Goose
Connect the Goose CLI to Divyam for reading files, editing code and running project commands.
You need a Divyam account and an API key. If you don't have them yet, follow Getting Started first.
Replace the shortened divyam-sw-v1-... shown in examples with your complete API key.
The examples use divyam-as/gpt-6-sol. For another model, select its current ID in your harness or copy it from Models and pricing, and check its context limit and supported features.
1. Install Goose
Install the Goose CLI using the official instructions.
2. Configure the OpenAI provider
These steps replace the URL, key and model in Goose's saved OpenAI connection with Divyam's values. Later sessions using that connection use Divyam. This guide does not create a separate provider named Divyam.
Run the provider wizard:
goose configure
Choose Manual Configuration on first setup, or Configure Providers if Goose is already configured. Then select OpenAI and enter:
| Setting | Value |
|---|---|
| OPENAI_API_KEY | divyam-sw-v1-... (replace with your key) |
| OPENAI_HOST | https://api.preview.divyam.ai/v1 |
| OPENAI_BASE_PATH | chat/completions |
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
| Setting | Value |
|---|---|
| Model | divyam-as/gpt-6-sol |
Keep /v1 on the host and chat/completions as the path. These values select Chat Completions. If the installer already opened this wizard, complete it there.
3. Start an interactive session
The Developer extension supplies file editing and shell commands and is enabled by default. If you disabled it, run goose configure → Toggle Extensions and enable developer.
From your project folder, run:
goose
Hello, what are your capabilities?
With the optional Summon extension, Goose's parent agent can misinterpret a completed child result. Conversation compaction can lose prior details.
To inspect a local image, ask Goose to read its path with read_image. The Developer extension supplies this tool.
Check your requests
Open the Divyam console and select Logs. Your requests appear there within a few seconds, newest first, with their status, token counts and latency. Usage and Credits & Billing catch up within a few minutes.
Some clients display zero when model prices are missing. Check Credits & Billing for Divyam charges. Local dollar limits depend on the client's price and usage data.
For filters, cached-token counts and the requested-versus-routed view, see Logs and usage.