Plugins

Right-sidebar page for DSH that draws the current session's repository as a VS Code-style commit graph - colored branch/merge lanes, ref chips and per-commit details - with a working-tree Changes area above it (staged/unstaged sections with inline diffs) for every working tree of the repository; read-only, works with or without dsh-better-sidebar, and follows the session's worktree label when dsh-session-worktree is installed.

Run one deterministic skill-routing pass on every user instruction, so the skill catalog is consulted before the model answers instead of after it remembers. On the host it scores the live catalog from the instruction's keywords and the catalog metadata, with no LLM or embedding call, and appends a single producer-tagged message to the step: a ranked shortlist by default, the winning SKILL.md body once the score clears a threshold, or an instruction to call a named router skill exactly once. Unrelated instructions stay silent.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Live progress bar under the composer with a percentage and an estimated time left for the current DeepSeek Harness turn; the estimate re-anchors as the turn runs and never reads 100% until the turn ends, and the bar turns red when the turn fails or is interrupted.

Plays a voice line or a sound when a turn finishes and a failure cue when a tool call or a turn errors — user aborts stay silent by default and subagent sessions are skipped, both configurable. Three alert modes: voice, effects, or off. Effects is the default and ships 20 built-in sounds (10 alert chimes + 10 nature), each assignable to the done, fail or approval event with per-row preview, so it needs no API key and no audio files; the voice route uses Volcengine TTS with cloned or preset voices, batch-imported voice IDs and fingerprint reuse that skips re-synthesis when text, voice and parameters are unchanged. A third approval slot exists but has no automatic trigger — it only plays when called manually. Playback goes through winmm/waveOut as-is, never changing the system volume or mute state, and the player is spawned detached so session teardown cannot silence it. Windows only.

Network and proxy doctor for DSH: checks system proxy settings, probes local proxy ports, detects TUN adapters, tests GitHub, TCP and HTTP reachability, scans hosts conflicts and prints concrete suggestions for what to change.

Adds a Quick Chat entry to the Web UI sidebar that opens a floating chat window with its own model and reasoning-effort picker, optionally seeded with the current session's transcript, and keeps every side conversation in a resumable, renamable, deletable history.

Turns a Xiaohongshu, Douyin, TikTok, YouTube or X link into text: transcript with timecodes, on-screen text, a description and OCR of every image, caption and metadata. Mounts the hosted MCP server over streamable HTTP.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

Official DeepSeek platform monitoring inside the provider card: a live balance chip left of the composer model name plus an expandable account-details panel with per-model monthly usage and a daily stacked chart.

Real DeepSeek account balance and official spend tracker in the session header, with peak/off-peak badge, monetary alert with auto-stop, and one-click top-up.

Read-only SonarQube Community Build tools: instance status, project Quality Gate for a branch or pull request, issue and Security Hotspot search, single hotspot detail, and coverage, duplication or caller-selected measures. Issue and hotspot results carry a normalized location with component key, file path, line and text range.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Peak-Valley Meter (峰谷电表) — a tiny DeepSeek usage companion: a minimal two-part balance chip above the composer (currency symbol + number, nothing else), official balance refreshed every 5s; click the symbol to open the official top-up page in a new tab; hovering the chip fades in a circular backdrop under the symbol, its left arc flush with the chip's own left edge, and expands a 24h peak/valley timeline (orange=peak, blue=valley, glowing marker at the current local time) so off-peak hours are obvious; independent today-spend metering; a settings panel with 10 muted color presets plus custom valley/peak colors, detailed/minimal styles and readout toggles; all-Chinese UI.

Sidebar session-title icons: an auxiliary model call on the same route as title generation draws a 24x24 monochrome SVG metaphor shown before each session row title, with disk caching.

DSH workspace hub: organize workspaces into color-coded folders in the sidebar (three-level drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, dual-channel search) with per-workspace and per-session token usage and cost stats from real session logs (official DeepSeek peak/off-peak pricing for any deepseek model, three spend calibers, hover detail cards, overview panel) plus OpenCode Go plan usage; data persists to host disk and refreshes live every 30 s.

DeepSeek API balance widget for the dsh web sidebar: a live, auto-refreshing balance pill (balance / today spend / today tokens) with a detail popover (cumulative spend, monthly usage, request count). Every user sees only their own balance — keys are reso

One-click start/stop button pinned to the window bottom-right corner: restarts DeepSeek Harness in place via a detached helper that relaunches the exact boot invocation (loopback same-origin guarded), with an optional stop-only action.

Unifies every DSH extensibility seam behind one declarative DSL: a runtime `fabric` service, `fabric_extend`/`fabric_inspect` tools, and a capability-graph settings page.

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Provides the bili_summary tool: Bilibili video metadata, subtitle timeline, and sharp-based frame capture with built-in error handling and graceful degradation.

Upload an image as a full-window frosted-glass theme: sidebar/conversation/details share one frost layer, Save/Delete, official Light/Dark/System stay in charge.

MiniMax token-plan quota dock for the Web UI: a drop-shape 5h-usage % chip in the conversation input area, click for a detail panel listing every model's 5h & weekly usage and reset countdown, auto-hidden when the active default model is not a MiniMax model.