Plugins

A human-in-the-loop curation workbench inside a DSH session: mark whole turns or single messages to keep verbatim or to summarize, rewrite user, assistant, tool-result and injected-context messages in place without a model call, then compress the marked ranges with model-written summaries or the official /compact. A local JSON backup is written before every write to the session.

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

Compaction backend that replaces the default compaction-basic: it summarizes the conversation with a configurable pool of low-cost models, sizes each chunk to the chosen model's context window, and merges all digests in one call, with per-route cooldown and session-model fallback.

Adds a manual, confirm-first title generator: a header button and a session-row menu entry ask a model to summarize the whole conversation, show the proposal in an editable dialog, and rename the session only after you confirm — without registering a title provider or changing automatic titling.

DSH slash command /commit: stages all changes, summarizes the staged diff with the session model, and commits; no browser UI required, with a local fallback when the model call fails.

Route conversation-compaction calls to a chosen summarizer model in the Web settings page, and retry them on a configured fallback model when the primary ends in an error.

Summarizes the current DeepSeek Harness session with /recap or after inactivity, with configurable models, Chinese and English output, and expandable summaries in the conversation.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Auto-renames DSH sessions with LLM-summarized titles: runs after the first prompt and on /handoff, or manually via a header button or /autotitle, with configurable title language and max title bytes.

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

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

One-click context compression for the dsh web GUI: a 压缩 button on the session title bar summarizes the whole conversation into a few lines, opens a new session in the same workspace seeded with the summary, and switches to it — the original session stays untouched.

Shows a floating toolbar above text selected in a conversation, with copy, quote, ask, explain, translate, summarize, and custom prompt actions.

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement