From 0ca6428554be9057926988ef4af0b95a958ca17e Mon Sep 17 00:00:00 2001
From: Huynh Duc Dung <dunghd.it@gmail.com>
Date: Thu, 5 Mar 2026 12:29:49 +0800
Subject: [PATCH] feat(api): add llama.cpp support as local model provider

- Add llamacpp provider preset to provider-presets.ts
- Add base-llamacpp.settings.json configuration
- Update help-command.ts with ccs llamacpp documentation
- Update UI provider presets for dashboard parity

llama.cpp is a popular C++ inference engine for LLaMA models.
This complements existing Ollama support for local inference.

Usage: ccs llamacpp (requires llama.cpp server on port 8080)

Closes #690
---
 config/base-llamacpp.settings.json   | 10 ++++++++++
 src/api/services/provider-presets.ts | 12 ++++++++++++
 src/commands/help-command.ts         |  1 +
 ui/bun.lock                          |  1 +
 ui/src/lib/provider-presets.ts       | 15 +++++++++++++++
 5 files changed, 39 insertions(+)
 create mode 100644 config/base-llamacpp.settings.json

diff --git a/config/base-llamacpp.settings.json b/config/base-llamacpp.settings.json
new file mode 100644
index 00000000..48de05dc
--- /dev/null
+++ b/config/base-llamacpp.settings.json
@@ -0,0 +1,10 @@
+{
+  "env": {
+    "ANTHROPIC_BASE_URL": "http://127.0.0.1:8080",
+    "ANTHROPIC_AUTH_TOKEN": "llamacpp",
+    "ANTHROPIC_MODEL": "llama3-8b",
+    "ANTHROPIC_DEFAULT_OPUS_MODEL": "llama3-70b",
+    "ANTHROPIC_DEFAULT_SONNET_MODEL": "llama3-8b",
+    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "llama3-2b"
+  }
+}
diff --git a/src/api/services/provider-presets.ts b/src/api/services/provider-presets.ts
index 510246e4..97760b24 100644
--- a/src/api/services/provider-presets.ts
+++ b/src/api/services/provider-presets.ts
@@ -58,6 +58,18 @@ export const PROVIDER_PRESETS: ProviderPreset[] = [
     category: 'recommended',
     requiresApiKey: false,
   },
+  {
+    id: 'llamacpp',
+    name: 'llama.cpp (Local)',
+    description: 'Local inference via llama.cpp (LLaMA models)',
+    baseUrl: 'http://127.0.0.1:8080',
+    defaultProfileName: 'llamacpp',
+    defaultModel: 'llama3-8b',
+    apiKeyPlaceholder: 'llamacpp',
+    apiKeyHint: 'Run llama.cpp server: ./server --host 0.0.0.0 --port 8080 -m model.gguf',
+    category: 'recommended',
+    requiresApiKey: false,
+  },
   // Alternative providers
   {
     id: 'glm',
diff --git a/src/commands/help-command.ts b/src/commands/help-command.ts
index ae632fb9..201849af 100644
--- a/src/commands/help-command.ts
+++ b/src/commands/help-command.ts
@@ -128,6 +128,7 @@ Run ${color('ccs config', 'command')} for web dashboard`.trim();
       ['ccs glmt', 'GLM with thinking mode'],
       ['ccs kimi', 'Kimi for Coding (API key)'],
       ['ccs ollama', 'Local Ollama (http://localhost:11434)'],
+      ['ccs llamacpp', 'Local llama.cpp (http://127.0.0.1:8080)'],
       ['ccs ollama-cloud', 'Ollama Cloud (API key required)'],
       ['', ''], // Spacer
       ['ccs api create', 'Create custom API profile'],
diff --git a/ui/bun.lock b/ui/bun.lock
index 2756da98..c2e29de1 100644
--- a/ui/bun.lock
+++ b/ui/bun.lock
@@ -1,5 +1,6 @@
 {
   "lockfileVersion": 1,
+  "configVersion": 0,
   "workspaces": {
     "": {
       "name": "ui",
diff --git a/ui/src/lib/provider-presets.ts b/ui/src/lib/provider-presets.ts
index d6d35486..1ce5274a 100644
--- a/ui/src/lib/provider-presets.ts
+++ b/ui/src/lib/provider-presets.ts
@@ -60,6 +60,21 @@ export const PROVIDER_PRESETS: ProviderPreset[] = [
     apiKeyHint: 'No API key required for local Ollama',
     category: 'recommended',
   },
+  // Recommended - llama.cpp (Local)
+  {
+    id: 'llamacpp',
+    name: 'llama.cpp (Local)',
+    description: 'Local inference via llama.cpp (LLaMA models)',
+    baseUrl: 'http://127.0.0.1:8080',
+    defaultProfileName: 'llamacpp',
+    badge: 'Local',
+    featured: true,
+    defaultModel: 'llama3-8b',
+    requiresApiKey: false,
+    apiKeyPlaceholder: 'llamacpp',
+    apiKeyHint: 'Run llama.cpp server: ./server --host 0.0.0.0 --port 8080 -m model.gguf',
+    category: 'recommended',
+  },
   // Alternative providers - GLM/GLMT/Kimi
   {
     id: 'glm',