feat: add OLLAMA_NUM_CTX config to cap context window (#83)

- Add ollama_num_ctx setting (default 4096) to config.py
- Pass num_ctx option to Ollama in agent.py and agents/base.py
- Add OLLAMA_NUM_CTX to .env.example with usage docs
- Add context_window note in providers.yaml
- Fix mock_settings in test_agent.py for new attribute
- qwen3:30b with 4096 ctx uses ~19GB vs 45GB default

src/config.py

@@ -22,6 +22,11 @@ class Settings(BaseSettings):
     # llama3.2 (3B) hallucinated tool output consistently in testing.
     ollama_model: str = "qwen3.5:latest"
 
+    # Context window size for Ollama inference — override with OLLAMA_NUM_CTX
+    # qwen3:30b with default context eats 45GB on a 39GB Mac.
+    # 4096 keeps memory at ~19GB. Set to 0 to use model defaults.
+    ollama_num_ctx: int = 4096
+
     # Fallback model chains — override with FALLBACK_MODELS / VISION_FALLBACK_MODELS
     # as comma-separated strings, e.g. FALLBACK_MODELS="qwen3.5:latest,llama3.1"
     # Or edit config/providers.yaml → fallback_chains for the canonical source.

src/timmy/agent.py

@@ -306,9 +306,12 @@ def create_timmy(
         logger.warning("Failed to load memory context: %s", exc)
         full_prompt = base_prompt
 
+    model_kwargs = {}
+    if settings.ollama_num_ctx > 0:
+        model_kwargs["options"] = {"num_ctx": settings.ollama_num_ctx}
     agent = Agent(
         name="Agent",
-        model=Ollama(id=model_name, host=settings.ollama_url, timeout=300),
+        model=Ollama(id=model_name, host=settings.ollama_url, timeout=300, **model_kwargs),
         db=SqliteDb(db_file=db_file),
         description=full_prompt,
         add_history_to_context=True,

src/timmy/agents/base.py

@@ -73,9 +73,12 @@ class BaseAgent(ABC):
                 if handler:
                     tool_instances.append(handler)
 
+        ollama_kwargs = {}
+        if settings.ollama_num_ctx > 0:
+            ollama_kwargs["options"] = {"num_ctx": settings.ollama_num_ctx}
         return Agent(
             name=self.name,
-            model=Ollama(id=self.model, host=settings.ollama_url, timeout=300),
+            model=Ollama(id=self.model, host=settings.ollama_url, timeout=300, **ollama_kwargs),
             description=system_prompt,
             tools=tool_instances if tool_instances else None,
             add_history_to_context=True,