842 results
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
One-way structured conversation, project, MCP, memory, and context migration between Codex and DeepSeek Harness. Codex 与 DSH 的单向结构化迁移插件。
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Zero-dependency MCP client bridge for DeepSeek Harness: connects stdio/HTTP MCP servers and auto-registers their tools for the agent.
Automatic ghost-text next-message suggestions for DeepSeek Harness, with direct-fill manual generation.
Structural context engine for DSH — tree-sitter symbol index, ranked search, repo map, call graph, and change-aware context.
DSH web plugin: roll back to before any of your questions, or edit the last one and resubmit, restoring the workspace files the discarded turns produced.
Adaptive Context Plane core bundle: Evidence Ledger + Governance + Context Composer + User Model (explicit)
Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model receives either a link (works with any chat model) or the image itself (needs dsh-vision-bridge or a vision-capable model).
Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.
Encoding-governed read/write/edit tools for DeepSeek Harness (dsh): UTF-8 BOM fidelity and byte-exact round-trips for GBK, Big5, Shift-JIS, EUC-KR, Windows-1251 and UTF-16 text files.
Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.
Multimodal eyes and hands for DeepSeek Harness: vision transcription, OCR, and text-to-image via OpenAI-compatible backends, with an in-conversation generated-image card.
PaddleOCR text-recognition and document-parsing skills with native DeepSeek Harness tools and GUI configuration.
DeepSeek Harness native plugin: vision capabilities for text-only LLMs (describe, OCR, VQA, layout analysis, clipboard)
DSH web client plugin: select text in a chat message and quote it into the composer as an inline reference chip; the full text materializes on submit via the input-trigger reference codec.
Select text in a conversation to get a floating toolbar: copy, quote-reply, ask/explain/translate/summarize, and a /btw side-question console (context-only answers that never enter the conversation). AI actions reuse the current session by default, with a per-action main-thread/side-channel destination switch.
纸质主题 — a warm paper-texture appearance for DeepSeek Harness, inspired by Claude Code (cream paper, ink text, terracotta accents).
dsh-voice — voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first, plain audio files under ~/.dsh/voice/
Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, writes take effect immediately, signal-driven injection, no embeddings
In-process graph memory for DeepSeek Harness, backed by TriviumDB.
Hands for your DeepSeek Harness agent — autonomous browser operation with a native permission model. Accessibility-ref page snapshots let a text-only model navigate, act, and test without vision or CSS-selector guessing.
DSH Web 麦克风语音输入插件：浏览器内置 Web Speech API 实时转写进输入框，自动去重/续听、智能标点、语言与自动发送设置（Edge=微软语音、Chrome=谷歌语音）。Microphone voice input for the DSH Web UI using the browser's Web Speech API.
Vision sidecar for DeepSeek Harness: accept image attachments on text-only models, describe them, then send text to the main model.