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)

src/agent/llm.py

@@ -100,8 +100,8 @@ class OpenAILLMService:
         model: str,
         api_key: str,
         base_url: str = "",
-        timeout_seconds: float = 30.0,
-        max_retries: int = 2,
+        timeout_seconds: float = 60.0,
+        max_retries: int = 3,
         temperature: float | None = None,
         extra_body: dict | None = None,
     ):

src/core/config.py

@@ -91,8 +91,8 @@ class Config:
                 "base_url": base_url,
                 "api_key": api_key,
                 "model": model,
-                "timeout_seconds": float(spec.get("timeout_seconds", 30)),
-                "max_retries": int(spec.get("max_retries", 2)),
+                "timeout_seconds": float(spec.get("timeout_seconds", 60)),
+                "max_retries": int(spec.get("max_retries", 3)),
                 "temperature": float(temperature) if temperature is not None else None,
                 "extra_body": str(extra_body),
             }
@@ -113,8 +113,8 @@ class Config:
                 "base_url": base_url,
                 "api_key": api_key,
                 "model": model,
-                "timeout_seconds": float(os.getenv(prefix + "TIMEOUT_SECONDS", "30")),
-                "max_retries": int(os.getenv(prefix + "MAX_RETRIES", "2")),
+                "timeout_seconds": float(os.getenv(prefix + "TIMEOUT_SECONDS", "60")),
+                "max_retries": int(os.getenv(prefix + "MAX_RETRIES", "3")),
                 "temperature": float(temperature) if temperature else None,
                 "extra_body": os.getenv(prefix + "EXTRA_BODY", ""),
             }

src/core/fastgpt_client.py

@@ -16,6 +16,14 @@ _chat_backend: ChatBackend | None = None
 _langgraph_graph = None
 _app_service: AccidentAppService | None = None
 
+# 后端超时/重试 SLA（两后端对齐；契约测试防止再漂移）。
+# FastGPT 侧：客户端每次请求总超时 + 重试次数；
+# LangGraph 侧：LLM 每次调用总超时 + 重试次数（退避为指数式，
+# 与 FastGPT 固定 1s 不同——总尝试次数与单次超时可比，见
+# test/backends/test_sla_alignment.py）。
+FASTGPT_TIMEOUT_SECONDS = 60.0
+FASTGPT_MAX_RETRIES = 3
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
@@ -39,8 +47,8 @@ async def lifespan(app: FastAPI):
         _fastgpt_client = AsyncChatClient(
             api_key=Config.FASTGPT_API_KEY,
             base_url=Config.FASTGPT_BASE_URL,
-            timeout=60.0,
-            max_retries=3,
+            timeout=FASTGPT_TIMEOUT_SECONDS,
+            max_retries=FASTGPT_MAX_RETRIES,
             retry_delay=1.0,
             enable_logging=Config.DEBUG,
         )