Plugin

Conversation font-size controls for the Web UI: a stepper in the composer row, keyboard shortcuts, and Ctrl+wheel zoom, all writing through the theme service setFontSize.

Next-step suggestions for the DSH composer: after each completed turn, one auxiliary call on the session's current model returns 3 clickable follow-up suggestions above the input box, and clicking one fills the draft.

\!WARNING\! this removes the authentication step !WARNING! Exchanges the process launch token for the browser-session cookie, so a first visit needs no ?token=... in the URL.

Bridges DeepSeek Harness sessions to Feishu/Lark, Telegram and DingTalk: each chat is bound to a resumable DSH session, replies stream back as cards, and a task-end card reports the model, token usage, step count and duration. Question and permission-approval cards are answerable from the chat, and a web settings pane configures the per-channel credentials.

Eyes for text-only models: mounts the bundled stdio MCP server as mcp__opencode_eyes__describe_image, which sends an image file to StepFun step-3.7-flash and returns a detailed description.

Observes consecutive identical tool failures and optionally pauses before the next model step, preserving original results and successful repeats, with an in-chat report in DSH Web.

Adds Copy session ID and permanent deletion of a Conversation's log, projection cache and workspace references to the session row's ⋯ menu, behind a two-step confirm.

Live token usage and estimated cost in the sidebar: the current task plus every session combined, an as-of clock for those totals, per-session time detail (elapsed, turns/steps, first-token, model vs tool time, decode speed), and a per-turn breakdown with each turn cost on hover.

A right-sidebar session panel that lists every Skill, MCP tool call and file read or write by turn and step, with per-failure error detail.

Convert Notion blocks and Markdown in both directions, with no API client and no external dependency. A Notion paragraph is an array of rich-text runs while Markdown says one string, so the two directions are a split and a merge rather than a pair of inverses — rich-text runs are cut at every annotation boundary one way and re-merged the other, with fences widened when the content already contains backticks. Reports every lossy step instead of swallowing it.

Recovers broken DSH turns: widens the product's own retry budget and renders the wait as a live countdown inside the same step, keeps a truncated output alive inside the same turn, and can open an opt-in continuation round when a turn has already ended; while the composer is empty it hands the send button to that continuation.

DSH plugin: hands a long session over to a fresh session in the same workspace on /handoff or at a token threshold, carrying the preset, model, permissions and plan mode across; the brief is written by the session's own model and the switch waits for a step boundary instead of interrupting running work.

Jev (TypeSafe System One) judgments at the DeepSeek Harness agent-loop gates: pre-step, pre-execute, post-execute, and turn-stopping. No UI dependencies; mount it in any Harness composition.

Bring a DSH plugin repository's build and release pipeline into the app: a sidebar panel listing each repository's latest workflow run, its releases, and how far the local checkout has drifted from the last release, with buttons to trigger a build, cut a release, publish a draft, re-run, cancel, or read the failed-step log. Drives the workflows through the machine's authenticated gh CLI, so the plugin stores no credential of its own, and which repositories are tracked lives in a config file rather than the package.

Sidebar unread / waiting / status hub for DSH Web: a bell jumps to the next unread session, a shortcut walks sessions waiting for input, and ⌘⇧, / ⌘⇧. step back and forward through the conversations you have visited; one overlay lists unread and pending sessions side by side; a six-metric readout at the sidebar foot makes every icon a button that jumps to the next session of that kind; a host-side ledger keeps the account across restarts, so an unread session keeps its green row dot after a restart, and a startup dialog offers to re-send a continue message to sessions whose turn was cut off.

English-only fork of dsh-model-router. Routes each agent step across a configurable model pool and adjusts reasoning effort based on task complexity, tool failures, and cost.

DeepSeek Harness 生图插件：文生图 / 图片生成，基于火山方舟 Seedream（豆包）。零依赖，纯 JavaScript，无需构建。 | DSH image generation plugin for DeepSeek Harness: text-to-image via Volcano Ark Seedream (Doubao). Zero dependencies, plain JavaScript, no build step.

Task-list staleness guard for DeepSeek Harness: watches the session event stream and counts tool calls since the last todo_write; past a configurable threshold it appends one short notice before the next step, quoting the current list, so the model writes it back to the real progress instead of leaving a stale snapshot on screen. Pure prompt injection, no blocking and no data mutation.

Ocean-blue theme for the DSH web interface: swimming fish, rising bubbles, a daily-quote ticker above the input box, and a replacement brand area; Settings → Marine Theme exposes 7 groups and 32 options (brand text and size, badge, primary color, watermark, fish, quotes, overall scale) that apply instantly without a reload, plus a two-step reset to defaults.

Persistent work-progress row in the band below the composer: task completion, a progress bar, and what the agent is doing right now (generating a reply or running a tool), expandable into the full task list with turns, steps, timings and context usage.

Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.

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.

Record every step the agent took, and walk through it forwards and backwards to find where it went wrong.

Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.