justin/morpheus-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
17 Commits 2 Branches 0 Tags
b31121d90c4e0f7f7ac11f50d36ac1d8a00c84e7
Commit Graph
3 Commits
Author SHA1 Message Date
claudeandClaude Opus 4.8 b31121d90c fix(scrape): make vision OCR a per-bundle allowlist, not a corpus sweep 
The first vision pass OCR'd every large image and, because the "transcribe
the table" prompt makes qwen render ANY image as a markdown table, it turned
60 product UI screenshots into junk "tables" in the corpus. In practice the
only image-only DATA in this corpus is the release-schedule matrix — the
upgrade-compatibility matrices etc. are already native HTML tables, no OCR
needed.

- Add BundleSpec.ocr (default False); the runner passes the OCR-enabling
  session only for bundles that opt in. Set ocr=True only on
  morpheus_release_schedule.
- Purge the 60 screenshot cache entries (keep the release-schedule one). The
  next --force refresh regenerates every other page's .md WITHOUT the bogus
  "## Image transcriptions" section, cleaning the deployed corpus + index.
- Update vision.py / refresh.yml docs to the allowlist model.

Also add scripts/vision_report.py — a self-contained HTML report pairing each
OCR'd source image with its transcription (uncertain-first) for accuracy
inspection. Regenerate anytime from corpus/.vision-cache/.

Verified: release schedule still transcribes (cache hit); cache is back to 1
entry; other bundles now pass no session so their images are left alone.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
Claude-Session: https://claude.ai/code/session_01LFowQzJu7k97QLCRDSAeh1
 2026-07-23 13:31:09 -04:00
hvm-docs-refresh 6686b033e6 weekly refresh: 2026-07-23T14:45Z — 156 content change(s) across 4 bundle(s) 
156 content change(s) across 4 bundle(s)
60 sidecar metadata update(s)

Bundles with content changes:
  morpheus_user_manual_8_1_0: 39 page(s)
    - GUID-06F0DB01-64F2-4D07-93F8-38AC80DBB09B
    - GUID-0A5AD977-07F5-4278-9CB3-F7D8AB8427A3
    - GUID-173469C2-D5C6-47F6-8A01-41C3D73B679B
    - GUID-180B8370-AEF2-45C1-9E72-99FF796CB222
    - GUID-2277183A-E315-4439-A885-C111A77C7154
    ... and 34 more
  morpheus_user_manual_8_1_1: 39 page(s)
    - GUID-06F0DB01-64F2-4D07-93F8-38AC80DBB09B
    - GUID-0A5AD977-07F5-4278-9CB3-F7D8AB8427A3
    - GUID-173469C2-D5C6-47F6-8A01-41C3D73B679B
    - GUID-180B8370-AEF2-45C1-9E72-99FF796CB222
    - GUID-2277183A-E315-4439-A885-C111A77C7154
    ... and 34 more
  morpheus_user_manual_8_1_2: 39 page(s)
    - GUID-06F0DB01-64F2-4D07-93F8-38AC80DBB09B
    - GUID-0A5AD977-07F5-4278-9CB3-F7D8AB8427A3
    - GUID-173469C2-D5C6-47F6-8A01-41C3D73B679B
    - GUID-180B8370-AEF2-45C1-9E72-99FF796CB222
    - GUID-2277183A-E315-4439-A885-C111A77C7154
    ... and 34 more
  morpheus_user_manual_9_0_0: 39 page(s)
    - GUID-06F0DB01-64F2-4D07-93F8-38AC80DBB09B
    - GUID-0A5AD977-07F5-4278-9CB3-F7D8AB8427A3
    - GUID-173469C2-D5C6-47F6-8A01-41C3D73B679B
    - GUID-180B8370-AEF2-45C1-9E72-99FF796CB222
    - GUID-2277183A-E315-4439-A885-C111A77C7154
    ... and 34 more

Bundles with sidecar-only drift (1): .vision-cache
 2026-07-23 14:45:49 +00:00
claude 698196bd63 feat(scrape): vision OCR of image-only doc pages (support matrices) (#5) 
Co-authored-by: claude <[email protected]>
 2026-07-23 09:48:38 -04:00