Plugins

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

Adds a native Store section to DSH Settings for catalog search, tag filtering, sorting, installation, and installed-plugin management.

Life-story skill: capture moments and fragments, build a user profile and generate novels, scripts or autobiographies.

Merged plugin: wallpaper customization (original-resolution uploads, crop editor, per-area opacity, MP4/WebM dynamic wallpapers) + Steam Workshop wallpaper extraction (parses scene.pkg/.tex via a bundled Python script, preview/download) + DeepSeek balance & usage widget + OpenCode Go plan usage (rolling/weekly/monthly percents in a top header pill; expand for progress bars & reset countdowns). API keys are read from DSH's credential store by the host — never stored in source or the browser.

Durable citation-thread learning companion for DeepSeek Harness conversations

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Ask-before-act approval for every edit and every bash command: a red/green line diff before a file is touched, a description+command panel before a command runs — approve once or reject, each gate with its own master switch in Settings → General.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

User-side undo/redo for DeepSeek Harness (dsh): the /undo command rolls the transcript back to before the last message and /redo restores it.

Steam Workshop-style plugin store for the DSH Web UI: browse, search, and one-click install community plugins with mirror acceleration, progress UI, security checks, and Chinese descriptions.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Lists the Markdown documents, images and video that already exist anywhere in the session workspace in the DSH sidebar, ranked by relevance to the current conversation: recent messages are matched locally against document title, summary and body with IDF weighting, with no model calls and no network. Because the list is scanned from the workspace instead of remembered, restarting DSH or starting a new session does not empty it. Images and video preview in place, with relative-path images resolved and video streamed over HTTP Range. The same ranking is exposed to the agent as a knit_docs tool, which returns the most relevant documents along with the passage that matched in each, where one is found.

Peak/off-peak billing clock with a provider-neutral account readout (DeepSeek balance, subscription plan windows, relay credits), per-turn spend measured from the provider's own counter, and a /hist token-history scene split per provider for dsh-tui

Multi-language codebase intelligence for MCP-compatible IDEs, the CLI and DeepSeek Harness: chat, search, audit, refactor, and board-ready reports from local code.

Workspace drift awareness for DeepSeek Harness agents: detects external/user file changes and injects them into the agent context at step boundaries.

Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.

Runs PowerShell scripts through base64 encoding, so quotes, $, backslashes and CJK survive as written. Same sandbox channel as the built-in pwsh tool.