Plugins

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

Token, cost, and balance dashboard under the composer: live indicator plus zero-dependency SVG charts for per-turn usage, estimated cost, and DeepSeek account balance.

Right-edge user-message navigator with an adaptive block layout that fits the available height, plus hover previews, keyboard controls, and click-to-jump navigation.

Mobile layout fixes for the Web UI on narrow screens: full-screen settings panel, one-row plugin nav, full-screen sidebar, centered popups, icon-only session-log button.

Auto thinking-effort routing for dsh: a locally fine-tuned 7-question classifier (ModernBERT, 842MB, <1s CPU inference) picks low/high/max for no-intent messages; in-session retries escalate the tier (low to high to max) under exclusion constraints; the judge service fails safe to low if unreachable. A tier chip in the input bar shows the live tier and the last 20 judgments. All inference is local - task text never leaves the machine.

Patent-writing gatekeeper for dsh - screens the idea against Chinese prior art first, then runs five-party alignment interviews, eight-chapter disclosure drafting, figures and simulation runs, seven-dimension review and docx/PDF export. Skills work out of the box; the search, export and experiment tools come from a bundled Python MCP service that ships disabled - one line in ~/.dsh/patent-services.yaml enables it, and uvx fetches the wheel from PyPI.

A whale-girl companion for the dsh web GUI: animations follow the agent state, with pat interactions and a feeding mechanic that raises intimacy from a calf to deep-sea bonds.

Tool-call discipline for DeepSeek Harness: injects a static behavior-constraint prompt section, drops the parallel pool to 1 after a tool failure (restoring after 3 consecutive successes), nudges the model to stop retrying after repeated failures, verifies writes with .bak rollback, gates high-risk commands, and tracks compliance stats via /behavior-status.

Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.

Manage MCP servers, skills, and tools for your agent — true in-context state (loaded/truncated/evicted) and per-session switches.

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

Git worktree panel for DSH Web: replaces the workspace sidebar with project → main/linked worktree → session groups, creates and removes worktrees, switches the main branch, and migrates configurable project-local or global storage with dirty-tree and active-session safeguards.

DSH plugin bundling the kimi-ppt skill: create, edit and export presentations as a locally generated .pptx with Pillow-rendered previews. Derived from the MIT open-kimi-ppt-skill.

Native Graphify knowledge graph plugin providing 10 code intelligence tools, topological search, god nodes discovery, and PR blast radius triage.

Self-contained literature library for DSH with optional Zotero export: full-text PDF fetching (Unpaywall/arXiv/custom URL templates), loose Crossref-backed search, APA/GB-T 7714/MLA/Chicago citation generation, a side-panel PDF reader with highlights and notes, and AI-assisted Q&A/translation steered into the current conversation.

Connect ChatGPT Codex, xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, and Cursor subscriptions to DeepSeek Harness through OAuth and a local proxy.

CodeBuddy supplier plugin for dsh-router. Handles one account at a time with polling OAuth login and token refresh, leaving account selection, cooldown and check-in to dsh-router core.

Codex-style side chat + selection annotations for DSH web.

For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.

Enhances data visualization in DeepSeek Harness by automatically selecting chart types from user input and generating images for trends, comparisons, proportions, relationships, and flows.

A self-healing layer for tool calls: missing params, wrong fields and out-of-range paths are fixed before they reach the model. Measured visible error rate fell from 7.95% to 2.20%.

Programming Mode agent preset bundle: the standard coding agent with its persona mandating the Superpowers discipline (skills first, brainstorming before building, plans before code, TDD, systematic debugging, verification before completion) plus an always-on Ponytail code-volume discipline (7-rung minimal-code ladder, default full); ships all twenty skills bundled (14 superpowers + 6 ponytail) and mechanically injects the full using-superpowers skill into every new session's first request.

Embeds a real VSCode editor (code-server, or your local desktop VS Code via the bundled bridge extension) as a GUI tab: agent file edits open turn-scoped red/green diffs that survive tab closes and page reloads, files lock while the agent writes, and a watchdog supervisor keeps zero orphan processes.

Inline +N −M badges on edit/write tool rows and a collapsible per-turn file-change summary card with aligned diffs, review and undo — covers native edit/write, str_replace_editor and Code Dispatch sub-calls, no git required.