Plugins

GPT image generation and editing for DeepSeek Harness: image_generate and image_edit tools, plus an in-app settings page with connection test, model picker, and gallery.

Adds an element and region picker to the DSH Desktop built-in browser: hovering labels the element under the pointer, a click records that element, a drag records a rectangle, and each pick opens a small note box beside the pick. A batch is then inserted into the composer draft, never sent automatically, as one text block plus one attached crop per pick, so the user reviews and sends it themselves. Desktop only: the Web profile browser is an iframe, so the picker does not appear there.

Disables the built-in llm-deepseek-account route so the DeepSeek account model group no longer appears in the picker.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

A zero-config composer model picker with one provider per tab, independent scrolling per provider, cross-provider search with provider badges and reasoning-effort chips; selections stay in sync with the built-in /model dialog.

Manages local llama.cpp servers and GGUF launch profiles on Windows and exposes the profiles in the DSH model picker.

Independent DSH plugin: Settings → brand color with preset swatches and a custom color picker; recolors only the sidebar/hero logo mark and favicon, never text. Works with DSH 0.2.0 and 0.2.2.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

Reference-image picker for the DSH web composer: browse face, costume and pose libraries, then insert high-resolution images and a generated prompt into the current draft in one click.

Replaces the sidebar workspace folder picker with a name box (type a name, get a same-named folder and a new workspace), adds a Move to workspace action that clones a session into another workspace and archives the original, and optional per-workspace memory that opens a continuation session after compaction and adds a workspace_memory search tool.

Codex-style composer model picker: a card showing the current model and a draggable slider that sets reasoning effort, with one stop per level the model advertises and an Off stop when the provider supports it. The slider snaps only to whole stops and updates the effort label while dragging; selecting a model or effort still goes through the session model directory, so it stays in sync with the rest of the composer.

Adds model speed tests to the DSH model picker and, on desktop, a plain-language "explain this error" button on failed turns with a user-selectable explainer model.

Prompt enhancement for the DSH composer, with a model picker that lists the models the host actually offers: a Boost button beside the composer sends the current draft to a model on the Host, shows the rewrite in a before/after overlay, and replaces the draft only when you confirm. While boosting, the button glyph becomes a spinning arc; once a rewrite is applied the same button becomes an in-place Undo that restores the original draft and then returns to its idle state. Settings hold the enable switch, a provider/model choice rendered as a grouped dropdown built from the live provider list (including configurable providers that are not set up yet) rather than free-text fields, temperature, output limit, timeout and optional custom instructions. Empty or reasoning-only model answers are reported with their real cause instead of a generic failure, and the Host endpoint only answers loopback requests from the same origin.

Drag a folder onto the sidebar workspace list to register it as a workspace and open a new session. The Desktop app supplies the folder path; a plain browser page falls back to the host folder picker.

Hides the signed-in deepseek-account model group from the model picker and rewrites an already-saved account selection to deepseek-official in prepareCall and stream, so a stale conversation cannot spend on the account; no settings page and no runtime dependencies. Requires an official API key configured under Settings → Models first — without one there is no model left to select after the account group is hidden.

Adds two-level tabs (provider and model family) to the composer model picker for large catalogs, with configurable family rules.

Composer tweaks for the DSH input box: a Markdown source/view toggle, Markdown rendering for user messages, one mixed file-and-folder picker backed by the macOS open panel, a GenUI prompt switch inside the plus menu, an open-in-new-window action on sidebar Session rows (needs the separate `dsh-popout-window` host plugin), and a collapsible subagent tree. Requires DSH 0.2.x.

VS Code-style multi-repository Git panel in the DSH right sidebar: repository and branch pickers, staged/unstaged changes with inline diffs and per-file actions, commit, stash/tag/worktree menus, a connected SVG commit graph with branch multi-select, and fetch/pull/push/sync.

Agent Teams management for the DSH Web GUI: inspect the teammates of any session, delete a role together with its session (the session folder moves to a recoverable trash), reclaim the freed member slot on pre-0.2.2-rc.1 teams, keep deleted members out of the subagent picker and the team roster, and restore a read-only members panel in the session header on 0.2.2-rc.1+ — works with both the old and the new Agent Teams implementations without patching DSH.

Adds a model picker to teammate (continuable subagent) sessions: switch a quota-exhausted teammate to a model that still has quota and let it continue, without rebuilding it or touching the Lead session.

Gives hand-declared models on custom or relay routes a vendor-matched reasoning-effort picker: detects Claude, GPT, DeepSeek, GLM, Kimi, Qwen, Gemini, Grok, Doubao or MiMo from the model id, display name or endpoint host, fills in only the levels that vendor accepts plus the pi-ai compat fields its request format needs, and writes them into the profile config so the Models page reasoning switch turns on. Models you edit or switch off are left alone, and a Models page card hands them back on request.

Writes one model and reasoning effort into every session at once from a control beside the composer model picker, since the shipped picker only changes the session you are in. Sessions that already match are skipped, subagent sessions follow their parent instead of being written, and the same selection can be pinned as the default for new sessions.

Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.

Ordered model rotation for the DSH model picker: a rate-limited or repeatedly timing-out member hands over to the next one, members that only timed out are retested once, and the DSH platform model is the sticky last resort. Ships a settings page with editable chains and a short-429 in-place retry switch.