# LiteLLM v1.101.0-dev.2

- Product: LiteLLM (https://whatsnew.fyi/product/litellm)
- Vendor: BerriAI
- Date: 2026-09-03
- Version: v1.101.0-dev.2
- Original notes: https://github.com/BerriAI/litellm/releases/tag/v1.101.0-dev.2
- Permalink: https://whatsnew.fyi/product/litellm/releases/v1.101.0-dev.2
- Labels: Pre-release

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **security** — All LiteLLM Docker images are now signed with cosign for signature verification
- **fixed** — Render the logs Tools panel with theme tokens in UI
- **fixed** — Default max_idle_connection_lifetime to 60s on DB URLs in proxy
- **fixed** — Follow tools/list pagination from upstream servers in MCP
- **fixed** — Resolve router model aliases in /utils/supported_openai_params
- **fixed** — Flatten top-level tool schema combinators on Azure chat completions
- **fixed** — Route streamed responses-API output through the unified guardrail in Bedrock
- **fixed** — Hide model write affordances from view-only admin sessions in UI
- **fixed** — Quote the Claude Code apiKeyHelper for cmd.exe on Windows in CLI
- **fixed** — Guarantee max_parallel_requests slot release when streaming logging fails
- **added** — Slack alerts for per-user daily/monthly spend thresholds and spend anomaly detection
- **fixed** — Add public Wolfi apk repo to runtime image in Docker
- **fixed** — Keep order fallback on the requested order level in router
- **fixed** — Reject known estimates over remaining budget under fail_closed_budget_enforcement
- **fixed** — Stop a cleared Team field from blocking personal key creation
- **added** — Fall back on anthropic safeguard refusals on /v1/messages in router
- **fixed** — Report requested model on Anthropic streaming message_start in proxy
- **fixed** — Reuse the generated master key Secret on helm upgrade
- **fixed** — Report per-server outcomes in aggregate REST tools/list in MCP
- **fixed** — Retry transient boot fetch failures and recover config deployments dropped by a stale cost map

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**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:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.101.0-dev.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:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.101.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.101.0-dev.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
* test: exempt MockTransport request-shape embedding tests from VCR replay by @mateo-berri in https://github.com/BerriAI/litellm/pull/39185
* fix(ui): render the logs Tools panel with theme tokens by @yuneng-berri in https://github.com/BerriAI/litellm/pull/39129
* fix(proxy): default max_idle_connection_lifetime to 60s on DB URLs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39134
* fix(mcp): follow tools/list pagination from upstream servers by @yucheng-berri in https://github.com/BerriAI/litellm/pull/39172
* fix(proxy): resolve router model aliases in /utils/supported_openai_params by @mateo-berri in https://github.com/BerriAI/litellm/pull/39000
* fix(azure): flatten top-level tool schema combinators on Azure chat completions by @mateo-berri in https://github.com/BerriAI/litellm/pull/38870
* fix(bedrock): route streamed responses-API output through the unified guardrail by @mateo-berri in https://github.com/BerriAI/litellm/pull/38734
* fix(ui): hide model write affordances from view-only admin sessions by @mateo-berri in https://github.com/BerriAI/litellm/pull/38872
* fix(cli): quote the Claude Code apiKeyHelper for cmd.exe on Windows by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39174
* fix(logging): guarantee max_parallel_requests slot release when streaming logging fails by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39093
* feat(alerting): slack alerts for per-user daily/monthly spend thresholds and spend anomaly detection by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38438
* fix(docker): add public Wolfi apk repo to runtime image by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39033
* fix(router): keep order fallback on the requested order level by @emerzon in https://github.com/BerriAI/litellm/pull/38969
* test(e2e): cover retry-on-timeout and the context-window fallback by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39197
* fix(budget): reject known estimates over remaining budget under fail_closed_budget_enforcement by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39214
* fix: stop a cleared Team field from blocking personal key creation by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39206
* test: record each e2e test's source location in the JUnit report by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39209
* feat(router): fall back on anthropic safeguard refusals on /v1/messages by @tin-berri in https://github.com/BerriAI/litellm/pull/39157
* fix(proxy): report requested model on Anthropic streaming message_start by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35816
* fix(helm): reuse the gen

_[Truncated at 4000 characters — full notes: https://github.com/BerriAI/litellm/releases/tag/v1.101.0-dev.2]_