Plugins

Model visibility manager for DeepSeek Harness: hide or show any model in the conversation model selector from a dedicated settings page. Per-model switches, search, provider-level batch actions, reset-all. Zero intrusion - writes only its own hidden list, never the provider config; hiding a model in use never interrupts a running session.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Daoist Canon (DaoZang) retrieval skill: keyword or semantic search over 285,117 scripture chunks with exact original-text extraction (line numbers, hit markers), and one-command workspace setup from the Godners/DaoZang dataset.

DeepSeek API balance + per-call cost tracker: durable per-call cost ledger from real usage chunks with official Beijing peak/off-peak (x2) pricing, 60 s balance polling, and a sidebar footer action showing balance and today's spend.

Triggers GitHub Actions workflows and local test pipelines, streams their logs back, and on failure hands the log tail to the agent for diagnosis.

Structured machine-readable CI output for DeepSeek Harness: JSON/NDJSON session reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction - a dsh profile bundle plus a standalone CLI.

Compaction quality / hallucination detector: when a conversation span is compacted, check on two axes that key information survived 鈥?FIDELITY (assertions in the summary must be found verbatim in the original leaf events, else flagged as fabricated) and C

Step-0 observation probe for dsh-compaction-audit: logs every compaction/* session event and probes whether shadowedSeqs still resolve to readable events in session.events. Observe-only; never injects, never blocks.

DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models

Local, auditable personal memory for DeepSeek Harness: preferences, project conventions, workflows and error lessons persisted as a changelogged JSON file in the workspace, with onboarding, auto project-convention extraction and evidence-backed lessons.

DSH sidebar footer ordering: forces the sidebar.footer.action slot into a vertical stack and lets users configure the top-to-bottom order of its entries.

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Bridges the LiuHe MCP code toolkit (44 tools) into dsh web: repo_map, symbol search, edit_batch with tolerant matching, transactional edits with undo journal, and deterministic quality gates — backed by a crash-isolated Rust tree-sitter parse daemon and SQLite index.

DeepSeek Harness memory and knowledge hub that routes update, retrieve, and subscribe calls across compatible plugins, with an optional transactional Rust backend.

Transactional data-only configuration pack manager with integrity, ownership, preview, diff, and rollback safeguards.

macOS Liquid Glass theme for DeepSeek Harness Web UI: floating frost, rounded refraction, mouse rim, custom wallpaper

pi-web-access for the DeepSeek Harness: multi-provider web search with automatic fallback (SearXNG → Tavily → Brave → keyless DuckDuckGo) plus URL content extraction, wired into the web seam so the built-in web_search tool is powered by piwa. Search engin

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Provider-neutral CI/CD capability for DeepSeek Harness with GitHub Actions support, bounded failure evidence, source-aware diagnostics, and approval-gated rerun/cancel controls.

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.