v0.5.0 — Lens Visualizations
TokenJam Lens grows from a single spend chart into a full visualization surface. This release ships the Lens Visualizations milestone — new ways to see where your tokens and dollars go, all offline, all plan-tier-honest.
Highlights
📊 Analytics pivot explorer — a new screen that turns one query into any view: pick a metric (spend / tokens / sessions / events), break it down by any dimension (model, agent, tool, day…), stack a second dimension, switch chart type, and export CSV. State lives in the URL, so any view is shareable and bookmarkable.
💸 Cost screen, deeper — stacked cost-by-model/agent breakdown over time, plus a cache-savings time-series showing cumulative captured savings against your cache hit-rate.
🔍 Optimize overview — cost-by-component with a recoverable-waste overlay, so the biggest savings opportunities surface at a glance.
✨ KPI sparklines + deltas — every Analytics headline tile now carries a trend sparkline and a period-over-period change vs. the prior window.
🧭 Trace waterfall, cost-first — the trace detail view annotates each span with cost and tokens alongside a magnitude bar, so you can see where the spend lands across a run.
🎨 Consistent coloring — one shared 12-hue color map gives every series the same color on every chart and screen; grouping by a time dimension no longer produces a confusing rainbow.
↪️ Deep-linked Overview — Overview tiles and the spend headline now click through into the Analytics explorer, pre-filtered to the relevant slice.
Honest by construction
Every dollar-bearing surface respects plan-tier framing: subscription users see token-share, never raw spend. Every estimate is "estimated recoverable," never "saved."
Docs
Install docs now lead with pipx install tokenjam (sidesteps PEP 668 on Homebrew/Debian/Ubuntu Python). The [mcp] extra is no longer needed — the MCP server ships in the base install.
Install
pipx install tokenjam # recommended
# or: pip install tokenjam (in a clean venv)Full changelog: v0.4.2...v0.5.0