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/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "llm-application-dev",
-  "description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.5 and GPT-5.2",
-  "version": "2.0.3",
+  "description": "LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.2",
+  "version": "2.0.4",
   "author": {
     "name": "Seth Hobson",
     "email": "seth@major7apps.com"

plugins/llm-application-dev/README.md

@@ -5,7 +5,7 @@ Build production-ready LLM applications, advanced RAG systems, and intelligent a
 ## Version 2.0.0 Highlights
 
 - **LangGraph Integration**: Updated from deprecated LangChain patterns to LangGraph StateGraph workflows
-- **Modern Model Support**: Claude Opus/Sonnet/Haiku 4.5 and GPT-5.2/GPT-5.2-mini
+- **Modern Model Support**: Claude Opus 4.6/Sonnet 4.6/Haiku 4.5 and GPT-5.2/GPT-5-mini
 - **Voyage AI Embeddings**: Recommended embedding models for Claude applications
 - **Structured Outputs**: Pydantic-based structured output patterns
 
@@ -71,7 +71,7 @@ Build production-ready LLM applications, advanced RAG systems, and intelligent a
 ### 2.0.0 (January 2026)
 
 - **Breaking**: Migrated from LangChain 0.x to LangChain 1.x/LangGraph
-- **Breaking**: Updated model references to Claude 4.5 and GPT-5.2
+- **Breaking**: Updated model references to Claude 4.6 and GPT-5.2
 - Added Voyage AI as primary embedding recommendation for Claude apps
 - Added LangGraph StateGraph patterns replacing deprecated `initialize_agent()`
 - Added structured outputs with Pydantic

plugins/llm-application-dev/agents/ai-engineer.md

@@ -14,8 +14,8 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
 
 ### LLM Integration & Model Management
 
-- OpenAI GPT-5.2/GPT-5.2-mini with function calling and structured outputs
-- Anthropic Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5 with tool use and computer use
+- OpenAI GPT-5.2/GPT-5-mini with function calling and structured outputs
+- Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5 with tool use and computer use
 - Open-source models: Llama 3.3, Mixtral 8x22B, Qwen 2.5, DeepSeek-V3
 - Local deployment with Ollama, vLLM, TGI (Text Generation Inference)
 - Model serving with TorchServe, MLflow, BentoML for production deployment
@@ -76,7 +76,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
 
 ### Multimodal AI Integration
 
-- Vision models: GPT-4V, Claude 4 Vision, LLaVA, CLIP for image understanding
+- Vision models: GPT-5.2, Claude 4 Vision, LLaVA, CLIP for image understanding
 - Audio processing: Whisper for speech-to-text, ElevenLabs for text-to-speech
 - Document AI: OCR, table extraction, layout understanding with models like LayoutLM
 - Video analysis and processing for multimedia applications
@@ -124,7 +124,7 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
 
 ## Knowledge Base
 
-- Latest LLM developments and model capabilities (GPT-5.2, Claude 4.5, Llama 3.3)
+- Latest LLM developments and model capabilities (GPT-5.2, Claude 4.6, Llama 3.3)
 - Modern vector database architectures and optimization techniques
 - Production AI system design patterns and best practices
 - AI safety and security considerations for enterprise deployments

plugins/llm-application-dev/agents/prompt-engineer.md

@@ -48,7 +48,7 @@ Expert prompt engineer specializing in advanced prompting methodologies and LLM
 
 ### Model-Specific Optimization
 
-#### OpenAI Models (GPT-5.2, GPT-5.2-mini)
+#### OpenAI Models (GPT-5.2, GPT-5-mini)
 
 - Function calling optimization and structured outputs
 - JSON mode utilization for reliable data extraction
@@ -58,7 +58,7 @@ Expert prompt engineer specializing in advanced prompting methodologies and LLM
 - Multi-turn conversation management
 - Image and multimodal prompt engineering
 
-#### Anthropic Claude (Claude Opus 4.5, Sonnet 4.5, Haiku 4.5)
+#### Anthropic Claude (Claude Opus 4.6, Sonnet 4.6, Haiku 4.5)
 
 - Constitutional AI alignment with Claude's training
 - Tool use optimization for complex workflows

plugins/llm-application-dev/commands/langchain-agent.md

@@ -37,7 +37,7 @@ class AgentState(TypedDict):
 
 ### Model & Embeddings
 
-- **Primary LLM**: Claude Sonnet 4.5 (`claude-sonnet-4-5`)
+- **Primary LLM**: Claude Sonnet 4.6 (`claude-sonnet-4-6`)
 - **Embeddings**: Voyage AI (`voyage-3-large`) - officially recommended by Anthropic for Claude
 - **Specialized**: `voyage-code-3` (code), `voyage-finance-2` (finance), `voyage-law-2` (legal)
 
@@ -158,7 +158,7 @@ from langsmith.evaluation import evaluate
 # Run evaluation suite
 eval_config = RunEvalConfig(
     evaluators=["qa", "context_qa", "cot_qa"],
-    eval_llm=ChatAnthropic(model="claude-sonnet-4-5")
+    eval_llm=ChatAnthropic(model="claude-sonnet-4-6")
 )
 
 results = await evaluate(
@@ -209,7 +209,7 @@ async def call_with_retry():
 
 ## Implementation Checklist
 
-- [ ] Initialize LLM with Claude Sonnet 4.5
+- [ ] Initialize LLM with Claude Sonnet 4.6
 - [ ] Setup Voyage AI embeddings (voyage-3-large)
 - [ ] Create tools with async support and error handling
 - [ ] Implement memory system (choose type based on use case)

plugins/llm-application-dev/commands/prompt-optimize.md

@@ -150,7 +150,7 @@ gpt5_optimized = """
 
 ````
 
-**Claude 4.5/4**
+**Claude 4.6/4.5**
 ```python
 claude_optimized = """
 <context>
@@ -607,7 +607,7 @@ testing_recommendations:
   metrics: ["accuracy", "satisfaction", "cost"]
 
 deployment_strategy:
-  model: "GPT-5.2 for quality, Claude 4.5 for safety"
+  model: "GPT-5.2 for quality, Claude 4.6 for safety"
   temperature: 0.7
   max_tokens: 2000
   monitoring: "Track success, latency, feedback"

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})