feat(config): align LLM timeout/retry SLA with FastGPT client (60s/3)

Replaces the unequal SLA (LLM 30s/2 retries vs FastGPT client 60s/3)
that made the LangGraph backend look less stable under gray release.

- core/fastgpt_client: FASTGPT_TIMEOUT_SECONDS / FASTGPT_MAX_RETRIES
  module constants (were inline literals in lifespan)
- agent/llm: OpenAILLMService defaults 60.0s / 3 retries
- core/config: named-profile fallback defaults 60/3 (prefixed and
  JSON-dict forms)
- contract test test/backends/test_sla_alignment.py pins both sides to
  the same constants so the SLA cannot drift apart again
- retry backoff intentionally differs (FastGPT fixed 1s vs LLM
  exponential) and is documented; aligned parameters are per-call
  timeout and max retry count

Verified: 215 unit tests (3 new SLA contract tests)

test/backends/test_sla_alignment.py

@@ -0,0 +1,42 @@
+"""后端超时/重试 SLA 对齐契约测试。
+
+背景（可替代性清单）：FastGPT 客户端为 60s/3 次，LangGraph LLM 侧
+曾是 30s/2 次，客户端感知到的超时行为不等价。本测试把两端常量
+钉在一起，防止再次漂移。
+
+注：退避策略有意不同——FastGPT 固定 1s，LLM 指数退避（限流场景
+更友好）；对齐的是"单次调用总超时"与"最大重试次数"两个 SLA 参数。
+"""
+
+import inspect
+
+from src.agent.llm import OpenAILLMService
+from src.core.fastgpt_client import FASTGPT_MAX_RETRIES, FASTGPT_TIMEOUT_SECONDS
+
+
+def test_llm_default_timeout_matches_fastgpt_client():
+    signature = inspect.signature(OpenAILLMService.__init__)
+    default_timeout = signature.parameters["timeout_seconds"].default
+    assert default_timeout == FASTGPT_TIMEOUT_SECONDS == 60.0
+
+
+def test_llm_default_max_retries_matches_fastgpt_client():
+    signature = inspect.signature(OpenAILLMService.__init__)
+    default_retries = signature.parameters["max_retries"].default
+    assert default_retries == FASTGPT_MAX_RETRIES == 3
+
+
+def test_named_profile_defaults_match_fastgpt_client(monkeypatch):
+    """未显式配置 _TIMEOUT_SECONDS/_MAX_RETRIES 的 profile 取 SLA 默认值。"""
+    monkeypatch.setenv("LLM_PROVIDERS", "probe")
+    monkeypatch.setenv("LLM_PROBE_BASE_URL", "http://127.0.0.1:1/v1")
+    monkeypatch.setenv("LLM_PROBE_API_KEY", "probe-key")
+    monkeypatch.setenv("LLM_PROBE_MODEL", "probe-model")
+
+    from src.core.config import Config
+
+    # LLM_PROVIDERS 是 import 时固化的类属性，需直接替换
+    monkeypatch.setattr(Config, "LLM_PROVIDERS", "probe")
+    profile = Config.llm_profile("probe")
+    assert profile["timeout_seconds"] == FASTGPT_TIMEOUT_SECONDS
+    assert profile["max_retries"] == FASTGPT_MAX_RETRIES