mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-17 07:03:25 +00:00
Add Mistral as AI provider
- Add Mistral to KnownProvider type and model generation - Implement Mistral-specific compat handling in openai-completions: - requiresToolResultName: tool results need name field - requiresAssistantAfterToolResult: synthetic assistant message between tool/user - requiresThinkingAsText: thinking blocks as <thinking> text - requiresMistralToolIds: tool IDs must be exactly 9 alphanumeric chars - Add MISTRAL_API_KEY environment variable support - Add Mistral tests across all test files - Update documentation (README, CHANGELOG) for both ai and coding-agent packages - Remove client IDs from gemini.md, reference upstream source instead Closes #165
This commit is contained in:
Mario Zechner
parent
a248e2547a
commit
99b4b1aca0
31 changed files with 1856 additions and 282 deletions
|
|
@ -1989,6 +1989,416 @@ export const MODELS = {
|
|||
contextWindow: 204800,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
"glm-4.6v": {
|
||||
id: "glm-4.6v",
|
||||
name: "GLM-4.6V",
|
||||
api: "anthropic-messages",
|
||||
provider: "zai",
|
||||
baseUrl: "https://api.z.ai/api/anthropic",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 0.9,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
},
|
||||
mistral: {
|
||||
"devstral-medium-2507": {
|
||||
id: "devstral-medium-2507",
|
||||
name: "Devstral Medium",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-large-2512": {
|
||||
id: "mistral-large-2512",
|
||||
name: "Mistral Large 3",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"open-mixtral-8x22b": {
|
||||
id: "open-mixtral-8x22b",
|
||||
name: "Mixtral 8x22B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 64000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"ministral-8b-latest": {
|
||||
id: "ministral-8b-latest",
|
||||
name: "Ministral 8B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"pixtral-large-latest": {
|
||||
id: "pixtral-large-latest",
|
||||
name: "Pixtral Large",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"ministral-3b-latest": {
|
||||
id: "ministral-3b-latest",
|
||||
name: "Ministral 3B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.04,
|
||||
output: 0.04,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"pixtral-12b": {
|
||||
id: "pixtral-12b",
|
||||
name: "Pixtral 12B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-medium-2505": {
|
||||
id: "mistral-medium-2505",
|
||||
name: "Mistral Medium 3",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"labs-devstral-small-2512": {
|
||||
id: "labs-devstral-small-2512",
|
||||
name: "Devstral Small 2",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"devstral-medium-latest": {
|
||||
id: "devstral-medium-latest",
|
||||
name: "Devstral 2",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"devstral-small-2505": {
|
||||
id: "devstral-small-2505",
|
||||
name: "Devstral Small 2505",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-medium-2508": {
|
||||
id: "mistral-medium-2508",
|
||||
name: "Mistral Medium 3.1",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-small-latest": {
|
||||
id: "mistral-small-latest",
|
||||
name: "Mistral Small",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"magistral-small": {
|
||||
id: "magistral-small",
|
||||
name: "Magistral Small",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"devstral-small-2507": {
|
||||
id: "devstral-small-2507",
|
||||
name: "Devstral Small",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"codestral-latest": {
|
||||
id: "codestral-latest",
|
||||
name: "Codestral",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 0.9,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"open-mixtral-8x7b": {
|
||||
id: "open-mixtral-8x7b",
|
||||
name: "Mixtral 8x7B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.7,
|
||||
output: 0.7,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-nemo": {
|
||||
id: "mistral-nemo",
|
||||
name: "Mistral Nemo",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"open-mistral-7b": {
|
||||
id: "open-mistral-7b",
|
||||
name: "Mistral 7B",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 0.25,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8000,
|
||||
maxTokens: 8000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-large-latest": {
|
||||
id: "mistral-large-latest",
|
||||
name: "Mistral Large",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 262144,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-medium-latest": {
|
||||
id: "mistral-medium-latest",
|
||||
name: "Mistral Medium",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.4,
|
||||
output: 2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistral-large-2411": {
|
||||
id: "mistral-large-2411",
|
||||
name: "Mistral Large 2.1",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"magistral-medium-latest": {
|
||||
id: "magistral-medium-latest",
|
||||
name: "Magistral Medium",
|
||||
api: "openai-completions",
|
||||
provider: "mistral",
|
||||
baseUrl: "https://api.mistral.ai/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 2,
|
||||
output: 5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
openrouter: {
|
||||
"mistralai/devstral-2512:free": {
|
||||
|
|
@ -4448,13 +4858,13 @@ export const MODELS = {
|
|||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.136,
|
||||
output: 0.6799999999999999,
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1048576,
|
||||
maxTokens: 8192,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-4-scout": {
|
||||
id: "meta-llama/llama-4-scout",
|
||||
|
|
@ -5068,23 +5478,6 @@ export const MODELS = {
|
|||
contextWindow: 200000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/ministral-3b": {
|
||||
id: "mistralai/ministral-3b",
|
||||
name: "Mistral: Ministral 3B",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.04,
|
||||
output: 0.04,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/ministral-8b": {
|
||||
id: "mistralai/ministral-8b",
|
||||
name: "Mistral: Ministral 8B",
|
||||
|
|
@ -5102,6 +5495,23 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/ministral-3b": {
|
||||
id: "mistralai/ministral-3b",
|
||||
name: "Mistral: Ministral 3B",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.04,
|
||||
output: 0.04,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"nvidia/llama-3.1-nemotron-70b-instruct": {
|
||||
id: "nvidia/llama-3.1-nemotron-70b-instruct",
|
||||
name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
|
||||
|
|
@ -5272,6 +5682,23 @@ export const MODELS = {
|
|||
contextWindow: 128000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3.1-8b-instruct": {
|
||||
id: "meta-llama/llama-3.1-8b-instruct",
|
||||
name: "Meta: Llama 3.1 8B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.02,
|
||||
output: 0.03,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3.1-405b-instruct": {
|
||||
id: "meta-llama/llama-3.1-405b-instruct",
|
||||
name: "Meta: Llama 3.1 405B Instruct",
|
||||
|
|
@ -5306,23 +5733,6 @@ export const MODELS = {
|
|||
contextWindow: 131072,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3.1-8b-instruct": {
|
||||
id: "meta-llama/llama-3.1-8b-instruct",
|
||||
name: "Meta: Llama 3.1 8B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.02,
|
||||
output: 0.03,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-nemo": {
|
||||
id: "mistralai/mistral-nemo",
|
||||
name: "Mistral: Mistral Nemo",
|
||||
|
|
@ -5459,6 +5869,23 @@ export const MODELS = {
|
|||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4o-2024-05-13": {
|
||||
id: "openai/gpt-4o-2024-05-13",
|
||||
name: "OpenAI: GPT-4o (2024-05-13)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 5,
|
||||
output: 15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4o": {
|
||||
id: "openai/gpt-4o",
|
||||
name: "OpenAI: GPT-4o",
|
||||
|
|
@ -5493,22 +5920,22 @@ export const MODELS = {
|
|||
contextWindow: 128000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4o-2024-05-13": {
|
||||
id: "openai/gpt-4o-2024-05-13",
|
||||
name: "OpenAI: GPT-4o (2024-05-13)",
|
||||
"meta-llama/llama-3-70b-instruct": {
|
||||
id: "meta-llama/llama-3-70b-instruct",
|
||||
name: "Meta: Llama 3 70B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 5,
|
||||
output: 15,
|
||||
input: 0.3,
|
||||
output: 0.39999999999999997,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
contextWindow: 8192,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3-8b-instruct": {
|
||||
id: "meta-llama/llama-3-8b-instruct",
|
||||
|
|
@ -5527,23 +5954,6 @@ export const MODELS = {
|
|||
contextWindow: 8192,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"meta-llama/llama-3-70b-instruct": {
|
||||
id: "meta-llama/llama-3-70b-instruct",
|
||||
name: "Meta: Llama 3 70B Instruct",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 0.39999999999999997,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8192,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mixtral-8x22b-instruct": {
|
||||
id: "mistralai/mixtral-8x22b-instruct",
|
||||
name: "Mistral: Mixtral 8x22B Instruct",
|
||||
|
|
@ -5629,23 +6039,6 @@ export const MODELS = {
|
|||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4-turbo-preview": {
|
||||
id: "openai/gpt-4-turbo-preview",
|
||||
name: "OpenAI: GPT-4 Turbo Preview",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 10,
|
||||
output: 30,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-3.5-turbo-0613": {
|
||||
id: "openai/gpt-3.5-turbo-0613",
|
||||
name: "OpenAI: GPT-3.5 Turbo (older v0613)",
|
||||
|
|
@ -5663,6 +6056,23 @@ export const MODELS = {
|
|||
contextWindow: 4095,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4-turbo-preview": {
|
||||
id: "openai/gpt-4-turbo-preview",
|
||||
name: "OpenAI: GPT-4 Turbo Preview",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 10,
|
||||
output: 30,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"mistralai/mistral-tiny": {
|
||||
id: "mistralai/mistral-tiny",
|
||||
name: "Mistral Tiny",
|
||||
|
|
@ -5731,6 +6141,23 @@ export const MODELS = {
|
|||
contextWindow: 16385,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4-0314": {
|
||||
id: "openai/gpt-4-0314",
|
||||
name: "OpenAI: GPT-4 (older v0314)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 30,
|
||||
output: 60,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8191,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4": {
|
||||
id: "openai/gpt-4",
|
||||
name: "OpenAI: GPT-4",
|
||||
|
|
@ -5765,23 +6192,6 @@ export const MODELS = {
|
|||
contextWindow: 16385,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openai/gpt-4-0314": {
|
||||
id: "openai/gpt-4-0314",
|
||||
name: "OpenAI: GPT-4 (older v0314)",
|
||||
api: "openai-completions",
|
||||
provider: "openrouter",
|
||||
baseUrl: "https://openrouter.ai/api/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 30,
|
||||
output: 60,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 8191,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"openrouter/auto": {
|
||||
id: "openrouter/auto",
|
||||
name: "OpenRouter: Auto Router",
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@ import type {
|
|||
ChatCompletionContentPartImage,
|
||||
ChatCompletionContentPartText,
|
||||
ChatCompletionMessageParam,
|
||||
ChatCompletionToolMessageParam,
|
||||
} from "openai/resources/chat/completions.js";
|
||||
import { calculateCost } from "../models.js";
|
||||
import type {
|
||||
|
|
@ -27,6 +28,25 @@ import { parseStreamingJson } from "../utils/json-parse.js";
|
|||
import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
|
||||
import { transformMessages } from "./transorm-messages.js";
|
||||
|
||||
/**
|
||||
* Normalize tool call ID for Mistral.
|
||||
* Mistral requires tool IDs to be exactly 9 alphanumeric characters (a-z, A-Z, 0-9).
|
||||
*/
|
||||
function normalizeMistralToolId(id: string, isMistral: boolean): string {
|
||||
if (!isMistral) return id;
|
||||
// Remove non-alphanumeric characters
|
||||
let normalized = id.replace(/[^a-zA-Z0-9]/g, "");
|
||||
// Mistral requires exactly 9 characters
|
||||
if (normalized.length < 9) {
|
||||
// Pad with deterministic characters based on original ID to ensure matching
|
||||
const padding = "ABCDEFGHI";
|
||||
normalized = normalized + padding.slice(0, 9 - normalized.length);
|
||||
} else if (normalized.length > 9) {
|
||||
normalized = normalized.slice(0, 9);
|
||||
}
|
||||
return normalized;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if conversation messages contain tool calls or tool results.
|
||||
* This is needed because Anthropic (via proxy) requires the tools param
|
||||
|
|
@ -346,7 +366,18 @@ function convertMessages(
|
|||
params.push({ role: role, content: sanitizeSurrogates(context.systemPrompt) });
|
||||
}
|
||||
|
||||
let lastRole: string | null = null;
|
||||
|
||||
for (const msg of transformedMessages) {
|
||||
// Some providers (e.g. Mistral) don't allow user messages directly after tool results
|
||||
// Insert a synthetic assistant message to bridge the gap
|
||||
if (compat.requiresAssistantAfterToolResult && lastRole === "toolResult" && msg.role === "user") {
|
||||
params.push({
|
||||
role: "assistant",
|
||||
content: "I have processed the tool results.",
|
||||
});
|
||||
}
|
||||
|
||||
if (msg.role === "user") {
|
||||
if (typeof msg.content === "string") {
|
||||
params.push({
|
||||
|
|
@ -379,9 +410,10 @@ function convertMessages(
|
|||
});
|
||||
}
|
||||
} else if (msg.role === "assistant") {
|
||||
// Some providers (e.g. Mistral) don't accept null content, use empty string instead
|
||||
const assistantMsg: ChatCompletionAssistantMessageParam = {
|
||||
role: "assistant",
|
||||
content: null,
|
||||
content: compat.requiresAssistantAfterToolResult ? "" : null,
|
||||
};
|
||||
|
||||
const textBlocks = msg.content.filter((b) => b.type === "text") as TextContent[];
|
||||
|
|
@ -391,20 +423,31 @@ function convertMessages(
|
|||
});
|
||||
}
|
||||
|
||||
// Handle thinking blocks for llama.cpp server + gpt-oss
|
||||
// Handle thinking blocks
|
||||
const thinkingBlocks = msg.content.filter((b) => b.type === "thinking") as ThinkingContent[];
|
||||
if (thinkingBlocks.length > 0) {
|
||||
// Use the signature from the first thinking block if available
|
||||
const signature = thinkingBlocks[0].thinkingSignature;
|
||||
if (signature && signature.length > 0) {
|
||||
(assistantMsg as any)[signature] = thinkingBlocks.map((b) => b.thinking).join("\n");
|
||||
if (compat.requiresThinkingAsText) {
|
||||
// Convert thinking blocks to text with <thinking> delimiters
|
||||
const thinkingText = thinkingBlocks.map((b) => `<thinking>\n${b.thinking}\n</thinking>`).join("\n");
|
||||
const textContent = assistantMsg.content as Array<{ type: "text"; text: string }> | null;
|
||||
if (textContent) {
|
||||
textContent.unshift({ type: "text", text: thinkingText });
|
||||
} else {
|
||||
assistantMsg.content = [{ type: "text", text: thinkingText }];
|
||||
}
|
||||
} else {
|
||||
// Use the signature from the first thinking block if available (for llama.cpp server + gpt-oss)
|
||||
const signature = thinkingBlocks[0].thinkingSignature;
|
||||
if (signature && signature.length > 0) {
|
||||
(assistantMsg as any)[signature] = thinkingBlocks.map((b) => b.thinking).join("\n");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const toolCalls = msg.content.filter((b) => b.type === "toolCall") as ToolCall[];
|
||||
if (toolCalls.length > 0) {
|
||||
assistantMsg.tool_calls = toolCalls.map((tc) => ({
|
||||
id: tc.id,
|
||||
id: normalizeMistralToolId(tc.id, compat.requiresMistralToolIds),
|
||||
type: "function" as const,
|
||||
function: {
|
||||
name: tc.name,
|
||||
|
|
@ -426,11 +469,16 @@ function convertMessages(
|
|||
|
||||
// Always send tool result with text (or placeholder if only images)
|
||||
const hasText = textResult.length > 0;
|
||||
params.push({
|
||||
// Some providers (e.g. Mistral) require the 'name' field in tool results
|
||||
const toolResultMsg: ChatCompletionToolMessageParam = {
|
||||
role: "tool",
|
||||
content: sanitizeSurrogates(hasText ? textResult : "(see attached image)"),
|
||||
tool_call_id: msg.toolCallId,
|
||||
});
|
||||
tool_call_id: normalizeMistralToolId(msg.toolCallId, compat.requiresMistralToolIds),
|
||||
};
|
||||
if (compat.requiresToolResultName && msg.toolName) {
|
||||
(toolResultMsg as any).name = msg.toolName;
|
||||
}
|
||||
params.push(toolResultMsg);
|
||||
|
||||
// If there are images and model supports them, send a follow-up user message with images
|
||||
if (hasImages && model.input.includes("image")) {
|
||||
|
|
@ -462,6 +510,8 @@ function convertMessages(
|
|||
});
|
||||
}
|
||||
}
|
||||
|
||||
lastRole = msg.role;
|
||||
}
|
||||
|
||||
return params;
|
||||
|
|
@ -512,11 +562,17 @@ function detectCompatFromUrl(baseUrl: string): Required<OpenAICompat> {
|
|||
|
||||
const isGrok = baseUrl.includes("api.x.ai");
|
||||
|
||||
const isMistral = baseUrl.includes("mistral.ai");
|
||||
|
||||
return {
|
||||
supportsStore: !isNonStandard,
|
||||
supportsDeveloperRole: !isNonStandard,
|
||||
supportsReasoningEffort: !isGrok,
|
||||
maxTokensField: useMaxTokens ? "max_tokens" : "max_completion_tokens",
|
||||
requiresToolResultName: isMistral,
|
||||
requiresAssistantAfterToolResult: isMistral,
|
||||
requiresThinkingAsText: isMistral,
|
||||
requiresMistralToolIds: isMistral,
|
||||
};
|
||||
}
|
||||
|
||||
|
|
@ -533,5 +589,10 @@ function getCompat(model: Model<"openai-completions">): Required<OpenAICompat> {
|
|||
supportsDeveloperRole: model.compat.supportsDeveloperRole ?? detected.supportsDeveloperRole,
|
||||
supportsReasoningEffort: model.compat.supportsReasoningEffort ?? detected.supportsReasoningEffort,
|
||||
maxTokensField: model.compat.maxTokensField ?? detected.maxTokensField,
|
||||
requiresToolResultName: model.compat.requiresToolResultName ?? detected.requiresToolResultName,
|
||||
requiresAssistantAfterToolResult:
|
||||
model.compat.requiresAssistantAfterToolResult ?? detected.requiresAssistantAfterToolResult,
|
||||
requiresThinkingAsText: model.compat.requiresThinkingAsText ?? detected.requiresThinkingAsText,
|
||||
requiresMistralToolIds: model.compat.requiresMistralToolIds ?? detected.requiresMistralToolIds,
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -39,6 +39,7 @@ export function getApiKey(provider: any): string | undefined {
|
|||
xai: "XAI_API_KEY",
|
||||
openrouter: "OPENROUTER_API_KEY",
|
||||
zai: "ZAI_API_KEY",
|
||||
mistral: "MISTRAL_API_KEY",
|
||||
};
|
||||
|
||||
const envVar = envMap[provider];
|
||||
|
|
|
|||
|
|
@ -26,7 +26,16 @@ const _exhaustive: _CheckExhaustive = true;
|
|||
// Helper type to get options for a specific API
|
||||
export type OptionsForApi<TApi extends Api> = ApiOptionsMap[TApi];
|
||||
|
||||
export type KnownProvider = "anthropic" | "google" | "openai" | "xai" | "groq" | "cerebras" | "openrouter" | "zai";
|
||||
export type KnownProvider =
|
||||
| "anthropic"
|
||||
| "google"
|
||||
| "openai"
|
||||
| "xai"
|
||||
| "groq"
|
||||
| "cerebras"
|
||||
| "openrouter"
|
||||
| "zai"
|
||||
| "mistral";
|
||||
export type Provider = KnownProvider | string;
|
||||
|
||||
export type ReasoningEffort = "minimal" | "low" | "medium" | "high" | "xhigh";
|
||||
|
|
@ -165,6 +174,14 @@ export interface OpenAICompat {
|
|||
supportsReasoningEffort?: boolean;
|
||||
/** Which field to use for max tokens. Default: auto-detected from URL. */
|
||||
maxTokensField?: "max_completion_tokens" | "max_tokens";
|
||||
/** Whether tool results require the `name` field. Default: auto-detected from URL. */
|
||||
requiresToolResultName?: boolean;
|
||||
/** Whether a user message after tool results requires an assistant message in between. Default: auto-detected from URL. */
|
||||
requiresAssistantAfterToolResult?: boolean;
|
||||
/** Whether thinking blocks must be converted to text blocks with <thinking> delimiters. Default: auto-detected from URL. */
|
||||
requiresThinkingAsText?: boolean;
|
||||
/** Whether tool call IDs must be normalized to Mistral format (exactly 9 alphanumeric chars). Default: auto-detected from URL. */
|
||||
requiresMistralToolIds?: boolean;
|
||||
}
|
||||
|
||||
// Model interface for the unified model system
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@ import type { AssistantMessage } from "../types.js";
|
|||
* - llama.cpp: "the request exceeds the available context size, try increasing it"
|
||||
* - LM Studio: "tokens to keep from the initial prompt is greater than the context length"
|
||||
* - Cerebras: Returns "400 status code (no body)" - handled separately below
|
||||
* - Mistral: Returns "400 status code (no body)" - handled separately below
|
||||
* - z.ai: Does NOT error, accepts overflow silently - handled via usage.input > contextWindow
|
||||
* - Ollama: Silently truncates input - not detectable via error message
|
||||
*/
|
||||
|
|
@ -52,6 +53,7 @@ const OVERFLOW_PATTERNS = [
|
|||
* - xAI (Grok): "maximum prompt length is X but request contains Y"
|
||||
* - Groq: "reduce the length of the messages"
|
||||
* - Cerebras: 400/413 status code (no body)
|
||||
* - Mistral: 400/413 status code (no body)
|
||||
* - OpenRouter (all backends): "maximum context length is X tokens"
|
||||
* - llama.cpp: "exceeds the available context size"
|
||||
* - LM Studio: "greater than the context length"
|
||||
|
|
@ -85,7 +87,7 @@ export function isContextOverflow(message: AssistantMessage, contextWindow?: num
|
|||
return true;
|
||||
}
|
||||
|
||||
// Cerebras returns 400/413 with no body - check for status code pattern
|
||||
// Cerebras and Mistral return 400/413 with no body - check for status code pattern
|
||||
if (/^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message.errorMessage)) {
|
||||
return true;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue