Phase 2: Add Code Interpreter for Data Analysis#2
Merged
Conversation
Contributor
Agent Evaluation ResultsPhase: 2 Full results are in the Actions summary. |
Contributor
Agent Evaluation ResultsPhase: 2 Full results are in the Actions summary. |
Contributor
Agent Evaluation ResultsPhase: 2 Full results are in the Actions summary. |
- agents/tech-trends-agent.json: replace bing_grounding with code_interpreter (Phase 2 uses only code_interpreter, not both tools) - evaluate.yml: add smoke test step that invokes the agent and validates a response before running the full evaluation suite; remove BING_CONNECTION_NAME - bootstrap.sh: add model availability check (validates current + upgrade target gpt-4.1); remove Bing Grounding references and connection variable - lifecycle/02-phase2-code-interpreter.sh: fix to deploy code_interpreter only - README: document model upgrade (gpt-4o-2024-11-20 → gpt-4.1), note eval naming limitation (action creates new "Agent Evaluation" each run)
Contributor
Agent Evaluation ResultsAgent: tech-trends-agent:8 Smoke Test: ❌ Full results are in the Actions summary. |
- get_agent() → agents.get(agent_name=...) - Use OpenAI responses API via get_openai_client() for smoke test invocation - Fix monitor.yml to use agent.latest_version
Contributor
Agent Evaluation ResultsAgent: tech-trends-agent:9 Smoke Test: ❌ Full results are in the Actions summary. |
- Smoke test: just print agent name (version not needed for invocation) - Monitor: use list_versions() to find the latest version number
Contributor
Agent Evaluation ResultsAgent: tech-trends-agent:10 Smoke Test: ❌ Full results are in the Actions summary. |
The responses.create() call was missing the model parameter, causing a 404 DeploymentNotFound error in Azure OpenAI.
Contributor
Agent Evaluation ResultsAgent: tech-trends-agent:11 Smoke Test: ❌ Full results are in the Actions summary. |
Contributor
✅ Agent Deployment & Evaluation Report🤖 Agent Details
📊 Pipeline Results
🛠️ Tools Configuration
🔗 Links🤖 Updated automatically by the CI pipeline · 2026-05-15 19:39:10 UTC |
AgentDetails object returned by project.agents.get() has 'versions' (list), not 'version' (scalar). Use versions[-1] for the latest version.
SDK model objects don't support negative indexing directly.
…sions is AgentObjectVersions (not a list).\nThe correct path is agent.versions.latest.version.\nVerified locally with SDK model objects.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Summary
code_interpretertool alongside existingbing_grounding## Data AnalysissectionChanges
agents/tech-trends-agent.jsoncode_interpreterto tools, phase →"2"prompts/tech-trends-agent.md## Data Analysis (Phase 2)sectionevals/eval-config.jsonphase_filter→null(run all cases)What to check
Phase
Phase 2 of 3 — web search + code interpreter. Phase 3 is model upgrade.