All Plugins

PDF parsing tools for DSH: pdf_info, pdf_extract_text, and pdf_render_page with dual pdfjs and built-in rendering engines, including system-font rendering for PDFs with non-embedded CJK fonts.

Upload an image as a full-window frosted-glass theme: sidebar/conversation/details share one frost layer, Save/Delete, official Light/Dark/System stay in charge.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web panel, and allowlist.

Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.

Auto-repairs the messages array after a tool-dispatch crash (orphaned tool_calls / tool messages), preventing 400 INVALID_REQUEST session lock-ups.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Registers a `config_doctor` tool that checks the harness's own configuration for problems that boot silently: fields a patch dropped by whole-config replacement, patches targeting missing entry ids, and tool-name collisions. Read-only.

Registers `list_profiles` and `export_profile`, so the agent can show what setups exist and hand back a whole profile — bundle order, plugin versions and patch — as one portable file to share. Read-only.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Reports bounded, repository-relative Git status as structured data without staging, committing, or changing branches.

Results-only conversation toggle for the Web GUI: hides thinking and tool-call process rows, keeps one live status line while the agent works, restores working animations under prefers-reduced-motion, zh-CN/en localized.

Hand off focused context without waiting for or interrupting the active Agent: freeze a bounded Session snapshot, summarize it asynchronously with an isolated no-tool LLM, and deliver a provenance-bearing capsule to another Session or an authorized Room—quiet by default for Sessions, with explicit wakeup available.

Neo-brutalism skin with two switchable schemes (Blue Command / Aged Newspaper), hard shadows, sharp corners, and light/dark theme support.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

Safe Kubernetes capability for DeepSeek Harness with workload inspection, bounded logs and events, failure diagnosis, and approval-gated operations.

Provider-neutral CI/CD capability for DeepSeek Harness with GitHub Actions support, bounded failure evidence, source-aware diagnostics, and approval-gated rerun/cancel controls.

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.