model : add KORMo model (#18032)

* vocab: add KORMo Tokenizer

* model: add KORMoForCausalLM

* vocab: change pretokenizer to qwen2

* lint: fix unintended line removal

* model: make qwen2 bias tensor optional

* model: use qwen2 architecture for KORMo

convert_hf_to_gguf.py

@@ -1203,6 +1203,9 @@ class TextModel(ModelBase):
         if chkhsh == "f4f37b6c8eb9ea29b3eac6bb8c8487c5ab7885f8d8022e67edc1c68ce8403e95":
             # ref: https://huggingface.co/MiniMaxAI/MiniMax-M2
             res = "minimax-m2"
+        if chkhsh == "4a2e2abae11ca2b86d570fc5b44be4d5eb5e72cc8f22dd136a94b37da83ab665":
+            # ref: https://huggingface.co/KORMo-Team/KORMo-tokenizer
+            res = "kormo"
 
         if res is None:
             logger.warning("\n")
@@ -3398,7 +3401,7 @@ class QwenModel(TextModel):
         self._set_vocab_qwen()
 
 
-@ModelBase.register("Qwen2Model", "Qwen2ForCausalLM", "Qwen2AudioForConditionalGeneration")
+@ModelBase.register("Qwen2Model", "Qwen2ForCausalLM", "Qwen2AudioForConditionalGeneration", "KORMoForCausalLM")
 class Qwen2Model(TextModel):
     model_arch = gguf.MODEL_ARCH.QWEN2
 

convert_hf_to_gguf_update.py

@@ -143,6 +143,7 @@ models = [
     {"name": "bailingmoe2",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/inclusionAI/Ling-mini-base-2.0", },
     {"name": "granite-docling",  "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ibm-granite/granite-docling-258M", },
     {"name": "minimax-m2",       "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/MiniMaxAI/MiniMax-M2", },
+    {"name": "kormo",            "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/KORMo-Team/KORMo-tokenizer", },
 ]
 
 # some models are known to be broken upstream, so we will skip them as exceptions

ggml/src/ggml-metal/ggml-metal-device.m

@@ -769,9 +769,16 @@ ggml_metal_device_t ggml_metal_device_init(void) {
 #endif
 
             dev->props.use_shared_buffers = dev->props.has_unified_memory;
+#if TARGET_OS_OSX
+            // In case of eGPU, shared memory may be preferable.
+            dev->props.use_shared_buffers |= [dev->mtl_device location] == MTLDeviceLocationExternal;
+#endif
             if (getenv("GGML_METAL_SHARED_BUFFERS_DISABLE") != NULL) {
                 dev->props.use_shared_buffers = false;
             }
+            if (getenv("GGML_METAL_SHARED_BUFFERS_ENABLE") != NULL) {
+                dev->props.use_shared_buffers = true;
+            }
 
             dev->props.supports_gpu_family_apple7 = [dev->mtl_device supportsFamily:MTLGPUFamilyApple7];
 

gguf-py/gguf/tensor_mapping.py

@@ -154,7 +154,8 @@ class TensorNameMap:
             "model.layers.{bid}.operator_norm",                     # lfm2
             "model.transformer.blocks.{bid}.attn_norm",             # llada
             "layers.{bid}.input_layernorm",                         # qwen3-embedding
-            "model.layers.{bid}.attention_layernorm"                # apertus
+            "model.layers.{bid}.attention_layernorm",               # apertus
+            "model.layers.{bid}.pre_attention_layernorm",           # kormo
         ),
 
         # Attention norm 2
@@ -342,6 +343,7 @@ class TensorNameMap:
             "model.transformer.blocks.{bid}.ff_norm",                        # llada
             "layers.{bid}.post_attention_layernorm",                         # qwen3-embedding
             "model.layers.{bid}.feedforward_layernorm",                      # apertus
+            "model.layers.{bid}.pre_mlp_layernorm",                          # kormo
         ),
 
         # Pre feed-forward norm

src/llama-kv-cache.cpp

@@ -1561,9 +1561,11 @@ void llama_kv_cache::state_read(llama_io_read_i & io, llama_seq_id seq_id, llama
 
         const uint32_t strm = seq_id == -1 ? s : seq_to_stream[seq_id];
 
+        slot_info sinfo;
+
         bool res = true;
-        res = res && state_read_meta(io, strm, cell_count, seq_id);
-        res = res && state_read_data(io, strm, cell_count);
+        res = res && state_read_meta(io, strm, cell_count, sinfo, seq_id);
+        res = res && state_read_data(io, strm, cell_count, sinfo);
 
         if (!res) {
             if (seq_id == -1) {
@@ -1702,7 +1704,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
     }
 }
 
-bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, llama_seq_id dest_seq_id) {
+bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, slot_info & sinfo, llama_seq_id dest_seq_id) {
     auto & cells = v_cells[strm];
     auto & head  = v_heads[strm];
 
@@ -1739,7 +1741,7 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
             ubatch.seq_id[i]   = &dest_seq_id;
         }
 
-        const auto sinfo = find_slot(ubatch, true);
+        sinfo = find_slot(ubatch, false);
         if (sinfo.empty()) {
             LLAMA_LOG_ERROR("%s: failed to find available cells in kv cache\n", __func__);
             return false;
@@ -1749,20 +1751,16 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
         //       see: https://github.com/ggml-org/llama.cpp/pull/16825#issuecomment-3460868350
         apply_ubatch(sinfo, ubatch);
 
-        const auto head_cur = sinfo.head();
+        LLAMA_LOG_DEBUG("%s: cell_count = %d, dest_seq_id = %d\n", __func__, cell_count, dest_seq_id);
 
-        // keep the head at the old position because we will read the KV data into it in state_read_data()
-        head = head_cur;
-
-        LLAMA_LOG_DEBUG("%s: head_cur = %d, head = %d, cell_count = %d, dest_seq_id = %d\n", __func__, head_cur, head, cell_count, dest_seq_id);
-
-        // DEBUG CHECK: head_cur should be our first cell, head_cur + cell_count - 1 should be our last cell (verify seq_id and pos values)
-        // Assume that this is one contiguous block of cells
-        GGML_ASSERT(head_cur + cell_count <= cells.size());
-        GGML_ASSERT(cells.pos_get(head_cur)                  == ubatch.pos[0]);
-        GGML_ASSERT(cells.pos_get(head_cur + cell_count - 1) == ubatch.pos[cell_count - 1]);
-        GGML_ASSERT(cells.seq_has(head_cur,                  dest_seq_id));
-        GGML_ASSERT(cells.seq_has(head_cur + cell_count - 1, dest_seq_id));
+        // DEBUG CHECK: verify that all cells were allocated and have correct seq_id and pos values
+        GGML_ASSERT(sinfo.n_stream() == 1);
+        GGML_ASSERT(sinfo.idxs[0].size() == cell_count);
+        for (uint32_t i = 0; i < cell_count; ++i) {
+            const uint32_t idx = sinfo.idxs[0][i];
+            GGML_ASSERT(cells.pos_get(idx) == ubatch.pos[i]);
+            GGML_ASSERT(cells.seq_has(idx, dest_seq_id));
+        }
     } else {
         // whole KV cache restore
 
@@ -1795,15 +1793,24 @@ bool llama_kv_cache::state_read_meta(llama_io_read_i & io, uint32_t strm, uint32
             }
         }
 
+        // Create contiguous slot_info for whole cache restore
+        sinfo.s0 = strm;
+        sinfo.s1 = strm;
+        sinfo.resize(1);
+        sinfo.strm[0] = strm;
+        sinfo.idxs[0].resize(cell_count);
+        for (uint32_t i = 0; i < cell_count; ++i) {
+            sinfo.idxs[0][i] = i;
+        }
+
         head = 0;
     }
 
     return true;
 }
 
-bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count) {
+bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, const slot_info & sinfo) {
     auto & cells = v_cells[strm];
-    auto & head  = v_heads[strm];
 
     uint32_t v_trans;
     uint32_t n_layer;
@@ -1853,8 +1860,17 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
         }
 
         if (cell_count) {
-            // Read and set the keys for the whole cell range
-            ggml_backend_tensor_set(k, io.read(cell_count * k_size_row), head * k_size_row, cell_count * k_size_row);
+            if (sinfo.is_contiguous()) {
+                // Fast path: contiguous cells, single memcpy
+                ggml_backend_tensor_set(k, io.read(cell_count * k_size_row), sinfo.head() * k_size_row, cell_count * k_size_row);
+            } else {
+                // Slow path: scatter to non-contiguous positions
+                const void * src = io.read(cell_count * k_size_row);
+                for (uint32_t i = 0; i < cell_count; ++i) {
+                    const size_t dst_offset = sinfo.idxs[0][i] * k_size_row;
+                    ggml_backend_tensor_set(k, (const char*)src + i * k_size_row, dst_offset, k_size_row);
+                }
+            }
         }
     }
 
@@ -1885,8 +1901,17 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
             }
 
             if (cell_count) {
-                // Read and set the values for the whole cell range
-                ggml_backend_tensor_set(v, io.read(cell_count * v_size_row), head * v_size_row, cell_count * v_size_row);
+                if (sinfo.is_contiguous()) {
+                    // Fast path: contiguous cells, single memcpy
+                    ggml_backend_tensor_set(v, io.read(cell_count * v_size_row), sinfo.head() * v_size_row, cell_count * v_size_row);
+                } else {
+                    // Slow path: scatter to non-contiguous positions
+                    const void * src = io.read(cell_count * v_size_row);
+                    for (uint32_t i = 0; i < cell_count; ++i) {
+                        const size_t dst_offset = sinfo.idxs[0][i] * v_size_row;
+                        ggml_backend_tensor_set(v, (const char*)src + i * v_size_row, dst_offset, v_size_row);
+                    }
+                }
             }
         }
     } else {
@@ -1925,10 +1950,22 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32
             }
 
             if (cell_count) {
-                // For each row in the transposed matrix, read the values for the whole cell range
-                for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
-                    const size_t dst_offset = (head + j * cells.size()) * v_size_el;
-                    ggml_backend_tensor_set(v, io.read(cell_count * v_size_el), dst_offset, cell_count * v_size_el);
+                if (sinfo.is_contiguous()) {
+                    // Fast path: contiguous cells
+                    const uint32_t h = sinfo.head();
+                    for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
+                        const size_t dst_offset = (h + j * cells.size()) * v_size_el;
+                        ggml_backend_tensor_set(v, io.read(cell_count * v_size_el), dst_offset, cell_count * v_size_el);
+                    }
+                } else {
+                    // Slow path: scatter to non-contiguous positions
+                    for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
+                        const void * src = io.read(cell_count * v_size_el);
+                        for (uint32_t i = 0; i < cell_count; ++i) {
+                            const size_t dst_offset = (sinfo.idxs[0][i] + j * cells.size()) * v_size_el;
+                            ggml_backend_tensor_set(v, (const char*)src + i * v_size_el, dst_offset, v_size_el);
+                        }
+                    }
                 }
             }
         }

src/llama-kv-cache.h

@@ -72,6 +72,23 @@ public:
         void clear() {
             idxs.clear();
         }
+
+        // check if indices are contiguous starting from head()
+        bool is_contiguous() const {
+            if (idxs.empty() || idxs[0].empty()) {
+                return true;
+            }
+            if (idxs.size() > 1) {
+                return false;
+            }
+            const uint32_t h = idxs[0][0];
+            for (size_t i = 0; i < idxs[0].size(); ++i) {
+                if (idxs[0][i] != h + i) {
+                    return false;
+                }
+            }
+            return true;
+        }
     };
 
     using slot_info_vec_t = std::vector<slot_info>;
@@ -264,8 +281,8 @@ private:
     void state_write_meta(llama_io_write_i & io, const cell_ranges_t & cr, llama_seq_id seq_id = -1) const;
     void state_write_data(llama_io_write_i & io, const cell_ranges_t & cr) const;
 
-    bool state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, llama_seq_id dest_seq_id = -1);
-    bool state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count);
+    bool state_read_meta(llama_io_read_i & io, uint32_t strm, uint32_t cell_count,       slot_info & sinfo, llama_seq_id dest_seq_id = -1);
+    bool state_read_data(llama_io_read_i & io, uint32_t strm, uint32_t cell_count, const slot_info & sinfo);
 };
 
 class llama_kv_cache_context : public llama_memory_context_i {

src/llama-model.cpp

@@ -3388,9 +3388,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                         layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
 
                         // optional bias tensors
-                        layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd}, 0);
-                        layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_gqa}, 0);
-                        layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_gqa}, 0);
+                        layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd}, TENSOR_NOT_REQUIRED);
+                        layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_gqa}, TENSOR_NOT_REQUIRED);
+                        layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_gqa}, TENSOR_NOT_REQUIRED);
 
                         layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
 

src/llama-vocab.cpp

@@ -1895,7 +1895,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
                 clean_spaces = false;
             } else if (
                     tokenizer_pre == "qwen2" ||
-                    tokenizer_pre == "deepseek-r1-qwen") {
+                    tokenizer_pre == "deepseek-r1-qwen" ||
+                    tokenizer_pre == "kormo") {
                 pre_type = LLAMA_VOCAB_PRE_TYPE_QWEN2;
                 clean_spaces = false;
             } else if (

src/models/qwen2.cpp

@@ -31,16 +31,25 @@ llm_build_qwen2::llm_build_qwen2(const llama_model & model, const llm_graph_para
         {
             // compute Q and K and RoPE them
             ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
-            Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
             cb(Qcur, "Qcur", il);
+            if (model.layers[il].bq) {
+                Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
+                cb(Qcur, "Qcur", il);
+            }
 
             ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
-            Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
             cb(Kcur, "Kcur", il);
+            if (model.layers[il].bk) {
+                Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
+                cb(Kcur, "Kcur", il);
+            }
 
             ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
-            Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
             cb(Vcur, "Vcur", il);
+            if (model.layers[il].bv) {
+                Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
+                cb(Vcur, "Vcur", il);
+            }
 
             Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
             Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);

tests/CMakeLists.txt

@@ -222,6 +222,14 @@ llama_build_and_test(test-backend-ops.cpp)
 llama_build_and_test(test-model-load-cancel.cpp  LABEL "model")
 llama_build_and_test(test-autorelease.cpp        LABEL "model")
 
+# Test for state restore with fragmented KV cache
+# Requires a model, uses same args pattern as test-thread-safety
+if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "s390x")
+    llama_build_and_test(test-state-restore-fragmented.cpp LABEL "model" ARGS -hf ggml-org/models -hff tinyllamas/stories15M-q4_0.gguf)
+else()
+    llama_build_and_test(test-state-restore-fragmented.cpp LABEL "model" ARGS -hf ggml-org/models -hff tinyllamas/stories15M-be.Q4_0.gguf)
+endif()
+
 if (NOT GGML_BACKEND_DL)
     # these tests use the backends directly and cannot be built with dynamic loading
     llama_build_and_test(test-barrier.cpp)

tests/test-state-restore-fragmented.cpp

@@ -0,0 +1,122 @@
+// Test for state restore with fragmented KV cache
+// This tests the fix for: https://github.com/ggml-org/llama.cpp/issues/17527
+// The issue was that state restore required contiguous KV cache slots,
+// which fails when the cache is fragmented.
+//
+// The fix changes find_slot(ubatch, true) to find_slot(ubatch, false)
+// in state_read_meta(), allowing non-contiguous slot allocation.
+
+#include "arg.h"
+#include "common.h"
+#include "llama.h"
+
+#include <vector>
+#include <cstdio>
+#include <cstring>
+
+int main(int argc, char ** argv) {
+    common_params params;
+
+    params.sampling.seed = 1234;
+    params.kv_unified = true;
+    params.n_parallel = 3;
+    params.n_ctx = 256;
+
+    if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMMON)) {
+        return 1;
+    }
+
+    common_init();
+
+    // init
+    common_init_result_ptr llama_init = common_init_from_params(params);
+
+    llama_model * model = llama_init->model();
+    llama_context * ctx = llama_init->context();
+
+    if (model == nullptr || ctx == nullptr) {
+        fprintf(stderr, "%s : failed to init\n", __func__);
+        return 1;
+    }
+
+    GGML_UNUSED(model);
+
+    // tokenize prompt
+    std::vector<llama_token> tokens(70, 1);
+
+    // interleave the 3 sequences:
+    // 01201230123...
+    llama_batch batch = llama_batch_init(params.n_parallel*tokens.size(), 0, 1);
+    for (size_t i = 0; i < tokens.size(); i++) {
+        for (int s = 0; s < params.n_parallel; ++s) {
+            common_batch_add(batch, tokens[i], i, {s}, false);
+        }
+    }
+    batch.logits[batch.n_tokens - 1] = true;
+
+    if (llama_decode(ctx, batch)) {
+        fprintf(stderr, "%s : failed to decode seq 0\n", __func__);
+        return 1;
+    }
+
+    fprintf(stderr, "%s : processed prompt on seq 0, 1, 2 (%zu tokens each)\n", __func__, tokens.size());
+
+    // Save state of seq 1
+    std::vector<uint8_t> seq_state(llama_state_seq_get_size(ctx, 1));
+    const size_t ncopy = llama_state_seq_get_data(ctx, seq_state.data(), seq_state.size(), 1);
+    if (ncopy != seq_state.size()) {
+        fprintf(stderr, "%s : failed to save seq 1 state\n", __func__);
+        return 1;
+    }
+    fprintf(stderr, "%s : saved seq 1 state, %zu bytes\n", __func__, ncopy);
+
+    // clear seq 1 to create a "hole" in the KV cache (fragmentation)
+    // 0.20.20.20.2....
+    llama_memory_t mem = llama_get_memory(ctx);
+    llama_memory_seq_rm(mem, 1, -1, -1);
+    fprintf(stderr, "%s : cleared seq 1 to create fragmentation\n", __func__);
+
+    // Now the cache has holes where seq 1 was
+    // This creates fragmentation - there's no contiguous block large enough
+    // for the seq 1 state if we only look for contiguous slots
+
+    // Restore seq 1 state into seq 1 (should work with non-contiguous allocation)
+    // We use seq 1 since it's a valid sequence ID (0 to n_parallel-1)
+    // Before the fix, this would fail with "failed to find available cells in kv cache"
+    const size_t nset = llama_state_seq_set_data(ctx, seq_state.data(), seq_state.size(), 1);
+    if (nset != seq_state.size()) {
+        fprintf(stderr, "%s : FAILED to restore seq state into fragmented cache (got %zu, expected %zu)\n",
+                __func__, nset, seq_state.size());
+        fprintf(stderr, "%s : This is the bug - state restore fails with fragmented KV cache\n", __func__);
+        llama_batch_free(batch);
+        return 1;
+    }
+    fprintf(stderr, "%s : restored state into seq 1, %zu bytes\n", __func__, nset);
+
+    // Verify we can decode with the restored state
+    // Generate one token to verify the restored state is usable
+    auto sparams = llama_sampler_chain_default_params();
+    llama_sampler * smpl = llama_sampler_chain_init(sparams);
+    llama_sampler_chain_add(smpl, llama_sampler_init_dist(params.sampling.seed));
+
+    auto next_token = llama_sampler_sample(smpl, ctx, -1);
+    auto next_token_str = common_token_to_piece(ctx, next_token);
+
+    common_batch_clear(batch);
+    common_batch_add(batch, next_token, (int)tokens.size(), {1}, true);
+
+    if (llama_decode(ctx, batch)) {
+        fprintf(stderr, "%s : failed to decode with restored state\n", __func__);
+        llama_sampler_free(smpl);
+        llama_batch_free(batch);
+        return 1;
+    }
+
+    fprintf(stderr, "%s : successfully decoded with restored state, generated: '%s'\n", __func__, next_token_str.c_str());
+    fprintf(stderr, "%s : SUCCESS - state restore works with fragmented KV cache\n", __func__);
+
+    llama_sampler_free(smpl);
+    llama_batch_free(batch);
+
+    return 0;
+}

tools/server/webui/src/lib/components/app/chat/ChatAttachments/ChatAttachmentThumbnailFile.svelte

@@ -1,6 +1,6 @@
 <script lang="ts">
 	import { RemoveButton } from '$lib/components/app';
-	import { getFileTypeLabel, getPreviewText, formatFileSize, isTextFile } from '$lib/utils';
+	import { formatFileSize, getFileTypeLabel, getPreviewText, isTextFile } from '$lib/utils';
 	import { AttachmentType } from '$lib/enums';
 
 	interface Props {

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

@@ -9,6 +9,7 @@
 	import Input from '$lib/components/ui/input/input.svelte';
 	import { conversationsStore, conversations } from '$lib/stores/conversations.svelte';
 	import { chatStore } from '$lib/stores/chat.svelte';
+	import { getPreviewText } from '$lib/utils/text';
 	import ChatSidebarActions from './ChatSidebarActions.svelte';
 
 	const sidebar = Sidebar.useSidebar();
@@ -20,6 +21,9 @@
 	let showEditDialog = $state(false);
 	let selectedConversation = $state<DatabaseConversation | null>(null);
 	let editedName = $state('');
+	let selectedConversationNamePreview = $derived.by(() =>
+		selectedConversation ? getPreviewText(selectedConversation.name) : ''
+	);
 
 	let filteredConversations = $derived.by(() => {
 		if (searchQuery.trim().length > 0) {
@@ -162,7 +166,7 @@
 	bind:open={showDeleteDialog}
 	title="Delete Conversation"
 	description={selectedConversation
-		? `Are you sure you want to delete "${selectedConversation.name}"? This action cannot be undone and will permanently remove all messages in this conversation.`
+		? `Are you sure you want to delete "${selectedConversationNamePreview}"? This action cannot be undone and will permanently remove all messages in this conversation.`
 		: ''}
 	confirmText="Delete"
 	cancelText="Cancel"

tools/server/webui/src/lib/components/app/misc/MarkdownContent.svelte

@@ -504,6 +504,14 @@
 		background: hsl(var(--muted) / 0.1);
 	}
 
+	/* User message markdown should keep table borders visible on light primary backgrounds */
+	div.markdown-user-content :global(table),
+	div.markdown-user-content :global(th),
+	div.markdown-user-content :global(td),
+	div.markdown-user-content :global(.table-wrapper) {
+		border-color: currentColor;
+	}
+
 	/* Horizontal rules */
 	div :global(hr) {
 		border: none;
@@ -642,6 +650,21 @@
 		background: var(--muted);
 	}
 
+	/* Disable hover effects when rendering user messages */
+	.markdown-user-content :global(a),
+	.markdown-user-content :global(a:hover) {
+		color: var(--primary-foreground);
+	}
+
+	.markdown-user-content :global(table:hover) {
+		box-shadow: none;
+	}
+
+	.markdown-user-content :global(th:hover),
+	.markdown-user-content :global(td:hover) {
+		background: inherit;
+	}
+
 	/* Enhanced blockquotes */
 	div :global(blockquote) {
 		transition: all 0.2s ease;

tools/server/webui/src/lib/utils/file-preview.ts

@@ -34,12 +34,3 @@ export function getFileTypeLabel(input: string | undefined): string {
 	// Handle AttachmentType or other plain strings
 	return input.toUpperCase();
 }
-
-/**
- * Truncates text content for preview display
- * @param content - The text content to truncate
- * @returns Truncated content with ellipsis if needed
- */
-export function getPreviewText(content: string): string {
-	return content.length > 150 ? content.substring(0, 150) + '...' : content;
-}

tools/server/webui/src/lib/utils/index.ts

@@ -43,7 +43,8 @@ export { createMessageCountMap, getMessageCount } from './conversation-utils';
 export { copyToClipboard, copyCodeToClipboard } from './copy';
 
 // File preview utilities
-export { getFileTypeLabel, getPreviewText } from './file-preview';
+export { getFileTypeLabel } from './file-preview';
+export { getPreviewText } from './text';
 
 // File type utilities
 export {

tools/server/webui/src/lib/utils/text.ts

@@ -0,0 +1,7 @@
+/**
+ * Returns a shortened preview of the provided content capped at the given length.
+ * Appends an ellipsis when the content exceeds the maximum.
+ */
+export function getPreviewText(content: string, max = 150): string {
+	return content.length > max ? content.slice(0, max) + '...' : content;
+}