Add native Anthropic API backend support

PROXY-API-TODO.md

@@ -4,11 +4,11 @@ Future work for Vimini's proxy/API backend support.
 
 ## Anthropic API support
 
-- Add a native Anthropic backend in addition to the current OpenAI-compatible proxy backend.
-- Map Vimini's generic chat, streaming, tools, and tool-response abstractions to Anthropic's Messages API.
-- Handle Anthropic-specific streaming events and content block formats.
-- Add global config support for `api: "anthropic"`, including model defaults and API key file loading.
-- Add tests for model listing behavior, streaming responses, tool calls, and error handling.
+- [x] Add a native Anthropic backend in addition to the current OpenAI-compatible proxy backend.
+- [x] Map Vimini's generic chat, streaming, tools, and tool-response abstractions to Anthropic's Messages API.
+- [x] Handle Anthropic-specific streaming events and content block formats.
+- [x] Add global config support for `api: "anthropic"`, including model defaults and API key file loading.
+- [x] Add tests for model listing behavior, streaming responses, tool calls, and error handling.
 
 ## OpenAI Files API for context files
 

README.md

@@ -179,7 +179,7 @@ customizations.
     }
     ```
 
-    You can configure multiple backends (Google Gemini via `"api": "genai"`, or OpenAI-compatible proxies and endpoints via `"api": "openai"`).
+    You can configure multiple backends (Google Gemini via `"api": "genai"`, OpenAI-compatible proxies and endpoints via `"api": "openai"`, or Anthropic via `"api": "anthropic"`).
 
     Backends that require credentials specify an `api_key_file`; Gemini requires
     one, while OpenAI-compatible local/proxy endpoints may omit it unless
@@ -194,7 +194,7 @@ Opens an interactive configuration editor in a new split window to configure glo
 **How to use the global configuration manager:**
 *   Move the cursor to any configuration option or backend line.
 *   **`<Enter>` or `e`**: Edits the selected value. On `active_backend`, enter one of the configured backend names. On a backend header, rename the backend. Under `UI PREFERENCES`, customize colors (e.g. `thinking_color`, `prompt_color`, `waiting_color`, `service_color`, `error_color`, `prompt_hint_color`).
-*   **`a`**: Adds a new backend and prompts for API type, default model, API key file, and base URL for OpenAI-compatible backends.
+*   **`a`**: Adds a new backend and prompts for API type, default model, API key file, and base URL for OpenAI-compatible or Anthropic backends.
 *   **`d`**: Clears the selected backend field, deletes a backend after confirmation, or resets a UI preference back to default. The last backend cannot be deleted.
 *   **`r`**: Resets all global configuration options to their last saved state.
 *   **`q`**: Closes the configuration window. If modifications were made, a confirmation prompt asks whether to save changes permanently to `~/.var/vimini/config.json`.

python3/vimini/common/backends/__init__.py

@@ -18,6 +18,12 @@
     convert_schema_to_openai,
     convert_tools_to_openai,
 )
+from vimini.common.backends.anthropic_backend import (
+    AnthropicBackend,
+    AnthropicChatSession,
+    convert_schema_to_anthropic,
+    convert_tools_to_anthropic,
+)
 from vimini.common.config import (
     load_global_config,
     get_active_backend,
@@ -85,6 +91,13 @@ def get_backend(
             base_url=backend_cfg.get("base_url"),
             headers=backend_cfg.get("headers"),
         )
+    elif api == "anthropic":
+        return AnthropicBackend(
+            config=backend_cfg,
+            api_key=api_key,
+            base_url=backend_cfg.get("base_url"),
+            headers=backend_cfg.get("headers"),
+        )
 
     raise ValueError(f"Unsupported API protocol '{api}' for backend '{backend_name}'.")
 
@@ -123,8 +136,12 @@ def get_client(
     "GenAIChatSession",
     "ProxyBackend",
     "ProxyChatSession",
+    "AnthropicBackend",
+    "AnthropicChatSession",
     "convert_schema_to_openai",
     "convert_tools_to_openai",
+    "convert_schema_to_anthropic",
+    "convert_tools_to_anthropic",
     "get_backend",
     "get_client",
 ]