docs: add Environments, Benchmarks & Data Generation guide

Comprehensive developer guide covering:
- Architecture (BaseEnv → HermesAgentBaseEnv → concrete envs)
- All three benchmarks (TerminalBench2, TBLite, YC-Bench)
- Training environments (TerminalTestEnv, HermesSweEnv)
- Core components (AgentLoop, ToolContext, Tool Call Parsers)
- Two-phase operation (Phase 1 OpenAI, Phase 2 VLLM)
- Running environments (evaluate, process, serve modes)
- Creating new environments (training + eval-only)
- Configuration reference and prerequisites

Also updates environments/README.md directory tree to include
TBLite and YC-Bench benchmarks.

environments/README.md

@@ -195,8 +195,12 @@ environments/
 │   └── hermes_swe_env.py
 │
 └── benchmarks/                   # Evaluation benchmarks
-    └── terminalbench_2/
-        └── terminalbench2_env.py
+    ├── terminalbench_2/          # 89 terminal tasks, Modal sandboxes
+    │   └── terminalbench2_env.py
+    ├── tblite/                   # 100 calibrated tasks (fast TB2 proxy)
+    │   └── tblite_env.py
+    └── yc_bench/                 # Long-horizon strategic benchmark
+        └── yc_bench_env.py
 ```
 
 ## Concrete Environments