更新 ZenMux Claude Sonnet 5.5

servers/tools-pve/asr-pipeline/asrpipe/llm.py

@@ -9,7 +9,7 @@ Behaviours encoded from measurement rather than guesswork:
   * HTTP 402 "Payment Required" is transient on ZenMux — credit seems reserved
     against max_tokens, so a burst of large-budget calls can trip it and then
     succeed moments later; it gets a much longer backoff than a rate limit
-  * `temperature` is rejected outright by claude-sonnet-5 / opus-5 but accepted by
+  * `temperature` is rejected outright by claude-sonnet-5.5 / opus-5 but accepted by
     haiku-4.5, sonnet-4.6, gemini and qwen, so it cannot be inferred from the
     vendor prefix; the client self-heals on the 400 and remembers
   * an empty completion (reasoning models burning the whole budget on hidden
@@ -34,13 +34,18 @@ PRICES = {
     "google/gemini-3.5-flash": (1.5, 9.0),
     "anthropic/claude-haiku-4.5": (1.0, 5.0),
     "anthropic/claude-sonnet-5": (2.0, 10.0),
+    "anthropic/claude-sonnet-5.5": (2.0, 10.0),
     "anthropic/claude-sonnet-4.6": (3.0, 15.0),
     "anthropic/claude-opus-5": (5.0, 25.0),
     "qwen/qwen3.7-plus": (0.1373076, 0.5492304),
 }
 
 _sem = threading.BoundedSemaphore(CFG.concurrency)
-_NO_TEMPERATURE: set[str] = {"anthropic/claude-sonnet-5", "anthropic/claude-opus-5"}
+_NO_TEMPERATURE: set[str] = {
+    "anthropic/claude-sonnet-5",
+    "anthropic/claude-sonnet-5.5",
+    "anthropic/claude-opus-5",
+}
 _lock = threading.Lock()
 _key: list[str] = []