Plugins

Delete DSH sessions into a restorable recycle bin — subagent sessions follow their parent as one tree, batch archive, restore and purge are supported, and only purge destroys bytes.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Lightweight crash-recovery for dsh: after a restart, it detects sessions whose last turn was killed mid-flight and re-injects a continuation prompt that first demands the agent verify real-world state before acting, so side-effecting operations are not blindly repeated. It only reacts to the genuine crash marker (turn/end reason 'interrupted', synthesized on cold read by session repair), so it never misfires on user cancels, rate limits or model errors - which is why it needs no error classification, backoff or configuration UI. Unlike general-purpose auto-continue plugins, it also covers the case where a subagent was interrupted mid-run: the parent turn has already ended normally while it waits, so a naive check sees nothing to resume and the whole subagent tree dies silently; this plugin detects the interrupted child and wakes the parent instead. Single host file, zero external dependencies, seven config constants.

Session-scoped checklists the agent maintains, with a tree per session, a token-budgeted prompt digest and a right-sidebar tab where item titles can be edited.

Deletes a whole conversation from the sidebar session menu, and opens a right-click menu on a chat text selection with Copy, Quote (insert a Markdown quote block into the composer) and Ask: Ask sends the selection plus your question to one reused continuable subagent (label `ask`, found again through the subagent catalog after a restart) and streams the answer into the right sidebar.

Mirrors other coding agents' sessions into DeepSeek Harness as continuable tasks, one workspace per application.

Indexes session transcripts into the Akasha session layer as turns end, records successful compactions, and adds a per-turn rhythm line to the runtime context. Companions: Hindsight (repo memory), OpenViking (user memory), and the built-in session search (see repo README). Setup: clone the repo, copy core/ aside, then replace <AKASHA_DIR> in cordis.patch.yml with its absolute path (or set the AKASHA_DIR env var); plugins fail loudly while the placeholder remains.

Registers /compact_queue, a compaction command that does not drop the request when the session is busy: it compacts immediately when idle, otherwise queues the request in that session and runs it at the session's next idle window, with a 2-second fallback tick beside the agent status event so the trigger is not missed, a 30-minute wait cap, and /compact_queue cancel to withdraw a queued request or abort a running one. Each session keeps its own queue state from a single command registration, completion and failure arrive as a collapsed notice that does not wake the model, and every ManualCompactionError code except busy is terminal so a failure is not retried. Host half only; the core /compact command is left untouched.

A human-in-the-loop curation workbench inside a DSH session: mark whole turns or single messages to keep verbatim or to summarize, rewrite user, assistant, tool-result and injected-context messages in place without a model call, then compress the marked ranges with model-written summaries or the official /compact. A local JSON backup is written before every write to the session.

Mounts a persona kept in Markdown as a system-prompt section, so editing ~/.dsh/persona/*.md changes how the agent speaks; it reloads 150ms after a save instead of requiring a restart, and project-level .dsh/persona/ files override the global ones.

Agent persona management, agent memory, edit-and-regenerate for past messages: create and manage agents, each with its own identity, long-term memory, global memory and chat history.

Describe the persona you want and the agent writes it: nickname, bio, taglines and links come from the host model, the avatar comes from your local asset library (or a path you give), then it fills your profile page and hands the picture to the site's own uploader. Dry-run by default - it only touches profile fields, never passwords or security settings.

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.

Use ChatGPT subscriptions in DeepSeek Harness Desktop via official Sign in with ChatGPT, with dynamic Agent registration and native model and reasoning selection.

Furina (Genshin Impact) theme for the DSH Web GUI: three palettes, switchable wallpapers, translucent glass, an in-Settings theme page, a themed startup splash and a replaceable Furina agent preset. Supports DSH 0.2.0–0.2.x (verified on 0.2.2).

Slims oversized MCP tool JSON Schemas per agent without changing dispatch, and reports token usage, cache hits and context composition on a settings page.

Watchdog for quota exhaustion: on a 429 or quota error it creates a recurring schedule that re-sends a continue-the-task prompt until a turn closes normally, so a long task resumes without manual restarts; /keep-running list and /keep-running cancel <id> manage those schedules. Requires @deepseek-ai/dsh-schedule to be mounted first (it registers the schedules).

A2UI-inspired agent-authored application cards with a persistent machine directory, SSH probes, and reviewed monitoring and control actions. SSH probes require OpenSSH (ssh, ssh-keyscan, ssh-keygen).

Live multi-way tree of the current session's agents in the DeepSeek Harness conversation view and right sidebar, with status, plan progress, tokens, cost (requires dsh-cost-meter), and runtime on every card.

Replaces the new-session hero with a combined picker: role cards for the agent presets and a workspace card, collapsed into capsule buttons that expand into two scrollable rows.

Disk review canvas: agent-written semantics, human decisions, previewed cleanup with undo.

Turns one plain-language request into a live workbench window: a sidebar panel asks a few clarifying questions, the model writes a single-file HTML artifact, and the plugin mounts it in a resizable floating window or a standalone browser tab. Declared window actions are recorded as info-level project journal entries (without their payloads), and workbenches can be imported, exported, or installed from a market index.

Renders an Agent Teams swimlane canvas above the composer: lead centred with members below, tasks laid out in lanes by longest dependency path, and four SVG connector families drawn as dashed paths (task dependency as a cubic bezier from the upstream card edge to the downstream card edge, lead bus, peer bus, member-to-task tether). Cards are absolutely positioned DOM, connectors are one SVG layer sharing the same geometry constants. Layout constants and path algorithms are ported from cc-haha. Reads the live per-session agentTeam projection (roster, shared tasks, dependency edges, running state) and falls back to the session todo list when the session has no team; team messages are not part of the projection yet, so the communication panel shows an empty state. Body colours come from host theme tokens; the eight member identity colours are the deliberate exception — fixed hues mixed with the theme accent via color-mix, declared as CSS variables because the same values feed an SVG stroke attribute that rejects colour functions. Ships zh/en dictionaries with identical keys.