mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-11-16 13:00:55 +00:00
* feat: Add Gemini 4 Argon Support Registers gemini-4-argon (GA 2026-10-13) for both the Gemini API and Google Cloud Gemini Enterprise Agent Platform, following the Gemini 3.8 Flash integration. - Model dropdown (config.ts) and both GOOGLE_MODELS examples - Shared 1,048,576-token context window in googleModels; output stays capped at the 65,535 synchronous limit by googleSettings - Thinking rule: medium default, minimal substituted with low, ignored sampling params and rejected thinkingBudget stripped; the allowlisted cyber-permissive variant defaults to high - Introductory rates ($2 in / $10 out / $0.10 implicit cache read per 1M) with the 2026-12-01 revert to $4 / $20 / $0.20 noted at both call sites; no long-context premium tier - Tests: thinking default and levels, minimal substitution, legacy param strip, Vertex eu multi-region, OpenAI-compatible addParams strip, context window, value key and rates Refs #17074 * test: Cover Gemini 4 Argon Request Shape and Billing End to End Adds a Gemini-compatible mock endpoint whose addParams carry sampling params, an E2E_REPORT_LLM_CONFIG fake-model marker that reports the resolved agent request, and scenarios asserting that an Argon turn sends no ignored sampling params (with gemini-2.5-pro as the control) and is billed at the Argon rates. * test: Read the Resolved Agent Request From the Graph in Argon Scenarios The hook's agents are the unresolved agent configs, so the report now reads the graph's agent context. The scenarios select the Gemini model explicitly and key billed rates by model so a mismatch names the model. * test: Match the Mobile Model Option Name in Argon Scenarios * fix: Route Gemini 4 Argon to a Multi-Region Vertex Endpoint by Default Argon is served only from the global, us and eu multi-regions, so with GOOGLE_LOC unset a Vertex request now uses global instead of the us-central1 regional default; a configured location is kept as is. Argon also rejects a candidate count, so candidateCount, candidate_count and its OpenAI alias n are stripped for Argon on the native and Gemini-compatible paths. * chore: Bump @librechat/agents to 4.0.6 for Gemini 4 Argon Input Rules * fix: Move Regional Vertex Locations to Their Multi-Region for Gemini 4 Argon A configured regional location such as europe-west1 does not serve Argon, so it now resolves to the multi-region that contains it (europe-* to eu, us-* to us) wherever the location comes from, GOOGLE_LOC or addParams. A region outside us and eu is kept rather than sent to global, so data never leaves the configured geography silently. * fix: Route Gemini 4 Argon Past Regional Vertex Endpoint Overrides
2113 lines
85 KiB
JavaScript
2113 lines
85 KiB
JavaScript
/** Note: No hard-coded values should be used in this file. */
|
|
const { EModelEndpoint } = require('librechat-data-provider');
|
|
const {
|
|
maxTokensMap,
|
|
matchModelName,
|
|
processModelData,
|
|
getModelMaxTokens,
|
|
findMatchingPattern,
|
|
} = require('@librechat/api');
|
|
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for exact match', () => {
|
|
expect(getModelMaxTokens('gpt-4-32k-0613')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-32k-0613'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for partial match', () => {
|
|
expect(getModelMaxTokens('gpt-4-32k-unknown')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-32k'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for partial match (OpenRouter)', () => {
|
|
expect(getModelMaxTokens('openai/gpt-4-32k')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-32k'],
|
|
);
|
|
});
|
|
|
|
test('should return undefined for no match', () => {
|
|
expect(getModelMaxTokens('unknown-model')).toBeUndefined();
|
|
});
|
|
|
|
test('should return correct tokens for another exact match', () => {
|
|
expect(getModelMaxTokens('gpt-3.5-turbo-16k-0613')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo-16k-0613'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for another partial match', () => {
|
|
expect(getModelMaxTokens('gpt-3.5-turbo-unknown')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo'],
|
|
);
|
|
});
|
|
|
|
test('should return undefined for undefined input', () => {
|
|
expect(getModelMaxTokens(undefined)).toBeUndefined();
|
|
});
|
|
|
|
test('should return undefined for null input', () => {
|
|
expect(getModelMaxTokens(null)).toBeUndefined();
|
|
});
|
|
|
|
test('should return undefined for number input', () => {
|
|
expect(getModelMaxTokens(123)).toBeUndefined();
|
|
});
|
|
|
|
// 11/06 Update
|
|
test('should return correct tokens for gpt-3.5-turbo-1106 exact match', () => {
|
|
expect(getModelMaxTokens('gpt-3.5-turbo-1106')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo-1106'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4-1106 exact match', () => {
|
|
expect(getModelMaxTokens('gpt-4-1106')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-4-1106']);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4-vision exact match', () => {
|
|
expect(getModelMaxTokens('gpt-4-vision')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-vision'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-3.5-turbo-1106 partial match', () => {
|
|
expect(getModelMaxTokens('something-/gpt-3.5-turbo-1106')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo-1106'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-3.5-turbo-1106/something-/')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo-1106'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4-1106 partial match', () => {
|
|
expect(getModelMaxTokens('gpt-4-1106/something')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-1106'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4-1106-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-1106'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4-1106-vision-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-1106'],
|
|
);
|
|
});
|
|
|
|
// 01/25 Update
|
|
test('should return correct tokens for gpt-4-turbo/0125 matches', () => {
|
|
expect(getModelMaxTokens('gpt-4-turbo')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-turbo'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4-turbo-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-turbo'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4-0125')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-4-0125']);
|
|
expect(getModelMaxTokens('gpt-4-0125-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4-0125'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-3.5-turbo-0125')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-3.5-turbo-0125'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4.5 matches', () => {
|
|
expect(getModelMaxTokens('gpt-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-4.5']);
|
|
expect(getModelMaxTokens('gpt-4.5-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.5'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-4.5-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.5'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4.1 matches', () => {
|
|
expect(getModelMaxTokens('gpt-4.1')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-4.1']);
|
|
expect(getModelMaxTokens('gpt-4.1-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-4.1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4.1-2024-08-06')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4.1-mini matches', () => {
|
|
expect(getModelMaxTokens('gpt-4.1-mini')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-mini'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4.1-mini-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-mini'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-4.1-mini')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-mini'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-4.1-nano matches', () => {
|
|
expect(getModelMaxTokens('gpt-4.1-nano')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-nano'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-4.1-nano-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-nano'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-4.1-nano')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-4.1-nano'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5 matches', () => {
|
|
expect(getModelMaxTokens('gpt-5')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5']);
|
|
expect(getModelMaxTokens('gpt-5-preview')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5']);
|
|
expect(getModelMaxTokens('openai/gpt-5')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5']);
|
|
expect(getModelMaxTokens('gpt-5-2025-01-30')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5-mini matches', () => {
|
|
expect(getModelMaxTokens('gpt-5-mini')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5-mini']);
|
|
expect(getModelMaxTokens('gpt-5-mini-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-mini'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5-mini')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-mini'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5-nano matches', () => {
|
|
expect(getModelMaxTokens('gpt-5-nano')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5-nano']);
|
|
expect(getModelMaxTokens('gpt-5-nano-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-nano'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5-nano')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-nano'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5-pro matches', () => {
|
|
expect(getModelMaxTokens('gpt-5-pro')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro']);
|
|
expect(getModelMaxTokens('gpt-5-pro-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5-pro')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5-pro-2025-01-30')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-pro'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.3 matches', () => {
|
|
expect(getModelMaxTokens('gpt-5.3')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.3']);
|
|
expect(getModelMaxTokens('gpt-5.3-codex')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.3']);
|
|
expect(getModelMaxTokens('openai/gpt-5.3')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.3'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.3-2025-03-01')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.3'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.3-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.3'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.4 matches', () => {
|
|
expect(getModelMaxTokens('gpt-5.4')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.4']);
|
|
expect(getModelMaxTokens('gpt-5.4-thinking')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.4'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5.4')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.4'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.4-pro matches', () => {
|
|
expect(getModelMaxTokens('gpt-5.4-pro')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.4-pro'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5.4-pro')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.4-pro'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.5 matches', () => {
|
|
expect(maxTokensMap[EModelEndpoint.openAI]['gpt-5.5']).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5-pro'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.5']);
|
|
expect(getModelMaxTokens('gpt-5.5-thinking')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5.5')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.5-2026-04-23')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.5-pro matches', () => {
|
|
expect(getModelMaxTokens('gpt-5.5-pro')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5-pro'],
|
|
);
|
|
expect(getModelMaxTokens('openai/gpt-5.5-pro')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5-pro'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for gpt-5.6 matches', () => {
|
|
expect(getModelMaxTokens('gpt-5.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.6']);
|
|
expect(getModelMaxTokens('gpt-5.6-sol')).toBe(maxTokensMap[EModelEndpoint.openAI]['gpt-5.6']);
|
|
expect(getModelMaxTokens('openai/gpt-5.6')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.6'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.6-terra')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.6-terra'],
|
|
);
|
|
expect(getModelMaxTokens('gpt-5.6-luna-2026-07-09')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.6-luna'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for Anthropic models', () => {
|
|
const models = [
|
|
'claude-2.1',
|
|
'claude-2',
|
|
'claude-1.2',
|
|
'claude-1',
|
|
'claude-1-100k',
|
|
'claude-instant-1',
|
|
'claude-instant-1-100k',
|
|
'claude-3-haiku',
|
|
'claude-3-sonnet',
|
|
'claude-3-opus',
|
|
'claude-3-5-sonnet',
|
|
'claude-3-7-sonnet',
|
|
];
|
|
|
|
const maxTokens = {
|
|
'claude-': maxTokensMap[EModelEndpoint.anthropic]['claude-'],
|
|
'claude-2.1': maxTokensMap[EModelEndpoint.anthropic]['claude-2.1'],
|
|
'claude-3': maxTokensMap[EModelEndpoint.anthropic]['claude-3-sonnet'],
|
|
};
|
|
|
|
models.forEach((model) => {
|
|
let expectedTokens;
|
|
|
|
if (model === 'claude-2.1') {
|
|
expectedTokens = maxTokens['claude-2.1'];
|
|
} else if (model.startsWith('claude-3')) {
|
|
expectedTokens = maxTokens['claude-3'];
|
|
} else {
|
|
expectedTokens = maxTokens['claude-'];
|
|
}
|
|
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toEqual(expectedTokens);
|
|
});
|
|
});
|
|
|
|
test('should return undefined for no match - Google models', () => {
|
|
expect(getModelMaxTokens('unknown-google-model', EModelEndpoint.google)).toBeUndefined();
|
|
});
|
|
|
|
test('should return correct tokens for partial match - Google models', () => {
|
|
expect(getModelMaxTokens('gemini-2.0-flash-lite-preview-02-05', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash-lite'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.0-flash-001', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.0-flash-exp', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.0-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.0-pro-exp-02-05', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.0'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-1.5-flash-8b', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-1.5-flash-8b'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-1.5-flash-thinking', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-1.5-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-1.5-pro-latest', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-1.5'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-1.5-pro-preview-0409', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-1.5'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.1-pro-preview', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.1'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.1-pro-preview-customtools', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.1'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.5-flash', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.5-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.5-flash-lite', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.5-flash-lite'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.6-flash', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.6-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.7-flash', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.7-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-3.8-flash', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-3.8-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-4-argon', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-4-argon'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.5-pro', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.5-pro'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.5-flash', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.5-flash'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-2.5-flash-lite', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-2.5-flash-lite'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-pro-vision', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini-pro-vision'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-1.0', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini'],
|
|
);
|
|
expect(getModelMaxTokens('gemini-pro', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemini'],
|
|
);
|
|
});
|
|
|
|
test('should return correct context tokens for Gemma models', () => {
|
|
expect(maxTokensMap[EModelEndpoint.google].gemma).toBe(32768);
|
|
expect(getModelMaxTokens('gemma', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google].gemma,
|
|
);
|
|
expect(getModelMaxTokens('gemma-2-9b-it', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemma-2'],
|
|
);
|
|
expect(getModelMaxTokens('gemma-3-27b-it', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemma-3-27b'],
|
|
);
|
|
expect(getModelMaxTokens('gemma4:latest', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google].gemma4,
|
|
);
|
|
expect(getModelMaxTokens('gemma4:e4b', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google].gemma4,
|
|
);
|
|
expect(getModelMaxTokens('Gemma4:31B', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['gemma4:31b'],
|
|
);
|
|
expect(getModelMaxTokens('ollama/gemma4:31b', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['gemma4:31b'],
|
|
);
|
|
expect(getModelMaxTokens('google/gemma-4-31B-it', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemma-4-31b'],
|
|
);
|
|
expect(getModelMaxTokens('google/gemma-4-26B-A4B-it', EModelEndpoint.google)).toBe(
|
|
maxTokensMap[EModelEndpoint.google]['gemma-4-26b-a4b'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for partial match - Cohere models', () => {
|
|
expect(getModelMaxTokens('command', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['command'],
|
|
);
|
|
expect(getModelMaxTokens('command-r-plus', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['command-r-plus'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens when using a custom endpointTokenConfig', () => {
|
|
const customTokenConfig = {
|
|
'custom-model': 12345,
|
|
};
|
|
expect(getModelMaxTokens('custom-model', EModelEndpoint.openAI, customTokenConfig)).toBe(12345);
|
|
});
|
|
|
|
test('should prioritize endpointTokenConfig over the default configuration', () => {
|
|
const customTokenConfig = {
|
|
'gpt-4-32k': 9999,
|
|
};
|
|
expect(getModelMaxTokens('gpt-4-32k', EModelEndpoint.openAI, customTokenConfig)).toBe(9999);
|
|
});
|
|
|
|
test('should return undefined if the model is not found in custom endpointTokenConfig', () => {
|
|
const customTokenConfig = {
|
|
'custom-model': 12345,
|
|
};
|
|
expect(
|
|
getModelMaxTokens('nonexistent-model', EModelEndpoint.openAI, customTokenConfig),
|
|
).toBeUndefined();
|
|
});
|
|
|
|
test('should return correct tokens for exact match in azureOpenAI models', () => {
|
|
expect(getModelMaxTokens('gpt-4-turbo', EModelEndpoint.azureOpenAI)).toBe(
|
|
maxTokensMap[EModelEndpoint.azureOpenAI]['gpt-4-turbo'],
|
|
);
|
|
});
|
|
|
|
test('should return undefined for no match in azureOpenAI models', () => {
|
|
expect(
|
|
getModelMaxTokens('nonexistent-azure-model', EModelEndpoint.azureOpenAI),
|
|
).toBeUndefined();
|
|
});
|
|
|
|
test('should return undefined for undefined, null, or number model argument with azureOpenAI endpoint', () => {
|
|
expect(getModelMaxTokens(undefined, EModelEndpoint.azureOpenAI)).toBeUndefined();
|
|
expect(getModelMaxTokens(null, EModelEndpoint.azureOpenAI)).toBeUndefined();
|
|
expect(getModelMaxTokens(1234, EModelEndpoint.azureOpenAI)).toBeUndefined();
|
|
});
|
|
|
|
test('should respect custom endpointTokenConfig over azureOpenAI defaults', () => {
|
|
const customTokenConfig = {
|
|
'custom-azure-model': 4096,
|
|
};
|
|
expect(
|
|
getModelMaxTokens('custom-azure-model', EModelEndpoint.azureOpenAI, customTokenConfig),
|
|
).toBe(4096);
|
|
});
|
|
|
|
test('should return correct tokens for partial match with custom endpointTokenConfig in azureOpenAI', () => {
|
|
const customTokenConfig = {
|
|
'azure-custom-': 1024,
|
|
};
|
|
expect(
|
|
getModelMaxTokens('azure-custom-gpt-3', EModelEndpoint.azureOpenAI, customTokenConfig),
|
|
).toBe(1024);
|
|
});
|
|
|
|
test('should return undefined for a model when using an unsupported endpoint', () => {
|
|
expect(getModelMaxTokens('azure-gpt-3', 'unsupportedEndpoint')).toBeUndefined();
|
|
});
|
|
|
|
test('should return correct max context tokens for o1-series models', () => {
|
|
// Standard o1 variations
|
|
const o1Tokens = maxTokensMap[EModelEndpoint.openAI]['o1'];
|
|
expect(getModelMaxTokens('o1')).toBe(o1Tokens);
|
|
expect(getModelMaxTokens('o1-latest')).toBe(o1Tokens);
|
|
expect(getModelMaxTokens('o1-2024-12-17')).toBe(o1Tokens);
|
|
expect(getModelMaxTokens('o1-something-else')).toBe(o1Tokens);
|
|
expect(getModelMaxTokens('openai/o1-something-else')).toBe(o1Tokens);
|
|
|
|
// Mini variations
|
|
const o1MiniTokens = maxTokensMap[EModelEndpoint.openAI]['o1-mini'];
|
|
expect(getModelMaxTokens('o1-mini')).toBe(o1MiniTokens);
|
|
expect(getModelMaxTokens('o1-mini-latest')).toBe(o1MiniTokens);
|
|
expect(getModelMaxTokens('o1-mini-2024-09-12')).toBe(o1MiniTokens);
|
|
expect(getModelMaxTokens('o1-mini-something')).toBe(o1MiniTokens);
|
|
expect(getModelMaxTokens('openai/o1-mini-something')).toBe(o1MiniTokens);
|
|
|
|
// Preview variations
|
|
const o1PreviewTokens = maxTokensMap[EModelEndpoint.openAI]['o1-preview'];
|
|
expect(getModelMaxTokens('o1-preview')).toBe(o1PreviewTokens);
|
|
expect(getModelMaxTokens('o1-preview-latest')).toBe(o1PreviewTokens);
|
|
expect(getModelMaxTokens('o1-preview-2024-09-12')).toBe(o1PreviewTokens);
|
|
expect(getModelMaxTokens('o1-preview-something')).toBe(o1PreviewTokens);
|
|
expect(getModelMaxTokens('openai/o1-preview-something')).toBe(o1PreviewTokens);
|
|
});
|
|
|
|
test('should return correct max context tokens for o4-mini and o3', () => {
|
|
const o4MiniTokens = maxTokensMap[EModelEndpoint.openAI]['o4-mini'];
|
|
const o3Tokens = maxTokensMap[EModelEndpoint.openAI]['o3'];
|
|
expect(getModelMaxTokens('o4-mini')).toBe(o4MiniTokens);
|
|
expect(getModelMaxTokens('openai/o4-mini')).toBe(o4MiniTokens);
|
|
expect(getModelMaxTokens('o3')).toBe(o3Tokens);
|
|
expect(getModelMaxTokens('openai/o3')).toBe(o3Tokens);
|
|
});
|
|
|
|
test('should return correct tokens for GPT-OSS models', () => {
|
|
const expected = maxTokensMap[EModelEndpoint.openAI]['gpt-oss'];
|
|
[
|
|
'gpt-oss:20b',
|
|
'gpt-oss-20b',
|
|
'gpt-oss-120b',
|
|
'openai/gpt-oss-20b',
|
|
'openai/gpt-oss-120b',
|
|
'openai/gpt-oss:120b',
|
|
].forEach((name) => {
|
|
expect(getModelMaxTokens(name)).toBe(expected);
|
|
});
|
|
});
|
|
|
|
test('should return correct tokens for GLM models', () => {
|
|
expect(getModelMaxTokens('glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('glm-4.5v')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5v']);
|
|
expect(getModelMaxTokens('glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
|
|
expect(getModelMaxTokens('glm-4-32b')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4-32b']);
|
|
expect(getModelMaxTokens('glm-4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4']);
|
|
expect(getModelMaxTokens('glm4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm4']);
|
|
});
|
|
|
|
test('should return correct tokens for GLM models with provider prefixes', () => {
|
|
expect(getModelMaxTokens('z-ai/glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5v')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4-32b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
|
|
);
|
|
|
|
expect(getModelMaxTokens('zai/glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('zai/glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('zai/glm-4.5v')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5v']);
|
|
|
|
expect(getModelMaxTokens('zai-org/GLM-4.6')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5-Air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5V')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4-32B-0414')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for GLM models with suffixes', () => {
|
|
expect(getModelMaxTokens('glm-4.6-fp8')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.6-FP8')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5-Air-FP8')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('findMatchingPattern - longest match wins', () => {
|
|
test('should prefer longer matching key over shorter cross-provider pattern', () => {
|
|
const result = findMatchingPattern(
|
|
'gpt-5.2-chat-2025-12-11',
|
|
maxTokensMap[EModelEndpoint.openAI],
|
|
);
|
|
expect(result).toBe('gpt-5.2');
|
|
});
|
|
|
|
test('should match gpt-5.2 tokens for date-suffixed chat variant', () => {
|
|
expect(getModelMaxTokens('gpt-5.2-chat-2025-12-11')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.2'],
|
|
);
|
|
});
|
|
|
|
test('should match gpt-5.2-pro over shorter patterns', () => {
|
|
expect(getModelMaxTokens('gpt-5.2-pro-chat-2025-12-11')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.2-pro'],
|
|
);
|
|
});
|
|
|
|
test('should match gpt-5.5-pro over shorter patterns', () => {
|
|
expect(getModelMaxTokens('gpt-5.5-pro-2026-04-23')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5.5-pro'],
|
|
);
|
|
});
|
|
|
|
test('should match gpt-5-mini over gpt-5 for mini variants', () => {
|
|
expect(getModelMaxTokens('gpt-5-mini-chat-2025-01-01')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['gpt-5-mini'],
|
|
);
|
|
});
|
|
|
|
test('should prefer gpt-4-1106 over gpt-4 for versioned model names', () => {
|
|
const result = findMatchingPattern('gpt-4-1106-preview', maxTokensMap[EModelEndpoint.openAI]);
|
|
expect(result).toBe('gpt-4-1106');
|
|
});
|
|
|
|
test('should prefer gpt-4-32k-0613 over gpt-4-32k for exact versioned names', () => {
|
|
const result = findMatchingPattern('gpt-4-32k-0613', maxTokensMap[EModelEndpoint.openAI]);
|
|
expect(result).toBe('gpt-4-32k-0613');
|
|
});
|
|
|
|
test('should prefer claude-3-5-sonnet over claude-3', () => {
|
|
const result = findMatchingPattern(
|
|
'claude-3-5-sonnet-20241022',
|
|
maxTokensMap[EModelEndpoint.anthropic],
|
|
);
|
|
expect(result).toBe('claude-3-5-sonnet');
|
|
});
|
|
|
|
test('should prefer gemini-2.0-flash-lite over gemini-2.0-flash', () => {
|
|
const result = findMatchingPattern(
|
|
'gemini-2.0-flash-lite-preview',
|
|
maxTokensMap[EModelEndpoint.google],
|
|
);
|
|
expect(result).toBe('gemini-2.0-flash-lite');
|
|
});
|
|
});
|
|
|
|
describe('findMatchingPattern - bestLength selection', () => {
|
|
test('should return the longest matching key when multiple keys match', () => {
|
|
const tokensMap = { short: 100, 'short-med': 200, 'short-med-long': 300 };
|
|
expect(findMatchingPattern('short-med-long-extra', tokensMap)).toBe('short-med-long');
|
|
});
|
|
|
|
test('should return the longest match regardless of key insertion order', () => {
|
|
const tokensMap = { 'a-b-c': 300, a: 100, 'a-b': 200 };
|
|
expect(findMatchingPattern('a-b-c-d', tokensMap)).toBe('a-b-c');
|
|
});
|
|
|
|
test('should return null when no key matches', () => {
|
|
const tokensMap = { alpha: 100, beta: 200 };
|
|
expect(findMatchingPattern('gamma-delta', tokensMap)).toBeNull();
|
|
});
|
|
|
|
test('should return the single matching key when only one matches', () => {
|
|
const tokensMap = { alpha: 100, beta: 200, gamma: 300 };
|
|
expect(findMatchingPattern('beta-extended', tokensMap)).toBe('beta');
|
|
});
|
|
|
|
test('should match case-insensitively against model name', () => {
|
|
const tokensMap = { 'gpt-5': 400000 };
|
|
expect(findMatchingPattern('GPT-5-turbo', tokensMap)).toBe('gpt-5');
|
|
});
|
|
|
|
test('should select the longest key among overlapping substring matches', () => {
|
|
const tokensMap = { 'gpt-': 100, 'gpt-5': 200, 'gpt-5.2': 300, 'gpt-5.2-pro': 400 };
|
|
expect(findMatchingPattern('gpt-5.2-pro-2025-01-01', tokensMap)).toBe('gpt-5.2-pro');
|
|
expect(findMatchingPattern('gpt-5.2-chat-2025-01-01', tokensMap)).toBe('gpt-5.2');
|
|
expect(findMatchingPattern('gpt-5.1-preview', tokensMap)).toBe('gpt-5');
|
|
expect(findMatchingPattern('gpt-unknown', tokensMap)).toBe('gpt-');
|
|
});
|
|
|
|
test('should not be confused by a short key that appears later in the model name', () => {
|
|
const tokensMap = { 'model-v2': 200, v2: 100 };
|
|
expect(findMatchingPattern('model-v2-extended', tokensMap)).toBe('model-v2');
|
|
});
|
|
|
|
test('should handle exact-length match as the best match', () => {
|
|
const tokensMap = { 'exact-model': 500, exact: 100 };
|
|
expect(findMatchingPattern('exact-model', tokensMap)).toBe('exact-model');
|
|
});
|
|
|
|
test('should return null for empty model name', () => {
|
|
expect(findMatchingPattern('', { 'gpt-5': 400000 })).toBeNull();
|
|
});
|
|
|
|
test('should prefer last-defined key on same-length ties', () => {
|
|
const tokensMap = { 'aa-bb': 100, 'cc-dd': 200 };
|
|
// model name contains both 5-char keys; last-defined wins in reverse iteration
|
|
expect(findMatchingPattern('aa-bb-cc-dd', tokensMap)).toBe('cc-dd');
|
|
});
|
|
|
|
test('longest match beats short cross-provider pattern even when both present', () => {
|
|
const tokensMap = { 'gpt-5.2': 400000, 'chat-': 8187 };
|
|
expect(findMatchingPattern('gpt-5.2-chat-2025-12-11', tokensMap)).toBe('gpt-5.2');
|
|
});
|
|
|
|
test('should match case-insensitively against keys', () => {
|
|
const tokensMap = { 'GPT-5': 400000 };
|
|
expect(findMatchingPattern('gpt-5-turbo', tokensMap)).toBe('GPT-5');
|
|
});
|
|
});
|
|
|
|
describe('findMatchingPattern - iteration performance', () => {
|
|
let includesSpy;
|
|
|
|
beforeEach(() => {
|
|
includesSpy = jest.spyOn(String.prototype, 'includes');
|
|
});
|
|
|
|
afterEach(() => {
|
|
includesSpy.mockRestore();
|
|
});
|
|
|
|
test('exact match early-exits with minimal includes() checks', () => {
|
|
const openAIMap = maxTokensMap[EModelEndpoint.openAI];
|
|
const keys = Object.keys(openAIMap);
|
|
const lastKey = keys[keys.length - 1];
|
|
includesSpy.mockClear();
|
|
const result = findMatchingPattern(lastKey, openAIMap);
|
|
const exactCalls = includesSpy.mock.calls.length;
|
|
|
|
expect(result).toBe(lastKey);
|
|
expect(exactCalls).toBe(1);
|
|
});
|
|
|
|
test('bestLength check skips includes() for shorter keys after a long match', () => {
|
|
const openAIMap = maxTokensMap[EModelEndpoint.openAI];
|
|
includesSpy.mockClear();
|
|
findMatchingPattern('gpt-3.5-turbo-0301-test', openAIMap);
|
|
const longKeyCalls = includesSpy.mock.calls.length;
|
|
|
|
includesSpy.mockClear();
|
|
findMatchingPattern('gpt-5.3-chat-latest', openAIMap);
|
|
const shortKeyCalls = includesSpy.mock.calls.length;
|
|
|
|
// gpt-3.5-turbo-0301 (20 chars) matches early, then bestLength prunes most keys
|
|
// gpt-5.3 (7 chars) is short, so fewer keys are pruned by the length check
|
|
expect(longKeyCalls).toBeLessThan(shortKeyCalls);
|
|
});
|
|
|
|
test('last-defined keys are checked first in reverse iteration', () => {
|
|
const tokensMap = { first: 100, second: 200, third: 300 };
|
|
includesSpy.mockClear();
|
|
const result = findMatchingPattern('third', tokensMap);
|
|
const calls = includesSpy.mock.calls.length;
|
|
|
|
// 'third' is last key, found on first reverse check, exact match exits immediately
|
|
expect(result).toBe('third');
|
|
expect(calls).toBe(1);
|
|
});
|
|
});
|
|
|
|
describe('deprecated PaLM2/Codey model removal', () => {
|
|
test('deprecated PaLM2/Codey models no longer have token entries', () => {
|
|
expect(getModelMaxTokens('text-bison-32k', EModelEndpoint.google)).toBeUndefined();
|
|
expect(getModelMaxTokens('codechat-bison-32k', EModelEndpoint.google)).toBeUndefined();
|
|
expect(getModelMaxTokens('code-bison', EModelEndpoint.google)).toBeUndefined();
|
|
expect(getModelMaxTokens('chat-bison', EModelEndpoint.google)).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
it('should return the exact model name if it exists in maxTokensMap', () => {
|
|
expect(matchModelName('gpt-4-32k-0613')).toBe('gpt-4-32k-0613');
|
|
});
|
|
|
|
it('should return the closest matching key for partial matches', () => {
|
|
expect(matchModelName('gpt-4-32k-unknown')).toBe('gpt-4-32k');
|
|
});
|
|
|
|
it('should return the input model name if no match is found', () => {
|
|
expect(matchModelName('unknown-model')).toBe('unknown-model');
|
|
});
|
|
|
|
it('should return undefined for non-string inputs', () => {
|
|
expect(matchModelName(undefined)).toBeUndefined();
|
|
expect(matchModelName(null)).toBeUndefined();
|
|
expect(matchModelName(123)).toBeUndefined();
|
|
expect(matchModelName({})).toBeUndefined();
|
|
});
|
|
|
|
// 11/06 Update
|
|
it('should return the exact model name for gpt-3.5-turbo-1106 if it exists in maxTokensMap', () => {
|
|
expect(matchModelName('gpt-3.5-turbo-1106')).toBe('gpt-3.5-turbo-1106');
|
|
});
|
|
|
|
it('should return the exact model name for gpt-4-1106 if it exists in maxTokensMap', () => {
|
|
expect(matchModelName('gpt-4-1106')).toBe('gpt-4-1106');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-3.5-turbo-1106 partial matches', () => {
|
|
expect(matchModelName('gpt-3.5-turbo-1106/something')).toBe('gpt-3.5-turbo-1106');
|
|
expect(matchModelName('something/gpt-3.5-turbo-1106')).toBe('gpt-3.5-turbo-1106');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-4-1106 partial matches', () => {
|
|
expect(matchModelName('gpt-4-1106/something')).toBe('gpt-4-1106');
|
|
expect(matchModelName('gpt-4-1106-preview')).toBe('gpt-4-1106');
|
|
expect(matchModelName('gpt-4-1106-vision-preview')).toBe('gpt-4-1106');
|
|
});
|
|
|
|
// 01/25 Update
|
|
it('should return the closest matching key for gpt-4-turbo/0125 matches', () => {
|
|
expect(matchModelName('openai/gpt-4-0125')).toBe('gpt-4-0125');
|
|
expect(matchModelName('gpt-4-turbo-preview')).toBe('gpt-4-turbo');
|
|
expect(matchModelName('gpt-4-turbo-vision-preview')).toBe('gpt-4-turbo');
|
|
expect(matchModelName('gpt-4-0125')).toBe('gpt-4-0125');
|
|
expect(matchModelName('gpt-4-0125-preview')).toBe('gpt-4-0125');
|
|
expect(matchModelName('gpt-4-0125-vision-preview')).toBe('gpt-4-0125');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-4.1 matches', () => {
|
|
expect(matchModelName('openai/gpt-4.1')).toBe('gpt-4.1');
|
|
expect(matchModelName('gpt-4.1-preview')).toBe('gpt-4.1');
|
|
expect(matchModelName('gpt-4.1-2024-08-06')).toBe('gpt-4.1');
|
|
expect(matchModelName('gpt-4.1-2024-08-06-0718')).toBe('gpt-4.1');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-4.1-mini matches', () => {
|
|
expect(matchModelName('openai/gpt-4.1-mini')).toBe('gpt-4.1-mini');
|
|
expect(matchModelName('gpt-4.1-mini-preview')).toBe('gpt-4.1-mini');
|
|
expect(matchModelName('gpt-4.1-mini-2024-08-06')).toBe('gpt-4.1-mini');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-4.1-nano matches', () => {
|
|
expect(matchModelName('openai/gpt-4.1-nano')).toBe('gpt-4.1-nano');
|
|
expect(matchModelName('gpt-4.1-nano-preview')).toBe('gpt-4.1-nano');
|
|
expect(matchModelName('gpt-4.1-nano-2024-08-06')).toBe('gpt-4.1-nano');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5 matches', () => {
|
|
expect(matchModelName('openai/gpt-5')).toBe('gpt-5');
|
|
expect(matchModelName('gpt-5-preview')).toBe('gpt-5');
|
|
expect(matchModelName('gpt-5-2025-01-30')).toBe('gpt-5');
|
|
expect(matchModelName('gpt-5-2025-01-30-0130')).toBe('gpt-5');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5-mini matches', () => {
|
|
expect(matchModelName('openai/gpt-5-mini')).toBe('gpt-5-mini');
|
|
expect(matchModelName('gpt-5-mini-preview')).toBe('gpt-5-mini');
|
|
expect(matchModelName('gpt-5-mini-2025-01-30')).toBe('gpt-5-mini');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5-nano matches', () => {
|
|
expect(matchModelName('openai/gpt-5-nano')).toBe('gpt-5-nano');
|
|
expect(matchModelName('gpt-5-nano-preview')).toBe('gpt-5-nano');
|
|
expect(matchModelName('gpt-5-nano-2025-01-30')).toBe('gpt-5-nano');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5-pro matches', () => {
|
|
expect(matchModelName('openai/gpt-5-pro')).toBe('gpt-5-pro');
|
|
expect(matchModelName('gpt-5-pro-preview')).toBe('gpt-5-pro');
|
|
expect(matchModelName('gpt-5-pro-2025-01-30')).toBe('gpt-5-pro');
|
|
expect(matchModelName('gpt-5-pro-2025-01-30-0130')).toBe('gpt-5-pro');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5.3 matches', () => {
|
|
expect(matchModelName('openai/gpt-5.3')).toBe('gpt-5.3');
|
|
expect(matchModelName('gpt-5.3-codex')).toBe('gpt-5.3');
|
|
expect(matchModelName('gpt-5.3-2025-03-01')).toBe('gpt-5.3');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5.4 matches', () => {
|
|
expect(matchModelName('openai/gpt-5.4')).toBe('gpt-5.4');
|
|
expect(matchModelName('gpt-5.4-thinking')).toBe('gpt-5.4');
|
|
expect(matchModelName('gpt-5.4-pro')).toBe('gpt-5.4-pro');
|
|
});
|
|
|
|
it('should return the closest matching key for gpt-5.5 matches', () => {
|
|
expect(matchModelName('openai/gpt-5.5')).toBe('gpt-5.5');
|
|
expect(matchModelName('gpt-5.5-thinking')).toBe('gpt-5.5');
|
|
expect(matchModelName('gpt-5.5-pro')).toBe('gpt-5.5-pro');
|
|
});
|
|
|
|
it('should return the input model name if no match is found - Google models', () => {
|
|
expect(matchModelName('unknown-google-model', EModelEndpoint.google)).toBe(
|
|
'unknown-google-model',
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('Meta Models Tests', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for LLaMa 2 models', () => {
|
|
const llama2Tokens = maxTokensMap[EModelEndpoint.openAI]['llama2'];
|
|
expect(getModelMaxTokens('llama2')).toBe(llama2Tokens);
|
|
expect(getModelMaxTokens('llama2.70b')).toBe(llama2Tokens);
|
|
expect(getModelMaxTokens('llama2-13b')).toBe(llama2Tokens);
|
|
expect(getModelMaxTokens('llama2-70b')).toBe(llama2Tokens);
|
|
});
|
|
|
|
test('should return correct tokens for LLaMa 3 models', () => {
|
|
const llama3Tokens = maxTokensMap[EModelEndpoint.openAI]['llama3'];
|
|
expect(getModelMaxTokens('llama3')).toBe(llama3Tokens);
|
|
expect(getModelMaxTokens('llama3.8b')).toBe(llama3Tokens);
|
|
expect(getModelMaxTokens('llama3.70b')).toBe(llama3Tokens);
|
|
expect(getModelMaxTokens('llama3-8b')).toBe(llama3Tokens);
|
|
expect(getModelMaxTokens('llama3-70b')).toBe(llama3Tokens);
|
|
});
|
|
|
|
test('should return correct tokens for LLaMa 3.1 models', () => {
|
|
const llama31Tokens = maxTokensMap[EModelEndpoint.openAI]['llama3.1:8b'];
|
|
expect(getModelMaxTokens('llama3.1:8b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('llama3.1:70b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('llama3.1:405b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('llama3-1-8b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('llama3-1-70b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('llama3-1-405b')).toBe(llama31Tokens);
|
|
});
|
|
|
|
test('should handle partial matches for Meta models', () => {
|
|
const llama31Tokens = maxTokensMap[EModelEndpoint.openAI]['llama3.1:8b'];
|
|
const llama3Tokens = maxTokensMap[EModelEndpoint.openAI]['llama3'];
|
|
const llama2Tokens = maxTokensMap[EModelEndpoint.openAI]['llama2'];
|
|
expect(getModelMaxTokens('meta/llama3.1:405b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('meta/llama3.1:70b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('meta/llama3.1:8b')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('meta/llama3-1-8b')).toBe(llama31Tokens);
|
|
|
|
expect(getModelMaxTokens('meta/llama3.1')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('meta/llama3-1')).toBe(llama31Tokens);
|
|
expect(getModelMaxTokens('meta/llama3')).toBe(llama3Tokens);
|
|
expect(getModelMaxTokens('meta/llama2')).toBe(llama2Tokens);
|
|
});
|
|
|
|
test('should match Deepseek model variations', () => {
|
|
expect(getModelMaxTokens('deepseek-chat')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-chat'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek-coder')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek-reasoner')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-reasoner'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek.r1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek.r1'],
|
|
);
|
|
});
|
|
|
|
test('should return correct context tokens for all DeepSeek models', () => {
|
|
const deepseekChatTokens = maxTokensMap[EModelEndpoint.openAI]['deepseek-chat'];
|
|
expect(getModelMaxTokens('deepseek-chat')).toBe(deepseekChatTokens);
|
|
expect(getModelMaxTokens('deepseek-reasoner')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-reasoner'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek-r1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-r1'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek-v3')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek'],
|
|
);
|
|
expect(getModelMaxTokens('deepseek.r1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek.r1'],
|
|
);
|
|
});
|
|
|
|
test('should handle DeepSeek models with provider prefixes', () => {
|
|
expect(getModelMaxTokens('deepseek/deepseek-chat')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-chat'],
|
|
);
|
|
expect(getModelMaxTokens('openrouter/deepseek-reasoner')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek-reasoner'],
|
|
);
|
|
expect(getModelMaxTokens('openai/deepseek-v3')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['deepseek'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match exact LLaMa model names', () => {
|
|
expect(matchModelName('llama2')).toBe('llama2');
|
|
expect(matchModelName('llama3')).toBe('llama3');
|
|
expect(matchModelName('llama3.1:8b')).toBe('llama3.1:8b');
|
|
});
|
|
|
|
test('should match LLaMa model variations', () => {
|
|
// Test full model names
|
|
expect(matchModelName('meta/llama3.1:405b')).toBe('llama3.1:405b');
|
|
expect(matchModelName('meta/llama3.1:70b')).toBe('llama3.1:70b');
|
|
expect(matchModelName('meta/llama3.1:8b')).toBe('llama3.1:8b');
|
|
expect(matchModelName('meta/llama3-1-8b')).toBe('llama3-1-8b');
|
|
|
|
// Test base versions
|
|
expect(matchModelName('meta/llama3.1')).toBe('llama3.1');
|
|
expect(matchModelName('meta/llama3-1')).toBe('llama3-1');
|
|
});
|
|
|
|
test('should handle custom endpoint for Meta models', () => {
|
|
expect(matchModelName('llama2', EModelEndpoint.bedrock)).toBe('llama2');
|
|
expect(matchModelName('llama3', EModelEndpoint.bedrock)).toBe('llama3');
|
|
expect(matchModelName('llama3.1:8b', EModelEndpoint.bedrock)).toBe('llama3.1:8b');
|
|
});
|
|
|
|
test('should match Deepseek model variations', () => {
|
|
expect(matchModelName('deepseek-chat')).toBe('deepseek-chat');
|
|
expect(matchModelName('deepseek-coder')).toBe('deepseek');
|
|
});
|
|
});
|
|
|
|
describe('processModelData with Meta models', () => {
|
|
test('should process Meta model data correctly', () => {
|
|
const input = {
|
|
data: [
|
|
{
|
|
id: 'llama2',
|
|
pricing: {
|
|
prompt: '0.00001',
|
|
completion: '0.00003',
|
|
},
|
|
context_length: 4000,
|
|
},
|
|
{
|
|
id: 'llama3',
|
|
pricing: {
|
|
prompt: '0.00002',
|
|
completion: '0.00004',
|
|
},
|
|
context_length: 8000,
|
|
},
|
|
],
|
|
};
|
|
|
|
const result = processModelData(input);
|
|
expect(result.llama2).toEqual({
|
|
prompt: 10,
|
|
completion: 30,
|
|
context: 4000,
|
|
});
|
|
expect(result.llama3).toEqual({
|
|
prompt: 20,
|
|
completion: 40,
|
|
context: 8000,
|
|
});
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('Grok Model Tests - Tokens', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for Grok vision models', () => {
|
|
const grok2VisionTokens = maxTokensMap[EModelEndpoint.openAI]['grok-2-vision'];
|
|
expect(getModelMaxTokens('grok-2-vision-1212')).toBe(grok2VisionTokens);
|
|
expect(getModelMaxTokens('grok-2-vision')).toBe(grok2VisionTokens);
|
|
expect(getModelMaxTokens('grok-2-vision-latest')).toBe(grok2VisionTokens);
|
|
});
|
|
|
|
test('should return correct tokens for Grok beta models', () => {
|
|
expect(getModelMaxTokens('grok-vision-beta')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-vision-beta'],
|
|
);
|
|
expect(getModelMaxTokens('grok-beta')).toBe(maxTokensMap[EModelEndpoint.openAI]['grok-beta']);
|
|
});
|
|
|
|
test('should return correct tokens for Grok text models', () => {
|
|
const grok2Tokens = maxTokensMap[EModelEndpoint.openAI]['grok-2'];
|
|
expect(getModelMaxTokens('grok-2-1212')).toBe(grok2Tokens);
|
|
expect(getModelMaxTokens('grok-2')).toBe(grok2Tokens);
|
|
expect(getModelMaxTokens('grok-2-latest')).toBe(grok2Tokens);
|
|
});
|
|
|
|
test('should return correct tokens for Grok 3 series models', () => {
|
|
expect(getModelMaxTokens('grok-3')).toBe(maxTokensMap[EModelEndpoint.openAI]['grok-3']);
|
|
expect(getModelMaxTokens('grok-3-fast')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-fast'],
|
|
);
|
|
expect(getModelMaxTokens('grok-3-mini')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-mini'],
|
|
);
|
|
expect(getModelMaxTokens('grok-3-mini-fast')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-mini-fast'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for Grok 4 model', () => {
|
|
expect(getModelMaxTokens('grok-4-0709')).toBe(maxTokensMap[EModelEndpoint.openAI]['grok-4']);
|
|
});
|
|
|
|
test('should return correct tokens for Grok 4 Fast and Grok 4.1 Fast models', () => {
|
|
const grok4FastTokens = maxTokensMap[EModelEndpoint.openAI]['grok-4-fast'];
|
|
const grok41FastTokens = maxTokensMap[EModelEndpoint.openAI]['grok-4-1-fast'];
|
|
expect(getModelMaxTokens('grok-4-fast')).toBe(grok4FastTokens);
|
|
expect(getModelMaxTokens('grok-4-1-fast-reasoning')).toBe(grok41FastTokens);
|
|
expect(getModelMaxTokens('grok-4-1-fast-non-reasoning')).toBe(grok41FastTokens);
|
|
});
|
|
|
|
test('should return correct tokens for Grok Code Fast model', () => {
|
|
expect(getModelMaxTokens('grok-code-fast-1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-code-fast'],
|
|
);
|
|
});
|
|
|
|
test('should handle partial matches for Grok models with prefixes', () => {
|
|
const grok2VisionTokens = maxTokensMap[EModelEndpoint.openAI]['grok-2-vision'];
|
|
const grokVisionBetaTokens = maxTokensMap[EModelEndpoint.openAI]['grok-vision-beta'];
|
|
const grokBetaTokens = maxTokensMap[EModelEndpoint.openAI]['grok-beta'];
|
|
const grok2Tokens = maxTokensMap[EModelEndpoint.openAI]['grok-2'];
|
|
const grok3Tokens = maxTokensMap[EModelEndpoint.openAI]['grok-3'];
|
|
const grok4Tokens = maxTokensMap[EModelEndpoint.openAI]['grok-4'];
|
|
const grok4FastTokens = maxTokensMap[EModelEndpoint.openAI]['grok-4-fast'];
|
|
const grok41FastTokens = maxTokensMap[EModelEndpoint.openAI]['grok-4-1-fast'];
|
|
const grokCodeFastTokens = maxTokensMap[EModelEndpoint.openAI]['grok-code-fast'];
|
|
expect(getModelMaxTokens('xai/grok-2-vision-1212')).toBe(grok2VisionTokens);
|
|
expect(getModelMaxTokens('xai/grok-2-vision')).toBe(grok2VisionTokens);
|
|
expect(getModelMaxTokens('xai/grok-2-vision-latest')).toBe(grok2VisionTokens);
|
|
expect(getModelMaxTokens('xai/grok-vision-beta')).toBe(grokVisionBetaTokens);
|
|
expect(getModelMaxTokens('xai/grok-beta')).toBe(grokBetaTokens);
|
|
expect(getModelMaxTokens('xai/grok-2-1212')).toBe(grok2Tokens);
|
|
expect(getModelMaxTokens('xai/grok-2')).toBe(grok2Tokens);
|
|
expect(getModelMaxTokens('xai/grok-2-latest')).toBe(grok2Tokens);
|
|
expect(getModelMaxTokens('xai/grok-3')).toBe(grok3Tokens);
|
|
expect(getModelMaxTokens('xai/grok-3-fast')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-fast'],
|
|
);
|
|
expect(getModelMaxTokens('xai/grok-3-mini')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-mini'],
|
|
);
|
|
expect(getModelMaxTokens('xai/grok-3-mini-fast')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['grok-3-mini-fast'],
|
|
);
|
|
expect(getModelMaxTokens('xai/grok-4-0709')).toBe(grok4Tokens);
|
|
expect(getModelMaxTokens('xai/grok-4-fast')).toBe(grok4FastTokens);
|
|
expect(getModelMaxTokens('xai/grok-4-1-fast-reasoning')).toBe(grok41FastTokens);
|
|
expect(getModelMaxTokens('xai/grok-4-1-fast-non-reasoning')).toBe(grok41FastTokens);
|
|
expect(getModelMaxTokens('xai/grok-code-fast-1')).toBe(grokCodeFastTokens);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match exact Grok model names', () => {
|
|
// Vision models
|
|
expect(matchModelName('grok-2-vision-1212')).toBe('grok-2-vision-1212');
|
|
expect(matchModelName('grok-2-vision')).toBe('grok-2-vision');
|
|
expect(matchModelName('grok-2-vision-latest')).toBe('grok-2-vision-latest');
|
|
// Beta models
|
|
expect(matchModelName('grok-vision-beta')).toBe('grok-vision-beta');
|
|
expect(matchModelName('grok-beta')).toBe('grok-beta');
|
|
// Text models
|
|
expect(matchModelName('grok-2-1212')).toBe('grok-2-1212');
|
|
expect(matchModelName('grok-2')).toBe('grok-2');
|
|
expect(matchModelName('grok-2-latest')).toBe('grok-2-latest');
|
|
// Grok 3 models
|
|
expect(matchModelName('grok-3')).toBe('grok-3');
|
|
expect(matchModelName('grok-3-fast')).toBe('grok-3-fast');
|
|
expect(matchModelName('grok-3-mini')).toBe('grok-3-mini');
|
|
expect(matchModelName('grok-3-mini-fast')).toBe('grok-3-mini-fast');
|
|
// Grok 4 model
|
|
expect(matchModelName('grok-4-0709')).toBe('grok-4');
|
|
// Grok 4 Fast and 4.1 Fast models
|
|
expect(matchModelName('grok-4-fast')).toBe('grok-4-fast');
|
|
expect(matchModelName('grok-4-1-fast-reasoning')).toBe('grok-4-1-fast');
|
|
expect(matchModelName('grok-4-1-fast-non-reasoning')).toBe('grok-4-1-fast');
|
|
// Grok Code Fast model
|
|
expect(matchModelName('grok-code-fast-1')).toBe('grok-code-fast');
|
|
});
|
|
|
|
test('should match Grok model variations with prefixes', () => {
|
|
// Vision models should match before general models
|
|
expect(matchModelName('xai/grok-2-vision-1212')).toBe('grok-2-vision-1212');
|
|
expect(matchModelName('xai/grok-2-vision')).toBe('grok-2-vision');
|
|
expect(matchModelName('xai/grok-2-vision-latest')).toBe('grok-2-vision-latest');
|
|
// Beta models
|
|
expect(matchModelName('xai/grok-vision-beta')).toBe('grok-vision-beta');
|
|
expect(matchModelName('xai/grok-beta')).toBe('grok-beta');
|
|
// Text models
|
|
expect(matchModelName('xai/grok-2-1212')).toBe('grok-2-1212');
|
|
expect(matchModelName('xai/grok-2')).toBe('grok-2');
|
|
expect(matchModelName('xai/grok-2-latest')).toBe('grok-2-latest');
|
|
// Grok 3 models
|
|
expect(matchModelName('xai/grok-3')).toBe('grok-3');
|
|
expect(matchModelName('xai/grok-3-fast')).toBe('grok-3-fast');
|
|
expect(matchModelName('xai/grok-3-mini')).toBe('grok-3-mini');
|
|
expect(matchModelName('xai/grok-3-mini-fast')).toBe('grok-3-mini-fast');
|
|
// Grok 4 model
|
|
expect(matchModelName('xai/grok-4-0709')).toBe('grok-4');
|
|
// Grok 4 Fast and 4.1 Fast models
|
|
expect(matchModelName('xai/grok-4-fast')).toBe('grok-4-fast');
|
|
expect(matchModelName('xai/grok-4-1-fast-reasoning')).toBe('grok-4-1-fast');
|
|
expect(matchModelName('xai/grok-4-1-fast-non-reasoning')).toBe('grok-4-1-fast');
|
|
// Grok Code Fast model
|
|
expect(matchModelName('xai/grok-code-fast-1')).toBe('grok-code-fast');
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('Claude Model Tests', () => {
|
|
it('should return correct context length for Claude 4 models', () => {
|
|
expect(getModelMaxTokens('claude-sonnet-4')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-4'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-4')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4'],
|
|
);
|
|
});
|
|
|
|
it('should return 200K for Claude Sonnet 4.5', () => {
|
|
expect(getModelMaxTokens('claude-sonnet-4-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-sonnet-4-5-20250929')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-5'],
|
|
);
|
|
});
|
|
|
|
it('should return correct context length for Claude Haiku 4.5', () => {
|
|
expect(getModelMaxTokens('claude-haiku-4-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-haiku-4-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
|
|
);
|
|
});
|
|
|
|
it('should return correct context length for Claude Opus 4.5', () => {
|
|
expect(getModelMaxTokens('claude-opus-4-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-4-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-5'],
|
|
);
|
|
});
|
|
|
|
it('should handle Claude Haiku 4.5 model name variations', () => {
|
|
const modelVariations = [
|
|
'claude-haiku-4-5',
|
|
'claude-haiku-4-5-20250420',
|
|
'claude-haiku-4-5-latest',
|
|
'anthropic/claude-haiku-4-5',
|
|
'claude-haiku-4-5/anthropic',
|
|
'claude-haiku-4-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(modelKey).toBe('claude-haiku-4-5');
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-haiku-4-5'],
|
|
);
|
|
});
|
|
});
|
|
|
|
it('should handle Claude Opus 4.5 model name variations', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-5',
|
|
'claude-opus-4-5-20250420',
|
|
'claude-opus-4-5-latest',
|
|
'anthropic/claude-opus-4-5',
|
|
'claude-opus-4-5/anthropic',
|
|
'claude-opus-4-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(modelKey).toBe('claude-opus-4-5');
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-5'],
|
|
);
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude Haiku 4.5', () => {
|
|
const modelVariations = [
|
|
'claude-haiku-4-5',
|
|
'claude-haiku-4-5-20250420',
|
|
'claude-haiku-4-5-latest',
|
|
'anthropic/claude-haiku-4-5',
|
|
'claude-haiku-4-5/anthropic',
|
|
'claude-haiku-4-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-haiku-4-5');
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude Opus 4.5', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-5',
|
|
'claude-opus-4-5-20250420',
|
|
'claude-opus-4-5-latest',
|
|
'anthropic/claude-opus-4-5',
|
|
'claude-opus-4-5/anthropic',
|
|
'claude-opus-4-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-opus-4-5');
|
|
});
|
|
});
|
|
|
|
it('should handle Claude 4 model name variations with different prefixes and suffixes', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-4',
|
|
'claude-sonnet-4-20240229',
|
|
'claude-sonnet-4-latest',
|
|
'anthropic/claude-sonnet-4',
|
|
'claude-sonnet-4/anthropic',
|
|
'claude-sonnet-4-preview',
|
|
'claude-sonnet-4-20240229-preview',
|
|
'claude-opus-4',
|
|
'claude-opus-4-20240229',
|
|
'claude-opus-4-latest',
|
|
'anthropic/claude-opus-4',
|
|
'claude-opus-4/anthropic',
|
|
'claude-opus-4-preview',
|
|
'claude-opus-4-20240229-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(getModelMaxTokens(model)).toBe(maxTokensMap[EModelEndpoint.anthropic][modelKey]);
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude 4 models', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-4',
|
|
'claude-sonnet-4-20240229',
|
|
'claude-sonnet-4-latest',
|
|
'anthropic/claude-sonnet-4',
|
|
'claude-sonnet-4/anthropic',
|
|
'claude-sonnet-4-preview',
|
|
'claude-sonnet-4-20240229-preview',
|
|
'claude-opus-4',
|
|
'claude-opus-4-20240229',
|
|
'claude-opus-4-latest',
|
|
'anthropic/claude-opus-4',
|
|
'claude-opus-4/anthropic',
|
|
'claude-opus-4-preview',
|
|
'claude-opus-4-20240229-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const isSonnet = model.includes('sonnet');
|
|
const expectedModel = isSonnet ? 'claude-sonnet-4' : 'claude-opus-4';
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe(expectedModel);
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Opus 4.6 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-opus-4-6', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-6'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-4-6')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-6'],
|
|
);
|
|
});
|
|
|
|
it('should handle Claude Opus 4.6 model name variations', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-6',
|
|
'claude-opus-4-6-20250801',
|
|
'claude-opus-4-6-latest',
|
|
'anthropic/claude-opus-4-6',
|
|
'claude-opus-4-6/anthropic',
|
|
'claude-opus-4-6-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(modelKey).toBe('claude-opus-4-6');
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-6'],
|
|
);
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude Opus 4.6', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-6',
|
|
'claude-opus-4-6-20250801',
|
|
'claude-opus-4-6-latest',
|
|
'anthropic/claude-opus-4-6',
|
|
'claude-opus-4-6/anthropic',
|
|
'claude-opus-4-6-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-opus-4-6');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Opus 4.7 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-opus-4-7', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-7'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-4-7')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-7'],
|
|
);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Opus 4.7', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-7',
|
|
'claude-opus-4-7-20260401',
|
|
'claude-opus-4-7-latest',
|
|
'anthropic/claude-opus-4-7',
|
|
'claude-opus-4-7/anthropic',
|
|
'claude-opus-4-7-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-opus-4-7');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Opus 4.8 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-opus-4-8', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-8'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-4-8')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-4-8'],
|
|
);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Opus 4.8', () => {
|
|
const modelVariations = [
|
|
'claude-opus-4-8',
|
|
'claude-opus-4-8-20260528',
|
|
'claude-opus-4-8-latest',
|
|
'anthropic/claude-opus-4-8',
|
|
'claude-opus-4-8/anthropic',
|
|
'claude-opus-4-8-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-opus-4-8');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Opus 5 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-opus-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-opus-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-opus-5'],
|
|
);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Opus 5', () => {
|
|
const modelVariations = [
|
|
'claude-opus-5',
|
|
'claude-opus-5-20260701',
|
|
'claude-opus-5-latest',
|
|
'anthropic/claude-opus-5',
|
|
'claude-opus-5/anthropic',
|
|
'claude-opus-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-opus-5');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Fable 5 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-fable-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-fable-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-fable-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-fable-5'],
|
|
);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Fable 5', () => {
|
|
const modelVariations = [
|
|
'claude-fable-5',
|
|
'claude-fable-5-20260609',
|
|
'claude-fable-5-latest',
|
|
'anthropic/claude-fable-5',
|
|
'claude-fable-5/anthropic',
|
|
'anthropic.claude-fable-5',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-fable-5');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Mythos 5 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-mythos-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-mythos-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-mythos-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-mythos-5'],
|
|
);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Mythos 5', () => {
|
|
const modelVariations = [
|
|
'claude-mythos-5',
|
|
'claude-mythos-5-20260609',
|
|
'claude-mythos-5-latest',
|
|
'anthropic/claude-mythos-5',
|
|
'claude-mythos-5/anthropic',
|
|
'anthropic.claude-mythos-5',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-mythos-5');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Fable 5.1 (1M)', () => {
|
|
expect(maxTokensMap[EModelEndpoint.anthropic]['claude-fable-5-1']).toBe(1000000);
|
|
expect(maxTokensMap[EModelEndpoint.anthropic]['claude-mythos-5-1']).toBe(1000000);
|
|
expect(getModelMaxTokens('claude-fable-5-1', EModelEndpoint.anthropic)).toBe(1000000);
|
|
expect(getModelMaxTokens('claude-mythos-5-1', EModelEndpoint.anthropic)).toBe(1000000);
|
|
});
|
|
|
|
it('should match model names correctly for Claude Fable 5.1 without collapsing to Fable 5', () => {
|
|
const modelVariations = [
|
|
'claude-fable-5-1',
|
|
'claude-fable-5-1-20260901',
|
|
'claude-fable-5-1-latest',
|
|
'anthropic/claude-fable-5-1',
|
|
'claude-fable-5-1/anthropic',
|
|
'anthropic.claude-fable-5-1',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-fable-5-1');
|
|
});
|
|
|
|
expect(matchModelName('claude-fable-5-20260609', EModelEndpoint.anthropic)).toBe(
|
|
'claude-fable-5',
|
|
);
|
|
});
|
|
|
|
it('should return correct context length for Claude Sonnet 4.6 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-sonnet-4-6', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-6'],
|
|
);
|
|
expect(getModelMaxTokens('claude-sonnet-4.6', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('claude-sonnet-4-6')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-6'],
|
|
);
|
|
expect(getModelMaxTokens('claude-sonnet-4-6')).toBeGreaterThan(
|
|
getModelMaxTokens('claude-sonnet-4-5'),
|
|
);
|
|
});
|
|
|
|
it('should return correct context length for Claude Sonnet 4.7+ aliases (1M)', () => {
|
|
[
|
|
'claude-sonnet-4-7',
|
|
'claude-sonnet-4.7',
|
|
'claude-sonnet-4-8',
|
|
'claude-sonnet-4.8',
|
|
'claude-sonnet-4-9',
|
|
'claude-sonnet-4.9',
|
|
'claude-sonnet-4-10',
|
|
'claude-sonnet-4.10',
|
|
'claude-4-10-sonnet',
|
|
'claude-4.10-sonnet',
|
|
'anthropic.claude-4-10-sonnet',
|
|
].forEach((model) => {
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(1000000);
|
|
});
|
|
expect(getModelMaxTokens('anthropic.claude-4-10-sonnet', EModelEndpoint.bedrock)).toBe(1000000);
|
|
});
|
|
|
|
it('should keep double-digit Claude Sonnet 4 minor names when matching models', () => {
|
|
expect(matchModelName('claude-sonnet-4-10', EModelEndpoint.anthropic)).toBe(
|
|
'claude-sonnet-4-10',
|
|
);
|
|
expect(matchModelName('claude-sonnet-4.10-latest', EModelEndpoint.anthropic)).toBe(
|
|
'claude-sonnet-4.10-latest',
|
|
);
|
|
expect(matchModelName('claude-4-10-sonnet', EModelEndpoint.bedrock)).toBe('claude-4-10-sonnet');
|
|
expect(matchModelName('anthropic.claude-4.10-sonnet', EModelEndpoint.bedrock)).toBe(
|
|
'anthropic.claude-4.10-sonnet',
|
|
);
|
|
});
|
|
|
|
it('should handle Claude Sonnet 4.6 model name variations', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-4-6',
|
|
'claude-sonnet-4-6-20260101',
|
|
'claude-sonnet-4-6-latest',
|
|
'anthropic/claude-sonnet-4-6',
|
|
'claude-sonnet-4-6/anthropic',
|
|
'claude-sonnet-4-6-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(modelKey).toBe('claude-sonnet-4-6');
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-6'],
|
|
);
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude Sonnet 4.6', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-4-6',
|
|
'claude-sonnet-4-6-20260101',
|
|
'claude-sonnet-4-6-latest',
|
|
'anthropic/claude-sonnet-4-6',
|
|
'claude-sonnet-4-6/anthropic',
|
|
'claude-sonnet-4-6-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-sonnet-4-6');
|
|
});
|
|
});
|
|
|
|
it('should return correct context length for Claude Sonnet 5 (1M)', () => {
|
|
expect(getModelMaxTokens('claude-sonnet-5', EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-5'],
|
|
);
|
|
expect(getModelMaxTokens('claude-sonnet-5')).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-5'],
|
|
);
|
|
});
|
|
|
|
it('should not match Claude Sonnet 5 against Claude Sonnet 4 keys', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-5',
|
|
'claude-sonnet-5-20260101',
|
|
'claude-sonnet-5-latest',
|
|
'anthropic/claude-sonnet-5',
|
|
'claude-sonnet-5/anthropic',
|
|
'anthropic.claude-sonnet-5',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
const modelKey = findMatchingPattern(model, maxTokensMap[EModelEndpoint.anthropic]);
|
|
expect(modelKey).toBe('claude-sonnet-5');
|
|
expect(getModelMaxTokens(model, EModelEndpoint.anthropic)).toBe(
|
|
maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-5'],
|
|
);
|
|
});
|
|
});
|
|
|
|
it('should match model names correctly for Claude Sonnet 5', () => {
|
|
const modelVariations = [
|
|
'claude-sonnet-5',
|
|
'claude-sonnet-5-20260101',
|
|
'claude-sonnet-5-latest',
|
|
'anthropic/claude-sonnet-5',
|
|
'claude-sonnet-5/anthropic',
|
|
'claude-sonnet-5-preview',
|
|
];
|
|
|
|
modelVariations.forEach((model) => {
|
|
expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-sonnet-5');
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('Moonshot/Kimi Model Tests', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for kimi-k2.5 (multi-modal)', () => {
|
|
expect(getModelMaxTokens('kimi-k2.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['kimi-k2.5']);
|
|
expect(getModelMaxTokens('kimi-k2.5-latest')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2.5'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for kimi-k2 series models', () => {
|
|
expect(getModelMaxTokens('kimi')).toBe(maxTokensMap[EModelEndpoint.openAI]['kimi']);
|
|
expect(getModelMaxTokens('kimi-k2')).toBe(maxTokensMap[EModelEndpoint.openAI]['kimi-k2']);
|
|
expect(getModelMaxTokens('kimi-k2-turbo')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-turbo'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-turbo-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-turbo-preview'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-0905')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-0905'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-0905-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-0905-preview'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-thinking')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-thinking'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-thinking-turbo')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-thinking-turbo'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for kimi-k2-0711 (smaller context)', () => {
|
|
expect(getModelMaxTokens('kimi-k2-0711')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-0711'],
|
|
);
|
|
expect(getModelMaxTokens('kimi-k2-0711-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-0711-preview'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for kimi-latest', () => {
|
|
expect(getModelMaxTokens('kimi-latest')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-latest'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for moonshot-v1 series models', () => {
|
|
expect(getModelMaxTokens('moonshot')).toBe(maxTokensMap[EModelEndpoint.openAI]['moonshot']);
|
|
expect(getModelMaxTokens('moonshot-v1')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-auto')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-auto'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-8k')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-8k'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-8k-vision')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-8k-vision'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-8k-vision-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-8k-vision-preview'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-32k')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-32k'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-32k-vision')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-32k-vision'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-32k-vision-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-32k-vision-preview'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-128k')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-128k'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-128k-vision')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-128k-vision'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot-v1-128k-vision-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-128k-vision-preview'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for Bedrock moonshot models', () => {
|
|
expect(getModelMaxTokens('moonshot.kimi', EModelEndpoint.bedrock)).toBe(
|
|
maxTokensMap[EModelEndpoint.bedrock]['moonshot.kimi'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot.kimi-k2', EModelEndpoint.bedrock)).toBe(
|
|
maxTokensMap[EModelEndpoint.bedrock]['moonshot.kimi-k2'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot.kimi-k2.5', EModelEndpoint.bedrock)).toBe(
|
|
maxTokensMap[EModelEndpoint.bedrock]['moonshot.kimi-k2.5'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot.kimi-k2-thinking', EModelEndpoint.bedrock)).toBe(
|
|
maxTokensMap[EModelEndpoint.bedrock]['moonshot.kimi-k2-thinking'],
|
|
);
|
|
expect(getModelMaxTokens('moonshot.kimi-k2-0711', EModelEndpoint.bedrock)).toBe(
|
|
maxTokensMap[EModelEndpoint.bedrock]['moonshot.kimi-k2-0711'],
|
|
);
|
|
});
|
|
|
|
test('should handle Moonshot/Kimi models with provider prefixes', () => {
|
|
expect(getModelMaxTokens('openrouter/kimi-k2')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2'],
|
|
);
|
|
expect(getModelMaxTokens('openrouter/kimi-k2.5')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2.5'],
|
|
);
|
|
expect(getModelMaxTokens('openrouter/kimi-k2-turbo')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['kimi-k2-turbo'],
|
|
);
|
|
expect(getModelMaxTokens('openrouter/moonshot-v1-128k')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['moonshot-v1-128k'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match exact Kimi model names', () => {
|
|
expect(matchModelName('kimi')).toBe('kimi');
|
|
expect(matchModelName('kimi-k2')).toBe('kimi-k2');
|
|
expect(matchModelName('kimi-k2.5')).toBe('kimi-k2.5');
|
|
expect(matchModelName('kimi-k2-turbo')).toBe('kimi-k2-turbo');
|
|
expect(matchModelName('kimi-k2-0711')).toBe('kimi-k2-0711');
|
|
});
|
|
|
|
test('should match moonshot model names', () => {
|
|
expect(matchModelName('moonshot')).toBe('moonshot');
|
|
expect(matchModelName('moonshot-v1-8k')).toBe('moonshot-v1-8k');
|
|
expect(matchModelName('moonshot-v1-32k')).toBe('moonshot-v1-32k');
|
|
expect(matchModelName('moonshot-v1-128k')).toBe('moonshot-v1-128k');
|
|
});
|
|
|
|
test('should match Kimi model variations with provider prefix', () => {
|
|
expect(matchModelName('openrouter/kimi')).toBe('kimi');
|
|
expect(matchModelName('openrouter/kimi-k2')).toBe('kimi-k2');
|
|
expect(matchModelName('openrouter/kimi-k2.5')).toBe('kimi-k2.5');
|
|
});
|
|
|
|
test('should match Kimi model variations with suffixes', () => {
|
|
expect(matchModelName('kimi-k2-latest')).toBe('kimi-k2');
|
|
expect(matchModelName('kimi-k2.5-preview')).toBe('kimi-k2.5');
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('Qwen3 Model Tests', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for Qwen3 base pattern', () => {
|
|
expect(getModelMaxTokens('qwen3')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
|
|
});
|
|
|
|
test('should return correct tokens for qwen3-4b (falls back to qwen3)', () => {
|
|
expect(getModelMaxTokens('qwen3-4b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
|
|
});
|
|
|
|
test('should return correct tokens for Qwen3 base models', () => {
|
|
expect(getModelMaxTokens('qwen3-8b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-8b']);
|
|
expect(getModelMaxTokens('qwen3-14b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-14b']);
|
|
expect(getModelMaxTokens('qwen3-32b')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-32b']);
|
|
expect(getModelMaxTokens('qwen3-235b-a22b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-235b-a22b'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for Qwen3 VL (Vision-Language) models', () => {
|
|
expect(getModelMaxTokens('qwen3-vl-8b-thinking')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-thinking'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-vl-8b-instruct')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-instruct'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-vl-30b-a3b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-30b-a3b'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-vl-235b-a22b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-235b-a22b'],
|
|
);
|
|
});
|
|
|
|
test('should return correct tokens for Qwen3 specialized models', () => {
|
|
expect(getModelMaxTokens('qwen3-max')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3-max']);
|
|
expect(getModelMaxTokens('qwen3-coder')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-coder-30b-a3b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-30b-a3b'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-coder-plus')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-plus'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-coder-flash')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder-flash'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-next-80b-a3b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-next-80b-a3b'],
|
|
);
|
|
});
|
|
|
|
test('should handle Qwen3 models with provider prefixes', () => {
|
|
expect(getModelMaxTokens('alibaba/qwen3')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
|
|
expect(getModelMaxTokens('alibaba/qwen3-4b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3'],
|
|
);
|
|
expect(getModelMaxTokens('qwen/qwen3-8b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-8b'],
|
|
);
|
|
expect(getModelMaxTokens('openrouter/qwen3-max')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-max'],
|
|
);
|
|
expect(getModelMaxTokens('alibaba/qwen3-vl-8b-instruct')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-vl-8b-instruct'],
|
|
);
|
|
expect(getModelMaxTokens('qwen/qwen3-coder')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-coder'],
|
|
);
|
|
});
|
|
|
|
test('should handle Qwen3 models with suffixes', () => {
|
|
expect(getModelMaxTokens('qwen3-preview')).toBe(maxTokensMap[EModelEndpoint.openAI]['qwen3']);
|
|
expect(getModelMaxTokens('qwen3-4b-preview')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-8b-latest')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-8b'],
|
|
);
|
|
expect(getModelMaxTokens('qwen3-max-2024')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['qwen3-max'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match exact Qwen3 model names', () => {
|
|
expect(matchModelName('qwen3')).toBe('qwen3');
|
|
expect(matchModelName('qwen3-4b')).toBe('qwen3');
|
|
expect(matchModelName('qwen3-8b')).toBe('qwen3-8b');
|
|
expect(matchModelName('qwen3-vl-8b-thinking')).toBe('qwen3-vl-8b-thinking');
|
|
expect(matchModelName('qwen3-max')).toBe('qwen3-max');
|
|
expect(matchModelName('qwen3-coder')).toBe('qwen3-coder');
|
|
});
|
|
|
|
test('should match Qwen3 model variations with provider prefixes', () => {
|
|
expect(matchModelName('alibaba/qwen3')).toBe('qwen3');
|
|
expect(matchModelName('alibaba/qwen3-4b')).toBe('qwen3');
|
|
expect(matchModelName('qwen/qwen3-8b')).toBe('qwen3-8b');
|
|
expect(matchModelName('openrouter/qwen3-max')).toBe('qwen3-max');
|
|
expect(matchModelName('alibaba/qwen3-vl-8b-instruct')).toBe('qwen3-vl-8b-instruct');
|
|
expect(matchModelName('qwen/qwen3-coder')).toBe('qwen3-coder');
|
|
});
|
|
|
|
test('should match Qwen3 model variations with suffixes', () => {
|
|
expect(matchModelName('qwen3-preview')).toBe('qwen3');
|
|
expect(matchModelName('qwen3-4b-preview')).toBe('qwen3');
|
|
expect(matchModelName('qwen3-8b-latest')).toBe('qwen3-8b');
|
|
expect(matchModelName('qwen3-max-2024')).toBe('qwen3-max');
|
|
expect(matchModelName('qwen3-coder-v1')).toBe('qwen3-coder');
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('GLM Model Tests (Zhipu AI)', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for GLM models', () => {
|
|
expect(getModelMaxTokens('glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('glm-4.5v')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5v']);
|
|
expect(getModelMaxTokens('glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
|
|
expect(getModelMaxTokens('glm-4-32b')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4-32b']);
|
|
expect(getModelMaxTokens('glm-4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4']);
|
|
expect(getModelMaxTokens('glm4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm4']);
|
|
});
|
|
|
|
test('should handle partial matches for GLM models with provider prefixes', () => {
|
|
expect(getModelMaxTokens('z-ai/glm-4.6')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4.5v')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
expect(getModelMaxTokens('z-ai/glm-4-32b')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
|
|
);
|
|
|
|
expect(getModelMaxTokens('zai/glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('zai/glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
|
|
expect(getModelMaxTokens('zai/glm-4.5-air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('zai/glm-4.5v')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
|
|
expect(getModelMaxTokens('zai-org/GLM-4.6')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5-Air')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5V')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4-32B-0414')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
|
|
);
|
|
});
|
|
|
|
test('should handle GLM model variations with suffixes', () => {
|
|
expect(getModelMaxTokens('glm-4.6-fp8')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.6-FP8')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
|
|
);
|
|
expect(getModelMaxTokens('zai-org/GLM-4.5-Air-FP8')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
});
|
|
|
|
test('should prioritize more specific GLM patterns', () => {
|
|
expect(getModelMaxTokens('glm-4.5-air-custom')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
|
|
);
|
|
expect(getModelMaxTokens('glm-4.5-custom')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5'],
|
|
);
|
|
expect(getModelMaxTokens('glm-4.5v-custom')).toBe(
|
|
maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match exact GLM model names', () => {
|
|
expect(matchModelName('glm-4.6')).toBe('glm-4.6');
|
|
expect(matchModelName('glm-4.5v')).toBe('glm-4.5v');
|
|
expect(matchModelName('glm-4.5-air')).toBe('glm-4.5-air');
|
|
expect(matchModelName('glm-4.5')).toBe('glm-4.5');
|
|
expect(matchModelName('glm-4-32b')).toBe('glm-4-32b');
|
|
expect(matchModelName('glm-4')).toBe('glm-4');
|
|
expect(matchModelName('glm4')).toBe('glm4');
|
|
});
|
|
|
|
test('should match GLM model variations with provider prefixes', () => {
|
|
expect(matchModelName('z-ai/glm-4.6')).toBe('glm-4.6');
|
|
expect(matchModelName('z-ai/glm-4.5')).toBe('glm-4.5');
|
|
expect(matchModelName('z-ai/glm-4.5-air')).toBe('glm-4.5-air');
|
|
expect(matchModelName('z-ai/glm-4.5v')).toBe('glm-4.5v');
|
|
expect(matchModelName('z-ai/glm-4-32b')).toBe('glm-4-32b');
|
|
|
|
expect(matchModelName('zai/glm-4.6')).toBe('glm-4.6');
|
|
expect(matchModelName('zai/glm-4.5')).toBe('glm-4.5');
|
|
expect(matchModelName('zai/glm-4.5-air')).toBe('glm-4.5-air');
|
|
expect(matchModelName('zai/glm-4.5v')).toBe('glm-4.5v');
|
|
|
|
expect(matchModelName('zai-org/GLM-4.6')).toBe('glm-4.6');
|
|
expect(matchModelName('zai-org/GLM-4.5')).toBe('glm-4.5');
|
|
expect(matchModelName('zai-org/GLM-4.5-Air')).toBe('glm-4.5-air');
|
|
expect(matchModelName('zai-org/GLM-4.5V')).toBe('glm-4.5v');
|
|
expect(matchModelName('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
|
|
});
|
|
|
|
test('should match GLM model variations with suffixes', () => {
|
|
expect(matchModelName('glm-4.6-fp8')).toBe('glm-4.6');
|
|
expect(matchModelName('zai-org/GLM-4.6-FP8')).toBe('glm-4.6');
|
|
expect(matchModelName('zai-org/GLM-4.5-Air-FP8')).toBe('glm-4.5-air');
|
|
});
|
|
|
|
test('should handle case-insensitive matching for GLM models', () => {
|
|
expect(matchModelName('zai-org/GLM-4.6')).toBe('glm-4.6');
|
|
expect(matchModelName('zai-org/GLM-4.5V')).toBe('glm-4.5v');
|
|
expect(matchModelName('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('Mistral Model Tests', () => {
|
|
describe('getModelMaxTokens', () => {
|
|
test('should return correct tokens for mistral-large-3 (256k context)', () => {
|
|
expect(getModelMaxTokens('mistral-large-3', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['mistral-large-3'],
|
|
);
|
|
});
|
|
|
|
test('should match mistral-large-3 for suffixed variants', () => {
|
|
expect(getModelMaxTokens('mistral-large-3-instruct', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['mistral-large-3'],
|
|
);
|
|
});
|
|
|
|
test('should not match mistral-large-3 for generic mistral-large', () => {
|
|
expect(getModelMaxTokens('mistral-large', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['mistral-large'],
|
|
);
|
|
expect(getModelMaxTokens('mistral-large-latest', EModelEndpoint.custom)).toBe(
|
|
maxTokensMap[EModelEndpoint.custom]['mistral-large'],
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('matchModelName', () => {
|
|
test('should match mistral-large-3 exactly', () => {
|
|
expect(matchModelName('mistral-large-3', EModelEndpoint.custom)).toBe('mistral-large-3');
|
|
});
|
|
|
|
test('should match mistral-large-3 for prefixed/suffixed variants', () => {
|
|
expect(matchModelName('mistral/mistral-large-3', EModelEndpoint.custom)).toBe(
|
|
'mistral-large-3',
|
|
);
|
|
expect(matchModelName('mistral-large-3-instruct', EModelEndpoint.custom)).toBe(
|
|
'mistral-large-3',
|
|
);
|
|
});
|
|
|
|
test('should match generic mistral-large for non-3 variants', () => {
|
|
expect(matchModelName('mistral-large-latest', EModelEndpoint.custom)).toBe('mistral-large');
|
|
});
|
|
});
|
|
|
|
describe('findMatchingPattern', () => {
|
|
test('should prefer mistral-large-3 over mistral-large for mistral-large-3 variants', () => {
|
|
const result = findMatchingPattern(
|
|
'mistral-large-3-instruct',
|
|
maxTokensMap[EModelEndpoint.custom],
|
|
);
|
|
expect(result).toBe('mistral-large-3');
|
|
});
|
|
});
|
|
});
|