Findings
-
[1] 2026-09-29 v0.35.0
Decision models Ollama now supports decision models through /v1/systemone, based on TypeSafe’s Jev API. Decision models return choices, probabilities, and scores instead of text. Use them for tasks such as ticket triage, model routing, and content classification. Available models: Nimble from Bespoke Labs Tev1 from Together AI ollama pull nimble Send context and one or more questions: curl http://localhost:11434/v1/systemone …
-
[2] 2026-09-28 langchain-fireworks==1.7.0
Changes since langchain-fireworks==1.6.3 hotfix(fireworks): replace unavailable integration test model (#40890) release(fireworks): 1.7.0 (#40889) feat(fireworks): add prompt caching middleware (#38823) fix(fireworks): classify mid-stream read timeouts (#40874) chore(model-profiles): refresh model profile data (#40833)
-
[3] 2026-09-28 v0.35.0
mlx: bound pull stall retries and let the watchdog interrupt them (#1…
-
[4] 2026-09-28 v0.35.0-rc0
feat: add System One scoring API (#18606)
-
[5] 2026-09-28 langchain==1.4.3
Changes since langchain==1.4.2 release(langchain): 1.4.3 (#40888) fix(langchain): sanitize cache settings for fallback models (#40886) feat(langchain): support Bedrock Mantle chat models in init_chat_model (#40837) fix(langchain): recognize GPT-6 structured output without profiles (#40844) docs(infra): fix AGENTS.md root setup guidance and package doc accuracy (#40794) fix(langchain): repair invalid tool calls in create_agent (#40530) chore(langchain): remove commented-out cohere extra (#40713) chore(deps): bump anyio from…
-
[6] 2026-09-28 v1.104.0-rc.1
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:v1.104.0-rc.1 Verify…
-
[7] 2026-09-28 v1.103.0
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… fix(responses): translate the reasoning object into a chat-completion reasoning effort by @joshgarnett in #36363 fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets by @devin-ai-integration[bot] in #40561 fix(mcp): require admission for delegated OAuth by @joshua-berri in #40923… from response metadata when routes omit call_id by @devin-ai-integration[bot] in #41056 chore(prices): sync Vertex AI prices: 14 models by @berriai-litellm-provider-info-sync[bot] in #40955 ci(codeql): exclude noisy Python quality queries by @yuneng-berri in #41142 feat(proxy): predict prompt-cache costs across deployments by @tin-berri… _proxy_failed_requests_metric by @devin-ai-integration[bot] in #41170 test: drop tests that pin vendor facts and add the CLAUDE.md rule by @devin-ai-integration[bot] in #41269 fix(proxy): run the remaining inline token counts off the event loop by @devin-ai-integration[bot] in #40262 fix(proxy): log blocked streaming… ix(xai): keep 'instructions' on the xAI Responses API so system messages survive web search by @devin-ai-integration[bot] in #38254 feat(ui): configure capability and Fuse v2 classifiers by @tin-berri in #41315 fix(anthropic): tolerate message_delta events without usage when streaming by @devin-ai-integration[bot] in… fail closed on missing upstream credentials by @joshua-berri in #41364 feat(rust): scaffold Redis cache crate by @devin-ai-integration[bot] in #41501 fix(dashscope): forward reasoning_effort to the provider by @devin-ai-integration[bot] in #37506 fix(proxy): carry litellm_call_id through endpoint specific error logs and failure responses…
-
[8] 2026-09-28 1.64.1.dev20260927
Streamlit nightly 1.64.1.dev20260927
Where Kimbodo Comes In
Kimbodo builds and operates this in production for businesses — see our AI Application Development practice, or Estimate My AI Application.
Sources
- [1] v0.35.0
- [2] langchain-fireworks==1.7.0
- [3] v0.35.0
- [4] v0.35.0-rc0
- [5] langchain==1.4.3
- [6] v1.104.0-rc.1
- [7] v1.103.0
- [8] 1.64.1.dev20260927