- Taxonomy sync keeps fig-/feat- by slug (hyphen), not name; HTML-unescape names
- Review: remove AI assist labels; Features picker for feat-*; derive fig_tag_ids
from Figure term names (casefold match, no bridges); decodeName on display
- Unit tests for scoped_tags, fig match, Review UI contract; docs slug wording
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).
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.
Docs written before this thread still carried the three-source copy model and
the Call 2 fields it implied.
- REQUIREMENTS.md REVIEW-10: title and short description are deterministic; the
description comes from the model or the server.
- CREATE.md: primary category declared before Call 2; deterministic copy; the
prompt revision interface; the slug; auth row in out-of-scope.
- API.md: infer-content inputs and result are the long description only.
- UAT-PRACTICE.md: the walk no longer tells the owner to leave copy for
templates.
- README.md: the deploy section duplicated docs/DEPLOYMENT.md and
deploy/INVENTORY.md; it now points at them.
- DEPLOYMENT.md: the prompt seed is stated per METADATA-105.
Both gates pass.
UAT requires prompt tuning, so the iteration system is M3; only the editing
UI is deferred.
- METADATA-105 now covers storage, append-only revisions, and recording the
revision used.
- METADATA-106 adds the REST revision interface (append, activate, read); no
prompt UI.
- METADATA-107 records the missing authentication as a later row; there is no
M4 yet, so the PoR carries it.
- PROMPTS.md owns the seed text as revision 0, the seed mechanism, and the
interface; sections renumbered after inserting them.
- DATA-MODEL.md §7 cites PROMPTS.md, adds content_hash, and states the
append-only rule.
- task_breakdown.md notes the S7 interface and the deferred auth.
155 requirements; both gates pass.
METADATA was ordered as it was written, not by topic, and used Call 1 /
Call 2 without defining them.
- Add a short METADATA preamble stating the inference flow: Call 1 vision
proposes taxonomy, the name and short description are deterministic, Call 2
writes the long description.
- Regroup the rows: taxonomy, then Call 1, then deterministic copy, then
Call 2, then cross-cutting.
- METADATA-70 said the deterministic name and short description were an
inference-off fallback; they are unconditional. It now covers only the
inference-off description.
- METADATA-81 folded into METADATA-80 (same rule, two strings).
- METADATA-45 now names the below-threshold outcome.
- METADATA-90 now states what the fact block drives.
153 requirements; check_requirements and check_coverage both pass.
Encode the recovered per-leaf title/short-description rule and the Call 2
input set into the point of record.
- REQUIREMENTS.md: METADATA-55 now produces the description only; METADATA-60
carries the ruled input set; METADATA-80 is the deterministic title; new
METADATA-81 is the deterministic spec-line short description; METADATA-85
selects the patterns; REVIEW-15 declares the primary before Call 2;
PUBLISH-55 carries an explicit name+SKU slug.
- CONTENT-WOO.md: per-leaf title and short-description catalog, slot order,
dimension placement, and the Cook Woods provenance.
- PROMPTS.md: Call 2 inputs and output; the deterministic patterns are cited,
not restated.
- CREATE.md, WOO-API.md, MILESTONES.md, task_breakdown.md updated to match.
Modeled on Cook Woods product-title form; the seven per-leaf prose templates
and Specialty cuts are parked in the M3 breakdown.
- R1 soft delete: add deleted_at to slabs; exclude deleted rows from GETs
- R2 publish: terminal poll returns woo_product_id then the working row is
discarded; the app never deletes from WooCommerce (reworks PUBLISH-25)
- R3 prompts: SQLite is the point of record; file-based prompts superseded,
compose prompt mount removed
- R4 images: photo bytes are SQLite BLOBs; /images is a health probe + staging
Details recorded in .audit/m3-build-plan.md.
- PUBLISH: attempt-level failure wording, no image cap, failure triage rows
- METADATA: title rule is fallback-only (Call 2 not run)
- REVIEW: calculated widths/sqft/bdft not user mutable
- IDs now step by 5 per namespace; rule recorded in STRUCTURE.md
Reconciles the scattered requirements onto the owner-job namespaces.
- docs/REQUIREMENTS.md: 128 requirements across CAPTURE, METADATA, REVIEW,
PUBLISH, SETTINGS, APP, OPS, QUALITY
- docs/STRUCTURE.md: Test may be a path, a requirement ID, or - ;
a shipped path must exist
- tools/check_requirements.py: resolve test refs accordingly
- .audit/2026-09-18-reconciliation-decisions.md: full decision record plus
18 deferred rulings for the final cleanup pass
Gate: python tools/check_requirements.py -> PASS
grokbot_ty
Ty