Files
graphify/tests
safishamsiandClaude Opus 4.8 5d0137388e Feat: opt-in GRAPHIFY_DISABLE_THINKING; correct deepseek thinking default (#1621)
@sub4biz verified against the live DeepSeek API that deepseek-v4-flash (and
v4-pro) have thinking ENABLED by default, contradicting the built-in config's
stale "non-thinking" comment (now corrected).

The naive fix (mirror the kimi branch and force thinking off) is the wrong
call: @sub4biz's production testing on real corpora found that disabling
thinking removes a rare reasoning-leak failure — which the adaptive
extraction/labeling retry already recovers from — but trades it for far more
frequent benign truncation AND measurably lower extraction quality and file
coverage, confirmed by a blind second reviewer.

So thinking stays ON by default (quality/coverage), with a documented opt-in
`GRAPHIFY_DISABLE_THINKING=1` for users who prefer run-to-run stability. Applies
to reasoning-capable OpenAI-compatible backends at both extra_body sites
(extraction + labeling). An explicit providers.json extra_body still wins, and
the moonshot/kimi branch is unchanged (it must disable thinking or content is empty).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-06 16:02:45 +01:00
..
2026-04-04 18:52:44 +01:00