Repository navigation
Use catalogue-supported efforts in model routing smoke - #9929
Conversation
Co-authored-by: lpcox <15877973+lpcox@users.noreply.github.com>
There was a problem hiding this comment.
🟢 Approval recommended
The focused change satisfies the issue requirements without altering routing behavior.
0 open findings
What changed in this PR
Updates the model-routing smoke test to use catalogue-supported reasoning efforts.
Changes:
- Validates routed effort metadata against
/reflect. - Selects lowest and highest supported efforts using a fixed ranking.
- Reuses the routed request body for explicit-effort checks.
| File | Description |
|---|---|
.github/workflows/test-model-routing.yml |
Adds catalogue-driven effort validation and requests. |
🧠 Review effort: Balanced
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
|
✅ Copilot review passed with no inline comments. @copilot Add the |
✅ Coverage Check PassedOverall Coverage
📁 Per-file Coverage Changes (1 files)
Coverage comparison generated by |
|
✅ Smoke Copilot BYOK completed. Copilot BYOK mode operational. 🔓
|
|
📡 Smoke OTel Tracing completed. All tracing scenarios validated. ✅
|
|
🔌 Smoke Services — All services reachable! ✅
|
|
🪪 Smoke Copilot BYOK AOAI (Entra) is testing Azure OpenAI BYOK (Entra / GitHub OIDC) mode on this pull request... |
|
✅ Smoke Claude passed
|
|
🔑 Smoke Copilot BYOK AOAI (api-key) is testing Azure OpenAI BYOK (api-key) mode on this pull request... |
|
✨ The prophecy is fulfilled... Smoke Codex has completed its mystical journey. The stars align. 🌟 Smoke CodexOutcome: The agent completed and reported no action. A no-op output alone does not verify that all required work was completed or that publication was possible. Agent messages are omitted from this comment. The category uses structured run status, not interpretation of agent prose.
|
|
🚀 Security Guard has started processing this pull request |
|
💎 Smoke Gemini is crystallizing results on this pull request... |
|
Chroot tests passed! Smoke Chroot - All security and functionality tests succeeded.
|
|
📰 VERDICT: Smoke Copilot has concluded. All systems operational. This is a developing story. 🎤
|
|
Smoke Cloud Hypervisor completed. Cloud Hypervisor + Copilot passed.
|
|
✅ Build Test Suite completed successfully!
|
|
🛡️ Smoke Copilot Network Isolation confirmed the egress allowlist is enforced. ✅
|
Smoke Test: Claude Engine Validation
Overall result: PASS
|
|
Smoke Copilot: PASS ✅
|
Smoke Test: Copilot BYOK Results✅ GitHub MCP Connectivity - Verified via list_pull_requests Status: PASS — All tests passed.
|
Cloud Hypervisor + Copilot Smoke Test
Overall: PASS ✅
|
|
OTEL smoke test
|
|
Smoke services: ✅ Redis PONG, ✅ pg_isready, ✅ SELECT 1. Overall: PASS
|
🏗️ Build Test Suite Results
Overall: 8/8 ecosystems passed — PASS Notes: Bun and Deno were installed via npm (curl installers were blocked). Maven used
|
Smoke Test
|
|
EGRESS_RESULT allow=pass deny=pass
Overall: PASS — cc @lpcox
|
Chroot Version Comparison
Result: Not all tests passed. Node.js differs between host and chroot, so the
|
The effort-routed Copilot smoke step requests
max, whichgpt-5.4-minidoes not support, causing exit 78 even after routed inference succeeds./reflectand exercise its lowest and highest supported efforts using the fixed rankingnone → minimal → low → medium → high → xhigh → max, regardless of catalogue order.For the current catalogue, the explicit requests become
noneandxhigh, rather thannoneandmax.