Upgrade llama.cpp from b9864 to b9866

Trivial additive upgrade — no incompatibilities, no project source changes.
Bumps GIT_TAG (+ the TTS provenance banner), the README badge/link, and the
CLAUDE.md pinned-version line + build examples.

The b9864..b9866 diff is backend/WebUI-only: the CUDA topk-moe kernel gains a
case 288 instantiation + accepts n_expert==288 (StepFun 3.7's non-power-of-2
expert count) — device-side, affecting only the cuda13 classifiers; a
test-backend-ops.cpp case (not built here, LLAMA_BUILD_TESTS OFF); and WebUI
changes (a config string-boolean normalization migration + a thinking-default
flip) that auto-follow the pinned GIT_TAG via the build-webui job. The project
binds no new symbol.

Patch verification: the diff touches no patch-target file and no OuteTTS anchor,
so all six patches are byte-identical to b9864. Confirmed end-to-end by a clean
cmake configure: b9866 fetched (case 288 present) and all six patches applied via
the fail-loud PATCH_COMMAND (exit 0; 0005 + 0006 markers present), OuteTTS anchors
held.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HL7d4uQ3cKR5HwYFPvZvv7

Author: claude

CLAUDE.md

@@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 Java bindings for [llama.cpp](https://github.com/ggerganov/llama.cpp) via JNI, providing a high-level API for LLM inference in Java. The Java layer communicates with a native C++ library through JNI.
 
-Current llama.cpp pinned version: **b9864**
+Current llama.cpp pinned version: **b9866**
 
 ## Upgrading CUDA Version
 
@@ -344,7 +344,7 @@ needs no extra step here, `build-webui` re-reads the tag and rebuilds the matchi
 ships no UI):
 ```bash
 # needs node/npm + network; embed.cpp is plain C++17 (no npm)
-git clone --depth 1 --branch b9864 https://github.com/ggml-org/llama.cpp /tmp/lc
+git clone --depth 1 --branch b9866 https://github.com/ggml-org/llama.cpp /tmp/lc
 ( cd /tmp/lc/tools/ui && npm ci && npm run build \
   && ( cd dist && find . -type f -not -path './_gzip/*' \
        | while read -r f; do mkdir -p "_gzip/$(dirname "$f")"; gzip -9 -c "$f" > "_gzip/$f"; done ) \
@@ -384,7 +384,7 @@ cache lives in **Depot Cache** over sccache's **WebDAV** backend:
 - `SCCACHE_WEBDAV_TOKEN: ${{ secrets.DEPOT_TOKEN }}` — a Depot **organization** token, stored
   as the repo secret **`DEPOT_TOKEN`**.
 
-Because `sccache` is **content-addressed** and llama.cpp is pinned (`GIT_TAG b9864`), the
+Because `sccache` is **content-addressed** and llama.cpp is pinned (`GIT_TAG b9866`), the
 ~280 upstream object files are byte-identical every run, so a warm cache recompiles only the
 *changed* files. Depot's cache is **shared across all branches** (unlike GitHub's
 per-branch `actions/cache`), so every branch builds incrementally; a `b<nnnn>` version bump
@@ -497,7 +497,7 @@ Current patches:
 | `0003-pr22393-server-add-slot-prompt-similarity-getter-setter.patch` | **Upstream-PR carry** of [ggml-org/llama.cpp#22393](https://github.com/ggml-org/llama.cpp/pull/22393) ("server : add slot_prompt_similarity getter/setter") while it is still open upstream. Purely additive: adds `server_context::get_slot_prompt_similarity()` / `set_slot_prompt_similarity(float)` (`tools/server/server-context.{cpp,h}`) so an embedding/JNI caller can query and tune the slot-selection threshold at runtime without reloading the model. Verbatim copy of the PR — drop it once a pinned `b<nnnn>` includes the change. |
 | `0004-pr23116-server-per-request-reasoning-budget-tokens.patch` | **Upstream-PR carry** of [ggml-org/llama.cpp#23116](https://github.com/ggml-org/llama.cpp/pull/23116) ("server: honour per-request reasoning_budget_tokens in chat completions"), motivated by java-llama.cpp#140, while it is still open upstream. `oaicompat_chat_params_parse` (`tools/server/server-common.cpp`) only read the Anthropic `thinking_budget_tokens` alias and always wrote the server-level `reasoning_budget_message`, so a per-request `reasoning_budget_tokens` / `reasoning_budget_message` on a chat-completions request was ignored. The patch reads both overrides **before** the generic copy loop (precedence: `reasoning_budget_tokens` > `thinking_budget_tokens` alias > server default) and threads the per-request message through. Carries the upstream `tests/test-chat.cpp` additions verbatim so the patch is submittable as-is; like `0001`'s test/call-site flips they are **applied-but-not-compiled** here (`LLAMA_BUILD_TESTS` is OFF for the FetchContent subproject). Drop it once a pinned `b<nnnn>` includes the change. |
 | `0005-server-recurrent-near-prompt-end-checkpoints.patch` | **Multi-turn tool-calling perf fix for recurrent/hybrid models (e.g. Granite-4)**, upstream-submittable. In `server_context::update_slots` (`tools/server/server-context.cpp`) the near-prompt-end context checkpoints are gated by `checkpoint_min_step` (default 8192 tokens). An agentic conversation that appends only assistant/tool messages never produces a new user-message checkpoint (`is_user_start`/`is_last_user_message` match `COMMON_CHAT_ROLE_USER` only), so after turn 1 no new checkpoint is ever created and — because recurrent state can only roll back to a checkpoint — **every turn re-prefills the whole conversation tail** (measured on a synthetic granitehybrid model: prefilled tokens grew 901 → 1544 → 2187 → 2830 → 3473 over turns 2–6). The patch (1) exempts near-prompt-end checkpoints from the min-step spacing when the memory can only roll back via checkpoints (`ctx_tgt_seq_rm_type` is `FULL` or `RS` — SWA-only models are unaffected), and (2) skips creating a checkpoint whose position equals the newest one (the last-user-message checkpoint was re-created identically on every turn, flooding the 32-entry list). After the patch each turn restores the previous turn's near-end checkpoint and prefill is constant (~new-turn-sized; 647 tokens/turn in the same measurement, ≈5.4× less prefill at turn 6 and growing with conversation length). Validated output-identical (`temperature=0`) vs. unpatched. Complements — not duplicates — open upstream PRs #24035/#24899/#24891 (they fix checkpoint *invalidation/retention*; this fixes checkpoint *starvation*). Drop once upstream solves agentic checkpoint placement (e.g. a merged role-boundary checkpointing design, cf. #21885 / #22826 discussion). |
-| `0006-server-embed-native-server-jni.patch` | **Makes `server.cpp`'s `llama_server` embeddable in the JVM** so the `NativeServer` JNI bridge can run the full upstream HTTP server (WebUI included) inside `libjllama` — see "Two server modes" below. b9864 already exposes `int llama_server(int, char**)` (non-static; no `main` in the file), so the patch only adds embedded-mode support: (1) a `g_llama_server_embedded` flag + `llama_server_set_embedded()` / `llama_server_request_shutdown()` (declared in the committed `src/main/cpp/native_server_bridge.h`); (2) skips installing the process-wide SIGINT/SIGTERM handlers when embedded (they would hijack the JVM's); (3) in embedded mode parses the **forwarded** argv via `common_params_parse` instead of `common_params_parse_main` (whose `GetCommandLineW` recovery would pick up `java.exe`'s command line — the same Windows class of bug `0001` fixes). `llama_server_request_shutdown()` mirrors the SIGTERM path (invokes the installed `shutdown_handler` → `ctx_server.terminate()` unblocks `start_loop()`), giving JNI an out-of-band stop since `ctx_server` is loop-local. Applies **after `0001`** (which flips this call site to `common_params_parse_main`), so its context is the post-`0001` tree; regenerate against `0001`+source on a bump. Only touches `tools/server/server.cpp`. |
+| `0006-server-embed-native-server-jni.patch` | **Makes `server.cpp`'s `llama_server` embeddable in the JVM** so the `NativeServer` JNI bridge can run the full upstream HTTP server (WebUI included) inside `libjllama` — see "Two server modes" below. b9866 already exposes `int llama_server(int, char**)` (non-static; no `main` in the file), so the patch only adds embedded-mode support: (1) a `g_llama_server_embedded` flag + `llama_server_set_embedded()` / `llama_server_request_shutdown()` (declared in the committed `src/main/cpp/native_server_bridge.h`); (2) skips installing the process-wide SIGINT/SIGTERM handlers when embedded (they would hijack the JVM's); (3) in embedded mode parses the **forwarded** argv via `common_params_parse` instead of `common_params_parse_main` (whose `GetCommandLineW` recovery would pick up `java.exe`'s command line — the same Windows class of bug `0001` fixes). `llama_server_request_shutdown()` mirrors the SIGTERM path (invokes the installed `shutdown_handler` → `ctx_server.terminate()` unblocks `start_loop()`), giving JNI an out-of-band stop since `ctx_server` is loop-local. Applies **after `0001`** (which flips this call site to `common_params_parse_main`), so its context is the post-`0001` tree; regenerate against `0001`+source on a bump. Only touches `tools/server/server.cpp`. |
 
 ## OuteTTS build-time extraction (`cmake/generate-tts-upstream.cmake`)
 
@@ -911,7 +911,7 @@ If the local check passes (`BUILD SUCCESS`), the `mvn package` job in
 - `json_helpers.hpp` — Pure JSON transformation helpers (no JNI, no llama state). Independently unit-testable.
 - `jni_helpers.hpp` — JNI bridge helpers (handle management + server orchestration). Includes `json_helpers.hpp`.
 - Uses `nlohmann/json` for JSON deserialization of parameters.
-- The upstream server library (`server-context.cpp`, `server-queue.cpp`, `server-task.cpp`, `server-schema.cpp`, `server-models.cpp`, and — since b9829 — `server-stream.cpp`) is compiled directly into `jllama` via CMake — there is no hand-ported `server.hpp` fork. **`server-stream.cpp` is mandatory, not optional:** it defines the resumable-streaming SSE replay buffer (`g_stream_sessions`, `stream_session_attach_pipe`, `stream_aware_should_stop`, `stream_conv_id_from_headers`, the `stream_pipe_*` types) that `server-context.cpp` / `server-http.cpp` / `server-models.cpp` now `#include "server-stream.h"` and call, so omitting it fails the link with undefined references. It is platform-neutral (threads + std mutex/condvar, no `subprocess.h`/`posix_spawn_*`), so it builds on Android too and sits outside the `server-models.cpp` Android guard. `jllama` wires its own JNI routes and never calls `g_stream_sessions.start_gc()` (only the excluded standalone `server.cpp` `main()` does), so its GC thread stays dormant. **Phase 2:** the upstream HTTP transport (`tools/server/server-http.cpp`) and its `cpp-httplib` backend (`vendor/cpp-httplib/httplib.cpp`) are now compiled into `jllama` too, so the OpenAI-compatible server can be driven natively from JNI *inside* `libjllama` — no separate `llama-server` executable (a JNI shared library loads anywhere a JVM runs, which a standalone binary does not). `server-http.cpp` does `#include "ui.h"` (the WebUI asset table that `tools/ui`/`llama-ui` normally generates); since the Svelte WebUI is not shipped, `src/main/cpp/webui_stub/ui.h` supplies the upstream **empty-asset** interface and leaves `LLAMA_UI_HAS_ASSETS` undefined (all static-asset-serving blocks compile out). `<cpp-httplib/httplib.h>` already resolves via `llama-common`'s `vendor/` include dir (same nlohmann/json 3.12.0 as the FetchContent copy). No SSL: `CPPHTTPLIB_OPENSSL_SUPPORT` is left undefined (plain-HTTP; bind localhost / front with a TLS proxy). **`server.cpp` is now compiled in too** (on non-Android — it and `server-tools.cpp` pull in `subprocess.h`/`posix_spawn_*`, so they share `server-models.cpp`'s Android guard): b9864 exposes its entry as `int llama_server(int, char**)` (no `main` in the file), and `patches/0006` makes it embeddable (no process signal handlers, forwarded-argv parse, out-of-band shutdown). The `NativeServer` JNI bridge (`src/main/cpp/native_server.cpp`) calls `llama_server` on a worker thread, so the **full** upstream server — WebUI and all — runs inside `libjllama`. See "Two server modes" below.
+- The upstream server library (`server-context.cpp`, `server-queue.cpp`, `server-task.cpp`, `server-schema.cpp`, `server-models.cpp`, and — since b9829 — `server-stream.cpp`) is compiled directly into `jllama` via CMake — there is no hand-ported `server.hpp` fork. **`server-stream.cpp` is mandatory, not optional:** it defines the resumable-streaming SSE replay buffer (`g_stream_sessions`, `stream_session_attach_pipe`, `stream_aware_should_stop`, `stream_conv_id_from_headers`, the `stream_pipe_*` types) that `server-context.cpp` / `server-http.cpp` / `server-models.cpp` now `#include "server-stream.h"` and call, so omitting it fails the link with undefined references. It is platform-neutral (threads + std mutex/condvar, no `subprocess.h`/`posix_spawn_*`), so it builds on Android too and sits outside the `server-models.cpp` Android guard. `jllama` wires its own JNI routes and never calls `g_stream_sessions.start_gc()` (only the excluded standalone `server.cpp` `main()` does), so its GC thread stays dormant. **Phase 2:** the upstream HTTP transport (`tools/server/server-http.cpp`) and its `cpp-httplib` backend (`vendor/cpp-httplib/httplib.cpp`) are now compiled into `jllama` too, so the OpenAI-compatible server can be driven natively from JNI *inside* `libjllama` — no separate `llama-server` executable (a JNI shared library loads anywhere a JVM runs, which a standalone binary does not). `server-http.cpp` does `#include "ui.h"` (the WebUI asset table that `tools/ui`/`llama-ui` normally generates); since the Svelte WebUI is not shipped, `src/main/cpp/webui_stub/ui.h` supplies the upstream **empty-asset** interface and leaves `LLAMA_UI_HAS_ASSETS` undefined (all static-asset-serving blocks compile out). `<cpp-httplib/httplib.h>` already resolves via `llama-common`'s `vendor/` include dir (same nlohmann/json 3.12.0 as the FetchContent copy). No SSL: `CPPHTTPLIB_OPENSSL_SUPPORT` is left undefined (plain-HTTP; bind localhost / front with a TLS proxy). **`server.cpp` is now compiled in too** (on non-Android — it and `server-tools.cpp` pull in `subprocess.h`/`posix_spawn_*`, so they share `server-models.cpp`'s Android guard): b9866 exposes its entry as `int llama_server(int, char**)` (no `main` in the file), and `patches/0006` makes it embeddable (no process signal handlers, forwarded-argv parse, out-of-band shutdown). The `NativeServer` JNI bridge (`src/main/cpp/native_server.cpp`) calls `llama_server` on a worker thread, so the **full** upstream server — WebUI and all — runs inside `libjllama`. See "Two server modes" below.
 
 ### Two server modes (`OpenAiCompatServer` vs `NativeServer`)
 
@@ -1100,7 +1100,7 @@ ctest --test-dir build --output-on-failure -R "ResultsToJson"
 
 #### Upstream source location (in CMake build tree)
 
-llama.cpp is fetched via CMake FetchContent, pinned to `GIT_TAG b9864`.
+llama.cpp is fetched via CMake FetchContent, pinned to `GIT_TAG b9866`.
 
 **GoogleTest** is a separate `BUILD_TESTING`-only FetchContent (`GIT_TAG v1.17.0`), used solely
 by the `jllama_test` C++ unit-test binary — not by the shipped library, and not coupled to the

README.md

@@ -7,7 +7,7 @@
 **Build:**  
 ![Java 8+](https://img.shields.io/badge/Java-8%2B-informational)  
 ![Platform](https://img.shields.io/badge/Platform-Linux%20%7C%20macOS%20%7C%20Windows%20%7C%20Android-lightgrey)  
-[![llama.cpp b9864](https://img.shields.io/badge/llama.cpp-%23b9864-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b9864)  
+[![llama.cpp b9866](https://img.shields.io/badge/llama.cpp-%23b9866-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b9866)  
 [![JPMS](https://img.shields.io/badge/JPMS-modular%20JAR-25A162)](https://openjdk.org/projects/jigsaw/)  
 ![JUnit](https://img.shields.io/badge/tested%20with-JUnit6-25A162)  
 [![JSpecify](https://img.shields.io/badge/JSpecify-1.0.0%20%40NullMarked-25A162)](https://jspecify.dev)