Plugins

Service farm for DSH: register, start, stop and restart long-running project services, with agent tools (farm_status/start/stop/restart/logs/register), farm.yaml declarations and an overview drawer UI with live log follow, search and export.

Web search provider powered by ZAI GLM MCP: search and fetch via Open BigModel API with credentials auto-injection from ~/.dsh/.credentials.yaml or environment variables — no API key in config files.

Model Health panel in Settings: lists every model configured in settings.yaml and batch-tests availability and latency for each.

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.

Formats and validates JSON/YAML/TOML/SQL, with line-and-column error locations.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

Workflow tools for the local aflare binary: generate, validate and run local-first deterministic YAML workflow DAGs (WAL crash recovery, Saga compensation) through the local aflare binary, with 300+ templates built in.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Plataforma de avaliação de agentes: benchmarks em YAML, orquestração de execuções headless, métricas baseadas em traces e relatórios de execução