mirror of
https://github.com/fosrl/docs-v2.git
synced 2026-08-31 03:01:30 +02:00
First pass on connections for different clients and new features
This commit is contained in:
Owen
14
docs.json
14
docs.json
@@ -184,6 +184,20 @@
|
||||
"manage/remote-node/backhaul"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "AI Gateway",
|
||||
"icon": "robot",
|
||||
"pages": [
|
||||
"manage/ai/overview",
|
||||
"manage/ai/claude",
|
||||
"manage/ai/codex",
|
||||
"manage/ai/opencode",
|
||||
"manage/ai/gemini",
|
||||
"manage/ai/open-webui",
|
||||
"manage/ai/claude-desktop",
|
||||
"manage/ai/openclaw"
|
||||
]
|
||||
},
|
||||
"manage/endpoints-and-pops",
|
||||
"manage/integration-api",
|
||||
"manage/branding"
|
||||
|
||||
35
manage/ai/claude-desktop.mdx
Normal file
35
manage/ai/claude-desktop.mdx
Normal file
@@ -0,0 +1,35 @@
|
||||
---
|
||||
title: "Claude Desktop"
|
||||
description: "Connect Claude Desktop's third-party inference to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
Claude Desktop can route its requests through a third-party inference gateway instead of Anthropic directly. Point it at an AI Gateway resource that has an Anthropic-compatible provider attached — Anthropic itself, Bedrock, Vertex AI, or a custom Anthropic-compatible endpoint. See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Steps
|
||||
|
||||
1. Open Claude Desktop, go to the menu in the top left and select **Help > Troubleshooting**, and turn on **Developer Mode**.
|
||||
2. From the menu bar, open **Developer**, then **Configure Third-Party Inference…**.
|
||||
3. Select **Gateway**
|
||||
4. Select **Credential kind** > **Static API Key**.
|
||||
3. Fill in:
|
||||
- **Gateway base URL:** `<endpoint>`
|
||||
- **Gateway API Key:** `<key>`
|
||||
4. Restart Claude Desktop.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/claude-desktop-inference-dialog.png`
|
||||
The "Configure Third-Party Inference" dialog with the Gateway URL and API Key fields filled in.
|
||||
<Frame>
|
||||
<img src="/images/ai/claude-desktop-inference-dialog.png" alt="Claude Desktop third-party inference settings" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
Send a message to confirm it's working — check the resource's activity in Pangolin's logs if you want to verify traffic is actually flowing through the gateway rather than straight to Anthropic.
|
||||
|
||||
For a private resource, put `none` in the API Key field rather than leaving it blank, and make sure the Pangolin client is installed and connected on the same machine as Claude Desktop.
|
||||
133
manage/ai/claude.mdx
Normal file
133
manage/ai/claude.mdx
Normal file
@@ -0,0 +1,133 @@
|
||||
---
|
||||
title: "Claude Code"
|
||||
description: "Connect Claude Code to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
Claude Code talks the Anthropic Messages API, so the resource you point it at needs an Anthropic-compatible provider attached - Anthropic itself, Bedrock, Vertex AI, or a custom Anthropic-compatible endpoint like Kimi K2. See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Fastest: Pangolin CLI
|
||||
|
||||
[Install the Pangolin CLI](/manage/clients/install-client#quick-install-recommended) if you don't have it, then log in:
|
||||
|
||||
```bash
|
||||
pangolin login
|
||||
```
|
||||
|
||||
Configure Claude Code against a resource:
|
||||
|
||||
```bash
|
||||
pangolin configure claude
|
||||
```
|
||||
|
||||
This prompts you to pick an organization and resource if you have more than one, fetches a key for you if the resource needs one, and writes `~/.claude/settings.json`. To skip the prompts:
|
||||
|
||||
```bash
|
||||
pangolin configure claude --resource <resource-niceid-or-domain>
|
||||
```
|
||||
|
||||
To undo it:
|
||||
|
||||
```bash
|
||||
pangolin configure claude --reset
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/claude-cli-tab.png`
|
||||
The Claude Code card on a resource's Keys page, expanded, with the CLI tab selected showing the `pangolin configure claude` command.
|
||||
<Frame>
|
||||
<img src="/images/ai/claude-cli-tab.png" alt="Claude Code CLI setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## Manual setup
|
||||
|
||||
Pick the preset that matches your provider.
|
||||
|
||||
### Default (Anthropic)
|
||||
|
||||
Write `~/.claude/settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"apiKeyHelper": "echo '<key>'",
|
||||
"env": {
|
||||
"ANTHROPIC_BASE_URL": "<endpoint>"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Or, for a one-off shell session instead of a permanent settings file:
|
||||
|
||||
```bash
|
||||
export ANTHROPIC_BASE_URL=<endpoint>
|
||||
export ANTHROPIC_API_KEY=<key>
|
||||
claude
|
||||
```
|
||||
|
||||
For a private resource, keep `apiKeyHelper`/`ANTHROPIC_API_KEY` in place and set the key to `none`. Claude Code only calls `apiKeyHelper` if it's present, and falls back to whatever account you're already signed into if it isn't - so removing it sends your traffic to Anthropic instead of through the gateway.
|
||||
|
||||
### Amazon Bedrock
|
||||
|
||||
Use this when the resource has a Bedrock provider attached. Write `~/.claude/settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"env": {
|
||||
"ANTHROPIC_MODEL": "claude-sonnet-4-6",
|
||||
"ANTHROPIC_BEDROCK_BASE_URL": "<endpoint>/bedrock",
|
||||
"CLAUDE_CODE_USE_BEDROCK": "1",
|
||||
"CLAUDE_CODE_SKIP_BEDROCK_AUTH": "1"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Google Vertex AI
|
||||
|
||||
Use this when the resource has a Vertex AI provider attached. Write `~/.claude/settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"env": {
|
||||
"CLOUD_ML_REGION": "global",
|
||||
"ANTHROPIC_VERTEX_PROJECT_ID": "<your-gcp-project-id>",
|
||||
"CLAUDE_CODE_USE_VERTEX": "1",
|
||||
"CLAUDE_CODE_SKIP_VERTEX_AUTH": "1",
|
||||
"ANTHROPIC_VERTEX_BASE_URL": "<endpoint>/v1"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Replace `<your-gcp-project-id>` with your actual GCP project ID.
|
||||
|
||||
### Kimi K2 (Moonshot AI)
|
||||
|
||||
Use this when the resource has a custom provider pointed at Moonshot AI's Anthropic-compatible endpoint. Write `~/.claude/settings.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"apiKeyHelper": "echo '<key>'",
|
||||
"env": {
|
||||
"ANTHROPIC_BASE_URL": "<endpoint>/anthropic",
|
||||
"ANTHROPIC_MODEL": "kimi-k2",
|
||||
"ANTHROPIC_DEFAULT_OPUS_MODEL": "kimi-k2",
|
||||
"ANTHROPIC_DEFAULT_SONNET_MODEL": "kimi-k2",
|
||||
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "kimi-k2",
|
||||
"CLAUDE_CODE_SUBAGENT_MODEL": "kimi-k2",
|
||||
"ENABLE_TOOL_SEARCH": "false"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/claude-manual-tab.png`
|
||||
The same card with the Manual tab selected and the preset dropdown open, showing Default/Bedrock/Vertex/Kimi options.
|
||||
<Frame>
|
||||
<img src="/images/ai/claude-manual-tab.png" alt="Claude Code manual setup presets" />
|
||||
</Frame>
|
||||
*/}
|
||||
76
manage/ai/codex.mdx
Normal file
76
manage/ai/codex.mdx
Normal file
@@ -0,0 +1,76 @@
|
||||
---
|
||||
title: "Codex"
|
||||
description: "Connect Codex to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
Codex talks the OpenAI API, so the resource you point it at needs an OpenAI-compatible provider attached — OpenAI, OpenRouter, Vercel AI Gateway, Microsoft Foundry, or a custom OpenAI-compatible endpoint. See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Fastest: Pangolin CLI
|
||||
|
||||
[Install the Pangolin CLI](/manage/clients/install-client#quick-install-recommended) if you don't have it, then log in:
|
||||
|
||||
```bash
|
||||
pangolin login
|
||||
```
|
||||
|
||||
Configure Codex against a resource:
|
||||
|
||||
```bash
|
||||
pangolin configure codex
|
||||
```
|
||||
|
||||
This prompts you to pick an organization and resource if you have more than one, fetches a key for you if the resource needs one, and merges a `pangolin` provider into `~/.codex/config.toml` without touching anything else in that file. To skip the prompts:
|
||||
|
||||
```bash
|
||||
pangolin configure codex --resource <resource-niceid-or-domain>
|
||||
```
|
||||
|
||||
To undo it:
|
||||
|
||||
```bash
|
||||
pangolin configure codex --reset
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/codex-cli-tab.png`
|
||||
The Codex card on a resource's Keys page, expanded, with the CLI tab selected showing the `pangolin configure codex` command.
|
||||
<Frame>
|
||||
<img src="/images/ai/codex-cli-tab.png" alt="Codex CLI setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## Manual setup
|
||||
|
||||
Merge this into `~/.codex/config.toml` (honors `$CODEX_HOME` if you've set it):
|
||||
|
||||
```toml
|
||||
model_provider = "pangolin"
|
||||
|
||||
[model_providers.pangolin]
|
||||
name = "Pangolin AI Gateway"
|
||||
base_url = "<endpoint>/v1"
|
||||
wire_api = "responses"
|
||||
env_key = "PANGOLIN_API_KEY"
|
||||
```
|
||||
|
||||
Codex reads the key from the environment variable named in `env_key`, not from the file. Before running Codex, export it in your shell:
|
||||
|
||||
```bash
|
||||
export PANGOLIN_API_KEY=<key>
|
||||
```
|
||||
|
||||
Codex is the one client here that also tolerates no key at all: for a private resource you can drop the `env_key` line and skip the export entirely. Exporting `PANGOLIN_API_KEY=none` works too, so use whichever you find clearer.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/codex-manual-tab.png`
|
||||
The same card with the Manual tab selected, showing the config.toml snippet.
|
||||
<Frame>
|
||||
<img src="/images/ai/codex-manual-tab.png" alt="Codex manual setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
75
manage/ai/gemini.mdx
Normal file
75
manage/ai/gemini.mdx
Normal file
@@ -0,0 +1,75 @@
|
||||
---
|
||||
title: "Gemini CLI"
|
||||
description: "Connect Gemini CLI to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
Gemini CLI talks Google's native `generateContent` API, so the resource you point it at needs a Google Gemini (or Vertex AI) provider attached. See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Fastest: Pangolin CLI
|
||||
|
||||
[Install the Pangolin CLI](/manage/clients/install-client#quick-install-recommended) if you don't have it, then log in:
|
||||
|
||||
```bash
|
||||
pangolin login
|
||||
```
|
||||
|
||||
Configure Gemini CLI against a resource:
|
||||
|
||||
```bash
|
||||
pangolin configure gemini
|
||||
```
|
||||
|
||||
This prompts you to pick an organization and resource if you have more than one, fetches a key for you if the resource needs one, and writes `~/.gemini/.env` - the file Gemini CLI loads automatically on every run, regardless of which directory you start it from. To skip the prompts:
|
||||
|
||||
```bash
|
||||
pangolin configure gemini --resource <resource-niceid-or-domain>
|
||||
```
|
||||
|
||||
To undo it:
|
||||
|
||||
```bash
|
||||
pangolin configure gemini --reset
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/gemini-cli-tab.png`
|
||||
The Gemini CLI card on a resource's Keys page, expanded, with the CLI tab selected showing the `pangolin configure gemini` command.
|
||||
<Frame>
|
||||
<img src="/images/ai/gemini-cli-tab.png" alt="Gemini CLI setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## Manual setup
|
||||
|
||||
Write `~/.gemini/.env`:
|
||||
|
||||
```bash
|
||||
GOOGLE_GEMINI_BASE_URL=<endpoint>
|
||||
GEMINI_API_KEY=<key>
|
||||
```
|
||||
|
||||
Gemini CLI also checks a project-local `.env` first (in the current directory or a parent, up to `.git` or your home directory) before falling back to `~/.gemini/.env`, so a project-level file with the same two lines overrides this for just that project.
|
||||
|
||||
Or, for a one-off shell session instead of a permanent file:
|
||||
|
||||
```bash
|
||||
export GOOGLE_GEMINI_BASE_URL=<endpoint>
|
||||
export GEMINI_API_KEY=<key>
|
||||
gemini
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/gemini-manual-tab.png`
|
||||
The same card with the Manual tab selected, showing the .env file and shell snippets.
|
||||
<Frame>
|
||||
<img src="/images/ai/gemini-manual-tab.png" alt="Gemini CLI manual setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
For a private resource, keep `GEMINI_API_KEY` in place and set it to `none`. Gemini CLI won't start without it set to something.
|
||||
55
manage/ai/open-webui.mdx
Normal file
55
manage/ai/open-webui.mdx
Normal file
@@ -0,0 +1,55 @@
|
||||
---
|
||||
title: "Open WebUI"
|
||||
description: "Connect Open WebUI to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
Open WebUI is a self-hosted chat interface. It talks the OpenAI API, so point it at an AI Gateway resource that has an OpenAI-compatible provider attached (OpenAI, OpenRouter, Vercel AI Gateway, Microsoft Foundry, or custom). See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## If you're running Open WebUI for the first time
|
||||
|
||||
```bash
|
||||
docker run -d -p 3000:8080 \
|
||||
-e OPENAI_API_BASE_URL=<endpoint>/v1 \
|
||||
-e OPENAI_API_KEY=<key> \
|
||||
-v open-webui:/app/backend/data \
|
||||
--name open-webui \
|
||||
--restart always \
|
||||
ghcr.io/open-webui/open-webui:main
|
||||
```
|
||||
|
||||
Open `http://localhost:3000`, finish the first-run account setup, and your Pangolin gateway is already the active connection.
|
||||
|
||||
## If Open WebUI is already running
|
||||
|
||||
Go to **Settings → Connections** and add a connection:
|
||||
|
||||
- **URL:** `<endpoint>/v1`
|
||||
- **Key:** `<key>`
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/openwebui-connections.png`
|
||||
Open WebUI's Settings → Connections page with the Pangolin gateway URL and key filled in.
|
||||
<Frame>
|
||||
<img src="/images/ai/openwebui-connections.png" alt="Open WebUI connection settings" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
Save, then open a new chat - the models exposed by your resource's attached provider(s) show up in the model picker.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/openwebui-model-picker.png`
|
||||
The Open WebUI model picker showing models served through the Pangolin gateway.
|
||||
<Frame>
|
||||
<img src="/images/ai/openwebui-model-picker.png" alt="Open WebUI model picker" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
For a private resource, set the key to `none` rather than leaving it blank. Open WebUI treats a blank key as "no connection configured" and won't list the models.
|
||||
|
||||
Note that Open WebUI runs as a server, not on your laptop - so it's the Open WebUI host that needs the Pangolin client installed and connected to reach a private resource, not the browser you're viewing it from.
|
||||
97
manage/ai/openclaw.mdx
Normal file
97
manage/ai/openclaw.mdx
Normal file
@@ -0,0 +1,97 @@
|
||||
---
|
||||
title: "OpenClaw"
|
||||
description: "Connect OpenClaw to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
[OpenClaw](https://openclaw.ai) is an open-source agent gateway that can run against any OpenAI- or Anthropic-compatible endpoint. Point it at an AI Gateway resource with a matching provider attached - OpenAI-compatible (OpenAI, OpenRouter, Vercel AI Gateway, Microsoft Foundry, custom) or Anthropic-compatible (Anthropic, Bedrock, Vertex AI, custom). See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`), both on the resource's Keys page, plus the name of a model your attached provider actually serves (e.g. `gpt-4o`, `claude-sonnet-4-6`) - that's `<model-id>` below.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
# macOS/Linux
|
||||
curl -fsSL https://openclaw.ai/install.sh | bash
|
||||
|
||||
# Windows PowerShell
|
||||
iwr -useb https://openclaw.ai/install.ps1 | iex
|
||||
```
|
||||
|
||||
## Connect it to your resource
|
||||
|
||||
```bash
|
||||
openclaw onboard --non-interactive --accept-risk \
|
||||
--auth-choice custom-api-key \
|
||||
--custom-base-url "<endpoint>/v1" \
|
||||
--custom-model-id "<model-id>" \
|
||||
--custom-api-key "<key>" \
|
||||
--custom-compatibility openai \
|
||||
--install-daemon --skip-channels --skip-skills
|
||||
```
|
||||
|
||||
Set `--custom-compatibility anthropic` instead of `openai` if the resource's provider is Anthropic/Bedrock/Vertex rather than OpenAI-compatible, and drop `--custom-base-url`'s trailing `/v1` in that case (Anthropic-style resources are addressed at the endpoint root).
|
||||
|
||||
Prefer the interactive wizard instead:
|
||||
|
||||
```bash
|
||||
openclaw onboard --install-daemon
|
||||
```
|
||||
|
||||
When prompted, choose **QuickStart or Manual mode**, select the custom/OpenAI-compatible provider option, and enter the base URL and key.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/openclaw-onboard.png`
|
||||
The `openclaw onboard` interactive wizard at the provider selection step.
|
||||
<Frame>
|
||||
<img src="/images/ai/openclaw-onboard.png" alt="OpenClaw onboarding wizard" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## Manual setup
|
||||
|
||||
Onboarding writes `~/.openclaw/openclaw.json`. You can edit it directly instead - changes reload automatically:
|
||||
|
||||
```json
|
||||
{
|
||||
"models": {
|
||||
"providers": {
|
||||
"pangolin": {
|
||||
"baseUrl": "<endpoint>/v1",
|
||||
"apiKey": "<key>",
|
||||
"api": "openai-completions",
|
||||
"models": [
|
||||
{
|
||||
"id": "<model-id>",
|
||||
"name": "<model-id> via Pangolin"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"agents": {
|
||||
"defaults": {
|
||||
"model": { "primary": "pangolin/<model-id>" }
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
To switch models later without re-editing the file:
|
||||
|
||||
```bash
|
||||
openclaw models set pangolin/<model-id>
|
||||
```
|
||||
|
||||
## Verify
|
||||
|
||||
```bash
|
||||
openclaw health
|
||||
openclaw models status
|
||||
openclaw agent --agent main -m "Hello, what model are you?"
|
||||
```
|
||||
|
||||
For a private resource, keep `--custom-api-key`/`apiKey` and set it to `none`, and make sure the Pangolin client is connected on whichever machine runs the OpenClaw daemon.
|
||||
97
manage/ai/opencode.mdx
Normal file
97
manage/ai/opencode.mdx
Normal file
@@ -0,0 +1,97 @@
|
||||
---
|
||||
title: "OpenCode"
|
||||
description: "Connect OpenCode to a Pangolin AI Gateway resource"
|
||||
---
|
||||
|
||||
OpenCode configures each model provider separately, so it can talk to whichever API formats your resource supports — Anthropic Messages, OpenAI Chat/Responses, or both, depending on which providers are attached. See [AI Gateway Overview](/manage/ai/overview) if you haven't set that up yet.
|
||||
|
||||
import AiGatewayKey from "/snippets/ai-gateway-key.mdx";
|
||||
|
||||
You'll need the resource's URL (its `<endpoint>`) and its API key (`<key>`). Both are on the resource's Keys page.
|
||||
|
||||
<AiGatewayKey />
|
||||
|
||||
## Fastest: Pangolin CLI
|
||||
|
||||
[Install the Pangolin CLI](/manage/clients/install-client#quick-install-recommended) if you don't have it, then log in:
|
||||
|
||||
```bash
|
||||
pangolin login
|
||||
```
|
||||
|
||||
Configure OpenCode against a resource:
|
||||
|
||||
```bash
|
||||
pangolin configure opencode
|
||||
```
|
||||
|
||||
This prompts you to pick an organization and resource (if you have more than one), then asks which OpenCode provider ID(s) should point at this gateway — defaults to `anthropic,openai`, but you can enter any comma-separated list OpenCode recognizes (e.g. `openrouter,google`). It fetches a key for you if needed and writes `opencode.json` and `auth.json`. To skip the org/resource prompts:
|
||||
|
||||
```bash
|
||||
pangolin configure opencode --resource <resource-niceid-or-domain>
|
||||
```
|
||||
|
||||
To undo it:
|
||||
|
||||
```bash
|
||||
pangolin configure opencode --reset
|
||||
```
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/opencode-cli-tab.png`
|
||||
The OpenCode card on a resource's Keys page, expanded, with the CLI tab selected showing the `pangolin configure opencode` command.
|
||||
<Frame>
|
||||
<img src="/images/ai/opencode-cli-tab.png" alt="OpenCode CLI setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## Manual setup
|
||||
|
||||
Merge this into your global `opencode.json` (`~/.config/opencode/opencode.json`, or `$XDG_CONFIG_HOME/opencode/opencode.json` if set):
|
||||
|
||||
```json
|
||||
{
|
||||
"$schema": "https://opencode.ai/config.json",
|
||||
"provider": {
|
||||
"anthropic": {
|
||||
"options": {
|
||||
"baseURL": "<endpoint>/v1"
|
||||
}
|
||||
},
|
||||
"openai": {
|
||||
"options": {
|
||||
"baseURL": "<endpoint>/v1"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Then merge your key into `auth.json` (`~/.local/share/opencode/auth.json`, or `$XDG_DATA_HOME/opencode/auth.json` if set):
|
||||
|
||||
```json
|
||||
{
|
||||
"anthropic": {
|
||||
"type": "api",
|
||||
"key": "<key>"
|
||||
},
|
||||
"openai": {
|
||||
"type": "api",
|
||||
"key": "<key>"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
<Warning>
|
||||
`auth.json` is required even for a private resource. OpenCode refuses to start a provider with no key at all and fails with `OpenAI API key is missing. Pass it using the 'apiKey' parameter or the OPENAI_API_KEY environment variable.` Set the key to `none` rather than leaving the entry out.
|
||||
</Warning>
|
||||
|
||||
Only add entries for the providers your resource actually supports. To point a different OpenCode provider (`openrouter`, `google`, `groq`, etc.) at this gateway, add a matching block under `provider` in `opencode.json` and a matching key in `auth.json`.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/opencode-manual-tab.png`
|
||||
The same card with the Manual tab selected, showing the opencode.json/auth.json snippets.
|
||||
<Frame>
|
||||
<img src="/images/ai/opencode-manual-tab.png" alt="OpenCode manual setup" />
|
||||
</Frame>
|
||||
*/}
|
||||
98
manage/ai/overview.mdx
Normal file
98
manage/ai/overview.mdx
Normal file
@@ -0,0 +1,98 @@
|
||||
---
|
||||
title: "AI Gateway Overview"
|
||||
description: "Route coding agents and AI clients through Pangolin with centralized providers and keys"
|
||||
---
|
||||
|
||||
An AI Gateway resource is a normal Pangolin resource that proxies requests to one or more upstream AI providers (OpenAI, Anthropic, Google Gemini, Bedrock, Vertex AI, or a custom endpoint). Point a client at the resource's URL instead of the provider's, and Pangolin handles auth, access control, and logging in front of it.
|
||||
|
||||
## How it fits together
|
||||
|
||||
- **Providers** are configured once per organization - the upstream URL and API key for OpenAI, Anthropic, etc.
|
||||
- **Resources** (type `AI Gateway`) attach one or more of those providers and get a normal Pangolin domain.
|
||||
- **Keys** are what clients authenticate to the resource with. Public resources check them; private resources don't, since only devices on the Pangolin network can reach them at all.
|
||||
|
||||
A resource only understands the API format(s) its attached providers support. An Anthropic provider makes the resource speak the Anthropic Messages API; an OpenAI provider makes it speak Chat Completions/Responses; a Gemini provider makes it speak Gemini's `generateContent` API. Attach whichever providers match the clients you plan to connect.
|
||||
|
||||
## 1. Add a provider
|
||||
|
||||
Sidebar → **AI Gateway** → **Providers** → **Create**. Pick a provider type, paste in its API key, and save. You can add as many as you need.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/create-provider.png`
|
||||
The AI Gateway → Providers → Create form, showing the provider type dropdown and API key field filled in for OpenAI or Anthropic.
|
||||
<Frame>
|
||||
<img src="/images/ai/create-provider.png" alt="Creating an AI provider" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## 2. Create a resource
|
||||
|
||||
Resources → **Create** → set **Type** to **AI Gateway**, pick a domain, and attach the provider(s) from step 1. You can also attach providers to an existing resource later from its **AI Gateway** settings tab.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/create-resource.png`
|
||||
The new resource dialog with Type set to "AI Gateway" and a provider selected in the AI Providers section.
|
||||
<Frame>
|
||||
<img src="/images/ai/create-resource.png" alt="Creating an AI Gateway resource" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## 3. Get a key
|
||||
|
||||
How a client authenticates depends on whether the resource is public or private.
|
||||
|
||||
### Public resources
|
||||
|
||||
Reachable from anywhere, so the gateway checks an API key. Find yours in either place:
|
||||
|
||||
- Your org's **Your API Keys** page (top-level nav)
|
||||
- The resource's **API Keys** panel in the Resource Launcher
|
||||
|
||||
Both show your personal **Identity Key** and any other keys attributed to you.
|
||||
|
||||
### Private resources
|
||||
|
||||
Only reachable from devices connected to your Pangolin network, so no key is checked. Instead, the machine running the client needs the [Pangolin client](/manage/clients/install-client) installed and connected.
|
||||
|
||||
You still have to put *something* in the client's key field. Most AI clients refuse to start with no key set at all, so use the literal string `none`. Deleting the field usually breaks things - Claude Code, for instance, silently falls back to your regular Anthropic account if `apiKeyHelper` is missing, and OpenCode errors out with `OpenAI API key is missing`.
|
||||
|
||||
{/*
|
||||
Screenshot: `/images/ai/api-keys-panel.png`
|
||||
The resource launcher's API Keys panel, showing the Identity Key section and the "Configure Coding Agents" cards below it.
|
||||
<Frame>
|
||||
<img src="/images/ai/api-keys-panel.png" alt="Resource API Keys panel" />
|
||||
</Frame>
|
||||
*/}
|
||||
|
||||
## 4. Connect a client
|
||||
|
||||
Every resource's Keys page has ready-to-copy setup for common clients, and `pangolin configure <client>` can write the config for you. Full instructions per client:
|
||||
|
||||
| Client | Needs a provider that speaks | Guide |
|
||||
|---|---|---|
|
||||
| Claude Code | Anthropic Messages | [Setup guide](/manage/ai/claude) |
|
||||
| Codex | OpenAI Chat/Responses | [Setup guide](/manage/ai/codex) |
|
||||
| OpenCode | Anthropic Messages and/or OpenAI Chat | [Setup guide](/manage/ai/opencode) |
|
||||
| Gemini CLI | Gemini `generateContent` | [Setup guide](/manage/ai/gemini) |
|
||||
|
||||
There are also guides for pointing other tools at a Pangolin AI Gateway resource:
|
||||
|
||||
- [Open WebUI](/manage/ai/open-webui)
|
||||
- [Claude Desktop](/manage/ai/claude-desktop)
|
||||
- [OpenClaw](/manage/ai/openclaw)
|
||||
|
||||
## Supported providers
|
||||
|
||||
| Provider | Speaks |
|
||||
|---|---|
|
||||
| OpenAI | Chat Completions, Responses |
|
||||
| Anthropic | Messages |
|
||||
| Google Gemini | `generateContent` |
|
||||
| Vertex AI | Google `generateContent`/`rawPredict` |
|
||||
| Bedrock | Converse |
|
||||
| Microsoft Foundry | Chat Completions, Responses, Messages |
|
||||
| OpenRouter | Chat Completions |
|
||||
| Vercel AI Gateway | Chat Completions, Responses |
|
||||
| Custom | Whatever you configure |
|
||||
|
||||
Use **Custom** for any OpenAI- or Anthropic-compatible endpoint that isn't in the list above - for example a Moonshot AI (Kimi) endpoint, which is Anthropic-compatible.
|
||||
@@ -57,7 +57,7 @@ For each type, decide whether the rule applies to all of that kind (for example
|
||||
|
||||
### 2. Trigger
|
||||
|
||||
Available triggers depend on the source type. For sites, options include coming online, going offline, or any status change. For resources and health checks, you get healthy, unhealthy, and combined toggle-style triggers that match how those entities change state—the dashboard only lists combinations that apply to what you selected.
|
||||
Available triggers depend on the source type. For sites, options include coming online, going offline, or any status change. For resources and health checks, you get healthy, unhealthy, and combined toggle-style triggers that match how those entities change state-the dashboard only lists combinations that apply to what you selected.
|
||||
|
||||
Pick the condition that should fire the rule (for example site status changes when you care about both online and offline transitions).
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@ Use All when the service needs arbitrary ports (for example ephemeral ports on t
|
||||
|
||||
### Blocked
|
||||
|
||||
Blocked means that protocol is not allowed to the destination through Pangolin: no TCP or no UDP traffic passes, depending on which row you set. The other protocol can still be All or Custom independently—for example TCP Custom (only `443`) with UDP Blocked for a HTTPS-only workload that should not receive UDP to that destination.
|
||||
Blocked means that protocol is not allowed to the destination through Pangolin: no TCP or no UDP traffic passes, depending on which row you set. The other protocol can still be All or Custom independently-for example TCP Custom (only `443`) with UDP Blocked for a HTTPS-only workload that should not receive UDP to that destination.
|
||||
|
||||
Use Blocked when you want to turn off a protocol entirely for that resource.
|
||||
|
||||
@@ -41,5 +41,5 @@ Use Custom for least-privilege access: allow only the ports your application act
|
||||
By default, ICMP (ping) to the resource’s destination is enabled. To turn it off, disable the ICMP option when configuring access to the resource. That stops ICMP echo requests (ping) to the destination for principals that have access.
|
||||
|
||||
<Note>
|
||||
ICMP ping does not work when using a resource [alias](/manage/resources/private/alias) as the target—ping applies to the resource’s configured destination (FQDN, IP, or CIDR), not to alias hostnames.
|
||||
ICMP ping does not work when using a resource [alias](/manage/resources/private/alias) as the target-ping applies to the resource’s configured destination (FQDN, IP, or CIDR), not to alias hostnames.
|
||||
</Note>
|
||||
|
||||
10
snippets/ai-gateway-key.mdx
Normal file
10
snippets/ai-gateway-key.mdx
Normal file
@@ -0,0 +1,10 @@
|
||||
<Note>
|
||||
**Public vs. private resources**
|
||||
|
||||
Wherever these instructions show `<key>`, what you put there depends on the resource type:
|
||||
|
||||
- **Public resource** - reachable from anywhere, so the gateway checks your API key. Use the key from the resource's Keys page or your personal org API key which can be retrieved from the dashboard.
|
||||
- **Private resource** - only reachable from devices connected to your Pangolin network, so no key is checked. You must have the [Pangolin client](/manage/clients/install-client) installed and connected. Use the literal string `none` as the key.
|
||||
|
||||
Don't delete the key field for private resources. Most clients refuse to start without *some* key set, so they need an inert placeholder rather than a missing one.
|
||||
</Note>
|
||||
Reference in New Issue
Block a user