Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

feat(image-recognition): independent key/url/model defaults

Browse Source 
Make the HTTP vision provider's configuration independent of the main chat
model: the API key default moves from DEEPSEEK_API_KEY to IMAGE_RECOGNITION_API_KEY,
and the URL and model get image-recognition-specific defaults (Aliyun DashScope
compatible-mode and qwen3-vl-flash) instead of the chat model's deepseek-v4-flash.
The provider fails loud when no model is configured.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Pine
2026-08-14 20:45:35 +08:00
parent e87a3084ea
commit 6890e87021
4 changed files with 27 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/vision/image-recognition-http/README.md
+3 -3
View File
@@ -8,10 +8,10 @@ URL and returns the recognized text.
| Key | Type | Meaning |
|---|---|---|
| `baseURL` | string | Endpoint base; `/chat/completions` is appended. Blank inherits `$DSH_IMAGE_RECOGNITION_BASE_URL`, else unavailable. |
| `baseURL` | string | Endpoint base; `/chat/completions` is appended. Defaults to `https://dashscope.aliyuncs.com/compatible-mode/v1` (Aliyun DashScope compatible-mode); `$DSH_IMAGE_RECOGNITION_BASE_URL` overrides. |
| `apiKey` | string (secret) | Literal key; prefer `apiKeyEnv`. |
| `apiKeyEnv` | string (credential-ref) | Credential reference resolved per recognition; defaults to `DEEPSEEK_API_KEY`. |
| `model` | string | Vision model name; defaults to `deepseek-v4-flash`. |
| `apiKeyEnv` | string (credential-ref) | Credential reference resolved per recognition; defaults to `IMAGE_RECOGNITION_API_KEY` (distinct from the main chat model's `DEEPSEEK_API_KEY`). |
| `model` | string | Vision model name; defaults to `qwen3-vl-flash` (an image-recognition-specific default, independent of the chat model). |
| `maxTokens` | number | Generated-token bound; defaults to 2048. |
The endpoint and key are editable live through the `image-recognition-http`
packages/vision/image-recognition-http/src/index.ts
+10 -6
View File
@@ -16,6 +16,7 @@ import type {} from '@deepseek-ai/dsh-session'
import type {} from '@deepseek-ai/dsh-image-recognition'
import {
ImageRecognitionHttpProvider,
IMAGE_RECOGNITION_DEFAULT_BASE_URL,
IMAGE_RECOGNITION_DEFAULT_MAX_TOKENS,
IMAGE_RECOGNITION_DEFAULT_MODEL,
} from './provider.ts'
@@ -23,6 +24,7 @@ import type { ImageRecognitionHttpProviderOptions } from './provider.ts'
export {
ImageRecognitionHttpProvider,
IMAGE_RECOGNITION_DEFAULT_BASE_URL,
IMAGE_RECOGNITION_DEFAULT_MAX_TOKENS,
IMAGE_RECOGNITION_DEFAULT_MODEL,
IMAGE_RECOGNITION_HTTP_PROVIDER_ID,
@@ -35,17 +37,19 @@ export const name = 'image-recognition-http'
/** The image-recognition seam this provider registers into. */
export const inject = ['imageRecognition']
const DEFAULT_API_KEY_ENV = 'DEEPSEEK_API_KEY'
// Distinct from the main chat model's key: image recognition may use a
// different provider (e.g. Aliyun DashScope) than the conversation LLM.
const DEFAULT_API_KEY_ENV = 'IMAGE_RECOGNITION_API_KEY'
/** Plugin config (all optional — `apply` fills env-var and constant defaults). */
export interface Config {
/** Literal API key; prefer {@link apiKeyEnv} so no secret enters configuration files. */
apiKey?: string
/** Credential reference resolved for each recognition; defaults to `DEEPSEEK_API_KEY`. */
/** Credential reference resolved per recognition; defaults to `IMAGE_RECOGNITION_API_KEY`. */
apiKeyEnv?: string
/** OpenAI-compatible endpoint base; `/chat/completions` is appended. */
/** OpenAI-compatible endpoint base; `/chat/completions` is appended. Defaults to Aliyun DashScope compatible-mode. */
baseURL?: string
/** Vision model name. Defaults to `deepseek-v4-flash`. */
/** Vision model name; defaults to `qwen3-vl-flash` (an image-recognition-specific default, not the chat model). */
model?: string
/** Upper bound on generated tokens. Defaults to 2048. */
maxTokens?: number
@@ -54,7 +58,7 @@ export interface Config {
export const Config: z<Config> = z.object({
apiKey: z.string().role('secret'),
apiKeyEnv: z.string().role('credential-ref').default(DEFAULT_API_KEY_ENV),
baseURL: z.string(),
baseURL: z.string().default(IMAGE_RECOGNITION_DEFAULT_BASE_URL),
model: z.string().default(IMAGE_RECOGNITION_DEFAULT_MODEL),
maxTokens: z.number().step(1).min(1).default(IMAGE_RECOGNITION_DEFAULT_MAX_TOKENS),
})
@@ -89,7 +93,7 @@ function resolveOptions(ctx: Context, config: Config): ImageRecognitionHttpProvi
},
baseURL: config.baseURL
?? launchEnvironmentOf(ctx).get(BASE_URL_ENV)?.value
?? '',
?? IMAGE_RECOGNITION_DEFAULT_BASE_URL,
model: config.model ?? IMAGE_RECOGNITION_DEFAULT_MODEL,
maxTokens: config.maxTokens ?? IMAGE_RECOGNITION_DEFAULT_MAX_TOKENS,
recordRequest: (request) => {
packages/vision/image-recognition-http/src/provider.ts
+8 -1
View File
@@ -32,8 +32,9 @@ declare module '@deepseek-ai/dsh-session/types' {
}
}
export const IMAGE_RECOGNITION_DEFAULT_MODEL = 'deepseek-v4-flash'
export const IMAGE_RECOGNITION_DEFAULT_MODEL = 'qwen3-vl-flash'
export const IMAGE_RECOGNITION_DEFAULT_MAX_TOKENS = 2048
export const IMAGE_RECOGNITION_DEFAULT_BASE_URL = 'https://dashscope.aliyuncs.com/compatible-mode/v1'
const USER_AGENT = 'deepseek-harness/0.0.1'
@@ -115,6 +116,12 @@ export class ImageRecognitionHttpProvider implements ImageRecognitionProvider {
'IMAGE_RECOGNITION_PROVIDER_CREDENTIAL_MISSING',
)
}
if (options.model.length === 0) {
throw new ImageRecognitionError(
'image-recognition provider has no model configured; set one in the plugin settings',
'IMAGE_RECOGNITION_PROVIDER_CREDENTIAL_MISSING',
)
}
const source = await imageSource(request.image)
const payload = {
model: options.model,
packages/vision/image-recognition-http/tests/provider.spec.ts
+6 -2
View File
@@ -2,7 +2,6 @@ import { afterEach, describe, expect, it, vi } from 'vitest'
import type { ImageRecognitionRequest } from '@deepseek-ai/dsh-image-recognition'
import {
ImageRecognitionHttpProvider,
IMAGE_RECOGNITION_DEFAULT_MODEL,
type ImageRecognitionHttpProviderOptions,
} from '../src/provider.ts'
@@ -15,7 +14,7 @@ function makeProvider(overrides: Partial<ImageRecognitionHttpProviderOptions> =
return new ImageRecognitionHttpProvider(() => ({
resolveApiKey: async () => 'key',
baseURL: 'https://vision.example.com/v1',
model: IMAGE_RECOGNITION_DEFAULT_MODEL,
model: 'vision-model',
maxTokens: 128,
...overrides,
}))
@@ -60,6 +59,11 @@ describe('ImageRecognitionHttpProvider.recognize', () => {
.rejects.toThrow(expect.objectContaining({ code: 'IMAGE_RECOGNITION_PROVIDER_CREDENTIAL_MISSING' }))
})
it('throws IMAGE_RECOGNITION_PROVIDER_CREDENTIAL_MISSING without a model', async () => {
await expect(makeProvider({ model: '' }).recognize(request))
.rejects.toThrow(expect.objectContaining({ code: 'IMAGE_RECOGNITION_PROVIDER_CREDENTIAL_MISSING' }))
})
it('maps a non-2xx response to IMAGE_RECOGNITION_PROVIDER_ERROR', async () => {
stubFetch({ ok: false, status: 429, json: async () => ({ error: { message: 'rate limited' } }) })
await expect(makeProvider().recognize(request))