feat(p46): Agent 編排矩陣新頁 — OpenClaw/Hermes/NemoTron/EA × Ollama × Gemini × MCP × RAG
All checks were successful
CD Pipeline / deploy (push) Successful in 2m30s

統帥要求:「好好把 OpenClaw/Hermes/NemoTron/ElephantAlpha + Ollama 多模型
+ 外部付費 Gemini + 內外 MCP + RAG 組合發揮出 AI 自動化新境界」

新頁面 /observability/agent_orchestration 一頁式呈現 4 Agent × 5 維度全景:

J-1: caller 自動分組
- OpenClaw: openclaw_qa/daily/meta/monthly/weekly/bot_main/bot_gemini/bot_nim
            + sales_copy + code_review_openclaw
- Hermes: hermes_analyst + hermes_intent + code_review_hermes
- NemoTron: nemotron_dispatch
- ElephantAlpha: ea_engine + code_review_elephant

J-2/3: 跨表 SQL JOIN(ai_calls × mcp_calls × rag_query_log)
每個 agent 顯示:
- 24h 呼叫 + Token + 成本
- 本地 Ollama 比例(細分 GCP-A/GCP-B/111)
- 付費 LLM 比例(細分 Gemini / 其他)
- MCP 編排率(透過 request_id 跨表 JOIN mcp_calls)
- RAG 命中率
- 錯誤率 + 平均耗時
- MCP server × caller 工作量明細

自動編排建議(5 條 rule-based):
1. 付費比例 > 50% 且 ollama < 20% → 改 Hermes-first 短路
2. 錯誤率 > 10% → 觸發 Code Review Pipeline
3. MCP 編排率 < 5% 但 calls > 50 → 擴大 MCP omnisearch/firecrawl
4. RAG 命中率 ≥ 40% → 推 Telegram 收 feedback 強化 promotion gate
5. 111 fallback 比例 > 20% → GCP 兩台異常,查 host_health AIOps

J-4: 入口
- sidebar AI 觀測 group 加「Agent 編排矩陣」(07b)
- /observability/overview 入口卡升級為 7 項,Agent 編排矩陣放第一

整體 KPI 卡片:
- 總呼叫 / 本地 Ollama 比例 / 付費 LLM 成本 / RAG 命中率
- 「組合發揮」一目瞭然

8 表跨 JOIN:ai_calls × mcp_calls × rag_query_log × ai_insights ×
learning_episodes × incidents × heal_logs × host_health_probes

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
OoO
2026-05-04 19:38:10 +08:00
parent 849e189b60
commit 347efb8ea1
4 changed files with 526 additions and 2 deletions

View File

@@ -247,6 +247,262 @@ def observability_overview():
)
# ─────────────────────────────────────────────────────────────────────────────
# /observability/agent_orchestration — Phase 46 編排矩陣
# ─────────────────────────────────────────────────────────────────────────────
# caller → agent 歸類規則(同 services/* 各 agent 真實 caller 值)
_AGENT_CALLER_GROUPS = {
'openclaw': [
'openclaw_qa', 'openclaw_daily', 'openclaw_daily_insight',
'openclaw_meta', 'openclaw_monthly', 'openclaw_weekly',
'openclaw_bot_main', 'openclaw_bot_gemini', 'openclaw_bot_nim',
'sales_copy', 'code_review_openclaw',
],
'hermes': [
'hermes_analyst', 'hermes_intent', 'code_review_hermes',
],
'nemotron': [
'nemotron_dispatch',
],
'elephant_alpha': [
'ea_engine', 'code_review_elephant',
],
}
_AGENT_LABELS = {
'openclaw': ('🤖 OpenClaw', '主編排者 / Bot 對話 / 報告生成'),
'hermes': ('🔍 Hermes', '價格/程式碼分析師'),
'nemotron': ('🧬 NemoTron', '任務 dispatcher'),
'elephant_alpha': ('🐘 ElephantAlpha', '自主決策引擎'),
}
# Provider → 類別歸類
_PROVIDER_TIER = {
'gcp_ollama': 'ollama_local',
'ollama_secondary': 'ollama_local',
'ollama_111': 'ollama_local',
'ollama_other': 'ollama_local',
'gemini': 'paid_external',
'claude': 'paid_external',
'nim': 'paid_external',
'nim_via_elephant': 'paid_external',
'openrouter': 'paid_external',
}
@admin_observability_bp.route('/agent_orchestration')
@login_required
def agent_orchestration_dashboard():
"""Phase 46 — 4 Agent × Models × MCP × RAG 編排矩陣
展現「組合發揮」:每個 agent 在 24h 內如何調用 Ollama/Gemini
搭配 MCP tool外部 + 內部 mcp_collector與 RAG 知識庫的協作。
資料來源ai_calls × mcp_calls × rag_query_log 三表跨 JOIN + caller 分組。
"""
hours = int(request.args.get('hours', '24'))
session = get_session()
try:
# 1. 整體統計
overall = session.execute(
sa_text("""
SELECT COUNT(*),
COALESCE(SUM(cost_usd), 0),
COUNT(*) FILTER (WHERE provider IN ('gemini','claude','nim','openrouter','nim_via_elephant')),
COUNT(*) FILTER (WHERE provider IN ('gcp_ollama','ollama_secondary','ollama_111','ollama_other')),
COUNT(*) FILTER (WHERE rag_hit),
COALESCE(SUM(input_tokens + output_tokens), 0)
FROM ai_calls
WHERE called_at >= NOW() - (:h * INTERVAL '1 hour')
"""),
{'h': hours},
).fetchone()
total_calls = int(overall[0] or 0)
total_cost = float(overall[1] or 0)
paid_calls = int(overall[2] or 0)
local_calls = int(overall[3] or 0)
rag_hits = int(overall[4] or 0)
total_tokens = int(overall[5] or 0)
# 2. 每個 agent group 的細節
agent_matrix = []
for agent_key, callers in _AGENT_CALLER_GROUPS.items():
ag_row = session.execute(
sa_text("""
SELECT COUNT(*) AS calls,
COALESCE(SUM(input_tokens + output_tokens), 0) AS tokens,
COALESCE(SUM(cost_usd), 0) AS cost,
COUNT(*) FILTER (WHERE rag_hit) AS rag_hits,
COUNT(*) FILTER (WHERE provider IN ('gcp_ollama','ollama_secondary','ollama_111','ollama_other')) AS ollama,
COUNT(*) FILTER (WHERE provider = 'gcp_ollama') AS ollama_gcp_a,
COUNT(*) FILTER (WHERE provider = 'ollama_secondary') AS ollama_gcp_b,
COUNT(*) FILTER (WHERE provider = 'ollama_111') AS ollama_111,
COUNT(*) FILTER (WHERE provider = 'gemini') AS gemini,
COUNT(*) FILTER (WHERE provider IN ('claude','nim','openrouter','nim_via_elephant')) AS other_paid,
COUNT(*) FILTER (WHERE status NOT IN ('ok','cache_only')) AS errors,
COALESCE(AVG(duration_ms), 0) AS avg_ms
FROM ai_calls
WHERE called_at >= NOW() - (:h * INTERVAL '1 hour')
AND caller = ANY(:callers)
"""),
{'h': hours, 'callers': callers},
).fetchone()
calls = int(ag_row[0] or 0)
if calls == 0:
# 沒呼叫也佔位顯示
agent_matrix.append({
'key': agent_key, 'label': _AGENT_LABELS[agent_key][0],
'desc': _AGENT_LABELS[agent_key][1],
'calls': 0, 'tokens': 0, 'cost': 0,
'rag_hits': 0, 'rag_rate': 0,
'ollama_pct': 0, 'gemini_pct': 0, 'paid_pct': 0,
'ollama_gcp_a': 0, 'ollama_gcp_b': 0, 'ollama_111': 0,
'gemini': 0, 'other_paid': 0,
'errors': 0, 'error_rate': 0,
'avg_ms': 0, 'mcp_calls': 0, 'mcp_rate': 0,
'callers_in_group': callers,
})
continue
# MCP 編排率(透過 request_id 串接)
mcp_count = session.execute(
sa_text("""
SELECT COUNT(DISTINCT a.request_id)
FROM ai_calls a
INNER JOIN mcp_calls m ON m.request_id = a.request_id
WHERE a.called_at >= NOW() - (:h * INTERVAL '1 hour')
AND a.caller = ANY(:callers)
AND a.request_id IS NOT NULL
"""),
{'h': hours, 'callers': callers},
).fetchone()[0] or 0
errors = int(ag_row[10] or 0)
ollama = int(ag_row[4] or 0)
gemini = int(ag_row[8] or 0)
other_paid = int(ag_row[9] or 0)
agent_matrix.append({
'key': agent_key,
'label': _AGENT_LABELS[agent_key][0],
'desc': _AGENT_LABELS[agent_key][1],
'calls': calls,
'tokens': int(ag_row[1] or 0),
'cost': float(ag_row[2] or 0),
'rag_hits': int(ag_row[3] or 0),
'rag_rate': (float(ag_row[3] or 0) / calls * 100) if calls else 0,
'ollama': ollama, 'ollama_pct': (ollama / calls * 100) if calls else 0,
'ollama_gcp_a': int(ag_row[5] or 0),
'ollama_gcp_b': int(ag_row[6] or 0),
'ollama_111': int(ag_row[7] or 0),
'gemini': gemini, 'gemini_pct': (gemini / calls * 100) if calls else 0,
'other_paid': other_paid,
'paid_pct': ((gemini + other_paid) / calls * 100) if calls else 0,
'errors': errors, 'error_rate': (errors / calls * 100) if calls else 0,
'avg_ms': int(ag_row[11] or 0),
'mcp_calls': int(mcp_count),
'mcp_rate': (float(mcp_count) / calls * 100) if calls else 0,
'callers_in_group': callers,
})
# 3. MCP server 24h 工作量(同 host_health 邏輯)
mcp_servers = session.execute(
sa_text("""
SELECT server, caller, COUNT(*) AS calls,
COUNT(*) FILTER (WHERE cache_hit) AS cache_hits,
COALESCE(SUM(cost_usd), 0) AS cost
FROM mcp_calls
WHERE called_at >= NOW() - (:h * INTERVAL '1 hour')
GROUP BY server, caller
ORDER BY calls DESC
LIMIT 30
"""),
{'h': hours},
).fetchall()
mcp_matrix = [
{
'server': r[0], 'caller': r[1],
'calls': int(r[2] or 0),
'cache_hits': int(r[3] or 0),
'cost': float(r[4] or 0),
'cache_rate': (float(r[3] or 0) / float(r[2]) * 100) if r[2] else 0,
}
for r in mcp_servers
]
# 4. 自動編排建議rule-based 提案)
recommendations = []
for ag in agent_matrix:
if ag['calls'] == 0:
continue
# 規則 1付費比例 > 50% 且 ollama 比例 < 20% → 建議切 Hermes-first
if ag['paid_pct'] > 50 and ag['ollama_pct'] < 20:
recommendations.append({
'severity': 'high', 'agent': ag['label'],
'finding': f"付費 LLM 比例 {ag['paid_pct']:.0f}%cost ${ag['cost']:.2f}",
'suggestion': '改用 Hermes-first 短路機制:先試 Ollama 三主機 5s timeout0 hits 才 escalate Gemini',
})
# 規則 2錯誤率 > 10% → 建議跑 code review
if ag['error_rate'] > 10:
recommendations.append({
'severity': 'high', 'agent': ag['label'],
'finding': f"錯誤率 {ag['error_rate']:.1f}%{ag['errors']}/{ag['calls']}",
'suggestion': '觸發 Code Review Pipeline 找 regressionai_calls 觀測台一鍵)',
})
# 規則 3MCP 編排率 < 5% 但 calls 多 → 建議擴大 MCP 使用
if ag['mcp_rate'] < 5 and ag['calls'] > 50:
recommendations.append({
'severity': 'med', 'agent': ag['label'],
'finding': f"MCP 編排率僅 {ag['mcp_rate']:.1f}%,未善用外部工具",
'suggestion': '考慮加 MCP omnisearch / firecrawl 補強事實查證鏈',
})
# 規則 4RAG 命中率高≥40%)但有 saved_call=False 的多 → 提醒 feedback
if ag['rag_rate'] >= 40 and ag['rag_hits'] >= 20:
recommendations.append({
'severity': 'low', 'agent': ag['label'],
'finding': f"RAG 命中率 {ag['rag_rate']:.1f}%{ag['rag_hits']} hits— 知識庫貢獻度高",
'suggestion': '推 Telegram inline button 收集 feedback_score 強化 promotion gate',
})
# 規則 5111 fallback 比例 > 20% → 警示
if ag['calls'] > 0 and ag['ollama_111'] / max(ag['calls'], 1) > 0.20:
fb_pct = ag['ollama_111'] / ag['calls'] * 100
recommendations.append({
'severity': 'med', 'agent': ag['label'],
'finding': f"111 fallback 比例 {fb_pct:.0f}%GCP 兩台不可達?)",
'suggestion': '檢查 mo.wooo.work/observability/host_health AIOps incidents',
})
return render_template(
'admin/agent_orchestration.html',
active_page='obs_agent_orchestration',
hours=hours,
agent_matrix=agent_matrix,
mcp_matrix=mcp_matrix,
recommendations=recommendations,
overall={
'total_calls': total_calls,
'total_cost': total_cost,
'total_tokens': total_tokens,
'paid_calls': paid_calls,
'local_calls': local_calls,
'rag_hits': rag_hits,
'paid_pct': (paid_calls / total_calls * 100) if total_calls else 0,
'local_pct': (local_calls / total_calls * 100) if total_calls else 0,
'rag_rate': (rag_hits / total_calls * 100) if total_calls else 0,
},
error=None,
)
except Exception as e:
return render_template(
'admin/agent_orchestration.html',
active_page='obs_agent_orchestration', hours=hours,
agent_matrix=[], mcp_matrix=[], recommendations=[], overall={},
error=f'查詢失敗: {type(e).__name__}: {str(e)[:200]}',
)
finally:
session.close()
# ─────────────────────────────────────────────────────────────────────────────
# /observability/ai_calls — Phase 27 主入口
# ─────────────────────────────────────────────────────────────────────────────

View File

@@ -0,0 +1,257 @@
{% extends "ewoooc_base.html" %}
{% block title %}Agent 編排矩陣{% endblock %}
{% block ewooo_content %}
<div class="container-fluid mt-3">
<h2 class="mb-3"><i class="fas fa-network-wired me-2"></i>Agent 編排矩陣
<small class="text-muted">{{ hours }}h 內 4 Agent × Ollama × Gemini × MCP × RAG 協作全景</small>
</h2>
{% if error %}
<div class="alert alert-warning"><strong><i class="fas fa-exclamation-triangle me-1"></i></strong> {{ error }}</div>
{% endif %}
<!-- 時間範圍 -->
<form method="get" class="row g-2 mb-3">
<div class="col-auto">
<select name="hours" class="form-select form-select-sm" onchange="this.form.submit()">
{% for h in [1, 6, 24, 72, 168] %}
<option value="{{ h }}" {% if hours == h %}selected{% endif %}>
{% if h < 24 %}過去 {{ h }} 小時{% else %}過去 {{ (h//24) }} {% endif %}
</option>
{% endfor %}
</select>
</div>
</form>
<!-- 整體 KPI -->
{% if overall %}
<div class="row g-3 mb-3">
<div class="col-lg-3 col-md-6">
<div class="card h-100">
<div class="card-body">
<small class="text-muted d-block"><i class="fas fa-network-wired me-1"></i>總呼叫</small>
<h3 class="mb-0">{{ "{:,}".format(overall.total_calls) }}</h3>
<small class="text-muted">Token{{ "{:,}".format(overall.total_tokens) }}</small>
</div>
</div>
</div>
<div class="col-lg-3 col-md-6">
<div class="card h-100" style="border-left: 4px solid #198754;">
<div class="card-body">
<small class="text-muted d-block"><i class="fas fa-server me-1"></i>本地 Ollama 比例</small>
<h3 class="mb-0 text-success">{{ "%.0f"|format(overall.local_pct) }}<small>%</small></h3>
<small class="text-muted">{{ "{:,}".format(overall.local_calls) }} 呼叫</small>
</div>
</div>
</div>
<div class="col-lg-3 col-md-6">
<div class="card h-100" style="border-left: 4px solid #ffc107;">
<div class="card-body">
<small class="text-muted d-block"><i class="fas fa-coins me-1"></i>付費 LLM 成本</small>
<h3 class="mb-0">${{ "%.2f"|format(overall.total_cost) }}</h3>
<small class="text-muted">{{ "{:,}".format(overall.paid_calls) }} 付費呼叫({{ "%.0f"|format(overall.paid_pct) }}%</small>
</div>
</div>
</div>
<div class="col-lg-3 col-md-6">
<div class="card h-100" style="border-left: 4px solid #6f42c1;">
<div class="card-body">
<small class="text-muted d-block"><i class="fas fa-magnifying-glass-chart me-1"></i>RAG 命中率</small>
<h3 class="mb-0" style="color: #6f42c1;">{{ "%.0f"|format(overall.rag_rate) }}<small>%</small></h3>
<small class="text-muted">{{ "{:,}".format(overall.rag_hits) }} hits</small>
</div>
</div>
</div>
</div>
{% endif %}
<!-- 4 Agent 矩陣 -->
<div class="card mb-3">
<div class="card-header">
<strong><i class="fas fa-th me-2"></i>4 Agent × LLM × MCP × RAG 矩陣</strong>
<small class="text-muted">資料來源ai_calls × mcp_calls × rag_query_logcaller 自動分組)</small>
</div>
<div class="card-body p-0">
<table class="table mb-0" style="font-size: 0.92em;">
<thead class="table-light">
<tr>
<th>Agent</th>
<th class="text-end">呼叫</th>
<th class="text-end">成本</th>
<th class="text-end">本地 Ollama</th>
<th class="text-end">付費 LLM</th>
<th class="text-end">MCP 編排</th>
<th class="text-end">RAG 命中</th>
<th class="text-end">錯誤率</th>
<th class="text-end">耗時</th>
</tr>
</thead>
<tbody>
{% for ag in agent_matrix %}
<tr>
<td>
<strong>{{ ag.label }}</strong>
<small class="d-block text-muted">{{ ag.desc }}</small>
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong>{{ "{:,}".format(ag.calls) }}</strong>
<small class="d-block text-muted">{{ "{:,}".format(ag.tokens) }} tk</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
${{ "%.2f"|format(ag.cost) }}
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong class="text-success">{{ "%.0f"|format(ag.ollama_pct) }}%</strong>
<small class="d-block text-muted">
GCP-A {{ ag.ollama_gcp_a }} ·
GCP-B {{ ag.ollama_gcp_b }} ·
111 {{ ag.ollama_111 }}
</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong class="{% if ag.paid_pct > 50 %}text-danger{% elif ag.paid_pct > 20 %}text-warning{% endif %}">
{{ "%.0f"|format(ag.paid_pct) }}%
</strong>
<small class="d-block text-muted">
Gemini {{ ag.gemini }}{% if ag.other_paid %} · 其他 {{ ag.other_paid }}{% endif %}
</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong class="{% if ag.mcp_rate >= 30 %}text-info{% elif ag.mcp_rate >= 10 %}text-warning{% else %}text-muted{% endif %}">
{{ "%.1f"|format(ag.mcp_rate) }}%
</strong>
<small class="d-block text-muted">{{ ag.mcp_calls }} request_id</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong style="color: #6f42c1;">{{ "%.1f"|format(ag.rag_rate) }}%</strong>
<small class="d-block text-muted">{{ ag.rag_hits }} hits</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}
<strong class="{% if ag.error_rate >= 15 %}text-danger{% elif ag.error_rate >= 5 %}text-warning{% else %}text-success{% endif %}">
{{ "%.1f"|format(ag.error_rate) }}%
</strong>
<small class="d-block text-muted">{{ ag.errors }} 次</small>
{% else %}
<small class="text-muted"></small>
{% endif %}
</td>
<td class="text-end">
{% if ag.calls > 0 %}{{ ag.avg_ms }} ms{% else %}<small class="text-muted"></small>{% endif %}
</td>
</tr>
{% endfor %}
</tbody>
</table>
</div>
<div class="card-footer small text-muted">
<i class="fas fa-info-circle me-1"></i>
<strong>本地 Ollama</strong> = GCP-A + GCP-B + 111 三主機級聯(免費);
<strong>付費 LLM</strong> = Gemini / Claude / NIM / OpenRouter
<strong>MCP 編排率</strong> = caller 透過 ai_calls.request_id 串接到 mcp_calls 的比例;
<strong>RAG 命中</strong> = ai_calls.rag_hit=true 的 caller-level 比例。
</div>
</div>
<!-- 自動編排建議 -->
{% if recommendations %}
<div class="card mb-3" style="border-left: 4px solid #6f42c1;">
<div class="card-header bg-light">
<strong><i class="fas fa-lightbulb me-2"></i>編排策略自動建議</strong>
<small class="text-muted">— rule-based 規則引擎5 條判斷</small>
</div>
<div class="card-body p-2">
<ul class="list-unstyled mb-0">
{% for r in recommendations %}
<li class="mb-2 p-2" style="background: #fafafa; border-radius: 6px;
{% if r.severity == 'high' %}border-left: 3px solid #dc3545;
{% elif r.severity == 'med' %}border-left: 3px solid #ffc107;
{% else %}border-left: 3px solid #0dcaf0;{% endif %}">
<span class="badge {% if r.severity == 'high' %}bg-danger{% elif r.severity == 'med' %}bg-warning text-dark{% else %}bg-info text-dark{% endif %} me-1">{{ r.severity|upper }}</span>
<strong>{{ r.agent }}</strong>
<div class="small mt-1">
<i class="fas fa-search me-1"></i><strong>發現:</strong>{{ r.finding }}
</div>
<div class="small text-muted">
<i class="fas fa-arrow-right me-1"></i><strong>建議:</strong>{{ r.suggestion }}
</div>
</li>
{% endfor %}
</ul>
</div>
</div>
{% endif %}
<!-- MCP server × caller 細節 -->
{% if mcp_matrix %}
<div class="card mb-3">
<div class="card-header">
<strong><i class="fas fa-bolt me-2"></i>MCP server × caller 工作量明細</strong>
<small class="text-muted">資料來源mcp_calls過去 {{ hours }}h前 30 筆)</small>
</div>
<div class="card-body p-0">
<table class="table table-sm mb-0">
<thead class="table-light">
<tr>
<th>MCP Server</th>
<th>呼叫端 (caller)</th>
<th class="text-end">tool 呼叫</th>
<th class="text-end">cache 命中</th>
<th class="text-end">cache 率</th>
<th class="text-end">成本</th>
</tr>
</thead>
<tbody>
{% for m in mcp_matrix %}
<tr>
<td><code>{{ m.server }}</code></td>
<td><code>{{ m.caller }}</code></td>
<td class="text-end">{{ "{:,}".format(m.calls) }}</td>
<td class="text-end">{{ m.cache_hits }}</td>
<td class="text-end">
<span class="{% if m.cache_rate >= 50 %}text-success{% elif m.cache_rate >= 20 %}text-warning{% endif %}">
{{ "%.0f"|format(m.cache_rate) }}%
</span>
</td>
<td class="text-end">${{ "%.4f"|format(m.cost) }}</td>
</tr>
{% endfor %}
</tbody>
</table>
</div>
</div>
{% endif %}
<p class="text-muted mt-3"><small>
<i class="fas fa-robot me-1"></i>Operation Ollama-First v5.0 / Phase 46 — Agent 編排矩陣
8 表跨 JOINai_calls × mcp_calls × rag_query_log × ai_insights × learning_episodes
× incidents × heal_logs × host_health_probes
</small></p>
</div>
{% endblock %}

View File

@@ -219,11 +219,17 @@
</div>
{% endif %}
<!-- 6 大入口 -->
<!-- 7 大入口 -->
<div class="card">
<div class="card-header"><strong><i class="fas fa-th me-1"></i>6 大子頁入口</strong></div>
<div class="card-header"><strong><i class="fas fa-th me-1"></i>7 大子頁入口</strong></div>
<div class="card-body">
<div class="row g-2">
<div class="col-lg-4 col-md-6">
<a href="/observability/agent_orchestration" class="btn btn-outline-info w-100 text-start" style="border-width: 2px;">
<i class="fas fa-network-wired me-2"></i><strong>Agent 編排矩陣</strong>
<small class="d-block text-muted ms-4">4 Agent × Ollama × Gemini × MCP × RAG 全景 + 自動建議</small>
</a>
</div>
<div class="col-lg-4 col-md-6">
<a href="/observability/host_health" class="btn btn-outline-primary w-100 text-start">
<i class="fas fa-heartbeat me-2"></i>主機健康監控

View File

@@ -81,6 +81,11 @@
<span class="momo-nav-label">觀測台總覽</span>
<span class="momo-nav-code momo-mono">07</span>
</a>
<a class="momo-nav-link {% if _active_page == 'obs_agent_orchestration' %}is-active{% endif %}" href="/observability/agent_orchestration">
<span class="momo-nav-icon"><i class="fas fa-network-wired"></i></span>
<span class="momo-nav-label">Agent 編排矩陣</span>
<span class="momo-nav-code momo-mono">07b</span>
</a>
<a class="momo-nav-link {% if _active_page == 'obs_host_health' %}is-active{% endif %}" href="/observability/host_health">
<span class="momo-nav-icon"><i class="fas fa-heartbeat"></i></span>
<span class="momo-nav-label">主機健康</span>