Ethanfel 0e9e99b8b2 Handle reasoning models (Qwen3.5/3.6): no-think + JSON-only + prose fallback ...

Qwen3.5/3.6 are reasoning models — they 'think out loud' in markdown and never
reach the JSON, then get cut off at the token limit -> '(no parseable judgement)'.
Fixes: apply_chat_template(enable_thinking=False) + strip <think> blocks; hardened
'output ONLY JSON, do not think out loud' instruction; default max_new_tokens
1024->2048 (max 8192); and a markdown fallback parser (_parse_markdown_verdicts /
_parse_axes) that extracts per-axis {verdict,ref,gen} from the prose the model
reliably emits. describe falls back to using the raw text as the caption.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-27 10:25:16 +02:00

..

__init__.py

Initial commit: VLM-as-judge prompt calibration loop

2026-06-26 22:15:56 +02:00

qwen_judge.py

Handle reasoning models (Qwen3.5/3.6): no-think + JSON-only + prose fallback

2026-06-27 10:25:16 +02:00

receptor.py

Fix: render text inputs as editable fields, not input sockets

2026-06-27 10:18:12 +02:00