fix: P2 Bugs: 24003, 23959, 23504 and dev container changes #534
+101
−59
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Purpose
This pull request introduces improvements and fixes across the development environment setup, agent team configurations, and backend agent lifecycle management. The most notable updates include enhancements to the dev container configuration and setup script, changes to agent tool capabilities, and new logic for managing Azure AI Agent definitions.
Development environment improvements:
.devcontainer/devcontainer.jsonto specify the latest versions fordocker-in-dockeranduvfeatures, and enabled shell autocompletion foruv..devcontainer/setupEnv.shto useshinstead ofbash, added code fetching steps, improved error handling, and streamlined backend/frontend/MCP setup commands.Agent team configuration fixes:
coding_toolsfromtruetofalsein bothdata/agent_teams/marketing.jsonanddata/agent_teams/retail.jsonto disable coding tool access for these agent teams. [1] [2]Backend agent lifecycle and diagnostics:
_get_azure_ai_agent_definitionmethod tofoundry_agent.pyfor retrieving or creating Azure AI Agent definitions, improving agent management logic._after_openinfoundry_agent.pyto initialize agents with existing definitions when available, and refactored diagnostics logging (commented out for now). [1] [2]foundry_agent.pyto includeAgentandAwaitablefor type safety and future extensibility.Orchestration prompt update:
human_approval_manager.pyto explicitly prohibit offering further help in the final response.Does this introduce a breaking change?
How to Test
What to Check
Verify that the following are valid
Other Information