fix(llama-cpp): terminate tensor_buft_overrides with sentinel (#9919)

llama.cpp's model loader asserts back().pattern == nullptr on
params.tensor_buft_overrides (and on params.kv_overrides.back().key[0]
== 0) before binding them into llama_model_params. PR #8560 attempted
to satisfy llama_params_fit's placeholder requirement by pre-filling
params.tensor_buft_overrides up to llama_max_tensor_buft_overrides()
*before* the option-parse loop. Any subsequent push_back from
override_tensor / draft_cpu_moe / draft_n_cpu_moe / draft_override_tensor
then appended real entries after the placeholders, leaving back() with
a real pattern and tripping the assert. The draft override vector
likewise had no terminator at all.

Mirror upstream common/arg.cpp:645-658 instead: real entries are
pushed during option parsing, and after parsing we pad the main vector
up to ntbo (placeholders land at the end, so back() is always nullptr)
and append a single {nullptr, nullptr} to the draft vector when it is
non-empty. The existing kv_overrides terminator block already matches
upstream and stays.

Verified against ggml-org/llama.cpp@5cbaa5e: only tensor_buft_overrides
(main + draft) and kv_overrides are sentinel-terminated common_params
fields; everything else is size-driven std::vector.

Assisted-by: claude-code:claude-opus-4-7

Signed-off-by: Richard Palethorpe <io@richiejp.com>

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=599e49d253971451f710cb8323344e789906ed6c
+# Upstream pin lives below as DS4_VERSION?=2606543be7a8c125a32cee37f5d1d85dc78f2fcf
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=599e49d253971451f710cb8323344e789906ed6c
+DS4_VERSION?=2606543be7a8c125a32cee37f5d1d85dc78f2fcf
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=77413bc900f9a2bfd8a5407f184427bcc0825f6c
+IK_LLAMA_VERSION?=11a1fea9e291f12ce2c803a9d7812c30ca806bcf
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=67ace021da905e27ecbdf1176b0eef578a5288c0
+LLAMA_VERSION?=ad277572619fcfb6ddd38f4c6437283a4b2b8636
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -522,12 +522,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
     // n_ctx_checkpoints: max context checkpoints per slot (default: 8)
     params.n_ctx_checkpoints = 8;
 
-    // llama memory fit fails if we don't provide a buffer for tensor overrides
-    const size_t ntbo = llama_max_tensor_buft_overrides();
-    while (params.tensor_buft_overrides.size() < ntbo) {
-        params.tensor_buft_overrides.push_back({nullptr, nullptr});
-    }
-
      // decode options. Options are in form optname:optvale, or if booleans only optname.
     for (int i = 0; i < request->options_size(); i++) {
         std::string opt = request->options(i);
@@ -1081,6 +1075,20 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
         params.kv_overrides.back().key[0] = 0;
     }
 
+    // tensor_buft_overrides sentinel termination (mirrors upstream common/arg.cpp).
+    // Real entries are pushed during option parsing; here we pad/terminate so the
+    // model loader sees back().pattern == nullptr (GGML_ASSERT at common.cpp:1543)
+    // and so llama_params_fit has the placeholder slots it requires.
+    {
+        const size_t ntbo = llama_max_tensor_buft_overrides();
+        while (params.tensor_buft_overrides.size() < ntbo) {
+            params.tensor_buft_overrides.push_back({nullptr, nullptr});
+        }
+    }
+    if (!params.speculative.draft.tensor_buft_overrides.empty()) {
+        params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
+    }
+
     // TODO: Add yarn
 
     if (!request->tensorsplit().empty()) {

backend/go/acestep-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # acestep.cpp version
 ACESTEP_REPO?=https://github.com/ace-step/acestep.cpp
-ACESTEP_CPP_VERSION?=e0c8d75a672fca5684c88c68dbf6d12f58754258
+ACESTEP_CPP_VERSION?=ed53caf164e4492a5620b2e3f2264629cf66da24
 SO_TARGET?=libgoacestepcpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/acestep-cpp/cpp/goacestepcpp.cpp

@@ -22,12 +22,11 @@
 #include <vector>
 
 // Global model contexts (loaded once, reused across requests)
-static DiTGGML       g_dit       = {};
-static DiTGGMLConfig g_dit_cfg;
-static VAEGGML       g_vae       = {};
-static bool          g_dit_loaded = false;
-static bool          g_vae_loaded = false;
-static bool          g_is_turbo   = false;
+static DiTGGML g_dit        = {};
+static VAEGGML g_vae        = {};
+static bool    g_dit_loaded = false;
+static bool    g_vae_loaded = false;
+static bool    g_is_turbo   = false;
 
 // Silence latent [15000, 64] — read once from DiT GGUF
 static std::vector<float> g_silence_full;
@@ -72,10 +71,9 @@ int load_model(const char * lm_model_path, const char * text_encoder_path,
     g_text_enc_path = text_encoder_path;
     g_dit_path      = dit_model_path;
 
-    // Load DiT model
+    // Load DiT model (backend init + config are handled inside dit_ggml_load)
     fprintf(stderr, "[acestep-cpp] Loading DiT from %s\n", dit_model_path);
-    dit_ggml_init_backend(&g_dit);
-    if (!dit_ggml_load(&g_dit, dit_model_path, g_dit_cfg, nullptr, 0.0f)) {
+    if (!dit_ggml_load(&g_dit, dit_model_path)) {
         fprintf(stderr, "[acestep-cpp] FATAL: failed to load DiT from %s\n", dit_model_path);
         return 1;
     }
@@ -149,16 +147,16 @@ int generate_music(const char * caption, const char * lyrics, int bpm,
 
     // Compute T (latent frames at 25Hz)
     int T = (int)(duration * FRAMES_PER_SECOND);
-    T     = ((T + g_dit_cfg.patch_size - 1) / g_dit_cfg.patch_size) * g_dit_cfg.patch_size;
-    int S = T / g_dit_cfg.patch_size;
+    T     = ((T + g_dit.cfg.patch_size - 1) / g_dit.cfg.patch_size) * g_dit.cfg.patch_size;
+    int S = T / g_dit.cfg.patch_size;
 
     if (T > 15000) {
         fprintf(stderr, "[acestep-cpp] ERROR: T=%d exceeds max 15000\n", T);
         return 2;
     }
 
-    int Oc     = g_dit_cfg.out_channels;      // 64
-    int ctx_ch = g_dit_cfg.in_channels - Oc;  // 128
+    int Oc     = g_dit.cfg.out_channels;      // 64
+    int ctx_ch = g_dit.cfg.in_channels - Oc;  // 128
 
     fprintf(stderr, "[acestep-cpp] T=%d, S=%d, duration=%.1fs, seed=%d\n", T, S, duration, seed);
 
@@ -191,9 +189,8 @@ int generate_music(const char * caption, const char * lyrics, int bpm,
 
     fprintf(stderr, "[acestep-cpp] caption: %d tokens, lyrics: %d tokens\n", S_text, S_lyric);
 
-    // 4. Text encoder forward
+    // 4. Text encoder forward (backend init handled inside qwen3_load_text_encoder)
     Qwen3GGML text_enc = {};
-    qwen3_init_backend(&text_enc);
     if (!qwen3_load_text_encoder(&text_enc, g_text_enc_path.c_str())) {
         fprintf(stderr, "[acestep-cpp] FATAL: failed to load text encoder\n");
         return 4;
@@ -209,9 +206,8 @@ int generate_music(const char * caption, const char * lyrics, int bpm,
     std::vector<float> lyric_embed(H_text * S_lyric);
     qwen3_embed_lookup(&text_enc, lyric_ids.data(), S_lyric, lyric_embed.data());
 
-    // 6. Condition encoder
+    // 6. Condition encoder (backend init handled inside cond_ggml_load)
     CondGGML cond = {};
-    cond_ggml_init_backend(&cond);
     if (!cond_ggml_load(&cond, g_dit_path.c_str())) {
         fprintf(stderr, "[acestep-cpp] FATAL: failed to load condition encoder\n");
         qwen3_free(&text_enc);

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=bd17f53b7386fb5f60e8587b75e73c4b2fed3426
+STABLEDIFFUSION_GGML_VERSION?=5b0267e941cade15bd80089d89838795d9f4baa6
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/stablediffusion-ggml/cpp/gosd.cpp

@@ -1188,6 +1188,9 @@ int gen_video(sd_vid_gen_params_t *p, int steps, char *dst, float cfg_scale, int
     p->high_noise_sample_params.scheduler                = scheduler;
     p->high_noise_sample_params.flow_shift               = flow_shift;
 
+    // Pin output fps in params; upstream uses it for audio sync (and we also mux at this rate).
+    p->fps = fps;
+
     // Load init/end reference images if provided (resized to output dims).
     uint8_t* init_buf = nullptr;
     uint8_t* end_buf  = nullptr;
@@ -1206,11 +1209,14 @@ int gen_video(sd_vid_gen_params_t *p, int steps, char *dst, float cfg_scale, int
 
     // Generate
     int num_frames_out = 0;
-    sd_image_t* frames = generate_video(sd_c, p, &num_frames_out);
+    sd_image_t* frames = nullptr;
+    sd_audio_t* audio = nullptr;
+    bool ok = generate_video(sd_c, p, &frames, &num_frames_out, &audio);
     std::free(p);
 
-    if (!frames || num_frames_out == 0) {
+    if (!ok || !frames || num_frames_out == 0) {
         fprintf(stderr, "generate_video produced no frames\n");
+        if (audio) free_sd_audio(audio);
         if (init_buf) free(init_buf);
         if (end_buf) free(end_buf);
         return 1;
@@ -1224,6 +1230,7 @@ int gen_video(sd_vid_gen_params_t *p, int steps, char *dst, float cfg_scale, int
         if (frames[i].data) free(frames[i].data);
     }
     free(frames);
+    if (audio) free_sd_audio(audio);
     if (init_buf) free(init_buf);
     if (end_buf) free(end_buf);
 

backend/python/transformers/requirements-cpu.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
-transformers>=5.8.0
+transformers>=5.8.1
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

backend/python/transformers/requirements-cublas12.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 accelerate
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.0
+transformers>=5.8.1
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

backend/python/transformers/requirements-cublas13.txt

@@ -2,9 +2,9 @@
 torch==2.9.0
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.0
+transformers>=5.8.1
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

backend/python/transformers/requirements-hipblas.txt

@@ -1,11 +1,11 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
 torch==2.10.0+rocm7.0
 accelerate
-transformers>=5.8.0
+transformers>=5.8.1
 llvmlite==0.43.0
 numba==0.60.0
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

backend/python/transformers/requirements-intel.txt

@@ -3,9 +3,9 @@ torch
 optimum[openvino]
 llvmlite==0.43.0
 numba==0.60.0
-transformers>=5.8.0
+transformers>=5.8.1
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

backend/python/transformers/requirements-mps.txt

@@ -2,9 +2,9 @@ torch==2.7.1
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
-transformers>=5.8.0
+transformers>=5.8.1
 bitsandbytes
-sentence-transformers==5.4.0
+sentence-transformers==5.5.0
 diffusers
 soundfile
 protobuf==6.33.5

core/http/react-ui/e2e/chat-polling-selection.spec.js

@@ -0,0 +1,143 @@
+import { test, expect } from '@playwright/test'
+
+// Regression coverage for issue #9904:
+// - /api/operations was polled every 1s and *always* re-rendered the Chat
+//   page, even when the response was unchanged. The reconciliation would
+//   collapse any text selection inside an assistant message.
+// - The copy button next to each assistant message used navigator.clipboard
+//   without any fallback, which is undefined when the page is served over
+//   plain http (non-secure context) from a remote host.
+
+async function setupChatPage(page) {
+  await page.route('**/api/models/capabilities', (route) => {
+    route.fulfill({
+      contentType: 'application/json',
+      body: JSON.stringify({
+        data: [{ id: 'test-model', capabilities: ['FLAG_CHAT'] }],
+      }),
+    })
+  })
+
+  // Poll-tracking mock: assert the hook is hammering /api/operations every
+  // ~1s, and always return an empty list so its contents never change.
+  let operationsHits = 0
+  await page.route('**/api/operations', (route) => {
+    operationsHits++
+    route.fulfill({
+      contentType: 'application/json',
+      body: JSON.stringify({ operations: [] }),
+    })
+  })
+
+  await page.route('**/v1/chat/completions', (route) => {
+    // One short SSE stream so the chat finishes streaming quickly and we
+    // can interact with a stable assistant message.
+    const body = [
+      'data: {"choices":[{"delta":{"content":"Hello world this is a long assistant reply that we can try to select."},"index":0}]}\n\n',
+      'data: {"choices":[{"delta":{},"index":0,"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1,"total_tokens":2}}\n\n',
+      'data: [DONE]\n\n',
+    ].join('')
+    route.fulfill({
+      status: 200,
+      headers: { 'Content-Type': 'text/event-stream' },
+      body,
+    })
+  })
+
+  return { getOperationsHits: () => operationsHits }
+}
+
+test.describe('Chat - /api/operations polling (#9904)', () => {
+  test('text selection inside an assistant message survives polling', async ({ page }) => {
+    const { getOperationsHits } = await setupChatPage(page)
+
+    await page.goto('/app/chat')
+    await expect(page.getByRole('button', { name: 'test-model' })).toBeVisible({ timeout: 10_000 })
+
+    await page.locator('.chat-input').fill('Hi')
+    await page.locator('.chat-send-btn').click()
+
+    const assistantContent = page.locator('.chat-message-assistant .chat-message-content').first()
+    await expect(assistantContent).toContainText('Hello world', { timeout: 10_000 })
+
+    // Sanity check: the polling we're regressing against is actually firing.
+    await page.waitForTimeout(2_500)
+    expect(getOperationsHits()).toBeGreaterThan(1)
+
+    // Sanity check that the bug we're guarding against is structurally
+    // possible: count how many times the assistant content node gets
+    // *touched* by React (childList / characterData mutations) over a
+    // 3-second window. Before the fix, every poll re-rendered Chat and
+    // re-set dangerouslySetInnerHTML, triggering a mutation cascade that
+    // collapsed the user's text selection. After the fix, polling with
+    // identical contents must not mutate the DOM at all.
+    const mutationCount = await assistantContent.evaluate((el) => new Promise((resolve) => {
+      let count = 0
+      const obs = new MutationObserver((records) => { count += records.length })
+      obs.observe(el, { childList: true, subtree: true, characterData: true })
+      setTimeout(() => { obs.disconnect(); resolve(count) }, 3_000)
+    }))
+    expect(mutationCount).toBe(0)
+
+    // Same sanity check translated to a user-observable property: a
+    // programmatically created selection survives the polling window.
+    await assistantContent.evaluate((el) => {
+      const range = document.createRange()
+      range.selectNodeContents(el)
+      const sel = window.getSelection()
+      sel.removeAllRanges()
+      sel.addRange(range)
+    })
+
+    const initialSelection = await page.evaluate(() => window.getSelection().toString())
+    expect(initialSelection).toContain('Hello world')
+
+    await page.waitForTimeout(2_500)
+
+    const selectionAfterPolling = await page.evaluate(() => window.getSelection().toString())
+    expect(selectionAfterPolling).toBe(initialSelection)
+  })
+})
+
+test.describe('Chat - copy button (#9904)', () => {
+  test('copy button works when navigator.clipboard is unavailable (plain http)', async ({ page }) => {
+    await setupChatPage(page)
+
+    // Simulate a non-secure context: hide navigator.clipboard before any of
+    // our app code touches it. This mirrors what browsers do over plain
+    // http from a remote host.
+    await page.addInitScript(() => {
+      Object.defineProperty(window, 'isSecureContext', { value: false, configurable: true })
+      try {
+        Object.defineProperty(navigator, 'clipboard', { value: undefined, configurable: true })
+      } catch { /* some browsers refuse — the secure-context flag is enough */ }
+    })
+
+    await page.goto('/app/chat')
+    await expect(page.getByRole('button', { name: 'test-model' })).toBeVisible({ timeout: 10_000 })
+
+    await page.locator('.chat-input').fill('Hi')
+    await page.locator('.chat-send-btn').click()
+
+    const assistantBubble = page.locator('.chat-message-assistant .chat-message-bubble').first()
+    await expect(assistantBubble).toContainText('Hello world', { timeout: 10_000 })
+
+    // Spy on document.execCommand so we can confirm the fallback path ran.
+    await page.evaluate(() => {
+      window.__execCommandCalls = []
+      const original = document.execCommand?.bind(document)
+      document.execCommand = (cmd, ...rest) => {
+        window.__execCommandCalls.push(cmd)
+        // execCommand('copy') in a headless browser may return false because
+        // there is no real clipboard, but the fact that we tried is what we
+        // care about for this regression.
+        return original ? original(cmd, ...rest) : false
+      }
+    })
+
+    await assistantBubble.locator('.chat-message-actions button').first().click()
+
+    const execCommandCalls = await page.evaluate(() => window.__execCommandCalls)
+    expect(execCommandCalls).toContain('copy')
+  })
+})

core/http/react-ui/public/locales/de/chat.json

@@ -97,7 +97,8 @@
   },
   "toasts": {
     "selectModel": "Bitte wählen Sie ein Modell",
-    "copied": "In die Zwischenablage kopiert"
+    "copied": "In die Zwischenablage kopiert",
+    "copyFailed": "Kopieren in die Zwischenablage fehlgeschlagen"
   },
   "menu": {
     "trigger": "Chats",

core/http/react-ui/public/locales/en/chat.json

@@ -97,7 +97,8 @@
   },
   "toasts": {
     "selectModel": "Please select a model",
-    "copied": "Copied to clipboard"
+    "copied": "Copied to clipboard",
+    "copyFailed": "Could not copy to clipboard"
   },
   "menu": {
     "trigger": "Chats",

core/http/react-ui/public/locales/es/chat.json

@@ -97,7 +97,8 @@
   },
   "toasts": {
     "selectModel": "Por favor selecciona un modelo",
-    "copied": "Copiado al portapapeles"
+    "copied": "Copiado al portapapeles",
+    "copyFailed": "No se pudo copiar al portapapeles"
   },
   "menu": {
     "trigger": "Chats",

core/http/react-ui/public/locales/it/chat.json

@@ -97,7 +97,8 @@
   },
   "toasts": {
     "selectModel": "Seleziona un modello",
-    "copied": "Copiato negli appunti"
+    "copied": "Copiato negli appunti",
+    "copyFailed": "Impossibile copiare negli appunti"
   },
   "menu": {
     "trigger": "Chat",

core/http/react-ui/public/locales/zh-CN/chat.json

@@ -97,7 +97,8 @@
   },
   "toasts": {
     "selectModel": "请选择一个模型",
-    "copied": "已复制到剪贴板"
+    "copied": "已复制到剪贴板",
+    "copyFailed": "无法复制到剪贴板"
   },
   "menu": {
     "trigger": "聊天",

core/http/react-ui/src/components/CanvasPanel.jsx

@@ -2,6 +2,7 @@ import { useState, useEffect, useRef } from 'react'
 import { renderMarkdown } from '../utils/markdown'
 import { getArtifactIcon } from '../utils/artifacts'
 import { safeHref } from '../utils/url'
+import { copyToClipboard } from '../utils/clipboard'
 import DOMPurify from 'dompurify'
 import hljs from 'highlight.js'
 
@@ -23,11 +24,13 @@ export default function CanvasPanel({ artifacts, selectedId, onSelect, onClose }
     }
   }, [current, showPreview])
 
-  const handleCopy = () => {
+  const handleCopy = async () => {
     const text = current.code || current.url || ''
-    navigator.clipboard.writeText(text)
-    setCopySuccess(true)
-    setTimeout(() => setCopySuccess(false), 2000)
+    const ok = await copyToClipboard(text)
+    if (ok) {
+      setCopySuccess(true)
+      setTimeout(() => setCopySuccess(false), 2000)
+    }
   }
 
   const handleDownload = () => {

core/http/react-ui/src/hooks/useOperations.js

@@ -2,6 +2,14 @@ import { useState, useEffect, useCallback, useRef } from 'react'
 import { operationsApi } from '../utils/api'
 import { useAuth } from '../context/AuthContext'
 
+// Serialize ops into a stable comparison key. Each op is a flat map of
+// primitives, so JSON.stringify is good enough and stable as long as the
+// server emits keys in the same order (Go's map iteration into JSON happens
+// to be stable here because we build an explicit map[string]any).
+function serializeOps(ops) {
+  return JSON.stringify(ops)
+}
+
 export function useOperations(pollInterval = 1000) {
   const [operations, setOperations] = useState([])
   const [loading, setLoading] = useState(true)
@@ -11,16 +19,26 @@ export function useOperations(pollInterval = 1000) {
 
   const previousCountRef = useRef(0)
   const onAllCompleteRef = useRef(null)
+  // Track the last payload we wrote into state. Each poll otherwise produces
+  // a fresh array reference even when nothing changed, and that re-render
+  // ripples into the Chat page — wiping the user's text selection mid-read
+  // (#9904).
+  const lastSerializedRef = useRef('[]')
 
   const fetchOperations = useCallback(async () => {
     if (!isAdmin) {
-      setLoading(false)
+      setLoading((prev) => (prev ? false : prev))
       return
     }
     try {
       const data = await operationsApi.list()
       const ops = data?.operations || (Array.isArray(data) ? data : [])
-      setOperations(ops)
+
+      const serialized = serializeOps(ops)
+      if (serialized !== lastSerializedRef.current) {
+        lastSerializedRef.current = serialized
+        setOperations(ops)
+      }
 
       // Separate active (non-failed) operations from failed ones
       const activeOps = ops.filter(op => !op.error)
@@ -32,11 +50,11 @@ export function useOperations(pollInterval = 1000) {
       }
       previousCountRef.current = activeOps.length
 
-      setError(null)
+      setError((prev) => (prev === null ? prev : null))
     } catch (err) {
-      setError(err.message)
+      setError((prev) => (prev === err.message ? prev : err.message))
     } finally {
-      setLoading(false)
+      setLoading((prev) => (prev ? false : prev))
     }
   }, [isAdmin])
 

core/http/react-ui/src/pages/AgentChat.jsx

@@ -9,6 +9,7 @@ import ResourceCards from '../components/ResourceCards'
 import ConfirmDialog from '../components/ConfirmDialog'
 import { useAgentChat } from '../hooks/useAgentChat'
 import { relativeTime } from '../utils/format'
+import { copyToClipboard } from '../utils/clipboard'
 
 function getLastMessagePreview(conv) {
   if (!conv.messages || conv.messages.length === 0) return ''
@@ -390,9 +391,13 @@ export default function AgentChat() {
     }
   }
 
-  const copyMessage = (content) => {
-    navigator.clipboard.writeText(content)
-    addToast('Copied to clipboard', 'success', 2000)
+  const copyMessage = async (content) => {
+    const ok = await copyToClipboard(content)
+    addToast(
+      ok ? 'Copied to clipboard' : 'Could not copy to clipboard',
+      ok ? 'success' : 'error',
+      ok ? 2000 : 3000,
+    )
   }
 
   const senderToRole = (sender) => {

core/http/react-ui/src/pages/Chat.jsx

@@ -17,6 +17,7 @@ import ChatsMenu from '../components/ChatsMenu'
 import { useAuth } from '../context/AuthContext'
 import { useOperations } from '../hooks/useOperations'
 import { relativeTime } from '../utils/format'
+import { copyToClipboard } from '../utils/clipboard'
 
 function getLastMessagePreview(chat) {
   if (!chat.history || chat.history.length === 0) return ''
@@ -798,10 +799,14 @@ export default function Chat() {
     }
   }
 
-  const copyMessage = (content) => {
+  const copyMessage = async (content) => {
     const text = typeof content === 'string' ? content : content?.[0]?.text || ''
-    navigator.clipboard.writeText(text)
-    addToast(t('toasts.copied'), 'success', 2000)
+    const ok = await copyToClipboard(text)
+    if (ok) {
+      addToast(t('toasts.copied'), 'success', 2000)
+    } else {
+      addToast(t('toasts.copyFailed'), 'error', 3000)
+    }
   }
 
   const contextPercent = getContextUsagePercent()

core/http/react-ui/src/utils/clipboard.js

@@ -0,0 +1,81 @@
+// Clipboard helper that works in non-secure contexts.
+//
+// navigator.clipboard is only defined on https:// origins and on
+// http://localhost. When LocalAI is served over plain http from a remote
+// host (LXC + Docker is a common deployment), every page that called
+// `navigator.clipboard.writeText` silently failed (#9904). This helper
+// transparently falls back to a hidden-textarea + execCommand('copy')
+// trick that browsers still honour when the page is not a secure context.
+//
+// Returns true on success, false on failure. Callers should use the return
+// value to drive the success/failure toast — the old code always claimed
+// success regardless of what actually happened.
+export async function copyToClipboard(text) {
+  if (text == null) return false
+  const value = typeof text === 'string' ? text : String(text)
+
+  if (typeof navigator !== 'undefined' && navigator.clipboard?.writeText && window.isSecureContext) {
+    try {
+      await navigator.clipboard.writeText(value)
+      return true
+    } catch {
+      // Permissions denied, browser refused, etc. — try the fallback.
+    }
+  }
+
+  return legacyCopy(value)
+}
+
+function legacyCopy(value) {
+  if (typeof document === 'undefined') return false
+  const ta = document.createElement('textarea')
+  ta.value = value
+  // Keep the textarea out of the viewport and out of layout reads. Using
+  // `position: fixed` + a negative offset avoids scrolling the page when
+  // we call .select() below.
+  ta.setAttribute('readonly', '')
+  ta.style.position = 'fixed'
+  ta.style.top = '0'
+  ta.style.left = '-9999px'
+  ta.style.opacity = '0'
+  document.body.appendChild(ta)
+  // Preserve the current selection so triggering execCommand doesn't blow
+  // away whatever the user had highlighted on the page.
+  const previousSelection = saveSelection()
+  let ok = false
+  try {
+    ta.select()
+    ta.setSelectionRange(0, value.length)
+    ok = document.execCommand('copy')
+  } catch {
+    ok = false
+  } finally {
+    document.body.removeChild(ta)
+    restoreSelection(previousSelection)
+  }
+  return ok
+}
+
+function saveSelection() {
+  try {
+    const sel = window.getSelection()
+    if (!sel || sel.rangeCount === 0) return null
+    const ranges = []
+    for (let i = 0; i < sel.rangeCount; i++) ranges.push(sel.getRangeAt(i).cloneRange())
+    return ranges
+  } catch {
+    return null
+  }
+}
+
+function restoreSelection(ranges) {
+  if (!ranges) return
+  try {
+    const sel = window.getSelection()
+    if (!sel) return
+    sel.removeAllRanges()
+    for (const r of ranges) sel.addRange(r)
+  } catch {
+    // best-effort
+  }
+}

gallery/index.yaml

@@ -1170,8 +1170,8 @@
       use_tokenizer_template: true
   files:
     - filename: llama-cpp/models/Qwen_Qwen3.5-35B-A3B-GGUF/Qwen_Qwen3.5-35B-A3B-Q4_K_M.gguf
-      sha256: ac15eef4c742ff7700cba697238b25832087b67578f213d5ea24c9e3a6dc4457
       uri: https://huggingface.co/bartowski/Qwen_Qwen3.5-35B-A3B-GGUF/resolve/main/Qwen_Qwen3.5-35B-A3B-Q4_K_M.gguf
+      sha256: 2f2df1e8b2e92b642c1850ea1734b341cc8ca5098c42cc0a8b8c436a8d4751ab
     - filename: llama-cpp/mmproj/Qwen_Qwen3.5-35B-A3B-GGUF/mmproj-Qwen_Qwen3.5-35B-A3B-f16.gguf
       sha256: 10cf13cb1f8434f30df8fa7e5bde98d542fbf397550cb489dfa9eb8ac7069035
       uri: https://huggingface.co/bartowski/Qwen_Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-Qwen_Qwen3.5-35B-A3B-f16.gguf