mirror of
https://github.com/openclaw/openclaw.git
synced 2026-03-12 07:20:45 +00:00
Feat/litellm provider (#12823)
* feat: add LiteLLM provider types, env var, credentials, and auth choice Add litellm-api-key auth choice, LITELLM_API_KEY env var mapping, setLitellmApiKey() credential storage, and LITELLM_DEFAULT_MODEL_REF. * feat: add LiteLLM onboarding handler and provider config Add applyLitellmProviderConfig which properly registers models.providers.litellm with baseUrl, api type, and model definitions. This fixes the critical bug from PR #6488 where the provider entry was never created, causing model resolution to fail at runtime. * docs: add LiteLLM provider documentation Add setup guide covering onboarding, manual config, virtual keys, model routing, and usage tracking. Link from provider index. * docs: add LiteLLM to sidebar navigation in docs.json Add providers/litellm to both English and Chinese provider page lists so the docs page appears in the sidebar navigation. * test: add LiteLLM non-interactive onboarding test Wire up litellmApiKey flag inference and auth-choice handler for the non-interactive onboarding path, and add an integration test covering profile, model default, and credential storage. * fix: register --litellm-api-key CLI flag and add preferred provider mapping Wire up the missing Commander CLI option, action handler mapping, and help text for --litellm-api-key. Add litellm-api-key to the preferred provider map for consistency with other providers. * fix: remove zh-CN sidebar entry for litellm (no localized page yet) * style: format buildLitellmModelDefinition return type * fix(onboarding): harden LiteLLM provider setup (#12823) * refactor(onboarding): keep auth-choice provider dispatcher under size limit --------- Co-authored-by: Peter Steinberger <steipete@gmail.com>
This commit is contained in:
ryan-crabbe
@@ -43,6 +43,7 @@ Docs: https://docs.openclaw.ai
|
||||
- Telegram: match DM `allowFrom` against sender user id (fallback to chat id) and clarify pairing logs. (#12779) Thanks @liuxiaopai-ai.
|
||||
- Pairing/Telegram: include the actual pairing code in approve commands, route Telegram pairing replies through the shared pairing message builder, and add regression checks to prevent `<code>` placeholder drift.
|
||||
- Onboarding: QuickStart now auto-installs shell completion (prompt only in Manual).
|
||||
- Onboarding/Providers: add LiteLLM provider onboarding and preserve custom LiteLLM proxy base URLs while enforcing API-key auth mode. (#12823) Thanks @ryan-crabbe.
|
||||
- Docker: make `docker-setup.sh` compatible with macOS Bash 3.2 and empty extra mounts. (#9441) Thanks @mateusz-michalik.
|
||||
- Auth: strip embedded line breaks from pasted API keys and tokens before storing/resolving credentials.
|
||||
- Agents: strip reasoning tags and downgraded tool markers from messaging tool and streaming output to prevent leakage. (#11053, #13453) Thanks @liebertar, @meaadore1221-afk, @gumadeiras.
|
||||
|
||||
@@ -1036,6 +1036,7 @@
|
||||
"providers/anthropic",
|
||||
"providers/openai",
|
||||
"providers/openrouter",
|
||||
"providers/litellm",
|
||||
"providers/bedrock",
|
||||
"providers/vercel-ai-gateway",
|
||||
"providers/moonshot",
|
||||
|
||||
@@ -343,6 +343,7 @@ For teams preferring infrastructure-as-code workflows, a community-maintained Te
|
||||
- SSH tunnel configuration for gateway access
|
||||
|
||||
**Repositories:**
|
||||
|
||||
- Infrastructure: [openclaw-terraform-hetzner](https://github.com/andreesg/openclaw-terraform-hetzner)
|
||||
- Docker config: [openclaw-docker-config](https://github.com/andreesg/openclaw-docker-config)
|
||||
|
||||
|
||||
@@ -39,6 +39,7 @@ See [Venice AI](/providers/venice).
|
||||
- [Anthropic (API + Claude Code CLI)](/providers/anthropic)
|
||||
- [Qwen (OAuth)](/providers/qwen)
|
||||
- [OpenRouter](/providers/openrouter)
|
||||
- [LiteLLM (unified gateway)](/providers/litellm)
|
||||
- [Vercel AI Gateway](/providers/vercel-ai-gateway)
|
||||
- [Together AI](/providers/together)
|
||||
- [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
|
||||
|
||||
153
docs/providers/litellm.md
Normal file
153
docs/providers/litellm.md
Normal file
@@ -0,0 +1,153 @@
|
||||
---
|
||||
summary: "Run OpenClaw through LiteLLM Proxy for unified model access and cost tracking"
|
||||
read_when:
|
||||
- You want to route OpenClaw through a LiteLLM proxy
|
||||
- You need cost tracking, logging, or model routing through LiteLLM
|
||||
---
|
||||
|
||||
# LiteLLM
|
||||
|
||||
[LiteLLM](https://litellm.ai) is an open-source LLM gateway that provides a unified API to 100+ model providers. Route OpenClaw through LiteLLM to get centralized cost tracking, logging, and the flexibility to switch backends without changing your OpenClaw config.
|
||||
|
||||
## Why use LiteLLM with OpenClaw?
|
||||
|
||||
- **Cost tracking** — See exactly what OpenClaw spends across all models
|
||||
- **Model routing** — Switch between Claude, GPT-4, Gemini, Bedrock without config changes
|
||||
- **Virtual keys** — Create keys with spend limits for OpenClaw
|
||||
- **Logging** — Full request/response logs for debugging
|
||||
- **Fallbacks** — Automatic failover if your primary provider is down
|
||||
|
||||
## Quick start
|
||||
|
||||
### Via onboarding
|
||||
|
||||
```bash
|
||||
openclaw onboard --auth-choice litellm-api-key
|
||||
```
|
||||
|
||||
### Manual setup
|
||||
|
||||
1. Start LiteLLM Proxy:
|
||||
|
||||
```bash
|
||||
pip install 'litellm[proxy]'
|
||||
litellm --model claude-opus-4-6
|
||||
```
|
||||
|
||||
2. Point OpenClaw to LiteLLM:
|
||||
|
||||
```bash
|
||||
export LITELLM_API_KEY="your-litellm-key"
|
||||
|
||||
openclaw
|
||||
```
|
||||
|
||||
That's it. OpenClaw now routes through LiteLLM.
|
||||
|
||||
## Configuration
|
||||
|
||||
### Environment variables
|
||||
|
||||
```bash
|
||||
export LITELLM_API_KEY="sk-litellm-key"
|
||||
```
|
||||
|
||||
### Config file
|
||||
|
||||
```json5
|
||||
{
|
||||
models: {
|
||||
providers: {
|
||||
litellm: {
|
||||
baseUrl: "http://localhost:4000",
|
||||
apiKey: "${LITELLM_API_KEY}",
|
||||
api: "openai-completions",
|
||||
models: [
|
||||
{
|
||||
id: "claude-opus-4-6",
|
||||
name: "Claude Opus 4.6",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
},
|
||||
{
|
||||
id: "gpt-4o",
|
||||
name: "GPT-4o",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
contextWindow: 128000,
|
||||
maxTokens: 8192,
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
agents: {
|
||||
defaults: {
|
||||
model: { primary: "litellm/claude-opus-4-6" },
|
||||
},
|
||||
},
|
||||
}
|
||||
```
|
||||
|
||||
## Virtual keys
|
||||
|
||||
Create a dedicated key for OpenClaw with spend limits:
|
||||
|
||||
```bash
|
||||
curl -X POST "http://localhost:4000/key/generate" \
|
||||
-H "Authorization: Bearer $LITELLM_MASTER_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"key_alias": "openclaw",
|
||||
"max_budget": 50.00,
|
||||
"budget_duration": "monthly"
|
||||
}'
|
||||
```
|
||||
|
||||
Use the generated key as `LITELLM_API_KEY`.
|
||||
|
||||
## Model routing
|
||||
|
||||
LiteLLM can route model requests to different backends. Configure in your LiteLLM `config.yaml`:
|
||||
|
||||
```yaml
|
||||
model_list:
|
||||
- model_name: claude-opus-4-6
|
||||
litellm_params:
|
||||
model: claude-opus-4-6
|
||||
api_key: os.environ/ANTHROPIC_API_KEY
|
||||
|
||||
- model_name: gpt-4o
|
||||
litellm_params:
|
||||
model: gpt-4o
|
||||
api_key: os.environ/OPENAI_API_KEY
|
||||
```
|
||||
|
||||
OpenClaw keeps requesting `claude-opus-4-6` — LiteLLM handles the routing.
|
||||
|
||||
## Viewing usage
|
||||
|
||||
Check LiteLLM's dashboard or API:
|
||||
|
||||
```bash
|
||||
# Key info
|
||||
curl "http://localhost:4000/key/info" \
|
||||
-H "Authorization: Bearer sk-litellm-key"
|
||||
|
||||
# Spend logs
|
||||
curl "http://localhost:4000/spend/logs" \
|
||||
-H "Authorization: Bearer $LITELLM_MASTER_KEY"
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- LiteLLM runs on `http://localhost:4000` by default
|
||||
- OpenClaw connects via the OpenAI-compatible `/v1/chat/completions` endpoint
|
||||
- All OpenClaw features work through LiteLLM — no limitations
|
||||
|
||||
## See also
|
||||
|
||||
- [LiteLLM Docs](https://docs.litellm.ai)
|
||||
- [Model Providers](/concepts/model-providers)
|
||||
@@ -296,6 +296,7 @@ export function resolveEnvApiKey(provider: string): EnvApiKeyResult | null {
|
||||
cerebras: "CEREBRAS_API_KEY",
|
||||
xai: "XAI_API_KEY",
|
||||
openrouter: "OPENROUTER_API_KEY",
|
||||
litellm: "LITELLM_API_KEY",
|
||||
"vercel-ai-gateway": "AI_GATEWAY_API_KEY",
|
||||
"cloudflare-ai-gateway": "CLOUDFLARE_AI_GATEWAY_API_KEY",
|
||||
moonshot: "MOONSHOT_API_KEY",
|
||||
|
||||
@@ -58,7 +58,7 @@ export function registerOnboardCommand(program: Command) {
|
||||
.option("--mode <mode>", "Wizard mode: local|remote")
|
||||
.option(
|
||||
"--auth-choice <choice>",
|
||||
"Auth: setup-token|token|chutes|openai-codex|openai-api-key|xai-api-key|qianfan-api-key|openrouter-api-key|ai-gateway-api-key|cloudflare-ai-gateway-api-key|moonshot-api-key|moonshot-api-key-cn|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|xiaomi-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|skip|together-api-key",
|
||||
"Auth: setup-token|token|chutes|openai-codex|openai-api-key|xai-api-key|qianfan-api-key|openrouter-api-key|litellm-api-key|ai-gateway-api-key|cloudflare-ai-gateway-api-key|moonshot-api-key|moonshot-api-key-cn|kimi-code-api-key|synthetic-api-key|venice-api-key|gemini-api-key|zai-api-key|xiaomi-api-key|apiKey|minimax-api|minimax-api-lightning|opencode-zen|skip|together-api-key",
|
||||
)
|
||||
.option(
|
||||
"--token-provider <id>",
|
||||
@@ -88,6 +88,7 @@ export function registerOnboardCommand(program: Command) {
|
||||
.option("--together-api-key <key>", "Together AI API key")
|
||||
.option("--opencode-zen-api-key <key>", "OpenCode Zen API key")
|
||||
.option("--xai-api-key <key>", "xAI API key")
|
||||
.option("--litellm-api-key <key>", "LiteLLM API key")
|
||||
.option("--qianfan-api-key <key>", "QIANFAN API key")
|
||||
.option("--gateway-port <port>", "Gateway port")
|
||||
.option("--gateway-bind <mode>", "Gateway bind: loopback|tailnet|lan|auto|custom")
|
||||
@@ -146,6 +147,7 @@ export function registerOnboardCommand(program: Command) {
|
||||
togetherApiKey: opts.togetherApiKey as string | undefined,
|
||||
opencodeZenApiKey: opts.opencodeZenApiKey as string | undefined,
|
||||
xaiApiKey: opts.xaiApiKey as string | undefined,
|
||||
litellmApiKey: opts.litellmApiKey as string | undefined,
|
||||
gatewayPort:
|
||||
typeof gatewayPort === "number" && Number.isFinite(gatewayPort)
|
||||
? gatewayPort
|
||||
|
||||
@@ -13,6 +13,7 @@ export type AuthChoiceGroupId =
|
||||
| "google"
|
||||
| "copilot"
|
||||
| "openrouter"
|
||||
| "litellm"
|
||||
| "ai-gateway"
|
||||
| "cloudflare-ai-gateway"
|
||||
| "moonshot"
|
||||
@@ -143,6 +144,12 @@ const AUTH_CHOICE_GROUP_DEFS: {
|
||||
hint: "Privacy-focused (uncensored models)",
|
||||
choices: ["venice-api-key"],
|
||||
},
|
||||
{
|
||||
value: "litellm",
|
||||
label: "LiteLLM",
|
||||
hint: "Unified LLM gateway (100+ providers)",
|
||||
choices: ["litellm-api-key"],
|
||||
},
|
||||
{
|
||||
value: "cloudflare-ai-gateway",
|
||||
label: "Cloudflare AI Gateway",
|
||||
@@ -182,6 +189,11 @@ export function buildAuthChoiceOptions(params: {
|
||||
label: "Qianfan API key",
|
||||
});
|
||||
options.push({ value: "openrouter-api-key", label: "OpenRouter API key" });
|
||||
options.push({
|
||||
value: "litellm-api-key",
|
||||
label: "LiteLLM API key",
|
||||
hint: "Unified gateway for 100+ LLM providers",
|
||||
});
|
||||
options.push({
|
||||
value: "ai-gateway-api-key",
|
||||
label: "Vercel AI Gateway API key",
|
||||
|
||||
@@ -19,6 +19,8 @@ import {
|
||||
applyQianfanProviderConfig,
|
||||
applyKimiCodeConfig,
|
||||
applyKimiCodeProviderConfig,
|
||||
applyLitellmConfig,
|
||||
applyLitellmProviderConfig,
|
||||
applyMoonshotConfig,
|
||||
applyMoonshotConfigCn,
|
||||
applyMoonshotProviderConfig,
|
||||
@@ -39,6 +41,7 @@ import {
|
||||
applyXiaomiProviderConfig,
|
||||
applyZaiConfig,
|
||||
CLOUDFLARE_AI_GATEWAY_DEFAULT_MODEL_REF,
|
||||
LITELLM_DEFAULT_MODEL_REF,
|
||||
QIANFAN_DEFAULT_MODEL_REF,
|
||||
KIMI_CODING_MODEL_REF,
|
||||
MOONSHOT_DEFAULT_MODEL_REF,
|
||||
@@ -51,6 +54,7 @@ import {
|
||||
setCloudflareAiGatewayConfig,
|
||||
setQianfanApiKey,
|
||||
setGeminiApiKey,
|
||||
setLitellmApiKey,
|
||||
setKimiCodingApiKey,
|
||||
setMoonshotApiKey,
|
||||
setOpencodeZenApiKey,
|
||||
@@ -89,6 +93,8 @@ export async function applyAuthChoiceApiProviders(
|
||||
) {
|
||||
if (params.opts.tokenProvider === "openrouter") {
|
||||
authChoice = "openrouter-api-key";
|
||||
} else if (params.opts.tokenProvider === "litellm") {
|
||||
authChoice = "litellm-api-key";
|
||||
} else if (params.opts.tokenProvider === "vercel-ai-gateway") {
|
||||
authChoice = "ai-gateway-api-key";
|
||||
} else if (params.opts.tokenProvider === "cloudflare-ai-gateway") {
|
||||
@@ -197,6 +203,69 @@ export async function applyAuthChoiceApiProviders(
|
||||
return { config: nextConfig, agentModelOverride };
|
||||
}
|
||||
|
||||
if (authChoice === "litellm-api-key") {
|
||||
const store = ensureAuthProfileStore(params.agentDir, { allowKeychainPrompt: false });
|
||||
const profileOrder = resolveAuthProfileOrder({ cfg: nextConfig, store, provider: "litellm" });
|
||||
const existingProfileId = profileOrder.find((profileId) => Boolean(store.profiles[profileId]));
|
||||
const existingCred = existingProfileId ? store.profiles[existingProfileId] : undefined;
|
||||
let profileId = "litellm:default";
|
||||
let hasCredential = false;
|
||||
|
||||
if (existingProfileId && existingCred?.type === "api_key") {
|
||||
profileId = existingProfileId;
|
||||
hasCredential = true;
|
||||
}
|
||||
if (!hasCredential && params.opts?.token && params.opts?.tokenProvider === "litellm") {
|
||||
await setLitellmApiKey(normalizeApiKeyInput(params.opts.token), params.agentDir);
|
||||
hasCredential = true;
|
||||
}
|
||||
if (!hasCredential) {
|
||||
await params.prompter.note(
|
||||
"LiteLLM provides a unified API to 100+ LLM providers.\nGet your API key from your LiteLLM proxy or https://litellm.ai\nDefault proxy runs on http://localhost:4000",
|
||||
"LiteLLM",
|
||||
);
|
||||
const envKey = resolveEnvApiKey("litellm");
|
||||
if (envKey) {
|
||||
const useExisting = await params.prompter.confirm({
|
||||
message: `Use existing LITELLM_API_KEY (${envKey.source}, ${formatApiKeyPreview(envKey.apiKey)})?`,
|
||||
initialValue: true,
|
||||
});
|
||||
if (useExisting) {
|
||||
await setLitellmApiKey(envKey.apiKey, params.agentDir);
|
||||
hasCredential = true;
|
||||
}
|
||||
}
|
||||
if (!hasCredential) {
|
||||
const key = await params.prompter.text({
|
||||
message: "Enter LiteLLM API key",
|
||||
validate: validateApiKeyInput,
|
||||
});
|
||||
await setLitellmApiKey(normalizeApiKeyInput(String(key)), params.agentDir);
|
||||
hasCredential = true;
|
||||
}
|
||||
}
|
||||
if (hasCredential) {
|
||||
nextConfig = applyAuthProfileConfig(nextConfig, {
|
||||
profileId,
|
||||
provider: "litellm",
|
||||
mode: "api_key",
|
||||
});
|
||||
}
|
||||
const applied = await applyDefaultModelChoice({
|
||||
config: nextConfig,
|
||||
setDefaultModel: params.setDefaultModel,
|
||||
defaultModel: LITELLM_DEFAULT_MODEL_REF,
|
||||
applyDefaultConfig: applyLitellmConfig,
|
||||
applyProviderConfig: applyLitellmProviderConfig,
|
||||
noteDefault: LITELLM_DEFAULT_MODEL_REF,
|
||||
noteAgentModel,
|
||||
prompter: params.prompter,
|
||||
});
|
||||
nextConfig = applied.config;
|
||||
agentModelOverride = applied.agentModelOverride ?? agentModelOverride;
|
||||
return { config: nextConfig, agentModelOverride };
|
||||
}
|
||||
|
||||
if (authChoice === "ai-gateway-api-key") {
|
||||
let hasCredential = false;
|
||||
|
||||
|
||||
@@ -32,6 +32,7 @@ const PREFERRED_PROVIDER_BY_AUTH_CHOICE: Partial<Record<AuthChoice, string>> = {
|
||||
minimax: "lmstudio",
|
||||
"opencode-zen": "opencode",
|
||||
"xai-api-key": "xai",
|
||||
"litellm-api-key": "litellm",
|
||||
"qwen-portal": "qwen-portal",
|
||||
"minimax-portal": "minimax-portal",
|
||||
"qianfan-api-key": "qianfan",
|
||||
|
||||
@@ -32,6 +32,7 @@ describe("applyAuthChoice", () => {
|
||||
const previousAgentDir = process.env.OPENCLAW_AGENT_DIR;
|
||||
const previousPiAgentDir = process.env.PI_CODING_AGENT_DIR;
|
||||
const previousOpenrouterKey = process.env.OPENROUTER_API_KEY;
|
||||
const previousLitellmKey = process.env.LITELLM_API_KEY;
|
||||
const previousAiGatewayKey = process.env.AI_GATEWAY_API_KEY;
|
||||
const previousCloudflareGatewayKey = process.env.CLOUDFLARE_AI_GATEWAY_API_KEY;
|
||||
const previousSshTty = process.env.SSH_TTY;
|
||||
@@ -65,6 +66,11 @@ describe("applyAuthChoice", () => {
|
||||
} else {
|
||||
process.env.OPENROUTER_API_KEY = previousOpenrouterKey;
|
||||
}
|
||||
if (previousLitellmKey === undefined) {
|
||||
delete process.env.LITELLM_API_KEY;
|
||||
} else {
|
||||
process.env.LITELLM_API_KEY = previousLitellmKey;
|
||||
}
|
||||
if (previousAiGatewayKey === undefined) {
|
||||
delete process.env.AI_GATEWAY_API_KEY;
|
||||
} else {
|
||||
@@ -402,6 +408,96 @@ describe("applyAuthChoice", () => {
|
||||
delete process.env.OPENROUTER_API_KEY;
|
||||
});
|
||||
|
||||
it("ignores legacy LiteLLM oauth profiles when selecting litellm-api-key", async () => {
|
||||
tempStateDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-auth-"));
|
||||
process.env.OPENCLAW_STATE_DIR = tempStateDir;
|
||||
process.env.OPENCLAW_AGENT_DIR = path.join(tempStateDir, "agent");
|
||||
process.env.PI_CODING_AGENT_DIR = process.env.OPENCLAW_AGENT_DIR;
|
||||
process.env.LITELLM_API_KEY = "sk-litellm-test";
|
||||
|
||||
const authProfilePath = authProfilePathFor(requireAgentDir());
|
||||
await fs.mkdir(path.dirname(authProfilePath), { recursive: true });
|
||||
await fs.writeFile(
|
||||
authProfilePath,
|
||||
JSON.stringify(
|
||||
{
|
||||
version: 1,
|
||||
profiles: {
|
||||
"litellm:legacy": {
|
||||
type: "oauth",
|
||||
provider: "litellm",
|
||||
access: "access-token",
|
||||
refresh: "refresh-token",
|
||||
expires: Date.now() + 60_000,
|
||||
},
|
||||
},
|
||||
},
|
||||
null,
|
||||
2,
|
||||
),
|
||||
"utf8",
|
||||
);
|
||||
|
||||
const text = vi.fn();
|
||||
const select: WizardPrompter["select"] = vi.fn(
|
||||
async (params) => params.options[0]?.value as never,
|
||||
);
|
||||
const multiselect: WizardPrompter["multiselect"] = vi.fn(async () => []);
|
||||
const confirm = vi.fn(async () => true);
|
||||
const prompter: WizardPrompter = {
|
||||
intro: vi.fn(noopAsync),
|
||||
outro: vi.fn(noopAsync),
|
||||
note: vi.fn(noopAsync),
|
||||
select,
|
||||
multiselect,
|
||||
text,
|
||||
confirm,
|
||||
progress: vi.fn(() => ({ update: noop, stop: noop })),
|
||||
};
|
||||
const runtime: RuntimeEnv = {
|
||||
log: vi.fn(),
|
||||
error: vi.fn(),
|
||||
exit: vi.fn((code: number) => {
|
||||
throw new Error(`exit:${code}`);
|
||||
}),
|
||||
};
|
||||
|
||||
const result = await applyAuthChoice({
|
||||
authChoice: "litellm-api-key",
|
||||
config: {
|
||||
auth: {
|
||||
profiles: {
|
||||
"litellm:legacy": { provider: "litellm", mode: "oauth" },
|
||||
},
|
||||
order: { litellm: ["litellm:legacy"] },
|
||||
},
|
||||
},
|
||||
prompter,
|
||||
runtime,
|
||||
setDefaultModel: true,
|
||||
});
|
||||
|
||||
expect(confirm).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
message: expect.stringContaining("LITELLM_API_KEY"),
|
||||
}),
|
||||
);
|
||||
expect(text).not.toHaveBeenCalled();
|
||||
expect(result.config.auth?.profiles?.["litellm:default"]).toMatchObject({
|
||||
provider: "litellm",
|
||||
mode: "api_key",
|
||||
});
|
||||
|
||||
const raw = await fs.readFile(authProfilePath, "utf8");
|
||||
const parsed = JSON.parse(raw) as {
|
||||
profiles?: Record<string, { type?: string; key?: string }>;
|
||||
};
|
||||
expect(parsed.profiles?.["litellm:default"]).toMatchObject({
|
||||
type: "api_key",
|
||||
key: "sk-litellm-test",
|
||||
});
|
||||
});
|
||||
|
||||
it("uses existing AI_GATEWAY_API_KEY when selecting ai-gateway-api-key", async () => {
|
||||
tempStateDir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-auth-"));
|
||||
process.env.OPENCLAW_STATE_DIR = tempStateDir;
|
||||
|
||||
@@ -29,6 +29,7 @@ import {
|
||||
} from "../agents/venice-models.js";
|
||||
import {
|
||||
CLOUDFLARE_AI_GATEWAY_DEFAULT_MODEL_REF,
|
||||
LITELLM_DEFAULT_MODEL_REF,
|
||||
OPENROUTER_DEFAULT_MODEL_REF,
|
||||
TOGETHER_DEFAULT_MODEL_REF,
|
||||
VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF,
|
||||
@@ -252,6 +253,105 @@ export function applyOpenrouterConfig(cfg: OpenClawConfig): OpenClawConfig {
|
||||
};
|
||||
}
|
||||
|
||||
export const LITELLM_BASE_URL = "http://localhost:4000";
|
||||
export const LITELLM_DEFAULT_MODEL_ID = "claude-opus-4-6";
|
||||
const LITELLM_DEFAULT_CONTEXT_WINDOW = 128_000;
|
||||
const LITELLM_DEFAULT_MAX_TOKENS = 8_192;
|
||||
const LITELLM_DEFAULT_COST = {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
};
|
||||
|
||||
function buildLitellmModelDefinition(): {
|
||||
id: string;
|
||||
name: string;
|
||||
reasoning: boolean;
|
||||
input: Array<"text" | "image">;
|
||||
cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
|
||||
contextWindow: number;
|
||||
maxTokens: number;
|
||||
} {
|
||||
return {
|
||||
id: LITELLM_DEFAULT_MODEL_ID,
|
||||
name: "Claude Opus 4.6",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
// LiteLLM routes to many upstreams; keep neutral placeholders.
|
||||
cost: LITELLM_DEFAULT_COST,
|
||||
contextWindow: LITELLM_DEFAULT_CONTEXT_WINDOW,
|
||||
maxTokens: LITELLM_DEFAULT_MAX_TOKENS,
|
||||
};
|
||||
}
|
||||
|
||||
export function applyLitellmProviderConfig(cfg: OpenClawConfig): OpenClawConfig {
|
||||
const models = { ...cfg.agents?.defaults?.models };
|
||||
models[LITELLM_DEFAULT_MODEL_REF] = {
|
||||
...models[LITELLM_DEFAULT_MODEL_REF],
|
||||
alias: models[LITELLM_DEFAULT_MODEL_REF]?.alias ?? "LiteLLM",
|
||||
};
|
||||
|
||||
const providers = { ...cfg.models?.providers };
|
||||
const existingProvider = providers.litellm;
|
||||
const existingModels = Array.isArray(existingProvider?.models) ? existingProvider.models : [];
|
||||
const defaultModel = buildLitellmModelDefinition();
|
||||
const hasDefaultModel = existingModels.some((model) => model.id === LITELLM_DEFAULT_MODEL_ID);
|
||||
const mergedModels = hasDefaultModel ? existingModels : [...existingModels, defaultModel];
|
||||
const { apiKey: existingApiKey, ...existingProviderRest } = (existingProvider ?? {}) as Record<
|
||||
string,
|
||||
unknown
|
||||
> as { apiKey?: string };
|
||||
const resolvedBaseUrl =
|
||||
typeof existingProvider?.baseUrl === "string" ? existingProvider.baseUrl.trim() : "";
|
||||
const resolvedApiKey = typeof existingApiKey === "string" ? existingApiKey : undefined;
|
||||
const normalizedApiKey = resolvedApiKey?.trim();
|
||||
providers.litellm = {
|
||||
...existingProviderRest,
|
||||
baseUrl: resolvedBaseUrl || LITELLM_BASE_URL,
|
||||
api: "openai-completions",
|
||||
...(normalizedApiKey ? { apiKey: normalizedApiKey } : {}),
|
||||
models: mergedModels.length > 0 ? mergedModels : [defaultModel],
|
||||
};
|
||||
|
||||
return {
|
||||
...cfg,
|
||||
agents: {
|
||||
...cfg.agents,
|
||||
defaults: {
|
||||
...cfg.agents?.defaults,
|
||||
models,
|
||||
},
|
||||
},
|
||||
models: {
|
||||
mode: cfg.models?.mode ?? "merge",
|
||||
providers,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export function applyLitellmConfig(cfg: OpenClawConfig): OpenClawConfig {
|
||||
const next = applyLitellmProviderConfig(cfg);
|
||||
const existingModel = next.agents?.defaults?.model;
|
||||
return {
|
||||
...next,
|
||||
agents: {
|
||||
...next.agents,
|
||||
defaults: {
|
||||
...next.agents?.defaults,
|
||||
model: {
|
||||
...(existingModel && "fallbacks" in (existingModel as Record<string, unknown>)
|
||||
? {
|
||||
fallbacks: (existingModel as { fallbacks?: string[] }).fallbacks,
|
||||
}
|
||||
: undefined),
|
||||
primary: LITELLM_DEFAULT_MODEL_REF,
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export function applyMoonshotProviderConfig(cfg: OpenClawConfig): OpenClawConfig {
|
||||
return applyMoonshotProviderConfigWithBaseUrl(cfg, MOONSHOT_BASE_URL);
|
||||
}
|
||||
|
||||
@@ -119,6 +119,7 @@ export const ZAI_DEFAULT_MODEL_REF = "zai/glm-4.7";
|
||||
export const XIAOMI_DEFAULT_MODEL_REF = "xiaomi/mimo-v2-flash";
|
||||
export const OPENROUTER_DEFAULT_MODEL_REF = "openrouter/auto";
|
||||
export const TOGETHER_DEFAULT_MODEL_REF = "together/moonshotai/Kimi-K2.5";
|
||||
export const LITELLM_DEFAULT_MODEL_REF = "litellm/claude-opus-4-6";
|
||||
export const VERCEL_AI_GATEWAY_DEFAULT_MODEL_REF = "vercel-ai-gateway/anthropic/claude-opus-4.6";
|
||||
|
||||
export async function setZaiApiKey(key: string, agentDir?: string) {
|
||||
@@ -182,6 +183,18 @@ export async function setCloudflareAiGatewayConfig(
|
||||
});
|
||||
}
|
||||
|
||||
export async function setLitellmApiKey(key: string, agentDir?: string) {
|
||||
upsertAuthProfile({
|
||||
profileId: "litellm:default",
|
||||
credential: {
|
||||
type: "api_key",
|
||||
provider: "litellm",
|
||||
key,
|
||||
},
|
||||
agentDir: resolveAuthAgentDir(agentDir),
|
||||
});
|
||||
}
|
||||
|
||||
export async function setVercelAiGatewayApiKey(key: string, agentDir?: string) {
|
||||
upsertAuthProfile({
|
||||
profileId: "vercel-ai-gateway:default",
|
||||
|
||||
@@ -5,6 +5,7 @@ import path from "node:path";
|
||||
import { afterEach, describe, expect, it } from "vitest";
|
||||
import {
|
||||
applyAuthProfileConfig,
|
||||
applyLitellmProviderConfig,
|
||||
applyMinimaxApiConfig,
|
||||
applyMinimaxApiProviderConfig,
|
||||
applyOpencodeZenConfig,
|
||||
@@ -511,6 +512,41 @@ describe("applyOpenrouterProviderConfig", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("applyLitellmProviderConfig", () => {
|
||||
it("preserves existing baseUrl and api key while adding the default model", () => {
|
||||
const cfg = applyLitellmProviderConfig({
|
||||
models: {
|
||||
providers: {
|
||||
litellm: {
|
||||
baseUrl: "https://litellm.example/v1",
|
||||
apiKey: " old-key ",
|
||||
api: "anthropic-messages",
|
||||
models: [
|
||||
{
|
||||
id: "custom-model",
|
||||
name: "Custom",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: { input: 1, output: 2, cacheRead: 0, cacheWrite: 0 },
|
||||
contextWindow: 1000,
|
||||
maxTokens: 100,
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
expect(cfg.models?.providers?.litellm?.baseUrl).toBe("https://litellm.example/v1");
|
||||
expect(cfg.models?.providers?.litellm?.api).toBe("openai-completions");
|
||||
expect(cfg.models?.providers?.litellm?.apiKey).toBe("old-key");
|
||||
expect(cfg.models?.providers?.litellm?.models.map((m) => m.id)).toEqual([
|
||||
"custom-model",
|
||||
"claude-opus-4-6",
|
||||
]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("applyOpenrouterConfig", () => {
|
||||
it("sets correct primary model", () => {
|
||||
const cfg = applyOpenrouterConfig({});
|
||||
|
||||
@@ -11,6 +11,8 @@ export {
|
||||
applyQianfanProviderConfig,
|
||||
applyKimiCodeConfig,
|
||||
applyKimiCodeProviderConfig,
|
||||
applyLitellmConfig,
|
||||
applyLitellmProviderConfig,
|
||||
applyMoonshotConfig,
|
||||
applyMoonshotConfigCn,
|
||||
applyMoonshotProviderConfig,
|
||||
@@ -46,11 +48,13 @@ export {
|
||||
} from "./onboard-auth.config-opencode.js";
|
||||
export {
|
||||
CLOUDFLARE_AI_GATEWAY_DEFAULT_MODEL_REF,
|
||||
LITELLM_DEFAULT_MODEL_REF,
|
||||
OPENROUTER_DEFAULT_MODEL_REF,
|
||||
setAnthropicApiKey,
|
||||
setCloudflareAiGatewayConfig,
|
||||
setQianfanApiKey,
|
||||
setGeminiApiKey,
|
||||
setLitellmApiKey,
|
||||
setKimiCodingApiKey,
|
||||
setMinimaxApiKey,
|
||||
setMoonshotApiKey,
|
||||
|
||||
91
src/commands/onboard-non-interactive.litellm.test.ts
Normal file
91
src/commands/onboard-non-interactive.litellm.test.ts
Normal file
@@ -0,0 +1,91 @@
|
||||
import fs from "node:fs/promises";
|
||||
import os from "node:os";
|
||||
import path from "node:path";
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
|
||||
describe("onboard (non-interactive): LiteLLM", () => {
|
||||
it("stores the API key and configures the default model", async () => {
|
||||
const prev = {
|
||||
home: process.env.HOME,
|
||||
stateDir: process.env.OPENCLAW_STATE_DIR,
|
||||
configPath: process.env.OPENCLAW_CONFIG_PATH,
|
||||
skipChannels: process.env.OPENCLAW_SKIP_CHANNELS,
|
||||
skipGmail: process.env.OPENCLAW_SKIP_GMAIL_WATCHER,
|
||||
skipCron: process.env.OPENCLAW_SKIP_CRON,
|
||||
skipCanvas: process.env.OPENCLAW_SKIP_CANVAS_HOST,
|
||||
token: process.env.OPENCLAW_GATEWAY_TOKEN,
|
||||
password: process.env.OPENCLAW_GATEWAY_PASSWORD,
|
||||
};
|
||||
|
||||
process.env.OPENCLAW_SKIP_CHANNELS = "1";
|
||||
process.env.OPENCLAW_SKIP_GMAIL_WATCHER = "1";
|
||||
process.env.OPENCLAW_SKIP_CRON = "1";
|
||||
process.env.OPENCLAW_SKIP_CANVAS_HOST = "1";
|
||||
delete process.env.OPENCLAW_GATEWAY_TOKEN;
|
||||
delete process.env.OPENCLAW_GATEWAY_PASSWORD;
|
||||
|
||||
const tempHome = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-onboard-litellm-"));
|
||||
process.env.HOME = tempHome;
|
||||
process.env.OPENCLAW_STATE_DIR = tempHome;
|
||||
process.env.OPENCLAW_CONFIG_PATH = path.join(tempHome, "openclaw.json");
|
||||
vi.resetModules();
|
||||
|
||||
const runtime = {
|
||||
log: () => {},
|
||||
error: (msg: string) => {
|
||||
throw new Error(msg);
|
||||
},
|
||||
exit: (code: number) => {
|
||||
throw new Error(`exit:${code}`);
|
||||
},
|
||||
};
|
||||
|
||||
try {
|
||||
const { runNonInteractiveOnboarding } = await import("./onboard-non-interactive.js");
|
||||
await runNonInteractiveOnboarding(
|
||||
{
|
||||
nonInteractive: true,
|
||||
authChoice: "litellm-api-key",
|
||||
litellmApiKey: "litellm-test-key",
|
||||
skipHealth: true,
|
||||
skipChannels: true,
|
||||
skipSkills: true,
|
||||
json: true,
|
||||
},
|
||||
runtime,
|
||||
);
|
||||
|
||||
const { CONFIG_PATH } = await import("../config/config.js");
|
||||
const cfg = JSON.parse(await fs.readFile(CONFIG_PATH, "utf8")) as {
|
||||
auth?: {
|
||||
profiles?: Record<string, { provider?: string; mode?: string }>;
|
||||
};
|
||||
agents?: { defaults?: { model?: { primary?: string } } };
|
||||
};
|
||||
|
||||
expect(cfg.auth?.profiles?.["litellm:default"]?.provider).toBe("litellm");
|
||||
expect(cfg.auth?.profiles?.["litellm:default"]?.mode).toBe("api_key");
|
||||
expect(cfg.agents?.defaults?.model?.primary).toBe("litellm/claude-opus-4-6");
|
||||
|
||||
const { ensureAuthProfileStore } = await import("../agents/auth-profiles.js");
|
||||
const store = ensureAuthProfileStore();
|
||||
const profile = store.profiles["litellm:default"];
|
||||
expect(profile?.type).toBe("api_key");
|
||||
if (profile?.type === "api_key") {
|
||||
expect(profile.provider).toBe("litellm");
|
||||
expect(profile.key).toBe("litellm-test-key");
|
||||
}
|
||||
} finally {
|
||||
await fs.rm(tempHome, { recursive: true, force: true });
|
||||
process.env.HOME = prev.home;
|
||||
process.env.OPENCLAW_STATE_DIR = prev.stateDir;
|
||||
process.env.OPENCLAW_CONFIG_PATH = prev.configPath;
|
||||
process.env.OPENCLAW_SKIP_CHANNELS = prev.skipChannels;
|
||||
process.env.OPENCLAW_SKIP_GMAIL_WATCHER = prev.skipGmail;
|
||||
process.env.OPENCLAW_SKIP_CRON = prev.skipCron;
|
||||
process.env.OPENCLAW_SKIP_CANVAS_HOST = prev.skipCanvas;
|
||||
process.env.OPENCLAW_GATEWAY_TOKEN = prev.token;
|
||||
process.env.OPENCLAW_GATEWAY_PASSWORD = prev.password;
|
||||
}
|
||||
}, 60_000);
|
||||
});
|
||||
@@ -23,6 +23,7 @@ type AuthChoiceFlagOptions = Pick<
|
||||
| "minimaxApiKey"
|
||||
| "opencodeZenApiKey"
|
||||
| "xaiApiKey"
|
||||
| "litellmApiKey"
|
||||
>;
|
||||
|
||||
const AUTH_CHOICE_FLAG_MAP = [
|
||||
@@ -45,6 +46,7 @@ const AUTH_CHOICE_FLAG_MAP = [
|
||||
{ flag: "xaiApiKey", authChoice: "xai-api-key", label: "--xai-api-key" },
|
||||
{ flag: "minimaxApiKey", authChoice: "minimax-api", label: "--minimax-api-key" },
|
||||
{ flag: "opencodeZenApiKey", authChoice: "opencode-zen", label: "--opencode-zen-api-key" },
|
||||
{ flag: "litellmApiKey", authChoice: "litellm-api-key", label: "--litellm-api-key" },
|
||||
] satisfies ReadonlyArray<AuthChoiceFlag>;
|
||||
|
||||
export type AuthChoiceInference = {
|
||||
|
||||
@@ -24,6 +24,7 @@ import {
|
||||
applyVeniceConfig,
|
||||
applyTogetherConfig,
|
||||
applyVercelAiGatewayConfig,
|
||||
applyLitellmConfig,
|
||||
applyXaiConfig,
|
||||
applyXiaomiConfig,
|
||||
applyZaiConfig,
|
||||
@@ -32,6 +33,7 @@ import {
|
||||
setQianfanApiKey,
|
||||
setGeminiApiKey,
|
||||
setKimiCodingApiKey,
|
||||
setLitellmApiKey,
|
||||
setMinimaxApiKey,
|
||||
setMoonshotApiKey,
|
||||
setOpencodeZenApiKey,
|
||||
@@ -314,6 +316,29 @@ export async function applyNonInteractiveAuthChoice(params: {
|
||||
return applyOpenrouterConfig(nextConfig);
|
||||
}
|
||||
|
||||
if (authChoice === "litellm-api-key") {
|
||||
const resolved = await resolveNonInteractiveApiKey({
|
||||
provider: "litellm",
|
||||
cfg: baseConfig,
|
||||
flagValue: opts.litellmApiKey,
|
||||
flagName: "--litellm-api-key",
|
||||
envVar: "LITELLM_API_KEY",
|
||||
runtime,
|
||||
});
|
||||
if (!resolved) {
|
||||
return null;
|
||||
}
|
||||
if (resolved.source !== "profile") {
|
||||
await setLitellmApiKey(resolved.key);
|
||||
}
|
||||
nextConfig = applyAuthProfileConfig(nextConfig, {
|
||||
profileId: "litellm:default",
|
||||
provider: "litellm",
|
||||
mode: "api_key",
|
||||
});
|
||||
return applyLitellmConfig(nextConfig);
|
||||
}
|
||||
|
||||
if (authChoice === "ai-gateway-api-key") {
|
||||
const resolved = await resolveNonInteractiveApiKey({
|
||||
provider: "vercel-ai-gateway",
|
||||
|
||||
@@ -12,6 +12,7 @@ export type AuthChoice =
|
||||
| "openai-codex"
|
||||
| "openai-api-key"
|
||||
| "openrouter-api-key"
|
||||
| "litellm-api-key"
|
||||
| "ai-gateway-api-key"
|
||||
| "cloudflare-ai-gateway-api-key"
|
||||
| "moonshot-api-key"
|
||||
@@ -89,6 +90,7 @@ export type OnboardOptions = {
|
||||
anthropicApiKey?: string;
|
||||
openaiApiKey?: string;
|
||||
openrouterApiKey?: string;
|
||||
litellmApiKey?: string;
|
||||
aiGatewayApiKey?: string;
|
||||
cloudflareAiGatewayAccountId?: string;
|
||||
cloudflareAiGatewayGatewayId?: string;
|
||||
|
||||
Reference in New Issue
Block a user