github alexgreensh/token-optimizer v5.1.0
Token Optimizer v5.1.0

latest releases: v5.8.8, v5.8.7, v5.8.6...
one month ago

Seven new bash compression handlers land in v5.1.0, covering the output families
that eat the most context in real sessions: lint (rule-code grouping), log tails
(adjacent-duplicate collapse), tree (depth-2 truncation), docker build/pull
progress, long listings (pip list, docker ps, npm ls — top-N plus tail marker),
JS/TS/Go build output (error-and-summary view), and test runners
(cypress/playwright/mocha/karma routed through the unified pytest compressor).

Compression classifiers are sharper across the board. Multilingual error lines in
12+ non-English languages now survive the preservation re-injection path. The git
status handler respects machine-readable format flags. The build handler produces
honest error counts on aggregate summary lines. Preserved-line re-injection uses
exact-line membership for precision.

Credential coverage gains an HTTP(S) basic-auth URL pattern alongside the existing
DB URI, JWT, PEM, and service-token families.

Lint gate: ruff clean, vulture clean at 80% confidence.
Benchmark: 57 fixtures, 57 passed, 0 failed, 56.9% overall compression ratio.

Don't miss a new token-optimizer release

NewReleases is sending notifications on new releases.