chore: update model references to Claude 4.6 and GPT-5.2

- Claude Opus 4.5 → Opus 4.6, Claude Sonnet 4.5 → Sonnet 4.6 (Haiku stays 4.5)
- Update claude-sonnet-4-5 model IDs to claude-sonnet-4-6 in code examples
- Update SWE-bench stat from 80.9% to 80.8% for Opus 4.6
- Update GPT refs: GPT-5 → GPT-5.2, GPT-4o → gpt-5.2, GPT-4o-mini → GPT-5-mini
- Fix GPT-5.2-mini → GPT-5-mini (correct model name per OpenAI)
- Bump marketplace to v1.5.2 and affected plugin versions

plugins/llm-application-dev/skills/langchain-architecture/SKILL.md

@@ -115,8 +115,8 @@ from langchain_core.tools import tool
 import ast
 import operator
 
-# Initialize LLM (Claude Sonnet 4.5 recommended)
-llm = ChatAnthropic(model="claude-sonnet-4-5", temperature=0)
+# Initialize LLM (Claude Sonnet 4.6 recommended)
+llm = ChatAnthropic(model="claude-sonnet-4-6", temperature=0)
 
 # Define tools with Pydantic schemas
 @tool
@@ -201,7 +201,7 @@ class RAGState(TypedDict):
     answer: str
 
 # Initialize components
-llm = ChatAnthropic(model="claude-sonnet-4-5")
+llm = ChatAnthropic(model="claude-sonnet-4-6")
 embeddings = VoyageAIEmbeddings(model="voyage-3-large")
 vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings)
 retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
@@ -489,7 +489,7 @@ os.environ["LANGCHAIN_API_KEY"] = "your-api-key"
 os.environ["LANGCHAIN_PROJECT"] = "my-project"
 
 # All LangChain/LangGraph operations are automatically traced
-llm = ChatAnthropic(model="claude-sonnet-4-5")
+llm = ChatAnthropic(model="claude-sonnet-4-6")
 ```
 
 ### Custom Callback Handler
@@ -530,7 +530,7 @@ result = await agent.ainvoke(
 ```python
 from langchain_anthropic import ChatAnthropic
 
-llm = ChatAnthropic(model="claude-sonnet-4-5", streaming=True)
+llm = ChatAnthropic(model="claude-sonnet-4-6", streaming=True)
 
 # Stream tokens
 async for chunk in llm.astream("Tell me a story"):

plugins/llm-application-dev/skills/llm-evaluation/SKILL.md

@@ -283,7 +283,7 @@ Provide ratings in JSON format:
 }}"""
 
     message = client.messages.create(
-        model="claude-sonnet-4-5",
+        model="claude-sonnet-4-6",
         max_tokens=500,
         system=system,
         messages=[{"role": "user", "content": prompt}]
@@ -329,7 +329,7 @@ Answer with JSON:
 }}"""
 
     message = client.messages.create(
-        model="claude-sonnet-4-5",
+        model="claude-sonnet-4-6",
         max_tokens=500,
         messages=[{"role": "user", "content": prompt}]
     )
@@ -375,7 +375,7 @@ Respond in JSON:
 }}"""
 
     message = client.messages.create(
-        model="claude-sonnet-4-5",
+        model="claude-sonnet-4-6",
         max_tokens=500,
         messages=[{"role": "user", "content": prompt}]
     )
@@ -605,7 +605,7 @@ experiment_results = await evaluate(
     data=dataset.name,
     evaluators=evaluators,
     experiment_prefix="v1.0.0",
-    metadata={"model": "claude-sonnet-4-5", "version": "1.0.0"}
+    metadata={"model": "claude-sonnet-4-6", "version": "1.0.0"}
 )
 
 print(f"Mean score: {experiment_results.aggregate_metrics['qa']['mean']}")

plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md

@@ -81,7 +81,7 @@ class SQLQuery(BaseModel):
     tables_used: list[str] = Field(description="List of tables referenced")
 
 # Initialize model with structured output
-llm = ChatAnthropic(model="claude-sonnet-4-5")
+llm = ChatAnthropic(model="claude-sonnet-4-6")
 structured_llm = llm.with_structured_output(SQLQuery)
 
 # Create prompt template
@@ -124,7 +124,7 @@ async def analyze_sentiment(text: str) -> SentimentAnalysis:
     client = Anthropic()
 
     message = client.messages.create(
-        model="claude-sonnet-4-5",
+        model="claude-sonnet-4-6",
         max_tokens=500,
         messages=[{
             "role": "user",
@@ -427,7 +427,7 @@ client = Anthropic()
 
 # Use prompt caching for repeated system prompts
 response = client.messages.create(
-    model="claude-sonnet-4-5",
+    model="claude-sonnet-4-6",
     max_tokens=1000,
     system=[
         {

plugins/llm-application-dev/skills/prompt-engineering-patterns/references/chain-of-thought.md

@@ -68,7 +68,7 @@ def self_consistency_cot(query, n=5, temperature=0.7):
     responses = []
     for _ in range(n):
         response = openai.ChatCompletion.create(
-            model="gpt-5",
+            model="gpt-5.2",
             messages=[{"role": "user", "content": prompt}],
             temperature=temperature
         )

plugins/llm-application-dev/skills/rag-implementation/SKILL.md

@@ -85,7 +85,7 @@ class RAGState(TypedDict):
     answer: str
 
 # Initialize components
-llm = ChatAnthropic(model="claude-sonnet-4-5")
+llm = ChatAnthropic(model="claude-sonnet-4-6")
 embeddings = VoyageAIEmbeddings(model="voyage-3-large")
 vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings)
 retriever = vectorstore.as_retriever(search_kwargs={"k": 4})