[pcbeingused333]

Summary

af doctor suggests an AI_MODEL for whichever provider key it finds, and for Anthropic and Google it suggested claude-3-5-sonnet-20241022 and gemini-1.5-pro. Both models are retired (claude-3-5-sonnet was retired on 2025-10-28 per Anthropic's model deprecations; no Gemini 1.5 model is listed any more on the Gemini API models page), so a scaffold that follows the recommendation fails on its first model call. The recommendation is now claude-sonnet-5-5 and gemini-3.8-flash (the current stable Flash model), and the commented examples in the docker .env template and the af init --default-model help text match.

The gpt-4o suggestion for OpenAI is left as it is.

Type of change

• Bug fix

Test plan

• cd control-plane && go test ./internal/cli ./internal/templates
• New subtest recommended models are not retired ones in doctor_additional_test.go sets only the Anthropic (then only the Google) key and checks the recommended model. It fails on main with the retired IDs and passes with this change.

Test coverage

• I ran tests for the surface(s) I changed locally.
• New code paths are covered by tests in this PR (no bare additions).

Checklist

• Commits are signed and follow conventional-commits style.

This change was prepared with Claude Code.

[CLAassistant]

All committers have signed the CLA.

[santoshkumarradha]

Thanks for updating these recommendations. The Google change is current, but the Anthropic model ID needs one small correction before this can land.

[github-actions]

📊 Coverage gate

Thresholds from .coverage-gate.toml: per-surface ≥ 84%, aggregate ≥ 85%, max per-surface regression ≤ 1.0 pp, max aggregate regression ≤ 0.50 pp.

Surface	Current	Baseline	Δ
control-plane	88.20%	87.40%	↑ +0.80 pp	🟡
sdk-go	93.70%	92.00%	↑ +1.70 pp	🟢
sdk-python	94.72%	93.73%	↑ +0.99 pp	🟢
sdk-typescript	92.50%	90.42%	↑ +2.08 pp	🟢
web-ui	84.90%	84.79%	↑ +0.11 pp	🟡
aggregate	86.12%	85.75%	↑ +0.37 pp	🟡

✅ Gate passed

No surface regressed past the allowed threshold and the aggregate stayed above the floor.

[github-actions]

📐 Patch coverage gate

Threshold: 80% on lines this PR touches vs origin/main (from .coverage-gate.toml:thresholds.min_patch).

Surface	Touched lines	Patch coverage	Status
control-plane	1	100.00%	✅
sdk-go	0	—	➖ no changes
sdk-python	0	—	➖ no changes
sdk-typescript	0	—	➖ no changes
web-ui	0	—	➖ no changes

✅ Patch gate passed

Every surface whose lines were touched by this PR has patch coverage at or above the threshold.

[AbirAbbas]

Both suggested models check out (details in the doctor.go thread), the doctor tests pass, and CI is green. The one leftover retired-model mention is the claude-3-sonnet example in the Python AIConfig.model description, which is out of scope here.