2026-04-27T00-11-29Z__iter_03

4/27/2026, 12:11:29 AM · 1 flow · 6,917ms 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	"820549133fead0599675fdd9b0d19628c92aff77134dc48a845f9322013d01af"	"48496a3017a2708a92d142281c5ab19f64f8132555514a00cbc35ca9d39daeba"

Build provenance

App

1.4·3

com.flashcopy.app.dev

Git

e0ead7ca32

feature/ocr-v2-structured-lambdas · dirty

Sim

AAC26DF1…

com.flashcopy.app.dev

Built at

4/26/2026, 11:49:50 PM

single-photo

v2 ok pipeline →

Input media

No media file found for this input.

—

Input id

AAAA0013

Total

6.92s

Output

14 words

85 chars

Cost est

$0.00004

gemini-2.5-flash · basis: chars

in 433 · out 21 tok

Stage timings

local-vision

860ms

moderation

270ms

s3-upload

1.02s

gemini-ocr

4.76s

Stage details

local-vision	regions 7 conf 0.929
moderation	lambda moderation_ocr_v2 approved true
s3-upload	bucket qr-uploads-sup key incoming/fc47a3a9-f346-4d82-93d9-51fa0d26501e.jpg
gemini-ocr	lambda moderation_ocr_v2 model gemini-2.5-flash

Extracted text

14 words · 85 chars

NEED MORE BOXES?
SCAN HERE OR VISIT US AT
WALMART.COM/MOVING
A Warning
TSA007
Redliro

Raw Gemini response (v2)

parseable

362 chars — click to expand

{
  "ocr_text": "NEED MORE BOXES?\nSCAN HERE OR VISIT US AT\nWALMART.COM/MOVING\nA Warning\nTSA007\nRedliro",
  "notes": "The small text below the warning symbol on the black device was too blurry to read and was omitted. The combination numbers on the suitcase lock (e.g., '224') were part of the lock mechanism, not printed text, and were therefore omitted."
}

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": "pre-F1"
}