fix: pass PII mapping config to auto-detecting Candle BERT classifier

Critical bug fix for PR #648 CI failures.

**Root Cause:**
The new auto-detecting PII classifier API was not receiving the PII
configuration mapping (pii_type_mapping.json), causing:
- 0% PII detection accuracy (classifier didn't know which entities to detect)
- 0/100 requests blocked (blocking policy received incomplete results)

**The Bug:**
Changed from ClassifyModernBertPIITokens(text, configPath) to
ClassifyCandleBertTokens(text) - dropping the configPath parameter.

**The Fix:**
Use ClassifyCandleBertTokensWithLabels(text, id2labelJSON) to pass
the PII entity mapping configuration to the classifier.

**Testing:**
- Local testing worked because it was using old code (ModernBERT path)
- CI failed because it builds from PR branch (new auto-detect path)
- This fix ensures both LoRA and Traditional paths receive PII config

**Related:**
- Fixes CI test failures in integration-test jobs
- LoRA loading still shows 'hidden_act' error but falls back to ModernBERT
- ModernBERT fallback now works correctly with this fix

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>
Signed-off-by: Yossi Ovadia <[email protected]>

Author: yossiovadia

src/semantic-router/pkg/classification/classifier.go

@@ -2,6 +2,7 @@ package classification
 
 import (
 	"fmt"
+	"os"
 	"slices"
 	"strings"
 	"time"
@@ -182,7 +183,12 @@ type PIIInferenceImpl struct{}
 
 func (c *PIIInferenceImpl) ClassifyTokens(text string, configPath string) (candle_binding.TokenClassificationResult, error) {
 	// Auto-detecting inference - uses whichever classifier was initialized (LoRA or Traditional)
-	return candle_binding.ClassifyCandleBertTokens(text)
+	// Load the PII mapping configuration to pass to the classifier
+	id2labelJSON, err := os.ReadFile(configPath)
+	if err != nil {
+		return candle_binding.TokenClassificationResult{}, fmt.Errorf("failed to read PII mapping config %s: %w", configPath, err)
+	}
+	return candle_binding.ClassifyCandleBertTokensWithLabels(text, string(id2labelJSON))
 }
 
 // createPIIInference creates the PII inference (auto-detecting)