部署运维
基础设施
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.
agent-observability
agent-trajectory
ai-agents
deepseek-harness
部署运维
基础设施
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.
agent-observability
ai-coding
deepseek-harness
distributed-tracing
部署运维
基础设施
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。
agent-observability
ai-coding
deepseek-harness
dsh
部署运维
基础设施
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
ai-agent
ai-agents
cordis
deepseek
部署运维
插件
DSH plugin: per-step timestamped DeepSeek API usage timeline + peak/off-peak cost readout. Official bundle; install via: dsh plugin --profile web add github:Dino6021/dsh-usage-cost#main
billing
cost-tracking
deepseek-harness
dsh
部署运维
技能
Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.
agent
agent-monitoring
agent-observability
agent-skills
