From bc8a1be8014e59d9126ae1b4139c41fbf2a1c06a Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Tue, 16 Jun 2026 07:46:43 +0000
Subject: [PATCH] feat(config): add chat_template_kwargs model field + resolver

Adds the ChatTemplateKwargs model-config map and RequestMetadata carrier,
plus ResolveChatTemplateKwargs which layers the config map under coerced
request metadata. Foundation for generic jinja chat-template kwargs (issue #10329).

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 core/config/chat_template_kwargs_test.go | 48 ++++++++++++++++++++++
 core/config/model_config.go              | 51 ++++++++++++++++++++++++
 2 files changed, 99 insertions(+)
 create mode 100644 core/config/chat_template_kwargs_test.go

diff --git a/core/config/chat_template_kwargs_test.go b/core/config/chat_template_kwargs_test.go
new file mode 100644
index 000000000..4b32e695e
--- /dev/null
+++ b/core/config/chat_template_kwargs_test.go
@@ -0,0 +1,48 @@
+package config_test
+
+import (
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"github.com/mudler/LocalAI/core/config"
+)
+
+// ResolveChatTemplateKwargs layers the model config map (base) under the coerced
+// backend metadata (server reasoning levers + client request overrides).
+var _ = Describe("ModelConfig.ResolveChatTemplateKwargs", func() {
+	It("returns nil when nothing is set", func() {
+		c := &config.ModelConfig{}
+		Expect(c.ResolveChatTemplateKwargs(nil)).To(BeNil())
+	})
+
+	It("returns the config map when no metadata is present", func() {
+		c := &config.ModelConfig{ChatTemplateKwargs: map[string]any{"preserve_thinking": true}}
+		Expect(c.ResolveChatTemplateKwargs(nil)).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+
+	It("lets metadata override the config map", func() {
+		c := &config.ModelConfig{ChatTemplateKwargs: map[string]any{"enable_thinking": true}}
+		got := c.ResolveChatTemplateKwargs(map[string]string{"enable_thinking": "false"})
+		Expect(got).To(HaveKeyWithValue("enable_thinking", false))
+	})
+
+	It("coerces true/false to bool and leaves other strings as-is", func() {
+		c := &config.ModelConfig{}
+		got := c.ResolveChatTemplateKwargs(map[string]string{
+			"enable_thinking":  "true",
+			"reasoning_effort": "high",
+		})
+		Expect(got).To(HaveKeyWithValue("enable_thinking", true))
+		Expect(got).To(HaveKeyWithValue("reasoning_effort", "high"))
+	})
+
+	It("skips the reserved chat_template_kwargs metadata key but keeps siblings", func() {
+		c := &config.ModelConfig{}
+		got := c.ResolveChatTemplateKwargs(map[string]string{
+			"chat_template_kwargs": "{\"x\":1}",
+			"preserve_thinking":    "true",
+		})
+		Expect(got).ToNot(HaveKey("chat_template_kwargs"))
+		Expect(got).To(HaveKeyWithValue("preserve_thinking", true))
+	})
+})
diff --git a/core/config/model_config.go b/core/config/model_config.go
index 755280cc3..955a7a6ec 100644
--- a/core/config/model_config.go
+++ b/core/config/model_config.go
@@ -70,6 +70,19 @@ type ModelConfig struct {
 	// (Harmony) or LFM2.5 — honor it; "none" also toggles enable_thinking off.
 	ReasoningEffort string `yaml:"reasoning_effort,omitempty" json:"reasoning_effort,omitempty"`
 
+	// ChatTemplateKwargs are arbitrary key/values forwarded to the backend's jinja
+	// chat template via chat_template_kwargs (e.g. preserve_thinking: true). The
+	// server-derived reasoning levers (enable_thinking / reasoning_effort) and any
+	// per-request metadata overrides layer on top. See gRPCPredictOpts.
+	ChatTemplateKwargs map[string]any `yaml:"chat_template_kwargs,omitempty" json:"chat_template_kwargs,omitempty"`
+
+	// RequestMetadata holds the raw client request `metadata` map for the current
+	// request. The request middleware stamps it; gRPCPredictOpts merges it into the
+	// backend gRPC metadata (overriding the server-derived enable_thinking /
+	// reasoning_effort) and folds it, coerced, into the chat_template_kwargs blob.
+	// Never persisted to YAML.
+	RequestMetadata map[string]string `yaml:"-" json:"-"`
+
 	FeatureFlag FeatureFlag `yaml:"feature_flags,omitempty" json:"feature_flags,omitempty"` // Feature Flag registry. We move fast, and features may break on a per model/backend basis. Registry for (usually temporary) flags that indicate aborting something early.
 	// LLM configs (GPT4ALL, Llama.cpp, ...)
 	LLMConfig `yaml:",inline" json:",inline"`
@@ -551,6 +564,44 @@ func (c *ModelConfig) ApplyReasoningEffort(requestEffort string) {
 	}
 }
 
+// coerceChatTemplateKwarg coerces a request-metadata string value for use as a
+// jinja chat_template_kwarg. "true"/"false" become real booleans (so a jinja
+// `{% if preserve_thinking %}` reads false correctly, since any non-empty string
+// is truthy); everything else stays a string. Numeric/typed per-request values are
+// out of scope - set those in the model YAML chat_template_kwargs (YAML keeps the type).
+func coerceChatTemplateKwarg(v string) any {
+	switch v {
+	case "true":
+		return true
+	case "false":
+		return false
+	default:
+		return v
+	}
+}
+
+// ResolveChatTemplateKwargs builds the final chat_template_kwargs map forwarded to
+// the backend, layered: the model config map (base) < the coerced backend metadata
+// (server reasoning levers + client request overrides). `meta` is the already-merged
+// backend metadata string map. The reserved "chat_template_kwargs" key is skipped so
+// a client cannot smuggle a nested blob. Returns nil when there is nothing to forward.
+func (c *ModelConfig) ResolveChatTemplateKwargs(meta map[string]string) map[string]any {
+	out := map[string]any{}
+	for k, v := range c.ChatTemplateKwargs {
+		out[k] = v
+	}
+	for k, v := range meta {
+		if k == "chat_template_kwargs" {
+			continue
+		}
+		out[k] = coerceChatTemplateKwarg(v)
+	}
+	if len(out) == 0 {
+		return nil
+	}
+	return out
+}
+
 // @Description PipelineStreaming toggles incremental delivery per realtime stage.
 type PipelineStreaming struct {
 	LLM           *bool `yaml:"llm,omitempty" json:"llm,omitempty"`