Add API retries and concurrent batch processing

2026-08-06 23:21:46 +08:00
parent 044bd03f0e
commit f1a090e8c4
8 changed files with 183 additions and 20 deletions
@@ -47,7 +47,7 @@ class Settings:
    api_path: str = "/v1/chat/completions"
    model: str = "glm-5.2"
    timeout_seconds: float = 300.0
-    max_retries: int = 3
+    max_retries: int = 5
    max_tokens: int = 8192
    temperature: float = 0.0
    reasoning_effort: str = "high"
@@ -85,7 +85,7 @@ class Settings:
            api_path=os.getenv("GLM_API_PATH", "/v1/chat/completions"),
            model=os.getenv("GLM_MODEL", "glm-5.2"),
            timeout_seconds=_get_float("GLM_TIMEOUT_SECONDS", 300.0, 1.0),
-            max_retries=_get_int("GLM_MAX_RETRIES", 3, 1),
+            max_retries=_get_int("GLM_MAX_RETRIES", 5, 0),
            max_tokens=_get_int("GLM_MAX_TOKENS", 8192, 1),
            temperature=_get_float("GLM_TEMPERATURE", 0.0, 0.0),
            reasoning_effort=reasoning_effort,