Plugin

Screen frames, log lines and (on Windows) key/mouse input on one millisecond timeline: record, mark the failing seconds, box the problem on the frame, then hand the agent a keyframe strip, an animated GIF and the aligned log slice.

Closes DeepSeek Harness runner processes that stay alive after their shell command finished on Windows, reclaiming about 140 MB each. A runner is closed only when its shell is gone and it supervises nothing, as a workaround for the runner not exiting by itself.

Adds a bell to the sidebar header: yellow when a conversation waits for approval, red when a turn was interrupted, blue when a conversation completed; clicking it opens a status summary panel and a session board, and a status with exactly one session opens that session directly.

Git tab that covers the session workspace root together with every additional root registered through multi-root-workspace, so sibling checkouts appear as separate sections with their own branch, ahead/behind, line counts, directory tree and commit history; clicking a file opens its unified diff (or whole content, for untracked files) and clicking a commit opens its patch. Each section also has a commit box that stages and commits only the listed files (`git add -- <files>` + `git commit -- <files>`).

Registers the github-push skill so every session follows one fixed commit-and-push flow, with a pre-flight secret scan, an abuse-resistant retry policy, and local-proxy discovery when github.com is unreachable directly. Runs on Windows only: the push skill uses Windows PowerShell 5.1+ and curl.exe.

VS Code-style multi-repository Git panel in the DSH right sidebar: repository and branch pickers, staged/unstaged changes with inline diffs and per-file actions, commit, stash/tag/worktree menus, a connected SVG commit graph with branch multi-select, and fetch/pull/push/sync.

GitHub console inside DSH: token sign-in, repositories, issues, PRs, commits, notifications, stars and activity, one-click cloning that keeps itself up to date, and a categorized skill library that installs GitHub skill projects for the agent.

Local-first task workbench for DeepSeek Harness with today, week and all-task views, single-day and multi-day tasks with optional times, a four-state idea pool, and daily/weekly/monthly reviews that only a human can write.

AI-native iteration cycle: 24 anic_* tools and 77 HTTP routes that run evaluation, convergence gates, and auto-fix loops across projects, with a live white-box panel (interactive workflow graph, invocation feed, autonomy gauge, gate ledger, HITL queue) and an inline installable SKILL.md workflow kit.

Agent preset that hands every task to a Claude Code subagent, so the session only writes the task brief, delegates and reports the result. Requires a locally installed, logged-in Claude Code.

Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.

Configurable serial agent-team workflows with a Manager, role Actors, an independent Judge, and a visual workflow editor.

Right-sidebar flow editor for prompts, model switches, commands, condition branches and loops, executed only at turn boundaries so an in-flight request keeps its model.

A fact layer for daily heartbeat turns: diffs the curated plugin market for newly published entries and the Chinese education SRC calendars (EDUSRC rounds, Beijing education SRC seasons, the standing vulnerability-hunting exercise) for new items. Reports deltas only — the first call seeds a baseline and stays quiet.

An on-demand Chinese editing skill that reduces formulaic phrasing while preserving facts, uncertainty, genre, and author voice.

Reusable experience for DeepSeek Harness: save a successful task as a structured playbook, recall it later as a native skill, and gate deliveries behind user-confirmed checks that require objective evidence before write actions are allowed.

Skill management panel inside DeepSeek Harness settings: lists global and per-project skills, marks whether the running DSH actually loads each one, offers one switch that controls both model and slash-command invocation, previews and edits SKILL.md with the chat UI markdown renderer, and creates, imports (folder or zip) or deletes skills into a recovery folder. It only reads and writes the local skill roots (~/.dsh/skills and <project>/.dsh/skills) through its own Host routes behind the DSH Connection trust fence; no telemetry, no outbound requests, no credentials.

Streaming video preview in the DSH sidebar — mp4, webm and mov play in place over an authenticated byte-range route, with 206 responses, instant seeking, no size cap and no build step.

Renders .ttl, .owl, .rdf, .jsonld, .nt, .n3, .nq and .trig ontology files as an interactive graph in the DSH sidebar preview, with local Turtle, N-Triples, RDF/XML and JSON-LD parsing and no runtime dependencies.

Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.

Synthesises speech through Alibaba Bailian's WebSocket TTS and returns a WAV file plus a preview URL, with an optional per-turn hint that nudges the model towards voice. Needs a Bailian API key and ffmpeg, and the text is sent to Alibaba Cloud; the plugin does not send messages itself — delivery is left to the session's own transport.

Host-side TTS bridge for dsh that synthesizes speech over the Edge TTS protocol and serves MP3 on a same-origin route, for containers with no audio device.

Image generation through the Volcano Ark / Doubao Seedream API: ark_generate_image for text-to-image, image-to-image and fixed-seed batches, ark_image_gen_status for checking the key, model and output directory. Requires a Volcano Ark API key (ARK_API_KEY).

Streams and inspects local video for agents: adaptive motion/settle canvas sampling, deterministic probe, timestamp and uniform frame extraction, and RoI zoom on 42px-grid-aligned canvases. Requires ffmpeg and ffprobe on PATH (or configured absolute paths); clips without subtitles also need a ~190 MB local whisper model or a cloud transcription API key.