Skip to content

v0.5.2 — first-run accuracy & polish

Choose a tag to compare

@anilmurty anilmurty released this 25 Jun 00:12
cce305e

TokenJam 0.5.2 — first-run accuracy & polish

Accuracy fixes (the headline)

  • Backfill no longer over-counts your spend. Claude Code sessions that were resumed or compacted were ingested 2–4× over — the same model calls re-counted under fresh message IDs. Token and cost figures (and everything derived from them) are now correct. If you backfilled before 0.5.2, wipe and re-run tj backfill claude-code to correct your historical numbers. (#294)
  • tj demo now works on installed versions. The incident scenarios were never packaged into the wheel, so tj demo listed nothing for pip/pipx users. Fixed — tj demo retry-loop runs out of the box. (#291)
  • Traces list raised to 200 by default, with "Showing N of M" + a Load more control. (#274)
  • tj budget --json for machine-readable budgets. (#281)

New capability

  • Full-request capture — sampling params and tools/tool_choice are now captured on LLM spans (gated by your [capture] settings). (#209)
  • Experimental enforcement-plane preview — an optional local proxy + policy engine (budget caps, routing/reuse policies) ships in suggest mode only: it shows what it would do and enforces nothing. Interfaces are unstable and off by default. (#219#223)

Docs & brand

  • Clearer contributing guide, Code of Conduct, refreshed dashboard screenshots, new black-on-white logo. (#289, #275, #273)

Thanks to our contributors 🙌

This release includes community contributions from @sanmaxdev (traces pagination #274, Code of Conduct #275) and @gitcommit90 (tj budget --json #281). Thank you!


Install: pipx install tokenjam
Full changelog: v0.5.1...v0.5.2