fix(container): update image ghcr.io/berriai/litellm-database (v1.103.0 → v1.103.2)

[banjo-bot]

This PR contains the following updates:

Package	Update	Change
ghcr.io/berriai/litellm-database (source)	patch	v1.103.0 → v1.103.2

---

Release Notes

BerriAI/litellm (ghcr.io/berriai/litellm-database)

v1.103.2

Compare Source

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:v1.103.2

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/v1.103.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.103.2

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

• chore(release): sync stable/1.103.x to v1.103.1 by @​yuneng-berri in #​43824
• fix(proxy): backport #​40541, #​43642, and #​43656 to stable/1.103.x for v1.103.2 by @​devin-ai-integration[bot] in #​43897
• fix(anthropic): backport #​42152 and #​42288 to stable/1.103.x by @​devin-ai-integration[bot] in #​43662
• fix(proxy): backport #​43962 to stable/1.103.x by @​yuneng-berri in #​43984

Full Changelog: BerriAI/litellm@v1.103.1...v1.103.2

v1.103.1

Compare Source

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:v1.103.1

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/v1.103.1/cosign.pub \
  ghcr.io/berriai/litellm:v1.103.1

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

---

Full Changelog: BerriAI/litellm@v1.103.0...v1.103.1

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • "every weekend"
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

---

• If you want to rebase/retry this PR, check this box

---

This PR has been generated by Mend Renovate CLI.

[banjo-bot]

Verdict: Safe to merge

Reviewed the patch bump v1.103.0 → v1.103.2 (spans v1.103.1 and v1.103.2). The diff itself only changes the image tag/digest in kubernetes/apps/llm/litellm/app/litellmproxy.yaml.

Checked every backported fix listed in the two releases against this repo's LiteLLM config (kubernetes/apps/llm/litellm/app/*.yaml):

• fix(spend): attribute CLI session spend to the per-user cli-session alias instead of the hashed session token BerriAI/litellm#40541, #43642, #43656 — CLI session (litellm-proxy login) spend/usage attribution fixes. Not applicable; this proxy has no CLI-session usage path, only virtual keys.
• fix(anthropic): forward safeguards and anthropic-beta unchanged on native /v1/messages BerriAI/litellm#42152, #42288 — forward Claude Code safeguards/dangerous-tool-use beta on anthropic, bedrock, bedrock_mantle, and vertex_ai routes. Not applicable; all configured models here are openai/llama-strix (local llama.cpp) and infinity/memini-rerank — no Anthropic/Bedrock/Vertex backends.
• fix(proxy): restore pre-config-wins handling of pass-through endpoints BerriAI/litellm#43962 — restores pre-#41779 handling of general_settings.pass_through_endpoints when STORE_MODEL_IN_DB=true. Not applicable; generalSettings.store_model_in_db: false is set here and no pass_through_endpoints are configured.

No removed/renamed flags or env vars affect this config, and no comment-documented tuning decisions in this repo's manifests reference anything touched by these releases.

Sources consulted:

• https://github.com/BerriAI/litellm/releases/tag/v1.103.2
• https://github.com/BerriAI/litellm/releases/tag/v1.103.1
• https://github.com/BerriAI/litellm/pull/43897
• https://github.com/BerriAI/litellm/pull/43662
• https://github.com/BerriAI/litellm/pull/43984
• https://github.com/BerriAI/litellm/pull/42152
• https://github.com/BerriAI/litellm/pull/42288
• https://github.com/BerriAI/litellm/pull/43962

🤖 Generated with Claude Code