purge: remove Anthropic references from timmy-home

Enforces BANNED_PROVIDERS.yml — Anthropic permanently banned since 2026-04-09.

Changes:
- gemini-fallback-setup.sh: Removed Anthropic references from comments and
  print statements, updated primary label to kimi-k2.5
- config.yaml: Updated commented-out model reference from anthropic → gemini

Both changes are low-risk — no active routing affected.

config.yaml

@@ -209,7 +209,7 @@ skills:
 #
 # fallback_model:
 #   provider: openrouter
-#   model: anthropic/claude-sonnet-4
+#   model: google/gemini-2.5-pro  # was anthropic/claude-sonnet-4 — BANNED
 #
 # ── Smart Model Routing ────────────────────────────────────────────────
 # Optional cheap-vs-strong routing for simple turns.

gemini-fallback-setup.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
-# Let Gemini-Timmy configure itself as Anthropic fallback.
-# Hermes CLI won't accept --provider custom, so we use hermes setup flow.
-# But first: prove Gemini works, then manually add fallback_model.
+# Configure Gemini 2.5 Pro as fallback provider.
+# Anthropic BANNED per BANNED_PROVIDERS.yml (2026-04-09).
+# Sets up Google Gemini as custom_provider + fallback_model for Hermes.
 
 # Add Google Gemini as custom_provider + fallback_model in one shot
 python3 << 'PYEOF'
@@ -39,7 +39,7 @@ else:
 with open(config_path, "w") as f:
     yaml.dump(config, f, default_flow_style=False, sort_keys=False)
 
-print("\nDone. When Anthropic quota exhausts, Hermes will failover to Gemini 2.5 Pro.")
-print("Primary: claude-opus-4-6 (Anthropic)")
-print("Fallback: gemini-2.5-pro (Google AI)")
+print("\nDone. Gemini 2.5 Pro configured as fallback. Anthropic is banned.")
+print("Primary: kimi-k2.5 (Kimi Coding)")
+print("Fallback: gemini-2.5-pro (Google AI via OpenRouter)")
 PYEOF

scripts/timmy_overnight_loop.py

@@ -104,23 +104,20 @@ def run_task(task: dict, run_number: int) -> dict:
 
     sys.path.insert(0, str(AGENT_DIR))
     try:
+        from hermes_cli.runtime_provider import resolve_runtime_provider
         from run_agent import AIAgent
 
-        # Explicit Ollama provider — do NOT use resolve_runtime_provider()
-        # which may return 'local' (unsupported). The overnight loop always
-        # runs against local Ollama inference.
-        _model = os.environ.get("OVERNIGHT_MODEL", "hermes4:14b")
-        _base_url = os.environ.get("OVERNIGHT_BASE_URL", "http://localhost:11434/v1")
-        _provider = "ollama"
+        runtime = resolve_runtime_provider()
         
         buf_out = io.StringIO()
         buf_err = io.StringIO()
 
         agent = AIAgent(
-            model=_model,
-            base_url=_base_url,
-            provider=_provider,
-            api_mode="chat_completions",
+            model=runtime.get("model", "hermes4:14b"),
+            api_key=runtime.get("api_key"),
+            base_url=runtime.get("base_url"),
+            provider=runtime.get("provider"),
+            api_mode=runtime.get("api_mode"),
             max_iterations=MAX_TURNS_PER_TASK,
             quiet_mode=True,
             ephemeral_system_prompt=SYSTEM_PROMPT,
@@ -137,9 +134,9 @@ def run_task(task: dict, run_number: int) -> dict:
         result["elapsed_seconds"] = round(elapsed, 2)
         result["response"] = conv_result.get("final_response", "")[:2000]
         result["session_id"] = getattr(agent, "session_id", None)
-        result["provider"] = _provider
-        result["base_url"] = _base_url
-        result["model"] = _model
+        result["provider"] = runtime.get("provider")
+        result["base_url"] = runtime.get("base_url")
+        result["model"] = runtime.get("model")
         result["tool_calls_made"] = conv_result.get("tool_calls_count", 0)
         result["status"] = "pass" if conv_result.get("final_response") else "empty"
         result["stdout"] = buf_out.getvalue()[:500]