Add Claude Code statusline estimating smart-routing savings (client side)

src/ucode/agents/claude.py

@@ -83,6 +83,7 @@
     external_provider_selected,
 )
 from ucode.os_compatibility import subprocess_cross_os
+from ucode.smart_routing import pricing
 from ucode.smart_routing import v2 as smart_routing_v2
 from ucode.smart_routing.claude_hooks import (
     FIRST_PROMPT_SOCKET_ENV,
@@ -2108,6 +2109,17 @@ def launch(
         }
         settings_override = _merge_claude_settings(settings_override or {}, {"env": fallback_env})
         os.environ.update(fallback_env)
+    if smart_routing_v2.savings_statusline_enabled() and workspace:
+        # Show "Smart routing off" in the status row when nothing is routed: a plain launch, or a
+        # routed one whose setup failed (`launch_claude` otherwise exits without reaching here).
+        settings_override = settings_override or {}
+        smart_routing_v2.install_savings_statusline(
+            settings_override,
+            CLAUDE_USER_SETTINGS_PATH,
+            price_cache=pricing.price_cache_path(APP_DIR, workspace),
+            routing_enabled=False,
+            baseline_session_start=False,
+        )
     exec_or_spawn(_build_claude_argv(binary, launch_args, settings_override=settings_override))
 
 

src/ucode/databricks.py

@@ -2092,6 +2092,38 @@ def fetch_external_model_prices(workspace: str, token: str) -> tuple[list[dict],
     return models, None
 
 
+# Per-token rates for Databricks-hosted (`system.ai`) model services from the gateway's
+# pay-per-token endpoint-rates API, which the smart-routing savings statusline prices usage with.
+# The model names travel as repeated `databricks_hosted_model_services` query parameters.
+_ENDPOINT_RATES_API_PATH = "/api/ai-gateway/v2/endpoint-rates:batchGet"
+_SYSTEM_AI_MODEL_PREFIX = "system.ai."
+
+
+def fetch_endpoint_rates(
+    workspace: str, token: str, model_services: list[str]
+) -> tuple[list[dict], str | None]:
+    """Batch-fetch per-token rates for ``system.ai`` model services.
+
+    Returns ``(rates, reason)`` with each rate the raw ``EndpointRate`` entry; models the caller
+    can't see are absent rather than errors. Names outside ``system.ai`` are dropped because the
+    API rejects them. ``reason`` is non-None on failure so callers omit the estimate, not fail.
+    """
+    names = sorted({name for name in model_services if name.startswith(_SYSTEM_AI_MODEL_PREFIX)})
+    if not names:
+        return [], "no system.ai model services to price"
+    query = urlencode([("databricks_hosted_model_services", name) for name in names])
+    url = f"https://{workspace_hostname(workspace)}{_ENDPOINT_RATES_API_PATH}?{query}"
+    payload, reason = _http_get_json(url, token, timeout=30)
+    if reason is not None:
+        return [], reason
+    if not isinstance(payload, dict):
+        return [], "endpoint-rates returned an unexpected response shape"
+    rates = payload.get("model_service_rates")
+    if not isinstance(rates, list):
+        return [], None
+    return [rate for rate in rates if isinstance(rate, dict)], None
+
+
 # The `update_mask` paths a config PATCH sends. The server rejects paths outside its mutable set,
 # so this omits `spec_version` (an estore-internal format marker, still sent in the body; naming it
 # in the mask is the 400 this fixes) and the reserved/deprecated fields (`display_name`, `tracing`,

src/ucode/mods.py

@@ -63,8 +63,9 @@ def write_mod(plugin_dir: Path, mod: ClaudeMod) -> None:
 
 
 # ug's smart-routing UI mod: a register.ts entry that composes the concern
-# modules it imports (today the status band).
+# modules it imports (the status band, the subagent routing line, and the
+# savings estimate the band appends).
 SMART_ROUTING_UI = ClaudeMod(
     source="register.ts",
-    extra=("smart-routing-status.ts", "subagent-routing.ts"),
+    extra=("smart-routing-status.ts", "subagent-routing.ts", "smart-routing-savings.ts"),
 )