Plugin

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

Persistent conversation memory for DeepSeek Harness: memory tab, automatic AI naming, per-AI privacy isolation, sidebar AI names, and automatic experience archiving. A static profile plugin available in every preset without disappearing on restart.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Native DSH foundation bundle that registers a persistent default workspace, provides paged read-only inspection of plugins, skills, memory, sessions, storage, settings, credentials, and DSH_HOME files, and synchronizes rich CLIProxyAPI model capabilities into native provider settings.

Automatically sends a "continue" prompt when a reply is cut off at the output token limit, resuming long answers without manual input; aimed at self-hosted Ollama deployments with small output caps.

Temporary workspace for DSH web — one click creates a throwaway workspace whose conversations are deleted at the next restart (immediately or after a delay, optionally behind a confirm dialog). Pin a temp workspace to keep it: its files move into the folder you pick, its title becomes that folder's name, its conversations migrate, and a real host-level restart re-indexes them.

Adds a handoff button to every assistant message that writes an LLM-summarized handoff document of the current conversation into the workspace handoff/ directory.

Dreaming for agents: replay recent conversations between sessions (dream_digest), reflect and write a dream journal (dream_save/journal/recall), and idempotently bridge recurring lessons into AGENTS.md (dream_bridge). Reads multi-frame zstd session archives with privacy masking on by default; six tools including a health self-check; zero runtime dependencies.

Floating todo panel for DSH sessions with server-side cross-device persistence and pending-task badges in the session list.

Manage archived conversations in the Settings UI: unarchive them back to the sidebar, or permanently delete them with confirmation.

Recall previously sent messages in the input box with Up/Down, and archive a workspace session from its right-click menu.

Neutralize tool calls with invalid JSON arguments on the wire so one malformed model generation cannot brick a session against strict OpenAI-compatible servers.

Launches a fresh, continuable parallel session from the composer command menu (/side-chat) while the main session keeps running.

Daily rotating anime companion persona: deterministic date pick from JSON character cards, roster/reroll tools, and a voice-map route.

Personal directives for DeepSeek Harness — system-prompt injection, tools, and a top-bar runtime toggle, shipping neutral placeholder instructions you replace with your own.

Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.

Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no API key; includes persistent quota tracker with rate-limit detection and reset countdown.

Model Health panel in Settings: lists every model configured in settings.yaml and batch-tests availability and latency for each.

Registers Kimi, Grok, Codex, and MiniMax as DeepSeek Harness model routes, vendor subagent recipes, and kernel_status / kernel_run / kernel_switch tools.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issues the request automatically, so subscription quota and rate-limit errors (429 / insufficient_quota) do not interrupt a run.

Taojian (陶笺): Claude-inspired DSH theme with warm paper, clay accent, Noto Serif SC, and Cascadia Mono.