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,
     ):