Plugins

Folder time machine for DeepSeek Harness: snapshot any folder, browse its timeline, roll back with one click — Git-like history without needing Git, for folders that never had a repo (game saves, app config dirs, loose documents). Snapshots are content-addressed and deduplicated, and unchanged files are not re-hashed. Automatic snapshots come in two modes: realtime (fs.watch — one version ~8s after the last change, so a save-all or a build counts once) and timed (checks every N minutes, stores only when something actually changed; identical content never adds an empty version). Empty folders are recorded and recreated on restore. Every restore takes a safety snapshot first, so a rollback is itself undoable, and exact-mode cleanup only removes files and empty folders — a non-empty folder is never deleted. Ships a folder_timemachine model tool (status/history/diff need no approval; writes ask first) plus a floating panel with the timeline, one-click restore and mode switching. Pure JS, zero runtime dependencies, 110 tests included.

Use the free AtomGit quota already signed in on this machine to have AtomCode run an independent code review: the model calls the atomcode_ask tool on its own, and you can also use the /atomcode-review command to review uncommitted changes, a branch or a PR in one click. The plugin reads no API key; a usage pill below the input box shows the CodingPlan quota.

Literature search tools for DeepSeek Harness: four model-facing tools — paper_search, paper_get, paper_citations and book_search — over OpenAlex, arXiv, Crossref, Semantic Scholar and PubMed, with open-access PDF resolution through Unpaywall.

Normalizes every tool schema before it reaches the model, rewriting it into the strict OpenAPI 3.0 subset that Gemini function declarations accept — a type on every node, items on every array, no empty enum entry, $ref inlined — so a single offending MCP or built-in tool no longer fails the whole request with HTTP 400.

Session map: a fork-tree canvas over DSH sessions, and a Settings page that clones a Git repository into a new workspace. The canvas is reachable from a session-header toggle and two right-side tabs, and from a conversation tab that is off by default; it starts on the current session's own tree, growing downward, with wheel pan, Ctrl/⌘-wheel zoom, a subagent-session filter and a per-session overview of turns, steps, model time, tool time, output tokens and running state. The clone page takes a repository address and a remembered parent directory with a native folder picker, offers a per-clone shallow switch (off by default), runs git clone on the host, and registers the cloned directory as a workspace.

Resume a conversation whose turn stopped early: /continue and an action-row button carry the interrupted reply on, covering manual stops, failed model requests, output-token cutoffs and crash recovery, and the continuation prompt is retired from the transcript once it has been answered.

Configure DMXAPI Chat Completions, Responses, Anthropic Messages, and custom providers; edit models on existing preset routes.

Adds an independent OpenCode Go connection with credential settings, manual model discovery, and per-conversation session headers.

Registers OpenCode Zen free models as a native provider: the catalog is discovered live from opencode.ai intersected with models.dev pricing, and a detail page can re-fetch it or test which models answer. Declares no dependencies, so the host's pi-ai stays the only one.

Recognizes a model ID in the DeepSeek Harness model catalog and fills that row's context window, input modalities and reasoning levels as editable suggestions, from a bundled offline rule table covering 33 vendors.

Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back declared to models.dev to a 7-tier default, and replaces the composer model chip with a Codex-style vertical picker.

Configure thinking toggles and reasoning efforts per model for llm-pi-ai and official DeepSeek, and specify input modalities (input or inputModalities) in the DSH settings panel.

Shows a Spark Scope card at the bottom of the dsh sidebar: model server decode and prefill rates with sparklines, running and queued requests, KV cache, TTFT and TPOT p95, and GPU temperature, power, load and memory for each DGX Spark node. Read-only; needs a running Spark Scope server. Works in dsh web and the desktop app.

Runs MoE4All models locally in DSH with automatic engine installation, model discovery and downloads, inference settings, and live speed monitoring, or connects to an existing service.

OpenAI provider for language models, embeddings, text-to-speech, speech-to-text, and image generation in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Adds Kimi models to native DSH sessions with per-model selection of the embedded Kimi core or DSH native execution.

ChatGPT-like conversation layout for the DeepSeek Harness Web client: a 768px centered column, right-aligned neutral bubbles for user turns, full-width assistant text at 16/28, and rounded code blocks with their own copy banner. Adds semantic inline markup (`==confirmed==`, `!!risk!!`, `++key word++`, with bare 4xx/5xx codes highlighted automatically) and line-start check/warn/tip callouts; a fast/thinking chip in the composer that switches the model reasoning effort through ctx.modelDirectories; and sidebar contrast, where the selected session gets a tinted row with an accent bar and workspace folder icons are colored.

Cross-session usage rollup that resolves opaque route keys to real model names, with a per-request log, an editable four-bucket price table that leaves unknown models unpriced instead of guessing, and a calendar-day-filled bar trend whose values appear only on hover or keyboard focus.

Token statistics for every stored DSH session: a Host service folds the durable session logs into a persisted checkpoint and serves them over one read-only HTTP route, and the Usage settings page paints the saved aggregate immediately, then updates it in the background. Days are bucketed by hour behind a date picker, next to a trailing window with per-model breakdowns, request and web-search counts; no cost or pricing model.

Queries the balance and token prices of the model providers configured in DSH, whichever endpoint or relay they use, accepts cc-switch usage scripts, and shows the selected provider's balance under the composer.

Shows GLM Coding Plan quota windows (5-hour, weekly, monthly tools) as an always-visible pill in the composer stats row with a 5h reset countdown, opening a card-grid detail panel with limits, reset times, 24h per-model token usage and one-click plugin self-update.

Token usage meter in the DSH sidebar footer that runs both data sources at once rather than picking one: the DeepSeek platform account's usage and cost endpoints, which cover every device on the account but only the official channel, and local session logs, which cover this machine in real time across every provider but carry no cost. The two are merged per day — the official channel takes the larger figure, since one call is recorded by both, and providers the platform cannot see are added on top. History is backfilled month by month from the platform, providers are classified by channel rather than model name, days follow the platform's UTC boundary, and no token has to be pasted because the platform figures reuse the DSH account you are already signed in to. Totals appear as all-time, current-project, today, week, month, last-7 and last-30 in a compact bar, an expand panel and a detail modal with calendar, chart, model, provider, year, month and day tabs.

Visualizes prompt-cache hit rates and model request activity in DSH Web, with request details, comparison, and conversation navigation.

Adds a four-pointed-star button left of the composer's model selector that rewrites the unsent draft in place — grammar, wording, punctuation and execution order — preserving code, commands, paths, identifiers, numbers and URLs byte-for-byte, answering nothing and never overwriting text typed while it runs. A pencil under every user message reopens that message for editing without touching the draft; because the Harness session log is append-only, an edit forks the conversation before that message rather than rewriting it. A circular restart icon under every reply asks that one question again in a fresh conversation that carries none of the earlier turns. Both are refused while a turn is still answering, and disabled when the reply used a tool that can leave a trace or when the files the message named have since changed. A right-sidebar memory tree draws the conversation as turns, showing what was actually asked and answered, every answer to one question on its own line labelled original, edited or memory-free, newest first, with arrows that re-read an answer in place; right-clicking jumps to a branch or removes it from the plugin's own history.