mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-05-27 07:51:43 +00:00
Add summarization config and package-level summarize handler contracts
Register summarize handlers across server controller paths
Port cursor dual-read/dual-write summary support and UI status handling
Selectively merge cursor branch files for BaseClient summary content
block detection (last-summary-wins), dual-write persistence, summary
block unit tests, and on_summarize_status SSE event handling with
started/completed/failed branches.
Co-authored-by: Cursor <cursoragent@cursor.com>
refactor: type safety
feat: add localization for summarization status messages
refactor: optimize summary block detection in BaseClient
Updated the logic for identifying existing summary content blocks to use a reverse loop for improved efficiency. Added a new test case to ensure the last summary content block is updated correctly when multiple summary blocks exist.
chore: add runName to chainOptions in AgentClient
refactor: streamline summarization configuration and handler integration
Removed the deprecated summarizeNotConfigured function and replaced it with a more flexible createSummarizeFn. Updated the summarization handler setup across various controllers to utilize the new function, enhancing error handling and configuration resolution. Improved overall code clarity and maintainability by consolidating summarization logic.
feat(summarization): add staged chunk-and-merge fallback
feat(usage): track summarization usage separately from messages
feat(summarization): resolve prompt from config in runtime
fix(endpoints): use @librechat/api provider config loader
refactor(agents): import getProviderConfig from @librechat/api
chore: code order
feat(app-config): auto-enable summarization when configured
feat: summarization config
refactor(summarization): streamline persist summary handling and enhance configuration validation
Removed the deprecated createDeferredPersistSummary function and integrated a new createPersistSummary function for MongoDB persistence. Updated summarization handlers across various controllers to utilize the new persistence method. Enhanced validation for summarization configuration to ensure provider, model, and prompt are properly set, improving error handling and overall robustness.
refactor(summarization): update event handling and remove legacy summarize handlers
Replaced the deprecated summarization handlers with new event-driven handlers for summarization start and completion across multiple controllers. This change enhances the clarity of the summarization process and improves the integration of summarization events in the application. Additionally, removed unused summarization functions and streamlined the configuration loading process.
refactor(summarization): standardize event names in handlers
Updated event names in the summarization handlers to use constants from GraphEvents for consistency and clarity. This change improves maintainability and reduces the risk of errors related to string literals in event handling.
feat(summarization): enhance usage tracking for summarization events
Added logic to track summarization usage in multiple controllers by checking the current node type. If the node indicates a summarization task, the usage type is set accordingly. This change improves the granularity of usage data collected during summarization processes.
feat(summarization): integrate SummarizationConfig into AppSummarizationConfig type
Enhanced the AppSummarizationConfig type by extending it with the SummarizationConfig type from librechat-data-provider. This change improves type safety and consistency in the summarization configuration structure.
test: add end-to-end tests for summarization functionality
Introduced a comprehensive suite of end-to-end tests for the summarization feature, covering the full LibreChat pipeline from message creation to summarization. This includes a new setup file for environment configuration and a Jest configuration specifically for E2E tests. The tests utilize real API keys and ensure proper integration with the summarization process, enhancing overall test coverage and reliability.
refactor(summarization): include initial summary in formatAgentMessages output
Updated the formatAgentMessages function to return an initial summary alongside messages and index token count map. This change is reflected in multiple controllers and the corresponding tests, enhancing the summarization process by providing additional context for each agent's response.
refactor: move hydrateMissingIndexTokenCounts to tokenMap utility
Extracted the hydrateMissingIndexTokenCounts function from the AgentClient and related tests into a new tokenMap utility file. This change improves code organization and reusability, allowing for better management of token counting logic across the application.
refactor(summarization): standardize step event handling and improve summary rendering
Refactored the step event handling in the useStepHandler and related components to utilize constants for event names, enhancing consistency and maintainability. Additionally, improved the rendering logic in the Summary component to conditionally display the summary text based on its availability, providing a better user experience during the summarization process.
feat(summarization): introduce baseContextTokens and reserveTokensRatio for improved context management
Added baseContextTokens to the InitializedAgent type to calculate the context budget based on agentMaxContextNum and maxOutputTokensNum. Implemented reserveTokensRatio in the createRun function to allow configurable context token management. Updated related tests to validate these changes and ensure proper functionality.
feat(summarization): add minReserveTokens, context pruning, and overflow recovery configurations
Introduced new configuration options for summarization, including minReserveTokens, context pruning settings, and overflow recovery parameters. Updated the createRun function to accommodate these new options and added a comprehensive test suite to validate their functionality and integration within the summarization process.
feat(summarization): add updatePrompt and reserveTokensRatio to summarization configuration
Introduced an updatePrompt field for updating existing summaries with new messages, enhancing the flexibility of the summarization process. Additionally, added reserveTokensRatio to the configuration schema, allowing for improved management of token allocation during summarization. Updated related tests to validate these new features.
feat(logging): add on_agent_log event handler for structured logging
Implemented an on_agent_log event handler in both the agents' callbacks and responses to facilitate structured logging of agent activities. This enhancement allows for better tracking and debugging of agent interactions by logging messages with associated metadata. Updated the summarization process to ensure proper handling of log events.
fix: remove duplicate IBalanceUpdate interface declaration
perf(usage): single-pass partition of collectedUsage
Replace two Array.filter() passes with a single for-of loop that
partitions message vs. summarization usages in one iteration.
fix(BaseClient): shallow-copy message content before mutating and preserve string content
Avoid mutating the original message.content array in-place when
appending a summary block. Also convert string content to a text
content part instead of silently discarding it.
fix(ui): fix Part.tsx indentation and useStepHandler summarize-complete handling
- Fix SUMMARY else-if branch indentation in Part.tsx to match chain level
- Guard ON_SUMMARIZE_COMPLETE with didFinalize flag to avoid unnecessary
re-renders when no summarizing parts exist
- Protect against undefined completeData.summary instead of unsafe spread
fix(agents): use strict enabled check for summarization handlers
Change summarizationConfig?.enabled !== false to === true so handlers
are not registered when summarizationConfig is undefined.
chore: fix initializeClient JSDoc and move DEFAULT_RESERVE_RATIO to module scope
refactor(Summary): align collapse/expand behavior with Reasoning component
- Single render path instead of separate streaming vs completed branches
- Use useMessageContext for isSubmitting/isLatestMessage awareness so
the "Summarizing..." label only shows during active streaming
- Default to collapsed (matching Reasoning), user toggles to expand
- Add proper aria attributes (aria-hidden, role, aria-controls, contentId)
- Hide copy button while actively streaming
feat(summarization): default to self-summarize using agent's own provider/model
When no summarization config is provided (neither in librechat.yaml nor
on the agent), automatically enable summarization using the agent's own
provider and model. The agents package already provides default prompts,
so no prompt configuration is needed.
Also removes the dead resolveSummarizationLLMConfig in summarize.ts
(and its spec) — run.ts buildAgentContext is the single source of truth
for summarization config resolution. Removes the duplicate
RuntimeSummarizationConfig local type in favor of the canonical
SummarizationConfig from data-provider.
chore: schema and type cleanup for summarization
- Add trigger field to summarizationAgentOverrideSchema so per-agent
trigger overrides in librechat.yaml are not silently stripped by Zod
- Remove unused SummarizationStatus type from runs.ts
- Make AppSummarizationConfig.enabled non-optional to reflect the
invariant that loadSummarizationConfig always sets it
refactor(responses): extract duplicated on_agent_log handler
refactor(run): use agents package types for summarization config
Import SummarizationConfig, ContextPruningConfig, and
OverflowRecoveryConfig from @librechat/agents and use them to
type-check the translation layer in buildAgentContext. This ensures
the config object passed to the agent graph matches what it expects.
- Use `satisfies AgentSummarizationConfig` on the config object
- Cast contextPruningConfig and overflowRecoveryConfig to agents types
- Properly narrow trigger fields from DeepPartial to required shape
feat(config): add maxToolResultChars to base endpoint schema
Add maxToolResultChars to baseEndpointSchema so it can be configured
on any endpoint in librechat.yaml. Resolved during agent initialization
using getProviderConfig's endpoint resolution: custom endpoint config
takes precedence, then the provider-specific endpoint config, then the
shared `all` config.
Passed through to the agents package ToolNode, which uses it to cap
tool result length before it enters the context window. When not
configured, the agents package computes a sensible default from
maxContextTokens.
fix(summarization): forward agent model_parameters in self-summarize default
When no explicit summarization config exists, the self-summarize
default now forwards the agent's model_parameters as the
summarization parameters. This ensures provider-specific settings
(e.g. Bedrock region, credentials, endpoint host) are available
when the agents package constructs the summarization LLM.
fix(agents): register summarization handlers by default
Change the enabled gate from === true to !== false so handlers
register when no explicit summarization config exists. This aligns
with the self-summarize default where summarization is always on
unless explicitly disabled via enabled: false.
refactor(summarization): let agents package inherit clientOptions for self-summarize
Remove model_parameters forwarding from the self-summarize default.
The agents package now reuses the agent's own clientOptions when the
summarization provider matches the agent's provider, inheriting all
provider-specific settings (region, credentials, proxy, etc.)
automatically.
refactor(summarization): use MessageContentComplex[] for summary content
Unify summary content to always use MessageContentComplex[] arrays,
matching the pattern used by on_message_delta. No more string | array
unions — content is always an array of typed blocks ({ type: 'text',
text: '...' } for text, { type: 'reasoning_content', ... } for
reasoning).
Agents package:
- SummaryContentBlock.content: MessageContentComplex[] (was string)
- tokenCount now optional (not sent on deltas)
- Removed reasoning field — reasoning is now a content block type
- streamAndCollect normalizes all chunks to content block arrays
- Delta events pass content blocks directly
LibreChat:
- SummaryContentPart.content: Agents.MessageContentComplex[]
- Updated Part.tsx, Summary.tsx, useStepHandler.ts, BaseClient.js
- Summary.tsx derives display text from content blocks via useMemo
- Aggregator uses simple array spread
refactor(summarization): enhance summary handling and text extraction
- Updated BaseClient.js to improve summary text extraction, accommodating both legacy and new content formats.
- Modified summarization logic to ensure consistent handling of summary content across different message formats.
- Adjusted test cases in summarization.e2e.spec.js to utilize the new summary text extraction method.
- Refined SSE useStepHandler to initialize summary content as an array.
- Updated configuration schema by removing unused minReserveTokens field.
- Cleaned up SummaryContentPart type by removing rangeHash property.
These changes streamline the summarization process and ensure compatibility with various content structures.
refactor(summarization): streamline usage tracking and logging
- Removed direct checks for summarization nodes in ModelEndHandler and replaced them with a dedicated markSummarizationUsage function for better readability and maintainability.
- Updated OpenAIChatCompletionController and responses handlers to utilize the new markSummarizationUsage function for setting usage types.
- Enhanced logging functionality by ensuring the logger correctly handles different log levels.
- Introduced a new useCopyToClipboard hook in the Summary component to encapsulate clipboard copy logic, improving code reusability and clarity.
These changes improve the overall structure and efficiency of the summarization handling and logging processes.
refactor(summarization): update summary content block documentation
- Removed outdated comment regarding the last summary content block in BaseClient.js.
- Added a new comment to clarify the purpose of the findSummaryContentBlock method, ensuring consistency in documentation.
These changes enhance code clarity and maintainability by providing accurate descriptions of the summarization logic.
refactor(summarization): update summary content structure in tests
- Modified the summarization content structure in e2e tests to use an array format for text, aligning with recent changes in summary handling.
- Updated test descriptions to clarify the behavior of context token calculations, ensuring consistency and clarity in the tests.
These changes enhance the accuracy and maintainability of the summarization tests by reflecting the updated content structure.
refactor(summarization): remove legacy E2E test setup and configuration
- Deleted the e2e-setup.js and jest.e2e.config.js files, which contained legacy configurations for E2E tests using real API keys.
- Introduced a new summarization.e2e.ts file that implements comprehensive E2E backend integration tests for the summarization process, utilizing real AI providers and tracking summaries throughout the run.
These changes streamline the testing framework by consolidating E2E tests into a single, more robust file while removing outdated configurations.
refactor(summarization): enhance E2E tests and error handling
- Added a cleanup step to force exit after all tests to manage Redis connections.
- Updated the summarization model to 'claude-haiku-4-5-20251001' for consistency across tests.
- Improved error handling in the processStream function to capture and return processing errors.
- Enhanced logging for cross-run tests and tight context scenarios to provide better insights into test execution.
These changes improve the reliability and clarity of the E2E tests for the summarization process.
refactor(summarization): enhance test coverage for maxContextTokens behavior
- Updated run-summarization.test.ts to include a new test case ensuring that maxContextTokens does not exceed user-defined limits, even when calculated ratios suggest otherwise.
- Modified summarization.e2e.ts to replace legacy UsageMetadata type with a more appropriate type for collectedUsage, improving type safety and clarity in the test setup.
These changes improve the robustness of the summarization tests by validating context token constraints and refining type definitions.
feat(summarization): add comprehensive E2E tests for summarization process
- Introduced a new summarization.e2e.test.ts file that implements extensive end-to-end integration tests for the summarization pipeline, covering the full flow from LibreChat to agents.
- The tests utilize real AI providers and include functionality to track summaries during and between runs.
- Added necessary cleanup steps to manage Redis connections post-tests and ensure proper exit.
These changes enhance the testing framework by providing robust coverage for the summarization process, ensuring reliability and performance under real-world conditions.
fix(service): import logger from winston configuration
- Removed the import statement for logger from '@librechat/data-schemas' and replaced it with an import from '~/config/winston'.
- This change ensures that the logger is correctly sourced from the updated configuration, improving consistency in logging practices across the application.
refactor(summary): simplify Summary component and enhance token display
- Removed the unused `meta` prop from the `SummaryButton` component to streamline its interface.
- Updated the token display logic to use a localized string for better internationalization support.
- Adjusted the rendering of the `meta` information to improve its visibility within the `Summary` component.
These changes enhance the clarity and usability of the Summary component while ensuring better localization practices.
feat(summarization): add maxInputTokens configuration for summarization
- Introduced a new `maxInputTokens` property in the summarization configuration schema to control the amount of conversation context sent to the summarizer, with a default value of 10000.
- Updated the `createRun` function to utilize the new `maxInputTokens` setting, allowing for more flexible summarization based on agent context.
These changes enhance the summarization capabilities by providing better control over input token limits, improving the overall summarization process.
refactor(summarization): simplify maxInputTokens logic in createRun function
- Updated the logic for the `maxInputTokens` property in the `createRun` function to directly use the agent's base context tokens when the resolved summarization configuration does not specify a value.
- This change streamlines the configuration process and enhances clarity in how input token limits are determined for summarization.
These modifications improve the maintainability of the summarization configuration by reducing complexity in the token calculation logic.
feat(summary): enhance Summary component to display meta information
- Updated the SummaryContent component to accept an optional `meta` prop, allowing for additional contextual information to be displayed above the main content.
- Adjusted the rendering logic in the Summary component to utilize the new `meta` prop, improving the visibility of supplementary details.
These changes enhance the user experience by providing more context within the Summary component, making it clearer and more informative.
refactor(summarization): standardize reserveRatio configuration in summarization logic
- Replaced instances of `reserveTokensRatio` with `reserveRatio` in the `createRun` function and related tests to unify the terminology across the codebase.
- Updated the summarization configuration schema to reflect this change, ensuring consistency in how the reserve ratio is defined and utilized.
- Removed the per-agent override logic for summarization configuration, simplifying the overall structure and enhancing clarity.
These modifications improve the maintainability and readability of the summarization logic by standardizing the configuration parameters.
2263 lines
73 KiB
JavaScript
2263 lines
73 KiB
JavaScript
const { Providers } = require('@librechat/agents');
|
|
const { Constants, EModelEndpoint } = require('librechat-data-provider');
|
|
const AgentClient = require('./client');
|
|
|
|
jest.mock('@librechat/agents', () => ({
|
|
...jest.requireActual('@librechat/agents'),
|
|
createMetadataAggregator: () => ({
|
|
handleLLMEnd: jest.fn(),
|
|
collected: [],
|
|
}),
|
|
}));
|
|
|
|
jest.mock('@librechat/api', () => ({
|
|
...jest.requireActual('@librechat/api'),
|
|
checkAccess: jest.fn(),
|
|
initializeAgent: jest.fn(),
|
|
createMemoryProcessor: jest.fn(),
|
|
loadAgent: jest.fn(),
|
|
}));
|
|
|
|
jest.mock('~/server/services/Config', () => ({
|
|
getMCPServerTools: jest.fn(),
|
|
}));
|
|
|
|
jest.mock('~/models', () => ({
|
|
getAgent: jest.fn(),
|
|
getRoleByName: jest.fn(),
|
|
}));
|
|
|
|
// Mock getMCPManager
|
|
const mockFormatInstructions = jest.fn();
|
|
jest.mock('~/config', () => ({
|
|
getMCPManager: jest.fn(() => ({
|
|
formatInstructionsForContext: mockFormatInstructions,
|
|
})),
|
|
}));
|
|
|
|
describe('AgentClient - titleConvo', () => {
|
|
let client;
|
|
let mockRun;
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
|
|
beforeEach(() => {
|
|
// Reset all mocks
|
|
jest.clearAllMocks();
|
|
|
|
// Mock run object
|
|
mockRun = {
|
|
generateTitle: jest.fn().mockResolvedValue({
|
|
title: 'Generated Title',
|
|
}),
|
|
};
|
|
|
|
// Mock agent - with both endpoint and provider
|
|
mockAgent = {
|
|
id: 'agent-123',
|
|
endpoint: EModelEndpoint.openAI, // Use a valid provider as endpoint for getProviderConfig
|
|
provider: EModelEndpoint.openAI, // Add provider property
|
|
model_parameters: {
|
|
model: 'gpt-4',
|
|
},
|
|
};
|
|
|
|
// Mock request and response
|
|
mockReq = {
|
|
user: {
|
|
id: 'user-123',
|
|
},
|
|
body: {
|
|
model: 'gpt-4',
|
|
endpoint: EModelEndpoint.openAI,
|
|
key: null,
|
|
},
|
|
config: {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
// Match the agent endpoint
|
|
titleModel: 'gpt-3.5-turbo',
|
|
titlePrompt: 'Custom title prompt',
|
|
titleMethod: 'structured',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
},
|
|
},
|
|
},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
// Mock options
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
endpointTokenConfig: {},
|
|
};
|
|
|
|
// Create client instance
|
|
client = new AgentClient(mockOptions);
|
|
client.run = mockRun;
|
|
client.responseMessageId = 'response-123';
|
|
client.conversationId = 'convo-123';
|
|
client.contentParts = [{ type: 'text', text: 'Test content' }];
|
|
client.recordCollectedUsage = jest.fn().mockResolvedValue(); // Mock as async function that resolves
|
|
});
|
|
|
|
describe('titleConvo method', () => {
|
|
it('should throw error if run is not initialized', async () => {
|
|
client.run = null;
|
|
|
|
await expect(
|
|
client.titleConvo({ text: 'Test', abortController: new AbortController() }),
|
|
).rejects.toThrow('Run not initialized');
|
|
});
|
|
|
|
it('should use titlePrompt from endpoint config', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titlePrompt: 'Custom title prompt',
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should use titlePromptTemplate from endpoint config', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should use titleMethod from endpoint config', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.OPENAI,
|
|
titleMethod: 'structured',
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should use titleModel from endpoint config when provided', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Check that generateTitle was called with correct clientOptions
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-3.5-turbo');
|
|
});
|
|
|
|
it('should handle missing endpoint config gracefully', async () => {
|
|
// Remove endpoint config
|
|
mockReq.config = { endpoints: {} };
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titlePrompt: undefined,
|
|
titlePromptTemplate: undefined,
|
|
titleMethod: undefined,
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should use agent model when titleModel is not provided', async () => {
|
|
// Remove titleModel from config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
titlePrompt: 'Custom title prompt',
|
|
titleMethod: 'structured',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
// titleModel is omitted
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-4'); // Should use agent's model
|
|
});
|
|
|
|
it('should not use titleModel when it equals CURRENT_MODEL constant', async () => {
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
titleModel: Constants.CURRENT_MODEL,
|
|
titlePrompt: 'Custom title prompt',
|
|
titleMethod: 'structured',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-4'); // Should use agent's model
|
|
});
|
|
|
|
it('should pass all required parameters to generateTitle', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith({
|
|
provider: expect.any(String),
|
|
inputText: text,
|
|
contentParts: client.contentParts,
|
|
clientOptions: expect.objectContaining({
|
|
model: 'gpt-3.5-turbo',
|
|
}),
|
|
titlePrompt: 'Custom title prompt',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
titleMethod: 'structured',
|
|
chainOptions: expect.objectContaining({
|
|
signal: abortController.signal,
|
|
}),
|
|
});
|
|
});
|
|
|
|
it('should record collected usage after title generation', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
expect(client.recordCollectedUsage).toHaveBeenCalledWith({
|
|
model: 'gpt-3.5-turbo',
|
|
context: 'title',
|
|
collectedUsage: expect.any(Array),
|
|
balance: {
|
|
enabled: false,
|
|
},
|
|
transactions: {
|
|
enabled: true,
|
|
},
|
|
messageId: 'response-123',
|
|
});
|
|
});
|
|
|
|
it('should return the generated title', async () => {
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
expect(result).toBe('Generated Title');
|
|
});
|
|
|
|
it('should sanitize the generated title by removing think blocks', async () => {
|
|
const titleWithThinkBlock = '<think>reasoning about the title</think> User Hi Greeting';
|
|
mockRun.generateTitle.mockResolvedValue({
|
|
title: titleWithThinkBlock,
|
|
});
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should remove the <think> block and return only the clean title
|
|
expect(result).toBe('User Hi Greeting');
|
|
expect(result).not.toContain('<think>');
|
|
expect(result).not.toContain('</think>');
|
|
});
|
|
|
|
it('should return fallback title when sanitization results in empty string', async () => {
|
|
const titleOnlyThinkBlock = '<think>only reasoning no actual title</think>';
|
|
mockRun.generateTitle.mockResolvedValue({
|
|
title: titleOnlyThinkBlock,
|
|
});
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should return the fallback title since sanitization would result in empty string
|
|
expect(result).toBe('Untitled Conversation');
|
|
});
|
|
|
|
it('should handle errors gracefully and return undefined', async () => {
|
|
mockRun.generateTitle.mockRejectedValue(new Error('Title generation failed'));
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
expect(result).toBeUndefined();
|
|
});
|
|
|
|
it('should skip title generation when titleConvo is set to false', async () => {
|
|
// Set titleConvo to false in endpoint config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
titleConvo: false,
|
|
titleModel: 'gpt-3.5-turbo',
|
|
titlePrompt: 'Custom title prompt',
|
|
titleMethod: 'structured',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should return undefined without generating title
|
|
expect(result).toBeUndefined();
|
|
|
|
// generateTitle should NOT have been called
|
|
expect(mockRun.generateTitle).not.toHaveBeenCalled();
|
|
|
|
// recordCollectedUsage should NOT have been called
|
|
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should skip title generation for temporary chats', async () => {
|
|
// Set isTemporary to true
|
|
mockReq.body.isTemporary = true;
|
|
|
|
const text = 'Test temporary chat';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should return undefined without generating title
|
|
expect(result).toBeUndefined();
|
|
|
|
// generateTitle should NOT have been called
|
|
expect(mockRun.generateTitle).not.toHaveBeenCalled();
|
|
|
|
// recordCollectedUsage should NOT have been called
|
|
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should skip title generation when titleConvo is false in all config', async () => {
|
|
// Set titleConvo to false in "all" config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
all: {
|
|
titleConvo: false,
|
|
titleModel: 'gpt-4o-mini',
|
|
titlePrompt: 'All config title prompt',
|
|
titleMethod: 'completion',
|
|
titlePromptTemplate: 'All config template',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should return undefined without generating title
|
|
expect(result).toBeUndefined();
|
|
|
|
// generateTitle should NOT have been called
|
|
expect(mockRun.generateTitle).not.toHaveBeenCalled();
|
|
|
|
// recordCollectedUsage should NOT have been called
|
|
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should skip title generation when titleConvo is false for custom endpoint scenario', async () => {
|
|
// This test validates the behavior when customEndpointConfig (retrieved via
|
|
// getProviderConfig for custom endpoints) has titleConvo: false.
|
|
//
|
|
// The code path is:
|
|
// 1. endpoints?.all is checked (undefined in this test)
|
|
// 2. endpoints?.[endpoint] is checked (our test config)
|
|
// 3. Would fall back to titleProviderConfig.customEndpointConfig (for real custom endpoints)
|
|
//
|
|
// We simulate a custom endpoint scenario using a dynamically named endpoint config
|
|
|
|
// Create a unique endpoint name that represents a custom endpoint
|
|
const customEndpointName = 'customEndpoint';
|
|
|
|
// Configure the endpoint to have titleConvo: false
|
|
// This simulates what would be in customEndpointConfig for a real custom endpoint
|
|
mockReq.config = {
|
|
endpoints: {
|
|
// No 'all' config - so it will check endpoints[endpoint]
|
|
// This config represents what customEndpointConfig would contain
|
|
[customEndpointName]: {
|
|
titleConvo: false,
|
|
titleModel: 'custom-model-v1',
|
|
titlePrompt: 'Custom endpoint title prompt',
|
|
titleMethod: 'completion',
|
|
titlePromptTemplate: 'Custom template: {{content}}',
|
|
baseURL: 'https://api.custom-llm.com/v1',
|
|
apiKey: 'test-custom-key',
|
|
// Additional custom endpoint properties
|
|
models: {
|
|
default: ['custom-model-v1', 'custom-model-v2'],
|
|
},
|
|
},
|
|
},
|
|
};
|
|
|
|
// Set up agent to use our custom endpoint
|
|
// Use openAI as base but override with custom endpoint name for this test
|
|
mockAgent.endpoint = EModelEndpoint.openAI;
|
|
mockAgent.provider = EModelEndpoint.openAI;
|
|
|
|
// Override the endpoint in the config to point to our custom config
|
|
mockReq.config.endpoints[EModelEndpoint.openAI] =
|
|
mockReq.config.endpoints[customEndpointName];
|
|
delete mockReq.config.endpoints[customEndpointName];
|
|
|
|
const text = 'Test custom endpoint conversation';
|
|
const abortController = new AbortController();
|
|
|
|
const result = await client.titleConvo({ text, abortController });
|
|
|
|
// Should return undefined without generating title because titleConvo is false
|
|
expect(result).toBeUndefined();
|
|
|
|
// generateTitle should NOT have been called
|
|
expect(mockRun.generateTitle).not.toHaveBeenCalled();
|
|
|
|
// recordCollectedUsage should NOT have been called
|
|
expect(client.recordCollectedUsage).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should pass titleEndpoint configuration to generateTitle', async () => {
|
|
// Mock the API key just for this test
|
|
const originalApiKey = process.env.ANTHROPIC_API_KEY;
|
|
process.env.ANTHROPIC_API_KEY = 'test-api-key';
|
|
|
|
// Add titleEndpoint to the config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
titleModel: 'gpt-3.5-turbo',
|
|
titleEndpoint: EModelEndpoint.anthropic,
|
|
titleMethod: 'structured',
|
|
titlePrompt: 'Custom title prompt',
|
|
titlePromptTemplate: 'Custom template',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify generateTitle was called with the custom configuration
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titleMethod: 'structured',
|
|
provider: Providers.ANTHROPIC,
|
|
titlePrompt: 'Custom title prompt',
|
|
titlePromptTemplate: 'Custom template',
|
|
}),
|
|
);
|
|
|
|
// Restore the original API key
|
|
if (originalApiKey) {
|
|
process.env.ANTHROPIC_API_KEY = originalApiKey;
|
|
} else {
|
|
delete process.env.ANTHROPIC_API_KEY;
|
|
}
|
|
});
|
|
|
|
it('should use all config when endpoint config is missing', async () => {
|
|
// Set 'all' config without endpoint-specific config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
all: {
|
|
titleModel: 'gpt-4o-mini',
|
|
titlePrompt: 'All config title prompt',
|
|
titleMethod: 'completion',
|
|
titlePromptTemplate: 'All config template: {{content}}',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify generateTitle was called with 'all' config values
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titleMethod: 'completion',
|
|
titlePrompt: 'All config title prompt',
|
|
titlePromptTemplate: 'All config template: {{content}}',
|
|
}),
|
|
);
|
|
|
|
// Check that the model was set from 'all' config
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-4o-mini');
|
|
});
|
|
|
|
it('should prioritize all config over endpoint config for title settings', async () => {
|
|
// Set both endpoint and 'all' config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.openAI]: {
|
|
titleModel: 'gpt-3.5-turbo',
|
|
titlePrompt: 'Endpoint title prompt',
|
|
titleMethod: 'structured',
|
|
// titlePromptTemplate is omitted to test fallback
|
|
},
|
|
all: {
|
|
titleModel: 'gpt-4o-mini',
|
|
titlePrompt: 'All config title prompt',
|
|
titleMethod: 'completion',
|
|
titlePromptTemplate: 'All config template',
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation text';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify 'all' config takes precedence over endpoint config
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titleMethod: 'completion',
|
|
titlePrompt: 'All config title prompt',
|
|
titlePromptTemplate: 'All config template',
|
|
}),
|
|
);
|
|
|
|
// Check that the model was set from 'all' config
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-4o-mini');
|
|
});
|
|
|
|
it('should use all config with titleEndpoint and verify provider switch', async () => {
|
|
// Mock the API key for the titleEndpoint provider
|
|
const originalApiKey = process.env.ANTHROPIC_API_KEY;
|
|
process.env.ANTHROPIC_API_KEY = 'test-anthropic-key';
|
|
|
|
// Set comprehensive 'all' config with all new title options
|
|
mockReq.config = {
|
|
endpoints: {
|
|
all: {
|
|
titleConvo: true,
|
|
titleModel: 'claude-3-haiku-20240307',
|
|
titleMethod: 'completion', // Testing the new default method
|
|
titlePrompt: 'Generate a concise, descriptive title for this conversation',
|
|
titlePromptTemplate: 'Conversation summary: {{content}}',
|
|
titleEndpoint: EModelEndpoint.anthropic, // Should switch provider to Anthropic
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test conversation about AI and machine learning';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify all config values were used
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.ANTHROPIC, // Critical: Verify provider switched to Anthropic
|
|
titleMethod: 'completion',
|
|
titlePrompt: 'Generate a concise, descriptive title for this conversation',
|
|
titlePromptTemplate: 'Conversation summary: {{content}}',
|
|
inputText: text,
|
|
contentParts: client.contentParts,
|
|
}),
|
|
);
|
|
|
|
// Verify the model was set from 'all' config
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('claude-3-haiku-20240307');
|
|
|
|
// Verify other client options are set correctly
|
|
expect(generateTitleCall.clientOptions).toMatchObject({
|
|
model: 'claude-3-haiku-20240307',
|
|
// Note: Anthropic's getOptions may set its own maxTokens value
|
|
});
|
|
|
|
// Restore the original API key
|
|
if (originalApiKey) {
|
|
process.env.ANTHROPIC_API_KEY = originalApiKey;
|
|
} else {
|
|
delete process.env.ANTHROPIC_API_KEY;
|
|
}
|
|
});
|
|
|
|
it('should test all titleMethod options from all config', async () => {
|
|
// Test each titleMethod: 'completion', 'functions', 'structured'
|
|
const titleMethods = ['completion', 'functions', 'structured'];
|
|
|
|
for (const method of titleMethods) {
|
|
// Clear previous calls
|
|
mockRun.generateTitle.mockClear();
|
|
|
|
// Set 'all' config with specific titleMethod
|
|
mockReq.config = {
|
|
endpoints: {
|
|
all: {
|
|
titleModel: 'gpt-4o-mini',
|
|
titleMethod: method,
|
|
titlePrompt: `Testing ${method} method`,
|
|
titlePromptTemplate: `Template for ${method}: {{content}}`,
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = `Test conversation for ${method} method`;
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify the correct titleMethod was used
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
titleMethod: method,
|
|
titlePrompt: `Testing ${method} method`,
|
|
titlePromptTemplate: `Template for ${method}: {{content}}`,
|
|
}),
|
|
);
|
|
}
|
|
});
|
|
|
|
describe('Azure-specific title generation', () => {
|
|
let originalEnv;
|
|
|
|
beforeEach(() => {
|
|
// Reset mocks
|
|
jest.clearAllMocks();
|
|
|
|
// Save original environment variables
|
|
originalEnv = { ...process.env };
|
|
|
|
// Mock Azure API keys
|
|
process.env.AZURE_OPENAI_API_KEY = 'test-azure-key';
|
|
process.env.AZURE_API_KEY = 'test-azure-key';
|
|
process.env.EASTUS_API_KEY = 'test-eastus-key';
|
|
process.env.EASTUS2_API_KEY = 'test-eastus2-key';
|
|
});
|
|
|
|
afterEach(() => {
|
|
// Restore environment variables
|
|
process.env = originalEnv;
|
|
});
|
|
|
|
it('should use OPENAI provider for Azure serverless endpoints', async () => {
|
|
// Set up Azure endpoint with serverless config
|
|
mockAgent.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockAgent.provider = EModelEndpoint.azureOpenAI;
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.azureOpenAI]: {
|
|
titleConvo: true,
|
|
titleModel: 'grok-3',
|
|
titleMethod: 'completion',
|
|
titlePrompt: 'Azure serverless title prompt',
|
|
streamRate: 35,
|
|
modelGroupMap: {
|
|
'grok-3': {
|
|
group: 'Azure AI Foundry',
|
|
deploymentName: 'grok-3',
|
|
},
|
|
},
|
|
groupMap: {
|
|
'Azure AI Foundry': {
|
|
apiKey: '${AZURE_API_KEY}',
|
|
baseURL: 'https://test.services.ai.azure.com/models',
|
|
version: '2024-05-01-preview',
|
|
serverless: true,
|
|
models: {
|
|
'grok-3': {
|
|
deploymentName: 'grok-3',
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
};
|
|
mockReq.body.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.model = 'grok-3';
|
|
|
|
const text = 'Test Azure serverless conversation';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify provider was switched to OPENAI for serverless
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.OPENAI, // Should be OPENAI for serverless
|
|
titleMethod: 'completion',
|
|
titlePrompt: 'Azure serverless title prompt',
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should use AZURE provider for Azure endpoints with instanceName', async () => {
|
|
// Set up Azure endpoint
|
|
mockAgent.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockAgent.provider = EModelEndpoint.azureOpenAI;
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.azureOpenAI]: {
|
|
titleConvo: true,
|
|
titleModel: 'gpt-4o',
|
|
titleMethod: 'structured',
|
|
titlePrompt: 'Azure instance title prompt',
|
|
streamRate: 35,
|
|
modelGroupMap: {
|
|
'gpt-4o': {
|
|
group: 'eastus',
|
|
deploymentName: 'gpt-4o',
|
|
},
|
|
},
|
|
groupMap: {
|
|
eastus: {
|
|
apiKey: '${EASTUS_API_KEY}',
|
|
instanceName: 'region-instance',
|
|
version: '2024-02-15-preview',
|
|
models: {
|
|
'gpt-4o': {
|
|
deploymentName: 'gpt-4o',
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
};
|
|
mockReq.body.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.model = 'gpt-4o';
|
|
|
|
const text = 'Test Azure instance conversation';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify provider remains AZURE with instanceName
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.AZURE,
|
|
titleMethod: 'structured',
|
|
titlePrompt: 'Azure instance title prompt',
|
|
}),
|
|
);
|
|
});
|
|
|
|
it('should handle Azure titleModel with CURRENT_MODEL constant', async () => {
|
|
// Set up Azure endpoint
|
|
mockAgent.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockAgent.provider = EModelEndpoint.azureOpenAI;
|
|
mockAgent.model_parameters.model = 'gpt-4o-latest';
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.azureOpenAI]: {
|
|
titleConvo: true,
|
|
titleModel: Constants.CURRENT_MODEL,
|
|
titleMethod: 'functions',
|
|
streamRate: 35,
|
|
modelGroupMap: {
|
|
'gpt-4o-latest': {
|
|
group: 'region-eastus',
|
|
deploymentName: 'gpt-4o-mini',
|
|
version: '2024-02-15-preview',
|
|
},
|
|
},
|
|
groupMap: {
|
|
'region-eastus': {
|
|
apiKey: '${EASTUS2_API_KEY}',
|
|
instanceName: 'test-instance',
|
|
version: '2024-12-01-preview',
|
|
models: {
|
|
'gpt-4o-latest': {
|
|
deploymentName: 'gpt-4o-mini',
|
|
version: '2024-02-15-preview',
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
};
|
|
mockReq.body.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.model = 'gpt-4o-latest';
|
|
|
|
const text = 'Test Azure current model';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify it uses the correct model when titleModel is CURRENT_MODEL
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
// When CURRENT_MODEL is used with Azure, the model gets mapped to the deployment name
|
|
// In this case, 'gpt-4o-latest' is mapped to 'gpt-4o-mini' deployment
|
|
expect(generateTitleCall.clientOptions.model).toBe('gpt-4o-mini');
|
|
// Also verify that CURRENT_MODEL constant was not passed as the model
|
|
expect(generateTitleCall.clientOptions.model).not.toBe(Constants.CURRENT_MODEL);
|
|
});
|
|
|
|
it('should handle Azure with multiple model groups', async () => {
|
|
// Set up Azure endpoint
|
|
mockAgent.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockAgent.provider = EModelEndpoint.azureOpenAI;
|
|
mockReq.config = {
|
|
endpoints: {
|
|
[EModelEndpoint.azureOpenAI]: {
|
|
titleConvo: true,
|
|
titleModel: 'o1-mini',
|
|
titleMethod: 'completion',
|
|
streamRate: 35,
|
|
modelGroupMap: {
|
|
'gpt-4o': {
|
|
group: 'eastus',
|
|
deploymentName: 'gpt-4o',
|
|
},
|
|
'o1-mini': {
|
|
group: 'region-eastus',
|
|
deploymentName: 'o1-mini',
|
|
},
|
|
'codex-mini': {
|
|
group: 'codex-mini',
|
|
deploymentName: 'codex-mini',
|
|
},
|
|
},
|
|
groupMap: {
|
|
eastus: {
|
|
apiKey: '${EASTUS_API_KEY}',
|
|
instanceName: 'region-eastus',
|
|
version: '2024-02-15-preview',
|
|
models: {
|
|
'gpt-4o': {
|
|
deploymentName: 'gpt-4o',
|
|
},
|
|
},
|
|
},
|
|
'region-eastus': {
|
|
apiKey: '${EASTUS2_API_KEY}',
|
|
instanceName: 'region-eastus2',
|
|
version: '2024-12-01-preview',
|
|
models: {
|
|
'o1-mini': {
|
|
deploymentName: 'o1-mini',
|
|
},
|
|
},
|
|
},
|
|
'codex-mini': {
|
|
apiKey: '${AZURE_API_KEY}',
|
|
baseURL: 'https://example.cognitiveservices.azure.com/openai/',
|
|
version: '2025-04-01-preview',
|
|
serverless: true,
|
|
models: {
|
|
'codex-mini': {
|
|
deploymentName: 'codex-mini',
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
};
|
|
mockReq.body.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.model = 'o1-mini';
|
|
|
|
const text = 'Test Azure multi-group conversation';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify correct model and provider are used
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.AZURE,
|
|
titleMethod: 'completion',
|
|
}),
|
|
);
|
|
|
|
const generateTitleCall = mockRun.generateTitle.mock.calls[0][0];
|
|
expect(generateTitleCall.clientOptions.model).toBe('o1-mini');
|
|
expect(generateTitleCall.clientOptions.maxTokens).toBeUndefined(); // o1 models shouldn't have maxTokens
|
|
});
|
|
|
|
it('should use all config as fallback for Azure endpoints', async () => {
|
|
// Set up Azure endpoint with minimal config
|
|
mockAgent.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockAgent.provider = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.endpoint = EModelEndpoint.azureOpenAI;
|
|
mockReq.body.model = 'gpt-4';
|
|
|
|
// Set 'all' config as fallback with a serverless Azure config
|
|
mockReq.config = {
|
|
endpoints: {
|
|
all: {
|
|
titleConvo: true,
|
|
titleModel: 'gpt-4',
|
|
titleMethod: 'structured',
|
|
titlePrompt: 'Fallback title prompt from all config',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
modelGroupMap: {
|
|
'gpt-4': {
|
|
group: 'default-group',
|
|
deploymentName: 'gpt-4',
|
|
},
|
|
},
|
|
groupMap: {
|
|
'default-group': {
|
|
apiKey: '${AZURE_API_KEY}',
|
|
baseURL: 'https://default.openai.azure.com/',
|
|
version: '2024-02-15-preview',
|
|
serverless: true,
|
|
models: {
|
|
'gpt-4': {
|
|
deploymentName: 'gpt-4',
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
};
|
|
|
|
const text = 'Test Azure with all config fallback';
|
|
const abortController = new AbortController();
|
|
|
|
await client.titleConvo({ text, abortController });
|
|
|
|
// Verify all config is used
|
|
expect(mockRun.generateTitle).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
provider: Providers.OPENAI, // Should be OPENAI when no instanceName
|
|
titleMethod: 'structured',
|
|
titlePrompt: 'Fallback title prompt from all config',
|
|
titlePromptTemplate: 'Template: {{content}}',
|
|
}),
|
|
);
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('getOptions method - GPT-5+ model handling', () => {
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
|
|
beforeEach(() => {
|
|
jest.clearAllMocks();
|
|
|
|
mockAgent = {
|
|
id: 'agent-123',
|
|
endpoint: EModelEndpoint.openAI,
|
|
provider: EModelEndpoint.openAI,
|
|
model_parameters: {
|
|
model: 'gpt-5',
|
|
},
|
|
};
|
|
|
|
mockReq = {
|
|
app: {
|
|
locals: {},
|
|
},
|
|
user: {
|
|
id: 'user-123',
|
|
},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
};
|
|
|
|
client = new AgentClient(mockOptions);
|
|
});
|
|
|
|
it('should move maxTokens to modelKwargs.max_completion_tokens for GPT-5 models', () => {
|
|
const clientOptions = {
|
|
model: 'gpt-5',
|
|
maxTokens: 2048,
|
|
temperature: 0.7,
|
|
};
|
|
|
|
// Simulate the getOptions logic that handles GPT-5+ models
|
|
if (/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) && clientOptions.maxTokens != null) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
clientOptions.modelKwargs.max_completion_tokens = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs).toBeDefined();
|
|
expect(clientOptions.modelKwargs.max_completion_tokens).toBe(2048);
|
|
expect(clientOptions.temperature).toBe(0.7); // Other options should remain
|
|
});
|
|
|
|
it('should move maxTokens to modelKwargs.max_output_tokens for GPT-5 models with useResponsesApi', () => {
|
|
const clientOptions = {
|
|
model: 'gpt-5',
|
|
maxTokens: 2048,
|
|
temperature: 0.7,
|
|
useResponsesApi: true,
|
|
};
|
|
|
|
if (/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) && clientOptions.maxTokens != null) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
const paramName =
|
|
clientOptions.useResponsesApi === true ? 'max_output_tokens' : 'max_completion_tokens';
|
|
clientOptions.modelKwargs[paramName] = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs).toBeDefined();
|
|
expect(clientOptions.modelKwargs.max_output_tokens).toBe(2048);
|
|
expect(clientOptions.temperature).toBe(0.7); // Other options should remain
|
|
});
|
|
|
|
it('should handle GPT-5+ models with existing modelKwargs', () => {
|
|
const clientOptions = {
|
|
model: 'gpt-6',
|
|
maxTokens: 1500,
|
|
temperature: 0.8,
|
|
modelKwargs: {
|
|
customParam: 'value',
|
|
},
|
|
};
|
|
|
|
// Simulate the getOptions logic
|
|
if (/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) && clientOptions.maxTokens != null) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
clientOptions.modelKwargs.max_completion_tokens = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs).toEqual({
|
|
customParam: 'value',
|
|
max_completion_tokens: 1500,
|
|
});
|
|
});
|
|
|
|
it('should not modify maxTokens for non-GPT-5+ models', () => {
|
|
const clientOptions = {
|
|
model: 'gpt-4',
|
|
maxTokens: 2048,
|
|
temperature: 0.7,
|
|
};
|
|
|
|
// Simulate the getOptions logic
|
|
if (/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) && clientOptions.maxTokens != null) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
clientOptions.modelKwargs.max_completion_tokens = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
// Should not be modified since it's GPT-4
|
|
expect(clientOptions.maxTokens).toBe(2048);
|
|
expect(clientOptions.modelKwargs).toBeUndefined();
|
|
});
|
|
|
|
it('should handle various GPT-5+ model formats', () => {
|
|
const testCases = [
|
|
{ model: 'gpt-5.1', shouldTransform: true },
|
|
{ model: 'gpt-5.1-chat-latest', shouldTransform: true },
|
|
{ model: 'gpt-5.1-codex', shouldTransform: true },
|
|
{ model: 'gpt-5', shouldTransform: true },
|
|
{ model: 'gpt-5-turbo', shouldTransform: true },
|
|
{ model: 'gpt-6', shouldTransform: true },
|
|
{ model: 'gpt-7-preview', shouldTransform: true },
|
|
{ model: 'gpt-8', shouldTransform: true },
|
|
{ model: 'gpt-9-mini', shouldTransform: true },
|
|
{ model: 'gpt-4', shouldTransform: false },
|
|
{ model: 'gpt-4o', shouldTransform: false },
|
|
{ model: 'gpt-3.5-turbo', shouldTransform: false },
|
|
{ model: 'claude-3', shouldTransform: false },
|
|
];
|
|
|
|
testCases.forEach(({ model, shouldTransform }) => {
|
|
const clientOptions = {
|
|
model,
|
|
maxTokens: 1000,
|
|
};
|
|
|
|
// Simulate the getOptions logic
|
|
if (
|
|
/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) &&
|
|
clientOptions.maxTokens != null
|
|
) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
clientOptions.modelKwargs.max_completion_tokens = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
if (shouldTransform) {
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs?.max_completion_tokens).toBe(1000);
|
|
} else {
|
|
expect(clientOptions.maxTokens).toBe(1000);
|
|
expect(clientOptions.modelKwargs).toBeUndefined();
|
|
}
|
|
});
|
|
});
|
|
|
|
it('should not swap max token param for older models when using useResponsesApi', () => {
|
|
const testCases = [
|
|
{ model: 'gpt-5.1', shouldTransform: true },
|
|
{ model: 'gpt-5.1-chat-latest', shouldTransform: true },
|
|
{ model: 'gpt-5.1-codex', shouldTransform: true },
|
|
{ model: 'gpt-5', shouldTransform: true },
|
|
{ model: 'gpt-5-turbo', shouldTransform: true },
|
|
{ model: 'gpt-6', shouldTransform: true },
|
|
{ model: 'gpt-7-preview', shouldTransform: true },
|
|
{ model: 'gpt-8', shouldTransform: true },
|
|
{ model: 'gpt-9-mini', shouldTransform: true },
|
|
{ model: 'gpt-4', shouldTransform: false },
|
|
{ model: 'gpt-4o', shouldTransform: false },
|
|
{ model: 'gpt-3.5-turbo', shouldTransform: false },
|
|
{ model: 'claude-3', shouldTransform: false },
|
|
];
|
|
|
|
testCases.forEach(({ model, shouldTransform }) => {
|
|
const clientOptions = {
|
|
model,
|
|
maxTokens: 1000,
|
|
useResponsesApi: true,
|
|
};
|
|
|
|
if (
|
|
/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) &&
|
|
clientOptions.maxTokens != null
|
|
) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
const paramName =
|
|
clientOptions.useResponsesApi === true ? 'max_output_tokens' : 'max_completion_tokens';
|
|
clientOptions.modelKwargs[paramName] = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
if (shouldTransform) {
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs?.max_output_tokens).toBe(1000);
|
|
} else {
|
|
expect(clientOptions.maxTokens).toBe(1000);
|
|
expect(clientOptions.modelKwargs).toBeUndefined();
|
|
}
|
|
});
|
|
});
|
|
|
|
it('should not transform if maxTokens is null or undefined', () => {
|
|
const testCases = [
|
|
{ model: 'gpt-5', maxTokens: null },
|
|
{ model: 'gpt-5', maxTokens: undefined },
|
|
{ model: 'gpt-6', maxTokens: 0 }, // Should transform even if 0
|
|
];
|
|
|
|
testCases.forEach(({ model, maxTokens }, index) => {
|
|
const clientOptions = {
|
|
model,
|
|
maxTokens,
|
|
temperature: 0.7,
|
|
};
|
|
|
|
// Simulate the getOptions logic
|
|
if (
|
|
/\bgpt-[5-9](?:\.\d+)?\b/i.test(clientOptions.model) &&
|
|
clientOptions.maxTokens != null
|
|
) {
|
|
clientOptions.modelKwargs = clientOptions.modelKwargs ?? {};
|
|
clientOptions.modelKwargs.max_completion_tokens = clientOptions.maxTokens;
|
|
delete clientOptions.maxTokens;
|
|
}
|
|
|
|
if (index < 2) {
|
|
// null or undefined cases
|
|
expect(clientOptions.maxTokens).toBe(maxTokens);
|
|
expect(clientOptions.modelKwargs).toBeUndefined();
|
|
} else {
|
|
// 0 case - should transform
|
|
expect(clientOptions.maxTokens).toBeUndefined();
|
|
expect(clientOptions.modelKwargs?.max_completion_tokens).toBe(0);
|
|
}
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('buildMessages with MCP server instructions', () => {
|
|
let client;
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
|
|
beforeEach(() => {
|
|
jest.clearAllMocks();
|
|
|
|
// Reset the mock to default behavior
|
|
mockFormatInstructions.mockResolvedValue(
|
|
'# MCP Server Instructions\n\nTest MCP instructions here',
|
|
);
|
|
|
|
const { DynamicStructuredTool } = require('@langchain/core/tools');
|
|
|
|
// Create mock MCP tools with the delimiter pattern
|
|
const mockMCPTool1 = new DynamicStructuredTool({
|
|
name: `tool1${Constants.mcp_delimiter}server1`,
|
|
description: 'Test MCP tool 1',
|
|
schema: {},
|
|
func: async () => 'result',
|
|
});
|
|
|
|
const mockMCPTool2 = new DynamicStructuredTool({
|
|
name: `tool2${Constants.mcp_delimiter}server2`,
|
|
description: 'Test MCP tool 2',
|
|
schema: {},
|
|
func: async () => 'result',
|
|
});
|
|
|
|
mockAgent = {
|
|
id: 'agent-123',
|
|
endpoint: EModelEndpoint.openAI,
|
|
provider: EModelEndpoint.openAI,
|
|
instructions: 'Base agent instructions',
|
|
model_parameters: {
|
|
model: 'gpt-4',
|
|
},
|
|
tools: [mockMCPTool1, mockMCPTool2],
|
|
};
|
|
|
|
mockReq = {
|
|
user: {
|
|
id: 'user-123',
|
|
},
|
|
body: {
|
|
endpoint: EModelEndpoint.openAI,
|
|
},
|
|
config: {},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
endpoint: EModelEndpoint.agents,
|
|
};
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
client.shouldSummarize = false;
|
|
client.maxContextTokens = 4096;
|
|
});
|
|
|
|
it('should await MCP instructions and not include [object Promise] in agent instructions', async () => {
|
|
// Set specific return value for this test
|
|
mockFormatInstructions.mockResolvedValue(
|
|
'# MCP Server Instructions\n\nUse these tools carefully',
|
|
);
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
// Verify formatInstructionsForContext was called with correct server names
|
|
expect(mockFormatInstructions).toHaveBeenCalledWith(['server1', 'server2']);
|
|
|
|
// Verify the instructions do NOT contain [object Promise]
|
|
expect(client.options.agent.instructions).not.toContain('[object Promise]');
|
|
|
|
// Verify the instructions DO contain the MCP instructions
|
|
expect(client.options.agent.instructions).toContain('# MCP Server Instructions');
|
|
expect(client.options.agent.instructions).toContain('Use these tools carefully');
|
|
|
|
// Verify the base instructions are also included (from agent config, not buildOptions)
|
|
expect(client.options.agent.instructions).toContain('Base agent instructions');
|
|
});
|
|
|
|
it('should handle MCP instructions with ephemeral agent', async () => {
|
|
// Set specific return value for this test
|
|
mockFormatInstructions.mockResolvedValue(
|
|
'# Ephemeral MCP Instructions\n\nSpecial ephemeral instructions',
|
|
);
|
|
|
|
// Set up ephemeral agent with MCP servers
|
|
mockReq.body.ephemeralAgent = {
|
|
mcp: ['ephemeral-server1', 'ephemeral-server2'],
|
|
};
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Test ephemeral',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Ephemeral instructions',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
// Verify formatInstructionsForContext was called with ephemeral server names
|
|
expect(mockFormatInstructions).toHaveBeenCalledWith([
|
|
'ephemeral-server1',
|
|
'ephemeral-server2',
|
|
]);
|
|
|
|
// Verify no [object Promise] in instructions
|
|
expect(client.options.agent.instructions).not.toContain('[object Promise]');
|
|
|
|
// Verify ephemeral MCP instructions are included
|
|
expect(client.options.agent.instructions).toContain('# Ephemeral MCP Instructions');
|
|
expect(client.options.agent.instructions).toContain('Special ephemeral instructions');
|
|
});
|
|
|
|
it('should handle empty MCP instructions gracefully', async () => {
|
|
// Set empty return value for this test
|
|
mockFormatInstructions.mockResolvedValue('');
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions only',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
// Verify the instructions still work without MCP content (from agent config, not buildOptions)
|
|
expect(client.options.agent.instructions).toBe('Base agent instructions');
|
|
expect(client.options.agent.instructions).not.toContain('[object Promise]');
|
|
});
|
|
|
|
it('should handle MCP instructions error gracefully', async () => {
|
|
// Set error return for this test
|
|
mockFormatInstructions.mockRejectedValue(new Error('MCP error'));
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
// Should not throw
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
// Should still have base instructions without MCP content (from agent config, not buildOptions)
|
|
expect(client.options.agent.instructions).toContain('Base agent instructions');
|
|
expect(client.options.agent.instructions).not.toContain('[object Promise]');
|
|
});
|
|
});
|
|
|
|
describe('runMemory method', () => {
|
|
let client;
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
let mockProcessMemory;
|
|
|
|
beforeEach(() => {
|
|
jest.clearAllMocks();
|
|
|
|
mockAgent = {
|
|
id: 'agent-123',
|
|
endpoint: EModelEndpoint.openAI,
|
|
provider: EModelEndpoint.openAI,
|
|
model_parameters: {
|
|
model: 'gpt-4',
|
|
},
|
|
};
|
|
|
|
mockReq = {
|
|
user: {
|
|
id: 'user-123',
|
|
personalization: {
|
|
memories: true,
|
|
},
|
|
},
|
|
};
|
|
|
|
// Mock getAppConfig for memory tests
|
|
mockReq.config = {
|
|
memory: {
|
|
messageWindowSize: 3,
|
|
},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
};
|
|
|
|
mockProcessMemory = jest.fn().mockResolvedValue([]);
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.processMemory = mockProcessMemory;
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
});
|
|
|
|
it('should filter out image URLs from message content', async () => {
|
|
const { HumanMessage, AIMessage } = require('@langchain/core/messages');
|
|
const messages = [
|
|
new HumanMessage({
|
|
content: [
|
|
{
|
|
type: 'text',
|
|
text: 'What is in this image?',
|
|
},
|
|
{
|
|
type: 'image_url',
|
|
image_url: {
|
|
url: 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg==',
|
|
detail: 'auto',
|
|
},
|
|
},
|
|
],
|
|
}),
|
|
new AIMessage('I can see a small red pixel in the image.'),
|
|
new HumanMessage({
|
|
content: [
|
|
{
|
|
type: 'text',
|
|
text: 'What about this one?',
|
|
},
|
|
{
|
|
type: 'image_url',
|
|
image_url: {
|
|
url: 'data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEAYABgAAD/',
|
|
detail: 'high',
|
|
},
|
|
},
|
|
],
|
|
}),
|
|
];
|
|
|
|
await client.runMemory(messages);
|
|
|
|
expect(mockProcessMemory).toHaveBeenCalledTimes(1);
|
|
const processedMessage = mockProcessMemory.mock.calls[0][0][0];
|
|
|
|
// Verify the buffer message was created
|
|
expect(processedMessage.constructor.name).toBe('HumanMessage');
|
|
expect(processedMessage.content).toContain('# Current Chat:');
|
|
|
|
// Verify that image URLs are not in the buffer string
|
|
expect(processedMessage.content).not.toContain('image_url');
|
|
expect(processedMessage.content).not.toContain('data:image');
|
|
expect(processedMessage.content).not.toContain('base64');
|
|
|
|
// Verify text content is preserved
|
|
expect(processedMessage.content).toContain('What is in this image?');
|
|
expect(processedMessage.content).toContain('I can see a small red pixel in the image.');
|
|
expect(processedMessage.content).toContain('What about this one?');
|
|
});
|
|
|
|
it('should handle messages with only text content', async () => {
|
|
const { HumanMessage, AIMessage } = require('@langchain/core/messages');
|
|
const messages = [
|
|
new HumanMessage('Hello, how are you?'),
|
|
new AIMessage('I am doing well, thank you!'),
|
|
new HumanMessage('That is great to hear.'),
|
|
];
|
|
|
|
await client.runMemory(messages);
|
|
|
|
expect(mockProcessMemory).toHaveBeenCalledTimes(1);
|
|
const processedMessage = mockProcessMemory.mock.calls[0][0][0];
|
|
|
|
expect(processedMessage.content).toContain('Hello, how are you?');
|
|
expect(processedMessage.content).toContain('I am doing well, thank you!');
|
|
expect(processedMessage.content).toContain('That is great to hear.');
|
|
});
|
|
|
|
it('should handle mixed content types correctly', async () => {
|
|
const { HumanMessage } = require('@langchain/core/messages');
|
|
const { ContentTypes } = require('librechat-data-provider');
|
|
|
|
const messages = [
|
|
new HumanMessage({
|
|
content: [
|
|
{
|
|
type: 'text',
|
|
text: 'Here is some text',
|
|
},
|
|
{
|
|
type: ContentTypes.IMAGE_URL,
|
|
image_url: {
|
|
url: 'https://example.com/image.png',
|
|
},
|
|
},
|
|
{
|
|
type: 'text',
|
|
text: ' and more text',
|
|
},
|
|
],
|
|
}),
|
|
];
|
|
|
|
await client.runMemory(messages);
|
|
|
|
expect(mockProcessMemory).toHaveBeenCalledTimes(1);
|
|
const processedMessage = mockProcessMemory.mock.calls[0][0][0];
|
|
|
|
// Should contain text parts but not image URLs
|
|
expect(processedMessage.content).toContain('Here is some text');
|
|
expect(processedMessage.content).toContain('and more text');
|
|
expect(processedMessage.content).not.toContain('example.com/image.png');
|
|
expect(processedMessage.content).not.toContain('IMAGE_URL');
|
|
});
|
|
|
|
it('should preserve original messages without mutation', async () => {
|
|
const { HumanMessage } = require('@langchain/core/messages');
|
|
const originalContent = [
|
|
{
|
|
type: 'text',
|
|
text: 'Original text',
|
|
},
|
|
{
|
|
type: 'image_url',
|
|
image_url: {
|
|
url: 'data:image/png;base64,ABC123',
|
|
},
|
|
},
|
|
];
|
|
|
|
const messages = [
|
|
new HumanMessage({
|
|
content: [...originalContent],
|
|
}),
|
|
];
|
|
|
|
await client.runMemory(messages);
|
|
|
|
// Verify original message wasn't mutated
|
|
expect(messages[0].content).toHaveLength(2);
|
|
expect(messages[0].content[1].type).toBe('image_url');
|
|
expect(messages[0].content[1].image_url.url).toBe('data:image/png;base64,ABC123');
|
|
});
|
|
|
|
it('should handle message window size correctly', async () => {
|
|
const { HumanMessage, AIMessage } = require('@langchain/core/messages');
|
|
const messages = [
|
|
new HumanMessage('Message 1'),
|
|
new AIMessage('Response 1'),
|
|
new HumanMessage('Message 2'),
|
|
new AIMessage('Response 2'),
|
|
new HumanMessage('Message 3'),
|
|
new AIMessage('Response 3'),
|
|
];
|
|
|
|
// Window size is set to 3 in mockReq
|
|
await client.runMemory(messages);
|
|
|
|
expect(mockProcessMemory).toHaveBeenCalledTimes(1);
|
|
const processedMessage = mockProcessMemory.mock.calls[0][0][0];
|
|
|
|
// Should only include last 3 messages due to window size
|
|
expect(processedMessage.content).toContain('Message 3');
|
|
expect(processedMessage.content).toContain('Response 3');
|
|
expect(processedMessage.content).not.toContain('Message 1');
|
|
expect(processedMessage.content).not.toContain('Response 1');
|
|
});
|
|
|
|
it('should return early if processMemory is not set', async () => {
|
|
const { HumanMessage } = require('@langchain/core/messages');
|
|
client.processMemory = null;
|
|
|
|
const result = await client.runMemory([new HumanMessage('Test')]);
|
|
|
|
expect(result).toBeUndefined();
|
|
expect(mockProcessMemory).not.toHaveBeenCalled();
|
|
});
|
|
});
|
|
|
|
describe('getMessagesForConversation - mapMethod and mapCondition', () => {
|
|
const createMessage = (id, parentId, text, extras = {}) => ({
|
|
messageId: id,
|
|
parentMessageId: parentId,
|
|
text,
|
|
isCreatedByUser: false,
|
|
...extras,
|
|
});
|
|
|
|
it('should apply mapMethod to all messages when mapCondition is not provided', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First message'),
|
|
createMessage('msg-2', 'msg-1', 'Second message'),
|
|
createMessage('msg-3', 'msg-2', 'Third message'),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, mapped: true }));
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-3',
|
|
mapMethod,
|
|
});
|
|
|
|
expect(result).toHaveLength(3);
|
|
expect(mapMethod).toHaveBeenCalledTimes(3);
|
|
result.forEach((msg) => {
|
|
expect(msg.mapped).toBe(true);
|
|
});
|
|
});
|
|
|
|
it('should apply mapMethod only to messages where mapCondition returns true', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First message', { addedConvo: false }),
|
|
createMessage('msg-2', 'msg-1', 'Second message', { addedConvo: true }),
|
|
createMessage('msg-3', 'msg-2', 'Third message', { addedConvo: true }),
|
|
createMessage('msg-4', 'msg-3', 'Fourth message', { addedConvo: false }),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, mapped: true }));
|
|
const mapCondition = (msg) => msg.addedConvo === true;
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-4',
|
|
mapMethod,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result).toHaveLength(4);
|
|
expect(mapMethod).toHaveBeenCalledTimes(2);
|
|
|
|
expect(result[0].mapped).toBeUndefined();
|
|
expect(result[1].mapped).toBe(true);
|
|
expect(result[2].mapped).toBe(true);
|
|
expect(result[3].mapped).toBeUndefined();
|
|
});
|
|
|
|
it('should not apply mapMethod when mapCondition returns false for all messages', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First message', { addedConvo: false }),
|
|
createMessage('msg-2', 'msg-1', 'Second message', { addedConvo: false }),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, mapped: true }));
|
|
const mapCondition = (msg) => msg.addedConvo === true;
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-2',
|
|
mapMethod,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result).toHaveLength(2);
|
|
expect(mapMethod).not.toHaveBeenCalled();
|
|
result.forEach((msg) => {
|
|
expect(msg.mapped).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
it('should not call mapMethod when mapMethod is null', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First message'),
|
|
createMessage('msg-2', 'msg-1', 'Second message'),
|
|
];
|
|
|
|
const mapCondition = jest.fn(() => true);
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-2',
|
|
mapMethod: null,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result).toHaveLength(2);
|
|
expect(mapCondition).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should handle mapCondition with complex logic', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'User message', { isCreatedByUser: true, addedConvo: true }),
|
|
createMessage('msg-2', 'msg-1', 'Assistant response', { addedConvo: true }),
|
|
createMessage('msg-3', 'msg-2', 'Another user message', { isCreatedByUser: true }),
|
|
createMessage('msg-4', 'msg-3', 'Another response', { addedConvo: true }),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, processed: true }));
|
|
const mapCondition = (msg) => msg.addedConvo === true && !msg.isCreatedByUser;
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-4',
|
|
mapMethod,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result).toHaveLength(4);
|
|
expect(mapMethod).toHaveBeenCalledTimes(2);
|
|
|
|
expect(result[0].processed).toBeUndefined();
|
|
expect(result[1].processed).toBe(true);
|
|
expect(result[2].processed).toBeUndefined();
|
|
expect(result[3].processed).toBe(true);
|
|
});
|
|
|
|
it('should preserve message order after applying mapMethod with mapCondition', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First', { addedConvo: true }),
|
|
createMessage('msg-2', 'msg-1', 'Second', { addedConvo: false }),
|
|
createMessage('msg-3', 'msg-2', 'Third', { addedConvo: true }),
|
|
];
|
|
|
|
const mapMethod = (msg) => ({ ...msg, text: `[MAPPED] ${msg.text}` });
|
|
const mapCondition = (msg) => msg.addedConvo === true;
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-3',
|
|
mapMethod,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result[0].text).toBe('[MAPPED] First');
|
|
expect(result[1].text).toBe('Second');
|
|
expect(result[2].text).toBe('[MAPPED] Third');
|
|
});
|
|
|
|
it('should work with summary option alongside mapMethod and mapCondition', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First', { addedConvo: false }),
|
|
createMessage('msg-2', 'msg-1', 'Second', {
|
|
summary: 'Summary of conversation',
|
|
addedConvo: true,
|
|
}),
|
|
createMessage('msg-3', 'msg-2', 'Third', { addedConvo: true }),
|
|
createMessage('msg-4', 'msg-3', 'Fourth', { addedConvo: false }),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, mapped: true }));
|
|
const mapCondition = (msg) => msg.addedConvo === true;
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-4',
|
|
mapMethod,
|
|
mapCondition,
|
|
summary: true,
|
|
});
|
|
|
|
/** Traversal stops at msg-2 (has summary), so we get msg-4 -> msg-3 -> msg-2 */
|
|
expect(result).toHaveLength(3);
|
|
expect(result[0].content).toEqual([{ type: 'text', text: 'Summary of conversation' }]);
|
|
expect(result[0].role).toBe('system');
|
|
expect(result[0].mapped).toBe(true);
|
|
expect(result[1].mapped).toBe(true);
|
|
expect(result[2].mapped).toBeUndefined();
|
|
});
|
|
|
|
it('should handle empty messages array', () => {
|
|
const mapMethod = jest.fn();
|
|
const mapCondition = jest.fn();
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages: [],
|
|
parentMessageId: 'msg-1',
|
|
mapMethod,
|
|
mapCondition,
|
|
});
|
|
|
|
expect(result).toHaveLength(0);
|
|
expect(mapMethod).not.toHaveBeenCalled();
|
|
expect(mapCondition).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should handle undefined mapCondition explicitly', () => {
|
|
const messages = [
|
|
createMessage('msg-1', null, 'First'),
|
|
createMessage('msg-2', 'msg-1', 'Second'),
|
|
];
|
|
|
|
const mapMethod = jest.fn((msg) => ({ ...msg, mapped: true }));
|
|
|
|
const result = AgentClient.getMessagesForConversation({
|
|
messages,
|
|
parentMessageId: 'msg-2',
|
|
mapMethod,
|
|
mapCondition: undefined,
|
|
});
|
|
|
|
expect(result).toHaveLength(2);
|
|
expect(mapMethod).toHaveBeenCalledTimes(2);
|
|
result.forEach((msg) => {
|
|
expect(msg.mapped).toBe(true);
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('buildMessages - memory context for parallel agents', () => {
|
|
let client;
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
|
|
beforeEach(() => {
|
|
jest.clearAllMocks();
|
|
|
|
mockAgent = {
|
|
id: 'primary-agent',
|
|
name: 'Primary Agent',
|
|
endpoint: EModelEndpoint.openAI,
|
|
provider: EModelEndpoint.openAI,
|
|
instructions: 'Primary agent instructions',
|
|
model_parameters: {
|
|
model: 'gpt-4',
|
|
},
|
|
tools: [],
|
|
};
|
|
|
|
mockReq = {
|
|
user: {
|
|
id: 'user-123',
|
|
personalization: {
|
|
memories: true,
|
|
},
|
|
},
|
|
body: {
|
|
endpoint: EModelEndpoint.openAI,
|
|
},
|
|
config: {
|
|
memory: {
|
|
disabled: false,
|
|
},
|
|
},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
endpoint: EModelEndpoint.agents,
|
|
};
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
client.shouldSummarize = false;
|
|
client.maxContextTokens = 4096;
|
|
});
|
|
|
|
it('should pass memory context to parallel agents (addedConvo)', async () => {
|
|
const memoryContent = 'User prefers dark mode. User is a software developer.';
|
|
client.useMemory = jest.fn().mockResolvedValue(memoryContent);
|
|
|
|
const parallelAgent1 = {
|
|
id: 'parallel-agent-1',
|
|
name: 'Parallel Agent 1',
|
|
instructions: 'Parallel agent 1 instructions',
|
|
provider: EModelEndpoint.openAI,
|
|
};
|
|
|
|
const parallelAgent2 = {
|
|
id: 'parallel-agent-2',
|
|
name: 'Parallel Agent 2',
|
|
instructions: 'Parallel agent 2 instructions',
|
|
provider: EModelEndpoint.anthropic,
|
|
};
|
|
|
|
client.agentConfigs = new Map([
|
|
['parallel-agent-1', parallelAgent1],
|
|
['parallel-agent-2', parallelAgent2],
|
|
]);
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
expect(client.useMemory).toHaveBeenCalled();
|
|
|
|
// Verify primary agent has its configured instructions (not from buildOptions) and memory context
|
|
expect(client.options.agent.instructions).toContain('Primary agent instructions');
|
|
expect(client.options.agent.instructions).toContain(memoryContent);
|
|
|
|
expect(parallelAgent1.instructions).toContain('Parallel agent 1 instructions');
|
|
expect(parallelAgent1.instructions).toContain(memoryContent);
|
|
|
|
expect(parallelAgent2.instructions).toContain('Parallel agent 2 instructions');
|
|
expect(parallelAgent2.instructions).toContain(memoryContent);
|
|
});
|
|
|
|
it('should not modify parallel agents when no memory context is available', async () => {
|
|
client.useMemory = jest.fn().mockResolvedValue(undefined);
|
|
|
|
const parallelAgent = {
|
|
id: 'parallel-agent-1',
|
|
name: 'Parallel Agent 1',
|
|
instructions: 'Original parallel instructions',
|
|
provider: EModelEndpoint.openAI,
|
|
};
|
|
|
|
client.agentConfigs = new Map([['parallel-agent-1', parallelAgent]]);
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
});
|
|
|
|
expect(parallelAgent.instructions).toBe('Original parallel instructions');
|
|
});
|
|
|
|
it('should handle parallel agents without existing instructions', async () => {
|
|
const memoryContent = 'User is a data scientist.';
|
|
client.useMemory = jest.fn().mockResolvedValue(memoryContent);
|
|
|
|
const parallelAgentNoInstructions = {
|
|
id: 'parallel-agent-no-instructions',
|
|
name: 'Parallel Agent No Instructions',
|
|
provider: EModelEndpoint.openAI,
|
|
};
|
|
|
|
client.agentConfigs = new Map([
|
|
['parallel-agent-no-instructions', parallelAgentNoInstructions],
|
|
]);
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await client.buildMessages(messages, null, {
|
|
instructions: null,
|
|
additional_instructions: null,
|
|
});
|
|
|
|
expect(parallelAgentNoInstructions.instructions).toContain(memoryContent);
|
|
});
|
|
|
|
it('should not modify agentConfigs when none exist', async () => {
|
|
const memoryContent = 'User prefers concise responses.';
|
|
client.useMemory = jest.fn().mockResolvedValue(memoryContent);
|
|
|
|
client.agentConfigs = null;
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await expect(
|
|
client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
}),
|
|
).resolves.not.toThrow();
|
|
|
|
expect(client.options.agent.instructions).toContain(memoryContent);
|
|
});
|
|
|
|
it('should handle empty agentConfigs map', async () => {
|
|
const memoryContent = 'User likes detailed explanations.';
|
|
client.useMemory = jest.fn().mockResolvedValue(memoryContent);
|
|
|
|
client.agentConfigs = new Map();
|
|
|
|
const messages = [
|
|
{
|
|
messageId: 'msg-1',
|
|
parentMessageId: null,
|
|
sender: 'User',
|
|
text: 'Hello',
|
|
isCreatedByUser: true,
|
|
},
|
|
];
|
|
|
|
await expect(
|
|
client.buildMessages(messages, null, {
|
|
instructions: 'Base instructions',
|
|
additional_instructions: null,
|
|
}),
|
|
).resolves.not.toThrow();
|
|
|
|
expect(client.options.agent.instructions).toContain(memoryContent);
|
|
});
|
|
});
|
|
|
|
describe('useMemory method - prelimAgent assignment', () => {
|
|
let client;
|
|
let mockReq;
|
|
let mockRes;
|
|
let mockAgent;
|
|
let mockOptions;
|
|
let mockCheckAccess;
|
|
let mockLoadAgent;
|
|
let mockInitializeAgent;
|
|
let mockCreateMemoryProcessor;
|
|
|
|
beforeEach(() => {
|
|
jest.clearAllMocks();
|
|
|
|
mockAgent = {
|
|
id: 'agent-123',
|
|
endpoint: EModelEndpoint.openAI,
|
|
provider: EModelEndpoint.openAI,
|
|
instructions: 'Test instructions',
|
|
model: 'gpt-4',
|
|
model_parameters: {
|
|
model: 'gpt-4',
|
|
},
|
|
};
|
|
|
|
mockReq = {
|
|
user: {
|
|
id: 'user-123',
|
|
personalization: {
|
|
memories: true,
|
|
},
|
|
},
|
|
config: {
|
|
memory: {
|
|
agent: {
|
|
id: 'agent-123',
|
|
},
|
|
},
|
|
endpoints: {
|
|
[EModelEndpoint.agents]: {
|
|
allowedProviders: [EModelEndpoint.openAI],
|
|
},
|
|
},
|
|
},
|
|
};
|
|
|
|
mockRes = {};
|
|
|
|
mockOptions = {
|
|
req: mockReq,
|
|
res: mockRes,
|
|
agent: mockAgent,
|
|
};
|
|
|
|
mockCheckAccess = require('@librechat/api').checkAccess;
|
|
mockLoadAgent = require('@librechat/api').loadAgent;
|
|
mockInitializeAgent = require('@librechat/api').initializeAgent;
|
|
mockCreateMemoryProcessor = require('@librechat/api').createMemoryProcessor;
|
|
});
|
|
|
|
it('should use current agent when memory config agent.id matches current agent id', async () => {
|
|
mockCheckAccess.mockResolvedValue(true);
|
|
mockInitializeAgent.mockResolvedValue({
|
|
...mockAgent,
|
|
provider: EModelEndpoint.openAI,
|
|
});
|
|
mockCreateMemoryProcessor.mockResolvedValue([undefined, jest.fn()]);
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
|
|
await client.useMemory();
|
|
|
|
expect(mockLoadAgent).not.toHaveBeenCalled();
|
|
expect(mockInitializeAgent).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
agent: mockAgent,
|
|
}),
|
|
expect.any(Object),
|
|
);
|
|
});
|
|
|
|
it('should load different agent when memory config agent.id differs from current agent id', async () => {
|
|
const differentAgentId = 'different-agent-456';
|
|
const differentAgent = {
|
|
id: differentAgentId,
|
|
provider: EModelEndpoint.openAI,
|
|
model: 'gpt-4',
|
|
instructions: 'Different agent instructions',
|
|
};
|
|
|
|
mockReq.config.memory.agent.id = differentAgentId;
|
|
|
|
mockCheckAccess.mockResolvedValue(true);
|
|
mockLoadAgent.mockResolvedValue(differentAgent);
|
|
mockInitializeAgent.mockResolvedValue({
|
|
...differentAgent,
|
|
provider: EModelEndpoint.openAI,
|
|
});
|
|
mockCreateMemoryProcessor.mockResolvedValue([undefined, jest.fn()]);
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
|
|
await client.useMemory();
|
|
|
|
expect(mockLoadAgent).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
agent_id: differentAgentId,
|
|
}),
|
|
expect.any(Object),
|
|
);
|
|
expect(mockInitializeAgent).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
agent: differentAgent,
|
|
}),
|
|
expect.any(Object),
|
|
);
|
|
});
|
|
|
|
it('should return early when prelimAgent is undefined (no valid memory agent config)', async () => {
|
|
mockReq.config.memory = {
|
|
agent: {},
|
|
};
|
|
|
|
mockCheckAccess.mockResolvedValue(true);
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
|
|
const result = await client.useMemory();
|
|
|
|
expect(result).toBeUndefined();
|
|
expect(mockInitializeAgent).not.toHaveBeenCalled();
|
|
expect(mockCreateMemoryProcessor).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('should create ephemeral agent when no id but model and provider are specified', async () => {
|
|
mockReq.config.memory = {
|
|
agent: {
|
|
model: 'gpt-4',
|
|
provider: EModelEndpoint.openAI,
|
|
},
|
|
};
|
|
|
|
mockCheckAccess.mockResolvedValue(true);
|
|
mockInitializeAgent.mockResolvedValue({
|
|
id: Constants.EPHEMERAL_AGENT_ID,
|
|
model: 'gpt-4',
|
|
provider: EModelEndpoint.openAI,
|
|
});
|
|
mockCreateMemoryProcessor.mockResolvedValue([undefined, jest.fn()]);
|
|
|
|
client = new AgentClient(mockOptions);
|
|
client.conversationId = 'convo-123';
|
|
client.responseMessageId = 'response-123';
|
|
|
|
await client.useMemory();
|
|
|
|
expect(mockLoadAgent).not.toHaveBeenCalled();
|
|
expect(mockInitializeAgent).toHaveBeenCalledWith(
|
|
expect.objectContaining({
|
|
agent: expect.objectContaining({
|
|
id: Constants.EPHEMERAL_AGENT_ID,
|
|
model: 'gpt-4',
|
|
provider: EModelEndpoint.openAI,
|
|
}),
|
|
}),
|
|
expect.any(Object),
|
|
);
|
|
});
|
|
});
|
|
});
|