panda 1210b926c3 fix: MAX_RETRY 5 + rolling continuation + namespace-aware JRXML extraction ...

- MAX_RETRY: 3→5 (graph.py:35, nodes.py:25) with env override
- Rolling continuation: _generate_with_continuation() auto-detects
  truncated JRXML and sends anchor-based continuation, max 3 rounds
- JRXML extraction: regex/end-tag now namespace-prefix aware
  (ns0:jasperReport, ns:jasperReport, etc.)
- All 5 generation nodes refactored to use continuation helper
- Tests updated: scenario1 accepts ns-prefixed root, max_retry
  verifies graph termination
- stop_reason capture + WARNING log on max_tokens truncation
- Correction prompt now injects OCR context + layout schema

2026-05-23 10:58:46 +08:00

..

__init__.py

feat: Streamlit多轮对话界面 + 集成测试

2026-05-14 23:21:22 +08:00

test_agent.py

fix: MAX_RETRY 5 + rolling continuation + namespace-aware JRXML extraction

2026-05-23 10:58:46 +08:00

test_annotation_detector.py

feat: v4 multimodal chat input, multi-format support, and annotation detection

2026-05-20 23:43:16 +08:00

test_api_integration.py

fix: address audit findings — session_id validation, streaming reset, state isolation

2026-05-23 09:08:53 +08:00

test_e2e_ocr.py

fix: logging KeyError with reserved 'filename' key, pytest return-not-none warnings

2026-05-21 22:28:07 +08:00

test_error_kb.py

test: add unit/integration/E2E test suites, fix create_session bug, update docs

2026-05-23 08:38:29 +08:00

test_file_parser_formats.py

feat: v4 multimodal chat input, multi-format support, and annotation detection

2026-05-20 23:43:16 +08:00

test_layered_generation.py

feat: layered precise generation for A4 report images

2026-05-21 08:34:32 +08:00

test_ocr_extraction.py

feat: 新增 OCR 单据字段精确提取模块

2026-05-20 08:06:55 +08:00

test_session.py

fix: address audit findings — session_id validation, streaming reset, state isolation

2026-05-23 09:08:53 +08:00

test_validation.py

feat: Streamlit多轮对话界面 + 集成测试

2026-05-14 23:21:22 +08:00