feat: add OpenRouter and Together AI provider support

.gitignore

@@ -62,3 +62,4 @@ __pycache__/
 # Config files with real API keys (for local testing)
 *-config-with-keys*
 *-with-keys*
+.rocketride/

demos/test-config-bad-provider

@@ -0,0 +1,4 @@
+# Test fixture: unknown provider name should raise an error on load.
+provider=opanai
+openai_api_key=test-key
+model=gpt-4o-mini

demos/tests/README.md

@@ -15,12 +15,17 @@ This suite is not part of default `sbt test`.
 ## Files
 
 - `tests.nlogox` - Manual test model
-- `config.txt` - Local config used by the model
+- `config.txt.example` - Template with placeholders for all 6 providers
+- `config.txt` - Local config used by the model (gitignored, create from template)
 
 ## Prerequisites
 
 1. Build and install the extension
-2. Configure valid credentials in `config.txt` for cloud providers, or run Ollama locally
+2. Create a local config from the template:
+   ```
+   cp config.txt.example config.txt
+   ```
+   Then edit `config.txt`, set `provider=` to your chosen provider, and replace the matching `*_api_key=REPLACE_ME` line with a real key. Or run Ollama locally for a no-key option.
 3. Ensure network access for cloud providers
 
 ## How To Run

demos/tests/config.txt.example

@@ -0,0 +1,47 @@
+# NetLogo LLM Extension — Test Configuration (Template)
+#
+# Copy this file to `config.txt` in the same directory and fill in
+# the API key for whichever provider you want to test:
+#
+#     cp config.txt.example config.txt
+#
+# `config.txt` is gitignored so your real key stays local.
+#
+# To switch providers: change `provider=` and `model=` below, then
+# uncomment the matching api_key line. Only one provider runs at a time.
+
+provider=openrouter
+model=openai/gpt-4o-mini
+
+temperature=0.7
+max_tokens=200
+timeout_seconds=60
+
+# --- OpenRouter (https://openrouter.ai/keys) ---
+openrouter_api_key=REPLACE_ME
+# Sample models:
+#   openai/gpt-4o-mini
+#   anthropic/claude-3.5-haiku
+#   deepseek/deepseek-r1
+
+# --- Together AI (https://api.together.ai/settings/api-keys) ---
+# together_api_key=REPLACE_ME
+# Sample models:
+#   meta-llama/Llama-3.3-70B-Instruct-Turbo
+#   deepseek-ai/DeepSeek-R1
+
+# --- OpenAI ---
+# openai_api_key=sk-REPLACE_ME
+# model: gpt-4o-mini
+
+# --- Anthropic (Claude) ---
+# anthropic_api_key=sk-ant-REPLACE_ME
+# model: claude-3-5-haiku-latest
+
+# --- Google Gemini ---
+# gemini_api_key=REPLACE_ME
+# model: gemini-1.5-flash
+
+# --- Ollama (local) ---
+# ollama_base_url=http://localhost:11434
+# model: llama3.2