Plugins

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Agent Sidecar as a native DSH plugin: cross-agent monitoring, injection and bypass analysis / 跨 agent 监控、注入与旁路分析

A tiny behavioral mood ring for AI coding agents — folds session behavior (consecutive failures, repeated calls, activity) into a four-state Mood (GOOD / CONFUSED / FRUSTRATED / OVERWHELMED) shown as a low-friction session-header status light.

Cross-agent monitoring board for local AI agent sessions (cursor-ide, claude, codex, copilot, kimi and dsh itself) with session timelines, and message injection behind a default-off two-phase confirmation gate.

DeepSeek-Harness (dsh) plugin that streams sessions, turns, and tool activity to a JARVIS Mission Control board

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Capture every upstream model API payload to JSON (debug & observability).

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

Local-first failure evidence capsules for DeepSeek Harness sessions

Telemetry backend exporting turns, model steps, and tool calls to yiTrace.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Live btop-style CPU/memory/temperature/GPU monitor tab for the DeepSeek Harness web GUI.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Per-turn token usage, request composition and cost breakdown panel for the DeepSeek Harness Web GUI.

Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.

Runtime observability and plugin operations panel for DeepSeek Harness: shows the profile plugin tree, real Loader fiber state, capabilities/dependencies/compatibility, current-session plugin activity and upstream source/version checks, with one-click enable/disable/update/uninstall plus a standalone startup-failure diagnostics page that works while DSH is not running.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Sleev routing observability for DeepSeek Harness

Lifecycle management UI for the llm-pi-ai model provider: create, edit, delete, enable and disable providers with custom headers and AES-GCM-encrypted API keys; uninstall-safe restore of parked providers, remote model discovery with batch write, smart routing with five strategies, union/intersection composites, per-model connectivity tests, and request observability.