FTMahringer/Synapse
1
0
Fork 0
Code Issues 35 Pull requests Projects Releases 152 Packages Wiki Activity Actions
152 releases 174 tags
  • v1.3.5-dev ddf1ab9df3

    v1.3.5-dev - Response metadata tracking Pre-release

    FTMahringer released this 2026-05-08 23:48:45 +02:00 | 258 commits to main since this release

    Response Metadata Persistence

    Tracks provider, model, latency, and token breakdown for AI responses.

    Features:

    • New message columns: provider_id, model_name, latency_ms, prompt_tokens, completion_tokens
    • Message entity with full metadata fields
    • MessageService captures response timing and token counts

    Database Schema:

    • V3 migration adds 5 columns to messages table
    • FK to model_providers for analytics
    • Index on provider_id for queries

    Metadata Fields:

    • Provider ID: Which provider generated response
    • Model name: Specific model (e.g., llama3.2)
    • Latency (ms): API call duration
    • Prompt tokens: Context token count
    • Completion tokens: Generated token count
    • Total tokens: prompt + completion

    Use Cases:

    • Cost tracking by provider/model
    • Performance analytics
    • Token usage reports
    • Provider comparison

    Part of v1.4.0 Chat Runtime milestone (step 5/7).

    Downloads