Model Upgrade: gpt-4o-2024-11-20 → gpt-4.1

[san360]

Summary

• Upgrades the agent model from gpt-4o-2024-11-20 to gpt-4.1
• GitHub variable GPT_DEPLOYMENT updated to gpt-4.1
• Model history annotation updated in agent config

Why this needs an eval gate

Swapping models is a behaviour change. The new model may:

• Format responses differently
• Handle tool calls differently
• Score higher or lower on evaluation dimensions

The eval workflow will deploy with the new model and verify all scores
meet thresholds before this can be merged.

Changes

File	Change
agents/tech-trends-agent.json	Updated _model_history annotation
GitHub variable GPT_DEPLOYMENT	gpt-4o-2024-11-20 → gpt-4.1

What to check

• All 4 evaluator scores meet or exceed current thresholds
• No regression on Phase 1 or Phase 2 queries
• Response format still follows the structured template
• Tool calls (web search + code interpreter) still work correctly

Phase

Phase 3 of 3 — model upgrade. Lifecycle demo complete after merge.

[github-actions]

✅ Agent Deployment & Evaluation Report

🤖 Agent Details

Property	Value
Agent	tech-trends-agent
Version	23
Semver	0.0.0-pr.6
Phase	2
Model	gpt-4.1
Commit	12b9c8e
Timestamp	2026-05-18 14:48:57 UTC

📊 Pipeline Results

Step	Status	Details
Deploy to TEST	✅ PASSED	Agent version 23 deployed
Smoke Test	✅ PASSED	Invoked agent via Responses API
Foundry Evaluation	✅ PASSED	Evaluated with golden dataset

🛠️ Tools Configuration

Tool	Enabled
web_search	✅
code_interpreter	✅

🔗 Links

• 📋 Full Actions Run
• 📁 Artifacts

---

_{🤖 Updated automatically by the CI pipeline · 2026-05-18 14:48:57 UTC}