Best DSH Statistics Plugins

Computer use for Windows: screenshot, mouse, keyboard, clipboard and window tools with per-app access that goes through DSH approval; while the agent is in control the screen shows an orange glow and a status bar, and Esc pauses or resumes.

Cost tracking priced from an online catalogue (models.dev + OpenRouter, 8000+ models, each call priced at its own instant): a per-turn cost line, a Cost tab attributing spend to tool output / model output / system prompt / commands, budget, monthly forecast, ~166 live-rate currencies, and a bill_stats agent tool.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

IDE-style Git panel in the DSH Web GUI: a resident tab with a three-column overview (branch/tag list, searchable commit-history graph, commit detail with changed-file tree and message) and a changes page (stats bar, uncommitted list with per-file stage/unstage/discard, commit box with amend); side-by-side diffs carry lazy highlight.js syntax highlighting, on-demand between-hunk context expansion and word-level intra-line emphasis, with image files shown as before/after panes; plus a zsh-style branch marker in the input bar. Every git command runs as an argv array through the host subprocess service, cwd locked to the repo root.

Academic writing guard (EN/ZH bilingual): removes AI-style defensive writing, protects scientific evidence (numbers, citations, claim strength, null findings, scope) during polishing, and calibrates writing toward a target journal (Journal Profile + Journal Fit). Deterministic local regex/statistics, zero network/LLM; writing_rules / writing_audit / writing_style_profile / writing_journal_profile with auto-audit on paper writes.

Multi-threaded downloader plugin for DeepSeek Harness with bundled aria2: probes the target for Range support, then picks aria2 (4 or 8 connections by file size) or falls back to curl.

Data cleaning and data enrichment for CSV/XLSX/JSON enterprise lists in DeepSeek Harness, including spreadsheet cleaning, deduplication, profiling, optional Qichacha MCP and exports.

Embedded C/C++ AI engineering plugin — firmware skills (FreeRTOS, Keil, HardFault, state machines) + 1% Rule / Plan Verification Gate discipline | 嵌入式 C/C++ 工程 AI 插件:固件技能与 agent 纪律。 For Claude Code, Codex, Cursor, Kimi, OpenCode, ZCode and DeepSeek Harness (dsh)

DSH plugin: shows your DeepSeek account balance at the bottom of the left sidebar (native UI)

Batch-port official Codex plugins into DSH skills (codex_list/port/status/health; measured: 186 plugins / 583 skills, 577 ported, 0 failures).

Database tools for agents: list/query/exec/schema/stats/health across SQLite/MySQL/PostgreSQL, with lexer-grade read-only protection, row caps, CSV/JSON query output and an approval-gated write path.

Dedicated read-only Git Graph view beside Chat and Trajectory: commit topology, local/remote/tag refs, HEAD and working-tree status, search, filtering, first-parent mode, refresh, and load more.

Git view for DeepSeek Harness: status, commit graph, branches and tags in one picker, diff, staging/commit, push/pull and blame.

Adds an unofficial Antigravity OAuth-backed LLM route, web search, image generation and editing, video understanding, quota status, and DSH Web settings controls.

GitHub-style usage heatmap dashboard: per-workspace turn counts and token spend (with cache-hit rate), DeepSeek account balance, and workspace aliases.

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, fetch/pull/push sync, branch and remote management, git init, multi-repo switch, color-coded file status, file-type icons), an editor view that opens every file reached from the chat, the file tree or source control (Markdown/HTML/PDF/image previews, 15-language syntax highlighting, hunk-level diff editing, Ctrl+S save), file operations (new/move/copy/delete, reveal in file explorer), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), and commit messages generated from the staged diff by a host-configured model.

Speaks or plays a sound at the end of every turn and plays a failure cue when a tool call or a turn errors. Ships 20 built-in effects (10 alert chimes + 10 nature sounds) and defaults to effect mode, so it needs no API key and no audio files; an optional Volcengine voice-clone route generates the three announcement clips in one click. Plays through winmm/waveOut as-is, never changing the system volume or mute state. Windows only.

Agnes Token Plan quota panel rendered as a config card on the Harness Plugins page: account-wide quota windows (5-hour requests, weekly requests, daily images, daily video) plus cumulative usage with a daily chart and the public plan catalogue, all read from the Agnes console API, with in-panel sign-in and automatic re-login. Four opt-in switches, off by default, register the Agnes models as an LLM provider, connect the AgnesCode desktop-app login state as a second upstream provider, and expose image- and video-generation tools to the agent.

PubMed deep-research toolset: literature search, author investigation, same-name disambiguation, institution statistics and mentor-student matching.

Read-only Odoo tools over JSON-RPC: server info, model field introspection, and a restricted search_read limited to an allow list of models whose domain field names may not contain dots, so related-record traversal is not possible. A draft-create tool is registered only when allowWrite is enabled, and is limited to sale.order and project.task with the draft state enforced by the plugin.

Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.

Tavily search and page fetch: tavily_search queries with a rotating pool of up to eight API keys that backs off per key on 401/403/429 so one exhausted account does not take the tool down, and web_fetch retrieves a single page through curl, returning its HTTP status with de-tagged text.

Network & proxy assistant for DeepSeek Harness (dsh): one-shot GitHub connectivity check, system proxy status, proxy port probing, full diag chain (DNS/TCP/HTTP) and hosts-file conflict scan — built from real-world China-network experience.

Measures design rules on the rendered page rather than in the CSS — type-scale count, WCAG AA contrast against the real composited backdrop, spacing-grid drift, palette size, tap targets, and the tells of generated UI such as violet gradients caught by hue angle; ships a design-system skill.

US stock quotes, price history, financial statements, analyst consensus and news via yahoo-finance2.

Tool-call discipline for DeepSeek Harness: injects a static behavior-constraint prompt section, drops the parallel pool to 1 after a tool failure (restoring after 3 consecutive successes), nudges the model to stop retrying after repeated failures, verifies writes with .bak rollback, gates high-risk commands, and tracks compliance stats via /behavior-status.

Wraps colbymchenry/codegraph into agent tools - status, search, callers/callees, impact, explore, and more.

Vets third-party plugins before you trust them: static scan for malicious patterns (exfiltration, credential access, obfuscation, persistence) and over-privileged path use, transitive-dependency coverage, official-package hash baseline for supply-chain tamper detection, and an optional plugin-tool call gate.

Cloudflare D1 tools for agents: d1_list/query/exec/schema/stats/health over the D1 HTTP API, read-only by default with a SQLite-accurate lexical guard, LIMIT row cap, CSV/JSON query output and an approval-gated write path.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Alternative plugin market for DSH: curated catalog plus live GitHub browsing, zh/en cross-language search, a fail-closed pre-install static security audit with an install-hook block, and per-plugin README viewing with garbled-encoding repair.

Browse the awesome-dsh-plugin catalog from a page in DSH Settings: filter by category or by installed state, search by name or description, sort by stars, downloads, name or date added, and install a plugin into the current profile. Two further tabs list what is already installed and which of those have a newer version in the catalog, with an update button on each row. The update view reports installed plugins whose update status cannot be determined, and overlapping install requests are refused. The catalog is cached locally for an hour with a mirror, a CDN and the npm registry as fallbacks when the official source is unreachable.

Git status, diff, log, commit, branch, and optional Change Ledger tools for DeepSeek Harness.

Search-first capability workflow for DSH agents (v1.0.0): reuse local tools or review exact-source plugins before installation, adapt or create capabilities in managed source work, and use receipts that distinguish installed, loaded, activated, and verified states; version tools cover rollback, adoption, and upstream updates.

GitHub MCP helper panel: shows copyable example prompts at Settings → Plugins → GitHub MCP (random 4 from a 30-example pool), visualizes a public user's repo star/fork/language, and adds the gh_repo_stats and gh_current_user model tools.

Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom address with one persistent toggle, an editable settings card, and agent-visible proxy status.

Connects GitHub's official remote MCP server as a DSH plugin: stores the PAT in DSH's credential center (.credentials.yaml) via github_set_token, and exposes GitHub tools as mcp__github__*.

Harness-kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax model routes (L1), distilled subagent recipes (L2) and kernel_run/kernel_status/kernel_switch tools.

Host-side Typert remote for dsh-tool-writing: serves project volumes, chapter status, corpus library, full-text search, evolution entries, and thread-graph data to the client writing panel.

Ten live-data tools over eight keyless public APIs: FX rates, weather, npm/PyPI versions, GitHub repo stats, Bilibili video stats, A-share/index/gold quotes, and IP geolocation. Tool defaults are configurable in settings.

Codebase Memory MCP bridge plugin for DeepSeek Harness: knowledge-graph code search, AST snippets, architecture analysis, call-graph tracing, auto-started graph UI, bundled skill, and /cbm command.

Ecosystem-wide plugin health audit: syncs the dsh-plugin topic into a local scored catalog (maintenance / docs / npm + weekly downloads / ecosystem, 0-100, A-D), static security scan with high-finding grade veto, star history snapshots, web leaderboard and agent tools.

DSH plugin bridging DeepSeek Harness agents to Cheat Engine: dynamic debugging, memory scanning, pointer analysis, breakpoints, and game memory hacking via ce_* tools.

Hosted tool server over MCP: invoice and bank-statement extraction with in-code arithmetic checks, ledger reconciliation in integer cents, PDF and table conversion, SQL dialect transpiling, and mainland-China reachability probes run from a China Mobile network vantage point.

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

Resident search index living in the host process: hot_find (fuzzy filename and path match, with frecency and git status), hot_fuzzy (content search that tolerates typos, including in Chinese), hot_grep (literal and regex content search), hot_plan (groups hits per file so a batch of files can be read in order) and hot_stats. One in-memory line index is built once and rebuilt on demand, so a query does not spawn a process.

Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.

Git development workbench for DeepSeek Harness: captures branch, status, worktrees, stashes and recent commits, with commands, tools and a settings UI.

Offline, deterministic public API catalog search for DeepSeek Harness, with Chinese and English queries plus exact filters for authentication, HTTPS, CORS, status, source tier, and category.

Project/task dual-mode workspaces for DSH: a task skips the workspace picker and gets a fresh scratch directory (D:\dsh_working\<name>-<timestamp>) per conversation, Codex-style; no-workspace sessions are grouped under a persistent Tasks section in the sidebar with empty states, and the new-session workspace picker gains a "no workspace (task)" option.

Per-execution HTTP/SOCKS5 proxy routing for Agent fetches, LLM providers, and shell commands, with settings-backed hot reload, approval-gated controls, and credential-safe status.

Specialized in Git branch and status handling: a Git status drawer on the right edge of the DSH web UI with a commit DAG lane graph, uncommitted changes and stash rows, inline diffs, right-click branch/tag actions, and one-click fetch from all remotes.

Static HTML auditor for Chinese line-breaking: checks explicit-`<br>` orphan lines, keep-all CSS coverage, CJK line-start/line-end punctuation rules, and protected-phrase splits, then inserts <wbr> at natural breakpoints; exposes a cn_linebreak_audit tool for agents.

Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock after install, local fingerprint peer search over GitHub topic:dsh-plugin, and mechanical detox. Never executes the target plugin.

Stage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.

Code management panel for the DSH web UI that handles everyday Git in five steps: ① env check auto-detects git/gh/ssh and one-click installs missing tools (gh mirror download sources speed up installs, Windows included) with check-update; ② SSH ed25519 key generation / connection tests plus one-click 443 config to bypass blocked port 22, with the Gitee personal token configured here; ③ repo status, side-by-side diffs, stage/commit, branch switching, history with revert/cherry-pick, one-click repo creation and push, auto-ignoring >100MB files; ④ lists all repos of your account for one-click clone; ⑤ five-step npm publish wizard. GitHub / Gitee dual-platform, with the UI switching between 中文 and English live.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Open a page, wait for it the way it actually needs, extract the readable article, and take a screenshot. Playwright is optional: when it is absent the tools fall back to a static fetch and say so in the result, because a page whose JavaScript never ran means something different from one that rendered. Content is chosen by scoring candidate subtrees on prose density rather than on tag names, so a container loses to the article inside it instead of winning by containing more of the document.

Real-time DeepSeek account balance badge in the sidebar footer with odometer roll animation, multi-currency support, balance trend chart, per-key usage statistics with historical backfill, and GitHub version auto-check.

Fold the DSH skill catalog prompt surface: static KV-cache-stable catalog + BM25/bge-m3 hybrid skill_search + autoRoute hints. v0.3.0. npm: dsh-skill-folder

Slash-command console for dsh: /web start|stop|restart|status, /tunnel SSH forward management, one-shot /ask, and a console TUI launcher.

Agent governance suite: policy-based tool gating (allow/deny/ask with wildcards and priorities), a structured JSONL audit trail, and per-agent token quotas against the host token meter, with state under $DSH_HOME/gov.

Turns a stated need into a plugin choice: an agent skill that queries a catalog of the whole `dsh-plugin` topic (2600+ repos, recrawled every 6 hours, Chinese descriptions from Workers AI) through a ranked search API, then hands back the matching `dsh plugin add` command.

DSH↔Godot engine runtime bridge: launch and drive a running Godot 4.x game through its in-game TCP interaction server — 16 tools (runtime control via ~130 game commands, scene/UI inspection, GDScript eval, input simulation, screenshots, headless static ops, project editing, export, script validation, engine-path setup), replaces godot-mcp.

Use local Ollama in DSH with Ollama native API and params support.

Unit conversion toolbox covering 20 categories — length, mass, temperature, area, volume (incl. US cooking units), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration incl. g-force, illumination (lux / foot-candle), pressure, energy, angle, frequency, power incl. three horsepower definitions, force, torque, typography (px/pt/em/rem), and fuel economy (mpg ↔ L/100km). Two tools — convert_unit and list_units — zero runtime dependencies, pure arithmetic; each result includes the formula applied.

Local AI code-review gate: review a workspace/branch/commit diff via the managed ocr.js, returning structured findings with token stats; gate mode fails on findings.

A-share and US stock trading toolkit for DSH agents: realtime quotes, OHLCV klines, ADX three-state regime signals and simple backtest previews via EastMoney. Read-only, never places orders.

AI-driven source-code security scanning workbench: 5 model tools (start/finding/status/report/list) plus a /hawkeye web UI and JSON/Markdown/HTML vulnerability reports; zero-dependency Cordis plugin, installable as agent preset or npm package.

Triggers GitHub Actions workflows and local test pipelines, streams their logs back, and on failure hands the log tail to the agent for diagnosis.

Financial research workflow and portfolio risk tools with source discipline for current market facts.

Local semantic code search for DeepSeek Harness (dsh): fragment-level, symbol-aware indexing, offline lexical embeddings or OpenAI-compatible endpoints, and hybrid vector + BM25 retrieval fused with RRF - three dsh tools (sema_search / sema_reindex / sema_stats) plus a sema CLI.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Role-based plugin recommender for DSH: asks the user's role (developer, designer, writer, researcher, ops, student...), recommends suitable plugins, and audits each with a local static security scan (dangerous code patterns + 0-100 risk score) and a reputation check (npm downloads / GitHub stars).

macOS menu bar app for the DSH web server, plus the host plugin it reads: the plugin writes the running server's port, PID and tokenized URL to ~/.config/dsh-launcher/runtime.json and removes it on shutdown, so start, open, restart and stop work from the status bar even for a server started from a terminal.

dsh-docker — typed, guarded container control for DSH: structured docker/compose tools, project-aware targeting, an approval gate for destructive ops, service-health context, and a replayable status-table renderer

Imports a proxy subscription, supervises a local mihomo core (proxy-provider plus a url-test group), and fetches direct-first with automatic proxy fallback and per-host routing memory; exposes one proxy_router tool (status, start, stop, test, fetch, routes, forget).

Cross-platform Web UI launcher for DeepSeek Harness: webui_start/stop/status/open model tools, a /webui start|stop|status|open slash command, a Settings-page launch card, and an optional desktop shortcut that starts the Web UI hidden and opens the browser once it is fully ready (dsh default icon).

Bayesian stock prediction plugin that fuses MACD, RSI, moving-average, volume and other technical signals into an up-move posterior probability with multi-horizon comparison, trend-state classification and position risk metrics for A-share and US stocks.

Git status badge in the composer tool row: a 14px branch glyph left of the model selector, with branch name, changed-file count and +added/-deleted lines on hover. Counts staged, unstaged and untracked files; nothing renders outside a git work tree.

Codex-backed `web_search`, `image_gen`, and `image_vision` tools for DeepSeek Harness, reusing ChatGPT OAuth login state.

GitHub REST API tools + browser sidebar panel: repos, search, issues, PRs, comments, account binding (credential-store), and one-click clone-as-workspace.

Human-operated Git worktree task board for DeepSeek Harness with validation-bound merge delivery.

Descriptive statistics, percentiles, frequency distributions, and correlation.

Reports bounded, repository-relative Git status as structured data without staging, committing, or changing branches.

Registers a real-browser URL-to-text MCP server in a DSH profile: fetch_url and fetch_urls render JavaScript-heavy and anti-bot Chinese pages (Zhihu, CSDN, Juejin, cnblogs) and return clean article text as JSON with per-tier diagnostics, and crawler_status reports whether the browser is available. Needs a one-time Python dependency setup after install.

MCP Connector for DeepSeek Harness: an MCP manager with one panel to connect servers, configure authorization, search tools across connections, and troubleshoot failures. Browse a continuously updated catalog of over one hundred connectors; filter by connection/server/status, inspect readable parameters and the last successful cache time, and rediscover tools. Supports OAuth 2.0 PKCE, API keys, stdio/HTTP, and mcpServers JSON import. Maintained by Qichacha/QCC.

SVN (Subversion) toolset for DeepSeek Harness: 33 agent tools (status, diff, log, blame, commit, merge, props, lock, changelist...) plus a sidebar panel with side-by-side BASE/working-copy diff, conflict resolution and AI commit logs.

Structured git tools for DeepSeek Harness agents: status, diff, log, branch, commit and stash. Output is pinned with ten `git -c` overrides so a user pager, colour or quotepath setting cannot reshape what the agent reads; every invocation is an argv array, so no shell ever parses an argument; and the mutating actions go through the harness approval service, refusing rather than proceeding when no approval service is mounted.

Usage statistics panel: silent per-model token collection, activity heatmap, trend charts, cost estimation and daily-limit guard.

Capped Git status / diff --stat / log --oneline (no full patches).

Live security beacon for DSH that follows tool activity. Click to view call statistics, risk provenance chains and blocked actions, with read-only task restrictions and tool metadata change detection.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Docker Compose ps/logs with richer status; up/down double-gated.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

Test/extract/safe-replace/statically explain regexes without executing code.

Per-model enable/disable and renaming for every provider in DeepSeek Harness: a panel at the bottom of Settings - Models with a search box, status chips with counts, a provider filter, collapsible provider groups with group-level switches, and batch actions scoped to the current view. Disabled models leave the model picker and custom names replace the built-in ones. Preferences persist in the profile and apply immediately, without reloading the page or restarting DSH.

Code-graph integration for the DSH Web GUI: a "Codegraph" card in Settings → Plugins with index status, symbol search, callers / callees / impact views, and one-click sync / index; hosts the codegraph MCP server and injects a CodeGraph usage guideline into the system prompt. Requires the codegraph CLI.

Visual GitHub login without a terminal: in-window device flow, token synced into the gh CLI, and host status/launch endpoints.