LLM-Bridge 2.0.7__tar.gz → 2.0.8__tar.gz

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: LLM-Bridge
-Version: 2.0.7
+Version: 2.0.8
 Summary: A library that wraps multiple LLM providers into a consistent API while using each provider's native SDK internally, supporting multimodal I/O, file processing, and stream output.
 Author-email: windsnow1025 <windsnow1025@gmail.com>
 License-Expression: MIT

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/llm_bridge/client/implementations/claude/non_stream_claude_client.py

@@ -18,7 +18,6 @@ class NonStreamClaudeClient(ClaudeClient):
             message = await self.client.beta.messages.create(
                 model=self.model,
                 max_tokens=self.max_tokens,
-                temperature=self.temperature,
                 system=self.system,
                 messages=serialize(self.messages),
                 betas=self.betas,

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/llm_bridge/client/implementations/claude/stream_claude_client.py

@@ -20,7 +20,6 @@ class StreamClaudeClient(ClaudeClient):
                 async with self.client.beta.messages.stream(
                     model=self.model,
                     max_tokens=self.max_tokens,
-                    temperature=self.temperature,
                     system=self.system,
                     messages=serialize(self.messages),
                     betas=self.betas,

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/llm_bridge/client/model_client/claude_client.py

@@ -16,7 +16,6 @@ class ClaudeClient(ChatClient):
             self,
             model: str,
             messages: list[ClaudeMessage],
-            temperature: float,
             system: str,
             client: anthropic.AsyncAnthropic,
             max_tokens: int,
@@ -28,7 +27,6 @@ class ClaudeClient(ChatClient):
     ):
         self.model = model
         self.messages = messages
-        self.temperature = temperature
         self.system = system
         self.client = client
         self.max_tokens = max_tokens

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/llm_bridge/logic/chat_generate/model_client_factory/claude_client_factory.py

@@ -46,9 +46,7 @@ async def create_claude_client(
         messages=claude_messages,
     )
 
-    context_window = 200_000
-    if model in ["claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6", "claude-sonnet-4-6", "claude-sonnet-4-5"]:
-        context_window = 1_000_000
+    context_window = 1_000_000
     max_output = 64_000
     max_tokens = min(
         max_output,
@@ -59,14 +57,7 @@ async def create_claude_client(
 
     thinking: BetaThinkingConfigParam | Omit = omit
     if thought:
-        if model in ["claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6", "claude-sonnet-4-6"]:
-            thinking = BetaThinkingConfigAdaptiveParam(type="adaptive", display="summarized")
-        else:
-            thinking = BetaThinkingConfigEnabledParam(
-                type="enabled",
-                budget_tokens=max(1024, max_tokens // 2),  # Minimum budget tokens: 1024
-            )
-        temperature = 1
+        thinking = BetaThinkingConfigAdaptiveParam(type="adaptive", display="summarized")
 
     betas: list[AnthropicBetaParam] = [
         "context-1m-2025-08-07",
@@ -107,7 +98,6 @@ async def create_claude_client(
         return StreamClaudeClient(
             model=model,
             messages=claude_messages,
-            temperature=temperature,
             system=system,
             client=client,
             max_tokens=max_tokens,
@@ -121,7 +111,6 @@ async def create_claude_client(
         return NonStreamClaudeClient(
             model=model,
             messages=claude_messages,
-            temperature=temperature,
             system=system,
             client=client,
             max_tokens=max_tokens,

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/llm_bridge/resources/model_prices.json

@@ -47,6 +47,12 @@
     "input": 2,
     "output": 8
   },
+  {
+    "apiType": "Claude",
+    "model": "claude-fable-5",
+    "input": 10,
+    "output": 50
+  },
   {
     "apiType": "Claude",
     "model": "claude-opus-4-8",
@@ -59,7 +65,7 @@
     "input": 5,
     "output": 25
   },
-    {
+  {
     "apiType": "Claude",
     "model": "claude-opus-4-6",
     "input": 5,
@@ -71,24 +77,6 @@
     "input": 3,
     "output": 15
   },
-  {
-    "apiType": "Claude",
-    "model": "claude-opus-4-5",
-    "input": 5,
-    "output": 25
-  },
-  {
-    "apiType": "Claude",
-    "model": "claude-sonnet-4-5",
-    "input": 6,
-    "output": 22.5
-  },
-  {
-    "apiType": "Claude",
-    "model": "claude-haiku-4-5",
-    "input": 1,
-    "output": 5
-  },
   {
     "apiType": "Vertex AI",
     "model": "gemini-3.1-pro-preview",

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "LLM-Bridge"
-version = "2.0.7"
+version = "2.0.8"
 dependencies = [
     "fastapi",
     "httpx",

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/usage/single/config.py

@@ -169,7 +169,7 @@ messages = [
 # model = "gemini-3-pro-image-preview"
 # model = "gemini-3.1-flash-image-preview"
 # model = "gemini-3-flash-preview"
-model = "claude-opus-4-8"
+model = "claude-fable-5"
 # model = "grok-4.3"
 
 # api_type = "Vertex AI"

{llm_bridge-2.0.7 → llm_bridge-2.0.8}/uv.lock

@@ -748,7 +748,7 @@ wheels = [
 
 [[package]]
 name = "llm-bridge"
-version = "2.0.7"
+version = "2.0.8"
 source = { editable = "." }
 dependencies = [
     { name = "anthropic" },