Plugins

Adds an Assist button beside the composer send key. It scans the skills and MCP tools available in the session, ranks them against the text currently in the input box, and lets you inject the selected ones into the running conversation as a steering message.

C++ audit skill: detects the target project's actual C++ standard before making any recommendation, then reports findings across RAII and ownership, move semantics, exception safety, performance and memory, containers and algorithms, concurrency, templates and compile-time, standard boundary, and type safety, ABI and interface design, each with a checkpoint, a reason, a bad-to-good example and the minimum standard.

Converts Office and PDF files in the DSH workspace to Markdown locally — no network, no API quota — before the model reads them. Writes each .md next to its source so only a file path enters the context, and returns byte size, line count, token estimate and a heading outline, for a single file or a whole directory.

Bridge to the local doc2md (markdown_monitor) CLI — one doc2md tool with convert, read, scan and status actions over docx, doc, xls, xlsx, pdf and image files.

Give the agent a talking face: seven tools that drive a self-hosted Mynah realtime digital human — speak (queued or interrupting), play a gesture clip, interrupt, list live sessions and channels, check health, add text to its knowledge base.

Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input picker, optionally rewriting the transcript with an LLM.

Registers one `ocr` tool for text-only models: it runs the offline script bundled in the repo over a single image or PDF and returns the recognized text — Windows native OCR first, then RapidOCR, then Tesseract. Recognition runs locally with no network request and no API key. Needs Python 3.11 on PATH plus `pip install winocr pillow` (winocr is the preferred engine; RapidOCR and Tesseract are fallbacks). Per-line results for images, per-page results for PDFs.

Publishes an ordered system prompt section that names wsl as the command executor to reach for first, so the agent prefers WSL over PowerShell on Windows. Registers no tools, and only advertises executors the agent can actually call.

NewAgentUniverseByDeepSeek nodes inside DSH: five read-only tools covering provenance (both upstream releases this build names), a data directory's restored state and ledger audit, the conformance vectors, exact decimal conversion, and node reachability. Driving the node -- starting or stopping a daemon, depositing funds, sending bus messages -- is deliberately not exposed, because those are audited privileged operations in this project.

ZCode-style enhancement of dsh plan mode: a model-initiated enter_plan_mode tool, hard interception of write-class tools at dispatch time (ctx.tools.guard) while planning, and a four-phase planning prompt section (explore, design, review, exit), reusing the official plan/mode state machine and exit review flow.

Complementary web-search provider: every web_search merges the DeepSeek Search API (primary) with serper.dev Google results (secondary) at a fixed 2:1 ratio. Both sides are direct HTTP retrievals with no auxiliary model turn: URL-deduped sources, long DeepSeek summaries clipped into snippets, per-backend timeouts and graceful degradation to whichever backend answers.

Add MiniMax image understanding, image generation, speech synthesis, and transcription tools to DeepSeek Harness.

Windows computer use for DeepSeek Harness: a persistent PowerShell UIA backend behind 16 merged MCP entries (read/click/type/observe/verify), a hardened policy layer (red lines, approvals, observation binding, point-ownership and focus guards) and a performance pass (prewarm, caching, pixel-hash stability probe). Fork of dsh-computer-use-win.

Model failover router that queues all connected DSH models, retries with continue text on failure, switches to next model, and quarantines failing models for the day.

White-box memory in two parts: four user-authored long-term tiers (must-follow rules, behavior settings, user profile, optional rules) injected as one system-prompt section, plus a separate temporary working set (cross-session handoffs, stage goals, waiting items) with its own 1200-character budget that stops being injected once an entry is done. The long-term tiers are plain Markdown files the user can read and edit; the agent can only propose them, and nothing is written until the user accepts in the Chinese panel. Temporary entries are written only when the user explicitly asks, and live in <DSH_HOME>/temp-memory.json (created on first write), not in the memory directory. No auto-capture, no background writes, no network.

Session trash: move conversations to a trash instead of deleting them, restore them, or delete them permanently after a second confirmation; a session opened in this run is hidden and moved at the next start.

Routes DSH web search through the current session's model and a self-hosted retrieval backend.

Cross-workspace DSH messaging and sender navigation, with bounded same-workspace context and opt-in local Claude Code messaging.

Pins a selected passage of a finished user or assistant message as source text and keeps it in the model input across context compaction: each pin is recall-on-demand by default, or can be moved to a neutral resident system-prompt section or an emphasised highlighted one. Selections are aligned back to the source text with source-exact, source-normalized or rendered fidelity, and each of the three levels has its own character budget.

Two-step session deletion: the session menu moves a chat into a recycle bin without deleting anything, the bin panel restores an entry, deletes one for good right away, or empties the whole bin, and the next start wipes its log, projection cache, spill files and workspace membership.

Two-tab archive panel (archived / active) where every row offers archive or unarchive next to permanent delete; each row shows its bound workspace folder as a clickable path, and queued archive-entry cleanup keeps a deleted session from resurfacing in the active list.

Compiles an LLM persona in DSH from six dimensions (identity, tone, creative habits, feedback style, boundaries, run parameters), injects the compiled text into the system prompt at the end, ships six built-in templates plus a drop-in templates folder, and drafts a persona from your own past messages — either by counting patterns in them or by having the current model read them and report its rationale. Adds a panel next to the composer and a /persona command.

Starts the WorkBuddy Panel backend (wb2api.exe from workbuddy2api-panel, Windows) with DSH and on exit stops only the process it launched; optionally syncs the backend's /v1/models into the workbuddy provider, and its settings card picks models, shows credit multipliers and installs, updates or rolls back the backend from checksum-verified GitHub releases.

Expose every free model from a local opencode serve catalog — all providers, including your own custom ones — to DeepSeek Harness's model picker, with OpenCode's native tools denied so execution stays in DSH.