Add ai-file-analysis sample

[Corina (corinagum)]

Adds @examples/ai-file-analysis, a sample for the file-receive API from #712. It reads files attached in a personal (1:1) chat and sends the ones it understands to Azure OpenAI.

One message handler covers two paths:

• Basic (no LLM) replies with an Adaptive Card for files the sample cannot analyze, showing the metadata the file API exposes and the bytes that were downloaded.
• AI converts text files and images into OpenAI content parts, sends them in a single request, and streams the analysis back.

The flow is files.list(), then download() once per file, then classifyFile to sort each download into text, image, or unsupported. classifyFile falls back to the file's extension when the MIME type does not match, because Teams often misreports source files (.ts comes through as video/vnd.dlna.mpeg-tts). Image bytes are inlined as a data URI rather than passing the model the download URL, which carries a short-lived tempauth credential.

Where a block is labeled, the label is either FILE RECEIVE (the SDK API, the part worth copying) or SAMPLE GUARDRAIL (limits this sample picked). The guardrails: 5 files per message, 100 KB text per file, 250 KB text per message, 1 MB per image, PNG/JPEG/GIF/WebP only, and no conversation state. Anything dropped or truncated sends the user a message saying why.

Prerequisites

The manifest needs supportsFiles: true on the bot entry. Without it Teams does not enable the attachment UI in the bot's chat, so there is nothing to receive.

Testing

turbo build lint --filter=@examples/ai-file-analysis passes (13/13 tasks including dependencies).

Manually tested against a real bot in the Teams web client:

Case	Result
No attachment	Prompts for a file
Text .txt	Analyzed and streamed
Image .png	Analyzed and streamed
Mixed text + image in one message	Both files reached the model in one request
Unsupported .zip	Basic card, no model call
192 KB text file	Truncated at the 100 KB cap with a warning

The .zip case was checked in the bot log: a SharePoint GET and a card POST, with no call to openai.azure.com.

Other languages:

• Python: Add ai-file-analysis example teams.py#562
• .NET: Add AIFileAnalysisBot sample teams.net#651

[Copilot]

Pull request overview

Adds a new @examples/ai-file-analysis sample demonstrating the Teams file-receive API in personal (1:1) chat, including a basic “no LLM” path for unsupported files and an Azure OpenAI path that streams analysis for supported text/images.

Changes:

• Introduces @examples/ai-file-analysis workspace (bot entrypoint, file classification + guardrails, and an Adaptive Card response for unsupported files).
• Adds documentation for the new example (root README link + example README).
• Updates the lockfile to include the new workspace and its dependencies.

Reviewed changes

Copilot reviewed 10 out of 11 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
README.md	Adds the new example to the repository’s examples list.
package-lock.json	Registers the new workspace and dependency graph updates.
examples/ai-file-analysis/turbo.json	Defines Turbo build task config for the example workspace.
examples/ai-file-analysis/tsconfig.json	TypeScript configuration for building the example.
examples/ai-file-analysis/src/index.ts	Main bot message handler: lists files, downloads, classifies, and triggers analysis/guards.
examples/ai-file-analysis/src/file-card.ts	Builds an Adaptive Card describing unsupported files (no-LLM path).
examples/ai-file-analysis/src/ai/index.ts	Azure OpenAI streaming call + error handling for file analysis.
examples/ai-file-analysis/src/ai/file-context.ts	File classification and conversion into OpenAI content parts with size/count guardrails.
examples/ai-file-analysis/README.md	Example documentation (setup, manifest requirement, and flow explanation).
examples/ai-file-analysis/package.json	Adds the new example as a workspace package with scripts and deps.
examples/ai-file-analysis/eslint.config.js	ESLint config wiring for the example workspace.

Suppressed comments (2)

examples/ai-file-analysis/src/ai/index.ts:45

• After lazily initializing the Azure OpenAI client, runAnalysis should use the helper rather than the removed top-level client/deployment constants.

    stream.update('Analyzing files...');

    const completion = await client.chat.completions.create({
      model: deployment,
      messages: [

examples/ai-file-analysis/src/index.ts:58

• If the download loop is capped to 5 files, add a user-facing warning when additional attachments were ignored so the behavior stays traceable (consistent with the sample’s other warnings).

  if (analyzable.length === 0) {
    return;
  }

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[Corina (corinagum)]

Copilot resolve the merge conflicts in this pull request