Plugins

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Model picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.

Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.

LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.

DSH model provider for the locally authenticated AGY CLI: Gemini/Claude model discovery, independent reasoning effort, DSH-owned tools, bounded context and tool-result handling, and Windows-safe streaming. Report problems in GitHub Issues: https://github.com/darkings/dsh-agy-provider/issues.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Keep a multi-PR effort on one board you can trust at a glance: the hub agent keeps a tree of steps, each linked to its issue, PR, branch and worktree, through four board tools, and you see what is done, what is blocked and what needs you in a right-sidebar Board tab and a progress strip above the composer. Each board is one plain JSON file your scripts can read, and an optional drift command you configure flags steps whose status no longer matches their work.

Remote-control DeepSeek Harness from a HarmonyOS phone: list, switch and create sessions; send prompts (the phone follows the host's busy-enter behaviour, queue or steer); stream assistant text, reasoning and tool steps; answer approval requests and questions; view session images as inline thumbnails with on-demand full-size fetch; switch model and reasoning effort; cancel running tasks; receive push notifications. Traffic is end-to-end encrypted (AES-256-GCM with HKDF-SHA256 key derivation) and travels through a dumb-pipe relay that only sees ciphertext; v1.1.3 adds a session-epoch anti-replay handshake and optional native TLS for the relay. The relay can be hosted on the local machine (managed by the plugin) or on a VPS; the phone app and the plugin ship in one repository. 5 Remote methods.

Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app cannot be injected and is not covered): filesystem, network and subprocess calls plugins make are attributed to the plugin that made them and judged against what that plugin declares, so a plugin doing its declared job stays silent and leaving it is recorded. Attribution is best-effort, not a guarantee - uncovered calls fall back to host, never to another plugin. Also adds a pre-install health card (capability surface, red-line combinations, PASS/WARN/BLOCK), boundary judging, opt-in pre-execution blocking with a credential-exfil rule, update diff with a trial install in an isolated child process, SARIF/CSV audit export, and multi-source aggregation. Local-only storage, no telemetry; the optional webhook is off by default.

Model settings panel for DeepSeek Harness: set the default model for new sessions, plus separate provider/model/reasoning-effort overrides for subagents and goal rounds, with live reload.

Replaces the composer's model and reasoning-effort selector with a two-level menu and six slider skins.

Four adjustable terse levels plus independent switches for reasoning effort, web search and subagents, on the conversation header and in the Settings page. No output ceiling.

Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH native agent teams, resolved at spawn time by wrapping SubagentRuntime.startContinuable. No official files are modified.

Enhanced model selector for the DSH composer with searchable provider groups, keyboard and accessibility support, and an inline reasoning-effort slider.

Replaces the native DSH reasoning-level option list in place with a draggable Off, Low, High, and Max slider while preserving the official model-selection flow.

Notched reasoning-effort slider grouped with the model picker in the composer, with theme variables and English, French and Chinese labels.

Command Code Provider API chat for DSH with a Host-held API key, discovered model catalog, effort defaults, an optional zero-data-retention header, quota meters, and per-model OpenAI or Anthropic protocol selection.

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

Manages a Magpie model list and writes the checked models into a Magpie provider group: full sync from /v1/models, manual entries, per-model context, output limit, image input and reasoning efforts, sorting and drag reordering. On Windows x64/ARM64 it also downloads and upgrades Magpie from yetone/magpie-releases with SHA-256 verification and rollback, auto-upgrades once a release is 30 minutes old and all conversations are idle, starts Magpie in the tray with DSH, and toggles its lite mode and sleep prevention.

Adds a power button to the session header with two actions, each requiring a second click to confirm. Restart terminates the Electron main process itself (taskkill /F without /T), so no crash dialog appears: the host then exits gracefully on its own once the IPC channel drops, and a detached helper relaunches the same executable after the single-instance lock is released, confirming the new instance by a real window handle. Shut down does the same without relaunching. Leftover GPU and renderer processes from the previous run are reaped best-effort. Windows desktop app.

A six-stop reasoning-effort slider for DeepSeek Harness, with a pixel-texture Ultracode mode that sweeps in from right to left and adapts to light and dark themes.