@fugood/buttress-server 2.24.2 → 2.25.0-beta.9

package/README.md

@@ -157,6 +157,25 @@ Examples:
   bricks-buttress --test-caps ggml-stt --test-caps-model-id BricksDisplay/whisper-ggml:ggml-small.bin
 ```
 
+## Compatibility Endpoints (Experimental)
+
+The server can expose OpenAI- and Anthropic-compatible HTTP endpoints in addition to the native RPC. Each endpoint is opt-in via the TOML config:
+
+```toml
+[openai_compat]
+enabled = true
+# cors_allowed_origins = "*"          # Or a list of origins; defaults to disabled
+
+[anthropic_messages]
+enabled = true
+# cors_allowed_origins = ["http://localhost:3000"]
+```
+
+| Endpoint              | Config flag                          |
+| --------------------- | ------------------------------------ |
+| `/oai-compat/v1/*`    | `[openai_compat] enabled = true`     |
+| `/anthropic-messages` | `[anthropic_messages] enabled = true` |
+
 ## Session State Cache
 
 The server supports session state caching for ggml-llm generators, which saves KV cache state to disk after completions. This enables:

package/config/sample.toml

@@ -11,15 +11,24 @@
 # HF_TOKEN = "your_huggingface_token_here"
 # CUDA_VISIBLE_DEVICES = "0"
 
+[autodiscover]
+enabled = true
+
 [server]
 port = 2080
 log_level = "info"
 # max_body_size = "100MB"  # Supports string (e.g., "100MB", "1GB") or number in bytes
 
 [openai_compat]
+enabled = true
 # cors_allowed_origins = ["http://localhost:3000", "https://example.com"]  # Restrict to specific origins
 # cors_allowed_origins = "*"  # Allow all origins (default)
 
+[anthropic_messages]
+enabled = true
+# cors_allowed_origins = ["http://localhost:3000", "https://example.com"]
+# cors_allowed_origins = "*"
+
 [runtime]
 cache_dir = "./.buttress-cache"
 # huggingface_token = "hf_xx"

package/lib/index.d.mts

@@ -229,9 +229,11 @@ type GeneratorConfig = {
 type GlobalConfig = {
   runtime?: RuntimeConfig;
   openai_compat?: {
+    enabled?: boolean;
     cors_allowed_origins?: string | string[];
   };
   anthropic_messages?: {
+    enabled?: boolean;
     cors_allowed_origins?: string | string[];
   };
 } & Record<string, any>;
@@ -277,18 +279,28 @@ type Config = {
   generators: GeneratorConfig[];
 };
 type GeneratorInfo = {
-  type: GeneratorType;
+  type: GeneratorType; /** Performance score 0–100 from buttress-hardware-guardrails. */
+  score?: number; /** Whether the host has an accelerator (GPU/Metal/etc) for this backend. */
+  hasGpu?: boolean; /** Usable memory in bytes for this backend (GPU when present, else CPU). */
+  usableBytes?: number;
 } & Record<string, any>;
 type ServerInfo = {
   id: string;
   name: string;
+  version: string;
   address: string;
   port: number;
   url: string;
   generators: GeneratorInfo[];
   authentication: {
     required: boolean;
-    type: string;
+    type: string; /** Issuer key id (when type === 'workspace-jwt'). */
+    kid?: string; /** True when buttress is paired with a workspace. */
+    bound?: boolean;
+  }; /** Workspace identity (only present when paired). */
+  workspace?: {
+    id: string;
+    name?: string;
   };
 };
 //#endregion