Plugins

Windows-only process control for the harness: a sidebar button that shuts DSH down through the host's own graceful exit path, an app-window / normal-tab switch on the Plugins card that rewrites the desktop shortcut and restarts, and advanced settings for the wait before exit, the process exit code and a force-quit option.

Host- and agent-layer DeepSeek Harness plugin that prices every automatic context rewrite before it lands, asks the human by default, and reports what the provider had to re-read cold.

Session cleanup for the DSH sidebar: drag a conversation row onto the balance widget's whale and it eats the row — the session directory goes to a recycle bin, not to rm. Deletion asks one short question first (how many tokens it burned, and that prompt can be turned off in Settings). Undo from the persistent toast or the 12-entry log in Settings. Clicking the whale jumps straight to the plugin's Settings, where you can swap the avatar, drag the mouth into place and rewrite all 17 UI strings; blank, currently-open and running sessions are refused in place with a reason.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Preventive content policy for DeepSeek Harness tool results: rewrite matched text with regex rules, or drop/truncate unpredictable payloads by field path before they are normalised, rendered, or persisted. The upstream counterpart to dsh-plugin-redact.

Session Steward for DSH: browse and bulk-prune the official session archive set, and run a four-gate health checkup (log integrity, projection cache, lossless JSON, cold read) that ends in a reversible, backup-first prescription. Never rewrites session logs.

Colors each DSH sidebar session title by state: unread (blue while the model is running, green once it has finished) and pinned (yellow, read from DSH's own pinned set), composed into one left-to-right gradient. Pinning, archiving and ordering stay with DSH itself — the plugin reimplements no pinning and rewrites no official bundle — and a settings section lists every unread session.

Route and rewrite the harness's outbound HTTP requests by host and path, with a native right-sidebar monitor.

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.

Embeds external AI chat sites in a DSH side panel through the same-origin reverse proxy with per-site DOM adapters, and adds a composer button that either rewrites the draft with the host model or runs a two-round loop: compress the conversation, optimize, send to the embedded site, capture the reply, then finalize it into the composer.

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Prompt optimizer for DeepSeek Harness: a composer tool-row button that rewrites the draft into a structured prompt via the session's selected model, with one-click restore

Display-layer text replacement for DSH chat messages: rewrite how any configured text appears on screen without touching the real conversation, with per-rule whole-word matching and code-block protection.

Turn codebase smells into an executable, priority-ordered refactoring plan: file-length / deep-nesting / function-length / god-object heuristics plus a staged runbook (read-only, no auto-rewrite).

dsh-new-ui — a full-site UI rewrite for DeepSeek Harness (deep tech blue + liquid glass) that auto-intercepts dsh-web-ui to avoid conflicts. 整站 UI 重写 + 自动拦截 dsh-web-ui。

The ast_grep (structural code search) and ast_edit (structural rewrite) tools for DeepSeek Harness over the packaged ast-grep native engine — a standalone plugin with no upstream harness changes required.

Rewrite the current composer draft through an auxiliary LLM call without sending a message.

Silence Chrome/iCloud password-manager prompts over DeepSeek Harness API-key inputs: rewrites password-type secret fields into masked text fields so browser password managers never treat DSH API keys as account passwords.

Prompt optimizer in the composer: rewrites the draft into an eleven-section analytical prompt using the conversation, workspace files and the session's selected model, with one-click undo.