feat: Add Streamlit dashboard with Blueprint compliance (v2.1.0)

Dashboard Features:
- 8 navigation sections: Overview, Outcomes, Poor CX, FCR, Churn, Agent, Call Explorer, Export
- Beyond Brand Identity styling (colors #6D84E3, Outfit font)
- RCA Sankey diagram (Driver → Outcome → Churn Risk flow)
- Correlation heatmaps (driver co-occurrence, driver-outcome)
- Outcome Deep Dive (root causes, correlation, duration analysis)
- Export functionality (Excel, HTML, JSON)

Blueprint Compliance:
- FCR: 4 categories (Primera Llamada/Rellamada × Sin/Con Riesgo de Fuga)
- Churn: Binary view (Sin Riesgo de Fuga / En Riesgo de Fuga)
- Agent: Talento Para Replicar / Oportunidades de Mejora
- Fixed FCR rate calculation (only FIRST_CALL counts as success)

Technical:
- Streamlit + Plotly for interactive visualizations
- Light theme configuration (.streamlit/config.toml)
- Fixed Plotly colorbar titlefont deprecation

Documentation:
- Updated PROJECT_CONTEXT.md, TODO.md, CHANGELOG.md
- Added 4 new technical decisions (TD-014 to TD-017)
- Created TROUBLESHOOTING.md with 10 common issues

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

config/prompts/call_analysis/v1.0/user.txt

@@ -0,0 +1,72 @@
+Analyze the following call transcript and provide structured analysis.
+
+## CALL METADATA
+- Call ID: {call_id}
+- Duration: {duration_sec} seconds
+- Queue: {queue}
+
+## OBSERVED EVENTS (Pre-detected)
+{observed_events}
+
+## TRANSCRIPT
+{transcript}
+
+## TAXONOMY - LOST SALES DRIVERS
+{lost_sales_taxonomy}
+
+## TAXONOMY - POOR CX DRIVERS
+{poor_cx_taxonomy}
+
+## INSTRUCTIONS
+
+1. Determine the call outcome from: SALE_COMPLETED, SALE_LOST, CANCELLATION_SAVED, CANCELLATION_COMPLETED, INQUIRY_RESOLVED, INQUIRY_UNRESOLVED, COMPLAINT_RESOLVED, COMPLAINT_UNRESOLVED, TRANSFER_OUT, CALLBACK_SCHEDULED, UNKNOWN
+
+2. Identify lost_sales_drivers (if applicable):
+   - Use ONLY codes from the Lost Sales taxonomy
+   - Each driver MUST have evidence_spans with exact quotes and timestamps
+   - Assign confidence based on evidence strength
+
+3. Identify poor_cx_drivers (if applicable):
+   - Use ONLY codes from the Poor CX taxonomy
+   - Each driver MUST have evidence_spans with exact quotes and timestamps
+   - Assign confidence based on evidence strength
+
+4. For OTHER_EMERGENT, provide a proposed_label describing the new cause.
+
+Respond with JSON only:
+
+```json
+{
+  "outcome": "SALE_LOST",
+  "lost_sales_drivers": [
+    {
+      "driver_code": "PRICE_TOO_HIGH",
+      "confidence": 0.85,
+      "evidence_spans": [
+        {
+          "text": "Es demasiado caro para mí",
+          "start_time": 45.2,
+          "end_time": 47.8,
+          "speaker": "customer"
+        }
+      ],
+      "reasoning": "Customer explicitly states price is too high"
+    }
+  ],
+  "poor_cx_drivers": [
+    {
+      "driver_code": "LONG_HOLD",
+      "confidence": 0.90,
+      "evidence_spans": [
+        {
+          "text": "Llevo esperando mucho tiempo",
+          "start_time": 120.5,
+          "end_time": 123.1,
+          "speaker": "customer"
+        }
+      ],
+      "reasoning": "Customer complains about wait time"
+    }
+  ]
+}
+```