copilot-swe-agent[bot] 89d5df71c8 feat(ocr): fine-tune OCR quality criteria with stricter threshold and head-to-head comparison ...

- Raise quality acceptance threshold from 65→85 (configurable via TEXT_QUALITY_THRESHOLD)
- Reject text with significant issues (excessive_typos, garbage_characters,
  incoherent_text, fragmented_sentences) even when score is above threshold
  (configurable via TEXT_QUALITY_SIGNIFICANT_ISSUES)
- Add compare_text_quality() for AI-powered head-to-head comparison of
  original embedded text vs fresh OCR output
- Update process_document to pass original text to OCR task for comparison
- Update process_with_ocr to run comparison and keep the higher-quality text
- Add new settings to settings_service.py metadata
- Update docs/ConfigurationGuide.md with new settings
- Add comprehensive tests for new threshold and comparison logic

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

2026-02-25 13:03:21 +00:00

..

config_validator

feat: update all OpenAI/ChatGPT refs + settings dropdown for fixed-value fields

2026-02-23 20:06:57 +00:00

__init__.py

feat(storage): implement immutable original/processed file storage and collision handling

2026-02-11 20:10:19 +00:00

ai_provider.py

feat(ai): handle temperature incompatibility for gpt-5 and o-series models, add model picker UI

2026-02-23 22:12:08 +00:00

config_loader.py

fix(config): decrypt sensitive settings when loading from database

2026-02-23 12:54:34 +00:00

config_validator.py

test: increase coverage for imap_tasks.py and fix config_validator.py

2026-02-13 23:42:49 +00:00

encryption.py

feat: add strict mypy type-checking for app/utils/ module

2026-02-14 00:27:52 +00:00

file_operations.py

feat: add strict mypy type-checking for app/utils/ module

2026-02-14 00:27:52 +00:00

file_queries.py

fix(ocr): sync workflow steps with process_with_ocr replacing legacy azure step

2026-02-24 22:22:06 +00:00

file_splitting.py

refactor: consolidate linting tools into Ruff

2026-02-13 09:10:52 +00:00

file_status.py

fix(ocr): sync workflow steps with process_with_ocr replacing legacy azure step

2026-02-24 22:22:06 +00:00

filename_utils.py

feat: add strict mypy type-checking for app/utils/ module

2026-02-14 00:27:52 +00:00

input_validation.py

fix(api): return 200 with value=None for unknown setting keys in GET endpoint

2026-02-22 20:04:57 +00:00

logging.py

fix: include exc_info in log_task_progress debug message

2026-02-17 11:41:56 +00:00

migrate_logs_to_steps.py

refactor: consolidate linting tools into Ruff

2026-02-13 09:10:52 +00:00

notification.py

style: fix all flake8 linter errors across app/ directory

2026-02-08 17:42:33 +00:00

oauth_helper.py

style: fix all flake8 linter errors across app/ directory

2026-02-08 17:42:33 +00:00

ocr_language_manager.py

fix(ocr): ensure Tesseract language data for embed_text_layer regardless of active OCR provider

2026-02-24 18:02:19 +00:00

ocr_provider.py

fix(ocr): ensure Tesseract language data for embed_text_layer regardless of active OCR provider

2026-02-24 18:02:19 +00:00

settings_service.py

feat(ocr): fine-tune OCR quality criteria with stricter threshold and head-to-head comparison

2026-02-25 13:03:21 +00:00

settings_sync.py

feat(ocr): auto-install Tesseract/EasyOCR languages from settings

2026-02-24 16:28:14 +00:00

setup_wizard.py

feat: update all OpenAI/ChatGPT refs + settings dropdown for fixed-value fields

2026-02-23 20:06:57 +00:00

step_manager.py

fix(ocr): sync workflow steps with process_with_ocr replacing legacy azure step

2026-02-24 22:22:06 +00:00

step_timeout.py

fix: apply Phase 1-2 correctness and constant extraction from PR #273

2026-02-13 11:25:30 +00:00

text_quality.py

feat(ocr): fine-tune OCR quality criteria with stricter threshold and head-to-head comparison

2026-02-25 13:03:21 +00:00