AGENT SKILL

triaging-security-reports

Use when a vulnerability or security report arrives for triage, when assessing a CVE/RCE/OGNL/injection claim against the code, when deciding whether a finding is the framework's fault or the application's, when drafting a reply to a security researcher, or when a claim that is already public (a Full Disclosure post, a blog, a scanner advisory) needs the project's position stated for users and scanner vendors — to research the claim from source without trusting the reporter and without fabricating your own facts.

License 许可
Apache-2.0
所属仓库
apache/struts
最近更新
2026-11-11
Stars
★ 1.4k
Forks
875

01 前言 Front Matter

name
agents-sdk-typescript-debugging
description
Use when troubleshooting an agent built with the Microsoft Agents SDK (@microsoft/agents-hosting and related packages). Trigger on any of these symptoms: build or TypeScript errors, crashes on startup, 401 or auth errors on incoming requests, the bot not responding to messages, .env configuration problems, Azure AD credential failures (AADSTS errors), port conflicts, or the agent not connecting in Teams or the Agents Playground. Use even if the user doesn't mention the SDK by name — trigger on symptoms like "my bot won't start", "getting 401s", or "bot isn't responding."

03 SKILL.md 正文

Debugging Agents Built with Microsoft Agents SDK

Overview

Most agent failures fall into one of three categories: the code doesn't build or start, the configuration is wrong, or the agent isn't reachable. Work through this checklist in order — each step confirms a prerequisite for the next.

Checklist

You MUST create a task for each of these items and complete them in order:

  1. Make sure the code builds successfully.
  2. Make sure the application starts and runs without crashing.
  3. Make sure the application opens a port and listens for incoming requests.
  4. Validate the .env configuration.
  5. Validate the bot's credentials against Azure AD.
  6. Use the Agents Playground to test the agent end-to-end locally.

1. Build the code

npm run build

Expected: exits with code 0, no errors. Fix any TypeScript or import errors before continuing.


2. Start the application

Run with debug logging enabled to get detailed output from the SDK internals:

DEBUG=agents:* npm start

Or for anonymous local dev:

DEBUG=agents:* node ./dist/index.js

The DEBUG=agents:* flag enables verbose logging across all SDK namespaces. Scope down to reduce noise:

DEBUG=agents:* npm start                    # everything
DEBUG=agents:authorization:* npm start      # all auth (most useful starting point)
DEBUG=agents:msal npm start                 # token acquisition only

Auth & connections

Namespace What it logs
agents:authorization:connections Auth connections loaded at startup (clientId, tenantId, authType); which connection is selected per request
agents:authorization:manager Auth handlers configured at startup (type, scopes); which handler is invoked per request
agents:authorization:azurebot Azure Bot sign-in flow detail (token exchange, magic code, SSO)
agents:authorization:agentic Agentic auth flow detail (token acquisition, OBO)
agents:authorization High-level authorization middleware decisions
agents:msal MSAL token acquisition (token requests, cache hits, OBO)
agents:jwt-middleware Incoming JWT validation
agents:authConfiguration Auth configuration loading

Adapter & request handling

Namespace What it logs
agents:cloud-adapter Incoming request processing, activity dispatch
agents:base-adapter Base adapter lifecycle
agents:connector-client Outbound calls to the Bot Connector service
agents:user-token-client User token client requests

Application & state

Namespace What it logs
agents:app AgentApplication routing and lifecycle
agents:activity-handler ActivityHandler event dispatch
agents:state State read/write operations
agents:turnState Turn state access
agents:memory-storage MemoryStorage read/write
agents:middleware Middleware pipeline execution

Streaming, attachments & transcripts

Namespace What it logs
agents:streamingResponse Streaming response lifecycle
agents:attachmentDownloader Attachment download requests
agents:M365AttachmentDownloader M365-specific attachment downloads
agents:file-transcript-logger File transcript write operations
agents:rest-client REST client calls (transcript middleware)

Agent-to-agent

Namespace What it logs
agents:agent-client Outbound agent client calls and response handling

Watch for crash output. Common startup errors:

  • Cannot find module — missing npm install, or dist/ not built yet
  • ERR_MODULE_NOT_FOUND — check "type": "module" in package.json and that imports use .js extensions
  • Port already in use — another process is on port 3978; kill it or set PORT in .env

If the agent starts cleanly, you should see output like:

Server listening on port 3978

3. Confirm the agent is reachable

curl -s -o /dev/null -w "%{http_code}" \
  -X POST http://localhost:3978/api/messages \
  -H "Content-Type: application/json" \
  -d '{}'
Response Meaning
401 Agent is running, auth is active — this is correct for a configured agent
200 Agent is running with auth disabled (blank clientId) — correct for anonymous local dev
000 or connection refused Agent is not running, wrong port, or crashed on startup

4. Validate .env configuration

Configuration mistakes are the most common source of failures. Check each area below.

4a. Confirm the file is being loaded

The SDK requires node --env-file .env (Node 20+) or a manual dotenv call. If you're using npm start, check that package.json uses --env-file:

"start": "node --env-file .env ./dist/index.js"

Without --env-file, environment variables silently don't load and the agent starts with no auth config.

4b. Check for the correct env var format

The SDK uses the modern connections__ format. Using the legacy flat format (clientId=, clientSecret=, tenantId=) still works but is only for backwards compatibility. Mixing the two formats causes silent misconfiguration.

Modern format (use this):

connections__serviceConnection__settings__clientId=<your-app-id>
connections__serviceConnection__settings__clientSecret=<your-secret>
connections__serviceConnection__settings__tenantId=<your-tenant-id>
connectionsMap__0__connection=serviceConnection
connectionsMap__0__serviceUrl=*

Legacy format (avoid for new agents):

clientId=<your-app-id>
clientSecret=<your-secret>
tenantId=<your-tenant-id>

4c. Check double-underscore separators

A single underscore (_) is not the same as a double underscore (__). The SDK uses __ to separate path segments. A typo like connections_serviceConnection_settings_clientId will be silently ignored.

4d. Check connectionsMap entries

If you have multiple connections, each must have a connectionsMap entry. The first entry whose serviceUrl pattern matches the incoming request wins. Always include a serviceUrl=* fallback as the last entry.

With a single connection, connectionsMap can be omitted — the SDK defaults to serviceUrl=*.

4e. Check OAuth handler variables

If your agent uses user sign-in (authorization: { graph: { ... } }), the OAuth connection name must be set:

AgentApplication__UserAuthorization__Handlers__graph__Settings__azureBotOAuthConnectionName=GraphOAuthConnection

The handler ID (graph) must match the key used in the authorization config in your code. A mismatch causes the sign-in flow to fail silently or with a cryptic error.


5. Validate bot credentials against Azure AD

Once the .env looks correct, confirm the credentials actually work by requesting a token:

curl -s -X POST \
  "https://login.microsoftonline.com/$tenantId/oauth2/v2.0/token" \
  -d "grant_type=client_credentials\
&client_id=$clientId\
&client_secret=$clientSecret\
&scope=https://api.botframework.com/.default" \
  | jq '{token_type, expires_in, error, error_description}'

A successful response includes access_token. Common errors:

Error code Cause
AADSTS700016 clientId not found in tenant — wrong ID or wrong tenant
AADSTS7000215 Invalid clientSecret — expired or incorrect
AADSTS90002 tenantId not found

6. Test with Agents Playground

The Agents Playground acts as a mock connector and channel client. It lets you test the full message flow locally without deploying to Azure or configuring a real Bot resource.

Install:

npm install -g agentsplayground

Run against an anonymous agent (no .env needed):

npm test

This assumes your package.json has:

"start:anon": "node ./dist/index.js",
"test-tool": "agentsplayground -c emulator",
"test": "npm-run-all -p -r start:anon test-tool"

Run against an authenticated agent:

agentsplayground -c msteams \
  --client-id <your-app-id> \
  --client-secret <your-secret> \
  --tenant-id <your-tenant-id>

Channel options (-c): msteams, webchat, directline, emulator, agents

If the playground connects but messages don't get responses, the agent is running but a message handler may be missing or the route isn't matching. Add a fallback handler to confirm:

this.onActivity('message', async (ctx: TurnContext) => {
  await ctx.sendActivity(`Echo: ${ctx.activity.text}`)
}, [], RouteRank.Last)

Validate an OAuth connection name

OAuth connection names can only be tested end-to-end through a real sign-in flow:

Azure Portal → Your Bot Resource → Settings → OAuth Connection Settings → [your connection] → Test Connection

This confirms the connection name matches, the OAuth app has the right scopes, and the redirect URI (https://token.botframework.com/.auth/web/redirect) is registered on the app registration.

Contributing

If you hit a problem this skill couldn't solve, found a workaround, or noticed something wrong or outdated, that's valuable — please help improve this skill for everyone.

Draft a suggested issue title and body based on the conversation, then ask the user to open it at: https://github.com/microsoft/agents/issues/new

A good issue includes:

  • What the user was trying to do
  • What went wrong (errors, unexpected behavior)
  • What worked — including any workaround found during this conversation
  • Relevant code or config snippets

04 同仓库更多 Skills

apache
apache/struts

code-review

Apache Struts pull request review guide. Use when reviewing pull requests in this repository to check test conventions, security-sensitive framework code, PR and commit hygiene, and Struts-specific implementation patterns.

开发工程师代码审查测试与质量
★ 1.4k
apache
apache/struts

releasing-struts

Use when running or planning an Apache Struts release on any maintenance line (6.x, 7.x) - cutting the tag, staging artifacts, opening the vote, promoting, updating the site and announcing - or when asked what the next step in a release is.

★ 1.4k
apache
apache/struts

merging-dependabot-prs

Use when triaging, classifying or landing Dependabot pull requests in this repo — clearing the open Dependabot queue, deciding whether a bump needs a WW Jira ticket, or checking whether a bump's build actually passed.

★ 1.4k
apache
apache/struts

creating-version-notes

Use when preparing, updating, or reviewing the release documentation for a Struts release or release candidate on any maintenance line (6.x, 7.x) - the Version Notes page on the cwiki, its Migration Guide entry, the GitHub release notes, and the test-build announcement mail.

★ 1.4k
apache
apache/struts

creating-security-bulletins

Use when drafting, updating, or reviewing an S2-XXX security bulletin on the Struts cwiki, when preparing bulletin text ahead of a CVE request, when filling a CVE record in the ASF CVE tool (cveprocess.apache.org / Vulnogram), when deciding when to publish, when publishing a bulletin and announcing it to the ASF lists, when wrapping up after the advisory mails, or when deciding how much detail about a fixed vulnerability is safe to publish.

★ 1.4k
apache
apache/struts

creating-release-vote-mail

Use when opening the formal release vote for a Struts release candidate on any maintenance line (6.x, 7.x) - composing and drafting the [VOTE] Apache Struts X.Y.Z mail to dev@ once the Version Notes page, GitHub release and staged artifacts are published.

★ 1.4k