Increase RPM capacity and fix key names in API requests/responses

[nadimakk]

No description provided.

[nadimakk]

@microsoft-github-policy-service agree company="Microsoft"

[Copilot]

Pull request overview

This pull request updates the Azure AI Foundry/OpenAI agent invocation payload to use the correct agent_reference key, and increases the default deployment capacity for the Mistral Document AI model to support higher request throughput.

Changes:

• Update openai_client.responses.create(..., extra_body=...) to send agent_reference (instead of agent) for agent-based calls.
• Increase ARM template deployment capacity for mistral-document-ai-2505 from 1 to 60.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
challenge-6/agents/policy_matching_agent.py	Fixes agent reference key in the Responses API request body for the policy matching agent call.
challenge-6/agents/coverage_validation_agent.py	Fixes agent reference key in the Responses API request body for the coverage validation agent call.
challenge-0/infra/azuredeploy.json	Raises the Mistral Document AI deployment capacity to improve throughput.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.