@goodandready/dsh-dsml-artifact-guard
Sanitizes leaked DeepSeek DSML closing tags from model text streams
161 results
Sanitizes leaked DeepSeek DSML closing tags from model text streams
Model availability tester panel in the Models settings page: one-click real streaming test per added model with TPS / first-token / elapsed metrics
DSH voice reader: read LLM replies aloud as they stream. Edge-tts built-in, any OpenAI-compatible cloud TTS plugs in via the settings panel, plus a voiced waiting-phrase ticker while the model thinks.
Patient auto-retry for DeepSeek Harness: honor the upstream gateway's retry_after_seconds on a 429 capacity cooldown instead of giving up after two fast retries. Optional floating countdown badge included.
Bundles the 14 obra/superpowers skills for the DeepSeek Harness (dsh) from a recorded upstream tag (v6.3.0), re-syncable with drift reporting.
Fixes malformed tool-call arguments (nested {"arguments":{…}} wrappers, wrapper-key aliases, param-key aliases) at the llm/stream seam — repairs execution, persistence and history replay in one place. 修复模型产出的畸形工具参数。
Live streaming terminal output for DeepSeek Harness
DSH 插件:让 AI 回答输出中文全角标点(用户直接复制回答内容也是全角)。监听 llm/stream 瀑布,在模型输出流上做智能半角→全角转换,跳过代码块/行内代码/数字小数点/URL/时间/markdown 链接,并注入 system prompt 提示模型输出全角。
Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run server). Bilingual UI (zh/en)
Codex-style right-edge workspace for DeepSeek dsh web: file tree + preview, embedded browser (direct/proxy iframe), and side chat via host ctx.llm streaming
DSH 提示词锻炉:零配置流式优化(复用会话模型)+ 轻量词库(JSON 文件)+ 一键存技能。Prompt Forge: zero-config streaming optimization + file-based prompt library + one-click skills.
Set up free, encrypted, deduplicated backups of remote Linux servers, pulled from a Windows PC with Restic — tar-over-SSH streaming, zero software installed server-side, with size verification against
DeepSeek Harness web plugin: an ambient balance/limit reading under the composer, showing upstream-reported DeepSeek balance and OpenCode Go usage, plus a day’s spend folded from the balance deltas the host samples.
DeepSeek Harness (dsh) plugin: WeCom (WeChat Work) smart-robot integration over the long-connection (WebSocket) API. Per-session agents, idempotent msgid dedup, stream/markdown replies, media download/upload, whitelist, welcome/feedback events.
LLM provider plugin for the DeepSeek Harness (dsh): streams Claude (Sonnet/Haiku/Opus) through your Claude Code subscription (claude.ai OAuth credentials), no Anthropic API key required.
Keyboard shortcut that injects an encouraging message into the running dsh-TUI conversation: steer when a tool is in flight, interrupt-and-deliver when the model is only streaming text
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot,扫码即用:dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.