webui: introduce OpenAI-compatible model selector in JSON payload #16562

ServeurpersoCom · 2025-10-13T13:31:34Z

Introduce OpenAI-compatible model selector in JSON payload

This PR adds a minimal model selector to the WebUI sidebar, allowing users to pick an available model exposed through the /v1/models OpenAI-compatible endpoint

The selector automatically fetches and lists models from the server, persists the selected model in local storage, and sends it in the JSON body of subsequent /v1/chat/completions requests. The selection logic mirrors OpenAI’s client behavior while remaining fully offline-compatible with local llama.cpp instances

This enables direct interoperability with OpenAI-compatible clients and simplifies multi-model setups in the WebUI

Restore OpenAI-Compatible model source of truth and unify metadata capture :

This change re-establishes a single, reliable source of truth for the active model:
fully aligned with the OpenAI-Compat API behavior

It introduces a unified metadata flow that captures the model field from both
streaming and non-streaming responses, wiring a new onModel callback through ChatService
The model name is now resolved directly from the API payload rather than relying on
server /props or UI assumptions

ChatStore records and persists the resolved model for each assistant message during
streaming, ensuring consistency across the UI and database
Type definitions for API and settings were also extended to include model metadata
and the onModel callback, completing the alignment with OpenAI-Compat semantics

Remaining '/props' usage audit in the WebUI :

A repository-wide search inside 'tools/server/webui' shows the remaining '/props' references are intentional because the WebUI still needs to bootstrap and validate server capabilities outside of chat responses:

'src/routes/+layout.svelte' and 'src/lib/stores/server.svelte.ts' fetch '/props' on application startup to populate the global server store with template, model alias, and capability metadata that never appears in chat completions.
'src/lib/components/app/server/ServerErrorSplash.svelte' and 'src/lib/components/app/chat/ChatScreen/ChatScreenWarning.svelte' surface fallback UI when '/props' is unreachable, ensuring the user understands cached data might be stale.
'src/lib/utils/api-key-validation.ts' validates API keys against '/props' so that the UI can warn about incompatible keys before issuing chat requests.
'src/lib/services/chat.ts' performs a last-resort fetch to '/props' when the streaming handshake fails, preserving compatibility with legacy servers that only expose model names via that endpoint.

ServeurpersoCom · 2025-10-13T13:34:53Z

TL;DR:
Adds a lightweight model selector for the WebUI using the /v1/models OpenAI-compatible endpoint.
Selected models are persisted locally and included in chat request payloads (model field).
Also unifies model metadata capture during streaming and non-streaming responses : the WebUI now uses a single source of truth for the active model across the stack.

ServeurpersoCom · 2025-10-13T13:37:40Z

@ngxson :) What do you think about this approach ?

aiming to stay compatible with the current standalone llama-server,
llama-swap
and future multi-model evolutions of llama-server?

It introduces a unified, KISS, OpenAI-compatible model selection path while keeping everything backward-compatible with existing setups

A standalone llama-server on a Raspberry Pi 5 :

I'll have to filter the model path here too (?)

ServeurpersoCom · 2025-10-13T15:04:47Z

@allozaur mind taking a look at those default Svelte arrows and the scrolling manager? I figured your Svelte wizardry might know the cleanest way to get rid of them 😄 I like things to be pixel-perfect, but it looks like this is built into the framework : and I’d rather not bypass Svelte just for that.

allozaur · 2025-10-13T15:06:15Z

@allozaur mind taking a look at those default Svelte arrows and the scrolling manager? I figured your Svelte wizardry might know the cleanest way to get rid of them 😄 I like things to be pixel-perfect, but it looks like this is built into the framework : and I’d rather not bypass Svelte just for that.

Yep, will take a look at that and come back to u with an answer 😉

tools/server/webui/src/lib/components/app/chat/ChatSidebar/ChatSidebar.svelte

tools/server/webui/src/routes/+layout.svelte

tools/server/webui/src/lib/stores/models.svelte.ts

tools/server/webui/src/lib/stores/chat.svelte.ts

ServeurpersoCom · 2025-10-20T06:16:19Z

Extracted determineInitialSelection helper
Centralized localStorage key constant
Minor Toaster cleanup per review
All checks passing locally

ServeurpersoCom · 2025-10-20T07:01:40Z

I think that placing the model selector in the Sidebar makes its UI a bit too heavy and bloated... Much better place for changing the model woud be in Chat Form, like here:

Computer :

Smartphone :

That’s actually a great idea : moving the selector into the Chat Form feels way more natural now that I’ve tested it 😄
The layout is cleaner, lighter, and it fits perfectly in the conversation flow. Definitely the right spot!

1324a4d

allozaur · 2025-10-20T07:22:09Z

I think that placing the model selector in the Sidebar makes its UI a bit too heavy and bloated... Much better place for changing the model woud be in Chat Form, like here:

Computer :

Smartphone :

That’s actually a great idea : moving the selector into the Chat Form feels way more natural now that I’ve tested it 😄

The layout is cleaner, lighter, and it fits perfectly in the conversation flow. Definitely the right spot!

1324a4d

I will post a PR to improve the UI of this selector as now it's just taking too much space and looks a bit off 😜

ServeurpersoCom · 2025-10-20T07:31:55Z

I will post a PR to improve the UI of this selector as now it's just taking too much space and looks a bit off 😜

Got it : you want to fine-tune the layout so the selector sits closer to the mic button, probably with a max width to keep long model names from stretching the form. We could even take it a step further : replace the full selector with a small model icon or dropdown button that pops the model list on click.

But we should still make sure the currently selected model (the one actually sent in the request) is clearly visible somewhere: since the /props display above only shows the model currently loaded on the llama-server, not the one chosen by the user through the selector. And on mobile there’s already very little screen space to work with, so keeping it minimal while still informative would be ideal. Actually, the small checkmark in the dropdown list might already be enough to show the active model, though in that case, we’d probably need to fix the scrolling glitch in the framework so the menu behaves properly.

ServeurpersoCom · 2025-10-20T08:36:34Z

Like this ?

(root|~/llama.cpp.pascal) git diff 0b9aaf8fe8fb36817c74f25e905aedaccfa9a825
diff --git a/tools/server/public/index.html.gz b/tools/server/public/index.html.gz
index c76f5778b..1897d50c8 100644
Binary files a/tools/server/public/index.html.gz and b/tools/server/public/index.html.gz differ
diff --git a/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte b/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte
index cbf0385a4..1bdb7f947 100644
--- a/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte
+++ b/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte
@@ -32,27 +32,29 @@
 <div class="flex w-full items-center gap-2 {className}">
        <ChatFormActionFileAttachments {disabled} {onFileUpload} />

-       <ChatFormModelSelector class="min-w-[140px] flex-1" />
+       <div class="ml-auto flex items-center gap-2">
+               <ChatFormModelSelector class="flex-shrink-0" />

-       {#if isLoading}
-               <Button
-                       type="button"
-                       onclick={onStop}
-                       class="h-8 w-8 bg-transparent p-0 hover:bg-destructive/20"
-               >
-                       <span class="sr-only">Stop</span>
-                       <Square class="h-8 w-8 fill-destructive stroke-destructive" />
-               </Button>
-       {:else}
-               <ChatFormActionRecord {disabled} {isLoading} {isRecording} {onMicClick} />
+               {#if isLoading}
+                       <Button
+                               type="button"
+                               onclick={onStop}
+                               class="h-8 w-8 bg-transparent p-0 hover:bg-destructive/20"
+                       >
+                               <span class="sr-only">Stop</span>
+                               <Square class="h-8 w-8 fill-destructive stroke-destructive" />
+                       </Button>
+               {:else}
+                       <ChatFormActionRecord {disabled} {isLoading} {isRecording} {onMicClick} />

-               <Button
-                       type="submit"
-                       disabled={!canSend || disabled || isLoading}
-                       class="h-8 w-8 rounded-full p-0"
-               >
-                       <span class="sr-only">Send</span>
-                       <ArrowUp class="h-12 w-12" />
-               </Button>
-       {/if}
+                       <Button
+                               type="submit"
+                               disabled={!canSend || disabled || isLoading}
+                               class="h-8 w-8 rounded-full p-0"
+                       >
+                               <span class="sr-only">Send</span>
+                               <ArrowUp class="h-12 w-12" />
+                       </Button>
+               {/if}
+       </div>
 </div>
diff --git a/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte b/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte
index ca48285da..d54147a5e 100644
--- a/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte
+++ b/tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte
@@ -1,6 +1,6 @@
 <script lang="ts">
        import { onMount } from 'svelte';
-       import { Loader2 } from '@lucide/svelte';
+       import { Bot, Loader2 } from '@lucide/svelte';
        import * as Select from '$lib/components/ui/select';
        import { cn } from '$lib/components/ui/utils';
        import {
@@ -63,7 +63,7 @@
        }
 </script>

-<div class={cn('flex min-w-0 flex-col gap-1', className)}>
+<div class={cn('flex min-w-0 flex-col items-center gap-1', className)}>
        {#if loading && options.length === 0 && !isMounted}
                <div class="flex items-center gap-2 text-xs text-muted-foreground">
                        <Loader2 class="h-4 w-4 animate-spin" />
@@ -81,13 +81,16 @@
                        disabled={loading || updating}
                >
                        <Select.Trigger
-                               class="h-9 w-full min-w-[140px] justify-between rounded-full border border-input bg-background/80 px-3 text-left text-sm sm:min-w-[200px]"
+                               aria-label="Select model"
+                               title={selectedOption?.name || 'Select model'}
+                               class="flex !h-8 !w-8 items-center justify-center !rounded-full border border-input !bg-background/80 !p-0 text-muted-foreground transition-colors hover:!bg-background data-[state=open]:!bg-background [&>svg:last-child]:hidden"
                        >
-                               <span class="truncate font-medium">{selectedOption?.name || 'Select model'}</span>
-
                                {#if updating}
                                        <Loader2 class="h-4 w-4 animate-spin text-muted-foreground" />
+                               {:else}
+                                       <Bot class="h-4 w-4" />
                                {/if}
+                               <span class="sr-only">{selectedOption?.name || 'Select model'}</span>
                        </Select.Trigger>

                        <Select.Content class="z-[100000]">
@@ -105,6 +108,6 @@
        {/if}

        {#if error}
-               <p class="text-xs text-destructive">{error}</p>
+               <p class="text-center text-xs text-destructive">{error}</p>
        {/if}
 </div>
(root|~/llama.cpp.pascal)

allozaur · 2025-10-20T08:38:32Z

Like this?

@ServeurpersoCom i thought more of sth similiar to what Claude has:

ServeurpersoCom · 2025-10-20T15:19:10Z

rebase master

ServeurpersoCom · 2025-10-20T16:34:31Z

ServeurpersoCom · 2025-10-20T18:14:29Z

No more Flowbite scroll bug on mobile :

I'll add a "developer" option with the model selector hidden by default.
But we can force it by default for all new users in lib/constants/settings-config.ts.
That's important so users can share decentralized AI services with friends, like I'm doing now,
otherwise it would be broken for anyone visiting the page for the first time!

ServeurpersoCom · 2025-10-20T18:46:20Z

Done. Now it’s compliant for all use cases @allozaur

ServeurpersoCom · 2025-10-20T19:13:40Z

PC :
https://github.com/user-attachments/assets/c7b55f8e-503d-4445-ab17-59ab4c75d35e

Mobile :
https://github.com/user-attachments/assets/f73c6e31-3246-4db0-b66a-75dba4d23b67

allozaur · 2025-10-20T23:09:53Z

@ServeurpersoCom

I've tested this on my end simply by running:

llama-server -hf ggml-org/Qwen2.5-Omni-7B-GGUF -c 0 --jinja --parallel 5

and

npm run dev

and I've spotted a few issues:

When i have the Enable model selector option unchecked, the default model should not be gpt-3.5-turbo but the one that i am actually running with llama-server

On the main screen i see the currently loaded model:

But under the message I am seeing this in the model info:

Also, after enabling the model selector in Settings, i am seeing full path to the model file instead of just the model file in the message model info.

Besides that the selector value string is good, but when the name is long, the UI breaks:

ServeurpersoCom · 2025-10-21T04:29:06Z

1. When i have the `Enable model selector` option unchecked, the default model should not be `gpt-3.5-turbo` but the one that i am actually running with `llama-server`

Oops, that's exactly what the backend does : we need to display the captured chunks ! and refactor the backend accordingly!

Normalized streamed model names during chat updates by trimming input and removing directory components before saving or persisting them, so the conversation UI shows only the filename Forced model names within the chat form selector dropdown to render as a single-line, truncated entry with a tooltip revealing the full name

When the selector is disabled, it falls back to the active server model name from /props When the model selector is enabled, the displayed model comes from the message metadata (the one explicitly selected and sent in the request)

…rmActions.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Co-authored-by: Aleksander Grygier <[email protected]>

…rmModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]>

…atMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Co-authored-by: Aleksander Grygier <[email protected]>

- Replace inline portal and event listeners with proper Svelte bindings - Introduce 'persisted' store helper for localStorage sync without runes - Extract 'normalizeModelName' utils + Vitest coverage - Simplify ChatFormModelSelector structure and cleanup logic Replaced the persisted store helper's use of '$state/$effect' runes with a plain TS implementation to prevent orphaned effect runtime errors outside component context Co-authored-by: Aleksander Grygier <[email protected]>

…rmModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Co-authored-by: Aleksander Grygier <[email protected]>

…ant model field

allozaur

Also please make this small change ;)

tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte

…atMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]>

allozaur

Okay, i think that we are good to go :)

@allozaur

…ml-org#16562) * webui: introduce OpenAI-compatible model selector in JSON payload * webui: restore OpenAI-Compatible model source of truth and unify metadata capture This change re-establishes a single, reliable source of truth for the active model: fully aligned with the OpenAI-Compat API behavior It introduces a unified metadata flow that captures the model field from both streaming and non-streaming responses, wiring a new onModel callback through ChatService The model name is now resolved directly from the API payload rather than relying on server /props or UI assumptions ChatStore records and persists the resolved model for each assistant message during streaming, ensuring consistency across the UI and database Type definitions for API and settings were also extended to include model metadata and the onModel callback, completing the alignment with OpenAI-Compat semantics * webui: address review feedback from allozaur * webui: move model selector into ChatForm (idea by @allozaur) * webui: make model selector more subtle and integrated into ChatForm * webui: replaced the Flowbite selector with a native Svelte dropdown * webui: add developer setting to toggle the chat model selector * webui: address review feedback from allozaur Normalized streamed model names during chat updates by trimming input and removing directory components before saving or persisting them, so the conversation UI shows only the filename Forced model names within the chat form selector dropdown to render as a single-line, truncated entry with a tooltip revealing the full name * webui: toggle displayed model source for legacy vs OpenAI-Compat modes When the selector is disabled, it falls back to the active server model name from /props When the model selector is enabled, the displayed model comes from the message metadata (the one explicitly selected and sent in the request) * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/constants/localstorage-keys.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/services/chat.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/services/chat.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: refactor model selector and persistence helpers - Replace inline portal and event listeners with proper Svelte bindings - Introduce 'persisted' store helper for localStorage sync without runes - Extract 'normalizeModelName' utils + Vitest coverage - Simplify ChatFormModelSelector structure and cleanup logic Replaced the persisted store helper's use of '$state/$effect' runes with a plain TS implementation to prevent orphaned effect runtime errors outside component context Co-authored-by: Aleksander Grygier <[email protected]> * webui: document normalizeModelName usage with inline examples * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/stores/models.svelte.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/stores/models.svelte.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: extract ModelOption type into dedicated models.d.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: refine ChatMessageAssistant displayedModel source logic * webui: stabilize dropdown, simplify model extraction, and init assistant model field * chore: update webui static build * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]> * chore: npm format, update webui static build * webui: align sidebar trigger position, remove z-index glitch * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <[email protected]>

@allozaur

…ml-org#16562) * webui: introduce OpenAI-compatible model selector in JSON payload * webui: restore OpenAI-Compatible model source of truth and unify metadata capture This change re-establishes a single, reliable source of truth for the active model: fully aligned with the OpenAI-Compat API behavior It introduces a unified metadata flow that captures the model field from both streaming and non-streaming responses, wiring a new onModel callback through ChatService The model name is now resolved directly from the API payload rather than relying on server /props or UI assumptions ChatStore records and persists the resolved model for each assistant message during streaming, ensuring consistency across the UI and database Type definitions for API and settings were also extended to include model metadata and the onModel callback, completing the alignment with OpenAI-Compat semantics * webui: address review feedback from allozaur * webui: move model selector into ChatForm (idea by @allozaur) * webui: make model selector more subtle and integrated into ChatForm * webui: replaced the Flowbite selector with a native Svelte dropdown * webui: add developer setting to toggle the chat model selector * webui: address review feedback from allozaur Normalized streamed model names during chat updates by trimming input and removing directory components before saving or persisting them, so the conversation UI shows only the filename Forced model names within the chat form selector dropdown to render as a single-line, truncated entry with a tooltip revealing the full name * webui: toggle displayed model source for legacy vs OpenAI-Compat modes When the selector is disabled, it falls back to the active server model name from /props When the model selector is enabled, the displayed model comes from the message metadata (the one explicitly selected and sent in the request) * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormActions.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/constants/localstorage-keys.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/services/chat.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/services/chat.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: refactor model selector and persistence helpers - Replace inline portal and event listeners with proper Svelte bindings - Introduce 'persisted' store helper for localStorage sync without runes - Extract 'normalizeModelName' utils + Vitest coverage - Simplify ChatFormModelSelector structure and cleanup logic Replaced the persisted store helper's use of '$state/$effect' runes with a plain TS implementation to prevent orphaned effect runtime errors outside component context Co-authored-by: Aleksander Grygier <[email protected]> * webui: document normalizeModelName usage with inline examples * Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFormModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/stores/models.svelte.ts Co-authored-by: Aleksander Grygier <[email protected]> * Update tools/server/webui/src/lib/stores/models.svelte.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: extract ModelOption type into dedicated models.d.ts Co-authored-by: Aleksander Grygier <[email protected]> * webui: refine ChatMessageAssistant displayedModel source logic * webui: stabilize dropdown, simplify model extraction, and init assistant model field * chore: update webui static build * Update tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]> * chore: npm format, update webui static build * webui: align sidebar trigger position, remove z-index glitch * chore: update webui build output --------- Co-authored-by: Aleksander Grygier <[email protected]>

ServeurpersoCom requested a review from allozaur as a code owner October 13, 2025 13:31

github-actions bot added examples server labels Oct 13, 2025

allozaur requested a review from ngxson October 13, 2025 13:46

This was referenced Oct 13, 2025

Svelte webui model selector #16335

Closed

Feature Request: tool to list and delete cached models #16393

Open

Feature request: allow load/unload models on server #16487

Open

ServeurpersoCom force-pushed the openai-model-selector branch from 6606ff7 to 03d383c Compare October 18, 2025 10:20

ServeurpersoCom mentioned this pull request Oct 18, 2025

webui: add OAI-Compat Harmony tool-call streaming visualization and persistence in chat UI #16618

Open

allozaur reviewed Oct 19, 2025

View reviewed changes

ServeurpersoCom force-pushed the openai-model-selector branch 2 times, most recently from 45298f8 to 286ca88 Compare October 20, 2025 06:07

ServeurpersoCom force-pushed the openai-model-selector branch from 48ad6c5 to b56058a Compare October 20, 2025 15:03

ServeurpersoCom and others added 19 commits October 22, 2025 13:00

webui: replaced the Flowbite selector with a native Svelte dropdown

0fa592a

webui: add developer setting to toggle the chat model selector

f06d663

Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFo…

2a7c4c0

…rmActions.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/constants/localstorage-keys.ts

f59cac2

Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFo…

938e68c

…rmModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/components/app/chat/ChatMessages/Ch…

da3c653

…atMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/services/chat.ts

0ad7601

Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/services/chat.ts

3a7ab7f

Co-authored-by: Aleksander Grygier <[email protected]>

webui: document normalizeModelName usage with inline examples

2d5bcad

Update tools/server/webui/src/lib/components/app/chat/ChatForm/ChatFo…

fd7866a

…rmModelSelector.svelte Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/stores/models.svelte.ts

8e54dd8

Co-authored-by: Aleksander Grygier <[email protected]>

Update tools/server/webui/src/lib/stores/models.svelte.ts

ab922d9

Co-authored-by: Aleksander Grygier <[email protected]>

webui: extract ModelOption type into dedicated models.d.ts

2173554

Co-authored-by: Aleksander Grygier <[email protected]>

webui: refine ChatMessageAssistant displayedModel source logic

e0dc324

webui: stabilize dropdown, simplify model extraction, and init assist…

cef7776

…ant model field

chore: update webui static build

d13a292

ServeurpersoCom force-pushed the openai-model-selector branch from f3a6387 to d13a292 Compare October 22, 2025 11:03

allozaur requested changes Oct 22, 2025

View reviewed changes

tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte Outdated Show resolved Hide resolved

ServeurpersoCom and others added 4 commits October 22, 2025 13:19

Update tools/server/webui/src/lib/components/app/chat/ChatMessages/Ch…

d90cb36

…atMessageAssistant.svelte Co-authored-by: Aleksander Grygier <[email protected]>

chore: npm format, update webui static build

0cf3135

webui: align sidebar trigger position, remove z-index glitch

0a907ef

chore: update webui build output

114cd56

allozaur approved these changes Oct 22, 2025

View reviewed changes

allozaur merged commit 9b9201f into ggml-org:master Oct 22, 2025
14 checks passed

firecoperana mentioned this pull request Oct 26, 2025

Add --webui arg to launch llama.cpp new webui ikawrakow/ik_llama.cpp#786

Merged

webui: introduce OpenAI-compatible model selector in JSON payload #16562

webui: introduce OpenAI-compatible model selector in JSON payload #16562

Uh oh!

Conversation

ServeurpersoCom commented Oct 13, 2025

Introduce OpenAI-compatible model selector in JSON payload

Restore OpenAI-Compatible model source of truth and unify metadata capture :

Remaining '/props' usage audit in the WebUI :

Uh oh!

ServeurpersoCom commented Oct 13, 2025

Uh oh!

ServeurpersoCom commented Oct 13, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 13, 2025

Uh oh!

allozaur commented Oct 13, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

allozaur commented Oct 20, 2025

Uh oh!

ServeurpersoCom commented Oct 20, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

allozaur commented Oct 20, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

ServeurpersoCom commented Oct 20, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 20, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 20, 2025

Uh oh!

allozaur commented Oct 20, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ServeurpersoCom commented Oct 21, 2025

Uh oh!

allozaur left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

allozaur left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

ServeurpersoCom commented Oct 13, 2025 •

edited

Loading

ServeurpersoCom commented Oct 20, 2025 •

edited

Loading

allozaur commented Oct 20, 2025 •

edited

Loading

ServeurpersoCom commented Oct 20, 2025 •

edited

Loading

ServeurpersoCom commented Oct 20, 2025 •

edited

Loading

allozaur commented Oct 20, 2025 •

edited

Loading