Spaces:
Running
Running
Commit History
4 days ago
-
Faster humanizing on the GPU Space; the automatic proofread no longer undoes the humanizing
unknown +1: Claude Opus 5.5- The meaning, fluency, clarity and vocabulary checking models now run on the GPU when the Space has a dedicated one (they ran on the CPU for every version of every sentence on every pass; HELPERS_GPU=0 keeps them on CPU). - Automatic proofread after humanizing: grammar fixes and repairs that raise the AI score are undone too (a repair put back the author's flagged wording: a live run went 0% -> 100%). If the proofread still scores worse, the humanized version is delivered and the customer is told to press Final check & proofread to apply it anyway. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>4d32393
9 days ago
-
Cut language-model cost and show what each job costs
unknown +1: Claude Opus 5.5Measured on the paid tier: one pass of every task over 5,000 words is about 6-7 US cents; the natural-style rewrites are over half of it. - Models: default list is gpt-oss-120b, gpt-oss-20b. qwen3.8-27b (about six times the price) and the unavailable llama model are no longer fallbacks. - Routing: verify and grammar run on the half-price GROQ_LIGHT_MODEL (GROQ_LIGHT_KINDS); writing tasks stay on the main model. - verify(): verdicts cached and packed through the shared batch runner. - Final polish is sent only for paragraphs the tool changed (POLISH_CHANGED_ONLY). - A rate limit that clears within GROQ_SHORT_LIMIT seconds is waited out instead of switching writing tasks to the weaker model. - GROQ_JOB_BUDGET: ceiling per job in US$ (default 1.00); past it the job continues with the local checks. - Accounting: every request booked by task (tokens in, cached, out, cost; GROQ_PRICES); "[cost]" line per Smart Humanize and proofread job in the log. - README: measured costs a…2906069 -
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
11 days ago
-
Upload 3 files
Verified signatured71d180 -
Upload 8 files
Verified signature0fdaff6
12 days ago
-
Upload 2 files
Verified signaturefbb10d7
14 days ago
-
Upload 9 files
Verified signature78dbb12
17 days ago
-
Upload proofread.py
Verified signature22cf011 -
Upload 2 files
Verified signature3a0c7c2
18 days ago
-
Upload 3 files
Verified signature370a123 -
Upload 3 files
Verified signaturecba1650 -
Upload 3 files
Verified signature1932dd5 -
Upload 3 files
Verified signatureb3e28f6