QVeris
快速入门实践指南命令行工具Python SDK 指南Python SDK API 参考TypeScript SDK 指南TypeScript SDK API 参考MCP 服务器REST API 参考编辑器与命令行配置OpenClaw 配置Codex 与 ChatGPT 桌面端配置Claude Code 配置OpenCode 配置
<!-- qveris-sdk-release: js-sdk-v0.6.0 -->

@qverisai/sdk

TypeScript SDK API 参考

本页根据 package 公开导出和源码注释自动生成。安装、认证与完整工作流请参阅 TypeScript SDK 指南。

类

ApiKeyCredentialProvider

A credential provider backed by a static QVeris API key.

实现

构造函数

构造函数

new ApiKeyCredentialProvider(apiKey): ApiKeyCredentialProvider

参数
apiKey

string

返回

ApiKeyCredentialProvider

方法

getCredential()

getCredential(_context): Promise<string>

参数
_context

CredentialContext

返回

Promise<string>

实现了

CredentialProvider.getCredential

Qveris

QVeris API client.

示例

import { Qveris } from '@qverisai/sdk';

const qveris = new Qveris({ apiKey: process.env.QVERIS_API_KEY! });

const found = await qveris.discover('stock price market data API', { limit: 5 });
const tool = found.results[0];

const outcome = await qveris.call(tool.tool_id, {
  searchId: found.search_id,
  parameters: { symbol: 'AAPL' },
});

构造函数

构造函数

new Qveris(config): Qveris

参数
config

QverisClientOptions

返回

Qveris

访问器

rateLimitRetryCount
Getter 签名

get rateLimitRetryCount(): number

How many times the client has backed off on a rate-limited (429) / transient (503) response so far. Rate-limit backoff is retried pressure, not failure — observe this rather than counting the retried responses.

返回

number

方法

call()

call(toolId, options): Promise<ExecuteResponse>

Call a capability. The response may include pre-settlement billing; final charges are reflected in usage() and ledger().

参数
toolId

string

options

CallOptions

返回

Promise<ExecuteResponse>

credits()

credits(): Promise<CreditsResponse>

Get current credit balance and bucket details.

返回

Promise<CreditsResponse>

discover()

discover(query, options?): Promise<SearchResponse>

Discover capabilities from a natural-language query. Free.

参数
query

string

options?

DiscoverOptions = {}

返回

Promise<SearchResponse>

inspect()

inspect(toolIds, options?): Promise<SearchResponse>

Inspect capabilities by id to get current parameter schemas. Free. An empty id list resolves locally without a network request.

参数
toolIds

string | string[]

options?

InspectOptions = {}

返回

Promise<SearchResponse>

ledger()

ledger(filters?): Promise<CreditsLedgerResponse>

Query final credits ledger entries.

参数
filters?

CreditsLedgerRequest = {}

返回

Promise<CreditsLedgerResponse>

probe()

probe(toolId, options?): Promise<ProbeResponse>

Validate candidate parameters and request a zero-cost quote without executing the capability.

参数
toolId

string

options?

ProbeOptions = {}

返回

Promise<ProbeResponse>

usage()

usage(filters?): Promise<UsageEventsResponse>

Query request-level usage audit history.

参数
filters?

UsageHistoryRequest = {}

返回

Promise<UsageEventsResponse>

fromEnv()

static fromEnv(overrides?): Qveris

Create a client from the QVERIS_API_KEY environment variable. An explicit baseUrl override takes priority over QVERIS_BASE_URL.

参数
overrides?

Omit<QverisClientOptions, "apiKey" | "credentialProvider">

返回

Qveris

QverisApiError

Error thrown for any failed QVeris API interaction: HTTP errors, failure envelopes, timeouts, and network failures.

Carries the same shape as the wire-level ApiError so callers can branch on status and inspect observability for diagnostics.

继承

  • Error

实现

构造函数

构造函数

new QverisApiError(error): QverisApiError

参数
error

ApiError

返回

QverisApiError

重写了

Error.constructor

属性

cause?

readonly optional cause?: string

Lower-level transport or runtime cause when available

实现了

ApiError.cause

重写了

Error.cause

details?

readonly optional details?: unknown

Original error details if available

实现了

ApiError.details

message

message: string

Error message

实现了

ApiError.message

继承自

Error.message

name

name: string

继承自

Error.name

observability?

readonly optional observability?: ApiObservability

Request metadata for diagnosing API failures

实现了

ApiError.observability

stack?

optional stack?: string

继承自

Error.stack

status

readonly status: number

HTTP status code (0 for network errors, 408 for timeouts)

实现了

ApiError.status

stackTraceLimit

static stackTraceLimit: number

The Error.stackTraceLimit property specifies the number of stack frames collected by a stack trace (whether generated by new Error().stack or Error.captureStackTrace(obj)).

The default value is 10 but may be set to any valid JavaScript number. Changes will affect any stack trace captured after the value has been changed.

If set to a non-number value, or set to a negative number, stack traces will not capture any frames.

继承自

Error.stackTraceLimit

方法

captureStackTrace()

static captureStackTrace(targetObject, constructorOpt?): void

Creates a .stack property on targetObject, which when accessed returns a string representing the location in the code at which Error.captureStackTrace() was called.

const myObject = {};
Error.captureStackTrace(myObject);
myObject.stack;  // Similar to `new Error().stack`

The first line of the trace will be prefixed with ${myObject.name}: ${myObject.message}.

The optional constructorOpt argument accepts a function. If given, all frames above constructorOpt, including constructorOpt, will be omitted from the generated stack trace.

The constructorOpt argument is useful for hiding implementation details of error generation from the user. For instance:

function a() {
  b();
}

function b() {
  c();
}

function c() {
  // Create an error without stack trace to avoid calculating the stack trace twice.
  const { stackTraceLimit } = Error;
  Error.stackTraceLimit = 0;
  const error = new Error();
  Error.stackTraceLimit = stackTraceLimit;

  // Capture the stack trace above function b
  Error.captureStackTrace(error, b); // Neither function c, nor b is included in the stack trace
  throw error;
}

a();
参数
targetObject

object

constructorOpt?

Function

返回

void

继承自

Error.captureStackTrace

prepareStackTrace()

static prepareStackTrace(err, stackTraces): any

参数
err

Error

stackTraces

CallSite[]

返回

any

参阅

https://v8.dev/docs/stack-trace-api#customizing-stack-traces

继承自

Error.prepareStackTrace

接口

ApiEnvelope

类型参数

T

T

属性

data

data: T

message?

optional message?: string

status

status: string

status_code?

optional status_code?: number

ApiError

属性

cause?

optional cause?: string

Lower-level transport or runtime cause when available.

details?

optional details?: unknown

Original error details if available

message

message: string

Error message

observability?

optional observability?: ApiObservability

Request metadata for diagnosing API/provider/tool-chain failures.

status

status: number

HTTP status code

ApiObservability

属性

endpoint

endpoint: string

error_type?

optional error_type?: ApiErrorType

http_status?

optional http_status?: number

method

method: "GET" | "POST"

operation

operation: ApiOperation

query_params?

optional query_params?: Record<string, string>

request_id?

optional request_id?: string

source

source: "qveris_api"

timeout_ms

timeout_ms: number

url

url: string

BillingChargeLine

属性

amount_credits?

optional amount_credits?: number | null

component_key

component_key: string

description?

optional description?: string | null

is_adjustment?

optional is_adjustment?: boolean | null

price?

optional price?: BillingPrice | null

quantity?

optional quantity?: number | null

unit?

optional unit?: string | null

unit_label?

optional unit_label?: string | null

BillingPrice

属性

amount_credits

amount_credits: number

per?

optional per?: number | null

unit?

optional unit?: string | null

unit_label?

optional unit_label?: string | null

BillingRule

属性

billing_unit?

optional billing_unit?: string

billing_unit_label?

optional billing_unit_label?: string

description?

optional description?: string

metering_mode?

optional metering_mode?: string

minimum_charge_credits?

optional minimum_charge_credits?: number | null

price?

optional price?: BillingPrice | null

price_breakdown?

optional price_breakdown?: Record<string, unknown>[] | null

pricing_dimensions?

optional pricing_dimensions?: Record<string, unknown>[] | null

pricing_source_system?

optional pricing_source_system?: string | null

runtime_pricing_version?

optional runtime_pricing_version?: string | null

snapshot_id?

optional snapshot_id?: number | null

snapshot_version?

optional snapshot_version?: string | null

CallOptions

Options for Qveris.call.

属性

maxResponseSize?

optional maxResponseSize?: number

Max response bytes before truncation (-1 for no limit, server default 20480)

parameters

parameters: Record<string, unknown>

Key-value parameters matching the tool's parameter schema

respondWith?

optional respondWith?: "full" | `fields:${string}` | "summary"

Server-side result projection. Omit for the legacy/full response.

searchId?

optional searchId?: string

The search_id from the discover call that returned this tool

sessionId?

optional sessionId?: string

Session identifier for tracking

timeoutMs?

optional timeoutMs?: number

Per-request timeout override in milliseconds (default 120s)

CompactBillingStatement

属性

charge_lines?

optional charge_lines?: BillingChargeLine[] | null

list_amount_credits?

optional list_amount_credits?: number | null

minimum_charge_credits?

optional minimum_charge_credits?: number | null

price?

optional price?: BillingPrice | null

quantity?

optional quantity?: number | null

requested_amount_credits?

optional requested_amount_credits?: number | null

summary?

optional summary?: string | null

CredentialContext

Context supplied whenever the client requests a credential.

属性

resource

resource: string

API resource the credential will be sent to.

scopes

scopes: readonly string[]

Requested authorization scopes. Empty until a public scope contract is available.

CredentialProvider

Supplies a bearer credential for an API request.

方法

getCredential()

getCredential(context): string | Promise<string>

参数
context

CredentialContext

返回

string | Promise<string>

CreditsLedgerItem

属性

amount_credits

amount_credits: number

balance_after?

optional balance_after?: Record<string, unknown> | null

balance_before?

optional balance_before?: Record<string, unknown> | null

created_at

created_at: string

description?

optional description?: string | null

entry_type

entry_type: string

id

id: string

ledger_metadata?

optional ledger_metadata?: Record<string, unknown> | null

pre_settlement_bill?

optional pre_settlement_bill?: Record<string, unknown> | null

settlement_result?

optional settlement_result?: Record<string, unknown> | null

source_ref_id?

optional source_ref_id?: string | null

source_ref_type?

optional source_ref_type?: string | null

source_system

source_system: string

CreditsLedgerRequest

属性

bucket?

optional bucket?: string

direction?

optional direction?: string

end_date?

optional end_date?: string

entry_type?

optional entry_type?: string

limit?

optional limit?: number

max_credits?

optional max_credits?: number

min_credits?

optional min_credits?: number

page?

optional page?: number

page_size?

optional page_size?: number

start_date?

optional start_date?: string

summary?

optional summary?: boolean

CreditsLedgerResponse

属性

items

items: CreditsLedgerItem[]

page

page: number

page_size

page_size: number

summary?

optional summary?: Record<string, unknown> | null

total

total: number

CreditsResponse

属性

daily_free?

optional daily_free?: Record<string, unknown>

invite_reward?

optional invite_reward?: Record<string, unknown>

purchased?

optional purchased?: Record<string, unknown>

remaining_credits

remaining_credits: number

welcome_bonus?

optional welcome_bonus?: Record<string, unknown>

DiscoverOptions

Options for Qveris.discover.

属性

lang?

optional lang?: "zh" | "en"

Response language. Omit to use server-side language negotiation.

limit?

optional limit?: number

Maximum number of results (1-100, server default 20)

sessionId?

optional sessionId?: string

Session identifier for tracking

timeoutMs?

optional timeoutMs?: number

Per-request timeout override in milliseconds

view?

optional view?: "routing" | "full"

Response projection. Omit for the legacy/full response shape.

ExecuteRequest

Request body for the Execute Tool API.

属性

max_response_size?

optional max_response_size?: number

Maximum size of response data in bytes. If the tool generates data longer than this, it will be truncated and a download URL will be provided for the full content. Minimum: -1 (-1 means no limit).

默认值
20480 (20KB)
parameters

parameters: Record<string, unknown>

Key-value pairs of parameters to pass to the tool. Must match the parameter schema from the tool's definition.

respond_with?

optional respond_with?: "full" | `fields:${string}` | "summary"

Server-side result projection. Omit for the legacy/full response.

search_id

search_id: string

The search_id from the search that returned this tool. Links the execution to the original search for analytics and billing.

session_id?

optional session_id?: string

Session identifier for tracking user sessions.

ExecuteResponse

Response from the Execute Tool API.

属性

billing?

optional billing?: CompactBillingStatement

Structured pre-settlement billing statement when available

cost?

optional cost?: number

Legacy fallback estimate; use usage audit or credits ledger for final charge

created_at?

optional created_at?: string

Timestamp of execution (ISO 8601 format)

elapsed_time_ms?

optional elapsed_time_ms?: number

Execution duration in milliseconds (alternative field)

error_message?

optional error_message?: string | null

Error message if execution failed. Common reasons: insufficient balance, quota exceeded, invalid parameters.

execution_id

execution_id: string

Unique identifier for this execution record

execution_time?

optional execution_time?: number

Execution duration in seconds

parameters?

optional parameters?: Record<string, unknown>

The parameters that were passed to the tool

pre_settlement_bill?

optional pre_settlement_bill?: Record<string, unknown>

Legacy/full pre-settlement bill snapshot when returned directly

remaining_credits?

optional remaining_credits?: number

User's remaining credits after this execution

result?

optional result?: ExecuteResult

The execution result. Contains either data (if within size limit) or truncation info.

success

success: boolean

Whether the execution completed successfully

tool_id?

optional tool_id?: string

The tool that was executed

ExecuteResultData

Result data when the response fits within max_response_size.

属性

data

data: unknown

The actual result data from the tool execution

ExecuteResultFields

Selected result fields returned by a fields:<JSONPath,...> projection.

属性

data?

optional data?: unknown

respond_with

respond_with: `fields:${string}`

ExecuteResultSummary

Compact result returned by respond_with: "summary".

属性

content_schema?

optional content_schema?: Record<string, unknown>

full_content_file_url?

optional full_content_file_url?: string

message?

optional message?: string

respond_with

respond_with: "summary"

summary?

optional summary?: object

索引签名

[key: string]: unknown

fields?

optional fields?: string[]

row_count?

optional row_count?: number

size_bytes?

optional size_bytes?: number

ExecuteResultTruncated

Result data when the response exceeds max_response_size. Provides truncated content and a URL to download the full result.

属性

content_schema?

optional content_schema?: Record<string, unknown>

JSON Schema describing the structure of the full content. Helps the agent understand the data shape without downloading.

full_content_file_url

full_content_file_url: string

URL to download the complete result file. Valid for 120 minutes.

message

message: string

Explanation message about the truncation

truncated_content

truncated_content: string

The initial portion of the response (max_response_size bytes). Useful for previewing the data structure.

GetToolsByIdsRequest

Request body for the Get Tools by IDs API.

属性

search_id?

optional search_id?: string

The search_id from the search that returned the tool(s).

session_id?

optional session_id?: string

Session identifier for tracking user sessions.

tool_ids

tool_ids: string[]

Array of tool IDs to retrieve information for.

InspectOptions

Options for Qveris.inspect.

属性

searchId?

optional searchId?: string

The search_id from the discover call that returned the tool(s)

sessionId?

optional sessionId?: string

Session identifier for tracking

timeoutMs?

optional timeoutMs?: number

Per-request timeout override in milliseconds

ProbeOptions

Options for Qveris.probe.

属性

checks?

optional checks?: ProbeCheck[]

Checks to run. Defaults to schema.

liveBudget?

optional liveBudget?: ProbeLiveBudget

Probe budget. Every current value avoids capability execution.

parameters?

optional parameters?: Record<string, unknown>

Candidate parameters to validate without executing the capability.

timeoutMs?

optional timeoutMs?: number

Per-request timeout override in milliseconds.

ProbeQuoteResult

属性

basis?

optional basis?: string | null

currency

currency: "credits"

detail?

optional detail?: Record<string, unknown> | null

estimate_credits?

optional estimate_credits?: number | null

exact

exact: boolean

ProbeRequest

属性

checks?

optional checks?: ProbeCheck[]

live_budget?

optional live_budget?: ProbeLiveBudget

parameters?

optional parameters?: Record<string, unknown>

ProbeResponse

属性

coverage?

optional coverage?: ProbeUnknownResult

quote?

optional quote?: ProbeQuoteResult

sample?

optional sample?: ProbeUnknownResult

schema?

optional schema?: ProbeSchemaResult

ProbeSchemaResult

属性

note?

optional note?: string | null

valid

valid: boolean

violations?

optional violations?: ProbeSchemaViolation[] | null

ProbeSchemaViolation

属性

message

message: string

param?

optional param?: string | null

type

type: string

ProbeUnknownResult

属性

reason

reason: string

verdict

verdict: "unknown"

QverisClientConfig

Configuration options for the Qveris API client.

属性

apiKey

apiKey: string

API authentication token

baseUrl?

optional baseUrl?: string

API base URL. Overrides QVERIS_BASE_URL and the built-in default.

maxRetries?

optional maxRetries?: number

Max automatic retries for rate-limited (429) / transient (503) responses. Honors Retry-After, otherwise backs off exponentially with jitter. Defaults to 3; set to 0 to disable.

timeoutMs?

optional timeoutMs?: number

Default request timeout in milliseconds

SearchRequest

Request body for the Search Tools API.

属性

lang?

optional lang?: "zh" | "en"

Response language. Omit to use server-side language negotiation.

limit?

optional limit?: number

Maximum number of results to return. Minimum: 1. Maximum: 100.

默认值
20
query

query: string

Natural language search query describing the tool capability you need.

session_id?

optional session_id?: string

Session identifier for tracking user sessions.

view?

optional view?: "routing" | "full"

Response projection. Omit for the legacy/full response shape.

SearchResponse

Response from the Search Tools API.

属性

elapsed_time_ms?

optional elapsed_time_ms?: number

Total elapsed time in milliseconds

query?

optional query?: string

The original search query

remaining_credits?

optional remaining_credits?: number

User's remaining credits after this operation

results

results: ToolInfo[]

Array of matching tools

search_id

search_id: string

Unique identifier for this search. Required when calling call for any tool from these results.

stats?

optional stats?: SearchStats

Search performance statistics

total?

optional total?: number

Total number of results returned

SearchStats

Performance statistics for a search operation.

属性

fulltext_recall_count?

optional fulltext_recall_count?: number

Fulltext recall count

search_time_ms?

optional search_time_ms?: number

Total time to complete the search in milliseconds

vector_recall_count?

optional vector_recall_count?: number

Vector recall count

ToolCapability

Standardized capability descriptor attached to a tool (e.g. "MKT.BARS.ADJUSTED" with market coverage tags).

属性

id?

optional id?: string

tag?

optional tag?: ToolCapabilityTag[]

ToolCapabilityTag

Coverage tag attached to a capability (e.g. market coverage).

属性

description?

optional description?: string

id?

optional id?: string

name?

optional name?: string

type?

optional type?: string

ToolCategory

Category/tag attached to a tool. Current API responses return category objects; legacy responses returned plain strings, so ToolInfo.categories accepts both.

属性

description?

optional description?: string

name?

optional name?: string

slug?

optional slug?: string

ToolExamples

Example usage for a tool, showing sample parameters.

属性

sample_parameters?

optional sample_parameters?: Record<string, unknown>

Sample parameter values demonstrating typical usage

ToolInfo

Information about a tool returned from search results. Contains everything needed to understand and execute the tool.

属性

as_of_support?

optional as_of_support?: boolean

Whether the capability supports point-in-time requests.

billing_rule?

optional billing_rule?: BillingRule

Structured rule-level billing metadata when available

capabilities?

optional capabilities?: ToolCapability[]

Standardized capability descriptors with coverage tags

capability?

optional capability?: string

Compact capability label returned by the routing projection.

categories?

optional categories?: (string | ToolCategory)[]

Tool categories/tags: category objects, or plain strings in legacy responses

cost_class?

optional cost_class?: string

Compact cost class returned by the routing projection.

description?

optional description?: string

Detailed description of what the tool does

docs_url?

optional docs_url?: string

Documentation URL for the tool

examples?

optional examples?: ToolExamples

Usage examples with sample parameters

expected_cost?

optional expected_cost?: string | number

Pre-call cost estimate in credits, when available

final_score?

optional final_score?: number

Relevance score for the search query (0.0 - 1.0, higher = better match)

has_last_execution?

optional has_last_execution?: boolean

Whether this tool has been executed before (verified in production)

last_execution_record?

optional last_execution_record?: Record<string, unknown>

Most recent execution record, if available

name?

optional name?: string

Human-readable display name

params?

optional params?: ToolParameter[]

List of parameters the tool accepts

protocol?

optional protocol?: string

Protocol type

provider_description?

optional provider_description?: string

Description of the provider

provider_id?

optional provider_id?: string

Provider identifier

provider_name?

optional provider_name?: string

Name of the organization/service providing this tool

provider_website_url?

optional provider_website_url?: string

Provider website URL

region?

optional region?: string

Geographic availability of the tool.

  • "global" - Available worldwide
  • "US|CA" - Whitelist: only available in US and Canada
  • "-CN|RU" - Blacklist: not available in China and Russia
reliability?

optional reliability?: string

Compact reliability grade returned by the routing projection.

stats?

optional stats?: ToolStats

Historical execution performance statistics

tool_id

tool_id: string

Unique identifier for the tool (used in call)

why_recommended?

optional why_recommended?: string

Human-readable explanation of why this tool was recommended (Discover results only)

ToolParameter

Parameter definition for a tool.

属性

description

description: string

Human-readable description of what this parameter does

enum?

optional enum?: string[]

If present, restricts valid values to this list

name

name: string

Parameter name (used as key in the parameters object)

required

required: boolean

Whether this parameter must be provided

type

type: "string" | "number" | "boolean" | "object" | "array"

Data type of the parameter

ToolStats

Historical execution performance statistics for a tool.

属性

avg_execution_time_ms?

optional avg_execution_time_ms?: number

Historical average execution time in milliseconds

cost?

optional cost?: number

Legacy fallback estimate in credits per call

success_rate?

optional success_rate?: number

Historical success rate (0.0 - 1.0)

UsageEventItem

属性

actual_amount_credits?

optional actual_amount_credits?: number | null

billing_snapshot_status?

optional billing_snapshot_status?: string | null

billing_summary?

optional billing_summary?: string | null

charge_outcome?

optional charge_outcome?: string | null

created_at

created_at: string

credits_ledger_entry_id?

optional credits_ledger_entry_id?: string | null

display_target?

optional display_target?: string | null

error_message?

optional error_message?: string | null

event_type

event_type: string

execution_id?

optional execution_id?: string | null

id

id: string

kind?

optional kind?: string | null

model?

optional model?: string | null

pre_settlement_amount_credits?

optional pre_settlement_amount_credits?: number | null

pre_settlement_bill?

optional pre_settlement_bill?: Record<string, unknown> | null

query?

optional query?: string | null

requested_amount_credits?

optional requested_amount_credits?: number | null

search_id?

optional search_id?: string | null

session_id?

optional session_id?: string | null

settled_amount_credits?

optional settled_amount_credits?: number | null

settlement_result?

optional settlement_result?: Record<string, unknown> | null

source_ref_id?

optional source_ref_id?: string | null

source_ref_type?

optional source_ref_type?: string | null

source_system

source_system: string

success

success: boolean

tool_id?

optional tool_id?: string | null

UsageEventsResponse

属性

items

items: UsageEventItem[]

page

page: number

page_size

page_size: number

summary?

optional summary?: Record<string, unknown> | null

total

total: number

UsageHistoryRequest

属性

bucket?

optional bucket?: string

charge_outcome?

optional charge_outcome?: string

end_date?

optional end_date?: string

event_type?

optional event_type?: string

execution_id?

optional execution_id?: string

kind?

optional kind?: string

limit?

optional limit?: number

max_credits?

optional max_credits?: number

min_credits?

optional min_credits?: number

page?

optional page?: number

page_size?

optional page_size?: number

search_id?

optional search_id?: string

start_date?

optional start_date?: string

success?

optional success?: boolean

summary?

optional summary?: boolean

类型别名

ApiErrorType

ApiErrorType = "http_error" | "invalid_json" | "timeout" | "network_error"

ApiOperation

ApiOperation = "discover" | "inspect" | "probe" | "call" | "credits" | "usage_history" | "credits_ledger"

Error response from the Qveris API.

ExecuteResult

ExecuteResult = ExecuteResultData | ExecuteResultTruncated | ExecuteResultSummary | ExecuteResultFields | unknown[] | string | number | boolean | null

Union type for execution results (either full data or truncated).

ProbeCheck

ProbeCheck = "schema" | "quote" | "coverage" | "sample"

ProbeLiveBudget

ProbeLiveBudget = "none" | "metadata" | "sampled"

QverisClientOptions

QverisClientOptions = Omit<QverisClientConfig, "apiKey"> & { apiKey: string; credentialProvider?: never; } | { apiKey?: never; credentialProvider: CredentialProvider; }

Configuration accepted by the QVeris REST client.

函数

getQverisTools()

getQverisTools(qveris, options?): object

Build Vercel AI SDK tools for the QVeris discover/inspect/call workflow.

参数

qveris

Qveris

The Qveris client to route calls through.

options?

Optional sessionId for correlation/pricing context.

sessionId?

string

返回

object

A tools object keyed by qveris_discover / qveris_inspect / qveris_call, ready to pass to generateText/streamText.

qveris_call

qveris_call: object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object | never

qveris_discover

qveris_discover: object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object | never

qveris_inspect

qveris_inspect: never | object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object | never | object & object & object & object & object