| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
fix(slidea): improve OOXML SVG bullets and svg-to-pptx text geometry Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 3 天前 | |
refactor(slidea,deep_research): consolidate deep_research output layout Two related changes that pull deep_research artifacts from scattered locations into one per-run / per-session directory. 1. Per-invocation workspace_dir replaces module-level constant. core/deep_research/context.py used to compute WORKSPACE_DIR at import time as <output_root>/research_workspace — a shared directory that mixed artifacts from every invocation. Now each caller injects workspace_dir through LangGraph config['configurable']: - slidea's deep_research_node sets it to <run_dir>/research/ - scripts/run_deep_research.py sets it to <output_root>/<session_id>/ reporter_node's filename changes from {title[:30]}.md to fixed deep_report.md so slidea's cache-reuse check on <run_dir>/research/deep_report.md lines up without an extra copy. The separate save_text() in deep_research_node is dropped because reporter_node now writes directly to the right location. 2. Per-run sqlite checkpointer. Both run_deep_research.py and run_ppt_pipeline.py now write their LangGraph sqlite to <run_dir>/checkpointer.sqlite (deep_research: <session_id>/checkpointer.sqlite) instead of <output_root>/dr_db/ and the process CWD respectively. The CWD placement in run_ppt_pipeline.py was a latent bug — sqlite landed wherever the pipeline was launched from. The cleanup loop is unchanged; only the target path moves. Docs: - deep_research/SKILL.md: drop the dr_db cleanup guidance; document the per-session layout and the auto-cleanup of checkpointer on success. - slidea/SKILL.md: drop the db_data cleanup guidance — that directory never existed in code, only in docs. - caching-and-paths.md: directory tree now shows research/ as {research.json (simple) | deep_report.md + todo_*.txt (deep)} and the new checkpointer.sqlite entry; Cleaning Up section rewrites around the per-run sqlite. - staged-execution.md: distinguish simple/deep research outputs in the stage table. - deep_research/.env.example: add OUTPUT_DIR option — deep_research already consumed output_files_dir via the shared config module, this just surfaces the knob to users. Verified end-to-end: - deep_research standalone (Python GIL topic, ~8 min): deep_report.md and todo_*.txt land at <session_id>/, no research_workspace/, no dr_db/, checkpointer.sqlite cleaned on success. - slidea deep mode (Python GIL topic, ~5 min, 5-page PPTX): all deep research artifacts under <run_id>/research/, no stray sqlite in the skill install dir (latent CWD bug fixed). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> | 23 天前 | |
docs(slidea): relax chapter writing rule - format fits audience/topic Replace the rigid prose-first rule with audience/topic-driven format selection (prose/tables/lists as the reader needs), keeping richness non-negotiable. Rule 2 reworded from "multi-paragraph" to "fully developed". | 2 天前 | |
feat(slidea): flow document images into PPT + short-text doc shortcut Doc-processor: - short-text shortcut: when merged doc text < 3x chunk threshold and VLM off, write raw merged text directly to structured.md (short_circuit=True), skipping chunk/summary/outline/chapter-writing/review - image scoring replaces per-chapter placement: score_images_from_files() globally scores images vs topic+outline, writes top-30 doc_images.json (images no longer embedded in structured.md) - batch VLM image filtering (3/call) with single-image fallback - chunker max lowered 65536 -> 32768 - lazy makedirs: readers/engines create output_dir on first write, not in __init__, eliminating empty structured_md_* leftover dirs PPT pipeline: - new doc_image_pool module: global pool claimed atomically by page workers under single-threaded asyncio (snapshot + claim, one page per image) - get_content_pages_node loads doc_images.json, copies images into <save_dir>/images/, initialises the pool - get_final_images_node offers pool images to LLM selection and claims the picked ones - run_ppt_pipeline.py: --image-json copies doc_images.json into the run dir SKILL.md / process-doc.md updated to the new output contract (structured_md_path + short_circuit + doc_images) and weight-based chapter writing. | 2 天前 | |
slidea: init. Adding a fully open-source AI-powered PPT generation skill whose name is slidea Signed-off-by: JiangYifei <jiangyifei@huawei.com> Signed-off-by: WanBo <wanbo13@huawei.com> Signed-off-by: SuBo <subo7@huawei.com> Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> Signed-off-by: Bin Wu <wu.wubin@huawei.com> | 3 个月前 | |
slidea: init. Adding a fully open-source AI-powered PPT generation skill whose name is slidea Signed-off-by: JiangYifei <jiangyifei@huawei.com> Signed-off-by: WanBo <wanbo13@huawei.com> Signed-off-by: SuBo <subo7@huawei.com> Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> Signed-off-by: Bin Wu <wu.wubin@huawei.com> | 3 个月前 | |
feat(slidea): add reference PPTX style-pack workflow Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 8 天前 | |
feat(slidea): add reference PPTX style-pack workflow Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 8 天前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 3 天前 | ||
| 23 天前 | ||
| 2 天前 | ||
| 2 天前 | ||
| 3 个月前 | ||
| 3 个月前 | ||
| 8 天前 | ||
| 8 天前 |