Bump tokentoll action SHA pin to v0.6.1

v0.6.1 reverts the v0.6.0 special-case that silently skipped
AzureChatOpenAI(deployment_name=...) calls. Those calls now flow
through the standard dynamic-default path like every other unresolved
model, restoring consistency with the rest of the SDK detectors. The
new skip_dynamic_models config option lets projects opt out of cost
estimation for dynamic models project-wide or per path.

Author: Jwrede

.github/workflows/llm-costs.yml

@@ -15,4 +15,4 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - uses: Jwrede/tokentoll@ff50a35604b7858d9064cca6354b6229a94f7235  # v0.6.0
+      - uses: Jwrede/tokentoll@753ca4d1150c74169b52a843439049b65e256d2b  # v0.6.1