docs: sync documentation with post-v0.2 changes

.env.example

@@ -8,6 +8,7 @@ export AZURE_OPENAI_API_VERSION=2024-12-01-preview
 # Authentication: choose one method
 #   Option 1: API Key
 export AZURE_OPENAI_API_KEY=
+export AZURE_OPENAI_AUTH_MODE=api_key
 #   Option 2: Azure CLI (no API key needed, recommended on Azure VMs)
 # export AZURE_OPENAI_AUTH_MODE=azure_cli
 #   Option 3: Managed Identity
@@ -15,20 +16,45 @@ export AZURE_OPENAI_API_KEY=
 # export AZURE_OPENAI_MANAGED_IDENTITY_CLIENT_ID=your-client-id
 
 # ── OpenAI-compatible endpoints ──────────────────────────────────────
-# Set AUTH_MODE to openai_compatible and reuse AZURE_OPENAI_ENDPOINT / _API_KEY.
-# The plain OpenAI client is used; no Azure auth, no api-version header.
+# Path 1: generic research backend. Select openai_compatible explicitly as
+# model.optimizer_backend and/or model.target_backend.
+# export OPENAI_COMPATIBLE_BASE_URL=https://api.deepseek.com/v1
+# export OPENAI_COMPATIBLE_API_KEY=sk-...
+# export OPENAI_COMPATIBLE_MODEL=deepseek-chat
+# Per-role overrides use OPTIMIZER_OPENAI_COMPATIBLE_* and
+# TARGET_OPENAI_COMPATIBLE_* (BASE_URL, API_KEY, MODEL, TEMPERATURE,
+# MAX_TOKENS, TIMEOUT_SECONDS).
+# For scripts/train.py and scripts/eval_only.py, also set model.optimizer and
+# model.target in YAML (or via --cfg-options). Those role model values are
+# applied after backend initialization and override *_MODEL environment values.
+
+# Path 2: research openai_chat compatibility mode. This reuses the Azure-family
+# variables but creates a plain OpenAI client (no Azure auth or api-version).
 # export AZURE_OPENAI_ENDPOINT=https://api.openai.com/v1
 # export AZURE_OPENAI_API_KEY=sk-...
 # export AZURE_OPENAI_AUTH_MODE=openai_compatible
 
-# ── Anthropic / Claude (for claude_chat backend) ─────────────────────
+# Path 3: SkillOpt-Sleep. `skillopt-sleep run --backend azure_openai` uses the
+# same three AZURE_* variables from path 2. Optional Sleep-only controls:
+# export SKILLOPT_SLEEP_COMPAT_MAX_TOKENS=8192
+# export SKILLOPT_SLEEP_CHAT_EXTRA_BODY='{"provider_option": true}'
+
+# ── Claude Code CLI (for claude_chat backend) ─────────────────────────
+# Install and authenticate the `claude` CLI before use. For a non-default path:
+# export CLAUDE_CLI_BIN=/path/to/claude
+# ANTHROPIC_API_KEY is one authentication option understood by the CLI; SkillOpt
+# does not create a direct Anthropic API client for this backend.
 # export ANTHROPIC_API_KEY=sk-ant-...
 
 # ── Qwen Local Model (for qwen_chat backend) ────────────────────────
 # export QWEN_CHAT_BASE_URL=http://localhost:8000/v1
 # export QWEN_CHAT_MODEL=Qwen/Qwen3.5-4B
+# The train/eval entry points likewise override this model with
+# model.optimizer/model.target for the selected Qwen roles.
 
 # ── MiniMax (for minimax_chat backend) ──────────────────────────────
 # export MINIMAX_BASE_URL=https://api.minimax.io/v1
 # export MINIMAX_API_KEY=...
-# export MINIMAX_MODEL=MiniMax-M2.7
+# When MiniMax is the target, set model.minimax_model in YAML. The current
+# adapter shares one deployment across MiniMax roles; mixed-backend runs cannot
+# independently select a MiniMax optimizer model and a different target model.