build(deps): Bump litellm from 1.85.0 to 1.94.0

[dependabot]

Bumps litellm from 1.85.0 to 1.94.0.

Release notes

Sourced from litellm's releases.

v1.94.0

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:v1.94.0

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:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.94.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.94.0

Expected output:

The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key

---

What's Changed

• feat(ui): working Test Connection for the complexity auto router by @​akapur99 in BerriAI/litellm#32950
• fix(xecguard): use StandardLoggingGuardrailInformation in logging hook by @​yucheng-berri in BerriAI/litellm#32911
• feat(ui): adopt openapi-react-query ($api) and convert useCustomers by @​ryan-crabbe-berri in BerriAI/litellm#32949
• refactor(ui): colocate the mcp-servers view, keeping the shared mcp_tools surface by @​ryan-crabbe-berri in BerriAI/litellm#32968
• refactor(ui): convert endpoint usage charts to shadcn/recharts by @​ryan-crabbe-berri in BerriAI/litellm#32723
• fix(proxy-auth): stop unrecognized model namespaces slipping through provider wildcard keys by @​mateo-berri in BerriAI/litellm#32979
• feat(router): random-pick multi-model complexity tiers by @​krrish-berri-2 in BerriAI/litellm#32967
• fix(xecguard): sanitize scan result before recording it for logging by @​yucheng-berri in BerriAI/litellm#32935
• fix(auto_router): filter embedding models in complexity tab dropdowns, require all tiers, inline validation by @​akapur99 in BerriAI/litellm#32978
• fix(anthropic): translate raw adaptive thinking for pre-4.6 models on chat completions and Bedrock Converse by @​akapur99 in BerriAI/litellm#32944
• feat(router): add Router(plugins=[...]) routing-plugin pipeline by @​krrish-berri-2 in BerriAI/litellm#32972
• feat(router): soft-floor adaptive mode for complexity router by @​krrish-berri-2 in BerriAI/litellm#32947
• docs(github): add QA runbook section to the PR template by @​mateo-berri in BerriAI/litellm#32965
• fix(model_cost): add supports_reasoning: false to Gemini image generation models by @​mateo-berri in BerriAI/litellm#32836
• build(dev-env): add make bootstrap and unprovisioned-checkout preflight to pre-commit by @​mateo-berri in BerriAI/litellm#32981

... (truncated)

Commits

• 38f2e02 Merge pull request #34995 from BerriAI/litellm_/cost-optimization-savings-pr-...
• 4d06852 chore: update Next.js build artifacts (2026-07-28 19:58 UTC, node v20.20.2)
• 7880e61 Merge pull request #34994 from BerriAI/litellm_/cost-optimization-savings-pr-...
• 99618fb feat(cost-optimization): anchor the savings line at a $0 range start
• 3322f24 fix(cost-optimization): replace savings methodology Collapse with per-card in...
• d3c8e5a Merge pull request #34982 from BerriAI/litellm_/release-ui-build-1-94-0-ff6e5a
• 1e85794 chore: update Next.js build artifacts (2026-07-28 19:23 UTC, node v20.20.2)
• 96103c9 Merge pull request #34987 from BerriAI/litellm_/cherry-pick-34984-rc-1-94-0-7...
• 3db78a8 feat(ui): mark Cost Optimization as beta in the left nav (#34984)
• 81ab74e Merge pull request #34967 from BerriAI/litellm_rc194_cost_optimization_page_m...
• Additional commits viewable in compare view