Files

T

Pine 768bcd4356 fix(image-recognition): keep the vision key on its own ref; add clear-key

Image recognition and the chat model shared DEEPSEEK_API_KEY: the
image-recognition bundle defaulted apiKeyEnv to the model key, so saving one
overwrote the other. Point the bundle at IMAGE_RECOGNITION_API_KEY and guard
both the provider and the settings card against a stale model ref, so vision
never reads or writes the chat key. Also add a clear-key button, default the
model to qwen3-vl-flash on the DashScope compatible-mode endpoint, and send
file images as base64 with a normalized base URL.

Co-Authored-By: Claude <noreply@anthropic.com>

2026-08-14 23:01:15 +08:00

src

fix(image-recognition): keep the vision key on its own ref; add clear-key

2026-08-14 23:01:15 +08:00

tests

fix(image-recognition): keep the vision key on its own ref; add clear-key

2026-08-14 23:01:15 +08:00

package.json

docs(vision): package READMEs, Model Experience, and the capability Agent Note

2026-08-14 11:15:59 +08:00

README.md

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

2026-08-14 20:45:35 +08:00

tsconfig.json

feat(vision): add the configurable HTTP vision provider

2026-08-14 10:56:10 +08:00

README.md

@deepseek-ai/dsh-image-recognition-http

A user-configurable HTTP vision provider for ctx.imageRecognition. It calls an OpenAI-compatible /chat/completions endpoint with the image encoded as a data URL and returns the recognized text.

Config

Key	Type	Meaning
`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 `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 settings section. The key never rides a response: it is resolved per recognition from the credentials domain, falling back to the launch environment.

A recognition under an initiating Agent appends the log-only image-recognition/llm-request session event carrying the secret-free request body before dispatch.

Known Limitations and Deferred Work

The provider assumes an OpenAI-compatible vision endpoint; non-standard endpoints must be adapted via baseURL/model (or a new provider).
file-path inputs require an inferable media type from the extension.