| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
refactor(slidea): bundle llm_invoke/vlm_invoke options and tidy lint findings - Introduce InvokeOptions dataclass to group optional invoke params (config / pydantic_schema / json_schema / work_node); migrate ~30 call sites across ppt_thought, page_generators, svg_page_generators, deep_research, outline_generator, utils, and ci/review. - Rewrite scripts/pixel_diff.py and scripts/verify_font_fallback.py to route output through logging and use PYTHONPATH for the worker subprocess instead of sys.path.insert. - Wrap overlong lines in preflight.py, test_pipeline_contracts.py, test_preflight.py, and test_llm_routing.py. - Add targeted pylint: disable=protected-access to test sites that intentionally probe private helpers. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> | 1 个月前 | |
docs(slidea): confine HTML route info to README; silence agent-facing surfaces Host agents were surfacing LibreOffice/Playwright in their run summaries even on the default SVG route, because the terms appeared across docs/, skill/INSTALL.md, and the installer's stdout — all of which the agent reads at runtime. The "do not mention HTML route" line in SKILL.md could not outweigh two dozen other files talking about it in detail. - Strip HTML-route sections from docs/quickstart, architecture, cli, core/ppt-generator, svg-route, and docs/README.md. - Trim skill/slidea/INSTALL.md and UPDATE.md to SVG-only flow; remove the leftover --skip-playwright/--skip-libreoffice flags from the deep_research INSTALL command template (default behavior now). - Silence the two skipped-step lines (Install Playwright Chromium, Check LibreOffice) and the RHEL-family info log in install.py's default SVG-only path; --with-html-route output is unchanged. - Flip the two install tests that asserted the old "should mention Step 3/4/RHEL helper" behavior to assert silence instead. - Expand README.md / README_CN.md HTML route section with a per-platform matrix of what --with-html-route does and a RHEL-family helper callout, since README is now the single source of truth for HTML route info. Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 28 天前 | |
feat(slidea): resolve session_id to run_id for CLI continuation Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 19 小时前 | |
optimize slidea skills directories structure Signed-off-by: SuBo <subo7@huawei.com> | 1 个月前 | |
fix(slidea): resolve gate issues for SVG export Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 2 个月前 | |
feat(slidea): resolve session_id to run_id for CLI continuation Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 19 小时前 | |
refactor(slidea): bundle llm_invoke/vlm_invoke options and tidy lint findings - Introduce InvokeOptions dataclass to group optional invoke params (config / pydantic_schema / json_schema / work_node); migrate ~30 call sites across ppt_thought, page_generators, svg_page_generators, deep_research, outline_generator, utils, and ci/review. - Rewrite scripts/pixel_diff.py and scripts/verify_font_fallback.py to route output through logging and use PYTHONPATH for the worker subprocess instead of sys.path.insert. - Wrap overlong lines in preflight.py, test_pipeline_contracts.py, test_preflight.py, and test_llm_routing.py. - Add targeted pylint: disable=protected-access to test sites that intentionally probe private helpers. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> | 1 个月前 | |
feat(slidea): preserve reusable style-pack image assets Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 6 天前 | |
feat(deep_research): align standalone run directories with slidea | 19 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. | 5 小时前 | |
fix(slidea): sanitize svg_to_pptx.py -n so Phase 3 re-export overwrites run_ppt_pipeline.py calls svgs_to_pptx(..., sanitize_filename(topic)) which converts spaces to underscores and strips illegal chars. The svg_to_pptx.py CLI, however, passed -n verbatim to svgs_to_pptx() without sanitizing. So when Phase 3 re-export ran with "-n <topic from ppt.json>", the new PPTX got a different filename (spaces preserved) than the original pipeline wrote (spaces underscored), and both files ended up coexisting in the run dir. ppt.json still pointed at the old file, so the user opened the unchanged PPTX and the edit appeared lost. Fix: apply sanitize_filename to args.filename in svg_to_pptx.py main(), exactly mirroring the pipeline. Idempotent for already-clean names, so no caller breaks. Doc updates in agent-edit.md Step 10: - Make explicit that <topic> is passed verbatim and the exporter sanitizes it (was wishful thinking before, now actually true) - Warn against pre-sanitizing -n (would double-transform) - Clarify the output path is <sanitized_topic>.pptx Also tightened the -n help text in svg_to_pptx.py to self-document the auto-sanitization. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> | 14 天前 | |
feat(slidea): preserve reusable style-pack image assets Signed-off-by: Zhukunpeng <zhukunpeng8@huawei.com> | 6 天前 | |
refactor(slidea): bundle llm_invoke/vlm_invoke options and tidy lint findings - Introduce InvokeOptions dataclass to group optional invoke params (config / pydantic_schema / json_schema / work_node); migrate ~30 call sites across ppt_thought, page_generators, svg_page_generators, deep_research, outline_generator, utils, and ci/review. - Rewrite scripts/pixel_diff.py and scripts/verify_font_fallback.py to route output through logging and use PYTHONPATH for the worker subprocess instead of sys.path.insert. - Wrap overlong lines in preflight.py, test_pipeline_contracts.py, test_preflight.py, and test_llm_routing.py. - Add targeted pylint: disable=protected-access to test sites that intentionally probe private helpers. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> | 1 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 1 个月前 | ||
| 28 天前 | ||
| 19 小时前 | ||
| 1 个月前 | ||
| 2 个月前 | ||
| 19 小时前 | ||
| 1 个月前 | ||
| 6 天前 | ||
| 19 天前 | ||
| 5 小时前 | ||
| 14 天前 | ||
| 6 天前 | ||
| 1 个月前 |