Commit graph

5 commits

Author SHA1 Message Date
Marco Beretta
227a99ede8
🧮 fix: Render Google Settings From the Shared Schema and Bound Them Per Model (#14989)
* fix: render Google settings from the shared schema and bound them correctly

Google was the last endpoint hand-rolling its own sliders. The schema was
already there and already wired, only the frontend never used it, so
rendering from it replaces 315 lines with the body OpenAI, Anthropic and
Bedrock share.

That closed a functional gap rather than only moving code: the old form
exposed six fields where the schema declares fifteen, so Resend Files,
Thinking, Thinking Budget, Thinking Level, Grounding with Google Search,
URL Context and File Token Limit were unreachable from a Google preset.
resendFiles is added to the Google schema so its switch round-trips, and
the endpoint type is resolved from the endpoints config, since a preset
for a Google-compatible endpoint need not carry endpointType and would
otherwise blank the panel.

Sharing the controls also meant inheriting their gaps, which this fixes:

- Number settings declared a range that nothing enforced, so a value past
  the provider's ceiling was persisted and rejected later. clampSettingRange
  applies it, and generateDynamicSchema validates the same rule, so the
  definition is the single source of truth for both.
- Thinking budget bounds are per model. The generic range capped 2.5 Pro
  below its documented 32,768 and admitted Flash values above 24,576.
  positiveMin carries the documented floors while -1 stays typeable as the
  decide-automatically sentinel.
- Ranges the model narrowed are marked modelSpecific, so a switch to a
  model that ignores the parameter cannot rewrite a value set for another.
- useDebouncedInput rebuilt its debouncer every render, because neither
  setOption nor the inline setter is memoized, so pending edits were never
  really superseded and a flush reached an instance holding nothing. The
  callbacks move to refs, and the text and slider controls flush on blur or
  value commit so Save and Export cannot read a stale preset.
- Controls reset to their definition default on a conversation or preset
  change and only recovered ~560ms later, which showed saved values as
  defaults and could write the default back.

The debounce regression test fails against the previous memo dependencies
and passes with the refs, so the flush is verified rather than assumed.

* fix: keep the context token bounds on the Google setting

The bounds came from the hand-rolled Google editor, but they were added to
the shared definition every endpoint renders, so blurring the field clamped
OpenAI, Anthropic, Bedrock and custom endpoints to a window that is only
Gemini's. Custom endpoints may declare context windows outside it.

* fix: agree with the generated schema across the sentinel gap

A stored value between range.min and zero passed through clampSettingRange
unchanged, though the schema admits only the sentinel or the positive floor,
so normalization could preserve a value the provider then rejects. Validate
a configured default against the same rule.

* fix: keep positiveMin on configured parameter definitions

The runtime schema for customParams.paramDefinitions retained only min, max
and step, so a configured positive floor was stripped before the UI saw it
while the shared SettingRange type advertised it.

* fix: commit a double-click slider reset immediately

The browser dispatches dblclick after the second pointer release, so the
value commit has already flushed and the reset sat in the debouncer. Saving
or exporting inside that window read the value the slider no longer showed.

* fix: normalize an out-of-range stored value on mount

The applied-range ref started at the first range, so the effect returned
immediately and a budget saved under the shared range stayed displayed and
savable when the selected model no longer allowed it.

* fix: normalize on navigation and keep sliders out of the sentinel gap

The parameters panel stays mounted across conversations, so a legacy budget
could arrive under a range that never changed; keying the normalization on
the conversation or preset identity as well catches it. After a navigation
the local value still belongs to the conversation being left, so the
incoming stored value is what gets normalized.

A slider steps straight through the gap between a sentinel minimum and its
positive floor, which the generated schema rejects, so the committed value
is clamped. It is also set before the flush: the keyboard path commits
before it reports the change, so the flush alone had nothing to write.

* fix: close the remaining paths into the sentinel gap

Applying a preset over the open conversation replaces the stored value
without changing the conversation id or the model, so normalization now also
triggers on a stored value that arrives differing from the local one. A
value the user typed reaches the conversation through this same field and
matches by the time it lands, so it stays on the blur-clamped path.

The slider's adjacent number input only flushed on blur, so a typed value
could sit in the gap the track is now kept out of.

A configured positiveMin above the maximum admits nothing but the sentinel
while the clamp maps every non-negative input onto a maximum the generated
schema rejects, so both the config schema and the definition validator
refuse it.

* fix: keep a non-negative sentinel and a loadable slider default

The minimum is the sentinel whatever its sign, and the generated schema
admits it outright, so a range like { min: 0, positiveMin: 10 } no longer
has its 0 lifted to the floor by the clamp.

The synthesized slider default took the midpoint of the whole range, which
for a sentinel range lands in the gap the validation added alongside it, so
an otherwise coherent custom definition failed to load. It now takes the
midpoint of the admissible interval.

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2026-08-25 21:21:28 -04:00
Danny Avila
f869d772f7
🪐 feat: Initial OpenAI Responses API Support (#8149)
* chore: update @librechat/agents to v2.4.47

* WIP: temporary auto-toggle responses api for o1/o3-pro

* feat: Enable Responses API for OpenAI models

- Updated the OpenAI client initialization to check for the useResponsesApi parameter in model options.
- Added translations for enabling the Responses API in the UI.
- Introduced useResponsesApi parameter in data provider settings and schemas.
- Updated relevant schemas to include useResponsesApi for conversation and preset configurations.

* refactor: Remove useResponsesApi check from OpenAI client initialization and update translation for Responses API

- Removed the check for useResponsesApi in the OpenAI client initialization.
- Updated the translation for enabling the Responses API to clarify its functionality.

* chore: update @librechat/agents dependency to version 2.4.48

* chore: update @librechat/agents dependency to version 2.4.49

* chore: linting

* chore: linting

* feat: Enhance DynamicSlider and validation for enumMappings

- Added support for enumMappings in DynamicSlider to display values correctly based on enum settings.
- Implemented validation for enumMappings in the generate function to ensure all options have corresponding mappings.
- Added tests for handling empty string options and incomplete enumMappings in the generate.spec.ts file.

* feat: Enhance DynamicSlider localization support

- Added localization handling for mapped values in DynamicSlider when using enumMappings.
- Updated the logic to check if the mapped value is a localization key and return the localized string if applicable.
- Adjusted dependencies in useCallback hooks to include localize for proper functionality.

* feat: Add reasoning summary and effort options to OpenAI configuration and UI

* feat: Add enumMappings for ImageDetail options in parameter settings

* style: Improve styling for DynamicSlider component labels and inputs

* chore: Update reasoning effort description and parameter order for OpenAI params

---------

Co-authored-by: Dustin Healy <dustinhealy1@gmail.com>
2025-06-30 18:34:47 -04:00
Danny Avila
099aa9dead
✋ feat: Stop Sequences for Conversations & Presets (#2536)
* feat: `stop` conversation parameter

* feat: Tag primitive

* feat: dynamic tags

* refactor: update tag styling

* feat: add stop sequences to OpenAI settings

* fix(Presentation): prevent `SidePanel` re-renders that flicker side panel

* refactor: use stop placeholder

* feat: type and schema update for `stop` and `TPreset` in generation param related types

* refactor: pass conversation to dynamic settings

* refactor(OpenAIClient): remove default handling for `modelOptions.stop`

* docs: fix Google AI Setup formatting

* feat: current_model

* docs: WIP update

* fix(ChatRoute): prevent default preset override before `hasSetConversation.current` becomes true by including latest conversation state as template

* docs: update docs with more info on `stop`

* chore: bump config_version

* refactor: CURRENT_MODEL handling
2024-04-25 11:40:17 -04:00
Danny Avila
c19dfddd0f
👷 fix: Minor Fixes and Refactors (#2388)
* refactor(useTextarea): set Textarea disabled message due to key higher in priority

* fix(SidePanel): intended behavior for non-user provided keys

* fix: generate specs

* style: update combobox styling as before, with better dynamic height

* chore: remove unused import
2024-04-11 02:12:48 -04:00
Danny Avila
8e5f1ad575
📦 feat: Model & Assistants Combobox for Side Panel (#2380)
* WIP: dynamic settings

* WIP: update tests and validations

* refactor(SidePanel): use hook for Links

* WIP: dynamic settings, slider implemented

* feat(useDebouncedInput): dynamic typing with generic

* refactor(generate): add `custom` optionType to be non-conforming to conversation schema

* feat: DynamicDropdown

* refactor(DynamicSlider): custom optionType handling and useEffect for conversation updates elsewhere

* refactor(Panel): add more test cases

* chore(DynamicSlider): note

* refactor(useDebouncedInput): import defaultDebouncedDelay from ~/common`

* WIP: implement remaining ComponentTypes

* chore: add com_sidepanel_parameters

* refactor: add langCode handling for dynamic settings

* chore(useOriginNavigate): change path to '/c/'

* refactor: explicit textarea focus on new convo, share textarea idea via ~/common

* refactor: useParameterEffects: reset if convo or preset Ids change, share and maintain statefulness in side panel

* wip: combobox

* chore: minor styling for Select components

* wip: combobox select styling for side panel

* feat: complete combobox

* refactor: model select for side panel switcher

* refactor(Combobox): add portal

* chore: comment out dynamic parameters panel for future PR and delete prompt files

* refactor(Combobox): add icon field for options, change hover bg-color, add displayValue

* fix(useNewConvo): proper textarea focus with setTimeout

* refactor(AssistantSwitcher): use Combobox

* refactor(ModelSwitcher): add textarea focus on model switch
2024-04-10 14:27:22 -04:00