profit 8cbbd0ef70 Phase 38 fix: default think=false on /v1/chat
Live-test caught the Phase 21 thinking-model trap on first call.
qwen3.5 with max_tokens=50 and default think behavior burned all 50
tokens on hidden reasoning; visible content was "". completion_tokens
exactly matching max_tokens was the tell.

Adapter now defaults think: Some(false) matching scenario.ts hot-path
discipline. Callers that want reasoning (overseers, T3+) opt in via
a non-OpenAI `think: true` extension field on the request.

Verified end-to-end after restart:
- "Lakehouse supports ACID and raw data." (5 words, 516ms)
- "tokio\nasync-std\nsmol" (3 Rust crates, 391ms)
- /v1/usage accumulates across calls (2 req / 95 total tokens)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-22 02:50:09 -05:00
2026-04-22 02:41:15 -05:00
2026-04-22 02:41:15 -05:00
2026-03-27 05:54:09 -05:00
2026-04-22 02:41:15 -05:00
2026-04-22 02:41:15 -05:00
Description
Rust-first object storage system
6.3 GiB
Languages
TypeScript 38.4%
Rust 35.8%
HTML 13.9%
Python 7.8%
Shell 2.1%
Other 2%