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.

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

Branch-based message editing, reroll, retry, and a 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 strategy.

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.

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`).

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.

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.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

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.

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.

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.

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.

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.

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 over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.

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.

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.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

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.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

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.