feat(backend): forward resolved chat_template_kwargs blob to backends

gRPCPredictOpts now merges per-request client metadata over the server-derived
enable_thinking/reasoning_effort (reaching all backends via the standalone keys)
and serialises the resolved chat_template_kwargs map into a JSON blob for
llama.cpp, written last so a client cannot clobber it. Issue #10329.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

core/backend/options.go

@@ -368,6 +368,25 @@ func gRPCPredictOpts(c config.ModelConfig, modelPath string) *pb.PredictOptions
 	if c.ReasoningEffort != "" {
 		metadata["reasoning_effort"] = c.ReasoningEffort
 	}
+	// Client request metadata overrides the server-derived reasoning levers and
+	// reaches every backend through these standalone string keys (Python backends
+	// read them directly). The reserved blob key is server-owned and skipped.
+	for k, v := range c.RequestMetadata {
+		if k == "chat_template_kwargs" {
+			continue
+		}
+		metadata[k] = v
+	}
+	// Build the generic chat_template_kwargs blob (model config map + coerced
+	// metadata) for llama.cpp and write it LAST so a client cannot clobber it.
+	if blob := c.ResolveChatTemplateKwargs(metadata); len(blob) > 0 {
+		b, err := json.Marshal(blob)
+		if err != nil {
+			xlog.Warn("failed to marshal chat_template_kwargs", "error", err)
+		} else {
+			metadata["chat_template_kwargs"] = string(b)
+		}
+	}
 	pbOpts.Metadata = metadata
 
 	// Logprobs and TopLogprobs are set by the caller if provided

core/backend/options_internal_test.go

@@ -161,3 +161,54 @@ var _ = Describe("grpcModelOpts NBatch", func() {
 		Expect(opts.ContextSize).To(BeEquivalentTo(4096), "n_batch must match the effective n_ctx the backend receives")
 	})
 })
+
+// Guards the generic chat_template_kwargs forwarding: the model config map plus any
+// per-request metadata overrides are merged, coerced, and serialised into the
+// backend metadata blob that llama.cpp reads. Client metadata also overrides the
+// server-derived standalone enable_thinking key (cross-backend consistency).
+var _ = Describe("gRPCPredictOpts chat_template_kwargs metadata", func() {
+	baseCfg := func() config.ModelConfig {
+		cfg := config.ModelConfig{}
+		cfg.SetDefaults()
+		return cfg
+	}
+
+	It("serialises the config map into the chat_template_kwargs blob", func() {
+		cfg := baseCfg()
+		cfg.ChatTemplateKwargs = map[string]any{"preserve_thinking": true}
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		Expect(opts.Metadata).To(HaveKey("chat_template_kwargs"))
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+
+	It("lets client request metadata override the server-derived enable_thinking key", func() {
+		cfg := baseCfg()
+		disable := true
+		cfg.ReasoningConfig = reasoning.Config{DisableReasoning: &disable} // server: enable_thinking=false
+		cfg.RequestMetadata = map[string]string{"enable_thinking": "true"} // client overrides
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		// standalone key (Python backends) reflects the client override
+		Expect(opts.Metadata).To(HaveKeyWithValue("enable_thinking", "true"))
+		// blob (llama.cpp) reflects it too, as a real bool
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("enable_thinking", true))
+	})
+
+	It("does not let a client clobber the blob via a chat_template_kwargs metadata key", func() {
+		cfg := baseCfg()
+		cfg.ChatTemplateKwargs = map[string]any{"preserve_thinking": true}
+		cfg.RequestMetadata = map[string]string{"chat_template_kwargs": "{\"preserve_thinking\": false}"}
+		opts := gRPCPredictOpts(cfg, "/tmp/models")
+		var blob map[string]any
+		Expect(json.Unmarshal([]byte(opts.Metadata["chat_template_kwargs"]), &blob)).To(Succeed())
+		Expect(blob).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+
+	It("omits the blob when there is nothing to forward", func() {
+		opts := gRPCPredictOpts(baseCfg(), "/tmp/models")
+		Expect(opts.Metadata).ToNot(HaveKey("chat_template_kwargs"))
+	})
+})