Ty_Tech/SlabUploader
6
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity
264 Commits 9 Branches 0 Tags
1ff082f77cf03a29a9177d168b8893a4793f77b3
Commit Graph

6 Commits

Author SHA1 Message Date
grokbot_ty 1ff082f77c feat(review): View prompt + Call 2 declared attrs, Create-desc gate 
Shared assemble_call2 for GET .../call2/prompt and POST call2 (seed +
DECLARED ATTRIBUTES + dimension fact + brand/geo; photo slots without
base64). Create desc disabled until content LLM + title/short + species +
wood cats/primary + edge + ≥1 figure + grade + moisture + price; show
missing. figure_term_ids required for ready. Moisture defaults to Kiln
dried (kd). Pin snl / liveedge in wood-cat UI. Ready-on-change via
MultiSelect onCommit.
 2026-09-26 10:11:50 -07:00
grokbot_ty 087557f89f chore(inference): disable Call 1 end-to-end; Call 2 stays 
overnight-whole-app: Call 1 (vision classification) is OUT.
- POST /api/v1/slabs/{id}/inference/call1 always returns 410 call1_disabled
  (no model chat, no inference_log). Prompt seed/revision APIs kept dormant.
- Review: remove "Suggest with AI" / runInference (inferTaxon).
- GenerateText: remove Classify metadata (Call 1) button; Call 2 generate stays.
- PROMPTS.md banner documents Call 1 OUT / Call 2 STAYS.
- Settings: inference_enabled toggle annotated as Call-1 latch (dormant).
- Backend tests updated to assert 410; Call 2 tests unchanged.
 2026-09-25 17:46:39 -07:00
Ty 41401a7266 fix(inference): #87 redact image bytes from inference_log 
Log full text + image_ref (photo_id/seq/bytes) only; wire path still
sends data-URLs. Call 1/2 SELECT id+seq for refs. Cap is safety net
after redaction (METADATA-66).
 2026-09-20 23:01:38 -07:00
Ty 7287a55707 fix(inference): #86 tighten Call 1 prompt and closed lists 
Ship locked expert Call 1 seed: order cats before edge, species=best
confidence, mill-count edge rules, Wild for cookies/burl, multi figure,
feature_tag_ids only (no free-text bags, no grade). LISTS keys match the
seed; feat- prefix stripped for the model. Gate and review UI apply
feature_tag_ids. Seed auto-activates on deploy when still seed-authored.
 2026-09-20 22:54:36 -07:00
Ty 81be17d5cd fix(inference): METADATA-35 fit Call 1/2 images to 1024 long edge 
Downscale processed PNGs only on the inference send path (keep alpha, never
upscale). Stored inventory/Woo blobs unchanged. Adds Pillow + unit/e2e-style
tests; cite tests on METADATA-35.
 2026-09-20 22:32:14 -07:00
Ty 8a8a89ed3e feat(inference): S7 Call 1/Call 2 + prompt revision REST + test-inference + Generate text UI 
- backend/inference.py: prompt seed (rev 0) + append-only revision REST
  (POST /prompts/{call}/revisions, /activate, GET; METADATA-105/106). Call 1 vision
  classification (1024px processed photos + synced taxonomy, 0.7 confidence gate,
  METADATA-35/40/45), Call 2 long description (user-triggered, METADATA-55/60/65),
  inference_log per call (METADATA-66), inference-off server_description (METADATA-70),
  test-inference probe (SETTINGS-45). Stdlib urllib, no new deps.
- frontend: create/inference/GenerateText.svelte (control visible only when content
  enabled + endpoint reachable, METADATA-110; Call 2 + Call 1 buttons) + dev toggle.
- tests: 6 inference tests (seed+revision, call1 gate, call2 stores desc, off->409,
  server desc, test-inference unconfigured).

Verified: pytest 54 passed; gates exit 0; npm build ok.
 2026-09-19 17:04:01 -07:00