mirror of
https://github.com/RooVetGit/Roo-Code.git
synced 2026-08-28 05:27:24 +00:00
chore: remove XML tool calling support (#10841)
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com> Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
This commit is contained in:
Hannes Rudolph
GitHub
parent
e356d058e9
commit
8de9337e63
270 changed files with 1867 additions and 14984 deletions
|
|
@ -56,7 +56,6 @@ import { useRooCodeCloudModels } from "@/hooks/use-roo-code-cloud-models"
|
|||
|
||||
import {
|
||||
Button,
|
||||
Checkbox,
|
||||
FormControl,
|
||||
FormField,
|
||||
FormItem,
|
||||
|
|
@ -111,7 +110,6 @@ export function NewRun() {
|
|||
|
||||
const [provider, setModelSource] = useState<"roo" | "openrouter" | "other">("other")
|
||||
const [executionMethod, setExecutionMethod] = useState<ExecutionMethod>("vscode")
|
||||
const [useNativeToolProtocol, setUseNativeToolProtocol] = useState(true)
|
||||
const [commandExecutionTimeout, setCommandExecutionTimeout] = useState(20)
|
||||
const [terminalShellIntegrationTimeout, setTerminalShellIntegrationTimeout] = useState(30) // seconds
|
||||
|
||||
|
|
@ -464,7 +462,6 @@ export function NewRun() {
|
|||
...(runValues.settings || {}),
|
||||
apiProvider: "openrouter",
|
||||
openRouterModelId: selection.model,
|
||||
toolProtocol: useNativeToolProtocol ? "native" : "xml",
|
||||
commandExecutionTimeout,
|
||||
terminalShellIntegrationTimeout: terminalShellIntegrationTimeout * 1000,
|
||||
}
|
||||
|
|
@ -474,7 +471,6 @@ export function NewRun() {
|
|||
...(runValues.settings || {}),
|
||||
apiProvider: "roo",
|
||||
apiModelId: selection.model,
|
||||
toolProtocol: useNativeToolProtocol ? "native" : "xml",
|
||||
commandExecutionTimeout,
|
||||
terminalShellIntegrationTimeout: terminalShellIntegrationTimeout * 1000,
|
||||
}
|
||||
|
|
@ -485,7 +481,6 @@ export function NewRun() {
|
|||
...EVALS_SETTINGS,
|
||||
...providerSettings,
|
||||
...importedSettings.globalSettings,
|
||||
toolProtocol: useNativeToolProtocol ? "native" : "xml",
|
||||
commandExecutionTimeout,
|
||||
terminalShellIntegrationTimeout: terminalShellIntegrationTimeout * 1000,
|
||||
}
|
||||
|
|
@ -512,7 +507,6 @@ export function NewRun() {
|
|||
configSelections,
|
||||
importedSettings,
|
||||
router,
|
||||
useNativeToolProtocol,
|
||||
commandExecutionTimeout,
|
||||
terminalShellIntegrationTimeout,
|
||||
],
|
||||
|
|
@ -688,26 +682,6 @@ export function NewRun() {
|
|||
</div>
|
||||
)}
|
||||
|
||||
<div className="mt-4 p-4 rounded-md bg-muted/30 border border-border space-y-3">
|
||||
<Label className="text-sm font-medium text-muted-foreground">
|
||||
Tool Protocol Options
|
||||
</Label>
|
||||
<div className="flex flex-col gap-2.5 pl-1">
|
||||
<label
|
||||
htmlFor="native-other"
|
||||
className="flex items-center gap-2 cursor-pointer">
|
||||
<Checkbox
|
||||
id="native-other"
|
||||
checked={useNativeToolProtocol}
|
||||
onCheckedChange={(checked: boolean) =>
|
||||
setUseNativeToolProtocol(checked)
|
||||
}
|
||||
/>
|
||||
<span className="text-sm">Use Native Tool Calls</span>
|
||||
</label>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{settings && (
|
||||
<SettingsDiff defaultSettings={EVALS_SETTINGS} customSettings={settings} />
|
||||
)}
|
||||
|
|
@ -792,26 +766,6 @@ export function NewRun() {
|
|||
</div>
|
||||
))}
|
||||
</div>
|
||||
|
||||
<div className="mt-4 p-4 rounded-md bg-muted/30 border border-border space-y-3">
|
||||
<Label className="text-sm font-medium text-muted-foreground">
|
||||
Tool Protocol Options
|
||||
</Label>
|
||||
<div className="flex flex-col gap-2.5 pl-1">
|
||||
<label
|
||||
htmlFor="native"
|
||||
className="flex items-center gap-2 cursor-pointer">
|
||||
<Checkbox
|
||||
id="native"
|
||||
checked={useNativeToolProtocol}
|
||||
onCheckedChange={(checked: boolean) =>
|
||||
setUseNativeToolProtocol(checked)
|
||||
}
|
||||
/>
|
||||
<span className="text-sm">Use Native Tool Calls</span>
|
||||
</label>
|
||||
</div>
|
||||
</div>
|
||||
</>
|
||||
)}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,129 +0,0 @@
|
|||
// Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for all fixtures combined 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## simple
|
||||
Description: Simple tool
|
||||
Parameters:
|
||||
- value: (required) The input value (type: string)
|
||||
Usage:
|
||||
<simple>
|
||||
<value>value value here</value>
|
||||
</simple>
|
||||
|
||||
## cached
|
||||
Description: Cached tool
|
||||
Parameters:
|
||||
Usage:
|
||||
<cached>
|
||||
</cached>
|
||||
|
||||
## legacy
|
||||
Description: Legacy tool using args
|
||||
Parameters:
|
||||
- input: (required) The input string (type: string)
|
||||
Usage:
|
||||
<legacy>
|
||||
<input>input value here</input>
|
||||
</legacy>
|
||||
|
||||
## multi_toolA
|
||||
Description: Tool A
|
||||
Parameters:
|
||||
Usage:
|
||||
<multi_toolA>
|
||||
</multi_toolA>
|
||||
|
||||
## multi_toolB
|
||||
Description: Tool B
|
||||
Parameters:
|
||||
Usage:
|
||||
<multi_toolB>
|
||||
</multi_toolB>
|
||||
|
||||
## mixed_validTool
|
||||
Description: Valid
|
||||
Parameters:
|
||||
Usage:
|
||||
<mixed_validTool>
|
||||
</mixed_validTool>"
|
||||
`;
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for cached tool 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## cached
|
||||
Description: Cached tool
|
||||
Parameters:
|
||||
Usage:
|
||||
<cached>
|
||||
</cached>"
|
||||
`;
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for legacy tool (using args) 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## legacy
|
||||
Description: Legacy tool using args
|
||||
Parameters:
|
||||
- input: (required) The input string (type: string)
|
||||
Usage:
|
||||
<legacy>
|
||||
<input>input value here</input>
|
||||
</legacy>"
|
||||
`;
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for mixed export tool 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## mixed_validTool
|
||||
Description: Valid
|
||||
Parameters:
|
||||
Usage:
|
||||
<mixed_validTool>
|
||||
</mixed_validTool>"
|
||||
`;
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for multi export tools 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## multi_toolA
|
||||
Description: Tool A
|
||||
Parameters:
|
||||
Usage:
|
||||
<multi_toolA>
|
||||
</multi_toolA>
|
||||
|
||||
## multi_toolB
|
||||
Description: Tool B
|
||||
Parameters:
|
||||
Usage:
|
||||
<multi_toolB>
|
||||
</multi_toolB>"
|
||||
`;
|
||||
|
||||
exports[`XML Protocol snapshots > should generate correct XML description for simple tool 1`] = `
|
||||
"# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
## simple
|
||||
Description: Simple tool
|
||||
Parameters:
|
||||
- value: (required) The input value (type: string)
|
||||
Usage:
|
||||
<simple>
|
||||
<value>value value here</value>
|
||||
</simple>"
|
||||
`;
|
||||
|
|
@ -1,192 +0,0 @@
|
|||
// pnpm --filter @roo-code/core test src/custom-tools/__tests__/format-xml.spec.ts
|
||||
|
||||
import { type SerializedCustomToolDefinition, parametersSchema as z, defineCustomTool } from "@roo-code/types"
|
||||
|
||||
import { serializeCustomTool, serializeCustomTools } from "../serialize.js"
|
||||
import { formatXml } from "../format-xml.js"
|
||||
|
||||
import simpleTool from "./fixtures/simple.js"
|
||||
import cachedTool from "./fixtures/cached.js"
|
||||
import legacyTool from "./fixtures/legacy.js"
|
||||
import { toolA, toolB } from "./fixtures/multi.js"
|
||||
import { validTool as mixedValidTool } from "./fixtures/mixed.js"
|
||||
|
||||
const fixtureTools = {
|
||||
simple: simpleTool,
|
||||
cached: cachedTool,
|
||||
legacy: legacyTool,
|
||||
multi_toolA: toolA,
|
||||
multi_toolB: toolB,
|
||||
mixed_validTool: mixedValidTool,
|
||||
}
|
||||
|
||||
describe("formatXml", () => {
|
||||
it("should return empty string for empty tools array", () => {
|
||||
expect(formatXml([])).toBe("")
|
||||
})
|
||||
|
||||
it("should throw for undefined tools", () => {
|
||||
expect(() => formatXml(undefined as unknown as SerializedCustomToolDefinition[])).toThrow()
|
||||
})
|
||||
|
||||
it("should generate description for a single tool without args", () => {
|
||||
const tool = defineCustomTool({
|
||||
name: "my_tool",
|
||||
description: "A simple tool that does something",
|
||||
async execute() {
|
||||
return "done"
|
||||
},
|
||||
})
|
||||
|
||||
const serialized = serializeCustomTool(tool)
|
||||
const result = formatXml([serialized])
|
||||
|
||||
expect(result).toContain("# Custom Tools")
|
||||
expect(result).toContain("## my_tool")
|
||||
expect(result).toContain("Description: A simple tool that does something")
|
||||
expect(result).toContain("Parameters: None")
|
||||
expect(result).toContain("<my_tool>")
|
||||
expect(result).toContain("</my_tool>")
|
||||
})
|
||||
|
||||
it("should generate description for a tool with required args", () => {
|
||||
const tool = defineCustomTool({
|
||||
name: "greeter",
|
||||
description: "Greets a person by name",
|
||||
parameters: z.object({
|
||||
name: z.string().describe("The name of the person to greet"),
|
||||
}),
|
||||
async execute({ name }) {
|
||||
return `Hello, ${name}!`
|
||||
},
|
||||
})
|
||||
|
||||
const serialized = serializeCustomTool(tool)
|
||||
const result = formatXml([serialized])
|
||||
|
||||
expect(result).toContain("## greeter")
|
||||
expect(result).toContain("Description: Greets a person by name")
|
||||
expect(result).toContain("Parameters:")
|
||||
expect(result).toContain("- name: (required) The name of the person to greet (type: string)")
|
||||
expect(result).toContain("<greeter>")
|
||||
expect(result).toContain("<name>name value here</name>")
|
||||
expect(result).toContain("</greeter>")
|
||||
})
|
||||
|
||||
it("should generate description for a tool with optional args", () => {
|
||||
const tool = defineCustomTool({
|
||||
name: "configurable_tool",
|
||||
description: "A tool with optional configuration",
|
||||
parameters: z.object({
|
||||
input: z.string().describe("The input to process"),
|
||||
format: z.string().optional().describe("Output format"),
|
||||
}),
|
||||
async execute({ input, format }) {
|
||||
return format ? `${input} (${format})` : input
|
||||
},
|
||||
})
|
||||
|
||||
const serialized = serializeCustomTool(tool)
|
||||
const result = formatXml([serialized])
|
||||
|
||||
expect(result).toContain("- input: (required) The input to process (type: string)")
|
||||
expect(result).toContain("- format: (optional) Output format (type: string)")
|
||||
expect(result).toContain("<input>input value here</input>")
|
||||
expect(result).toContain("<format>optional format value</format>")
|
||||
})
|
||||
|
||||
it("should generate descriptions for multiple tools", () => {
|
||||
const tools = [
|
||||
defineCustomTool({
|
||||
name: "tool_a",
|
||||
description: "First tool",
|
||||
async execute() {
|
||||
return "a"
|
||||
},
|
||||
}),
|
||||
defineCustomTool({
|
||||
name: "tool_b",
|
||||
description: "Second tool",
|
||||
parameters: z.object({
|
||||
value: z.number().describe("A numeric value"),
|
||||
}),
|
||||
async execute() {
|
||||
return "b"
|
||||
},
|
||||
}),
|
||||
]
|
||||
|
||||
const serialized = serializeCustomTools(tools)
|
||||
const result = formatXml(serialized)
|
||||
|
||||
expect(result).toContain("## tool_a")
|
||||
expect(result).toContain("Description: First tool")
|
||||
expect(result).toContain("## tool_b")
|
||||
expect(result).toContain("Description: Second tool")
|
||||
expect(result).toContain("- value: (required) A numeric value (type: number)")
|
||||
})
|
||||
|
||||
it("should treat args in required array as required", () => {
|
||||
// Using a raw SerializedToolDefinition to test the required behavior.
|
||||
const tools: SerializedCustomToolDefinition[] = [
|
||||
{
|
||||
name: "test_tool",
|
||||
description: "Test tool",
|
||||
parameters: {
|
||||
type: "object",
|
||||
properties: {
|
||||
data: {
|
||||
type: "object",
|
||||
description: "Some data",
|
||||
},
|
||||
},
|
||||
required: ["data"],
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
const result = formatXml(tools)
|
||||
|
||||
expect(result).toContain("- data: (required) Some data (type: object)")
|
||||
expect(result).toContain("<data>data value here</data>")
|
||||
})
|
||||
})
|
||||
|
||||
describe("XML Protocol snapshots", () => {
|
||||
it("should generate correct XML description for simple tool", () => {
|
||||
const serialized = serializeCustomTool(fixtureTools.simple)
|
||||
const result = formatXml([serialized])
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
|
||||
it("should generate correct XML description for cached tool", () => {
|
||||
const serialized = serializeCustomTool(fixtureTools.cached)
|
||||
const result = formatXml([serialized])
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
|
||||
it("should generate correct XML description for legacy tool (using args)", () => {
|
||||
const serialized = serializeCustomTool(fixtureTools.legacy)
|
||||
const result = formatXml([serialized])
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
|
||||
it("should generate correct XML description for multi export tools", () => {
|
||||
const serializedA = serializeCustomTool(fixtureTools.multi_toolA)
|
||||
const serializedB = serializeCustomTool(fixtureTools.multi_toolB)
|
||||
const result = formatXml([serializedA, serializedB])
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
|
||||
it("should generate correct XML description for mixed export tool", () => {
|
||||
const serialized = serializeCustomTool(fixtureTools.mixed_validTool)
|
||||
const result = formatXml([serialized])
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
|
||||
it("should generate correct XML description for all fixtures combined", () => {
|
||||
const allSerialized = Object.values(fixtureTools).map(serializeCustomTool)
|
||||
const result = formatXml(allSerialized)
|
||||
expect(result).toMatchSnapshot()
|
||||
})
|
||||
})
|
||||
|
|
@ -1,89 +0,0 @@
|
|||
import type { SerializedCustomToolDefinition, SerializedCustomToolParameters } from "@roo-code/types"
|
||||
|
||||
/**
|
||||
* Extract the type string from a parameter schema.
|
||||
* Handles both direct `type` property and `anyOf` schemas (used for nullable types).
|
||||
*/
|
||||
function getParameterType(parameter: SerializedCustomToolParameters): string {
|
||||
// Direct type property
|
||||
if (parameter.type) {
|
||||
return String(parameter.type)
|
||||
}
|
||||
|
||||
// Handle anyOf schema (used for nullable types like `string | null`)
|
||||
if (parameter.anyOf && Array.isArray(parameter.anyOf)) {
|
||||
const types = parameter.anyOf
|
||||
.map((schema) => (typeof schema === "object" && schema.type ? String(schema.type) : null))
|
||||
.filter((t): t is string => t !== null && t !== "null")
|
||||
|
||||
if (types.length > 0) {
|
||||
return types.join(" | ")
|
||||
}
|
||||
}
|
||||
|
||||
return "unknown"
|
||||
}
|
||||
|
||||
function getParameterDescription(name: string, parameter: SerializedCustomToolParameters, required: string[]): string {
|
||||
const requiredText = required.includes(name) ? "(required)" : "(optional)"
|
||||
const typeText = getParameterType(parameter)
|
||||
return `- ${name}: ${requiredText} ${parameter.description ?? ""} (type: ${typeText})`
|
||||
}
|
||||
|
||||
function getUsage(tool: SerializedCustomToolDefinition): string {
|
||||
const lines: string[] = [`<${tool.name}>`]
|
||||
|
||||
if (tool.parameters) {
|
||||
const required = tool.parameters.required ?? []
|
||||
|
||||
for (const [argName, _argType] of Object.entries(tool.parameters.properties ?? {})) {
|
||||
const placeholder = required.includes(argName) ? `${argName} value here` : `optional ${argName} value`
|
||||
lines.push(`<${argName}>${placeholder}</${argName}>`)
|
||||
}
|
||||
}
|
||||
|
||||
lines.push(`</${tool.name}>`)
|
||||
return lines.join("\n")
|
||||
}
|
||||
|
||||
function getDescription(tool: SerializedCustomToolDefinition): string {
|
||||
const parts: string[] = []
|
||||
|
||||
parts.push(`## ${tool.name}`)
|
||||
parts.push(`Description: ${tool.description}`)
|
||||
|
||||
if (tool.parameters?.properties) {
|
||||
const required = tool.parameters?.required ?? []
|
||||
parts.push("Parameters:")
|
||||
|
||||
for (const [name, parameter] of Object.entries(tool.parameters.properties)) {
|
||||
// What should we do with `boolean` values for `parameter`?
|
||||
if (typeof parameter !== "object") {
|
||||
continue
|
||||
}
|
||||
|
||||
parts.push(getParameterDescription(name, parameter, required))
|
||||
}
|
||||
} else {
|
||||
parts.push("Parameters: None")
|
||||
}
|
||||
|
||||
parts.push("Usage:")
|
||||
parts.push(getUsage(tool))
|
||||
|
||||
return parts.join("\n")
|
||||
}
|
||||
|
||||
export function formatXml(tools: SerializedCustomToolDefinition[]): string {
|
||||
if (tools.length === 0) {
|
||||
return ""
|
||||
}
|
||||
|
||||
const descriptions = tools.map((tool) => getDescription(tool))
|
||||
|
||||
return `# Custom Tools
|
||||
|
||||
The following custom tools are available for this mode. Use them in the same way as built-in tools.
|
||||
|
||||
${descriptions.join("\n\n")}`
|
||||
}
|
||||
|
|
@ -1,4 +1,3 @@
|
|||
export * from "./custom-tool-registry.js"
|
||||
export * from "./serialize.js"
|
||||
export * from "./format-xml.js"
|
||||
export * from "./format-native.js"
|
||||
|
|
|
|||
|
|
@ -111,8 +111,8 @@ export class TelemetryService {
|
|||
this.captureEvent(TelemetryEventName.MODE_SWITCH, { taskId, newMode })
|
||||
}
|
||||
|
||||
public captureToolUsage(taskId: string, tool: string, toolProtocol: string): void {
|
||||
this.captureEvent(TelemetryEventName.TOOL_USED, { taskId, tool, toolProtocol })
|
||||
public captureToolUsage(taskId: string, tool: string): void {
|
||||
this.captureEvent(TelemetryEventName.TOOL_USED, { taskId, tool })
|
||||
}
|
||||
|
||||
public captureCheckpointCreated(taskId: string): void {
|
||||
|
|
|
|||
|
|
@ -19,16 +19,6 @@ export const historyItemSchema = z.object({
|
|||
size: z.number().optional(),
|
||||
workspace: z.string().optional(),
|
||||
mode: z.string().optional(),
|
||||
/**
|
||||
* The tool protocol used by this task. Once a task uses tools with a specific
|
||||
* protocol (XML or Native), it is permanently locked to that protocol.
|
||||
*
|
||||
* - "xml": Tool calls are parsed from XML text (no tool IDs)
|
||||
* - "native": Tool calls come as tool_call chunks with IDs
|
||||
*
|
||||
* This ensures task resumption works correctly even when NTC settings change.
|
||||
*/
|
||||
toolProtocol: z.enum(["xml", "native"]).optional(),
|
||||
apiConfigName: z.string().optional(), // Provider profile name for sticky profile feature
|
||||
status: z.enum(["active", "completed", "delegated"]).optional(),
|
||||
delegatedToId: z.string().optional(), // Last child this parent delegated to
|
||||
|
|
|
|||
|
|
@ -110,10 +110,6 @@ export const modelInfoSchema = z.object({
|
|||
isStealthModel: z.boolean().optional(),
|
||||
// Flag to indicate if the model is free (no cost)
|
||||
isFree: z.boolean().optional(),
|
||||
// Flag to indicate if the model supports native tool calling (OpenAI-style function calling)
|
||||
supportsNativeTools: z.boolean().optional(),
|
||||
// Default tool protocol preferred by this model (if not specified, falls back to capability/provider defaults)
|
||||
defaultToolProtocol: z.enum(["xml", "native"]).optional(),
|
||||
// Exclude specific native tools from being available (only applies to native protocol)
|
||||
// These tools will be removed from the set of tools available to the model
|
||||
excludedTools: z.array(z.string()).optional(),
|
||||
|
|
|
|||
|
|
@ -185,9 +185,6 @@ const baseProviderSettingsSchema = z.object({
|
|||
|
||||
// Model verbosity.
|
||||
verbosity: verbosityLevelsSchema.optional(),
|
||||
|
||||
// Tool protocol override for this profile.
|
||||
toolProtocol: z.enum(["xml", "native"]).optional(),
|
||||
})
|
||||
|
||||
// Several of the providers share common model config properties.
|
||||
|
|
|
|||
|
|
@ -11,8 +11,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000, // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens (≤200K context)
|
||||
outputPrice: 15.0, // $15 per million output tokens (≤200K context)
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -34,8 +32,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000, // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens (≤200K context)
|
||||
outputPrice: 15.0, // $15 per million output tokens (≤200K context)
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -57,8 +53,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 5.0, // $5 per million input tokens
|
||||
outputPrice: 25.0, // $25 per million output tokens
|
||||
cacheWritesPrice: 6.25, // $6.25 per million tokens
|
||||
|
|
@ -70,8 +64,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0, // $15 per million input tokens
|
||||
outputPrice: 75.0, // $75 per million output tokens
|
||||
cacheWritesPrice: 18.75, // $18.75 per million tokens
|
||||
|
|
@ -83,8 +75,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0, // $15 per million input tokens
|
||||
outputPrice: 75.0, // $75 per million output tokens
|
||||
cacheWritesPrice: 18.75, // $18.75 per million tokens
|
||||
|
|
@ -96,8 +86,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens
|
||||
outputPrice: 15.0, // $15 per million output tokens
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -110,8 +98,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens
|
||||
outputPrice: 15.0, // $15 per million output tokens
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -122,8 +108,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens
|
||||
outputPrice: 15.0, // $15 per million output tokens
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -134,8 +118,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 5.0,
|
||||
cacheWritesPrice: 1.25,
|
||||
|
|
@ -146,8 +128,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -158,8 +138,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.25,
|
||||
outputPrice: 1.25,
|
||||
cacheWritesPrice: 0.3,
|
||||
|
|
@ -170,8 +148,6 @@ export const anthropicModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 5.0,
|
||||
cacheWritesPrice: 1.25,
|
||||
|
|
|
|||
|
|
@ -9,7 +9,6 @@ export const basetenModels = {
|
|||
contextWindow: 262_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -21,7 +20,6 @@ export const basetenModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.2,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -33,7 +31,6 @@ export const basetenModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.55,
|
||||
outputPrice: 5.95,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -45,7 +42,6 @@ export const basetenModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.55,
|
||||
outputPrice: 5.95,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -57,7 +53,6 @@ export const basetenModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.77,
|
||||
outputPrice: 0.77,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -69,7 +64,6 @@ export const basetenModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.5,
|
||||
outputPrice: 1.5,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -82,7 +76,6 @@ export const basetenModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 0.45,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -95,7 +88,6 @@ export const basetenModels = {
|
|||
contextWindow: 128_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -107,7 +99,6 @@ export const basetenModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.22,
|
||||
outputPrice: 0.8,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -119,7 +110,6 @@ export const basetenModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.38,
|
||||
outputPrice: 1.53,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -131,7 +121,6 @@ export const basetenModels = {
|
|||
contextWindow: 262_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
|
|||
|
|
@ -19,8 +19,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -34,7 +32,6 @@ export const bedrockModels = {
|
|||
contextWindow: 300_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.8,
|
||||
outputPrice: 3.2,
|
||||
cacheWritesPrice: 0.8, // per million tokens
|
||||
|
|
@ -48,7 +45,6 @@ export const bedrockModels = {
|
|||
contextWindow: 300_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 4.0,
|
||||
cacheWritesPrice: 1.0, // per million tokens
|
||||
|
|
@ -60,7 +56,6 @@ export const bedrockModels = {
|
|||
contextWindow: 300_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.06,
|
||||
outputPrice: 0.24,
|
||||
cacheWritesPrice: 0.06, // per million tokens
|
||||
|
|
@ -74,7 +69,6 @@ export const bedrockModels = {
|
|||
contextWindow: 1_000_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.33,
|
||||
outputPrice: 2.75,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -89,7 +83,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.035,
|
||||
outputPrice: 0.14,
|
||||
cacheWritesPrice: 0.035, // per million tokens
|
||||
|
|
@ -104,8 +97,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -120,8 +111,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -136,8 +125,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 5.0,
|
||||
outputPrice: 25.0,
|
||||
cacheWritesPrice: 6.25,
|
||||
|
|
@ -152,8 +139,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -168,8 +153,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -183,8 +166,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -198,8 +179,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.8,
|
||||
outputPrice: 4.0,
|
||||
cacheWritesPrice: 1.0,
|
||||
|
|
@ -214,8 +193,6 @@ export const bedrockModels = {
|
|||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 5.0,
|
||||
cacheWritesPrice: 1.25, // 5m cache writes
|
||||
|
|
@ -229,8 +206,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
},
|
||||
|
|
@ -239,8 +214,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
},
|
||||
|
|
@ -249,8 +222,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
},
|
||||
|
|
@ -259,8 +230,6 @@ export const bedrockModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.25,
|
||||
outputPrice: 1.25,
|
||||
},
|
||||
|
|
@ -269,7 +238,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 1.35,
|
||||
outputPrice: 5.4,
|
||||
},
|
||||
|
|
@ -278,7 +246,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.5,
|
||||
outputPrice: 1.5,
|
||||
description: "GPT-OSS 20B - Optimized for low latency and local/specialized use cases",
|
||||
|
|
@ -288,7 +255,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.0,
|
||||
outputPrice: 6.0,
|
||||
description: "GPT-OSS 120B - Production-ready, general-purpose, high-reasoning model",
|
||||
|
|
@ -298,7 +264,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.72,
|
||||
outputPrice: 0.72,
|
||||
description: "Llama 3.3 Instruct (70B)",
|
||||
|
|
@ -308,7 +273,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.72,
|
||||
outputPrice: 0.72,
|
||||
description: "Llama 3.2 Instruct (90B)",
|
||||
|
|
@ -318,7 +282,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.16,
|
||||
outputPrice: 0.16,
|
||||
description: "Llama 3.2 Instruct (11B)",
|
||||
|
|
@ -328,7 +291,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.15,
|
||||
description: "Llama 3.2 Instruct (3B)",
|
||||
|
|
@ -338,7 +300,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.1,
|
||||
description: "Llama 3.2 Instruct (1B)",
|
||||
|
|
@ -348,7 +309,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.4,
|
||||
outputPrice: 2.4,
|
||||
description: "Llama 3.1 Instruct (405B)",
|
||||
|
|
@ -358,7 +318,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.72,
|
||||
outputPrice: 0.72,
|
||||
description: "Llama 3.1 Instruct (70B)",
|
||||
|
|
@ -368,7 +327,6 @@ export const bedrockModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.9,
|
||||
outputPrice: 0.9,
|
||||
description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)",
|
||||
|
|
@ -378,7 +336,6 @@ export const bedrockModels = {
|
|||
contextWindow: 8_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.22,
|
||||
outputPrice: 0.22,
|
||||
description: "Llama 3.1 Instruct (8B)",
|
||||
|
|
@ -388,7 +345,6 @@ export const bedrockModels = {
|
|||
contextWindow: 8_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.65,
|
||||
outputPrice: 3.5,
|
||||
},
|
||||
|
|
@ -397,7 +353,6 @@ export const bedrockModels = {
|
|||
contextWindow: 4_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 0.6,
|
||||
},
|
||||
|
|
@ -406,7 +361,6 @@ export const bedrockModels = {
|
|||
contextWindow: 8_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.2,
|
||||
description: "Amazon Titan Text Lite",
|
||||
|
|
@ -416,7 +370,6 @@ export const bedrockModels = {
|
|||
contextWindow: 8_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.6,
|
||||
description: "Amazon Titan Text Express",
|
||||
|
|
@ -426,8 +379,6 @@ export const bedrockModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
preserveReasoning: true,
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
|
|
@ -438,8 +389,6 @@ export const bedrockModels = {
|
|||
contextWindow: 196_608,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
preserveReasoning: true,
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 1.2,
|
||||
|
|
@ -450,8 +399,6 @@ export const bedrockModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 1.2,
|
||||
description: "Qwen3 Next 80B (MoE model with 3B active parameters)",
|
||||
|
|
@ -461,8 +408,6 @@ export const bedrockModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.45,
|
||||
outputPrice: 1.8,
|
||||
description: "Qwen3 Coder 480B (MoE model with 35B active parameters)",
|
||||
|
|
|
|||
|
|
@ -11,8 +11,6 @@ export const cerebrasModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -23,8 +21,6 @@ export const cerebrasModels = {
|
|||
contextWindow: 64000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Intelligent model with ~1400 tokens/s",
|
||||
|
|
@ -34,8 +30,6 @@ export const cerebrasModels = {
|
|||
contextWindow: 64000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Powerful model with ~2600 tokens/s",
|
||||
|
|
@ -45,8 +39,6 @@ export const cerebrasModels = {
|
|||
contextWindow: 64000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "SOTA coding performance with ~2500 tokens/s",
|
||||
|
|
@ -56,8 +48,6 @@ export const cerebrasModels = {
|
|||
contextWindow: 64000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
|
|||
|
|
@ -51,8 +51,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek R1 0528 model.",
|
||||
|
|
@ -62,8 +60,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek R1 model.",
|
||||
|
|
@ -73,8 +69,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek V3 model.",
|
||||
|
|
@ -84,8 +78,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek V3.1 model.",
|
||||
|
|
@ -95,8 +87,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.23,
|
||||
outputPrice: 0.9,
|
||||
description:
|
||||
|
|
@ -107,8 +97,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 3.0,
|
||||
description:
|
||||
|
|
@ -119,8 +107,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.25,
|
||||
outputPrice: 0.35,
|
||||
description:
|
||||
|
|
@ -131,8 +117,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072, // From Groq
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Unsloth Llama 3.3 70B Instruct model.",
|
||||
|
|
@ -142,8 +126,6 @@ export const chutesModels = {
|
|||
contextWindow: 512000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "ChutesAI Llama 4 Scout 17B Instruct model, 512K context.",
|
||||
|
|
@ -153,8 +135,6 @@ export const chutesModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Unsloth Mistral Nemo Instruct model.",
|
||||
|
|
@ -164,8 +144,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Unsloth Gemma 3 12B IT model.",
|
||||
|
|
@ -175,8 +153,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Nous DeepHermes 3 Llama 3 8B Preview model.",
|
||||
|
|
@ -186,8 +162,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Unsloth Gemma 3 4B IT model.",
|
||||
|
|
@ -197,8 +171,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Nvidia Llama 3.3 Nemotron Super 49B model.",
|
||||
|
|
@ -208,8 +180,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Nvidia Llama 3.1 Nemotron Ultra 253B model.",
|
||||
|
|
@ -219,8 +189,6 @@ export const chutesModels = {
|
|||
contextWindow: 256000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "ChutesAI Llama 4 Maverick 17B Instruct FP8 model.",
|
||||
|
|
@ -230,8 +198,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek V3 Base model.",
|
||||
|
|
@ -241,8 +207,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek R1 Zero model.",
|
||||
|
|
@ -252,8 +216,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek V3 (0324) model.",
|
||||
|
|
@ -263,8 +225,6 @@ export const chutesModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 235B A22B Instruct 2507 model with 262K context window.",
|
||||
|
|
@ -274,8 +234,6 @@ export const chutesModels = {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 235B A22B model.",
|
||||
|
|
@ -285,8 +243,6 @@ export const chutesModels = {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 32B model.",
|
||||
|
|
@ -296,8 +252,6 @@ export const chutesModels = {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 30B A3B model.",
|
||||
|
|
@ -307,8 +261,6 @@ export const chutesModels = {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 14B model.",
|
||||
|
|
@ -318,8 +270,6 @@ export const chutesModels = {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 8B model.",
|
||||
|
|
@ -329,8 +279,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Microsoft MAI-DS-R1 FP8 model.",
|
||||
|
|
@ -340,8 +288,6 @@ export const chutesModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "TNGTech DeepSeek R1T Chimera model.",
|
||||
|
|
@ -351,8 +297,6 @@ export const chutesModels = {
|
|||
contextWindow: 151329,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -363,8 +307,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -375,8 +317,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1,
|
||||
outputPrice: 3,
|
||||
description: "GLM-4.5-turbo model with 128K token context window, optimized for fast inference.",
|
||||
|
|
@ -386,8 +326,6 @@ export const chutesModels = {
|
|||
contextWindow: 202752,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -398,8 +336,6 @@ export const chutesModels = {
|
|||
contextWindow: 202752,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.15,
|
||||
outputPrice: 3.25,
|
||||
description: "GLM-4.6-turbo model with 200K-token context window, optimized for fast inference.",
|
||||
|
|
@ -409,8 +345,6 @@ export const chutesModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -421,8 +355,6 @@ export const chutesModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 Coder 480B A35B Instruct FP8 model, optimized for coding tasks.",
|
||||
|
|
@ -432,8 +364,6 @@ export const chutesModels = {
|
|||
contextWindow: 75000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1481,
|
||||
outputPrice: 0.5926,
|
||||
description: "Moonshot AI Kimi K2 Instruct model with 75k context window.",
|
||||
|
|
@ -443,8 +373,6 @@ export const chutesModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1999,
|
||||
outputPrice: 0.8001,
|
||||
description: "Moonshot AI Kimi K2 Instruct 0905 model with 256k context window.",
|
||||
|
|
@ -454,8 +382,6 @@ export const chutesModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.077968332,
|
||||
outputPrice: 0.31202496,
|
||||
description: "Qwen3 235B A22B Thinking 2507 model with 262K context window.",
|
||||
|
|
@ -465,8 +391,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -477,8 +401,6 @@ export const chutesModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description:
|
||||
|
|
@ -489,8 +411,6 @@ export const chutesModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.16,
|
||||
outputPrice: 0.65,
|
||||
description:
|
||||
|
|
|
|||
|
|
@ -49,8 +49,6 @@ export const claudeCodeModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsReasoningEffort: ["disable", "low", "medium", "high"],
|
||||
reasoningEffort: "medium",
|
||||
description: "Claude Haiku 4.5 - Fast and efficient with thinking",
|
||||
|
|
@ -60,8 +58,6 @@ export const claudeCodeModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsReasoningEffort: ["disable", "low", "medium", "high"],
|
||||
reasoningEffort: "medium",
|
||||
description: "Claude Sonnet 4.5 - Balanced performance with thinking",
|
||||
|
|
@ -71,8 +67,6 @@ export const claudeCodeModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsReasoningEffort: ["disable", "low", "medium", "high"],
|
||||
reasoningEffort: "medium",
|
||||
description: "Claude Opus 4.5 - Most capable with thinking",
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ export const deepInfraDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 1.2,
|
||||
description: "Qwen 3 Coder 480B A35B Instruct Turbo model, 256K context.",
|
||||
|
|
|
|||
|
|
@ -14,8 +14,6 @@ export const deepSeekModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.28, // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
||||
outputPrice: 0.42, // $0.42 per million tokens - Updated Dec 9, 2025
|
||||
cacheWritesPrice: 0.28, // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
||||
|
|
@ -27,8 +25,6 @@ export const deepSeekModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
preserveReasoning: true,
|
||||
inputPrice: 0.28, // $0.28 per million tokens (cache miss) - Updated Dec 9, 2025
|
||||
outputPrice: 0.42, // $0.42 per million tokens - Updated Dec 9, 2025
|
||||
|
|
|
|||
|
|
@ -8,8 +8,6 @@ export const doubaoModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.0001, // $0.0001 per million tokens (cache miss)
|
||||
outputPrice: 0.0004, // $0.0004 per million tokens
|
||||
cacheWritesPrice: 0.0001, // $0.0001 per million tokens (cache miss)
|
||||
|
|
@ -21,8 +19,6 @@ export const doubaoModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.0002, // $0.0002 per million tokens
|
||||
outputPrice: 0.0008, // $0.0008 per million tokens
|
||||
cacheWritesPrice: 0.0002, // $0.0002 per million
|
||||
|
|
@ -34,8 +30,6 @@ export const doubaoModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.00015, // $0.00015 per million tokens
|
||||
outputPrice: 0.0006, // $0.0006 per million tokens
|
||||
cacheWritesPrice: 0.00015, // $0.00015 per million
|
||||
|
|
|
|||
|
|
@ -13,7 +13,6 @@ export const featherlessModels = {
|
|||
contextWindow: 32678,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek V3 0324 model.",
|
||||
|
|
@ -23,7 +22,6 @@ export const featherlessModels = {
|
|||
contextWindow: 32678,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "DeepSeek R1 0528 model.",
|
||||
|
|
@ -33,7 +31,6 @@ export const featherlessModels = {
|
|||
contextWindow: 32678,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Kimi K2 Instruct model.",
|
||||
|
|
@ -43,7 +40,6 @@ export const featherlessModels = {
|
|||
contextWindow: 32678,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "GPT-OSS 120B model.",
|
||||
|
|
@ -53,7 +49,6 @@ export const featherlessModels = {
|
|||
contextWindow: 32678,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Qwen3 Coder 480B A35B Instruct model.",
|
||||
|
|
|
|||
|
|
@ -24,8 +24,6 @@ export const fireworksModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
cacheReadsPrice: 0.15,
|
||||
|
|
@ -37,8 +35,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
description:
|
||||
|
|
@ -49,7 +45,6 @@ export const fireworksModels = {
|
|||
contextWindow: 256000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
supportsTemperature: true,
|
||||
preserveReasoning: true,
|
||||
defaultTemperature: 1.0,
|
||||
|
|
@ -64,8 +59,6 @@ export const fireworksModels = {
|
|||
contextWindow: 204800,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 1.2,
|
||||
description:
|
||||
|
|
@ -76,8 +69,6 @@ export const fireworksModels = {
|
|||
contextWindow: 256000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.22,
|
||||
outputPrice: 0.88,
|
||||
description: "Latest Qwen3 thinking model, competitive against the best closed source models in Jul 2025.",
|
||||
|
|
@ -87,8 +78,6 @@ export const fireworksModels = {
|
|||
contextWindow: 256000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.45,
|
||||
outputPrice: 1.8,
|
||||
description: "Qwen3's most agentic code model to date.",
|
||||
|
|
@ -98,8 +87,6 @@ export const fireworksModels = {
|
|||
contextWindow: 160000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3,
|
||||
outputPrice: 8,
|
||||
description:
|
||||
|
|
@ -110,8 +97,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.9,
|
||||
outputPrice: 0.9,
|
||||
description:
|
||||
|
|
@ -122,8 +107,6 @@ export const fireworksModels = {
|
|||
contextWindow: 163840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.56,
|
||||
outputPrice: 1.68,
|
||||
description:
|
||||
|
|
@ -134,8 +117,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.55,
|
||||
outputPrice: 2.19,
|
||||
description:
|
||||
|
|
@ -146,8 +127,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.55,
|
||||
outputPrice: 2.19,
|
||||
description:
|
||||
|
|
@ -158,8 +137,6 @@ export const fireworksModels = {
|
|||
contextWindow: 198000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.55,
|
||||
outputPrice: 2.19,
|
||||
description:
|
||||
|
|
@ -170,8 +147,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.07,
|
||||
outputPrice: 0.3,
|
||||
description:
|
||||
|
|
@ -182,8 +157,6 @@ export const fireworksModels = {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.6,
|
||||
description:
|
||||
|
|
|
|||
|
|
@ -10,8 +10,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningEffort: ["low", "high"],
|
||||
reasoningEffort: "low",
|
||||
|
|
@ -37,8 +35,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
||||
reasoningEffort: "medium",
|
||||
|
|
@ -55,8 +51,6 @@ export const geminiModels = {
|
|||
maxTokens: 64_000,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
|
||||
|
|
@ -85,8 +79,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
|
||||
|
|
@ -114,8 +106,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
|
||||
|
|
@ -141,8 +131,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
|
||||
|
|
@ -172,8 +160,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.3,
|
||||
|
|
@ -187,8 +173,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.3,
|
||||
|
|
@ -202,8 +186,6 @@ export const geminiModels = {
|
|||
maxTokens: 64_000,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.3,
|
||||
|
|
@ -219,8 +201,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.1,
|
||||
|
|
@ -234,8 +214,6 @@ export const geminiModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.1,
|
||||
|
|
|
|||
|
|
@ -19,8 +19,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.05,
|
||||
outputPrice: 0.08,
|
||||
description: "Meta Llama 3.1 8B Instant model, 128K context.",
|
||||
|
|
@ -30,8 +28,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.59,
|
||||
outputPrice: 0.79,
|
||||
description: "Meta Llama 3.3 70B Versatile model, 128K context.",
|
||||
|
|
@ -41,8 +37,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.11,
|
||||
outputPrice: 0.34,
|
||||
description: "Meta Llama 4 Scout 17B Instruct model, 128K context.",
|
||||
|
|
@ -52,8 +46,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.29,
|
||||
outputPrice: 0.59,
|
||||
description: "Alibaba Qwen 3 32B model, 128K context.",
|
||||
|
|
@ -63,8 +55,6 @@ export const groqModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
cacheReadsPrice: 0.15,
|
||||
|
|
@ -76,8 +66,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.75,
|
||||
description:
|
||||
|
|
@ -88,8 +76,6 @@ export const groqModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.5,
|
||||
description:
|
||||
|
|
|
|||
|
|
@ -18,7 +18,6 @@ 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": {
|
||||
|
|
@ -26,7 +25,6 @@ export const ioIntelligenceModels = {
|
|||
contextWindow: 430000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
description: "Llama 4 Maverick 17B model",
|
||||
},
|
||||
"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar": {
|
||||
|
|
@ -34,7 +32,6 @@ export const ioIntelligenceModels = {
|
|||
contextWindow: 106000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
description: "Qwen3 Coder 480B specialized for coding",
|
||||
},
|
||||
"openai/gpt-oss-120b": {
|
||||
|
|
@ -42,7 +39,6 @@ export const ioIntelligenceModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
description: "OpenAI GPT-OSS 120B model",
|
||||
},
|
||||
} as const satisfies Record<string, ModelInfo>
|
||||
|
|
|
|||
|
|
@ -8,8 +8,6 @@ export const litellmDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
|
|||
|
|
@ -10,8 +10,6 @@ export const lMStudioDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
|
|||
|
|
@ -13,8 +13,6 @@ export const minimaxModels = {
|
|||
contextWindow: 192_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["search_and_replace"],
|
||||
excludedTools: ["apply_diff"],
|
||||
preserveReasoning: true,
|
||||
|
|
@ -30,8 +28,6 @@ export const minimaxModels = {
|
|||
contextWindow: 192_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["search_and_replace"],
|
||||
excludedTools: ["apply_diff"],
|
||||
preserveReasoning: true,
|
||||
|
|
@ -47,8 +43,6 @@ export const minimaxModels = {
|
|||
contextWindow: 192_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["search_and_replace"],
|
||||
excludedTools: ["apply_diff"],
|
||||
preserveReasoning: true,
|
||||
|
|
|
|||
|
|
@ -11,8 +11,6 @@ export const mistralModels = {
|
|||
contextWindow: 128_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 2.0,
|
||||
outputPrice: 5.0,
|
||||
},
|
||||
|
|
@ -21,8 +19,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.4,
|
||||
outputPrice: 2.0,
|
||||
},
|
||||
|
|
@ -31,8 +27,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.4,
|
||||
outputPrice: 2.0,
|
||||
},
|
||||
|
|
@ -41,8 +35,6 @@ export const mistralModels = {
|
|||
contextWindow: 256_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 0.9,
|
||||
},
|
||||
|
|
@ -51,8 +43,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 2.0,
|
||||
outputPrice: 6.0,
|
||||
},
|
||||
|
|
@ -61,8 +51,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.1,
|
||||
},
|
||||
|
|
@ -71,8 +59,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.04,
|
||||
outputPrice: 0.04,
|
||||
},
|
||||
|
|
@ -81,8 +67,6 @@ export const mistralModels = {
|
|||
contextWindow: 32_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.6,
|
||||
},
|
||||
|
|
@ -91,8 +75,6 @@ export const mistralModels = {
|
|||
contextWindow: 131_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 2.0,
|
||||
outputPrice: 6.0,
|
||||
},
|
||||
|
|
|
|||
|
|
@ -11,8 +11,6 @@ export const moonshotModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6, // $0.60 per million tokens (cache miss)
|
||||
outputPrice: 2.5, // $2.50 per million tokens
|
||||
cacheWritesPrice: 0, // $0 per million tokens (cache miss)
|
||||
|
|
@ -24,8 +22,6 @@ export const moonshotModels = {
|
|||
contextWindow: 262144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.5,
|
||||
cacheReadsPrice: 0.15,
|
||||
|
|
@ -37,8 +33,6 @@ export const moonshotModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 2.4, // $2.40 per million tokens (cache miss)
|
||||
outputPrice: 10, // $10.00 per million tokens
|
||||
cacheWritesPrice: 0, // $0 per million tokens (cache miss)
|
||||
|
|
@ -50,8 +44,6 @@ export const moonshotModels = {
|
|||
contextWindow: 262_144, // 262,144 tokens
|
||||
supportsImages: false, // Text-only (no image/vision support)
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6, // $0.60 per million tokens (cache miss)
|
||||
outputPrice: 2.5, // $2.50 per million tokens
|
||||
cacheWritesPrice: 0, // $0 per million tokens (cache miss)
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ export const ollamaDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
|
|||
|
|
@ -27,8 +27,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.1-codex-max": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -44,8 +42,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.1-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -61,8 +57,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.2-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -77,8 +71,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.1": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -95,8 +87,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -113,8 +103,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -130,8 +118,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5-codex-mini": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -147,8 +133,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.1-codex-mini": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -163,8 +147,6 @@ export const openAiCodexModels = {
|
|||
"gpt-5.2": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
|
|||
|
|
@ -9,8 +9,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.1-codex-max": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -29,8 +27,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.2": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -52,8 +48,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.2-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -72,8 +66,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.2-chat-latest": {
|
||||
maxTokens: 16_384,
|
||||
contextWindow: 128_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -86,8 +78,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.1": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -109,8 +99,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.1-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -128,8 +116,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5.1-codex-mini": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -146,8 +132,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -168,8 +152,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-mini": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -190,8 +172,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-codex": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -208,8 +188,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-nano": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -227,8 +205,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-chat-latest": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -241,8 +217,6 @@ export const openAiNativeModels = {
|
|||
"gpt-4.1": {
|
||||
maxTokens: 32_768,
|
||||
contextWindow: 1_047_576,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -258,8 +232,6 @@ export const openAiNativeModels = {
|
|||
"gpt-4.1-mini": {
|
||||
maxTokens: 32_768,
|
||||
contextWindow: 1_047_576,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -275,8 +247,6 @@ export const openAiNativeModels = {
|
|||
"gpt-4.1-nano": {
|
||||
maxTokens: 32_768,
|
||||
contextWindow: 1_047_576,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -292,8 +262,6 @@ export const openAiNativeModels = {
|
|||
o3: {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 2.0,
|
||||
|
|
@ -310,8 +278,6 @@ export const openAiNativeModels = {
|
|||
"o3-high": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 2.0,
|
||||
|
|
@ -323,8 +289,6 @@ export const openAiNativeModels = {
|
|||
"o3-low": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 2.0,
|
||||
|
|
@ -336,8 +300,6 @@ export const openAiNativeModels = {
|
|||
"o4-mini": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -354,8 +316,6 @@ export const openAiNativeModels = {
|
|||
"o4-mini-high": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -367,8 +327,6 @@ export const openAiNativeModels = {
|
|||
"o4-mini-low": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -380,8 +338,6 @@ export const openAiNativeModels = {
|
|||
"o3-mini": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -394,8 +350,6 @@ export const openAiNativeModels = {
|
|||
"o3-mini-high": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -407,8 +361,6 @@ export const openAiNativeModels = {
|
|||
"o3-mini-low": {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -420,8 +372,6 @@ export const openAiNativeModels = {
|
|||
o1: {
|
||||
maxTokens: 100_000,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 15,
|
||||
|
|
@ -432,8 +382,6 @@ export const openAiNativeModels = {
|
|||
"o1-preview": {
|
||||
maxTokens: 32_768,
|
||||
contextWindow: 128_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 15,
|
||||
|
|
@ -444,8 +392,6 @@ export const openAiNativeModels = {
|
|||
"o1-mini": {
|
||||
maxTokens: 65_536,
|
||||
contextWindow: 128_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 1.1,
|
||||
|
|
@ -456,8 +402,6 @@ export const openAiNativeModels = {
|
|||
"gpt-4o": {
|
||||
maxTokens: 16_384,
|
||||
contextWindow: 128_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 2.5,
|
||||
|
|
@ -471,8 +415,6 @@ export const openAiNativeModels = {
|
|||
"gpt-4o-mini": {
|
||||
maxTokens: 16_384,
|
||||
contextWindow: 128_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -486,8 +428,6 @@ export const openAiNativeModels = {
|
|||
"codex-mini-latest": {
|
||||
maxTokens: 16_384,
|
||||
contextWindow: 200_000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
inputPrice: 1.5,
|
||||
|
|
@ -501,8 +441,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-2025-08-07": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -523,8 +461,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-mini-2025-08-07": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -545,8 +481,6 @@ export const openAiNativeModels = {
|
|||
"gpt-5-nano-2025-08-07": {
|
||||
maxTokens: 128000,
|
||||
contextWindow: 400000,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
includedTools: ["apply_patch"],
|
||||
excludedTools: ["apply_diff", "write_to_file"],
|
||||
supportsImages: true,
|
||||
|
|
@ -570,8 +504,6 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
|
|||
supportsPromptCache: false,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
}
|
||||
|
||||
// https://learn.microsoft.com/en-us/azure/ai-services/openai/api-version-deprecation
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ export const openRouterDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
|
|||
|
|
@ -10,8 +10,6 @@ export const qwenCodeModels = {
|
|||
contextWindow: 1_000_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -23,8 +21,6 @@ export const qwenCodeModels = {
|
|||
contextWindow: 1_000_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
|
|||
|
|
@ -9,8 +9,6 @@ export const requestyDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
|
|||
|
|
@ -19,8 +19,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 16384,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.2,
|
||||
description: "Meta Llama 3.1 8B Instruct model with 16K context window.",
|
||||
|
|
@ -30,8 +28,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 1.2,
|
||||
description: "Meta Llama 3.3 70B Instruct model with 128K context window.",
|
||||
|
|
@ -42,8 +38,6 @@ export const sambaNovaModels = {
|
|||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsReasoningBudget: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 5.0,
|
||||
outputPrice: 7.0,
|
||||
description: "DeepSeek R1 reasoning model with 32K context window.",
|
||||
|
|
@ -53,8 +47,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 32768,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 4.5,
|
||||
description: "DeepSeek V3 model with 32K context window.",
|
||||
|
|
@ -64,8 +56,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 32768,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 4.5,
|
||||
description: "DeepSeek V3.1 model with 32K context window.",
|
||||
|
|
@ -75,8 +65,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.63,
|
||||
outputPrice: 1.8,
|
||||
description: "Meta Llama 4 Maverick 17B 128E Instruct model with 128K context window.",
|
||||
|
|
@ -86,8 +74,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 8192,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.4,
|
||||
outputPrice: 0.8,
|
||||
description: "Alibaba Qwen 3 32B model with 8K context window.",
|
||||
|
|
@ -97,8 +83,6 @@ export const sambaNovaModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.22,
|
||||
outputPrice: 0.59,
|
||||
description: "OpenAI gpt oss 120b model with 128k context window.",
|
||||
|
|
|
|||
|
|
@ -7,7 +7,6 @@ export const unboundDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
|
|||
|
|
@ -90,7 +90,6 @@ export const vercelAiGatewayDefaultModelInfo: ModelInfo = {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
|
|||
|
|
@ -10,8 +10,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningEffort: ["low", "high"],
|
||||
reasoningEffort: "low",
|
||||
|
|
@ -37,8 +35,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_536,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
|
||||
reasoningEffort: "medium",
|
||||
|
|
@ -54,8 +50,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -68,8 +62,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -79,8 +71,6 @@ export const vertexModels = {
|
|||
maxTokens: 64_000,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.3,
|
||||
|
|
@ -94,8 +84,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -108,8 +96,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -119,8 +105,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5,
|
||||
|
|
@ -130,8 +114,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5,
|
||||
|
|
@ -141,8 +123,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5,
|
||||
|
|
@ -154,8 +134,6 @@ export const vertexModels = {
|
|||
maxTokens: 64_000,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 2.5,
|
||||
|
|
@ -182,8 +160,6 @@ export const vertexModels = {
|
|||
maxTokens: 65_535,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0,
|
||||
|
|
@ -193,8 +169,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 2_097_152,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0,
|
||||
|
|
@ -204,8 +178,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.15,
|
||||
|
|
@ -215,8 +187,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0.075,
|
||||
|
|
@ -226,8 +196,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 32_768,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 0,
|
||||
|
|
@ -237,8 +205,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.075,
|
||||
|
|
@ -248,8 +214,6 @@ export const vertexModels = {
|
|||
maxTokens: 8192,
|
||||
contextWindow: 2_097_152,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: false,
|
||||
|
||||
inputPrice: 1.25,
|
||||
|
|
@ -260,8 +224,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000, // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens (≤200K context)
|
||||
outputPrice: 15.0, // $15 per million output tokens (≤200K context)
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -283,8 +245,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000, // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0, // $3 per million input tokens (≤200K context)
|
||||
outputPrice: 15.0, // $15 per million output tokens (≤200K context)
|
||||
cacheWritesPrice: 3.75, // $3.75 per million tokens
|
||||
|
|
@ -306,8 +266,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 5.0,
|
||||
cacheWritesPrice: 1.25,
|
||||
|
|
@ -319,8 +277,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 5.0,
|
||||
outputPrice: 25.0,
|
||||
cacheWritesPrice: 6.25,
|
||||
|
|
@ -332,8 +288,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -345,8 +299,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -357,8 +309,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -371,8 +321,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -383,8 +331,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -395,8 +341,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -407,8 +351,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 5.0,
|
||||
cacheWritesPrice: 1.25,
|
||||
|
|
@ -419,8 +361,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 15.0,
|
||||
outputPrice: 75.0,
|
||||
cacheWritesPrice: 18.75,
|
||||
|
|
@ -431,8 +371,6 @@ export const vertexModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.25,
|
||||
outputPrice: 1.25,
|
||||
cacheWritesPrice: 0.3,
|
||||
|
|
@ -442,8 +380,6 @@ export const vertexModels = {
|
|||
maxTokens: 64_000,
|
||||
contextWindow: 1_048_576,
|
||||
supportsImages: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsPromptCache: true,
|
||||
|
||||
inputPrice: 0.1,
|
||||
|
|
@ -458,7 +394,6 @@ export const vertexModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.35,
|
||||
outputPrice: 1.15,
|
||||
description: "Meta Llama 4 Maverick 17B Instruct model, 128K context.",
|
||||
|
|
@ -468,7 +403,6 @@ export const vertexModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 1.35,
|
||||
outputPrice: 5.4,
|
||||
description: "DeepSeek R1 (0528). Available in us-central1",
|
||||
|
|
@ -478,7 +412,6 @@ export const vertexModels = {
|
|||
contextWindow: 163_840,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 1.7,
|
||||
description: "DeepSeek V3.1. Available in us-west2",
|
||||
|
|
@ -488,7 +421,6 @@ export const vertexModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.6,
|
||||
description: "OpenAI gpt-oss 120B. Available in us-central1",
|
||||
|
|
@ -498,7 +430,6 @@ export const vertexModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.075,
|
||||
outputPrice: 0.3,
|
||||
description: "OpenAI gpt-oss 20B. Available in us-central1",
|
||||
|
|
@ -508,7 +439,6 @@ export const vertexModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 1.0,
|
||||
outputPrice: 4.0,
|
||||
description: "Qwen3 Coder 480B A35B Instruct. Available in us-south1",
|
||||
|
|
@ -518,7 +448,6 @@ export const vertexModels = {
|
|||
contextWindow: 262_144,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.25,
|
||||
outputPrice: 1.0,
|
||||
description: "Qwen3 235B A22B Instruct. Available in us-south1",
|
||||
|
|
|
|||
|
|
@ -11,8 +11,6 @@ export const xaiModels = {
|
|||
contextWindow: 256_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 1.5,
|
||||
cacheWritesPrice: 0.02,
|
||||
|
|
@ -26,8 +24,6 @@ export const xaiModels = {
|
|||
contextWindow: 2_000_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0.05,
|
||||
|
|
@ -42,8 +38,6 @@ export const xaiModels = {
|
|||
contextWindow: 2_000_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0.05,
|
||||
|
|
@ -58,8 +52,6 @@ export const xaiModels = {
|
|||
contextWindow: 2_000_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0.05,
|
||||
|
|
@ -74,8 +66,6 @@ export const xaiModels = {
|
|||
contextWindow: 2_000_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0.05,
|
||||
|
|
@ -90,8 +80,6 @@ export const xaiModels = {
|
|||
contextWindow: 256_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 0.75,
|
||||
|
|
@ -105,8 +93,6 @@ export const xaiModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.3,
|
||||
outputPrice: 0.5,
|
||||
cacheWritesPrice: 0.07,
|
||||
|
|
@ -122,8 +108,6 @@ export const xaiModels = {
|
|||
contextWindow: 131072,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 3.0,
|
||||
outputPrice: 15.0,
|
||||
cacheWritesPrice: 0.75,
|
||||
|
|
|
|||
|
|
@ -16,8 +16,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.2,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -30,8 +28,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.2,
|
||||
outputPrice: 1.1,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -44,8 +40,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 2.2,
|
||||
outputPrice: 8.9,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -58,8 +52,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 1.1,
|
||||
outputPrice: 4.5,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -71,8 +63,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -84,8 +74,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 1.8,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -98,8 +86,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.6,
|
||||
outputPrice: 2.2,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -112,8 +98,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 200_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsReasoningEffort: ["disable", "medium"],
|
||||
reasoningEffort: "medium",
|
||||
preserveReasoning: true,
|
||||
|
|
@ -129,8 +113,6 @@ export const internationalZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.1,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -147,8 +129,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.29,
|
||||
outputPrice: 1.14,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -161,8 +141,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.6,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -175,8 +153,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.29,
|
||||
outputPrice: 1.14,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -189,8 +165,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.1,
|
||||
outputPrice: 0.6,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -202,8 +176,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -215,8 +187,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 131_072,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.29,
|
||||
outputPrice: 0.93,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -229,8 +199,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 204_800,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: 0.29,
|
||||
outputPrice: 1.14,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -243,8 +211,6 @@ export const mainlandZAiModels = {
|
|||
contextWindow: 204_800,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
supportsReasoningEffort: ["disable", "medium"],
|
||||
reasoningEffort: "medium",
|
||||
preserveReasoning: true,
|
||||
|
|
|
|||
|
|
@ -57,48 +57,3 @@ export const toolUsageSchema = z.record(
|
|||
)
|
||||
|
||||
export type ToolUsage = z.infer<typeof toolUsageSchema>
|
||||
|
||||
/**
|
||||
* Tool protocol constants
|
||||
*/
|
||||
export const TOOL_PROTOCOL = {
|
||||
XML: "xml",
|
||||
NATIVE: "native",
|
||||
} as const
|
||||
|
||||
/**
|
||||
* Tool protocol type for system prompt generation
|
||||
* Derived from TOOL_PROTOCOL constants to ensure type safety
|
||||
*/
|
||||
export type ToolProtocol = (typeof TOOL_PROTOCOL)[keyof typeof TOOL_PROTOCOL]
|
||||
|
||||
/**
|
||||
* Default model info properties for native tool support.
|
||||
* Used to merge with cached model info that may lack these fields.
|
||||
* Router providers (Requesty, Unbound, LiteLLM) assume all models support native tools.
|
||||
*/
|
||||
export const NATIVE_TOOL_DEFAULTS = {
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: TOOL_PROTOCOL.NATIVE,
|
||||
} as const
|
||||
|
||||
/**
|
||||
* Checks if the protocol is native (non-XML).
|
||||
*
|
||||
* @param protocol - The tool protocol to check
|
||||
* @returns True if protocol is native
|
||||
*/
|
||||
export function isNativeProtocol(protocol: ToolProtocol): boolean {
|
||||
return protocol === TOOL_PROTOCOL.NATIVE
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets the effective protocol from settings or falls back to the default XML.
|
||||
* This function is safe to use in webview-accessible code as it doesn't depend on vscode module.
|
||||
*
|
||||
* @param toolProtocol - Optional tool protocol from settings
|
||||
* @returns The effective tool protocol (defaults to "xml")
|
||||
*/
|
||||
export function getEffectiveProtocol(toolProtocol?: ToolProtocol): ToolProtocol {
|
||||
return toolProtocol || TOOL_PROTOCOL.XML
|
||||
}
|
||||
|
|
|
|||
|
|
@ -288,6 +288,56 @@ describe("History resume delegation - parent metadata transitions", () => {
|
|||
expect((injectedMsg.content[0] as any).tool_use_id).toBe("toolu_abc123")
|
||||
})
|
||||
|
||||
it("reopenParentFromDelegation injects plain text when no new_task tool_use exists in API history", async () => {
|
||||
const provider = {
|
||||
contextProxy: { globalStorageUri: { fsPath: "/storage" } },
|
||||
getTaskWithId: vi.fn().mockResolvedValue({
|
||||
historyItem: {
|
||||
id: "p-no-tool",
|
||||
status: "delegated",
|
||||
awaitingChildId: "c-no-tool",
|
||||
childIds: [],
|
||||
ts: 100,
|
||||
task: "Parent without tool_use",
|
||||
tokensIn: 0,
|
||||
tokensOut: 0,
|
||||
totalCost: 0,
|
||||
},
|
||||
}),
|
||||
emit: vi.fn(),
|
||||
getCurrentTask: vi.fn(() => ({ taskId: "c-no-tool" })),
|
||||
removeClineFromStack: vi.fn().mockResolvedValue(undefined),
|
||||
createTaskWithHistoryItem: vi.fn().mockResolvedValue({
|
||||
taskId: "p-no-tool",
|
||||
resumeAfterDelegation: vi.fn().mockResolvedValue(undefined),
|
||||
overwriteClineMessages: vi.fn().mockResolvedValue(undefined),
|
||||
overwriteApiConversationHistory: vi.fn().mockResolvedValue(undefined),
|
||||
}),
|
||||
updateTaskHistory: vi.fn().mockResolvedValue([]),
|
||||
} as unknown as ClineProvider
|
||||
|
||||
// No assistant tool_use in history
|
||||
const existingUiMessages = [{ type: "ask", ask: "tool", text: "subtask request", ts: 50 }]
|
||||
const existingApiMessages = [{ role: "user", content: [{ type: "text", text: "Create a subtask" }], ts: 40 }]
|
||||
|
||||
vi.mocked(readTaskMessages).mockResolvedValue(existingUiMessages as any)
|
||||
vi.mocked(readApiMessages).mockResolvedValue(existingApiMessages as any)
|
||||
|
||||
await (ClineProvider.prototype as any).reopenParentFromDelegation.call(provider, {
|
||||
parentTaskId: "p-no-tool",
|
||||
childTaskId: "c-no-tool",
|
||||
completionResultSummary: "Subtask completed without tool_use",
|
||||
})
|
||||
|
||||
const apiCall = vi.mocked(saveApiMessages).mock.calls[0][0]
|
||||
// Should append a user text note
|
||||
expect(apiCall.messages).toHaveLength(2)
|
||||
const injected = apiCall.messages[1]
|
||||
expect(injected.role).toBe("user")
|
||||
expect((injected.content[0] as any).type).toBe("text")
|
||||
expect((injected.content[0] as any).text).toContain("Subtask c-no-tool completed")
|
||||
})
|
||||
|
||||
it("reopenParentFromDelegation sets skipPrevResponseIdOnce via resumeAfterDelegation", async () => {
|
||||
const parentInstance: any = {
|
||||
skipPrevResponseIdOnce: false,
|
||||
|
|
|
|||
|
|
@ -187,18 +187,21 @@ describe("Nested delegation resume (A → B → C)", () => {
|
|||
type: "tool_use",
|
||||
name: "attempt_completion",
|
||||
params: { result: "C finished" },
|
||||
nativeArgs: { result: "C finished" },
|
||||
partial: false,
|
||||
} as any
|
||||
|
||||
const askFinishSubTaskApproval = vi.fn(async () => true)
|
||||
const handleError = vi.fn(async (_action: string, err: Error) => {
|
||||
// Fail fast in this test if the tool hits an error path.
|
||||
throw err
|
||||
})
|
||||
|
||||
await attemptCompletionTool.handle(clineC, blockC, {
|
||||
askApproval: vi.fn(),
|
||||
handleError: vi.fn(),
|
||||
handleError,
|
||||
pushToolResult: vi.fn(),
|
||||
removeClosingTag: vi.fn((_, v?: string) => v ?? ""),
|
||||
askFinishSubTaskApproval,
|
||||
toolProtocol: "xml",
|
||||
toolDescription: () => "desc",
|
||||
} as any)
|
||||
|
||||
|
|
@ -231,20 +234,21 @@ describe("Nested delegation resume (A → B → C)", () => {
|
|||
type: "tool_use",
|
||||
name: "attempt_completion",
|
||||
params: { result: "B finished" },
|
||||
nativeArgs: { result: "B finished" },
|
||||
partial: false,
|
||||
} as any
|
||||
|
||||
await attemptCompletionTool.handle(clineB, blockB, {
|
||||
askApproval: vi.fn(),
|
||||
handleError: vi.fn(),
|
||||
handleError,
|
||||
pushToolResult: vi.fn(),
|
||||
removeClosingTag: vi.fn((_, v?: string) => v ?? ""),
|
||||
askFinishSubTaskApproval,
|
||||
toolProtocol: "xml",
|
||||
toolDescription: () => "desc",
|
||||
} as any)
|
||||
|
||||
// After B completes, A must be current
|
||||
// After B completes, A should become current
|
||||
// Note: delegation resume may fall back to a non-tool_result user message when the parent history
|
||||
// does not contain a new_task tool_use. This should not prevent reopening the parent.
|
||||
expect(currentActiveId).toBe("A")
|
||||
|
||||
// Ensure no resume_task asks were scheduled: verified indirectly by startTask:false on both hops
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
import { Anthropic } from "@anthropic-ai/sdk"
|
||||
import OpenAI from "openai"
|
||||
|
||||
import type { ProviderSettings, ModelInfo, ToolProtocol } from "@roo-code/types"
|
||||
import type { ProviderSettings, ModelInfo } from "@roo-code/types"
|
||||
|
||||
import { ApiStream } from "./transform/stream"
|
||||
|
||||
|
|
@ -83,16 +83,11 @@ export interface ApiHandlerCreateMessageMetadata {
|
|||
* Can be "none", "auto", "required", or a specific tool choice.
|
||||
*/
|
||||
tool_choice?: OpenAI.Chat.ChatCompletionCreateParams["tool_choice"]
|
||||
/**
|
||||
* The tool protocol being used (XML or Native).
|
||||
* Used by providers to determine whether to include native tool definitions.
|
||||
*/
|
||||
toolProtocol?: ToolProtocol
|
||||
// Tool calling is native-only.
|
||||
/**
|
||||
* Controls whether the model can return multiple tool calls in a single response.
|
||||
* When true, parallel tool calls are enabled (OpenAI's parallel_tool_calls=true).
|
||||
* When false (default), only one tool call is returned per response.
|
||||
* Only applies when toolProtocol is "native".
|
||||
*/
|
||||
parallelToolCalls?: boolean
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -162,7 +162,7 @@ describe("VertexHandler", () => {
|
|||
})
|
||||
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
{
|
||||
expect.objectContaining({
|
||||
model: "claude-3-5-sonnet-v2@20241022",
|
||||
max_tokens: 8192,
|
||||
temperature: 0,
|
||||
|
|
@ -191,7 +191,10 @@ describe("VertexHandler", () => {
|
|||
},
|
||||
],
|
||||
stream: true,
|
||||
},
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
tools: expect.any(Array),
|
||||
tool_choice: expect.any(Object),
|
||||
}),
|
||||
undefined,
|
||||
)
|
||||
})
|
||||
|
|
@ -1200,13 +1203,11 @@ describe("VertexHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should include tools even when toolProtocol is set to xml (user preference now ignored)", async () => {
|
||||
// XML protocol deprecation: user preference is now ignored when model supports native tools
|
||||
it("should include tools when tools are provided", async () => {
|
||||
handler = new AnthropicVertexHandler({
|
||||
apiModelId: "claude-3-5-sonnet-v2@20241022",
|
||||
vertexProjectId: "test-project",
|
||||
vertexRegion: "us-central1",
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
|
||||
const mockStream = [
|
||||
|
|
@ -1242,7 +1243,7 @@ describe("VertexHandler", () => {
|
|||
// Just consume
|
||||
}
|
||||
|
||||
// Native is forced when supportsNativeTools===true, so tools should still be included
|
||||
// Tool calling is request-driven: if tools are provided, we should include them.
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
tools: expect.arrayContaining([
|
||||
|
|
|
|||
|
|
@ -420,8 +420,7 @@ describe("AnthropicHandler", () => {
|
|||
},
|
||||
]
|
||||
|
||||
it("should include tools in request by default (native is default)", async () => {
|
||||
// Handler uses native protocol by default via model's defaultToolProtocol
|
||||
it("should include tools in request when tools are provided", async () => {
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
tools: mockTools,
|
||||
|
|
@ -451,11 +450,9 @@ describe("AnthropicHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should include tools even when toolProtocol is set to xml (user preference now ignored)", async () => {
|
||||
// XML protocol deprecation: user preference is now ignored when model supports native tools
|
||||
it("should include tools when tools are provided", async () => {
|
||||
const xmlHandler = new AnthropicHandler({
|
||||
...mockOptions,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
|
||||
const stream = xmlHandler.createMessage(systemPrompt, messages, {
|
||||
|
|
@ -468,7 +465,7 @@ describe("AnthropicHandler", () => {
|
|||
// Just consume
|
||||
}
|
||||
|
||||
// Native is forced when supportsNativeTools===true, so tools should still be included
|
||||
// Tool calling is request-driven: if tools are provided, we should include them.
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
tools: expect.arrayContaining([
|
||||
|
|
@ -481,7 +478,7 @@ describe("AnthropicHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when no tools are provided", async () => {
|
||||
it("should always include tools in request (tools are always present after PR #10841)", async () => {
|
||||
// Handler uses native protocol by default
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
|
|
@ -492,9 +489,11 @@ describe("AnthropicHandler", () => {
|
|||
// Just consume
|
||||
}
|
||||
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
expect.objectContaining({
|
||||
tools: expect.any(Array),
|
||||
tool_choice: expect.any(Object),
|
||||
}),
|
||||
expect.anything(),
|
||||
)
|
||||
|
|
@ -542,7 +541,7 @@ describe("AnthropicHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should omit both tools and tool_choice when tool_choice is 'none'", async () => {
|
||||
it("should set tool_choice to undefined when tool_choice is 'none' (tools are still passed)", async () => {
|
||||
// Handler uses native protocol by default
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
|
|
@ -555,16 +554,13 @@ describe("AnthropicHandler", () => {
|
|||
// Just consume
|
||||
}
|
||||
|
||||
// Verify that neither tools nor tool_choice are included in the request
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
// When tool_choice is 'none', the converter returns undefined for tool_choice
|
||||
// but tools are still passed since they're always present
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
}),
|
||||
expect.anything(),
|
||||
)
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tool_choice: expect.anything(),
|
||||
expect.objectContaining({
|
||||
tools: expect.any(Array),
|
||||
tool_choice: undefined,
|
||||
}),
|
||||
expect.anything(),
|
||||
)
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ describe("BaseOpenAiCompatibleProvider", () => {
|
|||
vi.restoreAllMocks()
|
||||
})
|
||||
|
||||
describe("XmlMatcher reasoning tags", () => {
|
||||
describe("TagMatcher reasoning tags", () => {
|
||||
it("should handle reasoning tags (<think>) from stream", async () => {
|
||||
mockCreate.mockImplementationOnce(() => {
|
||||
return {
|
||||
|
|
@ -87,7 +87,7 @@ describe("BaseOpenAiCompatibleProvider", () => {
|
|||
chunks.push(chunk)
|
||||
}
|
||||
|
||||
// XmlMatcher yields chunks as they're processed
|
||||
// TagMatcher yields chunks as they're processed
|
||||
expect(chunks).toEqual([
|
||||
{ type: "reasoning", text: "Let me think" },
|
||||
{ type: "reasoning", text: " about this" },
|
||||
|
|
@ -124,7 +124,7 @@ describe("BaseOpenAiCompatibleProvider", () => {
|
|||
chunks.push(chunk)
|
||||
}
|
||||
|
||||
// When a complete tag arrives in one chunk, XmlMatcher may not parse it
|
||||
// When a complete tag arrives in one chunk, TagMatcher may not parse it
|
||||
// This test documents the actual behavior
|
||||
expect(chunks.length).toBeGreaterThan(0)
|
||||
expect(chunks[0]).toEqual({ type: "text", text: "Regular text before " })
|
||||
|
|
@ -151,7 +151,7 @@ describe("BaseOpenAiCompatibleProvider", () => {
|
|||
chunks.push(chunk)
|
||||
}
|
||||
|
||||
// XmlMatcher should handle incomplete tags and flush remaining content
|
||||
// TagMatcher should handle incomplete tags and flush remaining content
|
||||
expect(chunks.length).toBeGreaterThan(0)
|
||||
expect(
|
||||
chunks.some(
|
||||
|
|
|
|||
|
|
@ -242,11 +242,7 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
})
|
||||
|
||||
describe("createMessage with native tools", () => {
|
||||
it("should include toolConfig when tools are provided with native protocol", async () => {
|
||||
// Override model info to support native tools
|
||||
const modelInfo = handler.getModel().info
|
||||
;(modelInfo as any).supportsNativeTools = true
|
||||
|
||||
it("should include toolConfig when tools are provided", async () => {
|
||||
const handlerWithNativeTools = new AwsBedrockHandler({
|
||||
apiModelId: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
awsAccessKey: "test-access-key",
|
||||
|
|
@ -254,18 +250,9 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
awsRegion: "us-east-1",
|
||||
})
|
||||
|
||||
// Manually set supportsNativeTools
|
||||
const getModelOriginal = handlerWithNativeTools.getModel.bind(handlerWithNativeTools)
|
||||
handlerWithNativeTools.getModel = () => {
|
||||
const model = getModelOriginal()
|
||||
model.info.supportsNativeTools = true
|
||||
return model
|
||||
}
|
||||
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
}
|
||||
|
||||
const generator = handlerWithNativeTools.createMessage(
|
||||
|
|
@ -285,7 +272,7 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
expect(commandArg.toolConfig.toolChoice).toEqual({ auto: {} })
|
||||
})
|
||||
|
||||
it("should not include toolConfig when toolProtocol is xml", async () => {
|
||||
it("should always include toolConfig (tools are always present after PR #10841)", async () => {
|
||||
const handlerWithNativeTools = new AwsBedrockHandler({
|
||||
apiModelId: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
awsAccessKey: "test-access-key",
|
||||
|
|
@ -293,18 +280,9 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
awsRegion: "us-east-1",
|
||||
})
|
||||
|
||||
// Manually set supportsNativeTools
|
||||
const getModelOriginal = handlerWithNativeTools.getModel.bind(handlerWithNativeTools)
|
||||
handlerWithNativeTools.getModel = () => {
|
||||
const model = getModelOriginal()
|
||||
model.info.supportsNativeTools = true
|
||||
return model
|
||||
}
|
||||
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml", // XML protocol should not use native tools
|
||||
// Even without explicit tools, tools are always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
}
|
||||
|
||||
const generator = handlerWithNativeTools.createMessage(
|
||||
|
|
@ -318,10 +296,13 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
expect(commandArg.toolConfig).toBeUndefined()
|
||||
// Tools are now always present
|
||||
expect(commandArg.toolConfig).toBeDefined()
|
||||
expect(commandArg.toolConfig.tools).toBeDefined()
|
||||
expect(commandArg.toolConfig.toolChoice).toEqual({ auto: {} })
|
||||
})
|
||||
|
||||
it("should not include toolConfig when tool_choice is none", async () => {
|
||||
it("should include toolConfig with undefined toolChoice when tool_choice is none", async () => {
|
||||
const handlerWithNativeTools = new AwsBedrockHandler({
|
||||
apiModelId: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
awsAccessKey: "test-access-key",
|
||||
|
|
@ -329,18 +310,9 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
awsRegion: "us-east-1",
|
||||
})
|
||||
|
||||
// Manually set supportsNativeTools
|
||||
const getModelOriginal = handlerWithNativeTools.getModel.bind(handlerWithNativeTools)
|
||||
handlerWithNativeTools.getModel = () => {
|
||||
const model = getModelOriginal()
|
||||
model.info.supportsNativeTools = true
|
||||
return model
|
||||
}
|
||||
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
tool_choice: "none", // Explicitly disable tool use
|
||||
}
|
||||
|
||||
|
|
@ -355,7 +327,9 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
expect(commandArg.toolConfig).toBeUndefined()
|
||||
// toolConfig is still provided but toolChoice is undefined for "none"
|
||||
expect(commandArg.toolConfig).toBeDefined()
|
||||
expect(commandArg.toolConfig.toolChoice).toBeUndefined()
|
||||
})
|
||||
|
||||
it("should include fine-grained tool streaming beta for Claude models with native tools", async () => {
|
||||
|
|
@ -366,18 +340,9 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
awsRegion: "us-east-1",
|
||||
})
|
||||
|
||||
// Manually set supportsNativeTools
|
||||
const getModelOriginal = handlerWithNativeTools.getModel.bind(handlerWithNativeTools)
|
||||
handlerWithNativeTools.getModel = () => {
|
||||
const model = getModelOriginal()
|
||||
model.info.supportsNativeTools = true
|
||||
return model
|
||||
}
|
||||
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
}
|
||||
|
||||
const generator = handlerWithNativeTools.createMessage(
|
||||
|
|
@ -398,7 +363,7 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include fine-grained tool streaming beta when not using native tools", async () => {
|
||||
it("should always include fine-grained tool streaming beta for Claude models", async () => {
|
||||
const handlerWithNativeTools = new AwsBedrockHandler({
|
||||
apiModelId: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
awsAccessKey: "test-access-key",
|
||||
|
|
@ -422,12 +387,11 @@ describe("AwsBedrockHandler Native Tool Calling", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
// Should not include anthropic_beta when not using native tools
|
||||
if (commandArg.additionalModelRequestFields?.anthropic_beta) {
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).not.toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
}
|
||||
// Should always include anthropic_beta with fine-grained-tool-streaming for Claude models
|
||||
expect(commandArg.additionalModelRequestFields).toBeDefined()
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
})
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -221,8 +221,11 @@ describe("AwsBedrockHandler - Extended Thinking", () => {
|
|||
expect(capturedPayload).toBeDefined()
|
||||
expect(capturedPayload.inferenceConfig).not.toHaveProperty("topP")
|
||||
|
||||
// Verify that additionalModelRequestFields is not present or empty
|
||||
expect(capturedPayload.additionalModelRequestFields).toBeUndefined()
|
||||
// Verify that additionalModelRequestFields contains fine-grained-tool-streaming for Claude models
|
||||
expect(capturedPayload.additionalModelRequestFields).toBeDefined()
|
||||
expect(capturedPayload.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
})
|
||||
|
||||
it("should enable reasoning when enableReasoningEffort is true in settings", async () => {
|
||||
|
|
|
|||
|
|
@ -754,14 +754,17 @@ describe("AwsBedrockHandler", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
// Should include anthropic_beta in additionalModelRequestFields
|
||||
// Should include anthropic_beta in additionalModelRequestFields with both 1M context and fine-grained-tool-streaming
|
||||
expect(commandArg.additionalModelRequestFields).toBeDefined()
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toEqual(["context-1m-2025-08-07"])
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain("context-1m-2025-08-07")
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
// Should not include anthropic_version since thinking is not enabled
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_version).toBeUndefined()
|
||||
})
|
||||
|
||||
it("should not include anthropic_beta parameter when 1M context is disabled", async () => {
|
||||
it("should not include 1M context beta when 1M context is disabled but still include fine-grained-tool-streaming", async () => {
|
||||
const handler = new AwsBedrockHandler({
|
||||
apiModelId: BEDROCK_1M_CONTEXT_MODEL_IDS[0],
|
||||
awsAccessKey: "test",
|
||||
|
|
@ -784,11 +787,16 @@ describe("AwsBedrockHandler", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
// Should not include anthropic_beta in additionalModelRequestFields
|
||||
expect(commandArg.additionalModelRequestFields).toBeUndefined()
|
||||
// Should include anthropic_beta with fine-grained-tool-streaming for Claude models
|
||||
expect(commandArg.additionalModelRequestFields).toBeDefined()
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
// Should NOT include 1M context beta
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).not.toContain("context-1m-2025-08-07")
|
||||
})
|
||||
|
||||
it("should not include anthropic_beta parameter for non-Claude Sonnet 4 models", async () => {
|
||||
it("should not include 1M context beta for non-Claude Sonnet 4 models but still include fine-grained-tool-streaming", async () => {
|
||||
const handler = new AwsBedrockHandler({
|
||||
apiModelId: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
awsAccessKey: "test",
|
||||
|
|
@ -811,8 +819,13 @@ describe("AwsBedrockHandler", () => {
|
|||
expect(mockConverseStreamCommand).toHaveBeenCalled()
|
||||
const commandArg = mockConverseStreamCommand.mock.calls[0][0] as any
|
||||
|
||||
// Should not include anthropic_beta for non-Sonnet 4 models
|
||||
expect(commandArg.additionalModelRequestFields).toBeUndefined()
|
||||
// Should include anthropic_beta with fine-grained-tool-streaming for Claude models (even non-Sonnet 4)
|
||||
expect(commandArg.additionalModelRequestFields).toBeDefined()
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
// Should NOT include 1M context beta for non-Sonnet 4 models
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).not.toContain("context-1m-2025-08-07")
|
||||
})
|
||||
|
||||
it("should enable 1M context window with cross-region inference for Claude Sonnet 4", () => {
|
||||
|
|
@ -859,9 +872,12 @@ describe("AwsBedrockHandler", () => {
|
|||
mockConverseStreamCommand.mock.calls.length - 1
|
||||
][0] as any
|
||||
|
||||
// Should include anthropic_beta in additionalModelRequestFields
|
||||
// Should include anthropic_beta in additionalModelRequestFields with both 1M context and fine-grained-tool-streaming
|
||||
expect(commandArg.additionalModelRequestFields).toBeDefined()
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toEqual(["context-1m-2025-08-07"])
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain("context-1m-2025-08-07")
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_beta).toContain(
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
)
|
||||
// Should not include anthropic_version since thinking is not enabled
|
||||
expect(commandArg.additionalModelRequestFields.anthropic_version).toBeUndefined()
|
||||
// Model ID should have cross-region prefix
|
||||
|
|
|
|||
|
|
@ -112,22 +112,25 @@ describe("ClaudeCodeHandler", () => {
|
|||
// Verify createStreamingMessage was called with correct parameters
|
||||
// Default model has reasoning effort of "medium" so thinking should be enabled
|
||||
// With interleaved thinking, maxTokens comes from model definition (32768 for claude-sonnet-4-5)
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model's maxTokens from claudeCodeModels definition
|
||||
thinking: {
|
||||
type: "enabled",
|
||||
budget_tokens: 32000, // medium reasoning budget_tokens
|
||||
},
|
||||
tools: undefined,
|
||||
toolChoice: undefined,
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
})
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model's maxTokens from claudeCodeModels definition
|
||||
thinking: {
|
||||
type: "enabled",
|
||||
budget_tokens: 32000, // medium reasoning budget_tokens
|
||||
},
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
tools: expect.any(Array),
|
||||
toolChoice: expect.any(Object),
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
test("should disable thinking when reasoningEffort is set to disable", async () => {
|
||||
|
|
@ -155,19 +158,22 @@ describe("ClaudeCodeHandler", () => {
|
|||
await iterator.next()
|
||||
|
||||
// Verify createStreamingMessage was called with thinking disabled
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model maxTokens from claudeCodeModels definition
|
||||
thinking: { type: "disabled" },
|
||||
tools: undefined,
|
||||
toolChoice: undefined,
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
})
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model maxTokens from claudeCodeModels definition
|
||||
thinking: { type: "disabled" },
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
tools: expect.any(Array),
|
||||
toolChoice: expect.any(Object),
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
test("should use high reasoning config when reasoningEffort is high", async () => {
|
||||
|
|
@ -196,22 +202,25 @@ describe("ClaudeCodeHandler", () => {
|
|||
|
||||
// Verify createStreamingMessage was called with high thinking config
|
||||
// With interleaved thinking, maxTokens comes from model definition (32768 for claude-sonnet-4-5)
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model's maxTokens from claudeCodeModels definition
|
||||
thinking: {
|
||||
type: "enabled",
|
||||
budget_tokens: 64000, // high reasoning budget_tokens
|
||||
},
|
||||
tools: undefined,
|
||||
toolChoice: undefined,
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
})
|
||||
expect(mockCreateStreamingMessage).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
accessToken: "test-access-token",
|
||||
model: "claude-sonnet-4-5",
|
||||
systemPrompt,
|
||||
messages,
|
||||
maxTokens: 32768, // model's maxTokens from claudeCodeModels definition
|
||||
thinking: {
|
||||
type: "enabled",
|
||||
budget_tokens: 64000, // high reasoning budget_tokens
|
||||
},
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
tools: expect.any(Array),
|
||||
toolChoice: expect.any(Object),
|
||||
metadata: {
|
||||
user_id: "user_abc123_account_def456_session_ghi789",
|
||||
},
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
test("should handle text content from streaming", async () => {
|
||||
|
|
|
|||
|
|
@ -199,7 +199,6 @@ describe("DeepInfraHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
|
|
@ -213,9 +212,11 @@ describe("DeepInfraHandler", () => {
|
|||
}),
|
||||
}),
|
||||
]),
|
||||
parallel_tool_calls: false,
|
||||
}),
|
||||
)
|
||||
// parallel_tool_calls should be false when not explicitly set
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should include tool_choice when provided", async () => {
|
||||
|
|
@ -232,7 +233,6 @@ describe("DeepInfraHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
tool_choice: "auto",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
@ -244,7 +244,7 @@ describe("DeepInfraHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools and tool_choice in request (tools are always present after PR #10841)", async () => {
|
||||
mockWithResponse.mockResolvedValueOnce({
|
||||
data: {
|
||||
[Symbol.asyncIterator]: () => ({
|
||||
|
|
@ -257,14 +257,15 @@ describe("DeepInfraHandler", () => {
|
|||
|
||||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
const callArgs = mockCreate.mock.calls[mockCreate.mock.calls.length - 1][0]
|
||||
expect(callArgs).not.toHaveProperty("tools")
|
||||
expect(callArgs).not.toHaveProperty("tool_choice")
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
expect(callArgs).toHaveProperty("tools")
|
||||
expect(callArgs).toHaveProperty("tool_choice")
|
||||
// parallel_tool_calls should be false when not explicitly set
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should yield tool_call_partial chunks during streaming", async () => {
|
||||
|
|
@ -321,7 +322,6 @@ describe("DeepInfraHandler", () => {
|
|||
const stream = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
|
||||
const chunks = []
|
||||
|
|
@ -360,7 +360,6 @@ describe("DeepInfraHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
parallelToolCalls: true,
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
|
|||
|
|
@ -129,7 +129,6 @@ describe("FireworksHandler", () => {
|
|||
contextWindow: 256000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
supportsTemperature: true,
|
||||
preserveReasoning: true,
|
||||
defaultTemperature: 1.0,
|
||||
|
|
|
|||
|
|
@ -5,7 +5,10 @@ import { GeminiHandler } from "../gemini"
|
|||
import type { ApiHandlerOptions } from "../../../shared/api"
|
||||
|
||||
describe("GeminiHandler backend support", () => {
|
||||
it("passes tools for URL context and grounding in config", async () => {
|
||||
it("createMessage uses function declarations (URL context and grounding are only for completePrompt)", async () => {
|
||||
// URL context and grounding are mutually exclusive with function declarations
|
||||
// in Gemini API, so createMessage only uses function declarations.
|
||||
// URL context/grounding are only added in completePrompt.
|
||||
const options = {
|
||||
apiProvider: "gemini",
|
||||
enableUrlContext: true,
|
||||
|
|
@ -17,7 +20,9 @@ describe("GeminiHandler backend support", () => {
|
|||
handler["client"].models.generateContentStream = stub
|
||||
await handler.createMessage("instr", [] as any).next()
|
||||
const config = stub.mock.calls[0][0].config
|
||||
expect(config.tools).toEqual([{ urlContext: {} }, { googleSearch: {} }])
|
||||
// createMessage always uses function declarations only
|
||||
// (tools are always present from ALWAYS_AVAILABLE_TOOLS)
|
||||
expect(config.tools).toEqual([{ functionDeclarations: expect.any(Array) }])
|
||||
})
|
||||
|
||||
it("completePrompt passes config overrides without tools when URL context and grounding disabled", async () => {
|
||||
|
|
|
|||
|
|
@ -255,7 +255,6 @@ describe("IOIntelligenceHandler", () => {
|
|||
description: "Llama 4 Maverick 17B model",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
})
|
||||
})
|
||||
|
||||
|
|
@ -272,7 +271,6 @@ describe("IOIntelligenceHandler", () => {
|
|||
description: "Llama 4 Maverick 17B model",
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
})
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ import { Anthropic } from "@anthropic-ai/sdk"
|
|||
|
||||
import { LiteLLMHandler } from "../lite-llm"
|
||||
import { ApiHandlerOptions } from "../../../shared/api"
|
||||
import { litellmDefaultModelId, litellmDefaultModelInfo, TOOL_PROTOCOL } from "@roo-code/types"
|
||||
import { litellmDefaultModelId, litellmDefaultModelInfo } from "@roo-code/types"
|
||||
|
||||
// Mock vscode first to avoid import errors
|
||||
vi.mock("vscode", () => ({}))
|
||||
|
|
@ -41,11 +41,11 @@ vi.mock("../fetchers/modelCache", () => ({
|
|||
"llama-3": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
"gpt-4-turbo": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
// Gemini models for thought signature injection tests
|
||||
"gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
"gemini-3-flash": { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
"gemini-2.5-pro": { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
"google/gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
"vertex_ai/gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
"gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
"gemini-3-flash": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
"gemini-2.5-pro": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
"google/gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
"vertex_ai/gemini-3-pro": { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
})
|
||||
}),
|
||||
getModelsFromCache: vi.fn().mockReturnValue(undefined),
|
||||
|
|
@ -583,10 +583,10 @@ describe("LiteLLMHandler", () => {
|
|||
}
|
||||
handler = new LiteLLMHandler(optionsWithGemini)
|
||||
|
||||
// Mock fetchModel to return a Gemini model with native tool support
|
||||
// Mock fetchModel to return a Gemini model
|
||||
vi.spyOn(handler as any, "fetchModel").mockResolvedValue({
|
||||
id: "gemini-3-pro",
|
||||
info: { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
info: { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
})
|
||||
|
||||
const systemPrompt = "You are a helpful assistant"
|
||||
|
|
@ -632,7 +632,7 @@ describe("LiteLLMHandler", () => {
|
|||
function: { name: "read_file", description: "Read a file", parameters: {} },
|
||||
},
|
||||
],
|
||||
toolProtocol: TOOL_PROTOCOL.NATIVE,
|
||||
// Tool calling is native-only; legacy protocol fields are not supported.
|
||||
}
|
||||
|
||||
const generator = handler.createMessage(systemPrompt, messages, metadata as any)
|
||||
|
|
@ -661,7 +661,7 @@ describe("LiteLLMHandler", () => {
|
|||
|
||||
vi.spyOn(handler as any, "fetchModel").mockResolvedValue({
|
||||
id: "gpt-4",
|
||||
info: { ...litellmDefaultModelInfo, maxTokens: 8192, supportsNativeTools: true },
|
||||
info: { ...litellmDefaultModelInfo, maxTokens: 8192 },
|
||||
})
|
||||
|
||||
const systemPrompt = "You are a helpful assistant"
|
||||
|
|
@ -700,7 +700,7 @@ describe("LiteLLMHandler", () => {
|
|||
function: { name: "read_file", description: "Read a file", parameters: {} },
|
||||
},
|
||||
],
|
||||
toolProtocol: TOOL_PROTOCOL.NATIVE,
|
||||
// Tool calling is native-only; legacy protocol fields are not supported.
|
||||
}
|
||||
|
||||
const generator = handler.createMessage(systemPrompt, messages, metadata as any)
|
||||
|
|
|
|||
|
|
@ -80,9 +80,11 @@ describe("LmStudioHandler Native Tools", () => {
|
|||
}),
|
||||
}),
|
||||
]),
|
||||
parallel_tool_calls: false,
|
||||
}),
|
||||
)
|
||||
// parallel_tool_calls should be false when not explicitly set
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should include tool_choice when provided", async () => {
|
||||
|
|
@ -108,7 +110,7 @@ describe("LmStudioHandler Native Tools", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools and tool_choice in request (tools are always present after PR #10841)", async () => {
|
||||
mockCreate.mockImplementationOnce(() => ({
|
||||
[Symbol.asyncIterator]: async function* () {
|
||||
yield {
|
||||
|
|
@ -119,14 +121,15 @@ describe("LmStudioHandler Native Tools", () => {
|
|||
|
||||
const stream = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
await stream.next()
|
||||
|
||||
const callArgs = mockCreate.mock.calls[mockCreate.mock.calls.length - 1][0]
|
||||
expect(callArgs).not.toHaveProperty("tools")
|
||||
expect(callArgs).not.toHaveProperty("tool_choice")
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
expect(callArgs).toHaveProperty("tools")
|
||||
expect(callArgs).toHaveProperty("tool_choice")
|
||||
// parallel_tool_calls should be false when not explicitly set
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should yield tool_call_partial chunks during streaming", async () => {
|
||||
|
|
@ -280,7 +283,7 @@ describe("LmStudioHandler Native Tools", () => {
|
|||
expect(endChunks[0].id).toBe("call_lmstudio_test")
|
||||
})
|
||||
|
||||
it("should work with parallel tool calls disabled", async () => {
|
||||
it("should work with parallel tool calls disabled (sends false)", async () => {
|
||||
mockCreate.mockImplementationOnce(() => ({
|
||||
[Symbol.asyncIterator]: async function* () {
|
||||
yield {
|
||||
|
|
@ -296,11 +299,9 @@ describe("LmStudioHandler Native Tools", () => {
|
|||
})
|
||||
await stream.next()
|
||||
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
parallel_tool_calls: false,
|
||||
}),
|
||||
)
|
||||
// When parallelToolCalls is false, the parameter should be sent as false
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should handle reasoning content alongside tool calls", async () => {
|
||||
|
|
|
|||
|
|
@ -119,12 +119,17 @@ describe("MistralHandler", () => {
|
|||
const iterator = handler.createMessage(systemPrompt, messages)
|
||||
const result = await iterator.next()
|
||||
|
||||
expect(mockCreate).toHaveBeenCalledWith({
|
||||
model: mockOptions.apiModelId,
|
||||
messages: expect.any(Array),
|
||||
maxTokens: expect.any(Number),
|
||||
temperature: 0,
|
||||
})
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
model: mockOptions.apiModelId,
|
||||
messages: expect.any(Array),
|
||||
maxTokens: expect.any(Number),
|
||||
temperature: 0,
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
tools: expect.any(Array),
|
||||
toolChoice: "any",
|
||||
}),
|
||||
)
|
||||
|
||||
expect(result.value).toBeDefined()
|
||||
expect(result.done).toBe(false)
|
||||
|
|
@ -288,19 +293,19 @@ describe("MistralHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools in request (tools are always present after PR #10841)", async () => {
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: mockTools,
|
||||
toolProtocol: "xml",
|
||||
}
|
||||
|
||||
const iterator = handler.createMessage(systemPrompt, messages, metadata)
|
||||
await iterator.next()
|
||||
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
expect.objectContaining({
|
||||
tools: expect.any(Array),
|
||||
toolChoice: "any",
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
|
|
|||
|
|
@ -265,15 +265,14 @@ describe("NativeOllamaHandler", () => {
|
|||
})
|
||||
|
||||
describe("tool calling", () => {
|
||||
it("should include tools when model supports native tools", async () => {
|
||||
// Mock model with native tool support
|
||||
it("should include tools when tools are provided", async () => {
|
||||
// Model metadata should not gate tool inclusion; metadata.tools controls it.
|
||||
mockGetOllamaModels.mockResolvedValue({
|
||||
"llama3.2": {
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
},
|
||||
})
|
||||
|
||||
|
|
@ -341,15 +340,14 @@ describe("NativeOllamaHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when model does not support native tools", async () => {
|
||||
// Mock model without native tool support
|
||||
it("should include tools even when model metadata doesn't advertise tool support", async () => {
|
||||
// Model metadata should not gate tool inclusion; metadata.tools controls it.
|
||||
mockGetOllamaModels.mockResolvedValue({
|
||||
llama2: {
|
||||
contextWindow: 4096,
|
||||
maxTokens: 4096,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: false,
|
||||
},
|
||||
})
|
||||
|
||||
|
|
@ -379,23 +377,22 @@ describe("NativeOllamaHandler", () => {
|
|||
// consume stream
|
||||
}
|
||||
|
||||
// Verify tools were NOT passed
|
||||
// Verify tools were passed
|
||||
expect(mockChat).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
expect.objectContaining({
|
||||
tools: expect.any(Array),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
// Mock model with native tool support
|
||||
it("should not include tools when no tools are provided", async () => {
|
||||
// Model metadata should not gate tool inclusion; metadata.tools controls it.
|
||||
mockGetOllamaModels.mockResolvedValue({
|
||||
"llama3.2": {
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
},
|
||||
})
|
||||
|
||||
|
|
@ -412,21 +409,8 @@ describe("NativeOllamaHandler", () => {
|
|||
yield { message: { content: "Response" } }
|
||||
})
|
||||
|
||||
const tools = [
|
||||
{
|
||||
type: "function" as const,
|
||||
function: {
|
||||
name: "get_weather",
|
||||
description: "Get the weather",
|
||||
parameters: { type: "object", properties: {} },
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
const stream = handler.createMessage("System", [{ role: "user" as const, content: "Test" }], {
|
||||
taskId: "test",
|
||||
tools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
|
||||
// Consume the stream
|
||||
|
|
@ -434,7 +418,7 @@ describe("NativeOllamaHandler", () => {
|
|||
// consume stream
|
||||
}
|
||||
|
||||
// Verify tools were NOT passed (XML protocol forces XML format)
|
||||
// Verify tools were NOT passed
|
||||
expect(mockChat).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
|
|
@ -443,14 +427,13 @@ describe("NativeOllamaHandler", () => {
|
|||
})
|
||||
|
||||
it("should yield tool_call_partial when model returns tool calls", async () => {
|
||||
// Mock model with native tool support
|
||||
// Model metadata should not gate tool inclusion; metadata.tools controls it.
|
||||
mockGetOllamaModels.mockResolvedValue({
|
||||
"llama3.2": {
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
},
|
||||
})
|
||||
|
||||
|
|
@ -520,14 +503,13 @@ describe("NativeOllamaHandler", () => {
|
|||
})
|
||||
|
||||
it("should yield tool_call_end events after tool_call_partial chunks", async () => {
|
||||
// Mock model with native tool support
|
||||
// Model metadata should not gate tool inclusion; metadata.tools controls it.
|
||||
mockGetOllamaModels.mockResolvedValue({
|
||||
"llama3.2": {
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
},
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -72,7 +72,6 @@ describe("OpenAiCodexHandler native tool calls", () => {
|
|||
|
||||
const stream = handler.createMessage("system", [{ role: "user", content: "hello" } as any], {
|
||||
taskId: "t",
|
||||
toolProtocol: "native",
|
||||
tools: [],
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ import { OpenAiNativeHandler } from "../openai-native"
|
|||
import type { ApiHandlerOptions } from "../../../shared/api"
|
||||
|
||||
describe("OpenAiHandler native tools", () => {
|
||||
it("includes tools in request when custom model info lacks supportsNativeTools (regression test)", async () => {
|
||||
it("includes tools in request when tools are provided via metadata (regression test)", async () => {
|
||||
const mockCreate = vi.fn().mockImplementationOnce(() => ({
|
||||
[Symbol.asyncIterator]: async function* () {
|
||||
yield {
|
||||
|
|
@ -14,10 +14,8 @@ describe("OpenAiHandler native tools", () => {
|
|||
},
|
||||
}))
|
||||
|
||||
// Set openAiCustomModelInfo WITHOUT supportsNativeTools to simulate
|
||||
// a user-provided custom model info that doesn't specify native tool support.
|
||||
// The getModel() fix should merge NATIVE_TOOL_DEFAULTS to ensure
|
||||
// supportsNativeTools defaults to true.
|
||||
// Set openAiCustomModelInfo without any tool capability flags; tools should
|
||||
// still be passed whenever metadata.tools is present.
|
||||
const handler = new OpenAiHandler({
|
||||
openAiApiKey: "test-key",
|
||||
openAiBaseUrl: "https://example.com/v1",
|
||||
|
|
@ -49,17 +47,9 @@ describe("OpenAiHandler native tools", () => {
|
|||
},
|
||||
]
|
||||
|
||||
// Mimic the behavior in Task.attemptApiRequest() where tools are only
|
||||
// included when modelInfo.supportsNativeTools is true. This is the
|
||||
// actual regression path being tested - without the getModel() fix,
|
||||
// supportsNativeTools would be undefined and tools wouldn't be passed.
|
||||
const modelInfo = handler.getModel().info
|
||||
const supportsNativeTools = modelInfo.supportsNativeTools ?? false
|
||||
|
||||
const stream = handler.createMessage("system", [], {
|
||||
taskId: "test-task-id",
|
||||
...(supportsNativeTools && { tools }),
|
||||
...(supportsNativeTools && { toolProtocol: "native" as const }),
|
||||
tools,
|
||||
})
|
||||
await stream.next()
|
||||
|
||||
|
|
@ -71,13 +61,10 @@ describe("OpenAiHandler native tools", () => {
|
|||
function: expect.objectContaining({ name: "test_tool" }),
|
||||
}),
|
||||
]),
|
||||
parallel_tool_calls: false,
|
||||
}),
|
||||
expect.anything(),
|
||||
)
|
||||
// Verify parallel_tool_calls is NOT included when parallelToolCalls is not explicitly true
|
||||
// This is required for LiteLLM/Bedrock compatibility (see COM-406)
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).not.toHaveProperty("parallel_tool_calls")
|
||||
})
|
||||
})
|
||||
|
||||
|
|
@ -131,7 +118,6 @@ describe("OpenAiNativeHandler MCP tool schema handling", () => {
|
|||
const stream = handler.createMessage("system prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: mcpTools,
|
||||
toolProtocol: "native" as const,
|
||||
})
|
||||
|
||||
// Consume the stream
|
||||
|
|
@ -199,7 +185,6 @@ describe("OpenAiNativeHandler MCP tool schema handling", () => {
|
|||
const stream = handler.createMessage("system prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: regularTools,
|
||||
toolProtocol: "native" as const,
|
||||
})
|
||||
|
||||
// Consume the stream
|
||||
|
|
@ -281,7 +266,6 @@ describe("OpenAiNativeHandler MCP tool schema handling", () => {
|
|||
const stream = handler.createMessage("system prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: mcpToolsWithNestedObjects,
|
||||
toolProtocol: "native" as const,
|
||||
})
|
||||
|
||||
// Consume the stream
|
||||
|
|
|
|||
|
|
@ -221,45 +221,6 @@ describe("OpenAiNativeHandler", () => {
|
|||
expect(modelInfo.id).toBe("gpt-5.1-codex-max") // Default model
|
||||
expect(modelInfo.info).toBeDefined()
|
||||
})
|
||||
|
||||
it("should have defaultToolProtocol: native for all OpenAI Native models", () => {
|
||||
// Test that all models have defaultToolProtocol: native
|
||||
const testModels = [
|
||||
"gpt-5.1-codex-max",
|
||||
"gpt-5.2",
|
||||
"gpt-5.1",
|
||||
"gpt-5",
|
||||
"gpt-5-mini",
|
||||
"gpt-5-nano",
|
||||
"gpt-4.1",
|
||||
"gpt-4.1-mini",
|
||||
"gpt-4.1-nano",
|
||||
"o3",
|
||||
"o3-high",
|
||||
"o3-low",
|
||||
"o4-mini",
|
||||
"o4-mini-high",
|
||||
"o4-mini-low",
|
||||
"o3-mini",
|
||||
"o3-mini-high",
|
||||
"o3-mini-low",
|
||||
"o1",
|
||||
"o1-preview",
|
||||
"o1-mini",
|
||||
"gpt-4o",
|
||||
"gpt-4o-mini",
|
||||
"codex-mini-latest",
|
||||
]
|
||||
|
||||
for (const modelId of testModels) {
|
||||
const testHandler = new OpenAiNativeHandler({
|
||||
openAiNativeApiKey: "test-api-key",
|
||||
apiModelId: modelId,
|
||||
})
|
||||
const modelInfo = testHandler.getModel()
|
||||
expect(modelInfo.info.defaultToolProtocol).toBe("native")
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe("GPT-5 models", () => {
|
||||
|
|
|
|||
|
|
@ -633,11 +633,14 @@ describe("OpenAiHandler", () => {
|
|||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
temperature: 0,
|
||||
tools: undefined,
|
||||
tool_choice: undefined,
|
||||
parallel_tool_calls: false,
|
||||
},
|
||||
{ path: "/models/chat/completions" },
|
||||
)
|
||||
|
||||
// Verify max_tokens is NOT included when includeMaxTokens is not set
|
||||
// Verify max_tokens is NOT included when not explicitly set
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).not.toHaveProperty("max_completion_tokens")
|
||||
})
|
||||
|
|
@ -679,11 +682,14 @@ describe("OpenAiHandler", () => {
|
|||
{ role: "system", content: systemPrompt },
|
||||
{ role: "user", content: "Hello!" },
|
||||
],
|
||||
tools: undefined,
|
||||
tool_choice: undefined,
|
||||
parallel_tool_calls: false,
|
||||
},
|
||||
{ path: "/models/chat/completions" },
|
||||
)
|
||||
|
||||
// Verify max_tokens is NOT included when includeMaxTokens is not set
|
||||
// Verify max_tokens is NOT included when not explicitly set
|
||||
const callArgs = mockCreate.mock.calls[0][0]
|
||||
expect(callArgs).not.toHaveProperty("max_completion_tokens")
|
||||
})
|
||||
|
|
|
|||
|
|
@ -42,7 +42,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -66,7 +65,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 128000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 2.5,
|
||||
outputPrice: 10,
|
||||
description: "GPT-4o",
|
||||
|
|
@ -76,7 +74,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 15,
|
||||
outputPrice: 60,
|
||||
description: "OpenAI o1",
|
||||
|
|
@ -129,7 +126,6 @@ describe("OpenRouterHandler", () => {
|
|||
const result = await handler.fetchModel()
|
||||
expect(result.id).toBe("anthropic/claude-sonnet-4.5")
|
||||
expect(result.info.supportsPromptCache).toBe(true)
|
||||
expect(result.info.supportsNativeTools).toBe(true)
|
||||
})
|
||||
|
||||
it("honors custom maxTokens for thinking models", async () => {
|
||||
|
|
|
|||
|
|
@ -127,7 +127,7 @@ describe("QwenCodeHandler Native Tools", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools and tool_choice (tools are guaranteed to be present after ALWAYS_AVAILABLE_TOOLS)", async () => {
|
||||
mockCreate.mockImplementationOnce(() => ({
|
||||
[Symbol.asyncIterator]: async function* () {
|
||||
yield {
|
||||
|
|
@ -138,14 +138,14 @@ describe("QwenCodeHandler Native Tools", () => {
|
|||
|
||||
const stream = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
await stream.next()
|
||||
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
const callArgs = mockCreate.mock.calls[mockCreate.mock.calls.length - 1][0]
|
||||
expect(callArgs).not.toHaveProperty("tools")
|
||||
expect(callArgs).not.toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("tools")
|
||||
expect(callArgs).toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should yield tool_call_partial chunks during streaming", async () => {
|
||||
|
|
|
|||
|
|
@ -3,15 +3,12 @@
|
|||
import { Anthropic } from "@anthropic-ai/sdk"
|
||||
import OpenAI from "openai"
|
||||
|
||||
import { TOOL_PROTOCOL } from "@roo-code/types"
|
||||
|
||||
import { RequestyHandler } from "../requesty"
|
||||
import { ApiHandlerOptions } from "../../../shared/api"
|
||||
import { Package } from "../../../shared/package"
|
||||
import { ApiHandlerCreateMessageMetadata } from "../../index"
|
||||
|
||||
const mockCreate = vitest.fn()
|
||||
const mockResolveToolProtocol = vitest.fn()
|
||||
|
||||
vitest.mock("openai", () => {
|
||||
return {
|
||||
|
|
@ -27,10 +24,6 @@ vitest.mock("openai", () => {
|
|||
|
||||
vitest.mock("delay", () => ({ default: vitest.fn(() => Promise.resolve()) }))
|
||||
|
||||
vitest.mock("../../../utils/resolveToolProtocol", () => ({
|
||||
resolveToolProtocol: (...args: any[]) => mockResolveToolProtocol(...args),
|
||||
}))
|
||||
|
||||
vitest.mock("../fetchers/modelCache", () => ({
|
||||
getModels: vitest.fn().mockImplementation(() => {
|
||||
return Promise.resolve({
|
||||
|
|
@ -244,9 +237,7 @@ describe("RequestyHandler", () => {
|
|||
mockCreate.mockResolvedValue(mockStream)
|
||||
})
|
||||
|
||||
it("should include tools in request when toolProtocol is native", async () => {
|
||||
mockResolveToolProtocol.mockReturnValue(TOOL_PROTOCOL.NATIVE)
|
||||
|
||||
it("should include tools in request when tools are provided", async () => {
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: mockTools,
|
||||
|
|
@ -273,30 +264,7 @@ describe("RequestyHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is not native", async () => {
|
||||
mockResolveToolProtocol.mockReturnValue(TOOL_PROTOCOL.XML)
|
||||
|
||||
const metadata: ApiHandlerCreateMessageMetadata = {
|
||||
taskId: "test-task",
|
||||
tools: mockTools,
|
||||
tool_choice: "auto",
|
||||
}
|
||||
|
||||
const handler = new RequestyHandler(mockOptions)
|
||||
const iterator = handler.createMessage(systemPrompt, messages, metadata)
|
||||
await iterator.next()
|
||||
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.not.objectContaining({
|
||||
tools: expect.anything(),
|
||||
tool_choice: expect.anything(),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it("should handle tool_call_partial chunks in streaming response", async () => {
|
||||
mockResolveToolProtocol.mockReturnValue(TOOL_PROTOCOL.NATIVE)
|
||||
|
||||
const mockStreamWithToolCalls = {
|
||||
async *[Symbol.asyncIterator]() {
|
||||
yield {
|
||||
|
|
|
|||
|
|
@ -101,27 +101,22 @@ vitest.mock("../../providers/fetchers/modelCache", () => ({
|
|||
supportsPromptCache: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
defaultToolProtocol: "native",
|
||||
},
|
||||
"minimax/minimax-m2:free": {
|
||||
maxTokens: 32_768,
|
||||
contextWindow: 1_000_000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.15,
|
||||
outputPrice: 0.6,
|
||||
defaultToolProtocol: "native",
|
||||
},
|
||||
"anthropic/claude-haiku-4.5": {
|
||||
maxTokens: 8_192,
|
||||
contextWindow: 200_000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0.8,
|
||||
outputPrice: 4,
|
||||
defaultToolProtocol: "native",
|
||||
},
|
||||
}
|
||||
}
|
||||
|
|
@ -428,24 +423,12 @@ describe("RooHandler", () => {
|
|||
}
|
||||
})
|
||||
|
||||
it("should have defaultToolProtocol: native for all roo provider models", () => {
|
||||
// Test that all models have defaultToolProtocol: native
|
||||
const testModels = ["minimax/minimax-m2:free", "anthropic/claude-haiku-4.5", "xai/grok-code-fast-1"]
|
||||
for (const modelId of testModels) {
|
||||
const handlerWithModel = new RooHandler({ apiModelId: modelId })
|
||||
const modelInfo = handlerWithModel.getModel()
|
||||
expect(modelInfo.id).toBe(modelId)
|
||||
expect((modelInfo.info as any).defaultToolProtocol).toBe("native")
|
||||
}
|
||||
})
|
||||
|
||||
it("should return cached model info with settings applied from API", () => {
|
||||
const handlerWithMinimax = new RooHandler({
|
||||
apiModelId: "minimax/minimax-m2:free",
|
||||
})
|
||||
const modelInfo = handlerWithMinimax.getModel()
|
||||
// The settings from API should already be applied in the cached model info
|
||||
expect(modelInfo.info.supportsNativeTools).toBe(true)
|
||||
expect(modelInfo.info.inputPrice).toBe(0.15)
|
||||
expect(modelInfo.info.outputPrice).toBe(0.6)
|
||||
})
|
||||
|
|
|
|||
|
|
@ -15,7 +15,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -28,7 +27,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -41,7 +39,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: 3.75,
|
||||
|
|
@ -54,7 +51,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 128000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 5,
|
||||
outputPrice: 15,
|
||||
description: "GPT-4o",
|
||||
|
|
@ -64,7 +60,6 @@ vitest.mock("../fetchers/modelCache", () => ({
|
|||
contextWindow: 128000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 1,
|
||||
outputPrice: 3,
|
||||
description: "O3 Mini",
|
||||
|
|
@ -353,7 +348,7 @@ describe("UnboundHandler", () => {
|
|||
},
|
||||
]
|
||||
|
||||
it("should include tools in request when model supports native tools and tools are provided", async () => {
|
||||
it("should include tools in request when tools are provided", async () => {
|
||||
mockWithResponse.mockResolvedValueOnce({
|
||||
data: {
|
||||
[Symbol.asyncIterator]: () => ({
|
||||
|
|
@ -367,7 +362,6 @@ describe("UnboundHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
|
|
@ -405,7 +399,6 @@ describe("UnboundHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
tool_choice: "auto",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
@ -422,7 +415,7 @@ describe("UnboundHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools and tool_choice (tools are guaranteed to be present after ALWAYS_AVAILABLE_TOOLS)", async () => {
|
||||
mockWithResponse.mockResolvedValueOnce({
|
||||
data: {
|
||||
[Symbol.asyncIterator]: () => ({
|
||||
|
|
@ -435,14 +428,14 @@ describe("UnboundHandler", () => {
|
|||
|
||||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
const callArgs = mockCreate.mock.calls[mockCreate.mock.calls.length - 1][0]
|
||||
expect(callArgs).not.toHaveProperty("tools")
|
||||
expect(callArgs).not.toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("tools")
|
||||
expect(callArgs).toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should yield tool_call_partial chunks during streaming", async () => {
|
||||
|
|
@ -499,7 +492,6 @@ describe("UnboundHandler", () => {
|
|||
const stream = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
|
||||
const chunks = []
|
||||
|
|
@ -538,7 +530,6 @@ describe("UnboundHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
parallelToolCalls: true,
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
|
|||
|
|
@ -315,7 +315,6 @@ describe("VercelAiGatewayHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
|
|
@ -339,7 +338,6 @@ describe("VercelAiGatewayHandler", () => {
|
|||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
tool_choice: "auto",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
@ -351,13 +349,12 @@ describe("VercelAiGatewayHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should set parallel_tool_calls when toolProtocol is native", async () => {
|
||||
it("should set parallel_tool_calls when parallelToolCalls is enabled", async () => {
|
||||
const handler = new VercelAiGatewayHandler(mockOptions)
|
||||
|
||||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
parallelToolCalls: true,
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
|
@ -369,18 +366,18 @@ describe("VercelAiGatewayHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should default parallel_tool_calls to false", async () => {
|
||||
it("should include parallel_tool_calls: false by default", async () => {
|
||||
const handler = new VercelAiGatewayHandler(mockOptions)
|
||||
|
||||
const messageGenerator = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
expect(mockCreate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
tools: expect.any(Array),
|
||||
parallel_tool_calls: false,
|
||||
}),
|
||||
)
|
||||
|
|
@ -445,7 +442,6 @@ describe("VercelAiGatewayHandler", () => {
|
|||
const stream = handler.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "native",
|
||||
})
|
||||
|
||||
const chunks = []
|
||||
|
|
|
|||
|
|
@ -180,7 +180,7 @@ describe("VsCodeLmHandler", () => {
|
|||
})
|
||||
})
|
||||
|
||||
it("should handle tool calls as text when not using native tool protocol", async () => {
|
||||
it("should emit tool_call chunks when tools are provided", async () => {
|
||||
const systemPrompt = "You are a helpful assistant"
|
||||
const messages: Anthropic.Messages.MessageParam[] = [
|
||||
{
|
||||
|
|
@ -210,7 +210,27 @@ describe("VsCodeLmHandler", () => {
|
|||
})(),
|
||||
})
|
||||
|
||||
const stream = handler.createMessage(systemPrompt, messages)
|
||||
const tools = [
|
||||
{
|
||||
type: "function" as const,
|
||||
function: {
|
||||
name: "calculator",
|
||||
description: "A simple calculator",
|
||||
parameters: {
|
||||
type: "object",
|
||||
properties: {
|
||||
operation: { type: "string" },
|
||||
numbers: { type: "array", items: { type: "number" } },
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
tools,
|
||||
})
|
||||
const chunks = []
|
||||
for await (const chunk of stream) {
|
||||
chunks.push(chunk)
|
||||
|
|
@ -218,12 +238,14 @@ describe("VsCodeLmHandler", () => {
|
|||
|
||||
expect(chunks).toHaveLength(2) // Tool call chunk + usage chunk
|
||||
expect(chunks[0]).toEqual({
|
||||
type: "text",
|
||||
text: JSON.stringify({ type: "tool_call", ...toolCallData }),
|
||||
type: "tool_call",
|
||||
id: toolCallData.callId,
|
||||
name: toolCallData.name,
|
||||
arguments: JSON.stringify(toolCallData.arguments),
|
||||
})
|
||||
})
|
||||
|
||||
it("should handle native tool calls when using native tool protocol", async () => {
|
||||
it("should handle native tool calls when tools are provided", async () => {
|
||||
const systemPrompt = "You are a helpful assistant"
|
||||
const messages: Anthropic.Messages.MessageParam[] = [
|
||||
{
|
||||
|
|
@ -272,7 +294,6 @@ describe("VsCodeLmHandler", () => {
|
|||
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
toolProtocol: "native",
|
||||
tools,
|
||||
})
|
||||
const chunks = []
|
||||
|
|
@ -289,7 +310,7 @@ describe("VsCodeLmHandler", () => {
|
|||
})
|
||||
})
|
||||
|
||||
it("should pass tools to request options when using native tool protocol", async () => {
|
||||
it("should pass tools to request options when tools are provided", async () => {
|
||||
const systemPrompt = "You are a helpful assistant"
|
||||
const messages: Anthropic.Messages.MessageParam[] = [
|
||||
{
|
||||
|
|
@ -327,7 +348,6 @@ describe("VsCodeLmHandler", () => {
|
|||
|
||||
const stream = handler.createMessage(systemPrompt, messages, {
|
||||
taskId: "test-task",
|
||||
toolProtocol: "native",
|
||||
tools,
|
||||
})
|
||||
const chunks = []
|
||||
|
|
@ -376,10 +396,11 @@ describe("VsCodeLmHandler", () => {
|
|||
describe("getModel", () => {
|
||||
it("should return model info when client exists", async () => {
|
||||
const mockModel = { ...mockLanguageModelChat }
|
||||
;(vscode.lm.selectChatModels as Mock).mockResolvedValueOnce([mockModel])
|
||||
|
||||
// Initialize client
|
||||
await handler["getClient"]()
|
||||
// The handler starts async initialization in the constructor.
|
||||
// Make the test deterministic by explicitly (re)initializing here.
|
||||
;(vscode.lm.selectChatModels as Mock).mockResolvedValue([mockModel])
|
||||
handler["client"] = null
|
||||
await handler.initializeClient()
|
||||
|
||||
const model = handler.getModel()
|
||||
expect(model.id).toBe("test-model")
|
||||
|
|
@ -395,24 +416,24 @@ describe("VsCodeLmHandler", () => {
|
|||
expect(model.info).toBeDefined()
|
||||
})
|
||||
|
||||
it("should return supportsNativeTools and defaultToolProtocol in model info", async () => {
|
||||
it("should return basic model info when client exists", async () => {
|
||||
const mockModel = { ...mockLanguageModelChat }
|
||||
;(vscode.lm.selectChatModels as Mock).mockResolvedValueOnce([mockModel])
|
||||
|
||||
// Initialize client
|
||||
await handler["getClient"]()
|
||||
// The handler starts async initialization in the constructor.
|
||||
// Make the test deterministic by explicitly (re)initializing here.
|
||||
;(vscode.lm.selectChatModels as Mock).mockResolvedValue([mockModel])
|
||||
handler["client"] = null
|
||||
await handler.initializeClient()
|
||||
|
||||
const model = handler.getModel()
|
||||
expect(model.info.supportsNativeTools).toBe(true)
|
||||
expect(model.info.defaultToolProtocol).toBe("native")
|
||||
expect(model.info).toBeDefined()
|
||||
expect(model.info.contextWindow).toBe(4096)
|
||||
})
|
||||
|
||||
it("should return supportsNativeTools and defaultToolProtocol in fallback model info", () => {
|
||||
it("should return fallback model info when no client exists", () => {
|
||||
// Clear the client first
|
||||
handler["client"] = null
|
||||
const model = handler.getModel()
|
||||
expect(model.info.supportsNativeTools).toBe(true)
|
||||
expect(model.info.defaultToolProtocol).toBe("native")
|
||||
expect(model.info).toBeDefined()
|
||||
})
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -371,7 +371,7 @@ describe("XAIHandler", () => {
|
|||
)
|
||||
})
|
||||
|
||||
it("should not include tools when toolProtocol is xml", async () => {
|
||||
it("should always include tools and tool_choice (tools are guaranteed to be present after ALWAYS_AVAILABLE_TOOLS)", async () => {
|
||||
const handlerWithTools = new XAIHandler({ apiModelId: "grok-3" })
|
||||
|
||||
mockCreate.mockImplementationOnce(() => {
|
||||
|
|
@ -386,14 +386,14 @@ describe("XAIHandler", () => {
|
|||
|
||||
const messageGenerator = handlerWithTools.createMessage("test prompt", [], {
|
||||
taskId: "test-task-id",
|
||||
tools: testTools,
|
||||
toolProtocol: "xml",
|
||||
})
|
||||
await messageGenerator.next()
|
||||
|
||||
// Tools are now always present (minimum 6 from ALWAYS_AVAILABLE_TOOLS)
|
||||
const callArgs = mockCreate.mock.calls[mockCreate.mock.calls.length - 1][0]
|
||||
expect(callArgs).not.toHaveProperty("tools")
|
||||
expect(callArgs).not.toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("tools")
|
||||
expect(callArgs).toHaveProperty("tool_choice")
|
||||
expect(callArgs).toHaveProperty("parallel_tool_calls", false)
|
||||
})
|
||||
|
||||
it("should yield tool_call_partial chunks during streaming", async () => {
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ import {
|
|||
vertexDefaultModelId,
|
||||
vertexModels,
|
||||
ANTHROPIC_DEFAULT_MAX_TOKENS,
|
||||
TOOL_PROTOCOL,
|
||||
VERTEX_1M_CONTEXT_MODEL_IDS,
|
||||
} from "@roo-code/types"
|
||||
import { safeJsonParse } from "@roo-code/core"
|
||||
|
|
@ -19,7 +18,6 @@ import { ApiStream } from "../transform/stream"
|
|||
import { addCacheBreakpoints } from "../transform/caching/vertex"
|
||||
import { getModelParams } from "../transform/model-params"
|
||||
import { filterNonAnthropicBlocks } from "../transform/anthropic-filter"
|
||||
import { resolveToolProtocol } from "../../utils/resolveToolProtocol"
|
||||
import {
|
||||
convertOpenAIToolsToAnthropic,
|
||||
convertOpenAIToolChoiceToAnthropic,
|
||||
|
|
@ -77,22 +75,10 @@ export class AnthropicVertexHandler extends BaseProvider implements SingleComple
|
|||
// Filter out non-Anthropic blocks (reasoning, thoughtSignature, etc.) before sending to the API
|
||||
const sanitizedMessages = filterNonAnthropicBlocks(messages)
|
||||
|
||||
// Enable native tools using resolveToolProtocol (which checks model's defaultToolProtocol)
|
||||
// This matches the approach used in AnthropicHandler
|
||||
// Also exclude tools when tool_choice is "none" since that means "don't use tools"
|
||||
const toolProtocol = resolveToolProtocol(this.options, info, metadata?.toolProtocol)
|
||||
const shouldIncludeNativeTools =
|
||||
metadata?.tools &&
|
||||
metadata.tools.length > 0 &&
|
||||
toolProtocol === TOOL_PROTOCOL.NATIVE &&
|
||||
metadata?.tool_choice !== "none"
|
||||
|
||||
const nativeToolParams = shouldIncludeNativeTools
|
||||
? {
|
||||
tools: convertOpenAIToolsToAnthropic(metadata.tools!),
|
||||
tool_choice: convertOpenAIToolChoiceToAnthropic(metadata.tool_choice, metadata.parallelToolCalls),
|
||||
}
|
||||
: {}
|
||||
const nativeToolParams = {
|
||||
tools: convertOpenAIToolsToAnthropic(metadata?.tools ?? []),
|
||||
tool_choice: convertOpenAIToolChoiceToAnthropic(metadata?.tool_choice, metadata?.parallelToolCalls),
|
||||
}
|
||||
|
||||
/**
|
||||
* Vertex API has specific limitations for prompt caching:
|
||||
|
|
|
|||
|
|
@ -10,7 +10,6 @@ import {
|
|||
anthropicModels,
|
||||
ANTHROPIC_DEFAULT_MAX_TOKENS,
|
||||
ApiProviderError,
|
||||
TOOL_PROTOCOL,
|
||||
} from "@roo-code/types"
|
||||
import { TelemetryService } from "@roo-code/telemetry"
|
||||
|
||||
|
|
@ -19,7 +18,6 @@ import type { ApiHandlerOptions } from "../../shared/api"
|
|||
import { ApiStream } from "../transform/stream"
|
||||
import { getModelParams } from "../transform/model-params"
|
||||
import { filterNonAnthropicBlocks } from "../transform/anthropic-filter"
|
||||
import { resolveToolProtocol } from "../../utils/resolveToolProtocol"
|
||||
import { handleProviderError } from "./utils/error-handler"
|
||||
|
||||
import { BaseProvider } from "./base-provider"
|
||||
|
|
@ -74,24 +72,10 @@ export class AnthropicHandler extends BaseProvider implements SingleCompletionHa
|
|||
betas.push("context-1m-2025-08-07")
|
||||
}
|
||||
|
||||
// Enable native tools by default using resolveToolProtocol (which checks model's defaultToolProtocol)
|
||||
// This matches OpenRouter's approach of always including tools when provided
|
||||
// Also exclude tools when tool_choice is "none" since that means "don't use tools"
|
||||
// IMPORTANT: Use metadata.toolProtocol if provided (task's locked protocol) for consistency
|
||||
const model = this.getModel()
|
||||
const toolProtocol = resolveToolProtocol(this.options, model.info, metadata?.toolProtocol)
|
||||
const shouldIncludeNativeTools =
|
||||
metadata?.tools &&
|
||||
metadata.tools.length > 0 &&
|
||||
toolProtocol === TOOL_PROTOCOL.NATIVE &&
|
||||
metadata?.tool_choice !== "none"
|
||||
|
||||
const nativeToolParams = shouldIncludeNativeTools
|
||||
? {
|
||||
tools: convertOpenAIToolsToAnthropic(metadata.tools!),
|
||||
tool_choice: convertOpenAIToolChoiceToAnthropic(metadata.tool_choice, metadata.parallelToolCalls),
|
||||
}
|
||||
: {}
|
||||
const nativeToolParams = {
|
||||
tools: convertOpenAIToolsToAnthropic(metadata?.tools ?? []),
|
||||
tool_choice: convertOpenAIToolChoiceToAnthropic(metadata?.tool_choice, metadata?.parallelToolCalls),
|
||||
}
|
||||
|
||||
switch (modelId) {
|
||||
case "claude-sonnet-4-5":
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ import OpenAI from "openai"
|
|||
import type { ModelInfo } from "@roo-code/types"
|
||||
|
||||
import { type ApiHandlerOptions, getModelMaxOutputTokens } from "../../shared/api"
|
||||
import { XmlMatcher } from "../../utils/xml-matcher"
|
||||
import { TagMatcher } from "../../utils/tag-matcher"
|
||||
import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
|
||||
import { convertToOpenAiMessages } from "../transform/openai-format"
|
||||
|
||||
|
|
@ -93,11 +93,9 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
|
|||
messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
|
||||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
|
||||
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
|
||||
...(metadata?.toolProtocol === "native" && {
|
||||
parallel_tool_calls: metadata.parallelToolCalls ?? false,
|
||||
}),
|
||||
tools: this.convertToolsForOpenAI(metadata?.tools),
|
||||
tool_choice: metadata?.tool_choice,
|
||||
parallel_tool_calls: metadata?.parallelToolCalls ?? false,
|
||||
}
|
||||
|
||||
// Add thinking parameter if reasoning is enabled and model supports it
|
||||
|
|
@ -119,7 +117,7 @@ export abstract class BaseOpenAiCompatibleProvider<ModelName extends string>
|
|||
): ApiStream {
|
||||
const stream = await this.createStream(systemPrompt, messages, metadata)
|
||||
|
||||
const matcher = new XmlMatcher(
|
||||
const matcher = new TagMatcher(
|
||||
"think",
|
||||
(chunk) =>
|
||||
({
|
||||
|
|
|
|||
|
|
@ -359,15 +359,6 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
const modelConfig = this.getModel()
|
||||
const usePromptCache = Boolean(this.options.awsUsePromptCache && this.supportsAwsPromptCache(modelConfig))
|
||||
|
||||
// Determine early if native tools should be used (needed for message conversion)
|
||||
const supportsNativeTools = modelConfig.info.supportsNativeTools ?? false
|
||||
const useNativeTools =
|
||||
supportsNativeTools &&
|
||||
metadata?.tools &&
|
||||
metadata.tools.length > 0 &&
|
||||
metadata?.toolProtocol !== "xml" &&
|
||||
metadata?.tool_choice !== "none"
|
||||
|
||||
const conversationId =
|
||||
messages.length > 0
|
||||
? `conv_${messages[0].role}_${
|
||||
|
|
@ -383,7 +374,6 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
usePromptCache,
|
||||
modelConfig.info,
|
||||
conversationId,
|
||||
useNativeTools,
|
||||
)
|
||||
|
||||
let additionalModelRequestFields: BedrockAdditionalModelFields | undefined
|
||||
|
|
@ -424,29 +414,6 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
const is1MContextEnabled =
|
||||
BEDROCK_1M_CONTEXT_MODEL_IDS.includes(baseModelId as any) && this.options.awsBedrock1MContext
|
||||
|
||||
// Add anthropic_beta headers for various features
|
||||
// Start with an empty array and add betas as needed
|
||||
const anthropicBetas: string[] = []
|
||||
|
||||
// Add 1M context beta if enabled
|
||||
if (is1MContextEnabled) {
|
||||
anthropicBetas.push("context-1m-2025-08-07")
|
||||
}
|
||||
|
||||
// Add fine-grained tool streaming beta when native tools are used with Claude models
|
||||
// This enables proper tool use streaming for Anthropic models on Bedrock
|
||||
if (useNativeTools && baseModelId.includes("claude")) {
|
||||
anthropicBetas.push("fine-grained-tool-streaming-2025-05-14")
|
||||
}
|
||||
|
||||
// Apply anthropic_beta to additionalModelRequestFields if any betas are needed
|
||||
if (anthropicBetas.length > 0) {
|
||||
if (!additionalModelRequestFields) {
|
||||
additionalModelRequestFields = {} as BedrockAdditionalModelFields
|
||||
}
|
||||
additionalModelRequestFields.anthropic_beta = anthropicBetas
|
||||
}
|
||||
|
||||
// Determine if service tier should be applied (checked later when building payload)
|
||||
const useServiceTier =
|
||||
this.options.awsBedrockServiceTier && BEDROCK_SERVICE_TIER_MODEL_IDS.includes(baseModelId as any)
|
||||
|
|
@ -458,13 +425,32 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
})
|
||||
}
|
||||
|
||||
// Build tool configuration if native tools are enabled
|
||||
let toolConfig: ToolConfiguration | undefined
|
||||
if (useNativeTools && metadata?.tools) {
|
||||
toolConfig = {
|
||||
tools: this.convertToolsForBedrock(metadata.tools),
|
||||
toolChoice: this.convertToolChoiceForBedrock(metadata.tool_choice),
|
||||
// Add anthropic_beta headers for various features
|
||||
// Start with an empty array and add betas as needed
|
||||
const anthropicBetas: string[] = []
|
||||
|
||||
// Add 1M context beta if enabled
|
||||
if (is1MContextEnabled) {
|
||||
anthropicBetas.push("context-1m-2025-08-07")
|
||||
}
|
||||
|
||||
// Add fine-grained tool streaming beta for Claude models
|
||||
// This enables proper tool use streaming for Anthropic models on Bedrock
|
||||
if (baseModelId.includes("claude")) {
|
||||
anthropicBetas.push("fine-grained-tool-streaming-2025-05-14")
|
||||
}
|
||||
|
||||
// Apply anthropic_beta to additionalModelRequestFields if any betas are needed
|
||||
if (anthropicBetas.length > 0) {
|
||||
if (!additionalModelRequestFields) {
|
||||
additionalModelRequestFields = {} as BedrockAdditionalModelFields
|
||||
}
|
||||
additionalModelRequestFields.anthropic_beta = anthropicBetas
|
||||
}
|
||||
|
||||
const toolConfig: ToolConfiguration = {
|
||||
tools: this.convertToolsForBedrock(metadata?.tools ?? []),
|
||||
toolChoice: this.convertToolChoiceForBedrock(metadata?.tool_choice),
|
||||
}
|
||||
|
||||
// Build payload with optional service_tier at top level
|
||||
|
|
@ -478,7 +464,7 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
...(additionalModelRequestFields && { additionalModelRequestFields }),
|
||||
// Add anthropic_version at top level when using thinking features
|
||||
...(thinkingEnabled && { anthropic_version: "bedrock-2023-05-31" }),
|
||||
...(toolConfig && { toolConfig }),
|
||||
toolConfig,
|
||||
// Add service_tier as a top-level parameter (not inside additionalModelRequestFields)
|
||||
...(useServiceTier && { service_tier: this.options.awsBedrockServiceTier }),
|
||||
}
|
||||
|
|
@ -844,12 +830,9 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
|
|||
usePromptCache: boolean = false,
|
||||
modelInfo?: any,
|
||||
conversationId?: string, // Optional conversation ID to track cache points across messages
|
||||
useNativeTools: boolean = false, // Whether native tool calling is being used
|
||||
): { system: SystemContentBlock[]; messages: Message[] } {
|
||||
// First convert messages using shared converter for proper image handling
|
||||
const convertedMessages = sharedConverter(anthropicMessages as Anthropic.Messages.MessageParam[], {
|
||||
useNativeTools,
|
||||
})
|
||||
const convertedMessages = sharedConverter(anthropicMessages as Anthropic.Messages.MessageParam[])
|
||||
|
||||
// If prompt caching is disabled, return the converted messages directly
|
||||
if (!usePromptCache) {
|
||||
|
|
@ -1360,8 +1343,6 @@ Please verify:
|
|||
2. If using a provisioned model, check its throughput settings
|
||||
3. Contact AWS support to request a quota increase if needed
|
||||
|
||||
|
||||
|
||||
`,
|
||||
logLevel: "error",
|
||||
},
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ import type { ApiHandlerOptions } from "../../shared/api"
|
|||
import { calculateApiCostOpenAI } from "../../shared/cost"
|
||||
import { ApiStream } from "../transform/stream"
|
||||
import { convertToOpenAiMessages } from "../transform/openai-format"
|
||||
import { XmlMatcher } from "../../utils/xml-matcher"
|
||||
import { TagMatcher } from "../../utils/tag-matcher"
|
||||
|
||||
import type { ApiHandlerCreateMessageMetadata, SingleCompletionHandler } from "../index"
|
||||
import { BaseProvider } from "./base-provider"
|
||||
|
|
@ -125,13 +125,8 @@ export class CerebrasHandler extends BaseProvider implements SingleCompletionHan
|
|||
): ApiStream {
|
||||
const { id: model, info: modelInfo } = this.getModel()
|
||||
const max_tokens = modelInfo.maxTokens
|
||||
const supportsNativeTools = modelInfo.supportsNativeTools ?? false
|
||||
const temperature = this.options.modelTemperature ?? CEREBRAS_DEFAULT_TEMPERATURE
|
||||
|
||||
// Check if we should use native tool calling
|
||||
const useNativeTools =
|
||||
supportsNativeTools && metadata?.tools && metadata.tools.length > 0 && metadata?.toolProtocol !== "xml"
|
||||
|
||||
// Convert Anthropic messages to OpenAI format (Cerebras is OpenAI-compatible)
|
||||
const openaiMessages = convertToOpenAiMessages(messages)
|
||||
|
||||
|
|
@ -149,9 +144,9 @@ export class CerebrasHandler extends BaseProvider implements SingleCompletionHan
|
|||
}
|
||||
: {}),
|
||||
// Native tool calling support
|
||||
...(useNativeTools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
|
||||
...(useNativeTools && metadata.tool_choice && { tool_choice: metadata.tool_choice }),
|
||||
...(useNativeTools && { parallel_tool_calls: metadata?.parallelToolCalls ?? false }),
|
||||
tools: this.convertToolsForOpenAI(metadata?.tools),
|
||||
tool_choice: metadata?.tool_choice,
|
||||
parallel_tool_calls: metadata?.parallelToolCalls ?? false,
|
||||
}
|
||||
|
||||
try {
|
||||
|
|
@ -197,8 +192,8 @@ export class CerebrasHandler extends BaseProvider implements SingleCompletionHan
|
|||
throw new Error(t("common:errors.cerebras.noResponseBody"))
|
||||
}
|
||||
|
||||
// Initialize XmlMatcher to parse <think>...</think> tags
|
||||
const matcher = new XmlMatcher(
|
||||
// Initialize TagMatcher to parse <think>...</think> tags
|
||||
const matcher = new TagMatcher(
|
||||
"think",
|
||||
(chunk) =>
|
||||
({
|
||||
|
|
@ -240,7 +235,7 @@ export class CerebrasHandler extends BaseProvider implements SingleCompletionHan
|
|||
if (delta?.content) {
|
||||
const content = delta.content
|
||||
|
||||
// Use XmlMatcher to parse <think>...</think> tags
|
||||
// Use TagMatcher to parse <think>...</think> tags
|
||||
for (const chunk of matcher.update(content)) {
|
||||
yield chunk
|
||||
}
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ import OpenAI from "openai"
|
|||
|
||||
import type { ApiHandlerOptions } from "../../shared/api"
|
||||
import { getModelMaxOutputTokens } from "../../shared/api"
|
||||
import { XmlMatcher } from "../../utils/xml-matcher"
|
||||
import { TagMatcher } from "../../utils/tag-matcher"
|
||||
import { convertToR1Format } from "../transform/r1-format"
|
||||
import { convertToOpenAiMessages } from "../transform/openai-format"
|
||||
import { ApiStream } from "../transform/stream"
|
||||
|
|
@ -47,8 +47,8 @@ export class ChutesHandler extends RouterProvider implements SingleCompletionHan
|
|||
messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
|
||||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
...(metadata?.tools && { tools: metadata.tools }),
|
||||
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
|
||||
tools: metadata?.tools,
|
||||
tool_choice: metadata?.tool_choice,
|
||||
}
|
||||
|
||||
// Only add temperature if model supports it
|
||||
|
|
@ -72,7 +72,7 @@ export class ChutesHandler extends RouterProvider implements SingleCompletionHan
|
|||
messages: convertToR1Format([{ role: "user", content: systemPrompt }, ...messages]),
|
||||
})
|
||||
|
||||
const matcher = new XmlMatcher(
|
||||
const matcher = new TagMatcher(
|
||||
"think",
|
||||
(chunk) =>
|
||||
({
|
||||
|
|
|
|||
|
|
@ -144,19 +144,8 @@ export class ClaudeCodeHandler implements ApiHandler, SingleCompletionHandler {
|
|||
// Generate user_id metadata in the format required by Claude Code API
|
||||
const userId = generateUserId(email || undefined)
|
||||
|
||||
// Convert OpenAI tools to Anthropic format if provided and protocol is native
|
||||
// Exclude tools when tool_choice is "none" since that means "don't use tools"
|
||||
const shouldIncludeNativeTools =
|
||||
metadata?.tools &&
|
||||
metadata.tools.length > 0 &&
|
||||
metadata?.toolProtocol !== "xml" &&
|
||||
metadata?.tool_choice !== "none"
|
||||
|
||||
const anthropicTools = shouldIncludeNativeTools ? convertOpenAIToolsToAnthropic(metadata.tools!) : undefined
|
||||
|
||||
const anthropicToolChoice = shouldIncludeNativeTools
|
||||
? convertOpenAIToolChoice(metadata.tool_choice, metadata.parallelToolCalls)
|
||||
: undefined
|
||||
const anthropicTools = convertOpenAIToolsToAnthropic(metadata?.tools ?? [])
|
||||
const anthropicToolChoice = convertOpenAIToolChoice(metadata?.tool_choice, metadata?.parallelToolCalls)
|
||||
|
||||
// Determine reasoning effort and thinking configuration
|
||||
const reasoningLevel = this.getReasoningEffort(model.info)
|
||||
|
|
|
|||
|
|
@ -65,11 +65,6 @@ export class DeepInfraHandler extends RouterProvider implements SingleCompletion
|
|||
prompt_cache_key = _metadata.taskId
|
||||
}
|
||||
|
||||
// Check if model supports native tools and tools are provided with native protocol
|
||||
const supportsNativeTools = info.supportsNativeTools ?? false
|
||||
const useNativeTools =
|
||||
supportsNativeTools && _metadata?.tools && _metadata.tools.length > 0 && _metadata?.toolProtocol !== "xml"
|
||||
|
||||
const requestOptions: OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming = {
|
||||
model: modelId,
|
||||
messages: [{ role: "system", content: systemPrompt }, ...convertToOpenAiMessages(messages)],
|
||||
|
|
@ -77,9 +72,9 @@ export class DeepInfraHandler extends RouterProvider implements SingleCompletion
|
|||
stream_options: { include_usage: true },
|
||||
reasoning_effort,
|
||||
prompt_cache_key,
|
||||
...(useNativeTools && { tools: this.convertToolsForOpenAI(_metadata.tools) }),
|
||||
...(useNativeTools && _metadata.tool_choice && { tool_choice: _metadata.tool_choice }),
|
||||
...(useNativeTools && { parallel_tool_calls: _metadata?.parallelToolCalls ?? false }),
|
||||
tools: this.convertToolsForOpenAI(_metadata?.tools),
|
||||
tool_choice: _metadata?.tool_choice,
|
||||
parallel_tool_calls: _metadata?.parallelToolCalls ?? false,
|
||||
} as OpenAI.Chat.Completions.ChatCompletionCreateParamsStreaming
|
||||
|
||||
if (this.supportsTemperature(modelId)) {
|
||||
|
|
|
|||
|
|
@ -70,11 +70,9 @@ export class DeepSeekHandler extends OpenAiHandler {
|
|||
stream_options: { include_usage: true },
|
||||
// Enable thinking mode for deepseek-reasoner or when tools are used with thinking model
|
||||
...(isThinkingModel && { thinking: { type: "enabled" } }),
|
||||
...(metadata?.tools && { tools: this.convertToolsForOpenAI(metadata.tools) }),
|
||||
...(metadata?.tool_choice && { tool_choice: metadata.tool_choice }),
|
||||
...(metadata?.toolProtocol === "native" && {
|
||||
parallel_tool_calls: metadata.parallelToolCalls ?? false,
|
||||
}),
|
||||
tools: this.convertToolsForOpenAI(metadata?.tools),
|
||||
tool_choice: metadata?.tool_choice,
|
||||
parallel_tool_calls: metadata?.parallelToolCalls ?? false,
|
||||
}
|
||||
|
||||
// Add max_tokens if needed
|
||||
|
|
|
|||
|
|
@ -8,7 +8,7 @@ import { Anthropic } from "@anthropic-ai/sdk"
|
|||
import OpenAI from "openai"
|
||||
|
||||
import type { ApiHandlerOptions } from "../../shared/api"
|
||||
import { XmlMatcher } from "../../utils/xml-matcher"
|
||||
import { TagMatcher } from "../../utils/tag-matcher"
|
||||
import { convertToR1Format } from "../transform/r1-format"
|
||||
import { convertToOpenAiMessages } from "../transform/openai-format"
|
||||
import { ApiStream } from "../transform/stream"
|
||||
|
|
@ -63,7 +63,7 @@ export class FeatherlessHandler extends BaseOpenAiCompatibleProvider<Featherless
|
|||
messages: convertToR1Format([{ role: "user", content: systemPrompt }, ...messages]),
|
||||
})
|
||||
|
||||
const matcher = new XmlMatcher(
|
||||
const matcher = new TagMatcher(
|
||||
"think",
|
||||
(chunk) =>
|
||||
({
|
||||
|
|
|
|||
|
|
@ -51,7 +51,6 @@ describe("getChutesModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: false,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: "Chutes AI model: test/new-model",
|
||||
|
|
@ -162,7 +161,7 @@ describe("getChutesModels", () => {
|
|||
expect(models["test/image-model"].supportsImages).toBe(true)
|
||||
})
|
||||
|
||||
it("should detect native tool support from supported_features", async () => {
|
||||
it("should accept supported_features containing tools", async () => {
|
||||
const mockResponse = {
|
||||
data: {
|
||||
data: [
|
||||
|
|
@ -184,10 +183,11 @@ describe("getChutesModels", () => {
|
|||
|
||||
const models = await getChutesModels("test-api-key")
|
||||
|
||||
expect(models["test/tools-model"].supportsNativeTools).toBe(true)
|
||||
expect(models["test/tools-model"]).toBeDefined()
|
||||
expect(models["test/tools-model"].contextWindow).toBe(128000)
|
||||
})
|
||||
|
||||
it("should not enable native tool support when tools is not in supported_features", async () => {
|
||||
it("should accept supported_features without tools", async () => {
|
||||
const mockResponse = {
|
||||
data: {
|
||||
data: [
|
||||
|
|
@ -209,8 +209,8 @@ describe("getChutesModels", () => {
|
|||
|
||||
const models = await getChutesModels("test-api-key")
|
||||
|
||||
expect(models["test/no-tools-model"].supportsNativeTools).toBe(false)
|
||||
expect(models["test/no-tools-model"].defaultToolProtocol).toBeUndefined()
|
||||
expect(models["test/no-tools-model"]).toBeDefined()
|
||||
expect(models["test/no-tools-model"].contextWindow).toBe(128000)
|
||||
})
|
||||
|
||||
it("should skip empty objects in API response and still process valid models", async () => {
|
||||
|
|
@ -336,7 +336,6 @@ describe("getChutesModels", () => {
|
|||
// Both valid models should be processed
|
||||
expect(models["test/valid-1"]).toBeDefined()
|
||||
expect(models["test/valid-2"]).toBeDefined()
|
||||
expect(models["test/valid-2"].supportsNativeTools).toBe(true)
|
||||
|
||||
consoleErrorSpy.mockRestore()
|
||||
})
|
||||
|
|
|
|||
|
|
@ -222,7 +222,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -234,7 +233,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 10,
|
||||
outputPrice: 30,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -305,7 +303,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -318,7 +315,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -455,7 +451,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -468,7 +463,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -533,7 +527,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -546,7 +539,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -559,7 +551,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -673,7 +664,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -687,7 +677,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 128000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
@ -701,7 +690,6 @@ describe("getLiteLLMModels", () => {
|
|||
contextWindow: 100000,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: undefined,
|
||||
outputPrice: undefined,
|
||||
cacheWritesPrice: undefined,
|
||||
|
|
|
|||
|
|
@ -15,14 +15,13 @@ describe("modelEndpointCache", () => {
|
|||
|
||||
describe("getModelEndpoints", () => {
|
||||
it("should copy model-level capabilities from parent model to endpoints", async () => {
|
||||
// Mock the parent model data with native tools support
|
||||
// Mock the parent model data with capabilities
|
||||
const mockParentModels = {
|
||||
"anthropic/claude-sonnet-4": {
|
||||
maxTokens: 8192,
|
||||
contextWindow: 200000,
|
||||
supportsImages: true,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true, // Parent supports native tools
|
||||
supportsReasoningEffort: true,
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"] as any,
|
||||
inputPrice: 3,
|
||||
|
|
@ -39,7 +38,7 @@ describe("modelEndpointCache", () => {
|
|||
supportsPromptCache: true,
|
||||
inputPrice: 3,
|
||||
outputPrice: 15,
|
||||
// Note: No supportsNativeTools, supportsReasoningEffort, or supportedParameters
|
||||
// Note: No supportsReasoningEffort, or supportedParameters
|
||||
},
|
||||
"amazon-bedrock": {
|
||||
maxTokens: 8192,
|
||||
|
|
@ -61,11 +60,9 @@ describe("modelEndpointCache", () => {
|
|||
})
|
||||
|
||||
// Verify capabilities were copied from parent to ALL endpoints
|
||||
expect(result.anthropic.supportsNativeTools).toBe(true)
|
||||
expect(result.anthropic.supportsReasoningEffort).toBe(true)
|
||||
expect(result.anthropic.supportedParameters).toEqual(["max_tokens", "temperature", "reasoning"])
|
||||
|
||||
expect(result["amazon-bedrock"].supportsNativeTools).toBe(true)
|
||||
expect(result["amazon-bedrock"].supportsReasoningEffort).toBe(true)
|
||||
expect(result["amazon-bedrock"].supportedParameters).toEqual(["max_tokens", "temperature", "reasoning"])
|
||||
})
|
||||
|
|
@ -76,7 +73,6 @@ describe("modelEndpointCache", () => {
|
|||
maxTokens: 1000,
|
||||
contextWindow: 10000,
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: true,
|
||||
supportedParameters: ["max_tokens", "temperature"] as any,
|
||||
},
|
||||
}
|
||||
|
|
@ -131,9 +127,9 @@ describe("modelEndpointCache", () => {
|
|||
endpoint: "anthropic",
|
||||
})
|
||||
|
||||
// Should not crash, but capabilities will be undefined
|
||||
// Should not crash, but copied capabilities will be undefined
|
||||
expect(result.anthropic).toBeDefined()
|
||||
expect(result.anthropic.supportsNativeTools).toBeUndefined()
|
||||
expect(result.anthropic.supportedParameters).toBeUndefined()
|
||||
})
|
||||
|
||||
it("should return empty object for non-openrouter providers", async () => {
|
||||
|
|
|
|||
|
|
@ -22,7 +22,6 @@ describe("Ollama Fetcher", () => {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -47,7 +46,6 @@ describe("Ollama Fetcher", () => {
|
|||
contextWindow: 40960,
|
||||
supportsImages: false,
|
||||
supportsPromptCache: true,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
cacheWritesPrice: 0,
|
||||
|
|
@ -77,7 +75,7 @@ describe("Ollama Fetcher", () => {
|
|||
const parsedModel = parseOllamaModel(modelDataWithTools as any)
|
||||
|
||||
expect(parsedModel).not.toBeNull()
|
||||
expect(parsedModel!.supportsNativeTools).toBe(true)
|
||||
expect(parsedModel!.contextWindow).toBeGreaterThan(0)
|
||||
})
|
||||
|
||||
it("should return null when capabilities is undefined (no tool support)", () => {
|
||||
|
|
@ -114,7 +112,7 @@ describe("Ollama Fetcher", () => {
|
|||
|
||||
expect(parsedModel).not.toBeNull()
|
||||
expect(parsedModel!.supportsImages).toBe(true)
|
||||
expect(parsedModel!.supportsNativeTools).toBe(true)
|
||||
expect(parsedModel!.contextWindow).toBeGreaterThan(0)
|
||||
})
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -28,9 +28,7 @@ describe("OpenRouter API", () => {
|
|||
description: expect.any(String),
|
||||
supportsReasoningBudget: false,
|
||||
supportsReasoningEffort: false,
|
||||
supportsNativeTools: true,
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning", "include_reasoning"],
|
||||
defaultToolProtocol: "native",
|
||||
})
|
||||
|
||||
expect(models["anthropic/claude-3.7-sonnet:thinking"]).toEqual({
|
||||
|
|
@ -46,9 +44,7 @@ describe("OpenRouter API", () => {
|
|||
supportsReasoningBudget: true,
|
||||
requiredReasoningBudget: true,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: true,
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning", "include_reasoning"],
|
||||
defaultToolProtocol: "native",
|
||||
})
|
||||
|
||||
expect(models["google/gemini-2.5-flash-preview-05-20"].maxTokens).toEqual(65535)
|
||||
|
|
@ -136,7 +132,7 @@ describe("OpenRouter API", () => {
|
|||
cacheWritesPrice: 1.625,
|
||||
cacheReadsPrice: 0.31,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: false, // Gemini doesn't support native tools via "tools" parameter
|
||||
// Tool support is handled via metadata/tools at request time.
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"],
|
||||
},
|
||||
} as Record<string, any>
|
||||
|
|
@ -150,7 +146,6 @@ describe("OpenRouter API", () => {
|
|||
const parentModel = mockCachedModels["google/gemini-2.5-pro-preview"]
|
||||
if (parentModel) {
|
||||
for (const key of Object.keys(endpoints)) {
|
||||
endpoints[key].supportsNativeTools = parentModel.supportsNativeTools
|
||||
endpoints[key].supportsReasoningEffort = parentModel.supportsReasoningEffort
|
||||
endpoints[key].supportedParameters = parentModel.supportedParameters
|
||||
}
|
||||
|
|
@ -169,7 +164,6 @@ describe("OpenRouter API", () => {
|
|||
cacheReadsPrice: 0.31,
|
||||
description: undefined,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: false, // Copied from parent model
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"],
|
||||
},
|
||||
"google-ai-studio": {
|
||||
|
|
@ -184,7 +178,6 @@ describe("OpenRouter API", () => {
|
|||
cacheReadsPrice: 0.31,
|
||||
description: undefined,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: false, // Copied from parent model
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"],
|
||||
},
|
||||
})
|
||||
|
|
@ -221,7 +214,7 @@ describe("OpenRouter API", () => {
|
|||
},
|
||||
}
|
||||
|
||||
// Mock cached parent model with native tools support
|
||||
// Mock cached parent model capabilities
|
||||
const mockCachedModels = {
|
||||
"anthropic/claude-sonnet-4": {
|
||||
maxTokens: 8192,
|
||||
|
|
@ -234,7 +227,7 @@ describe("OpenRouter API", () => {
|
|||
cacheWritesPrice: 3.75,
|
||||
cacheReadsPrice: 0.3,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: true, // Anthropic supports native tools
|
||||
// Tool support is handled via metadata/tools at request time.
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"],
|
||||
},
|
||||
} as Record<string, any>
|
||||
|
|
@ -248,7 +241,6 @@ describe("OpenRouter API", () => {
|
|||
const parentModel = mockCachedModels["anthropic/claude-sonnet-4"]
|
||||
if (parentModel) {
|
||||
for (const key of Object.keys(endpoints)) {
|
||||
endpoints[key].supportsNativeTools = parentModel.supportsNativeTools
|
||||
endpoints[key].supportsReasoningEffort = parentModel.supportsReasoningEffort
|
||||
endpoints[key].supportedParameters = parentModel.supportedParameters
|
||||
}
|
||||
|
|
@ -266,7 +258,6 @@ describe("OpenRouter API", () => {
|
|||
description: undefined,
|
||||
supportsReasoningBudget: true,
|
||||
supportsReasoningEffort: true,
|
||||
supportsNativeTools: true, // Copied from parent model
|
||||
supportedParameters: ["max_tokens", "temperature", "reasoning"],
|
||||
})
|
||||
|
||||
|
|
@ -393,7 +384,7 @@ describe("OpenRouter API", () => {
|
|||
expect(imageResult.maxTokens).toBe(64000)
|
||||
})
|
||||
|
||||
it("sets defaultToolProtocol to native when model supports native tools", () => {
|
||||
it("treats supportedParameters containing tools as allowed", () => {
|
||||
const mockModel = {
|
||||
name: "Tools Model",
|
||||
description: "Model with native tool support",
|
||||
|
|
@ -414,11 +405,10 @@ describe("OpenRouter API", () => {
|
|||
supportedParameters: ["tools", "max_tokens", "temperature"],
|
||||
})
|
||||
|
||||
expect(resultWithTools.supportsNativeTools).toBe(true)
|
||||
expect(resultWithTools.defaultToolProtocol).toBe("native")
|
||||
expect(resultWithTools.supportedParameters).toContain("max_tokens")
|
||||
})
|
||||
|
||||
it("does not set defaultToolProtocol when model does not support native tools", () => {
|
||||
it("treats supportedParameters without tools as allowed", () => {
|
||||
const mockModel = {
|
||||
name: "No Tools Model",
|
||||
description: "Model without native tool support",
|
||||
|
|
@ -439,8 +429,7 @@ describe("OpenRouter API", () => {
|
|||
supportedParameters: ["max_tokens", "temperature"],
|
||||
})
|
||||
|
||||
expect(resultWithoutTools.supportsNativeTools).toBe(false)
|
||||
expect(resultWithoutTools.defaultToolProtocol).toBeUndefined()
|
||||
expect(resultWithoutTools.supportedParameters).toContain("max_tokens")
|
||||
})
|
||||
})
|
||||
})
|
||||
|
|
|
|||
|
|
@ -69,7 +69,6 @@ describe("getRooModels", () => {
|
|||
supportsImages: true,
|
||||
supportsReasoningEffort: true,
|
||||
requiredReasoningEffort: false,
|
||||
supportsNativeTools: false,
|
||||
supportsPromptCache: true,
|
||||
inputPrice: 100, // 0.0001 * 1_000_000
|
||||
outputPrice: 200, // 0.0002 * 1_000_000
|
||||
|
|
@ -78,7 +77,6 @@ describe("getRooModels", () => {
|
|||
description: "Fast coding model",
|
||||
deprecated: false,
|
||||
isFree: false,
|
||||
defaultToolProtocol: "native",
|
||||
},
|
||||
})
|
||||
})
|
||||
|
|
@ -119,7 +117,6 @@ describe("getRooModels", () => {
|
|||
supportsImages: false,
|
||||
supportsReasoningEffort: true,
|
||||
requiredReasoningEffort: true,
|
||||
supportsNativeTools: false,
|
||||
supportsPromptCache: false,
|
||||
inputPrice: 100, // 0.0001 * 1_000_000
|
||||
outputPrice: 200, // 0.0002 * 1_000_000
|
||||
|
|
@ -129,7 +126,7 @@ describe("getRooModels", () => {
|
|||
deprecated: false,
|
||||
isFree: false,
|
||||
defaultTemperature: undefined,
|
||||
defaultToolProtocol: "native",
|
||||
|
||||
isStealthModel: undefined,
|
||||
})
|
||||
})
|
||||
|
|
@ -169,7 +166,6 @@ describe("getRooModels", () => {
|
|||
supportsImages: false,
|
||||
supportsReasoningEffort: false,
|
||||
requiredReasoningEffort: false,
|
||||
supportsNativeTools: false,
|
||||
supportsPromptCache: false,
|
||||
inputPrice: 100, // 0.0001 * 1_000_000
|
||||
outputPrice: 200, // 0.0002 * 1_000_000
|
||||
|
|
@ -179,7 +175,7 @@ describe("getRooModels", () => {
|
|||
deprecated: false,
|
||||
isFree: false,
|
||||
defaultTemperature: undefined,
|
||||
defaultToolProtocol: "native",
|
||||
|
||||
isStealthModel: undefined,
|
||||
})
|
||||
})
|
||||
|
|
@ -551,7 +547,7 @@ describe("getRooModels", () => {
|
|||
expect(models["test/model-no-temp"].defaultTemperature).toBeUndefined()
|
||||
})
|
||||
|
||||
it("should set defaultToolProtocol to native when default-native-tools tag is present", async () => {
|
||||
it("should include models when tool-use tags are present", async () => {
|
||||
const mockResponse = {
|
||||
object: "list",
|
||||
data: [
|
||||
|
|
@ -581,11 +577,10 @@ describe("getRooModels", () => {
|
|||
|
||||
const models = await getRooModels(baseUrl, apiKey)
|
||||
|
||||
expect(models["test/native-tools-model"].supportsNativeTools).toBe(true)
|
||||
expect(models["test/native-tools-model"].defaultToolProtocol).toBe("native")
|
||||
expect(models["test/native-tools-model"]).toBeDefined()
|
||||
})
|
||||
|
||||
it("should set defaultToolProtocol to native for all models regardless of tags", async () => {
|
||||
it("handles models when tool tags are absent", async () => {
|
||||
const mockResponse = {
|
||||
object: "list",
|
||||
data: [
|
||||
|
|
@ -615,12 +610,10 @@ describe("getRooModels", () => {
|
|||
|
||||
const models = await getRooModels(baseUrl, apiKey)
|
||||
|
||||
// All Roo provider models now default to native tool protocol
|
||||
expect(models["test/model-without-tool-tags"].supportsNativeTools).toBe(false)
|
||||
expect(models["test/model-without-tool-tags"].defaultToolProtocol).toBe("native")
|
||||
expect(models["test/model-without-tool-tags"]).toBeDefined()
|
||||
})
|
||||
|
||||
it("should set supportsNativeTools from tool-use tag and always set defaultToolProtocol to native", async () => {
|
||||
it("handles models with tool-use tag", async () => {
|
||||
const mockResponse = {
|
||||
object: "list",
|
||||
data: [
|
||||
|
|
@ -650,9 +643,7 @@ describe("getRooModels", () => {
|
|||
|
||||
const models = await getRooModels(baseUrl, apiKey)
|
||||
|
||||
// tool-use tag sets supportsNativeTools, and all models get defaultToolProtocol: native
|
||||
expect(models["test/tool-use-model"].supportsNativeTools).toBe(true)
|
||||
expect(models["test/tool-use-model"].defaultToolProtocol).toBe("native")
|
||||
expect(models["test/tool-use-model"]).toBeDefined()
|
||||
})
|
||||
|
||||
it("should detect stealth mode from tags", async () => {
|
||||
|
|
|
|||
|
|
@ -173,7 +173,6 @@ describe("Vercel AI Gateway Fetchers", () => {
|
|||
maxTokens: 8000,
|
||||
contextWindow: 100000,
|
||||
supportsImages: false,
|
||||
supportsNativeTools: true,
|
||||
supportsPromptCache: false,
|
||||
inputPrice: 2500000,
|
||||
outputPrice: 10000000,
|
||||
|
|
|
|||
|
|
@ -197,14 +197,14 @@ describe("versionedSettings", () => {
|
|||
it("should handle versioned boolean values", () => {
|
||||
const versionedSettings: VersionedSettings = {
|
||||
"3.36.0": {
|
||||
supportsNativeTools: true,
|
||||
supportsReasoningEffort: true,
|
||||
},
|
||||
}
|
||||
|
||||
const resolved = resolveVersionedSettings(versionedSettings, currentVersion)
|
||||
|
||||
expect(resolved).toEqual({
|
||||
supportsNativeTools: true,
|
||||
supportsReasoningEffort: true,
|
||||
})
|
||||
})
|
||||
|
||||
|
|
|
|||
|
|
@ -57,8 +57,10 @@ export async function getChutesModels(apiKey?: string): Promise<Record<string, M
|
|||
continue
|
||||
}
|
||||
|
||||
const contextWindow = typeof m.context_length === "number" && Number.isFinite(m.context_length) ? m.context_length : undefined
|
||||
const maxModelLen = typeof m.max_model_len === "number" && Number.isFinite(m.max_model_len) ? m.max_model_len : undefined
|
||||
const contextWindow =
|
||||
typeof m.context_length === "number" && Number.isFinite(m.context_length) ? m.context_length : undefined
|
||||
const maxModelLen =
|
||||
typeof m.max_model_len === "number" && Number.isFinite(m.max_model_len) ? m.max_model_len : undefined
|
||||
|
||||
// Skip models without valid context window information
|
||||
if (!contextWindow) {
|
||||
|
|
@ -70,7 +72,6 @@ export async function getChutesModels(apiKey?: string): Promise<Record<string, M
|
|||
contextWindow,
|
||||
supportsImages: (m.input_modalities || []).includes("image"),
|
||||
supportsPromptCache: false,
|
||||
supportsNativeTools: (m.supported_features || []).includes("tools"),
|
||||
inputPrice: 0,
|
||||
outputPrice: 0,
|
||||
description: `Chutes AI model: ${m.id}`,
|
||||
|
|
|
|||
|
|
@ -58,7 +58,6 @@ export async function getDeepInfraModels(
|
|||
contextWindow,
|
||||
supportsImages: tags.includes("vision"),
|
||||
supportsPromptCache: tags.includes("prompt_cache"),
|
||||
supportsNativeTools: true,
|
||||
inputPrice: meta.pricing?.input_tokens,
|
||||
outputPrice: meta.pricing?.output_tokens,
|
||||
cacheReadsPrice: meta.pricing?.cache_read_tokens,
|
||||
|
|
|
|||
|
|
@ -45,7 +45,6 @@ export async function getLiteLLMModels(apiKey: string, baseUrl: string): Promise
|
|||
contextWindow: modelInfo.max_input_tokens || 200000,
|
||||
supportsImages: Boolean(modelInfo.supports_vision),
|
||||
supportsPromptCache: Boolean(modelInfo.supports_prompt_caching),
|
||||
supportsNativeTools: true,
|
||||
inputPrice: modelInfo.input_cost_per_token ? modelInfo.input_cost_per_token * 1000000 : undefined,
|
||||
outputPrice: modelInfo.output_cost_per_token
|
||||
? modelInfo.output_cost_per_token * 1000000
|
||||
|
|
|
|||
|
|
@ -68,7 +68,6 @@ export const getModelEndpoints = async ({
|
|||
// Copy model-level capabilities to all endpoints
|
||||
// Clone arrays to avoid shared mutable references
|
||||
for (const endpointKey of Object.keys(modelProviders)) {
|
||||
modelProviders[endpointKey].supportsNativeTools = parentModel.supportsNativeTools
|
||||
modelProviders[endpointKey].supportsReasoningEffort = parentModel.supportsReasoningEffort
|
||||
modelProviders[endpointKey].supportedParameters = parentModel.supportedParameters
|
||||
? [...parentModel.supportedParameters]
|
||||
|
|
|
|||
|
|
@ -42,13 +42,10 @@ export const parseOllamaModel = (rawModel: OllamaModelInfoResponse): ModelInfo |
|
|||
const contextWindow =
|
||||
contextKey && typeof rawModel.model_info[contextKey] === "number" ? rawModel.model_info[contextKey] : undefined
|
||||
|
||||
// Determine native tool support from capabilities array
|
||||
// The capabilities array is populated by Ollama based on model metadata
|
||||
const supportsNativeTools = rawModel.capabilities?.includes("tools") ?? false
|
||||
|
||||
// Filter out models that don't support native tools
|
||||
// This prevents users from selecting models that won't work properly with Roo Code's tool calling
|
||||
if (!supportsNativeTools) {
|
||||
// Filter out models that don't support tools.
|
||||
// Roo Code tool calling is native-only; models without tool capability won't work.
|
||||
const supportsTools = rawModel.capabilities?.includes("tools") ?? false
|
||||
if (!supportsTools) {
|
||||
return null
|
||||
}
|
||||
|
||||
|
|
@ -58,7 +55,6 @@ export const parseOllamaModel = (rawModel: OllamaModelInfoResponse): ModelInfo |
|
|||
supportsPromptCache: true,
|
||||
supportsImages: rawModel.capabilities?.includes("vision"),
|
||||
maxTokens: contextWindow || ollamaDefaultModelInfo.contextWindow,
|
||||
supportsNativeTools: true, // Only models with tools capability reach this point
|
||||
})
|
||||
|
||||
return modelInfo
|
||||
|
|
|
|||
|
|
@ -207,8 +207,6 @@ export const parseOpenRouterModel = ({
|
|||
|
||||
const supportsPromptCache = typeof cacheReadsPrice !== "undefined" // some models support caching but don't charge a cacheWritesPrice, e.g. GPT-5
|
||||
|
||||
const supportsNativeTools = supportedParameters ? supportedParameters.includes("tools") : undefined
|
||||
|
||||
const modelInfo: ModelInfo = {
|
||||
maxTokens: maxTokens || Math.ceil(model.context_length * 0.2),
|
||||
contextWindow: model.context_length,
|
||||
|
|
@ -220,10 +218,7 @@ export const parseOpenRouterModel = ({
|
|||
cacheReadsPrice,
|
||||
description: model.description,
|
||||
supportsReasoningEffort: supportedParameters ? supportedParameters.includes("reasoning") : undefined,
|
||||
supportsNativeTools,
|
||||
supportedParameters: supportedParameters ? supportedParameters.filter(isModelParameter) : undefined,
|
||||
// Default to native tool protocol when native tools are supported
|
||||
defaultToolProtocol: supportsNativeTools ? ("native" as const) : undefined,
|
||||
}
|
||||
|
||||
if (OPEN_ROUTER_REASONING_BUDGET_MODELS.has(id)) {
|
||||
|
|
|
|||
|
|
@ -38,8 +38,6 @@ export async function getRequestyModels(baseUrl?: string, apiKey?: string): Prom
|
|||
supportsImages: rawModel.supports_vision,
|
||||
supportsReasoningBudget: reasoningBudget,
|
||||
supportsReasoningEffort: reasoningEffort,
|
||||
supportsNativeTools: true,
|
||||
defaultToolProtocol: "native",
|
||||
inputPrice: parseApiPrice(rawModel.input_price),
|
||||
outputPrice: parseApiPrice(rawModel.output_price),
|
||||
description: rawModel.description,
|
||||
|
|
|
|||
|
|
@ -92,9 +92,6 @@ export async function getRooModels(baseUrl: string, apiKey?: string): Promise<Mo
|
|||
// Determine if the model requires reasoning effort based on tags
|
||||
const requiredReasoningEffort = tags.includes("reasoning-required")
|
||||
|
||||
// Determine if the model supports native tool calling based on tags
|
||||
const supportsNativeTools = tags.includes("tool-use")
|
||||
|
||||
// Determine if the model should hide vendor/company identity (stealth mode)
|
||||
const isStealthModel = tags.includes("stealth")
|
||||
|
||||
|
|
@ -111,7 +108,6 @@ export async function getRooModels(baseUrl: string, apiKey?: string): Promise<Mo
|
|||
supportsImages,
|
||||
supportsReasoningEffort,
|
||||
requiredReasoningEffort,
|
||||
supportsNativeTools,
|
||||
supportsPromptCache: Boolean(cacheReadPrice !== undefined),
|
||||
inputPrice,
|
||||
outputPrice,
|
||||
|
|
@ -121,7 +117,6 @@ export async function getRooModels(baseUrl: string, apiKey?: string): Promise<Mo
|
|||
deprecated: model.deprecated || false,
|
||||
isFree: tags.includes("free"),
|
||||
defaultTemperature: model.default_temperature,
|
||||
defaultToolProtocol: "native" as const,
|
||||
isStealthModel: isStealthModel || undefined,
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -23,7 +23,6 @@ export async function getUnboundModels(apiKey?: string | null): Promise<Record<s
|
|||
contextWindow: model?.contextWindow ? parseInt(model.contextWindow) : 0,
|
||||
supportsImages: model?.supportsImages ?? false,
|
||||
supportsPromptCache: model?.supportsPromptCaching ?? false,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: model?.inputTokenPrice ? parseFloat(model.inputTokenPrice) : undefined,
|
||||
outputPrice: model?.outputTokenPrice ? parseFloat(model.outputTokenPrice) : undefined,
|
||||
cacheWritesPrice: model?.cacheWritePrice ? parseFloat(model.cacheWritePrice) : undefined,
|
||||
|
|
|
|||
|
|
@ -106,7 +106,6 @@ export const parseVercelAiGatewayModel = ({ id, model }: { id: string; model: Ve
|
|||
contextWindow: model.context_window,
|
||||
supportsImages,
|
||||
supportsPromptCache,
|
||||
supportsNativeTools: true,
|
||||
inputPrice: parseApiPrice(model.pricing?.input),
|
||||
outputPrice: parseApiPrice(model.pricing?.output),
|
||||
cacheWritesPrice,
|
||||
|
|
|
|||
|
|
@ -93,8 +93,7 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
|
|||
// Gemini 3 validates thought signatures for tool/function calling steps.
|
||||
// We must round-trip the signature when tools are in use, even if the user chose
|
||||
// a minimal thinking level (or thinkingConfig is otherwise absent).
|
||||
const usingNativeTools = Boolean(metadata?.tools && metadata.tools.length > 0)
|
||||
const includeThoughtSignatures = Boolean(thinkingConfig) || usingNativeTools
|
||||
const includeThoughtSignatures = Boolean(thinkingConfig) || Boolean(metadata?.tools?.length)
|
||||
|
||||
// The message list can include provider-specific meta entries such as
|
||||
// `{ type: "reasoning", ... }` that are intended only for providers like
|
||||
|
|
@ -129,29 +128,19 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
|
|||
.map((message) => convertAnthropicMessageToGemini(message, { includeThoughtSignatures, toolIdToName }))
|
||||
.flat()
|
||||
|
||||
const tools: GenerateContentConfig["tools"] = []
|
||||
|
||||
// Google built-in tools (Grounding, URL Context) are currently mutually exclusive
|
||||
// with function declarations in the Gemini API. If native function calling is
|
||||
// used (Agent tools), we must prioritize it and skip built-in tools to avoid
|
||||
// "Tool use with function calling is unsupported" (HTTP 400) errors.
|
||||
if (metadata?.tools && metadata.tools.length > 0) {
|
||||
tools.push({
|
||||
functionDeclarations: metadata.tools.map((tool) => ({
|
||||
// Tools are always present (minimum ALWAYS_AVAILABLE_TOOLS).
|
||||
// Google built-in tools (Grounding, URL Context) are mutually exclusive
|
||||
// with function declarations in the Gemini API, so we always use
|
||||
// function declarations when tools are provided.
|
||||
const tools: GenerateContentConfig["tools"] = [
|
||||
{
|
||||
functionDeclarations: (metadata?.tools ?? []).map((tool) => ({
|
||||
name: (tool as any).function.name,
|
||||
description: (tool as any).function.description,
|
||||
parametersJsonSchema: (tool as any).function.parameters,
|
||||
})),
|
||||
})
|
||||
} else {
|
||||
if (this.options.enableUrlContext) {
|
||||
tools.push({ urlContext: {} })
|
||||
}
|
||||
|
||||
if (this.options.enableGrounding) {
|
||||
tools.push({ googleSearch: {} })
|
||||
}
|
||||
}
|
||||
},
|
||||
]
|
||||
|
||||
// Determine temperature respecting model capabilities and defaults:
|
||||
// - If supportsTemperature is explicitly false, ignore user overrides
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Reference in a new issue