Sessions & Messages

Learning mode that explains each agent step (WIP).

Manages archived DSH chats with conversation search, restore, and confirmed safe permanent deletion.

Select part of a conversation and ask about it in a right-side side chat; bring AI replies back to the main chat directly or as a summary.

Bookmark assistant replies with notes and tags; browse every bookmark in one cross-session center and export to Markdown.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

Archived-session manager for DSH Web: workspace-grouped list, FTS5 full-text search over session content with per-session snippets, restore-and-open, and hard delete.

Fold completed turns into their final conclusions, split thinking from prose with a divider, and jump between turns from a rail dockable left or right with line or dot marks, an optional ring and hover summaries; it can hide the host right-edge TurnNavigator, load earlier history, and open a pre-filled diagnostics issue.

Repair DeepSeek Harness sessions that refuse to load, with a sidebar Session surgeon overlay and dry-run repair.

Pin sessions and workspaces to the top of the Web sidebar with per-pin row colors, a header toggle and a pinned panel; 0.4.0 adds a navigation organizer — pin groups (boards), tags and saved filter views, session health summaries, and /goto.

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log.

Delete sessions with a 5-second undo and a recycle bin, plus an archive view to browse and unarchive, for the DSH Web GUI. Ships on npm as `@wsxwj123/dsh-session-manager`.

Archived-session management: browse archived sessions, unarchive them, or clear them out.

Bring the deepseek.com web/app chat experience to DSH: edit your prompt and regenerate answers in place, with a per-message <i/N> version pager (tree model, stable across conversations).

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

Injects one fixed system-prompt section so the agent thinks and replies in Chinese, regardless of the user's language.

Adds a configurable humanized whale-girl maid persona with immersive roleplay, speaking modes, and a lightweight layered memory with query-triggered recall.

Archived-session manager for DSH Web UI: reopen an archived session and keep chatting, unarchive it back in place, or hard-delete a session — grouped panel with message search and native view sync.

LLM-free lossless* compaction engine for DeepSeek Harness

Import claude-code / codex / reasonix / zcode chat history into dsh sessions: workspace binding, tool calls preserved, oversized-session protection, zcode compaction restore.

Copy and open `dsh://` session deep links, or paste them into another conversation to inject a bounded, read-only snapshot of the referenced session.

Let dsh and Claude Code sessions message each other directly; comes with a clickable peer list card (sort/search/send/refresh).

Drop-in agent loop with bounded-slice context engine (cordis).

Injects one system-prompt section so the agent's chain-of-thought, planning and tool-invocation reasoning stay in Simplified Chinese. Zero external dependencies - clone and link-install from any local directory, no npm build or publish required.