Summarize memory cards for a specific conversation. This creates a conversation-specific summary of relevant memory cards

Summarize long text content. Args: text: Text to summarize max_length: Target summary length use_llm: Whether to

* Switch ASR provider dynamically * @param {string} providerName - Provider name to switch to

Test that errors are properly formatted for the agent

Test basic conversation capabilities

Test basic agent functionality without API calls

Test basic functionality of the system

Test basic functionality of the system

Test basic agent functionality

Test BM25 scoring algorithm

Test browser tools (basic initialization).

Test that incorrect modes properly invalidate KV cache each iteration

Test that cached tokens are correctly parsed from API response

Test code interpreter integration

Test code interpreter functionality.

Test command execution tool

Test that the agent correctly handles responses without tool calls as final answers

Test configuration loading.

Test that conversation history persists between tasks

Test conversation mode with streaming

Test currency conversion tool

Test datetime parsing.

Test Doubao provider with a simple task

Test the dual memory system with a sample scenario

Test edge cases and special scenarios

Test that the agent continues when tools return errors

Test that errors are properly captured and formatted

Test evaluation dataset generation

Test evaluation dataset generation

Test the evaluation system with Layer 1 test cases

Test that the experiment runner works.

Test file edit functionality.

Test reading files with offset and size parameters

Test the local file system tools

Test file write functionality.

Test that the code interpreter has access to full Python environment

Test that the game environment works.

Test get_conversation_context with full logging

Test get_conversation_context with full logging

Test get_full_conversation with full logging

Test get_full_conversation with full logging

Test GitHub PR creation.

Test Google Calendar integration.

Test Agentic RAG with GraphRAG knowledge graph backend

Test and demonstrate the system hint behavior

Test human-in-the-loop functionality.

Test all imports work

Test all imports work

Test the modified indexer

Test the modified indexer

Test both RAPTOR and GraphRAG indexing with sample documentation.

Test component initialization

Test component initialization

Test 3: Intent matching algorithm.

Test inverted index functionality

Test 2: Knowledge base storage and retrieval.

Test a specific language.

Test that the LLM agent works (without API calls).

Test that LLM evaluation is properly integrated

Test that LLM evaluation is properly integrated

Test that LLM responses are properly logged

Test that LLM responses are properly logged

Test the interactive mode selection without running the agent

Test and display model information

Test Ollama's native tool calling

Test the new perception tools.

Test non-agentic mode with structured backends

Test notification tools (without actually sending).

Test direct API call to OpenRouter

Test various pattern matching scenarios

Test PDF parsing with currency conversion

Test 5: Performance improvement validation.

Test the complete retrieval pipeline.

Test the agent's ability to provide proactive service

Test switching between different providers

Test different provider configurations

Test a query against the system

Test the quality of search result ranking

Test Agentic RAG with RAPTOR tree-based backend

Test if retrieval pipeline is available and working

Test if retrieval pipeline is available and working

Test that the RL agent works.

Test that Q-learning can learn the game. Args: stochastic: If True, use stochastic environment episodes: List of episode coun

Test safety checks for file operations.

Test the complete search engine

Test search_memory tool with full logging

Test search_memory tool with full logging

Test that the server starts without deprecation warnings.

Test with a very simple task to check if the agent is working

Test evaluation with a single simple test case

Test the sparse service directly to ensure it handles external doc_ids.

Test retrieving specific documents by ID

Test streaming functionality with various queries

Test that code executes successfully with full Python environment

Test syntax verification.