Fran Jurmanović 6f0300f038 Fix Langfuse usage tracking: map to snake_case keys it recognizes ...

LangfuseTracer was passing our internal camelCase usage fields
(promptTokens/completionTokens/totalTokens) straight through as
usageDetails. Langfuse only recognizes a flat schema (input/output/...)
or OpenAI's native snake_case schema (prompt_tokens/completion_tokens/
total_tokens) for usage/cost calculation - anything else is silently
ignored, so every generation was showing zero usage regardless of
what LlmClient actually reported.

Note: cost still requires a price-list entry for the model name.
Langfuse's built-in list only covers hosted providers (OpenAI,
Anthropic, Google); self-hosted models (e.g. LLM_MODEL=llama3 via
Ollama) need a custom model price added in Project Settings > Models
for a $ figure to show up, even with token counts now correct.

Verified: full suite (80/80) passing, tsc/eslint clean.

2026-08-12 23:00:04 +02:00

..

app

Group pipeline runs into Langfuse sessions, tagged by trigger source

2026-08-12 22:51:17 +02:00

core

Fix Langfuse usage tracking: map to snake_case keys it recognizes

2026-08-12 23:00:04 +02:00