Plugins

Retry failed model requests automatically: intercepts every request error and replays the same step after a 2s / 5s / 10s / 20s backoff ladder, so gateway blips and rate limits no longer end the turn.

Deepseek harness plugin for control rate limits

Limits the images sent to chosen providers or models in DeepSeek Harness: cap the longest side and the number of images per request, with its own plugin page

Checks installed DSH plugins and previews upgrade risks, with source locations, dependency views, review records and evidence limits. Includes a panel and agent tool.

Composer status bar for GLM Coding Plan quota: 5-hour and weekly limits with reset times, MCP tool usage, and today's model usage, plus a glm_balance query tool.

DSH /btw side questions: streaming selectable panel, debounced persistence, schemastery Config for route and limits.

Port of the V2 memory pipeline from OpenAI Codex to DeepSeek Harness: a background agent extracts each idle session, consolidation folds the extractions into one memory_summary.md behind a git baseline diff, new sessions get that summary injected, and cited memory flows back as usage counts. A Settings page chooses the model, each stage's reasoning effort, and the idle, age, concurrency and timeout limits.

模型故障转移队列：P1 限额/限流/不可用时自动切到队列下一个模型继续，全部图形界面配置 | Model fallback queue for DeepSeek Harness: auto-switch to the next model when the current one hits quota or rate limits

Checks installed DSH plugins for version-declaration and API risks against the current host, with source locations when available, certainty, impact basis and coverage limits. Adds a compatibility settings panel, plugin-detail findings/badges, a compat_check agent tool and a skill provider.

Lightweight crash-recovery for dsh: after a restart, it detects sessions whose last turn was killed mid-flight and re-injects a continuation prompt that first demands the agent verify real-world state before acting, so side-effecting operations are not blindly repeated. It only reacts to the genuine crash marker (turn/end reason 'interrupted', synthesized on cold read by session repair), so it never misfires on user cancels, rate limits or model errors - which is why it needs no error classification, backoff or configuration UI. Unlike general-purpose auto-continue plugins, it also covers the case where a subagent was interrupted mid-run: the parent turn has already ended normally while it waits, so a naive check sees nothing to resume and the whole subagent tree dies silently; this plugin detects the interrupted child and wakes the parent instead. Single host file, zero external dependencies, seven config constants.

Interactive cards in replies, built from a fixed catalog of 31 components (sliders, inputs, sortable tables, charts, function plots, typeset formulas, tabs, checklists, flowcharts, quiz buttons, an animation player): controls recompute in the browser without another model call, and the model never writes HTML or JavaScript. Includes a calculus engine (integrals, derivatives, limits, sums, roots, Taylor polynomials) and a bundled skill that teaches the model when to use a card.

Host-side long-task detection for small-context local models: long outputs are scaffolded into a parts skeleton (one part per reply, then assemble), and multi-step work into a PLAN.md ledger with notes/ (plan first, one step per reply). Detection is heuristic and host-side, so it does not depend on the model judging its own limits.

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.

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

DeepSeek Harness plugin: a model-facing `chrome` tool that drives the installed Google Chrome over CDP — screenshots returned as images, DOM/text/eval, console & network diagnostics, real input events. Runs in the Host, so no per-call approval and no bash sandbox limits.

Expose every model already configured in your local DeepSeek Harness to the LAN over OpenAI- and Anthropic-compatible endpoints, with API keys, per-key rate limits, a circuit breaker, model filters and usage reports.

Controlled browser automation for DeepSeek Harness: the agent_browser tool and BrowserAutomationService drive a real Chromium or Chrome page (or an explicit CDP endpoint) through the agent-browser CLI, with allowedDomains containment and per-call output limits.

Session instruction anchor for DeepSeek Harness: the first step of a new session injects a freely composed instruction block as a plugin-sourced message, and it is re-anchored after a summarizing compaction, every N turns, or when metered context pressure crosses a threshold. An /anchor command re-anchors on demand without a model call; a settings page manages the paged preset library, injection order, re-anchor source and character limits.

DeepSeek Harness plugin bundle: grill_tree, a fixed-policy design-space search tool. Expands one decision per node, fans out independent proposers, has a separate judge prune the branches, beam-limits each depth, and ends with complete designs or an infea

Toolbar picture button in the DSH Web composer: click to pick multiple images through the native file dialog — they join the same draft-image rail as drag-and-drop and paste, with the host image-format, per-message-count and per-image-size limits enforced inline.

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.