LLM/CLIProxyAPIPlus
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPIPlus.git synced 2026-03-30 01:06:39 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
79033aee34299cdce32bff305beb5c8c6135343f
CLIProxyAPIPlus/internal/registry/model_definitions.go
Ravens2121 db80b20bc2 feat(kiro): enhance thinking support and fix truncation issues 
- **Thinking Support**:
    - Enabled thinking support for all Kiro Claude models, including Haiku 4.5 and agentic variants.
    - Updated `model_definitions.go` with thinking configuration (Min: 1024, Max: 32000, ZeroAllowed: true).
    - Fixed `extended_thinking` field names in `model_registry.go` (from `min_budget`/`max_budget` to `min`/`max`) to comply with Claude API specs, enabling thinking control in clients like Claude Code.

- **Kiro Executor Fixes**:
    - Fixed `budget_tokens` handling: explicitly disable thinking when budget is 0 or negative.
    - Removed aggressive duplicate content filtering logic that caused truncation/data loss.
    - Enhanced thinking tag parsing with `extractThinkingFromContent` to correctly handle interleaved thinking/text blocks.
    - Added EOF handling to flush pending thinking tag characters, preventing data loss at stream end.

- **Performance**:
    - Optimized Claude stream handler (v6.2) with reduced buffer size (4KB) and faster flush interval (50ms) to minimize latency and prevent timeouts.
2025-12-13 03:57:13 +08:00

1049 lines
45 KiB
Go
Raw Blame History

// Package registry provides model definitions for various AI service providers.
// This file contains static model definitions that can be used by clients
// when registering their supported models.
package registry
// GetClaudeModels returns the standard Claude model definitions
func GetClaudeModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "claude-haiku-4-5-20251001",
Object: "model",
Created: 1759276800, // 2025-10-01
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Haiku",
ContextLength: 200000,
MaxCompletionTokens: 64000,
// Thinking: not supported for Haiku models
},
{
ID: "claude-sonnet-4-5-20250929",
Object: "model",
Created: 1759104000, // 2025-09-29
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Sonnet",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-opus-4-5-20251101",
Object: "model",
Created: 1761955200, // 2025-11-01
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.5 Opus",
Description: "Premium model combining maximum intelligence with practical performance",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-opus-4-1-20250805",
Object: "model",
Created: 1722945600, // 2025-08-05
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4.1 Opus",
ContextLength: 200000,
MaxCompletionTokens: 32000,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-opus-4-20250514",
Object: "model",
Created: 1715644800, // 2025-05-14
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4 Opus",
ContextLength: 200000,
MaxCompletionTokens: 32000,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-sonnet-4-20250514",
Object: "model",
Created: 1715644800, // 2025-05-14
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 4 Sonnet",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-3-7-sonnet-20250219",
Object: "model",
Created: 1708300800, // 2025-02-19
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 3.7 Sonnet",
ContextLength: 128000,
MaxCompletionTokens: 8192,
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "claude-3-5-haiku-20241022",
Object: "model",
Created: 1729555200, // 2024-10-22
OwnedBy: "anthropic",
Type: "claude",
DisplayName: "Claude 3.5 Haiku",
ContextLength: 128000,
MaxCompletionTokens: 8192,
// Thinking: not supported for Haiku models
},
}
}
// GetGeminiModels returns the standard Gemini model definitions
func GetGeminiModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-image-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-image-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Image Preview",
Description: "Gemini 3 Pro Image Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
}
}
func GetGeminiVertexModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-image-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-image-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Image Preview",
Description: "Gemini 3 Pro Image Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
}
}
// GetGeminiCLIModels returns the standard Gemini model definitions
func GetGeminiCLIModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
}
}
// GetAIStudioModels returns the Gemini model definitions for AI Studio integrations
func GetAIStudioModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-pro",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-pro",
Version: "2.5",
DisplayName: "Gemini 2.5 Pro",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash",
Version: "001",
DisplayName: "Gemini 2.5 Flash",
Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Our smallest and most cost effective model, built for at scale usage.",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-3-pro-preview",
Object: "model",
Created: 1737158400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-3-pro-preview",
Version: "3.0",
DisplayName: "Gemini 3 Pro Preview",
Description: "Gemini 3 Pro Preview",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-pro-latest",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-pro-latest",
Version: "2.5",
DisplayName: "Gemini Pro Latest",
Description: "Latest release of Gemini Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
},
{
ID: "gemini-flash-latest",
Object: "model",
Created: 1750118400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-latest",
Version: "2.5",
DisplayName: "Gemini Flash Latest",
Description: "Latest release of Gemini Flash",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-flash-lite-latest",
Object: "model",
Created: 1753142400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-lite-latest",
Version: "2.5",
DisplayName: "Gemini Flash-Lite Latest",
Description: "Latest release of Gemini Flash-Lite",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
Thinking: &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "gemini-2.5-flash-image-preview",
Object: "model",
Created: 1756166400,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-image-preview",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Image Preview",
Description: "State-of-the-art image generation and editing model.",
InputTokenLimit: 1048576,
OutputTokenLimit: 8192,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
// image models don't support thinkingConfig; leave Thinking nil
},
{
ID: "gemini-2.5-flash-image",
Object: "model",
Created: 1759363200,
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-image",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Image",
Description: "State-of-the-art image generation and editing model.",
InputTokenLimit: 1048576,
OutputTokenLimit: 8192,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
// image models don't support thinkingConfig; leave Thinking nil
},
}
}
// GetOpenAIModels returns the standard OpenAI model definitions
func GetOpenAIModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gpt-5",
Object: "model",
Created: 1754524800,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-08-07",
DisplayName: "GPT 5",
Description: "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"minimal", "low", "medium", "high"}},
},
{
ID: "gpt-5-codex",
Object: "model",
Created: 1757894400,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-09-15",
DisplayName: "GPT 5 Codex",
Description: "Stable version of GPT 5 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5-codex-mini",
Object: "model",
Created: 1762473600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5-2025-11-07",
DisplayName: "GPT 5 Codex Mini",
Description: "Stable version of GPT 5 Codex Mini: cheaper, faster, but less capable version of GPT 5 Codex.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5",
Description: "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"none", "low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5.1 Codex",
Description: "Stable version of GPT 5.1 Codex, The best model for coding and agentic tasks across domains.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex-mini",
Object: "model",
Created: 1762905600,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-2025-11-12",
DisplayName: "GPT 5.1 Codex Mini",
Description: "Stable version of GPT 5.1 Codex Mini: cheaper, faster, but less capable version of GPT 5.1 Codex.",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}},
},
{
ID: "gpt-5.1-codex-max",
Object: "model",
Created: 1763424000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.1-max",
DisplayName: "GPT 5.1 Codex Max",
Description: "Stable version of GPT 5.1 Codex Max",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
},
{
ID: "gpt-5.2",
Object: "model",
Created: 1765440000,
OwnedBy: "openai",
Type: "openai",
Version: "gpt-5.2",
DisplayName: "GPT 5.2",
Description: "Stable version of GPT 5.2",
ContextLength: 400000,
MaxCompletionTokens: 128000,
SupportedParameters: []string{"tools"},
Thinking: &ThinkingSupport{Levels: []string{"none", "low", "medium", "high", "xhigh"}},
},
}
}
// GetQwenModels returns the standard Qwen model definitions
func GetQwenModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "qwen3-coder-plus",
Object: "model",
Created: 1753228800,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Coder Plus",
Description: "Advanced code generation and understanding model",
ContextLength: 32768,
MaxCompletionTokens: 8192,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
{
ID: "qwen3-coder-flash",
Object: "model",
Created: 1753228800,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Coder Flash",
Description: "Fast code generation model",
ContextLength: 8192,
MaxCompletionTokens: 2048,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
{
ID: "vision-model",
Object: "model",
Created: 1758672000,
OwnedBy: "qwen",
Type: "qwen",
Version: "3.0",
DisplayName: "Qwen3 Vision Model",
Description: "Vision model model",
ContextLength: 32768,
MaxCompletionTokens: 2048,
SupportedParameters: []string{"temperature", "top_p", "max_tokens", "stream", "stop"},
},
}
}
// GetIFlowModels returns supported models for iFlow OAuth accounts.
func GetIFlowModels() []*ModelInfo {
entries := []struct {
ID string
DisplayName string
Description string
Created int64
Thinking *ThinkingSupport
}{
{ID: "tstars2.0", DisplayName: "TStars-2.0", Description: "iFlow TStars-2.0 multimodal assistant", Created: 1746489600},
{ID: "qwen3-coder-plus", DisplayName: "Qwen3-Coder-Plus", Description: "Qwen3 Coder Plus code generation", Created: 1753228800},
{ID: "qwen3-max", DisplayName: "Qwen3-Max", Description: "Qwen3 flagship model", Created: 1758672000},
{ID: "qwen3-vl-plus", DisplayName: "Qwen3-VL-Plus", Description: "Qwen3 multimodal vision-language", Created: 1758672000},
{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400},
{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905", Created: 1757030400},
{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400},
{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
{ID: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2", Created: 1764576000},
{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental", Created: 1759104000},
{ID: "deepseek-v3.1", DisplayName: "DeepSeek-V3.1-Terminus", Description: "DeepSeek V3.1 Terminus", Created: 1756339200},
{ID: "deepseek-r1", DisplayName: "DeepSeek-R1", Description: "DeepSeek reasoning model R1", Created: 1737331200, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
{ID: "deepseek-v3", DisplayName: "DeepSeek-V3-671B", Description: "DeepSeek V3 671B", Created: 1734307200},
{ID: "qwen3-32b", DisplayName: "Qwen3-32B", Description: "Qwen3 32B", Created: 1747094400},
{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000, Thinking: &ThinkingSupport{Levels: []string{"low", "medium", "high"}}},
}
models := make([]*ModelInfo, 0, len(entries))
for _, entry := range entries {
models = append(models, &ModelInfo{
ID: entry.ID,
Object: "model",
Created: entry.Created,
OwnedBy: "iflow",
Type: "iflow",
DisplayName: entry.DisplayName,
Description: entry.Description,
Thinking: entry.Thinking,
})
}
return models
}
// AntigravityModelConfig captures static antigravity model overrides, including
// Thinking budget limits and provider max completion tokens.
type AntigravityModelConfig struct {
Thinking *ThinkingSupport
MaxCompletionTokens int
Name string
}
// GetAntigravityModelConfig returns static configuration for antigravity models.
// Keys use the ALIASED model names (after modelName2Alias conversion) for direct lookup.
func GetAntigravityModelConfig() map[string]*AntigravityModelConfig {
return map[string]*AntigravityModelConfig{
"gemini-2.5-flash": {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, Name: "models/gemini-2.5-flash"},
"gemini-2.5-flash-lite": {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, Name: "models/gemini-2.5-flash-lite"},
"gemini-2.5-computer-use-preview-10-2025": {Name: "models/gemini-2.5-computer-use-preview-10-2025"},
"gemini-3-pro-preview": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, Name: "models/gemini-3-pro-preview"},
"gemini-3-pro-image-preview": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, Name: "models/gemini-3-pro-image-preview"},
"gemini-claude-sonnet-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"gemini-claude-opus-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000},
}
}
// GetGitHubCopilotModels returns the available models for GitHub Copilot.
// These models are available through the GitHub Copilot API at api.githubcopilot.com.
func GetGitHubCopilotModels() []*ModelInfo {
now := int64(1732752000) // 2024-11-27
return []*ModelInfo{
{
ID: "gpt-4.1",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-4.1",
Description: "OpenAI GPT-4.1 via GitHub Copilot",
ContextLength: 128000,
MaxCompletionTokens: 16384,
},
{
ID: "gpt-5",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5",
Description: "OpenAI GPT-5 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 32768,
},
{
ID: "gpt-5-mini",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5 Mini",
Description: "OpenAI GPT-5 Mini via GitHub Copilot",
ContextLength: 128000,
MaxCompletionTokens: 16384,
},
{
ID: "gpt-5-codex",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5 Codex",
Description: "OpenAI GPT-5 Codex via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 32768,
},
{
ID: "gpt-5.1",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5.1",
Description: "OpenAI GPT-5.1 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 32768,
},
{
ID: "gpt-5.1-codex",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5.1 Codex",
Description: "OpenAI GPT-5.1 Codex via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 32768,
},
{
ID: "gpt-5.1-codex-mini",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "GPT-5.1 Codex Mini",
Description: "OpenAI GPT-5.1 Codex Mini via GitHub Copilot",
ContextLength: 128000,
MaxCompletionTokens: 16384,
},
{
ID: "claude-haiku-4.5",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Claude Haiku 4.5",
Description: "Anthropic Claude Haiku 4.5 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "claude-opus-4.1",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Claude Opus 4.1",
Description: "Anthropic Claude Opus 4.1 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 32000,
},
{
ID: "claude-opus-4.5",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Claude Opus 4.5",
Description: "Anthropic Claude Opus 4.5 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "claude-sonnet-4",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Claude Sonnet 4",
Description: "Anthropic Claude Sonnet 4 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "claude-sonnet-4.5",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Claude Sonnet 4.5",
Description: "Anthropic Claude Sonnet 4.5 via GitHub Copilot",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "gemini-2.5-pro",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Gemini 2.5 Pro",
Description: "Google Gemini 2.5 Pro via GitHub Copilot",
ContextLength: 1048576,
MaxCompletionTokens: 65536,
},
{
ID: "gemini-3-pro",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Gemini 3 Pro",
Description: "Google Gemini 3 Pro via GitHub Copilot",
ContextLength: 1048576,
MaxCompletionTokens: 65536,
},
{
ID: "grok-code-fast-1",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Grok Code Fast 1",
Description: "xAI Grok Code Fast 1 via GitHub Copilot",
ContextLength: 128000,
MaxCompletionTokens: 16384,
},
{
ID: "raptor-mini",
Object: "model",
Created: now,
OwnedBy: "github-copilot",
Type: "github-copilot",
DisplayName: "Raptor Mini",
Description: "Raptor Mini via GitHub Copilot",
ContextLength: 128000,
MaxCompletionTokens: 16384,
},
}
}
// GetKiroModels returns the Kiro (AWS CodeWhisperer) model definitions
func GetKiroModels() []*ModelInfo {
return []*ModelInfo{
// --- Base Models ---
{
ID: "kiro-claude-opus-4-5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Opus 4.5",
Description: "Claude Opus 4.5 via Kiro (2.2x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-sonnet-4-5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Sonnet 4.5",
Description: "Claude Sonnet 4.5 via Kiro (1.3x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-sonnet-4",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Sonnet 4",
Description: "Claude Sonnet 4 via Kiro (1.3x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-haiku-4-5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Haiku 4.5",
Description: "Claude Haiku 4.5 via Kiro (0.4x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
// --- Agentic Variants (Optimized for coding agents with chunked writes) ---
{
ID: "kiro-claude-opus-4-5-agentic",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Opus 4.5 (Agentic)",
Description: "Claude Opus 4.5 optimized for coding agents (chunked writes)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-sonnet-4-5-agentic",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Sonnet 4.5 (Agentic)",
Description: "Claude Sonnet 4.5 optimized for coding agents (chunked writes)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-sonnet-4-agentic",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Sonnet 4 (Agentic)",
Description: "Claude Sonnet 4 optimized for coding agents (chunked writes)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
{
ID: "kiro-claude-haiku-4-5-agentic",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Kiro Claude Haiku 4.5 (Agentic)",
Description: "Claude Haiku 4.5 optimized for coding agents (chunked writes)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
Thinking: &ThinkingSupport{Min: 1024, Max: 32000, ZeroAllowed: true, DynamicAllowed: true},
},
}
}
// GetAmazonQModels returns the Amazon Q (AWS CodeWhisperer) model definitions.
// These models use the same API as Kiro and share the same executor.
func GetAmazonQModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "amazonq-auto",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro", // Uses Kiro executor - same API
DisplayName: "Amazon Q Auto",
Description: "Automatic model selection by Amazon Q",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "amazonq-claude-opus-4.5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Amazon Q Claude Opus 4.5",
Description: "Claude Opus 4.5 via Amazon Q (2.2x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "amazonq-claude-sonnet-4.5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Amazon Q Claude Sonnet 4.5",
Description: "Claude Sonnet 4.5 via Amazon Q (1.3x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "amazonq-claude-sonnet-4",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Amazon Q Claude Sonnet 4",
Description: "Claude Sonnet 4 via Amazon Q (1.3x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
{
ID: "amazonq-claude-haiku-4.5",
Object: "model",
Created: 1732752000,
OwnedBy: "aws",
Type: "kiro",
DisplayName: "Amazon Q Claude Haiku 4.5",
Description: "Claude Haiku 4.5 via Amazon Q (0.4x credit)",
ContextLength: 200000,
MaxCompletionTokens: 64000,
},
}
}
Reference in New Issue View Git Blame Copy Permalink