Plugins

Codex-style keyboard answers for the pending command-approval panel — 1 allows once, 2 rejects, Enter confirms the highlighted choice, arrow keys move it, and Esc rejects, with the buttons still usable by mouse.

Turns the composer's reasoning-effort menu into a draggable slider and takes over the stock model-and-reasoning-level chip. Dragging follows the pointer continuously; releasing snaps to the nearest level and submits one session update per drag. The track draws its own fill, tick marks and white knob, only the highest levels (xhigh, max, ultra) get a flowing brand-colour gradient, and both ends carry the lowest and highest level names. The same card expands into the official model list. Arrow keys step one level, PageUp and PageDown two, Home and End jump to the ends, and each move submits. A generation counter on the directory object discards late responses, and reduced-motion turns the animations off. All data comes from the stock modelDirectories directory; no new capabilities are added.

Skill manager page in the DSH Web Settings panel, at the same level as Plugins: lists every skill the installation serves with its own summary, source and disk footprint, and removes any of them into a recoverable trash.

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

\!WARNING\! this removes the authentication step !WARNING! Exchanges the process launch token for the browser-session cookie, so a first visit needs no ?token=... in the URL.

Source Control panel in the DSH Web left rail: search, switch and create branches with ahead/behind counts, a topo-order commit graph, and a click-to-expand preview of any commit showing its files (A/M/D), insertions and deletions, message, author and timestamp. An always-on footer dock above Settings carries the branch dropdown and recent commits and follows the open session; fetch and fast-forward pull are one button, and a git_worktree agent tool creates, lists and removes worktrees.

Skill browser and switchboard for the DSH web GUI: a sidebar entry lists skills from configurable source directories as cards, clicking a card opens the full SKILL.md, and the per-card switch writes disable-model-invocation and registers or removes that skill in the agent skill catalog, so the model can load exactly the skills that are switched on. It also recognises WorkBuddy expert-team folders and shows avatar, tags, quick prompts and members, registering its lead prompt as a skill when switched on. Source directories are editable in the panel.

Invites people into one conversation through single-use links with no account: up to 20 guests discuss together and ask the AI, the shared fork runs read-only, and the owner can remove guests or end the share at any time.

Move a session to another folder, permanently delete it, or AI-rename it from the Web UI — by dragging a session row onto a folder title or from the session menu. Moving rewrites the session header cwd, relocates the persisted log and updates workspace accounting so history travels with it; deleting stops running agents and removes the log, projection-cache row and workspace accounting. The same three operations ship as agent tools: workbench_session_move, workbench_session_delete and workbench_session_rename_ai.

Fork of @michengai/dsh-pua that removes the upstream global kill-switch so the composer entry is always visible while the feature stays off by default and can be toggled per session; the entry is a dropdown (Turn on / Turn off / Options) with a more compact options panel.

Permanently delete a session from the session row menu — archives the id, removes the log directory and drops the row at once, with a Delete shortcut; built only on shipped extension points, and a session that was merely opened stays deletable.

API regression and acceptance workbench: snapshot the responses of the endpoints you register before the agent edits the backend, rerun them all after the edit, and review a structured field-level diff (status codes, added and removed fields, numeric old → new values with the delta) beside the captured source diff, accepting each endpoint one by one before exporting a Markdown or single-file HTML report.

Creates, activates, checks and removes external DSH plugins from a conversation through fixed tools; requires the external DSHX devkit.

Turns a ZSpace (极空间) NAS into native agent tools: list, stat, search, read, download, upload, write, create folders, rename, move, copy and delete files on the NAS. Works across networks through the desktop client relay — no LAN, no WebDAV, no SSH — and switches to the faster direct WebDAV transport automatically when the NAS is on the same network. Deletes require an explicit confirm: true; write, upload, create-folder, rename, move and copy run directly, and zspace_write overwrites a same-named file unless overwrite is false.

Manage DSH MCP servers from the web settings panel: list, add, edit, remove, enable/disable with live status.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

Adds a "删除会话 / Delete session" item to the session-row context menu (next to rename/fork/archive) — permanently removes session logs from disk, with live-session protection and a restart fallback queue.

Windows desktop control connector: through 10 agent tools it captures the screen (including occluded and partially off-screen windows), lists and focuses windows, moves, clicks, drags and scrolls the mouse, and sends key chords or arbitrary Unicode text. Built on koffi FFI: no compiler, no per-call subprocess, and its own GDI screenshot plus PNG encoder.

Moves selected messages from one conversation into another, and manages a workspace's conversations with archive, restore, delete and move between workspaces.

Layered cross-session memory for DSH that pushes only what changed - the first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed, with keys that merely repeat an entry id left out of the text so the baseline is about 26% smaller. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when due, and search is relevance-ranked with journal lines down-weighted and Chinese matched by bigram. A sidebar tab tells the lifecycle story instead of listing files - entries are grouped by stage (awaiting confirmation / in use / archived) along four axes (topic - one level, human-assigned, type, tag, date), each group can be ticked for batch promote / withdraw / archive / restore / delete / assign topic, and topics can be renamed store-wide or searched on their own. The archived stage reads in three levels - the category says why an entry left (distilled into the docs / useless for good / not needed right now, the first two being defaults you can add to), below it the entry topic stays collapsed until you click it, and entries with no topic sit right under the category. The tab also shows the global and workspace instruction files plus the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

System-audio visualizer for the turn navigator rail: the rail reacts in real time to whatever the default playback device is rendering, with four motion modes (spectrum, pulse, sway, travelling wave), a 16-band logarithmic spectrum from a 2048-point FFT on the host, and live sensitivity, strength, bass-punch and wave-speed controls. Audio is captured host-side through WASAPI loopback, so there is no permission prompt, no microphone and no screen capture. The browser half adds one attribute, one stylesheet, some CSS variables and a sidebar control row, and never patches the official component; switching it off removes the attribute, the stylesheet and the variables, returning the rail to its default styling. Windows only.

Customize the DeepSeek Harness desktop shortcut icon: pick a preset or upload an image, auto-remove the white backdrop, build a multi-size ICO, and write the shortcut in one click.

Unofficial DeepSeek Harness plugin: add, remove, enable and disable external MCP servers from the Web settings page or from chat, so the harness calls their tools as native tools

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.