Plugins

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

Live request metadata minimization for DeepSeek Harness, covering the native DeepSeek provider with WebUI settings.

Git-native, auditable long-term memory for AI agents

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

Session handoff for DeepSeek Harness: the session menu creates a successor session that rebuilds the old session's memory, tasks and rules through an eight-section takeover packet, with light context via on-demand transcript readback.

Session health-check: mechanically mines session logs into structured problem tickets (retry loops, tool-error clusters, interrupted turns, token waste) over the official session-query seam; works standalone.

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

Browse and govern the skill library from a floating-ball panel with three tabs — skills, call ledger and quick start. You choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin); skills are grouped into two levels of categories, with manual, keyword-based and AI grouping available and a tree or flat view toggle, and grouping is purely visual so no skill file is ever moved. Descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and writes a SKILL.md.bak-toggle-<timestamp> backup before saving, rolling back if the write fails; disabled cards grey out until restored. The call ledger separates automatic from manual entries, records skill successes and failures by listening to tools/result events, and reports call counts, success rate, trend and a ranking, reusing an existing ledger file found in the library. Hot reload picks up skill edits without a restart. The DSH settings page gains a floating-ball section that shows or hides the three balls, offers one-click restore of a ball dragged off-screen, and picks the shared 130-skin catalogue for all three balls.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Native RSS monitor for DeepSeek Harness: multi-source subscription, keyword filtering, scheduled polling with smart dedup, and email notifications for new items (HTML template with thumbnail cards), with SMTP passwords stored only in the credential store.

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.

DeepSeek Harness plugin: Bilibili keyword video search, video metadata, subtitle transcripts, direct play URLs, and multimodal frame viewing (bilibili_search / bilibili_video / bilibili_subtitles / bilibili_playurl / bilibili_frames). Anonymous by default

Piano performance plugin: ask the agent to play a piece and it renders on a Canvas2D grand piano with real Salamander Grand samples, an immersive stage, and an interactive 88-key keyboard.

One-click context compression for the dsh web GUI: a 压缩 button on the session title bar summarizes the whole conversation into a few lines, opens a new session in the same workspace seeded with the summary, and switches to it — the original session stays untouched.

DSH Web plugin for managing sessions: archive/unarchive, guaranteed physical deletion (transcript files + ~/storages/*.json sweep), drag-and-drop workspace reassignment, and branch-based message editing (edit/retry/reroll with reversible version timelines

Desktop notification plugin for the DeepSeek Harness (dsh): shows a native OS toast when the agent finishes a conversation turn. Zero runtime dependencies; works on Windows (native WinRT toast), macOS (osascript) and Linux (notify-send).

One-time Full access switch for DeepSeek Harness: new sessions (workspaces and conversations) start with danger-full-access and skip the per-session Full access confirmation; installable as a dsh bundle or via patch scripts.

Send QQ private-message notifications via a local NapCat bot: qq_send / qq_status / qq_napcat / qq_deploy native tools plus one-click deployment scripts.

A phone shell for the web GUI - the sidebar becomes an overlay drawer that closes when a session is tapped, the settings sheet goes full-screen single column, and the transcript is retuned for phone reading.

Terminal-native frontend for the DeepSeek Harness plugin ecosystem

Named user credentials the model uses by reference: values are entered on a Settings → Credentials page and injected into each shell execution as DSH_CM_* variables instead of being printed into the transcript, with credential_read as the documented last resort.