171 results
Diff cards in the DeepSeek Harness web chat for recognizable file mutations — MCP filesystem calls (edit_file, write_file), built-in edit/write, and file-mutating bash commands (heredoc replaces, sed -i, cat/tee/redirect writes).
DeepSeek Harness plugin: track todo_write progress and pop native desktop reminders (bottom-right).
Persistent DeepSeek Harness bundle: MIDI recognize/edit tools (midi_summary, midi_read, midi_write, midi_transpose, midi_quantize, midi_tempo, midi_chords) over @tonejs/midi.
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
FileLens — right-column file explorer for DeepSeek Harness: lazy directory tree, multi-format preview (Markdown/JSON/CSV/diff/log/hex/image), search & grep, tabs, inline editing with containment + version-guarded writes.
Durable layered memory (global / user / project / branch / daily), confirmation-gated writes, todos and skills. Preserves ~/.dsh/memories files in place with in-place adoption, SHA-256 verified backup and rollback.
LVGL 8.4 knowledge skill pack for DeepSeek Harness (dsh): registers an offline LVGL 8.4 skill library on ctx.skills so the agent writes correct v8 API code and avoids v9 confusion.
Hierarchical long-form writing for DeepSeek Harness — WriteHERE as an agent driver, not extra ReAct tools.
Collapsible before/after code-diff cards for edit/write tool calls in DeepSeek Harness (dsh), with absolute line numbers. Pure visual, injected into the conversation flow.
DSH bundle: Xiaohongshu (RED) viral-note agent skill — hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing, shipped as a bundled skill provider. Zero-dependency.
PostgreSQL-backed single-writer session handoff service for DeepSeek Harness
RTK command rewriting suggestions + tool output compaction for DSH. Suggests rtk-rewritten bash commands (deny-mode under rewrite) and compacts noisy tool output (bash/grep/read) to reduce context usage. Port of pi-rtk-optimizer for the Pi coding agent.
Windows access tools for WSL agents: win_ls/win_read/win_write/win_run/win_open/win_path/win_drives.
AiToEarn content-creation suite as a DeepSeek Harness plugin: creative director, script writer, image-text and video generation, and Douyin publishing.
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏：拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness
dsh-new-ui — a full-site UI rewrite for DeepSeek Harness (deep tech blue + liquid glass) that auto-intercepts dsh-web-ui to avoid conflicts. 整站 UI 重写 + 自动拦截 dsh-web-ui。
Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers
Conversation-local credential handoff that writes through the DSH credential service without returning the secret to model context.
Snapshot every write/edit the agent makes, then roll back to any earlier state. Includes a browser half: sidebar snapshot timeline and plugin settings card.
DeepSeek Harness 插件：发送前用提示词工程 playbook 自动改写用户输入为更优 prompt。官方 bundle 插件，dsh plugin --profile web add
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, write approval gate, and a JSONL SQL audit trail.