Increase max tool call and handle lm error

[bosesuneha]

• Fix LM tool-calling loop to gracefully produce output when max rounds are exhausted instead of failing
• Add error handling to skip workflow generation when deployment files (Dockerfile/manifests) fail to generate
• Refactor LMClient for readability: extract stream helpers, parallelize tool execution

[Copilot]

Pull request overview

This PR updates the Container Assist Language Model (LM) integration to be more resilient and configurable when using tool-calling, and adjusts the command orchestration so workflow generation depends on having deployment artifacts available.

Changes:

• Increase the default/max configured tool-calling rounds and, when rounds are exhausted, issue a final LM request without tools to force a textual output.
• Refactor LMClient response consumption into helper methods and execute tool calls concurrently.
• Update the “both actions selected” flow to run deployment generation first and skip workflow generation when Dockerfile/manifests aren’t present.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
src/commands/aksContainerAssist/lmClient.ts	Raises tool-round limit, adds final “no-tools” request on exhaustion, and refactors streaming/tool execution helpers.
src/commands/aksContainerAssist/containerAssistService.ts	Introduces MAX_TOOL_ROUNDS and passes it into LM tool-calling requests for Dockerfile/manifests generation.
src/commands/aksContainerAssist/aksContainerAssist.ts	Reworks action sequencing: deployment first when both actions are selected; conditionally proceeds to workflow generation based on artifact existence.

---

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

You can also share your feedback on Copilot code review. Take the survey.

[davidgamero]

lgtm