Skip to content

Tokentoll

v0.6.1 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

anthropic cost-optimization devtools github-action llm mlops
+3 more
openai python static-analysis

Summary

AI summary

Updates default, Upgrade ```yaml, and path across a mixed release.

Full changelog

Summary

Reverts the v0.6.0 special-case that skipped AzureChatOpenAI(deployment_name=...) calls. The skip was inconsistent: every other dynamic model gets a per-SDK default with a (default) label, only Azure was being silently dropped. v0.6.1 restores symmetry and adds an opt-in for users who want stricter behavior.

Changes

New: skip_dynamic_models config option

Set in .tokentoll.yml to suppress cost estimates for any call whose model name cannot be resolved statically:

skip_dynamic_models: true

Also supported as a per-path override:

overrides:
  - path: src/azure/
    skip_dynamic_models: true

When enabled, dynamic-model calls are still detected and listed but reported with no cost rather than priced against a default.

LangChain detector

AzureChatOpenAI(deployment_name=...) and AzureChatOpenAI(azure_deployment=...) calls without an explicit model= argument now flow through the standard dynamic-default path (priced as gpt-4o (default) unless overridden). Use the new skip_dynamic_models option to suppress these.

Upgrade

- uses: Jwrede/[email protected]

pip install --upgrade tokentoll
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Tokentoll

Get notified when new releases ship.

Sign up free

About Tokentoll

All releases →

Related context

Beta — feedback welcome: [email protected]