fix: omit temperature parameter when not explicitly set for OpenAI Compatible providers #7188
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
dosubot
bot
added
size:L
| const handlerWithModel = new GroqHandler({ apiModelId: modelId, groqApiKey: "test-groq-api-key" }) | ||
| const handlerWithModel = new GroqHandler({ | ||
| apiModelId: modelId, | ||
| groqApiKey: "test-groq-api-key", |
There was a problem hiding this comment.
Is this intentional? The temperature is set inline here (line 119) while in other tests it's part of the options object. Could we standardize this for better consistency?
| requestOptions.temperature = this.options.modelTemperature | ||
| } else if (deepseekReasoner) { | ||
| // DeepSeek Reasoner has a specific default temperature | ||
| requestOptions.temperature = DEEP_SEEK_DEFAULT_TEMPERATURE |
There was a problem hiding this comment.
The special handling for DeepSeek Reasoner models is well-implemented. Could we add a comment explaining why this model requires a specific default temperature? This would help future maintainers understand the reasoning behind this special case.
There was a problem hiding this comment.
I wonder if we don't need to send this anymore since we are letting the provider set it
hannesrudolph
added
the
Issue/PR - Triage
hannesrudolph
added
PR - Needs Preliminary Review
and removed
Issue/PR - Triage
…mpatible providers - Modified OpenAiHandler to only include temperature when modelTemperature is defined - Modified BaseOpenAiCompatibleProvider to only include temperature when modelTemperature is defined - Added tests to verify temperature is omitted when undefined - Updated existing tests to explicitly set temperature where needed This allows backend services (LiteLLM, vLLM) to use their configured default temperatures instead of being forced to use temperature=0 when "Use custom temperature" is unchecked. Fixes #7187
daniel-lxs
force-pushed
the
fix/openai-compatible-temperature-7187
branch
from
82062c2 to
a80ca11
Compare
- Remove temperature parameter expectations from provider tests - Tests now expect temperature to be omitted when not explicitly set - Aligns with PR #7188 changes to fix OpenAI Compatible provider behavior
daniel-lxs
moved this from PR [Needs Prelim Review]
to PR [Needs Review]
in Roo Code Roadmap
daniel-lxs
approved these changes
Aug 20, 2025
mrubens
approved these changes
Aug 21, 2025
github-project-automation
bot
moved this from PR [Needs Review]
to Done
in Roo Code Roadmap
daniel-lxs
added a commit
that referenced
this pull request
Sep 2, 2025
The requestOptions parameter was added after PR #7188, so tests need to be updated to not expect it after the revert
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR fixes an issue where the temperature parameter was always being sent with a value of 0.0 when "Use custom temperature" was unchecked in the OpenAI Compatible provider settings. This prevented backend services (like LiteLLM/vLLM) from using their configured default temperatures.
Problem
When configuring RooCode with an OpenAI Compatible Provider pointing at a LocalLLM (LiteLLM → vLLM stack):
temperature: 0.0(greedy decoding)Solution
Modified the temperature handling in two key places:
modelTemperatureis explicitly definedmodelTemperatureis explicitly definedSpecial case: DeepSeek Reasoner models still get their specific default temperature when not explicitly set.
Changes
src/api/providers/openai.tsto conditionally include temperaturesrc/api/providers/base-openai-compatible-provider.tsto conditionally include temperatureTesting
Fixes #7187
Important
Fixes temperature parameter handling in OpenAI Compatible providers to only include it when explicitly set, allowing backend defaults to be used.
OpenAiHandlerandBaseOpenAiCompatibleProvidernow only includetemperaturein requests ifmodelTemperatureis explicitly set.src/api/providers/openai.tsandsrc/api/providers/base-openai-compatible-provider.tsto conditionally includetemperature.temperatureis omitted when undefined and included when set inopenai.spec.ts,groq.spec.ts, and other test files.This description was created by
for 0b3c58b. You can customize this summary. It will automatically update as commits are pushed.