플러그인

DeepSeek 브레인 + 자동 이미지 전사: GUI에서 이미지를 첨부하면 기본적으로 공식 deepseek-v4-flash-vision-exp로 전사됩니다(순수 텍스트 V4-Pro 브레인도 이미지를 볼 수 있음). 대안으로 OpenAI 호환 VLM 또는 로컬 Ollama 사용 가능.

DeepSeek Harness 네이티브 비전 모델 deepseek-v4-flash-vision-exp를 위해 이미지 허용 한도를 32 MiB / 8192 px / 600장으로 상향하고, 큰 이미지를 타일로 분할한 뒤 호스트의 read_image 도구를 통해 전체 이미지와 800x800 타일을 반환하는 highres_read 도구를 추가합니다.

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

Vision browser tool: drives real Chrome over CDP with browser-use and reads the page with deepseek-v4-flash-vision-exp, so canvas text, text baked into images and values in rendered charts are readable; returns JSON validated against a caller-supplied schema and reports per-run token cost.

LLM-as-a-Verifier for dsh with the Best-of-N conversation mode built in: rank N candidates with a fine-grained verifier (expected grade over the logprob distribution), on demand via the verify tool or automatically on every turn of a Best-of-N session. In