Plugins

Chat recovery for DSH: edit the last finished user message and explicitly retry failed turns, both via session-fork branches that leave the original conversation untouched.

Keeps long DSH sessions alive when a model channel starts failing: daruma takes over after the in-box retry gives up, trips a self-healing circuit breaker on repeated 429/5xx or a terminal error, and moves the next request to another channel in your chain. Works on DSH 0.1.x and 0.2.x hosts, including 0.2.1-rc.2 with verified failover and backup-management RPC. The backup can be picked in Settings or from a panel beside the composer — both stay in sync — with a durable JSONL audit log for every switch. Channel switches are recorded in that audit log instead of as in-conversation notice rows, because a plugin session event of a type the host does not know makes it refuse to load the whole session.

Multi-source web search and fetch failover for DeepSeek Harness sessions: takes over the session searchProvider and fetchProvider seams and tries configured sources in a chosen order — TinyFish, Tavily and the official search as a fallback that always participates and can be repositioned but not removed. Multiple API keys per platform are spread round-robin, usage snapshots drive pre-flight exclusion of exhausted accounts, and per-request timeouts plus same-platform retry control failover granularity. Web fetching runs local HTTP first, then falls back to TinyFish Fetch server-side rendering and Tavily Extract, so pages still load when local egress is blocked by proxy or DNS policies. A per-platform panel shows key usage and plan limits. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-failover-search`.

Branch-based message editing, reroll, retry, and a version timeline.

Branch-based message editing / reroll / retry / version timeline.

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.

Role-based LLM retry & fallback strategies.

Role-based LLM retry & fallback strategies.

Role-based LLM retry/fallback strategy.

Task reliability: auto-retry on model timeouts/failures, auto-continue unfinished tasks, completion verification, thinking-repeat interruption, resume after sleep or restart, autopilot mode and a remote trigger endpoint (npm: `dsh-task-reliability`).

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Adds supplemental request retries, turn auto-continue and a no-response watchdog on top of built-in dsh retries, with a live countdown banner, toast notifications and a usage dashboard.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

Tool-call discipline for DeepSeek Harness with behavior prompts, failure-driven concurrency reduction and retry guidance, post-write checks with backup rollback, high-risk command gates, change summaries and verification reminders, advisory project-memory checks, configurable project-discipline reminders after compaction or at intervals, and compliance statistics.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Runs the WorkBuddy (CN) daily check-in on DSH startup — discovers every account logged in on this machine, claims the daily credits, and shows a status entry on the session title line with a details panel and failed-account retry.

Per-model proxy routing for LLM requests: selected models go through a proxy (Clash etc.) while the rest stay direct, with automatic retry on transport errors, 429 and 5xx, configured live from the settings page.

Let text-only models see images: when a picture arrives with a placeholder like \[image omitted because this model accepts text only], the model calls the vision_describe tool and the plugin forwards the image reference plus the question to a multimodal model, retrying with a fallback model on failure. Configured in the settings page and persisted via the official settings API.

Multi-threaded downloader plugin for DeepSeek Harness with bundled aria2: probes the target for Range support, then picks aria2 (4 or 8 connections by file size) or falls back to curl.

Prompt enhancer for the DSH web UI with basic/standard/expert modes: standard/expert modes rewrite drafts with project context and recent session history, retry gracefully when gateways reject reasoning-effort settings, and show a before/after review with undo.

Peak-hour auto session gate: weekend mode + global peak auto-pause + session-level freeze/resume + backend auto-retry, auto-resume on off-peak.