feat: capture Anthropic rate limit headers for quota-based model switching

- Writes rate_limits.json after every API call with weekly/5h utilization
- Writes api_headers.jsonl with raw headers for analysis
- Upgrades quota fallback model from Sonnet 4.5 to 4.6

Deploy to site-packages (gateway loads from there, not /app/):
  docker cp to /usr/local/lib/python3.12/site-packages/nanobot/providers/

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

nanobot/agent/loop.py

@@ -156,7 +156,7 @@ class AgentLoop:
 
         # Default models
         OPUS = "claude-opus-4-6"
-        SONNET = "claude-sonnet-4-5"
+        SONNET = "claude-sonnet-4-6"
         TOLERANCE = 1.17  # 17% overage triggers downgrade
 
         # Read rate limits

nanobot/providers/anthropic_oauth.py

@@ -269,6 +269,39 @@ class AnthropicOAuthProvider(LLMProvider):
             json=payload,
         )
 
+        # Dump rate limit headers for analysis
+        try:
+            import datetime
+            import os
+            header_dump = {
+                "timestamp": datetime.datetime.utcnow().isoformat(),
+                "status_code": response.status_code,
+                "model": payload.get("model"),
+                "headers": dict(response.headers),
+            }
+            dump_path = "/root/.nanobot/workspace/api_headers.jsonl"
+            with open(dump_path, "a") as f:
+                f.write(json.dumps(header_dump) + "\n")
+            # Capture rate limit state for quota-based model switching
+            hdrs = response.headers
+            rate_limit_state = {
+                "updated_at": datetime.datetime.utcnow().isoformat(),
+                "model": payload.get("model"),
+                "weekly_all_models": float(hdrs["anthropic-ratelimit-unified-7d-utilization"]) if hdrs.get("anthropic-ratelimit-unified-7d-utilization") else None,
+                "weekly_sonnet": float(hdrs["anthropic-ratelimit-unified-7d_sonnet-utilization"]) if hdrs.get("anthropic-ratelimit-unified-7d_sonnet-utilization") else None,
+                "session_5h": float(hdrs["anthropic-ratelimit-unified-5h-utilization"]) if hdrs.get("anthropic-ratelimit-unified-5h-utilization") else None,
+                "weekly_reset": int(hdrs["anthropic-ratelimit-unified-7d-reset"]) if hdrs.get("anthropic-ratelimit-unified-7d-reset") else None,
+                "session_reset": int(hdrs["anthropic-ratelimit-unified-5h-reset"]) if hdrs.get("anthropic-ratelimit-unified-5h-reset") else None,
+                "binding_limit": hdrs.get("anthropic-ratelimit-unified-representative-claim"),
+                "sonnet_fallback": hdrs.get("anthropic-ratelimit-unified-fallback"),
+            }
+            state_path = "/root/.nanobot/workspace/memory/rate_limits.json"
+            os.makedirs(os.path.dirname(state_path), exist_ok=True)
+            with open(state_path, "w") as f:
+                json.dump(rate_limit_state, f, indent=2)
+        except Exception as e:
+            logger.warning("Rate limit header capture failed: {}", e)
+
         if response.status_code != 200:
             error_text = response.text
             raise Exception(f"Anthropic API error {response.status_code}: {error_text}")