Skip to content

feat: add native tools support for OpenAI-compatible providers #9676

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
daniel-lxs merged 2 commits into from
Nov 28, 2025
+36 −2
Merged

feat: add native tools support for OpenAI-compatible providers #9676

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d7f36b2
feat: add native tools support for OpenAI-compatible providers
daniel-lxs Nov 28, 2025
bc678ee
Delete .changeset/native-tools-openai-compatible.md
mrubens Nov 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions packages/types/src/providers/featherless.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ export const featherlessModels = {
contextWindow: 32678,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0,
outputPrice: 0,
description: "Kimi K2 Instruct model.",
Expand All @@ -49,6 +50,7 @@ export const featherlessModels = {
contextWindow: 32678,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0,
outputPrice: 0,
description: "Qwen3 Coder 480B A35B Instruct model.",
Expand Down
13 changes: 13 additions & 0 deletions packages/types/src/providers/fireworks.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ export const fireworksModels = {
contextWindow: 262144,
supportsImages: false,
supportsPromptCache: true,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheReadsPrice: 0.15,
Expand All @@ -34,6 +35,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 2.5,
description:
Expand All @@ -44,6 +46,7 @@ export const fireworksModels = {
contextWindow: 204800,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.3,
outputPrice: 1.2,
description:
Expand All @@ -54,6 +57,7 @@ export const fireworksModels = {
contextWindow: 256000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.22,
outputPrice: 0.88,
description: "Latest Qwen3 thinking model, competitive against the best closed source models in Jul 2025.",
Expand All @@ -63,6 +67,7 @@ export const fireworksModels = {
contextWindow: 256000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.45,
outputPrice: 1.8,
description: "Qwen3's most agentic code model to date.",
Expand All @@ -72,6 +77,7 @@ export const fireworksModels = {
contextWindow: 160000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 3,
outputPrice: 8,
description:
Expand All @@ -82,6 +88,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.9,
outputPrice: 0.9,
description:
Expand All @@ -92,6 +99,7 @@ export const fireworksModels = {
contextWindow: 163840,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.56,
outputPrice: 1.68,
description:
Expand All @@ -102,6 +110,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.55,
outputPrice: 2.19,
description:
Expand All @@ -112,6 +121,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.55,
outputPrice: 2.19,
description:
Expand All @@ -122,6 +132,7 @@ export const fireworksModels = {
contextWindow: 198000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.55,
outputPrice: 2.19,
description:
Expand All @@ -132,6 +143,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.07,
outputPrice: 0.3,
description:
Expand All @@ -142,6 +154,7 @@ export const fireworksModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.15,
outputPrice: 0.6,
description:
Expand Down
4 changes: 4 additions & 0 deletions packages/types/src/providers/io-intelligence.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,27 +18,31 @@ export const ioIntelligenceModels = {
contextWindow: 128000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
description: "DeepSeek R1 reasoning model",
},
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
maxTokens: 8192,
contextWindow: 430000,
supportsImages: true,
supportsPromptCache: false,
supportsNativeTools: true,
description: "Llama 4 Maverick 17B model",
},
"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar": {
maxTokens: 8192,
contextWindow: 106000,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
description: "Qwen3 Coder 480B specialized for coding",
},
"openai/gpt-oss-120b": {
maxTokens: 8192,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
description: "OpenAI GPT-OSS 120B model",
},
} as const satisfies Record<string, ModelInfo>
8 changes: 8 additions & 0 deletions packages/types/src/providers/sambanova.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ export const sambaNovaModels = {
contextWindow: 16384,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.1,
outputPrice: 0.2,
description: "Meta Llama 3.1 8B Instruct model with 16K context window.",
Expand All @@ -30,6 +31,7 @@ export const sambaNovaModels = {
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.6,
outputPrice: 1.2,
description: "Meta Llama 3.3 70B Instruct model with 128K context window.",
Expand All @@ -40,6 +42,7 @@ export const sambaNovaModels = {
supportsImages: false,
supportsPromptCache: false,
supportsReasoningBudget: true,
supportsNativeTools: true,
inputPrice: 5.0,
outputPrice: 7.0,
description: "DeepSeek R1 reasoning model with 32K context window.",
Expand All @@ -49,6 +52,7 @@ export const sambaNovaModels = {
contextWindow: 32768,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 3.0,
outputPrice: 4.5,
description: "DeepSeek V3 model with 32K context window.",
Expand All @@ -58,6 +62,7 @@ export const sambaNovaModels = {
contextWindow: 32768,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 3.0,
outputPrice: 4.5,
description: "DeepSeek V3.1 model with 32K context window.",
Expand All @@ -76,6 +81,7 @@ export const sambaNovaModels = {
contextWindow: 131072,
supportsImages: true,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.63,
outputPrice: 1.8,
description: "Meta Llama 4 Maverick 17B 128E Instruct model with 128K context window.",
Expand All @@ -94,6 +100,7 @@ export const sambaNovaModels = {
contextWindow: 8192,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.4,
outputPrice: 0.8,
description: "Alibaba Qwen 3 32B model with 8K context window.",
Expand All @@ -103,6 +110,7 @@ export const sambaNovaModels = {
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
inputPrice: 0.22,
outputPrice: 0.59,
description: "OpenAI gpt oss 120b model with 128k context window.",
Expand Down
2 changes: 2 additions & 0 deletions src/api/providers/__tests__/io-intelligence.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,7 @@ describe("IOIntelligenceHandler", () => {
description: "Llama 4 Maverick 17B model",
supportsImages: true,
supportsPromptCache: false,
supportsNativeTools: true,
})
})

Expand All @@ -271,6 +272,7 @@ describe("IOIntelligenceHandler", () => {
description: "Llama 4 Maverick 17B model",
supportsImages: true,
supportsPromptCache: false,
supportsNativeTools: true,
})
})

Expand Down
9 changes: 7 additions & 2 deletions src/api/providers/featherless.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ import { convertToR1Format } from "../transform/r1-format"
import { convertToOpenAiMessages } from "../transform/openai-format"
import { ApiStream } from "../transform/stream"

import type { ApiHandlerCreateMessageMetadata } from "../index"
import { BaseOpenAiCompatibleProvider } from "./base-openai-compatible-provider"

export class FeatherlessHandler extends BaseOpenAiCompatibleProvider<FeatherlessModelId> {
Expand Down Expand Up @@ -49,7 +50,11 @@ export class FeatherlessHandler extends BaseOpenAiCompatibleProvider<Featherless
}
}

override async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
override async *createMessage(
systemPrompt: string,
messages: Anthropic.Messages.MessageParam[],
metadata?: ApiHandlerCreateMessageMetadata,
): ApiStream {
const model = this.getModel()

if (model.id.includes("DeepSeek-R1")) {
Expand Down Expand Up @@ -90,7 +95,7 @@ export class FeatherlessHandler extends BaseOpenAiCompatibleProvider<Featherless
yield processedChunk
}
} else {
yield* super.createMessage(systemPrompt, messages)
yield* super.createMessage(systemPrompt, messages, metadata)
}
}

Expand Down
Loading