Increase subagent max_iterations from 15 to 50

Dockerfile.oauth

@@ -56,7 +56,7 @@ ENV PATH="/root/.local/bin:${PATH}"
 
 COPY pyproject.toml README.md LICENSE /app/
 COPY nanobot/ /app/nanobot/
-RUN uv pip install --system --no-cache --reinstall /app psycopg2-binary
+RUN uv pip install --system --no-cache --reinstall /app
 
 ENTRYPOINT ["nanobot"]
 CMD ["gateway"]

nanobot/agent/loop.py

@@ -424,9 +424,7 @@ Respond with ONLY valid JSON, no markdown fences."""
                     {"role": "system", "content": "You are a memory consolidation agent. Respond only with valid JSON."},
                     {"role": "user", "content": prompt},
                 ],
-                model="claude-haiku-4-5",
-                thinking_budget=0,
-                max_tokens=16384,
+                model=self.model,
             )
             text = (response.content or "").strip()
             if text.startswith("```"):

nanobot/providers/anthropic_oauth.py

@@ -225,7 +225,6 @@ class AnthropicOAuthProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         tools: list[dict[str, Any]] | None = None,
-        thinking_budget_override: int | None = None,
     ) -> dict[str, Any]:
         """Make request to Anthropic API."""
         client = await self._get_client()
@@ -237,15 +236,14 @@ class AnthropicOAuthProvider(LLMProvider):
         }
 
         # Extended thinking: temperature must be 1 when enabled
-        effective_thinking = thinking_budget_override if thinking_budget_override is not None else self.thinking_budget
-        if effective_thinking > 0:
+        if self.thinking_budget > 0:
             payload["temperature"] = 1
             # max_tokens must exceed budget_tokens
-            if max_tokens <= effective_thinking:
-                payload["max_tokens"] = effective_thinking + 4096
+            if max_tokens <= self.thinking_budget:
+                payload["max_tokens"] = self.thinking_budget + 4096
             payload["thinking"] = {
                 "type": "enabled",
-                "budget_tokens": effective_thinking,
+                "budget_tokens": self.thinking_budget,
             }
         else:
             payload["temperature"] = temperature
@@ -268,43 +266,6 @@ class AnthropicOAuthProvider(LLMProvider):
             json=payload,
         )
 
-        # Dump rate limit headers for analysis
-        try:
-            import datetime, 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")
-        except Exception:
-            pass
-
-        # Capture rate limit state for heartbeat throttling
-        try:
-            import datetime, os
-            headers = response.headers
-            rate_limit_state = {
-                "updated_at": datetime.datetime.utcnow().isoformat(),
-                "model": payload.get("model"),
-                "weekly_all_models": float(headers.get("anthropic-ratelimit-unified-7d-utilization", 0)) if headers.get("anthropic-ratelimit-unified-7d-utilization") else None,
-                "weekly_sonnet": float(headers.get("anthropic-ratelimit-unified-7d_sonnet-utilization", 0)) if headers.get("anthropic-ratelimit-unified-7d_sonnet-utilization") else None,
-                "session_5h": float(headers.get("anthropic-ratelimit-unified-5h-utilization", 0)) if headers.get("anthropic-ratelimit-unified-5h-utilization") else None,
-                "weekly_reset": int(headers.get("anthropic-ratelimit-unified-7d-reset", 0)) if headers.get("anthropic-ratelimit-unified-7d-reset") else None,
-                "session_reset": int(headers.get("anthropic-ratelimit-unified-5h-reset", 0)) if headers.get("anthropic-ratelimit-unified-5h-reset") else None,
-                "binding_limit": headers.get("anthropic-ratelimit-unified-representative-claim"),
-                "sonnet_fallback": headers.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:
-            pass
-
         if response.status_code != 200:
             error_text = response.text
             raise Exception(f"Anthropic API error {response.status_code}: {error_text}")
@@ -318,7 +279,6 @@ class AnthropicOAuthProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
-        thinking_budget: int | None = None,
     ) -> LLMResponse:
         """Send chat completion request to Anthropic API."""
         model = model or self.default_model
@@ -333,9 +293,6 @@ class AnthropicOAuthProvider(LLMProvider):
         system, prepared_messages = self._prepare_messages(messages)
         anthropic_tools = self._convert_tools_to_anthropic(tools)
 
-        # Per-call thinking override (None = use instance default)
-        effective_thinking = self.thinking_budget if thinking_budget is None else thinking_budget
-
         try:
             response = await self._make_request(
                 messages=prepared_messages,
@@ -344,7 +301,6 @@ class AnthropicOAuthProvider(LLMProvider):
                 max_tokens=max_tokens,
                 temperature=temperature,
                 tools=anthropic_tools,
-                thinking_budget_override=effective_thinking,
             )
             return self._parse_response(response)
         except Exception as e:

nanobot/providers/base.py

@@ -48,7 +48,6 @@ class LLMProvider(ABC):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
-        thinking_budget: int | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request.

nanobot/providers/litellm_provider.py

@@ -106,7 +106,6 @@ class LiteLLMProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
-        thinking_budget: int | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request via LiteLLM.