fix: 4238 - fix default max_tokens set on remote models #4266
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Outdated suggestions cannot be applied.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.
Describe Your Changes
I've resolved the issue where it sets the default context_length as the first value for max_tokens.
Fixes Issues
max_tokens
, preventing users from using some remote models #4238Changes made
models.json
:max_tokens
parameter above thetemperature
parameter for better grouping in two sections of the file.ModelDropdown/index.tsx
:overriddenParameters
:ctx_len
to beundefined
ifisLocalEngine
returnsfalse
, otherwise usedefaultContextLength
.max_tokens
to use either the model'smax_tokens
ordefaultContextLength
based on whetherisLocalEngine
returnsfalse
.useCreateNewThread.ts
:isLocalEngine
.overriddenSettings
andoverriddenParameters
:ctx_len
to behave similarly to the changes inModelDropdown/index.tsx
.max_tokens
to use either the model'stoken_limit
ordefaultContextLength
based on whetherisLocalEngine
returnsfalse
.modelEngine.ts
:isLocalEngine
handle anundefined
engine
by returningfalse
, ensuring safety against calling the method with anull
or undefined value.