mirror of
https://github.com/open-jarvis/OpenJarvis.git
synced 2026-07-29 18:40:38 +00:00
Jon Saad-Falcon
3777086d3a
Ollama's prompt_eval_count may exclude KV-cached tokens (system prompt, prior conversation turns), under-counting the prompt size used for cost/FLOPs/energy calculations and leaderboard submissions. Engine changes: - Add estimate_prompt_tokens() helper in engine/_base.py that computes cache-agnostic token count from message content - Ollama + OpenAI-compat engines now use max(reported, estimated) to ensure system prompt and full context are always counted Savings/leaderboard changes: - Add TOKEN_COUNTING_VERSION=2 to savings.py so frontends can tag Supabase submissions (old=v1, corrected=v2) - Desktop + web frontends forward version in leaderboard submissions - Add POST /v1/telemetry/reset endpoint to clear stale telemetry Active users auto-correct via upsert on next session; no manual Supabase migration required.