Plugins

Adds an optimize button beside the composer that analyzes and rewrites the prompt draft with SSE streaming, conversation-context awareness (template vs intent-polish strategies), an edit-continuity memory chain, undo, and model routing with fallback and a connectivity test.

Four-source migration wizard: move Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DSH (/move wizard with approval gate and idempotent move.json, resumable sessions).

Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.

Official-grade GitHub CI integration: a composite action.yml, a polling PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval.

Claude Code /rewind for DeepSeek Harness: git-first workspace snapshots before every mutating tool execution, turn-boundary session forks, and a one-shot /rewind command that restores files and forks the session back to a checkpoint.

Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

DeepSeek Harness plugin for dsh-baton: adding it is the whole install. Switched on, it registers the dsh-baton MCP server for Claude Code and Codex, then takes the baton over a local, owner-only control socket, runs it in a specific session through the ho

Terminal-native TUI frontend for DeepSeek Harness that presents sessions, models, plugins, jobs, subagents, todos, and provider configuration through Harness capabilities while preserving real terminal scrollback.

Goal lifecycle management for dsh with an interactive kanban board: goals, criteria, attempts and reviews live in the workspace, driven by graph_* tools, with a two-lane board rendered in the conversation view.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Windows desktop computer-use tools (click, type, key, screenshot) with freshness checks, approval gating, process-identity verification around every action, and a sanitized audit trail.

DeepSeek Harness Cordis tools for All in Flash, powered by All in Luna

Imports sessions from pi, opencode, codex, claude-code and WorkBuddy into DSH, unifies AGENTS.md, skills, project and per-agent memory across harnesses with symlinks instead of copies, and migrates Codex and WorkBuddy automations into DSH scheduled tasks.

Model selector for the DSH composer that keeps the native button and menu and takes over only when the small dropdown would open: search across providers, probe any model with a real streaming request to measure TTFT and TPS, and browse a leaderboard of up to 100 rows built from OpenRouter's catalogue, where clicking a row searches local channels of that name.

Wraps the local GitHub CLI (gh) in agent tools for pull requests, issues, Actions runs, repository search and raw API calls, plus /gh status and /gh help slash commands and two web panels (a global repository cockpit and a per-session workspace panel).

Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.

Terminal-style input history for the web composer: edge-first arrow-key recall with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, and sliding-context awareness; 0.5.0 adds a smart input layer — cross-session snippets (/save, /load), prompt templates with variables, reuse insights, and compaction-summary highlighting.

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

Fine grained per tool permission rules for DSH at the tools/pre-execute gate, deny and ask lists in Claude Code rule syntax (`Bash(rm -rf:*), Read(_secrets_), mcp__server__tool`), works standalone without migrating.

Imports Claude Code setup into DeepSeek Harness from a native settings screen or CLI, with dry-run previews for skills, commands, agents, hooks, permission rules, and MCP config. Codex and OpenCode remain supported as secondary origins, with collision-safe apply and post-move checks.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

PII masking for DeepSeek Harness — anonymizes names, phones, emails, ids, and keys before requests and restores them at the display layer, keeping plaintext out of session logs.