プラグイン

Mind-map project planning with blocking drift protection: plans, modules and tasks as a dependency DAG with topological execution order, an agent position marker, a human approval gate on every board edit, git cross-checks, and evidence-gated task completion.

Auto-expands streaming thinking: always keeps the latest thinking block expanded, manual actions take priority, only the last block expands when opening a session, and nothing remains after uninstall.

Shows the running agent step above the web composer as a Chinese sentence: its step number, the tools it is running, and how long it has been going. A finished step keeps its duration on screen until the next one starts, so a slow step can be identified after the fact.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

Select text in the DeepSeek Harness Web conversation and append it to the composer as a markdown blockquote.

Quick-notes floating panel for dsh web: timestamped entries, clock, alarms with flashing reminder, API prices & balances, day/week/month/year grouping.

Replacement session-title provider that compresses oversized or code-heavy first prompts before calling the model (in the tested DSH version the built-in provider rejects inputs above 4096 bytes without a model call) and waits for a real task instead of titling a greeting. Titles use the session’s own provider and model by default and manual titles are protected; title rules cover a character cap, an optional date affix, style, language and exclusion words, plus a per-session lock. Also re-titles stored sessions in bulk, with a progress overlay that keeps running after Settings is closed.

DSH plugin: sync model settings, plugin manifests, patch layers and lockfiles across devices through a private Git repository (manual push/pull; https+token or ssh public-key auth).

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.

Preventive content policy for tool results: rewrites matched text, and drops or truncates whole fields by path before a result is normalised, rendered or persisted, so an unreviewed payload never enters it. Ships inert with no built-in category or domain blocklist.

Diagnose duplicate DSH loader entry IDs before startup, report version-locked repair status in a read-only settings card, and apply or revert audited loader repairs through an external CLI.

Project-based learning coach: a subject-agnostic teaching engine plus swappable domain packs (Unity/C# included), shipped both as a DSH skill and as an installable bundle. The skill protocol enforces attempt-first teaching and graded hints; a zero-dependency validator rejects ability claims their evidence does not support and blocks stage acceptance while blockers are open.

Merged, version-locked plugin upgrade skill for DeepSeek Harness (0.1.3-alpha.1 to 0.1.5-rc.1 as two closed legs): an evidence-bound version card plus a zero-dependency 20-seam scanner, shipped as a bundle skill and an npx CLI.

Adds /dev/dxg and /proc read-write grants to the DSH Landlock sandbox on WSL2, so CUDA is available inside a confined agent bash session.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

GitHub-style alert cards for DSH assistant Markdown: a qualifying `> [!NOTE]`, TIP, IMPORTANT, WARNING, or CAUTION blockquote becomes a theme-aware card. Stored session content is left unchanged.

TOTP-only access control for personal DeepSeek Harness Web instances, with in-app QR enrollment, single-use recovery codes, live protection controls and lock-all revocation of page access.

Prevents concurrent-write session corruption: takes a per-session advisory lock on session start and every step, so a second dsh process fails loudly instead of writing a duplicate-seq gap; dead owners are taken over automatically.

Context-window attribution for DSH Web: a Mini Utility Dock panel that ranks the user messages, assistant turns, reasoning blocks and tool results of a session by the tokens each one occupies, so it is clear which entries hold the window. It also shows the share by entry type, the heaviest entries across the live sessions of the host, and, where the host provides them, provider usage and the estimated system/tools/messages composition. The panel is read-only: it does not estimate cost, modify a session, or trigger compaction.

Teaches Herdr about DSH panes: reports agent working/idle/blocked state — including the blocked state DSH itself lacks — enabling panel jump and --wait. (Herdr integration / agent state display / panel jump)

Erii (Sakura) themed boot splash animation — falling sakura petals, a mint monster mascot with a blossom on its head, and a soft pink progress bar; fades out after ~3 seconds without blocking input.

Code management panel for the DSH web UI that handles everyday Git in five steps: ① env check auto-detects git/gh/ssh and one-click installs missing tools (gh mirror download sources speed up installs, Windows included) with check-update; ② SSH ed25519 key generation / connection tests plus one-click 443 config to bypass blocked port 22, with the Gitee personal token configured here; ③ repo status, side-by-side diffs, stage/commit, branch switching, history with revert/cherry-pick, one-click repo creation and push, auto-ignoring >100MB files; ④ lists all repos of your account for one-click clone; ⑤ five-step npm publish wizard. GitHub / Gitee dual-platform, with the UI switching between 中文 and English live.

Task-completion notifications: desktop alerts via macOS Notification Center and Windows Toast, plus mobile push through Bark, ntfy, ServerChan or any webhook when an agent run goes idle, errors or blocks.