Mirror_Repos/Kilo-Org_kilocode
2
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

docs: document auto-detect models for custom providers and settings export/import (#7824)

Browse Source 
* docs: add auto-detect models for custom providers, update settings export/import

- openai-compatible.md: document automatic model detection from /v1/models
  endpoint when setting up custom OpenAI-compatible providers (#7793)
- settings/index.md: update VSCode tab to describe the new Export/Import
  buttons in the About Kilo Code settings tab (#7794)

* Update packages/kilo-docs/pages/getting-started/settings/index.md

Co-authored-by: kilo-code-bot[bot] <240665456+kilo-code-bot[bot]@users.noreply.github.com>

---------

Co-authored-by: scuttlebot <scuttlebot@olearycrew.com>
Co-authored-by: Brendan O'Leary <github@olearycrew.com>
Co-authored-by: kilo-code-bot[bot] <240665456+kilo-code-bot[bot]@users.noreply.github.com>
Co-authored-by: Johnny Amancio <johnnyeric@gmail.com>
This commit is contained in:
Scuttle Bot
2026-04-23 13:35:25 -04:00
committed by GitHub
parent 8853ff5811
commit 0a39e11a04
2 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/kilo-docs/pages/ai-providers/openai-compatible.md
+13 -1
View File
@@ -53,13 +53,25 @@ You'll find these settings in the Kilo Code settings panel (click the {% codicon
- **Display name** — A human-readable name shown in the UI.
- **Base URL** — The provider's OpenAI-compatible API endpoint (e.g., `https://api.your-provider.com/v1`). Kilo auto-fetches available models when a valid URL is entered.
- **API key** — Your API key. Optional — leave empty if authentication is handled via headers.
- **Models** — Add models manually or select from the auto-fetched list.
- **Models** — Add models manually or select from the auto-fetched list (see [Automatic Model Detection](#automatic-model-detection) below).
- **Headers** (optional) — Custom HTTP headers as key-value pairs.
4. Click **Submit** to save. The provider's models appear in the model picker.
For additional model configuration (token limits, tool calling, variants), edit the `kilo.jsonc` config file directly — see the **CLI** tab or the [Custom Models](/docs/code-with-ai/agents/custom-models) guide.
### Automatic Model Detection
When configuring a custom OpenAI-compatible provider, Kilo Code can automatically detect available models from your provider's `/v1/models` endpoint.
Once you enter a valid **Base URL** and **API Key**, Kilo Code will query the provider and present a searchable model picker with all available models. You can:
- **Search** with fuzzy matching (e.g., typing "gpt4o" finds "gpt-4o-mini")
- **Select** individual models to add to the provider configuration
- **Edit** an existing custom provider to add or remove models later
This eliminates the need to manually look up and type model IDs. If auto-detection fails (for example, if the provider doesn't support the `/v1/models` endpoint), you can still enter model IDs manually.
{% /tab %}
{% tab label="CLI" %}
packages/kilo-docs/pages/getting-started/settings/index.md
+6 -1
View File
@@ -47,7 +47,12 @@ If you check config files into version control, make sure they do not contain AP
### Export and Import
Config files are plain-text and portable — copy them between machines and you're done.
You can export and import settings from the **About Kilo Code** tab in the Settings UI:
- **Export**: Saves your global config as a `kilo-settings.json` file. Review it before sharing, because config values are exported as-is.
- **Import**: Loads a previously exported JSON file into the settings draft. Changes are not applied immediately — you can review them and click Save or Discard, just like any manual edit.
Config files are also plain-text and portable — you can copy `~/.config/kilo/kilo.jsonc` between machines directly.
{% /tab %}
{% tab label="CLI" %}