feat(wip): add support for ReSpeaker XVF3800

main/CMakeLists.txt

@@ -21,10 +21,11 @@ idf_component_register(
         "tools/tool_get_time.c"
         "tools/tool_files.c"
         "skills/skill_loader.c"
+        "voice/voice_channel.c"
     INCLUDE_DIRS
         "."
     REQUIRES
         nvs_flash esp_wifi esp_netif esp_http_client esp_http_server
         esp_https_ota esp_event json spiffs console vfs app_update esp-tls
-        esp_timer esp_websocket_client
+        esp_timer esp_websocket_client driver
 )

main/agent/agent_loop.c

@@ -86,6 +86,30 @@ static void append_turn_context_prompt(char *prompt, size_t size, const mimi_msg
     if (n < 0 || (size_t)n >= (size - off)) {
         prompt[size - 1] = '\0';
     }
+
+    if (msg->channel[0] && strcmp(msg->channel, MIMI_CHAN_VOICE) == 0) {
+        off = strnlen(prompt, size - 1);
+        if (off >= size - 1) {
+            return;
+        }
+
+        n = snprintf(
+            prompt + off, size - off,
+            "\n## Voice Output Constraints\n"
+            "This reply will be converted to speech (TTS) and played on a small speaker.\n"
+            "- Use English, natural spoken style.\n"
+            "- Keep it short: keep playback within ~%d seconds.\n"
+            "- Structure: at most 2 sentences + 1 short follow-up question.\n"
+            "- Length: <= %d characters total.\n"
+            "- No markdown, no lists, no code blocks, no URLs.\n"
+            "- Avoid long explanations; if the answer is long, give a 1–2 sentence summary and ask if the user wants more.\n",
+            (int)MIMI_VOICE_TTS_MAX_SECONDS,
+            (int)MIMI_VOICE_LLM_MAX_CHARS);
+
+        if (n < 0 || (size_t)n >= (size - off)) {
+            prompt[size - 1] = '\0';
+        }
+    }
 }
 
 static char *patch_tool_input_with_context(const llm_tool_call_t *call, const mimi_msg_t *msg)
@@ -218,7 +242,7 @@ static void agent_loop_task(void *arg)
         while (iteration < MIMI_AGENT_MAX_TOOL_ITER) {
             /* Send "working" indicator before each API call */
 #if MIMI_AGENT_SEND_WORKING_STATUS
-            if (!sent_working_status && strcmp(msg.channel, MIMI_CHAN_SYSTEM) != 0) {
+            if (!sent_working_status && strcmp(msg.channel, MIMI_CHAN_SYSTEM) != 0 && strcmp(msg.channel, MIMI_CHAN_VOICE) != 0) {
                 mimi_msg_t status = {0};
                 strncpy(status.channel, msg.channel, sizeof(status.channel) - 1);
                 strncpy(status.chat_id, msg.chat_id, sizeof(status.chat_id) - 1);

main/bus/message_bus.h

@@ -10,6 +10,7 @@
 #define MIMI_CHAN_WEBSOCKET  "websocket"
 #define MIMI_CHAN_CLI        "cli"
 #define MIMI_CHAN_SYSTEM     "system"
+#define MIMI_CHAN_VOICE      "voice"
 
 /* Message types on the bus */
 typedef struct {

main/cli/serial_cli.c

@@ -123,6 +123,12 @@ static struct {
     struct arg_end *end;
 } api_key_args;
 
+/* --- set_api_base command --- */
+static struct {
+    struct arg_str *base;
+    struct arg_end *end;
+} api_base_args;
+
 static int cmd_set_api_key(int argc, char **argv)
 {
     int nerrors = arg_parse(argc, argv, (void **)&api_key_args);
@@ -135,6 +141,18 @@ static int cmd_set_api_key(int argc, char **argv)
     return 0;
 }
 
+static int cmd_set_api_base(int argc, char **argv)
+{
+    int nerrors = arg_parse(argc, argv, (void **)&api_base_args);
+    if (nerrors != 0) {
+        arg_print_errors(stderr, api_base_args.end, argv[0]);
+        return 1;
+    }
+    llm_set_api_base(api_base_args.base->sval[0]);
+    printf("API base set.\n");
+    return 0;
+}
+
 /* --- set_model command --- */
 static struct {
     struct arg_str *model;
@@ -535,6 +553,7 @@ static int cmd_config_show(int argc, char **argv)
     print_config("WiFi Pass",  MIMI_NVS_WIFI,   MIMI_NVS_KEY_PASS,     MIMI_SECRET_WIFI_PASS,  true);
     print_config("TG Token",   MIMI_NVS_TG,     MIMI_NVS_KEY_TG_TOKEN, MIMI_SECRET_TG_TOKEN,   true);
     print_config("API Key",    MIMI_NVS_LLM,    MIMI_NVS_KEY_API_KEY,  MIMI_SECRET_API_KEY,    true);
+    print_config("API Base",   MIMI_NVS_LLM,    MIMI_NVS_KEY_API_BASE, MIMI_SECRET_API_BASE,   false);
     print_config("Model",      MIMI_NVS_LLM,    MIMI_NVS_KEY_MODEL,    MIMI_SECRET_MODEL,      false);
     print_config("Provider",   MIMI_NVS_LLM,    MIMI_NVS_KEY_PROVIDER, MIMI_SECRET_MODEL_PROVIDER, false);
     print_config("Proxy Host", MIMI_NVS_PROXY,  MIMI_NVS_KEY_PROXY_HOST, MIMI_SECRET_PROXY_HOST, false);
@@ -849,6 +868,17 @@ esp_err_t serial_cli_init(void)
     };
     esp_console_cmd_register(&api_key_cmd);
 
+    /* set_api_base */
+    api_base_args.base = arg_str1(NULL, NULL, "<base>", "LLM API base (http(s)://host[:port][/path])");
+    api_base_args.end = arg_end(1);
+    esp_console_cmd_t api_base_cmd = {
+        .command = "set_api_base",
+        .help = "Set LLM API base (e.g. https://api.anthropic.com/v1)",
+        .func = &cmd_set_api_base,
+        .argtable = &api_base_args,
+    };
+    esp_console_cmd_register(&api_base_cmd);
+
     /* set_model */
     model_args.model = arg_str1(NULL, NULL, "<model>", "Model identifier");
     model_args.end = arg_end(1);
@@ -1054,4 +1084,4 @@ esp_err_t serial_cli_init(void)
     ESP_LOGI(TAG, "Serial CLI started");
 
     return ESP_OK;
-}
+}