2026-04-20T16-25-02Z__iter_01

4/20/2026, 4:25:02 PM · 1 flow · 77,470ms total

clean All settings match production defaults (app_defaults.yaml asOf 2026-04-19).

Build provenance

App

1.4·3

com.flashcopy.app.dev

Git

36652cef76

feature/processing-animation-variants · dirty

Sim

AAC26DF1…

com.flashcopy.app.dev

Built at

4/19/2026, 1:55:28 AM

video

ok pipeline →

Input media

No media file found for this input.

ScreenRecording_03-03-2026 10-36-16_1.MOV2.39 MBsha256 7e986ca659…

Input id

BBBB0004

Total

77.47s

Output

616 words

3523 chars

Cost est

$0.00092

gemini-2.5-flash · basis: chars

in 5,279 · out 1,762 tok

Stage timings

frame-extraction

0ms

s3-upload

1.07s

cloud-processing

76.40s

Stage details

frame-extraction	model gemini-2.5-flash frames 15
s3-upload	bucket qr-video-ocr-frames
cloud-processing	lambda backgroundProcessor model gemini-2.5-flash persisted true chars 3523

Extracted text

616 words · 3,523 charspolish json parsed

CLASSIC BROWN BUTTER CHOCOLATE CHIP
BANANA BREAD

One of my most beloved recipes and it's for
gooddd reason (and it's updated and better
than ever) 🥺 It's just the classic that really,
never gets old — I promise you'll be in love!!
Recipe below OR go to my website at
wellmadebykiley.com 🤎

#Recipe Details (serves 8-10):
Brown Butter Chocolate Chip Banana Bread:
- 1/2 cup (113g) salted butter @Kerrygold USA
- 3 large ripe bananas, mashed (~1 1/2 cups; 425g)
- 3/4 cup (165g) brown sugar, light or dark
- 1/2 cup (120g) Greek yogurt or sour cream, at room temperature
- 2 eggs, at room temperatur…

Prompts used

all prompts →

frame_ocr gemini-2.5-flash 66326cc5be… · 81 chars

Perform OCR on this image and return plain text only. Do not describe the image.

qr_reader_v1/frame_ocr_lambda.py:31

video_polish gemini-2.5-flash structured JSON sha n/a · 898 chars

Please stitch together the OCRs that are taken from individual screenshots/frames from a video. There should be overlapping lines which can be used as a marker for when one frame ends and another begins. Please do not alter the content in any way besides stitching the content together and please add correct indentation. Do not alter or add any content.

Your final output must be a single, valid JSON object and nothing else. The JSON object must conform to the following structure:
{
  "stitched_response": "(string) This key must hold the final, fully reconstructed and cleaned document text.",
  "additional_notes": "(string) Use this field to briefly describe your process. Mention any significant noise you filtered out (e.g., 'Removed text from a Save As dialog box') or any ambiguities you encountered during the reconstruction."
}

Here is the raw OCR text from video frames:

{raw_text}

qr_reader_v1/video_ocr_polishing_lambda_rest.py:102

Output diff

no baseline

No prior run for this input (sha256 7e986ca659…) and no ground-truth file at data/ground_truth/<sha>.md. After another ingest the diff will render here.

Video credit reconciliation

1 credit / frame

Frames

Charged

Expected (1/frame)

Current app bills by duration seconds; at fps=1.0 frames == seconds so this matches by accident. Any non-1.0 fps surfaces a mismatch.

Run settings

Show all 20 values

{
  "videoFramesPerSecond": 1,
  "videoStitchingMethod": "gemini_only",
  "videoPipelineMode": "s3_parallel",
  "useBackgroundVideoProcessing": true,
  "rekognitionThreshold": 80,
  "geminiModel": "gemini-2.5-flash",
  "photoOcrPromptSha": "48496a3017a2708a92d142281c5ab19f64f8132555514a00cbc35ca9d39daeba",
  "frameOcrPromptSha": "66326cc5be6bdd434dbbdd330b519e26bd8bbcab4a6037a64c2148b66cd2aceb",
  "imageRetentionHours": 24,
  "bypassImageSaveConfirmation": true,
  "bypassProcessingResultWindow": true,
  "enableAnalytics": true,
  "confirmCollectionReset": true,
  "enableNotifications": false,
  "autoProcessImages": true,
  "includeBrandingInSharedText": true,
  "autoSavePhotos": true,
  "multiPhotoSeparator": "double_line",
  "showDebugInfo": false,
  "headerFooterStyle": "equals"
}