feat: 添加好友功能并集成 LiteLLM 代理服务

- 新增好友搜索、添加、好友列表功能
- 集成 LiteLLM 代理服务及多模型定价配置
- 更新 iOS CocoaPods 配置
- 更新 .gitignore 和环境变量配置

backend/tests/unit/core/agent/test_init_data.py

@@ -31,3 +31,26 @@ def test_seed_data_does_not_keep_legacy_deepseek_alias() -> None:
     catalog = load_llm_catalog()
 
     assert all(entry["model_code"] != "deepseek-v3.2" for entry in catalog["llms"])
+
+
+def test_llm_catalog_contains_litellm_routing_and_pricing_fields() -> None:
+    catalog = load_llm_catalog()
+
+    for entry in catalog["llms"]:
+        assert set(entry.keys()) == {
+            "model_code",
+            "factory_name",
+            "litellm_model",
+            "pricing_tiers",
+        }
+        assert isinstance(entry["litellm_model"], str)
+        assert "/" in entry["litellm_model"]
+        pricing_tiers = entry["pricing_tiers"]
+        assert isinstance(pricing_tiers, list)
+        assert len(pricing_tiers) > 0
+        for tier in pricing_tiers:
+            assert isinstance(tier, dict)
+            assert int(tier["max_prompt_tokens"]) > 0
+            assert float(tier["input_cost_per_token"]) >= 0
+            assert float(tier["output_cost_per_token"]) >= 0
+            assert float(tier["cache_hit_cost_per_token"]) >= 0

backend/tests/unit/services/test_litellm_service.py

@@ -0,0 +1,55 @@
+from __future__ import annotations
+
+import pytest
+
+from services.litellm.service import LiteLLMService
+
+
+def test_calculate_cost_uses_first_qwen_tier() -> None:
+    service = LiteLLMService()
+
+    cost = service.calculate_cost(
+        model="dashscope/qwen3.5-flash",
+        prompt_tokens=100_000,
+        completion_tokens=1_000,
+        cached_prompt_tokens=10_000,
+    )
+
+    assert cost == pytest.approx(0.0202)
+
+
+def test_calculate_cost_uses_second_qwen_tier() -> None:
+    service = LiteLLMService()
+
+    cost = service.calculate_cost(
+        model="dashscope/qwen3.5-flash",
+        prompt_tokens=200_000,
+        completion_tokens=5_000,
+        cached_prompt_tokens=20_000,
+    )
+
+    assert cost == pytest.approx(0.1856)
+
+
+def test_run_completion_extracts_usage_and_cost() -> None:
+    service = LiteLLMService()
+
+    result = service.run_completion_with_cost(
+        model="dashscope/qwen3.5-flash",
+        messages=[{"role": "user", "content": "hello"}],
+        completion_fn=lambda **_: {
+            "model": "dashscope/qwen3.5-flash",
+            "usage": {
+                "prompt_tokens": 2000,
+                "completion_tokens": 100,
+                "total_tokens": 2100,
+                "prompt_tokens_details": {"cached_tokens": 500},
+            },
+            "choices": [{"message": {"content": "ok"}}],
+        },
+    )
+
+    assert result.usage.prompt_tokens == 2000
+    assert result.usage.completion_tokens == 100
+    assert result.usage.total_tokens == 2100
+    assert result.usage.cost == pytest.approx(0.00051)