[pull] master from mudler:master

backend/cpp/ds4/dsml_parser.cpp

@@ -92,7 +92,8 @@ std::string json_escape(const std::string &in) {
 
 } // namespace
 
-DsmlParser::DsmlParser() = default;
+DsmlParser::DsmlParser(bool starts_in_thinking)
+    : state_(starts_in_thinking ? State::THINK : State::TEXT) {}
 
 bool DsmlParser::IsInDsmlStructural() const {
     switch (state_) {

backend/cpp/ds4/dsml_parser.h

@@ -17,7 +17,9 @@ struct ParserEvent {
 // Streaming parser. Stateless across instances; one per Predict call.
 class DsmlParser {
 public:
-    DsmlParser();
+    // The chat prompt may already contain the opening thinking marker, so the
+    // generated text can begin directly with reasoning bytes.
+    explicit DsmlParser(bool starts_in_thinking = false);
 
     // Feed a chunk of raw model-emitted text. Appends classified events to
     // `out`. May buffer the tail of `chunk` internally if it looks like a
@@ -43,7 +45,7 @@ class DsmlParser {
 
 private:
     enum class State { TEXT, THINK, TOOL_CALLS, INVOKE, PARAM_VALUE };
-    State state_ = State::TEXT;
+    State state_;
     std::string buf_;
     std::string current_tool_name_;
     int tool_index_ = -1;

backend/cpp/ds4/dsml_parser_test.cpp

@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: MIT
+// Standalone regression tests for the DSML streaming parser.
+//
+// The repository's backend/cpp/run-unit-tests.sh harness compiles each
+// *_test.cpp as a single translation unit, so include the implementation here.
+
+#include "dsml_parser.cpp"
+
+#include <cstdio>
+#include <string>
+#include <type_traits>
+#include <vector>
+
+namespace {
+
+struct ParsedText {
+    std::string content;
+    std::string reasoning;
+};
+
+int failures = 0;
+
+void check_equal(const std::string &got, const std::string &want,
+                 const char *name) {
+    if (got == want) return;
+    std::fprintf(stderr, "FAIL %s: got \"%s\", want \"%s\"\n",
+                 name, got.c_str(), want.c_str());
+    failures++;
+}
+
+void collect_text(const std::vector<ds4cpp::ParserEvent> &events,
+                  ParsedText *parsed) {
+    for (const auto &event : events) {
+        if (event.type == ds4cpp::ParserEvent::CONTENT) {
+            parsed->content += event.text;
+        } else if (event.type == ds4cpp::ParserEvent::REASONING) {
+            parsed->reasoning += event.text;
+        }
+    }
+}
+
+ParsedText parse_chunks(ds4cpp::DsmlParser *parser,
+                        const std::vector<std::string> &chunks) {
+    ParsedText parsed;
+    for (const auto &chunk : chunks) {
+        std::vector<ds4cpp::ParserEvent> events;
+        parser->Feed(chunk, events);
+        collect_text(events, &parsed);
+    }
+    std::vector<ds4cpp::ParserEvent> events;
+    parser->Flush(events);
+    collect_text(events, &parsed);
+    return parsed;
+}
+
+template <typename Parser>
+void test_reasoning_opened_by_prompt() {
+    if constexpr (!std::is_constructible_v<Parser, bool>) {
+        std::fprintf(stderr,
+                     "FAIL reasoning_opened_by_prompt: parser cannot start in thinking state\n");
+        failures++;
+    } else {
+        Parser parser(true);
+        ParsedText parsed = parse_chunks(
+            &parser,
+            {"We need to calculate factorial recursively.</think>Here is the answer."});
+        check_equal(parsed.reasoning,
+                    "We need to calculate factorial recursively.",
+                    "reasoning_opened_by_prompt:reasoning");
+        check_equal(parsed.content, "Here is the answer.",
+                    "reasoning_opened_by_prompt:content");
+    }
+}
+
+template <typename Parser>
+Parser text_parser() {
+    if constexpr (std::is_constructible_v<Parser, bool>) {
+        return Parser(false);
+    } else {
+        return Parser();
+    }
+}
+
+void test_reasoning_disabled() {
+    auto parser = text_parser<ds4cpp::DsmlParser>();
+    ParsedText parsed = parse_chunks(&parser, {"Here is the answer."});
+    check_equal(parsed.reasoning, "", "reasoning_disabled:reasoning");
+    check_equal(parsed.content, "Here is the answer.",
+                "reasoning_disabled:content");
+}
+
+void test_explicit_think_tag() {
+    auto parser = text_parser<ds4cpp::DsmlParser>();
+    ParsedText parsed = parse_chunks(
+        &parser, {"<think>reasoning</think>answer"});
+    check_equal(parsed.reasoning, "reasoning", "explicit_think_tag:reasoning");
+    check_equal(parsed.content, "answer", "explicit_think_tag:content");
+}
+
+template <typename Parser>
+void test_split_think_close_marker() {
+    if constexpr (!std::is_constructible_v<Parser, bool>) {
+        std::fprintf(stderr,
+                     "FAIL split_think_close_marker: parser cannot start in thinking state\n");
+        failures++;
+    } else {
+        Parser parser(true);
+        ParsedText parsed = parse_chunks(
+            &parser,
+            {"We need ", "to calculate ", "factorial", "</thi", "nk>",
+             "Here is ", "the answer."});
+        check_equal(parsed.reasoning, "We need to calculate factorial",
+                    "split_think_close_marker:reasoning");
+        check_equal(parsed.content, "Here is the answer.",
+                    "split_think_close_marker:content");
+    }
+}
+
+} // namespace
+
+int main() {
+    test_reasoning_opened_by_prompt<ds4cpp::DsmlParser>();
+    test_reasoning_disabled();
+    test_explicit_think_tag();
+    test_split_think_close_marker<ds4cpp::DsmlParser>();
+
+    if (failures == 0) {
+        std::fprintf(stderr, "all dsml_parser checks passed\n");
+        return 0;
+    }
+    std::fprintf(stderr, "%d check(s) failed\n", failures);
+    return 1;
+}

backend/cpp/ds4/grpc-server.cpp

@@ -771,7 +771,12 @@ class DS4Backend final : public backend::Backend::Service {
         build_prompt(g_engine, request, &prompt);
         int n_predict = request->tokens() > 0 ? request->tokens() : 256;
 
-        CollectCtx collect = {g_engine, "", {}, reply, 0, {}, "", ""};
+        const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
+        const bool starts_in_thinking = think_enabled &&
+            request->usetokenizertemplate() && request->messages_size() > 0;
+        CollectCtx collect = {
+            g_engine, "", ds4cpp::DsmlParser(starts_in_thinking),
+            reply, 0, {}, "", ""};
         std::string cache_key = render_prompt_text(request);
         size_t cache_hit = maybe_load_cache(cache_key);
         (void)cache_hit; // future: skip prompt prefix if hit covers full prompt
@@ -789,7 +794,6 @@ class DS4Backend final : public backend::Backend::Service {
         if (rc == 0) {
             const int eos = ds4_token_eos(g_engine);
             const int draft_max = ds4_engine_mtp_draft_tokens(g_engine);
-            const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
             int produced = 0;
             while (produced < n_predict) {
                 SampleParams sp = compute_sample_params(request, collect.parser, think_enabled);
@@ -871,7 +875,12 @@ class DS4Backend final : public backend::Backend::Service {
         build_prompt(g_engine, request, &prompt);
         int n_predict = request->tokens() > 0 ? request->tokens() : 256;
 
-        StreamCtx s = {g_engine, writer, {}, 0, false, {}};
+        const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
+        const bool starts_in_thinking = think_enabled &&
+            request->usetokenizertemplate() && request->messages_size() > 0;
+        StreamCtx s = {
+            g_engine, writer, ds4cpp::DsmlParser(starts_in_thinking),
+            0, false, {}};
         std::string cache_key = render_prompt_text(request);
         size_t cache_hit = maybe_load_cache(cache_key);
         (void)cache_hit;
@@ -884,7 +893,6 @@ class DS4Backend final : public backend::Backend::Service {
         if (rc == 0) {
             const int eos = ds4_token_eos(g_engine);
             const int draft_max = ds4_engine_mtp_draft_tokens(g_engine);
-            const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
             int produced = 0;
             while (produced < n_predict && !s.aborted) {
                 SampleParams sp = compute_sample_params(request, s.parser, think_enabled);

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=15dddc60b3fc937a9e2a210359ecce392ccdf446
+IK_LLAMA_VERSION?=3c58ae373a0081c884099f435fb16ca720852bf7
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/go/vllm-cpp/Makefile

@@ -11,7 +11,7 @@ JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || e
 
 # vllm.cpp version
 VLLM_CPP_REPO?=https://github.com/mudler/vllm.cpp
-VLLM_CPP_VERSION?=150b37852c123f7855fb219b37347572ca9427e7
+VLLM_CPP_VERSION?=6a544bdb89eb5a3512ac922241439e45f24d74d4
 
 # MLX GEMM provider (darwin/metal only; see the metal branch below for why).
 # Consumed as the prebuilt pip wheel: building MLX from source needs `xcrun

core/services/nodes/router.go

@@ -1874,6 +1874,16 @@ func (r *SmartRouter) stageOptionDir(ctx context.Context, node *BackendNode, dir
 		if walkErr != nil || d.IsDir() {
 			return nil
 		}
+		// Same reason as stageDirectory: the receiver writes "<file>.sha256" for
+		// every file it accepts, so staging the sidecars makes it write sidecars
+		// for those in turn. Option dirs are walked on every load, so each pass
+		// added a level - an espeak-ng-data tree observed in the wild had grown
+		// to "<file>.sha256" repeated eleven times and 5077 junk files, which is
+		// enough to keep a sherpa-onnx voice permanently "staging" and fail
+		// every realtime warmup that needs it.
+		if isHashSidecar(path) {
+			return nil
+		}
 		if _, err := r.fileStager.EnsureRemote(ctx, node.ID, path, keyFn(path)); err != nil {
 			xlog.Warn("Failed to stage option directory file, skipping", "path", path, "error", err)
 		}