feat(Designer): Add reasoning flag to agent loop in consumption

[Elaina-Lee]

Commit Type

• feature - New functionality
• fix - Bug fix
• refactor - Code restructuring without behavior change
• perf - Performance improvement
• docs - Documentation update
• test - Test-related changes
• chore - Maintenance/tooling

Risk Level

• Low - Minor changes, limited scope
• Medium - Moderate changes, some user impact
• High - Major changes, significant user/system impact

What & Why

Adding resoning flag to the agent loop

Impact of Change

• Users: Users can now find and add reasoning flag as a advanced parameter option
• Developers: none
• System: none

Test Plan

• Unit tests added/updated
• E2E tests added/updated
• Manual testing completed
• Tested in: Local standalone

Contributors

Screenshots/Videos

[github-actions]

🤖 AI PR Validation Report

PR Review Results

Thank you for your submission! Here's detailed feedback on your PR title and body compliance:

✅ PR Title

• Current: feat(Designer): Add reasoning flag to agent loop in consumption
• Issue: None — title is clear, follows conventional commit style and describes the change.
• Recommendation: (No change needed.)

---

✅ Commit Type

• Properly selected (feature).
• Note: Only one commit type is selected which is correct.

---

⚠️ Risk Level

• Assessment: The PR body selects Low risk.
• Issue: There is no corresponding risk label on the PR (expected label: risk:low, risk:medium or risk:high). The only label present is needs-pr-update.
• Recommendation: Add the repository risk label that matches the PR body. For example: risk:low.

---

⚠️ What & Why

• Current: "Adding resoning flag to the agent loop"
• Issue: Minor spelling mistake (resoning -> reasoning) and the description is very brief.
• Recommendation: Fix the typo and expand to one short sentence describing the user-visible behavior and where the change is made. Example: "Add a reasoningEffort dropdown option to the agent loop manifest used by the Consumption designer so users can set reasoning effort (low/medium/high/none/minimal) as an advanced parameter."

---

⚠️ Impact of Change

• Impact issue: The Impact section is present but minimal. It lists "none" for Developers and System which is likely fine but could be clearer.
• Recommendation:
  • Users: Users can now select a reasoning effort option for agent loops in the Consumption designer (UI will show a new dropdown labeled "Reasoning effort").
  • Developers: Manifest/schema change only; no runtime logic changes. Note the file changed: libs/logic-apps-shared/.../manifests/agentloop.ts (29 additions). If any consumers parse or validate the manifest, call out whether backward compatibility is preserved.
  • System: No performance impact expected; confirm there are no new service dependencies.

---

✅ Test Plan

• Assessment: Manual testing is marked and includes "Tested in: Local standalone".
• Note: No unit or E2E tests were added. For a small manifest/UI schema change this is acceptable if manual testing is sufficient, but please add a short justification in the Test Plan explaining why automated tests are not necessary (for example: purely manifest metadata change that does not affect runtime codepaths or is covered by higher-level UI tests).

---

⚠️ Contributors

• Current: (Missing/blank)
• Recommendation: Add contributors/credit if others (PM, designer, reviewer) contributed. If none, you can leave blank but consider adding a quick line acknowledging reviewers.

---

✅ Screenshots/Videos

• Assessment: Screenshot included in the PR body.
• Recommendation: Ensure the screenshot clearly shows the new dropdown and its options; that helps reviewers.

---

Summary Table

Section	Status	Recommendation
Title	✅	No change needed
Commit Type	✅	No change needed
Risk Level	⚠️	Add repository risk label risk:low to match PR body
What & Why	⚠️	Fix typo and expand to briefly describe behavior and location
Impact of Change	⚠️	Expand impacts for Users/Developers/System; mention changed file
Test Plan	⚠️	Add brief justification for manual-only testing or add a lightweight automated test
Contributors	⚠️	Add credits or a short note if applicable
Screenshots/Videos	✅	Screenshot present; ensure it clearly shows the dropdown

---

Final message
This PR is small and low risk (29 additions to a single manifest file). I recommend the following actionable updates before merging:

1. Add the repository risk label that matches the PR body (e.g. risk:low).
2. Fix the typo in the "What & Why" section: change resoning to reasoning and expand the line to briefly describe the user-visible effect and the manifest file changed (libs/logic-apps-shared/.../manifests/agentloop.ts).
3. In Impact of Change, explicitly state the user/developer/system impacts as suggested above to help reviewers.
4. In Test Plan, either add a short justification why automated tests are not required for this manifest-only change or add a small automated test if feasible.
5. Add contributor credits if others helped with design/review, or add a short note if none.

Once those small updates are made, this PR looks good to merge (advised risk: Low). Thank you for the clear title and the included screenshot!

---

Last updated: Thu, 15 Jan 2026 20:31:20 GMT

[github-actions]

📊 Coverage check completed. See workflow run for details.

[Copilot]

Pull request overview

This PR adds the reasoningEffort parameter as an advanced option to the agent loop configuration in the consumption manifest. This allows users to control the level of reasoning effort applied by AI models during agent loop execution.

Changes:

• Added reasoningEffort field to agentChatCompletionSettings in the consumption agent loop manifest
• Configured as a dropdown with five options: low, medium, high, none, and minimal
• Follows the same implementation pattern as the standard manifest