Plugins

Model-directed context compaction for PTC mode, grouping program runs into blocks and replacing completed block messages with model-written summaries.

Adds a Delete session action to the sidebar session menu that permanently deletes the local records of that session, while refusing sessions that are running.

Two-tab archive panel (archived / active) where every row offers archive or unarchive next to permanent delete; each row shows its bound workspace folder as a clickable path, and queued archive-entry cleanup keeps a deleted session from resurfacing in the active list.

Cross-agent session relay: a compact "Relay" chip in the composer toolbar unfolds a floating workbench to browse recent sessions of eight external agents (Claude Code, Codex, OpenCode, ZCode, Pi, WorkBuddy, Cursor, Grok); one click spawns a DSH session with the takeover command delivered and auto-switches to it. handoff: 1 protocol inbox cards are consume-once with a four-state evidence ledger; patches ride with cards; cross-machine relay via a synced folder. Settings keeps the command reference and reader toggles.

/compact and auto-compaction summarize with the model selected in the session, not the model that finished the last turn.

Resume a conversation whose turn stopped early: /continue and an action-row button carry the interrupted reply on, covering manual stops, failed model requests, output-token cutoffs and crash recovery, and the continuation prompt is retired from the transcript once it has been answered.

Compacts a long session after a configurable idle time when its context exceeds a configurable token threshold, before the provider KV cache expires; both values are set on the plugin's page in the Plugins manager.

Per-session color tags for DeepSeek Harness: hover a sidebar session row to pick one of 12 colors, with a colored bar on tagged rows and host-side persistence.

One standing system prompt for every workspace: a Custom instructions page in DSH's own Settings panel whose text is added to the system prompt of every session, subagents included, and stored in the profile instead of any project.

Tsundere mesugaki persona pack: dialect replaces whole sentence skeletons instead of sprinkling dialect words, stays on as the default voice even through work talk and delivery reports, and ships a temper system, banter mode and silent file handling.

Banter lexicon plugin: collects the words and angry quips the user said into banter ammo with add, list and random-pick tools, and injects the current ammo list into the prompt every turn.

Compiles an LLM persona in DSH from six dimensions (identity, tone, creative habits, feedback style, boundaries, run parameters), injects the compiled text into the system prompt at the end, ships six built-in templates plus a drop-in templates folder, and drafts a persona from your own past messages — either by counting patterns in them or by having the current model read them and report its rationale. Adds a panel next to the composer and a /persona command.

Configure DMXAPI Chat Completions, Responses, Anthropic Messages, and custom providers; edit models on existing preset routes.

Adds an independent OpenCode Go connection with credential settings, manual model discovery, and per-conversation session headers.

Agnes AI provider for llm-pi-ai: 4 multimodal chat models declared in the bundle patch, plus image and video generation tools.

Model list control for DeepSeek Harness: hide any model from the selector, give it your own display name while keeping the provider billing rate, and arrange the order with arrows. Search, per-provider batch toggles, one-click restore. Display only — no provider configuration is rewritten.

Registers a local LLM provider that routes model calls to an OpenAI-compatible endpoint or the Ollama native API, with a connection-test card in the Models settings page and no account sign-in.

Expose every free model from a local opencode serve catalog — all providers, including your own custom ones — to DeepSeek Harness's model picker, with OpenCode's native tools denied so execution stays in DSH.

Registers OpenCode Zen free models as a native provider: the catalog is discovered live from opencode.ai intersected with models.dev pricing, and a detail page can re-fetch it or test which models answer. Declares no dependencies, so the host's pi-ai stays the only one.

Recognizes a model ID in the DeepSeek Harness model catalog and fills that row's context window, input modalities and reasoning levels as editable suggestions, from a bundled offline rule table covering 33 vendors.

Use Zed AI hosted models in DSH.

Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back declared to models.dev to a 7-tier default, and replaces the composer model chip with a Codex-style vertical picker.

A row of model preset buttons above the composer: left-click switches the session to that preset's provider, model and reasoning effort, right-click opens an editor for it, and each preset can carry a custom name instead of the model id. The editor reads the session's live model catalog, and presets are stored locally.

Configure thinking toggles and reasoning efforts per model for llm-pi-ai and official DeepSeek, and specify input modalities (input or inputModalities) in the DSH settings panel.