跳到主要内容

Class: TextCompletionAdapter

Defined in: provider-sdk/src/adapters/textCompletion.ts:65

A provider that can generate completions and optionally speech, images and transcriptions (ТЗ §4.3). Text generation is the base capability; the other modalities are optional so an LLM-only adapter stays a valid provider.

Implements​

Constructors​

Constructor​

new TextCompletionAdapter(config): TextCompletionAdapter

Defined in: provider-sdk/src/adapters/textCompletion.ts:73

Parameters​

config​

ProviderRuntimeConfig

Returns​

TextCompletionAdapter

Properties​

capabilities​

readonly capabilities: object

Defined in: provider-sdk/src/adapters/textCompletion.ts:67

Optional generation-wire capabilities. Plugin adapters must opt in before a connection profile can use the respective feature; the host never silently drops a persisted profile override.

assistantPrefill​

readonly assistantPrefill: true = true

textCompletion​

readonly textCompletion: true = true

Implementation of​

ProviderAdapter.capabilities

kind​

readonly kind: "text-completion" = 'text-completion'

Defined in: provider-sdk/src/adapters/textCompletion.ts:66

Stable provider kind, e.g. "openai-compatible".

Implementation of​

ProviderAdapter.kind

Methods​

countTokens()​

countTokens(request): Promise<TokenCount>

Defined in: provider-sdk/src/adapters/textCompletion.ts:330

Approximate counting over the serialized prompt. Local text-completion models rarely ship a bundled tokenizer, so the count is explicitly marked approximate (AGENTS.md §10).

Parameters​

request​

TokenCountRequest

Returns​

Promise<TokenCount>

Implementation of​

ProviderAdapter.countTokens

generate()​

generate(request, signal): AsyncIterable<{ chatId: string; messages: object[]; meta: {[key: string]: unknown; }; requestId: string; responseToken: string; type: "plugin_intercept"; } | { requestId: string; type: "start"; } | { text: string; type: "delta"; } | { text: string; type: "done"; usage?: { completionTokens: number; promptTokens: number; totalTokens: number; }; } | { code: string; message: string; type: "error"; }>

Defined in: provider-sdk/src/adapters/textCompletion.ts:143

Generate a completion, streaming unified events. Exactly one terminal event (done or error) is yielded. Must abort promptly on signal.

Parameters​

request​
assistantPrefill?​

string

Provider-neutral assistant prefill. Adapters serialize it as the beginning of the assistant turn; the host prepends it to the streamed/saved reply. Plugin adapters must explicitly opt in before a connection profile using this field can be applied.

frequencyPenalty?​

number

maxTokens​

number

messages​

object[]

minP?​

number

model​

string

presencePenalty?​

number

reasoning?​

boolean

reasoningEffort?​

"none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max"

repetitionPenalty?​

number

seed?​

number

stop?​

string[]

stream​

boolean

temperature​

number

topA?​

number

topK?​

number

topP?​

number

signal​

AbortSignal

Returns​

AsyncIterable<{ chatId: string; messages: object[]; meta: {[key: string]: unknown; }; requestId: string; responseToken: string; type: "plugin_intercept"; } | { requestId: string; type: "start"; } | { text: string; type: "delta"; } | { text: string; type: "done"; usage?: { completionTokens: number; promptTokens: number; totalTokens: number; }; } | { code: string; message: string; type: "error"; }>

Implementation of​

ProviderAdapter.generate

listModels()​

listModels(signal): Promise<object[]>

Defined in: provider-sdk/src/adapters/textCompletion.ts:113

List available models. Must respect the abort signal.

Parameters​

signal​

AbortSignal

Returns​

Promise<object[]>

Implementation of​

ProviderAdapter.listModels

validateConfig()​

validateConfig(): Promise<ValidationResult>

Defined in: provider-sdk/src/adapters/textCompletion.ts:106

Validate provider configuration without performing network calls.

Returns​

Promise<ValidationResult>

Implementation of​

ProviderAdapter.validateConfig