mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-07-07 11:02:12 +02:00
7e2750f83f
Two call sites dropped the MPS billing-v2 protocol, so orgs on model config v2 got 400 "Service Key uses billing v2" from MPS: - text_chat_runner built PipecatEngine without embeddings_provider (extracted but never passed), so knowledge-base retrieval fell through to the plain OpenAI-compatible client instead of DograhEmbeddingService and sent no correlation_id/mps_billing_version metadata. Also pass endpoint/api_version for Azure BYOK parity with run_pipeline. - node_summary built its QA LLM without the run's correlation id, unlike its sibling call in qa/analysis.py. Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| node_specs | ||
| qa | ||
| tools | ||
| __init__.py | ||
| audit.py | ||
| dto.py | ||
| duplicate.py | ||
| errors.py | ||
| layout.py | ||
| mcp_tool_session.py | ||
| node_data.py | ||
| pipecat_engine.py | ||
| pipecat_engine_callbacks.py | ||
| pipecat_engine_context_composer.py | ||
| pipecat_engine_context_summarizer.py | ||
| pipecat_engine_custom_tools.py | ||
| pipecat_engine_variable_extractor.py | ||
| run_usage_response.py | ||
| text_chat_logs.py | ||
| text_chat_runner.py | ||
| text_chat_session_service.py | ||
| trigger_paths.py | ||
| workflow_graph.py | ||