Plugins

Reopens the conversation you were last in after restarting DeepSeek Harness, by keeping a pointer file under the DSH home directory instead of patching engine files.

OpenCode Go provider that verifies a model against the gateway rather than treating a recommendation as a measurement: the models.dev protocol suggestion is probed before it is used, reasoning levels follow a measured contract, and requests run through an ordered protocol fallback chain. Context window, max output and image-input numbers are declared by a runtime-refreshed models.dev layer rather than probed, with operator overrides above both. Several OpenCode Go credentials can be stored and switched from the settings page.

Holds DeepSeek model calls for the rest of each peak-hour window you configure instead of sending them, so they are billed at off-peak rates; also pauses active goals while it waits and shows the account balance with an 8-hour spend chart.

Shows the active model's usage and remaining balance in the session header: OpenCode Go plan usage (rolling, weekly, monthly) with the selected model's monthly cap, Command Code 5-hour and weekly window usage with remaining credits, and DeepSeek account balance.

Configures from the settings window's General page whether Enter, Shift+Enter and Ctrl/Cmd+Enter send the message or insert a line break; the engine default is kept until you change it.

Session-local scheduled tasks: inject a prompt into the current session after a delay, at a fixed time, or on a repeating interval, so the model wakes up and runs it on time. Manage them from a panel above the composer, the /schedule command, or seven model-facing tools. Timers freeze while DSH is closed and never auto-resume; pause keeps the remaining time, so resuming continues from where it stopped.

Context compaction that keeps its receipts: a five-section handoff summary, a durable segment index, review tools that read compacted text back, optional working notes, and a read-only extraction exit. Mounts as the compaction-basic row's replacement; cha

Event-driven Hypatia memory for DSH: automatic conversation logging via session events, queued background consolidation (span summaries + work-unit extraction) with a dedicated model route, and recall injection — zero per-call model work in the main sessi

DEPRECATED — dsh does this itself since 0.1.7-alpha.1 (the width handle bridges the wheel), so this plugin is unnecessary there and would scroll twice; frozen, do not install. Small usability fixes for the DeepSeek Harness Web GUI.

--- description: "面向 DeepSeek Harness 的可安装单包 FreeCodeGo 组合：安装渠道、发布打标，以及随包交付的 Agent Teams 组合。" kind: "package-bundle" ---

Motor-design AI assistant plugin: requirement parsing → parameter identification → candidate matrix → Top10 verification. L0 is a millisecond-level broad filter (pure JS, zero solver dependency) that ranks candidates and emits the handoff payload for the L1/L2 precision tools; usable as a local agent preset and Cordis plugin. L1 (RMxprt) and L2 (Motor-CAD) are reserved in this version — the level gate fails fast above l0.

Generic idea manager for the DSH Web GUI: Host-authoritative /api/ideas ledger, capture, 4-column kanban (open / under review / archived / declined), optional TaskBoard mirror; mounted without DSH source changes.

GitHub operations for DeepSeek Harness: releases, tags, a guarded generic API pass-through, workflow runs, secrets and sanitized mirror publication.

把多个 WorkBuddy / Trae 账号汇成账号池接入 DeepSeek Harness：自动切换、限流熔断退避、凭证安全落盘

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

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.

Multi-instance ComfyUI orchestration: probes every configured ComfyUI endpoint for its GPU, free VRAM and queue depth, then dispatches a generation job to the idlest eligible instance. Ships three tools (comfyui_farm_status, comfyui_farm_pick, comfyui_farm_run). An instance is eligible only if it is reachable, has at least the requested free VRAM, and its queue is no deeper than the configured ceiling; eligible instances are ranked by free VRAM minus queue depth times a weight, so an idle shallow queue wins over a busy large one. Zero runtime dependencies. Optional retry on probe failure, because a single timeout across an SSH tunnel is not proof that an instance is down.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Workspace checkpoints per tool call: records every file mutation inside the workspace (excluding .git and node_modules by default), including changes made by shell commands rather than by write/edit, and stores the previous content of each changed path in a content-addressed store kept outside the workspace. Restores have two modes — undo one record, or return to a point in time — with a line-level diff preview, a dry run by default, and a rescue record written before every restore so the restore itself can be undone.

Rapid-refill circuit breaker for DeepSeek Harness automatic compaction. It refuses a compaction that would be futile — the context refilled within fewer than N tool turns M times in a row, which the unbounded step-pressure trigger cannot detect — and instead of burning a summarization call on every step it reports the situation with advice, usually that a single read or tool output was too large. Shows state and re-arms through /compaction-breaker, and injects one prompt section so the model relays it to the user. Covers host-plane sessions through its profile bundle; ordinary sessions need one row replaced inside an agent preset.

Sign in with a ChatGPT account and view Codex subscription usage directly in DSH Web's model settings, with browser or device-code OAuth.

Shows the account balance or coding-plan quota (5h/7d/30d) of the provider behind the current model, on its own line above the composer input; display only, no cost accounting.

Adds a sparkle button left of the model selector in the composer: it rewrites the draft into a clearer, more complete task brief, replaces it in place with one-click undo, offers five rewrite styles, and greys out while the draft carries file/command chips.