Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

Pin sessions and workspaces to the top of the DeepSeek Harness sidebar with per-pin row colors — a dual-face (host + client) dsh plugin with row [pin][swatch] controls, a header toggle, and a pinned panel.

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-t

Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval

Requires dsh >= 0.1.7 (session format 4); on dsh 0.1.5 use dsh-repeat-tool-breaker@0.7. Escalating repeat detection for dsh: a synchronous ctx.tools.guard gate that counts semantic fingerprints (exact/cmd/net/host/sink) over a per-agent sliding window, wa

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.