Merge commit '12280ae9058600b0b14335fe59848e601e10eebc' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/model-conversion/scripts/causal/compare-logits.py
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	tests/test-backend-ops.cpp
#	tests/test-barrier.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2025-12-16 16:29:01 +08:00
49 changed files with 1380 additions and 583 deletions
Binary file not shown.
+182 -85
View File
@@ -1,6 +1,7 @@
#include "server-common.h"
#include "server-models.h"
#include "preset.h"
#include "download.h"
#include <cpp-httplib/httplib.h> // TODO: remove this once we use HTTP client from download.h
@@ -33,6 +34,10 @@
#define CMD_EXIT "exit"
// address for child process, this is needed because router may run on 0.0.0.0
// ref: https://github.com/ggml-org/llama.cpp/issues/17862
#define CHILD_ADDR "127.0.0.1"
static std::filesystem::path get_server_exec_path() {
#if defined(_WIN32)
wchar_t buf[32768] = { 0 }; // Large buffer to handle long paths
@@ -132,6 +137,93 @@ static std::vector<local_model> list_local_models(const std::string & dir) {
return models;
}
//
// server_presets
//
server_presets::server_presets(int argc, char ** argv, common_params & base_params, const std::string & presets_path)
: ctx_params(common_params_parser_init(base_params, LLAMA_EXAMPLE_SERVER)) {
if (!presets_path.empty()) {
presets = common_presets_load(presets_path, ctx_params);
SRV_INF("Loaded %zu presets from %s\n", presets.size(), presets_path.c_str());
}
// populate reserved args (will be appended by the router)
for (auto & opt : ctx_params.options) {
if (opt.env == nullptr) {
continue;
}
std::string env = opt.env;
if (env == "LLAMA_ARG_PORT" ||
env == "LLAMA_ARG_HOST" ||
env == "LLAMA_ARG_ALIAS" ||
env == "LLAMA_ARG_API_KEY" ||
env == "LLAMA_ARG_MODELS_DIR" ||
env == "LLAMA_ARG_MODELS_MAX" ||
env == "LLAMA_ARG_MODELS_PRESET" ||
env == "LLAMA_ARG_MODEL" ||
env == "LLAMA_ARG_MMPROJ" ||
env == "LLAMA_ARG_HF_REPO" ||
env == "LLAMA_ARG_NO_MODELS_AUTOLOAD") {
control_args[env] = opt;
}
}
// read base args from router's argv
common_params_parse(argc, argv, LLAMA_EXAMPLE_SERVER, base_args);
// remove any router-controlled args from base_args
for (const auto & cargs : control_args) {
auto it = base_args.find(cargs.second);
if (it != base_args.end()) {
base_args.erase(it);
}
}
}
common_preset server_presets::get_preset(const std::string & name) {
auto it = presets.find(name);
if (it != presets.end()) {
return it->second;
}
return common_preset();
}
void server_presets::render_args(server_model_meta & meta) {
common_preset preset = meta.preset; // copy
// merging 3 kinds of args:
// 1. model-specific args (from preset)
// force removing control args if any
for (auto & cargs : control_args) {
if (preset.options.find(cargs.second) != preset.options.end()) {
SRV_WRN("Preset '%s' contains reserved arg '%s', removing it\n", preset.name.c_str(), cargs.second.args[0]);
preset.options.erase(cargs.second);
}
}
// 2. base args (from router)
// inherit from base args
for (const auto & [arg, value] : base_args) {
preset.options[arg] = value;
}
// 3. control args (from router)
// set control values
preset.options[control_args["LLAMA_ARG_HOST"]] = CHILD_ADDR;
preset.options[control_args["LLAMA_ARG_PORT"]] = std::to_string(meta.port);
preset.options[control_args["LLAMA_ARG_ALIAS"]] = meta.name;
if (meta.in_cache) {
preset.options[control_args["LLAMA_ARG_HF_REPO"]] = meta.name;
} else {
preset.options[control_args["LLAMA_ARG_MODEL"]] = meta.path;
if (!meta.path_mmproj.empty()) {
preset.options[control_args["LLAMA_ARG_MMPROJ"]] = meta.path_mmproj;
}
}
meta.args = preset.to_args();
// add back the binary path at the front
meta.args.insert(meta.args.begin(), get_server_exec_path().string());
}
//
// server_models
//
@@ -140,7 +232,7 @@ server_models::server_models(
const common_params & params,
int argc,
char ** argv,
char ** envp) : base_params(params) {
char ** envp) : base_params(params), presets(argc, argv, base_params, params.models_preset) {
for (int i = 0; i < argc; i++) {
base_args.push_back(std::string(argv[i]));
}
@@ -155,11 +247,58 @@ server_models::server_models(
LOG_WRN("failed to get server executable path: %s\n", e.what());
LOG_WRN("using original argv[0] as fallback: %s\n", base_args[0].c_str());
}
// TODO: allow refreshing cached model list
// add cached models
load_models();
}
void server_models::add_model(server_model_meta && meta) {
if (mapping.find(meta.name) != mapping.end()) {
throw std::runtime_error(string_format("model '%s' appears multiple times", meta.name.c_str()));
}
presets.render_args(meta); // populate meta.args
std::string name = meta.name;
mapping[name] = instance_t{
/* subproc */ std::make_shared<subprocess_s>(),
/* th */ std::thread(),
/* meta */ std::move(meta)
};
}
static std::vector<local_model> list_custom_path_models(server_presets & presets) {
// detect any custom-path models in presets
std::vector<local_model> custom_models;
for (auto & [model_name, preset] : presets.presets) {
local_model model;
model.name = model_name;
std::vector<common_arg> to_erase;
for (auto & [arg, value] : preset.options) {
std::string env(arg.env ? arg.env : "");
if (env == "LLAMA_ARG_MODEL") {
model.path = value;
to_erase.push_back(arg);
}
if (env == "LLAMA_ARG_MMPROJ") {
model.path_mmproj = value;
to_erase.push_back(arg);
}
}
for (auto & arg : to_erase) {
preset.options.erase(arg);
}
if (!model.name.empty() && !model.path.empty()) {
custom_models.push_back(model);
}
}
return custom_models;
}
// TODO: allow refreshing cached model list
void server_models::load_models() {
// loading models from 3 sources:
// 1. cached models
auto cached_models = common_list_cached_models();
for (const auto & model : cached_models) {
server_model_meta meta{
/* preset */ presets.get_preset(model.to_string()),
/* name */ model.to_string(),
/* path */ model.manifest_path,
/* path_mmproj */ "", // auto-detected when loading
@@ -170,21 +309,18 @@ server_models::server_models(
/* args */ std::vector<std::string>(),
/* exit_code */ 0
};
mapping[meta.name] = instance_t{
/* subproc */ std::make_shared<subprocess_s>(),
/* th */ std::thread(),
/* meta */ meta
};
add_model(std::move(meta));
}
// add local models specificed via --models-dir
if (!params.models_dir.empty()) {
auto local_models = list_local_models(params.models_dir);
// 2. local models specificed via --models-dir
if (!base_params.models_dir.empty()) {
auto local_models = list_local_models(base_params.models_dir);
for (const auto & model : local_models) {
if (mapping.find(model.name) != mapping.end()) {
// already exists in cached models, skip
continue;
}
server_model_meta meta{
/* preset */ presets.get_preset(model.name),
/* name */ model.name,
/* path */ model.path,
/* path_mmproj */ model.path_mmproj,
@@ -195,13 +331,31 @@ server_models::server_models(
/* args */ std::vector<std::string>(),
/* exit_code */ 0
};
mapping[meta.name] = instance_t{
/* subproc */ std::make_shared<subprocess_s>(),
/* th */ std::thread(),
/* meta */ meta
};
add_model(std::move(meta));
}
}
// 3. custom-path models specified in presets
auto custom_models = list_custom_path_models(presets);
for (const auto & model : custom_models) {
server_model_meta meta{
/* preset */ presets.get_preset(model.name),
/* name */ model.name,
/* path */ model.path,
/* path_mmproj */ model.path_mmproj,
/* in_cache */ false,
/* port */ 0,
/* status */ SERVER_MODEL_STATUS_UNLOADED,
/* last_used */ 0,
/* args */ std::vector<std::string>(),
/* exit_code */ 0
};
add_model(std::move(meta));
}
// log available models
SRV_INF("Available models (%zu) (*: custom preset)\n", mapping.size());
for (const auto & [name, inst] : mapping) {
SRV_INF(" %c %s\n", inst.meta.preset.name.empty() ? ' ' : '*', name.c_str());
}
}
void server_models::update_meta(const std::string & name, const server_model_meta & meta) {
@@ -335,19 +489,7 @@ void server_models::unload_lru() {
}
}
static void add_or_replace_arg(std::vector<std::string> & args, const std::string & key, const std::string & value) {
for (size_t i = 0; i < args.size(); i++) {
if (args[i] == key && i + 1 < args.size()) {
args[i + 1] = value;
return;
}
}
// not found, append
args.push_back(key);
args.push_back(value);
}
void server_models::load(const std::string & name, bool auto_load) {
void server_models::load(const std::string & name) {
if (!has_model(name)) {
throw std::runtime_error("model name=" + name + " is not found");
}
@@ -376,26 +518,10 @@ void server_models::load(const std::string & name, bool auto_load) {
{
SRV_INF("spawning server instance with name=%s on port %d\n", inst.meta.name.c_str(), inst.meta.port);
std::vector<std::string> child_args;
if (auto_load && !meta.args.empty()) {
child_args = meta.args; // copy previous args
} else {
child_args = base_args; // copy
if (inst.meta.in_cache) {
add_or_replace_arg(child_args, "-hf", inst.meta.name);
} else {
add_or_replace_arg(child_args, "-m", inst.meta.path);
if (!inst.meta.path_mmproj.empty()) {
add_or_replace_arg(child_args, "--mmproj", inst.meta.path_mmproj);
}
}
}
presets.render_args(inst.meta); // update meta.args
// set model args
add_or_replace_arg(child_args, "--port", std::to_string(inst.meta.port));
add_or_replace_arg(child_args, "--alias", inst.meta.name);
std::vector<std::string> child_env = base_env; // copy
std::vector<std::string> child_args = inst.meta.args; // copy
std::vector<std::string> child_env = base_env; // copy
child_env.push_back("LLAMA_SERVER_ROUTER_PORT=" + std::to_string(base_params.port));
SRV_INF("%s", "spawning server instance with args:\n");
@@ -541,7 +667,7 @@ bool server_models::ensure_model_loaded(const std::string & name) {
}
if (meta->status == SERVER_MODEL_STATUS_UNLOADED) {
SRV_INF("model name=%s is not loaded, loading...\n", name.c_str());
load(name, true);
load(name);
}
SRV_INF("waiting until model name=%s is fully loaded...\n", name.c_str());
@@ -571,7 +697,7 @@ server_http_res_ptr server_models::proxy_request(const server_http_req & req, co
SRV_INF("proxying request to model %s on port %d\n", name.c_str(), meta->port);
auto proxy = std::make_unique<server_http_proxy>(
method,
base_params.hostname,
CHILD_ADDR,
meta->port,
req.path,
req.headers,
@@ -724,38 +850,6 @@ void server_models_routes::init_routes() {
return models.proxy_request(req, method, name, true); // update last usage for POST request only
};
this->get_router_models = [this](const server_http_req &) {
auto res = std::make_unique<server_http_res>();
json models_json = json::array();
auto all_models = models.get_all_meta();
std::time_t t = std::time(0);
for (const auto & meta : all_models) {
json status {
{"value", server_model_status_to_string(meta.status)},
{"args", meta.args},
};
if (meta.is_failed()) {
status["exit_code"] = meta.exit_code;
status["failed"] = true;
}
models_json.push_back(json {
{"id", meta.name},
{"object", "model"}, // for OAI-compat
{"owned_by", "llamacpp"}, // for OAI-compat
{"created", t}, // for OAI-compat
{"in_cache", meta.in_cache},
{"path", meta.path},
{"status", status},
// TODO: add other fields, may require reading GGUF metadata
});
}
res_ok(res, {
{"data", models_json},
{"object", "list"},
});
return res;
};
this->post_router_models_load = [this](const server_http_req & req) {
auto res = std::make_unique<server_http_res>();
json body = json::parse(req.body);
@@ -769,7 +863,7 @@ void server_models_routes::init_routes() {
res_err(res, format_error_response("model is already loaded", ERROR_TYPE_INVALID_REQUEST));
return res;
}
models.load(name, false);
models.load(name);
res_ok(res, {{"success", true}});
return res;
};
@@ -793,9 +887,12 @@ void server_models_routes::init_routes() {
std::time_t t = std::time(0);
for (const auto & meta : all_models) {
json status {
{"value", server_model_status_to_string(meta.status)},
{"args", meta.args},
{"value", server_model_status_to_string(meta.status)},
{"args", meta.args},
};
if (!meta.preset.name.empty()) {
status["preset"] = meta.preset.to_ini();
}
if (meta.is_failed()) {
status["exit_code"] = meta.exit_code;
status["failed"] = true;
+24 -3
View File
@@ -1,6 +1,7 @@
#pragma once
#include "common.h"
#include "preset.h"
#include "server-http.h"
#include <mutex>
@@ -47,6 +48,7 @@ static std::string server_model_status_to_string(server_model_status status) {
}
struct server_model_meta {
common_preset preset;
std::string name;
std::string path;
std::string path_mmproj; // only available if in_cache=false
@@ -54,7 +56,7 @@ struct server_model_meta {
int port = 0;
server_model_status status = SERVER_MODEL_STATUS_UNLOADED;
int64_t last_used = 0; // for LRU unloading
std::vector<std::string> args; // additional args passed to the model instance (used for debugging)
std::vector<std::string> args; // args passed to the model instance, will be populated by render_args()
int exit_code = 0; // exit code of the model instance process (only valid if status == FAILED)
bool is_active() const {
@@ -66,6 +68,19 @@ struct server_model_meta {
}
};
// the server_presets struct holds the presets read from presets.ini
// as well as base args from the router server
struct server_presets {
common_presets presets;
common_params_context ctx_params;
std::map<common_arg, std::string> base_args;
std::map<std::string, common_arg> control_args; // args reserved for server control
server_presets(int argc, char ** argv, common_params & base_params, const std::string & models_dir);
common_preset get_preset(const std::string & name);
void render_args(server_model_meta & meta);
};
struct subprocess_s;
struct server_models {
@@ -85,14 +100,21 @@ private:
std::vector<std::string> base_args;
std::vector<std::string> base_env;
server_presets presets;
void update_meta(const std::string & name, const server_model_meta & meta);
// unload least recently used models if the limit is reached
void unload_lru();
// not thread-safe, caller must hold mutex
void add_model(server_model_meta && meta);
public:
server_models(const common_params & params, int argc, char ** argv, char ** envp);
void load_models();
// check if a model instance exists
bool has_model(const std::string & name);
@@ -102,8 +124,7 @@ public:
// return a copy of all model metadata
std::vector<server_model_meta> get_all_meta();
// if auto_load is true, load the model with previous args if any
void load(const std::string & name, bool auto_load);
void load(const std::string & name);
void unload(const std::string & name);
void unload_all();
+22 -14
View File
@@ -41,7 +41,7 @@
"@tailwindcss/vite": "^4.0.0",
"@types/node": "^22",
"@vitest/browser": "^3.2.3",
"bits-ui": "^2.8.11",
"bits-ui": "^2.14.4",
"clsx": "^2.1.1",
"dexie": "^4.0.11",
"eslint": "^9.18.0",
@@ -3343,17 +3343,17 @@
}
},
"node_modules/bits-ui": {
"version": "2.8.11",
"resolved": "https://registry.npmjs.org/bits-ui/-/bits-ui-2.8.11.tgz",
"integrity": "sha512-lKN9rAk69my6j7H1D4B87r8LrHuEtfEsf1xCixBj9yViql2BdI3f04HyyyT7T1GOCpgb9+8b0B+nm3LN81Konw==",
"version": "2.14.4",
"resolved": "https://registry.npmjs.org/bits-ui/-/bits-ui-2.14.4.tgz",
"integrity": "sha512-W6kenhnbd/YVvur+DKkaVJ6GldE53eLewur5AhUCqslYQ0vjZr8eWlOfwZnMiPB+PF5HMVqf61vXBvmyrAmPWg==",
"dev": true,
"license": "MIT",
"dependencies": {
"@floating-ui/core": "^1.7.1",
"@floating-ui/dom": "^1.7.1",
"esm-env": "^1.1.2",
"runed": "^0.29.1",
"svelte-toolbelt": "^0.9.3",
"runed": "^0.35.1",
"svelte-toolbelt": "^0.10.6",
"tabbable": "^6.2.0"
},
"engines": {
@@ -3368,9 +3368,9 @@
}
},
"node_modules/bits-ui/node_modules/runed": {
"version": "0.29.2",
"resolved": "https://registry.npmjs.org/runed/-/runed-0.29.2.tgz",
"integrity": "sha512-0cq6cA6sYGZwl/FvVqjx9YN+1xEBu9sDDyuWdDW1yWX7JF2wmvmVKfH+hVCZs+csW+P3ARH92MjI3H9QTagOQA==",
"version": "0.35.1",
"resolved": "https://registry.npmjs.org/runed/-/runed-0.35.1.tgz",
"integrity": "sha512-2F4Q/FZzbeJTFdIS/PuOoPRSm92sA2LhzTnv6FXhCoENb3huf5+fDuNOg1LNvGOouy3u/225qxmuJvcV3IZK5Q==",
"dev": true,
"funding": [
"https://github.com/sponsors/huntabyte",
@@ -3378,23 +3378,31 @@
],
"license": "MIT",
"dependencies": {
"esm-env": "^1.0.0"
"dequal": "^2.0.3",
"esm-env": "^1.0.0",
"lz-string": "^1.5.0"
},
"peerDependencies": {
"@sveltejs/kit": "^2.21.0",
"svelte": "^5.7.0"
},
"peerDependenciesMeta": {
"@sveltejs/kit": {
"optional": true
}
}
},
"node_modules/bits-ui/node_modules/svelte-toolbelt": {
"version": "0.9.3",
"resolved": "https://registry.npmjs.org/svelte-toolbelt/-/svelte-toolbelt-0.9.3.tgz",
"integrity": "sha512-HCSWxCtVmv+c6g1ACb8LTwHVbDqLKJvHpo6J8TaqwUme2hj9ATJCpjCPNISR1OCq2Q4U1KT41if9ON0isINQZw==",
"version": "0.10.6",
"resolved": "https://registry.npmjs.org/svelte-toolbelt/-/svelte-toolbelt-0.10.6.tgz",
"integrity": "sha512-YWuX+RE+CnWYx09yseAe4ZVMM7e7GRFZM6OYWpBKOb++s+SQ8RBIMMe+Bs/CznBMc0QPLjr+vDBxTAkozXsFXQ==",
"dev": true,
"funding": [
"https://github.com/sponsors/huntabyte"
],
"dependencies": {
"clsx": "^2.1.1",
"runed": "^0.29.0",
"runed": "^0.35.1",
"style-to-object": "^1.0.8"
},
"engines": {
+1 -1
View File
@@ -43,7 +43,7 @@
"@tailwindcss/vite": "^4.0.0",
"@types/node": "^22",
"@vitest/browser": "^3.2.3",
"bits-ui": "^2.8.11",
"bits-ui": "^2.14.4",
"clsx": "^2.1.1",
"dexie": "^4.0.11",
"eslint": "^9.18.0",
@@ -331,6 +331,7 @@
class="{INPUT_CLASSES} border-radius-bottom-none mx-auto max-w-[48rem] overflow-hidden rounded-3xl backdrop-blur-md {disabled
? 'cursor-not-allowed opacity-60'
: ''} {className}"
data-slot="chat-form"
>
<ChatAttachmentsList
bind:uploadedFiles
@@ -1,6 +1,5 @@
<script lang="ts">
import { Input } from '$lib/components/ui/input';
import { Search } from '@lucide/svelte';
import { SearchInput } from '$lib/components/app';
interface Props {
value?: string;
@@ -15,19 +14,6 @@
onInput,
class: className
}: Props = $props();
function handleInput(event: Event) {
const target = event.target as HTMLInputElement;
value = target.value;
onInput?.(target.value);
}
</script>
<div class="relative mb-4 {className}">
<Search
class="absolute top-1/2 left-3 h-4 w-4 -translate-y-1/2 transform text-muted-foreground"
/>
<Input bind:value class="pl-10" oninput={handleInput} {placeholder} type="search" />
</div>
<SearchInput bind:value {placeholder} {onInput} class="mb-4 {className}" />
@@ -64,6 +64,7 @@ export { default as CopyToClipboardIcon } from './misc/CopyToClipboardIcon.svelt
export { default as KeyboardShortcutInfo } from './misc/KeyboardShortcutInfo.svelte';
export { default as MarkdownContent } from './misc/MarkdownContent.svelte';
export { default as RemoveButton } from './misc/RemoveButton.svelte';
export { default as SearchInput } from './misc/SearchInput.svelte';
export { default as SyntaxHighlightedCode } from './misc/SyntaxHighlightedCode.svelte';
export { default as ModelsSelector } from './models/ModelsSelector.svelte';
@@ -0,0 +1,73 @@
<script lang="ts">
import { Input } from '$lib/components/ui/input';
import { Search, X } from '@lucide/svelte';
interface Props {
value?: string;
placeholder?: string;
onInput?: (value: string) => void;
onClose?: () => void;
onKeyDown?: (event: KeyboardEvent) => void;
class?: string;
id?: string;
ref?: HTMLInputElement | null;
}
let {
value = $bindable(''),
placeholder = 'Search...',
onInput,
onClose,
onKeyDown,
class: className,
id,
ref = $bindable(null)
}: Props = $props();
let showClearButton = $derived(!!value || !!onClose);
function handleInput(event: Event) {
const target = event.target as HTMLInputElement;
value = target.value;
onInput?.(target.value);
}
function handleClear() {
if (value) {
value = '';
onInput?.('');
ref?.focus();
} else {
onClose?.();
}
}
</script>
<div class="relative {className}">
<Search
class="absolute top-1/2 left-3 h-4 w-4 -translate-y-1/2 transform text-muted-foreground"
/>
<Input
{id}
bind:value
bind:ref
class="pl-9 {showClearButton ? 'pr-9' : ''}"
oninput={handleInput}
onkeydown={onKeyDown}
{placeholder}
type="search"
/>
{#if showClearButton}
<button
type="button"
class="absolute top-1/2 right-3 -translate-y-1/2 transform text-muted-foreground transition-colors hover:text-foreground"
onclick={handleClear}
aria-label={value ? 'Clear search' : 'Close'}
>
<X class="h-4 w-4" />
</button>
{/if}
</div>
@@ -2,8 +2,8 @@
import { onMount, tick } from 'svelte';
import { ChevronDown, EyeOff, Loader2, MicOff, Package, Power } from '@lucide/svelte';
import * as Tooltip from '$lib/components/ui/tooltip';
import * as Popover from '$lib/components/ui/popover';
import { cn } from '$lib/components/ui/utils';
import { portalToBody } from '$lib/utils';
import {
modelsStore,
modelOptions,
@@ -17,12 +17,8 @@
import { usedModalities, conversationsStore } from '$lib/stores/conversations.svelte';
import { ServerModelStatus } from '$lib/enums';
import { isRouterMode } from '$lib/stores/server.svelte';
import { DialogModelInformation } from '$lib/components/app';
import {
MENU_MAX_WIDTH,
MENU_OFFSET,
VIEWPORT_GUTTER
} from '$lib/constants/floating-ui-constraints';
import { DialogModelInformation, SearchInput } from '$lib/components/app';
import type { ModelOption } from '$lib/types/models';
interface Props {
class?: string;
@@ -145,185 +141,126 @@
return options.some((option) => option.model === currentModel);
});
let isOpen = $state(false);
let showModelDialog = $state(false);
let container: HTMLDivElement | null = null;
let menuRef = $state<HTMLDivElement | null>(null);
let triggerButton = $state<HTMLButtonElement | null>(null);
let menuPosition = $state<{
top: number;
left: number;
width: number;
placement: 'top' | 'bottom';
maxHeight: number;
} | null>(null);
let searchTerm = $state('');
let searchInputRef = $state<HTMLInputElement | null>(null);
let highlightedIndex = $state<number>(-1);
onMount(async () => {
try {
await modelsStore.fetch();
} catch (error) {
console.error('Unable to load models:', error);
}
let filteredOptions: ModelOption[] = $derived(
(() => {
const term = searchTerm.trim().toLowerCase();
if (!term) return options;
return options.filter(
(option) =>
option.model.toLowerCase().includes(term) || option.name?.toLowerCase().includes(term)
);
})()
);
// Get indices of compatible options for keyboard navigation
let compatibleIndices = $derived(
filteredOptions
.map((option, index) => (isModelCompatible(option) ? index : -1))
.filter((i) => i !== -1)
);
// Reset highlighted index when search term changes
$effect(() => {
void searchTerm;
highlightedIndex = -1;
});
function toggleOpen() {
let isOpen = $state(false);
let showModelDialog = $state(false);
onMount(() => {
modelsStore.fetch().catch((error) => {
console.error('Unable to load models:', error);
});
});
function handleOpenChange(open: boolean) {
if (loading || updating) return;
if (isRouter) {
// Router mode: show dropdown
if (isOpen) {
closeMenu();
} else {
openMenu();
if (open) {
isOpen = true;
searchTerm = '';
highlightedIndex = -1;
// Focus search input after popover opens
tick().then(() => {
requestAnimationFrame(() => searchInputRef?.focus());
});
if (isRouter) {
modelsStore.fetchRouterModels().then(() => {
modelsStore.fetchModalitiesForLoadedModels();
});
}
} else {
// Single model mode: show dialog
showModelDialog = true;
isOpen = false;
searchTerm = '';
highlightedIndex = -1;
}
}
async function openMenu() {
function handleTriggerClick() {
if (loading || updating) return;
isOpen = true;
await tick();
updateMenuPosition();
requestAnimationFrame(() => updateMenuPosition());
if (isRouter) {
modelsStore.fetchRouterModels().then(() => {
modelsStore.fetchModalitiesForLoadedModels();
});
if (!isRouter) {
// Single model mode: show dialog instead of popover
showModelDialog = true;
}
// For router mode, the Popover handles open/close
}
export function open() {
if (isRouter) {
openMenu();
handleOpenChange(true);
} else {
showModelDialog = true;
}
}
function closeMenu() {
if (!isOpen) return;
isOpen = false;
menuPosition = null;
handleOpenChange(false);
}
function handlePointerDown(event: PointerEvent) {
if (!container) return;
function handleSearchKeyDown(event: KeyboardEvent) {
if (event.isComposing) return;
const target = event.target as Node | null;
if (event.key === 'ArrowDown') {
event.preventDefault();
if (compatibleIndices.length === 0) return;
if (target && !container.contains(target) && !(menuRef && menuRef.contains(target))) {
closeMenu();
}
}
function handleKeydown(event: KeyboardEvent) {
if (event.key === 'Escape') {
closeMenu();
}
}
function handleResize() {
if (isOpen) {
updateMenuPosition();
}
}
function updateMenuPosition() {
if (!isOpen || !triggerButton || !menuRef) return;
const triggerRect = triggerButton.getBoundingClientRect();
const viewportWidth = window.innerWidth;
const viewportHeight = window.innerHeight;
if (viewportWidth === 0 || viewportHeight === 0) return;
const scrollWidth = menuRef.scrollWidth;
const scrollHeight = menuRef.scrollHeight;
const availableWidth = Math.max(0, viewportWidth - VIEWPORT_GUTTER * 2);
const constrainedMaxWidth = Math.min(MENU_MAX_WIDTH, availableWidth || MENU_MAX_WIDTH);
const safeMaxWidth =
constrainedMaxWidth > 0 ? constrainedMaxWidth : Math.min(MENU_MAX_WIDTH, viewportWidth);
const desiredMinWidth = Math.min(160, safeMaxWidth || 160);
let width = Math.min(
Math.max(triggerRect.width, scrollWidth, desiredMinWidth),
safeMaxWidth || 320
);
const availableBelow = Math.max(
0,
viewportHeight - VIEWPORT_GUTTER - triggerRect.bottom - MENU_OFFSET
);
const availableAbove = Math.max(0, triggerRect.top - VIEWPORT_GUTTER - MENU_OFFSET);
const viewportAllowance = Math.max(0, viewportHeight - VIEWPORT_GUTTER * 2);
const fallbackAllowance = Math.max(1, viewportAllowance > 0 ? viewportAllowance : scrollHeight);
function computePlacement(placement: 'top' | 'bottom') {
const available = placement === 'bottom' ? availableBelow : availableAbove;
const allowedHeight =
available > 0 ? Math.min(available, fallbackAllowance) : fallbackAllowance;
const maxHeight = Math.min(scrollHeight, allowedHeight);
const height = Math.max(0, maxHeight);
let top: number;
if (placement === 'bottom') {
const rawTop = triggerRect.bottom + MENU_OFFSET;
const minTop = VIEWPORT_GUTTER;
const maxTop = viewportHeight - VIEWPORT_GUTTER - height;
if (maxTop < minTop) {
top = minTop;
} else {
top = Math.min(Math.max(rawTop, minTop), maxTop);
}
const currentPos = compatibleIndices.indexOf(highlightedIndex);
if (currentPos === -1 || currentPos === compatibleIndices.length - 1) {
highlightedIndex = compatibleIndices[0];
} else {
const rawTop = triggerRect.top - MENU_OFFSET - height;
const minTop = VIEWPORT_GUTTER;
const maxTop = viewportHeight - VIEWPORT_GUTTER - height;
if (maxTop < minTop) {
top = minTop;
} else {
top = Math.max(Math.min(rawTop, maxTop), minTop);
highlightedIndex = compatibleIndices[currentPos + 1];
}
} else if (event.key === 'ArrowUp') {
event.preventDefault();
if (compatibleIndices.length === 0) return;
const currentPos = compatibleIndices.indexOf(highlightedIndex);
if (currentPos === -1 || currentPos === 0) {
highlightedIndex = compatibleIndices[compatibleIndices.length - 1];
} else {
highlightedIndex = compatibleIndices[currentPos - 1];
}
} else if (event.key === 'Enter') {
event.preventDefault();
if (highlightedIndex >= 0 && highlightedIndex < filteredOptions.length) {
const option = filteredOptions[highlightedIndex];
if (isModelCompatible(option)) {
handleSelect(option.id);
}
}
return { placement, top, height, maxHeight };
}
const belowMetrics = computePlacement('bottom');
const aboveMetrics = computePlacement('top');
let metrics = belowMetrics;
if (scrollHeight > belowMetrics.maxHeight && aboveMetrics.maxHeight > belowMetrics.maxHeight) {
metrics = aboveMetrics;
}
let left = triggerRect.right - width;
const maxLeft = viewportWidth - VIEWPORT_GUTTER - width;
if (maxLeft < VIEWPORT_GUTTER) {
left = VIEWPORT_GUTTER;
} else {
if (left > maxLeft) {
left = maxLeft;
}
if (left < VIEWPORT_GUTTER) {
left = VIEWPORT_GUTTER;
} else if (compatibleIndices.length > 0) {
// No selection - highlight first compatible option
highlightedIndex = compatibleIndices[0];
}
}
menuPosition = {
top: Math.round(metrics.top),
left: Math.round(left),
width: Math.round(width),
placement: metrics.placement,
maxHeight: Math.round(metrics.maxHeight)
};
}
async function handleSelect(modelId: string) {
@@ -356,6 +293,14 @@
if (shouldCloseMenu) {
closeMenu();
// Focus the chat textarea after model selection
requestAnimationFrame(() => {
const textarea = document.querySelector<HTMLTextAreaElement>(
'[data-slot="chat-form"] textarea'
);
textarea?.focus();
});
}
}
@@ -404,10 +349,7 @@
}
</script>
<svelte:window onresize={handleResize} />
<svelte:document onpointerdown={handlePointerDown} onkeydown={handleKeydown} />
<div class={cn('relative inline-flex flex-col items-end gap-1', className)} bind:this={container}>
<div class={cn('relative inline-flex flex-col items-end gap-1', className)}>
{#if loading && options.length === 0 && isRouter}
<div class="flex items-center gap-2 text-xs text-muted-foreground">
<Loader2 class="h-3.5 w-3.5 animate-spin" />
@@ -418,9 +360,8 @@
{:else}
{@const selectedOption = getDisplayOption()}
<div class="relative">
<button
type="button"
<Popover.Root bind:open={isOpen} onOpenChange={handleOpenChange}>
<Popover.Trigger
class={cn(
`inline-flex cursor-pointer items-center gap-1.5 rounded-sm bg-muted-foreground/10 px-1.5 py-1 text-xs transition hover:text-foreground focus:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-60`,
!isCurrentModelInCache()
@@ -430,15 +371,11 @@
: isHighlightedCurrentModelActive
? 'text-foreground'
: 'text-muted-foreground',
isOpen ? 'text-foreground' : '',
className
isOpen ? 'text-foreground' : ''
)}
style="max-width: min(calc(100cqw - 6.5rem), 32rem)"
aria-haspopup={isRouter ? 'listbox' : undefined}
aria-expanded={isRouter ? isOpen : undefined}
onclick={toggleOpen}
bind:this={triggerButton}
disabled={disabled || updating}
onclick={handleTriggerClick}
disabled={disabled || updating || !isRouter}
>
<Package class="h-3.5 w-3.5" />
@@ -451,33 +388,35 @@
{:else if isRouter}
<ChevronDown class="h-3 w-3.5" />
{/if}
</button>
</Popover.Trigger>
{#if isOpen && isRouter}
<div
bind:this={menuRef}
use:portalToBody
class={cn(
'fixed z-[1000] overflow-hidden rounded-md border bg-popover shadow-lg transition-opacity',
menuPosition ? 'opacity-100' : 'pointer-events-none opacity-0'
)}
role="listbox"
style:top={menuPosition ? `${menuPosition.top}px` : undefined}
style:left={menuPosition ? `${menuPosition.left}px` : undefined}
style:width={menuPosition ? `${menuPosition.width}px` : undefined}
data-placement={menuPosition?.placement ?? 'bottom'}
>
<Popover.Content
class="group/popover-content w-96 max-w-[calc(100vw-2rem)] p-0"
align="end"
sideOffset={8}
collisionPadding={16}
>
<div class="flex max-h-[50dvh] flex-col overflow-hidden">
<div
class="overflow-y-auto py-1"
style:max-height={menuPosition && menuPosition.maxHeight > 0
? `${menuPosition.maxHeight}px`
: undefined}
class="order-1 shrink-0 border-b p-4 group-data-[side=top]/popover-content:order-2 group-data-[side=top]/popover-content:border-t group-data-[side=top]/popover-content:border-b-0"
>
<SearchInput
id="model-search"
placeholder="Search models..."
bind:value={searchTerm}
bind:ref={searchInputRef}
onClose={closeMenu}
onKeyDown={handleSearchKeyDown}
/>
</div>
<div
class="models-list order-2 min-h-0 flex-1 overflow-y-auto group-data-[side=top]/popover-content:order-1"
>
{#if !isCurrentModelInCache() && currentModel}
<!-- Show unavailable model as first option (disabled) -->
<button
type="button"
class="flex w-full cursor-not-allowed items-center bg-red-400/10 px-3 py-2 text-left text-sm text-red-400"
class="flex w-full cursor-not-allowed items-center bg-red-400/10 px-4 py-2 text-left text-sm text-red-400"
role="option"
aria-selected="true"
aria-disabled="true"
@@ -488,20 +427,25 @@
</button>
<div class="my-1 h-px bg-border"></div>
{/if}
{#each options as option (option.id)}
{#if filteredOptions.length === 0}
<p class="px-4 py-3 text-sm text-muted-foreground">No models found.</p>
{/if}
{#each filteredOptions as option, index (option.id)}
{@const status = getModelStatus(option.model)}
{@const isLoaded = status === ServerModelStatus.LOADED}
{@const isLoading = status === ServerModelStatus.LOADING}
{@const isSelected = currentModel === option.model || activeId === option.id}
{@const isCompatible = isModelCompatible(option)}
{@const isHighlighted = index === highlightedIndex}
{@const missingModalities = getMissingModalities(option)}
<div
class={cn(
'group flex w-full items-center gap-2 px-3 py-2 text-left text-sm transition focus:outline-none',
'group flex w-full items-center gap-2 px-4 py-2 text-left text-sm transition focus:outline-none',
isCompatible
? 'cursor-pointer hover:bg-muted focus:bg-muted'
: 'cursor-not-allowed opacity-50',
isSelected
isSelected || isHighlighted
? 'bg-accent text-accent-foreground'
: isCompatible
? 'hover:bg-accent hover:text-accent-foreground'
@@ -509,10 +453,11 @@
isLoaded ? 'text-popover-foreground' : 'text-muted-foreground'
)}
role="option"
aria-selected={isSelected}
aria-selected={isSelected || isHighlighted}
aria-disabled={!isCompatible}
tabindex={isCompatible ? 0 : -1}
onclick={() => isCompatible && handleSelect(option.id)}
onmouseenter={() => (highlightedIndex = index)}
onkeydown={(e) => {
if (isCompatible && (e.key === 'Enter' || e.key === ' ')) {
e.preventDefault();
@@ -586,8 +531,8 @@
{/each}
</div>
</div>
{/if}
</div>
</Popover.Content>
</Popover.Root>
{/if}
</div>
@@ -0,0 +1,19 @@
import Root from './popover.svelte';
import Close from './popover-close.svelte';
import Content from './popover-content.svelte';
import Trigger from './popover-trigger.svelte';
import Portal from './popover-portal.svelte';
export {
Root,
Content,
Trigger,
Close,
Portal,
//
Root as Popover,
Content as PopoverContent,
Trigger as PopoverTrigger,
Close as PopoverClose,
Portal as PopoverPortal
};
@@ -0,0 +1,7 @@
<script lang="ts">
import { Popover as PopoverPrimitive } from 'bits-ui';
let { ref = $bindable(null), ...restProps }: PopoverPrimitive.CloseProps = $props();
</script>
<PopoverPrimitive.Close bind:ref data-slot="popover-close" {...restProps} />
@@ -0,0 +1,37 @@
<script lang="ts">
import { Popover as PopoverPrimitive } from 'bits-ui';
import PopoverPortal from './popover-portal.svelte';
import { cn, type WithoutChildrenOrChild } from '$lib/components/ui/utils.js';
import type { ComponentProps } from 'svelte';
let {
ref = $bindable(null),
class: className,
sideOffset = 4,
side,
align = 'center',
collisionPadding = 8,
avoidCollisions = true,
portalProps,
...restProps
}: PopoverPrimitive.ContentProps & {
portalProps?: WithoutChildrenOrChild<ComponentProps<typeof PopoverPortal>>;
} = $props();
</script>
<PopoverPortal {...portalProps}>
<PopoverPrimitive.Content
bind:ref
data-slot="popover-content"
{sideOffset}
{side}
{align}
{collisionPadding}
{avoidCollisions}
class={cn(
'z-50 w-72 origin-(--bits-popover-content-transform-origin) rounded-md border bg-popover p-4 text-popover-foreground shadow-md outline-hidden data-[side=bottom]:slide-in-from-top-2 data-[side=left]:slide-in-from-end-2 data-[side=right]:slide-in-from-start-2 data-[side=top]:slide-in-from-bottom-2 data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=closed]:zoom-out-95 data-[state=open]:animate-in data-[state=open]:fade-in-0 data-[state=open]:zoom-in-95',
className
)}
{...restProps}
/>
</PopoverPortal>
@@ -0,0 +1,7 @@
<script lang="ts">
import { Popover as PopoverPrimitive } from 'bits-ui';
let { ...restProps }: PopoverPrimitive.PortalProps = $props();
</script>
<PopoverPrimitive.Portal {...restProps} />
@@ -0,0 +1,17 @@
<script lang="ts">
import { cn } from '$lib/components/ui/utils.js';
import { Popover as PopoverPrimitive } from 'bits-ui';
let {
ref = $bindable(null),
class: className,
...restProps
}: PopoverPrimitive.TriggerProps = $props();
</script>
<PopoverPrimitive.Trigger
bind:ref
data-slot="popover-trigger"
class={cn('', className)}
{...restProps}
/>
@@ -0,0 +1,7 @@
<script lang="ts">
import { Popover as PopoverPrimitive } from 'bits-ui';
let { open = $bindable(false), ...restProps }: PopoverPrimitive.RootProps = $props();
</script>
<PopoverPrimitive.Root bind:open {...restProps} />
@@ -1,3 +1,2 @@
export const VIEWPORT_GUTTER = 8;
export const MENU_OFFSET = 6;
export const MENU_MAX_WIDTH = 320;
@@ -295,14 +295,21 @@ class ModelsStore {
* Fetch props for a specific model from /props endpoint
* Uses caching to avoid redundant requests
*
* In ROUTER mode, this will only fetch props if the model is loaded,
* since unloaded models return 400 from /props endpoint.
*
* @param modelId - Model identifier to fetch props for
* @returns Props data or null if fetch failed
* @returns Props data or null if fetch failed or model not loaded
*/
async fetchModelProps(modelId: string): Promise<ApiLlamaCppServerProps | null> {
// Return cached props if available
const cached = this.modelPropsCache.get(modelId);
if (cached) return cached;
if (serverStore.isRouterMode && !this.isModelLoaded(modelId)) {
return null;
}
// Avoid duplicate fetches
if (this.modelPropsFetching.has(modelId)) return null;
@@ -303,6 +303,27 @@ $$\n\\pi_n(\\mathbb{S}^3) = \\begin{cases}
expect(output).toBe(input); // Code blocks prevent misinterpretation
});
test('preserves backslash parentheses in code blocks (GitHub issue)', () => {
const input = '```python\nfoo = "\\(bar\\)"\n```';
const output = preprocessLaTeX(input);
expect(output).toBe(input); // Code blocks should not have LaTeX conversion applied
});
test('preserves backslash brackets in code blocks', () => {
const input = '```python\nfoo = "\\[bar\\]"\n```';
const output = preprocessLaTeX(input);
expect(output).toBe(input); // Code blocks should not have LaTeX conversion applied
});
test('preserves backslash parentheses in inline code', () => {
const input = 'Use `foo = "\\(bar\\)"` in your code.';
const output = preprocessLaTeX(input);
expect(output).toBe(input);
});
test('escape backslash in mchem ce', () => {
const input = 'mchem ce:\n$\\ce{2H2(g) + O2(g) -> 2H2O(l)}$';
const output = preprocessLaTeX(input);
@@ -226,19 +226,16 @@ export function preprocessLaTeX(content: string): string {
return expr;
});
// Step 5: Restore code blocks
content = content.replace(/<<CODE_BLOCK_(\d+)>>/g, (_, index) => {
return codeBlocks[parseInt(index)];
});
// Step 6: Apply additional escaping functions (brackets and mhchem)
// Step 5: Apply additional escaping functions (brackets and mhchem)
// This must happen BEFORE restoring code blocks to avoid affecting code content
content = escapeBrackets(content);
if (doEscapeMhchem && (content.includes('\\ce{') || content.includes('\\pu{'))) {
content = escapeMhchem(content);
}
// Final pass: Convert \(...\) → $...$, \[...\] → $$...$$
// Step 6: Convert remaining \(...\) → $...$, \[...\] → $$...$$
// This must happen BEFORE restoring code blocks to avoid affecting code content
content = content
// Using the lookbehind pattern `(?<!\\)` we skip matches
// that are preceded by a backslash, e.g.
@@ -248,12 +245,18 @@ export function preprocessLaTeX(content: string): string {
// Using the lookbehind pattern `(?<!\\)` we skip matches
// that are preceded by a backslash, e.g. `\\[4pt]`.
/(?<!\\)\\\[([\s\S]*?)\\\]/g, // display, see also PR #16599
(_, prefix: string, content: string) => {
return `${prefix}$$${content}$$`;
(_, content: string) => {
return `$$${content}$$`;
}
);
// Step 7: Restore blockquote markers
// Step 7: Restore code blocks
// This happens AFTER all LaTeX conversions to preserve code content
content = content.replace(/<<CODE_BLOCK_(\d+)>>/g, (_, index) => {
return codeBlocks[parseInt(index)];
});
// Step 8: Restore blockquote markers
if (blockquoteMarkers.size > 0) {
const finalLines = content.split('\n');
const restoredLines = finalLines.map((line, index) => {