chore(planning): elevate B5c/d/e + B8 for v1.4.16

Split former bullet-under-B5 items into first-class Wave-B work items:

  B5a — Medical-reference grounding (AHA / ESC / ESH / WHO)
  B5b — Multi-provider redundancy
  B5c — Per-recommendation explainability (WHY / WINDOW / CITATIONS)
  B5d — Confidence score per recommendation (0-100)
  B5e — User-feedback loop (thumbs up/down → prompt tuning)

Add new B8 — Extended comparison views (Vormonat / Vorjahr) across
charts, tiles, and the insights surface.

ROADMAP.md updated to mirror the expanded bucket.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.planning/ROADMAP.md

@@ -18,9 +18,14 @@ Latest tag at start: v1.4.15 (live in prod, image digest `sha256:ace7d441f47b…
 | B2    | AI provider settings UX cleanup — single pulldown-driven form, no top/bottom split                                | pending |
 | B3    | Admin System-Status host-load chart — CPU/memory/disk-io graph last 2h                                            | pending |
 | B4    | Admin logs visibility deepening — filterable audit log + structured wide-event tail                               | pending |
-| B5    | AI hallucination-hardening v2 — medical-reference grounding + multi-provider + explainability                     | pending |
+| B5a   | Medical-reference grounding — AHA / ESC / ESH / WHO target ranges as system context + UI citations                | pending |
+| B5b   | Multi-provider redundancy — try-each-on-hard-failure, configurable fallback order                                 | pending |
+| B5c   | Per-recommendation explainability — WHY / WINDOW / CITATIONS card with mini-chart                                 | pending |
+| B5d   | Confidence score per recommendation — 0-100 from sufficiency / recency / signal strength                          | pending |
+| B5e   | User-feedback loop — thumbs up/down persisted to RecommendationFeedback, fed into prompt tuning                   | pending |
 | B6    | Settings naming-audit — stringency, consistency, no double naming                                                 | pending |
 | B7    | Settings → Export menu (Arztbrief consolidated) — new `/settings/export` route                                    | pending |
+| B8    | Extended comparison views — Vormonat / Vorjahr overlay across charts + tiles + insights                           | pending |
 | C     | Catch-up — 8 deferred HIGH + 5 mobile MED + Coolify image-digest trigger + docker-publish hang                    | pending |
 | D     | Multi-agent QA + Product-Lead — code-review, security, design (Apple-Health lens), senior, simplify, product-lead | pending |
 | E     | Release v1.4.16 — bump, CHANGELOG, tag, GHCR, deploy, /api/version=1.4.16, smoke, docs+landing sync               | pending |
@@ -30,7 +35,7 @@ or budget short of polish — write status doc, do not auto-rollback.
 
 Time-runs-short minimum to ship v1.4.16: Wave A (any subset) + Wave D
 
-- Phase E. Wave B (B1-B7) and Wave C catch-up are deferrable to v1.4.17
+- Phase E. Wave B (B1-B8) and Wave C catch-up are deferrable to v1.4.17
   if context budget tightens.
 
 Phase 0 spec for this marathon: orchestrator user message in this

.planning/STATE.md

@@ -98,13 +98,38 @@ Last update: 2026-05-09T23:12:52+02:00
 - [ ] App-log preview: tail of structured wide-events for last 1h, filterable by trace_id
 - Detailed report: `.planning/phase-B4-report.md`
 
-### B5 — AI hallucination-hardening v2 (medical grounding + multi-provider)
+### B5a — Medical-reference grounding
 
-- [ ] Medical-reference grounding: AHA/ESH/WHO target-range citations in system context
-- [ ] Multi-provider redundancy: try-each-on-hard-failure
-- [ ] Per-recommendation explainability + confidence score
-- [ ] User-feedback loop ("was this helpful?" → prompt-tuning over time)
-- Detailed report: `.planning/phase-B5-report.md`
+- [ ] AHA / ESC / ESH / WHO target ranges as system context
+- [ ] Citations link to source guideline in UI
+- Detailed report: `.planning/phase-B5a-report.md`
+
+### B5b — Multi-provider redundancy
+
+- [ ] try-each-on-hard-failure across configured providers
+- [ ] Fallback ordering configurable per user
+- Detailed report: `.planning/phase-B5b-report.md`
+
+### B5c — Per-Recommendation Explainability
+
+- [ ] Each rec carries: WHY (what user-data triggered it), WINDOW (which time range was analyzed), CITATIONS (which medical guideline + which user metric)
+- [ ] UI: expand-arrow on each rec → reveals the explainability card with mini-chart of the data window
+- [ ] Schema enforces presence (extends v1.4.15 C1's strict schema)
+- Detailed report: `.planning/phase-B5c-report.md`
+
+### B5d — Confidence Score per Recommendation
+
+- [ ] Each rec carries a 0-100 confidence score derived from: data sufficiency (n samples), recency, signal strength
+- [ ] UI: visual confidence indicator (e.g., color-coded ring or 5-bar meter) per rec
+- [ ] Below-threshold recs are tagged "Low confidence — based on limited data" rather than hidden
+- Detailed report: `.planning/phase-B5d-report.md`
+
+### B5e — User-Feedback Loop
+
+- [ ] "War das hilfreich?" thumbs-up/down on each rec, persisted as RecommendationFeedback (new table)
+- [ ] Aggregated feedback feeds into prompt-tuning: low-helpful patterns get a system-prompt addendum next generation
+- [ ] Privacy: feedback is per-user; no cross-user training (offline only, opt-in for any aggregation)
+- Detailed report: `.planning/phase-B5e-report.md`
 
 ### B6 — Settings naming-audit
 
@@ -120,6 +145,14 @@ Last update: 2026-05-09T23:12:52+02:00
 - [ ] Rename current doctor-report entry-point to live under /settings/export
 - Detailed report: `.planning/phase-B7-report.md`
 
+### B8 — Extended Comparison Views (Vormonat / Vorjahr)
+
+- [ ] Each chart + tile + insight gets toggleable comparison overlay: "vs. last month" / "vs. last year"
+- [ ] Visual treatment: dimmed historical line beneath current; delta callout (Δ +5%, etc.)
+- [ ] Insights surface narrates the comparison ("Your average BP improved by 4 mmHg vs. last month")
+- [ ] Mobile-friendly comparison toggle (not a fragile hover-only interaction)
+- Detailed report: `.planning/phase-B8-report.md`
+
 ## Wave C — Catch-up (deferred from v1.4.15)
 
 - [ ] 8 deferred HIGH-Findings from v1.4.15 Wave-D (see `v1416-backlog.md`)