Plugins

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

Per-turn and per-session API cost estimation for DeepSeek Harness conversations.

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

Watches Feishu (Lark) conversations with your own user identity and forwards new messages as prompts into a chosen DeepSeek Harness session: per-monitor sender filters, @bot-mention bypass and keyword allow/block lists, auto-created pinned target sessions, and cursor-based polling that re-reads messages after a failed delivery.

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

Conveniently shut down the dsh web server: a conversation-header exit button plus an agent tool, using the launcher's bounded shutdown path.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Global Schedule tab for DeepSeek Harness Web: view built-in scheduled reminders across all dialogs and open their source conversations.

OpenCode Go provider for DeepSeek Harness: live gateway catalog, per-conversation session header, usage

DeepSeek Harness (dsh) 设置卡片 + 对话节点插件

One-click publish of DSH conversations as Markdown articles on a Halo CMS blog: confirm in the GUI, type the console password (never stored), and the Q&A record is created through the Halo REST API.

Brings the models included in the Xiaomi MiMo desktop app (free during beta) into DeepSeek Harness, with zero configuration in the DSH conversation window.

Session-header balance readout for DeepSeek Harness: shows the spendable account total (recharge and bonus wallets combined) in the conversation header, refreshed every two minutes, and renders nothing when the account is signed out or the query fails.

Read Google Antigravity SQLite conversations in DeepSeek Harness and import them as native sidebar sessions with list, read and import tools plus slash commands.

Reopens the conversation you were last in after restarting DeepSeek Harness, by keeping a pointer file under the DSH home directory instead of patching engine files.

Give any Session a colour mark, shown as a chip in the sidebar and picked from the conversation header; marks are stored on the Host, so a colour chosen on one device is visible on every other one.

Moves selected messages from one conversation into another, and manages a workspace's conversations with archive, restore, delete and move between workspaces.

Declares the wire protocol for the opencode-go route so models the installed catalog does not describe resolve, adds the DeepSeek V4.1 models to that route when they are missing, and attaches a per-conversation x-opencode-session header to OpenCode requests.

Cross-agent token usage dashboard: aggregates local conversation logs from Claude Code, OpenCode, Cursor IDE, DSH, OpenClaw, CodeWhale, Hermes and more into a persistent ledger that survives log deletion, with cache-hit rate, cost estimation, period comparison and day drill-down analytics in a sidebar panel.

Event-driven Hypatia memory for DSH: automatic conversation logging via session events, queued background consolidation (span summaries + work-unit extraction) with a dedicated model route, and recall injection — zero per-call model work in the main sessi

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Adds the right sidebar's expand trigger on pages with no conversation, matching the product's own control.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

Keeps the question you are currently on pinned above the composer, with a dropdown of every earlier question that scrolls the conversation back to that turn; questions folded into process groups are expanded first, and Escape, scrolling or clicking outside collapses the panel.