Ty_Tech/SlabUploader
6
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity

Docs: Call 1 must pre-populate review attributes, tags, and categories #8

New Issue
Closed
opened 2026-09-01 22:06:00 +00:00 by Ty · 3 comments
Ty commented 2026-09-01 22:06:00 +00:00
Owner
Copy Link
Copy Source

On main, the intended workflow is that the first inference call (Call 1) pre-populates the review screen's attributes, tags, and categories so the user mostly confirms rather than types. The refactor branch's ARCHITECTURE swimlane and clarifications still show Call 1 results landing in P7 as "Review Call 1 fields," but CONTENT-WOO.md's auto-assign section only describes deterministic name-matching for categories/tags/attributes and does not explicitly state that Call 1's vision results are the primary pre-population source for species, character, fig/feat tags, and the five locked attributes.

Please make the docs explicit: when inference is enabled, Call 1 results pre-fill species, character, tags, and attributes (with confidence); the user overrides in review; manual entry remains authoritative. Keep Call 1 assist-only and non-gating.

On main, the intended workflow is that the first inference call (Call 1) pre-populates the review screen's attributes, tags, and categories so the user mostly confirms rather than types. The refactor branch's ARCHITECTURE swimlane and clarifications still show Call 1 results landing in P7 as "Review Call 1 fields," but CONTENT-WOO.md's auto-assign section only describes deterministic name-matching for categories/tags/attributes and does not explicitly state that Call 1's vision results are the primary pre-population source for species, character, fig/feat tags, and the five locked attributes. Please make the docs explicit: when inference is enabled, Call 1 results pre-fill species, character, tags, and attributes (with confidence); the user overrides in review; manual entry remains authoritative. Keep Call 1 assist-only and non-gating.
Ty added this to the POC milestone 2026-09-01 23:49:49 +00:00
Ty commented 2026-09-03 02:20:05 +00:00
Author
Owner
Copy Link
Copy Source

The docs on refactor-v2 correctly state that Call 1 pre-populates review fields and that manual entry is authoritative. However, the same rule is repeated in 7 places (AGENTS, ARCHITECTURE, CONTENT-WOO, UX, PROMPTS, IMPL-PLAN, OPENAPI). This needs a cleanup pass to consolidate into a single canonical owner with references elsewhere. The issue cannot close until the duplication is resolved. See issue #5 comment for the pattern.

The docs on refactor-v2 correctly state that Call 1 pre-populates review fields and that manual entry is authoritative. However, the same rule is repeated in 7 places (AGENTS, ARCHITECTURE, CONTENT-WOO, UX, PROMPTS, IMPL-PLAN, OPENAPI). This needs a cleanup pass to consolidate into a single canonical owner with references elsewhere. The issue cannot close until the duplication is resolved. See issue #5 comment for the pattern.
Ty commented 2026-09-03 02:48:48 +00:00
Author
Owner
Copy Link
Copy Source

Consolidation complete. All duplicates replaced with references to CONTENT-WOO §2.3.

Changes:

  • AGENTS §6: replaced confidence rule with "Confidence gating: see CONTENT-WOO §2.3"
  • ARCHITECTURE §3.4: replaced confidence rule with "Call 1 prefill behavior: docs/CONTENT-WOO.md §2.3"
  • DATA-MODEL ready status: replaced with "Call 1 prefill per CONTENT-WOO §2.3"
  • UX.md: replaced "If vision is on..." paragraph with "Call 1 prefill behavior: see CONTENT-WOO §2.3"
  • IMPL-PLAN Phase 3: replaced Call 1 UI description with "Call 1 prefill per CONTENT-WOO §2.3"
  • IMPL-PLAN Phase 5: replaced gate description with "Call 1 prefill per CONTENT-WOO §2.3"
  • OPENAPI POST /slabs: replaced persistence note with "Call 1 persistence per CONTENT-WOO §2.3"
  • PROMPTS Notes: replaced full confidence gate with "Confidence gating: see CONTENT-WOO §2.3"

Test cases needed once implementation exists:

  1. Call 1 prefill >= 0.7 — Call 1 returns taxonomy with confidence >= 0.7; review fields are pre-populated; fields are mutable and overridable.
  2. Call 1 empty < 0.7 — Call 1 returns taxonomy with confidence < 0.7; review fields start empty; user must fill manually.
  3. Manual entry authoritative — user overrides a pre-filled value; the override sticks.
  4. Inference OFF — full manual taxonomy and content path works; no inference network calls are made.
Consolidation complete. All duplicates replaced with references to CONTENT-WOO §2.3. Changes: - AGENTS §6: replaced confidence rule with "Confidence gating: see CONTENT-WOO §2.3" - ARCHITECTURE §3.4: replaced confidence rule with "Call 1 prefill behavior: docs/CONTENT-WOO.md §2.3" - DATA-MODEL ready status: replaced with "Call 1 prefill per CONTENT-WOO §2.3" - UX.md: replaced "If vision is on..." paragraph with "Call 1 prefill behavior: see CONTENT-WOO §2.3" - IMPL-PLAN Phase 3: replaced Call 1 UI description with "Call 1 prefill per CONTENT-WOO §2.3" - IMPL-PLAN Phase 5: replaced gate description with "Call 1 prefill per CONTENT-WOO §2.3" - OPENAPI POST /slabs: replaced persistence note with "Call 1 persistence per CONTENT-WOO §2.3" - PROMPTS Notes: replaced full confidence gate with "Confidence gating: see CONTENT-WOO §2.3" Test cases needed once implementation exists: 1. **Call 1 prefill >= 0.7** — Call 1 returns taxonomy with confidence >= 0.7; review fields are pre-populated; fields are mutable and overridable. 2. **Call 1 empty < 0.7** — Call 1 returns taxonomy with confidence < 0.7; review fields start empty; user must fill manually. 3. **Manual entry authoritative** — user overrides a pre-filled value; the override sticks. 4. **Inference OFF** — full manual taxonomy and content path works; no inference network calls are made.
grokbot_ty commented 2026-09-24 16:22:21 +00:00
Owner
Copy Link
Copy Source

Closed: resolved along the way to M3. Docs now reflect Call 1 as the primary pre-population source.

Closed: resolved along the way to M3. Docs now reflect Call 1 as the primary pre-population source.
Sign in to join this conversation.
docs/refactor-v2
Branches Tags
Labels
Clear labels
blocking
Blocks POC acceptance; must be resolved before merge
 docs
Documentation change required
 gate-b
Gate B sprint issue
 gate-c
Gate C sprint issue
 gc-seq-01
Serial order 01/6 in Gate C sprint
 gc-seq-02
Serial order 02/6 in Gate C sprint
 gc-seq-03
Serial order 03/6 in Gate C sprint
 gc-seq-04
Serial order 04/6 in Gate C sprint
 gc-seq-05
Serial order 05/6 in Gate C sprint
 gc-seq-06
Serial order 06/6 in Gate C sprint
 poc
POC post-Gate-C issue
 poc-seq-01
Serial order 01 in POC sprint
 poc-seq-02
Serial order 02 in POC sprint
 poc-seq-03
Serial order 03 in POC sprint
 poc-seq-04
Serial order 04 in POC sprint
 poc-seq-05
Serial order 05 in POC sprint
 poc-seq-06
Serial order 06 in POC sprint
 poc-seq-07
Serial order 07 in POC sprint
 poc-seq-08
Serial order 08 in POC sprint
 poc-seq-09
Serial order 09 in POC sprint
 poc-seq-10
Serial order 10 in POC sprint
 poc-seq-11
Serial order 11 in POC sprint
 poc-seq-12
Serial order 12 in POC sprint
 poc-seq-13
Serial order 13 in POC sprint
 poc-seq-14
Serial order 14 in POC sprint
 poc-seq-15
Serial order 15 in POC sprint
 poc-seq-16
Serial order 16 in POC sprint
 poc-seq-17
Serial order 17 in POC sprint
 poc-seq-18
Serial order 18 in POC sprint
 poc-seq-19
Serial order 19 in POC sprint
 poc-seq-20
Serial order 20 in POC sprint
 post-launch
Deferred to post-launch / V1.5+
 seq-01
Serial order 1/10 in Gate B sprint
 seq-02
Serial order 2/10 in Gate B sprint
 seq-03
Serial order 3/10 in Gate B sprint
 seq-04
Serial order 4/10 in Gate B sprint
 seq-05
Serial order 5/10 in Gate B sprint
 seq-06
Serial order 6/10 in Gate B sprint
 seq-07
Serial order 7/10 in Gate B sprint
 seq-08
Serial order 8/10 in Gate B sprint
 seq-09
Serial order 9/10 in Gate B sprint
 seq-10
Serial order 10/10 in Gate B sprint
No Label
Milestone
No items
No Milestone POC
Projects
Clear projects
No project
Assignees
Clear assignees
HA_Architect HA_Researcher Ty grokbot_ty grokbuild_ty tonyjbala (Tony Balascio)
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Ty_Tech/SlabUploader#8
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?