[dependabot]

Bumps litellm from 1.96.2 to 1.106.1.

Release notes

Sourced from litellm's releases.

v1.106.1

Verify this release

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.106.1

Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images

What's new in 1.106.1

9 PRs. 6 fixed. 1 needs action

Action required

• Vector stores: Run db_scripts/strip_vector_store_internal_metadata.py to fix stores created before this release (#47021)

Changes

• Anthropic: Fixed signed thinking blocks and thinking.block_binding being dropped on multi-turn requests (#41362, #46342) Also in 1.105.2
• Chat completions: Fixed tool calls landing on choices[1] with gpt-5.4+ models, broken since v1.97.0 (#46099) Also in 1.105.2
• Batches and files: Fixed 403 when team keys retrieve, cancel or download their own batches (#47067) Also in 1.105.2
• Vector stores: Fixed HTTP 400 on metadata updates caused by keys the proxy added to the store (#47021)
• Token counting: Fixed undercounted PDFs, system prompts and tools, and rejected Google countTokens requests (#47389, #47446, #47454) Also in 1.104.4, 1.105.2
• MCP: Fixed Tool not found when calling a bare tool name on /{server}/mcp, broken since v1.103.0 (#46225)

---

Backport #47517 · Full changelog

v1.106.0

Verify Docker Image Signature

All LiteLLM Docker images are signed with cosign. Every release is signed with the same key introduced in commit 0112e53.

Verify using the pinned commit hash (recommended):

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.106.0

Verify using the release tag (convenience):

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

... (truncated)

Commits

• 978b4d1 Merge pull request #47517 from BerriAI/patch_4fe6df3e
• 207148f style(openai): drop the unused Any import from the responses count handler
• 1e23ad4 fix(anthropic): forward thinking.block_binding only from the exact Anthropic,...
• e46904b fix(anthropic): carry only thinking.block_binding through the legacy thinking...
• 1fe5581 chore: bump litellm 1.106.0 -> 1.106.1
• 699e79c Merge pull request #47454 from BerriAI/litellm_restore_token_count_input_prec...
• 98d702f Merge pull request #47446 from BerriAI/litellm_backport_google_count_shapes_s...
• 9781763 Merge pull request #47389 from BerriAI/litellm_backport_count_tokens_stable_1...
• 07f72a6 fix(proxy): authorize the public name of a team-scoped model on batch retriev...
• da5b2b5 fix(vector-stores): keep proxy context out of provider vector store metadata ...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ All tests successful. No failed tests found.

📢 Thoughts on this report? Let us know!

[dependabot]

Superseded by #58.