Plugins

Vendor marks in the model picker plus a model list kept in step with the provider: mirrors the public catalog and logos to loopback, and regenerates the pi-ai route's models from that route's own endpoint, showing the drift before anything is written.

Local-only, read-only DSH token dashboard: provider-reported usage across all backends, all-time totals, a 365-day heatmap, input+output and cache read/write details, turn/step counts, average tok/s, and durable history after sessions are archived.

A right-sidebar assistant that knows the main session's finished turns, follows the main agent's running steps and background jobs, and answers in the panel; its model, context budget and answer style are configurable.

A plain-notebook calendar in the DSH sidebar: a 70-day, Monday-first grid whose cells print that day's note; one note per day is stored in a .xlsx you choose, in the DesktopCal two-column layout (Excel date serial plus free text, newest date first). Clicking a day opens the editor for it, and import/export move that same format in and out, with a preview step and a conflict policy (keep, overwrite, concat or skip).

A conversation-style layer that rephrases trade-off warnings: when a shortcut is cheap but has a catch, the reply may say the fast road is the rival shop and the slow one keeps its rules. Ships a rewrite engine that turns any text into a fixed-format dialogue with five independent knobs (act count, catchphrase density, ending turn, seed, preset), a slider for four on/off intensity levels, and a /bushaoxin command that reports a joke "heartburn index" from the session tool-call log. Every rewrite ends with a real technical conclusion that cannot be disabled. Zero dependencies, no build step, engine is pure functions.

Kids' coding classroom: run Python and LOGO-turtle code, explain, practice, review and step through programs.

Runs the local Cursor CLI as a child coding agent from DSH - a `cursor_code` tool plus the native one-shot `cursor_subagent` tool, one mirrored DSH sub-session per run, per-task model choice, resumable conversations, a step timeline with real file diffs, and a usage, model and session panel.

Two-step session deletion: the session menu moves a chat into a recycle bin without deleting anything, the bin panel restores an entry, deletes one for good right away, or empties the whole bin, and the next start wipes its log, projection cache, spill files and workspace membership.

Realtime token counter beside the deep-thinking indicator in chat, with merged or split input/output display, per-step operation counts, and auto-scaling K/M/G/T units.

A composer switch between running always and running only in off-peak hours, set per session: a task is judged by the session that owns it, so changing one session no longer changes the others, and a session without its own choice follows a default. In off-peak mode every task, including one already running, is held at its next agent step or tool dispatch when a Beijing peak window starts (Monday to Friday 09:00-12:00 and 14:00-18:00, statutory holidays excluded), and one timer releases it at the boundary; weekends and holidays are idle all day. The holiday calendar lists every statutory day off in 2025 and 2026 from the State Council notices, and a year with no data is reported as unknown rather than assumed to be a workday.

A prompt optimizer in the composer input tool row: pick a category and a template, then ✨ rewrites the draft in place with one-click undo. Pick from the Basic, Context and Image categories; you can cancel a run, and it shows elapsed time and token usage. Ships 15 templates covering task-instruction rewriting, step planning, safety-research framing, system-prompt role cards, and text-to-image / image-to-image prompts; context templates read the recent turns of the session for coreference resolution. Calls go through the host model service, and a settings section exposes the model and the budgets. Output guards check that user-written constraints survive, warning rather than auto-retrying. Adapted for dsh 0.1.7 and 0.2.

Conversation navigation with full-history turns, collapsible process steps, final-result and structured question-and-answer keys, and pointer-following piano interaction.

Round-table meetings for DeepSeek Harness 0.2.0-rc.2 on Windows desktop, reusing existing Agent sessions with discussion, editable task cards, sequential and parallel steps, shared meeting files, and secretary minutes.

Live usage gauge injected into the system prompt every turn: session tokens and estimated spend, a next-turn estimate, and two predictions the model can act on — which step fills the context window and which step burns the budget. /qm panels, zero-config by default, optional price table, and it publishes a summary.json budget contract sibling plugins read.

Checks each step of a plan before you approve it, using command rules plus Jev or an OpenAI-compatible endpoint with logprobs, and marks steps that can't be undone, affect things outside the workspace, weren't asked for or are too vague on the plan review card.

Page zoom for the DSH Web UI: Ctrl+mouse wheel scales the entire interface in 5% steps (30%-200%), remembers the zoom level locally, and shows a magnifier with the percentage in the bottom-right corner.

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.

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

2D engineering prints (PDF/PNG/JPG) of plate parts to noBS CAD scripts and STEP files: modelling skill, CAD tools over the noBS CAD MCP engine, packed native print probe, and a 2D → 3D panel in the Web UI.

Nearly half the agent cost, with accuracy intact. Just enough tools is a DeepSeek Harness plugin that uses Jev to reveal tools and skills progressively. The main model starts with a clean planning step. Jev then selects which capabilities to add as the task unfolds.

Explain supported DSH plugin failures with composition source paths and manual next steps: duplicate insertions, missing bundle patches and peer mismatches; standalone CLI and report viewer, read-only diagnosis offline by default, with unobserved runtime left unknown.

A GitHub-connected visual git manager for DeepSeek Harness: guided GitHub-Flow steps, commit graph with PR/CI badges, one-click GitHub login, PR and issue management, and structured git tools for the agent. Renamed from gitcompass in 2.0.0.

Injects the rule files under $DSH_HOME/rules and <cwd>/.dsh/rules into the conversation at the first agent pre-step, re-injecting them after compaction.

Video-style turn navigation for the Web UI: full-map progress bar with hover preview cards (tools/files/tokens), drag scrub, ⌘K in-conversation search, ⌘↑/⌘↓ stepping, Esc-return. Event-log powered — works beyond the loaded window. Dual-half plugin on the official composer.dock slot.