Spaces:
Paused
Paused
Commit History
-
Scoped tokens, bounded archives and frames, build deadline, circuit breaker, honest note caps
Malina +1: Claude Fable 5.1- auth.py shared with NINA: scope + iat checks, jti persisted across restarts; NINA secret fallback removed - extract: ZIP members through real parsers with per-member and total byte caps, media listed as not read; doc/ppt/rtf/xls/ods refused with a conversion hint; PDF page cap announced - frames: bounded reservoir for streams without a duration (64 frames, stride doubling, downscaled at pick) - pipeline: reading and note-taking stop at 6 minutes and the Note is written from what is there; note cap grows to the REDUCE budget for small tasks and says when it cuts; long video transcripts read past the first window; transcript says where it stops; stage timings; prompt not logged - synthesis: prompt-marker lines stripped from file notes; failure reasons without provider messages - models: circuit breaker after 5 consecutive transport failures (30 s fail-fast) - app: clarify scope, max_file_size; parsers pinned; README python_version and API table - tests: 96 (18 new) Co-Authored-By: Cla…da9de03
-
Etap 1: przestac gubic tresc i palic dzienny limit
MalinaWygasle uploady palily limit. Space kasuje pliki po godzinie, a front wgrywa je w kroku 1 kreatora i buduje w kroku 4. _validate lapalo OSError przy getsize i robilo continue, wiec walidacja przechodzila mimo znikniętych plikow. Kazdy plik potem nie dawal sie odczytac, REDUCE generowal uprzejma Notatke "nie znaleziono trafnych materialow", a ta jest niepusta, wiec worker uznawal zadanie za udane i naliczal jedno z trzech dziennych uzyc. Teraz brak pliku to FileNotFoundError i czytelny blad, wiec worker nic nie zapisuje i nic nie nalicza. Awaria VLM na wideo kasowala transkrypcje. map_video zwracalo puste notatki, przez co plik ladowal jako nieczytelny, mimo ze Whisper wlasnie go przemielil i transkrypcja siedziala w argumencie. Teraz degraduje do sciezki tekstowej. Komunikat przy padnietym modelu nie zrzuca juz winy na plik. Pliki poza budzetem REDUCE znikaly z rozliczenia: nie trafialy ani do syntezy, ani na liste "Not used". Teraz sa ksiegowane jako odlozone. Sprawdzone: przy 100 p…a416f24
-
LUNA: grade relevance instead of a destructive binary gate; REDUCE decides
Malina +1: Claude Opus 4.8The cheap per-file MAP model judged relevance in isolation and, on a false "not relevant", DISCARDED the file's extracted notes (notes=""). One shaky call by the weak model could therefore permanently lose a file's content, producing three user-visible failures: 1. Relevance flips wrongly (single-file, no cross-file context). 2. Files reported "not used" yet still summarized — REDUCE wrote both the body and the Not-used line from separate instincts and could contradict itself. 3. "what did Kris text at 19:34" + screenshots → "No relevant files found": the strict ("BE ACCURATE, NOT GENEROUS") MAP marked the screenshot irrelevant and nuked its notes, so the fallback had nothing to rescue. Fix — decouple extraction from relevance: - MAP now ALWAYS extracts notes and emits a GRADED signal (high/medium/low/none) instead of a binary keep/drop. Notes are never discarded for a readable file. _parse_json tolerates the legacy boolean. - pipeline keeps every readable file with i…983d2be
-
LUNA v0.1 — multi-file task → structured Note (map-reduce backend)
Malina +1: Claude Opus 4.8Drop ≤100 files of any type, give a prompt, get one structured Note (Title · Agenda · Body · Sources). Parallel two-tier map-reduce over HF Inference Providers; faster-whisper for audio/video, VLM for images. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>281f5b1
-
initial commit
Verified signatureb67e3ef -
Duplicate from gradio-templates/chatbot
Co-authored-by: Pete <pngwn@users.noreply.huggingface.co>62d6859