remove old models, add latest ones

packages/llm-info/README.md

@@ -8,4 +8,8 @@ Models and providers are stored in the `data` directory.
 
 ## Adding a New LLM Model
 
-If you want to add a new LLM model or provider, you can do so by editing the YAML files in the `data` directory (`models.yaml` or `providers.yaml`) and running `pnpm codegen`.
+If you want to add a new LLM model or provider, you can do so by editing the YAML files in the `data` directory (`models.yml` or `providers.yml`) and running `pnpm codegen`.
+
+> **Note:**
+> To make it easier for users to choose, keep the number of models to a minimum. Focus on including the latest or recommended models from each provider.
+> Review https://openrouter.ai/provider/{provider_name} for the latest models and capabilities.

packages/llm-info/data/models.yml

@@ -1,99 +1,72 @@
-# Information provided by https://hub.continue.dev/
+# Information provided by https://openrouter.ai/
+# Keep latest models at the top, deprecate old models
 
 # Anthropic
 
-- name: Claude 4.6 Opus
-  model: claude-opus-4-6
-  description: Latest Opus model with enhanced capabilities and performance improvements
-  providers: [anthropic]
-  roles: [chat, edit]
-  thinking: true
-
-- name: Claude 4.5 Opus
-  model: claude-opus-4-5
-  description: Modern Opus model with enhanced capabilities and performance improvements
+- name: Claude Sonnet 4.6
+  model: claude-sonnet-4-6
+  description: Most capable Sonnet-class model, with frontier performance across coding, agents, and professional work
   providers: [anthropic]
   roles: [chat, edit]
   thinking: true
 
-- name: Claude 4.5 Sonnet
-  model: claude-sonnet-4-5
-  description: Latest Sonnet model with enhanced capabilities and performance improvements
+- name: Claude Opus 4.6
+  model: claude-opus-4-6
+  description: Strongest model for coding and long-running professional tasks
   providers: [anthropic]
   roles: [chat, edit]
   thinking: true
 
-- name: Claude 4.1 Opus
-  model: claude-opus-4-1
-  description: Latest Opus model with enhanced capabilities and performance improvements
+- name: Claude Opus 4.5
+  model: claude-opus-4-5
+  description: Frontier reasoning model optimized for complex software engineering
   providers: [anthropic]
   roles: [chat, edit]
   thinking: true
 
-- name: Claude 4 Opus
-  model: claude-opus-4-0
-  description: Most capable model with superior performance on complex tasks and reasoning
+- name: Claude Sonnet 4.5
+  model: claude-sonnet-4-5
+  description: Advanced Sonnet model optimized for real-world agents and coding workflows
   providers: [anthropic]
   roles: [chat, edit]
   thinking: true
 
-- name: Claude 4 Sonnet
-  model: claude-sonnet-4-0
-  description: Next-generation Sonnet model with advanced reasoning and multimodal capabilities
+- name: Claude Haiku 4.5
+  model: claude-haiku-4-5
+  description: Most efficient model, delivering near-frontier intelligence at a fraction of the cost
   providers: [anthropic]
   roles: [chat, edit]
   thinking: true
 
-- name: Claude 3.7 Sonnet
-  model: claude-3-7-sonnet-latest
-  description: Enhanced Sonnet model with improved capabilities
-  providers: [anthropic]
-  roles: [chat, edit]
-  thinking: false
-
-- name: Claude 3.5 Sonnet
-  model: claude-3-5-sonnet-latest
-  description: Balanced model with strong performance across reasoning, math, and coding
-  providers: [anthropic]
-  roles: [chat, edit]
-  thinking: false
-
-- name: Claude 3.5 Haiku
-  model: claude-3-5-haiku-latest
-  description: Fast and efficient model with excellent performance for everyday tasks
-  providers: [anthropic]
-  roles: [chat, edit]
-  thinking: false
-
 # Google
 
-- name: Gemini 3.0 Pro
-  model: gemini-3-pro-preview
-  description: Most capable Gemini model with advanced reasoning and large context support
+- name: Gemini 3.1 Flash Lite Preview
+  model: gemini-3.1-flash-lite-preview
+  description: High-efficiency model optimized for high-volume use cases
   providers: [google]
   roles: [chat, edit]
-  thinking: true
+  thinking: false
 
-- name: Gemini 2.5 Pro
-  model: gemini-2.5-pro
-  description: Most capable Gemini model with advanced reasoning and large context support
+- name: Gemini 3.1 Pro Preview
+  model: gemini-3.1-pro-preview
+  description: Frontier reasoning model with enhanced software engineering and agentic reliability
   providers: [google]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
-- name: Gemini 2.5 Pro Experimental
-  model: gemini-2.5-pro-exp
-  description: Experimental version of Gemini 2.5 Pro with latest improvements
+- name: Gemini 3 Flash Preview
+  model: gemini-3-flash-preview
+  description: High-speed thinking model for agentic workflows, multi-turn chat, and coding assistance
   providers: [google]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
 - name: Gemini 2.5 Flash
   model: gemini-2.5-flash
-  description: Adaptive thinking, cost efficiency
+  description: State-of-the-art workhorse model with built-in thinking capabilities
   providers: [google]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
 - name: Gemini 2.5 Flash Lite
   model: gemini-2.5-flash-lite
@@ -102,61 +75,33 @@
   roles: [chat, edit]
   thinking: false
 
-- name: Gemini 2.0 Flash
-  model: gemini-2.0-flash
-  description: Next-generation Flash model with improved performance and capabilities
-  providers: [google]
-  roles: [chat, edit]
-  thinking: false
-
-- name: Gemini 2.0 Flash Experimental
-  model: gemini-2.0-flash-exp
-  description: Experimental version of Gemini 2.0 Flash with cutting-edge features
-  providers: [google]
-  roles: [chat, edit]
-  thinking: false
+# OpenAI
 
-- name: Gemini 2.0 Flash Lite
-  model: gemini-2.0-flash-lite
-  description: Lightweight version of Gemini 2.0 Flash optimized for efficiency
-  providers: [google]
+- name: GPT-5.3 Chat
+  model: gpt-5.3-chat
+  description: Most-used model that makes everyday conversations smoother and more useful
+  providers: [openai, azure]
   roles: [chat, edit]
   thinking: false
 
-- name: Gemini 2.0 Flash Thinking
-  model: gemini-2.0-flash-thinking-exp-01-21
-  description: Specialized reasoning model with enhanced thinking capabilities
-  providers: [google]
-  roles: [chat]
-  thinking: true
-
-- name: Gemini 1.5 Flash
-  model: gemini-1.5-flash
-  description: Fast and efficient model optimized for speed and everyday tasks
-  providers: [google]
+- name: GPT-5.3-Codex
+  model: gpt-5.3-codex
+  description: Most advanced agentic coding model combining frontier software engineering with broad reasoning
+  providers: [openai]
   roles: [chat, edit]
   thinking: false
 
-- name: Gemini 1.5 Flash 8B
-  model: gemini-1.5-flash-8b
-  description: Lightweight version of Gemini 1.5 Flash with 8 billion parameters
-  providers: [google]
-  roles: [chat, edit]
-  thinking: false
-
-- name: Gemini 1.5 Pro
-  model: gemini-1.5-pro
-  description: Advanced model with superior reasoning capabilities and large context window
-  providers: [google]
+- name: GPT-5.2
+  model: gpt-5.2
+  description: Latest frontier-grade model with strong agentic and long context performance
+  providers: [openai, azure]
   roles: [chat, edit]
   thinking: false
 
-# OpenAI
-
-- name: GPT-5
-  model: gpt-5
-  description: The best model for coding and agentic tasks across domains
-  providers: [openai, azure, github]
+- name: GPT-5.2 Pro
+  model: gpt-5.2-pro
+  description: Powerful model for complex coding tasks, long-form writing, and advanced reasoning
+  providers: [openai]
   roles: [chat, edit]
   thinking: false
 
@@ -174,51 +119,9 @@
   roles: [chat, edit]
   thinking: false
 
-- name: GPT-4.1
-  model: gpt-4.1
-  description: Fast, highly intelligent model with largest context window (1 million tokens)
-  providers: [openai, azure]
-  roles: [chat, edit]
-  thinking: false
-
-- name: GPT-4.1 Mini
-  model: gpt-4.1-mini
-  description: Balanced for intelligence, speed, and cost
-  providers: [openai, azure]
-  roles: [chat, edit]
-  thinking: false
-
-- name: GPT-4o
-  model: gpt-4o
-  description: Fast, intelligent, flexible GPT model with multimodal capabilities
-  providers: [openai, azure]
-  roles: [chat, edit]
-  thinking: false
-
-- name: GPT-4o Mini
-  model: gpt-4o-mini
-  description: Fast, affordable small model for focused tasks
-  providers: [openai, azure, github]
-  roles: [chat, edit]
-  thinking: false
-
 - name: o3
   model: o3
-  description: Our most powerful reasoning model with chain-of-thought capabilities
-  providers: [openai, azure]
-  roles: [chat, edit]
-  thinking: true
-
-- name: o3 Mini
-  model: o3-mini
-  description: A small model alternative to o3 for reasoning tasks
-  providers: [openai, azure]
-  roles: [chat, edit]
-  thinking: true
-
-- name: o3 Pro
-  model: o3-pro
-  description: Version of o3 designed to think longer and provide most reliable responses
+  description: Most powerful reasoning model with chain-of-thought capabilities
   providers: [openai, azure]
   roles: [chat, edit]
   thinking: true
@@ -241,40 +144,33 @@
 
 # Bedrock
 
-- name: Claude 4.5 Sonnet (Bedrock)
-  model: global.anthropic.claude-sonnet-4-5-20250929-v1:0
-  description: Enhanced Sonnet model with improved capabilities
-  providers: [bedrock]
-  roles: [chat, edit]
-  thinking: false
-
-- name: Claude 4.1 Opus (Bedrock)
-  model: us.anthropic.claude-opus-4-1-20250805-v1:0
-  description: Opus model for deep thinking
+- name: Claude 4.6 Opus (Bedrock)
+  model: global.anthropic.claude-opus-4-6-20260206-v1:0
+  description: Strongest model for coding and long-running professional tasks
   providers: [bedrock]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
-- name: Claude 3.7 Sonnet (Bedrock)
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
-  description: Enhanced Sonnet model with improved capabilities
+- name: Claude 4.5 Opus (Bedrock)
+  model: global.anthropic.claude-opus-4-5-20251120-v1:0
+  description: Frontier reasoning model optimized for complex software engineering
   providers: [bedrock]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
-- name: Claude 3.5 Sonnet v2 (Bedrock)
-  model: us.anthropic.claude-3-5-sonnet-20241022-v2:0
-  description: Balanced model with strong performance across reasoning, math, and coding
+- name: Claude 4.5 Sonnet (Bedrock)
+  model: global.anthropic.claude-sonnet-4-5-20250929-v1:0
+  description: Most advanced Sonnet model to date, optimized for real-world agents
   providers: [bedrock]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
-- name: Claude 3.5 Haiku (Bedrock)
-  model: us.anthropic.claude-3-5-haiku-20241022-v1:0
-  description: Fast and efficient model with excellent performance for everyday tasks
+- name: Claude 4.5 Haiku (Bedrock)
+  model: global.anthropic.claude-haiku-4-5-latest-v1:0
+  description: Most efficient model, delivering near-frontier intelligence at a fraction of the cost
   providers: [bedrock]
   roles: [chat, edit]
-  thinking: false
+  thinking: true
 
 - name: Llama 3.3 70B Instruct
   model: us.meta.llama3-3-70b-instruct-v1:0
@@ -301,7 +197,7 @@
 
 - name: gpt-oss 20b
   model: gpt-oss:20b
-  description: OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
+  description: OpenAI's open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
   providers: [ollama]
   roles: [chat, edit]
   thinking: true

packages/llm-info/src/generate.ts

@@ -7,7 +7,7 @@ import { parse } from "yaml";
 import { z } from "zod";
 import { Logger } from "./simple_logger.ts";
 
-const ROLES = ["chat", "edit", "rerank", "embed"] as const;
+const ROLES = ["chat", "edit", "rerank", "embed", "autocomplete"] as const;
 
 export const LLMInfoSchema = z.object({
   name: z.string(),