chore(.env): add PEPA_FAST_LLM_* placeholders for v0.3.0 fast advisor

Empty values keep the fast-advisor tier disabled (safe no-op). Fill
in BASE_URL + API_KEY + MODEL to enable. TimeWeb-style endpoint
example included.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.env.example

@@ -29,6 +29,25 @@ GOOGLE_API_KEY=
 PI_DEFAULT_PROVIDER=openai
 PI_DEFAULT_MODEL=gpt-5-mini
 
+# --- Fast LLM tier (v0.3.0+) --------------------------------------------------
+# Pi (CLI) handles slow deep analytics — post-mortem and 30-min reflection.
+# A parallel "fast advisor" tier handles tactical "what to do RIGHT NOW"
+# decisions when the reflex is stuck / preempted. Any OpenAI-compatible
+# endpoint works: TimeWeb, OpenAI direct, Groq, OpenRouter, local Ollama.
+#
+# Leave blank to disable — the bot then runs without the fast tier
+# (rc.1 scaffold is a safe no-op when API_KEY is unset).
+#
+# Example for TimeWeb (replace with your own endpoint + key + model):
+#   PEPA_FAST_LLM_BASE_URL=https://api.gen-api.ru/api/v1
+#   PEPA_FAST_LLM_API_KEY=<paste your key here>
+#   PEPA_FAST_LLM_MODEL=gpt-5-mini
+PEPA_FAST_LLM_BASE_URL=
+PEPA_FAST_LLM_API_KEY=
+PEPA_FAST_LLM_MODEL=
+# Optional: request timeout in ms (default 8000)
+PEPA_FAST_LLM_TIMEOUT_MS=
+
 # --- Bot behaviour ------------------------------------------------------------
 # How often (seconds) the autonomous tick prompt fires. Set to 0 to disable.
 TICK_INTERVAL_SECONDS=60