graphiti/graphiti_core/llm_client
supmo668 acd54afdef Clarify that max_tokens mapping represents standard limits
Updated comments to explicitly state that ANTHROPIC_MODEL_MAX_TOKENS
represents standard limits without beta headers. This prevents confusion
about extended limits (e.g., Claude 3.7's 128K with beta header) which
are not currently implemented in this mapping.
2025-11-03 17:53:00 -08:00
..
__init__.py
anthropic_client.py Clarify that max_tokens mapping represents standard limits 2025-11-03 17:53:00 -08:00
azure_openai_client.py Fix Azure structured completions (#1039) 2025-11-01 18:40:43 -07:00
client.py Add OpenTelemetry distributed tracing support (#982) 2025-10-05 12:26:14 -07:00
config.py Gpt 5 default (#849) 2025-08-21 12:10:57 -04:00
errors.py
gemini_client.py Add OpenTelemetry distributed tracing support (#982) 2025-10-05 12:26:14 -07:00
groq_client.py Refactor imports (#675) 2025-07-05 08:57:07 -07:00
openai_base_client.py feat: MCP Server v1.0.0 - Modular architecture with multi-provider support (#1024) 2025-10-30 22:59:01 -07:00
openai_client.py feat: MCP Server v1.0.0 - Modular architecture with multi-provider support (#1024) 2025-10-30 22:59:01 -07:00
openai_generic_client.py Remove JSON indentation from prompts to reduce token usage (#985) 2025-10-06 16:08:43 -07:00
utils.py