app/priv/blog/engineering/2026/04-24-how-to-get-started-with-the-pi-coding-agent-on-a-vps.md

@@ -2,8 +2,8 @@
   title: "How to get started with the Pi coding agent (on a VPS)",
   author: "Willem",
   tags: ~w(agentic-engeeringing getting-started how-to),
-  description: "Setting up Pi on a VPS is easier than I thought. Open source with a great unboxing experience. Follow along and enjoy!",
+  description: "",
-  published: true
+  published: false
 }
 ---
 
@@ -65,15 +65,37 @@ One thing you can do in Pi without a model, is use `!` to run a shell command. I
 
 ``` sh
 !cat  [..]/lib/node_modules/@mariozechner/pi-coding-agent/docs/providers.md
+ ```
+ [..]
+
+ ## Custom Providers
+
+ **Via models.json:** Add Ollama, LM Studio, vLLM, or any provider that speaks a supported API (OpenAI Completions, OpenAI Responses, Anthropic Messages, Google Generative AI). See [models.md](models.md).
+
+ ## Resolution Order
+
+ When resolving credentials for a provider:
+
+ 1. CLI `--api-key` flag
+ 2. `auth.json` entry (API key or OAuth token)
+ 3. Environment variable
+ 4. Custom provider keys from `models.json`
+
+
+ ... 179 more lines (ctrl+o to expand)
+
 ```
 
-Now we can edit `$HOME/pi/agent/models.json` to set our provider endpoint and api key. You can specify models there as well, but that is not necessary to get started. `/model` in the UI lets you search provided models.
+I prefer the environment variable, so I don't have it in a text file, but the latter is more fire and forget. Up to you.` If you press ctrl+o you can probably find exactly what you need for your provider.
+Because Pi can hot-reload it's configuration files, and everything can go in one file, I will start there.
+
+Now we can edit `$HOME/pi/agent/models.json` to set our provider endpoint and first model.
 
 I already have set up 'pi' on another machine, so I asked it. Next section co-written with Qwen3.6:27b :
 
 
-Tell Pi where your LLM is hosted (by Qwen)
+Tell Pi where your LLM is hosted, and what model you want to use
----
+====
 
 Pi has built-in OpenRouter support. You just need to configure it in ~/.pi/agent/models.json.
 
@@ -103,30 +125,31 @@ Pi has built-in OpenRouter support. You just need to configure it in ~/.pi/agent
  1. Open Pi and run /model to see available OpenRouter models
  2. Pick one with /model openrouter/anthropic/claude-sonnet-4 (or whatever model you want)
 
+ Per-Model Routing (Optional)
+
+ You can control which upstream provider OpenRouter routes to using modelOverrides:
+
+ ```json
+   {
+     "providers": {
+       "openrouter": {
+         "apiKey": "OPENROUTER_API_KEY",
+         "modelOverrides": {
+           "anthropic/claude-sonnet-4": {
+             "compat": {
+               "openRouterRouting": {
+                 "only": ["anthropic"]
+               }
+             }
+           }
+         }
+       }
+     }
+   }
+ ```
 
  See the full compat.openRouterRouting options in the models docs for order, ignore, max_price, preferred_min_throughput, etc.
 
-First prompt
-----
-
-Finally, we can issue a prompt. I learned (from Claude Code) that asking a model to write a haiku is a way to get started when you just want to see if it works. Sometimes I put my frustrations in the prompt. Not this time.
-
-> Model: qwen3.5:35b-a3b
-
-
-Me: write a haiku
-
-
-(reasoning tokens:) 
-> The user is asking me to write a haiku. A haiku is a form of Japanese poetry with three lines following a 5-7-5 syllable pattern. Let me write one about nature, which is the traditional subject.
-
-> Soft rain falls gently,
-> Droplets kiss the green leaves now,
-> Spring's breath fills the air.
- 
-I hope this works for you. Enjoy!
-
-
 Afterword
 ----