feat: Sprint 1 — IPA hardening, regression framework, ground-truth review

Track A (Backend):
- Compound word IPA decomposition (schoolbag→school+bag)
- Trailing garbled IPA fragment removal after brackets (R21 fix)
- Regression runner with DB persistence, history endpoints
- Page crop determinism verified with tests

Track B (Frontend):
- OCR Regression dashboard (/ai/ocr-regression)
- Ground Truth Review workflow (/ai/ocr-ground-truth)
  with split-view, confidence highlighting, inline edit,
  batch mark, progress tracking

Track C (Docs):
- OCR-Pipeline.md v5.0 (Steps 5e-5h)
- Regression testing guide
- mkdocs.yml nav update

Track D (Infra):
- TrOCR baseline benchmark script
- run-regression.sh shell script
- Migration 008: regression_runs table

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

klausur-service/backend/migrations/008_regression_runs.sql

@@ -0,0 +1,18 @@
+-- Migration 008: Regression test run history
+-- Stores results of regression test runs for trend analysis.
+
+CREATE TABLE IF NOT EXISTS regression_runs (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    run_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    status VARCHAR(20) NOT NULL,  -- 'pass', 'fail', 'error'
+    total INT NOT NULL DEFAULT 0,
+    passed INT NOT NULL DEFAULT 0,
+    failed INT NOT NULL DEFAULT 0,
+    errors INT NOT NULL DEFAULT 0,
+    duration_ms INT,
+    results JSONB NOT NULL DEFAULT '[]',
+    triggered_by VARCHAR(50) DEFAULT 'manual'  -- 'manual', 'script', 'ci'
+);
+
+CREATE INDEX IF NOT EXISTS idx_regression_runs_run_at
+    ON regression_runs (run_at DESC);