Fix scheduled automation tool selection

[louis4li]

Issue

Closes aevatarAI/aevatar-framework#171

Scope

• Add scheduled automation tools to the Mainnet NyxID chat default tool set through the scheduled module's registered AgentBuilderToolSource.
• Expand the default system NyxID chat profile ceiling/recovery policy so scheduled automation tools are not filtered out before turn materialization.
• Route scheduled/reminder-style profile-task turns to scheduled automation tools while keeping ordinary chat from exposing schedule-exclusive or managed workflow execution tools.
• Add regression coverage for empty profile members and Mainnet host tool discovery.

Verification

• dotnet test test/Aevatar.AI.Tests/Aevatar.AI.Tests.csproj --nologo --no-restore --filter AgentTurnToolCatalogMaterializerTests -v minimal
• dotnet test test/Aevatar.Capabilities.Tests/Aevatar.Capabilities.Tests.csproj --nologo --no-restore --filter MainnetHostCompositionTests -v minimal
• bash tools/ci/test_stability_guards.sh
• bash tools/ci/architecture_guards.sh
• Local Mainnet host http://127.0.0.1:5080 started with authentication enabled.
• NyxID proxy /api/workflow/observatory/me returned owner scopeId=ee363bd4-33e1-4123-a789-17e9b8b8ca71 through local diagnostic binding.
• /api/chat ordinary weather request exposed only ask_user, not scheduled or managed workflow tools.
• /api/chat scheduled reminder request exposed scheduled_agent_creator, ornn_publish_skill, ornn_search_skills, use_skill, and ask_user; the run advanced to missing time/timezone input instead of failing with no tools.

Notes

• A newly created service slug aevatar-local-5080-scheduled-task-tools could not proxy because the local NyxID node lacked a matching local credential entry. Verification used the existing aevatar-local-diag-catalog binding temporarily pointed at 5080, then restored to 5107.

Generated with Claude Code.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-07T10:13:02.724072Z	53d30f5	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 53d30f5774

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 83.44%. Comparing base (74fd34e) to head (e483895).
⚠️ Report is 1 commits behind head on feature/integrate.

@@                  Coverage Diff                  @@
##           feature/integrate    #3603      +/-   ##
=====================================================
- Coverage              83.45%   83.44%   -0.01%     
=====================================================
  Files                   1709     1709              
  Lines                 197728   197728              
  Branches               23735    23735              
=====================================================
- Hits                  165011   165004       -7     
- Misses                 21676    21683       +7     
  Partials               11041    11041              

Flag	Coverage Δ
ci	83.44% <ø> (-0.01%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.
see 4 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.