azure.ai.agents - filter out unsupported models and locations from init prompts

[JeffreyCA]

Resolves #7351

This PR builds on #7397 and updates the azure.ai.agents extension to filter out unsupported models (incompatible with agents) and locations from prompts during azd ai agent init. Previously, the prompts would show all Azure locations and available models.

The init flow now limits location selection to these regions via a hardcoded list (due to lack of API). It also filters model selection to ones with the agentsV2 capability so the extension only offers models that are valid for agent scenarios.

This PR also brings the code-first init path in line with the manifest-based flow. When deployment resolution cannot complete directly for the selected model and location, the extension now falls back to the shared recovery flow instead of failing early, which gives users a clearer path to recover from model or region mismatches.

Screenshots

[Copilot]

Pull request overview

Updates the azure.ai.agents extension init experience to avoid offering invalid Azure regions and AI models during azd ai agent init, and aligns the code-first init path with the manifest-based recovery behavior when deployment resolution can’t complete directly.

Changes:

• Filters AI model prompts/catalog to models with the agentsV2 capability.
• Restricts location selection during init to a hardcoded “hosted agents supported regions” allow-list via PromptLocationRequest.AllowedLocations.
• Adjusts code-first init to fall back into the shared recovery flow when deployment candidate selection fails or can’t find a valid no-prompt capacity candidate.

Reviewed changes

Copilot reviewed 8 out of 9 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
cli/azd/extensions/azure.ai.agents/internal/cmd/init.go	Adds agentsV2 capability constant used for filtering models.
cli/azd/extensions/azure.ai.agents/internal/cmd/init_models.go	Applies capability-based model filtering and tweaks env location update behavior.
cli/azd/extensions/azure.ai.agents/internal/cmd/init_locations.go	Introduces hardcoded hosted-agent supported region allow-list for init.
cli/azd/extensions/azure.ai.agents/internal/cmd/init_from_code.go	Uses shared recovery flow when direct deployment resolution/candidate selection can’t complete.
cli/azd/extensions/azure.ai.agents/internal/cmd/init_foundry_resources_helpers.go	Enforces allowed locations in ensureLocation, adds shared helpers for model filtering and deployment resolution.
cli/azd/extensions/azure.ai.agents/internal/cmd/init_foundry_resources_helpers_test.go	Adds unit test for agentModelFilter.
cli/azd/extensions/azure.ai.agents/go.mod	Bumps azd dependency, adds local replace, and updates indirect deps.
cli/azd/extensions/azure.ai.agents/go.sum	Updates dependency checksums to match go.mod changes.
cli/azd/extensions/azure.ai.agents/extension.yaml	Raises required azd version to include needed host prompt features.

[jongio]

Filters models and locations for the agents init flow. Clean refactoring of deployment resolution into smaller functions.

Findings: 0 critical, 0 high, 2 medium, 2 low

Issues to address:

• init_from_code.go:643 - partial InitAction construction is fragile; nil-pointer risk if called methods evolve
• init_foundry_resources_helpers_test.go:298 - test coverage gaps for new helper functions
• init_foundry_resources_helpers.go:782 - manual loop where slices.ContainsFunc fits
• init_foundry_resources_helpers.go:865 - doc comment stale after function rename

Note: The recovery paths in promptForModelLocationMismatch pass model.Locations as AllowedLocations rather than intersecting with supportedRegionsForInit(). Users in the recovery flow can pick a location where the model is available but the hosted agent platform is not supported.

[jongio]

Previous findings still apply. One more nit:

• init_models.go:78 - err variable shadow in updateEnvLocation else block

[jongio]

All previous findings addressed. The modelSelector extraction is clean - proper encapsulation, lazy init, clear doc comment. The supportedModelLocations intersection fixes the recovery-flow location gap. Tests are thorough with good edge coverage (nil, empty, case-insensitive, mutation safety).

One remaining item: merge conflicts need resolution before this can merge.

[wbreza]

Code Review — PR #7415

azure.ai.agents — filter out unsupported models and locations from init by @JeffreyCA

Summary

Clean implementation that correctly filters init prompts to supported regions and agentsV2-capable models. The modelSelector extraction elegantly addresses the partial-struct concern from the prior review round. Recovery flow alignment between code-first and manifest-based paths is well-designed.

Prior Review Regression Check

All 7 findings from @jongio's two review rounds are verified resolved:

• Partial InitAction → ✅ Extracted modelSelector
• slices.ContainsFunc → ✅ Applied
• Stale doc comment → ✅ Fixed
• Test coverage gaps → ✅ Comprehensive tests added
• Variable shadowing → ✅ Fixed
• Recovery flow location gap → ✅ supportedModelLocations intersection
• go.mod replace comment → ✅ N/A (outdated)

✅ What Looks Good

• modelSelector struct encapsulates exactly the needed dependencies — clean, testable, safe
• slices.Clone prevents mutation of the supported regions list
• Table-driven tests cover nil, empty, case-insensitive, whitespace, and mutation safety
• supportedHostedAgentRegions documented with source link and vNext TODO
• agentModelFilter always includes agentsV2 capability — correct by construction

Findings: None

No new issues found. Code is well-structured and thoroughly tested.

Overall Assessment: Approve

Note: Merge conflicts need resolution before merge.

Review performed with GitHub Copilot CLI