Plugins

File d'attente de tâches inter-sessions avec notes de passation : les sessions et sous-agents publient, réclament, terminent et annulent des tâches sur une file partagée sauvegardée sur fichier, et laissent un résumé de passation pour la personne suivante.

Pastille de statistiques repliable façon iOS sous le composeur : coût de la session, solde du compte DeepSeek, taux de cache-hit et usage de tokens, dans un panneau dépoli.

Animated DSH Web pet with model-adaptive output pacing, tool-state reactions, replaceable character packs, and a bundled skill for creating or extending pet animations.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

Command Code plan quota in the DSH sidebar above Settings: 5-hour, weekly and monthly windows as used percentages with reset countdowns, a /quota command, and a zero-dependency CLI. It reads the key from your own provider route, so it needs no configuration and no other plugin.

A dsh-better-sidebar tab that renders a session brief — a todo board read from the `todos` projection plus a deliverables section listing the files written this turn — and hides the official todo panel above the composer while it is mounted.

Discord-like communities in DSH with channels, roles and permissions, message search, and sharing or cloning of DSH sessions.

Bridges Feishu, WeCom aibot, DingTalk Stream and QQ Gateway chats into dsh agents over outbound long connections, with an im_status tool. Ships with an empty user allowlist, which means EVERYONE can drive your agent — set allowedUserIds before exposing a bot; IM input can run tools on the host.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

Automatically highlights key points, definitions, warnings, and questions in completed assistant answers using one separate model call.

Pre-install compatibility gate for DSH plugins: locks the resolved version, checks peer/engines declarations, dry-installs into an isolated DSH_HOME and boots it with a timeout, blocks on any failure, and restores the profile if the real install fails. Optionally intercepts dsh-market install/update clicks.

Registers the imagegen skill on the skill registry, so generating and editing raster images needs no hand-copied files under $DSH_HOME/skills. The agent drives a bundled image_gen.py CLI against any OpenAI-compatible GPT Image endpoint for text-to-image, reference-image editing, and transparent-background cutouts.

Share a selected chat segment as Markdown, HTML, TXT, or PNG; Session-header dialog with range or multi-select, redaction, tool calls, and subagent conversations, plus the /share command.

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.

Live progress bar under the composer with a percentage and an estimated time left for the current DeepSeek Harness turn; the estimate re-anchors as the turn runs and never reads 100% until the turn ends, and the bar turns red when the turn fails or is interrupted.

Manage VPS servers over SSH key login: 21 zero-token /vps- commands (status queries, recipe installs with a plan and /vps-yes confirmation, reboot that waits for the machine to come back), an in-conversation terminal (xterm.js over ssh -tt) for interactive programs, 5 agent tools with risk-tiered confirmation, file backup with automatic restore and a firewall/SSH safety net, 29 built-in recipes, and a settings page for adding machines.

Read-only DSH/Cordis composition doctor for plugin conflicts and upgrade rehearsal: scan profile manifests and patches, find duplicate rows, hook-order and UI ownership conflicts, compare redacted snapshots, diff plugin/row/hook changes, and preflight target DSH releases with explicit evidence boundaries — without mutating a real profile.

Adds /review, /review-status, and /review-cancel to spawn an independent native subagent that inspects a chosen Git scope (base branch, uncommitted changes, a commit, or custom instructions) and returns a findings report in the current conversation, with English or Chinese output from the host locale.

Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatible /audio/speech endpoint, with voice, emotion, speed and model selection plus an auto-read toggle.

One-click draft polish for the DSH composer: rewrites your spoken draft into professional wording, sends only the draft snapshot (never conversation context), and never blocks sending if the LLM is unavailable.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Injects the rule files under $DSH_HOME/rules and <cwd>/.dsh/rules into the conversation at the first agent pre-step, re-injecting them after compaction.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.