESHOLD == 5
+    assert DEMOTE_AVG_SCORE_THRESHOLD == 2.5
+    assert PROMOTE_THUMBS_UP_THRESHOLD == 10
+    assert PROMOTE_AVG_SCORE_THRESHOLD == 4.5
+
+
+def test_compute_trend_db_fail_returns_empty(monkeypatch):
+    """DB 異常應回 {} 不 raise"""
+    from services.feedback_quality_tracker import compute_caller_quality_trend
+
+    class _BrokenSession:
+        def execute(self, *a, **kw):
+            raise RuntimeError('rag_query_log not exist')
+        def close(self):
+            pass
+
+    monkeypatch.setattr('database.manager.get_session', lambda: _BrokenSession())
+    result = compute_caller_quality_trend(days=7)
+    assert result == {}
+
+
+def test_render_summary_empty():
+    from services.feedback_quality_tracker import render_quality_summary
+    assert '無反饋資料' in render_quality_summary({})
+
+
+def test_render_summary_with_trends():
+    from services.feedback_quality_tracker import render_quality_summary
+    trends = {
+        'openclaw_qa': {
+            'total_feedback': 20, 'thumbs_up': 15, 'thumbs_down': 2,
+            'avg_score': 4.2, 'trend': 'neutral',
+        },
+        'hermes_analyst': {
+            'total_feedback': 8, 'thumbs_up': 1, 'thumbs_down': 6,
+            'avg_score': 1.8, 'trend': 'negative',
+        },
+    }
+    out = render_quality_summary(trends)
+    assert 'openclaw_qa' in out
+    assert 'hermes_analyst' in out
+    # negative 排前面（avg_score 升序）
+    assert out.index('hermes_analyst') < out.index('openclaw_qa')
+    assert '⚠️' in out  # negative emoji
+    assert '➖' in out  # neutral emoji
+
+
+def test_get_recommendations_demote_on_thumbs_down(monkeypatch):
+    """👎 ≥ 5 → review 建議"""
+    from services.feedback_quality_tracker import get_caller_recommendations
+    import services.feedback_quality_tracker as fqt
+
+    monkeypatch.setattr(fqt, 'compute_caller_quality_trend', lambda days: {
+        'bad_caller': {
+            'total_feedback': 8, 'thumbs_up': 1, 'thumbs_down': 6,
+            'avg_score': 1.8, 'trend': 'negative',
+        },
+    })
+
+    recs = get_caller_recommendations(days=7)
+    assert len(recs) == 1
+    assert recs[0]['caller'] == 'bad_caller'
+    assert recs[0]['action'] == 'review'
+    assert '6' in recs[0]['reason']  # 👎 6 次
+
+
+def test_get_recommendations_promote_on_thumbs_up(monkeypatch):
+    """👍 ≥ 10 + avg ≥ 4.5 → promote 建議"""
+    from services.feedback_quality_tracker import get_caller_recommendations
+    import services.feedback_quality_tracker as fqt
+
+    monkeypatch.setattr(fqt, 'compute_caller_quality_trend', lambda days: {
+        'great_caller': {
+            'total_feedback': 15, 'thumbs_up': 12, 'thumbs_down': 0,
+            'avg_score': 4.8, 'trend': 'positive',
+        },
+    })
+
+    recs = get_caller_recommendations(days=7)
+    assert len(recs) == 1
+    assert recs[0]['action'] == 'promote'
+    assert '可考慮關閉 Gemini fallback' in recs[0]['reason']
+
+
+def test_get_recommendations_neutral_no_action(monkeypatch):
+    """中等樣本不該觸發任何建議"""
+    from services.feedback_quality_tracker import get_caller_recommendations
+    import services.feedback_quality_tracker as fqt
+
+    monkeypatch.setattr(fqt, 'compute_caller_quality_trend', lambda days: {
+        'avg_caller': {
+            'total_feedback': 5, 'thumbs_up': 2, 'thumbs_down': 1,
+            'avg_score': 3.5, 'trend': 'neutral',
+        },
+    })
+
+    recs = get_caller_recommendations(days=7)
+    assert recs == []
+
+
+def test_should_demote_caller_with_low_avg(monkeypatch):
+    from services.feedback_quality_tracker import should_demote_caller
+    import services.feedback_quality_tracker as fqt
+
+    monkeypatch.setattr(fqt, 'compute_caller_quality_trend', lambda days: {
+        'troubled_caller': {
+            'total_feedback': 10, 'thumbs_up': 0, 'thumbs_down': 8,
+            'avg_score': 1.5, 'trend': 'negative',
+        },
+    })
+
+    assert should_demote_caller('troubled_caller', days=7) is True
+    assert should_demote_caller('not_in_trends', days=7) is False
+
+
+def test_should_demote_caller_insufficient_feedback(monkeypatch):
+    """樣本 < 5 不該降權（避免少量負面誤判）"""
+    from services.feedback_quality_tracker import should_demote_caller
+    import services.feedback_quality_tracker as fqt
+
+    monkeypatch.setattr(fqt, 'compute_caller_quality_trend', lambda days: {
+        'new_caller': {
+            'total_feedback': 3, 'thumbs_up': 0, 'thumbs_down': 2,
+            'avg_score': 1.5, 'trend': 'negative',
+        },
+    })
+
+    assert should_demote_caller('new_caller', days=7) is False
+
+
+def test_compute_trend_classifies_correctly(monkeypatch):
+    """模擬 SQL 結果驗證 trend 分類"""
+    from services.feedback_quality_tracker import compute_caller_quality_trend
+
+    fake_session = MagicMock()
+    fake_session.execute.return_value.fetchall.return_value = [
+        ('caller_positive', 12, 10, 0, 4.8),
+        ('caller_negative', 8, 0, 6, 1.5),
+        ('caller_neutral', 6, 3, 2, 3.2),
+        ('caller_no_data', 2, 1, 0, 4.0),
+    ]
+    monkeypatch.setattr('database.manager.get_session', lambda: fake_session)
+
+    trends = compute_caller_quality_trend(days=7)
+    assert trends['caller_positive']['trend'] == 'positive'
+    assert trends['caller_negative']['trend'] == 'negative'
+    assert trends['caller_neutral']['trend'] == 'neutral'
+    assert trends['caller_no_data']['trend'] == 'no_data'  # n < 3