2026-04-25T13-34-13Z__iter_01

4/25/2026, 1:34:13 PM · 1 flow · 18,453ms total

⚠️

Settings differ from production defaults

This run used 1 setting that don't match the current app_defaults.yaml (asOf 2026-04-19).

Key	Run value	Default
promptSha256.photo	"5e132458afcec510bc01e1854440ca8951afc13045629f093d3b868bd86087e1"	"48496a3017a2708a92d142281c5ab19f64f8132555514a00cbc35ca9d39daeba"

Build provenance

App

1.4·3

com.flashcopy.app.dev

Git

321150070a

feature/ocr-v2-structured-lambdas · dirty

Sim

AAC26DF1…

com.flashcopy.app.dev

Built at

4/25/2026, 10:22:38 AM

single-photo

v2 ok pipeline →

Input media

No media file found for this input.

—

Input id

AAAA0013

Total

18.45s

Output

26 words

139 chars

Cost est

$0.00004

gemini-2.5-flash · basis: chars

in 433 · out 35 tok

Stage timings

local-vision

889ms

moderation

386ms

s3-upload

998ms

gemini-ocr

16.18s

Stage details

local-vision	regions 7 conf 0.929
moderation	lambda moderation_ocr_v2 approved true
s3-upload	bucket qr-uploads-sup key incoming/fb5481c7-3797-493a-b55f-f4d105d5b9a8.jpg
gemini-ocr	lambda moderation_ocr_v2 model gemini-2.5-flash

Extracted text

26 words · 139 chars

NEED MORE BOXES?
SCAN HERE OR VISIT US AT
WALMART.COM/MOVING

DO NOT STEP ON THE EDGE OF THE BELT
KEEP THE MACHINE LEVEL
▲ Warning

Redliro

Raw Gemini response (v2)

parseable

278 chars — click to expand

{"ocr_text": "NEED MORE BOXES?\nSCAN HERE OR VISIT US AT\nWALMART.COM/MOVING\n\nDO NOT STEP ON THE EDGE OF THE BELT\nKEEP THE MACHINE LEVEL\n▲ Warning\n\nRedliro", "notes": "The text on the treadmill warning label is very blurry and the transcription is a best-effort attempt."}

Prompts used

all prompts →

photo_ocr gemini-2.5-flash 48496a3017… · 699 chars

Can you please OCR this image? Please OCR and do not modify the content and try and generate the OCR result with the same exact formatting as the input image. Please focus in ensuring the OCR process flawlessly retains the source's formatting. I aim to go line-by-line, capturing every detail, including special characters, comments, and those crucial line breaks, indentations, and case differences, thus guaranteeing the output mirrors the original. However, please remove any items from an editor or parts of the IDE/word processor that are shown in any potential screenshot to as just show only the content instead. (For instance removing the list of windows open/ line numbers, file name etc.)

qr_reader_v1/EXTENDED_LAMBDA_OCR.py:108

Output diff

no baseline

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

Run settings

Show all 5 values

{
  "rekognitionThreshold": 80,
  "geminiModel": "gemini-2.5-flash",
  "photoOcrPromptSha": "48496a3017a2708a92d142281c5ab19f64f8132555514a00cbc35ca9d39daeba",
  "frameOcrPromptSha": "66326cc5be6bdd434dbbdd330b519e26bd8bbcab4a6037a64c2148b66cd2aceb",
  "provenance": "post-F1"
}