feat(ubi): engine-neutral User Behavior Insights judgment generation - #317

Merged

SoundMindsAI merged 21 commits into

mainfrom

feat/ubi-judgments

May 29, 2026

Commits on May 29, 2026

docs(mvp2): feat_ubi_judgments — idea refresh + spec + plan (planning bundle)

SoundMindsAI
and
claude
committed
feat(ubi): migration 0021 — judgment_lists.generation_params JSONB (Story 1.1)

SoundMindsAI
and
claude
committed
feat(ubi): domain/ubi/ pure-domain library (Story 1.2)

SoundMindsAI
and
claude
committed
feat(ubi): UbiReader service — engine-neutral two-index scan (Story 2.1)

SoundMindsAI
and
claude
committed
feat(ubi): readiness service + start_ubi_judgment_generation dispatcher (Story 2.2)

SoundMindsAI
and
claude
committed
feat(ubi): _SourceBreakdown three-term + UBI wire Literals (Story 2.3)

SoundMindsAI
and
claude
committed
feat(ubi): GET /api/v1/clusters/{id}/ubi-readiness endpoint (Story 3.1)

SoundMindsAI
and
claude
committed
feat(ubi): POST /api/v1/judgments/generate-from-ubi endpoint (Story 3.2)

SoundMindsAI
and
claude
committed
feat(ubi): generate_judgments_from_ubi Arq worker (Story 3.3)

SoundMindsAI
and
claude
committed
feat(ubi): generate_judgments_from_ubi agent tool + orchestrator prompt (Story 3.4)

SoundMindsAI
and
claude
committed
feat(ubi): wire enums + useUbiReadiness + <UbiRungBadge> (Story 4.1)

SoundMindsAI
and
claude
committed
feat(ubi): dialog method picker + on-ramp nudge + sparse-data card (Story 4.2)

SoundMindsAI
and
claude
committed
feat(ubi): value-delta + ambiguous-skip recovery cards (Story 4.3)

SoundMindsAI
and
claude
committed
docs(ubi): operator runbook + 3 FAQ entries + data-model patches (Story 5.1)

SoundMindsAI
and
claude
committed
docs: dashboard regen + state for feat_ubi_judgments
SoundMindsAI
committed
fix(ubi): adjudicate Gemini PR #317 review — 6 findings accepted

SoundMindsAI
and
claude
committed
test(ubi): fold in deferred integration tests + remaining Story 5.1 docs

SoundMindsAI
and
claude
committed
fix(ubi): adjudicate GPT-5.5 PR #317 final review — 4 accepted, 1 documented, 1 deferred

SoundMindsAI
and
claude
committed
docs(planned): capture feat_demo_ubi_study_comparison idea

SoundMindsAI
and
claude
committed
feat(ubi): E2E suite + fix UbiReader result-window overflow

SoundMindsAI
and
claude
committed
docs(ubi): correct hybrid LLM-fill design note (GPT-5.5 #6 is working-as-designed)

SoundMindsAI
and
claude
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(ubi): engine-neutral User Behavior Insights judgment generation - #317

feat(ubi): engine-neutral User Behavior Insights judgment generation#317
SoundMindsAI merged 21 commits into
mainfrom
feat/ubi-judgments

Commits on May 29, 2026

docs(mvp2): feat_ubi_judgments — idea refresh + spec + plan (planning bundle)

feat(ubi): migration 0021 — judgment_lists.generation_params JSONB (Story 1.1)

feat(ubi): domain/ubi/ pure-domain library (Story 1.2)

feat(ubi): UbiReader service — engine-neutral two-index scan (Story 2.1)

feat(ubi): readiness service + start_ubi_judgment_generation dispatcher (Story 2.2)

feat(ubi): _SourceBreakdown three-term + UBI wire Literals (Story 2.3)

feat(ubi): GET /api/v1/clusters/{id}/ubi-readiness endpoint (Story 3.1)

feat(ubi): POST /api/v1/judgments/generate-from-ubi endpoint (Story 3.2)

feat(ubi): generate_judgments_from_ubi Arq worker (Story 3.3)

feat(ubi): generate_judgments_from_ubi agent tool + orchestrator prompt (Story 3.4)

feat(ubi): wire enums + useUbiReadiness + <UbiRungBadge> (Story 4.1)

feat(ubi): dialog method picker + on-ramp nudge + sparse-data card (Story 4.2)

feat(ubi): value-delta + ambiguous-skip recovery cards (Story 4.3)

docs(ubi): operator runbook + 3 FAQ entries + data-model patches (Story 5.1)

docs: dashboard regen + state for feat_ubi_judgments

fix(ubi): adjudicate Gemini PR #317 review — 6 findings accepted

test(ubi): fold in deferred integration tests + remaining Story 5.1 docs

fix(ubi): adjudicate GPT-5.5 PR #317 final review — 4 accepted, 1 documented, 1 deferred

docs(planned): capture feat_demo_ubi_study_comparison idea

feat(ubi): E2E suite + fix UbiReader result-window overflow

docs(ubi): correct hybrid LLM-fill design note (GPT-5.5 #6 is working-as-designed)