@molecule/api-ai-zhipu | Molecule.dev

Auto-generated, AI-first package reference for the molecule.dev ecosystem. It is written to be read by coding agents as much as by people, and is generated from this package's source — edit src/index.ts JSDoc, not this file.

Zhipu GLM AI provider for molecule.dev.

Type

provider

Installation

npm install @molecule/api-ai-zhipu @molecule/api-ai @molecule/api-bond @molecule/api-i18n @molecule/api-secrets

API

Interfaces

`ProcessEnv`

Process Env interface.

interface ProcessEnv {
  ZHIPU_API_KEY: string
  /** Base URL override (for credential brokers / gateways / US OpenAI-compatible hosts). */
  ZHIPU_BASE_URL?: string
  /** Chat-completions path override (see {@link ZhipuConfig.completionsPath}). */
  ZHIPU_COMPLETIONS_PATH?: string
}

`ZhipuConfig`

Configuration for Zhipu.

interface ZhipuConfig {
  /** Called on each rate-limited/overloaded upstream response, before any retry sleep. */
  onRateLimit?: AiRateLimitCallback
  /** API key. Defaults to ZHIPU_API_KEY env var. */
  apiKey?: string
  /** Default model. Defaults to 'glm-5.3'. */
  defaultModel?: string
  /** Maximum tokens for completions. */
  maxTokens?: number
  /** Base URL override (for proxies). Defaults to 'https://open.bigmodel.cn/api/paas'. */
  baseUrl?: string
  /**
   * Chat-completions path appended to {@link baseUrl}. Defaults to
   * `/v4/chat/completions` (Zhipu-native). Set to `/chat/completions` when the
   * GLM open weights are served from a US OpenAI-compatible host (DeepInfra:
   * baseUrl='https://api.deepinfra.com/v1/openai').
   */
  completionsPath?: string
  /**
   * Catalog-id → upstream-model-id map, applied to the outbound request only, so
   * a US host (DeepInfra) receives its namespaced id (`zai-org/GLM-5.2`) while
   * pricing/cost/display keep the canonical catalog id (`glm-5.2`).
   */
  modelMap?: Record<string, string>
  /**
   * Whether the upstream host serves Zhipu's provider-side server tools
   * (`web_search`). Defaults to `true` (the native z.ai/bigmodel endpoint).
   * Set to `false` for OpenAI-compatible re-hosts of the open weights
   * (DeepInfra), which run the model only — a server-tool entry in `tools`
   * is rejected there (HTTP 422) and would fail the whole request, so the
   * provider drops `params.serverTools` instead of forwarding them.
   */
  supportsServerTools?: boolean
}

Functions

`createProvider(config)`

Creates a Zhipu GLM AI provider instance.

function createProvider(config?: ZhipuConfig): AIProvider

config — Zhipu-specific configuration (API key, model, max tokens, base URL).

Returns: An AIProvider backed by the Zhipu Chat Completions API.

Constants

`aiZhipuSecretDefinitions`

Secret definitions required by the Zhipu AI bond.

const aiZhipuSecretDefinitions: SecretDefinition[]

`provider`

The provider implementation.

const provider: AIProvider

Core Interface

Implements @molecule/api-ai interface.

Bond Wiring

Setup function to register this provider with the bond system:

import { bond } from '@molecule/api-bond'
import { provider } from '@molecule/api-ai-zhipu'

export function setupAiZhipu(): void {
  bond('ai', 'zhipu', provider)
}

Injection Notes

Requirements

Peer dependencies:

@molecule/api-ai ^1.0.1
@molecule/api-bond ^1.0.1
@molecule/api-i18n ^1.0.1
@molecule/api-secrets ^1.0.1

Environment Variables

ZHIPU_API_KEY (required) — Zhipu AI API key
- Setup: Create an API key in the Zhipu AI (BigModel) user center.
- Get it here: https://open.bigmodel.cn/usercenter/apikeys

Runtime Dependencies

@molecule/api-ai
@molecule/api-bond
@molecule/api-i18n
@molecule/api-secrets

Config: ZHIPU_API_KEY (SERVER-side only) plus an optional default model id/base URL.

Missing ZHIPU_API_KEY fails fast: the provider throws naming the exact env var on first use (the exported provider is a lazy proxy, so this fires on the first chat() call, not at bond/module-load time) — it never silently sends an empty key.

Error message disambiguation: a plain 400 that ISN'T a context-length error (bad param, malformed tool schema) gets its own non-retryable message distinct from the generic "AI service error. Please try again." used for retryable failures.

E2E Tests

Integration checklist — drive the real UI (live preview, no mocks), adapt each item to this app's actual chat/AI screens, and check every box off one by one. A box you can't check is an integration bug to fix — not a skip. The sandbox HAS an AI provider bonded, so the flow runs live end-to-end; AI output is NON-DETERMINISTIC, so assert on STRUCTURE/behavior, not exact text:

A message sent through the real chat UI comes back as a RELEVANT AI reply — not an echo of the prompt, a hardcoded stub, or an empty bubble. Ask something with a checkable answer (e.g. "What is 2 + 2?") and confirm the response actually contains it ("4"), proving a live model answered.
If the app streams, tokens render INCREMENTALLY — text grows word by word in the UI, not one final blob dumped after a long frozen spinner. (A streamed chat() yields text chunks then a final done; a single late blob means the reply was awaited whole and streaming is broken.)
Multi-turn CONTEXT is preserved: a follow-up that refers back to the previous turn (e.g. after "2 + 2", ask "now double that" -> understood as 8) works — proving the full messages history is sent, not just the last line.
A provider failure (bad/missing key, rate limit, timeout) surfaces as a graceful in-UI error message, NOT a crash, blank screen, a spinner that never resolves, or an unhandled 500. Force one and watch the UI recover.
The provider key + the provider call are SERVER-side only: the key never reaches the browser (check the network tab, the JS bundle, and page globals), and no route proxies arbitrary prompts to the model without auth
- a token cap — an open AI endpoint is an unbounded bill and abuse vector.

`@molecule/api-ai-zhipu`

How it works

Reference