Root cause: ~/.openclaw/skills/kb-workflow/kb_workflow.py used old
import paths (kb_pipeline.*) after v1.1 refactor renamed package to
kb_workflow.pipeline
Fix applied to external skill directory:
- Updated imports from kb_pipeline.* to kb_workflow.pipeline.*
- Fixed project_root path calculation
- Updated SKILL.md documentation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
9/9 core functions verified, but gaps found:
- 4 remaining sys.path manipulations
- Pipeline not exported at package level
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move kb_pipeline/ to kb_workflow.pipeline/
- Update all imports to use absolute paths
- 278 tests pass (14 pre-existing failures unrelated to refactoring)
- CLI works with new module structure
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add SUMMARY.md with 8 tests (5 unit + 3 integration)
- Update STATE.md: Phase 5 complete, advance to Phase 6
- Mark requirements OUT-01, OUT-02, OUT-03, OUT-04 complete
- Document test patterns and decisions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix test_workflow_skips_completed_steps to mock _ask_rerun_step
- Fix test_fetch_video_metadata_success to use AsyncMock
- Document other pre-existing test issues in deferred-items.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added intermediate_path config field with KB_INTERMEDIATE_PATH env var support
- Updated Pipeline to use configurable intermediate directory
- Updated CLI to default to intermediate_path instead of cwd
- Completed requirements: INT-01, INT-02, INT-03
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Update ROADMAP.md to include INT-03 (configurable intermediate path)
- Update 05-01 plan description to reflect INT-03 coverage
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add INT-03 requirement to 05-01-PLAN.md requirements field
- Add Task 1 for KB_INTERMEDIATE_PATH config in KBSettings
- Update Task 2 and Task 3 to use configurable path instead of hardcoded
- Update 05-CONTEXT.md to reflect new decision (config support vs hardcoded)
Addresses checker issue: requirement_coverage for INT-03
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Zhihu HTML structure includes noscript fallback images:
<figure><img data-actualsrc=...><noscript><img src=...></noscript></figure>
After fixing lazy-load (replacing src with data-actualsrc), both imgs
have real URLs, causing duplicates. The fix removes noscript tags before
processing img elements.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
All fixes verified working:
- Video download for videos without official subtitles
- Whisper transcription with correct offset parsing
- Text extraction from Whisper JSON format
- End-to-end analysis with real video content
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- When content_type is video and no official subtitle available:
- Download video using yt-dlp
- Extract audio for Whisper fallback
- Update content_file with actual video path
This enables the pipeline to handle videos that don't have
official Bilibili subtitles.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause: BilibiliExtractor sync wrappers use asyncio.run() internally,
which fails when called from async context in BilibiliAdapter.
Fix: Call async methods directly instead of sync wrappers.
Verified: Human confirmed fix works (bilibili_BV16cNMzpExh)
- Archive ROADMAP and REQUIREMENTS to milestones/
- Delete original ROADMAP.md and REQUIREMENTS.md
- Update PROJECT.md with v1.0 validated requirements
- Update STATE.md for milestone complete status
- Update MILESTONES.md with key accomplishments
- Add VERIFICATION.md for phase 04
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- AnalyzeProcessor wraps DeepAnalyzer for AI-powered content analysis
- Analysis reports saved as Markdown with YAML frontmatter
- All 15 tests passing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- BaseProcessor abstract class with unified interface
- ParseProcessor wrapping LinkParser for URL parsing
- ParseInput/ParseOutput schemas for parse step
- All tests passing (18 tests)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
starmen1265