Plugins

File claim/release protection for parallel DSH sessions on the same workspace (heartbeat stale takeover, pending 3-way merge area).

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

Aggregated web search provider that fans one query out to 11 engines (Exa, Parallel, DuckDuckGo, SearXNG, Brave, Tavily, Serper, Mojeek, DeepSeek, Anthropic, OpenAI) concurrently, URL-dedupes and merges the results. Ships a settings card for toggling backends, storing API keys in the credential store, and tuning concurrency and timeouts.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Cron job board: schedules local scripts or dsh session tasks (fresh or pinned sessions) by cron expression, with centralized environment-variable management, run logs, and concurrency and timeout control.

Run RunningHub cloud ComfyUI workflows from chat — settings card, sha256 media upload cache, concurrency gate, and background task ledger.

Reorder the messages queued while a DSH agent is busy, from inside the official queue dock: a drag handle and per-row ↑ / ↓ buttons on the dock's own rows, applied on the host as one concurrency-checked inbox splice. The dock is decorated rather than replaced, so previews, inline editing, steering, removal and attachments stay as shipped. A move is refused when the queue has changed since the caller last saw it, when the row is not a user prompt (a goal round prompt, for example), or when the queue belongs to a subagent session.

Tiered task queue as the single source of truth for DSH↔Hermes work (reset > approve > review): enqueue tools for all submission paths, lease/claim model with concurrency 1, priority aging against starvation, atomic busy mutex, and a Hermes-side consumer (cron */1 + monitor gating) that drains tasks, writes review-handoff requests with single-slot checks, and invokes the reset agent.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation, bounded-concurrency DOI validation and health self-check.