agent-host-logs

Analisar exportações de logs de depuração do Agent Host. Use quando receber um zip/pasta ah-logs ou ahp-logs, um pacote Export Agent Host Debug Logs, events.jsonl, AHP JSONL…

npx skills add https://github.com/microsoft/vscode --skill agent-host-logs

Agent Host Debug Logs

Use this skill to orient to bundles produced by Developer: Export Agent Host Debug Logs.... These are different from the normal timestamped Code OSS log directory.

Treat the bundle as sensitive: it can contain tokens, prompts, file contents, terminal output, paths, and settings. Keep analysis local and avoid quoting secrets or unrelated user content. Timestamps, event names, IDs, status values, and general property values are fine.

Open the Bundle

The export name usually starts with ah-logs and may be a zip or an already-unpacked folder. For a zip, use the bundled extractor:

python3 .github/skills/agent-host-logs/scripts/extract.py "<archive>.zip"

The final line gives the temporary extraction path. Work from that folder and delete only that exact folder when finished.

Files are collected best-effort, so a valid bundle may contain only some of these:

events.jsonl
usage.jsonl
customizations.json
agenthost.log
agenthost.1.log
agenthost-server.log
vscode-logs/Window/renderer.log
vscode-logs/Window/renderer.1.log
vscode-logs/Shared/sharedprocess.log
ahp/*.jsonl
copilot-logs/*.log
remote-agenthost.log

What the Files Mean

The basic flow is:

Window/client <-> AHP <-> Agent Host process <-> Copilot SDK
PathWhat it shows
events.jsonlPersisted Copilot SDK events for the selected session: turns, messages, tools, permissions, hooks, skills, and subagents. It can cover a much longer period than the other logs.
usage.jsonlClient-captured token/credit usage, one record per model call (turnId, model, input/output/cache tokens, cumulative totalNanoAiu). The SDK's assistant.usage event is ephemeral and never reaches events.jsonl, so this is the only per-call usage record. Present only when agent-host debug logging was on.
customizations.jsonSnapshot of the skills/hooks/agents/MCP servers loaded for the session. The SDK's session.*_loaded events are ephemeral, so this is the only record of what was actually active. Present only when agent-host debug logging was on.
ahp/*.jsonlAHP traffic for a client connection. _ahpLog.dir is c2s or s2c; _ahpLog.ts is the wire timestamp. Use this to see requests, responses, subscriptions, actions, notifications, and client-visible ordering.
agenthost*.logLocal or server Agent Host process behavior: startup, auth, sessions, provider events, tools, Git/worktrees, and host-side errors. Numbered files are older rotated segments.
copilot-logs/*.logCopilot SDK process logs that mention the selected session ID. A process log may contain other sessions too.
vscode-logs/Window/*Current and rotated files from the Window log group, including renderer/client behavior, network activity, views, and other window-owned logs.
vscode-logs/Shared/*Current and rotated files from the Shared log group. Usually secondary evidence and often noisy.
Agent Host (<name>).logForwarded logs from a named remote Agent Host.
remote-agenthost.logA directly downloaded remote agenthost.log, when available.

How to Start

  1. List the files and note their sizes.
  2. Identify the reported symptom, approximate time, local or remote host, and any known session, chat, turn, request, or tool ID.
  3. Start with the file closest to the symptom:
    • Turn or provider behavior: events.jsonl
    • Token/credit usage or cost questions: usage.jsonl
    • Client/server state or ordering: ahp/*.jsonl
    • Host implementation failure: agenthost*.log
    • SDK behavior: copilot-logs/*.log
    • UI behavior: vscode-logs/Window/renderer.log and its rotated segments
  4. Search by the known time or ID, then follow the same operation into the adjacent layer.

Useful correlation fields include the raw session ID, session/chat URI, turnId, interactionId, tool/request IDs, JSON-RPC request id, AHP serverSeq, and event id/parentId.

Copilot Session Refresh Failures

At the default Info log level, agenthost*.log records the refresh operation, configuration and SDK session IDs, chat, turn, and first matching reason. Only the first matching trigger is reported, preserving the restart checks' short-circuit order. Structural reasons distinguish client tools, client plugins, and root MCP configuration without logging their contents.

Follow Preparing SDK session and the paired SDK resumeSession started / settled records by attemptId. Follow each attached SDK session's shutdown and disconnect records by instanceId, which distinguishes successive wrappers of the same SDK session. A disconnect wait completed record with disconnectRpc=pending and shutdownReceived=true means the shutdown notification unblocked the caller before the disconnect RPC settled. A later RPC completion or failure, including after disposed=true, is logged separately. Neither the notification nor the host-side wait alone proves that native cleanup finished; correlate these with the SDK process log before concluding there was a teardown/resume race.

Important Tips

  • events.jsonl, Copilot SDK logs, and AHP timestamps are normally UTC. The plain .log files may use local machine time; remote logs may use another timezone.
  • An AHP log is connection-scoped and can contain multiple sessions. A Copilot SDK process log can also contain multiple sessions.
  • AHP files rotate as .jsonl, .1.jsonl, .2.jsonl, and so on. Use _ahpLog.ts to reconstruct order.
  • A subscribe result can contain a full snapshot; its contents did not necessarily change at subscription time.
  • _ahpLog.truncated: true means large values were omitted from that log record.
  • Warning or error severity alone does not prove causality. Look for the matching failed response, missing completion, or user-visible consequence.
  • Missing files are normal because export collection is best-effort.

Mais skills de microsoft

oss-growth
microsoft
Persona de growth hacker OSS
agent-framework-azure-ai-py
microsoft
Crie agentes do Azure AI Foundry usando o SDK Python do Microsoft Agent Framework (agent-framework-azure-ai). Use ao criar agentes persistentes com AzureAIAgentsProvider, usando ferramentas hospedadas (interpretador de código, pesquisa de arquivos, pesquisa na web), integrando servidores MCP, gerenciando threads de conversa ou implementando respostas em streaming. Abrange ferramentas de função, saídas estruturadas e agentes com múltiplas ferramentas.
development
airunway-aks-setup
microsoft
Configure o AI Runway no AKS — do cluster vazio ao modelo em execução. Abrange verificação do cluster, instalação do controlador, avaliação de GPU, configuração do provedor e primeira implantação. QUANDO: "configurar AI Runway", "integrar cluster AKS", "instalar AI Runway", "configuração do airunway", "implantar modelo no AKS", "inferência GPU no AKS", "configuração KAITO no AKS", "executar LLM no AKS", "vLLM no AKS", "configurar serviço de modelo no AKS", "controlador AI Runway".
devops
appinsights-instrumentation
microsoft
Orientação para instrumentar aplicações web com Azure Application Insights. Fornece padrões de telemetria, configuração de SDK e referências de configuração. QUANDO: como instrumentar o app, SDK do App Insights, padrões de telemetria, o que é App Insights, orientação sobre Application Insights, exemplos de instrumentação, melhores práticas de APM.
devops
applicationinsights-web-ts
microsoft
Instrumente aplicativos de navegador/web com o SDK JavaScript do Application Insights (@microsoft/applicationinsights-web). Use para Real User Monitoring (RUM) — visualizações de página, cliques, dependências AJAX/fetch, exceções, eventos personalizados e rastreamentos de agentes GenAI no lado do navegador correlacionados a rastreamentos OpenTelemetry no backend. Abrange o Script de Carregamento do SDK e a configuração via npm, extensões de frameworks (React, React Native, Angular), Click Analytics, inicializadores de telemetria e convenções semânticas GenAI do OTel para spans de agente/ferramenta/modelo emitidos pelo navegador.
devops
azure-ai-anomalydetector-java
microsoft
Crie aplicativos de detecção de anomalias com o SDK do Azure AI Anomaly Detector para Java. Use ao implementar detecção de anomalias univariada/multivariada, análise de séries temporais ou monitoramento com IA.
development
azure-ai-language-conversations-py
microsoft
Implemente o reconhecimento de linguagem conversacional (CLU) usando o SDK Python azure-ai-language-conversations. Use ao trabalhar com ConversationAnalysisClient para analisar intenção e entidades de conversas, criar recursos de NLP ou integrar o reconhecimento de linguagem em aplicativos.
development
azure-ai-ml-py
microsoft
SDK v2 do Azure Machine Learning para Python. Use para workspaces de ML, jobs, modelos, conjuntos de dados, computação e pipelines. Gatilhos: "azure-ai-ml", "MLClient", "workspace", "registro de modelos", "jobs de treinamento", "conjuntos de dados".
development