feat: fresh install starts with an empty model pool

- config.rs: validate() no longer errors on zero models — an empty pool is
  allowed (warns instead), so the admin console comes up on a fresh install and
  the user adds models in /admin -> Models (or points [cmf] at a local .cmf).
- gateway.example.toml: ships an EMPTY pool (no seed cmf-local/local-embed, empty
  routing), so `cp example -> gateway.toml && run` shows an empty list — what a
  new user expects.

config/gateway.example.toml

@@ -28,40 +28,29 @@ cache_ttl     = "60s"
 profile       = "balanced"    # cost-saver | balanced | quality-first
 
 # ============================================================================
-# Model pool. This example ships ONE local CMF model, served by the managed
-# cortiq server (see the [cmf] section below). Add more models — local or cloud —
-# by copying the [[models]] shape: provider = "openai"/"anthropic", and for a
-# hosted provider an api_key_env = "..." (never put secrets in this file).
+# Model pool — EMPTY by default. A fresh gateway starts with no models and an
+# empty pool; add them in the admin console (/admin → Models), or run a local
+# .cmf via the [cmf] section below. To add one by hand, copy this shape:
+#
+#   [[models]]
+#   id        = "my-model"
+#   provider  = "openai"                    # openai | anthropic (openai also covers
+#   base_url  = "http://127.0.0.1:8081/v1"  #   OpenRouter/Together/Groq/vLLM/Ollama)
+#   model     = "my-model"
+#   # api_key_env = "OPENAI_API_KEY"        # for hosted providers (never inline a key)
+#   cost_tier = "local"
+#   caps      = ["tools"]
 # ============================================================================
 
-[[models]]
-id        = "cmf-local"
-provider  = "openai"
-base_url  = "http://127.0.0.1:8081/v1"   # the managed cortiq server (see [cmf])
-model     = "cmf-local"
-cost_tier = "local"
-price_in  = 0.0
-price_out = 0.0
-caps      = ["tools"]
-
-# --- embedding model (optional: /v1/embeddings + the semantic cache) ---------
-[[models]]
-id          = "local-embed"
-provider    = "openai"
-base_url    = "http://localhost:8000/v1"   # a local embeddings server (vLLM / llama.cpp / Ollama)
-model       = "nomic-embed-text"
-cost_tier   = "local"
-kind        = "embedding"
-
 # ============================================================================
 # Routing table: complexity tier → ordered pool (priority = fallback chain).
-# Add cloud models above and list them here for cost/quality-based fallback.
+# Leave default empty for a fresh install; set it to a model id once you add one.
 # ============================================================================
 [routing]
-low     = ["cmf-local"]
-medium  = ["cmf-local"]
-high    = ["cmf-local"]
-default = "cmf-local"        # used when the router is unreachable
+low     = []
+medium  = []
+high    = []
+default = ""                 # set to a model id once you add one
 
 [routing.policy]
 mode = "fixed_table"           # fixed_table | cost_aware

src/config.rs

@@ -599,7 +599,12 @@ impl Config {
         // is what lets the gateway run on local models alone (no cloud, no router).
         let has_local = self.cmf.manage_server && !self.cmf.local_model.trim().is_empty();
         if self.models.is_empty() && !has_local {
-            anyhow::bail!("config: at least one [[models]] entry (or a managed local CMF model) is required");
+            // Fresh install: start with an EMPTY model pool so the admin console
+            // comes up — the user adds models in /admin → Models (or points [cmf]
+            // at a local .cmf). Routing simply has nothing to select until then.
+            tracing::warn!(
+                "no models configured — starting with an empty pool; add one in /admin → Models"
+            );
         }
         // uniqueness of model ids
         let mut seen = std::collections::HashSet::new();