Skip to content

build: lift the litellm cap; 1.109 fixed the mcp import it was for - #687

Merged
rejojer merged 1 commit into
mainfrom
build/litellm-1109
Nov 18, 2026
Merged

rejojer merged 1 commit into
mainfrom
build/litellm-1109

Conversation

@rejojer

@rejojer rejojer commented Nov 18, 2026

Copy link
Copy Markdown
Member

Installs get current LiteLLM again instead of staying on 1.105, and own-model chat keeps working with an older mcp: the <1.106 cap gives way to litellm>=1.109.0.

LiteLLM 1.106 through 1.108.3 import the proxy MCP handler on every call with tools, and that import fails under mcp<2.2 (BerriAI/litellm#46045). 1.108.4 and 1.109.0 onward import it only for a gateway tool (#45961). Every broken release, 1.107.0 included, sits below the new floor, so no != list and no upper bound are needed. Fresh installs move to openai 3 and openai-agents 0.25.

Changes

  • pyproject.toml, requirements.txt: litellm>=1.109.0, cap and its comments gone.
  • Kept for an install below the floor (another package can pin litellm lower, and pip lets the last install win): _drop_repeated_thinking, and the Claude "none" ladder and Databricks fill, which 1.110 makes redundant but 1.109 still needs. Two comments now say which versions need them.
  • Removed the tripwire tests asserting LiteLLM still has those three bugs: 1.109 or 1.110 fixed each, so they fail on every version CI installs. The behaviour tests of the kept code stay.
  • New direct test for _drop_repeated_thinking with both stream shapes, since no LiteLLM in range produces the repeat any more.
  • ModelSettings.timeout (openai-agents 0.25) added to the settings samples; LitellmModel does not forward it.
  • From 1.109 LiteLLM passes an unknown Bedrock model's reasoning_effort through instead of dropping it, so the summary ladder tries it; the test expects that now.

Verification

  • A real gpt-6-luna chat with tools under mcp 1.30.0 works on litellm 1.109.0 and fails on 1.106.10 with the mcp hint.
  • Full suite on litellm 1.109.0 and 1.110.0: py3.13 with frameworks 1270 passed, 7 skipped; py3.10 without 1097 passed, 180 skipped.
  • The new test fails on two mutants of _drop_repeated_thinking (never blanks; blanks any closing text).

LiteLLM 1.106 through 1.108.3 import the proxy MCP handler on every call
with tools, and that import fails under mcp<2.2 (BerriAI/litellm#46045).
1.108.4 and 1.109.0 onward import it only for a gateway tool (#45961).
The floor is now 1.109.0 with no upper bound: 1.106.*, 1.107.* (1.107.0
was malware) and 1.108.0-1.108.3 all sit below it. Fresh installs move
to openai 3 and openai-agents 0.25.

Kept for an install below the floor (another package can pin litellm
lower, and pip lets the last install win): _drop_repeated_thinking, and
the Claude "none" ladder and Databricks fill, which 1.110 makes redundant
but 1.109 still needs.

Tests:
- The tripwires asserting LiteLLM still repeats streamed thinking, still
  sends Claude no thinking for "none", and still drops a Databricks switch
  beside "none" are removed: 1.109 or 1.110 fixed each, so they fail on
  every version CI installs. The behaviour tests of the kept code stay.
- No LiteLLM in range repeats streamed thinking any more, so
  _drop_repeated_thinking gets a direct test with both stream shapes.
- openai-agents 0.25 adds ModelSettings.timeout; LitellmModel does not
  forward it, so only the samples change.
- From 1.109 LiteLLM passes an unknown Bedrock model's reasoning_effort
  through instead of dropping it, so the summary ladder tries it.

Verified: a real gpt-6-luna chat with tools under mcp 1.30.0 works on
litellm 1.109.0 and fails on 1.106.10 with the mcp hint. Full suite on
litellm 1.109.0 and 1.110.0: py3.13 with frameworks 1270 passed, 7
skipped; py3.10 without 1097 passed, 180 skipped.
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 18, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-18T07:57:53.187579Z a303e3b PR opened
🔒 Security Review ✅ Completed 2026-11-18T07:58:08.645839Z a303e3b PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@rejojer
rejojer merged commit 340b853 into main Nov 18, 2026
10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant