a84214dad1
Some checks failed
CI/CD / typecheck (pull_request) Successful in 56s
CI/CD / lint (pull_request) Successful in 3m6s
CI/CD / test (pull_request) Successful in 1m9s
CI/CD / build (pull_request) Successful in 2m39s
CI/CD / smoke (pull_request) Failing after 3m58s
CI/CD / publish (pull_request) Has been skipped
Live deploy showed qwen3-thinking failing the probe with "empty content": at max_tokens=8 the model spent its entire budget on the reasoning trace and never emitted a final \`content\` block. Fix: - Bump max_tokens to 64. Still caps latency at ~1-2 sec on cheap models but gives reasoning models enough headroom. - If \`message.content\` is empty but \`reasoning_content\` is non-empty, count it as alive and prefix the preview with "[thinking]" so the user knows the model didn't actually answer "hi" but is responsive. - Replace the prompt with the terser "Reply with just: hi" — closer to what a thinking model can short-circuit on. Tests: existing 25 pass; the failure-path test still asserts on the "empty content" path because reasoning_content is empty there too. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>