Plugins

Cérebro DeepSeek + transcrição automática de imagens: anexe imagens na GUI e cada uma é transcrita pelo deepseek-v4-flash-vision-exp oficial por padrão (um cérebro V4-Pro puramente textual pode ver imagens), com qualquer VLM compatível com OpenAI ou Ollama local como alternativas.

Para o modelo de visão nativo do DeepSeek Harness deepseek-v4-flash-vision-exp, eleva os limites de admissão de imagens para 32 MiB / 8192 px / 600 imagens e adiciona uma ferramenta highres_read que divide imagens grandes em blocos e depois retorna a imagem inteira mais blocos de 800x800 por meio da ferramenta read_image do host.

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