更新 ZenMux Claude Sonnet 5.5

servers/hindsight/hindsight/.env.example

@@ -56,7 +56,7 @@ HINDSIGHT_API_CONSOLIDATION_LLM_REASONING_EFFORT=low
 # Reflect: highest-quality synthesis and belief evolution.
 HINDSIGHT_API_REFLECT_LLM_PROVIDER=openai
 HINDSIGHT_API_REFLECT_LLM_BASE_URL=https://zenmux.ai/api/v1
-HINDSIGHT_API_REFLECT_LLM_MODEL=anthropic/claude-sonnet-5
+HINDSIGHT_API_REFLECT_LLM_MODEL=anthropic/claude-sonnet-5.5
 HINDSIGHT_API_REFLECT_LLM_MAX_CONCURRENT=1
 HINDSIGHT_API_REFLECT_LLM_TIMEOUT=600
 

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

@@ -56,9 +56,9 @@ class Config:
     # and deleted terms such as AUTOIMMUNE/ADCS/CD), while being 2x faster and
     # 2.9x cheaper. Hence flash-lite is the default cleaner.
     clean_model: str = _env("ASR_CLEAN_MODEL", "google/gemini-3.5-flash-lite")
-    # Drafting: one call, needs judgement and structure. sonnet-5 replaces the
+    # Drafting: one call, needs judgement and structure. sonnet-5.5 replaces the
     # legacy headless opus-4-8.
-    draft_model: str = _env("ASR_DRAFT_MODEL", "anthropic/claude-sonnet-5")
+    draft_model: str = _env("ASR_DRAFT_MODEL", "anthropic/claude-sonnet-5.5")
     keyword_model: str = _env("ASR_KEYWORD_MODEL", "google/gemini-3.5-flash-lite")
 
     endpoint: str = _env("ASR_ENDPOINT", "https://zenmux.ai/api/v1/chat/completions")

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] = []
 

servers/tools-pve/asr-pipeline/compose.yaml

@@ -1,5 +1,6 @@
 x-asr-environment: &asr-environment
   ZENMUX_API_KEY: ${ZENMUX_API_KEY:-}
+  ASR_DRAFT_MODEL: ${ASR_DRAFT_MODEL:-anthropic/claude-sonnet-5.5}
   ASR_AGENT_TOKEN: ${ASR_AGENT_TOKEN:-}
   ASR_PUBLIC_URL: ${ASR_PUBLIC_URL:-http://192.168.50.49:8788}
   ASR_DIARIZE_URL: ${ASR_DIARIZE_URL:-http://192.168.50.100:10099/asr}