Merge f-0243-rel (721c6f7ff) into f-025-readme

The Windows commit limit decides how many experts an integrated GPU may hold (place_experts). With AMD driver 26.10.1 the limit
went from 74 GB to 133 GB on a Strix Halo, the engine put 9506 experts (86 GB) on the GPU instead of 8105, every byte of the
GPU's address space was gone, and the 32K prompt's later allocations spilled into RAM: free RAM fell to 0 and the engine died
("rocBLAS: No devices found"). The experts now leave 4 GiB + 0.2 MB a token of context above 16384 (DS4_UMA_GPU_RESERVE_GB sets
it, tests); only an integrated GPU on Windows is affected.

Strix Halo (gfx1151, 2.00 pack, shipped profile), driver 26.10.1:
  32K prompt: killed (min free RAM 0) before, 113.2 tok/s with min free 13.6 GB now; 64K prompt (70000 context): 122.2 tok/s, min free 14.4 GB
  4K / 8K prompt: 62.8 / 83.9 tok/s (64.9 / 86.2 with the 9506 experts: -3%), min free 13.4-13.8 GB
  KL, code segment, 999 positions: 0.1020 (0.1028 before)
A smaller reserve (3 GiB + 0.1 MB a token) gained 0.0% on 4K / 8K / code decode and left 0.9 GB less free at 64K, so it was not taken.

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -66,7 +66,7 @@ body:
     attributes:
       label: Strata version
       description: "In the app: Settings > About. In the Terminal: `strata --version`. From source: the About tab of the web page, or `engine` in `GET /v1/status`, or the git commit."
-      placeholder: "Strata 0.2.3 · engine 0.1.48"
+      placeholder: "Strata 0.2.5 · engine 0.1.50"
     validations:
       required: true
   - type: input

AGENTS.md

@@ -2,7 +2,7 @@
 
 Strata runs the Qwen3.8-Flash-Next mixture-of-experts model (and its Coder, Swift 1.5, Unsloth, Gyro and NVFP4
 variants, and Qwen3.6-35B-A3B) on a normal PC: one NVIDIA or AMD graphics card plus system RAM on Windows or Linux,
-or an Apple Silicon Mac. Version 0.2.3, engine 0.1.48. It has three parts:
+or an Apple Silicon Mac. Version 0.2.5, engine 0.1.50. It has three parts:
 
 - **The app** (`apps/desktop`, the Tauri shell; `apps/host`, the Node host and the web UI). It is for people who do
   not want a terminal. The installer has the engine inside.
@@ -19,7 +19,7 @@ Follow **[docs/AI_SETUP.md](docs/AI_SETUP.md)**. For an agent that has a shell,
 1. Install the Terminal. It needs no administrator rights.
 
    ```sh
-   curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh                  # Linux, Mac
+   curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh                  # Linux, Mac
    irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex                         # Windows PowerShell
    ```
 

CMakeLists.txt

@@ -1,4 +1,4 @@
-# Strata Engine - top-level build (P1.S1).
+# Strata Engine - top-level build (P1.S1).
 #
 # Targets (phase-1 §P1.S1): `strata_artifact` (no CUDA dependency), `tests`.  `strata_plan` and the C++
 # `strata-pack` are added when their sources exist - a target with no sources would make the build graph
@@ -8,7 +8,7 @@
 # below refuses anything older: silently building for a pre-Ampere arch would produce a binary that runs
 # and is wrong about its own performance, which is the worst of both outcomes.
 cmake_minimum_required(VERSION 3.24)
-project(strata VERSION 0.1.48 LANGUAGES CXX)
+project(strata VERSION 0.1.50 LANGUAGES CXX)
 # EXPERIMENTAL: the Intel Arc engine, the SYCL port in sycl/ (PR #423; icpx + oneMKL, docs/INTEL_ARC.md). It is its
 # own project that takes the unported sources from src/; with this on, nothing below is configured.
 option(STRATA_ENABLE_SYCL "EXPERIMENTAL: build the Intel Arc (SYCL) engine from sycl/ - docs/INTEL_ARC.md" OFF)
@@ -794,6 +794,114 @@ if(STRATA_ENABLE_CUDA OR STRATA_ENABLE_HIP)
   target_compile_definitions(strata PRIVATE STRATA_HAVE_QWEN35=1)
   endif()
 
+  # DeepSeek-V4.1-Flash: the third engine path (src/dsv41, from Project Maya's maya-ds4, MIT, third_party/project-maya).
+  # Its own executable for now (strata-dsv41); a family switch in `strata` comes after first light.  OFF by default: it
+  # changes no existing target (the vendored kernels live in strata::dsv41k, so no symbol is shared with strata_kernels).
+  option(STRATA_BUILD_DSV41 "Build the DeepSeek-V4.1 engine path (strata-dsv41)" OFF)
+  if(STRATA_BUILD_DSV41 AND NOT STRATA_HIP_GFX906)
+    add_library(strata_dsv41_kernels STATIC src/dsv41/vendor/exl3.cu src/dsv41/vendor/sampler.cu src/dsv41/vendor/moe_win.cu
+                src/dsv41/vendor/exl3_cpu.cpp)
+    if(NOT STRATA_ENABLE_HIP)   # (the pre-sm_80 NVIDIA decode kernels exl3.cu dispatches to)
+      target_sources(strata_dsv41_kernels PRIVATE src/dsv41/vendor/exl3_legacy.cu)
+    endif()
+    target_include_directories(strata_dsv41_kernels PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include ${_strata_gpu_include_directories})
+    target_link_libraries(strata_dsv41_kernels PUBLIC ${_strata_gpu_runtime_target})
+    add_executable(strata-dsv41 src/dsv41/ds4_main.cpp src/dsv41/ds4_model.cu src/dsv41/ds4_kernels.cu src/dsv41/ds4_vision.cu
+                   src/dsv41/ds4_gguf.cu src/dsv41/ds4_gguf_cpu.cpp src/dsv41/ds4_iq.cu src/dsv41/ds4_iq_cpu.cpp
+                   src/dsv41/ds4_tq.cu src/dsv41/ds4_tq_cpu.cpp src/dsv41/ds4_gg_cpu.cpp src/dsv41/ds4_packinfo.cpp)
+    # the commit the binary was built from, readable with --version (set -DSTRATA_BUILD_ID=... for a tree without .git)
+    if(NOT STRATA_BUILD_ID AND EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/BUILD_ID)   # (a git archive has no .git: the packer writes the commit here)
+      file(STRINGS ${CMAKE_CURRENT_SOURCE_DIR}/BUILD_ID STRATA_BUILD_ID LIMIT_COUNT 1)
+    endif()
+    if(NOT STRATA_BUILD_ID)
+      execute_process(COMMAND git -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse --short=9 HEAD OUTPUT_VARIABLE STRATA_BUILD_ID
+                      OUTPUT_STRIP_TRAILING_WHITESPACE ERROR_QUIET)
+    endif()
+    if(NOT STRATA_BUILD_ID)
+      set(STRATA_BUILD_ID unknown)
+    endif()
+    set_source_files_properties(src/dsv41/ds4_main.cpp PROPERTIES COMPILE_DEFINITIONS "DS4_BUILD_ID=\"${STRATA_BUILD_ID}\"")
+    target_include_directories(strata-dsv41 PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${_strata_gpu_include_directories}
+                               ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml)
+    target_link_libraries(strata-dsv41 PRIVATE strata_dsv41_kernels ${_strata_gpu_runtime_target} ${_strata_gpu_blas_target})
+    find_package(Threads REQUIRED)
+    target_link_libraries(strata-dsv41 PRIVATE Threads::Threads)
+    if(WIN32 AND STRATA_ENABLE_HIP)   # cudaMemGetInfo is the DXGI-budgeted hip_compat::mem_get_info (src/core/device.cu): on a Strix Halo the
+      # carve-out is not all the GPU may use, and the engine sizes its expert tiers by what the budget says is free
+      target_link_libraries(strata-dsv41 PRIVATE strata_core)
+    endif()
+    if(STRATA_NATIVE_EXPERTS)   # Strata's CPU trellis kernels (tq_cpu.hpp) for the trellis experts on the CPU lane
+      target_link_libraries(strata-dsv41 PRIVATE strata_kernels_cpu)
+      target_compile_definitions(strata-dsv41 PRIVATE STRATA_DSV41_TQ_CPU=1)
+    endif()
+    if(STRATA_NATIVE_EXPERTS)
+      # the CPU lane's ggml-type rows: ggml-cpu's dots against Strata's AVX2 i-quant rows (bits and GB/s); no GPU, no model
+      add_executable(ds4_gg_bench tests/dsv41/gg_dot_bench.cpp src/dsv41/ds4_gg_cpu.cpp)
+      target_include_directories(ds4_gg_bench PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${CMAKE_CURRENT_SOURCE_DIR}/src/dsv41
+                                 ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml)
+      target_link_libraries(ds4_gg_bench PRIVATE strata_kernels_cpu Threads::Threads)
+      target_compile_definitions(ds4_gg_bench PRIVATE STRATA_DSV41_TQ_CPU=1)
+    endif()
+    if(STRATA_NATIVE_EXPERTS)
+      # the trellis experts (device kernels ds4_tq.cu, CPU lane ds4_tq_cpu.cpp) against a double reference; needs a GPU, no model
+      # both test .cpp files launch kernels, so they compile as HIP on the AMD backend and as CUDA on the NVIDIA one
+      if(STRATA_ENABLE_HIP)
+        set(_ds4_test_lang HIP)
+      elseif(STRATA_ENABLE_CUDA)
+        set(_ds4_test_lang CUDA)
+      else()
+        set(_ds4_test_lang CXX)
+      endif()
+      set_source_files_properties(tests/dsv41/tq_expert_test.cpp PROPERTIES LANGUAGE ${_ds4_test_lang})
+      add_executable(ds4_tq_test tests/dsv41/tq_expert_test.cpp src/dsv41/ds4_tq.cu src/dsv41/ds4_iq.cu src/dsv41/ds4_tq_cpu.cpp
+                     src/dsv41/ds4_iq_cpu.cpp src/dsv41/ds4_gg_cpu.cpp tools/trellis/tqenc.cpp)
+      target_include_directories(ds4_tq_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${_strata_gpu_include_directories}
+                                 ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml ${CMAKE_CURRENT_SOURCE_DIR}/src/kernels/cpu)
+      target_link_libraries(ds4_tq_test PRIVATE strata_kernels_cpu ${_strata_gpu_runtime_target} Threads::Threads)
+      target_compile_definitions(ds4_tq_test PRIVATE STRATA_DSV41_TQ_CPU=1)
+      # the same with the plain-FMA tile instead of the gfx12 WMMA one (what CUDA and gfx11 builds run)
+      add_executable(ds4_tq_test_portable tests/dsv41/tq_expert_test.cpp src/dsv41/ds4_tq.cu src/dsv41/ds4_iq.cu src/dsv41/ds4_tq_cpu.cpp
+                     src/dsv41/ds4_iq_cpu.cpp src/dsv41/ds4_gg_cpu.cpp tools/trellis/tqenc.cpp)
+      target_include_directories(ds4_tq_test_portable PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${_strata_gpu_include_directories}
+                                 ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml ${CMAKE_CURRENT_SOURCE_DIR}/src/kernels/cpu)
+      target_link_libraries(ds4_tq_test_portable PRIVATE strata_kernels_cpu ${_strata_gpu_runtime_target} Threads::Threads)
+      target_compile_definitions(ds4_tq_test_portable PRIVATE STRATA_DSV41_TQ_CPU=1 DS4_TQ_PORTABLE=1)
+      if(STRATA_ENABLE_HIP)
+        target_compile_options(ds4_tq_test_portable PRIVATE "$<$<COMPILE_LANGUAGE:HIP,CXX>:SHELL:-include ${CMAKE_CURRENT_SOURCE_DIR}/include/strata/dsv41/hip_extra.h>")
+      endif()
+      if(STRATA_ENABLE_HIP)
+        target_compile_options(ds4_tq_test PRIVATE "$<$<COMPILE_LANGUAGE:HIP,CXX>:SHELL:-include ${CMAKE_CURRENT_SOURCE_DIR}/include/strata/dsv41/hip_extra.h>")
+      endif()
+      # the i-quant experts (ds4_iq.cu) against ggml's own decode of the same blocks + a double reference, device and CPU
+      # lane, for every type the device takes: the gate a new type (IQ2_XS ..) has to pass before the engine uses it
+      set_source_files_properties(tests/dsv41/iq_expert_test.cpp PROPERTIES LANGUAGE ${_ds4_test_lang})
+      add_executable(ds4_iq_test tests/dsv41/iq_expert_test.cpp src/dsv41/ds4_iq.cu src/dsv41/ds4_iq_cpu.cpp
+                     src/dsv41/ds4_gg_cpu.cpp src/dsv41/ds4_tq.cu src/dsv41/ds4_tq_cpu.cpp)
+      target_include_directories(ds4_iq_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${_strata_gpu_include_directories}
+                                 ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml ${CMAKE_CURRENT_SOURCE_DIR}/src/kernels/cpu)
+      target_link_libraries(ds4_iq_test PRIVATE strata_kernels_cpu ${_strata_gpu_runtime_target} Threads::Threads)
+      target_compile_definitions(ds4_iq_test PRIVATE STRATA_DSV41_TQ_CPU=1)
+      if(STRATA_ENABLE_HIP)
+        target_compile_options(ds4_iq_test PRIVATE "$<$<COMPILE_LANGUAGE:HIP,CXX>:SHELL:-include ${CMAKE_CURRENT_SOURCE_DIR}/include/strata/dsv41/hip_extra.h>")
+      endif()
+      # the kept conversations' .meta file and prefix matching (ds4_slotmeta.hpp): no GPU, no model
+      add_executable(ds4_slot_test tests/dsv41/slot_test.cpp)
+      target_include_directories(ds4_slot_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src/dsv41)
+      target_compile_features(ds4_slot_test PRIVATE cxx_std_17)
+      add_executable(ds4_experts_rule_test tests/dsv41/experts_rule_test.cpp)
+      target_include_directories(ds4_experts_rule_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src/dsv41)
+      target_compile_features(ds4_experts_rule_test PRIVATE cxx_std_17)
+      add_executable(ds4_pick_rule_test tests/dsv41/pick_rule_test.cpp)
+      target_include_directories(ds4_pick_rule_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src/dsv41)
+      target_compile_features(ds4_pick_rule_test PRIVATE cxx_std_17)
+    endif()
+    if(STRATA_ENABLE_HIP)
+      foreach(_t strata_dsv41_kernels strata-dsv41)
+        target_compile_options(${_t} PRIVATE "$<$<COMPILE_LANGUAGE:HIP,CXX>:SHELL:-include ${CMAKE_CURRENT_SOURCE_DIR}/include/strata/dsv41/hip_extra.h>")
+      endforeach()
+    endif()
+  endif()
+
   if(STRATA_ENABLE_HIP)
     enable_testing()
     set(_strata_hip_tests)
@@ -1436,6 +1544,9 @@ if(STRATA_BUILD_TESTS)
   add_executable(arch_defaults_test src/core/arch_defaults_test.cpp src/core/arch_defaults.cpp)
   target_include_directories(arch_defaults_test PRIVATE include)
   add_test(NAME arch_defaults_test COMMAND arch_defaults_test)
+  add_executable(adapt_async_default_test src/core/adapt_async_default_test.cpp)
+  target_include_directories(adapt_async_default_test PRIVATE include)
+  add_test(NAME adapt_async_default_test COMMAND adapt_async_default_test)
   add_executable(uma_cache_test src/core/uma_cache_test.cpp)
   target_include_directories(uma_cache_test PRIVATE include)
   add_test(NAME uma_cache_test COMMAND uma_cache_test)
@@ -1565,6 +1676,13 @@ if(STRATA_NATIVE_EXPERTS)
     foreach(_f GGML_AVX GGML_AVX2 GGML_FMA GGML_F16C GGML_BMI2)
       set(${_f} ON CACHE BOOL "" FORCE)
     endforeach()
+    # The DeepSeek engine (STRATA_BUILD_DSV41) builds ggml-cpu with BMI2 OFF: ggml's IQ1_S / IQ1_M dots use _pdep_u64 with it, and AMD
+    # Zen 1/2 run PDEP in microcode (EPYC 7452, IQ1_M one-token dot 1.8 GB/s against 32 GB/s without it; IQ1_S 2.3 against 37). The
+    # results are bit-identical either way (ds4_gg_bench --dump, types 19 and 29, 1-16 tokens). Other engines keep BMI2 until their
+    # next rebuild is looked at: no Qwen package changes with this commit.
+    if(STRATA_BUILD_DSV41)
+      set(GGML_BMI2 OFF CACHE BOOL "" FORCE)
+    endif()
   elseif(STRATA_ISA_FLOOR)
     # the experimental older-CPU build (STRATA_ISA_FLOOR above): one ggml-cpu for the floor, ggml's "sandybridge"
     # feature set (SSE4.2 + AVX) or SSE4.2 alone - not the build host's, which may be newer than the PC it runs on.
@@ -1623,7 +1741,7 @@ if(STRATA_NATIVE_EXPERTS)
     set_source_files_properties(src/kernels/cpu/iq_avx1.cpp PROPERTIES COMPILE_OPTIONS "/arch:AVX")
   else()
     set_source_files_properties(src/kernels/cpu/iq_avx512.cpp src/kernels/cpu/nvfp4_avx512.cpp PROPERTIES COMPILE_OPTIONS
-                                "-mavx512f;-mavx512bw;-mavx512vl;-mavx512dq;-mavx512vnni;-mavx512vbmi;-mf16c;-mfma")
+                                "-mavx512f;-mavx512bw;-mavx512vl;-mavx512dq;-mavx512vnni;-mavx512vbmi;-mavx512vpopcntdq;-mbmi2;-mf16c;-mfma")
     set_source_files_properties(src/kernels/cpu/iq_avx2.cpp PROPERTIES COMPILE_OPTIONS "-mavx2;-mfma;-mf16c")
     set_source_files_properties(src/kernels/cpu/kq_avx2.cpp PROPERTIES COMPILE_OPTIONS "-mavx2;-mfma;-mf16c")
     set_source_files_properties(src/kernels/cpu/nvfp4_avx2.cpp PROPERTIES COMPILE_OPTIONS "-mavx2;-mfma;-mf16c")
@@ -1671,6 +1789,14 @@ if(STRATA_NATIVE_EXPERTS)
   # against ggml-cpu's dot, on random blocks; --bench: ms per expert on one thread, the weights streamed from DRAM
   add_executable(iq_avx2_parity src/kernels/cpu/iq_avx2_parity.cpp)
   target_link_libraries(iq_avx2_parity PRIVATE strata_kernels_cpu)
+  # the 512-bit i-quant rows against ggml-cpu's dot: the exact rows bit for bit at 1-4 tokens, the engine's multi-token rows to float
+  # rounding, with the grid lookups as scalar loads and as gathers (SKIP without AVX-512)
+  add_executable(iq512_gather_parity src/kernels/cpu/iq512_gather_parity.cpp)
+  target_link_libraries(iq512_gather_parity PRIVATE strata_kernels_cpu)
+  if(STRATA_BUILD_TESTS)
+    add_test(NAME iq512_gather_parity_scalar COMMAND ${CMAKE_COMMAND} -E env STRATA_IQ_GATHER=0 $<TARGET_FILE:iq512_gather_parity>)
+    add_test(NAME iq512_gather_parity_gather COMMAND ${CMAKE_COMMAND} -E env STRATA_IQ_GATHER=1 $<TARGET_FILE:iq512_gather_parity>)
+  endif()
   # MODEL-UPDATE: the pool's expert rows per format on T threads against the RAM bandwidth (a benchmark, no test)
   add_executable(kq_cpu_bench src/kernels/cpu/kq_cpu_bench.cpp)
   target_link_libraries(kq_cpu_bench PRIVATE strata_kernels_cpu)
@@ -2265,3 +2391,19 @@ if(STRATA_HIP_GFX906)
   add_executable(gfx906_qsa_query_swizzle_probe bench/gfx906_qsa_query_swizzle_probe.cpp)
   target_link_libraries(gfx906_qsa_query_swizzle_probe PRIVATE strata_kernels ${_strata_gpu_runtime_target})
 endif()
+
+# ---- DeepSeek-V4.1 on a box with no GPU toolkit ------------------------------------------------
+# The whole DSV41 block above lives inside if(STRATA_ENABLE_CUDA OR STRATA_ENABLE_HIP), so with neither backend on
+# -DSTRATA_BUILD_DSV41=ON was silently unused and the host-side benchmark could not be built at all (found on p1004,
+# 2026-10-23: the CPU lane is exactly what a box without a usable GPU needs to measure).  This branch builds the one target
+# that has no device code, so the CPU-lane A/B runs anywhere.
+if(STRATA_BUILD_DSV41 AND NOT STRATA_ENABLE_CUDA AND NOT STRATA_ENABLE_HIP AND NOT STRATA_HIP_GFX906)
+  message(STATUS "STRATA_BUILD_DSV41: no GPU backend, building the host-side benchmark only (ds4_gg_bench)")
+  if(STRATA_NATIVE_EXPERTS)
+    add_executable(ds4_gg_bench tests/dsv41/gg_dot_bench.cpp src/dsv41/ds4_gg_cpu.cpp)
+    target_include_directories(ds4_gg_bench PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/include ${CMAKE_CURRENT_SOURCE_DIR}/src/dsv41
+                               ${CMAKE_CURRENT_SOURCE_DIR}/third_party/ggml)
+    target_link_libraries(ds4_gg_bench PRIVATE strata_kernels_cpu Threads::Threads)
+    target_compile_definitions(ds4_gg_bench PRIVATE STRATA_DSV41_TQ_CPU=1)
+  endif()
+endif()

README.de.md

@@ -12,103 +12,91 @@
 <p align="center">Unterstützt NVIDIA, AMD, Intel · Windows, Linux, Mac · kostenlos und Open Source</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Neueste Version"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT-Lizenz"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub-Sterne"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="Spendier mir einen Kaffee"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Ein Voxel-Pagodengarten, den das Modell von Strata geschrieben hat, im Browser"></a><br>
 <sub>Ein Voxel-Pagodengarten aus einem einzigen Prompt, auf einer RTX 5070 mit Strata (IQ3_S, 128K Kontext) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">ganzes Video (49 s)</a></sub></p>
 
-Strata lässt **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)** laufen, ein Modell mit 125
-Milliarden Parametern, für das man sonst einen Server braucht, auf einem normalen PC. Es chattet, schreibt Code, liest
-Bilder und arbeitet mit deinen Apps und Coding-Agents zusammen. Deine Chats und Dateien bleiben auf deinem PC.
+<p align="center">
+  <a href="#installation"><b>Installation</b></a> ·
+  <a href="#modelle">Modelle</a> ·
+  <a href="#wie-schnell-ist-es">Tempo</a> ·
+  <a href="#benutzung">Benutzung</a> ·
+  <a href="#wie-funktioniert-das">Wie es funktioniert</a> ·
+  <a href="#etwas-ist-schiefgegangen">Hilfe</a> ·
+  <a href="#strata-unterstützen">Unterstützen</a>
+</p>
 
-**Neu hier?** Sieh dir an, [was du brauchst](#was-du-brauchst), und [installiere dann die App](#option-a-die-strata-app).
+Strata lässt **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)** laufen, ein Modell mit 125
+Milliarden Parametern, für das man sonst einen Server braucht, auf einem normalen PC. Ab 0.2.4 läuft im Terminal auch
+**DeepSeek V4.1-Flash**. Es chattet, schreibt Code, liest Bilder und arbeitet mit deinen Apps und Coding-Agents zusammen.
+Deine Chats und Dateien bleiben auf deinem PC.
 
 - **Läuft auf einem Gaming-PC.** 32 GB Arbeitsspeicher (RAM) und Grafikspeicher zusammen reichen für den Anfang.
-- **Passt zu deinen Werkzeugen.** Strata spricht die OpenAI- und die Anthropic-API, deshalb verbinden sich Claude Code, Codex CLI, OpenCode und andere Agents damit.
+- **Passt zu deinen Werkzeugen.** Claude Code, Codex CLI, OpenCode und andere Agents verbinden sich über die OpenAI- und die Anthropic-API.
 - **Liest Bilder.** Das ist standardmäßig eingeschaltet.
-- **Kostenlos.** MIT-Lizenz, kein Konto, keine Cloud.
-- **Privat.** Keine Telemetrie. Was Strata herunterlädt, wann es das Internet nutzt und wie es Downloads prüft, steht in [docs/SAFETY.md](docs/SAFETY.md).
-
-Version 0.2.3 · Engine 0.1.48
+- **Kostenlos und privat.** MIT-Lizenz, kein Konto, keine Cloud, keine Telemetrie ([was es herunterlädt und wann](docs/SAFETY.md)).
 
 ## Was du brauchst
 
-**Du brauchst mindestens 32 GB Arbeitsspeicher (RAM) und Grafikspeicher (VRAM) zusammen.** Bei einem Mac oder einem Ryzen AI Max
-ist das der gemeinsame Speicher. Mit mehr Speicher läuft ein größeres oder ein schnelleres Modell.
+**Du brauchst mindestens 32 GB Speicher: Arbeitsspeicher (RAM) und Grafikspeicher (VRAM) zusammen.** Bei einem Mac oder einem
+Ryzen AI Max ist das der gemeinsame Speicher. Ein PC mit 32 GB und einer Karte mit 12-16 GB führt die kleineren Größen aus,
+mit 64 GB laufen alle Größen.
 
-- Ein PC mit 32 GB und einer Grafikkarte mit 12-16 GB führt den Coder aus.
-- Mit 64 GB RAM laufen alle Größen.
-
-| Dein Computer | Details |
+| Läuft auf | Anleitung |
 | --- | --- |
-| **NVIDIA** GeForce RTX 20, 30, 40, 50 Serie (12 GB oder mehr) | Installiere die App oder das Terminal. |
-| **AMD** Radeon RX 6800 und neuer, Radeon AI PRO R9700 (12 GB oder mehr) | [AMD-Karten](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md), [Intel-Engine](docs/INTEL.md) |
-| **Apple-Silicon-Mac** (M1 oder neuer, macOS 15 oder neuer) | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max (Strix Halo)** und andere Systeme mit gemeinsamem Speicher | [Strix Halo](docs/STRIX_HALO.md) |
-| Ältere Karten und Prozessoren | [Ältere GPUs](docs/OLDER_GPUS.md), [Ältere CPUs](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX 20, 30, 40 und 50 Serie, 12 GB oder mehr | [Installation](#installation) |
+| **AMD** Radeon RX 6800 und neuer, Radeon AI PRO R9700 | [AMD-Karten](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Apple-Silicon-Mac**, M1 oder neuer, macOS 15 oder neuer | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max (Strix Halo)** und andere PCs mit gemeinsamem Speicher | [Strix Halo](docs/STRIX_HALO.md) |
+| Ältere Karten und Prozessoren | [Ältere GPUs](docs/OLDER_GPUS.md) |
 
-Außerdem nötig:
-
-- etwa 80 GB freier Speicherplatz (mit einer SSD startet es beim ersten Mal viel schneller)
-- Windows 10 / 11, Linux oder macOS
-- ein aktueller Grafiktreiber
-
-Zwei oder drei Karten desselben Herstellers können sich ein Modell teilen ([Multi-GPU](docs/MULTI_GPU.md)). Strata teilt ein
-Modell nie auf NVIDIA- und AMD-Karten auf. Die vollständige Liste: [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
+Außerdem brauchst du etwa 80 GB freien Speicherplatz (eine SSD), Windows 10 / 11, Linux oder macOS und einen aktuellen
+Grafiktreiber. Zwei oder drei Karten desselben Herstellers können sich ein Modell teilen ([Multi-GPU](docs/MULTI_GPU.md)).
 
 ## Installation
 
-Such dir eine Option aus. Alle starten dieselbe Engine und nutzen dieselben Modelle.
+### 1. Die Strata-App (am einfachsten)
 
-### Option A: die Strata-App
+Lade die Datei für deinen Computer herunter, öffne sie und drück auf Installieren beim empfohlenen Modell.
 
-Der einfachste Weg. Die App bringt die Engine mit: installieren, ein Modell wählen, chatten. Lade die Datei für dein
-System und deine Grafikkarte von der [Releases-Seite](https://github.com/Niko1221/Strata/releases/latest) herunter. Du bist
-unsicher, welche du brauchst? Lies den Absatz unter der Tabelle.
+**Windows 10 / 11**
 
-| System | Deine Grafikkarte | Datei zum Herunterladen |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX, Treiber 580 oder neuer | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA, ältere Karte oder Treiber älter als 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon RX 9000 Serie oder Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon RX 7000 Serie oder Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX, Treiber 580 oder neuer | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA, ältere Karte oder Treiber älter als 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon RX 9000 Serie oder Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon RX 7000 Serie | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac** (Apple Silicon, macOS 15 oder neuer) | eingebaut | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**Wenn du unsicher bist:** Bei NVIDIA nimmst du `cuda13`, wenn dein Treiber Version 580 oder neuer ist, sonst `cuda12`.
-`cuda12` ist für ältere Karten und ältere Treiber. Die Dateien `hip` und `amd` sind für AMD-Karten. Für andere AMD-Karten
-(RX 6000) gibt es noch keine fertige App: siehe [AMD-Karten](docs/AMD_HIP.md).
+**Linux**
 
-Danach:
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows:** Starte die `.exe`. Sie wird für deinen Benutzer installiert und braucht keine Administratorrechte. Wenn
-  Windows "Der Computer wurde durch Windows geschützt" meldet, wähle **Weitere Informationen** und dann **Trotzdem
-  ausführen** (der Installer ist noch nicht signiert).
-- **Linux:** Mach die Datei ausführbar (`chmod +x`) und starte sie. Sie braucht FUSE 2: `sudo apt install libfuse2`
-  (Ubuntu 22.04) oder `libfuse2t64` (Ubuntu 24.04 und neuer).
-- **Mac:** Öffne die `.dmg` und zieh Strata in den Ordner "Programme".
+**Mac** (Apple Silicon, macOS 15 oder neuer)
 
-Auf dem ersten Bildschirm liest die App deinen PC aus und empfiehlt ein passendes Modell. Drück auf Installieren. Das Modell
-ist ein großer Download (etwa 40-70 GB) und wird nach einer Unterbrechung dort fortgesetzt, wo er aufgehört hat. Wenn du
-das Fenster schließt, beenden sich Strata und die Engine.
+[![Mac, Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### Option B: das Terminal (eine Zeile)
+Die App wählt die passende Engine für deine Grafikkarte selbst. Alle Dateien stehen auf der
+[Releases-Seite](https://github.com/Niko1221/Strata/releases/latest).
 
-Das Terminal ist der Befehl `strata`, gedacht für Skripte, Server und KI-Agents.
+| Erster Start | Was du tust |
+| --- | --- |
+| **Windows** | Starte die `.exe`. Du brauchst keine Administratorrechte. Wenn Windows "Der Computer wurde durch Windows geschützt" meldet, wähle **Weitere Informationen** und dann **Trotzdem ausführen**. |
+| **Linux** | Mach die Datei ausführbar (`chmod +x`) und starte sie. Sie braucht FUSE 2: `sudo apt install libfuse2t64` (Ubuntu 24.04 und neuer) oder `libfuse2` (22.04). |
+| **Mac** | Öffne die `.dmg` und zieh Strata in den Ordner "Programme". |
+
+Das Modell ist ein großer Download (40-70 GB). Wenn er abbricht, geht er dort weiter, wo er aufgehört hat.
+
+### 2. Das Terminal (eine Zeile)
+
+Der Befehl `strata`, für Skripte, Server und KI-Agents. Damit läuft auch DeepSeek.
 
 Linux und Mac:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows (PowerShell):
@@ -117,26 +105,17 @@ Windows (PowerShell):
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-Das Skript prüft deinen PC, lädt das Terminal herunter, kontrolliert die SHA-256-Prüfsumme und entpackt es in deinen
-Home-Ordner. Es braucht keine Administratorrechte. Öffne unter Windows danach ein neues Terminalfenster. Dann startest du
-Strata:
+Dann startest du es. Es stellt dir eine Frage nach der anderen (Modell, Kontext, Bilder, wer sich verbinden darf), lädt,
+was es braucht, und beginnt zu laufen:
 
 ```sh
 strata launch
 ```
 
-Es stellt dir eine Frage nach der anderen: Modell, Kontext, Bilder, wer sich verbinden darf. Danach lädt es die Engine für
-deine Grafikkarte herunter (signiert und vor der Nutzung probeweise gestartet), dazu das Modell, und beginnt zu laufen.
-Für Skripte und KI-Agents gibt es Flags:
+Du brauchst keine Administratorrechte. Die Installation prüft die SHA-256-Prüfsumme von allem, was sie herunterlädt. Öffne
+unter Windows nach der Installation ein neues Terminalfenster. Alle Bildschirme und Flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-Wenn du das Installationsskript vor dem Ausführen lesen willst, lade es zuerst mit `curl -fsSL <address> -o install.sh`
-herunter, lies es und führe dann `sh install.sh` aus. Alle Bildschirme und Flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
-
-### Option C: deine KI richtet es ein
+### 3. Deine KI richtet es ein
 
 Füge das in Claude Code, Cursor, Codex, GitHub Copilot oder einen anderen Coding-Assistenten ein:
 
@@ -152,48 +131,58 @@ Du willst es lieber selbst bauen? Siehe [Aus dem Quellcode bauen](#aus-dem-quell
 
 ## Modelle
 
-Die App und `strata launch` empfehlen ein Modell passend zu deinem Speicher. Es ist ein einziges Modell in mehreren
-Größen, mehr oder weniger stark komprimiert. Kleinere Größen sind schneller. Größere Größen sind etwas klüger.
+Die App und `strata launch` empfehlen eine Größe passend zu deinem Speicher. Kleinere Größen sind schneller, größere
+Größen sind etwas klüger.
 
 ### Wenig Speicher? Probier Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) (von agentionai) ist die kleinste Möglichkeit, dieses Modell auszuführen.
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) von agentionai ist die kleinste Möglichkeit, Qwen3.8-Flash-Next
+auszuführen. Es läuft auf NVIDIA, AMD, Intel Arc und Apple Silicon.
 
-| Größe | Benötigter Speicher (RAM + VRAM) | Download | Was es ist |
+| Größe | Benötigter Speicher (RAM + VRAM) | Download | Geeignet für |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27,6 GB | 58,5 GB | Für PCs, auf denen nichts anderes läuft. Die Qualität ist geringer als bei IQ2_XS. |
-| **Gyro-M** | 35 GB | 92,0 GB | Ungefähr die Qualität von IQ3_XXS bei etwa 20 % weniger GPU-Speicher. Es schreibt Antworten langsamer als Q2_0: 16 % auf einer RTX 3060 mit 12 GB, 21 % auf einer R9700. |
+| **Gyro-S** | 27,6 GB | 58,5 GB | PCs, auf denen nichts anderes läuft. 9 Tokens/s auf einem Mac mini mit 32 GB. |
+| **Gyro-M** | 35 GB | 92,0 GB | Ungefähr die Qualität von IQ3_XXS bei 20 % weniger GPU-Speicher. |
 
-Gyro läuft auf NVIDIA- und AMD-Karten (bei AMD experimentell) auf Intel-Arc-Karten unter Linux (getestet auf einer Arc A750) und ab 0.2.2 auf Macs mit Apple Silicon (Gyro-S auf einem Mac mini mit 32 GB: 9 Tokens/s, die Experten werden von der SSD gelesen). Details und Messwerte:
-[docs/GYRO.md](docs/GYRO.md). Starte es mit `strata launch --model gyro-s`.
+Starte es mit `strata launch --model gyro-s`. Details: [docs/GYRO.md](docs/GYRO.md).
 
-### Die anderen Größen
+### Die Größen von Qwen3.8-Flash-Next
 
-| Dein Speicher (RAM + VRAM) | Nimm | Hinweise |
+| Dein Speicher (RAM + VRAM) | Nimm | Warum |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**, oder den **[Coder](docs/MODELS.md#coder)** für Code | Der Coder braucht 32 GB RAM und behält die Hälfte der Experten, deshalb ist er außerhalb von Code schwächer |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB), oder **Gyro-M** (35 GB) | Swift denkt kürzer nach, bevor es antwortet. Gyro-M kommt der Qualität von IQ3_XXS nahe, schreibt Antworten aber 16-21 % langsamer als Q2_0 |
+| **32 GB** | **Gyro-S**, oder den **[Coder](docs/MODELS.md#coder)** für Code | Der Coder behält die Experten, die Code braucht |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB) oder **Gyro-M** | Swift denkt kürzer nach, bevor es antwortet |
 | **48 GB** | **IQ3_XXS** (47,0 GB) | Langsamer, besser |
-| **64 GB** | **IQ3_S** (54,8 GB), das Original oder Swift 1.5 | Am langsamsten, am besten. Es erreicht in den veröffentlichten Tests das volle Modell |
-| **96 GB oder mehr** | **UD-IQ4_XS** von Unsloth (etwa 72 GB RAM) bis **Q8_0** (etwa 136 GB), 4 bis 8 Bit | Näher am vollen Modell. Bei weniger RAM liest Strata einen Teil von der SSD, das ist viel langsamer |
+| **64 GB** | **IQ3_S** (54,8 GB) | Erreicht in den veröffentlichten Tests das volle Modell |
+| **96 GB oder mehr** | **UD-IQ4_XS** bis **Q8_0** von Unsloth | Am nächsten am vollen Modell |
 
-Auch mit weniger RAM, als eine Zeile nennt, kann es funktionieren: Strata wechselt von selbst in seinen
-[Modus für wenig RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Rechne mit weniger Tempo, mit einer kleinen
-Grafikkarte mit deutlich weniger.
+Auch mit weniger RAM, als eine Zeile nennt, kann es funktionieren, nur langsamer: Strata wechselt von selbst in seinen
+[Modus für wenig RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Außerdem gibt es:
+[NVFP4](docs/NVFP4.md) für NVIDIA-Karten, [Qwen3.6-35B-A3B](docs/QWEN36.md) (kleiner, mehrere Anfragen gleichzeitig) und
+[OrcaRouters Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs). Alle Größen und was wo läuft:
+[docs/MODELS.md](docs/MODELS.md).
 
-Weitere Auswahl:
+### DeepSeek V4.1-Flash (Terminal, ab 0.2.4)
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** ist eine Feinabstimmung, die kürzer nachdenkt, bevor sie antwortet, bei etwa gleicher Qualität und gleichem RAM-Bedarf.
-- **[NVFP4](docs/NVFP4.md)** ist NVIDIAs 4-Bit-Version für NVIDIA-Karten. Sie braucht etwa 80 GB RAM, um alle Experten im RAM zu halten.
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** ist ein kleineres, anderes Modell, das Bilder liest und mehrere Anfragen gleichzeitig beantworten kann.
-- **[OrcaRouters Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** richtest du von Hand ein.
+Ein deutlich größeres Modell, das auf einer Grafikkarte mit 12 GB und 46 bis 64 GB RAM läuft. Strata hält die meistgenutzten
+Teile im Speicher und liest den Rest von deiner SSD. [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)
+hat die Sets gebaut. Es läuft auf NVIDIA-RTX-Karten der Serien 30, 40 und 50 und auf der Radeon AI PRO R9700. Wähle es in
+`strata launch`. Die Desktop-App bietet es noch nicht an.
 
-Alle Größen, Downloads und was wo läuft: [docs/MODELS.md](docs/MODELS.md).
+| Set | Download | Qualität | Schreibt Code mit |
+| --- | ---: | --- | --- |
+| **IQ1_M** (1,75 Bit) | 239 GB | Das kleinste, schwächer bei einfacher Prosa | auf einem PC noch nicht gemessen |
+| **IQ2_XXS** (2.00 Bit) | 257 GB | Gute Balance | 10 Tokens/s (RTX 3060), 5 (RTX 5070), 48 (4x R9700) |
+| **IQ2_XS** (2.25 Bit) | 274 GB | Am nächsten am Original | 15 Tokens/s (eine R9700), 80 (4x R9700) |
+| **IQ4_NL** (Engram-Tabelle) | in jedem Download oben enthalten | Die Nachschlagetabelle, die alle drei Sets teilen | |
+
+Starte es mit `strata launch --model ist-das-2.00bpw` (oder `ist-das-1.75bpw`, `ist-das-2.25bpw`). Qualitätswerte,
+Geschwindigkeiten je PC und die manuelle Installation: [docs/DEEPSEEK41.md](docs/DEEPSEEK41.md).
 
 ## Wie schnell ist es?
 
-Gemessen mit einer Grafikkarte mit 12 GB (RTX 5070, Ryzen 5 7600, 64 GB RAM). Ergebnisse anderer Karten findest du hier:
-[Tempo jeder Größe](docs/MODELS.md#how-fast-is-each-size), [Ergebnisse der Community](docs/COMMUNITY_BENCHMARKS.md).
+Gemessen mit einer Grafikkarte mit 12 GB (RTX 5070, 64 GB RAM). Ergebnisse anderer Karten:
+[Tempo jeder Größe](docs/MODELS.md#how-fast-is-each-size) und [Ergebnisse der Community](docs/COMMUNITY_BENCHMARKS.md).
 
 | Modell | Antworten erscheinen mit | Liest deinen Prompt mit |
 | --- | --- | --- |
@@ -203,10 +192,7 @@ Gemessen mit einer Grafikkarte mit 12 GB (RTX 5070, Ryzen 5 7600, 64 GB RAM). Er
 | **IQ3_S** | `███████░░░░░` 53 Tokens/s | `███████░░░░░` 1.620 Tokens/s |
 | **Coder** | `███████░░░░░` 55 Tokens/s | `██████████░░` 2.180 Tokens/s |
 
-Ein Token ist etwa ¾ eines Wortes, 60 Tokens pro Sekunde sind also schneller, als du lesen kannst. "Liest deinen Prompt"
-beschreibt, wie schnell Strata ein langes Dokument, Code oder einen Chatverlauf aufnimmt.
-
-Gemessen mit einer AMD-Karte mit 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB RAM):
+Auf einer AMD-Karte mit 16 GB (RX 9070 XT, 47 GB RAM):
 
 | Modell | Antworten erscheinen mit | Liest deinen Prompt mit |
 | --- | --- | --- |
@@ -214,84 +200,59 @@ Gemessen mit einer AMD-Karte mit 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB RAM):
 | **IQ2_XS** | `███████░░░░░` 52 Tokens/s | `█████░░░░░░░` 1.110 Tokens/s |
 | **Coder** | `██████░░░░░░` 44 Tokens/s | `██████░░░░░░` 1.420 Tokens/s |
 
-Die Balken haben in beiden Tabellen denselben Maßstab. Eine Karte mit mehr VRAM ist schneller. Eine RTX 3090 (24 GB) sollte
-etwa 100-140 Tokens pro Sekunde schreiben. Die Engine-Version hinter jeder Zahl steht in [DETAILS.md](docs/DETAILS.md#speed-measured).
+Ein Token ist etwa ¾ eines Wortes, 60 Tokens pro Sekunde sind also schneller, als du lesen kannst. "Liest deinen Prompt"
+beschreibt, wie schnell Strata ein langes Dokument, Code oder einen Chatverlauf aufnimmt.
 
 ## Benutzung
 
 ### In der App
 
-Die App hat einen **Chat**, einen **Monitor** für das Modell sowie für GPU, CPU und RAM, eine Seite **Modelle** und die
-**Einstellungen**. Der Chat kann in einem Ordner auf deinem PC arbeiten. Im Modus **Manuell** fragt er nach, bevor er eine
-Datei ändert oder einen Befehl ausführt. Mit `/loop 10m <what to do>` wiederholst du eine Nachricht alle 10 Minuten, solange
-der Chat geöffnet ist.
+Ein Chat, ein **Monitor** für das Modell sowie für GPU, CPU und RAM, eine Seite **Modelle** und die **Einstellungen**. Der
+Chat kann in einem Ordner auf deinem PC arbeiten. Im Modus **Manuell** fragt er nach, bevor er eine Datei ändert oder einen
+Befehl ausführt. Er kann das Web durchsuchen (DuckDuckGo oder Bing, ohne Konto). Die Suchbegriffe sind das Einzige, was
+deinen PC verlässt.
 
-Der Chat kann das Web mit DuckDuckGo (oder Bing) durchsuchen, ohne Konto. Unter **Einstellungen, Tools** kannst du einen
-Suchschlüssel hinzufügen. Die Suche ist die einzige Funktion, die etwas von deinem PC sendet (die Suchbegriffe).
-
-Um zwei Modelle auszuführen, schalte **Mehrere Modelle ausführen** ein und gib jedem Modell eine eigene Karte desselben
-Herstellers.
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Ein Chat in der Strata-App: Der Agent hat einen kleinen Voxel-Pagodengarten als eine HTML-Datei geschrieben, und die Seite öffnet sich in der Vorschau neben dem Gespräch</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="Die Strata-App: ein Chat, in dem der Agent einen kleinen Voxel-Pagodengarten gebaut hat, die Seite ist rechts in der Vorschau geöffnet"><br>
+<sub>Der Agent hat einen Voxel-Pagodengarten als eine HTML-Datei geschrieben, und die Seite öffnet sich in der Vorschau neben dem Chat</sub></p>
 
 ### Im Terminal
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="Die Übersicht des Strata-Terminal-Monitors, während das Modell eine Antwort schreibt"><br>
 <sub><code>strata monitor</code>, während das Modell antwortet: Geschwindigkeit, GPU, Speicher und die letzten Anfragen</sub></p>
 
 ```sh
-strata launch                                  # guided screens: model, context, pictures, access, then serve
-strata launch --model q2_0 --yes --no-tui     # no questions: serve, print the address, return
-strata launch --plan --model q2_0              # show what would happen; nothing changes
-strata launch --status                         # what is being served now
-strata launch --stop                           # stop it
-strata monitor --url http://127.0.0.1:8080     # watch speed, GPU, memory and requests
-strata update --check                          # is there a new engine? (strata update installs it)
-strata doctor                                  # check the installed engine files
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` listet alles auf. Starten und Bereitstellen laden nichts herunter. Nur die Installation, `strata launch`
-(wenn du ein Modell wählst) und `strata update` tun das. Um Strata von deinem Handy oder einem anderen PC aus zu erreichen,
-nutze `strata launch --access lan`. Der Befehl erzeugt einen API-Schlüssel und startet in einem Netzwerk nicht ohne einen.
-Ein Browser öffnet sich nur, wenn du `--open` angibst. Anleitung: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md). Der ganze Client: [docs/TERMINAL.md](docs/TERMINAL.md).
+Um Strata von deinem Handy oder einem anderen PC aus zu erreichen, nutze `strata launch --access lan`. Der Befehl erzeugt
+einen API-Schlüssel für dich. `strata --help` listet alles auf, und [docs/TERMINAL.md](docs/TERMINAL.md) erklärt es.
 
-### Mit KI-Agents
+### Mit KI-Agents und anderen Apps
 
-Ein Agent installiert Strata mit dem Einzeiler aus Option B und führt
-`strata launch --model NAME --yes --no-tui` aus. Die Schritte, Flags und Exit-Codes stehen in [docs/AI_SETUP.md](docs/AI_SETUP.md),
-die Regeln für das Repository in [AGENTS.md](AGENTS.md).
+Ein Agent installiert Strata mit dem Einzeiler oben und führt `strata launch --model NAME --yes --no-tui` aus. Die Schritte,
+Flags und Exit-Codes stehen in [docs/AI_SETUP.md](docs/AI_SETUP.md). Die Regeln für das Repository stehen in [AGENTS.md](AGENTS.md).
 
-### Andere Apps verbinden
-
-| App-Typ | Basis-URL |
+| Deine App spricht | Basis-URL |
 | --- | --- |
-| OpenAI-kompatibel (die meisten Apps und Agents) | `http://127.0.0.1:8080/v1` (beliebiger API-Schlüssel, beliebiger Modellname) |
-| Anthropic-API (Claude Code und andere) | `http://127.0.0.1:8080`, ohne `/v1`. Diese Apps hängen `/v1/messages` selbst an. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| OpenAI-API (die meisten Apps und Agents) | `http://127.0.0.1:8080/v1` (beliebiger API-Schlüssel, beliebiger Modellname) |
+| Anthropic-API (Claude Code) | `http://127.0.0.1:8080`, ohne `/v1`. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | OpenAI Responses API (Codex CLI) | `http://127.0.0.1:8080/v1/responses` ([Einrichtung](docs/DETAILS.md#the-responses-api-and-codex-cli)) |
 
-`strata connect` gibt die genauen Einstellungen für OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent und OpenClaw aus.
-`strata connect opencode --write` schreibt die Datei nach einer Rückfrage und legt eine Sicherung an.
-
-### Bilder
-
-Bilder sind für Modelle, die sie lesen können, standardmäßig eingeschaltet. Hänge ein Bild im Chat an oder füge es ein, oder
-sende es aus deiner App. Der Bildleser läuft auf dem Prozessor, wenn deine Grafikkarte weniger als 24 GB hat (einige Sekunden
-pro Bild, ohne Speicher der Karte zu belegen), und ab 24 GB auf der Grafikkarte. Die Regel gilt für NVIDIA und AMD gleich.
-Du kannst Bilder pro Modell ausschalten oder den Leser mit `--vision off`, `--vision gpu` oder `--vision cpu` wählen.
-
-Die Zahlen hinter der Regel: Auf einer Radeon AI PRO R9700 brauchte der Bildleser der Karte 57 ms für ein Bild mit 260 Tokens,
-der des Prozessors 3,1 s. Auf Karten mit 16 GB (Tesla P100 und RTX A4000, Linux) kostete der Bildleser der Karte 3-5 % des
-Texttempos, weil er etwa 1,4 GB belegt, die sonst das Modell nutzen würde. Auf dem Mac liest die GPU, egal wie viel Speicher er hat (0,45 s für ein Bild mit 260 Tokens auf einem M4 mit 32 GB, etwa 1,2 GB des gemeinsamen
-Speichers); der Prozessor braucht dort etwa 50 s pro Bild und liest deshalb nur mit `--vision cpu`.
+`strata connect` gibt die genauen Einstellungen für OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent und OpenClaw
+aus, und `strata connect opencode --write` schreibt sie für dich (mit einer Sicherung).
 
 ### Gut zu wissen
 
-- Das Denkniveau (**aus, niedrig, mittel oder hoch**) stellst du im Chat-Menü oder unter "reasoning effort" in deiner App ein. Aus ist am schnellsten.
-- Strata beantwortet standardmäßig eine Anfrage nach der anderen. Für mehrere gleichzeitig nutze `--parallel N` in `strata launch` oder
-  `"parallel": 2` in der Konfiguration ([BATCHING.md](docs/BATCHING.md)). Auf einer Karte mit 12 GB wird dadurch jede Antwort langsamer.
-- Strata liest die erste Nachricht eines Chats komplett, etwa 1 Minute pro 30.000 Tokens. Folgenachrichten starten in Sekunden.
-- Wo deine Chats gespeichert werden und die ganze API: [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored), [docs/DETAILS.md](docs/DETAILS.md#using-it).
+- **Bilder** sind für jedes Modell eingeschaltet, das sie lesen kann. Hänge ein Bild im Chat an oder füge es ein, oder sende es aus deiner App. Details: [docs/IMAGES.md](docs/IMAGES.md).
+- **Das Denkniveau** kann aus, niedrig, mittel oder hoch sein, im Chat-Menü oder unter "reasoning effort" in deiner App. Aus ist am schnellsten.
+- **Die erste Nachricht** eines Chats wird komplett gelesen, etwa 1 Minute pro 30.000 Tokens. Folgenachrichten starten in Sekunden.
+- **Eine Anfrage nach der anderen** ist die Standardeinstellung. Für mehrere nutze `--parallel N` ([BATCHING.md](docs/BATCHING.md)). Auf einer Karte mit 12 GB wird dadurch jede Antwort langsamer.
 
 ## Aus dem Quellcode bauen
 
@@ -353,13 +314,13 @@ Strata bringt das Modell auf deinen PC, indem es die Arbeit auf den ganzen Rechn
 - **Deine SSD ist das Archiv.** Sie enthält eine Nachschlagetabelle von 29 GB. Das Modell liest pro Wort nur wenige Zeilen
   daraus, deshalb muss sie nicht im RAM liegen.
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="Die 24.576 Experten des Modells: die meistgenutzten auf der Grafikkarte, alle im RAM, eine Nachschlagetabelle auf der SSD"></p>
 
 Ein kleiner Helfer rät außerdem die nächsten Wörter. Das große Modell prüft sie alle auf einmal und behält die richtigen. Du
 bekommst dieselbe Antwort, 1,6-1,8-mal früher. Lange Texte werden in großen Stücken gelesen, bis zu 8.192 Tokens auf einmal,
 mit über 1.000 Tokens pro Sekunde.
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="Ein kleiner Helfer rät die nächsten Wörter, das große Modell prüft sie alle auf einmal und behält die richtigen"></p>
 
 Die ausführliche Erklärung: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Jeder Teil mit seinen Zahlen:
 [die Details](docs/DETAILS.md#how-it-works) und das [Paper](docs/paper/Strata-Paper.pdf).
@@ -369,25 +330,27 @@ Die ausführliche Erklärung: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Jede
 - **Mein PC ist beim ersten Start von Strata eingefroren.** Strata lädt das Modell in den RAM. Warte ab und schließe das
   Fenster nicht. Nach 10 Minuten immer noch eingefroren? Starte den PC neu, schließe andere Programme und versuch es noch
   einmal, oder wähle eine kleinere Größe.
-- **Es ist beim Herunterladen oder Installieren stehen geblieben.** Starte die App oder `strata launch` noch einmal, oder
-  führe `START-HERE.bat` (oder `./setup.sh`) erneut aus. Es macht dort weiter, wo es aufgehört hat.
-- **Es ist sehr langsam, die Festplattenanzeige blinkt ständig, oder es meldet "the engine stopped unexpectedly".** Dein PC
-  hat nicht genug freien RAM. Schließe andere Programme (Browser brauchen viel) oder wähle eine kleinere Größe wie Q2_0 oder IQ2_XS.
+- **Es ist beim Herunterladen oder Installieren stehen geblieben.** Starte die App oder `strata launch` noch einmal. Es
+  macht dort weiter, wo es aufgehört hat.
+- **Es ist sehr langsam, oder es meldet "the engine stopped unexpectedly".** Dein PC hat nicht genug freien RAM. Schließe
+  andere Programme (Browser brauchen viel) oder wähle eine kleinere Größe wie Q2_0 oder IQ2_XS.
 - **Es meldet, dass es keine Engine für diesen PC gibt.** Öffne in der App **Einstellungen, Engine** und drücke **Engine
-  aktualisieren**. Führe im Terminal `strata update` aus. `strata doctor` zeigt, welche Engine-Dateien installiert sind.
+  aktualisieren**. Führe im Terminal `strata update` aus.
 - **Es meldet, dass Port 8080 schon belegt ist.** Strata läuft bereits. Such das Fenster.
 
-Weitere Probleme und Lösungen: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Du kommst nicht weiter? Öffne ein
-[Issue](https://github.com/Niko1221/Strata/issues). Hänge in der App die Datei aus **Einstellungen, Engine, Diagnose, Protokolle anzeigen, Protokolle speichern** an. Füge im Terminal die Ausgabe von `strata doctor` ein. Hänge beim Start aus dem Quellcode die
-Datei `strata-<model>.log` aus dem Strata-Ordner an. Ein Sicherheitsproblem meldest du bitte privat: [SECURITY.md](SECURITY.md).
+Weitere Lösungen: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Du kommst nicht weiter? Öffne ein
+[Issue](https://github.com/Niko1221/Strata/issues) und hänge die Protokolle an: in der App unter **Einstellungen, Engine,
+Diagnose, Protokolle speichern**, im Terminal die Ausgabe von `strata doctor`. Ein Sicherheitsproblem meldest du bitte
+privat: [SECURITY.md](SECURITY.md).
 
 ## Danksagung und Lizenz
 
 Das Modell ist [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) vom Qwen-Team. Komprimiert wurde es von
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5), agentionai (Gyro)
-und Unsloth. Strata nutzt Teile von [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Alle Danksagungen:
-[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). Strata ist Open Source unter der [MIT-Lizenz](LICENSE). Einige Teile und
-alle Modelle haben eigene Lizenzen ([welche](docs/HOW_IT_WORKS.md#license)).
+und Unsloth. ISTA-DASLab hat auch die Sets von DeepSeek V4.1-Flash gebaut. Strata nutzt Teile von
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Alle Danksagungen: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits).
+Strata ist Open Source unter der [MIT-Lizenz](LICENSE). Einige Teile und alle Modelle haben eigene Lizenzen
+([welche](docs/HOW_IT_WORKS.md#license)).
 
 ## Mitmachen
 

README.es.md

@@ -12,104 +12,91 @@
 <p align="center">Compatible con NVIDIA, AMD, Intel · Windows, Linux, Mac · libre y de código abierto</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Última versión"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="Licencia MIT"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="Estrellas en GitHub"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="Invítame a un café"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Un jardín con una pagoda de vóxeles que escribió el modelo de Strata, funcionando en el navegador"></a><br>
 <sub>Un jardín con una pagoda de vóxeles, hecho con un solo prompt en una RTX 5070 con Strata (IQ3_S, contexto de 128K) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">vídeo completo (49 s)</a></sub></p>
 
-Strata ejecuta **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, un modelo de 125 mil millones
-de parámetros que normalmente necesita un servidor, en un PC normal. Conversa, escribe código, lee imágenes y funciona
-con tus aplicaciones y tus agentes de programación. Tus chats y tus archivos se quedan en tu PC.
+<p align="center">
+  <a href="#instalación"><b>Instalación</b></a> ·
+  <a href="#modelos">Modelos</a> ·
+  <a href="#qué-velocidad-tiene">Velocidad</a> ·
+  <a href="#uso">Uso</a> ·
+  <a href="#cómo-funciona">Cómo funciona</a> ·
+  <a href="#algo-ha-ido-mal">Ayuda</a> ·
+  <a href="#apoya-strata">Apoyar</a>
+</p>
 
-**¿Eres nuevo?** Mira [lo que necesitas](#lo-que-necesitas) y luego [instala la aplicación](#opción-a-la-aplicación-strata).
+Strata ejecuta **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, un modelo de 125 mil millones
+de parámetros que normalmente necesita un servidor, en un PC normal. Desde 0.2.4 también ejecuta **DeepSeek V4.1-Flash**
+en la Terminal. Conversa, escribe código, lee imágenes y funciona con tus aplicaciones y tus agentes de programación. Tus
+chats y tus archivos se quedan en tu PC.
 
 - **Funciona en un PC gaming.** Con 32 GB entre RAM y memoria gráfica ya puedes empezar.
-- **Funciona con tus herramientas.** Habla las API de OpenAI y de Anthropic, así que Claude Code, Codex CLI, OpenCode y otros agentes se conectan a él.
-- **Lee imágenes.** Viene activado por defecto.
-- **Gratis.** Licencia MIT, sin cuenta, sin nube.
-- **Privado.** Sin telemetría. Lo que Strata descarga, cuándo usa internet y cómo comprueba las descargas está en [docs/SAFETY.md](docs/SAFETY.md).
-
-Versión 0.2.3 · motor 0.1.48
+- **Funciona con tus herramientas.** Claude Code, Codex CLI, OpenCode y otros agentes se conectan por las API de OpenAI y de Anthropic.
+- **Lee imágenes**, activado por defecto.
+- **Gratis y privado.** Licencia MIT, sin cuenta, sin nube, sin telemetría ([qué descarga y cuándo](docs/SAFETY.md)).
 
 ## Lo que necesitas
 
-**Necesitas al menos 32 GB entre RAM y memoria gráfica (VRAM).** En un Mac o un Ryzen AI Max, es la memoria unificada.
-Con más memoria puedes usar un modelo más grande o más rápido.
+**Necesitas al menos 32 GB de memoria: RAM y memoria gráfica (VRAM) juntas.** En un Mac o un Ryzen AI Max, es la memoria
+unificada. Un PC de 32 GB con una tarjeta de 12 a 16 GB ejecuta los tamaños más pequeños, y con 64 GB funcionan todos los
+tamaños.
 
-- Un PC de 32 GB con una tarjeta de 12 a 16 GB ejecuta el Coder.
-- Con 64 GB de RAM funcionan todos los tamaños.
-
-| Tu ordenador | Detalles |
+| Funciona en | Guía |
 | --- | --- |
-| **NVIDIA** GeForce RTX serie 20, 30, 40, 50 (12 GB o más) | Instala la aplicación o la Terminal. |
-| **AMD** Radeon RX 6800 y posteriores, Radeon AI PRO R9700 (12 GB o más) | [Tarjetas AMD](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md), [motor Intel](docs/INTEL.md) |
-| **Mac con Apple Silicon** (M1 o posterior, macOS 15 o posterior) | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max (Strix Halo)** y otros sistemas con memoria unificada | [Strix Halo](docs/STRIX_HALO.md) |
-| Tarjetas y procesadores antiguos | [GPU antiguas](docs/OLDER_GPUS.md), [CPU antiguas](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX serie 20, 30, 40 y 50, 12 GB o más | [Instalación](#instalación) |
+| **AMD** Radeon RX 6800 y posteriores, Radeon AI PRO R9700 | [Tarjetas AMD](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Mac con Apple Silicon**, M1 o posterior, macOS 15 o posterior | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max (Strix Halo)** y otros PC con memoria unificada | [Strix Halo](docs/STRIX_HALO.md) |
+| Tarjetas y procesadores antiguos | [GPU antiguas](docs/OLDER_GPUS.md) |
 
-También hace falta:
-
-- unos 80 GB de disco libre (con un SSD el primer arranque es mucho más rápido)
-- Windows 10 / 11, Linux o macOS
-- un controlador gráfico actual
-
-Dos o tres tarjetas de la misma marca pueden compartir un modelo ([multi-GPU](docs/MULTI_GPU.md)). Strata nunca reparte un
-modelo entre tarjetas NVIDIA y AMD. Lista completa: [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
+También necesitas unos 80 GB de disco libre (un SSD), Windows 10 / 11, Linux o macOS, y un controlador gráfico actual. Dos
+o tres tarjetas de la misma marca pueden compartir un modelo ([multi-GPU](docs/MULTI_GPU.md)).
 
 ## Instalación
 
-Elige una opción. Todas arrancan el mismo motor y usan los mismos modelos.
+### 1. La aplicación Strata (la más fácil)
 
-### Opción A: la aplicación Strata
+Descarga el archivo para tu ordenador, ábrelo y pulsa Instalar en el modelo que recomienda.
 
-La forma más fácil. La aplicación lleva el motor dentro: la instalas, eliges un modelo y chateas. Descarga el archivo para
-tu sistema y tu tarjeta gráfica desde la [página de versiones](https://github.com/Niko1221/Strata/releases/latest). ¿No
-sabes cuál elegir? Mira el párrafo que hay debajo de la tabla.
+**Windows 10 / 11**
 
-| Sistema | Tu tarjeta gráfica | Archivo que descargar |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX, controlador 580 o posterior | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA, tarjeta más antigua o controlador anterior a 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon serie RX 9000 o Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon serie RX 7000 o Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX, controlador 580 o posterior | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA, tarjeta más antigua o controlador anterior a 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon serie RX 9000 o Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon serie RX 7000 | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac** (Apple Silicon, macOS 15 o posterior) | integrada | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**Si no estás seguro:** con NVIDIA, elige `cuda13` si la versión de tu controlador es la 580 o posterior, y `cuda12` en caso
-contrario. `cuda12` es para tarjetas y controladores más antiguos. Los archivos `hip` y `amd` son para tarjetas AMD. Las
-demás tarjetas AMD (RX 6000) todavía no tienen una aplicación ya preparada: mira
-[Tarjetas AMD](docs/AMD_HIP.md).
+**Linux**
 
-Después:
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows:** ejecuta el `.exe`. Se instala para tu usuario y no necesita permisos de administrador. Si Windows muestra
-  "Windows protegió tu PC", elige **Más información** y luego **Ejecutar de todas formas** (el instalador todavía no está
-  firmado).
-- **Linux:** haz el archivo ejecutable (`chmod +x`) y lánzalo. Necesita FUSE 2: `sudo apt install libfuse2` (Ubuntu 22.04)
-  o `libfuse2t64` (Ubuntu 24.04 y posteriores).
-- **Mac:** abre el `.dmg` y arrastra Strata a Aplicaciones.
+**Mac** (Apple Silicon, macOS 15 o posterior)
 
-En la primera pantalla, la aplicación analiza tu PC y recomienda un modelo adecuado. Pulsa Instalar. El modelo es una
-descarga grande (unos 40 a 70 GB) y, si se interrumpe, continúa donde se quedó. Al cerrar la ventana, Strata y el motor se
-detienen.
+[![Mac, Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### Opción B: la Terminal (una línea)
+La aplicación elige sola el motor adecuado para tu tarjeta gráfica. Todos los archivos están en la
+[página de versiones](https://github.com/Niko1221/Strata/releases/latest).
 
-La Terminal es el comando `strata`, pensado para scripts, servidores y agentes de IA.
+| Primer arranque | Qué hacer |
+| --- | --- |
+| **Windows** | Ejecuta el `.exe`. No necesita permisos de administrador. Si Windows muestra "Windows protegió tu PC", elige **Más información** y luego **Ejecutar de todas formas**. |
+| **Linux** | Haz el archivo ejecutable (`chmod +x`) y lánzalo. Necesita FUSE 2: `sudo apt install libfuse2t64` (Ubuntu 24.04 y posteriores) o `libfuse2` (22.04). |
+| **Mac** | Abre el `.dmg` y arrastra Strata a Aplicaciones. |
+
+La descarga del modelo es grande (40-70 GB). Si se detiene, continúa donde se quedó.
+
+### 2. La Terminal (una línea)
+
+El comando `strata`, para scripts, servidores y agentes de IA. Es también la forma de ejecutar DeepSeek.
 
 Linux y Mac:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows (PowerShell):
@@ -118,25 +105,17 @@ Windows (PowerShell):
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-El script analiza tu PC, descarga la Terminal, verifica su SHA-256 y la descomprime en tu carpeta personal. No necesita
-permisos de administrador. En Windows, abre una ventana de terminal nueva después. Luego arranca Strata:
+Después arráncalo. Te hace una pregunta cada vez (modelo, contexto, imágenes, quién puede conectarse), descarga lo que
+necesita y empieza a servir:
 
 ```sh
 strata launch
 ```
 
-Te hace una pregunta cada vez: modelo, contexto, imágenes, quién puede conectarse. Después descarga el motor para tu tarjeta
-gráfica (firmado y arrancado como prueba antes de usarlo) y el modelo, y empieza a servir. Para scripts y agentes de IA, usa
-opciones:
+No necesita permisos de administrador. La instalación comprueba el SHA-256 de todo lo que descarga. En Windows, abre una
+ventana de terminal nueva después de la instalación. Todas las pantallas y opciones: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-Si quieres leer el script de instalación antes de ejecutarlo, descárgalo primero con `curl -fsSL <address> -o install.sh`,
-léelo y luego ejecuta `sh install.sh`. Todas las pantallas y opciones: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
-
-### Opción C: que lo instale tu IA
+### 3. Que lo instale tu IA
 
 Pega esto en Claude Code, Cursor, Codex, GitHub Copilot u otro asistente de programación:
 
@@ -152,48 +131,58 @@ cómo conectar tus aplicaciones. Las herramientas de IA también pueden instalar
 
 ## Modelos
 
-La aplicación y `strata launch` recomiendan un modelo según tu memoria. Es un solo modelo en varios tamaños, más o menos
-comprimido. Los tamaños pequeños son más rápidos. Los grandes son algo más inteligentes.
+La aplicación y `strata launch` recomiendan un tamaño según tu memoria. Los tamaños pequeños son más rápidos. Los grandes
+son algo más inteligentes.
 
 ### ¿Poca memoria? Prueba Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) (de agentionai) es la forma más pequeña de ejecutar este modelo.
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) de agentionai es la forma más pequeña de ejecutar
+Qwen3.8-Flash-Next. Funciona en NVIDIA, AMD, Intel Arc y Apple Silicon.
 
-| Tamaño | Memoria que necesita (RAM + VRAM) | Descarga | Qué es |
+| Tamaño | Memoria que necesita (RAM + VRAM) | Descarga | Para qué sirve |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27,6 GB | 58,5 GB | Para PC donde no cabe nada más. La calidad es menor que la de IQ2_XS. |
-| **Gyro-M** | 35 GB | 92,0 GB | Calidad parecida a IQ3_XXS con un 20 % menos de memoria de GPU. Escribe las respuestas un 16 % más despacio que Q2_0 en una RTX 3060 de 12 GB y un 21 % más despacio en una R9700. |
+| **Gyro-S** | 27,6 GB | 58,5 GB | PC donde no cabe nada más. 9 tokens/s en un Mac mini de 32 GB. |
+| **Gyro-M** | 35 GB | 92,0 GB | Calidad parecida a IQ3_XXS con un 20 % menos de memoria de GPU. |
 
-Gyro funciona en tarjetas NVIDIA y AMD (en AMD es experimental) en tarjetas Intel Arc con Linux (probado en una Arc A750) y, desde 0.2.2, en Mac con Apple Silicon (Gyro-S en un Mac mini de 32 GB: 9 tokens/s, con los expertos leídos del SSD). Detalles y mediciones:
-[docs/GYRO.md](docs/GYRO.md). Arráncalo con `strata launch --model gyro-s`.
+Arráncalo con `strata launch --model gyro-s`. Detalles: [docs/GYRO.md](docs/GYRO.md).
 
-### Los demás tamaños
+### Los tamaños de Qwen3.8-Flash-Next
 
-| Tu memoria (RAM + VRAM) | Elige | Notas |
+| Tu memoria (RAM + VRAM) | Elige | Por qué |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**, o el **[Coder](docs/MODELS.md#coder)** para código | El Coder necesita 32 GB de RAM y conserva la mitad de los expertos, así que es más flojo fuera del código |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB), o **Gyro-M** (35 GB) | Swift piensa menos tiempo antes de responder. Gyro-M se acerca a la calidad de IQ3_XXS, pero escribe las respuestas un 16-21 % más despacio que Q2_0 |
+| **32 GB** | **Gyro-S**, o el **[Coder](docs/MODELS.md#coder)** para código | El Coder conserva los expertos que usa el código |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB) o **Gyro-M** | Swift piensa menos tiempo antes de responder |
 | **48 GB** | **IQ3_XXS** (47,0 GB) | Más lento, mejor |
-| **64 GB** | **IQ3_S** (54,8 GB), el original o Swift 1.5 | El más lento, el mejor. Iguala al modelo completo en las pruebas publicadas |
-| **96 GB o más** | **UD-IQ4_XS** de Unsloth (unos 72 GB de RAM) hasta **Q8_0** (unos 136 GB), de 4 a 8 bits | Más cerca del modelo completo. Con menos RAM, Strata lee una parte desde el SSD, que es mucho más lento |
+| **64 GB** | **IQ3_S** (54,8 GB) | Iguala al modelo completo en las pruebas publicadas |
+| **96 GB o más** | **UD-IQ4_XS** hasta **Q8_0** de Unsloth | Lo más cerca del modelo completo |
 
-Con menos RAM de la que indica una fila también puede funcionar: Strata pasa solo a su
-[modo de poca RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Espera que sea más lento, y mucho más lento con una
-tarjeta gráfica pequeña.
+Con menos RAM de la que indica una fila también puede funcionar, solo que más lento: Strata pasa solo a su
+[modo de poca RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). También hay:
+[NVFP4](docs/NVFP4.md) para tarjetas NVIDIA, [Qwen3.6-35B-A3B](docs/QWEN36.md) (más pequeño, varias peticiones a la vez) y
+[el Uncensored IQ3_XXS de OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs). Todos los tamaños y lo que cabe en cada equipo:
+[docs/MODELS.md](docs/MODELS.md).
 
-Más opciones:
+### DeepSeek V4.1-Flash (Terminal, desde 0.2.4)
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** es un ajuste fino que piensa menos tiempo antes de responder, con una calidad y un uso de RAM casi iguales.
-- **[NVFP4](docs/NVFP4.md)** es la versión de 4 bits de NVIDIA para tarjetas NVIDIA. Necesita unos 80 GB de RAM para tener todos los expertos en RAM.
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** es un modelo más pequeño y distinto que lee imágenes y puede atender varias peticiones a la vez.
-- **[El Uncensored IQ3_XXS de OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** se configura a mano.
+Un modelo mucho más grande que funciona con una sola tarjeta gráfica de 12 GB y de 46 a 64 GB de RAM. Strata mantiene en
+memoria las partes más usadas y lee el resto de tu SSD. [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)
+hizo los conjuntos. Funciona en tarjetas NVIDIA RTX de las series 30, 40 y 50 y en la Radeon AI PRO R9700. Elígelo en
+`strata launch`. La aplicación de escritorio todavía no lo ofrece.
 
-Todos los tamaños, descargas y lo que cabe en cada equipo: [docs/MODELS.md](docs/MODELS.md).
+| Conjunto | Descarga | Calidad | Escribe código a |
+| --- | ---: | --- | --- |
+| **IQ1_M** (1,75 bits) | 239 GB | El más pequeño, más débil con prosa sencilla | aún sin medir en un PC |
+| **IQ2_XXS** (2.00 bits) | 257 GB | Buen equilibrio | 10 tokens/s (RTX 3060), 5 (RTX 5070), 48 (4x R9700) |
+| **IQ2_XS** (2.25 bits) | 274 GB | Lo más cerca del original | 15 tokens/s (una R9700), 80 (4x R9700) |
+| **IQ4_NL** (tabla Engram) | incluida en cada descarga de arriba | La tabla de consulta que comparten los tres conjuntos | |
+
+Arráncalo con `strata launch --model ist-das-2.00bpw` (o `ist-das-1.75bpw`, `ist-das-2.25bpw`). Cifras de calidad,
+velocidades por PC e instalación manual: [docs/DEEPSEEK41.md](docs/DEEPSEEK41.md).
 
 ## ¿Qué velocidad tiene?
 
-Medido con una tarjeta gráfica de 12 GB (RTX 5070, Ryzen 5 7600, 64 GB de RAM). Resultados con otras tarjetas:
-[velocidad de cada tamaño](docs/MODELS.md#how-fast-is-each-size), [resultados de la comunidad](docs/COMMUNITY_BENCHMARKS.md).
+Medido con una tarjeta gráfica de 12 GB (RTX 5070, 64 GB de RAM). Resultados con otras tarjetas:
+[velocidad de cada tamaño](docs/MODELS.md#how-fast-is-each-size) y [resultados de la comunidad](docs/COMMUNITY_BENCHMARKS.md).
 
 | Modelo | Las respuestas aparecen a | Lee tu prompt a |
 | --- | --- | --- |
@@ -203,10 +192,7 @@ Medido con una tarjeta gráfica de 12 GB (RTX 5070, Ryzen 5 7600, 64 GB de RAM).
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1.620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2.180 tokens/s |
 
-Un token equivale a unos ¾ de palabra, así que 60 tokens por segundo es más rápido de lo que puedes leer. "Lee tu prompt"
-es lo rápido que Strata procesa un documento largo, código o un historial de chat.
-
-Medido con una tarjeta AMD de 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB de RAM):
+Con una tarjeta AMD de 16 GB (RX 9070 XT, 47 GB de RAM):
 
 | Modelo | Las respuestas aparecen a | Lee tu prompt a |
 | --- | --- | --- |
@@ -214,83 +200,58 @@ Medido con una tarjeta AMD de 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB de RAM):
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1.110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1.420 tokens/s |
 
-Las barras usan la misma escala en las dos tablas. Una tarjeta con más VRAM es más rápida. Una RTX 3090 (24 GB) debería
-escribir unos 100-140 tokens por segundo. La versión del motor detrás de cada cifra está en [DETAILS.md](docs/DETAILS.md#speed-measured).
+Un token equivale a unos ¾ de palabra, así que 60 tokens por segundo es más rápido de lo que puedes leer. "Lee tu prompt"
+es lo rápido que Strata procesa un documento largo, código o un historial de chat.
 
 ## Uso
 
 ### En la aplicación
 
-La aplicación tiene un **Chat**, un **Monitor** del modelo y de tu GPU, CPU y RAM, una página de **Modelos** y los
-**Ajustes**. El chat puede trabajar en una carpeta de tu PC. En modo **Manual** pregunta antes de cambiar un archivo o
-ejecutar un comando. Escribe `/loop 10m <what to do>` para repetir un mensaje cada 10 minutos mientras el chat esté abierto.
+Un chat, un **Monitor** del modelo y de tu GPU, CPU y RAM, una página de **Modelos** y los **Ajustes**. El chat puede
+trabajar en una carpeta de tu PC. En modo **Manual** pregunta antes de cambiar un archivo o ejecutar un comando. Puede buscar
+en la web (DuckDuckGo o Bing, sin cuenta). Las palabras que buscas son lo único que sale de tu PC.
 
-El chat puede buscar en la web con DuckDuckGo (o Bing), sin cuenta. Puedes añadir una clave de búsqueda en **Ajustes,
-Herramientas**. La búsqueda es la única función que envía algo fuera de tu PC (las palabras que buscas).
-
-Para ejecutar dos modelos, activa **Ejecutar varios modelos** y dale a cada modelo su propia tarjeta de la misma marca.
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Un chat en la app de Strata: el agente escribió un pequeño jardín de pagoda de vóxeles en un solo archivo HTML, y la página se abre en la vista previa junto a la conversación</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="La aplicación Strata: un chat donde el agente construyó un pequeño jardín con una pagoda de vóxeles, con la página abierta en la vista previa a la derecha"><br>
+<sub>El agente escribió un jardín con una pagoda de vóxeles en un solo archivo HTML, y la página se abre en la vista previa junto al chat</sub></p>
 
 ### En la Terminal
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="La vista general del monitor de la Terminal de Strata mientras el modelo escribe una respuesta"><br>
 <sub><code>strata monitor</code> mientras el modelo responde: velocidad, GPU, memoria y las últimas solicitudes</sub></p>
 
 ```sh
-strata launch                                  # guided screens: model, context, pictures, access, then serve
-strata launch --model q2_0 --yes --no-tui     # no questions: serve, print the address, return
-strata launch --plan --model q2_0              # show what would happen; nothing changes
-strata launch --status                         # what is being served now
-strata launch --stop                           # stop it
-strata monitor --url http://127.0.0.1:8080     # watch speed, GPU, memory and requests
-strata update --check                          # is there a new engine? (strata update installs it)
-strata doctor                                  # check the installed engine files
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` lo lista todo. Arrancar y servir no descargan nada. Solo lo hacen la instalación, `strata launch` (cuando
-eliges un modelo) y `strata update`. Para llegar a Strata desde tu móvil u otro PC, usa `strata launch --access lan`. Crea
-una clave de API y no arranca en una red sin ella. No se abre ningún navegador salvo que añadas `--open`. Guía:
-[docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md). El cliente completo: [docs/TERMINAL.md](docs/TERMINAL.md).
+Para llegar a Strata desde tu móvil u otro PC, usa `strata launch --access lan`. Crea una clave de API para ti.
+`strata --help` lo lista todo, y [docs/TERMINAL.md](docs/TERMINAL.md) lo explica.
 
-### Con agentes de IA
+### Con agentes de IA y otras aplicaciones
 
-Un agente instala Strata con el comando de una línea de la opción B y ejecuta
-`strata launch --model NAME --yes --no-tui`. Los pasos, las opciones y los códigos de salida están en [docs/AI_SETUP.md](docs/AI_SETUP.md),
-y las reglas del repositorio en [AGENTS.md](AGENTS.md).
+Un agente instala Strata con el comando de una línea de arriba y ejecuta `strata launch --model NAME --yes --no-tui`. Los
+pasos, las opciones y los códigos de salida están en [docs/AI_SETUP.md](docs/AI_SETUP.md). Las reglas del repositorio para agentes: [AGENTS.md](AGENTS.md).
 
-### Conecta tus otras aplicaciones
-
-| Tipo de aplicación | URL base |
+| Tu aplicación habla | URL base |
 | --- | --- |
-| Compatible con OpenAI (la mayoría de aplicaciones y agentes) | `http://127.0.0.1:8080/v1` (cualquier clave de API, cualquier nombre de modelo) |
-| API de Anthropic (Claude Code y otros) | `http://127.0.0.1:8080`, sin `/v1`. Estas aplicaciones añaden `/v1/messages` por su cuenta. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| API de OpenAI (la mayoría de aplicaciones y agentes) | `http://127.0.0.1:8080/v1` (cualquier clave de API, cualquier nombre de modelo) |
+| API de Anthropic (Claude Code) | `http://127.0.0.1:8080`, sin `/v1`. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | API OpenAI Responses (Codex CLI) | `http://127.0.0.1:8080/v1/responses` ([configuración](docs/DETAILS.md#the-responses-api-and-codex-cli)) |
 
-`strata connect` muestra los ajustes exactos para OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent y OpenClaw.
-`strata connect opencode --write` escribe el archivo después de preguntar y guarda una copia de seguridad.
-
-### Imágenes
-
-Las imágenes vienen activadas por defecto en los modelos que pueden leerlas. Adjunta o pega una imagen en el chat, o envíala
-desde tu aplicación. El lector de imágenes funciona en el procesador cuando tu tarjeta gráfica tiene menos de 24 GB (unos
-segundos por imagen, sin quitar memoria a la tarjeta) y en la tarjeta gráfica a partir de 24 GB. La regla es la misma para
-NVIDIA y AMD. Puedes desactivar las imágenes por modelo, o elegir el lector con `--vision off`, `--vision gpu` o
-`--vision cpu`.
-
-Las cifras detrás de la regla: en una Radeon AI PRO R9700, el lector de la tarjeta tardó 57 ms en una imagen de 260 tokens y
-el del procesador 3,1 s. En tarjetas de 16 GB (Tesla P100 y RTX A4000, Linux), el lector de la tarjeta costó un 3-5 % de
-velocidad en texto, porque ocupa unos 1,4 GB que de otro modo usaría el modelo. En un Mac lee la GPU, tenga la memoria que tenga (0,45 s para una imagen de 260 tokens en un M4 de 32 GB, unos 1,2 GB de la memoria compartida);
-el procesador tarda unos 50 s por imagen, así que solo lee con `--vision cpu`.
+`strata connect` muestra los ajustes exactos para OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent y OpenClaw,
+y `strata connect opencode --write` los escribe por ti (con una copia de seguridad).
 
 ### Conviene saber
 
-- Elige el nivel de razonamiento (**desactivado, bajo, medio o alto**) en el menú del chat o en "reasoning effort" de tu aplicación. Desactivado es lo más rápido.
-- Strata responde a una petición a la vez por defecto. Para varias a la vez, usa `--parallel N` en `strata launch` o
-  `"parallel": 2` en la configuración ([BATCHING.md](docs/BATCHING.md)). En una tarjeta de 12 GB, esto hace más lenta cada respuesta.
-- Strata lee entero el primer mensaje de un chat, unos 1 minuto por cada 30.000 tokens. Los mensajes siguientes empiezan en segundos.
-- Dónde se guardan tus chats y la API completa: [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored), [docs/DETAILS.md](docs/DETAILS.md#using-it).
+- **Las imágenes** vienen activadas en todos los modelos que pueden leerlas. Adjunta o pega una imagen en el chat, o envíala desde tu aplicación. Detalles: [docs/IMAGES.md](docs/IMAGES.md).
+- **El razonamiento** puede estar desactivado, bajo, medio o alto, en el menú del chat o en "reasoning effort" de tu aplicación. Desactivado es lo más rápido.
+- **El primer mensaje** de un chat se lee entero, unos 1 minuto por cada 30.000 tokens. Los mensajes siguientes empiezan en segundos.
+- **Una petición a la vez** es lo normal. Para varias, usa `--parallel N` ([BATCHING.md](docs/BATCHING.md)). En una tarjeta de 12 GB, esto hace más lenta cada respuesta.
 
 ## Compilar desde el código fuente
 
@@ -351,13 +312,13 @@ Los modelos como este suelen ejecutarse en servidores con cientos de gigabytes d
 - **Tu SSD es el archivo.** Guarda una tabla de consulta de 29 GB. El modelo lee unas pocas filas por palabra, así que no
   hace falta que esté en la RAM.
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="Los 24.576 expertos del modelo: los más usados en la tarjeta gráfica, todos en la RAM, una tabla de consulta en el SSD"></p>
 
 Un pequeño ayudante también adivina las siguientes palabras. El modelo grande las comprueba todas a la vez y se queda con
 las correctas. Obtienes la misma respuesta, entre 1,6 y 1,8 veces antes. Los textos largos se leen en trozos grandes, de
 hasta 8.192 tokens a la vez, a más de 1.000 tokens por segundo.
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="Un pequeño ayudante adivina las siguientes palabras; el modelo grande las comprueba todas a la vez y se queda con las correctas"></p>
 
 La explicación más larga: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Cada parte con sus cifras:
 [los detalles](docs/DETAILS.md#how-it-works) y el [artículo](docs/paper/Strata-Paper.pdf).
@@ -366,27 +327,27 @@ La explicación más larga: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Cada p
 
 - **Mi PC se congeló la primera vez que arrancó Strata.** Carga el modelo en la RAM. Espera y no cierres la ventana. ¿Sigue
   congelado después de 10 minutos? Reinicia el PC, cierra otros programas e inténtalo de nuevo, o elige un tamaño más pequeño.
-- **Se detuvo durante la descarga o la instalación.** Abre de nuevo la aplicación o `strata launch`, o vuelve a ejecutar
-  `START-HERE.bat` (o `./setup.sh`). Continúa donde se quedó.
-- **Va muy lento, la luz del disco parpadea sin parar, o dice "the engine stopped unexpectedly".** Tu PC no tiene bastante
-  RAM libre. Cierra otros programas (los navegadores gastan mucha) o elige un tamaño más pequeño, como Q2_0 o IQ2_XS.
+- **Se detuvo durante la descarga o la instalación.** Abre de nuevo la aplicación o `strata launch`. Continúa donde se
+  quedó.
+- **Va muy lento, o dice "the engine stopped unexpectedly".** Tu PC no tiene bastante RAM libre. Cierra otros programas
+  (los navegadores gastan mucha) o elige un tamaño más pequeño, como Q2_0 o IQ2_XS.
 - **Dice que no hay motor para este PC.** En la aplicación, abre **Ajustes, Motor** y pulsa **Actualizar motor**. En la
-  Terminal, ejecuta `strata update`. `strata doctor` muestra qué archivos del motor están instalados.
+  Terminal, ejecuta `strata update`.
 - **Dice que el puerto 8080 ya está en uso.** Strata ya se está ejecutando. Busca su ventana.
 
-Más problemas y soluciones: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). ¿Sigues atascado? Abre una
-[incidencia](https://github.com/Niko1221/Strata/issues). En la aplicación, adjunta el archivo de **Ajustes, Motor,
-Diagnóstico, Ver registros, Guardar registros**. En la Terminal, pega la salida de `strata doctor`. Si lo ejecutas desde el
-código fuente, adjunta `strata-<model>.log` de la carpeta de Strata. Para un problema de seguridad, avísanos en privado:
-[SECURITY.md](SECURITY.md).
+Más soluciones: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). ¿Sigues atascado? Abre una
+[incidencia](https://github.com/Niko1221/Strata/issues) y adjunta los registros: en la aplicación desde **Ajustes, Motor,
+Diagnóstico, Guardar registros**, en la Terminal la salida de `strata doctor`. Para un problema de seguridad, avísanos en
+privado: [SECURITY.md](SECURITY.md).
 
 ## Créditos y licencia
 
 El modelo es [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next), del equipo de Qwen. Lo comprimieron
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5), agentionai (Gyro)
-y Unsloth. Strata usa partes de [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Todos los créditos:
-[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). Strata es de código abierto con la [licencia MIT](LICENSE). Algunas
-partes y todos los modelos tienen sus propias licencias ([cuáles](docs/HOW_IT_WORKS.md#license)).
+y Unsloth. ISTA-DASLab hizo también los conjuntos de DeepSeek V4.1-Flash. Strata usa partes de
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Todos los créditos: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits).
+Strata es de código abierto con la [licencia MIT](LICENSE). Algunas partes y todos los modelos tienen sus propias licencias
+([cuáles](docs/HOW_IT_WORKS.md#license)).
 
 ## Contribuir
 

README.fr.md

@@ -12,104 +12,91 @@
 <p align="center">Compatible avec NVIDIA, AMD, Intel · Windows, Linux, Mac · gratuit et open source</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Dernière version"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="Licence MIT"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="Étoiles GitHub"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="Offrez-moi un café"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Un jardin de pagode en voxels écrit par le modèle de Strata, qui tourne dans le navigateur"></a><br>
 <sub>Un jardin de pagode en voxels, généré en une seule requête sur une RTX 5070 avec Strata (IQ3_S, contexte de 128K) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">vidéo complète (49 s)</a></sub></p>
 
-Strata fait tourner **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, un modèle de 125 milliards
-de paramètres qui demande normalement un serveur, sur un PC ordinaire. Il discute, écrit du code, lit des images et
-fonctionne avec vos applications et vos agents de code. Vos conversations et vos fichiers restent sur votre PC.
+<p align="center">
+  <a href="#installation"><b>Installation</b></a> ·
+  <a href="#modèles">Modèles</a> ·
+  <a href="#quelle-est-sa-vitesse-">Vitesse</a> ·
+  <a href="#utilisation">Utilisation</a> ·
+  <a href="#comment-ça-marche-">Comment ça marche</a> ·
+  <a href="#un-problème-">Aide</a> ·
+  <a href="#soutenir-strata">Soutenir</a>
+</p>
 
-**Nouveau ici ?** Regardez [ce qu'il vous faut](#ce-quil-vous-faut), puis [installez l'application](#option-a--lapplication-strata).
+Strata fait tourner **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, un modèle de 125 milliards
+de paramètres qui demande normalement un serveur, sur un PC ordinaire. Depuis la 0.2.4, il fait aussi tourner **DeepSeek
+V4.1-Flash** dans le Terminal. Il discute, écrit du code, lit des images et fonctionne avec vos applications et vos agents
+de code. Vos conversations et vos fichiers restent sur votre PC.
 
 - **Tourne sur un PC de jeu.** 32 Go de RAM et de mémoire graphique réunis suffisent pour commencer.
-- **Fonctionne avec vos outils.** Il parle les API d'OpenAI et d'Anthropic, donc Claude Code, Codex CLI, OpenCode et d'autres agents peuvent s'y connecter.
-- **Lit les images.** C'est activé par défaut.
-- **Gratuit.** Licence MIT, pas de compte, pas de cloud.
-- **Privé.** Aucune télémétrie. Ce que Strata télécharge, quand il utilise internet et comment il vérifie les téléchargements est expliqué dans [docs/SAFETY.md](docs/SAFETY.md).
-
-Version 0.2.3 · moteur 0.1.48
+- **Fonctionne avec vos outils.** Claude Code, Codex CLI, OpenCode et d'autres agents se connectent par les API d'OpenAI et d'Anthropic.
+- **Lit les images**, activé par défaut.
+- **Gratuit et privé.** Licence MIT, pas de compte, pas de cloud, aucune télémétrie ([ce qu'il télécharge et quand](docs/SAFETY.md)).
 
 ## Ce qu'il vous faut
 
-**Il vous faut au moins 32 Go de RAM et de mémoire graphique (VRAM) réunis.** Sur un Mac ou un Ryzen AI Max, c'est la
-mémoire unifiée. Plus de mémoire permet un modèle plus gros ou plus rapide.
+**Il vous faut au moins 32 Go de mémoire : RAM et mémoire graphique (VRAM) réunis.** Sur un Mac ou un Ryzen AI Max, c'est
+la mémoire unifiée. Un PC de 32 Go avec une carte de 12 à 16 Go fait tourner les petites tailles, et 64 Go font tourner
+toutes les tailles.
 
-- Un PC de 32 Go avec une carte de 12 à 16 Go fait tourner le Coder.
-- Avec 64 Go de RAM, toutes les tailles fonctionnent.
-
-| Votre ordinateur | Détails |
+| Fonctionne sur | Guide |
 | --- | --- |
-| **NVIDIA** GeForce RTX série 20, 30, 40, 50 (12 Go ou plus) | Installez l'application ou le Terminal. |
-| **AMD** Radeon RX 6800 et plus récent, Radeon AI PRO R9700 (12 Go ou plus) | [Cartes AMD](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md), [moteur Intel](docs/INTEL.md) |
-| **Mac Apple Silicon** (M1 ou plus récent, macOS 15 ou plus récent) | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max (Strix Halo)** et autres systèmes à mémoire unifiée | [Strix Halo](docs/STRIX_HALO.md) |
-| Cartes et processeurs plus anciens | [GPU anciens](docs/OLDER_GPUS.md), [CPU anciens](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX série 20, 30, 40 et 50, 12 Go ou plus | [Installation](#installation) |
+| **AMD** Radeon RX 6800 et plus récent, Radeon AI PRO R9700 | [Cartes AMD](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Mac Apple Silicon**, M1 ou plus récent, macOS 15 ou plus récent | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max (Strix Halo)** et autres PC à mémoire unifiée | [Strix Halo](docs/STRIX_HALO.md) |
+| Cartes et processeurs plus anciens | [GPU anciens](docs/OLDER_GPUS.md) |
 
-Il faut aussi :
-
-- environ 80 Go d'espace disque libre (un SSD accélère beaucoup le premier démarrage)
-- Windows 10 / 11, Linux ou macOS
-- un pilote graphique récent
-
-Deux ou trois cartes de la même marque peuvent se partager un modèle ([multi-GPU](docs/MULTI_GPU.md)). Strata ne répartit
-jamais un modèle entre des cartes NVIDIA et AMD. Liste complète : [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
+Il vous faut aussi environ 80 Go d'espace disque libre (un SSD), Windows 10 / 11, Linux ou macOS, et un pilote graphique
+récent. Deux ou trois cartes de la même marque peuvent se partager un modèle ([multi-GPU](docs/MULTI_GPU.md)).
 
 ## Installation
 
-Choisissez une option. Elles lancent toutes le même moteur et utilisent les mêmes modèles.
+### 1. L'application Strata (le plus simple)
 
-### Option A : l'application Strata
+Téléchargez le fichier pour votre ordinateur, ouvrez-le et appuyez sur Installer pour le modèle qu'elle recommande.
 
-Le plus simple. L'application contient le moteur : installez-la, choisissez un modèle, discutez. Téléchargez le fichier
-correspondant à votre système et à votre carte graphique depuis la [page des versions](https://github.com/Niko1221/Strata/releases/latest).
-Vous ne savez pas lequel prendre ? Lisez le paragraphe sous le tableau.
+**Windows 10 / 11**
 
-| Système | Votre carte graphique | Fichier à télécharger |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX, pilote 580 ou plus récent | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA, carte plus ancienne ou pilote antérieur à 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon série RX 9000 ou Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon série RX 7000 ou Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX, pilote 580 ou plus récent | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA, carte plus ancienne ou pilote antérieur à 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon série RX 9000 ou Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon série RX 7000 | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac** (Apple Silicon, macOS 15 ou plus récent) | intégrée | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**Si vous hésitez :** pour NVIDIA, prenez `cuda13` si la version de votre pilote est 580 ou plus récente, sinon `cuda12`.
-`cuda12` convient aux cartes plus anciennes et aux pilotes plus anciens. Les fichiers `hip` et `amd` sont pour les cartes
-AMD. Les autres cartes AMD (RX 6000) n'ont pas encore d'application prête à l'emploi : voir
-[Cartes AMD](docs/AMD_HIP.md).
+**Linux**
 
-Ensuite :
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows :** lancez le `.exe`. Il s'installe pour votre utilisateur et ne demande pas de droits d'administrateur. Si
-  Windows affiche « Windows a protégé votre ordinateur », choisissez **Informations complémentaires**, puis **Exécuter
-  quand même** (l'installateur n'est pas encore signé).
-- **Linux :** rendez le fichier exécutable (`chmod +x`) et lancez-le. Il a besoin de FUSE 2 : `sudo apt install libfuse2`
-  (Ubuntu 22.04) ou `libfuse2t64` (Ubuntu 24.04 et plus récent).
-- **Mac :** ouvrez le `.dmg` et faites glisser Strata dans Applications.
+**Mac** (Apple Silicon, macOS 15 ou plus récent)
 
-Sur le premier écran, l'application analyse votre PC et recommande un modèle adapté. Appuyez sur Installer. Le modèle est un
-gros téléchargement (environ 40 à 70 Go) qui reprend là où il s'est arrêté en cas d'interruption. Quand vous fermez la
-fenêtre, Strata et le moteur s'arrêtent.
+[![Mac, Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### Option B : le Terminal (une ligne)
+L'application choisit toute seule le bon moteur pour votre carte graphique. Tous les fichiers sont sur la
+[page des versions](https://github.com/Niko1221/Strata/releases/latest).
 
-Le Terminal est la commande `strata`, pensée pour les scripts, les serveurs et les agents d'IA.
+| Premier démarrage | Ce qu'il faut faire |
+| --- | --- |
+| **Windows** | Lancez le `.exe`. Pas besoin de droits d'administrateur. Si Windows affiche « Windows a protégé votre ordinateur », choisissez **Informations complémentaires**, puis **Exécuter quand même**. |
+| **Linux** | Rendez le fichier exécutable (`chmod +x`) et lancez-le. Il a besoin de FUSE 2 : `sudo apt install libfuse2t64` (Ubuntu 24.04 et plus récent) ou `libfuse2` (22.04). |
+| **Mac** | Ouvrez le `.dmg` et faites glisser Strata dans Applications. |
+
+Le téléchargement du modèle est gros (40 à 70 Go). S'il s'arrête, il reprend là où il s'était arrêté.
+
+### 2. Le Terminal (une ligne)
+
+La commande `strata`, pour les scripts, les serveurs et les agents d'IA. C'est aussi le moyen de faire tourner DeepSeek.
 
 Linux et Mac :
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows (PowerShell) :
@@ -118,26 +105,17 @@ Windows (PowerShell) :
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-Le script analyse votre PC, télécharge le Terminal, vérifie son empreinte SHA-256 et le décompresse dans votre dossier
-personnel. Il ne demande pas de droits d'administrateur. Sous Windows, ouvrez ensuite une nouvelle fenêtre de terminal.
-Puis lancez Strata :
+Puis lancez-le. Il pose une question à la fois (modèle, contexte, images, qui peut se connecter), télécharge ce dont il a
+besoin et commence à servir :
 
 ```sh
 strata launch
 ```
 
-Il pose une question à la fois : modèle, contexte, images, qui peut se connecter. Ensuite il télécharge le moteur pour votre
-carte graphique (signé, et lancé à titre d'essai avant usage) ainsi que le modèle, puis commence à servir. Pour les scripts
-et les agents d'IA, utilisez des options :
+Pas besoin de droits d'administrateur. L'installation vérifie l'empreinte SHA-256 de tout ce qu'elle télécharge. Sous
+Windows, ouvrez une nouvelle fenêtre de terminal après l'installation. Tous les écrans et toutes les options : [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-Pour lire le script d'installation avant de l'exécuter, téléchargez-le d'abord avec `curl -fsSL <address> -o install.sh`,
-lisez-le, puis lancez `sh install.sh`. Tous les écrans et toutes les options : [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
-
-### Option C : laissez votre IA l'installer
+### 3. Laissez votre IA l'installer
 
 Collez ceci dans Claude Code, Cursor, Codex, GitHub Copilot ou un autre assistant de programmation :
 
@@ -153,48 +131,58 @@ Vous préférez le compiler vous-même ? Voir [Compiler depuis les sources](#com
 
 ## Modèles
 
-L'application et `strata launch` recommandent un modèle selon votre mémoire. C'est un seul modèle en plusieurs tailles,
-plus ou moins compressé. Les petites tailles sont plus rapides. Les grandes sont un peu plus intelligentes.
+L'application et `strata launch` recommandent une taille selon votre mémoire. Les petites tailles sont plus rapides. Les
+grandes sont un peu plus intelligentes.
 
 ### Peu de mémoire ? Essayez Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) (par agentionai) est la façon la plus légère de faire tourner ce modèle.
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) d'agentionai est la façon la plus légère de faire tourner
+Qwen3.8-Flash-Next. Il fonctionne sur NVIDIA, AMD, Intel Arc et Apple Silicon.
 
-| Taille | Mémoire nécessaire (RAM + VRAM) | Téléchargement | Ce que c'est |
+| Taille | Mémoire nécessaire (RAM + VRAM) | Téléchargement | Pour quoi |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27,6 Go | 58,5 Go | Pour les PC où rien d'autre ne tient. La qualité est inférieure à celle d'IQ2_XS. |
-| **Gyro-M** | 35 Go | 92,0 Go | À peu près la qualité d'IQ3_XXS avec environ 20 % de mémoire GPU en moins. Il écrit les réponses 16 % plus lentement que Q2_0 sur une RTX 3060 de 12 Go et 21 % plus lentement sur une R9700. |
+| **Gyro-S** | 27,6 Go | 58,5 Go | Les PC où rien d'autre ne tient. 9 tokens/s sur un Mac mini de 32 Go. |
+| **Gyro-M** | 35 Go | 92,0 Go | À peu près la qualité d'IQ3_XXS avec 20 % de mémoire GPU en moins. |
 
-Gyro fonctionne sur les cartes NVIDIA et AMD (expérimental sur AMD) sur les cartes Intel Arc sous Linux (testé sur une Arc A750) et, depuis la 0.2.2, sur les Mac Apple Silicon (Gyro-S sur un Mac mini de 32 Go : 9 tokens/s, experts lus sur le SSD). Détails et mesures :
-[docs/GYRO.md](docs/GYRO.md). Lancez-le avec `strata launch --model gyro-s`.
+Lancez-le avec `strata launch --model gyro-s`. Détails : [docs/GYRO.md](docs/GYRO.md).
 
-### Les autres tailles
+### Les tailles de Qwen3.8-Flash-Next
 
-| Votre mémoire (RAM + VRAM) | Prenez | Remarques |
+| Votre mémoire (RAM + VRAM) | Prenez | Pourquoi |
 | --- | --- | --- |
-| **32 Go** | **Gyro-S**, ou le **[Coder](docs/MODELS.md#coder)** pour le code | Le Coder demande 32 Go de RAM et garde la moitié des experts, il est donc moins bon hors du code |
-| **40 Go** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 Go), ou **Gyro-M** (35 Go) | Swift réfléchit moins longtemps avant de répondre. Gyro-M approche la qualité d'IQ3_XXS, mais il écrit les réponses 16 à 21 % plus lentement que Q2_0 |
+| **32 Go** | **Gyro-S**, ou le **[Coder](docs/MODELS.md#coder)** pour le code | Le Coder garde les experts dont le code a besoin |
+| **40 Go** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 Go) ou **Gyro-M** | Swift réfléchit moins longtemps avant de répondre |
 | **48 Go** | **IQ3_XXS** (47,0 Go) | Plus lent, meilleur |
-| **64 Go** | **IQ3_S** (54,8 Go), l'original ou Swift 1.5 | Le plus lent, le meilleur. Il égale le modèle complet dans les tests publiés |
-| **96 Go ou plus** | **UD-IQ4_XS** d'Unsloth (environ 72 Go de RAM) jusqu'à **Q8_0** (environ 136 Go), 4 à 8 bits | Plus proche du modèle complet. Avec moins de RAM, Strata lit une partie depuis le SSD, ce qui est beaucoup plus lent |
+| **64 Go** | **IQ3_S** (54,8 Go) | Égale le modèle complet dans les tests publiés |
+| **96 Go ou plus** | **UD-IQ4_XS** à **Q8_0** d'Unsloth | Au plus près du modèle complet |
 
-Avoir moins de RAM que ce qu'indique une ligne peut encore fonctionner : Strata passe tout seul en
-[mode peu de RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Attendez-vous à plus de lenteur, et à bien plus avec
-une petite carte graphique.
+Avoir moins de RAM que ce qu'indique une ligne peut encore fonctionner, en plus lent : Strata passe tout seul en
+[mode peu de RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Il existe aussi :
+[NVFP4](docs/NVFP4.md) pour les cartes NVIDIA, [Qwen3.6-35B-A3B](docs/QWEN36.md) (plus petit, plusieurs requêtes à la fois) et
+[l'Uncensored IQ3_XXS d'OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs). Toutes les tailles et ce qui tient où :
+[docs/MODELS.md](docs/MODELS.md).
 
-Autres choix :
+### DeepSeek V4.1-Flash (Terminal, depuis 0.2.4)
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** est une version affinée qui réfléchit moins longtemps avant de répondre, pour une qualité et un besoin en RAM à peu près identiques.
-- **[NVFP4](docs/NVFP4.md)** est la version 4 bits de NVIDIA pour les cartes NVIDIA. Elle demande environ 80 Go de RAM pour garder tous les experts en RAM.
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** est un modèle plus petit et différent, qui lit les images et peut répondre à plusieurs requêtes à la fois.
-- **[L'Uncensored IQ3_XXS d'OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** se configure à la main.
+Un modèle bien plus gros, qui tourne sur une seule carte graphique de 12 Go avec 46 à 64 Go de RAM. Strata garde en mémoire
+les parties les plus utilisées et lit le reste sur votre SSD. [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)
+a produit les versions. Il fonctionne sur les cartes NVIDIA RTX des séries 30, 40 et 50 et sur la Radeon AI PRO R9700. Choisissez-le
+dans `strata launch`. L'application de bureau ne le propose pas encore.
 
-Toutes les tailles, les téléchargements et ce qui tient où : [docs/MODELS.md](docs/MODELS.md).
+| Version | Téléchargement | Qualité | Écrit du code à |
+| --- | ---: | --- | --- |
+| **IQ1_M** (1,75 bit) | 239 Go | La plus petite, plus faible sur la prose simple | pas encore mesuré sur un PC |
+| **IQ2_XXS** (2.00 bits) | 257 Go | Bon équilibre | 10 tokens/s (RTX 3060), 5 (RTX 5070), 48 (4x R9700) |
+| **IQ2_XS** (2.25 bits) | 274 Go | Au plus près de l'original | 15 tokens/s (une R9700), 80 (4x R9700) |
+| **IQ4_NL** (table Engram) | compris dans chaque téléchargement ci-dessus | La table de consultation que les trois versions partagent | |
+
+Lancez-le avec `strata launch --model ist-das-2.00bpw` (ou `ist-das-1.75bpw`, `ist-das-2.25bpw`). Chiffres de qualité,
+vitesses par PC et installation manuelle : [docs/DEEPSEEK41.md](docs/DEEPSEEK41.md).
 
 ## Quelle est sa vitesse ?
 
-Mesuré avec une carte graphique de 12 Go (RTX 5070, Ryzen 5 7600, 64 Go de RAM). Voir les résultats d'autres cartes :
-[vitesse de chaque taille](docs/MODELS.md#how-fast-is-each-size), [résultats de la communauté](docs/COMMUNITY_BENCHMARKS.md).
+Mesuré avec une carte graphique de 12 Go (RTX 5070, 64 Go de RAM). Voir les résultats d'autres cartes :
+[vitesse de chaque taille](docs/MODELS.md#how-fast-is-each-size) et [résultats de la communauté](docs/COMMUNITY_BENCHMARKS.md).
 
 | Modèle | Les réponses s'affichent à | Lit votre prompt à |
 | --- | --- | --- |
@@ -204,10 +192,7 @@ Mesuré avec une carte graphique de 12 Go (RTX 5070, Ryzen 5 7600, 64 Go de RAM)
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1 620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2 180 tokens/s |
 
-Un token vaut environ ¾ de mot, donc 60 tokens par seconde, c'est plus rapide que votre lecture. « Lit votre prompt »
-indique la vitesse à laquelle Strata absorbe un long document, du code ou un historique de discussion.
-
-Mesuré avec une carte AMD de 16 Go (RX 9070 XT, Ryzen 9 3900X, 47 Go de RAM) :
+Avec une carte AMD de 16 Go (RX 9070 XT, 47 Go de RAM) :
 
 | Modèle | Les réponses s'affichent à | Lit votre prompt à |
 | --- | --- | --- |
@@ -215,84 +200,59 @@ Mesuré avec une carte AMD de 16 Go (RX 9070 XT, Ryzen 9 3900X, 47 Go de RAM) :
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1 110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1 420 tokens/s |
 
-Les barres utilisent la même échelle dans les deux tableaux. Une carte avec plus de VRAM est plus rapide. Une RTX 3090
-(24 Go) devrait écrire environ 100 à 140 tokens par seconde. La version du moteur derrière chaque chiffre est indiquée dans
-[DETAILS.md](docs/DETAILS.md#speed-measured).
+Un token vaut environ ¾ de mot, donc 60 tokens par seconde, c'est plus rapide que votre lecture. « Lit votre prompt »
+indique la vitesse à laquelle Strata absorbe un long document, du code ou un historique de discussion.
 
 ## Utilisation
 
 ### Dans l'application
 
-L'application comprend un **Chat**, un **Monitor** du modèle, de votre GPU, de votre CPU et de votre RAM, une page **Models** et les **Settings**. Le chat peut travailler dans un dossier de votre PC. En mode **Manual**, il demande
-avant de modifier un fichier ou d'exécuter une commande. Tapez `/loop 10m <what to do>` pour répéter un message toutes les
-10 minutes tant que le chat est ouvert.
+Un chat, un **Monitor** du modèle et de votre GPU, CPU et RAM, une page **Models** et les **Settings**. Le chat peut
+travailler dans un dossier de votre PC. En mode **Manual**, il demande avant de modifier un fichier ou d'exécuter une
+commande. Il peut chercher sur le web (DuckDuckGo ou Bing, sans compte). Les mots recherchés sont la seule chose qui quitte
+votre PC.
 
-Le chat peut chercher sur le web avec DuckDuckGo (ou Bing), sans compte. Vous pouvez ajouter une clé de recherche sous
-**Settings, Tools**. La recherche est la seule fonction qui envoie quelque chose hors de votre PC (les mots recherchés).
-
-Pour faire tourner deux modèles, activez **Run multiple models** (exécuter plusieurs modèles) et donnez à chacun sa propre carte de la même marque.
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Une discussion dans l'app Strata : l'agent a écrit un petit jardin de pagode en voxels dans un seul fichier HTML, et la page s'ouvre dans l'aperçu à côté de la conversation</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="L'application Strata : un chat où l'agent a construit un petit jardin de pagode en voxels, avec la page ouverte dans l'aperçu à droite"><br>
+<sub>L'agent a écrit un jardin de pagode en voxels dans un seul fichier HTML, et la page s'ouvre dans l'aperçu à côté du chat</sub></p>
 
 ### Dans le Terminal
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="La vue d'ensemble du moniteur du Terminal Strata pendant que le modèle écrit une réponse"><br>
 <sub><code>strata monitor</code> pendant que le modèle répond : vitesse, GPU, mémoire et les dernières requêtes</sub></p>
 
 ```sh
-strata launch                                  # guided screens: model, context, pictures, access, then serve
-strata launch --model q2_0 --yes --no-tui     # no questions: serve, print the address, return
-strata launch --plan --model q2_0              # show what would happen; nothing changes
-strata launch --status                         # what is being served now
-strata launch --stop                           # stop it
-strata monitor --url http://127.0.0.1:8080     # watch speed, GPU, memory and requests
-strata update --check                          # is there a new engine? (strata update installs it)
-strata doctor                                  # check the installed engine files
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` liste tout. Démarrer et servir ne téléchargent rien. Seuls l'installation, `strata launch` (quand vous
-choisissez un modèle) et `strata update` le font. Pour joindre Strata depuis votre téléphone ou un autre PC, utilisez
-`strata launch --access lan`. La commande crée une clé d'API et refuse de démarrer sur un réseau sans elle. Aucun
-navigateur ne s'ouvre, sauf si vous ajoutez `--open`. Guide : [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md). Le client complet : [docs/TERMINAL.md](docs/TERMINAL.md).
+Pour joindre Strata depuis votre téléphone ou un autre PC, utilisez `strata launch --access lan`. La commande crée une clé
+d'API pour vous. `strata --help` liste tout, et [docs/TERMINAL.md](docs/TERMINAL.md) l'explique.
 
-### Avec des agents d'IA
+### Avec des agents d'IA et d'autres applications
 
-Un agent installe Strata avec la commande en une ligne de l'option B et lance
-`strata launch --model NAME --yes --no-tui`. Les étapes, les options et les codes de sortie sont dans [docs/AI_SETUP.md](docs/AI_SETUP.md),
-et les règles du dépôt dans [AGENTS.md](AGENTS.md).
+Un agent installe Strata avec la commande en une ligne ci-dessus et lance `strata launch --model NAME --yes --no-tui`. Les
+étapes, les options et les codes de sortie sont dans [docs/AI_SETUP.md](docs/AI_SETUP.md). Les règles du dépôt pour les agents : [AGENTS.md](AGENTS.md).
 
-### Connecter vos autres applications
-
-| Type d'application | URL de base |
+| Votre application parle | URL de base |
 | --- | --- |
-| Compatible OpenAI (la plupart des applications et des agents) | `http://127.0.0.1:8080/v1` (n'importe quelle clé d'API, n'importe quel nom de modèle) |
-| API Anthropic (Claude Code et d'autres) | `http://127.0.0.1:8080`, sans `/v1`. Ces applications ajoutent `/v1/messages` elles-mêmes. Claude Code : `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| API OpenAI (la plupart des applications et des agents) | `http://127.0.0.1:8080/v1` (n'importe quelle clé d'API, n'importe quel nom de modèle) |
+| API Anthropic (Claude Code) | `http://127.0.0.1:8080`, sans `/v1`. Claude Code : `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | API OpenAI Responses (Codex CLI) | `http://127.0.0.1:8080/v1/responses` ([configuration](docs/DETAILS.md#the-responses-api-and-codex-cli)) |
 
-`strata connect` affiche les réglages exacts pour OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent et OpenClaw.
-`strata connect opencode --write` écrit le fichier après confirmation et garde une sauvegarde.
-
-### Images
-
-Les images sont activées par défaut pour les modèles qui savent les lire. Joignez ou collez une image dans le chat, ou
-envoyez-la depuis votre application. Le lecteur d'images tourne sur le processeur quand votre carte graphique a moins de
-24 Go (quelques secondes par image, sans prendre de mémoire à la carte) et sur la carte graphique à partir de 24 Go. La
-règle est la même pour NVIDIA et AMD. Vous pouvez désactiver les images par modèle, ou choisir le lecteur avec
-`--vision off`, `--vision gpu` ou `--vision cpu`.
-
-Les chiffres derrière la règle : sur une Radeon AI PRO R9700, le lecteur de la carte a pris 57 ms pour une image de
-260 tokens et celui du processeur 3,1 s. Sur des cartes de 16 Go (Tesla P100 et RTX A4000, Linux), le lecteur de la carte
-a coûté 3 à 5 % de vitesse sur le texte, parce qu'il occupe environ 1,4 Go que le modèle utiliserait sinon. Sur un Mac, le lecteur tourne sur le GPU quelle que soit la mémoire (0,45 s pour une image de 260 tokens sur un M4 de 32 Go, environ 1,2 Go de la
-mémoire partagée) ; le processeur met environ 50 s par image, il ne lit donc qu'avec `--vision cpu`.
+`strata connect` affiche les réglages exacts pour OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent et OpenClaw,
+et `strata connect opencode --write` les écrit pour vous (avec une sauvegarde).
 
 ### Bon à savoir
 
-- Choisissez le niveau de réflexion (**désactivé, faible, moyen ou élevé**) dans le menu du chat ou dans le réglage « reasoning effort » de votre application. Désactivé est le plus rapide.
-- Strata répond à une requête à la fois par défaut. Pour en traiter plusieurs en même temps, utilisez `--parallel N` dans `strata launch` ou
-  `"parallel": 2` dans la configuration ([BATCHING.md](docs/BATCHING.md)). Sur une carte de 12 Go, chaque réponse devient alors plus lente.
-- Strata lit en entier le premier message d'une discussion, soit environ 1 minute pour 30 000 tokens. Les messages suivants démarrent en quelques secondes.
-- Où sont stockées vos discussions et l'API complète : [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored), [docs/DETAILS.md](docs/DETAILS.md#using-it).
+- **Les images** sont activées pour tous les modèles qui savent les lire. Joignez ou collez une image dans le chat, ou envoyez-la depuis votre application. Détails : [docs/IMAGES.md](docs/IMAGES.md).
+- **La réflexion** peut être désactivée, faible, moyenne ou élevée, dans le menu du chat ou dans le réglage « reasoning effort » de votre application. Désactivée est le plus rapide.
+- **Le premier message** d'une discussion est lu en entier, environ 1 minute pour 30 000 tokens. Les messages suivants démarrent en quelques secondes.
+- **Une requête à la fois** par défaut. Pour en traiter plusieurs, utilisez `--parallel N` ([BATCHING.md](docs/BATCHING.md)). Sur une carte de 12 Go, chaque réponse devient alors plus lente.
 
 ## Compiler depuis les sources
 
@@ -355,13 +315,13 @@ bibliothèque.
 - **Votre SSD, ce sont les archives.** Il contient une table de consultation de 29 Go. Le modèle n'en lit que quelques lignes par
   mot, elle n'a donc pas besoin de tenir en RAM.
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="Les 24 576 experts du modèle : les plus sollicités sur la carte graphique, tous dans la RAM, une table de consultation sur le SSD"></p>
 
 Un petit assistant devine aussi les mots suivants. Le grand modèle les vérifie tous d'un coup et garde les bons. Vous
 obtenez la même réponse, 1,6 à 1,8 fois plus tôt. Les textes longs sont lus par gros morceaux, jusqu'à 8 192 tokens à la
 fois, à plus de 1 000 tokens par seconde.
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="Un petit assistant devine les mots suivants ; le grand modèle les vérifie tous d'un coup et garde les bons"></p>
 
 L'explication plus longue : [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Chaque élément avec ses chiffres :
 [les détails](docs/DETAILS.md#how-it-works) et l'[article](docs/paper/Strata-Paper.pdf).
@@ -370,25 +330,27 @@ L'explication plus longue : [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Chaque
 
 - **Mon PC s'est figé au premier démarrage de Strata.** Il charge le modèle en RAM. Patientez et ne fermez pas la fenêtre.
   Toujours figé après 10 minutes ? Redémarrez le PC, fermez les autres programmes et réessayez, ou choisissez une taille plus petite.
-- **Ça s'est arrêté pendant le téléchargement ou l'installation.** Relancez l'application ou `strata launch`, ou relancez
-  `START-HERE.bat` (ou `./setup.sh`). Cela reprend là où ça s'était arrêté.
-- **C'est très lent, le voyant du disque clignote sans arrêt, ou il affiche « the engine stopped unexpectedly ».** Votre PC
-  n'a pas assez de RAM libre. Fermez d'autres programmes (les navigateurs en consomment beaucoup) ou choisissez une taille plus petite, comme Q2_0 ou IQ2_XS.
-- **Il indique qu'il n'y a pas de moteur pour ce PC.** Dans l'application, ouvrez **Settings, Engine** et appuyez sur **Update engine** (mettre à jour le moteur). Dans le Terminal, lancez `strata update`. `strata doctor` montre quels fichiers du moteur sont installés.
+- **Ça s'est arrêté pendant le téléchargement ou l'installation.** Relancez l'application ou `strata launch`. Cela reprend là
+  où ça s'était arrêté.
+- **C'est très lent, ou il affiche « the engine stopped unexpectedly ».** Votre PC n'a pas assez de RAM libre. Fermez
+  d'autres programmes (les navigateurs en consomment beaucoup) ou choisissez une taille plus petite, comme Q2_0 ou IQ2_XS.
+- **Il indique qu'il n'y a pas de moteur pour ce PC.** Dans l'application, ouvrez **Settings, Engine** et appuyez sur **Update engine**
+  (mettre à jour le moteur). Dans le Terminal, lancez `strata update`.
 - **Il indique que le port 8080 est déjà utilisé.** Strata tourne déjà. Cherchez sa fenêtre.
 
-Autres problèmes et solutions : [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Toujours bloqué ? Ouvrez une
-[issue](https://github.com/Niko1221/Strata/issues). Dans l'application, joignez le fichier obtenu par **Settings, Engine, Diagnostics, View logs, Save logs**. Dans le Terminal, collez la sortie de `strata doctor`. Si
-vous avez lancé depuis les sources, joignez `strata-<model>.log` du dossier Strata. Pour un problème de sécurité,
-signalez-le en privé : [SECURITY.md](SECURITY.md).
+Autres solutions : [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Toujours bloqué ? Ouvrez une
+[issue](https://github.com/Niko1221/Strata/issues) et joignez les journaux : dans l'application via **Settings, Engine,
+Diagnostics, Save logs**, dans le Terminal la sortie de `strata doctor`. Pour un problème de sécurité, signalez-le en
+privé : [SECURITY.md](SECURITY.md).
 
 ## Remerciements et licence
 
 Le modèle est [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next), de l'équipe Qwen. Il a été compressé par
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5), agentionai (Gyro)
-et Unsloth. Strata utilise des parties de [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Tous les
-remerciements : [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). Strata est open source sous [licence MIT](LICENSE).
-Quelques parties et tous les modèles ont leurs propres licences ([lesquelles](docs/HOW_IT_WORKS.md#license)).
+et Unsloth. ISTA-DASLab a aussi produit les versions de DeepSeek V4.1-Flash. Strata utilise des parties de
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Tous les remerciements : [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits).
+Strata est open source sous [licence MIT](LICENSE). Quelques parties et tous les modèles ont leurs propres licences
+([lesquelles](docs/HOW_IT_WORKS.md#license)).
 
 ## Contribuer
 

README.ja.md

@@ -12,100 +12,89 @@
 <p align="center">NVIDIA、AMD、Intel に対応 · Windows、Linux、Mac · 無料のオープンソース</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="最新リリース"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT ライセンス"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub のスター"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="コーヒーをおごる"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Strata のモデルが書いたボクセルの塔の庭園。ブラウザで動いています"></a><br>
 <sub>ボクセルの塔の庭園。1回のプロンプトで生成し、RTX 5070 上の Strata で動かしています（IQ3_S、128K コンテキスト） ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">動画全体（49秒）</a></sub></p>
 
-Strata は **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)** を動かします。1250億パラメータのモデルで、
-ふつうはサーバーが必要ですが、Strata なら一般的なPCで使えます。チャット、コード作成、画像の読み取りができ、
-お使いのアプリやコーディングエージェントとも連携します。チャットとファイルはPCの外に出ません。
+<p align="center">
+  <a href="#インストール"><b>インストール</b></a> ·
+  <a href="#モデル">モデル</a> ·
+  <a href="#どのくらい速い">速度</a> ·
+  <a href="#使い方">使い方</a> ·
+  <a href="#仕組み">仕組み</a> ·
+  <a href="#うまくいかないとき">ヘルプ</a> ·
+  <a href="#strata-を応援する">応援する</a>
+</p>
 
-**はじめての方へ。** まず[必要な環境](#必要な環境)を確認して、[アプリをインストール](#方法a-strata-アプリ)してください。
+Strata は **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)** を動かします。1250億パラメータのモデルで、
+ふつうはサーバーが必要ですが、Strata なら一般的なPCで使えます。0.2.4 からは、ターミナル版で **DeepSeek V4.1-Flash** も動かせます。
+チャット、コード作成、画像の読み取りができ、お使いのアプリやコーディングエージェントとも連携します。チャットとファイルはPCの外に出ません。
 
 - **ゲーミングPCで動きます。** RAMとグラフィックスメモリの合計が32 GBあれば始められます。
-- **お使いのツールと連携します。** OpenAI と Anthropic の API に対応しているので、Claude Code、Codex CLI、OpenCode などのエージェントから接続できます。
+- **お使いのツールと連携します。** Claude Code、Codex CLI、OpenCode などのエージェントが、OpenAI と Anthropic の API で接続できます。
 - **画像を読めます。** 初期設定でオンです。
-- **無料です。** MIT ライセンス。アカウントもクラウドも不要です。
-- **プライバシーを守ります。** テレメトリはありません。Strata が何をダウンロードするか、いつインターネットを使うか、ダウンロードをどう検証するかは [docs/SAFETY.md](docs/SAFETY.md) に書いてあります。
-
-バージョン 0.2.3 · エンジン 0.1.48
+- **無料でプライバシーも守ります。** MIT ライセンス。アカウントもクラウドもテレメトリも不要です（[何をいつダウンロードするか](docs/SAFETY.md)）。
 
 ## 必要な環境
 
 **RAMとグラフィックスメモリ（VRAM）の合計が、少なくとも32 GB必要です。** MacやRyzen AI Maxでは、ユニファイドメモリがその量にあたります。
-メモリが多いほど、大きなモデルを使えたり、速く動いたりします。
+RAM 32 GBのPCに12〜16 GBのカードがあれば小さいサイズが動き、64 GBならどのサイズも動きます。
 
-- RAM 32 GBのPCに12〜16 GBのグラフィックスカードがあれば、Coder が動きます。
-- RAM 64 GBなら、どのサイズも動きます。
-
-| お使いのPC | 詳細 |
+| 動く環境 | ガイド |
 | --- | --- |
-| **NVIDIA** GeForce RTX 20、30、40、50 シリーズ（12 GB以上） | アプリまたはターミナル版をインストールしてください。 |
-| **AMD** Radeon RX 6800 以降、Radeon AI PRO R9700（12 GB以上） | [AMD のカード](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md)、[Intel エンジン](docs/INTEL.md) |
-| **Apple Silicon の Mac**（M1 以降、macOS 15 以降） | [Mac](docs/MAC.md) |
+| **NVIDIA** GeForce RTX 20、30、40、50 シリーズ、12 GB以上 | [インストール](#インストール) |
+| **AMD** Radeon RX 6800 以降、Radeon AI PRO R9700 | [AMD のカード](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Apple Silicon の Mac**、M1 以降、macOS 15 以降 | [Mac](docs/MAC.md) |
 | **AMD Ryzen AI Max（Strix Halo）** などのユニファイドメモリ搭載機 | [Strix Halo](docs/STRIX_HALO.md) |
-| 古いカードやプロセッサ | [古いGPU](docs/OLDER_GPUS.md)、[古いCPU](docs/INSTALL.md#older-cpus-experimental) |
+| 古いカードやプロセッサ | [古いGPU](docs/OLDER_GPUS.md) |
 
-そのほかに必要なもの:
-
-- 約80 GBの空きディスク容量（SSDなら初回の起動がずっと速くなります）
-- Windows 10 / 11、Linux、または macOS
-- 最新のグラフィックスドライバー
-
-同じメーカーのカードを2〜3枚使って、1つのモデルを動かせます（[マルチGPU](docs/MULTI_GPU.md)）。NVIDIA と AMD のカードにまたがってモデルを分けることはありません。
-一覧は [docs/INSTALL.md](docs/INSTALL.md#what-you-need) にあります。
+そのほかに、約80 GBの空きディスク容量（SSD）、Windows 10 / 11、Linux、または macOS、最新のグラフィックスドライバーが必要です。
+同じメーカーのカードを2〜3枚使って、1つのモデルを動かせます（[マルチGPU](docs/MULTI_GPU.md)）。
 
 ## インストール
 
-3つの方法から1つ選んでください。どれも同じエンジンを起動し、同じモデルを使います。
+### 1. Strata アプリ（いちばん簡単）
 
-### 方法A: Strata アプリ
+お使いのPCに合うファイルをダウンロードして開き、すすめられたモデルのインストールを押します。
 
-いちばん簡単な方法です。エンジンはアプリに入っているので、インストールしてモデルを選べばチャットを始められます。お使いのOSとグラフィックスカードに合うファイルを
-[リリースページ](https://github.com/Niko1221/Strata/releases/latest)からダウンロードしてください。どれか分からない場合は、表の下の説明を見てください。
+**Windows 10 / 11**
 
-| OS | グラフィックスカード | ダウンロードするファイル |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX、ドライバー 580 以降 | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA、古いカード、またはドライバーが 580 より古い場合 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon RX 9000 シリーズまたは Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon RX 7000 シリーズまたは Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX、ドライバー 580 以降 | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA、古いカード、またはドライバーが 580 より古い場合 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon RX 9000 シリーズまたは Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon RX 7000 シリーズ | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac**（Apple Silicon、macOS 15 以降） | 内蔵 | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**迷ったときは:** NVIDIA の場合、ドライバーがバージョン 580 以降なら `cuda13`、それより古ければ `cuda12` を選びます。`cuda12` は古いカードと古いドライバー向けです。
-`hip` と `amd` のファイルは AMD のカード用です。それ以外の AMD カード（RX 6000）には、まだ用意されたアプリがありません。
-[AMD のカード](docs/AMD_HIP.md)を見てください。
+**Linux**
 
-そのあとの手順:
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows:** `.exe` を実行します。ユーザー単位でインストールされ、管理者権限は不要です。「Windows によってPCが保護されました」と表示されたら、
-  **詳細情報**を選び、**実行**を選んでください（インストーラーにはまだコード署名がありません）。
-- **Linux:** ファイルを実行可能にして（`chmod +x`）起動します。FUSE 2 が必要です。`sudo apt install libfuse2`（Ubuntu 22.04）
-  または `libfuse2t64`（Ubuntu 24.04 以降）を実行してください。
-- **Mac:** `.dmg` を開き、Strata を「アプリケーション」にドラッグします。
+**Mac**（Apple Silicon、macOS 15 以降）
 
-最初の画面で、アプリがPCを調べて合うモデルをすすめます。インストールを押してください。モデルは大きく（約40〜70 GB）、中断しても続きからダウンロードできます。
-ウィンドウを閉じると、Strata とエンジンが止まります。
+[![Mac、Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### 方法B: ターミナル（1行）
+お使いのグラフィックスカードに合うエンジンは、アプリが自動で選びます。すべてのファイルは
+[リリースページ](https://github.com/Niko1221/Strata/releases/latest)にあります。
 
-ターミナル版は `strata` コマンドです。スクリプトやサーバー、AI エージェント向けです。
+| 初回の起動 | すること |
+| --- | --- |
+| **Windows** | `.exe` を実行します。管理者権限は不要です。「Windows によってPCが保護されました」と表示されたら、**詳細情報**を選び、**実行**を選んでください。 |
+| **Linux** | ファイルを実行可能にして（`chmod +x`）起動します。FUSE 2 が必要です。`sudo apt install libfuse2t64`（Ubuntu 24.04 以降）または `libfuse2`（22.04）を実行してください。 |
+| **Mac** | `.dmg` を開き、Strata を「アプリケーション」にドラッグします。 |
+
+モデルのダウンロードは大きく（40〜70 GB）、止まっても続きから再開します。
+
+### 2. ターミナル（1行）
+
+`strata` コマンドです。スクリプトやサーバー、AI エージェント向けです。DeepSeek を動かすにもこれを使います。
 
 Linux と Mac:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows（PowerShell）:
@@ -114,24 +103,17 @@ Windows（PowerShell）:
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-スクリプトはPCを調べ、ターミナル版をダウンロードし、SHA-256 を検証して、ホームフォルダに展開します。管理者権限は不要です。Windows では、終わったら
-新しいターミナルを開いてください。そのあと Strata を起動します。
+そのあと起動します。質問は1つずつ表示されます（モデル、コンテキスト、画像、接続を許可する相手）。必要なものをダウンロードして、
+サーバーを開始します。
 
 ```sh
 strata launch
 ```
 
-質問は1つずつ表示されます。モデル、コンテキスト、画像、接続を許可する相手の順です。そのあと、お使いのグラフィックスカード用のエンジン
-（署名付きで、使う前にテスト起動します）とモデルをダウンロードして、サーバーを開始します。スクリプトや AI エージェントからは、フラグを使います。
+管理者権限は不要です。インストールでは、ダウンロードしたものすべての SHA-256 を検証します。Windows では、インストール後に新しいターミナルを開いてください。
+すべての画面とフラグは [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md) にあります。
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-実行前にインストールスクリプトを読みたい場合は、先に `curl -fsSL <address> -o install.sh` でダウンロードし、内容を確認してから
-`sh install.sh` を実行してください。すべての画面とフラグは [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md) にあります。
-
-### 方法C: AI にセットアップを任せる
+### 3. AI にセットアップを任せる
 
 Claude Code、Cursor、Codex、GitHub Copilot などのコーディングアシスタントに、次の文を貼り付けます。
 
@@ -146,47 +128,55 @@ AI ツールは [MCP サーバー](docs/MCP_SERVER.md)を通じて、Strata の
 
 ## モデル
 
-アプリと `strata launch` は、メモリ量に合うモデルをすすめます。モデルは1つで、圧縮の度合いが違う複数のサイズがあります。
-小さいサイズは速く、大きいサイズは少し賢くなります。
+アプリと `strata launch` は、メモリ量に合うサイズをすすめます。小さいサイズは速く、大きいサイズは少し賢くなります。
 
 ### メモリが少ないなら Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)（agentionai 製）は、このモデルをいちばん小さく動かせる方法です。
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)（agentionai 製）は、Qwen3.8-Flash-Next をいちばん小さく動かせる方法です。
+NVIDIA、AMD、Intel Arc、Apple Silicon で動きます。
 
-| サイズ | 必要なメモリ（RAM + VRAM） | ダウンロード | 内容 |
+| サイズ | 必要なメモリ（RAM + VRAM） | ダウンロード | 向いているPC |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27.6 GB | 58.5 GB | ほかのサイズが入らないPC向け。品質は IQ2_XS より下がります。 |
-| **Gyro-M** | 35 GB | 92.0 GB | 品質は IQ3_XXS 程度で、GPUメモリの使用量は約20%少なくなります。回答の書き出しは Q2_0 より、12 GBの RTX 3060 で16%、R9700 で21%遅くなります。 |
+| **Gyro-S** | 27.6 GB | 58.5 GB | ほかのサイズが入らないPC向け。32 GB の Mac mini で毎秒 9 トークン。 |
+| **Gyro-M** | 35 GB | 92.0 GB | 品質は IQ3_XXS 程度で、GPUメモリの使用量は20%少なくなります。 |
 
-Gyro は NVIDIA と AMD のカード（AMD は実験的）、および Linux 上の Intel Arc カード（Arc A750 で確認）で動きます。0.2.2 からは Apple Silicon の Mac でも動きます（32 GB の Mac mini で Gyro-S は 9 トークン/秒、エキスパートは SSD から読み込み）。詳細と測定結果は
-[docs/GYRO.md](docs/GYRO.md) にあります。`strata launch --model gyro-s` で起動します。
+`strata launch --model gyro-s` で起動します。詳細は [docs/GYRO.md](docs/GYRO.md) にあります。
 
-### ほかのサイズ
+### Qwen3.8-Flash-Next のサイズ
 
-| メモリ（RAM + VRAM） | 選ぶモデル | 備考 |
+| メモリ（RAM + VRAM） | 選ぶモデル | 理由 |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**、またはコード向けの **[Coder](docs/MODELS.md#coder)** | Coder はRAM 32 GBが必要で、エキスパートを半分だけ保持するため、コード以外は弱くなります |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS（39.2 GB）、または **Gyro-M**（35 GB） | Swift は答える前に考える時間が短くなります。Gyro-M は品質が IQ3_XXS に近いものの、回答の書き出しは Q2_0 より16〜21%遅くなります |
+| **32 GB** | **Gyro-S**、またはコード向けの **[Coder](docs/MODELS.md#coder)** | Coder は、コードで使うエキスパートを残します |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS（39.2 GB）、または **Gyro-M** | Swift は答える前に考える時間が短くなります |
 | **48 GB** | **IQ3_XXS**（47.0 GB） | 遅くなりますが、品質は上がります |
-| **64 GB** | **IQ3_S**（54.8 GB）、オリジナルまたは Swift 1.5 | いちばん遅く、いちばん高品質です。公開されているテストでは完全版と同等です |
-| **96 GB 以上** | Unsloth の **UD-IQ4_XS**（RAM 約72 GB）から **Q8_0**（約136 GB）まで、4〜8ビット | 完全版に近づきます。RAM が足りないと、Strata は一部を SSD から読むため、ずっと遅くなります |
+| **64 GB** | **IQ3_S**（54.8 GB） | 公開されているテストでは完全版と同等です |
+| **96 GB 以上** | Unsloth の **UD-IQ4_XS** から **Q8_0** | 完全版にいちばん近いです |
 
-表の行より RAM が少なくても動くことがあります。Strata は自動で[低RAMモード](docs/MODELS.md#a-big-graphics-card-and-little-ram)に切り替わります。
-速度は落ち、グラフィックスカードが小さいとさらに大きく落ちます。
+表の行より RAM が少なくても、遅くなるだけで動くことがあります。Strata は自動で[低RAMモード](docs/MODELS.md#a-big-graphics-card-and-little-ram)に切り替わります。
+そのほかに、NVIDIA カード向けの [NVFP4](docs/NVFP4.md)、[Qwen3.6-35B-A3B](docs/QWEN36.md)（より小さく、複数のリクエストを同時に処理）、
+[OrcaRouter の Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs) があります。すべてのサイズと、どの構成で何が動くか:
+[docs/MODELS.md](docs/MODELS.md)。
 
-そのほかの選択肢:
+### DeepSeek V4.1-Flash（ターミナル版、0.2.4 から）
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** はファインチューン版で、答える前に考える時間が短くなります。品質と RAM の必要量はほぼ同じです。
-- **[NVFP4](docs/NVFP4.md)** は NVIDIA カード向けの NVIDIA 製4ビット版です。すべてのエキスパートを RAM に置くには、約80 GBの RAM が必要です。
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** は、より小さい別のモデルです。画像を読め、複数のリクエストに同時に答えられます。
-- **[OrcaRouter の Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** は手動で設定します。
+ずっと大きなモデルで、12 GB のグラフィックスカード 1 枚と 46 から 64 GB の RAM で動きます。Strata はよく使う部分をメモリに置き、
+残りは SSD から読みます。セットは [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF) が作りました。
+NVIDIA RTX 30、40、50 シリーズのカードと Radeon AI PRO R9700 で動きます。`strata launch` で選んでください。デスクトップアプリはまだ対応していません。
 
-すべてのサイズ、ダウンロード、どの構成で何が動くかは [docs/MODELS.md](docs/MODELS.md) にあります。
+| セット | ダウンロード | 品質 | コードの出力速度 |
+| --- | ---: | --- | --- |
+| **IQ1_M**（1.75 ビット） | 239 GB | いちばん小さく、ふつうの文章は弱めです | PC ではまだ測っていません |
+| **IQ2_XXS**（2.00 ビット） | 257 GB | バランスが良いです | 毎秒 10 トークン（RTX 3060）、5（RTX 5070）、48（R9700 4 枚） |
+| **IQ2_XS**（2.25 ビット） | 274 GB | 元のモデルにいちばん近いです | 毎秒 15 トークン（R9700 1 枚）、80（R9700 4 枚） |
+| **IQ4_NL**（Engram テーブル） | 上のどのダウンロードにも含まれます | 3 つのセットが共有する参照テーブルです | |
+
+`strata launch --model ist-das-2.00bpw`（または `ist-das-1.75bpw`、`ist-das-2.25bpw`）で起動します。品質の数値、PC ごとの速度、手動インストールは
+[docs/DEEPSEEK41.md](docs/DEEPSEEK41.md) にあります。
 
 ## どのくらい速い？
 
-12 GBのグラフィックスカード（RTX 5070、Ryzen 5 7600、RAM 64 GB）での数値です。ほかのカードの結果は
-[各モデルの速度](docs/MODELS.md#how-fast-is-each-size)、[コミュニティの結果](docs/COMMUNITY_BENCHMARKS.md)を見てください。
+12 GBのグラフィックスカード（RTX 5070、RAM 64 GB）での数値です。ほかのカードの結果は
+[各サイズの速度](docs/MODELS.md#how-fast-is-each-size)と[コミュニティの結果](docs/COMMUNITY_BENCHMARKS.md)を見てください。
 
 | モデル | 回答が出る速さ | プロンプトを読む速さ |
 | --- | --- | --- |
@@ -196,9 +186,7 @@ Gyro は NVIDIA と AMD のカード（AMD は実験的）、および Linux 上
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1,620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2,180 tokens/s |
 
-1トークンは英単語の約¾にあたるので、毎秒60トークンは読む速さより速くなります。「プロンプトを読む速さ」は、長い文書やコード、チャット履歴を Strata が取り込む速さです。
-
-16 GBの AMD カード（RX 9070 XT、Ryzen 9 3900X、RAM 47 GB）での測定値:
+16 GBの AMD カード（RX 9070 XT、RAM 47 GB）の場合:
 
 | モデル | 回答が出る速さ | プロンプトを読む速さ |
 | --- | --- | --- |
@@ -206,79 +194,57 @@ Gyro は NVIDIA と AMD のカード（AMD は実験的）、および Linux 上
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1,110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1,420 tokens/s |
 
-バーは2つの表で同じ目盛りです。VRAM が多いカードほど速くなり、RTX 3090（24 GB）なら毎秒100〜140トークンほどになるはずです。各数値のエンジンのバージョンは
-[DETAILS.md](docs/DETAILS.md#speed-measured) にあります。
+1トークンは英単語の約¾にあたるので、毎秒60トークンは読む速さより速くなります。「プロンプトを読む速さ」は、長い文書やコード、チャット履歴を Strata が取り込む速さです。
 
 ## 使い方
 
 ### アプリで
 
-アプリには、**チャット**、モデルとGPU・CPU・RAMの状態を見る**モニター**、**モデル**ページ、**設定**があります。チャットはPC上のフォルダで作業できます。
-**手動**モードでは、ファイルを変更したりコマンドを実行したりする前に確認します。`/loop 10m <やること>` と入力すると、チャットを開いている間、メッセージを10分ごとに繰り返し送ります。
+チャット、モデルとGPU・CPU・RAMの状態を見る**モニター**、**モデル**ページ、**設定**があります。チャットはPC上のフォルダで作業できます。
+**手動**モードでは、ファイルを変更したりコマンドを実行したりする前に確認します。ウェブ検索もできます（DuckDuckGo または Bing、アカウント不要）。
+PCの外に出るのは検索語だけです。
 
-チャットは DuckDuckGo（または Bing）でウェブ検索ができ、アカウントは不要です。**設定、ツール**で検索キーを追加することもできます。
-検索は、PCの外に何かを送る唯一の機能で、送られるのは検索語です。
-
-2つのモデルを動かすには、**複数のモデルを実行**をオンにして、それぞれのモデルに同じメーカーのカードを1枚ずつ割り当てます。
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Strata アプリでのチャット。エージェントが小さなボクセルの塔の庭を 1 つの HTML ファイルとして書き、そのページが会話の横のプレビューで開きます</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="Strata アプリ。エージェントが小さなボクセルの塔の庭を作ったチャットで、右側のプレビューにそのページが開いています"><br>
+<sub>エージェントがボクセルの塔の庭を 1 つの HTML ファイルとして書き、そのページがチャットの横のプレビューで開きます</sub></p>
 
 ### ターミナルで
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="モデルが返信を書いている間の Strata ターミナルのモニター概要"><br>
 <sub>モデルが返信を書いている間の <code>strata monitor</code>。速度、GPU、メモリ、最近のリクエストが表示されます</sub></p>
 
 ```sh
-strata launch                                  # ガイド付きの画面: モデル、コンテキスト、画像、アクセス、そして開始
-strata launch --model q2_0 --yes --no-tui     # 質問なし: 開始し、アドレスを表示して戻る
-strata launch --plan --model q2_0              # 実行内容を表示するだけで、何も変更しない
-strata launch --status                         # 今、何が動いているか
-strata launch --stop                           # 停止する
-strata monitor --url http://127.0.0.1:8080     # 速度、GPU、メモリ、リクエストを見る
-strata update --check                          # 新しいエンジンがあるか確認（strata update でインストール）
-strata doctor                                  # インストール済みのエンジンファイルを調べる
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` ですべてのコマンドを確認できます。起動とサーバーの稼働では、何もダウンロードしません。ダウンロードするのは、インストール、
-`strata launch`（モデルを選んだとき）、`strata update` だけです。スマートフォンや別のPCから Strata に接続するには、
-`strata launch --access lan` を使います。API キーが作られ、キーがない状態ではネットワーク上で起動しません。`--open` を付けない限り、ブラウザは開きません。
-ガイド: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md)。クライアント全体: [docs/TERMINAL.md](docs/TERMINAL.md)。
+スマートフォンや別のPCから Strata に接続するには、`strata launch --access lan` を使います。API キーが自動で作られます。
+`strata --help` ですべてのコマンドを確認できます。説明は [docs/TERMINAL.md](docs/TERMINAL.md) にあります。
 
-### AI エージェントと使う
+### AI エージェントやほかのアプリと使う
 
-エージェントは、方法Bの1行コマンドで Strata をインストールし、
-`strata launch --model NAME --yes --no-tui` を実行します。手順、フラグ、終了コードは [docs/AI_SETUP.md](docs/AI_SETUP.md) に、
-リポジトリのルールは [AGENTS.md](AGENTS.md) にあります。
+エージェントは、上の1行コマンドで Strata をインストールし、`strata launch --model NAME --yes --no-tui` を実行します。手順、フラグ、終了コードは
+[docs/AI_SETUP.md](docs/AI_SETUP.md) にあります。エージェント向けのリポジトリのルールは [AGENTS.md](AGENTS.md) にあります。
 
-### ほかのアプリをつなぐ
-
-| アプリの種類 | ベース URL |
+| アプリが使うもの | ベース URL |
 | --- | --- |
-| OpenAI 互換（ほとんどのアプリとエージェント） | `http://127.0.0.1:8080/v1`（API キーもモデル名も何でも可） |
-| Anthropic API（Claude Code など） | `http://127.0.0.1:8080`、`/v1` は付けません。これらのアプリは `/v1/messages` を自分で付けます。Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| OpenAI API（ほとんどのアプリとエージェント） | `http://127.0.0.1:8080/v1`（API キーもモデル名も何でも可） |
+| Anthropic API（Claude Code） | `http://127.0.0.1:8080`、`/v1` は付けません。Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | OpenAI Responses API（Codex CLI） | `http://127.0.0.1:8080/v1/responses`（[設定方法](docs/DETAILS.md#the-responses-api-and-codex-cli)） |
 
 `strata connect` は、OpenCode、Codex CLI、Claude Code、oh-my-pi、pi、Hermes Agent、OpenClaw の正確な設定を表示します。
-`strata connect opencode --write` は、確認したうえでファイルを書き込み、バックアップを残します。
-
-### 画像
-
-画像を読めるモデルでは、画像は初期設定でオンです。チャットに画像を添付または貼り付けるか、アプリから送ってください。
-グラフィックスカードが24 GB未満のときは、画像リーダーがプロセッサで動きます（画像1枚につき数秒、カードのメモリは使いません）。24 GB以上のときはグラフィックスカードで動きます。
-このルールは NVIDIA と AMD で同じです。画像はモデルごとにオフにでき、`--vision off`、`--vision gpu`、`--vision cpu` でリーダーを選べます。
-
-このルールの根拠となる数値です。Radeon AI PRO R9700 では、カードのリーダーは260トークンの画像に57 ms、プロセッサのリーダーは3.1秒かかりました。
-16 GBのカード（Tesla P100 と RTX A4000、Linux）では、カードのリーダーを使うとテキストの速度が3〜5%下がりました。
-本来モデルが使う約1.4 GBをリーダーが占めるためです。Mac ではメモリ量にかかわらず GPU が読み取ります（32 GB の M4 で260トークンの画像に0.45秒、共有メモリを約1.2 GB使います）。プロセッサでは1枚あたり約50秒かかるため、`--vision cpu` を指定したときだけ使います。
+`strata connect opencode --write` なら、設定を書き込みます（バックアップ付き）。
 
 ### 知っておくと便利なこと
 
-- 思考のレベル（**off、low、medium、high**）は、チャットのメニューか、お使いのアプリの「reasoning effort」で選びます。off がいちばん速くなります。
-- Strata は初期設定では、一度に1つのリクエストに答えます。同時に複数処理するには、`strata launch` で `--parallel N` を使うか、設定に
-  `"parallel": 2` を書きます（[BATCHING.md](docs/BATCHING.md)）。12 GBのカードでは、1つずつの回答が遅くなります。
-- Strata はチャットの最初のメッセージを全文読みます。30,000トークンあたり約1分かかります。続きのメッセージは数秒で始まります。
-- チャットの保存場所と API 全体: [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored)、[docs/DETAILS.md](docs/DETAILS.md#using-it)。
+- **画像**は、画像を読めるモデルすべてでオンです。チャットに画像を添付または貼り付けるか、アプリから送ってください。詳細: [docs/IMAGES.md](docs/IMAGES.md)。
+- **思考のレベル**は off、low、medium、high から、チャットのメニューか、お使いのアプリの「reasoning effort」で選びます。off がいちばん速くなります。
+- **チャットの最初のメッセージ**は全文読みます。30,000トークンあたり約1分かかります。続きのメッセージは数秒で始まります。
+- **一度に1つのリクエスト**が初期設定です。複数にするには `--parallel N` を使います（[BATCHING.md](docs/BATCHING.md)）。12 GBのカードでは、1つずつの回答が遅くなります。
 
 ## ソースからビルド
 
@@ -335,12 +301,12 @@ Strata のデータフォルダにある `strata-<model>.json`（[場所](docs/I
 - **RAM は閲覧室の書棚です。** 24,576冊すべてがここにあります。単語に必要な本が机になければ、プロセッサがすぐに書棚から読み、その間もカードは作業を続けます。
 - **SSD は書庫です。** 29 GBの参照テーブルがしまってあります。モデルは単語ごとにその数行だけを読むので、RAM に置いておく必要はありません。
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="モデルの24,576人のエキスパート。よく使うものはグラフィックスカードに、全員が RAM に、参照テーブルは SSD にあります"></p>
 
 小さな助手が、次の数単語も予想します。大きなモデルがそれをまとめて確認し、正しいものだけを残します。答えは同じで、1.6〜1.8倍早く返ります。
 長い文章は、一度に最大8,192トークンの大きな塊で、毎秒1,000トークンを超える速さで読みます。
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="小さな助手が次の単語を予想し、大きなモデルがそれをまとめて確認して、正しいものだけを残します"></p>
 
 詳しい説明は [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md) にあります。各部分と数値は
 [詳細](docs/DETAILS.md#how-it-works)と[論文](docs/paper/Strata-Paper.pdf)を見てください。
@@ -349,24 +315,23 @@ Strata のデータフォルダにある `strata-<model>.json`（[場所](docs/I
 
 - **Strata を初めて起動したときに、PCが固まりました。** モデルを RAM に読み込んでいます。ウィンドウを閉じずに待ってください。10分たっても固まったままなら、
   PCを再起動し、ほかのプログラムを閉じてからもう一度試すか、小さいサイズを選んでください。
-- **ダウンロードやインストールの途中で止まりました。** アプリか `strata launch` をもう一度起動するか、`START-HERE.bat`（または
-  `./setup.sh`）をもう一度実行してください。止まったところから再開します。
-- **とても遅い、ディスクのランプが点滅し続ける、または「エンジンが予期せず停止しました」と表示される。** PCの空き RAM が足りません。
+- **ダウンロードやインストールの途中で止まりました。** アプリか `strata launch` をもう一度起動してください。止まったところから再開します。
+- **とても遅い、または「the engine stopped unexpectedly」と表示される。** PCの空き RAM が足りません。
   ほかのプログラムを閉じるか（ブラウザはメモリを多く使います）、Q2_0 や IQ2_XS のような小さいサイズを選んでください。
 - **このPCに合うエンジンがないと表示される。** アプリでは、**設定、エンジン**を開いて**エンジンを更新**を押します。ターミナルでは
-  `strata update` を実行します。`strata doctor` で、どのエンジンファイルがインストールされているか分かります。
+  `strata update` を実行します。
 - **ポート 8080 はすでに使われていると表示される。** Strata がすでに動いています。ウィンドウを探してください。
 
-そのほかの問題と対処法は [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) にあります。それでも解決しない場合は、
-[issue](https://github.com/Niko1221/Strata/issues) を作成してください。アプリでは、**設定、エンジン、診断、ログを見る、ログを保存**で作られるファイルを添付します。
-ターミナルでは、`strata doctor` の出力を貼り付けます。ソースから動かしている場合は、Strata フォルダの `strata-<model>.log` を添付してください。
-セキュリティ上の問題は、非公開で報告してください: [SECURITY.md](SECURITY.md)。
+そのほかの対処法は [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md) にあります。それでも解決しない場合は、
+[issue](https://github.com/Niko1221/Strata/issues) を作成して、ログを添付してください。アプリでは**設定、エンジン、診断、ログを保存**、
+ターミナルでは `strata doctor` の出力です。セキュリティ上の問題は、非公開で報告してください: [SECURITY.md](SECURITY.md)。
 
 ## クレジットとライセンス
 
 モデルは Qwen チームの [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) です。圧縮は
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF)、UkisAI（Swift 1.5）、agentionai（Gyro）、
-Unsloth が行いました。Strata は [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp) の一部を使っています。すべてのクレジットは
+Unsloth が行いました。DeepSeek V4.1-Flash のセットも ISTA-DASLab が作りました。Strata は
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp) の一部を使っています。すべてのクレジットは
 [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits) にあります。Strata は [MIT ライセンス](LICENSE)のオープンソースです。一部のコンポーネントと
 すべてのモデルには、それぞれのライセンスがあります（[該当するもの](docs/HOW_IT_WORKS.md#license)）。
 

README.md

@@ -12,102 +12,88 @@
 <p align="center">Support for NVIDIA, AMD, Intel · Windows, Linux, Mac · free and open source</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
   <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
   <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="Buy me a coffee"></a>
 </p>
 
 <p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
 <sub>A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata (IQ3_S, 128K context) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">full video (49 s)</a></sub></p>
 
-Strata runs **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, a 125-billion-parameter model that
-normally needs a server, on a normal PC. It chats, writes code, reads pictures and works with your apps and coding
-agents. Your chats and files stay on your PC.
+<p align="center">
+  <a href="#install"><b>Install</b></a> ·
+  <a href="#models">Models</a> ·
+  <a href="#how-fast-is-it">Speed</a> ·
+  <a href="#using-it">Using it</a> ·
+  <a href="#how-does-it-work">How it works</a> ·
+  <a href="#something-went-wrong">Help</a> ·
+  <a href="#support-strata">Support</a>
+</p>
 
-**New here?** Check [what you need](#what-you-need), then [install the app](#option-a-the-strata-app).
+Strata runs **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, a 125-billion-parameter model that
+normally needs a server, on a normal PC. From 0.2.4 it also runs **DeepSeek V4.1-Flash** in the Terminal. It chats, writes
+code, reads pictures and works with your apps and coding agents. Your chats and files stay on your PC.
 
 - **Runs on a gaming PC.** 32 GB of RAM and graphics memory together is enough to start.
-- **Works with your tools.** It speaks the OpenAI and Anthropic APIs, so Claude Code, Codex CLI, OpenCode and other agents connect to it.
-- **Reads pictures.** They are on by default.
-- **Free.** MIT license, no account, no cloud.
-- **Private.** No telemetry. What Strata downloads, when it uses the internet and how it checks downloads is in [docs/SAFETY.md](docs/SAFETY.md).
-
-Version 0.2.3 · engine 0.1.48
+- **Works with your tools.** Claude Code, Codex CLI, OpenCode and other agents connect through the OpenAI and Anthropic APIs.
+- **Reads pictures**, on by default.
+- **Free and private.** MIT license, no account, no cloud, no telemetry ([what it downloads and when](docs/SAFETY.md)).
 
 ## What you need
 
-**You need at least 32 GB of RAM and graphics memory (VRAM) together.** On a Mac or a Ryzen AI Max, that is the unified
-memory. More memory gives a bigger model or a faster one.
+**At least 32 GB of memory: RAM and graphics memory (VRAM) together.** On a Mac or a Ryzen AI Max that is the unified
+memory. A 32 GB PC with a 12-16 GB card runs the smaller sizes, and 64 GB runs every size.
 
-- A 32 GB PC with a 12-16 GB card runs the Coder.
-- 64 GB of RAM runs every size.
-
-| Your computer | Details |
+| Works on | Guide |
 | --- | --- |
-| **NVIDIA** GeForce RTX 20, 30, 40, 50 series (12 GB or more) | Install the app or the Terminal. |
-| **AMD** Radeon RX 6800 and newer, Radeon AI PRO R9700 (12 GB or more) | [AMD cards](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md), [Intel engine](docs/INTEL.md) |
-| **Apple Silicon Mac** (M1 or newer, macOS 15 or newer) | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max (Strix Halo)** and other unified-memory systems | [Strix Halo](docs/STRIX_HALO.md) |
-| Older cards and processors | [Older GPUs](docs/OLDER_GPUS.md), [Older CPUs](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX 20, 30, 40 and 50 series, 12 GB or more | [Install](#install) |
+| **AMD** Radeon RX 6800 and newer, Radeon AI PRO R9700 | [AMD cards](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Apple Silicon Mac**, M1 or newer, macOS 15 or newer | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max (Strix Halo)** and other unified-memory PCs | [Strix Halo](docs/STRIX_HALO.md) |
+| Older cards and processors | [Older GPUs](docs/OLDER_GPUS.md) |
 
-Also needed:
-
-- about 80 GB of free disk (an SSD makes the first start much faster)
-- Windows 10 / 11, Linux or macOS
-- a current graphics driver
-
-Two or three cards of the same make can share a model ([multi-GPU](docs/MULTI_GPU.md)). Strata never splits a model across
-NVIDIA and AMD cards. Full list: [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
+You also need about 80 GB of free disk (an SSD), Windows 10 / 11, Linux or macOS, and a current graphics driver. Two or
+three cards of the same make can share a model ([multi-GPU](docs/MULTI_GPU.md)).
 
 ## Install
 
-Pick one option. They all start the same engine and use the same models.
+### 1. The Strata app (easiest)
 
-### Option A: the Strata app
+Download the file for your computer, open it, and press install on the model it recommends.
 
-The easiest way. The app has the engine inside: install it, pick a model, chat. Download the file for your system and
-graphics card from the [releases page](https://github.com/Niko1221/Strata/releases/latest). Not sure which one? See the
-line under the table.
+**Windows 10 / 11**
 
-| System | Your graphics card | File to download |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX, driver 580 or newer | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA, older card or driver older than 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon RX 9000 series or Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon RX 7000 series or Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX, driver 580 or newer | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA, older card or driver older than 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon RX 9000 series or Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon RX 7000 series | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac** (Apple Silicon, macOS 15 or newer) | built in | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**If you are unsure:** for NVIDIA, take `cuda13` if your driver is version 580 or newer, otherwise `cuda12`. `cuda12` is
-for older cards and older drivers. The `hip` and `amd` files are for AMD cards. RX 6000 cards have no installer of
-their own: install `hip-rdna3` (Windows) or `amd-rx7900` (Linux), and on a PC with an RX 6000 card it fetches the RX 6000 engine by itself
-(also `strata update`). That engine is built but not yet tested on a real RX 6000 card: see [AMD cards](docs/AMD_HIP.md).
+**Linux**
 
-Then:
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows:** run the `.exe`. It installs for your user and needs no administrator rights. If Windows says "Windows
-  protected your PC", choose **More info**, then **Run anyway** (the installer is not code-signed yet).
-- **Linux:** make the file runnable (`chmod +x`) and start it. It needs FUSE 2: `sudo apt install libfuse2` (Ubuntu 22.04)
-  or `libfuse2t64` (Ubuntu 24.04 and newer).
-- **Mac:** open the `.dmg` and drag Strata onto Applications.
+**Mac** (Apple Silicon, macOS 15 or newer)
 
-On the first screen the app reads your PC and recommends a model that fits. Press install. The model is a big download
-(about 40-70 GB) and continues where it stopped if it is interrupted. Closing the window stops Strata and the engine.
+[![Mac, Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### Option B: the Terminal (one line)
+The app picks the right engine for your graphics card by itself. All files are on the [releases page](https://github.com/Niko1221/Strata/releases/latest).
 
-The Terminal is the `strata` command, for scripts, servers and AI agents.
+| First start | What to do |
+| --- | --- |
+| **Windows** | Run the `.exe`. No administrator rights needed. If Windows says "Windows protected your PC", choose **More info**, then **Run anyway**. |
+| **Linux** | `chmod +x` the file and start it. It needs FUSE 2: `sudo apt install libfuse2t64` (Ubuntu 24.04 and newer) or `libfuse2` (22.04). |
+| **Mac** | Open the `.dmg` and drag Strata onto Applications. |
+
+The model download is big (40-70 GB). If it stops, it continues where it left off.
+
+### 2. The Terminal (one line)
+
+The `strata` command, for scripts, servers and AI agents. It is also the way to run DeepSeek.
 
 Linux and Mac:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows (PowerShell):
@@ -116,24 +102,17 @@ Windows (PowerShell):
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-The script checks your PC, downloads the Terminal, verifies its SHA-256 and unpacks it into your home folder. It needs no
-administrator rights. On Windows, open a new terminal window afterwards. Then start Strata:
+Then start it. It asks one question at a time (model, context, pictures, who may connect), downloads what it needs and
+starts serving:
 
 ```sh
 strata launch
 ```
 
-It asks one question at a time: model, context, pictures, who may connect. Then it downloads the engine for your graphics
-card (signed, and test-started before use) and the model, and starts serving. For scripts and AI agents, use flags:
+No admin rights needed. The install checks the SHA-256 of everything it downloads. On Windows, open a new terminal window
+after the install. All screens and flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-To read the install script before it runs, download it first with `curl -fsSL <address> -o install.sh`, read it, then run
-`sh install.sh`. All screens and flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
-
-### Option C: let your AI set it up
+### 3. Let your AI set it up
 
 Paste this into Claude Code, Cursor, Codex, GitHub Copilot or another coding assistant:
 
@@ -141,57 +120,64 @@ Paste this into Claude Code, Cursor, Codex, GitHub Copilot or another coding ass
 Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow docs/AI_SETUP.md in that repository.
 ```
 
-It checks your graphics card, RAM and disk, picks the model that fits, installs and starts it, and tells you how to
-connect your apps. AI tools can also install, start and stop Strata through its [MCP server](docs/MCP_SERVER.md).
+It checks your graphics card, RAM and disk, picks the model that fits, installs it, starts it and tells you how to connect
+your apps. AI tools can also install, start and stop Strata through its [MCP server](docs/MCP_SERVER.md).
 
 Prefer to build it yourself? See [Build from source](#build-from-source).
 
 ## Models
 
-The app and `strata launch` recommend a model for your memory. It is one model in several sizes, compressed more or less.
-Smaller sizes are faster. Larger sizes are a bit smarter.
+The app and `strata launch` recommend a size for your memory. Smaller sizes are faster, larger sizes are a bit smarter.
 
-### Low on memory? Try Gyro
+### Low on memory? Start with Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) (by agentionai) is the smallest way to run this model.
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) by agentionai is the smallest way to run
+Qwen3.8-Flash-Next. It runs on NVIDIA, AMD, Intel Arc and Apple Silicon.
 
-| Size | Memory it needs (RAM + VRAM) | Download | What it is |
+| Size | Memory it needs (RAM + VRAM) | Download | Good for |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27.6 GB | 58.5 GB | For PCs that fit nothing else. Quality is lower than IQ2_XS. |
-| **Gyro-M** | 35 GB | 92.0 GB | About IQ3_XXS quality with about 20% less GPU memory. It writes answers 16% (12 GB RTX 3060) to 21% (R9700) slower than Q2_0. |
+| **Gyro-S** | 27.6 GB | 58.5 GB | PCs that fit nothing else. 9 tokens/s on a 32 GB Mac mini. |
+| **Gyro-M** | 35 GB | 92.0 GB | About IQ3_XXS quality with 20% less GPU memory. |
 
-Gyro runs on NVIDIA and AMD cards (AMD is experimental) on Intel Arc cards on Linux (tested on an Arc A750) and, from 0.2.2, on Apple Silicon Macs (Gyro-S on a 32 GB Mac mini: 9 tok/s, streaming from the SSD; [docs/MAC.md](docs/MAC.md#gyro-s-and-gyro-m-agentionais-trellis-experts)). Details and measurements:
-[docs/GYRO.md](docs/GYRO.md). Start it with `strata launch --model gyro-s`.
+Start it with `strata launch --model gyro-s`. Details: [docs/GYRO.md](docs/GYRO.md).
 
-### The other sizes
+### Qwen3.8-Flash-Next sizes
 
-The tiers count your RAM plus your VRAM, less 5 GB that Windows and the system keep for themselves. Every other size stays a choice.
-
-| Your memory (RAM + VRAM) | Take | Notes |
+| Your memory (RAM + VRAM) | Take | Why |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**, or the **[Coder](docs/MODELS.md#coder)** for code | The Coder needs 32 GB of RAM and keeps half of the experts, so it is weaker outside code |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39.2 GB), or **Gyro-M** (35 GB) | Swift thinks for a shorter time before it answers. Gyro-M is close to IQ3_XXS in quality, but it writes answers 16-21% slower than Q2_0 |
+| **32 GB** | **Gyro-S**, or the **[Coder](docs/MODELS.md#coder)** for code | The Coder keeps the experts that code uses |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39.2 GB) or **Gyro-M** | Swift thinks for a shorter time before it answers |
 | **48 GB** | **IQ3_XXS** (47.0 GB) | Slower, better |
-| **64 GB** | **IQ3_S** (54.8 GB), the original or Swift 1.5 | The slowest, the best: it matches the full model on the published tests |
-| **96 GB or more** | Unsloth's **UD-IQ4_XS** (about 72 GB of RAM) to **Q8_0** (about 136 GB), 4 to 8 bit | Closer to the full model. With less RAM, Strata reads part of them from the SSD, which is much slower |
+| **64 GB** | **IQ3_S** (54.8 GB) | Matches the full model on the published tests |
+| **96 GB or more** | Unsloth's **UD-IQ4_XS** to **Q8_0** | Closest to the full model |
 
-Less RAM than a row says can still work: Strata switches to its
-[low-RAM mode](docs/MODELS.md#a-big-graphics-card-and-little-ram) by itself. Expect it to be slower, and much slower
-with a small graphics card.
+Less RAM than a row says can still work, only slower: Strata switches to its
+[low-RAM mode](docs/MODELS.md#a-big-graphics-card-and-little-ram) by itself. Also available:
+[NVFP4](docs/NVFP4.md) for NVIDIA cards, [Qwen3.6-35B-A3B](docs/QWEN36.md) (smaller, several requests at once) and
+[OrcaRouter's Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs). Every size and what fits where:
+[docs/MODELS.md](docs/MODELS.md).
 
-More choices:
+### DeepSeek V4.1-Flash (Terminal, from 0.2.4)
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** is a fine-tune that thinks for a shorter time before it answers, at about the same quality and RAM.
-- **[NVFP4](docs/NVFP4.md)** is NVIDIA's 4-bit version for NVIDIA cards. It needs about 80 GB of RAM to keep every expert in RAM.
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** is a smaller, different model that reads pictures and can answer several requests at once.
-- **[OrcaRouter's Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** is set up by hand.
+A much bigger model that runs on one 12 GB graphics card with 46 to 64 GB of RAM. Strata keeps the busiest parts in memory and
+reads the rest from your SSD. [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)
+made the sets. It runs on NVIDIA RTX 30, 40 and 50 cards and the Radeon AI PRO R9700. Pick it in `strata launch`; the desktop
+app does not offer it yet.
 
-Every size, download and what fits where: [docs/MODELS.md](docs/MODELS.md).
+| Set | Download | Quality | Writes code at |
+| --- | ---: | --- | --- |
+| **IQ1_M** (1.75 bits) | 239 GB | The smallest; weaker on plain prose | not measured on a PC yet |
+| **IQ2_XXS** (2.00 bits) | 257 GB | Good balance | 10 tokens/s (RTX 3060), 5 (RTX 5070), 48 (4x R9700) |
+| **IQ2_XS** (2.25 bits) | 274 GB | Closest to the original | 15 tokens/s (one R9700), 80 (4x R9700) |
+| **IQ4_NL** (Engram table) | in every download above | The lookup table all three sets share | |
+
+Start it with `strata launch --model ist-das-2.00bpw` (or `ist-das-1.75bpw`, `ist-das-2.25bpw`). Quality numbers, speeds
+per PC and the manual install: [docs/DEEPSEEK41.md](docs/DEEPSEEK41.md).
 
 ## How fast is it?
 
-Based on a 12 GB graphics card (RTX 5070, Ryzen 5 7600, 64 GB RAM). See results from other cards:
-[speed of each model](docs/MODELS.md#how-fast-is-each-size), [community results](docs/COMMUNITY_BENCHMARKS.md).
+Based on a 12 GB graphics card (RTX 5070, 64 GB RAM). Results from other cards:
+[speed of each model](docs/MODELS.md#how-fast-is-each-size) and [community results](docs/COMMUNITY_BENCHMARKS.md).
 
 | Model | Answers appear at | Reads your prompt at |
 | --- | --- | --- |
@@ -201,10 +187,7 @@ Based on a 12 GB graphics card (RTX 5070, Ryzen 5 7600, 64 GB RAM). See results
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1,620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2,180 tokens/s |
 
-A token is about ¾ of a word, so 60 tokens per second is faster than you can read. "Reads your prompt" is how fast Strata
-takes in a long document, code or chat history.
-
-Measured on a 16 GB AMD card (RX 9070 XT, Ryzen 9 3900X, 47 GB RAM):
+On a 16 GB AMD card (RX 9070 XT, 47 GB RAM):
 
 | Model | Answers appear at | Reads your prompt at |
 | --- | --- | --- |
@@ -212,24 +195,19 @@ Measured on a 16 GB AMD card (RX 9070 XT, Ryzen 9 3900X, 47 GB RAM):
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1,110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1,420 tokens/s |
 
-The bars use one scale for both tables. A card with more VRAM is faster: an RTX 3090 (24 GB) should write about 100-140
-tokens per second. The engine version behind each number is in [DETAILS.md](docs/DETAILS.md#speed-measured).
+A token is about ¾ of a word, so 60 tokens per second is faster than you can read. "Reads your prompt" is how fast Strata
+takes in a long document, code or chat history.
 
 ## Using it
 
 ### In the app
 
-The app has a **Chat**, a **Monitor** of the model and your GPU, CPU and RAM, a **Models** page and **Settings**. The chat
-can work in a folder on your PC. In **Manual** mode it asks before it changes a file or runs a command. Type
-`/loop 10m <what to do>` to repeat a message every 10 minutes while the chat is open.
-
-The chat can search the web with DuckDuckGo (or Bing), with no account. You can add a search key under **Settings, Tools**.
-Search is the one feature that sends something off your PC, the search words.
-
-To run two models, turn on **Run multiple models** and give each model its own card of the same make.
+Chat, a **Monitor** of the model and your GPU, CPU and RAM, a **Models** page and **Settings**. The chat can work in a
+folder on your PC. In **Manual** mode it asks before it changes a file or runs a command. It can search the web
+(DuckDuckGo or Bing, no account); the search words are the one thing that leaves your PC.
 
 <p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>A chat in the Strata app: the agent wrote a small voxel pagoda garden as one HTML file, and the page opens in the preview next to the conversation</sub></p>
+<sub>The agent wrote a voxel pagoda garden as one HTML file, and the page opens in the preview next to the chat</sub></p>
 
 ### In the Terminal
 
@@ -237,57 +215,38 @@ To run two models, turn on **Run multiple models** and give each model its own c
 <sub><code>strata monitor</code> while the model writes a reply: speed, GPU, memory and the recent requests</sub></p>
 
 ```sh
-strata launch                                  # guided screens: model, context, pictures, access, then serve
-strata launch --model q2_0 --yes --no-tui     # no questions: serve, print the address, return
-strata launch --plan --model q2_0              # show what would happen; nothing changes
-strata launch --status                         # what is being served now
-strata launch --stop                           # stop it
-strata monitor --url http://127.0.0.1:8080     # watch speed, GPU, memory and requests
-strata update --check                          # is there a new engine? (strata update installs it)
-strata doctor                                  # check the installed engine files
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` lists everything. Starting and serving never download anything. Only the install, `strata launch` (when
-you choose a model) and `strata update` do. To reach Strata from your phone or another PC, use
-`strata launch --access lan`. It makes an API key (recommended; add `--no-api-key` to go without, with a warning). No browser opens unless
-you add `--open`. Guide: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md). Whole client: [docs/TERMINAL.md](docs/TERMINAL.md).
+To reach Strata from your phone or another PC, use `strata launch --access lan`. It makes an API key for you.
+`strata --help` lists everything, and [docs/TERMINAL.md](docs/TERMINAL.md) explains it.
 
-### With AI agents
+### With AI agents and other apps
 
-An agent installs Strata with the one-line command in Option B and runs
-`strata launch --model NAME --yes --no-tui`. The steps, flags and exit codes are in [docs/AI_SETUP.md](docs/AI_SETUP.md),
-and the repository rules are in [AGENTS.md](AGENTS.md).
+An agent installs Strata with the one-line command above and runs `strata launch --model NAME --yes --no-tui`. Steps,
+flags and exit codes: [docs/AI_SETUP.md](docs/AI_SETUP.md). Repository rules for agents: [AGENTS.md](AGENTS.md).
 
-### Connect your other apps
-
-| App type | Base URL |
+| Your app speaks | Base URL |
 | --- | --- |
-| OpenAI-compatible (most apps and agents) | `http://127.0.0.1:8080/v1` (any API key, any model name) |
-| Anthropic API (Claude Code and others) | `http://127.0.0.1:8080`, without `/v1`. These apps add `/v1/messages` themselves. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| OpenAI API (most apps and agents) | `http://127.0.0.1:8080/v1` (any API key, any model name) |
+| Anthropic API (Claude Code) | `http://127.0.0.1:8080`, without `/v1`. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | OpenAI Responses API (Codex CLI) | `http://127.0.0.1:8080/v1/responses` ([setup](docs/DETAILS.md#the-responses-api-and-codex-cli)) |
 
-`strata connect` prints the exact settings for OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent and OpenClaw.
-`strata connect opencode --write` writes the file after asking and keeps a backup.
-
-### Pictures
-
-Pictures are on by default for models that can read them. Attach or paste a picture in the chat, or send it from your app.
-The picture reader runs on the processor when your graphics card has less than 24 GB (a few seconds per picture, nothing
-taken from the card's memory) and on the graphics card from 24 GB. The rule is the same for NVIDIA and AMD. Turn pictures
-off per model, or choose the reader with `--vision off`, `--vision gpu` or `--vision cpu`.
-
-The numbers behind the rule: on a Radeon AI PRO R9700 the card's reader took 57 ms for a 260-token picture and the
-processor's took 3.1 s. On 16 GB cards (Tesla P100 and RTX A4000, Linux) the card's reader cost 3-5% of text speed,
-because it holds about 1.4 GB that the model would use otherwise. On a Mac the reader runs on the Mac's GPU whatever its memory (0.45 s for a 260-token picture on an M4 with 32 GB, about 1.2 GB of the shared
-memory); the processor reader needs about 50 s per picture there, so it runs only when you ask for it with `--vision cpu`.
+`strata connect` prints the exact settings for OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent and OpenClaw,
+and `strata connect opencode --write` writes them for you (with a backup).
 
 ### Good to know
 
-- Choose the thinking level (**off, low, medium or high**) in the chat menu or in your app's "reasoning effort". Off is fastest.
-- Strata answers one request at a time by default. For several at once, use `--parallel N` in `strata launch` or
-  `"parallel": 2` in the config ([BATCHING.md](docs/BATCHING.md)). On a 12 GB card this makes each answer slower.
-- Strata reads the first message of a chat in full, about 1 minute per 30,000 tokens. Follow-up messages start in seconds.
-- Where your chats are stored and the whole API: [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored), [docs/DETAILS.md](docs/DETAILS.md#using-it).
+- **Pictures** are on for every model that can read them. Attach or paste one in the chat, or send it from your app. Details: [docs/IMAGES.md](docs/IMAGES.md).
+- **Thinking** can be off, low, medium or high, in the chat menu or your app's "reasoning effort". Off is fastest.
+- **The first message** of a chat is read in full, about 1 minute per 30,000 tokens. Follow-ups start in seconds.
+- **One request at a time** by default. For more, use `--parallel N` ([BATCHING.md](docs/BATCHING.md)). On a 12 GB card each answer gets slower.
 
 ## Build from source
 
@@ -363,26 +322,25 @@ The longer explanation: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Every part
 
 - **My PC froze the first time Strata started.** It loads the model into RAM. Wait, and don't close the window. Still
   frozen after 10 minutes? Restart the PC, close other programs and try again, or pick a smaller size.
-- **It stopped while downloading or installing.** Start the app or `strata launch` again, or run `START-HERE.bat` (or
-  `./setup.sh`) again. It continues where it stopped.
-- **It is very slow, the disk light keeps blinking, or it says "the engine stopped unexpectedly".** Your PC does not have
-  enough free RAM. Close other programs (browsers use a lot), or pick a smaller size such as Q2_0 or IQ2_XS.
+- **It stopped while downloading or installing.** Start the app or `strata launch` again. It continues where it stopped.
+- **It is very slow, or it says "the engine stopped unexpectedly".** Your PC is short on free RAM. Close other programs
+  (browsers use a lot), or pick a smaller size such as Q2_0 or IQ2_XS.
 - **It says there is no engine for this PC.** In the app, open **Settings, Engine** and press **Update engine**. In the
-  Terminal, run `strata update`. `strata doctor` shows which engine files are installed.
+  Terminal, run `strata update`.
 - **It says port 8080 is already in use.** Strata is already running. Look for its window.
 
-More problems and fixes: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Still stuck? Open an
-[issue](https://github.com/Niko1221/Strata/issues). In the app, attach the file from **Settings, Engine, Diagnostics, View
-logs, Save logs**. In the Terminal, paste the output of `strata doctor`. From source, attach `strata-<model>.log` from the
-Strata folder. For a security problem, report it privately: [SECURITY.md](SECURITY.md).
+More fixes: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Still stuck? Open an
+[issue](https://github.com/Niko1221/Strata/issues) and attach the logs: in the app from **Settings, Engine, Diagnostics,
+Save logs**, in the Terminal the output of `strata doctor`. For a security problem, report it privately: [SECURITY.md](SECURITY.md).
 
 ## Credits and license
 
 The model is [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) by the Qwen team. It was compressed by
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5), agentionai (Gyro)
-and Unsloth. Strata uses parts of [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). All credits:
-[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). Strata is open source under the [MIT License](LICENSE). A few parts and
-every model have their own licenses ([which ones](docs/HOW_IT_WORKS.md#license)).
+and Unsloth. ISTA-DASLab also made the DeepSeek V4.1-Flash sets. Strata uses parts of
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). All credits: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits).
+Strata is open source under the [MIT License](LICENSE). A few parts and every model have their own licenses
+([which ones](docs/HOW_IT_WORKS.md#license)).
 
 ## Contributing
 

README.pt-BR.md

@@ -12,100 +12,90 @@
 <p align="center">Suporte a NVIDIA, AMD, Intel · Windows, Linux, Mac · gratuito e de código aberto</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Última versão"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="Licença MIT"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="Estrelas no GitHub"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="Me pague um café"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Um jardim de pagodes em voxels que o modelo do Strata escreveu, rodando no navegador"></a><br>
 <sub>Um jardim de pagodes em voxels, gerado com um único prompt, rodando numa RTX 5070 com o Strata (IQ3_S, contexto de 128K) ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">vídeo completo (49 s)</a></sub></p>
 
-O Strata roda o **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, um modelo de 125 bilhões de parâmetros que
-normalmente precisa de um servidor, num PC comum. Ele conversa, escreve código, lê imagens e funciona com os seus aplicativos e
-agentes de programação. Suas conversas e arquivos ficam no seu PC.
+<p align="center">
+  <a href="#instalação"><b>Instalação</b></a> ·
+  <a href="#modelos">Modelos</a> ·
+  <a href="#qual-é-a-velocidade">Velocidade</a> ·
+  <a href="#como-usar">Como usar</a> ·
+  <a href="#como-funciona">Como funciona</a> ·
+  <a href="#algo-deu-errado">Ajuda</a> ·
+  <a href="#apoie-o-strata">Apoiar</a>
+</p>
 
-**Primeira vez aqui?** Veja [o que você precisa](#o-que-você-precisa) e depois [instale o app](#opção-a-o-app-strata).
+O Strata roda o **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**, um modelo de 125 bilhões de parâmetros que
+normalmente precisa de um servidor, num PC comum. A partir da 0.2.4 ele também roda o **DeepSeek V4.1-Flash** no Terminal. Ele
+conversa, escreve código, lê imagens e funciona com os seus aplicativos e agentes de programação. Suas conversas e arquivos
+ficam no seu PC.
 
 - **Roda num PC gamer.** 32 GB somando memória RAM e memória da placa de vídeo já bastam para começar.
-- **Funciona com as suas ferramentas.** Ele fala as APIs da OpenAI e da Anthropic, então Claude Code, Codex CLI, OpenCode e outros agentes se conectam a ele.
-- **Lê imagens.** Já vêm ativadas.
-- **Gratuito.** Licença MIT, sem conta, sem nuvem.
-- **Privado.** Sem telemetria. O que o Strata baixa, quando usa a internet e como confere os downloads está em [docs/SAFETY.md](docs/SAFETY.md).
-
-Versão 0.2.3 · mecanismo 0.1.48
+- **Funciona com as suas ferramentas.** Claude Code, Codex CLI, OpenCode e outros agentes se conectam pelas APIs da OpenAI e da Anthropic.
+- **Lê imagens**, ativado por padrão.
+- **Gratuito e privado.** Licença MIT, sem conta, sem nuvem, sem telemetria ([o que ele baixa e quando](docs/SAFETY.md)).
 
 ## O que você precisa
 
-**Você precisa de pelo menos 32 GB somando a memória RAM e a memória da placa de vídeo (VRAM).** Num Mac ou num Ryzen AI Max, isso é a
-memória unificada. Mais memória permite um modelo maior ou mais rápido.
+**Você precisa de pelo menos 32 GB de memória: RAM e memória da placa de vídeo (VRAM) somadas.** Num Mac ou num Ryzen AI Max, isso é a
+memória unificada. Um PC de 32 GB com uma placa de 12 a 16 GB roda os tamanhos menores, e 64 GB rodam todos os tamanhos.
 
-- Um PC de 32 GB com uma placa de 12 a 16 GB roda o Coder.
-- 64 GB de RAM rodam todos os tamanhos.
-
-| Seu computador | Detalhes |
+| Funciona em | Guia |
 | --- | --- |
-| **NVIDIA** GeForce RTX série 20, 30, 40, 50 (12 GB ou mais) | Instale o app ou o Terminal. |
-| **AMD** Radeon RX 6800 e mais novas, Radeon AI PRO R9700 (12 GB ou mais) | [Placas AMD](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md), [mecanismo Intel](docs/INTEL.md) |
-| **Mac com Apple Silicon** (M1 ou mais novo, macOS 15 ou mais novo) | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max (Strix Halo)** e outros sistemas de memória unificada | [Strix Halo](docs/STRIX_HALO.md) |
-| Placas e processadores mais antigos | [GPUs antigas](docs/OLDER_GPUS.md), [CPUs antigas](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX série 20, 30, 40 e 50, 12 GB ou mais | [Instalação](#instalação) |
+| **AMD** Radeon RX 6800 e mais novas, Radeon AI PRO R9700 | [Placas AMD](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Mac com Apple Silicon**, M1 ou mais novo, macOS 15 ou mais novo | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max (Strix Halo)** e outros PCs de memória unificada | [Strix Halo](docs/STRIX_HALO.md) |
+| Placas e processadores mais antigos | [GPUs antigas](docs/OLDER_GPUS.md) |
 
-Você também precisa de:
-
-- cerca de 80 GB de espaço livre no disco (um SSD deixa a primeira inicialização bem mais rápida)
-- Windows 10 / 11, Linux ou macOS
-- um driver de vídeo atualizado
-
-Duas ou três placas da mesma marca podem dividir um modelo ([multi-GPU](docs/MULTI_GPU.md)). O Strata nunca divide um modelo entre
-placas NVIDIA e AMD. Lista completa: [docs/INSTALL.md](docs/INSTALL.md#what-you-need).
+Você também precisa de cerca de 80 GB de espaço livre no disco (um SSD), Windows 10 / 11, Linux ou macOS, e um driver de vídeo
+atualizado. Duas ou três placas da mesma marca podem dividir um modelo ([multi-GPU](docs/MULTI_GPU.md)).
 
 ## Instalação
 
-Escolha uma opção. Todas iniciam o mesmo mecanismo e usam os mesmos modelos.
+### 1. O app Strata (o mais fácil)
 
-### Opção A: o app Strata
+Baixe o arquivo para o seu computador, abra e clique em instalar no modelo que ele recomenda.
 
-O jeito mais fácil. O app já traz o mecanismo: instale, escolha um modelo e converse. Baixe o arquivo para o seu sistema e a sua
-placa de vídeo na [página de releases](https://github.com/Niko1221/Strata/releases/latest). Não sabe qual? Veja a explicação
-logo abaixo da tabela.
+**Windows 10 / 11**
 
-| Sistema | Sua placa de vídeo | Arquivo para baixar |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX, driver 580 ou mais novo | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA, placa mais antiga ou driver anterior ao 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon série RX 9000 ou Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon série RX 7000 ou Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX, driver 580 ou mais novo | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA, placa mais antiga ou driver anterior ao 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon série RX 9000 ou Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon série RX 7000 | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac** (Apple Silicon, macOS 15 ou mais novo) | integrada | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**Se você estiver em dúvida:** para NVIDIA, use `cuda13` se o seu driver for a versão 580 ou mais nova, e `cuda12` nos outros casos. O `cuda12`
-serve para placas e drivers mais antigos. Os arquivos `hip` e `amd` são para placas AMD. Outras placas AMD (RX 6000) ainda não têm app pronto: veja [Placas AMD](docs/AMD_HIP.md).
+**Linux**
 
-Depois:
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows:** execute o `.exe`. Ele instala só para o seu usuário e não pede direitos de administrador. Se o Windows disser "O Windows
-  protegeu o computador", escolha **Mais informações** e depois **Executar assim mesmo** (o instalador ainda não tem assinatura de código).
-- **Linux:** torne o arquivo executável (`chmod +x`) e inicie. É preciso ter o FUSE 2: `sudo apt install libfuse2` (Ubuntu 22.04)
-  ou `libfuse2t64` (Ubuntu 24.04 e mais novos).
-- **Mac:** abra o `.dmg` e arraste o Strata para Aplicativos.
+**Mac** (Apple Silicon, macOS 15 ou mais novo)
 
-Na primeira tela, o app lê o seu PC e recomenda um modelo que caiba nele. Clique em instalar. O modelo é um download grande
-(cerca de 40 a 70 GB) e continua de onde parou se for interrompido. Fechar a janela encerra o Strata e o mecanismo.
+[![Mac, Apple Silicon](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### Opção B: o Terminal (uma linha)
+O aplicativo escolhe sozinho o mecanismo certo para a sua placa de vídeo. Todos os arquivos estão na
+[página de releases](https://github.com/Niko1221/Strata/releases/latest).
 
-O Terminal é o comando `strata`, para scripts, servidores e agentes de IA.
+| Primeira inicialização | O que fazer |
+| --- | --- |
+| **Windows** | Execute o `.exe`. Não precisa de direitos de administrador. Se o Windows disser "O Windows protegeu o computador", escolha **Mais informações** e depois **Executar assim mesmo**. |
+| **Linux** | Torne o arquivo executável (`chmod +x`) e inicie. É preciso ter o FUSE 2: `sudo apt install libfuse2t64` (Ubuntu 24.04 e mais novos) ou `libfuse2` (22.04). |
+| **Mac** | Abra o `.dmg` e arraste o Strata para Aplicativos. |
+
+O download do modelo é grande (40 a 70 GB). Se parar, continua de onde parou.
+
+### 2. O Terminal (uma linha)
+
+O comando `strata`, para scripts, servidores e agentes de IA. É também o jeito de rodar o DeepSeek.
 
 Linux e Mac:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows (PowerShell):
@@ -114,24 +104,17 @@ Windows (PowerShell):
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-O script confere o seu PC, baixa o Terminal, verifica o SHA-256 e descompacta na sua pasta pessoal. Não precisa de direitos de
-administrador. No Windows, abra uma nova janela do terminal depois. Então inicie o Strata:
+Depois inicie. Ele faz uma pergunta por vez (modelo, contexto, imagens, quem pode se conectar), baixa o que precisa e começa
+a servir:
 
 ```sh
 strata launch
 ```
 
-Ele faz uma pergunta por vez: modelo, contexto, imagens, quem pode se conectar. Depois baixa o mecanismo para a sua placa de vídeo
-(assinada e testada antes do uso) e o modelo, e começa a servir. Em scripts e agentes de IA, use flags:
+Não precisa de direitos de administrador. A instalação confere o SHA-256 de tudo que baixa. No Windows, abra uma nova janela do
+terminal depois da instalação. Todas as telas e flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
 
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-Para ler o script de instalação antes de executá-lo, baixe-o primeiro com `curl -fsSL <address> -o install.sh`, leia e então rode
-`sh install.sh`. Todas as telas e flags: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md).
-
-### Opção C: deixe a sua IA configurar
+### 3. Deixe a sua IA configurar
 
 Cole isto no Claude Code, Cursor, Codex, GitHub Copilot ou outro assistente de programação:
 
@@ -146,47 +129,58 @@ Prefere compilar por conta própria? Veja [Compilar a partir do código-fonte](#
 
 ## Modelos
 
-O app e o `strata launch` recomendam um modelo para a sua memória. É um único modelo em vários tamanhos, mais ou menos comprimidos.
-Os tamanhos menores são mais rápidos. Os maiores são um pouco mais inteligentes.
+O app e o `strata launch` recomendam um tamanho para a sua memória. Os tamanhos menores são mais rápidos. Os maiores são um
+pouco mais inteligentes.
 
 ### Pouca memória? Experimente o Gyro
 
-O [Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF) (da agentionai) é a menor forma de rodar este modelo.
+O [Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF), da agentionai, é a menor forma de rodar o
+Qwen3.8-Flash-Next. Ele roda em NVIDIA, AMD, Intel Arc e Apple Silicon.
 
-| Tamanho | Memória necessária (RAM + VRAM) | Download | O que é |
+| Tamanho | Memória necessária (RAM + VRAM) | Download | Serve para |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27,6 GB | 58,5 GB | Para PCs onde nenhum outro tamanho cabe. A qualidade é menor que a do IQ2_XS. |
-| **Gyro-M** | 35 GB | 92,0 GB | Qualidade próxima à do IQ3_XXS, com cerca de 20% menos memória da GPU. Ele escreve as respostas 16% mais devagar que o Q2_0 numa RTX 3060 de 12 GB e 21% mais devagar numa R9700. |
+| **Gyro-S** | 27,6 GB | 58,5 GB | PCs onde nenhum outro tamanho cabe. 9 tokens/s num Mac mini de 32 GB. |
+| **Gyro-M** | 35 GB | 92,0 GB | Qualidade próxima à do IQ3_XXS, com 20% menos memória da GPU. |
 
-O Gyro roda em placas NVIDIA e AMD (AMD é experimental) em placas Intel Arc no Linux (testado numa Arc A750) e, desde a 0.2.2, em Macs com Apple Silicon (Gyro-S num Mac mini de 32 GB: 9 tokens/s, com os especialistas lidos do SSD). Detalhes e medições:
-[docs/GYRO.md](docs/GYRO.md). Inicie com `strata launch --model gyro-s`.
+Inicie com `strata launch --model gyro-s`. Detalhes: [docs/GYRO.md](docs/GYRO.md).
 
-### Os outros tamanhos
+### Os tamanhos do Qwen3.8-Flash-Next
 
-| Sua memória (RAM + VRAM) | Escolha | Observações |
+| Sua memória (RAM + VRAM) | Escolha | Por quê |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**, ou o **[Coder](docs/MODELS.md#coder)** para código | O Coder precisa de 32 GB de RAM e mantém metade dos experts, então é mais fraco fora de código |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB), ou **Gyro-M** (35 GB) | O Swift pensa por menos tempo antes de responder. O Gyro-M chega perto do IQ3_XXS em qualidade, mas escreve as respostas 16 a 21% mais devagar que o Q2_0 |
+| **32 GB** | **Gyro-S**, ou o **[Coder](docs/MODELS.md#coder)** para código | O Coder mantém os experts que o código usa |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS (39,2 GB) ou **Gyro-M** | O Swift pensa por menos tempo antes de responder |
 | **48 GB** | **IQ3_XXS** (47,0 GB) | Mais lento, melhor |
-| **64 GB** | **IQ3_S** (54,8 GB), o original ou o Swift 1.5 | O mais lento, o melhor: empata com o modelo completo nos testes publicados |
-| **96 GB ou mais** | **UD-IQ4_XS** da Unsloth (cerca de 72 GB de RAM) até **Q8_0** (cerca de 136 GB), de 4 a 8 bits | Mais perto do modelo completo. Com menos RAM, o Strata lê parte deles do SSD, o que é bem mais lento |
+| **64 GB** | **IQ3_S** (54,8 GB) | Empata com o modelo completo nos testes publicados |
+| **96 GB ou mais** | **UD-IQ4_XS** a **Q8_0** da Unsloth | O mais perto do modelo completo |
 
-Com menos RAM do que a linha indica, ainda pode funcionar: o Strata muda sozinho para o
-[modo de pouca RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Espere mais lentidão, e muito mais com uma placa de vídeo pequena.
+Com menos RAM do que a linha indica, ainda pode funcionar, só que mais devagar: o Strata muda sozinho para o
+[modo de pouca RAM](docs/MODELS.md#a-big-graphics-card-and-little-ram). Há também:
+[NVFP4](docs/NVFP4.md) para placas NVIDIA, [Qwen3.6-35B-A3B](docs/QWEN36.md) (menor, vários pedidos ao mesmo tempo) e
+[o Uncensored IQ3_XXS da OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs). Todos os tamanhos e o que cabe em cada configuração:
+[docs/MODELS.md](docs/MODELS.md).
 
-Mais opções:
+### DeepSeek V4.1-Flash (Terminal, a partir da 0.2.4)
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** é um ajuste fino que pensa por menos tempo antes de responder, com qualidade e RAM parecidas.
-- **[NVFP4](docs/NVFP4.md)** é a versão de 4 bits da NVIDIA para placas NVIDIA. Precisa de cerca de 80 GB de RAM para manter todos os experts na RAM.
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** é outro modelo, menor, que lê imagens e pode atender vários pedidos ao mesmo tempo.
-- **[Uncensored IQ3_XXS da OrcaRouter](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** é configurado manualmente.
+Um modelo bem maior, que roda numa única placa de vídeo de 12 GB com 46 a 64 GB de RAM. O Strata mantém na memória as partes mais
+usadas e lê o resto do seu SSD. A [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)
+fez os conjuntos. Ele roda em placas NVIDIA RTX das séries 30, 40 e 50 e na Radeon AI PRO R9700. Escolha no `strata launch`. O
+app de desktop ainda não o oferece.
 
-Todos os tamanhos, downloads e o que cabe em cada configuração: [docs/MODELS.md](docs/MODELS.md).
+| Conjunto | Download | Qualidade | Escreve código a |
+| --- | ---: | --- | --- |
+| **IQ1_M** (1,75 bits) | 239 GB | O menor, mais fraco em prosa simples | ainda não medido num PC |
+| **IQ2_XXS** (2.00 bits) | 257 GB | Bom equilíbrio | 10 tokens/s (RTX 3060), 5 (RTX 5070), 48 (4x R9700) |
+| **IQ2_XS** (2.25 bits) | 274 GB | O mais perto do original | 15 tokens/s (uma R9700), 80 (4x R9700) |
+| **IQ4_NL** (tabela Engram) | incluída em cada download acima | A tabela de consulta que os três conjuntos compartilham | |
+
+Inicie com `strata launch --model ist-das-2.00bpw` (ou `ist-das-1.75bpw`, `ist-das-2.25bpw`). Números de qualidade,
+velocidades por PC e a instalação manual: [docs/DEEPSEEK41.md](docs/DEEPSEEK41.md).
 
 ## Qual é a velocidade?
 
-Com base numa placa de vídeo de 12 GB (RTX 5070, Ryzen 5 7600, 64 GB de RAM). Veja resultados de outras placas:
-[velocidade de cada modelo](docs/MODELS.md#how-fast-is-each-size), [resultados da comunidade](docs/COMMUNITY_BENCHMARKS.md).
+Com base numa placa de vídeo de 12 GB (RTX 5070, 64 GB de RAM). Veja resultados de outras placas:
+[velocidade de cada tamanho](docs/MODELS.md#how-fast-is-each-size) e [resultados da comunidade](docs/COMMUNITY_BENCHMARKS.md).
 
 | Modelo | As respostas aparecem a | Lê o seu prompt a |
 | --- | --- | --- |
@@ -196,10 +190,7 @@ Com base numa placa de vídeo de 12 GB (RTX 5070, Ryzen 5 7600, 64 GB de RAM). V
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1.620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2.180 tokens/s |
 
-Um token equivale a cerca de ¾ de palavra, então 60 tokens por segundo é mais rápido do que você lê. "Lê o seu prompt" é a velocidade com que o Strata
-absorve um documento longo, um código ou um histórico de conversa.
-
-Medido numa placa AMD de 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB de RAM):
+Numa placa AMD de 16 GB (RX 9070 XT, 47 GB de RAM):
 
 | Modelo | As respostas aparecem a | Lê o seu prompt a |
 | --- | --- | --- |
@@ -207,82 +198,58 @@ Medido numa placa AMD de 16 GB (RX 9070 XT, Ryzen 9 3900X, 47 GB de RAM):
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1.110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1.420 tokens/s |
 
-As barras usam a mesma escala nas duas tabelas. Uma placa com mais VRAM é mais rápida: uma RTX 3090 (24 GB) deve escrever cerca de 100 a 140
-tokens por segundo. A versão do mecanismo por trás de cada número está em [DETAILS.md](docs/DETAILS.md#speed-measured).
+Um token equivale a cerca de ¾ de palavra, então 60 tokens por segundo é mais rápido do que você lê. "Lê o seu prompt" é a velocidade com que o Strata
+absorve um documento longo, um código ou um histórico de conversa.
 
 ## Como usar
 
 ### No app
 
-O app tem um **Chat**, um **Monitor** do modelo e da sua GPU, CPU e RAM, uma página de **Modelos** e as **Configurações**. O chat
-pode trabalhar numa pasta do seu PC. No modo **Manual**, ele pergunta antes de alterar um arquivo ou executar um comando. Digite
-`/loop 10m <o que fazer>` para repetir uma mensagem a cada 10 minutos enquanto o chat estiver aberto.
+Um chat, um **Monitor** do modelo e da sua GPU, CPU e RAM, uma página de **Modelos** e as **Configurações**. O chat pode
+trabalhar numa pasta do seu PC. No modo **Manual**, ele pergunta antes de alterar um arquivo ou executar um comando. Ele pode
+pesquisar na web (DuckDuckGo ou Bing, sem conta). Os termos da pesquisa são a única coisa que sai do seu PC.
 
-O chat pode pesquisar na web com o DuckDuckGo (ou o Bing), sem conta. Você pode adicionar uma chave de busca em **Configurações, Ferramentas**.
-A busca é o único recurso que envia algo para fora do seu PC: os termos da pesquisa.
-
-Para rodar dois modelos, ative **Executar vários modelos** e dê a cada modelo a sua própria placa da mesma marca.
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Um chat no app Strata: o agente escreveu um pequeno jardim de pagode em voxels em um único arquivo HTML, e a página abre na pré-visualização ao lado da conversa</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="O app Strata: um chat em que o agente montou um pequeno jardim de pagodes em voxels, com a página aberta na pré-visualização à direita"><br>
+<sub>O agente escreveu um jardim de pagodes em voxels em um único arquivo HTML, e a página abre na pré-visualização ao lado do chat</sub></p>
 
 ### No Terminal
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="A visão geral do monitor do Terminal do Strata enquanto o modelo escreve uma resposta"><br>
 <sub><code>strata monitor</code> enquanto o modelo responde: velocidade, GPU, memória e as solicitações recentes</sub></p>
 
 ```sh
-strata launch                                  # telas guiadas: modelo, contexto, imagens, acesso e depois servir
-strata launch --model q2_0 --yes --no-tui     # sem perguntas: serve, mostra o endereço e volta
-strata launch --plan --model q2_0              # mostra o que aconteceria; nada muda
-strata launch --status                         # o que está sendo servido agora
-strata launch --stop                           # para o serviço
-strata monitor --url http://127.0.0.1:8080     # acompanha velocidade, GPU, memória e requisições
-strata update --check                          # há um mecanismo novo? (strata update instala)
-strata doctor                                  # confere os arquivos do mecanismo instalada
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` lista tudo. Iniciar e servir nunca baixam nada. Só a instalação, o `strata launch` (quando você
-escolhe um modelo) e o `strata update` baixam. Para acessar o Strata do celular ou de outro PC, use
-`strata launch --access lan`. Ele cria uma chave de API e não inicia numa rede sem uma. Nenhum navegador abre, a menos que
-você adicione `--open`. Guia: [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md). Cliente completo: [docs/TERMINAL.md](docs/TERMINAL.md).
+Para acessar o Strata do celular ou de outro PC, use `strata launch --access lan`. Ele cria uma chave de API para você.
+`strata --help` lista tudo, e o [docs/TERMINAL.md](docs/TERMINAL.md) explica.
 
-### Com agentes de IA
+### Com agentes de IA e outros aplicativos
 
-Um agente instala o Strata com o comando de uma linha da Opção B e executa
-`strata launch --model NAME --yes --no-tui`. Os passos, as flags e os códigos de saída estão em [docs/AI_SETUP.md](docs/AI_SETUP.md),
-e as regras do repositório estão em [AGENTS.md](AGENTS.md).
+Um agente instala o Strata com o comando de uma linha acima e executa `strata launch --model NAME --yes --no-tui`. Os passos,
+as flags e os códigos de saída estão em [docs/AI_SETUP.md](docs/AI_SETUP.md). As regras do repositório para agentes: [AGENTS.md](AGENTS.md).
 
-### Conecte os seus outros aplicativos
-
-| Tipo de aplicativo | URL base |
+| Seu aplicativo fala | URL base |
 | --- | --- |
-| Compatível com OpenAI (a maioria dos apps e agentes) | `http://127.0.0.1:8080/v1` (qualquer chave de API, qualquer nome de modelo) |
-| API da Anthropic (Claude Code e outros) | `http://127.0.0.1:8080`, sem `/v1`. Esses aplicativos adicionam `/v1/messages` sozinhos. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| API da OpenAI (a maioria dos apps e agentes) | `http://127.0.0.1:8080/v1` (qualquer chave de API, qualquer nome de modelo) |
+| API da Anthropic (Claude Code) | `http://127.0.0.1:8080`, sem `/v1`. Claude Code: `ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | OpenAI Responses API (Codex CLI) | `http://127.0.0.1:8080/v1/responses` ([configuração](docs/DETAILS.md#the-responses-api-and-codex-cli)) |
 
-`strata connect` mostra as configurações exatas para OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent e OpenClaw.
-`strata connect opencode --write` grava o arquivo depois de perguntar e mantém um backup.
-
-### Imagens
-
-As imagens vêm ativadas nos modelos que sabem lê-las. Anexe ou cole uma imagem no chat, ou envie pelo seu aplicativo.
-O leitor de imagens roda no processador quando a sua placa de vídeo tem menos de 24 GB (alguns segundos por imagem, sem tirar nada
-da memória da placa) e roda na placa de vídeo a partir de 24 GB. A regra é a mesma para NVIDIA e AMD. Desative as imagens
-por modelo, ou escolha o leitor com `--vision off`, `--vision gpu` ou `--vision cpu`.
-
-Os números por trás da regra: numa Radeon AI PRO R9700, o leitor da placa levou 57 ms para uma imagem de 260 tokens e o do
-processador levou 3,1 s. Em placas de 16 GB (Tesla P100 e RTX A4000, Linux), o leitor da placa custou de 3 a 5% da velocidade do texto,
-porque ocupa cerca de 1,4 GB que o modelo usaria de outra forma. No Mac, a GPU faz a leitura, seja qual for a memória (0,45 s para uma imagem de 260 tokens em um M4 de 32 GB, cerca de 1,2 GB da memória compartilhada);
-o processador leva cerca de 50 s por imagem, então só lê com `--vision cpu`.
+`strata connect` mostra as configurações exatas para OpenCode, Codex CLI, Claude Code, oh-my-pi, pi, Hermes Agent e OpenClaw,
+e `strata connect opencode --write` grava para você (com um backup).
 
 ### Bom saber
 
-- Escolha o nível de raciocínio (**off, low, medium ou high**) no menu do chat ou no "reasoning effort" do seu aplicativo. Off é o mais rápido.
-- Por padrão, o Strata responde a um pedido por vez. Para vários ao mesmo tempo, use `--parallel N` no `strata launch` ou
-  `"parallel": 2` na configuração ([BATCHING.md](docs/BATCHING.md)). Numa placa de 12 GB, isso deixa cada resposta mais lenta.
-- O Strata lê a primeira mensagem de uma conversa por inteiro, cerca de 1 minuto a cada 30.000 tokens. As mensagens seguintes começam em segundos.
-- Onde ficam as suas conversas e a API completa: [docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored), [docs/DETAILS.md](docs/DETAILS.md#using-it).
+- **As imagens** vêm ativadas em todo modelo que sabe lê-las. Anexe ou cole uma imagem no chat, ou envie pelo seu aplicativo. Detalhes: [docs/IMAGES.md](docs/IMAGES.md).
+- **O raciocínio** pode ser off, low, medium ou high, no menu do chat ou no "reasoning effort" do seu aplicativo. Off é o mais rápido.
+- **A primeira mensagem** de uma conversa é lida por inteiro, cerca de 1 minuto a cada 30.000 tokens. As mensagens seguintes começam em segundos.
+- **Um pedido por vez** é o padrão. Para mais de um, use `--parallel N` ([BATCHING.md](docs/BATCHING.md)). Numa placa de 12 GB, isso deixa cada resposta mais lenta.
 
 ## Compilar a partir do código-fonte
 
@@ -343,13 +310,13 @@ Modelos como este costumam rodar em servidores com centenas de gigabytes de mem
 - **O seu SSD é o arquivo.** Ele guarda uma tabela de consulta de 29 GB. O modelo lê algumas linhas dela por palavra, então ela não
   precisa ficar na RAM.
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="Os 24.576 experts do modelo: os mais usados na placa de vídeo, todos na RAM, uma tabela de consulta no SSD"></p>
 
 Um pequeno ajudante também adivinha as próximas palavras. O modelo grande confere todas de uma vez e fica com as certas. Você recebe
 a mesma resposta, de 1,6 a 1,8 vez mais rápido. Textos longos são lidos em blocos grandes, de até 8.192 tokens por vez, a mais de 1.000 tokens
 por segundo.
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="Um pequeno ajudante adivinha as próximas palavras; o modelo grande confere todas de uma vez e fica com as certas"></p>
 
 A explicação mais longa: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Cada parte e seus números:
 [os detalhes](docs/DETAILS.md#how-it-works) e o [artigo](docs/paper/Strata-Paper.pdf).
@@ -358,26 +325,25 @@ A explicação mais longa: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md). Cada pa
 
 - **Meu PC travou na primeira vez que o Strata iniciou.** Ele carrega o modelo na RAM. Espere e não feche a janela. Ainda
   travado depois de 10 minutos? Reinicie o PC, feche outros programas e tente de novo, ou escolha um tamanho menor.
-- **Parou durante o download ou a instalação.** Abra o app ou o `strata launch` de novo, ou execute `START-HERE.bat` (ou
-  `./setup.sh`) outra vez. Ele continua de onde parou.
-- **Está muito lento, a luz do disco não para de piscar, ou aparece "o mecanismo parou inesperadamente".** O seu PC não tem
-  RAM livre suficiente. Feche outros programas (os navegadores usam muita), ou escolha um tamanho menor, como Q2_0 ou IQ2_XS.
+- **Parou durante o download ou a instalação.** Abra o app ou o `strata launch` de novo. Ele continua de onde parou.
+- **Está muito lento, ou aparece "the engine stopped unexpectedly".** O seu PC não tem RAM livre suficiente. Feche outros
+  programas (os navegadores usam muita), ou escolha um tamanho menor, como Q2_0 ou IQ2_XS.
 - **Diz que não há mecanismo para este PC.** No app, abra **Configurações, Mecanismo** e clique em **Atualizar mecanismo**. No
-  Terminal, execute `strata update`. O `strata doctor` mostra quais arquivos do mecanismo estão instalados.
+  Terminal, execute `strata update`.
 - **Diz que a porta 8080 já está em uso.** O Strata já está rodando. Procure a janela dele.
 
-Mais problemas e soluções: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Ainda sem resolver? Abra uma
-[issue](https://github.com/Niko1221/Strata/issues). No app, anexe o arquivo de **Configurações, Mecanismo, Diagnóstico, Ver
-registros, Salvar logs**. No Terminal, cole a saída de `strata doctor`. Se estiver rodando pelo código-fonte, anexe o `strata-<model>.log` da pasta do
-Strata. Para um problema de segurança, informe em particular: [SECURITY.md](SECURITY.md).
+Mais soluções: [docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md). Ainda sem resolver? Abra uma
+[issue](https://github.com/Niko1221/Strata/issues) e anexe os logs: no app, em **Configurações, Mecanismo, Diagnóstico,
+Salvar logs**; no Terminal, a saída de `strata doctor`. Para um problema de segurança, informe em particular: [SECURITY.md](SECURITY.md).
 
 ## Créditos e licença
 
 O modelo é o [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next), da equipe Qwen. Ele foi comprimido por
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF), UkisAI (Swift 1.5), agentionai (Gyro)
-e Unsloth. O Strata usa partes do [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Todos os créditos:
-[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits). O Strata é de código aberto sob a [Licença MIT](LICENSE). Algumas partes e
-todos os modelos têm licenças próprias ([quais](docs/HOW_IT_WORKS.md#license)).
+e Unsloth. A ISTA-DASLab também fez os conjuntos do DeepSeek V4.1-Flash. O Strata usa partes do
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp). Todos os créditos: [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits).
+O Strata é de código aberto sob a [Licença MIT](LICENSE). Algumas partes e todos os modelos têm licenças próprias
+([quais](docs/HOW_IT_WORKS.md#license)).
 
 ## Contribuindo
 

README.zh-CN.md

@@ -12,100 +12,87 @@
 <p align="center">支持 NVIDIA、AMD、Intel · Windows、Linux、Mac · 免费开源</p>
 
 <p align="center">
-  <a href="https://github.com/Niko1221/Strata/releases"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="Latest release"></a>
-  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT license"></a>
-  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub stars"></a>
+  <a href="https://github.com/Niko1221/Strata/releases/latest"><img src="https://img.shields.io/github/v/release/Niko1221/Strata?include_prereleases&label=release" alt="最新版本"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/github/license/Niko1221/Strata" alt="MIT 许可证"></a>
+  <a href="https://github.com/Niko1221/Strata/stargazers"><img src="https://img.shields.io/github/stars/Niko1221/Strata?style=flat" alt="GitHub 星标"></a>
+  <a href="https://buymeacoffee.com/strataengine"><img src="https://img.shields.io/badge/Buy%20me%20a%20coffee-FFDD00?logo=buymeacoffee&logoColor=black" alt="请我喝杯咖啡"></a>
 </p>
 
-<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="A voxel pagoda garden that Strata's model wrote, running in the browser"></a><br>
+<p align="center"><a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4"><img src="docs/media/pagoda-preview.webp" width="720" alt="Strata 的模型写出的体素宝塔花园，在浏览器里运行"></a><br>
 <sub>一座体素宝塔花园，由一条提示词一次生成，在装有 RTX 5070 的电脑上用 Strata 运行（IQ3_S，128K 上下文） ·
 <a href="https://github.com/Niko1221/Strata/releases/download/v0.1.10/Pagoda.mp4">完整视频（49 秒）</a></sub></p>
 
-Strata 运行 **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**。这是一个 1250 亿参数的模型，
-通常需要服务器才能跑，现在用普通电脑就行。它能聊天、写代码、看图片，也能配合你的应用和编程智能体使用。
-你的聊天记录和文件都留在你自己的电脑上。
+<p align="center">
+  <a href="#安装"><b>安装</b></a> ·
+  <a href="#模型">模型</a> ·
+  <a href="#速度如何">速度</a> ·
+  <a href="#使用方法">使用方法</a> ·
+  <a href="#工作原理">工作原理</a> ·
+  <a href="#出问题了">帮助</a> ·
+  <a href="#支持-strata">支持</a>
+</p>
 
-**第一次用？** 先看[硬件要求](#硬件要求)，再[安装应用](#方式-astrata-应用)。
+Strata 运行 **[Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)**。这是一个 1250 亿参数的模型，
+通常需要服务器才能跑，现在用普通电脑就行。从 0.2.4 起，它在终端版里也能运行 **DeepSeek V4.1-Flash**。它能聊天、写代码、
+看图片，也能配合你的应用和编程智能体使用。你的聊天记录和文件都留在你自己的电脑上。
 
 - **游戏电脑就能跑。** 内存和显存加起来有 32 GB 就可以开始。
-- **能接入你的工具。** 支持 OpenAI 和 Anthropic 的 API，Claude Code、Codex CLI、OpenCode 等智能体都能连上。
-- **能看图片。** 默认开启。
-- **免费。** MIT 许可证，不用注册账号，不走云端。
-- **隐私。** 没有遥测。Strata 下载什么、什么时候联网、如何校验下载内容，都写在 [docs/SAFETY.md](docs/SAFETY.md)。
-
-版本 0.2.3 · 引擎 0.1.48
+- **能接入你的工具。** Claude Code、Codex CLI、OpenCode 等智能体通过 OpenAI 和 Anthropic 的 API 连接。
+- **能看图片**，默认开启。
+- **免费且隐私。** MIT 许可证，不用注册账号，不走云端，没有遥测（[它下载什么、什么时候下载](docs/SAFETY.md)）。
 
 ## 硬件要求
 
-**内存和显存（VRAM）加起来至少要有 32 GB。** Mac 和 Ryzen AI Max 上指的是统一内存。内存越大，能跑的模型越大，
-或者速度越快。
+**内存和显存（VRAM）加起来至少要有 32 GB。** Mac 和 Ryzen AI Max 上指的是统一内存。32 GB 内存加一张 12-16 GB 显存的显卡，
+可以跑较小的尺寸；64 GB 可以跑所有尺寸。
 
-- 32 GB 内存加一张 12-16 GB 显存的显卡，可以跑 Coder。
-- 64 GB 内存可以跑所有尺寸。
-
-| 你的电脑 | 说明 |
+| 适用于 | 指南 |
 | --- | --- |
-| **NVIDIA** GeForce RTX 20、30、40、50 系列（12 GB 及以上） | 安装应用或终端版即可。 |
-| **AMD** Radeon RX 6800 及更新型号、Radeon AI PRO R9700（12 GB 及以上） | [AMD 显卡](docs/AMD_HIP.md) |
-| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md)、[Intel 引擎](docs/INTEL.md) |
-| **Apple 芯片 Mac**（M1 及更新，macOS 15 及以上） | [Mac](docs/MAC.md) |
-| **AMD Ryzen AI Max（Strix Halo）** 及其他统一内存系统 | [Strix Halo](docs/STRIX_HALO.md) |
-| 较旧的显卡和处理器 | [旧显卡](docs/OLDER_GPUS.md)、[旧处理器](docs/INSTALL.md#older-cpus-experimental) |
+| **NVIDIA** GeForce RTX 20、30、40 和 50 系列，12 GB 及以上 | [安装](#安装) |
+| **AMD** Radeon RX 6800 及更新型号、Radeon AI PRO R9700 | [AMD 显卡](docs/AMD_HIP.md) |
+| **Intel** Arc | [Intel Arc](docs/INTEL_ARC.md) |
+| **Apple 芯片 Mac**，M1 及更新，macOS 15 及以上 | [Mac](docs/MAC.md) |
+| **AMD Ryzen AI Max（Strix Halo）** 及其他统一内存的电脑 | [Strix Halo](docs/STRIX_HALO.md) |
+| 较旧的显卡和处理器 | [旧显卡](docs/OLDER_GPUS.md) |
 
-另外还需要：
-
-- 约 80 GB 的可用磁盘空间（用固态硬盘，首次启动会快很多）
-- Windows 10 / 11、Linux 或 macOS
-- 较新的显卡驱动
-
-同一品牌的两三张显卡可以共同运行一个模型（[多显卡](docs/MULTI_GPU.md)）。Strata 不会把一个模型拆到 NVIDIA 和 AMD
-显卡上。完整列表见 [docs/INSTALL.md](docs/INSTALL.md#what-you-need)。
+你还需要约 80 GB 的可用磁盘空间（固态硬盘）、Windows 10 / 11、Linux 或 macOS，以及较新的显卡驱动。同一品牌的两三张显卡可以共同运行一个模型（[多显卡](docs/MULTI_GPU.md)）。
 
 ## 安装
 
-三种方式任选一种。它们启动的是同一个引擎，用的是同样的模型。
+### 1. Strata 应用（最简单）
 
-### 方式 A：Strata 应用
+下载适合你电脑的文件，打开它，然后对推荐的模型点击安装。
 
-最简单的方式。应用内置引擎：安装、选模型、开始聊天。请根据你的系统和显卡，从
-[发布页](https://github.com/Niko1221/Strata/releases/latest)下载对应的文件。不确定选哪个？看表格下面那一段。
+**Windows 10 / 11**
 
-| 系统 | 你的显卡 | 要下载的文件 |
-| --- | --- | --- |
-| **Windows 10 / 11** | NVIDIA RTX，驱动 580 或更新 | [`Strata-0.2.3-windows-cuda13.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda13.exe) |
-| | NVIDIA，较旧的显卡，或驱动低于 580 | [`Strata-0.2.3-windows-cuda12.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-cuda12.exe) |
-| | AMD Radeon RX 9000 系列或 Radeon AI PRO R9700 | [`Strata-0.2.3-windows-hip.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip.exe) |
-| | AMD Radeon RX 7000 系列或 Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-windows-hip-rdna3.exe`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-windows-hip-rdna3.exe) |
-| **Linux** | NVIDIA RTX，驱动 580 或更新 | [`Strata-0.2.3-linux-nvidia-cuda13.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda13.AppImage) |
-| | NVIDIA，较旧的显卡，或驱动低于 580 | [`Strata-0.2.3-linux-nvidia-cuda12.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-nvidia-cuda12.AppImage) |
-| | AMD Radeon RX 9000 系列或 Radeon AI PRO R9700 | [`Strata-0.2.3-linux-amd-rx9070.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx9070.AppImage) |
-| | AMD Radeon RX 7000 系列 | [`Strata-0.2.3-linux-amd-rx7900.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-rx7900.AppImage) |
-| | AMD Ryzen AI Max (Strix Halo) | [`Strata-0.2.3-linux-amd-strixhalo.AppImage`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-linux-amd-strixhalo.AppImage) |
-| **Mac**（Apple 芯片，macOS 15 及以上） | 内置 | [`Strata-0.2.3-mac.dmg`](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.3-mac.dmg) |
+[![Windows](https://img.shields.io/badge/Windows-10%20%2F%2011-0078D4?style=for-the-badge&logo=windows&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-windows-x64-setup.exe)
 
-**不确定时：** NVIDIA 显卡的驱动版本在 580 及以上就选 `cuda13`，否则选 `cuda12`。`cuda12` 适用于较旧的显卡和驱动。
-`hip` 和 `amd` 的文件是给 AMD 显卡用的。其他 AMD 显卡（RX 6000）目前还没有现成的应用，
-请看 [AMD 显卡](docs/AMD_HIP.md)。
+**Linux**
 
-然后：
+[![Linux](https://img.shields.io/badge/Linux-AppImage-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-linux-x86_64.AppImage)
 
-- **Windows：** 运行 `.exe`。它只为当前用户安装，不需要管理员权限。如果 Windows 提示“Windows 已保护你的电脑”，
-  点击**更多信息**，再点**仍要运行**（安装程序还没有代码签名）。
-- **Linux：** 给文件加上可执行权限（`chmod +x`），然后启动。需要 FUSE 2：`sudo apt install libfuse2`（Ubuntu 22.04），
-  或 `libfuse2t64`（Ubuntu 24.04 及更新）。
-- **Mac：** 打开 `.dmg`，把 Strata 拖到“应用程序”。
+**Mac**（Apple 芯片，macOS 15 及以上）
 
-第一个界面里，应用会检测你的电脑，并推荐合适的模型。点击安装即可。模型很大，要下载约 40-70 GB，中断后会从断点继续。
-关闭窗口会同时停止 Strata 和引擎。
+[![Mac，Apple 芯片](https://img.shields.io/badge/Mac-Apple%20Silicon-333333?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Niko1221/Strata/releases/latest/download/Strata-0.2.5-macos-arm64.dmg)
 
-### 方式 B：终端（一行命令）
+应用会自己为你的显卡选择合适的引擎。所有文件都在[发布页](https://github.com/Niko1221/Strata/releases/latest)。
 
-终端版就是 `strata` 命令，适合脚本、服务器和 AI 智能体。
+| 首次启动 | 怎么做 |
+| --- | --- |
+| **Windows** | 运行 `.exe`。不需要管理员权限。如果 Windows 提示“Windows 已保护你的电脑”，点击**更多信息**，再点**仍要运行**。 |
+| **Linux** | 给文件加上可执行权限（`chmod +x`），然后启动。需要 FUSE 2：`sudo apt install libfuse2t64`（Ubuntu 24.04 及更新）或 `libfuse2`（22.04）。 |
+| **Mac** | 打开 `.dmg`，把 Strata 拖到“应用程序”。 |
+
+模型下载很大（40-70 GB）。如果中断，会从断点继续。
+
+### 2. 终端版（一行命令）
+
+`strata` 命令，适合脚本、服务器和 AI 智能体。运行 DeepSeek 也要用它。
 
 Linux 和 Mac：
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 ```
 
 Windows（PowerShell）：
@@ -114,24 +101,16 @@ Windows（PowerShell）：
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 
-脚本会检查你的电脑，下载终端版，校验 SHA-256，然后解压到你的用户目录。不需要管理员权限。在 Windows 上，装完后请
-打开一个新的终端窗口。然后启动 Strata：
+然后启动它。它会一次问一个问题（模型、上下文、图片、允许谁连接），下载需要的东西，并开始提供服务：
 
 ```sh
 strata launch
 ```
 
-它会一次问一个问题：模型、上下文、图片、允许谁连接。接着为你的显卡下载引擎（已签名，使用前会先试启动），再下载
-模型，并开始提供服务。在脚本和 AI 智能体里，请使用参数：
-
-```sh
-strata launch --model q2_0 --yes --no-tui
-```
-
-如果想在运行前先看看安装脚本，先用 `curl -fsSL <address> -o install.sh` 下载，读完后再用 `sh install.sh` 运行。
+不需要管理员权限。安装程序会校验它下载的所有内容的 SHA-256。在 Windows 上，装完后请打开一个新的终端窗口。
 所有界面和参数见 [docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md)。
 
-### 方式 C：让你的 AI 来安装
+### 3. 让你的 AI 来安装
 
 把下面这段话粘贴到 Claude Code、Cursor、Codex、GitHub Copilot 或其他编程助手里：
 
@@ -146,46 +125,55 @@ Set up Strata on this PC for me: https://github.com/Niko1221/Strata - follow doc
 
 ## 模型
 
-应用和 `strata launch` 会按你的内存推荐模型。它是同一个模型的几种尺寸，压缩程度不同。尺寸小的更快，尺寸大的稍微更聪明一点。
+应用和 `strata launch` 会按你的内存推荐尺寸。尺寸小的更快，尺寸大的稍微更聪明一点。
 
 ### 内存不够？试试 Gyro
 
-[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)（作者 agentionai）是运行这个模型占用最小的方式。
+[Gyro](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)（作者 agentionai）是运行 Qwen3.8-Flash-Next 占用最小的方式。
+它可在 NVIDIA、AMD、Intel Arc 和 Apple 芯片上运行。
 
-| 尺寸 | 所需内存（RAM + VRAM） | 下载大小 | 说明 |
+| 尺寸 | 所需内存（RAM + VRAM） | 下载大小 | 适合 |
 | --- | ---: | ---: | --- |
-| **Gyro-S** | 27.6 GB | 58.5 GB | 给其他尺寸都放不下的电脑。质量低于 IQ2_XS。 |
-| **Gyro-M** | 35 GB | 92.0 GB | 质量约相当于 IQ3_XXS，显存占用少约 20%。输出回答比 Q2_0 慢，12 GB 的 RTX 3060 上慢 16%，R9700 上慢 21%。 |
+| **Gyro-S** | 27.6 GB | 58.5 GB | 其他尺寸都放不下的电脑。32 GB 的 Mac mini 上每秒 9 个 token。 |
+| **Gyro-M** | 35 GB | 92.0 GB | 质量约相当于 IQ3_XXS，显存占用少 20%。 |
 
-Gyro 可在 NVIDIA 和 AMD 显卡（AMD 为实验性支持）以及 Linux 上的 Intel Arc 显卡（已在 Arc A750 上测试）上运行，自 0.2.2 起也可在 Apple Silicon 的 Mac 上运行（32 GB 的 Mac mini 上 Gyro-S 为 9 token/秒，专家权重从 SSD 读取）。详情和测试数据：
-[docs/GYRO.md](docs/GYRO.md)。用 `strata launch --model gyro-s` 启动。
+用 `strata launch --model gyro-s` 启动。详情：[docs/GYRO.md](docs/GYRO.md)。
 
-### 其他尺寸
+### Qwen3.8-Flash-Next 的尺寸
 
-| 你的内存（RAM + VRAM） | 选择 | 备注 |
+| 你的内存（RAM + VRAM） | 选择 | 原因 |
 | --- | --- | --- |
-| **32 GB** | **Gyro-S**，写代码可选 **[Coder](docs/MODELS.md#coder)** | Coder 需要 32 GB 内存，只保留一半的专家，所以代码以外的能力较弱 |
-| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS（39.2 GB），或 **Gyro-M**（35 GB） | Swift 回答前思考的时间更短。Gyro-M 的质量接近 IQ3_XXS，但输出回答比 Q2_0 慢 16-21% |
+| **32 GB** | **Gyro-S**，写代码可选 **[Coder](docs/MODELS.md#coder)** | Coder 保留代码用到的专家 |
+| **40 GB** | **[Swift 1.5](docs/MODELS.md#swift-15)** IQ2_XS（39.2 GB）或 **Gyro-M** | Swift 回答前思考的时间更短 |
 | **48 GB** | **IQ3_XXS**（47.0 GB） | 更慢，更好 |
-| **64 GB** | **IQ3_S**（54.8 GB），原版或 Swift 1.5 | 最慢，最好：在公开测试中与完整模型持平 |
-| **96 GB 及以上** | Unsloth 的 **UD-IQ4_XS**（约 72 GB 内存）到 **Q8_0**（约 136 GB），4 到 8 位 | 更接近完整模型。内存不足时，Strata 会从固态硬盘读取一部分，速度会慢很多 |
+| **64 GB** | **IQ3_S**（54.8 GB） | 在公开测试中与完整模型持平 |
+| **96 GB 及以上** | Unsloth 的 **UD-IQ4_XS** 到 **Q8_0** | 最接近完整模型 |
 
-内存比这一行写的少，也可能能用：Strata 会自动切换到[低内存模式](docs/MODELS.md#a-big-graphics-card-and-little-ram)。
-速度会变慢，显卡较小时会慢得多。
+内存比这一行写的少，也可能能用，只是更慢：Strata 会自动切换到[低内存模式](docs/MODELS.md#a-big-graphics-card-and-little-ram)。
+另外还有：给 NVIDIA 显卡用的 [NVFP4](docs/NVFP4.md)、[Qwen3.6-35B-A3B](docs/QWEN36.md)（更小，能同时处理多个请求），
+以及 [OrcaRouter 的 Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)。所有尺寸，以及各种配置能跑什么：
+[docs/MODELS.md](docs/MODELS.md)。
 
-更多选择：
+### DeepSeek V4.1-Flash（终端版，0.2.4 起）
 
-- **[Swift 1.5](docs/MODELS.md#swift-15)** 是微调版本，回答前思考的时间更短，质量和内存占用大致相同。
-- **[NVFP4](docs/NVFP4.md)** 是 NVIDIA 为 NVIDIA 显卡提供的 4 位版本。要把所有专家放进内存，需要约 80 GB 内存。
-- **[Qwen3.6-35B-A3B](docs/QWEN36.md)** 是另一个更小的模型，能看图片，还能同时回答多个请求。
-- **[OrcaRouter 的 Uncensored IQ3_XXS](docs/MODELS.md#orcarouter-uncensored-iq3_xxs)** 需要手动设置。
+一个大得多的模型，用一块 12 GB 显卡加 46 到 64 GB 内存就能运行。Strata 把最常用的部分留在内存里，其余的从你的固态硬盘读取。
+这些版本由 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF) 制作。它可在
+NVIDIA RTX 30、40、50 系列显卡和 Radeon AI PRO R9700 上运行。请在 `strata launch` 里选择它。桌面应用暂时不提供。
 
-所有尺寸、下载大小，以及各种配置能跑什么：[docs/MODELS.md](docs/MODELS.md)。
+| 版本 | 下载大小 | 质量 | 写代码速度 |
+| --- | ---: | --- | --- |
+| **IQ1_M**（1.75 位） | 239 GB | 最小，普通文字表现较弱 | 还没在电脑上测量 |
+| **IQ2_XXS**（2.00 位） | 257 GB | 平衡得不错 | 每秒 10 个 token（RTX 3060），5（RTX 5070），48（4 块 R9700） |
+| **IQ2_XS**（2.25 位） | 274 GB | 最接近原模型 | 每秒 15 个 token（一块 R9700），80（4 块 R9700） |
+| **IQ4_NL**（Engram 表） | 已包含在上面每个下载中 | 三个版本共用的查找表 | |
+
+用 `strata launch --model ist-das-2.00bpw`（或 `ist-das-1.75bpw`、`ist-das-2.25bpw`）启动。质量数据、各台电脑的速度和手动安装：
+[docs/DEEPSEEK41.md](docs/DEEPSEEK41.md)。
 
 ## 速度如何？
 
-以下数据基于 12 GB 显卡（RTX 5070、Ryzen 5 7600、64 GB 内存）。其他显卡的结果见：
-[各模型的速度](docs/MODELS.md#how-fast-is-each-size)、[社区测试结果](docs/COMMUNITY_BENCHMARKS.md)。
+以下数据基于 12 GB 显卡（RTX 5070、64 GB 内存）。其他显卡的结果见：
+[各尺寸的速度](docs/MODELS.md#how-fast-is-each-size)和[社区测试结果](docs/COMMUNITY_BENCHMARKS.md)。
 
 | 模型 | 回答输出速度 | 读取提示词速度 |
 | --- | --- | --- |
@@ -195,9 +183,7 @@ Gyro 可在 NVIDIA 和 AMD 显卡（AMD 为实验性支持）以及 Linux 上的
 | **IQ3_S** | `███████░░░░░` 53 tokens/s | `███████░░░░░` 1,620 tokens/s |
 | **Coder** | `███████░░░░░` 55 tokens/s | `██████████░░` 2,180 tokens/s |
 
-一个 token 约等于 ¾ 个英文单词，所以每秒 60 个 token 比你阅读的速度还快。“读取提示词”指 Strata 吸收长文档、代码或聊天历史的速度。
-
-在 16 GB 的 AMD 显卡上测得的结果（RX 9070 XT、Ryzen 9 3900X、47 GB 内存）：
+在 16 GB 的 AMD 显卡上（RX 9070 XT、47 GB 内存）：
 
 | 模型 | 回答输出速度 | 读取提示词速度 |
 | --- | --- | --- |
@@ -205,78 +191,57 @@ Gyro 可在 NVIDIA 和 AMD 显卡（AMD 为实验性支持）以及 Linux 上的
 | **IQ2_XS** | `███████░░░░░` 52 tokens/s | `█████░░░░░░░` 1,110 tokens/s |
 | **Coder** | `██████░░░░░░` 44 tokens/s | `██████░░░░░░` 1,420 tokens/s |
 
-两张表的进度条使用同一个比例。显存更大的显卡更快：RTX 3090（24 GB）每秒大约能输出 100-140 个 token。每个数字对应的引擎版本见
-[DETAILS.md](docs/DETAILS.md#speed-measured)。
+一个 token 约等于 ¾ 个英文单词，所以每秒 60 个 token 比你阅读的速度还快。“读取提示词”指 Strata 吸收长文档、代码或聊天历史的速度。
 
 ## 使用方法
 
 ### 在应用里
 
-应用包含**聊天**、显示模型以及 GPU、CPU 和内存状态的**监控**、**模型**页面和**设置**。聊天可以在你电脑上的某个文件夹里工作。
-在**手动**模式下，修改文件或运行命令之前它会先询问你。输入 `/loop 10m <要做的事>`，在聊天保持打开期间每 10 分钟重复发送一次消息。
+聊天、显示模型以及 GPU、CPU 和内存状态的**监控**、**模型**页面和**设置**。聊天可以在你电脑上的某个文件夹里工作。
+在**手动**模式下，修改文件或运行命令之前它会先询问你。它可以搜索网页（DuckDuckGo 或 Bing，不需要账号）。
+发出电脑的只有搜索词。
 
-聊天可以用 DuckDuckGo（或 Bing）搜索网页，不需要账号。你也可以在**设置，工具**里添加搜索密钥。搜索是唯一会把内容发出电脑的功能，
-发出的就是搜索词。
-
-要同时运行两个模型，请打开**运行多个模型**，并为每个模型分配同一品牌的单独一张显卡。
-
-<p align="center"><img src="docs/media/app-chat.png" width="900" alt="The Strata app: a chat where the agent built a small voxel pagoda garden, with the page open in the preview on the right"><br>
-<sub>Strata 应用中的一次对话：智能体用一个 HTML 文件写出了一个小型体素宝塔花园，页面在对话旁的预览中打开</sub></p>
+<p align="center"><img src="docs/media/app-chat.png" width="900" alt="Strata 应用：一次对话，智能体做出了一个小型体素宝塔花园，页面在右侧的预览中打开"><br>
+<sub>智能体用一个 HTML 文件写出了体素宝塔花园，页面在聊天旁的预览中打开</sub></p>
 
 ### 在终端里
 
-<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="The Strata Terminal monitor overview while the model writes a reply"><br>
+<p align="center"><img src="docs/media/terminal-monitor.png" width="900" alt="模型写回复时，Strata 终端监控的总览界面"><br>
 <sub>模型回复时的 <code>strata monitor</code>：速度、GPU、内存和最近的请求</sub></p>
 
 ```sh
-strata launch                                  # 引导界面：模型、上下文、图片、访问方式，然后开始服务
-strata launch --model q2_0 --yes --no-tui     # 不提问：开始服务，打印地址，然后返回
-strata launch --plan --model q2_0              # 显示将要执行的操作；不做任何更改
-strata launch --status                         # 当前正在提供什么服务
-strata launch --stop                           # 停止服务
-strata monitor --url http://127.0.0.1:8080     # 查看速度、GPU、内存和请求
-strata update --check                          # 有新引擎吗？（strata update 会安装它）
-strata doctor                                  # 检查已安装的引擎文件
+strata launch                              # guided: model, context, pictures, access, then serve
+strata launch --model q2_0 --yes --no-tui  # no questions: serve and print the address
+strata launch --status                     # what is being served now
+strata launch --stop                       # stop it
+strata monitor                             # watch speed, GPU, memory and requests
+strata update                              # get the newest engine
+strata doctor                              # check the installed files
 ```
 
-`strata --help` 会列出所有命令。启动和提供服务时不会下载任何东西。只有安装、`strata launch`（在你选择模型时）和
-`strata update` 会下载。要从手机或另一台电脑访问 Strata，请使用 `strata launch --access lan`。它会生成一个 API 密钥，
-没有密钥就不会在网络上启动。除非你加上 `--open`，否则不会打开浏览器。指南：[docs/TERMINAL_LAUNCH.md](docs/TERMINAL_LAUNCH.md)。
-完整的客户端说明：[docs/TERMINAL.md](docs/TERMINAL.md)。
+要从手机或另一台电脑访问 Strata，请使用 `strata launch --access lan`。它会为你生成一个 API 密钥。
+`strata --help` 会列出所有命令，[docs/TERMINAL.md](docs/TERMINAL.md) 有详细说明。
 
-### 配合 AI 智能体
+### 配合 AI 智能体和其他应用
 
-智能体用方式 B 中的一行命令安装 Strata，然后运行 `strata launch --model NAME --yes --no-tui`。步骤、参数和退出码见
-[docs/AI_SETUP.md](docs/AI_SETUP.md)，仓库规则见 [AGENTS.md](AGENTS.md)。
+智能体用上面的一行命令安装 Strata，然后运行 `strata launch --model NAME --yes --no-tui`。步骤、参数和退出码见
+[docs/AI_SETUP.md](docs/AI_SETUP.md)。给智能体看的仓库规则：[AGENTS.md](AGENTS.md)。
 
-### 连接你的其他应用
-
-| 应用类型 | 基础 URL |
+| 你的应用使用 | 基础 URL |
 | --- | --- |
-| 兼容 OpenAI（大多数应用和智能体） | `http://127.0.0.1:8080/v1`（API 密钥和模型名称随便填） |
-| Anthropic API（Claude Code 等） | `http://127.0.0.1:8080`，不带 `/v1`。这些应用会自己加上 `/v1/messages`。Claude Code：`ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
+| OpenAI API（大多数应用和智能体） | `http://127.0.0.1:8080/v1`（API 密钥和模型名称随便填） |
+| Anthropic API（Claude Code） | `http://127.0.0.1:8080`，不带 `/v1`。Claude Code：`ANTHROPIC_BASE_URL=http://127.0.0.1:8080` |
 | OpenAI Responses API（Codex CLI） | `http://127.0.0.1:8080/v1/responses`（[设置方法](docs/DETAILS.md#the-responses-api-and-codex-cli)） |
 
-`strata connect` 会打印 OpenCode、Codex CLI、Claude Code、oh-my-pi、pi、Hermes Agent 和 OpenClaw 的具体设置。
-`strata connect opencode --write` 会在询问后写入配置文件，并保留备份。
-
-### 图片
-
-能看图片的模型默认开启图片功能。在聊天里附加或粘贴图片，或者从你的应用发送图片。显卡的显存小于 24 GB 时，读图由处理器完成
-（每张图片几秒钟，不占用显卡的显存）；显存达到 24 GB 时，由显卡完成。NVIDIA 和 AMD 的规则相同。你可以按模型关闭图片功能，
-也可以用 `--vision off`、`--vision gpu` 或 `--vision cpu` 选择读图方式。
-
-这条规则背后的数据：在 Radeon AI PRO R9700 上，显卡读一张 260 token 的图片用了 57 ms，处理器用了 3.1 秒。在 16 GB 的显卡
-（Tesla P100 和 RTX A4000，Linux）上，用显卡读图会让文字速度下降 3-5%，因为它占用约 1.4 GB 显存，否则这部分会被模型使用。
-在 Mac 上，无论内存多大，都由 GPU 读图（32 GB 的 M4 上读一张 260 token 的图片用 0.45 秒，占用约 1.2 GB 共享内存）；处理器读一张约需 50 秒，所以只有指定 `--vision cpu` 时才用。
+`strata connect` 会打印 OpenCode、Codex CLI、Claude Code、oh-my-pi、pi、Hermes Agent 和 OpenClaw 的具体设置，
+`strata connect opencode --write` 会帮你写入（并保留备份）。
 
 ### 使用须知
 
-- 在聊天菜单或你的应用的“reasoning effort”里选择思考级别（**off、low、medium 或 high**）。off 最快。
-- Strata 默认一次回答一个请求。要同时处理多个，请在 `strata launch` 中使用 `--parallel N`，或在配置里写
-  `"parallel": 2`（[BATCHING.md](docs/BATCHING.md)）。在 12 GB 显卡上，这会让每个回答变慢。
-- Strata 会完整读取聊天的第一条消息，每 30,000 个 token 约需 1 分钟。之后的消息几秒钟就开始。
-- 聊天记录存放的位置和完整的 API：[docs/INSTALL.md](docs/INSTALL.md#where-things-are-stored)、[docs/DETAILS.md](docs/DETAILS.md#using-it)。
+- **图片**对每个能看图片的模型都是默认开启的。在聊天里附加或粘贴图片，或者从你的应用发送图片。详情：[docs/IMAGES.md](docs/IMAGES.md)。
+- **思考级别**可以是 off、low、medium 或 high，在聊天菜单或你的应用的“reasoning effort”里设置。off 最快。
+- **聊天的第一条消息**会被完整读取，每 30,000 个 token 约需 1 分钟。之后的消息几秒钟就开始。
+- **默认一次处理一个请求。** 要处理更多，请使用 `--parallel N`（[BATCHING.md](docs/BATCHING.md)）。在 12 GB 显卡上，这会让每个回答变慢。
 
 ## 从源码构建
 
@@ -331,12 +296,12 @@ strata doctor                                  # 检查已安装的引擎文件
 - **你的内存是阅览室的书架。** 24,576 本书都在这里。某个词需要一本不在书桌上的书时，处理器会立刻从书架上取来读，显卡则继续工作。
 - **你的固态硬盘是档案室。** 里面存着一张 29 GB 的查找表。模型每个词只读其中几行，所以不用常驻内存。
 
-<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="The model's 24,576 experts: the busiest on the graphics card, all of them in RAM, a lookup table on the SSD"></p>
+<p align="center"><img src="docs/media/how-it-works.svg" width="860" alt="模型的 24,576 位专家：最忙的在显卡上，全部在内存里，查找表在固态硬盘上"></p>
 
 另外有一个小助手会猜接下来的几个词。大模型一次检查所有猜测，保留正确的部分。得到的答案不变，但快了 1.6-1.8 倍。
 长文本按大块读取，一次最多 8,192 个 token，速度超过每秒 1,000 个 token。
 
-<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="A small helper guesses the next words; the big model checks them all at once and keeps the right ones"></p>
+<p align="center"><img src="docs/media/guess-and-check.svg" width="860" alt="小助手猜接下来的几个词；大模型一次检查全部猜测，保留正确的部分"></p>
 
 更详细的解释：[docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md)。每个部分和它的数据：
 [详细说明](docs/DETAILS.md#how-it-works)和[论文](docs/paper/Strata-Paper.pdf)。
@@ -345,24 +310,22 @@ strata doctor                                  # 检查已安装的引擎文件
 
 - **第一次启动 Strata 时我的电脑卡住了。** 它在把模型加载到内存。请等待，不要关闭窗口。10 分钟后还是卡住？重启电脑，
   关闭其他程序后再试，或者选一个更小的尺寸。
-- **下载或安装时中断了。** 重新启动应用或 `strata launch`，或者再运行一次 `START-HERE.bat`（或 `./setup.sh`）。
-  它会从中断的地方继续。
-- **非常慢、硬盘灯一直闪，或者提示“引擎意外停止”。** 你的电脑可用内存不够。关闭其他程序（浏览器很占内存），
+- **下载或安装时中断了。** 重新启动应用或 `strata launch`。它会从中断的地方继续。
+- **非常慢，或者提示“the engine stopped unexpectedly”。** 你的电脑可用内存不够。关闭其他程序（浏览器很占内存），
   或者选一个更小的尺寸，比如 Q2_0 或 IQ2_XS。
 - **提示这台电脑没有可用的引擎。** 在应用里打开**设置，引擎**，点击**更新引擎**。在终端里运行 `strata update`。
-  `strata doctor` 会显示已安装哪些引擎文件。
 - **提示 8080 端口已被占用。** Strata 已经在运行了。找一下它的窗口。
 
-更多问题和解决办法：[docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md)。还是解决不了？请提交
-[issue](https://github.com/Niko1221/Strata/issues)。在应用里，附上**设置，引擎，诊断，查看日志，保存日志**得到的文件。
-在终端里，粘贴 `strata doctor` 的输出。从源码运行时，附上 Strata 文件夹里的 `strata-<model>.log`。
-如果是安全问题，请私下报告：[SECURITY.md](SECURITY.md)。
+更多解决办法：[docs/TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md)。还是解决不了？请提交
+[issue](https://github.com/Niko1221/Strata/issues) 并附上日志：在应用里是**设置，引擎，诊断，保存日志**，在终端里是
+`strata doctor` 的输出。如果是安全问题，请私下报告：[SECURITY.md](SECURITY.md)。
 
 ## 致谢与许可证
 
 模型是 Qwen 团队的 [Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)。压缩工作由
 [ISTA-DASLab](https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF)、UkisAI（Swift 1.5）、agentionai（Gyro）
-和 Unsloth 完成。Strata 使用了 [llama.cpp / ggml](https://github.com/ggml-org/llama.cpp) 的部分代码。全部致谢：
+和 Unsloth 完成。DeepSeek V4.1-Flash 的各个版本也由 ISTA-DASLab 制作。Strata 使用了
+[llama.cpp / ggml](https://github.com/ggml-org/llama.cpp) 的部分代码。全部致谢：
 [docs/HOW_IT_WORKS.md](docs/HOW_IT_WORKS.md#credits)。Strata 以 [MIT 许可证](LICENSE)开源。少数部分和所有模型有各自的许可证
 （[具体是哪些](docs/HOW_IT_WORKS.md#license)）。
 

SECURITY.md

@@ -74,7 +74,7 @@ the model. The section above is about the engine's HTTP server. This is what the
 The Terminal installs with one line:
 
 ```sh
-curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh | sh
+curl -fsSL https://github.com/Niko1221/Strata/releases/latest/download/install.sh -o install.sh && sh install.sh
 irm https://github.com/Niko1221/Strata/releases/latest/download/install.ps1 | iex
 ```
 

apps/desktop/package.json

@@ -1,7 +1,7 @@
 {
   "name": "strata-desktop",
   "productName": "Strata",
-  "version": "0.2.3",
+  "version": "0.2.5",
   "private": true,
   "description": "Strata Desktop - local AI, tuned to one model.",
   "scripts": {

apps/desktop/src-tauri/Cargo.lock

@@ -3524,7 +3524,7 @@ checksum = "ff7589a1859b09232522bb9edf076ca7fcf14ded96685d3fa629db73023ffbb7"
 
 [[package]]
 name = "strata-desktop"
-version = "0.2.3"
+version = "0.2.5"
 dependencies = [
  "gtk",
  "serde",

apps/desktop/src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "strata-desktop"
-version = "0.2.3"
+version = "0.2.5"
 description = "Strata Desktop — local AI, tuned to one model."
 edition = "2021"
 rust-version = "1.77"

apps/host/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "strata",
-  "version": "0.2.3",
+  "version": "0.2.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "strata",
-      "version": "0.2.3",
+      "version": "0.2.5",
       "dependencies": {
         "html-to-image": "^1.11.13",
         "katex": "^0.19.0",

apps/host/package.json

@@ -1,7 +1,7 @@
 {
   "name": "strata",
   "private": true,
-  "version": "0.2.3",
+  "version": "0.2.5",
   "type": "module",
   "description": "Strata \u2014 local AI, tuned to one model. Web shell + engine host.",
   "scripts": {

apps/host/scripts/make-fix-locales.py

@@ -0,0 +1,385 @@
+"""Writes src/locales/fix-<lang>.json: the interface strings that had no key in the locale files (#3479, #3825) and the strings of the 0.2.4.3 bug fixes.
+Run from apps/host:  python scripts/make-fix-locales.py
+The keys are fx01.. in this order; fix-en.json is the English source. Placeholders ({0}, {1}) must be kept in every language."""
+import json
+from pathlib import Path
+
+EN = [
+    "will stop running and be removed.",
+    "Downloaded, not loaded. Open Models to load it.",
+    "{0} lines added, {1} removed",
+    "Edited {0} files",
+    "Drop files to add them",
+    "Pictures and text files",
+    "Keep goal",
+    "Remove goal",
+    "The assistant stops working towards it. Your chat and files stay as they are.",
+    "This model can read pictures, but the engine installed here does not include the picture reader yet, so Read pictures is off. Update the engine in Settings → About to turn it on.",
+    "Showing the values of your tuning '{0}'.",
+    "Your tuning '{0}' sets",
+    "was {0}",
+    "· {0} RAM",
+    "The message was not cancelled",
+    "Extra settings for the program",
+    "Draft it with AI",
+    "Thinking time",
+    "Writing time",
+    "tokens/s",
+    "% of context",
+    "This page asks for files from the internet, which the preview does not load, so it may look incomplete. View code shows exactly what was written.",
+    "Keep A",
+    "Keep B",
+    "Took",
+    "Variation",
+    "Changed",
+    "Nothing",
+    "Both versions are ready. Compare A and B, then keep one.",
+    "The assistant is still answering",
+    "Send your message when it has finished.",
+    "The message was not queued",
+    "Scroll to the latest message",
+    "Remove task",
+    "Start a new conversation; keep this one",
+    "Have the assistant write a plan first; nothing runs until you approve it",
+    "Search the web, read the pages and answer with sources",
+    "Copied",
+    "Response",
+    "Message",
+    "PDF added",
+    "Select the text and copy it with Ctrl+C.",
+    "{0} is in this chat. Ask about it in your next message.",
+]
+
+T = {
+"zh": [
+    "将停止运行并被移除。",
+    "已下载，尚未加载。打开“模型”页面来加载它。",
+    "新增 {0} 行，删除 {1} 行",
+    "已编辑 {0} 个文件",
+    "拖放文件即可添加",
+    "图片和文本文件",
+    "保留目标",
+    "移除目标",
+    "助手将不再朝这个目标工作。你的对话和文件保持不变。",
+    "此模型可以读取图片，但这里安装的引擎还不包含图片读取器，所以“读取图片”已关闭。请在“设置 → 关于”中更新引擎后再开启。",
+    "显示你的调优“{0}”的取值。",
+    "你的调优“{0}”设置了",
+    "原为 {0}",
+    "· {0} 内存",
+    "消息没有被取消",
+    "程序的额外设置",
+    "用 AI 起草",
+    "思考时间",
+    "写作时间",
+    "词元/秒",
+    "% 的上下文",
+    "此页面需要从互联网加载文件，预览不会加载这些文件，所以看起来可能不完整。“查看代码”会显示实际写入的内容。",
+    "保留 A",
+    "保留 B",
+    "用时",
+    "波动",
+    "已更改",
+    "无",
+    "两个版本都已就绪。比较 A 和 B，然后保留其中一个。",
+    "助手仍在回答",
+    "等它回答完再发送你的消息。",
+    "消息没有进入队列",
+    "滚动到最新消息",
+    "移除任务",
+    "开始新对话；保留当前这个",
+    "让助手先写一份计划；在你批准之前不会运行任何内容",
+    "搜索网络、阅读网页，并附上来源作答",
+    "已复制",
+    "回复",
+    "消息",
+    "已添加 PDF",
+    "请选中文字，然后按 Ctrl+C 复制。",
+    "{0} 已在此对话中。请在下一条消息里询问它。",
+],
+"ja": [
+    "は停止され、削除されます。",
+    "ダウンロード済みですが、読み込まれていません。「モデル」を開いて読み込んでください。",
+    "{0} 行追加、{1} 行削除",
+    "{0} 個のファイルを編集しました",
+    "ファイルをドロップして追加",
+    "画像とテキストファイル",
+    "目標を残す",
+    "目標を削除",
+    "アシスタントはこの目標に向けた作業をやめます。チャットとファイルはそのまま残ります。",
+    "このモデルは画像を読めますが、ここにインストールされているエンジンにはまだ画像リーダーが含まれていないため、「画像を読む」はオフです。設定 → 情報 でエンジンを更新するとオンにできます。",
+    "チューニング「{0}」の値を表示しています。",
+    "チューニング「{0}」が設定する項目",
+    "変更前: {0}",
+    "· {0} RAM",
+    "メッセージはキャンセルされませんでした",
+    "プログラムの追加設定",
+    "AI で下書きを作成",
+    "思考時間",
+    "執筆時間",
+    "トークン/秒",
+    "% のコンテキスト",
+    "このページはインターネット上のファイルを必要としますが、プレビューでは読み込まれないため、表示が不完全になることがあります。「コードを表示」で書かれた内容をそのまま確認できます。",
+    "A を残す",
+    "B を残す",
+    "所要時間",
+    "ばらつき",
+    "変更点",
+    "なし",
+    "両方のバージョンの準備ができました。A と B を比べて、どちらかを残してください。",
+    "アシスタントはまだ回答中です",
+    "回答が終わってからメッセージを送ってください。",
+    "メッセージは待機列に入りませんでした",
+    "最新のメッセージへスクロール",
+    "タスクを削除",
+    "新しい会話を始めます。今の会話は残ります",
+    "アシスタントにまず計画を書かせます。承認するまで何も実行されません",
+    "ウェブを検索し、ページを読み、出典付きで回答します",
+    "コピーしました",
+    "返信",
+    "メッセージ",
+    "PDF を追加しました",
+    "テキストを選択して Ctrl+C でコピーしてください。",
+    "{0} をこのチャットに追加しました。次のメッセージで質問してください。",
+],
+"de": [
+    "wird nicht mehr ausgeführt und entfernt.",
+    "Heruntergeladen, aber nicht geladen. Öffne „Modelle“, um es zu laden.",
+    "{0} Zeilen hinzugefügt, {1} entfernt",
+    "{0} Dateien bearbeitet",
+    "Dateien hier ablegen, um sie hinzuzufügen",
+    "Bilder und Textdateien",
+    "Ziel behalten",
+    "Ziel entfernen",
+    "Der Assistent arbeitet nicht mehr darauf hin. Dein Chat und deine Dateien bleiben unverändert.",
+    "Dieses Modell kann Bilder lesen, aber die hier installierte Engine enthält den Bildleser noch nicht, deshalb ist „Bilder lesen“ aus. Aktualisiere die Engine unter Einstellungen → Info, um es einzuschalten.",
+    "Zeigt die Werte deiner Abstimmung „{0}“.",
+    "Deine Abstimmung „{0}“ setzt",
+    "war {0}",
+    "· {0} RAM",
+    "Die Nachricht wurde nicht abgebrochen",
+    "Zusätzliche Einstellungen für das Programm",
+    "Mit KI entwerfen",
+    "Denkzeit",
+    "Schreibzeit",
+    "Token/s",
+    "% des Kontexts",
+    "Diese Seite lädt Dateien aus dem Internet, was die Vorschau nicht tut. Sie kann deshalb unvollständig aussehen. „Code anzeigen“ zeigt genau, was geschrieben wurde.",
+    "A behalten",
+    "B behalten",
+    "Dauer",
+    "Schwankung",
+    "Geändert",
+    "Nichts",
+    "Beide Versionen sind fertig. Vergleiche A und B und behalte eine.",
+    "Der Assistent antwortet noch",
+    "Sende deine Nachricht, wenn er fertig ist.",
+    "Die Nachricht wurde nicht eingereiht",
+    "Zur neuesten Nachricht scrollen",
+    "Aufgabe entfernen",
+    "Neue Unterhaltung beginnen; diese bleibt erhalten",
+    "Der Assistent schreibt zuerst einen Plan; nichts läuft, bis du ihn freigibst",
+    "Im Web suchen, die Seiten lesen und mit Quellen antworten",
+    "Kopiert",
+    "Antwort",
+    "Nachricht",
+    "PDF hinzugefügt",
+    "Markiere den Text und kopiere ihn mit Strg+C.",
+    "{0} ist in diesem Chat. Frag in deiner nächsten Nachricht danach.",
+],
+"es": [
+    "dejará de ejecutarse y se eliminará.",
+    "Descargado, pero no cargado. Abre Modelos para cargarlo.",
+    "{0} líneas añadidas, {1} eliminadas",
+    "{0} archivos editados",
+    "Suelta los archivos para añadirlos",
+    "Imágenes y archivos de texto",
+    "Mantener el objetivo",
+    "Quitar el objetivo",
+    "El asistente deja de trabajar en ello. Tu chat y tus archivos se quedan como están.",
+    "Este modelo puede leer imágenes, pero el motor instalado aquí aún no incluye el lector de imágenes, así que Leer imágenes está desactivado. Actualiza el motor en Ajustes → Acerca de para activarlo.",
+    "Se muestran los valores de tu ajuste «{0}».",
+    "Tu ajuste «{0}» establece",
+    "antes {0}",
+    "· {0} de RAM",
+    "El mensaje no se canceló",
+    "Ajustes adicionales del programa",
+    "Redactar con IA",
+    "Tiempo de pensar",
+    "Tiempo de escribir",
+    "tokens/s",
+    "% del contexto",
+    "Esta página pide archivos de internet, que la vista previa no carga, así que puede verse incompleta. Ver código muestra exactamente lo que se escribió.",
+    "Mantener A",
+    "Mantener B",
+    "Tardó",
+    "Variación",
+    "Cambiado",
+    "Nada",
+    "Las dos versiones están listas. Compara A y B y quédate con una.",
+    "El asistente sigue respondiendo",
+    "Envía tu mensaje cuando termine.",
+    "El mensaje no se puso en cola",
+    "Ir al último mensaje",
+    "Quitar tarea",
+    "Empieza una conversación nueva; esta se conserva",
+    "El asistente escribe primero un plan; no se ejecuta nada hasta que lo apruebes",
+    "Busca en la web, lee las páginas y responde con fuentes",
+    "Copiado",
+    "Respuesta",
+    "Mensaje",
+    "PDF añadido",
+    "Selecciona el texto y cópialo con Ctrl+C.",
+    "{0} está en este chat. Pregunta por él en tu próximo mensaje.",
+],
+"ru": [
+    "перестанет работать и будет удалена.",
+    "Скачана, но не загружена. Откройте «Модели», чтобы загрузить её.",
+    "Добавлено строк: {0}, удалено: {1}",
+    "Изменено файлов: {0}",
+    "Перетащите файлы сюда, чтобы добавить",
+    "Картинки и текстовые файлы",
+    "Оставить цель",
+    "Удалить цель",
+    "Ассистент перестанет работать над ней. Ваш чат и файлы останутся как есть.",
+    "Эта модель умеет читать картинки, но установленный здесь движок пока не содержит модуль чтения картинок, поэтому «Читать картинки» выключено. Обновите движок в разделе «Настройки → О программе», чтобы включить.",
+    "Показаны значения вашей настройки «{0}».",
+    "Ваша настройка «{0}» задаёт",
+    "было {0}",
+    "· {0} ОЗУ",
+    "Сообщение не было отменено",
+    "Дополнительные настройки программы",
+    "Набросать с помощью ИИ",
+    "Время размышления",
+    "Время написания",
+    "токенов/с",
+    "% контекста",
+    "Эта страница запрашивает файлы из интернета, а предпросмотр их не загружает, поэтому она может выглядеть неполной. «Показать код» показывает, что именно было написано.",
+    "Оставить A",
+    "Оставить B",
+    "Заняло",
+    "Разброс",
+    "Изменено",
+    "Ничего",
+    "Обе версии готовы. Сравните A и B и оставьте одну.",
+    "Ассистент ещё отвечает",
+    "Отправьте сообщение, когда он закончит.",
+    "Сообщение не поставлено в очередь",
+    "К последнему сообщению",
+    "Удалить задачу",
+    "Начать новый разговор; этот сохраняется",
+    "Ассистент сначала напишет план; ничего не запустится, пока вы его не одобрите",
+    "Искать в интернете, читать страницы и отвечать со ссылками на источники",
+    "Скопировано",
+    "Ответ",
+    "Сообщение",
+    "PDF добавлен",
+    "Выделите текст и скопируйте его клавишами Ctrl+C.",
+    "{0} добавлен в этот чат. Спросите о нём в следующем сообщении.",
+],
+"pt": [
+    "vai parar de funcionar e será removido.",
+    "Baixado, mas não carregado. Abra Modelos para carregá-lo.",
+    "{0} linhas adicionadas, {1} removidas",
+    "{0} arquivos editados",
+    "Solte os arquivos para adicioná-los",
+    "Imagens e arquivos de texto",
+    "Manter a meta",
+    "Remover a meta",
+    "O assistente deixa de trabalhar nela. Seu chat e seus arquivos continuam como estão.",
+    "Este modelo consegue ler imagens, mas o motor instalado aqui ainda não inclui o leitor de imagens, então Ler imagens está desligado. Atualize o motor em Configurações → Sobre para ligar.",
+    "Mostrando os valores do seu ajuste \"{0}\".",
+    "Seu ajuste \"{0}\" define",
+    "era {0}",
+    "· {0} de RAM",
+    "A mensagem não foi cancelada",
+    "Configurações extras do programa",
+    "Rascunhar com IA",
+    "Tempo de raciocínio",
+    "Tempo de escrita",
+    "tokens/s",
+    "% do contexto",
+    "Esta página pede arquivos da internet, que a visualização não carrega, então pode parecer incompleta. Ver código mostra exatamente o que foi escrito.",
+    "Manter A",
+    "Manter B",
+    "Levou",
+    "Variação",
+    "Alterado",
+    "Nada",
+    "As duas versões estão prontas. Compare A e B e mantenha uma.",
+    "O assistente ainda está respondendo",
+    "Envie sua mensagem quando ele terminar.",
+    "A mensagem não entrou na fila",
+    "Ir para a última mensagem",
+    "Remover tarefa",
+    "Começar uma nova conversa; esta continua salva",
+    "O assistente escreve um plano primeiro; nada roda até você aprovar",
+    "Pesquisar na web, ler as páginas e responder com fontes",
+    "Copiado",
+    "Resposta",
+    "Mensagem",
+    "PDF adicionado",
+    "Selecione o texto e copie com Ctrl+C.",
+    "{0} está neste chat. Pergunte sobre ele na próxima mensagem.",
+],
+"ko": [
+    "실행이 중지되고 제거됩니다.",
+    "다운로드했지만 아직 불러오지 않았습니다. 모델 화면을 열어 불러오세요.",
+    "{0}줄 추가, {1}줄 삭제",
+    "파일 {0}개 편집함",
+    "파일을 놓아서 추가하세요",
+    "그림과 텍스트 파일",
+    "목표 유지",
+    "목표 제거",
+    "어시스턴트가 이 목표를 향한 작업을 멈춥니다. 대화와 파일은 그대로 남습니다.",
+    "이 모델은 그림을 읽을 수 있지만, 여기에 설치된 엔진에는 아직 그림 읽기 기능이 없어서 '그림 읽기'가 꺼져 있습니다. 설정 → 정보에서 엔진을 업데이트하면 켤 수 있습니다.",
+    "튜닝 '{0}'의 값을 보여 줍니다.",
+    "튜닝 '{0}'이(가) 설정하는 항목",
+    "이전 값 {0}",
+    "· RAM {0}",
+    "메시지가 취소되지 않았습니다",
+    "프로그램 추가 설정",
+    "AI로 초안 작성",
+    "생각한 시간",
+    "작성한 시간",
+    "토큰/초",
+    "컨텍스트 %",
+    "이 페이지는 인터넷의 파일을 불러와야 하는데 미리보기는 이를 불러오지 않으므로 불완전하게 보일 수 있습니다. '코드 보기'에서 작성된 내용을 그대로 볼 수 있습니다.",
+    "A 유지",
+    "B 유지",
+    "걸린 시간",
+    "편차",
+    "변경됨",
+    "없음",
+    "두 버전이 모두 준비되었습니다. A와 B를 비교한 뒤 하나를 유지하세요.",
+    "어시스턴트가 아직 답하는 중입니다",
+    "답이 끝나면 메시지를 보내세요.",
+    "메시지가 대기열에 들어가지 않았습니다",
+    "최신 메시지로 이동",
+    "작업 제거",
+    "새 대화를 시작합니다. 이 대화는 그대로 둡니다",
+    "어시스턴트가 먼저 계획을 작성합니다. 승인하기 전에는 아무것도 실행되지 않습니다",
+    "웹을 검색하고 페이지를 읽어 출처와 함께 답합니다",
+    "복사했습니다",
+    "답변",
+    "메시지",
+    "PDF를 추가했습니다",
+    "텍스트를 선택한 뒤 Ctrl+C로 복사하세요.",
+    "{0}이(가) 이 채팅에 있습니다. 다음 메시지에서 물어보세요.",
+],
+}
+
+here = Path(__file__).resolve().parent.parent / "locales" if False else Path(__file__).resolve().parent.parent / "src" / "locales"
+
+
+def write(lang, values):
+    assert len(values) == len(EN), (lang, len(values), len(EN))
+    for source, text in zip(EN, values):
+        assert sorted(__import__("re").findall(r"\{\d+\}", source)) == sorted(__import__("re").findall(r"\{\d+\}", text)), (lang, source, text)
+    data = {f"fx{i + 1:02d}": text for i, text in enumerate(values)}
+    (here / f"fix-{lang}.json").write_text(json.dumps(data, ensure_ascii=False, indent=1) + "\n", encoding="utf-8")
+
+
+write("en", EN)
+for lang, values in T.items():
+    write(lang, values)
+print("written", len(EN), "strings in", len(T) + 1, "languages")

apps/host/scripts/test.mjs

@@ -5,6 +5,12 @@ import {spawn} from 'node:child_process';
 import {resolve} from 'node:path';
 const root=resolve(import.meta.dirname,'..');
 const files=readdirSync(resolve(root,'tests')).filter(name=>name.endsWith('.test.mjs')).sort().map(name=>resolve(root,'tests',name));
-const child=spawn(process.execPath,['--test',...files],{cwd:root,stdio:'inherit'});
+/* Every test file runs against scratch copies of the per-user places the host writes to (the owner's real profile is never touched). */
+import {mkdtempSync} from 'node:fs';
+import {tmpdir} from 'node:os';
+import {join} from 'node:path';
+const scratch=mkdtempSync(join(tmpdir(),'strata-host-suite-profile-'));
+const env={...process.env,STRATA_SETTINGS_FILE:join(scratch,'app-settings.json'),STRATA_COMPONENTS_DIR:join(scratch,'components'),LOCALAPPDATA:join(scratch,'Local'),APPDATA:join(scratch,'Roaming'),XDG_DATA_HOME:join(scratch,'xdg-data'),XDG_STATE_HOME:join(scratch,'xdg-state'),XDG_CONFIG_HOME:join(scratch,'xdg-config')};
+const child=spawn(process.execPath,['--test',...files],{cwd:root,stdio:'inherit',env});
 child.on('error',error=>{console.error(error.message);process.exitCode=1;});
 child.on('exit',(code,signal)=>{process.exitCode=code??(signal?1:0);});

apps/host/server/bundled-engine.mjs

@@ -234,3 +234,55 @@ export async function installBundledEngine({ bundleDir, components, platform = n
     return { action: 'refused', reason: error?.message ?? String(error) };
   }
 }
+
+/**
+ * After an update from an installer that carried an engine (a per-GPU build), its `engine-bundle` folder is still in the install folder
+ * (about 570 MB) although the engine was copied to the engine store long ago. It is removed only when EVERY package in it exists complete in
+ * the store (every file there with the size and SHA-256 its manifest lists); otherwise it stays and one line says why.
+ * Returns { removed: bool, reason?: string, packages?: number }; never throws.
+ */
+export async function removeVerifiedBundle({ bundleDir, components, log = () => {} } = {}) {
+  try {
+    if (!bundleDir || !components || !existsSync(bundleDir)) return { removed: false, reason: 'no bundle' };
+    // Files inside a signed macOS app must stay intact after installation.
+    if (process.platform === 'darwin' && resolve(bundleDir).split(sep).some(part => part.toLowerCase().endsWith('.app'))) return keepBundle(log, 'macOS app bundles must remain unchanged after signing');
+    const packages = [];
+    for (const entry of await readdir(bundleDir, { withFileTypes: true })) {
+      if (!entry.isDirectory()) continue;
+      const folder = join(bundleDir, entry.name);
+      const manifest = await readManifest(folder);
+      packages.push({ folder, manifest, name: entry.name });
+    }
+    if (!packages.length) return { removed: false, reason: 'nothing in the bundle' };
+    const store = join(components, 'engine');
+    const stored = existsSync(store) ? (await readdir(store, { withFileTypes: true })).filter(e => e.isDirectory() && !e.name.startsWith('.')).map(e => join(store, e.name)) : [];
+    for (const pkg of packages) {
+      if (!pkg.manifest) return keepBundle(log, `${pkg.name} has no readable manifest`);
+      let found = false;
+      for (const candidate of stored) {
+        const theirs = await readManifest(candidate);
+        if (!theirs || theirs.version !== pkg.manifest.version || theirs.platform !== pkg.manifest.platform || theirs.backend !== pkg.manifest.backend
+          || (theirs.variant ?? '') !== (pkg.manifest.variant ?? '') || (theirs.build_id ?? '') !== (pkg.manifest.build_id ?? '')) continue;
+        if (await packageIsWhole(candidate, pkg.manifest, { deep: true })) { found = true; break; }
+      }
+      if (!found) return keepBundle(log, `${pkg.name} is not (or not completely) in the engine store`);
+    }
+    for (const pkg of packages) await rm(pkg.folder, { recursive: true, force: true });
+    log(`engine bundle: the copy that came with the installer (${packages.map(p => p.name).join(', ')}) was removed; the same engine is complete in the engine store`);
+    return { removed: true, packages: packages.length };
+  } catch (error) {
+    return keepBundle(log, `could not be checked (${error?.message ?? error})`);
+  }
+}
+function keepBundle(log, why) {
+  log(`engine bundle: kept in the install folder (${why})`);
+  return { removed: false, reason: why };
+}
+
+/**
+ * What the host does once its engine step has settled: for an engine that is (or was) there, look at the install folder's leftover bundle.
+ * The lines go to the host's output (console.log), which the desktop shell copies to its log file (`[host] engine bundle: ...`).
+ */
+export function cleanupAfterInstall(settled, { bundleDir, components, log = line => console.log(line) } = {}) {
+  return Promise.resolve(settled).then(result => (['installed', 'kept', 'repaired'].includes(result?.action) ? removeVerifiedBundle({ bundleDir, components, log }) : null), () => null);
+}

apps/host/server/control-runtime.mjs

@@ -183,6 +183,12 @@ export function createControl({ control = findControl(), env = process.env, run
       if (failed) throw Object.assign(new ControlError(failed.error, { exitCode: failed.exit_code ?? result.code, output: result.json }), { code: result.code === 7 ? 'engine_serving' : 'update_failed' });
       throw failure(result, 'The update failed.');
     },
+    /** Install an engine package the person downloaded and chose (the offline path): no network; Control checks the package's own signature. */
+    async installEngineFile(path, { onEvent = null, signal = null } = {}) {
+      const result = await call(['components', 'install-file', path, '--output', 'jsonl'], { timeoutMs: 3600_000, onLine: onEvent ?? (() => {}), signal });
+      if (result.json?.ok) return { ok: true, results: [result.json] };
+      throw failure(result, 'This file could not be installed.');
+    },
     async rollbackEngine() {
       const result = await call(['components', 'rollback', '--output', 'json'], { timeoutMs: 120_000 });
       if (result.json?.ok) return result.json;

apps/host/server/device-probes.mjs

@@ -1,6 +1,7 @@
 /** Physical topology and GPU sensors; unavailable values stay null. */
 import { readFile, readdir, realpath } from 'node:fs/promises';
 import { probe, round } from './util.mjs';
+import { windowsGpuReading } from './windows-gpu.mjs';
 
 /** Unified GPUs share one system memory pool; dedicated GPUs each have their own. */
 export function gpuMemoryTotals(devices, readings) {
@@ -83,6 +84,10 @@ export async function readGpuTelemetry(gpus) {
   return Promise.all(gpus.map(async gpu=>{
     let reading=nvidia.get(gpu.id)??{id:gpu.id??`${gpu.vendor}:${gpu.index}`,temperatureC:null,utilizationPct:null,memoryUsedGb:null,powerW:null,powerLimitW:null,pcieGen:null,pcieGenMax:null,pcieWidth:null,pcieRxMbs:null};
     if(gpu.vendor==='nvidia')reading={...reading,pcieRxMbs:transfer.get(gpu.sensorIndex??gpu.index)??null};
+    if(gpu.luid&&!nvidia.has(gpu.id)) {
+      const counters=windowsGpuReading(gpu.luid);
+      if(counters)reading={...reading,utilizationPct:counters.utilizationPct,memoryUsedGb:round(counters.memoryUsedGb,2)};
+    }
     if(gpu.sensorPath&&!nvidia.has(gpu.id)) {
       let temperature=null,power=null,powerLimit=null;
       for(const hwmon of await list(`${gpu.sensorPath}/hwmon`)) {

apps/host/server/folder-dialog.mjs

@@ -62,7 +62,10 @@ export function watchedWindowsDialog(shell, args, { readyMs = 30_000, openMs = 2
     const later = () => { clearTimeout(timer); ready = true; setTimeout(() => end(resolve, { stdout: '' }), openMs).unref?.(); };
     child.stdout?.on('data', chunk => { stdout += chunk; if (!ready && /^READY\s*$/m.test(stdout)) { clearTimeout(timer); later(); } });
     child.on('error', error => end(reject, error));
-    child.on('close', code => { if (settled) return; settled = true; clearTimeout(timer); code === 0 ? resolve({ stdout }) : reject(Object.assign(new Error('exit ' + code), { code })); });
+    child.on('close', code => { if (settled) return; settled = true; clearTimeout(timer);
+      // PowerShell ended before its window opened (security software ended it, #3831): the person types the path instead.
+      if (!ready) return resolve({ noDialog: true });
+      code === 0 ? resolve({ stdout }) : reject(Object.assign(new Error('exit ' + code), { code })); });
   });
 }
 

apps/host/server/hardware.mjs

@@ -12,6 +12,7 @@ import { CONTEXT_TOKENS, VARIANTS, footprint } from './catalog.mjs';
 import { MODELS_DIR, diskFreeGb, diskTotalGb } from './store.mjs';
 import { probe, round } from './util.mjs';
 import { utf8Script } from './powershell-utf8.mjs';
+import { DX_ADAPTERS_SCRIPT, parseDxAdapters, windowsOtherGpus } from './windows-gpu.mjs';
 
 let cached = null;
 let cachedAt = 0;
@@ -187,11 +188,12 @@ async function detectGpus(platform, totalGb) {
   }
   if(platform==='win32') {
     const raw=await probe('powershell.exe',['-NoProfile','-NonInteractive','-Command',utf8Script('Get-CimInstance Win32_VideoController | Select-Object Name,PNPDeviceID | ConvertTo-Json -Compress')]);
-    try {const parsed=JSON.parse(raw);for(const row of Array.isArray(parsed)?parsed:[parsed]) {
-      if(!row?.Name||(/nvidia/i.test(row.Name)&&gpus.some(g=>g.vendor==='nvidia')))continue;
-      const vendor=/amd|radeon/i.test(row.Name)?'amd':/intel/i.test(row.Name)?'intel':'unknown';
-      gpus.push({id:String(row.PNPDeviceID),index:gpus.length,vendor,name:row.Name,vramGb:0,unified:false,backend:'vulkan'});
-    }}catch{}
+    try {
+      const parsed=JSON.parse(raw);
+      const rows=(Array.isArray(parsed)?parsed:[parsed]).filter(row=>row?.Name&&!(/nvidia/i.test(row.Name)&&gpus.some(g=>g.vendor==='nvidia')));
+      const dx=rows.length?parseDxAdapters(await probe('powershell.exe',['-NoProfile','-NonInteractive','-Command',DX_ADAPTERS_SCRIPT],8000)):[];
+      for(const card of windowsOtherGpus(rows,dx))gpus.push({...card,index:gpus.length,unified:false,backend:'vulkan'});
+    }catch{}
   }
   gpus.forEach((g,i)=>{g.index=i;});
 

apps/host/server/index.mjs

@@ -32,7 +32,8 @@ import { findBrowser, findPlaywrightMcp } from './agent/browser-probe.mjs';
  */
 import http from 'node:http';
 import { homedir } from 'node:os';
-import { cpSync, createReadStream, existsSync, mkdirSync, readFileSync, readdirSync, rmSync, statSync, writeFileSync } from 'node:fs';
+import { statfsSync, cpSync, createReadStream, createWriteStream, existsSync, mkdirSync, readFileSync, readdirSync, rmSync, statSync, writeFileSync } from 'node:fs';
+import { pipeline } from 'node:stream/promises';
 import { spawn } from 'node:child_process';
 import { execFile } from 'node:child_process';
 import { promisify } from 'node:util';
@@ -61,7 +62,7 @@ import { createForkTimeskip } from './timeskip-fork.mjs';
 import { prepareOversized } from './oversize.mjs';
 import { createChatFolders, chatRootOf, openFile, resolveChatFile, previewFile, rawFile, createAttachments, withAttachments } from './chat-files.mjs';
 import { createLlmProxy, samplingFromExpert } from './agent/llm-shape.mjs';
-import { checkUpdates, checkComponentUpdates } from './updates.mjs';
+import { checkUpdates, checkComponentUpdates, engineFirstRun } from './updates.mjs';
 import { plainNoModel } from './no-model-text.mjs';
 import { createAppUi } from './app-ui.mjs';
 import { appVersionFrom, appVersionToShow } from './app-version.mjs';
@@ -69,7 +70,7 @@ import { createImageModels } from './image-models.mjs';
 import { createRuntimeModels } from './runtime-models.mjs';
 import { createNativeControl } from './native-control.mjs';
 import { nativeUnloadPlan } from './storage-check.mjs';
-import { installBundledEngine } from './bundled-engine.mjs';
+import { installBundledEngine, cleanupAfterInstall } from './bundled-engine.mjs';
 import { findControl, createControl, componentsDirectory } from './control-runtime.mjs';
 import { forbidden as acquisitionForbidden } from './acquisition.mjs';
 import { randomBytes, timingSafeEqual } from 'node:crypto';
@@ -130,6 +131,9 @@ const appUpdater = appUi.updater;
 const bundledEngine = control && !process.env.STRATA_NO_BUNDLED_ENGINE
   ? installBundledEngine({ bundleDir: process.env.STRATA_ENGINE_BUNDLE_DIR || resolve(HERE, '..', '..', 'engine-bundle'), components: componentsDirectory(), log: line => console.log(line) })
   : Promise.resolve({ action: 'none' });
+const engineBundleDir = process.env.STRATA_ENGINE_BUNDLE_DIR || resolve(HERE, '..', '..', 'engine-bundle');
+/* An update from a per-GPU installer leaves its engine-bundle behind; it goes only when the same engine is complete in the store (sizes and hashes). */
+cleanupAfterInstall(bundledEngine, { bundleDir: engineBundleDir, components: componentsDirectory() });
 let bundledEngineSettled = !(control && !process.env.STRATA_NO_BUNDLED_ENGINE);
 bundledEngine.then(() => { bundledEngineSettled = true; }, () => { bundledEngineSettled = true; });
 /* A build made for another make of graphics card is not unpacked; Control's answer then carries the plain sentence (with the right download) instead of its own. */
@@ -1022,11 +1026,11 @@ async function api(req, res, path, method, url) {
   if(nativeOperation&&method==='POST')return json(res,200,await native.cancel(nativeOperation[1]));
   const nativeInstance=/^\/api\/native\/instances\/([a-z0-9-]+)\/(unload|default)$/.exec(path);
   if(nativeInstance&&method==='POST')return json(res,200,nativeInstance[2]==='unload'?await native.unload(nativeInstance[1]):native.setDefault(nativeInstance[1]));
-  const nativeSettings=/^\/api\/native\/models\/([a-z0-9_-]+)\/settings$/.exec(path);
+  const nativeSettings=/^\/api\/native\/models\/([a-z0-9_.-]+)\/settings$/.exec(path);
   /* Expert mode shows what will actually run: the saved tuning's values come with the settings (null when none applies or unreadable). */
   if(nativeSettings&&method==='GET'){const settings=native.settings(nativeSettings[1]);let tuned=null;try{const t=await native.tuneEffective({model:nativeSettings[1],resourceProfile:url.searchParams.get('resourceProfile')||undefined,vision:url.searchParams.get('vision')||undefined});tuned=t.applied?t:null;}catch{tuned=null;}return json(res,200,{...settings,tuned});}
   if(nativeSettings&&method==='PATCH')return json(res,200,native.save(nativeSettings[1],await readBody(req)));
-  const nativeSettingsFile=/^\/api\/native\/models\/([a-z0-9_-]+)\/settings-file$/.exec(path);
+  const nativeSettingsFile=/^\/api\/native\/models\/([a-z0-9_.-]+)\/settings-file$/.exec(path);
   if(nativeSettingsFile&&method==='GET')return json(res,200,native.settingsFile(nativeSettingsFile[1]));
   if(nativeSettingsFile&&method==='POST')return json(res,200,await native.openSettingsFile(nativeSettingsFile[1]));
 
@@ -1327,6 +1331,27 @@ async function api(req, res, path, method, url) {
   }
 
   if (path === '/api/setup' && method === 'GET') return json(res, 200, setupState());
+  if (path === '/api/engine/first-run' && method === 'GET') {
+    if (!control?.updateCheck) return json(res, 200, { status: 'unavailable', gpus: [] });
+    const info = await engineFirstRun({ control, gpus: hardware.cachedHardware()?.gpus ?? [] });
+    try { let at = componentsDirectory(); while (at && !existsSync(at) && dirname(at) !== at) at = dirname(at); const f = statfsSync(at); info.freeBytes = Number(f.bavail) * Number(f.bsize); } catch { /* unknown: no warning */ }
+    return json(res, 200, info);
+  }
+  if (path === '/api/engine/job' && method === 'GET') {
+    // The newest engine download / file install, read without waiting for the native snapshot to connect (the first-run card needs it before that).
+    const kinds = ['update-engine', 'install-engine-file'];
+    return json(res, 200, { job: native.state().jobs.filter(j => kinds.includes(j.kind)).slice(-1)[0] ?? null });
+  }
+  if (path === '/api/engine/from-file' && method === 'POST') {
+    // The person chose an engine package in the page (the offline path). The bytes come here; Control checks and installs them.
+    const name = String(req.headers['x-file-name'] ?? 'engine.tar.gz').replace(/[^A-Za-z0-9._-]/g, '_').slice(-120);
+    if (!/\.(tar\.gz|tgz|tar\.xz|zip)$/i.test(name)) return error(res, 400, 'This is not a Strata engine package. Choose the .tar.gz or .zip file from the release page.');
+    const folder = join(store.DATA_DIR, 'incoming-engine');
+    mkdirSync(folder, { recursive: true, mode: 0o700 });
+    const target = join(folder, name);
+    await pipeline(req, createWriteStream(target, { mode: 0o600 }));
+    return json(res, 202, native.operation('install-engine-file', { path: target }));
+  }
   if (path === '/api/updates/check' && method === 'GET' && control?.updateCheck) return json(res, 200, await checkComponentUpdates({ control, appUpdater, appVersion: process.env.STRATA_APP_VERSION || null }));
   if (path === '/api/updates/check' && method === 'GET') return json(res, 200, await checkUpdates({ appVersion:appVersionToShow(setupState().app.version,native.state().version), engineVersion:native.state().available?(native.state().installed?.engine?.version??null):(await engine.config()).engine.version }));
 

apps/host/server/missing-files.mjs

@@ -5,15 +5,15 @@
  */
 import { basename } from 'node:path';
 
-const PART_WORDS = { engine: 'the engine program', 'tokenizer/vocab.json': 'the tokenizer', 'tokenizer/merges.txt': 'the tokenizer', 'tokenizer/token_type.json': 'the tokenizer' };
+const PART_WORDS = { engine: 'the engine program', 'component:strata-engine': 'the engine program', 'tokenizer/vocab.json': 'the tokenizer', 'tokenizer/merges.txt': 'the tokenizer', 'tokenizer/token_type.json': 'the tokenizer' };
 
 /** Short readable names, no duplicates, most useful first. */
 export function missingNames(controlParts, installerFiles) {
   const names = [];
   const add = text => { const t = String(text ?? '').trim(); if (t && !names.includes(t)) names.push(t); };
-  for (const file of Array.isArray(installerFiles) ? installerFiles : []) add(basename(String(file).split(String.fromCharCode(92)).join('/')));
+  for (const file of Array.isArray(installerFiles) ? installerFiles : []) { const name = basename(String(file).split(String.fromCharCode(92)).join('/')); add(PART_WORDS[name] ?? name); }
   for (const item of Array.isArray(controlParts) ? controlParts : []) {
-    add(PART_WORDS[item?.part] ?? item?.file ?? item?.part);
+    add(PART_WORDS[item?.part] ?? PART_WORDS[item?.file] ?? item?.file ?? item?.part);
   }
   return names;
 }

apps/host/server/native-control.mjs

@@ -25,7 +25,7 @@ import { friendlyModelName } from './model-names.mjs';
 import { parseSaved as parseRoles, mirror as mirrorRoles } from './gpu-roles.mjs';
 
 const ROOT=resolve(dirname(fileURLToPath(import.meta.url)),'..');
-const safeId=value=>typeof value==='string'&&/^[a-z0-9_-]{1,80}$/i.test(value);
+const safeId=value=>typeof value==='string'&&/^[a-z0-9](?:[a-z0-9_-]|\.(?!\.)){0,79}$/i.test(value);   /* a dot inside the name: deepseek-v4.1-flash-ist-das-2.00bpw */
 const busy=requests=>requests.some(r=>['queued','generating'].includes(r.state));
 function readJson(path,fallback={}){try{return JSON.parse(readFileSync(path,'utf8').replace(/^\uFEFF/,''));}catch{return fallback;}}
 
@@ -38,7 +38,13 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
  let child=null,seq=0,buffer='',pending=new Map(),definitions=[],refreshing=null,lastRead=0,connecting=null;
  let snapshot={available:false,repo:preferences.repo,summary:'Connect a local Strata installation.',catalog:null,installed:null,hardware:null,error:null};
  const instances=new Map(),processes=new Map(),jobs=new Map(),logs=[];
- const savedJobs=readJson(join(directory,'native-jobs.json'),[]);for(const j of (Array.isArray(savedJobs)?savedJobs:[]).slice(-12))jobs.set(j.id,{...j,...(j.state==='running'?{state:'error',error:'The host restarted before completion. Check diagnostics, then retry; completed files are kept.',summary:'Interrupted operation'}:{})});
+ const savedJobs=readJson(join(directory,'native-jobs.json'),[]);/* An app update ends the app on purpose: the installer replaces it and starts it again. The job that asked for it was saved as running together with the app version it started from (appUpdateFrom); a start that finds a different version knows the update finished, instead of calling it an interrupted operation. */
+ const thisAppVersion=()=>process.env.STRATA_APP_VERSION||null;
+ /* A record an OLDER host wrote (no appUpdateFrom): the app's own program file was replaced after the job began, so the installer finished. <install>/host/server is ROOT's parent chain: ROOT = <install>/host. */
+ const appProgramNewerThan=started=>{try{const t=Date.parse(started);if(!Number.isFinite(t))return false;const dir=dirname(ROOT),exe=join(dir,process.platform==='win32'?'strata-desktop.exe':'strata-desktop'),times=[];for(const f of [exe,join(dir,'uninstall.exe')])if(existsSync(f)){const st=statSync(f);times.push(st.mtimeMs,st.ctimeMs);}/* the installer keeps the build time as the program's modified time but writes uninstall.exe and changes the program file's metadata when it installs */return times.some(x=>x>t);}catch{return false;}};
+ const settledByAppUpdate=j=>j.state==='running'&&j.kind==='update-strata'&&((typeof j.appUpdateFrom==='string'&&!!thisAppVersion()&&thisAppVersion()!==j.appUpdateFrom)||(typeof j.appUpdateFrom!=='string'&&appProgramNewerThan(j.startedAt)));
+ const neverFinishedAppUpdate=j=>j.state==='running'&&j.kind==='update-strata'&&typeof j.appUpdateFrom==='string'&&!!thisAppVersion()&&thisAppVersion()===j.appUpdateFrom;
+ for(const j of (Array.isArray(savedJobs)?savedJobs:[]).slice(-12))jobs.set(j.id,{...j,...(settledByAppUpdate(j)?{state:'done',error:null,summary:`Strata is updated to ${thisAppVersion()}.`,finishedAt:new Date().toISOString()}:neverFinishedAppUpdate(j)?{state:'error',error:`The update to ${j.appUpdateTo??'the new version'} did not finish: the app closed for the installer, but the old version ${j.appUpdateFrom} started again. Try Update again, or download the installer from the Strata release page (https://github.com/Niko1221/Strata/releases/latest).`,summary:'The app update did not finish',finishedAt:new Date().toISOString()}:j.state==='running'?{state:'error',error:'The host restarted before completion. Check diagnostics, then retry; completed files are kept.',summary:'Interrupted operation'}:{})});
  /* Packaged mode: the app ships Strata Control (control-runtime.mjs). Models are run configs in an install folder, the engine
     comes from the component folder, and a start is `strata runtime start` under the owner runtime. Nothing is installed,
     updated or fetched from here. Without `control` (a source checkout) every path below is the original one. */
@@ -50,6 +56,9 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
     The install only runs when the user clicks Download; starting and serving (control.start) keep STRATA_NO_ACQUIRE. */
  const defaultInstall=()=>process.env.STRATA_INSTALL_DIR?resolve(process.env.STRATA_INSTALL_DIR):join(dirname(componentsDirectory()),'install');
  let packagedInstall=null;
+ /* The component updates and the rollback go through Control, not through the native snapshot, so they work in the first seconds after the app starts and on a PC that has no engine yet. */
+ const COMPONENT_KINDS=['update-engine','update-strata','rollback','install-engine-file'];
+ const updateLog=line=>{try{console.log(`update · ${line}`);}catch{/* no console */}};
  const NO_INSTALL='Installing, updating, tuning with calibration or rolling back model files and engines happens from the Terminal (strata install), never while the app runs.';
  let defaultId=null,timer=null,closing=false,polling=false;
  const emit=()=>{const value=state();writeFileSync(join(directory,'native-jobs.json'),JSON.stringify(value.jobs),{mode:0o600});changed(value);};
@@ -71,13 +80,13 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
     app is reinstalled to another folder, or an update moves Control, those absolute paths point at nothing and every installed
     model breaks. At every read of the installed models, a path that ends up inside a folder called `control` that no longer
     exists is pointed at the Control this app has now, when the file is there. The config is saved (with a .bak) only then. */
- function repairControlPaths(dir){if(!packaged||!dir||!existsSync(dir))return;let names=[];try{names=readdirSync(dir).filter(n=>/^strata-[a-z0-9_-]+\.json$/i.test(n));}catch{return;}
+ function repairControlPaths(dir){if(!packaged||!dir||!existsSync(dir))return;let names=[];try{names=readdirSync(dir).filter(n=>/^strata-[a-z0-9_.-]+\.json$/i.test(n));}catch{return;}
   const here=control.control.dir,inside=/^(.+?[\/]control)(?=[\/]|$)(.*)$/i;
   const fix=value=>{if(typeof value!=='string')return value;const m=value.match(inside);if(!m||existsSync(value)||resolve(m[1]).toLowerCase()===resolve(here).toLowerCase())return value;const candidate=join(here,m[2]);return existsSync(candidate)?candidate:value;};
   for(const name of names){const path=join(dir,name),config=readJson(path,null);if(!config||typeof config!=='object')continue;
    const next={...config,...(config.cwd!==undefined?{cwd:fix(config.cwd)}:{}),...(Array.isArray(config.args)?{args:config.args.map(fix)}:{})};
    if(JSON.stringify(next)!==JSON.stringify(config)){try{writeModelConfig(path,next);}catch{/* read-only folder: the load reports it */}}}}
- function installedInfo(info){if(!info)return info;return {...info,models:(info.models??[]).map(entry=>{const cfg=/^strata-[a-z0-9_-]+\.json$/i.test(entry.config??'')?readJson(entry.configPath??join(repo(),entry.config)):{};const at=cfg.args?.indexOf('--native')??-1,nativeFile=at>=0?cfg.args[at+1]:null;const dataFolder=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))==='models'?dirname(dirname(dirname(nativeFile))):info.data_folder;/* A model the person pointed at their own GGUF folder (not <data>/models/<tag>): remembered, so a later load runs setup with that folder again instead of downloading the files (#3199). */const ownGgufDir=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))!=='models'&&existsSync(nativeFile)?dirname(nativeFile):undefined;return {...entry,ownGgufDir,diskGb:entry.diskGb??entry.disk_gb,diskBytes:entry.diskBytes??entry.disk_bytes,sharedBytes:entry.sharedBytes??entry.shared_bytes,removableGb:entry.removableGb??entry.removable_gb,dataFolder,visionPrepared:!!cfg.vision,/* The picture files are prepared when the run config has a vision section: the Models screen then loads straight away instead of running setup again (it used to read 'off' for every model, which sent every load of a picture-capable model through "Apply settings and load", and setup writes the arguments, the draft layer and the reader back each time). */images:cfg.vision?'yes':'off',draftLayer:cfg.mtp!==false,drafting:cfg.drafting??'auto',/* Picture reading is ON unless the person turned it off: no saved choice and not loaded is undefined, not false (owner rule: pictures on by default). */visionEnabled:cfg.ui_vision_enabled??(()=>{const running=[...instances.values()].find(i=>i.model===entry.model&&i.status==='ready');return running?!!running.vision:undefined;})(),visionDevice:cfg.ui_vision_device,resourceProfile:cfg.ui_resource_profile,lowRamMode:cfg.args?.includes('--resident-experts')?'resident':cfg.args?.includes('--mmap-experts')?'mmap':'auto'};})};}
+ function installedInfo(info){if(!info)return info;return {...info,models:(info.models??[]).map(entry=>{const cfg=/^strata-[a-z0-9_.-]+\.json$/i.test(entry.config??'')?readJson(entry.configPath??join(repo(),entry.config)):{};const at=cfg.args?.indexOf('--native')??-1,nativeFile=at>=0?cfg.args[at+1]:null;const dataFolder=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))==='models'?dirname(dirname(dirname(nativeFile))):info.data_folder;/* A model the person pointed at their own GGUF folder (not <data>/models/<tag>): remembered, so a later load runs setup with that folder again instead of downloading the files (#3199). */const ownGgufDir=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))!=='models'&&existsSync(nativeFile)?dirname(nativeFile):undefined;return {...entry,ownGgufDir,diskGb:entry.diskGb??entry.disk_gb,diskBytes:entry.diskBytes??entry.disk_bytes,sharedBytes:entry.sharedBytes??entry.shared_bytes,removableGb:entry.removableGb??entry.removable_gb,dataFolder,visionPrepared:!!cfg.vision,/* The picture files are prepared when the run config has a vision section: the Models screen then loads straight away instead of running setup again (it used to read 'off' for every model, which sent every load of a picture-capable model through "Apply settings and load", and setup writes the arguments, the draft layer and the reader back each time). */images:cfg.vision?'yes':'off',draftLayer:cfg.mtp!==false,drafting:cfg.drafting??'auto',/* Picture reading is ON unless the person turned it off: no saved choice and not loaded is undefined, not false (owner rule: pictures on by default). */visionEnabled:cfg.ui_vision_enabled??(()=>{const running=[...instances.values()].find(i=>i.model===entry.model&&i.status==='ready');return running?!!running.vision:undefined;})(),visionDevice:cfg.ui_vision_device,resourceProfile:cfg.ui_resource_profile,lowRamMode:cfg.args?.includes('--resident-experts')?'resident':cfg.args?.includes('--mmap-experts')?'mmap':'auto'};})};}
  function installRoot(){const found=[preferences.installDir].find(d=>d&&existsSync(d));if(found)return realpathSync(found);mkdirSync(defaultInstall(),{recursive:true});return realpathSync(defaultInstall());}
  /* The settings file Strata Control and the installer read (control-runtime.mjs sets STRATA_SETTINGS_FILE to it): the app's data folder is written there. */
  function controlSettingsFile(){return process.env.STRATA_SETTINGS_FILE||join(dirname(componentsDirectory()),'app-settings.json');}
@@ -134,15 +143,15 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
  }
  function configure({repository}){if(packaged){if(instances.size||[...jobs.values()].some(j=>j.state==='running'))throw new Error('Unload models and finish operations before changing the installation.');const next=realpathSync(String(repository));if(!statSync(next).isDirectory())throw new Error('Choose the folder that holds your Strata model configurations.');preferences={...preferences,installDir:next};packagedInstall=null;disconnect();writeFileSync(settingsPath,JSON.stringify(preferences,null,2),{mode:0o600});lastRead=0;return refresh(true);}if(instances.size||[...jobs.values()].some(j=>j.state==='running'))throw new Error('Unload models and finish operations before changing the installation.');const next=realpathSync(String(repository));const old=preferences;preferences={...preferences,repo:next};try{repo();}catch(e){preferences=old;throw e;}disconnect();writeFileSync(settingsPath,JSON.stringify(preferences,null,2),{mode:0o600});lastRead=0;return refresh(true);}
  function setDownloadDirectory(input,{insideJob=false}={}){if(!insideJob&&[...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish the current operation before changing the folder.');if(typeof input!=='string'||!input.trim()||/[\r\n\0]/.test(input))throw new Error('Choose a model folder.');let path;try{path=realpathSync(input.trim());}catch{throw new Error('That folder does not exist. Check the path, or that the drive is connected.');}if(!statSync(path).isDirectory())throw new Error('Choose a folder, not a file.');/* A whole drive (D:\) is not filled with models: D:\Strata is made and used. */if(isDriveRoot(path)){const own=dataFolderFromPick(path).path;makeFolder(own);path=realpathSync(own);}try{accessSync(path,constants.R_OK|constants.W_OK);}catch{throw new Error('Strata cannot write in that folder. Choose a folder you can save files in.');}preferences={...preferences,downloadDirectory:path};/* the same choice for the installer and the Terminal: the Control settings file */if(packaged)rememberDataFolder(controlSettingsFile(),path,Date.now()/1000,true);writeFileSync(settingsPath,JSON.stringify(preferences,null,2),{mode:0o600});shareDataFolder();emit();return state();}
- function recordFile(model){if(!safeId(model))throw new Error('Choose an installed model.');const entry=snapshot.installed?.models?.find(i=>i.model===model);if(!entry)throw new Error('This model is not installed. Download and prepare it first.');const path=realpathSync(entry.configPath??join(repo(),entry.config));if(dirname(path)!==repo()||!/^strata-[a-z0-9_-]+\.json$/i.test(basename(path)))throw new Error('The model configuration is outside the Strata installation.');return {entry,path};}
+ function recordFile(model){if(!safeId(model))throw new Error('Choose an installed model.');const entry=snapshot.installed?.models?.find(i=>i.model===model);if(!entry)throw new Error('This model is not installed. Download and prepare it first.');const path=realpathSync(entry.configPath??join(repo(),entry.config));if(dirname(path)!==repo()||!/^strata-[a-z0-9_.-]+\.json$/i.test(basename(path)))throw new Error('The model configuration is outside the Strata installation.');return {entry,path};}
  function record(model){const {entry,path}=recordFile(model);return {entry,path,config:readJson(path)};}
  /* The text file a power user edits by hand: where it is and what is wrong in it (run-config-check.mjs). */
  function settingsFile(model){const {path}=recordFile(model);return {model,path,name:basename(path),...checkRunConfig(readFileSync(path,'utf8')),note:'Changes you make in the file apply the next time the model starts.'};}
  async function openSettingsFile(model,options={}){const info=settingsFile(model);await openTextFile(info.path,options);return info;}
  /* A mistake in the file holds the start back with the line, instead of an engine that dies on it. Warnings (an unknown key) never do. */
  function assertSettingsFile(path){const check=checkRunConfig(readFileSync(path,'utf8'));if(!check.ok)throw new Error(`The settings file for this model has a mistake, so the model was not started. ${describeIssues(check.issues,'error').join(' ')}`);}
- function settings(model){const {config}=record(model);const values=Object.fromEntries(NATIVE_FIELDS.map(f=>[f.id,config[f.id]??null]));if(typeof values.aliases==='string')values.aliases=values.aliases.split(',').map(v=>v.trim()).filter(Boolean);values.sampling=config.sampling??{};values.args=config.args??[];values.env=publicNativeEnv(config.env??{});return {model,values,mcp:publicMcpServers(config.mcp_servers??config.mcpServers??{}),restartNeeded:true};}
- function save(model,{values,mcp}){if([...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish the current operation before saving native settings.');const {path,config}=record(model);if(busy(requests().filter(r=>instances.get(r.instanceId)?.model===model)))throw new Error('Finish this model’s requests before saving its settings.');const patch=validateNativeSettings(values??{}),next={...config};for(const field of nativeFields())if(field.supported===false&&patch[field.id]!=null&&JSON.stringify(patch[field.id])!==JSON.stringify(config[field.id]))throw new Error(`${field.label} needs a newer native Strata installation. Update it in Settings → About.`);for(const [key,value] of Object.entries(patch)){if(key==='env')next.env=restoreNativeEnv(value,config.env??{});else if(value===null)delete next[key];else next[key]=value;}if('vram_reserve_mib' in patch){const base=captureUserArgs(next);const mine=setUserFlag(base,'--vram-reserve-mib',patch.vram_reserve_mib);if(mine.length)next[USER_KEY]=mine;else delete next[USER_KEY];next.args=mine.length&&patch.vram_reserve_mib!==null?mergeUserArgs(next.args??[],mine):setUserFlag(next.args??[],'--vram-reserve-mib',null);delete next.ui_reserve_applied;if(Array.isArray(next.args_written))next.args_written=[...next.args];}if(mcp!==undefined){next.mcp_servers=validateMcpServers(mcp,config.mcp_servers??config.mcpServers??{});delete next.mcpServers;}copyFileSync(path,path+'.bak');chmodSync(path+'.bak',0o600);const temp=path+'.ui-tmp';writeFileSync(temp,JSON.stringify(next,null,2)+'\n',{mode:0o600});renameSync(temp,path);return settings(model);}
+ function settings(model){const {config}=record(model);const values=Object.fromEntries(NATIVE_FIELDS.map(f=>[f.id,config[f.id]??null]));if(typeof values.aliases==='string')values.aliases=values.aliases.split(',').map(v=>v.trim()).filter(Boolean);values.sampling=config.sampling??{};values.args=config.args??[];values.env=publicNativeEnv(config.env??{});return {model,values,mcp:publicMcpServers(config.mcp_servers??config.mcpServers??{}),restartNeeded:true,capabilities:{dsExperts:ownEngine(config)&&dsExpertsSupported(config)}};}
+ function save(model,{values,mcp}){if([...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish the current operation before saving native settings.');const {path,config}=record(model);if(busy(requests().filter(r=>instances.get(r.instanceId)?.model===model)))throw new Error('Finish this model’s requests before saving its settings.');const patch=validateNativeSettings(values??{}),next={...config};if(patch.ds_experts!=null&&!dsExpertsSupported(config))throw new Error('The Speed choice needs the newer DeepSeek engine. Update the engine in Settings, then choose it.');for(const field of nativeFields())if(field.supported===false&&patch[field.id]!=null&&JSON.stringify(patch[field.id])!==JSON.stringify(config[field.id]))throw new Error(`${field.label} needs a newer native Strata installation. Update it in Settings → About.`);for(const [key,value] of Object.entries(patch)){if(key==='env')next.env=restoreNativeEnv(value,config.env??{});else if(value===null)delete next[key];else next[key]=value;}if('vram_reserve_mib' in patch){const base=captureUserArgs(next);const mine=setUserFlag(base,'--vram-reserve-mib',patch.vram_reserve_mib);if(mine.length)next[USER_KEY]=mine;else delete next[USER_KEY];next.args=mine.length&&patch.vram_reserve_mib!==null?mergeUserArgs(next.args??[],mine):setUserFlag(next.args??[],'--vram-reserve-mib',null);delete next.ui_reserve_applied;if(Array.isArray(next.args_written))next.args_written=[...next.args];}if(mcp!==undefined){next.mcp_servers=validateMcpServers(mcp,config.mcp_servers??config.mcpServers??{});delete next.mcpServers;}copyFileSync(path,path+'.bak');chmodSync(path+'.bak',0o600);const temp=path+'.ui-tmp';writeFileSync(temp,JSON.stringify(next,null,2)+'\n',{mode:0o600});renameSync(temp,path);return settings(model);}
  function previousEngine(){if(packaged)return !!snapshot.engine?.previous;try{const data=snapshot.installed?.data_dir??snapshot.installed?.data_folder;return [join(preferences.repo,'engine/.previous'),data&&join(data,'engine/.previous')].filter(Boolean).some(existsSync)&&readFileSync(join(preferences.repo,'setup.py'),'utf8').includes('--rollback-engine');}catch{return false;}}
  async function plan(args){await refresh();if(!snapshot.available)throw new Error(snapshot.error);const result=await tool('strata_install',installArgs(args,false));
   /* A chosen drafter that is not on this computer yet is part of the download: its size is listed beside the model's (Control decides; nothing is fetched here). */
@@ -207,6 +216,12 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
   if(still.length)throw new Error(`Some files could not be removed: ${still.slice(0,3).map(p=>basename(p)).join('; ')}`);
 return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
  /* The configuration a load starts the engine with (before its port and key): the saved model config, the user's choices and the resource profile. The tuner measures exactly this, so a saved tuning belongs to the same choices a load makes. */
+ /* DeepSeek-V4.1-Flash runs on its own engine (strata-dsv41) that takes none of the Flash-Next options the app adds on its own (request slots, the RAM budget, the output clamp, the resource profile): a flag it does not know ends the start with "unknown option". */
+ const ownEngine=config=>config?.arch==='deepseek41'||/strata-dsv41/i.test(String(config?.exe??''));
+ /* The DeepSeek engine's version, read from the folder the run config names (engine-dsv41/<version>-<platform>-...). --experts exists from engine 0.1.50: an older engine ends the start with "unknown option", so the choice is offered and passed only for 0.1.50 or newer. */
+ const DS_EXPERTS_MIN=[0,1,50];
+ function dsEngineVersion(config){const m=/engine-dsv41[\\/](\d+(?:\.\d+)+)-/.exec(String(config?.exe??''))||/engine-dsv41[\\/](\d+(?:\.\d+)+)-/.exec(String((config?.lib_dirs??[])[0]??''));return m?m[1].split('.').map(Number):null;}
+ function dsExpertsSupported(config){const v=dsEngineVersion(config);if(!v)return false;for(let i=0;i<DS_EXPERTS_MIN.length;i++){const a=v[i]??0,b=DS_EXPERTS_MIN[i];if(a!==b)return a>b;}return true;}
  function buildConfig(args,config){
   const vision=runtimeVision(config,args.vision);
   const visionPreferences=args.vision!==undefined?{ui_vision_enabled:args.vision!=='no',ui_vision_device:args.vision==='no'?config.ui_vision_device??'yes':args.vision}:{};
@@ -215,7 +230,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
   const values0=args.values??{},cleared='vram_reserve_mib' in values0&&(values0.vram_reserve_mib===null||values0.vram_reserve_mib===''),base0=cleared?{...config,vram_reserve_mib:undefined,[USER_KEY]:setUserFlag(config[USER_KEY],'--vram-reserve-mib',null)}:config;
   let mine=captureUserArgs(base0);const asked=cleared?null:reserveChoice({...base0,[USER_KEY]:mine},snapshot.hardware,values0).asked;
   if(asked!==null)mine=setUserFlag(mine,'--vram-reserve-mib',asked);
-  const resources=args.resourceProfile?resourceSettings({...base0,[USER_KEY]:mine,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model),values0):null;
+  const resources=args.resourceProfile&&!ownEngine(config)?resourceSettings({...base0,[USER_KEY]:mine,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model),values0):null;
   const cfg={...config,...visionPreferences,...(resources?{...resources,ui_resource_profile:args.resourceProfile}:{}),host:'127.0.0.1',open_browser:false,...validateNativeSettings(args.values??{}),vision};
   /* The app's suggested cards only fill a gap: a model whose settings file already names its GPUs ("gpu": [1, 0], with "gpu_order": "as_given") keeps them (#3256). A card the person picked in the screen always wins. */
   const namedInFile=(Array.isArray(config.gpu)?config.gpu.length>0:config.gpu!==undefined&&config.gpu!==null&&config.gpu!=='')||!!config.gpu_roles;
@@ -230,11 +245,14 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
   if(!cfg.vision&&Array.isArray(cfg.args))cfg.args=cfg.args.filter(a=>a!=='--vision');
   for(const arg of cfg.args??[])if(arg.endsWith('.gguf')&&!existsSync(resolve(repo(),arg)))throw new Error('An engine argument names a missing GGUF. Restore the saved arguments or repair the files.');
   /* The app's own choice of request slots (4, fewer where the card has no room) is part of the configuration, so a tune measures the engine a load will start: slots take VRAM from the expert cache. */
-  const parallelChoice=packaged?chooseParallel({config:cfg,values:args.values??{},hardware:snapshot.hardware?.gpus?.length?snapshot.hardware:{gpus:hardwareProbe()??[]}}):null;
+  const parallelChoice=packaged&&!ownEngine(config)?chooseParallel({config:cfg,values:args.values??{},hardware:snapshot.hardware?.gpus?.length?snapshot.hardware:{gpus:hardwareProbe()??[]}}):null;
   let parallelNote=null;
   /* The agent asks for long answers (a thinking model can use most of the window): let the engine clamp the output to what is left of the context instead of refusing the request. */
-  if(packaged&&cfg.fit_max_tokens===undefined)cfg.fit_max_tokens=true;
+  if(packaged&&!ownEngine(config)&&cfg.fit_max_tokens===undefined)cfg.fit_max_tokens=true;
   if(parallelChoice){const applied=applyParallel(cfg,parallelChoice);for(const k of Object.keys(cfg))if(!(k in applied.cfg))delete cfg[k];Object.assign(cfg,applied.cfg);parallelNote=applied.note;}
+  /* DeepSeek's Speed choice: the engine decides by itself (--experts auto: 5 when the cards total 16 GB or less, else 6), so nothing is passed unless the person chose 5 or 6. */
+  if(ownEngine(config)){const list=[];const old=Array.isArray(cfg.args)?cfg.args:[];for(let i=0;i<old.length;i++){if(old[i]==='--experts'){i++;continue;}list.push(old[i]);}if(dsExpertsSupported(config)&&(cfg.ds_experts==='5'||cfg.ds_experts==='6'))list.push('--experts',cfg.ds_experts);else if(!dsExpertsSupported(config)&&old.includes('--experts'))list.splice(0,list.length,...old);cfg.args=list;delete cfg.ds_experts;}
+  else delete cfg.ds_experts;
   return {cfg,resources,visionPreferences,parallelChoice,parallelNote};
  }
  /* The DFlash2 drafter, before a load that uses it: Control says whether the choice needs it (and the file is not here), downloads it pinned and checked, and packs it, with plain progress in the job.
@@ -286,7 +304,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
    /* The engine starts under Control's owner runtime, not as our child: a saved profile per slot, then `runtime start`. */
    const used=new Set([...instances.values()].map(i=>i.profile));let slot=1;while(used.has('app-'+slot))slot++;instance.profile='app-'+slot;
    instances.set(id,instance);if(!defaultId||!args.multiple||wasDefault)defaultId=id;emit();
-   const startWith=value=>{writeFileSync(configPath,JSON.stringify(value,null,2),{mode:0o600});return control.stop(instance.profile).catch(()=>{}).then(()=>control.saveProfile(instance.profile,configPath)).then(()=>control.start(instance.profile,{waitSeconds:300}));};
+   const startWith=value=>{writeFileSync(configPath,JSON.stringify(value,null,2),{mode:0o600});return control.stop(instance.profile).catch(()=>{}).then(()=>control.saveProfile(instance.profile,configPath)).then(()=>control.start(instance.profile,{waitSeconds:ownEngine(config)?Math.min(600,Math.max(300,Number(config.engine_ready_s)||300)):300}));};
    started=startWith(cfg);
    started.then(()=>append(id,'Strata Control reports the engine is ready.'),error=>{append(id,error.message);});
    try{await started;}catch(firstError){let error=firstError;
@@ -299,7 +317,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
     /* ONE automatic second try in all, never saved, never repeated (args.retrySafer false turns it off): with a safer memory setting when the
        failure looks like a memory stop, and without several-requests-at-once when that was the app's own default (not a number the user chose).
        Both changes ride on the same single try, with the plain sentence of the memory change when there is one. */
-    const allowed=args.retrySafer!==false&&job.state==='running';
+    const allowed=args.retrySafer!==false&&job.state==='running'&&!ownEngine(config);
     const safer=allowed?saferStart(cfg,snapshot.hardware,modelArena(args.model),said):null;
     const dropParallel=allowed&&cfg.parallel>1&&!parallelChoice?.explicit;
     if(!safer&&!dropParallel){instance.status='error';instance.error=said;emit();throw new Error(said);}
@@ -331,7 +349,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
  function ensurePoll(){if(!timer){timer=setInterval(()=>void poll(),2000);timer.unref?.();}void poll();}
  async function benchmark(job,args){const instance=resolveInstance(args.instanceId);job.instanceId=instance.id;if(busy(requests().filter(r=>r.instanceId===instance.id)))throw new Error('Wait for this model to finish before benchmarking.');const started=Date.now();job.abort=new AbortController();const response=await fetcher(`http://127.0.0.1:${instance.port}/v1/chat/completions`,{method:'POST',headers:{'content-type':'application/json',authorization:`Bearer ${instance.key}`},signal:AbortSignal.any([job.abort.signal,AbortSignal.timeout(180000)]),body:JSON.stringify({model:instance.apiModelId,messages:[{role:'user',content:'Explain how a rainbow forms in clear, simple language.'}],temperature:0,reasoning_effort:'none',max_tokens:200,stream:false})});const body=await response.json();if(!response.ok)throw new Error(body.error?.message??'Benchmark failed.');if(job.state!=='running')return;const result={summary:'Measured benchmark complete.',at:new Date().toISOString(),model:instance.apiModelId,durationMs:Date.now()-started,tokensIn:body.usage?.prompt_tokens??null,tokensOut:body.usage?.completion_tokens??null,outputTps:body.timings?.predicted_per_second??null,promptTps:body.timings?.prompt_per_second??null,source:'engine',settings:'Greedy · thinking off · up to 200 output tokens'};writeFileSync(join(directory,'native-benchmark.json'),JSON.stringify(result,null,2),{mode:0o600});return result;}
  function resolveInstance(id){const aliases=[...instances.values()].filter(i=>i.aliases?.includes(id));if(aliases.length>1&&!instances.has(id)&&![...instances.values()].some(i=>i.apiModelId===id))throw new Error('This alias matches more than one instance. Choose its exact model ID.');const i=instances.get(id)??[...instances.values()].find(i=>i.apiModelId===id)??aliases[0]??(!id&&instances.size===1?[...instances.values()][0]:undefined);if(!i)throw new Error('Choose a loaded model ID.');if(i.status!=='ready')throw new Error('This model is not ready.');return i;}
- async function program(job,args){if(packaged)return componentProgram(job);if(externalRunning().length)throw new Error('Stop the native server running outside this UI before changing engine files.');if(instances.size)throw new Error('Unload native models before changing engine files.');const folder=repo();let {command,args:prefix}=python(),argv;
+ async function program(job,args){if(packaged)return componentProgram(job,args);if(externalRunning().length)throw new Error('Stop the native server running outside this UI before changing engine files.');if(instances.size)throw new Error('Unload native models before changing engine files.');const folder=repo();let {command,args:prefix}=python(),argv;
   if(job.kind==='calibrate'||job.kind==='tune'){if(!state().capabilities.calibration)throw new Error('This installation calibrates NVIDIA GPUs only. Use the short benchmark on other devices.');const model=args.model??snapshot.installed?.models?.[0]?.model;const chosen=record(model);if(!chosen.entry.ready)throw new Error('Prepare this model before calibrating.');command=venvPython(folder);prefix=[];if(!existsSync(command))throw new Error('Prepare the Python environment first.');argv=['-c','import sys; from pathlib import Path; import setup; sys.exit(0 if setup.calibrate_config(Path(sys.argv[1])) else 1)',chosen.path];}
   else if(job.kind==='rollback'){if(!previousEngine())throw new Error('No saved previous engine is available.');argv=[join(folder,'setup.py'),'--rollback-engine'];}
   else if(job.kind==='update-engine'){if(!snapshot.installed?.models?.length)throw new Error('Prepare a model first. Its installer downloads the matching engine.');argv=[join(folder,'setup.py'),'--update'];}
@@ -342,29 +360,33 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
  /* Packaged app: engine and Control updates and the engine rollback go through Control's explicit update step (`strata update`,
     `strata components rollback`), never through git, setup.py or a download in this process. The app itself is updated by the
     shell's signed Tauri updater. Models are not part of any of it. */
- async function componentProgram(job){
-  if(!['update-engine','update-strata','rollback'].includes(job.kind)||typeof control.update!=='function')throw new Error(NO_INSTALL);
+ async function componentProgram(job,args={}){
+  if(!COMPONENT_KINDS.includes(job.kind)||typeof control.update!=='function')throw new Error(NO_INSTALL);
   if(instances.size)throw new Error('Unload native models before changing engine files.');
   job.abort=new AbortController();
   const subject=job.kind==='update-strata'?'Strata':'engine';
-  try{return await componentSteps(job,subject);}catch(error){throw error?.details!==undefined&&error.message?error:plainError(error,subject);}
+  try{return await componentSteps(job,subject,args);}catch(error){updateLog(`${job.kind} failed: ${String(error?.message??error).slice(0,400)}`);throw error?.details!==undefined&&error.message?error:plainError(error,subject);}
  }
- async function componentSteps(job,subject){
+ async function componentSteps(job,subject,args={}){
   const onEvent=event=>{
    if(event.event==='progress'){job.summary=`Downloading: ${event.percent}%`;job.result={install:{step:job.summary,download:{file:event.label,percent:event.percent}}};}
    else if(event.event==='phase'&&PHASE_TEXT[event.phase])job.summary=PHASE_TEXT[event.phase];
    else if(event.event==='waiting')job.summary='Waiting for the running model to stop…';
    emit();
   };
+  updateLog(`${job.kind} started (app ${thisAppVersion()??'unknown'})`);
+  if(job.kind==='install-engine-file'){if(typeof args.path!=='string'||!args.path)throw new Error('Choose the engine file first.');let done;try{done=await control.installEngineFile(args.path,{onEvent,signal:job.abort.signal});}finally{try{const own=resolve(directory,'incoming-engine')+sep;if(resolve(args.path).startsWith(own))rmSync(args.path,{force:true});}catch{/* the copy in the host's own folder; a leftover is harmless */}}return {summary:updateSummary(done)==='Everything is already up to date.'?(done.results?.[0]?.note??'Nothing was changed.'):updateSummary(done),result:done};}
   if(job.kind==='rollback'){const done=await control.rollbackEngine();return {summary:'The previous engine is back. Your models and settings are unchanged.',result:done};}
   if(job.kind==='update-engine'){const done=await control.update({engine:true,control:false,onEvent,signal:job.abort.signal});return {summary:updateSummary(done),result:done};}
   const done=await control.update({engine:false,control:true,onEvent,signal:job.abort.signal});
+  updateLog(`Control step finished: ${updateSummary(done)}`);
   const notes=[updateSummary(done)];
   if(appUpdater){
    job.summary='Looking for a new version of the app…';emit();
    let verdict;
    try{verdict=await appUpdater.check();}catch(error){if(error?.code!=='app-update-unavailable')throw error;verdict={available:false};notes.push(appUpdater.unavailable||error.message);}
-   if(verdict.available){await appUpdater.install({signal:job.abort.signal,onProgress:p=>{if(p.total){job.summary=`Downloading the app update: ${Math.round(100*p.downloaded/p.total)}%`;job.result={install:{step:job.summary,download:{file:'Strata app',percent:Math.round(100*p.downloaded/p.total)}}};emit();}}});notes.push('The app update is installed. Strata will restart.');}
+   updateLog(`app check: ${verdict.available?`version ${verdict.version} is available`:'no newer app version'}`);
+   if(verdict.available){job.appUpdateFrom=thisAppVersion();job.appUpdateTo=verdict.version??null;emit();updateLog(`app update to ${verdict.version??'?'} starting; the installer will end this app`);await appUpdater.install({signal:job.abort.signal,onProgress:p=>{if(p.total){job.summary=`Downloading the app update: ${Math.round(100*p.downloaded/p.total)}%`;job.result={install:{step:job.summary,download:{file:'Strata app',percent:Math.round(100*p.downloaded/p.total)}}};emit();}}});notes.push('The app update is installed. Strata will restart.');}
   }
   return {summary:notes.filter(Boolean).join(' '),result:done};
  }
@@ -410,7 +432,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
   const room=args.resourceProfile==='work';
   return autotuner.start(job,job.kind==='recheck'?'recheck':'tune',{configPath:path,presetId:args.presetId,mode:args.mode,use:args.use,goal:room?'room':'speed',leaveRam:room?20:0,allowSmallDifferences:args.allowSmallDifferences===true,name:args.name},{onProgress:p=>{job.summary=p.text??job.summary;emit();}});
  }
- function operation(kind,args={}){if(!['install','load','benchmark','tune','autotune','recheck','calibrate','update-engine','update-strata','rollback','remove'].includes(kind))throw new Error('Choose a supported native operation.');if(!snapshot.available)throw new Error(snapshot.error??'Connect the native Strata installation first.');if(kind==='install'||kind==='load'){const refusal=engineRefusal(snapshot.catalog,args.model,snapshot.engineInfo);if(refusal)throw new Error(refusal);}return begin(kind,job=>kind==='install'?install(job,args):kind==='load'?loadEngine(job,args):kind==='benchmark'?benchmark(job,args):kind==='tune'?tune(job,args):kind==='autotune'||kind==='recheck'?autotune(job,args):kind==='remove'?removeModel(job,args):program(job,args),{guided:args.guided===true,model:args.model,...(args.family?{family:args.family}:{})});}
+ function operation(kind,args={}){if(!['install','load','benchmark','tune','autotune','recheck','calibrate','update-engine','update-strata','rollback','install-engine-file','remove'].includes(kind))throw new Error('Choose a supported native operation.');if(!snapshot.available&&!(packaged&&COMPONENT_KINDS.includes(kind)))throw new Error(snapshot.error??'Connect the native Strata installation first.');if(kind==='install'||kind==='load'){const refusal=engineRefusal(snapshot.catalog,args.model,snapshot.engineInfo);if(refusal)throw new Error(refusal);}return begin(kind,job=>kind==='install'?install(job,args):kind==='load'?loadEngine(job,args):kind==='benchmark'?benchmark(job,args):kind==='tune'?tune(job,args):kind==='autotune'||kind==='recheck'?autotune(job,args):kind==='remove'?removeModel(job,args):program(job,args),{guided:args.guided===true,model:args.model,...(args.family?{family:args.family}:{})});}
  /* ---- The models folder card (0.2.2): what a picked folder means, and the three choices. The copying is Control's (strata models move). ---- */
  const currentModelsFolder=()=>preferences.downloadDirectory??(modelsDirectory?modelsDirectory():snapshot.installed?.data_folder)??null;
  const moveFile=()=>join(directory,'models-move.cancel');
@@ -433,7 +455,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
   const under=value=>typeof value==='string'&&[ 'models','packs','mtp' ].some(item=>{const base=join(old,item).toLowerCase();const v=value.toLowerCase();return v===base||v.startsWith(base+sep)||v.startsWith(base+'/');});
   const scan=value=>Array.isArray(value)?value.some(scan):value&&typeof value==='object'?Object.values(value).some(scan):under(value);
   for(const name of readdirSync(folder)){
-   if(!/^strata-[a-z0-9_-]+\.json$/i.test(name)||name.endsWith('.shared-settings.json'))continue;
+   if(!/^strata-[a-z0-9_.-]+\.json$/i.test(name)||name.endsWith('.shared-settings.json'))continue;
    if(!scan(readJson(join(folder,name))))continue;
    mkdirSync(kept,{recursive:true});renameSync(join(folder,name),join(kept,name));aside.push(name);
   }

apps/host/server/native-settings.mjs

@@ -11,6 +11,7 @@ export const NATIVE_FIELDS=[
  {id:'mtp',label:'Draft layer (MTP)',group:'Serving',type:'boolean',hint:'The draft layer guesses several words ahead, which makes answers faster, and costs about 1 GB of graphics memory and some RAM. Turn it off if the model stops while it starts, or the card is small: the expert cache gets that memory back and answers are slower. Default is on.'},
  {id:'drafting',label:'Drafting',group:'Serving',type:'enum',choices:['auto','mtp','dflash2','off'],hint:'Which drafter guesses words ahead to make answers faster. Auto (recommended) lets Strata pick from what it measured on cards like yours; today that is the MTP. DFlash2 is for Qwen3.8-Flash-Next only and downloads a 1.2 GB drafter once. If DFlash2 cannot run, the MTP is used and Details says why. Off turns the draft layer off.'},
  {id:'batchMtp',label:'MTP per request',group:'Serving',type:'boolean',hint:'Each concurrent request uses the draft layer. Left alone, Strata turns it on for one graphics card with 24 GB or more and several requests at once, and off otherwise; choose on or off here to decide yourself.'},
+ {id:'ds_experts',label:'Speed (DeepSeek)',group:'Serving',type:'enum',choices:['5','6'],forModel:'deepseek',hint:'Faster uses 5 of 6 experts per word: a small quality change, usually not noticeable. Full quality uses all 6. Left alone, the engine picks Faster on a PC whose graphics cards total 16 GB or less.'},
  {id:'parallel',label:'Concurrent requests',group:'Serving',type:'number',min:1,max:8,hint:'More slots need more memory and can slow each response.'},
  {id:'engine_silence_s',label:'Engine stall timeout (seconds)',group:'Recovery',type:'number',min:10,max:3600},
  {id:'api_monitor',label:'Keep API request metadata',group:'Recovery',type:'boolean'},
@@ -26,7 +27,7 @@ export const NATIVE_FIELDS=[
  {id:'mcp_max_result_chars',label:'Maximum tool result characters',group:'Tools',type:'number',min:100,max:1000000},
 ];
 /** Settings the app itself applies when it starts a model (they are not read from the engine's source, so the engine's text never says it supports them). */
-export const APP_OWNED_FIELDS=['mtp','batchMtp','drafting'];
+export const APP_OWNED_FIELDS=['mtp','batchMtp','drafting','ds_experts'];
 /** The engine arguments without the draft layer: --mtp <folder or count>, --spec-min-p <p> (its confidence threshold) and --batch-mtp. --spec stays: prompt lookup still uses its windows. Same rule as strata_control/draft_layer.py. */
 export function withoutDraftLayer(args){
  const out=[];const list=(args??[]).map(String);

apps/host/server/system-telemetry.mjs

@@ -1,5 +1,7 @@
 /** Host counters. CPU sockets are measured only when their logical CPU IDs are known. */
 import os from 'node:os';
+import { spawn } from 'node:child_process';
+import { createPowerShellLoop, endWithHost } from './windows-poll.mjs';
 import { readFile, readdir } from 'node:fs/promises';
 import { availableMemoryGb } from './hardware.mjs';
 import { probe } from './util.mjs';
@@ -18,7 +20,7 @@ export function cpuUtilization(previous, current, ids) {
 }
 
 export function diskRate(previous, current, time) {
-  const elapsed=previous?(time-previous.time)/1000:0;
+  const elapsed=previous?((current?.at??time)-(previous.counters?.at??previous.time))/1000:0;
   if(elapsed<=0||!current||!previous?.counters)return {readMbs:null,writeMbs:null};
   const read=current.read-previous.counters.read,write=current.write-previous.counters.write;
   return {readMbs:read>=0?read/1024**2/elapsed:null,writeMbs:write>=0?write/1024**2/elapsed:null};
@@ -41,6 +43,33 @@ export function parseMacDiskCounters(raw) {
   return reads.length&&writes.length?{read:reads.reduce((n,m)=>n+Number(m[1]),0),write:writes.reduce((n,m)=>n+Number(m[1]),0)}:null;
 }
 
+export function parseWindowsDiskLine(line) {
+  const m=/^\s*(\d+)\s+(\d+)\s*$/.exec(String(line));
+  return m?{read:Number(m[1]),write:Number(m[2])}:null;
+}
+
+/** The disk counters, read by one long-lived PowerShell (windows-poll.mjs; #3939). */
+export function createWindowsDiskReader({ spawnFn=spawn, intervalSec=4, maxStarts=3, now=Date.now }={}) {
+  let latest=null;
+  const script=`while($true){$d=Get-CimInstance Win32_PerfRawData_PerfDisk_PhysicalDisk -Filter "Name='_Total'";if($d){[Console]::Out.WriteLine(([string]$d.DiskReadBytesPersec)+' '+([string]$d.DiskWriteBytesPersec));[Console]::Out.Flush()};Start-Sleep -Seconds ${intervalSec}}`;
+  const loop=createPowerShellLoop({script,spawnFn,maxStarts,onLine:line=>{
+    const parsed=parseWindowsDiskLine(line);
+    if(parsed)latest={...parsed,at:now()};
+    return !!parsed;
+  }});
+  return {
+    read() { loop.start(); return latest&&now()-latest.at<5*intervalSec*1000?latest:null; },
+    stop() { loop.stop(); },
+    get starts() { return loop.starts; },
+  };
+}
+
+let windowsReader=null;
+function windowsDisks() {
+  windowsReader??=endWithHost(createWindowsDiskReader());
+  return windowsReader.read();
+}
+
 async function disks() {
   try {
     if(process.platform==='linux') {
@@ -49,24 +78,26 @@ async function disks() {
     }
     if(process.platform==='darwin')return parseMacDiskCounters(await probe('ioreg',['-r','-c','IOBlockStorageDriver','-l'],1500));
     if(process.platform==='win32') {
-      const raw=await probe('powershell.exe',['-NoProfile','-NonInteractive','-Command',"Get-CimInstance Win32_PerfRawData_PerfDisk_PhysicalDisk -Filter \"Name='_Total'\" | Select-Object DiskReadBytesPersec,DiskWriteBytesPersec | ConvertTo-Json -Compress"],2000);
-      const value=JSON.parse(raw);
-      if(value.DiskReadBytesPersec!=null&&value.DiskWriteBytesPersec!=null)return {read:Number(value.DiskReadBytesPersec),write:Number(value.DiskWriteBytesPersec)};
+      return windowsDisks();
     }
   } catch { /* An unsupported counter stays unavailable. */ }
   return null;
 }
 
 export function createSystemSampler() {
-  let previousCpu=null,previousDisk=null;
+  let previousCpu=null,previousDisk=null,lastRate={readMbs:null,writeMbs:null};
   return async processors => {
     const current=os.cpus(),time=Date.now();
     const cpuLoad=cpuUtilization(previousCpu,current,current.map((_,i)=>i));
     const cpus=processors.map(p=>({id:p.id,utilizationPct:cpuUtilization(previousCpu,current,p.logicalIds??(processors.length===1?current.map((_,i)=>i):[]))}));
     previousCpu=current;
     const [available,counters]=await Promise.all([availableMemoryGb(process.platform),disks()]);
-    const rate=diskRate(previousDisk,counters,time);
-    previousDisk={time,counters};
+    let rate=lastRate;
+    if(!(counters&&counters.at!==undefined&&previousDisk?.counters?.at===counters.at)) {
+      rate=diskRate(previousDisk,counters,time);
+      previousDisk={time,counters};
+      lastRate=rate;
+    }
     const total=os.totalmem()/1024**3,free=available??os.freemem()/1024**3;
     return {cpuLoad,cpus,ramUsedGb:Math.max(0,Math.min(total,total-free)),ramTotalGb:total,diskReadGbs:rate.readMbs===null?null:rate.readMbs/1024,diskWriteMbs:rate.writeMbs};
   };

apps/host/server/updates.mjs

@@ -59,7 +59,7 @@ export async function checkComponentUpdates({ control, appUpdater = null, appVer
     const message = /update server|aren't available|No internet/.test(plain.headline) ? plain.message : `Couldn't check for updates. Try again in a moment.`;
     return { checkedAt, strata: { installedVersion: appVersion ?? control.version ?? null, status: 'error', message, details: plain.details, canInstall: false }, engine: { installedVersion: null, status: 'error', message, details: plain.details, canInstall: false } };
   }
-  const mib = bytes => `${Math.round((bytes ?? 0) / (1 << 20))} MB`;
+  const mib = bytes => `${Math.round((bytes ?? 0) / 1_000_000)} MB`;      // decimal megabytes, like the Terminal and the release page
   const engine = report.engine ?? {};
   const installedEngine = engine.installed?.version ?? null;
   const offered = engine.offered?.version ?? null;
@@ -74,6 +74,7 @@ export async function checkComponentUpdates({ control, appUpdater = null, appVer
   const app = report.app ?? {};
   let appNew = app.status === 'available' ? app.offered : null;
   let appNotes = app.notes ?? '';
+  let appCheckFailed = null;   // the shell's own (Tauri) check threw: before this, the Settings check hid it and showed only Control's text
   let appCannot = null;   // browser mode: the app window's updater is not running, so the app itself cannot be updated from here
   if (appUpdater) {
     try {
@@ -81,12 +82,41 @@ export async function checkComponentUpdates({ control, appUpdater = null, appVer
       appNew = verdict.available ? verdict.version : null;
       appNotes = verdict.notes ?? appNotes;
     } catch (error) {
-      if (error?.code === 'app-update-unavailable' && appUpdater.unavailable) appCannot = appUpdater.unavailable;   // otherwise the feed's own view stands
+      if (error?.code === 'app-update-unavailable' && appUpdater.unavailable) appCannot = appUpdater.unavailable;
+      else appCheckFailed = String(error?.message ?? error ?? 'The app update check failed.');   // the app's own check did not work: say so, raw text behind Details
     }
   }
   const controlNew = control_.status === 'available' ? control_.offered : null;
   const strata = { installedVersion: appVersion ?? control_.installed ?? control.version ?? null, canInstall: !!((appNew && !appCannot) || controlNew) };
-  if (appNew || controlNew) Object.assign(strata, { status: 'available', latestVersion: appNew ?? controlNew, message: `A new version of Strata is available.${appNotes ? ` ${appNotes}` : ''}${appNew && appCannot ? ` ${appCannot}` : ''}` });
+  const appCheckLine = "Strata couldn't check for a new version of the app itself. Try again later.";
+  if (appNew || controlNew) Object.assign(strata, { status: 'available', latestVersion: appNew ?? controlNew, message: `A new version of Strata is available.${appNotes ? ` ${appNotes}` : ''}${appNew && appCannot ? ` ${appCannot}` : ''}${appCheckFailed ? ` ${appCheckLine}` : ''}` });
+  else if (appCheckFailed) Object.assign(strata, { status: 'error', message: appCheckLine });
   else Object.assign(strata, { status: 'current', message: 'Strata is up to date.' });
+  if (appCheckFailed) strata.details = appCheckFailed;
   return { checkedAt, feed: report.feed, strata, engine: engineView, serving: report.serving ?? [] };
 }
+
+/**
+ * What the first-run card shows: this PC's graphics card(s), the engine package the signed feed offers for it and how big it is.
+ * One feed read, nothing downloaded. `status`: offer (a package fits), none (nothing fits; `reasons` say why), offline (the feed could not be
+ * read), installed (an engine is already here), wrong-make (an engine for another make of card is installed).
+ */
+export async function engineFirstRun({ control, gpus = [] }) {
+  const cards = gpus.map(g => ({ name: g.name ?? 'Graphics card', vramGb: g.vramGb ?? null }));
+  let report;
+  try {
+    report = await control.updateCheck({});
+  } catch (error) {
+    const plain = plainUpdateError(error, 'Strata');
+    return { status: looksOffline(error) || /update server|No internet/.test(plain.headline ?? '') ? 'offline' : 'error', gpus: cards, message: plain.message, details: plain.details };
+  }
+  const engine = report.engine ?? {};
+  const hardware = report.hardware ?? {};
+  const base = { gpus: cards, driver: hardware.nvidia_driver ?? null, backend: hardware.backend ?? null };
+  if (engine.installed) return { ...base, status: 'installed', installedVersion: engine.installed.version ?? null };
+  if (engine.status === 'wrong-make') return { ...base, status: 'wrong-make', message: engine.note ?? null, reasons: engine.reasons ?? [] };
+  if (engine.offered && (engine.status === 'install' || engine.status === 'available')) {
+    return { ...base, status: 'offer', offer: { version: engine.offered.version, bytes: engine.download_bytes || engine.offered.size || 0, variant: engine.offered.variant ?? '', backend: engine.offered.backend ?? null } };
+  }
+  return { ...base, status: 'none', message: engine.note ?? null, reasons: engine.reasons ?? [] };
+}

apps/host/server/windows-gpu.mjs

@@ -0,0 +1,90 @@
+/**
+ * Windows graphics cards that nvidia-smi does not cover (AMD, Intel): their size and their load.
+ *  - size: the DirectX adapter list in the registry (HKLM\SOFTWARE\Microsoft\DirectX) has a 64-bit DedicatedVideoMemory and the adapter
+ *    LUID. Win32_VideoController.AdapterRAM is 32 bits and reads 0 or 4 GB for a 16 GB card (#3727, #3836).
+ *  - load and memory in use: the Windows GPU performance counters (the ones Task Manager shows), read by one long-lived PowerShell and
+ *    matched to the card by LUID. Temperature, power and the PCIe link need the vendor's own library, so they stay "not available".
+ */
+import { createPowerShellLoop, endWithHost } from './windows-poll.mjs';
+import { utf8Script } from './powershell-utf8.mjs';
+
+export const DX_ADAPTERS_SCRIPT = utf8Script(
+  "Get-ChildItem HKLM:\\SOFTWARE\\Microsoft\\DirectX | ForEach-Object { $p = Get-ItemProperty $_.PSPath; " +
+  "if ($p.Description -and $null -ne $p.AdapterLuid) { [pscustomobject]@{ Description = [string]$p.Description; VendorId = [string]$p.VendorId; " +
+  "Luid = [string]$p.AdapterLuid; Dedicated = [string]$p.DedicatedVideoMemory; Software = [string]$p.SoftwareAdapter } } } | ConvertTo-Json -Compress");
+
+/** luid_0x<high>_0x<low> in the spelling of the performance counters, from the registry's 64-bit number. */
+export function luidName(value) {
+  try {
+    const n = BigInt.asUintN(64, BigInt(String(value)));
+    const hex = v => '0x' + v.toString(16).padStart(8, '0');
+    return `luid_${hex(n >> 32n)}_${hex(n & 0xffffffffn)}`;
+  } catch { return null; }
+}
+
+/** The adapters the DirectX registry lists: [{ description, vendorId, luid, bytes, software }]. Never throws. */
+export function parseDxAdapters(raw) {
+  try {
+    const parsed = JSON.parse(raw), rows = Array.isArray(parsed) ? parsed : [parsed];
+    return rows.filter(r => r?.Description).map(r => ({
+      description: String(r.Description), vendorId: Number(r.VendorId) || 0, luid: luidName(r.Luid),
+      bytes: Number(r.Dedicated) || 0, software: String(r.Software) === '1' || String(r.Software).toLowerCase() === 'true',
+    }));
+  } catch { return []; }
+}
+
+const norm = text => String(text ?? '').toLowerCase().replace(/[^a-z0-9]/g, '');
+const VIRTUAL = /virtual|remote|indirect|mirror|basic render|meta |parsec|displaylink|idd/i;
+
+/**
+ * Win32_VideoController rows + the DirectX adapter list -> the cards this app can show. A card keeps the size from the registry;
+ * a display driver for a virtual monitor (no size, no known maker) is not a graphics card and is dropped.
+ */
+export function windowsOtherGpus(videoRows, dx) {
+  const used = new Set();
+  const out = [];
+  for (const row of videoRows) {
+    if (!row?.Name) continue;
+    const match = dx.find((a, i) => !used.has(i) && !a.software && norm(a.description) === norm(row.Name));
+    if (match) used.add(dx.indexOf(match));
+    const vendor = /amd|radeon/i.test(row.Name) ? 'amd' : /intel/i.test(row.Name) ? 'intel' : 'unknown';
+    const vramGb = match?.bytes ? Math.round(match.bytes / 1024 ** 3 * 10) / 10 : 0;
+    if (vendor === 'unknown' && (!vramGb || VIRTUAL.test(row.Name))) continue;
+    out.push({ id: String(row.PNPDeviceID), vendor, name: row.Name, vramGb, luid: match?.luid ?? null });
+  }
+  return out;
+}
+
+/** One counter line: "G <luid> <load percent> <dedicated bytes in use>". */
+export function parseGpuCounterLine(line) {
+  const m = /^G\s+(luid_0x[0-9a-f]+_0x[0-9a-f]+)\s+(\d+(?:\.\d+)?)\s+(\d+)\s*$/i.exec(String(line));
+  return m ? { luid: m[1].toLowerCase(), utilizationPct: Math.max(0, Math.min(100, Number(m[2]))), memoryUsedGb: Number(m[3]) / 1024 ** 3 } : null;
+}
+
+export function createWindowsGpuReader({ spawnFn, intervalSec = 4, maxStarts = 3, now = Date.now } = {}) {
+  const readings = new Map();
+  const script = utf8Script(
+    `while($true){` +
+    `$e=@(Get-CimInstance Win32_PerfFormattedData_GPUPerformanceCounters_GPUEngine);$m=@(Get-CimInstance Win32_PerfFormattedData_GPUPerformanceCounters_GPUAdapterMemory);` +
+    `$u=@{};foreach($r in $e){if($r.Name -match '(luid_0x[0-9A-Fa-f]+_0x[0-9A-Fa-f]+)_phys_\\d+_eng_\\d+_engtype_(\\w+)'){$k=$matches[1].ToLower()+'|'+$matches[2];$u[$k]=[double]$u[$k]+[double]$r.UtilizationPercentage}};` +
+    `$b=@{};foreach($k in $u.Keys){$l=$k.Split('|')[0];if(-not $b.ContainsKey($l) -or $u[$k] -gt $b[$l]){$b[$l]=$u[$k]}};` +
+    `foreach($r in $m){if($r.Name -match '(luid_0x[0-9A-Fa-f]+_0x[0-9A-Fa-f]+)'){$l=$matches[1].ToLower();[Console]::Out.WriteLine('G '+$l+' '+[math]::Round([double]$b[$l],0)+' '+$r.DedicatedUsage)}};` +
+    `[Console]::Out.Flush();Start-Sleep -Seconds ${intervalSec}}`);
+  const loop = createPowerShellLoop({ script, spawnFn, maxStarts, onLine: line => {
+    const parsed = parseGpuCounterLine(line);
+    if (parsed) readings.set(parsed.luid, { ...parsed, at: now() });
+    return !!parsed;
+  } });
+  return {
+    read(luid) { loop.start(); const r = readings.get(String(luid ?? '').toLowerCase()); return r && now() - r.at < 6 * intervalSec * 1000 ? r : null; },
+    stop() { loop.stop(); },
+  };
+}
+
+let shared = null;
+/** The card's load and memory in use from the Windows counters; null when there is no reading. */
+export function windowsGpuReading(luid) {
+  if (process.platform !== 'win32' || !luid) return null;
+  shared ??= endWithHost(createWindowsGpuReader());
+  return shared.read(luid);
+}

apps/host/server/windows-poll.mjs

@@ -0,0 +1,45 @@
+/**
+ * One long-lived PowerShell that prints a line per reading, in a loop. The monitor used to start a cold PowerShell for every sample;
+ * its WMI start cost more than the probe timeout, so every query failed and WmiPrvSE burned a core (#3939).
+ * The loop gives up after `maxStarts` early exits in a row, so a counter that cannot be read stays quiet.
+ */
+import { spawn } from 'node:child_process';
+
+export function createPowerShellLoop({ script, onLine, spawnFn = spawn, maxStarts = 3 }) {
+  let child = null, starts = 0, buffer = '';
+  function start() {
+    if (child || starts >= maxStarts) return;
+    starts++;
+    let proc;
+    try { proc = spawnFn('powershell.exe', ['-NoProfile', '-NonInteractive', '-Command', script], { windowsHide: true, stdio: ['ignore', 'pipe', 'ignore'] }); }
+    catch { return; }
+    child = proc;
+    buffer = '';
+    proc.on?.('error', () => { if (child === proc) child = null; });
+    proc.on?.('exit', () => { if (child === proc) child = null; });
+    proc.stdout?.on('data', chunk => {
+      buffer += chunk;
+      let i;
+      while ((i = buffer.indexOf('\n')) >= 0) {
+        const line = buffer.slice(0, i);
+        buffer = buffer.slice(i + 1);
+        if (onLine(line)) starts = 0;
+      }
+    });
+    proc.unref?.();
+    proc.stdout?.unref?.();
+  }
+  return {
+    start,
+    stop() { try { child?.kill(); } catch { /* gone */ } child = null; },
+    get starts() { return starts; },
+  };
+}
+
+let stoppers = null;
+/** Every loop is ended with the host. */
+export function endWithHost(loop) {
+  if (!stoppers) { stoppers = new Set(); process.once('exit', () => stoppers.forEach(l => l.stop())); }
+  stoppers.add(loop);
+  return loop;
+}

apps/host/src/components/ChatModelPicker.tsx

@@ -4,7 +4,7 @@ import { useId, useRef, useState } from 'react';
 import { FloatingMenu } from './FloatingMenu';
 import { Bar, Btn, Dialog, ErrorNotice, Icon } from './ui';
 import { go, useLifecycle, loadVariant, selectRemoteModel, setSettingsSection, useStore } from '../lib/store';
-import { pickerGroups, pickerVersionState } from '../lib/model-picker';
+import { pickerGroups, pickerNativeModels, pickerVersionState } from '../lib/model-picker';
 import { versionFit } from '../lib/model-versions';
 import type { ModelVariant } from '../lib/types';
 import { sizeGb } from '../lib/format';
@@ -37,6 +37,7 @@ function LegacyChatModelPicker() {
     const running = library?.variants.find(v => v.id === library.loaded);
     const version = library?.variants.find(v => v.id === selected);
     const groups = library ? pickerGroups(library) : [];
+    const installedNative = pickerNativeModels(native?.installed?.models, native?.instances);
     const status = version ? pickerVersionState(version, library?.loaded ?? null) : null;
     const tooBig = !!version && library?.mode === 'real' && versionFit(version, hardware, contextTokens(engine?.beginner.contextLength ?? '32K')).zone === 'too-big';
     async function apply() {
@@ -78,7 +79,8 @@ function LegacyChatModelPicker() {
     <button ref={trigger} className="chat-model-badge chat-model-picker" aria-label={tr("Choose model: {0}", [apiModel?.name ?? (running?.local ? running.name : running?.family) ?? 'No model loaded'])} title={tr(apiModel ? `${connection?.name} · ${apiModel.id}` : 'View and switch models')} disabled={!library && !providers} aria-haspopup="menu" aria-expanded={open} onClick={() => setOpen(v => !v)}><Icon name={apiModel ? 'link' : modelFamilyIcon(running?.family ?? groups[0]?.family)} size={16}/><span>{tr(apiModel?.name ?? (running?.local ? running.name : running?.family) ?? groups[0]?.family ?? 'No model loaded')}</span><Icon name="chevron" size={12}/></button>
     {tr(open ? <FloatingMenu anchor={trigger.current} title={tr("Models")} width={380} onClose={() => setOpen(false)}>
       {tr(native?.instances.filter(i => i.status !== 'error').map(i => <button key={i.id} className="menu__item" role="menuitem" disabled={streaming || i.status !== 'ready'} onClick={() => void nativeAction(`instances/${i.id}/default`).then(() => { selectRemoteModel(null); setOpen(false); }).catch(e => setError(e.message))}><Icon name="models"/><span>{tr(i.label)}<small>{tr(i.gpus.map(g => `GPU ${g + 1}`).join(" + ") || "Automatic GPU")}</small></span></button>))}<p className="model-picker-heading">{tr("Local models")}</p>
-      {tr(!groups.length ? <p className="model-picker-empty">{tr("No local models downloaded yet.")}</p> : null)}
+      {tr(installedNative.map(m => <button key={m.config || m.model} className="menu__item model-picker-option model-picker-api" role="menuitem" disabled={streaming} onClick={() => { setOpen(false); go('models'); }}><span><strong>{tr(m.model_name || m.model)}</strong><small>{tr("Downloaded, not loaded. Open Models to load it.")}</small></span></button>))}
+      {tr(!groups.length && !installedNative.length ? <p className="model-picker-empty">{tr("No local models downloaded yet.")}</p> : null)}
       {tr(groups.map(({ family, versions }, index) => {
                 const main = versions[0], state = pickerVersionState(main, library!.loaded);
                 const others = versions.slice(1), isExpanded = expanded.includes(family), id = `${groupsId}-${index}`;

apps/host/src/components/ComposerControls.tsx

@@ -5,10 +5,11 @@ import { FloatingMenu } from './FloatingMenu';
 import { DictationControl } from './DictationControl';
 import { Btn, Dialog, Icon, ErrorNotice } from './ui';
 import { MOD } from '../lib/commands';
-import { setChatPreferences, useStore } from '../lib/store';
+import { pushToast, setChatPreferences, useStore } from '../lib/store';
 import { artifactFromUrl, type PreviewArtifact } from '../lib/artifacts';
 import type { ChatMode, Session } from '../lib/types';
 import { attachChatPhoto } from '../lib/chat-photos';
+import { uploadChatFile, FILE_ACCEPT } from '../lib/chat-attach-file';
 import { useNative } from '../lib/native';
 import { pictureStatus } from '../lib/pictures';
 const modes: {
@@ -91,6 +92,12 @@ export function ComposerControls({ session, onPreview, onAttach, onError, onSlas
                     await attachChatPhoto(file, session?.id);
                     continue;
                 }
+                if (!directory && session?.id && /\.pdf$/i.test(file.name) && file.size <= 12 * 1024 * 1024) {
+                    // A PDF goes to the chat's folder and is named in the next message; "Open a file" still previews it.
+                    const saved = await uploadChatFile(file, session.id);
+                    pushToast('success', 'PDF added', `${saved.name} is in this chat. Ask about it in your next message.`);
+                    continue;
+                }
                 if (!directory && (photoTypes.test(file.name) || /\.pdf$/i.test(file.name))) {
                     await openFile(file);
                     if (photoTypes.test(file.name))
@@ -157,7 +164,7 @@ export function ComposerControls({ session, onPreview, onAttach, onError, onSlas
     return <>
     {tr(!remoteModel && nativeModel?.metrics?.mcp?.servers?.length ? <button className="composer-choice" aria-label={tr("Use connected MCP tools")} aria-pressed={session?.preferences?.useTools === true} onClick={() => session?.preferences?.useTools ? setChatPreferences(session.id, { useTools: false }) : setToolsOpen(true)}><Icon name="skills" size={16}/>{tr("Tools")}{tr(session?.preferences?.useTools ? ' on' : '')}</button> : null)}
     <Dialog open={toolsOpen} compact title={tr("Enable connected tools?")} onClose={() => setToolsOpen(false)} actions={<><Btn onClick={() => setToolsOpen(false)}>{tr("Keep tools off")}</Btn><Btn variant="primary" onClick={() => { setChatPreferences(session?.id, { useTools: true, mode: 'bypass' }); setToolsOpen(false); }}>{tr("Enable tools")}</Btn></>}><p>{tr("Connected servers can act on the resources you configured. Calls run automatically when the model chooses them, and their results appear in chat.")}</p><p className="small muted">{tr("This switches this conversation to Bypass permissions. Servers: ")}{tr((nativeModel?.metrics?.mcp?.servers ?? []).map((s: any) => s.name).join(', '))}.</p></Dialog>
-    <input ref={files} type="file" multiple hidden accept="image/*,.pdf,.txt,.md,.markdown,.csv,.ts,.tsx,.js,.jsx,.py,.json,.css,.rs,.go,.sh,.html,.htm,.yaml,.yml,.toml,.xml,.log" onChange={e => { void addFiles(Array.from(e.target.files ?? [])); e.target.value = ''; }}/>
+    <input ref={files} type="file" multiple hidden accept={FILE_ACCEPT} onChange={e => { void addFiles(Array.from(e.target.files ?? [])); e.target.value = ''; }}/>
     <input ref={folder} type="file" multiple hidden onChange={e => { void addFiles(Array.from(e.target.files ?? []), true); e.target.value = ''; }}/>
     <input ref={previewFile} type="file" hidden onChange={e => { void openFile(e.target.files?.[0]); e.target.value = ''; }}/>
     <button ref={trigger} className="composer-add" aria-label={tr("Add or open")} title={tr("Add or open")} disabled={reading || streaming} aria-haspopup="menu" aria-expanded={menu} onClick={() => { setPreferences(null); setMenu(v => !v); }}><Icon name="plus" size={22}/></button>

apps/host/src/components/DecimalInput.tsx

@@ -0,0 +1,28 @@
+import { useEffect, useState } from 'react';
+import { parseDecimal, partialDecimal } from '../lib/decimal';
+
+/** A number field that lets the person type a decimal point: it keeps the text while it is typed and tells the page the number once it is one (#3736). */
+export function DecimalInput({ value, onChange, ariaLabel, className = 'st-input', placeholder, disabled }: {
+  value: number | null | undefined;
+  onChange: (value: number | null) => void;
+  ariaLabel: string;
+  className?: string;
+  placeholder?: string;
+  disabled?: boolean;
+}) {
+  const [text, setText] = useState(value === null || value === undefined ? '' : String(value));
+  // A change that came from elsewhere (Restore saved, another tab) replaces the text, but never while the typed text already means this number.
+  useEffect(() => {
+    const shown = text === '' ? null : parseDecimal(text);
+    if ((value ?? null) !== shown) setText(value === null || value === undefined ? '' : String(value));
+  }, [value]);
+  return <input className={className} aria-label={ariaLabel} inputMode="decimal" disabled={disabled} placeholder={placeholder} value={text}
+    onChange={e => {
+      const next = e.target.value;
+      if (!partialDecimal(next)) return;
+      setText(next);
+      if (next.trim() === '') onChange(null);
+      else { const n = parseDecimal(next); if (n !== null) onChange(n); }
+    }}
+    onBlur={() => { const n = text.trim() === '' ? null : parseDecimal(text); setText(n === null ? '' : String(n)); }}/>;
+}

apps/host/src/components/DropZone.tsx

@@ -6,16 +6,7 @@ import { Icon } from './ui';
 
 /** Files dropped on the chat go where the attach button would put them: the composer reads the 'strata:drop-files' event. */
 export const DROP_EVENT = 'strata:drop-files';
-/** The pictures on the clipboard, named so each one is told apart in the composer (a pasted screenshot arrives as "image.png"). */
-export function pastedFiles(data: DataTransfer | null | undefined): File[] {
-  const out: File[] = [];
-  for (const file of Array.from(data?.files ?? [])) {
-    if (!file.type.startsWith('image/')) continue;
-    const extension = file.type.split('/')[1]?.replace('jpeg', 'jpg').replace(/[+].*/, '') || 'png';
-    out.push(new File([file], `Pasted picture ${new Date().toLocaleTimeString().replace(/[^0-9]+/g, '-').replace(/-$/, '')}${out.length ? `-${out.length + 1}` : ''}.${extension}`, { type: file.type }));
-  }
-  return out;
-}
+export { pastedFiles } from '../lib/pasted-files';
 const hasFiles = (e: React.DragEvent) => Array.from(e.dataTransfer?.types ?? []).includes('Files');
 
 /** A file dropped outside the chat must not take the window to that file: the page ignores it (called once at start). */

apps/host/src/components/EngineFirstRun.tsx

@@ -0,0 +1,173 @@
+import { tr } from '../lib/i18n';
+import { useCallback, useEffect, useRef, useState } from 'react';
+import { Brand } from './Brand';
+import { Bar, Btn, Icon } from './ui';
+import { api } from '../lib/client';
+import { useDownloadEta } from '../lib/download-eta';
+import type { NativeJob } from '../lib/native';
+import { megabytes } from '../lib/format';
+
+/** What the host says about this PC's engine (GET /api/engine/first-run). */
+export interface FirstRunInfo {
+    status: 'offer' | 'none' | 'offline' | 'error' | 'installed' | 'wrong-make' | 'unavailable';
+    gpus: { name: string; vramGb: number | null }[];
+    driver?: string | null;
+    offer?: { version: string; bytes: number; variant: string; backend: string | null };
+    message?: string | null;
+    reasons?: string[];
+    details?: string;
+    freeBytes?: number;
+}
+
+export const mb = megabytes;
+
+/**
+ * Whether this PC still needs its engine. Reads only Control's local answer (no network): the engine is missing and the engine that came
+ * with the app is not being unpacked. `null` while that is not known yet.
+ */
+export function useEngineNeeded(): boolean | null {
+    const [needed, setNeeded] = useState<boolean | null>(null);
+    useEffect(() => {
+        let live = true;
+        const ask = () => api.get<{ engine?: { usable?: boolean } | null; engineSetup?: boolean }>('/api/control/status').then(s => {
+            if (!live) return;
+            if (s.engineSetup) return setNeeded(null);
+            setNeeded(!!s.engine && s.engine.usable === false);
+        }, () => { if (live) setNeeded(false); });
+        void ask();
+        const timer = setInterval(() => void ask(), 3000);
+        return () => { live = false; clearInterval(timer); };
+    }, []);
+    return needed;
+}
+
+function gpuLine(info: FirstRunInfo) {
+    // a processor's own tiny graphics (no memory of its own) is not "a card"
+    const first = info.gpus.find(g => (g.vramGb ?? 0) >= 1) ?? info.gpus[0];
+    if (!first) return '';
+    const vram = first.vramGb ? `, ${Math.round(first.vramGb)} GB` : '';
+    const driver = info.driver ? `, driver ${info.driver}` : '';
+    return `${first.name}${vram}${driver}`;
+}
+
+/**
+ * The first-run card: the engine this PC needs, one button to download it, progress, and the offline way (choose a downloaded file).
+ * Nothing is downloaded before a button is pressed.
+ */
+export function EngineFirstRun({ onDone }: { onDone: () => void }) {
+    const [info, setInfo] = useState<FirstRunInfo | null>(null);
+    const [job, setJob] = useState<NativeJob | null>(null);
+    const [busy, setBusy] = useState(false), [problem, setProblem] = useState('');
+    const [finished, setFinished] = useState(false);
+    const file = useRef<HTMLInputElement>(null);
+    const started = useRef(false);
+
+    const look = useCallback(() => {
+        setInfo(null);
+        setProblem('');
+        api.get<FirstRunInfo>('/api/engine/first-run').then(setInfo, e => setInfo({ status: 'error', gpus: [], message: e instanceof Error ? e.message : String(e) }));
+    }, []);
+    useEffect(() => { look(); }, [look]);
+
+    // follow the download / install job
+    useEffect(() => {
+        const timer = setInterval(() => {
+            if (!started.current) return;
+            api.get<{ job: NativeJob | null }>('/api/engine/job').then(r => {
+                setJob(r.job);
+                if (r.job?.state === 'done') setFinished(true);
+                if (r.job && r.job.state !== 'running') started.current = false;
+            }, () => { });
+        }, 700);
+        return () => clearInterval(timer);
+    }, []);
+
+    async function start() {
+        setBusy(true);
+        setProblem('');
+        try {
+            started.current = true;
+            setJob(await api.post<NativeJob>('/api/native/operations', { kind: 'update-engine', args: {} }));
+        }
+        catch (e) {
+            started.current = false;
+            setProblem(e instanceof Error ? e.message : String(e));
+        }
+        finally {
+            setBusy(false);
+        }
+    }
+    async function chosen(files: FileList | null) {
+        const picked = files?.[0];
+        if (!picked) return;
+        setBusy(true);
+        setProblem('');
+        try {
+            const response = await fetch('/api/engine/from-file', { method: 'POST', headers: { 'x-file-name': picked.name }, body: picked });
+            const body = await response.json().catch(() => ({}));
+            if (!response.ok) throw new Error(body?.error ?? `The file could not be used (${response.status}).`);
+            started.current = true;
+            setJob(body as NativeJob);
+        }
+        catch (e) {
+            setProblem(e instanceof Error ? e.message : String(e));
+        }
+        finally {
+            setBusy(false);
+            if (file.current) file.current.value = '';
+        }
+    }
+
+    const running = job?.state === 'running';
+    const failed = !!job && (job.state === 'error' || job.state === 'cancelled');
+    const percent = Number(job?.result?.install?.download?.percent ?? 0);
+    const bytes = info?.offer?.bytes ?? 0;
+    const doneMb = Math.round(mb(bytes) * percent / 100);
+    const eta = useDownloadEta(running && bytes ? { done_gb: bytes * percent / 100 / 1e9, remaining_gb: bytes * (100 - percent) / 100 / 1e9 } : undefined, job?.id);
+    const cards = (info?.gpus ?? []).filter(g => (g.vramGb ?? 0) >= 1).length;
+    const hidden = <input ref={file} type="file" accept=".gz,.tgz,.xz,.zip" hidden onChange={e => void chosen(e.target.files)}/>;
+    const pick = (label: string) => <button type="button" className="onboard-continue-anyway" disabled={busy || running} onClick={() => file.current?.click()}>{tr(label)}</button>;
+
+    let body;
+    if (finished) {
+        body = <><div className="onboard-welcome-copy"><h1 tabIndex={-1} data-initial-focus>{tr("The engine is ready.")}</h1><p>{tr("Next: pick a model.")}</p></div>
+            <footer className="onboard-footer onboard-footer--welcome"><Btn variant="primary" onClick={onDone}>{tr("Continue")}<Icon name="chevron" size={16}/></Btn></footer></>;
+    }
+    else if (running) {
+        body = <><div className="onboard-welcome-copy"><h1 tabIndex={-1} data-initial-focus>{tr("Downloading the engine")}</h1>
+            <p>{bytes && job?.result?.install?.download ? `${doneMb} of ${mb(bytes)} MB${eta ? ' · ' + eta : ''}` : tr(job?.summary ?? 'Starting…')}</p></div>
+            <div className="onboard-error" style={{ maxWidth: 520, margin: '0 auto', width: '100%' }}><Bar value={percent} label="Downloading the engine"/><p className="small muted" style={{ textAlign: 'center' }}>{tr("You can close Strata; it continues where it stopped.")}</p></div></>;
+    }
+    else if (!info) {
+        body = <div className="onboard-welcome-copy"><h1 tabIndex={-1} data-initial-focus>{tr("Welcome to Strata")}</h1><p role="status">{tr("Looking at your graphics card…")}</p></div>;
+    }
+    else {
+        const card = gpuLine(info);
+        const found = card ? <p>{tr("Strata found your graphics card:")}<br/><strong>{card}</strong>{cards > 1 ? <><br/><span className="small muted">{tr("{0} cards found. Strata uses the first one for the engine; change it later in Settings.", [cards])}</span></> : null}</p>
+            : <p>{tr("Strata did not recognise a supported graphics card.")}</p>;
+        let main, actions;
+        if (info.status === 'offer' && info.offer) {
+            main = <>{found}<p>{tr("To run models on it, Strata needs one download:")}<br/><strong>{tr("The engine for this card")}: {mb(info.offer.bytes)} MB</strong></p>
+                {info.freeBytes !== undefined && info.freeBytes < info.offer.bytes * 2.5 ? <p className="small inline-error">{tr("The engine needs about {0} GB of free space on this drive and only {1} GB is free. Free some space, then continue.", [Math.ceil(info.offer.bytes * 2.5 / 1e9), (info.freeBytes / 1e9).toFixed(1)])}</p> : null}
+                <p className="small muted">{tr("It comes from Strata’s own update server and is checked before it is used. Your models and chats are never touched by it.")}</p></>;
+            actions = <><Btn variant="primary" disabled={busy} onClick={() => void start()}>{tr(failed ? 'Continue' : 'Download the engine')}</Btn>{pick("I already have the file…")}</>;
+        }
+        else if (info.status === 'offline') {
+            main = <>{found}<p>{tr("Strata could not reach github.com. Check your connection and try again, or download the engine file on another PC and choose it here.")}</p></>;
+            actions = <><Btn variant="primary" disabled={busy} onClick={look}>{tr("Try again")}</Btn>{pick("Choose a downloaded file…")}</>;
+        }
+        else if (info.status === 'wrong-make') {
+            main = <>{found}<p>{info.message ?? tr("The engine installed here is for another make of graphics card.")}</p></>;
+            actions = <><Btn variant="primary" disabled={busy} onClick={look}>{tr("Try again")}</Btn>{pick("Choose a downloaded file…")}</>;
+        }
+        else {
+            main = <>{found}<p>{tr("Strata can’t pick an engine for this PC from its update list.")}</p>{info.message ? <p className="small muted">{info.message}</p> : null}{(info.reasons ?? []).length ? <ul className="small muted" style={{ textAlign: 'left', display: 'inline-block' }}>{(info.reasons ?? []).map(r => <li key={r}>{r}</li>)}</ul> : null}</>;
+            actions = <><Btn variant="primary" disabled={busy} onClick={look}>{tr("Try again")}</Btn>{pick("Choose a downloaded file…")}<button type="button" className="onboard-continue-anyway" onClick={onDone}>{tr("Continue without an engine")}</button></>;
+        }
+        body = <><div className="onboard-welcome-copy"><h1 tabIndex={-1} data-initial-focus>{tr("Welcome to Strata")}</h1>{main}</div>
+            {failed ? <div className="onboard-error" style={{ maxWidth: 560, margin: '0 auto' }}><p role="alert" className="small inline-error">{job?.error ?? job?.summary}</p><p className="small muted">{tr("The download stopped. Continue picks it up where it stopped.")}</p></div> : null}
+            {problem ? <div className="onboard-error" style={{ maxWidth: 560, margin: '0 auto' }}><p role="alert" className="small inline-error">{problem}</p></div> : null}
+            <footer className="onboard-footer onboard-footer--welcome">{actions}</footer></>;
+    }
+    return <div className="setup guided-onboarding" data-step="engine">{hidden}<header className="onboard-header"><Brand variant="lockup" height={22}/></header>{body}</div>;
+}

apps/host/src/components/GuidedSetup.tsx

@@ -22,6 +22,15 @@ type Choices = NonNullable<NonNullable<SetupState['choices']>['onboarding']>;
 function radioKeys(event: KeyboardEvent<HTMLDivElement>) { if (!['ArrowLeft', 'ArrowRight', 'ArrowUp', 'ArrowDown', 'Home', 'End'].includes(event.key))
     return; event.preventDefault(); const items = Array.from(event.currentTarget.querySelectorAll<HTMLButtonElement>('[role=radio]')); const current = items.indexOf(event.target as HTMLButtonElement); const next = event.key === 'Home' ? 0 : event.key === 'End' ? items.length - 1 : (current + (['ArrowLeft', 'ArrowUp'].includes(event.key) ? -1 : 1) + items.length) % items.length; items[next]?.focus(); items[next]?.click(); }
 const steps = ['Welcome', 'Your model', 'Prepare', 'Make it yours'];
+/** What a person is told before choosing DeepSeek: the size, where it runs, how fast, what it needs. Every line is a warning or a fact; nothing here stops the download. */
+function DeepSeekNote({ version, plan }: { version: NonNullable<ReturnType<typeof nativeCatalogModels>[number]['sizes'][number]>; plan: Record<string, any> | null }) {
+    void plan;   // the plan's own disk line repeats what the version says in on_this_pc
+    return <div className="engine-warning" role="status"><Icon name="info" size={18}/><div>
+        <p>{tr("This is a very large model. The download is {0} GB and it needs about as much free disk space. It runs on one 12 GB graphics card with 46 to 64 GB of RAM, slowly: about 5 to 7 words a second. What does not fit in memory is read from your SSD, so an NVMe drive matters.", [Math.round(version.download_gb)])}</p>
+        {version.on_this_pc ? <p className="small muted">{version.on_this_pc}</p> : null}
+        <p className="small muted">{tr("You can stop the download and continue later; it picks up where it stopped. Strata warns you here but never blocks you.")}</p>
+    </div></div>;
+}
 export function GuidedSetup() {
     const native = useNative(), setup = useStore(s => s.setup), hardware = useStore(s => s.hardware);
     const families = nativeCatalogModels(native?.catalog?.families ?? []);
@@ -132,7 +141,8 @@ export function GuidedSetup() {
         setTuneJobId(tuneJob.id);
         void persist(4, { tuneJobId: tuneJob.id }).catch(e => setError(e.message));
     } }, [step, installJob?.id, tuneJob?.id]);
-    const values = { guided: true, family: version?.sourceFamily, model: version?.model, context, vision: version?.images ? 'yes' : 'no', kv: 'int8', low_ram: 'auto', loadAfter: false, multiple: false, ...(directory ? { data_dir: directory } : {}) };
+    const fixedContext = version?.multi_file ? 8192 : null;      // the one context DeepSeek's engine was checked at
+    const values = { guided: true, family: version?.sourceFamily, model: version?.model, context: fixedContext ?? context, vision: version?.images ? 'yes' : 'no', kv: 'int8', low_ram: 'auto', loadAfter: false, multiple: false, ...(directory ? { data_dir: directory } : {}) };
     async function review() {
         await perform(async () => {
             setInstallJobId('');
@@ -154,7 +164,7 @@ export function GuidedSetup() {
     }
     async function tune() {
         await perform(async () => {
-            const result = await nativeAction<NativeJob>('operations', { kind: 'tune', args: { guided: true, model: version?.id, profile, calibrate, vision: version?.images && vision ? 'yes' : 'no', multiple: false } });
+            const result = await nativeAction<NativeJob>('operations', { kind: 'tune', args: { guided: true, model: version?.id, profile, calibrate: calibrate && !version?.multi_file, vision: version?.images && vision ? 'yes' : 'no', multiple: false } });
             setTuneJobId(result.id);
             await persist(4, { tuneJobId: result.id });
         });
@@ -201,9 +211,10 @@ export function GuidedSetup() {
    <div className="onboard-stage-heading"><h1 ref={titleRef} tabIndex={-1} data-initial-focus>{tr(title)}</h1>{tr(step === 2 ? <p>{tr("You can always change your models later.")}</p> : step === 4 && tuneJob?.state === 'running' ? <p>{tr("We\u2019re measuring, applying your preference, and getting ready to chat.")}</p> : null)}</div>
    {tr(step === 2 ? <div className="onboard-model-stage">
     {tr(selectedFamily ? <>
-     <div className="onboard-model-top"><div className="onboard-model-picker"><span className="onboard-control-label">{tr("Model")}</span><div><span className="onboard-model-symbol"><Icon name="models" size={23}/></span><Select ariaLabel={tr("Setup model")} value={selectedFamily.family} options={families.map(f => ({ value: f.family, label: f.title }))} onChange={value => chooseNative(value, '')}/></div></div><div className="onboard-context"><span className="onboard-control-label">{tr("Conversation context")}</span><Select ariaLabel={tr("Setup conversation context")} value={String(context)} options={(native?.catalog?.contexts ?? [32768]).map(n => ({ value: String(n), label: `${n / 1024}K` }))} onChange={value => setContext(Number(value))}/></div></div>
+     <div className="onboard-model-top"><div className="onboard-model-picker"><span className="onboard-control-label">{tr("Model")}</span><div><span className="onboard-model-symbol"><Icon name="models" size={23}/></span><Select ariaLabel={tr("Setup model")} value={selectedFamily.family} options={families.map(f => ({ value: f.family, label: f.title }))} onChange={value => chooseNative(value, '')}/></div></div><div className="onboard-context"><span className="onboard-control-label">{tr("Conversation context")}</span><Select ariaLabel={tr("Setup conversation context")} value={String(version?.multi_file ? 8192 : context)} options={(version?.multi_file ? [8192] : native?.catalog?.contexts ?? [32768]).map(n => ({ value: String(n), label: `${n / 1024}K` }))} onChange={value => setContext(Number(value))}/></div></div>
      <OnboardingMemory hardware={hardware} native={native?.hardware}/>{tr(!version || version.needsNewerEngine ? <p className="small muted">{tr("This model needs a newer engine. Update your engine or import a local GGUF for this model.")}</p> : null)}
      <div className="onboard-version-heading"><strong>{tr("Choose a version")}</strong><span>{tr(version ? `${catalogVersionLabel(version)} selected` : '')}</span></div>
+     {tr(version?.multi_file ? <DeepSeekNote version={version} plan={plan}/> : null)}
      <div className="onboard-versions" role="radiogroup" aria-label={tr("Model version")} onKeyDown={radioKeys}>{tr(cards.map(v => versionCard(v)))}</div>
      {tr(others.length ? <div className="onboard-more-versions"><VersionPicker versions={others} selectedId={version?.id ?? ''} hardware={hardware ? { ram_gb: native?.hardware?.ram_gb ?? hardware.memory.totalGb, vram_gb: Math.max(0, ...(native?.hardware?.gpus ?? []).filter(g => g.usable !== false).map(g => g.vram_gb)) } : null} downloaded={readyIds} showRecommended={false} moreLabel="More versions" onSelect={id => { setSize(id); setPlan(null); }} onOwnGguf={() => void ownModel()}/></div> : null)}
      <div className="onboard-folder"><Icon name="folder" size={20}/><div><strong>{tr(directory ? 'Your model folder' : 'Already downloaded the model?')}</strong><small>{tr(directory || "Choose the folder and we'll start your models with Strata.")}</small></div><Btn size="sm" onClick={() => setFolderOpen(v => !v)}>{tr(folderOpen ? 'Close' : directory ? 'Change' : 'Choose folder')}</Btn></div>

apps/host/src/components/Markdown.tsx

@@ -1,4 +1,5 @@
 import { tr } from '../lib/i18n';
+import { copyText } from '../lib/clipboard';
 /** Safe, dependency-free rendering of the Markdown structures used in answers. */
 import { Fragment, type ReactNode } from 'react';
 import { Btn, IconBtn } from './ui';
@@ -47,6 +48,20 @@ function inline(text: string, onOpenLink?: (url: string) => void, imageSession?:
             : <Fragment key={p}>{inlineMarks(part.text, onOpenLink, imageSession)}</Fragment>)}</Fragment>;
     });
 }
+/** Does this line continue the paragraph above it, or does it start a block of its own? */
+export function continuesParagraph(lines: string[], at: number): boolean {
+    const line = lines[at];
+    if (!line.trim() || /^\s*```/.test(line) || /^(#{1,6})\s+(.+)$/.test(line) || /^\s*[-*+]\s+\S/.test(line) || /^\s*\d+[.)]\s+\S/.test(line) || /^>\s?/.test(line))
+        return false;
+    if (line.includes('|') && at + 1 < lines.length && /^\s*\|?\s*:?-{3,}/.test(lines[at + 1]))
+        return false;
+    return !displayBlock(lines, at);
+}
+/** Copy a code block. The toast store needs a browser, so it is loaded here, when someone copies: the renderer itself must render without one. */
+async function copyCode(text: string) {
+    const { pushToast } = await import('../lib/store');
+    await copyText(text, 'Code', { toast: pushToast });
+}
 export function Markdown({ text, onOpenLink, onPreviewHtml, imageSession }: {
     text: string;
     onOpenLink?: (url: string) => void;
@@ -69,7 +84,7 @@ export function Markdown({ text, onOpenLink, onPreviewHtml, imageSession }: {
             while (i < lines.length && !/^\s*```/.test(lines[i]))
                 body.push(lines[i++]);
             i++;
-            nodes.push(<div className="st-code" key={key}><div className="st-code__head"><span>{language || tr('code')}</span>{tr(/^html$/i.test(language) && onPreviewHtml ? <Btn size="sm" onClick={() => onPreviewHtml(body.join('\n'))}>{tr("Open preview")}</Btn> : null)}<IconBtn name="copy" title={tr("Copy code")} onClick={() => void navigator.clipboard.writeText(body.join('\n'))}/></div><SyntaxCode text={body.join('\n')} language={language}/></div>);
+            nodes.push(<div className="st-code" key={key}><div className="st-code__head"><span>{language || tr('code')}</span>{tr(/^html$/i.test(language) && onPreviewHtml ? <Btn size="sm" onClick={() => onPreviewHtml(body.join('\n'))}>{tr("Open preview")}</Btn> : null)}<IconBtn name="copy" title={tr("Copy code")} onClick={() => void copyCode(body.join('\n'))}/></div><SyntaxCode text={body.join('\n')} language={language}/></div>);
             continue;
         }
         const block = displayBlock(lines, i);
@@ -113,8 +128,19 @@ export function Markdown({ text, onOpenLink, onPreviewHtml, imageSession }: {
             i++;
             continue;
         }
-        nodes.push(<p key={i}>{tr(inline(line, onOpenLink, imageSession))}</p>);
+        // One paragraph: a single newline inside it is a soft break (a space); two spaces or a backslash at the end of a line is a hard break (#3818).
+        const key = i, parts: ReactNode[] = [];
+        let current = line;
         i++;
+        while (true) {
+            const hard = /( {2,}|\\)$/.test(current);
+            parts.push(<Fragment key={parts.length}>{tr(inline(current.replace(/( {2,}|\\)$/, ''), onOpenLink, imageSession))}</Fragment>);
+            if (i >= lines.length || !continuesParagraph(lines, i))
+                break;
+            parts.push(hard ? <br key={`b${parts.length}`}/> : ' ');
+            current = lines[i++].trimStart();
+        }
+        nodes.push(<p key={key}>{tr(parts)}</p>);
     }
     return <>{tr(nodes)}</>;
 }

apps/host/src/components/NativeModels.tsx

@@ -204,7 +204,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
     {tr(expert && IMAGE_GENERATION_VISIBLE ? <><details className="native-generation"><summary>{tr("Image generation ")}<span className="muted">{tr("Optional")}</span></summary><RunImageModel library={imageLibrary} disabled={pending || !!active} onChange={() => { }}/></details></> : null)}
     {tr(expert ? <section id="native-expert-settings" ref={expertSection} className="st-card native-execution"><h2 className="h4">{tr("Expert settings")}</h2>{tr(tunedNow ? <p className="small muted native-tuned-note">{tr("Showing the values of your tuning '{0}'.", [tunedNow.name])}</p> : null)}<label className="native-toggle"><span><strong>{tr("Run multiple models")}</strong><small>{tr("Loading another model keeps the others loaded.")}</small></span><button className="st-toggle" role="switch" aria-label={tr("Run multiple models")} aria-checked={multiple} onClick={() => setMultiple(v => !v)}/></label>{tr(cardsGpus.length > 1 ? <label className="input-field"><span>{tr("Layer split")}</span><input className="st-input" value={split} placeholder={tr("auto or 16,32")} onChange={e => setSplit(e.target.value)}/></label> : null)}<div className="native-field-grid"><label className="input-field"><span>{tr("Context memory")}</span><Select ariaLabel={tr("Native KV format")} value={kv} options={[{ value: 'int8', label: 'INT8' }, { value: 'q4_0', label: 'Q4' }, { value: 'k8v4', label: 'K8 / V4' }]} onChange={setKv}/></label><label className="input-field"><span>{tr("Low-RAM mode")}</span><Select ariaLabel={tr("Native low RAM mode")} value={lowRam} options={['auto', 'resident', 'mmap'].map(v => ({ value: v, label: v === 'auto' ? 'Automatic' : v === 'resident' ? 'Keep experts in RAM' : 'Read experts from disk' }))} onChange={setLowRam}/></label></div>{tr(installed ? <><NativeSettingsFile model={installed.model}/><NativeSettings model={installed.model}/></> : <p className="small muted">{tr("More engine parameters become available after preparing this version.")}</p>)}</section> : null)}
    </div>
-   <aside className="stack stack--lg"><PcFitCard gpuName={pcGpu?.name} ramGb={pcRam} vramGb={pcVram} inUse={keptModels.length ? { ramGb: Math.round(keptRam), vramGb: Math.round(keptVramOn(chosenCards)) } : null} fit={selectedSize ? fitOn(selectedSize, fitHardware) : null}/><section className="st-card"><h2 className="h4">{tr("Model files")}</h2><p className="small muted">{tr("Strata prepares all shards, the draft layer and shared files. Completed downloads are reused.")}</p><code className="native-path">{installed?.dataFolder ?? native?.downloadDirectory ?? native?.installed?.data_folder ?? 'Choose an installation'}</code><Btn size="sm" variant="ghost" onClick={() => { setSettingsSection('Storage'); go('settings'); }}>{tr("Storage settings")}</Btn></section><Btn size="sm" variant="ghost" onClick={onOtherModels}>{tr("Other local models\u2026")}</Btn></aside>
+   <aside className="stack stack--lg"><PcFitCard gpuName={pcGpu?.name} ramGb={pcRam} vramGb={pcVram} inUse={keptModels.length ? { ramGb: Math.round(keptRam), vramGb: Math.round(keptVramOn(chosenCards)) } : null} fit={selectedSize ? fitOn(selectedSize, fitHardware, true, { context, kv }) : null}/><section className="st-card"><h2 className="h4">{tr("Model files")}</h2><p className="small muted">{tr("Strata prepares all shards, the draft layer and shared files. Completed downloads are reused.")}</p><code className="native-path">{installed?.dataFolder ?? native?.downloadDirectory ?? native?.installed?.data_folder ?? 'Choose an installation'}</code><Btn size="sm" variant="ghost" onClick={() => { setSettingsSection('Storage'); go('settings'); }}>{tr("Storage settings")}</Btn></section><Btn size="sm" variant="ghost" onClick={onOtherModels}>{tr("Other local models\u2026")}</Btn></aside>
   </div>
   
 <Dialog open={!!plan} title={tr(installed?.ready ? "Apply settings and load" : "Download and prepare")} compact onClose={() => !pending && setPlan(null)} actions={<><Btn disabled={pending} onClick={() => setPlan(null)}>{tr("Cancel")}</Btn><Btn variant="primary" disabled={pending || !!plan?.plan?.disk_short} onClick={() => void download()}>{tr(installed?.ready ? "Apply & load" : "Download & load")}</Btn></>}><p><strong>{tr(plan?.plan?.title ?? selectedFamily?.title)}</strong>{tr(installed?.ready ? null : <>{tr(" \u00B7 approximately ")}{tr(plan?.plan?.download_gb ?? selectedSize?.download_gb)}{tr(" GB")}</>)}</p>{tr(plan?.drafting?.needed ? <p className="small muted">{tr("Choosing DFlash2 also downloads its drafter: about {0} GB, once. If it does not fit in graphics memory, the model uses the MTP instead.", [plan.drafting.gb])}</p> : null)}{tr(installed?.ready ? <p className="small muted">{tr("The model files are already on this computer. Nothing will be downloaded; only the settings you chose are applied.")}</p> : null)}{tr(plan?.plan?.disk_short ? <ErrorNotice message={plan.plan.disk_short}/> : null)}{tr(installed?.ready ? <p className="small muted">{tr("Any currently loaded native models will be unloaded first.")}</p> : <><p className="small muted">{tr("Existing files are checked and reused. Any currently loaded native models will be unloaded before preparing files.")}</p><p className="small muted">{tr("Your computer may feel slower while weights load. You can stop the download and resume later.")}</p></>)}{tr(selectedSize?.images ? <p className="small muted">{tr("Vision encoder files are included. Picture reading loads only when enabled.")}</p> : null)}</Dialog>

apps/host/src/components/NativeSettings.tsx

@@ -1,3 +1,4 @@
+import { DecimalInput } from './DecimalInput';
 import { tr } from '../lib/i18n';
 import {nativeSettingsResponse,nativeSettingsValues} from '../lib/native-settings-response';
 import { describeChange, type TunedChange } from '../lib/tune-values';
@@ -5,12 +6,15 @@ import { useEffect, useState } from 'react';
 import { api } from '../lib/client';
 import { refreshNative, useNative, type NativeField } from '../lib/native';
 import { Btn, ErrorNotice, Select } from './ui';
+import { speedOptions } from '../lib/deepseek-speed';
+import type { RunCard } from '../lib/native-fit';
 import { NativeMcpEditor } from './NativeMcpEditor';
 export function NativeSettings({ model }: {
     model: string;
 }) {
     const native = useNative();
     const [revision,setRevision]=useState(0);
+    const [dsExperts, setDsExperts] = useState(false);      // the installed DeepSeek engine knows --experts (0.1.50 or newer)
     const [tuned, setTuned] = useState<{ preset: { name: string } | null; changed: TunedChange[] } | null>(null);
     const [values, setValues] = useState<Record<string, any>>({}), [mcp, setMcp] = useState('{}'), [original, setOriginal] = useState(''), [text, setText] = useState(''), [tab, setTab] = useState('fields'), [pending, setPending] = useState(false), [error, setError] = useState(''), [notice, setNotice] = useState(''), [query, setQuery] = useState('');
     useEffect(() => {
@@ -25,9 +29,11 @@ export function NativeSettings({ model }: {
             values: Record<string, any>;
             mcp: Record<string, any>;
             tuned?: { preset: { name: string } | null; changed: TunedChange[] } | null;
+            capabilities?: { dsExperts?: boolean };
         }>(`/api/native/models/${model}/settings`).then(input => {
             if (!active)
                 return;
+            setDsExperts(!!input.capabilities?.dsExperts);
             setTuned(input.tuned ?? null);
             const value = nativeSettingsResponse(input);
             setValues(value.values);
@@ -90,16 +96,9 @@ export function NativeSettings({ model }: {
       <summary>{tr('Native engine settings')}</summary>
       {error ? <><ErrorNotice message={tr('Couldn’t load model settings.')} next={tr('Check that the engine is connected and this model is installed, then try again.')} onRetry={() => setRevision(value => value + 1)}/><details className="native-settings-diagnostic"><summary className="small">{tr('Details')}</summary><p className="small muted">{error}</p></details></> : <p className="small muted" role="status">{tr('Reading saved settings…')}</p>}
     </details>;
-    const rows = (native?.fields ?? []).filter(f => `${tr(f.label)} ${f.id} ${tr(f.group)}`.toLowerCase().includes(query.toLowerCase()));
+    const rows = (native?.fields ?? []).filter(f => (!f.forModel || (model.toLowerCase().includes(f.forModel) && (f.id !== 'ds_experts' || dsExperts))) && `${tr(f.label)} ${f.id} ${tr(f.group)}`.toLowerCase().includes(query.toLowerCase()));
     return <details className="native-settings"><summary>{tr("Native engine settings")}</summary>{tr(tuned?.changed?.length ? <div className="native-tuned"><p className="small"><strong>{tr("Your tuning '{0}' sets", [tuned.preset?.name ?? ''])}</strong></p><ul>{tuned.changed.map(c => { const d = describeChange(c); return <li key={c.flag}><span>{d.name}</span><b>{d.now || tr('off')}</b>{d.was !== null ? <small className="muted">{tr("was {0}", [d.was])}</small> : null}</li>; })}</ul></div> : null)}<p className="small muted">{tr(!original ? 'Reading saved settings… ' : '')}{tr("Settings for this model. Blank values use Strata\u2019s defaults.")}</p><div className="editor-tabs" role="tablist" aria-label={tr("Native settings editor")}>{tr(['fields', 'json', 'tools'].map(t => <button key={t} role="tab" aria-selected={tab === t} onClick={() => chooseTab(t)}>{tr(t === 'fields' ? 'Parameters' : t === 'json' ? 'JSON' : 'MCP tools')}</button>))}</div>
-  {tr(tab === 'fields' ? <><input className="st-input" type="search" aria-label={tr("Search native parameters")} placeholder={tr("Search parameters…")} value={query} onChange={e => setQuery(e.target.value)}/>{tr(['Responses', 'GPU & memory', 'Serving', 'Image reading', 'Tools', 'Recovery'].map(group => rows.some(f => f.group === group) ? <section className="native-settings-group" key={group}><h3 className="h4">{tr(group)}</h3>{tr(rows.filter(f => f.group === group).map(f => <label className="native-setting-row" key={f.id}><span><strong>{tr(f.label)}</strong>{tr(f.supported === false ? <small>{tr("Requires a newer Strata installation.")}</small> : f.hint ? <small>{tr(f.hint)}</small> : null)}</span><NativeFieldInput field={f} value={values[f.id]} onChange={v => change(f.id, v)}/></label>))}</section> : null))}<section className="native-settings-group"><h3 className="h4">{tr("Sampling")}</h3>{tr([['temperature', 'Temperature'], ['top_p', 'Top-p'], ['top_k', 'Top-k'], ['min_p', 'Min-p'], ['repetition_penalty', 'Repetition penalty'], ['presence_penalty', 'Presence penalty'], ['frequency_penalty', 'Frequency penalty'], ['penalty_last_n', 'Penalty window'], ['seed', 'Seed']].map(([id, label]) => <label className="native-setting-row" key={id}><span><strong>{tr(label)}</strong></span><input className="st-input" aria-label={tr("Native {0}", [label])} inputMode="decimal" value={values.sampling?.[id] ?? ''} onChange={e => {
-                    const sampling = { ...values.sampling };
-                    if (e.target.value === '')
-                        delete sampling[id];
-                    else
-                        sampling[id] = Number(e.target.value);
-                    change('sampling', sampling);
-                }}/></label>))}</section></> : tab === 'json' ? <><p className="small muted">{tr("Engine arguments and STRATA environment flags are editable here. Program paths and network access remain managed by the host.")}</p><textarea className="st-input native-json" aria-label={tr("Native configuration JSON")} spellCheck={false} value={text} onChange={e => { setText(e.target.value); setNotice(''); }}/></> : <><p className="small muted">{tr("Add local programs or HTTP MCP servers. Connected tools can read or change the resources you give them access to. Enable tools in chat when you want the model to use them.")}</p><NativeMcpEditor text={mcp} onChange={value => { setMcp(value); setNotice(''); }}/><details><summary className="small">{tr("Configuration example")}</summary><pre className="native-example">{'{\n  "files": {\n    "command": "npx",\n    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/your/folder"],\n    "disabled": false\n  }\n}'}</pre><p className="xs muted">{tr("Saved credentials are masked. Keep the mask to preserve an existing value; type a new value to replace it.")}</p></details></>)}
+  {tr(tab === 'fields' ? <><input className="st-input" type="search" aria-label={tr("Search native parameters")} placeholder={tr("Search parameters…")} value={query} onChange={e => setQuery(e.target.value)}/>{tr(['Responses', 'GPU & memory', 'Serving', 'Image reading', 'Tools', 'Recovery'].map(group => rows.some(f => f.group === group) ? <section className="native-settings-group" key={group}><h3 className="h4">{tr(group)}</h3>{tr(rows.filter(f => f.group === group).map(f => <label className="native-setting-row" key={f.id}><span><strong>{tr(f.label)}</strong>{tr(f.supported === false ? <small>{tr("Requires a newer Strata installation.")}</small> : f.hint ? <small>{tr(f.hint)}</small> : null)}</span><NativeFieldInput field={f} value={values[f.id]} onChange={v => change(f.id, v)}/></label>))}</section> : null))}<section className="native-settings-group"><h3 className="h4">{tr("Sampling")}</h3>{tr([['temperature', 'Temperature'], ['top_p', 'Top-p'], ['top_k', 'Top-k'], ['min_p', 'Min-p'], ['repetition_penalty', 'Repetition penalty'], ['presence_penalty', 'Presence penalty'], ['frequency_penalty', 'Frequency penalty'], ['penalty_last_n', 'Penalty window'], ['seed', 'Seed']].map(([id, label]) => <label className="native-setting-row" key={id}><span><strong>{tr(label)}</strong></span><DecimalInput ariaLabel={tr("Native {0}", [label])} value={values.sampling?.[id] ?? null} onChange={n => { const sampling = { ...values.sampling }; if (n === null) delete sampling[id]; else sampling[id] = n; change('sampling', sampling); }}/></label>))}</section></> : tab === 'json' ? <><p className="small muted">{tr("Engine arguments and STRATA environment flags are editable here. Program paths and network access remain managed by the host.")}</p><textarea className="st-input native-json" aria-label={tr("Native configuration JSON")} spellCheck={false} value={text} onChange={e => { setText(e.target.value); setNotice(''); }}/></> : <><p className="small muted">{tr("Add local programs or HTTP MCP servers. Connected tools can read or change the resources you give them access to. Enable tools in chat when you want the model to use them.")}</p><NativeMcpEditor text={mcp} onChange={value => { setMcp(value); setNotice(''); }}/><details><summary className="small">{tr("Configuration example")}</summary><pre className="native-example">{'{\n  "files": {\n    "command": "npx",\n    "args": ["-y", "@modelcontextprotocol/server-filesystem", "/your/folder"],\n    "disabled": false\n  }\n}'}</pre><p className="xs muted">{tr("Saved credentials are masked. Keep the mask to preserve an existing value; type a new value to replace it.")}</p></details></>)}
   <div className="native-settings-actions"><Btn disabled={pending || !original || !dirty} variant="primary" onClick={() => void save()}>{tr(pending ? 'Saving…' : 'Save settings')}</Btn><Btn disabled={pending} onClick={() => { const saved = JSON.parse(original || '{"values":{},"mcp":{}}'); setValues(saved.values); setText(JSON.stringify(saved.values, null, 2)); setMcp(JSON.stringify(saved.mcp, null, 2)); setError(''); }}>{tr("Restore saved")}</Btn></div>{tr(notice ? <p role="status" className="small">{tr(notice)}</p> : null)}{tr(error ? <ErrorNotice message={error} onRetry={() => setRevision(value => value + 1)}/> : null)}
  </details>;
 }
@@ -112,9 +111,20 @@ function NativeFieldInput({ field, value, onChange }: {
         return <NativeAliases field={field} value={value} onChange={onChange}/>;
     if (field.type === 'boolean')
         return <Select disabled={field.supported === false} ariaLabel={tr(field.label)} value={value === null || value === undefined ? '' : String(value)} options={[{ value: '', label: 'Default' }, { value: 'true', label: 'On' }, { value: 'false', label: 'Off' }]} onChange={v => onChange(v === '' ? null : v === 'true')}/>;
+    if (field.id === 'ds_experts')
+        return <DeepSeekSpeed field={field} value={value} onChange={onChange}/>;
     if (field.type === 'enum')
         return <Select disabled={field.supported === false} ariaLabel={tr(field.label)} value={value ?? ''} options={[{ value: '', label: 'Default' }, ...(field.choices ?? []).map(v => ({ value: v, label: v }))]} onChange={v => onChange(v || null)}/>;
-    return <input disabled={field.supported === false} className="st-input" aria-label={tr(field.label)} inputMode={field.type === 'number' ? 'numeric' : undefined} placeholder={tr("Default")} value={Array.isArray(value) ? value.join(', ') : value ?? ''} onChange={e => onChange(e.target.value === '' ? null : field.type === 'array' ? e.target.value.split(',').map(s => s.trim()).filter(Boolean) : field.type === 'number' ? Number(e.target.value) : e.target.value)}/>;
+    if (field.type === 'number')
+        return <DecimalInput disabled={field.supported === false} ariaLabel={tr(field.label)} placeholder={tr("Default")} value={value === null || value === undefined || value === '' || !Number.isFinite(Number(value)) ? null : Number(value)} onChange={onChange}/>;
+    return <input disabled={field.supported === false} className="st-input" aria-label={tr(field.label)} placeholder={tr("Default")} value={Array.isArray(value) ? value.join(', ') : value ?? ''} onChange={e => onChange(e.target.value === '' ? null : field.type === 'array' ? e.target.value.split(',').map(s => s.trim()).filter(Boolean) : field.type === 'number' ? Number(e.target.value) : e.target.value)}/>;
+}
+/** DeepSeek's Speed choice. The engine decides the default itself (--experts auto); the labels name the same default (lib/deepseek-speed.ts). */
+function DeepSeekSpeed({ field, value, onChange }: { field: NativeField; value: any; onChange: (v: any) => void }) {
+    const native = useNative();
+    const options = speedOptions(native?.hardware?.gpus as RunCard[] | undefined).map(o => ({ ...o, label: tr(o.label) }));
+    return <Select disabled={field.supported === false} ariaLabel={tr(field.label)} value={value === null || value === undefined ? '' : String(value)}
+      options={options} onChange={v => onChange(v === '' ? null : v)}/>;
 }
 function NativeAliases({ field, value, onChange }: {
     field: NativeField;

apps/host/src/components/OnboardingMemory.tsx

@@ -8,9 +8,20 @@ export function OnboardingMemory({ hardware, native }: {
     hardware: Hardware | null;
     native: NativeState['hardware'] | undefined;
 }) {
-    const gpus = hardware ? hardware.gpus.filter(gpu => gpu.backend !== 'cpu').map(gpu => ({ id: gpu.id ?? String(gpu.index), name: gpu.name, memory: gpu.vramGb, shared: gpu.unified })) : native?.gpus.map(gpu => ({ id: String(gpu.index), name: gpu.name, memory: gpu.vram_gb, shared: false })) ?? [];
+    // The Windows host probe (Win32_VideoController) cannot read the VRAM of AMD cards and reports 0 for them; the engine's own list has
+    // the real size. For a dedicated card the host reports as 0, take the engine's figure for the card of the same name, or for the
+    // card in the same position when both lists have the same length. A card the engine does not list stays at 0.
+    const nativeGpus = native?.gpus ?? [];
+    const hostGpus = hardware ? hardware.gpus.filter(gpu => gpu.backend !== 'cpu') : [];
+    const engineVram = (name: string, position: number) => {
+        const norm = (value: string) => value.toLowerCase().replace(/[^a-z0-9]/g, '');
+        const byName = nativeGpus.find(g => norm(g.name).includes(norm(name)) || norm(name).includes(norm(g.name)));
+        return (byName ?? (nativeGpus.length === hostGpus.length ? nativeGpus[position] : undefined))?.vram_gb || 0;
+    };
+    const gpus = hardware ? hostGpus.map((gpu, position) => ({ id: gpu.id ?? String(gpu.index), name: gpu.name, memory: gpu.unified || gpu.vramGb > 0 ? gpu.vramGb : engineVram(gpu.name, position), shared: gpu.unified })) : nativeGpus.map(gpu => ({ id: String(gpu.index), name: gpu.name, memory: gpu.vram_gb, shared: false }));
     const dedicatedCount = gpus.filter(gpu => !gpu.shared).length;
-    const memory = hardware ? memoryInventory(hardware) : native ? { ram: native.ram_gb, vram: native.gpus.reduce((sum, gpu) => sum + Math.max(0, gpu.vram_gb || 0), 0), total: 0, shared: false } : null;
+    const base = hardware ? memoryInventory(hardware) : null;
+    const memory = base ? (base.shared ? base : { ...base, vram: gpus.reduce((sum, gpu) => sum + (gpu.shared ? 0 : Math.max(0, gpu.memory || 0)), 0) }) : native ? { ram: native.ram_gb, vram: native.gpus.reduce((sum, gpu) => sum + Math.max(0, gpu.vram_gb || 0), 0), total: 0, shared: false } : null;
     if (!memory)
         return <div className="onboard-hardware" role="group" aria-label={tr("Computer memory")}><div className="onboard-memory-intro"><Icon name="memory" size={18}/><span>{tr("Reading memory\u2026")}</span></div></div>;
     const total = memory.ram + memory.vram;

apps/host/src/components/SettingsUpdates.tsx

@@ -71,7 +71,7 @@ export function SettingsUpdates() {
         const labels: Record<SoftwareUpdate['status'], string> = { available: 'Update available', current: 'Up to date', unavailable: 'Check unavailable', error: 'Check failed', 'no-releases': 'No release yet' };
         return <div className="settings-version" data-update={update?.status}>
       <Icon name={name === 'Strata' ? 'layers' : 'engine'} size={20}/>
-      <span><strong>{tr(name)}</strong><small>{tr(version ?? 'Version unavailable')}</small>{tr(!checking && update ? <small className="settings-version__message">{tr(update.message)}</small> : null)}</span>
+      <span><strong>{tr(name)}</strong><small>{tr(version ?? 'Version unavailable')}</small>{tr(!checking && update ? <small className="settings-version__message">{tr(update.message)}</small> : null)}{tr(!checking && name === 'Strata' && update?.details ? <details className="native-settings-diagnostic"><summary className="small">{tr("Details")}</summary><p className="small muted">{update.details}</p></details> : null)}</span>
       {tr(!checking && update?.status === 'available' ? (native?.available ? <Btn size="sm" variant="primary" disabled={!!active || (name === 'Engine' && !native.installed?.models.length && !native.capabilities.componentUpdates)} onClick={() => setConfirm(name === 'Strata' ? 'update-strata' : 'update-engine')}>{tr("Update available")}</Btn> : update.releaseUrl ? <a className="st-btn st-btn--secondary st-btn--sm" href={update.releaseUrl} target="_blank" rel="noreferrer" title={tr("Open the release page to update this installation")}>{tr("Update available")}<Icon name="download" size={15}/></a> : <span className="settings-version__label">{tr(labels[update.status])}</span>) : <span className="settings-version__label">{tr(checking ? 'Checking…' : update ? labels[update.status] : version === 'Not installed' ? 'Not installed' : 'Installed')}</span>)}
     </div>;
     }
@@ -95,7 +95,7 @@ export function SettingsUpdates() {
   </>;
 }
 
-/** "Strata 0.2.3 · Engine 0.1.48": the app's own version first, the engine's beside it (About). */
+/** "Strata 0.2.5 · Engine 0.1.50": the app's own version first, the engine's beside it (About). */
 export function AboutVersions() {
     const native = useNative();
     const app = appVersionLabel(useStore(s => s.setup?.app.version), native?.version);

apps/host/src/lib/chat-attach-file.ts

@@ -0,0 +1,11 @@
+/** A file that is not a picture or plain text (a PDF) is saved by the host in the chat's folder and named in the next message, so the assistant can open it (#3838). */
+export async function uploadChatFile(file: File, sessionId: string, fetchFn: typeof fetch = fetch): Promise<{ name: string }> {
+  const host = (globalThis as { __STRATA_HOST__?: string }).__STRATA_HOST__ ?? '';
+  const res = await fetchFn(`${host}/api/chat/upload?sessionId=${encodeURIComponent(sessionId)}&name=${encodeURIComponent(file.name)}`, { method: 'POST', headers: { 'content-type': file.type || 'application/octet-stream' }, body: file });
+  const data = await res.json().catch(() => ({})) as { files?: { name: string; attached?: boolean }[]; error?: string };
+  if (!res.ok) throw new Error(data.error || 'The file could not be added. Try again.');
+  return { name: data.files?.find(f => f.attached)?.name ?? file.name };
+}
+
+/** Types the Linux file dialog needs next to the extensions (WebKitGTK reads only the type part of `accept`). */
+export const FILE_ACCEPT = 'image/*,application/pdf,text/*,application/json,application/xml,.pdf,.txt,.md,.markdown,.csv,.ts,.tsx,.js,.jsx,.py,.json,.css,.rs,.go,.sh,.html,.htm,.yaml,.yml,.toml,.xml,.log';

apps/host/src/lib/clipboard.ts

@@ -0,0 +1,35 @@
+/**
+ * Copy text for the person. The browser clipboard call can be refused (the desktop web view asks for permission, or has no clipboard
+ * object); the older copy command through a hidden field still works there. The answer is always a toast: "Copied", or one plain
+ * sentence and what to do next (#3731).
+ */
+export interface ClipboardDeps {
+  clipboard?: { writeText(text: string): Promise<void> } | null;
+  legacyCopy?: (text: string) => boolean;
+  toast: (tone: 'success' | 'warn', title: string, body?: string) => void;
+}
+
+function legacyCopy(text: string): boolean {
+  if (typeof document === 'undefined') return false;
+  const field = document.createElement('textarea');
+  field.value = text;
+  field.setAttribute('readonly', '');
+  field.style.cssText = 'position:fixed;top:0;left:0;opacity:0;pointer-events:none';
+  document.body.appendChild(field);
+  const active = document.activeElement as HTMLElement | null;
+  try {
+    field.select();
+    return document.execCommand('copy');
+  } catch { return false; }
+  finally { field.remove(); active?.focus?.(); }
+}
+
+export async function copyText(text: string, label: string, deps: ClipboardDeps): Promise<boolean> {
+  const clipboard = deps.clipboard === undefined ? (typeof navigator === 'undefined' ? null : navigator.clipboard) : deps.clipboard;
+  let done = false;
+  try { if (clipboard) { await clipboard.writeText(text); done = true; } } catch { /* the fallback is next */ }
+  if (!done) { try { done = (deps.legacyCopy ?? legacyCopy)(text); } catch { done = false; } }
+  if (done) deps.toast('success', 'Copied', label);
+  else deps.toast('warn', 'Couldn’t copy', 'Select the text and copy it with Ctrl+C.');
+  return done;
+}

apps/host/src/lib/decimal.ts

@@ -0,0 +1,9 @@
+/** A number typed by a person: "0.95", ".95", "0,95" (a comma is a decimal point in many languages). null while it is not a whole number yet ("", ".", "0.", "-"). */
+export function parseDecimal(text: string): number | null {
+  const t = String(text ?? '').trim().replace(',', '.');
+  if (!/^-?(\d+\.?\d*|\.\d+)$/.test(t) || t.endsWith('.')) return null;
+  const n = Number(t);
+  return Number.isFinite(n) ? n : null;
+}
+/** Whether what is typed could still become a number: the field keeps it while the person is in the middle of "0." */
+export const partialDecimal = (text: string) => /^-?\d*[.,]?\d*$/.test(String(text ?? '').trim());

apps/host/src/lib/deepseek-speed.ts

@@ -0,0 +1,30 @@
+import type { RunCard } from './native-fit';
+
+/**
+ * DeepSeek's Speed default, said the way the engine decides it (`--experts auto`, src/dsv41/ds4_experts_rule.hpp): Faster (5 experts a word) when
+ * a card in use is an integrated / unified-memory GPU (Strix Halo, gfx1151: the model shares the PC's memory), or when the cards in use total
+ * 16 GiB or less; otherwise Full quality (6). The app never decides: the engine does; this only names the same default beside the choice.
+ * The total is compared in whole MiB (a 16 GB card reports 16376 MiB = 15.99 GiB and counts as 16 GiB or less).
+ */
+export const FASTER_MIB = 16 * 1024;
+
+export const isIntegrated = (card: RunCard) => !!(card.uma || card.integrated || (card.unified_gb ?? 0) > 0);
+
+export function fasterByDefault(cards: readonly RunCard[] | null | undefined): boolean {
+  const used = (cards ?? []).filter(card => card.usable !== false);
+  if (!used.length) return false;
+  if (used.some(isIntegrated)) return true;
+  const mib = used.reduce((sum, card) => sum + Math.round((card.vram_gb ?? 0) * 1024), 0);
+  return mib > 0 && mib <= FASTER_MIB;
+}
+
+/** The three entries of the Speed select: "Faster" or "Full quality" says "(default on this PC)" when it is what the engine picks by itself. */
+export function speedOptions(cards: readonly RunCard[] | null | undefined): { value: string; label: string }[] {
+  const faster = fasterByDefault(cards);
+  const mark = ' (default on this PC)';
+  return [
+    { value: '', label: faster ? 'Default (Faster on this PC)' : 'Default (Full quality on this PC)' },
+    { value: '5', label: 'Faster' + (faster ? mark : '') },
+    { value: '6', label: 'Full quality' + (faster ? '' : mark) },
+  ];
+}

apps/host/src/lib/format.ts

@@ -128,3 +128,6 @@ export function formatModelName(model: {
 export function userError(message: string): string {
     return message.replace(/^\s*Fixture:\s*/i, '').replace(/^./, c => c.toUpperCase());
 }
+
+/** Decimal megabytes (1 MB = 1,000,000 bytes, at least 1): the same figure as the Terminal and the release page. The only size helper in MB; no binary units. */
+export const megabytes = (bytes: number) => Math.max(1, Math.round(bytes / 1_000_000));

apps/host/src/lib/i18n.ts

@@ -15,6 +15,14 @@ import tools_es from '../locales/tools-es.json';
 import tools_ru from '../locales/tools-ru.json';
 import tools_pt from '../locales/tools-pt.json';
 import tools_ko from '../locales/tools-ko.json';
+import fix_en from '../locales/fix-en.json';
+import fix_zh from '../locales/fix-zh.json';
+import fix_ja from '../locales/fix-ja.json';
+import fix_de from '../locales/fix-de.json';
+import fix_es from '../locales/fix-es.json';
+import fix_ru from '../locales/fix-ru.json';
+import fix_pt from '../locales/fix-pt.json';
+import fix_ko from '../locales/fix-ko.json';
 import base_zh from '../locales/zh.json';
 import base_ja from '../locales/ja.json';
 import base_de from '../locales/de.json';
@@ -27,8 +35,9 @@ export const LANGUAGES=[{value:'en',label:'English'},{value:'zh',label:'中文
 export type Language=typeof LANGUAGES[number]['value'];
 /* The Tune model dialog's strings live in tune-<lang>.json (apps/host/scripts/make-tune-locales.py) so other interface work does not collide with them. */
 /* The tool-server, picture and agent-result strings of the tools and images fixes live in tools-<lang>.json for the same reason. */
-const english:Record<string,string>={...baseEnglish,...tune_en,...tools_en};
-const [zh,ja,de,es,ru,pt,ko]=[{...base_zh,...tune_zh,...tools_zh},{...base_ja,...tune_ja,...tools_ja},{...base_de,...tune_de,...tools_de},{...base_es,...tune_es,...tools_es},{...base_ru,...tune_ru,...tools_ru},{...base_pt,...tune_pt,...tools_pt},{...base_ko,...tune_ko,...tools_ko}] as Record<string,string>[];
+/* The strings that had no key in the files above (#3479, #3825) and the 0.2.4.3 fixes live in fix-<lang>.json (scripts/make-fix-locales.py). */
+const english:Record<string,string>={...baseEnglish,...tune_en,...tools_en,...fix_en};
+const [zh,ja,de,es,ru,pt,ko]=[{...base_zh,...tune_zh,...tools_zh,...fix_zh},{...base_ja,...tune_ja,...tools_ja,...fix_ja},{...base_de,...tune_de,...tools_de,...fix_de},{...base_es,...tune_es,...tools_es,...fix_es},{...base_ru,...tune_ru,...tools_ru,...fix_ru},{...base_pt,...tune_pt,...tools_pt,...fix_pt},{...base_ko,...tune_ko,...tools_ko,...fix_ko}] as Record<string,string>[];
 const catalogs:Record<Language,Record<string,string>>={en:english,zh,ja,de,es,ru,pt,ko};
 const entities:Record<string,string>={amp:'&',lt:'<',gt:'>',quot:'"',apos:"'",nbsp:'\u00a0'};
 const decode=(text:string)=>text.replace(/&(#x[\da-f]+|#\d+|amp|lt|gt|quot|apos|nbsp);/gi,(whole,key:string)=>key[0]==='#'?String.fromCodePoint(key[1].toLowerCase()==='x'?parseInt(key.slice(2),16):parseInt(key.slice(1),10)):entities[key]??whole);
@@ -45,7 +54,7 @@ const patterns=Object.entries(english).filter(([,value])=>/\{\d+\}/.test(value))
  expression+=escape(value.slice(at));
  return{id,slots,pattern:new RegExp('^'+expression+'$'),specificity:value.replace(/\{\d+\}/g,'').length};
 }).sort((a,b)=>b.specificity-a.specificity);
-const localizedTemplateSlots:Record<string,number[]>={s2473:[1,2],s0825:[0,1],s2455:[0],s2456:[0],s7400:[1]};
+const localizedTemplateSlots:Record<string,number[]>={s1242:[0],s2473:[1,2],s0825:[0,1],s2455:[0],s2456:[0],s7400:[1]};
 
 /** Translate interface copy only. Non-string React children pass through unchanged. */
 export function tr<T>(value:T,values?:readonly unknown[]):T{

apps/host/src/lib/model-picker.ts

@@ -22,3 +22,9 @@ export function pickerGroups(library: ModelLibrary) {
   }
   return Array.from(groups, ([family, versions]) => ({ family, versions }));
 }
+
+/** Optimized models that are on this PC but not loaded yet: the chat picker must list them, or it says "none downloaded" while Storage shows them (#3814). */
+export function pickerNativeModels<M extends { model: string; model_name?: string; ready?: boolean }>(installed: M[] | undefined | null, instances: { label: string }[] | undefined | null): M[] {
+  const loaded = new Set((instances ?? []).map(i => i.label));
+  return (installed ?? []).filter(m => m.ready !== false && !loaded.has(m.model_name ?? m.model));
+}

apps/host/src/lib/monitor-hardware.ts

@@ -13,6 +13,18 @@ export function gpuMetric(devices:GpuInfo[],readings:GpuReading[]|undefined,key:
   return mode==='max'?Math.max(...values):values.reduce((n,v)=>n+v,0)/(mode==='mean'?values.length:1);
 }
 
+/** The card's name without its maker: "NVIDIA GeForce RTX 5070" -> "RTX 5070". */
+export const shortGpuName=(name:string)=>String(name??'').replace(/^(NVIDIA|AMD|Intel)(\(R\)|\(TM\))?\s+/i,'').replace(/^(GeForce|Radeon|Arc)(\(TM\))?\s+/i,'').trim()||String(name??'');
+
+/**
+ * The reading over the cards that DO report this value. A card that cannot report it (an integrated one without a temperature sensor) is left
+ * out instead of blanking the figure; `partial` says some were left out, and `devices` names the cards the figure is from.
+ */
+export function gpuReported(devices:GpuInfo[],readings:GpuReading[]|undefined,key:keyof GpuReading,mode:'sum'|'mean'|'max'='sum'):{value:number|null;devices:GpuInfo[];partial:boolean} {
+  const reporting=devices.filter(device=>hasReading(readings?.find(reading=>reading.id===gpuId(device))?.[key]));
+  return {value:reporting.length?gpuMetric(reporting,readings,key,mode):null,devices:reporting,partial:reporting.length>0&&reporting.length<devices.length};
+}
+
 export function gpuCapacity(devices:GpuInfo[]) {
   const shared=devices.filter(g=>g.unified).map(g=>g.vramGb);
   return devices.filter(g=>!g.unified).reduce((n,g)=>n+g.vramGb,0)+(shared.length?Math.max(...shared):0);

apps/host/src/lib/native-catalog.ts

@@ -3,7 +3,7 @@ import {tr} from './i18n';
 import {nvfp4Version} from './native-names';
 export interface CatalogVersion extends NativeSize{sourceFamily:string;edition:string;images:boolean}
 export interface CatalogModel extends Omit<NativeFamily,'sizes'>{sizes:CatalogVersion[]}
-export function nativeVersionLabel(model:string){const nv=nvfp4Version(model);if(nv)return tr(nv.name);return tr(({Q2_0:'Fastest',IQ2_XS:'Compact',IQ3_XXS:'Balanced',IQ3_S:'High quality',IQ1_M:'Coding','Gyro-S':'Smallest','Gyro-M':'Small memory'} as Record<string,string>)[model]??model);}
+export function nativeVersionLabel(model:string){const nv=nvfp4Version(model);if(nv)return tr(nv.name);return tr(({Q2_0:'Fastest',IQ2_XS:'Compact',IQ3_XXS:'Balanced',IQ3_S:'High quality',IQ1_M:'Coding','Gyro-S':'Smallest','Gyro-M':'Small memory','IST-DAS-1.75bpw':'Smallest','IST-DAS-2.00bpw':'Balanced','IST-DAS-2.25bpw':'Best quality'} as Record<string,string>)[model]??model);}
 export const catalogVersionLabel=(version:CatalogVersion)=>{const label=nativeVersionLabel(version.model);return [tr(version.edition),label===version.model&&version.edition?'':label].filter(Boolean).join(' · ');};
 /** The one line that says how a version differs from its neighbours (the three NVFP4 versions); empty for the rest. */
 export const versionNote=(model:string)=>{const nv=nvfp4Version(model);return nv?tr(nv.note):'';};
@@ -12,6 +12,7 @@ export function nativeCatalogModels(families:NativeFamily[]):CatalogModel[]{
  if(!families.length)return[];
  const groups:CatalogModel[]=[{family:'qwen3.8',title:'Qwen3.8-Flash-Next',about:'',experimental:false,images:false,sizes:[]},{family:'qwen3.6',title:'Qwen3.6-35B-A3B',about:'',experimental:false,images:false,sizes:[]}];
  for(const family of families){
+  if(family.family==='deepseek41'){const sizes=family.sizes.filter(size=>!/^UD-Q8/i.test(size.model));if(sizes.length)groups.push({family:'deepseek41',title:family.title||'DeepSeek-V4.1-Flash',about:family.about??'',experimental:false,images:false,sizes:sizes.map(size=>({...size,sourceFamily:family.family,edition:'',images:false}))});continue;}
   const target=/qwen3[._-]?6|35b[-_]?a3b/i.test(family.title+' '+family.family)?groups[1]:['qwen','swift','coder','unsloth','gyro'].includes(family.family)||/qwen3[._-]?8|flash.next/i.test(family.title)?groups[0]:undefined;
   if(!target)continue;
   const edition=target===groups[0]?({swift:'Swift 1.5',coder:'Coder',unsloth:'Unsloth',gyro:'Gyro'} as Record<string,string>)[family.family]??'':'';

apps/host/src/lib/native-fit.ts

@@ -30,16 +30,27 @@ export function memoryNeeded(v: FitInput): number {
   return round1((v.experts_gb ?? v.ram_needed_gb ?? 0) + DENSE_EXTRA_GB);
 }
 
-export function fitOn(v: FitInput, hw: FitHardware | null | undefined, mtp = true): Fit {
+/** The conversation cache of Flash-Next: 13 attention layers, bytes per token per layer by cache format, 5.4% over the bare cache
+ *  (strata_control/vram_fit.py KV_BYTES, KV_MEASURED_FACTOR; setup.py UD_FIT_KV_BYTES). */
+const KV_BYTES: Record<string, number> = { fp16: 2112, int8: 1056, q4_0: 576, k8v4: 816 };
+const KV_LAYERS = 13, KV_FACTOR = 1.054, BASE_CONTEXT = 32768;
+export function cacheGb(context: number, kv = 'int8'): number {
+  return (121 + context * KV_LAYERS * (KV_BYTES[String(kv).toLowerCase()] ?? KV_BYTES.int8) * KV_FACTOR / 2 ** 20) / 1024;   // 121 MiB fixed per session
+}
+export interface CacheChoice { context: number; kv?: string }
+
+export function fitOn(v: FitInput, hw: FitHardware | null | undefined, mtp = true, cache?: CacheChoice | null): Fit {
   const memoryGb = memoryNeeded(v);
+  // DENSE_GB already holds a 32K cache in the default format; the person's context and format replace it (#3832).
+  const denseGb = cache && cache.context > 0 ? Math.max(DENSE_GB - cacheGb(BASE_CONTEXT), 0) + cacheGb(cache.context, cache.kv) : DENSE_GB;
   const ram = Number(hw?.ram_gb), vram = Number(hw?.vram_gb) || 0;
   if (!Number.isFinite(ram) || ram <= 0) return { memoryGb, vramUseGb: 0, ramUseGb: 0, spillGb: 0, known: false };
   const experts = Math.max(0, memoryNeeded(v) - DENSE_EXTRA_GB);
-  const onGpu = Math.max(0, Math.min(experts, vram - DENSE_GB - (mtp && vram > 0 ? MTP_VRAM_GB : 0)));
+  const onGpu = Math.max(0, Math.min(experts, vram - denseGb - (mtp && vram > 0 ? MTP_VRAM_GB : 0)));
   const ramRoom = Math.max(0, ram - SYSTEM_ROOM_GB);
   const spillGb = Math.max(0, experts - onGpu - ramRoom);
   const inRam = Math.max(0, experts - onGpu - spillGb);
-  const vramUseGb = vram > 0 ? Math.min(vram, DENSE_GB + (mtp ? MTP_VRAM_GB : 0) + onGpu) : 0;
+  const vramUseGb = vram > 0 ? Math.min(vram, denseGb + (mtp ? MTP_VRAM_GB : 0) + onGpu) : 0;
   return { memoryGb, vramUseGb: round1(vramUseGb), ramUseGb: round1(inRam + DENSE_EXTRA_GB * (vram > 0 ? 0 : 1)), spillGb: round1(spillGb), known: true };
 }
 

apps/host/src/lib/native.ts

@@ -3,9 +3,9 @@ import { api } from './client';
 import type { Hardware, RuntimeModels } from './types';
 export interface GpuChoiceOption {key:string;cards:number[];label:string;verdict:'fits'|'tight'|'spills'|'unknown';words:string;notes:string[];recommended:boolean}
 export interface GpuChoice {options:GpuChoiceOption[];recommended:string|null;ignored:{name?:string;why_ignored:string}[];cards:number}
-export interface NativeSize {/** The first engine that reads this size's files (the catalog), and whether the installed engine is older: the screen then says "needs a newer engine" and offers the update. */engine_min?:string|null;needsNewerEngine?:boolean;id:string;model:string;about:string;download_gb:number;ram_needed_gb:number;experts_gb:number;on_this_pc:string|null;installed:boolean;gpu_options?:GpuChoice|null;images?:boolean;imagesCapable?:boolean}
+export interface NativeSize {/** The first engine that reads this size's files (the catalog), and whether the installed engine is older: the screen then says "needs a newer engine" and offers the update. */engine_min?:string|null;needsNewerEngine?:boolean;id:string;model:string;about:string;download_gb:number;ram_needed_gb:number;experts_gb:number;on_this_pc:string|null;installed:boolean;gpu_options?:GpuChoice|null;images?:boolean;imagesCapable?:boolean;/** DeepSeek-V4.1-Flash and the like: several big files and an engine of their own. */multi_file?:boolean}
 export interface NativeFamily {family:string;title:string;about:string;experimental:boolean;images:boolean;sizes:NativeSize[]}
-export interface NativeField {id:string;label:string;group:string;type:'number'|'boolean'|'string'|'enum'|'array';min?:number;max?:number;choices?:string[];hint?:string;supported?:boolean}
+export interface NativeField {id:string;label:string;group:string;type:'number'|'boolean'|'string'|'enum'|'array';min?:number;max?:number;choices?:string[];hint?:string;supported?:boolean;forModel?:string}
 export interface NativeJob {id:string;kind:string;guided?:boolean;model?:string;family?:string;state:'running'|'done'|'error'|'cancelled';startedAt:string;summary:string;error:string|null;details?:string;result:Record<string,any>|null;progress?:Record<string,any>|null}
 export interface NativeInstance {id:string;apiModelId:string;model:string;label:string;aliases?:string[];vision?:boolean;resourceProfile?:'work'|'performance'|null;context?:number;port:number;gpus:number[];status:'loading'|'ready'|'unloading'|'error';phase:string;loadedAt:string;error:string|null;metrics:Record<string,any>|null}
 export interface NativeState {
@@ -15,6 +15,10 @@ export interface NativeState {
   visionReader?: boolean;available:boolean;repo:string;downloadDirectory?:string;/** Free bytes on the drive that holds the models folder. */downloadFreeBytes?:number|null;downloadTotalBytes?:number|null;version?:string|null;summary:string;error:string|null;catalog:{families:NativeFamily[];contexts:number[];recommendation:{family:string|null;model:string|null;context?:number;why?:string};context_note:string}|null;installed:{models:{model:string;config:string;model_name:string;ready:boolean;/** The picture-reading files are on this computer (notes-split-agent8.md, item 8). */visionPrepared?:boolean;context?:number;kv?:string;images?:string;visionEnabled?:boolean;visionDevice?:string;lowRamMode?:string;resourceProfile?:'work'|'performance';/** The Drafting choice saved with the model: auto | mtp | dflash2 | off. */drafting?:string;dataFolder?:string;diskGb?:number;diskBytes?:number;/** Files this model shares with another (the picture reader, the draft layer): counted once, in `usage`. */sharedBytes?:number;/** What Delete frees: files in Strata's own folders that no other model uses. */removableGb?:number;missing_files?:string[]}[];/** What all models take on disk, from their real files, shared files counted once. */usage?:{total_bytes:number;total_gb:number;shared_bytes:number;shared_gb:number;models:Record<string,{bytes:number;gb:number}>}|null;data_folder:string;engine:{version:string|null}}|null;hardware:{ram_gb:number;engine_vendor?:string;gpus:{index:number;name:string;vram_gb:number;usable:boolean;/** SMs x clock: only the order between cards matters (strata_control/gpu_roles.py). */speed?:number;vendor?:string;uma?:boolean;integrated?:boolean;unified_gb?:number;problem?:string|null}[]}|null;fields:NativeField[];instances:NativeInstance[];defaultId:string|null;jobs:NativeJob[];capabilities:{/** The engine serves DFlash2 (Control says): the Drafting choice then offers it. */dflash2?:boolean;responses?:boolean;updates:boolean;rollback:boolean;calibration:boolean;componentUpdates?:boolean}}
 let state:NativeState|null=null;
 const listeners=new Set<()=>void>();
+/** True once the first read of the native state has ended, whatever its answer: until then the Models page must not pick a model of its own (#3740). */
+let settled=false;
+export const nativeSettled=()=>settled;
+export function subscribeNative(fn:()=>void){listeners.add(fn);return()=>{listeners.delete(fn);};}
 function put(value:NativeState){if(state&&JSON.stringify(state)===JSON.stringify(value))return;state=value;listeners.forEach(fn=>fn());}
 /** The host pushes its whole native state (jobs included) at every progress step: the page shows it at once, without waiting for the next poll. */
 export function applyNativeEvent(value:unknown){if(value&&typeof value==='object'&&'available' in value&&'jobs' in value)put(value as NativeState);}
@@ -24,7 +28,7 @@ function read(force:boolean):Promise<void>{
  // A read that never answers must not freeze the page: after the limit the next poll starts a fresh one.
  let stop:ReturnType<typeof setTimeout>|undefined;
  const limit=new Promise<never>((_,reject)=>{stop=setTimeout(()=>reject(new Error('The host did not answer in time.')),READ_LIMIT_MS);});
- return Promise.race([request,limit]).then(put).catch(error=>{if(state){state={...state,error:error.message,instances:state.instances.map(i=>({...i,metrics:null,phase:'unavailable'}))};listeners.forEach(fn=>fn());}}).finally(()=>clearTimeout(stop));
+ return Promise.race([request,limit]).then(put).catch(error=>{if(state){state={...state,error:error.message,instances:state.instances.map(i=>({...i,metrics:null,phase:'unavailable'}))};listeners.forEach(fn=>fn());}}).finally(()=>{clearTimeout(stop);if(!settled){settled=true;listeners.forEach(fn=>fn());}});
 }
 /* Two kinds of read that never wait for each other: the light poll (the host answers at once with the jobs it holds) and the forced read after an action (the host
    re-reads the installation, which can take many seconds while a download is writing). A slow forced read used to hold every later poll, so a running download looked stuck. */

apps/host/src/lib/pasted-files.ts

@@ -0,0 +1,19 @@
+/** The pictures on the clipboard, named so each one is told apart in the composer (a pasted screenshot arrives as "image.png"). */
+export function pastedFiles(data: DataTransfer | null | undefined): File[] {
+  const out: File[] = [];
+  const found: File[] = Array.from(data?.files ?? []);
+  // A screenshot from the clipboard (Win+Shift+S) often comes as an item and not in `files` (#3748).
+  if (!found.some(f => f.type.startsWith('image/'))) {
+    for (const item of Array.from(data?.items ?? [])) {
+      if (item.kind !== 'file' || !item.type.startsWith('image/')) continue;
+      const file = item.getAsFile();
+      if (file) found.push(file);
+    }
+  }
+  for (const file of found) {
+    if (!file.type.startsWith('image/')) continue;
+    const extension = file.type.split('/')[1]?.replace('jpeg', 'jpg').replace(/[+].*/, '') || 'png';
+    out.push(new File([file], `Pasted picture ${new Date().toLocaleTimeString().replace(/[^0-9]+/g, '-').replace(/-$/, '')}${out.length ? `-${out.length + 1}` : ''}.${extension}`, { type: file.type }));
+  }
+  return out;
+}

apps/host/src/lib/session-workspace.ts

@@ -0,0 +1,8 @@
+import type { Session, Workspace } from './types';
+
+/** The workspace a chat was made in: the sidebar groups chats by this same rule (the saved path, or an earlier folder of the workspace). */
+export function workspaceIdForSession(workspaces: Workspace[], session: Pick<Session, 'workspace'> | null | undefined): string | null {
+  const path = session?.workspace;
+  if (!path) return null;
+  return workspaces.find(w => w.path === path || !!w.aliases?.includes(path))?.id ?? null;
+}

apps/host/src/lib/store.ts

@@ -1,3 +1,4 @@
+import { workspaceIdForSession } from './session-workspace';
 import { plainFailure, plainFailureText } from './plain-errors';
 import { showcaseMessages, SHOWCASE_AGENTS } from './chat-showcase';
 import { updateAgent } from './agents';
@@ -721,7 +722,7 @@ export async function bootstrap() {
       skills,
       workspacePath: workspaceState.workspaces[0]?.path ?? '',
       workspaces: workspaceState.workspaces,
-      activeWorkspace: workspaceState.workspaces.some(w => w.id === state.activeWorkspace) ? state.activeWorkspace : workspaceState.workspaces[0]?.id ?? null,
+      activeWorkspace: workspaceState.workspaces.some(w => w.id === state.activeWorkspace) ? state.activeWorkspace : workspaceIdForSession(workspaceState.workspaces, state.sessions.find(s => s.id === state.activeSession)) ?? workspaceState.workspaces[0]?.id ?? null,
       connection: 'live',
     });
     applyProviders(providers);
@@ -1104,7 +1105,11 @@ export function continueTaskInNewChat(task: Task) {
 }
 
 export function selectSession(id: string) {
-  set({ activeSession: id });
+  // A chat comes back in the workspace it was made in, so its next turn runs in the same folder (#3754).
+  const workspace = workspaceIdForSession(state.workspaces, state.sessions.find(s => s.id === id));
+  const change = workspace && workspace !== state.activeWorkspace;
+  set(change ? { activeSession: id, activeWorkspace: workspace } : { activeSession: id });
+  if (change) void loadWorkspaceFiles();
   markRead(id);
 }
 
@@ -1728,7 +1733,7 @@ export async function sendMessage(text: string, options: { fromLoop?: boolean; g
         // The Mode menu's choice for this chat, read when the turn starts; the host applies it to the agent.
         mode:state.sessions.find(s=>s.id===sessionId)?.preferences?.mode??'manual',
         // So a skill narrowed to another workspace does not fire here.
-        workspaceId: state.activeWorkspace,
+        workspaceId: workspaceIdForSession(state.workspaces, state.sessions.find(s => s.id === sessionId)) ?? state.activeWorkspace,
       },
       (frame) => {
         // A line from the app itself carries `key` (the English sentence): shown in the person's language.

apps/host/src/lib/types.ts

@@ -8,6 +8,8 @@ export interface SoftwareUpdate {
   releaseUrl?: string;
   canInstall: boolean;
   message: string;
+  /** The technical reason behind `message`, shown only behind the Details disclosure. */
+  details?: string;
 }
 export interface UpdateCheckResult { checkedAt: string; strata: SoftwareUpdate; engine: SoftwareUpdate }
 

apps/host/src/locales/fix-de.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "wird nicht mehr ausgeführt und entfernt.",
+ "fx02": "Heruntergeladen, aber nicht geladen. Öffne „Modelle“, um es zu laden.",
+ "fx03": "{0} Zeilen hinzugefügt, {1} entfernt",
+ "fx04": "{0} Dateien bearbeitet",
+ "fx05": "Dateien hier ablegen, um sie hinzuzufügen",
+ "fx06": "Bilder und Textdateien",
+ "fx07": "Ziel behalten",
+ "fx08": "Ziel entfernen",
+ "fx09": "Der Assistent arbeitet nicht mehr darauf hin. Dein Chat und deine Dateien bleiben unverändert.",
+ "fx10": "Dieses Modell kann Bilder lesen, aber die hier installierte Engine enthält den Bildleser noch nicht, deshalb ist „Bilder lesen“ aus. Aktualisiere die Engine unter Einstellungen → Info, um es einzuschalten.",
+ "fx11": "Zeigt die Werte deiner Abstimmung „{0}“.",
+ "fx12": "Deine Abstimmung „{0}“ setzt",
+ "fx13": "war {0}",
+ "fx14": "· {0} RAM",
+ "fx15": "Die Nachricht wurde nicht abgebrochen",
+ "fx16": "Zusätzliche Einstellungen für das Programm",
+ "fx17": "Mit KI entwerfen",
+ "fx18": "Denkzeit",
+ "fx19": "Schreibzeit",
+ "fx20": "Token/s",
+ "fx21": "% des Kontexts",
+ "fx22": "Diese Seite lädt Dateien aus dem Internet, was die Vorschau nicht tut. Sie kann deshalb unvollständig aussehen. „Code anzeigen“ zeigt genau, was geschrieben wurde.",
+ "fx23": "A behalten",
+ "fx24": "B behalten",
+ "fx25": "Dauer",
+ "fx26": "Schwankung",
+ "fx27": "Geändert",
+ "fx28": "Nichts",
+ "fx29": "Beide Versionen sind fertig. Vergleiche A und B und behalte eine.",
+ "fx30": "Der Assistent antwortet noch",
+ "fx31": "Sende deine Nachricht, wenn er fertig ist.",
+ "fx32": "Die Nachricht wurde nicht eingereiht",
+ "fx33": "Zur neuesten Nachricht scrollen",
+ "fx34": "Aufgabe entfernen",
+ "fx35": "Neue Unterhaltung beginnen; diese bleibt erhalten",
+ "fx36": "Der Assistent schreibt zuerst einen Plan; nichts läuft, bis du ihn freigibst",
+ "fx37": "Im Web suchen, die Seiten lesen und mit Quellen antworten",
+ "fx38": "Kopiert",
+ "fx39": "Antwort",
+ "fx40": "Nachricht",
+ "fx41": "PDF hinzugefügt",
+ "fx42": "Markiere den Text und kopiere ihn mit Strg+C.",
+ "fx43": "{0} ist in diesem Chat. Frag in deiner nächsten Nachricht danach.",
+ "fx44": "Die Engine ist bereit.",
+ "fx45": "Als Nächstes: ein Modell auswählen.",
+ "fx46": "Die Engine wird heruntergeladen",
+ "fx47": "Du kannst Strata schließen; der Download geht dort weiter, wo er aufgehört hat.",
+ "fx48": "Willkommen bei Strata",
+ "fx49": "Deine Grafikkarte wird erkannt…",
+ "fx50": "Strata hat deine Grafikkarte gefunden:",
+ "fx51": "{0} Grafikkarten gefunden. Strata nimmt für die Engine die erste; ändere das später in den Einstellungen.",
+ "fx52": "Strata hat keine unterstützte Grafikkarte erkannt.",
+ "fx53": "Um darauf Modelle auszuführen, braucht Strata einen Download:",
+ "fx54": "Die Engine für diese Grafikkarte",
+ "fx55": "Die Engine braucht etwa {0} GB freien Platz auf diesem Laufwerk, frei sind nur {1} GB. Schaffe Platz und mach dann weiter.",
+ "fx56": "Sie kommt von Stratas eigenem Update-Server und wird vor der Nutzung geprüft. Deine Modelle und Chats bleiben unberührt.",
+ "fx57": "Strata konnte github.com nicht erreichen. Prüfe deine Verbindung und versuche es erneut, oder lade die Engine-Datei auf einem anderen PC herunter und wähle sie hier aus.",
+ "fx58": "Die hier installierte Engine ist für einen anderen Grafikkarten-Hersteller.",
+ "fx59": "Strata kann aus seiner Update-Liste keine Engine für diesen PC wählen.",
+ "fx60": "Ohne Engine fortfahren",
+ "fx61": "Der Download wurde unterbrochen. „Weiter“ setzt ihn dort fort, wo er aufgehört hat.",
+ "fx62": "Das ist ein sehr großes Modell. Der Download umfasst {0} GB und braucht etwa so viel freien Speicherplatz. Es läuft auf einer Grafikkarte mit 12 GB und 46 bis 64 GB RAM, langsam: etwa 5 bis 7 Wörter pro Sekunde. Was nicht in den Speicher passt, wird von deiner SSD gelesen, deshalb zählt eine NVMe-SSD.",
+ "fx63": "Du kannst den Download stoppen und später fortsetzen; er macht dort weiter, wo er aufgehört hat. Strata warnt dich hier, hält dich aber nie auf.",
+ "fx64": "Schneller",
+ "fx65": "Volle Qualität",
+ "fx66": "Standard (Schneller auf diesem PC)",
+ "fx67": "Standard (Volle Qualität auf diesem PC)",
+ "fx68": "Schneller (Standard auf diesem PC)",
+ "fx69": "Volle Qualität (Standard auf diesem PC)"
+}

apps/host/src/locales/fix-en.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "will stop running and be removed.",
+ "fx02": "Downloaded, not loaded. Open Models to load it.",
+ "fx03": "{0} lines added, {1} removed",
+ "fx04": "Edited {0} files",
+ "fx05": "Drop files to add them",
+ "fx06": "Pictures and text files",
+ "fx07": "Keep goal",
+ "fx08": "Remove goal",
+ "fx09": "The assistant stops working towards it. Your chat and files stay as they are.",
+ "fx10": "This model can read pictures, but the engine installed here does not include the picture reader yet, so Read pictures is off. Update the engine in Settings → About to turn it on.",
+ "fx11": "Showing the values of your tuning '{0}'.",
+ "fx12": "Your tuning '{0}' sets",
+ "fx13": "was {0}",
+ "fx14": "· {0} RAM",
+ "fx15": "The message was not cancelled",
+ "fx16": "Extra settings for the program",
+ "fx17": "Draft it with AI",
+ "fx18": "Thinking time",
+ "fx19": "Writing time",
+ "fx20": "tokens/s",
+ "fx21": "% of context",
+ "fx22": "This page asks for files from the internet, which the preview does not load, so it may look incomplete. View code shows exactly what was written.",
+ "fx23": "Keep A",
+ "fx24": "Keep B",
+ "fx25": "Took",
+ "fx26": "Variation",
+ "fx27": "Changed",
+ "fx28": "Nothing",
+ "fx29": "Both versions are ready. Compare A and B, then keep one.",
+ "fx30": "The assistant is still answering",
+ "fx31": "Send your message when it has finished.",
+ "fx32": "The message was not queued",
+ "fx33": "Scroll to the latest message",
+ "fx34": "Remove task",
+ "fx35": "Start a new conversation; keep this one",
+ "fx36": "Have the assistant write a plan first; nothing runs until you approve it",
+ "fx37": "Search the web, read the pages and answer with sources",
+ "fx38": "Copied",
+ "fx39": "Response",
+ "fx40": "Message",
+ "fx41": "PDF added",
+ "fx42": "Select the text and copy it with Ctrl+C.",
+ "fx43": "{0} is in this chat. Ask about it in your next message.",
+ "fx44": "The engine is ready.",
+ "fx45": "Next: pick a model.",
+ "fx46": "Downloading the engine",
+ "fx47": "You can close Strata; it continues where it stopped.",
+ "fx48": "Welcome to Strata",
+ "fx49": "Looking at your graphics card…",
+ "fx50": "Strata found your graphics card:",
+ "fx51": "{0} cards found. Strata uses the first one for the engine; change it later in Settings.",
+ "fx52": "Strata did not recognise a supported graphics card.",
+ "fx53": "To run models on it, Strata needs one download:",
+ "fx54": "The engine for this card",
+ "fx55": "The engine needs about {0} GB of free space on this drive and only {1} GB is free. Free some space, then continue.",
+ "fx56": "It comes from Strata’s own update server and is checked before it is used. Your models and chats are never touched by it.",
+ "fx57": "Strata could not reach github.com. Check your connection and try again, or download the engine file on another PC and choose it here.",
+ "fx58": "The engine installed here is for another make of graphics card.",
+ "fx59": "Strata can’t pick an engine for this PC from its update list.",
+ "fx60": "Continue without an engine",
+ "fx61": "The download stopped. Continue picks it up where it stopped.",
+ "fx62": "This is a very large model. The download is {0} GB and it needs about as much free disk space. It runs on one 12 GB graphics card with 46 to 64 GB of RAM, slowly: about 5 to 7 words a second. What does not fit in memory is read from your SSD, so an NVMe drive matters.",
+ "fx63": "You can stop the download and continue later; it picks up where it stopped. Strata warns you here but never blocks you.",
+ "fx64": "Faster",
+ "fx65": "Full quality",
+ "fx66": "Default (Faster on this PC)",
+ "fx67": "Default (Full quality on this PC)",
+ "fx68": "Faster (default on this PC)",
+ "fx69": "Full quality (default on this PC)"
+}

apps/host/src/locales/fix-es.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "dejará de ejecutarse y se eliminará.",
+ "fx02": "Descargado, pero no cargado. Abre Modelos para cargarlo.",
+ "fx03": "{0} líneas añadidas, {1} eliminadas",
+ "fx04": "{0} archivos editados",
+ "fx05": "Suelta los archivos para añadirlos",
+ "fx06": "Imágenes y archivos de texto",
+ "fx07": "Mantener el objetivo",
+ "fx08": "Quitar el objetivo",
+ "fx09": "El asistente deja de trabajar en ello. Tu chat y tus archivos se quedan como están.",
+ "fx10": "Este modelo puede leer imágenes, pero el motor instalado aquí aún no incluye el lector de imágenes, así que Leer imágenes está desactivado. Actualiza el motor en Ajustes → Acerca de para activarlo.",
+ "fx11": "Se muestran los valores de tu ajuste «{0}».",
+ "fx12": "Tu ajuste «{0}» establece",
+ "fx13": "antes {0}",
+ "fx14": "· {0} de RAM",
+ "fx15": "El mensaje no se canceló",
+ "fx16": "Ajustes adicionales del programa",
+ "fx17": "Redactar con IA",
+ "fx18": "Tiempo de pensar",
+ "fx19": "Tiempo de escribir",
+ "fx20": "tokens/s",
+ "fx21": "% del contexto",
+ "fx22": "Esta página pide archivos de internet, que la vista previa no carga, así que puede verse incompleta. Ver código muestra exactamente lo que se escribió.",
+ "fx23": "Mantener A",
+ "fx24": "Mantener B",
+ "fx25": "Tardó",
+ "fx26": "Variación",
+ "fx27": "Cambiado",
+ "fx28": "Nada",
+ "fx29": "Las dos versiones están listas. Compara A y B y quédate con una.",
+ "fx30": "El asistente sigue respondiendo",
+ "fx31": "Envía tu mensaje cuando termine.",
+ "fx32": "El mensaje no se puso en cola",
+ "fx33": "Ir al último mensaje",
+ "fx34": "Quitar tarea",
+ "fx35": "Empieza una conversación nueva; esta se conserva",
+ "fx36": "El asistente escribe primero un plan; no se ejecuta nada hasta que lo apruebes",
+ "fx37": "Busca en la web, lee las páginas y responde con fuentes",
+ "fx38": "Copiado",
+ "fx39": "Respuesta",
+ "fx40": "Mensaje",
+ "fx41": "PDF añadido",
+ "fx42": "Selecciona el texto y cópialo con Ctrl+C.",
+ "fx43": "{0} está en este chat. Pregunta por él en tu próximo mensaje.",
+ "fx44": "El motor está listo.",
+ "fx45": "Siguiente: elige un modelo.",
+ "fx46": "Descargando el motor",
+ "fx47": "Puedes cerrar Strata; la descarga sigue donde se quedó.",
+ "fx48": "Te damos la bienvenida a Strata",
+ "fx49": "Mirando tu tarjeta gráfica…",
+ "fx50": "Strata encontró tu tarjeta gráfica:",
+ "fx51": "Se encontraron {0} tarjetas. Strata usa la primera para el motor; puedes cambiarlo después en Ajustes.",
+ "fx52": "Strata no reconoció ninguna tarjeta gráfica compatible.",
+ "fx53": "Para ejecutar modelos en ella, Strata necesita una descarga:",
+ "fx54": "El motor para esta tarjeta",
+ "fx55": "El motor necesita unos {0} GB de espacio libre en esta unidad y solo hay {1} GB libres. Libera espacio y sigue.",
+ "fx56": "Viene del servidor de actualizaciones de Strata y se comprueba antes de usarlo. Tus modelos y chats no se tocan.",
+ "fx57": "Strata no pudo conectar con github.com. Revisa tu conexión y vuelve a intentarlo, o descarga el archivo del motor en otro PC y elígelo aquí.",
+ "fx58": "El motor instalado aquí es para otra marca de tarjeta gráfica.",
+ "fx59": "Strata no puede elegir un motor para este PC a partir de su lista de actualizaciones.",
+ "fx60": "Continuar sin motor",
+ "fx61": "La descarga se detuvo. «Continuar» la retoma donde se quedó.",
+ "fx62": "Es un modelo muy grande. La descarga es de {0} GB y necesita casi el mismo espacio libre en disco. Funciona con una tarjeta gráfica de 12 GB y de 46 a 64 GB de RAM, despacio: unas 5 a 7 palabras por segundo. Lo que no cabe en memoria se lee de tu SSD, así que importa que sea NVMe.",
+ "fx63": "Puedes detener la descarga y seguir más tarde; continúa donde se quedó. Strata te avisa aquí, pero nunca te lo impide.",
+ "fx64": "Más rápido",
+ "fx65": "Calidad completa",
+ "fx66": "Predeterminado (Más rápido en este PC)",
+ "fx67": "Predeterminado (Calidad completa en este PC)",
+ "fx68": "Más rápido (predeterminado en este PC)",
+ "fx69": "Calidad completa (predeterminado en este PC)"
+}

apps/host/src/locales/fix-ja.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "は停止され、削除されます。",
+ "fx02": "ダウンロード済みですが、読み込まれていません。「モデル」を開いて読み込んでください。",
+ "fx03": "{0} 行追加、{1} 行削除",
+ "fx04": "{0} 個のファイルを編集しました",
+ "fx05": "ファイルをドロップして追加",
+ "fx06": "画像とテキストファイル",
+ "fx07": "目標を残す",
+ "fx08": "目標を削除",
+ "fx09": "アシスタントはこの目標に向けた作業をやめます。チャットとファイルはそのまま残ります。",
+ "fx10": "このモデルは画像を読めますが、ここにインストールされているエンジンにはまだ画像リーダーが含まれていないため、「画像を読む」はオフです。設定 → 情報 でエンジンを更新するとオンにできます。",
+ "fx11": "チューニング「{0}」の値を表示しています。",
+ "fx12": "チューニング「{0}」が設定する項目",
+ "fx13": "変更前: {0}",
+ "fx14": "· {0} RAM",
+ "fx15": "メッセージはキャンセルされませんでした",
+ "fx16": "プログラムの追加設定",
+ "fx17": "AI で下書きを作成",
+ "fx18": "思考時間",
+ "fx19": "執筆時間",
+ "fx20": "トークン/秒",
+ "fx21": "% のコンテキスト",
+ "fx22": "このページはインターネット上のファイルを必要としますが、プレビューでは読み込まれないため、表示が不完全になることがあります。「コードを表示」で書かれた内容をそのまま確認できます。",
+ "fx23": "A を残す",
+ "fx24": "B を残す",
+ "fx25": "所要時間",
+ "fx26": "ばらつき",
+ "fx27": "変更点",
+ "fx28": "なし",
+ "fx29": "両方のバージョンの準備ができました。A と B を比べて、どちらかを残してください。",
+ "fx30": "アシスタントはまだ回答中です",
+ "fx31": "回答が終わってからメッセージを送ってください。",
+ "fx32": "メッセージは待機列に入りませんでした",
+ "fx33": "最新のメッセージへスクロール",
+ "fx34": "タスクを削除",
+ "fx35": "新しい会話を始めます。今の会話は残ります",
+ "fx36": "アシスタントにまず計画を書かせます。承認するまで何も実行されません",
+ "fx37": "ウェブを検索し、ページを読み、出典付きで回答します",
+ "fx38": "コピーしました",
+ "fx39": "返信",
+ "fx40": "メッセージ",
+ "fx41": "PDF を追加しました",
+ "fx42": "テキストを選択して Ctrl+C でコピーしてください。",
+ "fx43": "{0} をこのチャットに追加しました。次のメッセージで質問してください。",
+ "fx44": "エンジンの準備ができました。",
+ "fx45": "次へ：モデルを選んでください。",
+ "fx46": "エンジンをダウンロードしています",
+ "fx47": "Strata を閉じても大丈夫です。止まった場所から続きをダウンロードします。",
+ "fx48": "Strata へようこそ",
+ "fx49": "グラフィックスカードを確認しています…",
+ "fx50": "Strata がグラフィックスカードを見つけました：",
+ "fx51": "グラフィックスカードが {0} 枚見つかりました。エンジンには最初の1枚を使います。あとで設定から変更できます。",
+ "fx52": "Strata は対応しているグラフィックスカードを認識できませんでした。",
+ "fx53": "このカードでモデルを動かすには、ダウンロードが1つ必要です：",
+ "fx54": "このカード用のエンジン",
+ "fx55": "エンジンにはこのドライブの空き容量が約 {0} GB 必要ですが、空きは {1} GB しかありません。空き容量を作ってから続けてください。",
+ "fx56": "Strata 自身の更新サーバーから取得し、使う前に検証します。モデルやチャットには一切触れません。",
+ "fx57": "Strata は github.com に接続できませんでした。接続を確認してもう一度試すか、別の PC でエンジンのファイルをダウンロードして、ここで選んでください。",
+ "fx58": "ここにインストールされているエンジンは、別のメーカーのグラフィックスカード用です。",
+ "fx59": "Strata は更新リストからこの PC 用のエンジンを選べません。",
+ "fx60": "エンジンなしで続ける",
+ "fx61": "ダウンロードが止まりました。「続ける」を押すと、止まった場所から再開します。",
+ "fx62": "とても大きなモデルです。ダウンロードは {0} GB で、ほぼ同じ大きさの空き容量が必要です。12 GB のグラフィックスカードと 46〜64 GB の RAM で動きますが、速度はゆっくりで、1秒に約 5〜7 語です。メモリに入らない分は SSD から読むため、NVMe ドライブが重要です。",
+ "fx63": "ダウンロードはいつでも止めて、あとで続けられます。止まった場所から再開します。Strata はここで注意はしますが、実行を止めることはありません。",
+ "fx64": "高速",
+ "fx65": "フル品質",
+ "fx66": "既定（この PC では「高速」）",
+ "fx67": "既定（この PC では「フル品質」）",
+ "fx68": "高速（この PC の既定）",
+ "fx69": "フル品質（この PC の既定）"
+}

apps/host/src/locales/fix-ko.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "실행이 중지되고 제거됩니다.",
+ "fx02": "다운로드했지만 아직 불러오지 않았습니다. 모델 화면을 열어 불러오세요.",
+ "fx03": "{0}줄 추가, {1}줄 삭제",
+ "fx04": "파일 {0}개 편집함",
+ "fx05": "파일을 놓아서 추가하세요",
+ "fx06": "그림과 텍스트 파일",
+ "fx07": "목표 유지",
+ "fx08": "목표 제거",
+ "fx09": "어시스턴트가 이 목표를 향한 작업을 멈춥니다. 대화와 파일은 그대로 남습니다.",
+ "fx10": "이 모델은 그림을 읽을 수 있지만, 여기에 설치된 엔진에는 아직 그림 읽기 기능이 없어서 '그림 읽기'가 꺼져 있습니다. 설정 → 정보에서 엔진을 업데이트하면 켤 수 있습니다.",
+ "fx11": "튜닝 '{0}'의 값을 보여 줍니다.",
+ "fx12": "튜닝 '{0}'이(가) 설정하는 항목",
+ "fx13": "이전 값 {0}",
+ "fx14": "· RAM {0}",
+ "fx15": "메시지가 취소되지 않았습니다",
+ "fx16": "프로그램 추가 설정",
+ "fx17": "AI로 초안 작성",
+ "fx18": "생각한 시간",
+ "fx19": "작성한 시간",
+ "fx20": "토큰/초",
+ "fx21": "컨텍스트 %",
+ "fx22": "이 페이지는 인터넷의 파일을 불러와야 하는데 미리보기는 이를 불러오지 않으므로 불완전하게 보일 수 있습니다. '코드 보기'에서 작성된 내용을 그대로 볼 수 있습니다.",
+ "fx23": "A 유지",
+ "fx24": "B 유지",
+ "fx25": "걸린 시간",
+ "fx26": "편차",
+ "fx27": "변경됨",
+ "fx28": "없음",
+ "fx29": "두 버전이 모두 준비되었습니다. A와 B를 비교한 뒤 하나를 유지하세요.",
+ "fx30": "어시스턴트가 아직 답하는 중입니다",
+ "fx31": "답이 끝나면 메시지를 보내세요.",
+ "fx32": "메시지가 대기열에 들어가지 않았습니다",
+ "fx33": "최신 메시지로 이동",
+ "fx34": "작업 제거",
+ "fx35": "새 대화를 시작합니다. 이 대화는 그대로 둡니다",
+ "fx36": "어시스턴트가 먼저 계획을 작성합니다. 승인하기 전에는 아무것도 실행되지 않습니다",
+ "fx37": "웹을 검색하고 페이지를 읽어 출처와 함께 답합니다",
+ "fx38": "복사했습니다",
+ "fx39": "답변",
+ "fx40": "메시지",
+ "fx41": "PDF를 추가했습니다",
+ "fx42": "텍스트를 선택한 뒤 Ctrl+C로 복사하세요.",
+ "fx43": "{0}이(가) 이 채팅에 있습니다. 다음 메시지에서 물어보세요.",
+ "fx44": "엔진이 준비되었습니다.",
+ "fx45": "다음: 모델을 고르세요.",
+ "fx46": "엔진을 다운로드하는 중",
+ "fx47": "Strata를 닫아도 됩니다. 멈춘 곳에서 이어서 받습니다.",
+ "fx48": "Strata에 오신 것을 환영합니다",
+ "fx49": "그래픽 카드를 확인하는 중…",
+ "fx50": "Strata가 그래픽 카드를 찾았습니다:",
+ "fx51": "그래픽 카드 {0}개를 찾았습니다. 엔진에는 첫 번째 카드를 사용하며, 나중에 설정에서 바꿀 수 있습니다.",
+ "fx52": "Strata가 지원되는 그래픽 카드를 인식하지 못했습니다.",
+ "fx53": "이 카드에서 모델을 실행하려면 다운로드가 하나 필요합니다:",
+ "fx54": "이 카드용 엔진",
+ "fx55": "엔진에는 이 드라이브의 여유 공간이 약 {0}GB 필요한데, 남은 공간은 {1}GB뿐입니다. 공간을 확보한 뒤 계속하세요.",
+ "fx56": "Strata의 자체 업데이트 서버에서 받으며, 사용하기 전에 검증합니다. 모델과 채팅은 건드리지 않습니다.",
+ "fx57": "Strata가 github.com에 연결하지 못했습니다. 연결을 확인하고 다시 시도하거나, 다른 PC에서 엔진 파일을 받아 여기서 선택하세요.",
+ "fx58": "여기에 설치된 엔진은 다른 제조사의 그래픽 카드용입니다.",
+ "fx59": "Strata가 업데이트 목록에서 이 PC에 맞는 엔진을 고르지 못했습니다.",
+ "fx60": "엔진 없이 계속",
+ "fx61": "다운로드가 멈췄습니다. 계속을 누르면 멈춘 곳에서 이어서 받습니다.",
+ "fx62": "매우 큰 모델입니다. 다운로드는 {0}GB이고, 거의 같은 크기의 여유 디스크 공간이 필요합니다. 12GB 그래픽 카드 한 장과 46~64GB RAM에서 느리게 실행되며, 초당 약 5~7단어입니다. 메모리에 들어가지 않는 부분은 SSD에서 읽으므로 NVMe 드라이브가 중요합니다.",
+ "fx63": "다운로드는 멈췄다가 나중에 이어서 받을 수 있으며, 멈춘 곳에서 다시 시작합니다. Strata는 여기서 알려 드리지만 막지는 않습니다.",
+ "fx64": "더 빠르게",
+ "fx65": "전체 품질",
+ "fx66": "기본값(이 PC에서는 더 빠르게)",
+ "fx67": "기본값(이 PC에서는 전체 품질)",
+ "fx68": "더 빠르게(이 PC의 기본값)",
+ "fx69": "전체 품질(이 PC의 기본값)"
+}

apps/host/src/locales/fix-pt.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "vai parar de funcionar e será removido.",
+ "fx02": "Baixado, mas não carregado. Abra Modelos para carregá-lo.",
+ "fx03": "{0} linhas adicionadas, {1} removidas",
+ "fx04": "{0} arquivos editados",
+ "fx05": "Solte os arquivos para adicioná-los",
+ "fx06": "Imagens e arquivos de texto",
+ "fx07": "Manter a meta",
+ "fx08": "Remover a meta",
+ "fx09": "O assistente deixa de trabalhar nela. Seu chat e seus arquivos continuam como estão.",
+ "fx10": "Este modelo consegue ler imagens, mas o motor instalado aqui ainda não inclui o leitor de imagens, então Ler imagens está desligado. Atualize o motor em Configurações → Sobre para ligar.",
+ "fx11": "Mostrando os valores do seu ajuste \"{0}\".",
+ "fx12": "Seu ajuste \"{0}\" define",
+ "fx13": "era {0}",
+ "fx14": "· {0} de RAM",
+ "fx15": "A mensagem não foi cancelada",
+ "fx16": "Configurações extras do programa",
+ "fx17": "Rascunhar com IA",
+ "fx18": "Tempo de raciocínio",
+ "fx19": "Tempo de escrita",
+ "fx20": "tokens/s",
+ "fx21": "% do contexto",
+ "fx22": "Esta página pede arquivos da internet, que a visualização não carrega, então pode parecer incompleta. Ver código mostra exatamente o que foi escrito.",
+ "fx23": "Manter A",
+ "fx24": "Manter B",
+ "fx25": "Levou",
+ "fx26": "Variação",
+ "fx27": "Alterado",
+ "fx28": "Nada",
+ "fx29": "As duas versões estão prontas. Compare A e B e mantenha uma.",
+ "fx30": "O assistente ainda está respondendo",
+ "fx31": "Envie sua mensagem quando ele terminar.",
+ "fx32": "A mensagem não entrou na fila",
+ "fx33": "Ir para a última mensagem",
+ "fx34": "Remover tarefa",
+ "fx35": "Começar uma nova conversa; esta continua salva",
+ "fx36": "O assistente escreve um plano primeiro; nada roda até você aprovar",
+ "fx37": "Pesquisar na web, ler as páginas e responder com fontes",
+ "fx38": "Copiado",
+ "fx39": "Resposta",
+ "fx40": "Mensagem",
+ "fx41": "PDF adicionado",
+ "fx42": "Selecione o texto e copie com Ctrl+C.",
+ "fx43": "{0} está neste chat. Pergunte sobre ele na próxima mensagem.",
+ "fx44": "O motor está pronto.",
+ "fx45": "Próximo passo: escolha um modelo.",
+ "fx46": "Baixando o motor",
+ "fx47": "Você pode fechar o Strata; o download continua de onde parou.",
+ "fx48": "Bem-vindo ao Strata",
+ "fx49": "Verificando sua placa de vídeo…",
+ "fx50": "O Strata encontrou sua placa de vídeo:",
+ "fx51": "{0} placas de vídeo encontradas. O Strata usa a primeira para o motor; você pode mudar isso depois nas Configurações.",
+ "fx52": "O Strata não reconheceu nenhuma placa de vídeo compatível.",
+ "fx53": "Para executar modelos nela, o Strata precisa de um download:",
+ "fx54": "O motor para esta placa",
+ "fx55": "O motor precisa de cerca de {0} GB de espaço livre neste disco e só há {1} GB livres. Libere espaço e continue.",
+ "fx56": "Ele vem do servidor de atualizações do próprio Strata e é verificado antes do uso. Seus modelos e chats não são tocados.",
+ "fx57": "O Strata não conseguiu acessar github.com. Verifique a conexão e tente de novo, ou baixe o arquivo do motor em outro PC e escolha-o aqui.",
+ "fx58": "O motor instalado aqui é para outra marca de placa de vídeo.",
+ "fx59": "O Strata não consegue escolher um motor para este PC a partir da lista de atualizações.",
+ "fx60": "Continuar sem motor",
+ "fx61": "O download parou. “Continuar” retoma de onde parou.",
+ "fx62": "Este é um modelo muito grande. O download tem {0} GB e precisa de quase o mesmo espaço livre em disco. Ele roda em uma placa de vídeo de 12 GB com 46 a 64 GB de RAM, devagar: cerca de 5 a 7 palavras por segundo. O que não cabe na memória é lido do seu SSD, então um NVMe faz diferença.",
+ "fx63": "Você pode parar o download e continuar depois; ele retoma de onde parou. O Strata avisa você aqui, mas nunca impede.",
+ "fx64": "Mais rápido",
+ "fx65": "Qualidade total",
+ "fx66": "Padrão (Mais rápido neste PC)",
+ "fx67": "Padrão (Qualidade total neste PC)",
+ "fx68": "Mais rápido (padrão neste PC)",
+ "fx69": "Qualidade total (padrão neste PC)"
+}

apps/host/src/locales/fix-ru.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "перестанет работать и будет удалена.",
+ "fx02": "Скачана, но не загружена. Откройте «Модели», чтобы загрузить её.",
+ "fx03": "Добавлено строк: {0}, удалено: {1}",
+ "fx04": "Изменено файлов: {0}",
+ "fx05": "Перетащите файлы сюда, чтобы добавить",
+ "fx06": "Картинки и текстовые файлы",
+ "fx07": "Оставить цель",
+ "fx08": "Удалить цель",
+ "fx09": "Ассистент перестанет работать над ней. Ваш чат и файлы останутся как есть.",
+ "fx10": "Эта модель умеет читать картинки, но установленный здесь движок пока не содержит модуль чтения картинок, поэтому «Читать картинки» выключено. Обновите движок в разделе «Настройки → О программе», чтобы включить.",
+ "fx11": "Показаны значения вашей настройки «{0}».",
+ "fx12": "Ваша настройка «{0}» задаёт",
+ "fx13": "было {0}",
+ "fx14": "· {0} ОЗУ",
+ "fx15": "Сообщение не было отменено",
+ "fx16": "Дополнительные настройки программы",
+ "fx17": "Набросать с помощью ИИ",
+ "fx18": "Время размышления",
+ "fx19": "Время написания",
+ "fx20": "токенов/с",
+ "fx21": "% контекста",
+ "fx22": "Эта страница запрашивает файлы из интернета, а предпросмотр их не загружает, поэтому она может выглядеть неполной. «Показать код» показывает, что именно было написано.",
+ "fx23": "Оставить A",
+ "fx24": "Оставить B",
+ "fx25": "Заняло",
+ "fx26": "Разброс",
+ "fx27": "Изменено",
+ "fx28": "Ничего",
+ "fx29": "Обе версии готовы. Сравните A и B и оставьте одну.",
+ "fx30": "Ассистент ещё отвечает",
+ "fx31": "Отправьте сообщение, когда он закончит.",
+ "fx32": "Сообщение не поставлено в очередь",
+ "fx33": "К последнему сообщению",
+ "fx34": "Удалить задачу",
+ "fx35": "Начать новый разговор; этот сохраняется",
+ "fx36": "Ассистент сначала напишет план; ничего не запустится, пока вы его не одобрите",
+ "fx37": "Искать в интернете, читать страницы и отвечать со ссылками на источники",
+ "fx38": "Скопировано",
+ "fx39": "Ответ",
+ "fx40": "Сообщение",
+ "fx41": "PDF добавлен",
+ "fx42": "Выделите текст и скопируйте его клавишами Ctrl+C.",
+ "fx43": "{0} добавлен в этот чат. Спросите о нём в следующем сообщении.",
+ "fx44": "Движок готов.",
+ "fx45": "Дальше: выберите модель.",
+ "fx46": "Загрузка движка",
+ "fx47": "Можно закрыть Strata; загрузка продолжится с того места, где остановилась.",
+ "fx48": "Добро пожаловать в Strata",
+ "fx49": "Смотрим вашу видеокарту…",
+ "fx50": "Strata нашла вашу видеокарту:",
+ "fx51": "Найдено видеокарт: {0}. Для движка Strata использует первую; позже это можно изменить в настройках.",
+ "fx52": "Strata не распознала поддерживаемую видеокарту.",
+ "fx53": "Чтобы запускать на ней модели, Strata нужно одно скачивание:",
+ "fx54": "Движок для этой видеокарты",
+ "fx55": "Движку нужно около {0} ГБ свободного места на этом диске, а свободно только {1} ГБ. Освободите место и продолжайте.",
+ "fx56": "Он приходит с собственного сервера обновлений Strata и проверяется перед использованием. Ваши модели и чаты он не затрагивает.",
+ "fx57": "Strata не смогла подключиться к github.com. Проверьте соединение и повторите попытку, либо скачайте файл движка на другом компьютере и выберите его здесь.",
+ "fx58": "Установленный здесь движок предназначен для видеокарт другого производителя.",
+ "fx59": "Strata не может выбрать движок для этого компьютера по своему списку обновлений.",
+ "fx60": "Продолжить без движка",
+ "fx61": "Загрузка остановилась. «Продолжить» возобновит её с того места, где она остановилась.",
+ "fx62": "Это очень большая модель. Загрузка — {0} ГБ, и нужно почти столько же свободного места на диске. Она работает на одной видеокарте с 12 ГБ и 46–64 ГБ оперативной памяти, медленно: около 5–7 слов в секунду. То, что не помещается в память, читается с вашего SSD, поэтому важен накопитель NVMe.",
+ "fx63": "Загрузку можно остановить и продолжить позже; она продолжится с того же места. Strata предупреждает вас здесь, но никогда не мешает.",
+ "fx64": "Быстрее",
+ "fx65": "Полное качество",
+ "fx66": "По умолчанию (на этом компьютере — «Быстрее»)",
+ "fx67": "По умолчанию (на этом компьютере — «Полное качество»)",
+ "fx68": "Быстрее (по умолчанию на этом компьютере)",
+ "fx69": "Полное качество (по умолчанию на этом компьютере)"
+}

apps/host/src/locales/fix-zh.json

@@ -0,0 +1,71 @@
+{
+ "fx01": "将停止运行并被移除。",
+ "fx02": "已下载，尚未加载。打开“模型”页面来加载它。",
+ "fx03": "新增 {0} 行，删除 {1} 行",
+ "fx04": "已编辑 {0} 个文件",
+ "fx05": "拖放文件即可添加",
+ "fx06": "图片和文本文件",
+ "fx07": "保留目标",
+ "fx08": "移除目标",
+ "fx09": "助手将不再朝这个目标工作。你的对话和文件保持不变。",
+ "fx10": "此模型可以读取图片，但这里安装的引擎还不包含图片读取器，所以“读取图片”已关闭。请在“设置 → 关于”中更新引擎后再开启。",
+ "fx11": "显示你的调优“{0}”的取值。",
+ "fx12": "你的调优“{0}”设置了",
+ "fx13": "原为 {0}",
+ "fx14": "· {0} 内存",
+ "fx15": "消息没有被取消",
+ "fx16": "程序的额外设置",
+ "fx17": "用 AI 起草",
+ "fx18": "思考时间",
+ "fx19": "写作时间",
+ "fx20": "词元/秒",
+ "fx21": "% 的上下文",
+ "fx22": "此页面需要从互联网加载文件，预览不会加载这些文件，所以看起来可能不完整。“查看代码”会显示实际写入的内容。",
+ "fx23": "保留 A",
+ "fx24": "保留 B",
+ "fx25": "用时",
+ "fx26": "波动",
+ "fx27": "已更改",
+ "fx28": "无",
+ "fx29": "两个版本都已就绪。比较 A 和 B，然后保留其中一个。",
+ "fx30": "助手仍在回答",
+ "fx31": "等它回答完再发送你的消息。",
+ "fx32": "消息没有进入队列",
+ "fx33": "滚动到最新消息",
+ "fx34": "移除任务",
+ "fx35": "开始新对话；保留当前这个",
+ "fx36": "让助手先写一份计划；在你批准之前不会运行任何内容",
+ "fx37": "搜索网络、阅读网页，并附上来源作答",
+ "fx38": "已复制",
+ "fx39": "回复",
+ "fx40": "消息",
+ "fx41": "已添加 PDF",
+ "fx42": "请选中文字，然后按 Ctrl+C 复制。",
+ "fx43": "{0} 已在此对话中。请在下一条消息里询问它。",
+ "fx44": "引擎已就绪。",
+ "fx45": "下一步：选择一个模型。",
+ "fx46": "正在下载引擎",
+ "fx47": "你可以关闭 Strata；下次会从中断的位置继续下载。",
+ "fx48": "欢迎使用 Strata",
+ "fx49": "正在查看你的显卡…",
+ "fx50": "Strata 找到了你的显卡：",
+ "fx51": "找到 {0} 张显卡。Strata 会用第一张来运行引擎；之后可在设置中更改。",
+ "fx52": "Strata 没有识别到受支持的显卡。",
+ "fx53": "要在它上面运行模型，Strata 需要先下载一个文件：",
+ "fx54": "这张显卡对应的引擎",
+ "fx55": "引擎大约需要此磁盘上 {0} GB 的可用空间，目前只有 {1} GB 可用。请先腾出空间，然后继续。",
+ "fx56": "它来自 Strata 自己的更新服务器，使用前会先校验。你的模型和对话不会受到影响。",
+ "fx57": "Strata 无法连接 github.com。请检查网络后重试，或在另一台电脑上下载引擎文件，再在这里选择它。",
+ "fx58": "这里已安装的引擎适用于另一品牌的显卡。",
+ "fx59": "Strata 无法根据更新列表为这台电脑选择引擎。",
+ "fx60": "不安装引擎，继续",
+ "fx61": "下载已中断。点“继续”会从中断的位置接着下载。",
+ "fx62": "这是一个非常大的模型。下载大小为 {0} GB，需要差不多同样大小的可用磁盘空间。它可在一张 12 GB 显卡加 46 到 64 GB 内存上运行，速度较慢：每秒约 5 到 7 个词。内存放不下的部分会从你的 SSD 读取，所以 NVMe 硬盘很重要。",
+ "fx63": "你可以随时停止下载，之后再继续；它会从中断的位置接着下载。Strata 会在这里提醒你，但从不阻止你。",
+ "fx64": "更快",
+ "fx65": "完整质量",
+ "fx66": "默认（这台电脑上为“更快”）",
+ "fx67": "默认（这台电脑上为“完整质量”）",
+ "fx68": "更快（这台电脑上的默认）",
+ "fx69": "完整质量（这台电脑上的默认）"
+}

apps/host/src/screens/Chat.tsx

@@ -39,6 +39,7 @@ import { Btn, Icon, IconBtn, ErrorNotice, type IconName } from '../components/ui
 import { composerCap, scrollBehavior } from '../lib/responsive';
 import { relTime, cx, duration, tokens, tps } from '../lib/format';
 import { createSubagentExample, pushToast, setPreviewTabClosed, branchFrom, continueLast, markRead, resolveTool, retryLast, selectSession, rewindTo, sendMessage, stopStreaming, useStore, } from '../lib/store';
+import { copyText } from '../lib/clipboard';
 import { getSlashCommands } from '../lib/commands';
 import { useLocation } from '../lib/router';
 import { composerSends } from '../lib/shortcut-bindings';
@@ -616,11 +617,11 @@ function Message({ message: m, isLast, onEditPrompt, onPreview, onOpenLink, onOp
     const [sentTime, setSentTime] = useState(() => relTime(m.at));
     if (m.role === 'user') {
         return (<div className="st-msg st-msg--user" onMouseEnter={() => setSentTime(relTime(m.at))} onFocus={() => setSentTime(relTime(m.at))}>
-        <div className="st-bubble">{tr(m.photos?.length ? <ChatPhotos photos={m.photos}/> : null)}{m.markdown ? <Markdown text={m.content} onOpenLink={onOpenLink} imageSession={activeSession}/> : m.content}</div>
+        <div className="st-bubble">{tr(m.photos?.length ? <ChatPhotos photos={m.photos}/> : null)}{m.markdown ? <Markdown text={m.content} onOpenLink={onOpenLink} imageSession={activeSession}/> : <span className="st-bubble__text">{m.content}</span>}</div>
         <div className="st-msg__meta">
           <time dateTime={m.at} title={tr(new Date(m.at).toLocaleString(localeTag()))}>{tr(sentTime)}</time>
           <span className="st-msg__actions">
-            <IconBtn name="copy" title={tr("Copy message")} onClick={() => void navigator.clipboard.writeText(m.content)}/>
+            <IconBtn name="copy" title={tr("Copy message")} onClick={() => void copyText(m.content, 'Message', { toast: pushToast })}/>
             <IconBtn name="refresh" title={tr("Rewind to here")} disabled={streaming} onClick={() => {
                 const prompt = rewindTo(m.id);
                 if (prompt !== null)
@@ -659,11 +660,11 @@ function Message({ message: m, isLast, onEditPrompt, onPreview, onOpenLink, onOp
       {tr(!m.streaming && !m.timeSkipId && (m.content || m.error) ? (<div className="st-msg__meta">
           <span className="st-msg__actions">
             {tr(isLast ? <>
-              <IconBtn name="copy" title={tr("Copy response")} onClick={() => void navigator.clipboard.writeText(m.content)}/>
+              <IconBtn name="copy" title={tr("Copy response")} onClick={() => void copyText(m.content, 'Response', { toast: pushToast })}/>
               <IconBtn name="refresh" title={tr("Ask again")} onClick={() => void retryLast(m.id)}/>
             </> : null)}
             <MessageMenu label={tr("More response actions")}>
-              {tr(!isLast ? <><button role="menuitem" className="menu__item" onClick={() => void navigator.clipboard.writeText(m.content)}>{tr("Copy response")}</button><button role="menuitem" className="menu__item" onClick={() => void retryLast(m.id)}>{tr("Ask again")}</button></> : null)}
+              {tr(!isLast ? <><button role="menuitem" className="menu__item" onClick={() => void copyText(m.content, 'Response', { toast: pushToast })}>{tr("Copy response")}</button><button role="menuitem" className="menu__item" onClick={() => void retryLast(m.id)}>{tr("Ask again")}</button></> : null)}
               {tr(isLast ? <button role="menuitem" className="menu__item" onClick={() => void continueLast()}>{tr("Continue")}</button> : null)}
               <button role="menuitem" className="menu__item" onClick={() => branchFrom(m.id)}>{tr("Branch from here")}</button>
               {tr(m.tokens || m.tps || m.durationMs ? <p className="xs muted response-stats">{tr(m.tokens ? `${tokens(m.tokens)} tokens` : '')}{tr(m.tps ? ` · ${tps(m.tps)} tok/s` : '')}{tr(m.durationMs ? ` · ${duration(m.durationMs)}` : '')}{tr(m.demo ? ' · Example' : '')}</p> : null)}

apps/host/src/screens/ModelRun.tsx

@@ -1,5 +1,5 @@
 import { tr } from '../lib/i18n';
-import { useEffect, useMemo, useRef, useState } from 'react';
+import { useEffect, useMemo, useRef, useState, useSyncExternalStore } from 'react';
 import { ActionError, Btn, Dialog, ErrorNotice, Icon, Select } from '../components/ui';
 import { Screen } from '../components/layout';
 import { DemoTest } from '../components/EngineExperience';
@@ -24,7 +24,7 @@ import { familyVersion, modelFamilies } from '../lib/model-versions';
 import { sizeGb } from '../lib/format';
 import { applyImageModel, getState, useLifecycle, loadRuntimeModel, loadVariant, pushToast, restartEngine, saveEngine, selectImageModel, setConfigDraft, useStore, validateEngine } from '../lib/store';
 import type { ImageModelChoice, RuntimeModels, RuntimeModel } from '../lib/types';
-import { useNative } from '../lib/native';
+import { useNative, nativeSettled, subscribeNative } from '../lib/native';
 import { NativeModels } from '../components/NativeModels';
 import { NativeLocalModel } from '../components/NativeLocalModel';
 import { parseLocation } from '../lib/router';
@@ -35,8 +35,12 @@ type Issue = {
 type RunStage = 'idle' | 'checking' | 'loading' | 'ready';
 export function ModelRunScreen() {
     const native = useNative();
+    const settled = useSyncExternalStore(subscribeNative, nativeSettled);
     const location = parseLocation(window.location.hash), entry = location.param;
     const [other, setOther] = useState(entry === 'local' || entry === 'local-import'), [importFirst, setImportFirst] = useState(entry === 'local-import');
+    // Before the engine's answer arrives the page would show the bundled Starter and then jump to the installed model (#3740): show a neutral placeholder instead.
+    if (!native && !settled)
+        return <div className="main__body"><div className="wrap stack" role="status" aria-label={tr("Loading…")}><div className="skel" style={{ height: 20, width: '60%' }}/><div className="skel" style={{ height: 20, width: '80%' }}/><div className="skel" style={{ height: 20, width: '70%' }}/></div></div>;
     if (native && other)
         return <NativeLocalModel onBack={() => { setOther(false); setImportFirst(false); }}/>;
     if (native && !other)

apps/host/src/screens/Monitor.tsx

@@ -12,7 +12,7 @@ import { Brand } from '../components/Brand';
 import { Bar, Btn, Icon, IconBtn, Select, type IconName } from '../components/ui';
 import { Screen } from '../components/layout';
 import { contextLabel, duration, tokens, tps } from '../lib/format';
-import { gpuCapacity, gpuId, gpuMetric, hasReading } from '../lib/monitor-hardware';
+import { gpuCapacity, gpuId, gpuMetric, gpuReported, hasReading, shortGpuName } from '../lib/monitor-hardware';
 import { useStore } from '../lib/store';
 import { useKept } from '../lib/kept-state';
 import type { Hardware, MonitorState, ServeRequest } from '../lib/types';
@@ -115,10 +115,13 @@ function LegacyMonitorScreen({ native }: {
     const selectedCpus = cpuChoice === 'all' ? processors : processors.filter(p => p.id === cpuChoice);
     const multipleGpus = selectedGpus.length > 1, shared = selectedGpus.length > 0 && selectedGpus.every(g => g.unified);
     const readings = data.hardware.gpus;
-    const gpuValue = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => gpuMetric(selectedGpus, readings, key, mode);
-    const gpuSource = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => hasReading(gpuValue(key, mode)) ? sourceLabel(readings?.find(r => r.id === gpuId(selectedGpus[0]))?.source) : 'Unavailable';
+    // A card that cannot report a value (an integrated one with no temperature sensor) is left out of that value, and the card the figure is from is named.
+    const report = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => gpuReported(selectedGpus, readings, key, mode);
+    const gpuValue = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => report(key, mode).value;
+    const whose = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => { const r = report(key, mode); return r.partial ? r.devices.map(d => shortGpuName(d.name)).join(' + ') : null; };
+    const gpuSource = (key: Parameters<typeof gpuMetric>[2], mode: Parameters<typeof gpuMetric>[3] = 'sum') => hasReading(gpuValue(key, mode)) ? sourceLabel(readings?.find(r => r.id === gpuId(report(key, mode).devices[0] ?? selectedGpus[0]))?.source) : 'Unavailable';
     const gpuLoad = gpuValue('utilizationPct', 'mean'), vram = gpuValue('memoryUsedGb'), temperature = gpuValue('temperatureC', 'max'), power = gpuValue('powerW'), powerLimit = gpuValue('powerLimitW'), pcieRx = gpuValue('pcieRxMbs');
-    const vramTotal = gpuCapacity(selectedGpus);
+    const vramTotal = gpuCapacity(report('memoryUsedGb').partial ? report('memoryUsedGb').devices : selectedGpus);
     const singleReading = selectedGpus.length === 1 ? readings?.find(r => r.id === gpuId(selectedGpus[0])) : undefined;
     const gen = singleReading?.pcieGenMax ?? singleReading?.pcieGen, width = singleReading?.pcieWidth;
     const cpu = cpuChoice === 'all' ? data.hardware.cpuLoad : data.hardware.cpus?.find(p => p.id === cpuChoice)?.utilizationPct;
@@ -164,11 +167,11 @@ function LegacyMonitorScreen({ native }: {
     </section>
     <div className="monitor-metrics">
       {tr(!multipleScope ? <MonitorMetric label={tr("Speed")} icon="gauge" value={number(decode, 1)} unit={hasReading(decode) ? 't/s' : ''} source={throughput} sub={writing ? 'Decode now' : last ? 'Decode last request' : 'Decode'} secondary={<div><div className="st-metric__value">{tr(number(prefill))}{tr(hasReading(prefill) ? <span className="st-metric__unit">{tr("t/s")}</span> : null)}</div><div className="monitor-metric__sub xs muted">{tr(data.phase === 'reading' ? 'Prefill now' : writing ? 'Prefill this request' : last ? 'Prefill last request' : 'Prefill')}</div></div>} chart={<ReferenceSpark label={tr("Speed")} data={history.map(s => throughputKnown ? s.outputTps : null)} secondary={{ data: history.map(s => throughputKnown ? s.promptTps : null), label: 'Prefill', tone: 'var(--st-chart-prefill)' }} tone="var(--st-chart-decode)" unit="t/s" timestamps={timestamps}/>}/> : null)}
-      <MonitorMetric label={tr("GPU load")} icon="gpu" value={number(gpuLoad)} unit={hasReading(gpuLoad) ? '%' : ''} source={gpuSource('utilizationPct', 'mean')} sub={gpuName} chart={chart('GPU load', historyGpu('utilizationPct', 'gpuLoad', 'mean'), '%', 100)}/>
-      <MonitorMetric label={tr(shared ? 'Shared GPU memory' : 'VRAM')} icon="layers" value={number(vram, 1)} unit={hasReading(vram) ? vramTotal ? `/ ${number(vramTotal, 0)} GB` : 'GB' : ''} source={gpuSource('memoryUsedGb')} sub={shared ? 'Same memory pool as system RAM' : multipleGpus ? 'Total across selected GPUs' : cacheKnown && devices.length === 1 ? `${number(data.expertCache.used)} experts cached` : 'GPU memory'} chart={chart(shared ? 'Shared GPU memory' : 'VRAM', historyGpu('memoryUsedGb', 'vramUsedGb'), 'GB', vramTotal)}/>
-      <MonitorMetric label={tr("GPU temp")} icon="thermometer" value={number(temperature)} unit={hasReading(temperature) ? '°C' : ''} source={gpuSource('temperatureC', 'max')} sub={multipleGpus ? 'Hottest selected GPU' : selectedGpus[0]?.name ?? (selectedInstance && !selectedInstance.gpuIds.length ? native ? 'Automatic GPU placement' : 'CPU only · no GPU assigned' : 'No GPU detected')} chart={chart('GPU temperature', historyGpu('temperatureC', 'gpuTempC', 'max'), '°C', 90, 'var(--st-warn)')}/>
-      <MonitorMetric label={tr("Power")} icon="bolt" value={number(power)} unit={hasReading(power) ? 'W' : ''} source={gpuSource('powerW')} sub={hasReading(powerLimit) ? `of ${number(powerLimit)} W limit` : multipleGpus ? 'Total across selected GPUs' : 'GPU power draw'} chart={chart('GPU power', historyGpu('powerW', 'powerW'), 'W', powerLimit ?? undefined)}/>
-      <MonitorMetric label={tr("PCIe")} icon="link" value={hasReading(gen) ? `Gen${gen}` : multipleGpus ? number(pcieRx, 1) : '—'} unit={hasReading(gen) && hasReading(width) ? `x${width}` : multipleGpus && hasReading(pcieRx) ? 'MB/s' : ''} source={hasReading(gen) ? sourceLabel(singleReading?.source) : gpuSource('pcieRxMbs')} sub={hasReading(pcieRx) ? `To GPU ${number(pcieRx, 1)} MB/s${hasReading(gen) && hasReading(singleReading?.pcieGen) && singleReading.pcieGen < gen ? ` · idle Gen${singleReading.pcieGen}` : ''}` : shared ? 'Shared memory · no PCIe link' : multipleGpus ? 'Total transfer to selected GPUs' : 'Transfer to GPU unavailable'} chart={chart('PCIe transfer', historyGpu('pcieRxMbs', 'pcieRxMbs'), 'MB/s', undefined, 'var(--st-info)')}/>
+      <MonitorMetric label={tr("GPU load")} icon="gpu" value={number(gpuLoad)} unit={hasReading(gpuLoad) ? '%' : ''} source={gpuSource('utilizationPct', 'mean')} sub={whose('utilizationPct', 'mean') ?? gpuName} chart={chart('GPU load', historyGpu('utilizationPct', 'gpuLoad', 'mean'), '%', 100)}/>
+      <MonitorMetric label={tr(shared ? 'Shared GPU memory' : 'VRAM')} icon="layers" value={number(vram, 1)} unit={hasReading(vram) ? vramTotal ? `/ ${number(vramTotal, 0)} GB` : 'GB' : ''} source={gpuSource('memoryUsedGb')} sub={whose('memoryUsedGb') ?? (shared ? 'Same memory pool as system RAM' : multipleGpus ? 'Total across selected GPUs' : cacheKnown && devices.length === 1 ? `${number(data.expertCache.used)} experts cached` : 'GPU memory')} chart={chart(shared ? 'Shared GPU memory' : 'VRAM', historyGpu('memoryUsedGb', 'vramUsedGb'), 'GB', vramTotal)}/>
+      <MonitorMetric label={tr("GPU temp")} icon="thermometer" value={number(temperature)} unit={hasReading(temperature) ? '°C' : ''} source={gpuSource('temperatureC', 'max')} sub={whose('temperatureC', 'max') ?? (multipleGpus ? 'Hottest selected GPU' : selectedGpus[0]?.name ?? (selectedInstance && !selectedInstance.gpuIds.length ? native ? 'Automatic GPU placement' : 'CPU only · no GPU assigned' : 'No GPU detected'))} chart={chart('GPU temperature', historyGpu('temperatureC', 'gpuTempC', 'max'), '°C', 90, 'var(--st-warn)')}/>
+      <MonitorMetric label={tr("Power")} icon="bolt" value={number(power)} unit={hasReading(power) ? 'W' : ''} source={gpuSource('powerW')} sub={whose('powerW') ?? (hasReading(powerLimit) ? `of ${number(powerLimit)} W limit` : multipleGpus ? 'Total across selected GPUs' : 'GPU power draw')} chart={chart('GPU power', historyGpu('powerW', 'powerW'), 'W', powerLimit ?? undefined)}/>
+      <MonitorMetric label={tr("PCIe")} icon="link" value={hasReading(gen) ? `Gen${gen}` : multipleGpus ? number(pcieRx, 1) : '—'} unit={hasReading(gen) && hasReading(width) ? `x${width}` : multipleGpus && hasReading(pcieRx) ? 'MB/s' : ''} source={hasReading(gen) ? sourceLabel(singleReading?.source) : gpuSource('pcieRxMbs')} sub={hasReading(pcieRx) ? `To GPU ${number(pcieRx, 1)} MB/s${whose('pcieRxMbs') ? ` · ${whose('pcieRxMbs')}` : ''}${hasReading(gen) && hasReading(singleReading?.pcieGen) && singleReading.pcieGen < gen ? ` · idle Gen${singleReading.pcieGen}` : ''}` : shared ? 'Shared memory · no PCIe link' : multipleGpus ? 'Total transfer to selected GPUs' : 'Transfer to GPU unavailable'} chart={chart('PCIe transfer', historyGpu('pcieRxMbs', 'pcieRxMbs'), 'MB/s', undefined, 'var(--st-info)')}/>
       <MonitorMetric label={tr("CPU")} icon="cpu" value={number(cpu)} unit={hasReading(cpu) ? '%' : ''} source={hasReading(cpu) ? 'Measured' : 'Unavailable'} sub={cpuName} chart={chart('CPU utilization', historyCpu, '%', 100)}/>
       <MonitorMetric label={tr("Disk read")} icon="disk" value={number(hasReading(data.hardware.diskReadGbs) ? data.hardware.diskReadGbs >= 1 ? data.hardware.diskReadGbs : data.hardware.diskReadGbs * 1024 : null, 1)} unit={hasReading(data.hardware.diskReadGbs) ? data.hardware.diskReadGbs >= 1 ? 'GB/s' : 'MB/s' : ''} source={hasReading(data.hardware.diskReadGbs) ? 'Measured' : 'Unavailable'} sub={hasReading(data.hardware.diskWriteMbs) ? `Write ${number(data.hardware.diskWriteMbs, 1)} MB/s` : 'Read throughput'} chart={chart('Disk read', history.map(s => hasReading(s.diskReadGbs) ? s.diskReadGbs * 1024 : null), 'MB/s', undefined, 'var(--st-info)')}/>
     </div>

apps/host/src/screens/Serving.tsx

@@ -1,3 +1,4 @@
+import { copyText } from '../lib/clipboard';
 import { tr } from '../lib/i18n';
 import { appBaseUrl } from '../lib/connect-urls';
 import { deviceLabel, instanceLabel } from '../lib/runtime-models';
@@ -73,13 +74,7 @@ export function ServingScreen() {
         }
     }
     async function copyConnectionValue(value: string, label: string) {
-        try {
-            await navigator.clipboard.writeText(value);
-            pushToast('success', 'Copied', label);
-        }
-        catch {
-            pushToast('warn', 'Couldn’t copy', 'Select the value and copy it manually.');
-        }
+        await copyText(value, label, { toast: pushToast });
     }
     const code = `curl ${serving.baseUrl}${protocol === 'responses' ? '/responses' : protocol === 'openai' ? serving.endpoints.openai : serving.endpoints.anthropic} \\\n  -H 'Content-Type: application/json'${serving.access.apiKeySet ? " \\\n  -H 'Authorization: Bearer YOUR_API_KEY'" : ''} \\\n  -d '${JSON.stringify({ model: loaded?.apiModelId ?? 'YOUR_MODEL_ID', ...(protocol === 'responses' ? { input: 'Hello', store: false } : { ...(protocol === 'anthropic' ? { max_tokens: 256 } : {}), messages: [{ role: 'user', content: 'Hello' }] }) }, null, 2)}'`;
     return <Screen title={tr("Serving")} actions={<><Btn icon="link" onClick={() => setCloudflareOpen(true)}>{tr("Cloudflare tunnel")}</Btn><IconBtn name="info" title={tr("Connection guide")} onClick={() => setGuide(true)}/></>}><div className="stack stack--lg">

apps/host/src/screens/Setup.tsx

@@ -3,10 +3,17 @@ import { GuidedSetup } from '../components/GuidedSetup';
 import { useNative } from '../lib/native';
 import { useStore } from '../lib/store';
 import { useEngineUnpacking } from '../lib/engine-setup';
+import { EngineFirstRun, useEngineNeeded } from '../components/EngineFirstRun';
+import { useEffect, useState } from 'react';
 /** Every setup entry uses the same guided onboarding. */
 export function SetupScreen() {
     const native = useNative(), setup = useStore(s => s.setup);
+    const needsEngine = useEngineNeeded(), [engineStepDone, setEngineStepDone] = useState(false), [cardShown, setCardShown] = useState(false);
+    useEffect(() => { if (needsEngine) setCardShown(true); }, [needsEngine]);
     const unpacking = useEngineUnpacking(!native || !setup);
+    // No engine on this PC yet: the first-run card comes before the model steps (it works before the native snapshot has connected).
+    if (!engineStepDone && !setup?.complete && (needsEngine || cardShown))
+        return <EngineFirstRun onDone={() => setEngineStepDone(true)}/>;
     if (!native || !setup)
         return <div className="setup guided-onboarding"><p className="onboard-loading" role="status">{tr("Getting your setup ready\u2026")}</p>{unpacking ? <p className="onboard-loading small" role="status">{tr("Unpacking the engine that came with the app. This takes about a minute the first time.")}</p> : null}</div>;
     return <GuidedSetup />;

apps/host/src/styles/app.css

@@ -4083,6 +4083,8 @@ textarea.st-input {
 .st-msg--user .st-bubble {
   background: var(--st-accent-surface);
   color: var(--st-accent-surface-ink);
+  white-space: pre-wrap;   /* a typed or pasted message keeps its line breaks (#3720) */
+  overflow-wrap: anywhere;
 }
 
 /* October 2026 clarity pass. App-specific extensions survive design-kit sync. */
@@ -7517,3 +7519,6 @@ textarea {
 .md-math-block .md-math--display { margin: 0; }
 .md-math .katex { font-size: 1.08em; }
 .md-math .katex-display { margin: 0; }
+
+/* A message the person typed keeps its line breaks (#3720). */
+.st-bubble__text { white-space: pre-wrap; overflow-wrap: anywhere; }

apps/host/tests/bundled-engine.test.mjs

@@ -5,7 +5,7 @@ import { mkdtempSync, mkdirSync, writeFileSync, readFileSync, existsSync, readdi
 import { createHash } from 'node:crypto';
 import { tmpdir } from 'node:os';
 import { join } from 'node:path';
-import { installBundledEngine, compareVersions, wrongMakeNotice } from '../server/bundled-engine.mjs';
+import { installBundledEngine, removeVerifiedBundle, cleanupAfterInstall, compareVersions, wrongMakeNotice } from '../server/bundled-engine.mjs';
 
 // the make of card is read from this computer unless a test names it; the existing tests are written for an NVIDIA PC
 process.env.STRATA_ENGINE_BACKEND = 'cuda';
@@ -185,3 +185,108 @@ test('Windows: the display adapters decide the make, and a leftover nvidia-smi d
   assert.equal(windowsDisplayVendors({ platform: 'linux', run: () => { throw new Error('must not run'); } }).size, 0);
   assert.equal(windowsDisplayVendors({ platform: 'win32', run: () => { throw new Error('no registry'); } }).size, 0);
 });
+
+test('after an update, the engine bundle of the old install folder is removed only when the same engine is complete in the store', async () => {
+  const t = setup();
+  try {
+    const name = makePackage(t.bundle, '0.1.48');
+    writeFileSync(join(t.bundle, '.gitignore'), 'ignore-all');
+    const lines = [];
+    // 1. nothing in the store yet: kept, and one line says why
+    let r = await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components, log: l => lines.push(l) });
+    assert.equal(r.removed, false);
+    assert.equal(lines.length, 1);
+    assert.match(lines[0], /kept in the install folder.*not \(or not completely\) in the engine store/);
+    assert.ok(existsSync(join(t.bundle, name)));
+    // 2. the engine is copied (the app's own first start does this)
+    assert.equal((await installBundledEngine({ bundleDir: t.bundle, components: t.components })).action, 'installed');
+    // 3. a store file with the right size and the wrong content: kept (the hash is checked, not only the size)
+    const target = join(t.engine, name, 'strata.exe');
+    const good = readFileSync(target);
+    writeFileSync(target, Buffer.alloc(good.length, 'x'));
+    lines.length = 0;
+    r = await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components, log: l => lines.push(l) });
+    assert.equal(r.removed, false);
+    assert.equal(lines.length, 1, 'exactly one line');
+    assert.ok(existsSync(join(t.bundle, name)));
+    // 4. a store file with the wrong size: kept
+    writeFileSync(target, Buffer.concat([good, Buffer.from('extra')]));
+    assert.equal((await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components })).removed, false);
+    // 5. the store copy is whole: the bundle goes, its .gitignore stays, and the store is untouched
+    writeFileSync(target, good);
+    lines.length = 0;
+    r = await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components, log: l => lines.push(l) });
+    assert.equal(r.removed, true);
+    assert.equal(existsSync(join(t.bundle, name)), false);
+    assert.ok(existsSync(join(t.bundle, '.gitignore')));
+    assert.equal(readFileSync(target, 'utf8'), 'engine-0.1.48');
+    assert.match(lines.at(-1), /was removed; the same engine is complete in the engine store/);
+    // 6. nothing left to do
+    assert.equal((await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components })).removed, false);
+    // 7. a different version in the store does not count
+    const other = makePackage(t.bundle, '0.1.49');
+    assert.equal((await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components })).removed, false);
+    assert.ok(existsSync(join(t.bundle, other)));
+  } finally { t.cleanup(); }
+});
+
+test('the bundle cleanup lines reach the output of the host (the desktop log copies it), for "removed" and for "kept"', async () => {
+  const t = setup();
+  const seen = [], real = console.log;
+  try {
+    const name = makePackage(t.bundle, '0.1.48');
+    console.log = line => { seen.push(String(line)); };
+    // kept: the engine is not in the store yet
+    await cleanupAfterInstall(Promise.resolve({ action: 'kept' }), { bundleDir: t.bundle, components: t.components });
+    assert.equal(seen.length, 1);
+    assert.match(seen[0], /^engine bundle: kept in the install folder/);
+    // removed: the engine is in the store and whole
+    const installed = await installBundledEngine({ bundleDir: t.bundle, components: t.components });
+    assert.equal(installed.action, 'installed');
+    seen.length = 0;
+    await cleanupAfterInstall(Promise.resolve({ action: 'kept' }), { bundleDir: t.bundle, components: t.components });
+    assert.equal(seen.length, 1);
+    assert.match(seen[0], /^engine bundle: the copy that came with the installer \(.*\) was removed/);
+    assert.equal(existsSync(join(t.bundle, name)), false);
+    // nothing to say when the engine step did nothing (no bundle) or was refused
+    seen.length = 0;
+    await cleanupAfterInstall(Promise.resolve({ action: 'none' }), { bundleDir: t.bundle, components: t.components });
+    await cleanupAfterInstall(Promise.resolve({ action: 'wrong-make' }), { bundleDir: t.bundle, components: t.components });
+    await cleanupAfterInstall(Promise.reject(new Error('boom')), { bundleDir: t.bundle, components: t.components });
+    assert.deepEqual(seen, []);
+  } finally { console.log = real; t.cleanup(); }
+});
+
+test('macOS: the engine bundle inside a signed .app stays (deleting it breaks the signature); outside an .app, or on another system, it is removed as before', async () => {
+  const t = setup();
+  const platform = Object.getOwnPropertyDescriptor(process, 'platform');
+  const as = value => Object.defineProperty(process, 'platform', { value, configurable: true });
+  try {
+    const app = join(t.base, 'Strata.app', 'Contents', 'Resources', 'engine-bundle');
+    mkdirSync(app, { recursive: true });
+    const inApp = makePackage(app, '0.1.48');
+    const outside = makePackage(t.bundle, '0.1.48');
+    // the engine is in the store (the app's own first start copies it), so the bundle would be removable
+    assert.equal((await installBundledEngine({ bundleDir: t.bundle, components: t.components })).action, 'installed');
+    const lines = [];
+    // 1. macOS, bundle inside Strata.app: kept, with one line that says why
+    as('darwin');
+    let r = await removeVerifiedBundle({ bundleDir: app, components: t.components, log: l => lines.push(l) });
+    assert.equal(r.removed, false);
+    assert.ok(existsSync(join(app, inApp, 'strata.exe')), 'the signed app keeps its engine files');
+    assert.equal(lines.length, 1);
+    assert.match(lines[0], /kept in the install folder.*macOS app bundles must remain unchanged after signing/);
+    // 2. macOS, bundle outside an .app: removed as before
+    r = await removeVerifiedBundle({ bundleDir: t.bundle, components: t.components, log: () => {} });
+    assert.equal(r.removed, true);
+    assert.equal(existsSync(join(t.bundle, outside)), false);
+    // 3. another system, bundle inside a folder called .app: removed as before (the guard is for macOS only)
+    as('linux');
+    r = await removeVerifiedBundle({ bundleDir: app, components: t.components, log: () => {} });
+    assert.equal(r.removed, true);
+    assert.equal(existsSync(join(app, inApp)), false);
+  } finally {
+    Object.defineProperty(process, 'platform', platform);
+    t.cleanup();
+  }
+});

apps/host/tests/chat-attach-file.test.mjs

@@ -0,0 +1,22 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { readFile } from 'node:fs/promises';
+import { transform } from 'esbuild';
+
+const { code } = await transform(await readFile(new URL('../src/lib/chat-attach-file.ts', import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' });
+const { uploadChatFile, FILE_ACCEPT } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
+
+test('the file dialog lists PDFs and text on Linux: the types sit next to the extensions (#3838)', () => {
+  for (const t of ['image/*', 'application/pdf', 'text/*', '.pdf', '.md']) assert.ok(FILE_ACCEPT.split(',').includes(t), t);
+});
+test('a PDF is sent to the chat folder through the upload route and named back', async () => {
+  let seen;
+  const fake = async (url, init) => { seen = { url, init }; return { ok: true, json: async () => ({ files: [{ name: 'report-2.pdf', attached: true }] }) }; };
+  const out = await uploadChatFile(new File(['%PDF-1.4'], 'report.pdf', { type: 'application/pdf' }), 's 1', fake);
+  assert.equal(out.name, 'report-2.pdf');
+  assert.match(seen.url, /\/api\/chat\/upload\?sessionId=s%201&name=report\.pdf$/);
+  assert.equal(seen.init.method, 'POST'); assert.equal(seen.init.headers['content-type'], 'application/pdf');
+});
+test('a refused upload says why', async () => {
+  await assert.rejects(uploadChatFile(new File(['x'], 'a.pdf'), 's', async () => ({ ok: false, json: async () => ({ error: '"a.pdf" is bigger than 12 MB.' }) })), /bigger than 12 MB/);
+});

apps/host/tests/clipboard-copy.test.mjs

@@ -0,0 +1,30 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { readFile } from 'node:fs/promises';
+import { transform } from 'esbuild';
+
+const { code } = await transform(await readFile(new URL('../src/lib/clipboard.ts', import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' });
+const { copyText } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
+const toasts = () => { const list = []; return { list, toast: (...a) => list.push(a) }; };
+
+test('Copy says Copied when the clipboard takes the text (#3731)', async () => {
+  const t = toasts(); let got = '';
+  assert.equal(await copyText('hello', 'Response', { clipboard: { writeText: async v => { got = v; } }, toast: t.toast }), true);
+  assert.equal(got, 'hello'); assert.equal(t.list[0][0], 'success');
+});
+test('a refused clipboard falls back to the older copy command', async () => {
+  const t = toasts(); let got = '';
+  assert.equal(await copyText('x', 'Response', { clipboard: { writeText: async () => { throw new Error('denied'); } }, legacyCopy: v => { got = v; return true; }, toast: t.toast }), true);
+  assert.equal(got, 'x'); assert.equal(t.list[0][0], 'success');
+});
+test('when nothing works the person is told, never left with a silent click', async () => {
+  const t = toasts();
+  assert.equal(await copyText('x', 'Response', { clipboard: null, legacyCopy: () => false, toast: t.toast }), false);
+  assert.equal(t.list.length, 1); assert.equal(t.list[0][0], 'warn'); assert.match(t.list[0][2], /Ctrl\+C/);
+});
+test('the typed message keeps its line breaks (#3720) and the chat uses the shared copy', async () => {
+  const css = await readFile(new URL('../src/styles/app.css', import.meta.url), 'utf8');
+  assert.match(css, /\.st-bubble__text\s*\{[^}]*white-space:\s*pre-wrap/);
+  const chat = await readFile(new URL('../src/screens/Chat.tsx', import.meta.url), 'utf8');
+  assert.doesNotMatch(chat, /void navigator\.clipboard\.writeText/);
+});

apps/host/tests/component-updates.test.mjs

@@ -1,11 +1,12 @@
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { EventEmitter } from 'node:events';
-import { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
+import { mkdtempSync, mkdirSync, writeFileSync, rmSync, readFileSync, existsSync } from 'node:fs';
 import { join, basename } from 'node:path';
 import { tmpdir } from 'node:os';
 import { bundledPython, controlEnvironment, createControl, findControl, runCli, updatedControlDirectory } from '../server/control-runtime.mjs';
-import { checkComponentUpdates } from '../server/updates.mjs';
+import { checkComponentUpdates, engineFirstRun } from '../server/updates.mjs';
 import { createAppUpdater } from '../server/app-updater.mjs';
 import { createNativeControl } from '../server/native-control.mjs';
 
@@ -103,8 +104,25 @@ test('createControl: the update calls ask the explicit commands; a failed step c
   await assert.rejects(failing.update({}), err => err.code === 'engine_serving' && /serving/.test(err.message) && err.exitCode === 7);
 });
 
+test('the Settings check says so, in plain words, when the own update check of the app fails, and keeps the raw text for Details', async () => {
+  const feed = (control = { installed: '0.2.5', offered: '0.2.5', status: 'current' }) => ({ version: '0.2.5', async updateCheck() { return { ok: true, feed: { sequence: 3 }, engine: { installed: { version: '0.1.50' }, offered: { version: '0.1.50' }, status: 'current' }, control, app: { status: 'not-in-feed' } }; } });
+  const failing = { check: async () => { throw new Error('error decoding response body for url (http://127.0.0.1:19090/latest.json)'); } };
+  const nothing = await checkComponentUpdates({ control: feed(), appUpdater: failing, appVersion: '0.2.5' });
+  assert.equal(nothing.strata.status, 'error', 'it no longer says "up to date" when the app could not be checked');
+  assert.match(nothing.strata.message, /couldn't check for a new version of the app itself/);
+  assert.doesNotMatch(nothing.strata.message, /decoding|http|latest\.json/, 'no raw text in the main line');
+  assert.match(nothing.strata.details, /error decoding response body/);
+  const withControl = await checkComponentUpdates({ control: feed({ installed: '0.2.5', offered: '0.2.6', status: 'available' }), appUpdater: failing, appVersion: '0.2.5' });
+  assert.equal(withControl.strata.status, 'available');
+  assert.match(withControl.strata.message, /new version of Strata is available.*couldn't check for a new version of the app itself/s);
+  assert.match(withControl.strata.details, /decoding/);
+  const fine = await checkComponentUpdates({ control: feed(), appUpdater: { check: async () => ({ available: false }) }, appVersion: '0.2.5' });
+  assert.equal(fine.strata.status, 'current');
+  assert.equal(fine.strata.details, undefined);
+});
+
 test('the Settings update check maps the feed to the existing result shape', async () => {
-  const report = overrides => ({ ok: true, feed: { sequence: 3 }, engine: { installed: { version: '0.1.45' }, offered: { version: '0.1.46' }, status: 'available', download_bytes: 505 * (1 << 20) }, control: { installed: '0.1.45', offered: '0.1.45', status: 'current' }, app: { status: 'not-in-feed' }, ...overrides });
+  const report = overrides => ({ ok: true, feed: { sequence: 3 }, engine: { installed: { version: '0.1.45' }, offered: { version: '0.1.46' }, status: 'available', download_bytes: 505_000_000 }, control: { installed: '0.1.45', offered: '0.1.45', status: 'current' }, app: { status: 'not-in-feed' }, ...overrides });
   const make = value => ({ version: '0.1.45', async updateCheck() { if (value instanceof Error) throw value; return value; } });
   let result = await checkComponentUpdates({ control: make(report()), appVersion: '0.1.0' });
   assert.equal(result.engine.status, 'available');
@@ -113,7 +131,7 @@ test('the Settings update check maps the feed to the existing result shape', asy
   assert.doesNotMatch(result.engine.message, /0\.1\.4|sha|exit/i);
   assert.equal(result.engine.canInstall, true);
   assert.equal(result.strata.status, 'current');
-  result = await checkComponentUpdates({ control: make(report({ engine: { installed: null, offered: { version: '0.1.46' }, status: 'install', download_bytes: 505 * (1 << 20) } })) });
+  result = await checkComponentUpdates({ control: make(report({ engine: { installed: null, offered: { version: '0.1.46' }, status: 'install', download_bytes: 505_000_000 } })) });
   assert.equal(result.engine.status, 'available');
   assert.match(result.engine.message, /needs an engine to run models\. Press Update engine/);
   result = await checkComponentUpdates({ control: make(report({ engine: { installed: { version: '0.1.46' }, offered: { version: '0.1.46' }, status: 'current' } })) });
@@ -165,7 +183,7 @@ test('the shell bridge client exists only inside the desktop app, speaks to loop
 
 // ---------------------------------------------------------------------------------- the Settings buttons in the packaged app
 
-function fixture({ withApp = false, update } = {}) {
+function fixture({ withApp = false, update, appInstall } = {}) {
   const root = mkdtempSync(join(tmpdir(), 'strata-update-ops-'));
   const install = join(root, 'install'), data = join(root, 'data');
   mkdirSync(install, { recursive: true });
@@ -187,15 +205,16 @@ function fixture({ withApp = false, update } = {}) {
       previous = '0.1.45-windows-x86_64-cuda';
       return { ok: true, results: [{ component: 'engine', status: 'updated', installed_after: { version: '0.1.46' } }] };
     },
+    async installEngineFile(path, options) { calls.push(['install-file', path]); options.onEvent?.({ event: 'phase', phase: 'verify', message: 'Checking' }); return { ok: true, results: [{ component: 'engine', status: 'updated', installed_after: { version: '0.1.46' } }] }; },
     async rollbackEngine() { calls.push(['rollback']); previous = null; return { ok: true, to: '0.1.45' }; },
   };
   const spawned = [];
   const appUpdater = withApp ? {
     check: async () => ({ available: true, version: '0.2.0' }),
-    install: async ({ onProgress }) => { calls.push(['app-install']); onProgress({ downloaded: 50, total: 100 }); return { state: 'done' }; },
+    install: appInstall ?? (async ({ onProgress }) => { calls.push(['app-install']); onProgress({ downloaded: 50, total: 100 }); return { state: 'done' }; }),
   } : null;
   const native = createNativeControl({ control, appUpdater, directory: data, spawnProcess: (...args) => { if (!args[1]?.some(a => String(a).endsWith('strata_mcp.py'))) spawned.push(args); throw new Error('no process but the installer tool (Control strata_mcp.py, absent in this fixture) may be started by the host in packaged mode'); }, fetcher: async () => Response.json({}), requests: () => [] });
-  return { native, calls, spawned, cleanup: () => rmSync(root, { recursive: true, force: true }) };
+  return { native, calls, spawned, data, control, cleanup: () => rmSync(root, { recursive: true, force: true }) };
 }
 const finish = async (native, id) => { for (let i = 0; i < 400; i++) { const job = native.state().jobs.find(j => j.id === id); if (job.state !== 'running') return job; await new Promise(r => setTimeout(r, 10)); } throw new Error('job did not finish'); };
 
@@ -264,6 +283,101 @@ test('packaged: "Update Strata" updates Control through the feed, then the app t
   } finally { await f.native.close(); f.cleanup(); }
 });
 
+test('packaged: an app update that ends the app is recorded as finished by the new version, not as an interrupted operation', async () => {
+  const before = process.env.STRATA_APP_VERSION;
+  process.env.STRATA_APP_VERSION = '0.2.2';
+  const f = fixture({ withApp: true, appInstall: () => new Promise(() => {}) });      // the installer ends the app: install() never returns
+  try {
+    await f.native.refresh(true);
+    const started = f.native.operation('update-strata', {});
+    await new Promise(r => setTimeout(r, 60));
+    assert.equal(f.native.state().jobs.find(j => j.id === started.id).state, 'running');
+    const saved = JSON.parse(readFileSync(join(f.data, 'native-jobs.json'), 'utf8')).find(j => j.id === started.id);
+    assert.equal(saved.appUpdateFrom, '0.2.2', 'the job was saved with the version it started from before the app was ended');
+    // the app is gone; the installer starts the new one (0.2.3) on the same data
+    process.env.STRATA_APP_VERSION = '0.2.3';
+    const again = createNativeControl({ control: f.control, directory: f.data, spawnProcess: () => { throw new Error('no process'); }, fetcher: async () => Response.json({}), requests: () => [] });
+    const job = again.state().jobs.find(j => j.id === started.id);
+    assert.equal(job.state, 'done');
+    assert.equal(job.error, null);
+    assert.match(job.summary, /updated to 0\.2\.3/);
+    await again.close();
+    // the same record read by an app that did NOT change version stays an interruption
+    process.env.STRATA_APP_VERSION = '0.2.2';
+    const same = createNativeControl({ control: f.control, directory: f.data, spawnProcess: () => { throw new Error('no process'); }, fetcher: async () => Response.json({}), requests: () => [] });
+    const unfinished = same.state().jobs.find(j => j.id === started.id);
+    assert.equal(unfinished.state, 'error');
+    assert.match(unfinished.error, /update to 0\.2\.[0-9] did not finish.*releases/s, 'the app came back as the old version: the installer did not finish, and the alert says so');
+    await same.close();
+  } finally { if (before === undefined) delete process.env.STRATA_APP_VERSION; else process.env.STRATA_APP_VERSION = before; await f.native.close(); f.cleanup(); }
+});
+
+test('packaged: an update job an OLDER host left running is finished when the app program file is newer than the job', async () => {
+  const exe = new URL('../../strata-desktop.exe', import.meta.url);          // <install>/strata-desktop.exe as seen from <install>/host
+  const f = fixture({ withApp: true });
+  try {
+    const { fileURLToPath } = await import('node:url');
+    const old = { id: 'old-1', kind: 'update-strata', state: 'running', startedAt: new Date(Date.now() - 60_000).toISOString(), summary: 'Starting…', result: null, error: null };
+    writeFileSync(join(f.data, 'native-jobs.json'), JSON.stringify([old]));
+    const mk = () => createNativeControl({ control: f.control, directory: f.data, spawnProcess: () => { throw new Error('no process'); }, fetcher: async () => Response.json({}), requests: () => [] });
+    const before = mk();
+    assert.equal(before.state().jobs[0].state, 'error', 'no new program file: still an interruption');
+    await before.close();
+    writeFileSync(join(f.data, 'native-jobs.json'), JSON.stringify([old]));
+    writeFileSync(fileURLToPath(exe), 'new program');
+    try {
+      const after = mk();
+      assert.equal(after.state().jobs[0].state, 'done');
+      assert.match(after.state().jobs[0].summary, /updated/i);
+      await after.close();
+    } finally { rmSync(fileURLToPath(exe), { force: true }); }
+  } finally { await f.native.close(); f.cleanup(); }
+});
+
+test('packaged: "Update engine" works in the first seconds, before the native snapshot has connected', async () => {
+  const f = fixture();
+  try {
+    assert.equal(f.native.state().available, false, 'nothing has been read yet');
+    const started = f.native.operation('update-engine', {});      // used to throw "Connect the native Strata installation first."
+    const job = await finish(f.native, started.id);
+    assert.equal(job.state, 'done', job.error);
+  } finally { await f.native.close(); f.cleanup(); }
+});
+
+test('packaged: a chosen engine file goes to Control; only a file in the own incoming folder is deleted afterwards', async () => {
+  const f = fixture();
+  try {
+    const incoming = join(f.data, 'incoming-engine');
+    mkdirSync(incoming, { recursive: true });
+    const mine = join(incoming, 'strata-engine-x.tar.gz'), theirs = join(f.data, 'keep-me.tar.gz');
+    writeFileSync(mine, 'x'); writeFileSync(theirs, 'y');
+    const job = await finish(f.native, f.native.operation('install-engine-file', { path: mine }).id);
+    assert.equal(job.state, 'done', job.error);
+    assert.deepEqual(f.calls.at(-1), ['install-file', mine]);
+    assert.equal(existsSync(mine), false, 'the copy the page uploaded is removed');
+    const other = await finish(f.native, f.native.operation('install-engine-file', { path: theirs }).id);
+    assert.equal(other.state, 'done', other.error);
+    assert.equal(existsSync(theirs), true, 'a file anywhere else is never deleted');
+    const none = await finish(f.native, f.native.operation('install-engine-file', {}).id);
+    assert.equal(none.state, 'error');
+    assert.equal(f.calls.filter(c => c[0] === 'install-file').length, 2, 'no file, no install');
+  } finally { await f.native.close(); f.cleanup(); }
+});
+
+test('first-run card data: an offer with its size, nothing-fits with reasons, offline, and an engine already there', async () => {
+  const gpus = [{ name: 'NVIDIA GeForce RTX 5070', vramGb: 12 }];
+  const report = engine => ({ ok: true, hardware: { nvidia_driver: '581.15', backend: 'cuda' }, engine });
+  const offer = await engineFirstRun({ control: { updateCheck: async () => report({ status: 'install', installed: null, offered: { version: '0.1.48', variant: 'cuda13', backend: 'cuda' }, download_bytes: 581299508 }) }, gpus });
+  assert.deepEqual([offer.status, offer.offer.bytes, offer.driver, offer.gpus[0].name], ['offer', 581299508, '581.15', 'NVIDIA GeForce RTX 5070']);
+  const none = await engineFirstRun({ control: { updateCheck: async () => report({ status: 'none-for-this-pc', installed: null, offered: null, reasons: ['needs NVIDIA driver 580.65 or newer, this PC has 560.1'] }) }, gpus });
+  assert.equal(none.status, 'none');
+  assert.match(none.reasons[0], /driver 580/);
+  const installed = await engineFirstRun({ control: { updateCheck: async () => report({ status: 'current', installed: { version: '0.1.48' }, offered: null }) }, gpus });
+  assert.equal(installed.status, 'installed');
+  const offline = await engineFirstRun({ control: { updateCheck: async () => { throw new Error('the update feed could not be read: could not read https://github.com/x (URLError: [WinError 10060] timed out)'); } }, gpus });
+  assert.equal(offline.status, 'offline');
+});
+
 test('without the shell bridge "Update Strata" still updates Control and says nothing false about the app', async () => {
   const f = fixture();
   try {

apps/host/tests/deepseek-speed.test.mjs

@@ -0,0 +1,38 @@
+/** The Speed label names the default the way the engine decides it: integrated / unified-memory GPU, or cards totalling 16 GiB or less. */
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { build } from 'esbuild';
+import { fileURLToPath } from 'node:url';
+
+const out = await build({ entryPoints: [fileURLToPath(new URL('../src/lib/deepseek-speed.ts', import.meta.url))], bundle: true, format: 'esm', platform: 'node', write: false, logLevel: 'silent' });
+const { fasterByDefault, speedOptions } = await import(`data:text/javascript;base64,${Buffer.from(out.outputFiles[0].text).toString('base64')}`);
+const card = (vram_gb, extra = {}) => ({ index: 0, name: 'GPU', vram_gb, ...extra });
+
+test('Strix Halo (an integrated / unified-memory GPU) defaults to Faster, whatever its memory figure says', () => {
+  assert.equal(fasterByDefault([card(96, { uma: true })]), true, 'a 96 GB share is not "16 GiB or less", the integrated rule applies');
+  assert.equal(fasterByDefault([card(0, { unified_gb: 128 })]), true);
+  assert.equal(fasterByDefault([card(64, { integrated: true })]), true);
+  assert.equal(fasterByDefault([card(24), card(96, { uma: true })]), true, 'an integrated card among the cards in use');
+});
+
+test('discrete cards: Faster at 16 GiB or less in total, Full quality above', () => {
+  assert.equal(fasterByDefault([card(11.9)]), true, 'RTX 5070 / 3060 12 GB');
+  assert.equal(fasterByDefault([card(15.99)]), true, 'a 16 GB card reports 16376 MiB');
+  assert.equal(fasterByDefault([card(16)]), true);
+  assert.equal(fasterByDefault([card(8), card(8)]), true, 'two 8 GB cards total 16');
+  assert.equal(fasterByDefault([card(16.05)]), false);
+  assert.equal(fasterByDefault([card(24)]), false);
+  assert.equal(fasterByDefault([card(8), card(12)]), false);
+  assert.equal(fasterByDefault([card(24, { usable: false }), card(12)]), true, 'a card the engine cannot use does not count');
+  assert.equal(fasterByDefault([]), false);
+  assert.equal(fasterByDefault(null), false);
+});
+
+test('the labels say "(default on this PC)" beside the choice that is the default, once', () => {
+  const faster = speedOptions([card(12)]).map(o => o.label);
+  assert.deepEqual(faster, ['Default (Faster on this PC)', 'Faster (default on this PC)', 'Full quality']);
+  const full = speedOptions([card(24)]).map(o => o.label);
+  assert.deepEqual(full, ['Default (Full quality on this PC)', 'Faster', 'Full quality (default on this PC)']);
+  const strix = speedOptions([card(96, { uma: true })]).map(o => o.label);
+  assert.deepEqual(strix, ['Default (Faster on this PC)', 'Faster (default on this PC)', 'Full quality']);
+});

apps/host/tests/draft-layer.test.mjs

@@ -3,6 +3,7 @@
  * Setup writes --mtp, --spec-min-p and --vision into the arguments every time it runs; the host applies the saved choices on every
  * load. Nothing here starts an engine; Control is a fake that records what the host saved and asked it to start.
  */
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { mkdtempSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';
@@ -45,7 +46,7 @@ test('withoutDraftLayer takes out --mtp, --spec-min-p and --batch-mtp and keeps
 
 test('"Draft layer (MTP)" is a setting of the app, not frozen, and "MTP per request" is not frozen either', async () => {
   assert.ok(NATIVE_FIELDS.some(f => f.id === 'mtp' && f.type === 'boolean'));
-  assert.deepEqual(APP_OWNED_FIELDS.sort(), ['batchMtp', 'drafting', 'mtp']);
+  assert.deepEqual(APP_OWNED_FIELDS.sort(), ['batchMtp', 'drafting', 'ds_experts', 'mtp']);
   const f = fixture();
   try {
     await f.native.refresh(true);

apps/host/tests/folder-dialog.test.mjs

@@ -170,5 +170,9 @@ test('Windows: a PowerShell that is missing or fails is reported as before', asy
   f.child.emit('error', Object.assign(new Error('x'), { code: 'ENOENT' }));
   await assert.rejects(missing, e => e.code === 'ENOENT');
   const g = fakeShell(); const failed = watchedWindowsDialog('powershell.exe', [], { spawnProcess: g.spawnProcess });
-  g.child.emit('close', 1); await assert.rejects(failed, e => e.code === 1);
+  g.child.emit('close', 1);
+  // Ended by security software before any window opened (#3831): the app asks for the path instead of an error.
+  assert.deepEqual(await failed, { noDialog: true });
+  const h = fakeShell(); const late = watchedWindowsDialog('powershell.exe', [], { spawnProcess: h.spawnProcess });
+  h.child.stdout.emit('data', 'READY\n'); h.child.emit('close', 1); await assert.rejects(late, e => e.code === 1);
 });

apps/host/tests/helpers/isolate-profile.mjs

@@ -0,0 +1,19 @@
+/**
+ * Import this FIRST in a test that builds the host's native control or starts the host: it points the per-user places the host writes to
+ * (the settings file Control reads, the components folder, the app's local data) at a scratch folder.
+ * On 2026-10-24 a host test run rewrote the owner's real %LOCALAPPDATA%\Strata\app-settings.json (its data_dir became a deleted test folder).
+ */
+import { mkdtempSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+
+if (!process.env.STRATA_TEST_KEEP_PROFILE) {
+  const scratch = mkdtempSync(join(tmpdir(), 'strata-host-test-profile-'));
+  process.env.STRATA_SETTINGS_FILE = join(scratch, 'app-settings.json');
+  process.env.STRATA_COMPONENTS_DIR = join(scratch, 'components');
+  process.env.LOCALAPPDATA = join(scratch, 'Local');
+  process.env.APPDATA = join(scratch, 'Roaming');
+  process.env.XDG_DATA_HOME = join(scratch, 'xdg-data');
+  process.env.XDG_STATE_HOME = join(scratch, 'xdg-state');
+  process.env.XDG_CONFIG_HOME = join(scratch, 'xdg-config');
+}

apps/host/tests/locale-gaps.test.mjs

@@ -0,0 +1,65 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import ts from 'typescript';
+import { readdir, readFile } from 'node:fs/promises';
+import { join } from 'node:path';
+import { build } from 'esbuild';
+
+const languages = ['en', 'zh', 'ja', 'de', 'es', 'ru', 'pt', 'ko'];
+const read = async name => JSON.parse(await readFile(`src/locales/${name}.json`, 'utf8'));
+const built = await build({ stdin: { contents: "export * from './src/lib/i18n';", resolveDir: process.cwd() }, bundle: true, write: false, format: 'esm', platform: 'node', loader: { '.json': 'json' } });
+const { tr, setTranslationLanguage } = await import(`data:text/javascript;base64,${Buffer.from(built.outputFiles[0].text).toString('base64')}`);
+
+test('every tr("...") literal and every command hint has a key in the English catalog, so no language is stuck in English (#3479)', async () => {
+  const known = new Set();
+  for (const name of ['en', 'tune-en', 'tools-en', 'fix-en']) for (const v of Object.values(await read(name))) known.add(String(v));
+  const missing = [];
+  const scan = async dir => {
+    for (const entry of await readdir(dir, { withFileTypes: true })) {
+      const path = join(dir, entry.name);
+      if (entry.isDirectory()) { if (entry.name !== 'locales') await scan(path); continue; }
+      if (!/\.tsx?$/.test(path)) continue;
+      const source = await readFile(path, 'utf8'), sf = ts.createSourceFile(path, source, ts.ScriptTarget.Latest, true, path.endsWith('.tsx') ? ts.ScriptKind.TSX : ts.ScriptKind.TS);
+      const visit = node => {
+        if (ts.isCallExpression(node) && node.expression.getText(sf) === 'tr' && node.arguments[0] && (ts.isStringLiteral(node.arguments[0]) || ts.isNoSubstitutionTemplateLiteral(node.arguments[0]))) {
+          const text = node.arguments[0].text.trim();
+          if (text && /[a-zA-Z]{2}/.test(text) && !known.has(text)) missing.push(`${path}: ${text}`);
+        }
+        if (ts.isPropertyAssignment(node) && node.name.getText(sf) === 'hint' && ts.isStringLiteral(node.initializer) && !path.endsWith('chat-showcase.ts')) {
+          const text = node.initializer.text.trim();
+          if (text && !known.has(text)) missing.push(`${path}: hint ${text}`);
+        }
+        ts.forEachChild(node, visit);
+      };
+      visit(sf);
+    }
+  };
+  await scan('src');
+  assert.deepEqual(missing, []);
+});
+
+test('the fix catalogs have the same keys and placeholders in all eight languages', async () => {
+  const en = await read('fix-en');
+  for (const language of languages) {
+    const catalog = await read(`fix-${language}`);
+    assert.deepEqual(Object.keys(catalog), Object.keys(en), language);
+    for (const [id, text] of Object.entries(catalog)) assert.deepEqual((text.match(/\{\d+\}/g) ?? []).sort(), (en[id].match(/\{\d+\}/g) ?? []).sort(), `${language} ${id}`);
+  }
+});
+
+test('the /plan, /research and /new hints and the four "Open ..." hints are translated (#3479, #3825)', () => {
+  for (const language of ['zh', 'ru']) {
+    setTranslationLanguage(language);
+    for (const hint of ['Have the assistant write a plan first; nothing runs until you approve it', 'Search the web, read the pages and answer with sources', 'Start a new conversation; keep this one'])
+      assert.notEqual(tr(hint), hint, `${language}: ${hint}`);
+    for (const label of ['Model settings', 'Serving', 'Models', 'Skills']) {
+      const hint = tr(`Open ${label}`);
+      assert.notEqual(hint, `Open ${label}`, `${language}: ${label} template`);
+      assert.ok(!hint.includes(label), `${language}: the label is translated too: ${hint}`);
+    }
+  }
+  setTranslationLanguage('zh');
+  assert.equal(tr('Open Skills'), '打开 技能');
+  setTranslationLanguage('en');
+  assert.equal(tr('Open Skills'), 'Open Skills');
+});

apps/host/tests/markdown-soft-breaks.test.mjs

@@ -0,0 +1,34 @@
+// #3818: a single newline inside a paragraph is a space; a blank line starts a new paragraph; two trailing spaces or a backslash is a line break.
+import assert from 'node:assert/strict';
+import test from 'node:test';
+import { resolve } from 'node:path';
+import { createRequire } from 'node:module';
+import { build } from 'esbuild';
+
+const root = resolve(import.meta.dirname, '..');
+const bundle = await build({
+  stdin: { contents: `import React from 'react'; import { renderToStaticMarkup } from 'react-dom/server'; import { Markdown } from './src/components/Markdown.tsx'; export const html = text => renderToStaticMarkup(React.createElement(Markdown, { text }));`, resolveDir: root, loader: 'ts' },
+  bundle: true, write: false, platform: 'node', format: 'cjs', jsx: 'automatic', external: ['katex', 'katex/dist/katex.min.css'],
+  plugins: [{ name: 'stub', setup(b) {
+    b.onResolve({ filter: /^\.\/ui$/ }, () => ({ path: 'ui', namespace: 'test-stub' }));
+    b.onLoad({ filter: /.*/, namespace: 'test-stub' }, () => ({ contents: 'export const IconBtn = () => null; export const Btn = () => null;' }));
+  } }],
+});
+const mod = { exports: {} };
+new Function('require', 'module', 'exports', bundle.outputFiles[0].text)(createRequire(import.meta.url), mod, mod.exports);
+const { html } = mod.exports;
+const paragraphs = out => (out.match(/<p>/g) ?? []).length;
+
+test('a single newline is a soft break, a blank line a new paragraph', () => {
+  const soft = html('Line one\nLine two');
+  assert.equal(paragraphs(soft), 1); assert.match(soft, /Line one Line two/);
+  assert.equal(paragraphs(html('One\n\nTwo')), 2);
+});
+test('two trailing spaces or a backslash keep a line break', () => {
+  assert.match(html('One  \nTwo'), /One<br\/>Two/);
+  assert.match(html('One' + String.fromCharCode(92) + String.fromCharCode(10) + 'Two'), /One<br\/>Two/);
+});
+test('a list, heading or code block right after a line still starts its own block', () => {
+  const out = html('Intro\n- a\n- b\n## Head\ntext\n```\ncode\n```');
+  assert.match(out, /<p>Intro<\/p><ul>/); assert.match(out, /<h2>Head<\/h2><p>text<\/p>/);
+});

apps/host/tests/model-picker.test.mjs

@@ -4,7 +4,7 @@ import { readFile } from 'node:fs/promises';
 import { transform } from 'esbuild';
 
 const { code } = await transform(await readFile(new URL('../src/lib/model-picker.ts', import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' });
-const { pickerGroups } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
+const { pickerGroups, pickerNativeModels } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
 const version = (id, family, state, diskGb, extra = {}) => ({ id, family, state, diskGb, ...extra });
 
 test('chat picker groups every downloaded family and puts its running version first', () => {
@@ -35,3 +35,10 @@ test('downloaded files stay visible during load transitions and recoverable fail
   assert.deepEqual(pickerGroups(library)[0].versions.map(v => v.id), ['loading', 'unloading', 'failed-load']);
   assert.deepEqual(pickerGroups({ loaded: null, variants: [library.variants[0]] }), []);
 });
+
+test('downloaded optimized models that are not loaded still appear in the chat picker (#3814)', () => {
+  const installed = [{ model: 'swift', model_name: 'Swift IQ3_XXS', ready: true }, { model: 'half', model_name: 'Half', ready: false }, { model: 'run', model_name: 'Running one', ready: true }];
+  const out = pickerNativeModels(installed, [{ label: 'Running one' }]);
+  assert.deepEqual(out.map(m => m.model), ['swift']);
+  assert.deepEqual(pickerNativeModels(undefined, null), []);
+});

apps/host/tests/models-folder.test.mjs

@@ -1,3 +1,4 @@
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { EventEmitter } from 'node:events';

apps/host/tests/monitor-dashboard.test.mjs

@@ -4,7 +4,7 @@ import { parseCpuTopology, parseNvidiaReadings, parsePcieThroughput, gpuMemoryTo
 import { cpuUtilization, diskRate, parseLinuxDiskCounters, parseMacDiskCounters } from '../server/system-telemetry.mjs';
 import { parseEngineMetrics } from '../server/supervisor.mjs';
 import { originalDashboard } from '../server/monitor-dashboard.mjs';
-import { gpuMetric, gpuCapacity } from '../src/lib/monitor-hardware.ts';
+import { gpuMetric, gpuCapacity, gpuReported, shortGpuName } from '../src/lib/monitor-hardware.ts';
 import { referencePaths } from '../src/lib/monitor-chart.ts';
 
 const gpu=(id,index=0,unified=false)=>({id,index,unified,vramGb:24,name:id,vendor:'nvidia',backend:'cuda'});
@@ -92,3 +92,15 @@ test('original requests, cache, progress, hardware and MCP facts are translated
   assert.equal(mapped.generation.total,600);assert.equal(mapped.history[0].gpuTempC,null);
   assert.equal(mapped.mcp.servers[0].state,'ready');assert.equal(mapped.mcp.servers[0].tools[0].name,'read_file');
 });
+
+test('All GPUs: a card with no temperature sensor is left out and the card that reports is named (#3727 follow-up)',()=>{
+  const devices=[{...gpu('nv',0),name:'NVIDIA GeForce RTX 5070'},{...gpu('igpu',1),name:'AMD Radeon(TM) Graphics',vramGb:0.4}];
+  const readings=[reading('nv',3,0.8,34,7),reading('igpu',0,0.001,null,null)];
+  const temp=gpuReported(devices,readings,'temperatureC','max');
+  assert.equal(temp.value,34); assert.equal(temp.partial,true); assert.deepEqual(temp.devices.map(d=>shortGpuName(d.name)),['RTX 5070']);
+  const load=gpuReported(devices,readings,'utilizationPct','mean');
+  assert.equal(load.partial,false); assert.equal(load.value,1.5);
+  assert.equal(gpuReported(devices,[reading('nv',3,0.8,null,null),reading('igpu',0,0,null,null)],'temperatureC','max').value,null,'no card reports: still unavailable');
+  assert.equal(shortGpuName('AMD Radeon RX 9070 XT'),'RX 9070 XT');
+  assert.equal(shortGpuName('Intel(R) Arc(TM) A750 Graphics'),'A750 Graphics');
+});

apps/host/tests/native-fit.test.mjs

@@ -5,7 +5,7 @@ import { readFile } from 'node:fs/promises';
 import { transform } from 'esbuild';
 
 const { code } = await transform(await readFile(new URL('../src/lib/native-fit.ts', import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' });
-const { fitOn, memoryNeeded, RECOMMENDED, VERSION_GROUPS, groupOpen, recommendedVersions, PICK_NOTE, OTHER_NOTE, MTP_VRAM_GB } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
+const { fitOn, cacheGb, memoryNeeded, RECOMMENDED, VERSION_GROUPS, groupOpen, recommendedVersions, PICK_NOTE, OTHER_NOTE, MTP_VRAM_GB } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
 
 const swift = { ram_needed_gb: 48, experts_gb: 35.5 };
 const gyroS = { ram_needed_gb: 27.6, experts_gb: 25.8, mem_total: true };
@@ -83,3 +83,15 @@ test('the tiers of the engine are 40 GB Swift IQ2_XS, 48 GB IQ3_XXS, 64 GB IQ3_S
     assert.deepEqual([...m[1].matchAll(/\(([\d.]+),\s*"(\w+)",\s*"(\w+)"\)/g)].map(x => [Number(x[1]), x[2], x[3]]), [[62, 'qwen', 'IQ3_S'], [46, 'qwen', 'IQ3_XXS'], [38, 'swift', 'IQ2_XS']], file);
   }
 });
+
+test('the conversation context and cache format move the estimate (#3832)', () => {
+  const pc = { ram_gb: 64, vram_gb: 16 };
+  const base = fitOn(swift, pc);
+  assert.deepEqual(fitOn(swift, pc, true, { context: 32768, kv: 'int8' }), base, 'the default context is what the fixed figure already held');
+  const big = fitOn(swift, pc, true, { context: 524288, kv: 'int8' });
+  assert.ok(big.vramUseGb >= base.vramUseGb && big.ramUseGb > base.ramUseGb, 'a bigger cache takes graphics memory from the experts, which then sit in RAM');
+  assert.ok(fitOn(swift, pc, true, { context: 524288, kv: 'q4_0' }).ramUseGb < big.ramUseGb, 'a smaller cache format leaves more room');
+  assert.ok(Math.abs(cacheGb(524288, 'int8') * 1024 - 7361) < 25, 'the 512K Int8 cache is the 7361 MiB the engine reports');
+  const tight = fitOn(q4, pc, true, { context: 524288, kv: 'int8' });
+  assert.ok(tight.spillGb > fitOn(q4, pc).spillGb, 'what no longer fits is read from the SSD and the card says so');
+});

apps/host/tests/native-settled.test.mjs

@@ -0,0 +1,21 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { build } from 'esbuild';
+
+const compiled = await build({ stdin: { contents: "export * from './src/lib/native';", resolveDir: process.cwd() }, bundle: true, write: false, platform: 'node', format: 'esm' });
+const lib = await import(`data:text/javascript;base64,${Buffer.from(compiled.outputFiles[0].text).toString('base64')}`);
+
+test('the Models page waits for the first native answer before it picks a model (#3740)', async () => {
+  let release;
+  globalThis.fetch = () => new Promise(resolve => { release = () => resolve({ ok: true, status: 200, statusText: 'OK', text: async () => JSON.stringify({ available: true, jobs: [], instances: [] }) }); });
+  let heard = 0;
+  const off = lib.subscribeNative(() => { heard++; });
+  assert.equal(lib.nativeSettled(), false, 'nothing read yet: show a placeholder, not the Starter');
+  const reading = lib.refreshNative();
+  assert.equal(lib.nativeSettled(), false);
+  release();
+  await reading;
+  assert.equal(lib.nativeSettled(), true);
+  assert.ok(heard >= 1, 'the page is told');
+  off();
+});

apps/host/tests/no-acquire.test.mjs

@@ -1,3 +1,4 @@
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { spawn } from 'node:child_process';

apps/host/tests/packaged-control.test.mjs

@@ -1,3 +1,4 @@
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { EventEmitter } from 'node:events';
@@ -85,13 +86,13 @@ test('runCli passes the arguments untouched (no shell) and reads JSON', async ()
 
 // ---------------------------------------------------------------------------------- native-control in packaged mode
 
-function packagedFixture({ engineUsable = true, updater = null, repair = false } = {}) {
+function packagedFixture({ engineUsable = true, updater = null, repair = false, ids = ['iq2_xs', 'iq3_s'] } = {}) {
   const root = mkdtempSync(join(tmpdir(), 'strata-packaged-test-'));
   const install = join(root, 'install'), data = join(root, 'data');
   mkdirSync(install, { recursive: true });
   const earlierInstallEnv = process.env.STRATA_INSTALL_DIR;
   process.env.STRATA_INSTALL_DIR = install;      // the app's own install folder (the host always tells Control which one; it never falls back to an older CLI folder)
-  const configs = ['iq2_xs', 'iq3_s'].map(id => {
+  const configs = ids.map(id => {
     const path = join(install, `strata-${id}.json`);
     writeFileSync(path, JSON.stringify({ exe: 'component:strata-engine', tokenizer: join(install, 'tok'), args: ['--max-context', '32768'], model_name: `Qwen ${id}`, port: 8080 }));
     return { id, path };
@@ -201,6 +202,59 @@ test('packaged: load = saved profile + runtime start under Control; unload = run
   } finally { await f.native.close(); f.cleanup(); }
 });
 
+test('packaged: a model id with dots (DeepSeek) is listed, loaded from its run config, and unloaded', async () => {
+  const id = 'deepseek-v4.1-flash-ist-das-2.00bpw';
+  const f = packagedFixture({ ids: [id] });
+  try {
+    writeFileSync(join(f.install, `strata-${id}.json`), JSON.stringify({ exe: join(f.install, 'engine-dsv41', 'strata-dsv41'), arch: 'deepseek41', tokenizer: join(f.install, 'tok'), args: ['--pack', join(f.install, 'pack'), '--max-context', '8192', '--eos', '1'], model_name: 'deepseek-v4.1-flash', port: 8080, engine_ready_s: 3600 }));
+    const state = await f.native.refresh(true);
+    assert.deepEqual(state.installed.models.map(m => m.model), [id], 'listed (the install finished but the app used to show nothing)');
+    assert.equal(state.installed.models[0].ready, true);
+    const job = await finish(f.native, f.native.operation('load', { model: id }).id);
+    assert.equal(job.state, 'done', job.error);                    // used to end with "The model configuration is outside the Strata installation."
+    assert.deepEqual(f.calls.filter(c => ['saveProfile', 'start'].includes(c[0])).map(c => c.slice(0, 2)), [['saveProfile', 'app-1'], ['start', 'app-1']]);
+    const flags = f.saved[0].args.filter(a => a.startsWith('--'));
+    assert.deepEqual(flags, ['--pack', '--max-context', '--eos'], 'The own engine of DeepSeek gets none of the Flash-Next options (it ended with "unknown option --batch")');
+    assert.equal(f.calls.find(c => c[0] === 'start')[2], 600, 'it waits longer than the usual 300 s, up to the 600 s Control allows');
+    const instance = f.native.state().instances[0];
+    assert.equal(instance.model, id);
+    assert.equal(instance.status, 'ready');
+    await f.native.unload(instance.id);
+    assert.deepEqual(f.calls.filter(c => c[0] === 'stop').at(-1), ['stop', 'app-1']);
+    assert.equal(f.native.state().instances.length, 0);
+    for (const odd of ['a..b', '../x', 'x/y', '.hidden']) assert.equal((await finish(f.native, f.native.operation('load', { model: odd }).id)).state, 'error', odd);
+  } finally { await f.native.close(); f.cleanup(); }
+});
+
+test('packaged: the Speed choice of DeepSeek passes --experts 5 or 6 only when chosen and only for an engine that knows it (0.1.50 or newer)', async () => {
+  const id = 'deepseek-v4.1-flash-ist-das-2.00bpw';
+  const run = async (values, extraArgs = [], engine = '0.1.50-windows-x86_64-cuda-cuda13') => {
+    const f = packagedFixture({ ids: [id] });
+    try {
+      writeFileSync(join(f.install, `strata-${id}.json`), JSON.stringify({ exe: join(f.install, 'engine-dsv41', engine, 'strata-dsv41'), arch: 'deepseek41', tokenizer: join(f.install, 'tok'), args: ['--pack', join(f.install, 'pack'), '--max-context', '8192', ...extraArgs], model_name: 'deepseek-v4.1-flash', port: 8080 }));
+      await f.native.refresh(true);
+      const capability = f.native.settings(id).capabilities.dsExperts;
+      const job = await finish(f.native, f.native.operation('load', { model: id, ...(values ? { values } : {}) }).id);
+      assert.equal(job.state, 'done', job.error);
+      return { cfg: f.saved[0], capability };
+    } finally { await f.native.close(); f.cleanup(); }
+  };
+  const flag = cfg => { const i = cfg.args.indexOf('--experts'); return i < 0 ? null : cfg.args[i + 1]; };
+  const none = await run(null);
+  assert.equal(flag(none.cfg), null, 'nothing chosen: the engine decides (--experts auto)');
+  assert.equal(none.capability, true);
+  assert.equal(flag((await run({ ds_experts: '5' })).cfg), '5');
+  assert.equal(flag((await run({ ds_experts: '6' }, ['--experts', '5'])).cfg), '6', 'the choice replaces an older flag');
+  assert.equal(flag((await run({ ds_experts: null }, ['--experts', '5'])).cfg), null, 'Default clears an older flag');
+  assert.equal('ds_experts' in (await run({ ds_experts: '5' })).cfg, false, 'the app-only key is not handed to the engine');
+  assert.equal(flag((await run({ ds_experts: '5' }, [], '0.1.60-windows-x86_64-cuda-cuda13')).cfg), '5', 'a newer engine knows it');
+  for (const old of ['0.1.49.2-windows-x86_64-cuda-cuda13', '0.1.49-linux-x86_64-cuda-cuda13']) {
+    const r = await run({ ds_experts: '5' }, [], old);
+    assert.equal(r.capability, false, `${old}: the choice is hidden`);
+    assert.equal(flag(r.cfg), null, `${old}: nothing is passed (it would end the start with "unknown option --experts")`);
+  }
+});
+
 test('packaged: no engine for this PC is the notice, and nothing is started', async () => {
   const f = packagedFixture({ engineUsable: false });
   try {

apps/host/tests/parallel-default.test.mjs

@@ -3,6 +3,7 @@
  * retry with one when a load with several slots fails. Nothing here starts an engine; Control is a fake that records what
  * the host saved and asked it to start.
  */
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { mkdtempSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';

apps/host/tests/plain-errors.test.mjs

@@ -102,3 +102,8 @@ test('missing model files are named, in every language, with a next step (#3478)
   setTranslationLanguage('en');
   assert.equal(plainFailure(missingFilesError('m', []).message).kind, 'plain', 'with no names the old sentence is left as it was');
 });
+
+test('the engine component is named in words, once (#3900)', async () => {
+  const { missingNames } = await import('../server/missing-files.mjs');
+  assert.deepEqual(missingNames([{ part: 'engine', file: 'component:strata-engine' }], ['component:strata-engine']), ['the engine program']);
+});

apps/host/tests/qa1-storage.test.mjs

@@ -57,5 +57,5 @@ test('Cargo.toml, tauri.conf.json and the desktop package agree on the app versi
   const cargo = /^version\s*=\s*"([^"]+)"/m.exec(await readFile(new URL('src-tauri/Cargo.toml', root), 'utf8'))[1];
   const pkg = JSON.parse(await readFile(new URL('package.json', root), 'utf8')).version;
   assert.equal(cargo, pkg);
-  assert.equal(cargo, '0.2.3');
+  assert.equal(cargo, '0.2.5');
 });

apps/host/tests/session-workspace.test.mjs

@@ -0,0 +1,17 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { readFile } from 'node:fs/promises';
+import { transform } from 'esbuild';
+
+const { code } = await transform(await readFile(new URL('../src/lib/session-workspace.ts', import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' });
+const { workspaceIdForSession } = await import(`data:text/javascript;base64,${Buffer.from(code).toString('base64')}`);
+const workspaces = [{ id: 'a', name: 'A', path: 'C:\A', aliases: ['C:\old'] }, { id: 'b', name: 'B', path: 'D:\Project' }];
+
+test('a chat finds the workspace it was made in, by path or by an earlier folder (#3754)', () => {
+  assert.equal(workspaceIdForSession(workspaces, { workspace: 'D:\Project' }), 'b');
+  assert.equal(workspaceIdForSession(workspaces, { workspace: 'C:\old' }), 'a');
+});
+test('a chat with an unknown or no workspace changes nothing', () => {
+  assert.equal(workspaceIdForSession(workspaces, { workspace: 'E:\gone' }), null);
+  assert.equal(workspaceIdForSession(workspaces, undefined), null);
+});

apps/host/tests/size-label.test.mjs

@@ -0,0 +1,17 @@
+/** The first-run card and the update check show decimal megabytes, the same figure as the Terminal and the release page. */
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { build } from 'esbuild';
+import { fileURLToPath } from 'node:url';
+
+const out = await build({ entryPoints: [fileURLToPath(new URL('../src/lib/format.ts', import.meta.url))], bundle: true, format: 'esm', platform: 'node', write: false, logLevel: 'silent' });
+const { megabytes } = await import(`data:text/javascript;base64,${Buffer.from(out.outputFiles[0].text).toString('base64')}`);
+
+test('engine sizes are decimal megabytes: 606,513,890 bytes is 607 MB, not 578', () => {
+  assert.equal(megabytes(606513890), 607);
+  assert.equal(megabytes(581299508), 581);
+  assert.equal(megabytes(1), 1);
+  assert.equal(megabytes(0), 1);
+  // the same samples as tests/terminal/test_size_label.py: the Terminal and the app agree
+  for (const [bytes, expected] of [[606513890, 607], [581299508, 581], [1, 1], [0, 1], [999_999, 1], [1_500_000, 2], [2_499_999, 2]]) assert.equal(megabytes(bytes), expected, String(bytes));
+});

apps/host/tests/typed-and-pasted.test.mjs

@@ -0,0 +1,24 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { readFile } from 'node:fs/promises';
+import { transform } from 'esbuild';
+
+const load = async name => import(`data:text/javascript;base64,${Buffer.from((await transform(await readFile(new URL(`../src/lib/${name}.ts`, import.meta.url), 'utf8'), { loader: 'ts', format: 'esm' })).code).toString('base64')}`);
+const { parseDecimal, partialDecimal } = await load('decimal');
+const { pastedFiles } = await load('pasted-files');
+
+test('a decimal point can be typed step by step (#3736)', () => {
+  for (const step of ['', '.', '0', '0.', '0.9', '0.95']) assert.equal(partialDecimal(step), true, step);
+  assert.equal(parseDecimal('.'), null); assert.equal(parseDecimal('0.'), null);
+  assert.equal(parseDecimal('0.95'), 0.95); assert.equal(parseDecimal('.95'), 0.95); assert.equal(parseDecimal('0,95'), 0.95); assert.equal(parseDecimal('20'), 20);
+  assert.equal(partialDecimal('0.9x'), false); assert.equal(parseDecimal('1e3'), null);
+});
+
+test('a screenshot that is only in clipboard items is attached (#3748)', () => {
+  const png = new File(['x'], 'image.png', { type: 'image/png' });
+  const data = { files: [], items: [{ kind: 'file', type: 'image/png', getAsFile: () => png }, { kind: 'string', type: 'text/plain', getAsFile: () => null }] };
+  const out = pastedFiles(data);
+  assert.equal(out.length, 1); assert.equal(out[0].type, 'image/png'); assert.match(out[0].name, /^Pasted picture .*\.png$/);
+  assert.equal(pastedFiles({ files: [png], items: [{ kind: 'file', type: 'image/png', getAsFile: () => png }] }).length, 1, 'never twice');
+  assert.deepEqual(pastedFiles({ files: [], items: [{ kind: 'string', type: 'text/plain', getAsFile: () => null }] }), []);
+});

apps/host/tests/user-args.test.mjs

@@ -3,6 +3,7 @@
  * apps", and engine arguments the app does not know (the control vector options). Nothing here starts an engine; Control is a fake that
  * records the run file the host saved and asked it to start.
  */
+import './helpers/isolate-profile.mjs';   // a test run never writes the owner's real Strata profile
 import test from 'node:test';
 import assert from 'node:assert/strict';
 import { mkdtempSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs';

apps/host/tests/windows-disk-reader.test.mjs

@@ -0,0 +1,43 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { EventEmitter } from 'node:events';
+import { parseWindowsDiskLine, createWindowsDiskReader, diskRate } from '../server/system-telemetry.mjs';
+
+function fakeSpawn(log) {
+  return (cmd, args) => {
+    const proc = new EventEmitter();
+    proc.stdout = new EventEmitter();
+    proc.stdout.unref = () => {};
+    proc.unref = () => {};
+    proc.kill = () => { proc.killed = true; };
+    log.push({ cmd, args, proc });
+    return proc;
+  };
+}
+
+test('one PowerShell is started and reused for every sample (#3939)', () => {
+  const log = [];
+  const reader = createWindowsDiskReader({ spawnFn: fakeSpawn(log), now: () => 1000 });
+  assert.equal(reader.read(), null, 'nothing before the first line');
+  reader.read(); reader.read();
+  assert.equal(log.length, 1);
+  log[0].proc.stdout.emit('data', '1000 2');
+  log[0].proc.stdout.emit('data', '000\n');
+  assert.deepEqual(reader.read(), { read: 1000, write: 2000, at: 1000 });
+  assert.equal(log.length, 1);
+});
+
+test('after repeated early exits it stops starting processes', () => {
+  const log = [];
+  const reader = createWindowsDiskReader({ spawnFn: fakeSpawn(log), maxStarts: 3 });
+  for (let i = 0; i < 6; i++) { reader.read(); log.at(-1).proc.emit('exit'); }
+  assert.equal(log.length, 3);
+  assert.equal(reader.read(), null);
+});
+
+test('garbage lines are ignored and a repeated reading gives no new rate', () => {
+  assert.equal(parseWindowsDiskLine('Name : x'), null);
+  assert.deepEqual(parseWindowsDiskLine('12 34\r'), { read: 12, write: 34 });
+  const prev = { time: 0, counters: { read: 0, write: 0, at: 1000 } };
+  assert.deepEqual(diskRate(prev, { read: 1048576, write: 0, at: 2000 }, 5000), { readMbs: 1, writeMbs: 0 });
+});

apps/host/tests/windows-gpu.test.mjs

@@ -0,0 +1,47 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { EventEmitter } from 'node:events';
+import { luidName, parseDxAdapters, windowsOtherGpus, parseGpuCounterLine, createWindowsGpuReader } from '../server/windows-gpu.mjs';
+
+const dxRaw = JSON.stringify([
+  { Description: 'AMD Radeon RX 9070 XT', VendorId: '4098', Luid: '90370', Dedicated: '17094934528', Software: '0' },
+  { Description: 'Microsoft Basic Render Driver', VendorId: '5140', Luid: '1', Dedicated: '0', Software: '1' },
+]);
+
+test('the LUID is spelled as the performance counters spell it', () => {
+  assert.equal(luidName('90370'), 'luid_0x00000000_0x00016102');
+  assert.equal(luidName(String(0x12n * 2n ** 32n + 5n)), 'luid_0x00000012_0x00000005');
+  assert.equal(luidName('nope'), null);
+});
+
+test('an AMD card on Windows gets its real memory size and a LUID, virtual monitors are not cards (#3727, #3836)', () => {
+  const dx = parseDxAdapters(dxRaw);
+  const cards = windowsOtherGpus([
+    { Name: 'AMD Radeon RX 9070 XT', PNPDeviceID: 'PCI-A' },
+    { Name: 'Meta Virtual Monitor', PNPDeviceID: 'ROOT-1' },
+    { Name: 'Virtual Desktop Monitor', PNPDeviceID: 'ROOT-2' },
+  ], dx);
+  assert.equal(cards.length, 1);
+  assert.equal(cards[0].vendor, 'amd');
+  assert.equal(cards[0].vramGb, 15.9);
+  assert.equal(cards[0].luid, 'luid_0x00000000_0x00016102');
+});
+
+test('without the registry list an AMD card is still listed, with no size', () => {
+  const cards = windowsOtherGpus([{ Name: 'AMD Radeon RX 7900 XT', PNPDeviceID: 'PCI-B' }], parseDxAdapters('garbage'));
+  assert.deepEqual(cards.map(c => [c.vendor, c.vramGb, c.luid]), [['amd', 0, null]]);
+});
+
+test('counter lines are read, and the load and VRAM in use reach the card by its LUID', () => {
+  assert.equal(parseGpuCounterLine('nonsense'), null);
+  const line = parseGpuCounterLine('G luid_0x00000000_0x00016102 37 4294967296');
+  assert.equal(line.utilizationPct, 37);
+  assert.equal(line.memoryUsedGb, 4);
+  const procs = [];
+  const reader = createWindowsGpuReader({ spawnFn: () => { const p = new EventEmitter(); p.stdout = new EventEmitter(); p.kill = () => {}; procs.push(p); return p; }, now: () => 5 });
+  assert.equal(reader.read('luid_0x00000000_0x00016102'), null, 'nothing before the first line');
+  procs[0].stdout.emit('data', 'G luid_0x00000000_0x00016102 37 4294967296\nG luid_0x00000000_0x00000001 0 0\n');
+  assert.equal(reader.read('LUID_0x00000000_0x00016102').utilizationPct, 37);
+  assert.equal(reader.read('luid_0x00000000_0x00099999'), null);
+  assert.equal(procs.length, 1, 'one process for every read');
+});

conftest.py

@@ -7,3 +7,9 @@ import tempfile
 _home = tempfile.mkdtemp(prefix="strata-pytest-config-")
 os.environ["APPDATA"] = _home
 os.environ["XDG_CONFIG_HOME"] = _home
+# The per-user STATE and DATA folders too (%LOCALAPPDATA%\Strata: tuning/recheck.json, the engine store, the update records; ~/.local/state, ~/.local/share).
+# A test that installs a stub engine marks saved tuning presets for a re-check there: on 2026-10-24 one such run left an entry in the owner's real
+# tuning\recheck.json. A test that wants a place of its own still names it (STRATA_COMPONENTS_DIR, state_base=...).
+os.environ["LOCALAPPDATA"] = _home
+os.environ["XDG_STATE_HOME"] = _home
+os.environ["XDG_DATA_HOME"] = _home

data/dsv41/profile-2.00.bin.sha256

@@ -0,0 +1 @@
+8db93e483b34b15dbf63a0826601f1db2107a8cfea73774e7d21d8559e0a9568 *profile-2.00.bin