Spaces:
Running
Running
Commit History
9 days ago
-
Proofread: basic check instead of an error when no language model is reachable
unknown +1: Claude Opus 5.5With every Groq key and model at its usage limit and no credit on the other provider, "Final check & proofread" failed with "the proofreading engine has reached its usage limit". It now completes with what needs no model (rule-based clean-up, LanguageTool, the AI-score checks) and says plainly that the full check (unclear sentences, academic wording, flow, consistency) has not been done yet and should be run again later. - proofread: `limited` result flag; PROOF_BASIC_FALLBACK=0 restores the error. - app: the result headline reads "Basic proofread done" in that case. - tests/test_proofread_fallback.py. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>a130a73