Docs: Synchronize technical ethics implementation with public guides

Author: darestack

.env.example

@@ -10,6 +10,11 @@ GROQ_API_KEY=""
 # LLM_PROVIDER="groq"
 # MODEL_NAME="llama3-8b-8192" # Use gpt-4o for OpenAI, llama3-8b-8192 for Groq
 
+# Ethical & Sensitivity Settings
+# CULTURAL_DIRECTNESS_LEVEL="high" # Options: low, medium, high
+# COOLING_OFF_PERIOD_HOURS=48
+
+
 # Infrastructure
 REDIS_URL="redis://localhost:6380"
 DATABASE_URL="postgresql+asyncpg://postgres:postgres@localhost:5432/commitguard"

docs/guides/managers.md

@@ -31,3 +31,8 @@ High-stakes interventions should never be 100% autonomous.
 ## 3. Best Practices for Professionalism
 *   **Public vs. Private**: CommitGuard monitors public channels, but follow-up interventions for **high-risk signals** should often be moved to a 1-on-1 private DM thread once the manager is alerted.
 *   **Celebrate the Reliability**: When someone consistently hits 100% on their Reliability Score, use the report as a basis for formal recognition. Accountability is as much about **Praise** as it is about Progress.
+## 4. Configuring Your Team's Voice 🎚️
+Managers can adjust the system's "psychological pressure" via environment variables:
+
+*   **`CULTURAL_DIRECTNESS_LEVEL`**: Set to `low` for high-context or sensitive teams. This forces the LLM to use more indirect, softer language even when flagging risks.
+*   **`COOLING_OFF_PERIOD_HOURS`**: Adjust the duration of the "Tone Damping" state (Default: 48 hours).

docs/overviews/ethics.md

@@ -9,7 +9,8 @@ One of our most discussed features is the **"Confrontational"** tone. Here is ho
 
 *   **The Empathy Buffer**: The system is hardcoded to prioritize `SUPPORTIVE` tones if anything resembling burnout or personal distress is detected.
 *   **The Burnout Safety Valve**: If the `ExcuseDetector` identifies signs of fatigue, the system **blocks** confrontational escalation and triggers a "Burnout Alert" for the manager instead. 
-*   **Tone Drift & Cooling-off**: To prevent morale fatigue, the system implements **tone-damping**. If a user has received multiple "Firm" follow-ups, the system enters a 48-hour "Cooling-off" state where only supportive or neutral tones are permitted to avoid wearing down the individual.
+*   **Tone Drift & Cooling-off**: To prevent morale fatigue, the system implements **mathematical tone-damping**. If a user receives **3 consecutive "Firm" or "Confrontational" follow-ups**, the logic automatically locks the agent into a `NEUTRAL` or `SUPPORTIVE` state for 48 hours (configurable via `COOLING_OFF_PERIOD_HOURS`).
+
 
 ## 2. Cultural & Contextual Sensitivity
 "Deflection" is relative. What is seen as blunt in one culture is polite in another: