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>

.env.example

@@ -0,0 +1,61 @@
+# ============================================
+# CXInsights - Environment Variables
+# ============================================
+# Copy this file to .env and configure your values
+# cp .env.example .env
+# ============================================
+
+# === API KEYS (Required) ===
+ASSEMBLYAI_API_KEY=your_assemblyai_key_here
+OPENAI_API_KEY=sk-your_openai_key_here
+
+# === API KEYS (Optional) ===
+ANTHROPIC_API_KEY=sk-ant-your_anthropic_key_here
+
+# === PATHS ===
+INPUT_FOLDER=./data/raw/audio
+OUTPUT_FOLDER=./data/outputs
+DATA_DIR=./data
+CONFIG_DIR=./config
+LOG_DIR=./data/logs
+
+# === BATCH CONTROLS ===
+# Maximum calls per batch execution
+BATCH_SIZE=1000
+
+# Maximum total audio minutes per batch (cost protection)
+MAX_AUDIO_MINUTES_PER_RUN=10000
+
+# === STT THROTTLING ===
+# AssemblyAI concurrent transcriptions (start conservative: 30)
+MAX_CONCURRENT_TRANSCRIPTIONS=30
+
+# === LLM THROTTLING ===
+# OpenAI requests per minute (adjust based on your tier)
+# Tier 1 (free): 500 RPM -> configure 200 internal
+# Tier 2: 5000 RPM -> configure 2000 internal
+# Tier 3+: adjust as needed
+LLM_REQUESTS_PER_MINUTE=200
+
+# Max tokens per call (controls cost)
+LLM_MAX_TOKENS_PER_CALL=4000
+
+# Retry configuration
+LLM_MAX_RETRIES=5
+LLM_BACKOFF_BASE=2.0
+LLM_BACKOFF_MAX=60.0
+
+# === LLM MODEL ===
+# Default model for inference
+LLM_MODEL=gpt-4o-mini
+# Alternative: gpt-4o, claude-3-haiku-20240307
+
+# === LOGGING ===
+LOG_LEVEL=INFO
+# Options: DEBUG, INFO, WARNING, ERROR
+
+# === PII HANDLING ===
+# Enable PII redaction before sending to external APIs
+PII_REDACTION_ENABLED=true
+# Redaction strategy: redact, hash, mask
+PII_REDACTION_STRATEGY=redact