Plugins

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Native desktop and webhook notifications for turn completions, failures, and approval requests, with outcome filters, content rules, privacy controls, and retrying delivery.

Play different configurable sounds for five conversation events in the DeepSeek Harness web GUI: normal completion, interrupt, error, approval wait, and auto-retry success; each event has its own audio setting and bundled default, with auto-retry after errors using a configurable wait (10-300s), plus a community sound library. Compatible with DSH 0.1.5-rc.2.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Adds six AI coding platforms to DSH — OpenCode, Qoder, Qoder CN, TRAE, WorkBuddy and WorkBuddy International — each as its own group in the native model picker, and manages their accounts from one settings page, with daily check-in where the platform has one, credit balance lookups, and retry on another account of the same platform when one is rate-limited. Models carry their credit multiplier where the platform declares one. OpenCode's anonymous free tier works with no credential, and TRAE stays hidden by default until it is enabled in the settings.

Brings SenseNova (日日新) models into dsh with a per-key rotation pool: paste any number of API keys and requests rotate across them, a 429 rate-limit immediately retries on the next key with per-key exponential-backoff cooldown, local RPM pre-throttling avoids the limit instead of reacting to it, and an exhausted pool answers 503 with Retry-After so a 429 never reaches the caller. Ships a built-in model catalogue that works offline and refreshes from /v1/models, plus a settings card with masked keys, per-key probing and removal.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Enhanced vision toolbox: 14 pixel-level vision tools (describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) driven by one OpenAI-compatible endpoint, with clean \[图片: path] bridge markers, content-safety classification and rate-limit auto-retry.

Auto-resumes interrupted DSH turns: sends a queued 「继续」 after turn/end with error, interrupted or max-tokens reasons, with a grace period, cooldown, exponential backoff, a consecutive-attempts cap, boot-time scanning, a settings card and a per-session stop/restore button in the composer toolbar; it never switches models or providers.

Retries a model request that no other recovery layer claimed, unbounded by default with an exponential backoff ceiling, never retrying a cancellation; the policy is editable from a Settings panel.

Permanently deletes one session from the sidebar session menu, or several at once from the "..." menu beside the sidebar section title: tick sessions in the list (running ones are refused), then confirm in a dialog — log directory, workspace membership, live Host instances and the client list row are all cleaned. The same "..." menu also collects the session search and view options. It also sweeps rows whose log is already gone, and retries a user message or an assistant reply from the button right of Copy.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

After official llm-retry (n/5) gives up, keep retrying transient API failures (timeout, transport, rate-limit, 5xx, dropped SSE) on the same open step until success, cancel, or pause; AUTH, QUOTA, and user Stop are never retried.

LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issues the request automatically, so subscription quota and rate-limit errors (429 / insufficient_quota) do not interrupt a run.

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, one-click interrupt and breakpoint fork via official APIs, independent GUI tab.

Strips DSML markers that leak into the assistant text stream and resumes a turn only when it genuinely produced nothing — an invoke-block leak with no tool call emitted, or a closing-tag leak whose prose is near-empty; upstream jitter codes retry, while quota, rate-limit, auth and context-window errors never do. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0, and Node 20 or newer.

Automatically retries model failures (drops, timeouts, rate limits, 5xx) in-turn. Retry count, delays, backoff, fallback and more are configurable. Rate-limit backoff is capped and jittered, server retry hints are honored, and optional retry-until-success keeps going within a time ceiling. Every option is editable from the plugin config or the sidebar panel: retry count, initial and max delay, backoff factor and jitter, rate-limit delay window, retry-until-success ceiling, fallback trigger and switch cap, dead-route blacklist TTL, log file. When a route keeps failing it can switch to a pinned, allowlist-filtered, or catalog-picked alternate model route, with a 30-minute dead-route blacklist (auth failure, subscription expired, billing) and a stale-assembly guard that keeps retried requests on the switched route. Ships a right-sidebar panel with live retry state, route labels and incident counters, Chinese and English locale, and memory-only logging by default.

Reuses stored Responses IDs for continuation, with retry and branch isolation and verified history replay.

Prepares a repository README before pushing: scans repo facts, renders banner and process-diagram images (needs Pillow and the Microsoft YaHei font), lints layout and section numbering, then commits and pushes with retry.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.2 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Preview 0.6.0-community.5 with optional Retry is available separately in GitHub Releases. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox. Derived from kyle123740/dsh-zcode-cli-proxy (AGPL-3.0); it registers the same `zcode-cli` provider id, so it cannot be installed alongside the original.

One-click prompt refinement for the DSH composer: the ✦ button next to Send rewrites the draft into an agent-ready prompt in Standard or Light mode, with Revert and Retry; asks follow-up questions through the question card when the draft is missing information; checks that paths, identifiers, numbers, URLs, inline code and @mentions survive the rewrite and adds back any that were dropped; runs on the conversation model or a dedicated model chosen on the Plugins page.

Manage skills and MCP servers from one DSH settings panel. Skills are read from disk: browse, search, preview the body, create, rename and delete, with a backup written before every removal. Global MCP servers are the real cordis.patch.yml loader rows; per-project entries mount only for sessions in that project. Each expanded card lists the tools that server actually registered, and a per-server allow/deny rule keeps only the ones you need — a blocked tool never enters the tool registry, so it costs no context on every turn. Every MCP card carries a connection status tag (connected with a tool count, retrying, gave up, activation failed) plus a one-click reconnect, so a server that fails at startup is visible instead of silently missing its tools. Imports existing configs from 26 other MCP clients.