feat(transcription): add Chat Completions API provider for audio transcription (#1130)

* feat(transcription): add Chat Completions API provider for audio transcription

The existing transcription pipeline only supports the OpenAI Whisper API
(/v1/audio/transcriptions with multipart upload). Providers like OpenRouter
expose audio transcription through the Chat Completions API instead, using
base64-encoded audio in the `input_audio` content type.

Add `ChatCompletionsTranscriptionProvider` that sends audio as base64 in
a chat completion request and extracts the transcript from the response.
Compatible with OpenRouter, OpenAI GPT-4o-audio, and any provider that
supports audio input via Chat Completions.

Config changes:
- TRANSCRIPTION_PROVIDER=chat_completions selects the new provider
- TRANSCRIPTION_API_KEY overrides provider-specific keys
- LLM_API_KEY used as fallback for chat_completions provider
- Default model per provider (whisper-1 for openai, gemini-2.0-flash for
  chat_completions)

* style: address review feedback — formatting, idiomatic patterns

- Fix rustfmt formatting for provider constructor chain
- Use or_else for resolve_api_key priority chain (Gemini review)
- Use trim_end_matches('/') instead of while loop (Gemini review)

---------

Co-authored-by: SMKRV <[email protected]>

src/config/transcription.rs

@@ -9,11 +9,15 @@ use crate::settings::Settings;
 pub struct TranscriptionConfig {
     /// Whether audio transcription is enabled.
     pub enabled: bool,
-    /// Provider: "openai" (default).
+    /// Provider: "openai" (default) or "chat_completions".
     pub provider: String,
     /// OpenAI API key (reuses OPENAI_API_KEY).
     pub openai_api_key: Option<SecretString>,
-    /// Model to use (default: "whisper-1").
+    /// Explicit transcription API key (overrides provider-specific keys).
+    pub api_key: Option<SecretString>,
+    /// LLM API key (reuses LLM_API_KEY, used as fallback for chat_completions).
+    pub llm_api_key: Option<SecretString>,
+    /// Model to use (default depends on provider).
     pub model: String,
     /// Base URL override for the transcription API.
     pub base_url: Option<String>,
@@ -25,6 +29,8 @@ impl Default for TranscriptionConfig {
             enabled: false,
             provider: "openai".to_string(),
             openai_api_key: None,
+            api_key: None,
+            llm_api_key: None,
             model: "whisper-1".to_string(),
             base_url: None,
         }
@@ -42,8 +48,15 @@ impl TranscriptionConfig {
             optional_env("TRANSCRIPTION_PROVIDER")?.unwrap_or_else(|| "openai".to_string());
 
         let openai_api_key = optional_env("OPENAI_API_KEY")?.map(SecretString::from);
+        let api_key = optional_env("TRANSCRIPTION_API_KEY")?.map(SecretString::from);
+        let llm_api_key = optional_env("LLM_API_KEY")?.map(SecretString::from);
 
-        let model = optional_env("TRANSCRIPTION_MODEL")?.unwrap_or_else(|| "whisper-1".to_string());
+        let default_model = match provider.as_str() {
+            "chat_completions" => "google/gemini-2.0-flash-001",
+            _ => "whisper-1",
+        };
+        let model =
+            optional_env("TRANSCRIPTION_MODEL")?.unwrap_or_else(|| default_model.to_string());
 
         let base_url = optional_env("TRANSCRIPTION_BASE_URL")?;
 
@@ -51,29 +64,67 @@ impl TranscriptionConfig {
             enabled,
             provider,
             openai_api_key,
+            api_key,
+            llm_api_key,
             model,
             base_url,
         })
     }
 
+    /// Resolve the API key for the configured provider.
+    ///
+    /// Priority: `TRANSCRIPTION_API_KEY` > provider-specific key.
+    fn resolve_api_key(&self) -> Option<&SecretString> {
+        self.api_key
+            .as_ref()
+            .or_else(|| match self.provider.as_str() {
+                "chat_completions" => self.llm_api_key.as_ref().or(self.openai_api_key.as_ref()),
+                _ => self.openai_api_key.as_ref(),
+            })
+    }
+
     /// Create the transcription provider if enabled and configured.
     pub fn create_provider(&self) -> Option<Box<dyn crate::transcription::TranscriptionProvider>> {
         if !self.enabled {
             return None;
         }
 
-        // Currently only OpenAI Whisper is supported; more providers can be
-        // added here with a match on self.provider.
-        let api_key = self.openai_api_key.as_ref()?;
-        tracing::info!(model = %self.model, "Audio transcription enabled via OpenAI Whisper");
+        let api_key = self.resolve_api_key()?;
 
-        let mut provider = crate::transcription::OpenAiWhisperProvider::new(api_key.clone())
-            .with_model(&self.model);
+        match self.provider.as_str() {
+            "chat_completions" => {
+                tracing::info!(
+                    model = %self.model,
+                    "Audio transcription enabled via Chat Completions API"
+                );
 
-        if let Some(ref base_url) = self.base_url {
-            provider = provider.with_base_url(base_url);
+                let mut provider = crate::transcription::ChatCompletionsTranscriptionProvider::new(
+                    api_key.clone(),
+                )
+                .with_model(&self.model);
+
+                if let Some(ref base_url) = self.base_url {
+                    provider = provider.with_base_url(base_url);
+                }
+
+                Some(Box::new(provider))
+            }
+            _ => {
+                tracing::info!(
+                    model = %self.model,
+                    "Audio transcription enabled via OpenAI Whisper"
+                );
+
+                let mut provider =
+                    crate::transcription::OpenAiWhisperProvider::new(api_key.clone())
+                        .with_model(&self.model);
+
+                if let Some(ref base_url) = self.base_url {
+                    provider = provider.with_base_url(base_url);
+                }
+
+                Some(Box::new(provider))
+            }
         }
-
-        Some(Box::new(provider))
     }
 }