panda
bb6cc6e241
feat: add Java JRXML-to-PNG rendering pipeline with pixel-level SSIM comparison
...
- lib/java/: Java renderer (JrxmlRenderer) using JasperReports 6.21.0
- JrxmlDebug for diagnostics, JrxmlGen for format reference
- download_jars.sh for one-time dependency setup
- agent/nodes.py: _render_jrxml_to_png() and _compute_pixel_similarity()
- Pixel comparison integrates into validate node (SSIM < 0.4 fails)
- Pixel fidelity context injected into correct_jrxml for targeted fixes
- tests/test_pixel_comparison.py: 15 unit tests (render, SSIM, integration)
- .gitignore: exclude lib/java/*.jar, lib/java/*.class, tmp/
- CLAUDE.md: v11 changelog documenting the rendering pipeline
- All non-LLM tests pass (97/97)
2026-05-23 15:09:55 +08:00
panda
9de75d2f25
fix: escape $F{field_N} in correction.md to prevent Python format KeyError
...
$F{field_N} was being parsed by str.format() as a replacement field,
causing KeyError and crashing correct_jrxml node.
Changed to $F{{field_N}} (double braces -> literal brace in output).
2026-05-23 11:27:31 +08:00
panda
23cdfa8c2b
fix: map_fields empty-retry + correction prompt field_N guidance
...
- map_fields: retry with simplified prompt on empty LLM response
- correction.md: add explicit guidance for undeclared field_N errors
(add <field> declarations + try OCR name replacement)
- MAX_RETRY=5 now effective (was overridden by .env:3)
2026-05-23 11:15:09 +08:00
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
panda
4dfc418fc5
fix: escape {field_N} braces in prompt templates to prevent .format() KeyError
...
$F{field_1} literal text in skeleton_generation/refine_layout/field_mapping
prompts was being parsed as Python .format() placeholder, causing KeyError
on every image-based initial_generation request. Escaped with double braces
so .format() outputs literal {field_1} for the LLM.
2026-05-22 08:12:56 +08:00
panda
43a0542a11
feat: layered precise generation for A4 report images
...
3-phase pipeline to solve LLM prompt overflow from too many OCR elements:
Phase 1 (generate_skeleton): compressed layout schema → skeleton JRXML
Phase 2 (refine_layout): sampled coordinates → pixel-level position tuning
Phase 3 (map_fields): OCR field names → replace $F{field_N} placeholders
Only triggered when layout_schema.total_rows > 0 on initial_generation intent.
Text requests and all other intents are unaffected (zero behavior change).
2026-05-21 08:34:32 +08:00
panda
9bb011e429
feat: v4 multimodal chat input, multi-format support, and annotation detection
...
- Replace st.chat_input with st-multimodal-chatinput (Ctrl+V paste, drag-drop, file button)
- Extract _process_uploaded_file() shared handler (eliminates ~70 duplicated lines)
- Add XLSX (openpyxl), XLS (xlrd), DOC (olefile) parsers to file_parser.py
- Add backend/annotation_detector.py: circle detection (HoughCircles) + arrow detection (HoughLinesP clustering) + OCR correlation + LLM context formatting
- Add annotation_result field to AgentState with session persistence
- Wire annotation detection into process_input and _format_ocr_context
- Add 11 new tests: 7 annotation detector + 4 multi-format parser
- Update all docs: CLAUDE.md, README.md, CODE_GUIDE.md, ROADMAP.md
2026-05-20 23:43:16 +08:00
panda
70614dff5e
feat: comprehensive v2 upgrade — streaming, error KB, file upload, layout analysis
...
Major changes:
- Streaming: LLM统一 _BaseLLM 接口 (invoke + stream), generate/modify/correct
节点使用 get_stream_writer() 实现逐字输出, UI 节点平铺展开自动折叠
- Prompt外部化: 7个prompt拆分到 prompts/*.md, loader.py 支持热重载
- 错误自增长: backend/error_kb.py — 指纹去重 + ChromaDB持久化,
correct_jrxml→validate 通过时自动入库, retrieve同时搜索错误KB
- 文件上传: backend/file_parser.py — PDF/DOCX/图片/文本解析,
侧边栏多文件上传, 文本自动注入下一条消息
- A4模板识别: backend/layout_analyzer.py — 三种模式(完整A4/行片段修改/行片段新建),
PaddleOCR元素提取 + 行分组 + JRXML section匹配
- 会话历史下载: jrxml_versions版本追踪 + 侧边栏历史版本下载按钮
- 预览修复: route_after_save跳过预览/导出意图的验证循环
- Ctrl+C修复: JS注入拦截Streamlit裸c键清缓存
Docs: CLAUDE.md (完整项目文档), ROADMAP.md (改进路线图)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-19 15:02:53 +08:00
panda