observability

MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.

What a DeepSeek Harness run costs in tokens, money, and time. OpenTelemetry traces, metrics, and logs in GreptimeDB, with seven Grafana dashboards.

OpenTelemetry tracing for DeepSeek Harness (dsh): turns each agent turn into a GenAI span tree — steps, LLM calls with TTFT, tool executions, token usage — exported over standard OTLP to Jaeger, Grafana Tempo, SigNoz, Langfuse, or any compatible backend.

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, sanitized prompt/completion capture, async batching, bounded offline buffering, retry with backoff

Local-first failure evidence capsules for DeepSeek Harness sessions

tencentcloud-agentobs-sdk-dsh 是一个 DeepSeek Harness (DSH) 可观测插件，直接将 GenAI trace 数据上报到腾讯云日志服务 (CLS)。 它观察 DSH 原生的 session、agent loop、LLM stream 和 tool 生命周期，将其转换为 腾讯云AI Agent可观测规范的 5 层 span 层级模型（entry → agent → step → chat → tool），并通过 tencentcloud-cls-sdk-js 直接上报到 CLS，无需额外部署 OTLP 收集器或 sidecar。

🐳 鲸鱼电表：你在 DeepSeek Harness 上烧了多少 token？消耗量段位、可晒的战绩卡、6 家厂商 46 个模型精准计价（含国内分档）、8·17 调价前后对比。零配置，数据全在本机 | Token usage tiers & cost dashboard for DSH

Observe-only provenance ledger over public DeepSeek Harness runtime evidence

DSH Web UI 文件追踪插件：记录并查看模型读取/写入/编辑的文件，带行号内容与终端风逐行 diff(红删绿增蓝改)、hunk 上下文折叠、可拖拽高度。适配 DSH dsh-v0.1.2-alpha.1，纯客户端零核心改动。

洞察 — read-only insight panel for a DeepSeek Harness profile: where every plugin, service, tool and model came from, which config layer inserted or disabled it, and what is running right now.

Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.

DSH Web UI 文件追踪插件：记录并查看模型读取/写入/编辑的文件，带行号内容与终端风逐行 diff(红删绿增蓝改)、hunk 上下文折叠、可拖拽高度。适配 DSH dsh-v0.1.2-alpha.1，纯客户端零核心改动。

Unified plugin-dimension observability (trace/log/metric) for deepseek-harness: registers global OTel providers + OTLP export, bridges dsh session telemetry, GenAI semconv ready

A local-first CLI for observing AI-agent sessions

Zero-touch runtime telemetry for DeepSeek Harness: every session writes its own report card (task/model/tools/failures/duration) into a human-readable journal. 纯观察者运行事实遥测。

Observability / debug tooling for DeepSeek Harness: trace, cost, and health capture + client dashboard.

External plugins for DeepSeek Harness (dsh): Scheduled Tasks (run agent instructions on a schedule) and Token Tracing (per-turn token attribution with a waterfall and a cross-session dashboard).

Processes tab for DeepSeek Harness: every agent and subagent of a conversation as a live console with paired tool requests and responses, installed as one profile bundle.

Per-model capability profiling for DSH: turns local session history into tool-usage and error-rate dashboards with time-range filters

Observability for DeepSeek Harness (dsh), use the OpenTelemetry Protocol

Token usage dashboard, provider balances, and subscription quotas for the DeepSeek Harness (DSH) web GUI

DeepSeek Harness 会话回放与脱敏分享插件：将真实 Agent 轨迹导出为独立交互 HTML，用于文档、演示和问题反馈。

Evidence-first Kubernetes runtime diagnosis with case memory — a DSH skill (+ aiops CLI twin).

该仓库暂未提供项目说明。

DSH web plugin: see every session's conversation progress and token usage at a glance — all-windows overview, session analysis, cost estimation, and a token heatmap. 窗口统计插件：一屏看全所有会话的对话进度与 Token 消耗——全窗口总览、会话分析、成本估算、Token 热力图。

Privacy-conscious Prometheus metrics and Grafana dashboards for DeepSeek Harness

🌊 深海事务所 · Abyss — 把 DeepSeek Harness 的多 agent 运行画成一间看得见的事务所：委派谱系、每个 agent 的成本与失败归因、上下文水位、考勤时间线，历史案子可回放并一键导出 Markdown 复盘。A DeepSeek Harness plugin that turns an agent fleet into an office you can watch.

Turn a DeepSeek Harness run into a readable story — chapter stream, causal nesting, every claim backed by evidence.

DSH plugin spec: observing soft-signal drift

DSH-Plugin: structural observability layer - real tool/skill usage recording (tools/result), skill-catalog audit, watchdog. No model self-reporting.

Agent Trace — visualize an agent's reasoning, parallel tool calls, and results as an interactive DAG inside DeepSeek Harness.

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

OpenTelemetry plugin for DeepSeek Harness (dsh) — traces and metrics for agent runs, tools, and model calls

A tiny behavioral mood ring for your AI coding agent: a four-state session-header status light (GOOD/CONFUSED/FRUSTRATED/OVERWHELMED) for DeepSeek Harness

Runtime data-flow audit log for DeepSeek Harness: who mutated what, in what order - per-plugin, per-fiber attribution.

DeepSeek Harness 本地费用估算器：macOS 菜单栏按小时、项目和任务查看用量｜Local cost and usage tracker

Prometheus and Alertmanager tool plugin for DeepSeek Harness

A DeepSeek Harness Web plugin for inspecting redacted LLM HTTP request and response traces.

Privacy-safe request flight recorder for DeepSeek Harness

Runtime nutrition labels for DeepSeek Harness plugins and tools, with bounded evidence for tool, filesystem, network, and side-effect activity.

Privacy-safe flight recorder and incident reports for DeepSeek Harness.

Self-diagnosing plugin family for DeepSeek Harness (dsh): deterministic detour detection over the SessionEvent log, replay-verified optimization suggestions, and accepted-fix sediment.

Observability for DeepSeek Harness code-mode sub-dispatches: the tool calls a run_code program makes that the model never sees.

DeepSeek Harness dsh-plugin for bounded, cursor-aware log inspection

Execution trajectories for work that isn't code — a DeepSeek Harness plugin, starting with content production.