Plugins

See your real ChatGPT / Codex subscription quota inside DSH. Reads /wham/usage: 5-hour and weekly windows, reset countdown, extra-usage balance, additional limit groups and the code-review limit; lists and redeems server-issued reset credits with a stable, retry-safe idempotency key; switches between multiple accounts; reads /codex/models to show the account's real model catalog, showing empty rather than a built-in list when unavailable. One-click sign-in from Settings (browser authorization or device code, with a paste-the-callback fallback); credentials stay in DSH's credential service. Model calls reuse DSH's built-in llm-pi-ai Codex route instead of claiming a provider route — it degrades to a pure quota console when another plugin owns it. A remaining-quota chip sits beside the composer.

Holds every final answer before delivery, has one independent minimal-context model call re-derive and check it, and releases only the verified text; the draft is never shown. Reviewed answers cost one extra model request and appear a few seconds later.

Improves conversation drafts with optional conversation, memory and project context, side-by-side previews, a dedicated model and one-step restore; never sends messages automatically.

A polish button in the composer trailing controls that rewrites the draft in place with the model. Context is matched by topic, not by recency: anchors from the draft (paths, identifiers, quoted text, CJK bigrams) pick the earlier messages about the same task, so a session that interleaves several tasks does not leak another task goal or files into the rewrite — and the prompt explicitly lets the model ignore the extract when it does not fit. The result goes back through the same undo-able editor path a human edit uses. Drafts holding reference chips (@file, folder, session) or a claimed /command, and drafts mid-submission, disable the button instead of silently dropping references.

Composer history that restores the whole input state: composer contents, image and file attachments, @ references and slash commands, plus the model, thinking effort, permission and agent preset used.

Merges AprilCrystal/dsh-client-ui-gpt-helper and zszz3/dsh-model-provider-prefix — two composer model-seat plugins that cannot be installed together — into one control: a Provider / Model trigger opening a two-column card where hovering the provider column swaps the models without moving the card, a separate reasoning-effort trigger with a particle slider, and a search that spans every provider while the card keeps its size.

Adds a Plan/Build mode toggle to the composer, switched with the Tab key or a toolbar button, and remembers a separate model for each mode from the native model selector.

Sidebar chip showing the current DeepSeek price period (peak or off-peak), the selected model's price per million tokens for cache hits, cache misses and output, the account balance and today's spend.

A collapsible column beside the conversation that organises conversations into a workspace/topic tree, opens the real sessions in place, and exposes the tree to the assistant through 9 model tools.

Adds an optional note field under each selected option in the DSH Web UI ask_user_question popup; submitted notes travel to the model in the answer's custom field.

DeepSeek Harness 用マルチプロバイダ・モデルルート管理プラグイン。Claude、OpenAI、Gemini 等のサブスク（OAuth）と API キーを独立登録し、モデル一覧での表示・非表示を制御可能にします。

Author your own skills in the Harness Settings page: every entry is published into the skill registry, so the model sees one line and loads the body on demand.

DeepSeek Harness read-only companion for dsh-cost-meter: a sidebar row that splits today's cost per provider:model, hovering for the full breakdown. Reads the main plugin's in-memory statistics when available so numbers track it exactly; never writes the

Better subagents for DeepSeek Harness: choose the default subagent model, see each subagent conversation's model in its header, and wait for subagents with a blocking wait_subagents tool instead of sleeping or polling.

1flowbase instance manager and model/MCP bridge for the DeepSeek Harness Web profile

Limits the images sent to chosen providers or models in DeepSeek Harness: cap the longest side and the number of images per request, with its own plugin page

CAD 3D model preview for dsh-better-sidebar: renders STEP/STP/IGES/BREP (OpenCascade WASM) and STL/3MF/OBJ/PLY with an orbit camera in the DSH right sidebar.

Deterministic, one-way PII anonymizer for everything the DeepSeek Harness sends to the model: prompt, system prompt, context, and tool results

Task-list staleness guard for DeepSeek Harness: when the model stops updating its todo list but keeps working, the guard appends a short reminder before the next step so the list gets written back to the real progress. / 任务清单陈旧度守卫：模型建了清单却忘记回写时，在下一步之前自动追加一

DSH model provider for Cohere — OpenAI-compatible wire by default, Cohere's native v2 lane for citations/RAG/thinking-budget. Direct wire adapter, no proxy.

DSH agent tools for local Ollama System One decision models: classify, answer yes/no, and score against a rubric in one batched request.

Matt Pocock's engineering and productivity skills for DeepSeek Harness: grilling, spec and ticket flows, TDD, code review, domain modelling and more.

模型清单与余额管理：列出当前模型列表中的全部 provider / 模型及其可查到的余额信息