Edit any user turn in DeepSeek Harness and re-run it: an inline editor rolls the conversation back through the official surface-replace contract, then re-prompts the agent with the revised text. The append-only session log is never rewritten.
Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first: plain audio files under ~/.dsh/voice/.
Nightly self-improvement for your DeepSeek Harness agent: harvest past sessions, replay recurring tasks, and consolidate validated skills behind a held-out gate. Brings microsoft/SkillOpt's SkillOpt-Sleep engine to dsh as native tools + a bundled skill (MIT).
DeepSeek Harness plugin that does QA: an agent explores your app like a real user and leaves evidence, then the explored path is exported as a deterministic replay scenario you run every release. Orchestrates the browser, macOS desktop, iOS and Android drivers — never a false green.
A DeepSeek Harness bundle reimplementing opengsd-core (Git Ship Done) as host-plane Cordis plugins, replacing the default agent-loop behaviour with the GSD phase loop.
Audit citation sources in AI responses – extract URLs from the reply, score and rank them by threat level, and output a detailed report. Domains on your blocklist will be genuinely blocked – web tools such as web_search and web_fetch will directly refuse to access them. The blocklist is fully maintained by you.
Per-message delete for DeepSeek Harness: remove a user message, one reply step, or a whole assistant reply from the derived model context via the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.
