Document reactive world and metric-driven backgrounds

README.md

@@ -96,6 +96,50 @@ Each turn combines:
 
 The result is not a prediction engine and not an advice bot. It is a playable mirror: a fictional system for feeling how tradeoffs compound.
 
+## Reactive Worlds
+
+The visual world is not static. LifeChoice chooses a background family from the player's chosen path, then switches the image as the metrics change.
+
+There are **6 environment types**:
+
+| Environment | Trigger Examples |
+|---|---|
+| `campus_academic` | MTech, PhD, college, study, masters, research |
+| `studio_creative` | artist, art, music, design, film, creative, writer |
+| `startup_chaotic` | startup, founder, business |
+| `medical_clinical` | doctor, medical, NEET, hospital |
+| `corporate` | corporate, manager, consulting, MBA |
+| `tech_office` | default environment for other paths |
+
+Each environment has **3 metric-driven states**:
+
+| State | Meaning |
+|---|---|
+| `stable` | The path is tense but balanced enough to continue |
+| `thriving` | Overall wellbeing is high and stress is controlled |
+| `struggling` | Stress, money pressure, or low wellbeing is visibly damaging the world |
+
+That creates **18 background variants** in total, such as:
+
+```text
+campus_academic_stable.png
+campus_academic_thriving.png
+campus_academic_struggling.png
+startup_chaotic_stable.png
+startup_chaotic_thriving.png
+startup_chaotic_struggling.png
+```
+
+The character also reacts to the same simulation state:
+
+| Character State | Trigger |
+|---|---|
+| `neutral` | Default state |
+| `stressed` | Stress rises above the danger threshold |
+| `confident` | Fulfillment is high while stress stays low |
+
+The background represents the condition of the world around the player. The character represents how the player is holding up inside that world.
+
 ## AI Role
 
 The LLM is central to the project. It generates the adaptive future scenarios that make each run feel personal to the player's dilemma, chosen path, calibration pressure, and earlier decisions.
@@ -140,7 +184,7 @@ Hugging Face model metadata reports `7,615,616,512` parameters. No secondary mod
 | Bounded memory | Recent choices, facts, obligations, and closed options are carried forward |
 | Consequential choices | Every decision mutates metrics and the causal ledger |
 | Delayed consequences | Prior decisions return at cascade moments instead of disappearing |
-| Reactive visuals | Backgrounds, metrics, world label, and sprite expression change with state |
+| Reactive visuals | 6 environment families, 18 background states, metric bars, world label, and sprite expression change with state |
 | Final report | The ending is computed from what happened in the playthrough |
 
 ## Safety
@@ -196,6 +240,8 @@ This submission does not claim Tiny Titan, OpenBMB, NVIDIA, Modal credits, Off t
 - `Qwen/Qwen2.5-7B-Instruct` at 7.616B parameters
 - Thread-pool prefetching
 - Deterministic state engine
+- 6 environment families and 18 metric-driven background variants
+- 3 character states: `neutral`, `stressed`, and `confident`
 - Pixel-art environment assets
 - Public Hugging Face Space deployment