chore_ubi_hybrid_template_render: chore_ubi_hybrid_template_render — resolve the vestigial hybrid template requirement

[SoundMindsAI]

Why

Date: 2026-05-29 (revised after analysis)
Status: Idea — contract decision deferred (NOT a worker bug)
Origin: GPT-5.5 PR #317 final-review finding #6 flagged that the hybrid
LLM-fill worker uses adapter.get_document rather than rendering
current_template_id + search_batch. On analysis (during the
chore_ubi_e2e_suite work), this is not a bug — see below.
Depends on: feat_ubi_judgments shipped
Priority: P3 (cosmetic contract cleanup; current behavior is correct)

Status

• Stage: IDEA
• Priority: P3 (cosmetic contract cleanup; current behavior is correct)

What this is

Not a bug — a deferred contract decision (P3). current_template_id is REQUIRED when converter == "hybrid_ubi_llm" (backend/app/api/v1/schemas.py:1548-1556), but the hybrid LLM-fill worker never uses it for retrieval — it scores the exact sparse (query, doc) pairs UBI surfaced via adapter.get_document (backend/workers/judgments_ubi.py:245), which is correct per the per-pair FR-2 callback contract. The template field is kept only for lineage/FK parity, so it is vestigial for the hybrid path.

Definition of done (if picked up)

• Drop the current_template_id requirement for the hybrid converter (keep rubric required) across CreateJudgmentListFromUbiRequest + GenerateJudgmentsFromUbiArgs + the generate-judgments dialog + the hybrid-conditional tests/E2E
• Correct the spec FR-3 prose that implies hybrid renders a template
• Product call on the operator flow first — deferred until an operator signal asks for it

Artifacts

• Idea: docs/00_overview/planned_features/02_mvp2/chore_ubi_hybrid_template_render/idea.md

How to execute

1. Preflight the idea against the current codebase (catches stale file/line references, obsolete deferral rationale, drifted dependencies):

   /idea-preflight docs/00_overview/planned_features/02_mvp2/chore_ubi_hybrid_template_render/idea.md
   

   The skill applies patches in-place; review with git diff after it runs.

2. Run the full pipeline autonomously (spec → plan → implement → PR):

   /pipeline docs/00_overview/planned_features/02_mvp2/chore_ubi_hybrid_template_render --auto
   

   --auto skips inter-stage approval pauses but keeps all hard quality gates (cross-model review via GPT-5.5 in spec-gen + impl-plan-gen, per-story verification gates, test coverage audit, CI watch, Gemini adjudication, final cross-model review). The PR is opened but NOT merged — you merge it manually after review.

3. If you don't want full autonomy, drop the --auto flag — the pipeline will pause for approval between each stage (spec, plan, implement) so you can review and request changes.

Notes

This issue is part of the MVP2 backlog issue-coverage sweep (2026-06-02) — every active MVP2 folder should have a tracking issue so external contributors can discover the work without grep-ing the planned-features tree. If you pick this up, drop a comment so others don't duplicate; if you find the linked idea/spec stale, run /idea-preflight first to refresh it.