stella-ops.org/git.stella-ops.org
1
0
Fork 0
Code Issues Pull Requests Actions 2 Releases Wiki Activity

Publish final search-first correction phases

Browse Source
This commit is contained in:
master
2026-03-07 23:58:48 +02:00
parent c568e09a1d
commit a295841d25
7 changed files with 366 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/modules/ui/TASKS.md
View File

@@ -10,6 +10,9 @@
- `docs/implplan/SPRINT_20260307_022_FE_policy_vex_release_decisioning_studio.md`
- `docs/implplan/SPRINT_20260307_023_DOCS_ui_restoration_topic_shapes.md`
- `docs/implplan/SPRINT_20260307_029_FE_contextual_actions_and_stray_surfaces.md`
- `docs/implplan/SPRINT_20260307_035_DOCS_search_first_final_correction_phases.md`
- `docs/implplan/SPRINT_20260307_036_FE_search_first_shell_consolidation.md`
- `docs/implplan/SPRINT_20260307_038_FE_live_search_supported_route_execution_matrix.md`
## Delivery Tasks
- [DONE] 041-T1 Root IA/nav rewrite (Mission Control + Ops + Setup)
@@ -48,6 +51,13 @@
- [DONE] FE-UX-E2E Playwright coverage for mode switching, rescue flows, and AdvisoryAI next-step cards
- [DONE] WEB-CTX-NONOBVIOUS Strategic non-obvious suggestion recipes (cross-domain + action-aware)
- [DOING] FE-QA-LOOP-001 Web-only Playwright full-iteration loop at stella-ops.local (fresh route/action evidence, triage, fix, retest)
- [TODO] FE-SF-001 Search-first shell language consolidation
- [TODO] FE-SF-002 Automatic answer/overflow presentation cleanup
- [TODO] FE-SF-003 Suggestion execution and success-only history hardening
- [TODO] FE-SF-004 Search-first shell verification coverage
- [TODO] QA-SF-001 Live route preflight and corpus readiness gate
- [TODO] QA-SF-002 Execute surfaced suggestions on supported routes
- [TODO] QA-SF-003 Align deterministic and live search-first matrices
- [DONE] DOCS-UCM-001 UI component preservation map scaffold and inventory
- [DONE] DOCS-UCM-002 First-pass preservation judgments for unused and weakly surfaced UI components
- [DONE] DOCS-UCM-003 Summary tree for keep / merge / wire / archive decisions

36
docs/modules/ui/search-zero-learning-primary-entry.md
View File

@@ -19,6 +19,13 @@
- `Did you mean` is still visually tied to the results surface rather than the input correction moment. It needs to live immediately below the search field.
- Suggestions are still too easy to surface without enough corpus proof. Search must treat corpus readiness and suggestion executability as a product requirement, not a test-only concern.
## What still fails after direct operator usage
- Search and assistant still feel like sibling products in some flows. The operator should always start from search; assistant is a secondary detail view opened from that same surface.
- Any visible "scope" mechanic is wrong for the default path. Current route, visible entities, and recent actions should weight results automatically. If the best answer is outside the current page, show it as overflow only after trying the current page first.
- The product still risks teaching internal mechanics through labels, panels, and helper copy. The operator should not need to learn Stella structure, search science, or result modes just to get a useful answer.
- Suggestions are not acceptable unless they execute. A surfaced starter chip that leads to zero useful results is a product defect even when the service is healthy.
- When multiple high-confidence results are close, search should summarize them automatically. The assistant exists to expand and deepen the answer, not to compensate for a weak primary result.
## Product rules
1. Search is the primary entry point.
2. AdvisoryAI is a secondary deep-dive opened from search, not a competing starting point or route jump.
@@ -30,6 +37,8 @@
8. Search UI must avoid teaching Stella terminology or search mechanics before the operator has even started.
9. `Did you mean` belongs directly below the search field because it is an input correction, not a downstream refinement.
10. Search should summarize close evidence automatically. AdvisoryAI expands detail; it should not be required to make the primary result understandable.
11. Search suggestions are only valid when end-to-end execution against the active ingested corpus returns a grounded or materially useful answer.
12. Search verification is incomplete until live ingestion-backed route coverage proves the surfaced suggestions on every supported page family.
## Target interaction model
### Entry
@@ -52,6 +61,7 @@
- If top results are close in score, compose one short summary across them.
- If one result is clearly dominant, present that answer first and then cards.
- Prefer concise operator-facing labels over implementation-facing labels. The UI should show "best match here" and "also relevant elsewhere", not expose ranking jargon.
- Search-origin assistant actions should use secondary language such as "Open details" or "Ask for deeper help" rather than presenting a competing primary workflow.
### Suggestions
- Page suggestions become executable search intents, not static chips.
@@ -59,6 +69,7 @@
- its preferred domain has live evidence, or
- the backend confirms non-zero candidate coverage for it.
- If the current corpus is empty for that page/domain, suppress those suggestion chips instead of showing dead leads.
- A preflight result is not enough on its own for release quality. The supported live routes must be verified by running the surfaced suggestions end to end against ingested data.
### History
- Persist and render only searches that returned results.
@@ -132,3 +143,28 @@
- Run live Playwright against ingested corpora and fail early on empty corpus, missing rebuilds, or uncompiled CLI assumptions.
- Assert that every surfaced suggestion on covered routes resolves to a non-dead-end state.
- Treat corpus readiness as part of release verification for search suggestions.
## Final corrective pass
### Phase 4 - Search-first shell consolidation
- Keep one primary operator entry in the top bar: the search field.
- Keep the assistant available from a compact secondary icon beside the search field and from grounded answers, not as a competing entry model.
- Reduce primary-surface assistant branding so the product reads as one experience: search first, deeper help second.
- Remove or down-rank shell affordances that look like explicit scope controls when they only expose context.
### Phase 5 - Automatic answer shaping and weighted overflow
- Rank current-page evidence first using route, entity, and recent-action weighting without exposing that mechanism.
- When top results are genuinely close, compose one short grounded summary across them with citations.
- When one result is clearly dominant, show that answer first and push everything else down into supporting cards.
- Keep overflow secondary and quiet; it should feel like helpful spillover, not a mode or refinement path.
### Phase 6 - Suggestion executability proof across supported routes
- Extend live ingestion-backed verification beyond the Doctor page into findings, policy, and VEX-supported routes.
- Every surfaced starter chip on covered routes must execute successfully in Playwright against rebuilt corpora.
- Empty or unsupported corpora must suppress suggestions explicitly instead of letting the UI guess.
## Non-negotiable release checks
- Search must remain usable with telemetry disabled.
- Search history must persist only successful searches.
- Search must never require the operator to choose a mode or a scope.
- `Did you mean` must remain input-adjacent.
- Surfaced suggestions on supported live routes must be proven executable against ingested corpora before the search UX can be considered release-ready.