dograh/api/services/workflow/qa
Abhishek 7e2750f83f
fix: forward billing-v2 protocol on textchat KB retrieval and node summaries (#503)
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>
2026-07-06 22:58:53 +05:30
..
__init__.py feat: run per node QA 2026-02-25 17:17:48 +05:30
analysis.py fix: send correlation ID in QA analysis 2026-06-19 18:54:55 +05:30
conversation.py fix: safe parse timestamp 2026-02-25 22:59:19 +05:30
llm_config.py chore: finish renaming UserConfiguration 2026-06-09 16:30:03 +05:30
metrics.py feat: run per node QA 2026-02-25 17:17:48 +05:30
node_summary.py fix: forward billing-v2 protocol on textchat KB retrieval and node summaries (#503) 2026-07-06 22:58:53 +05:30
tracing.py feat: add chat based testing for voice agent (#308) 2026-05-21 15:20:02 +05:30