root e27a17e950 Phase 39: Provider Adapter Refactor
- ProviderAdapter trait with chat(), embed(), unload(), health()
- OllamaAdapter wrapping existing AiClient
- OpenRouterAdapter for openrouter.ai API integration
- provider_key() routing by model prefix (openrouter/*, etc)
2026-04-23 02:24:15 -05:00

150 lines
4.3 KiB
Rust

use async_trait::async_trait;
use reqwest::Client;
use serde::{Deserialize, Serialize};
use std::time::Duration;
use crate::client::{GenerateRequest, GenerateResponse, EmbedRequest, EmbedResponse};
use crate::provider::ProviderAdapter;
pub struct OpenRouterAdapter {
client: Client,
base_url: String,
api_key: String,
default_model: String,
}
#[derive(Serialize)]
struct OpenRouterChatRequest {
model: String,
messages: Vec<OpenRouterMessage>,
temperature: Option<f64>,
max_tokens: Option<u32>,
}
#[derive(Serialize)]
struct OpenRouterMessage {
role: String,
content: String,
}
#[derive(Deserialize)]
struct OpenRouterChatResponse {
choices: Vec<OpenRouterChoice>,
usage: OpenRouterUsage,
model: String,
}
#[derive(Deserialize)]
struct OpenRouterChoice {
message: OpenRouterMessageOut,
}
#[derive(Deserialize)]
struct OpenRouterMessageOut {
role: String,
content: String,
}
#[derive(Deserialize)]
struct OpenRouterUsage {
prompt_tokens: Option<u32>,
completion_tokens: Option<u32>,
total_tokens: Option<u32>,
}
impl OpenRouterAdapter {
pub fn new(base_url: &str, api_key: String, default_model: &str) -> Self {
let client = Client::builder()
.timeout(Duration::from_secs(180))
.build()
.expect("failed to build HTTP client");
Self {
client,
base_url: base_url.trim_end_matches('/').to_string(),
api_key,
default_model: default_model.to_string(),
}
}
fn chat_model(&self, model: &str) -> String {
// Strip "openrouter/" prefix if present
let m = model.trim_start_matches("openrouter/");
if m.is_empty() || m == model {
self.default_model.clone()
} else {
m.to_string()
}
}
fn to_openrouter_messages(req: &GenerateRequest) -> Vec<OpenRouterMessage> {
let mut out = vec![];
if let Some(sys) = &req.system {
out.push(OpenRouterMessage { role: "system".into(), content: sys.clone() });
}
out.push(OpenRouterMessage {
role: "user".into(),
content: req.prompt.clone(),
});
out
}
}
#[async_trait]
impl ProviderAdapter for OpenRouterAdapter {
fn name(&self) -> &str {
"openrouter"
}
async fn chat(&self, req: GenerateRequest) -> Result<GenerateResponse, String> {
let model = self.chat_model(req.model.as_deref().unwrap_or(""));
let or_req = OpenRouterChatRequest {
model: model.clone(),
messages: OpenRouterAdapter::to_openrouter_messages(&req),
temperature: req.temperature,
max_tokens: req.max_tokens,
};
let resp = self.client
.post(format!("{}/chat/completions", self.base_url))
.header("Authorization", format!("Bearer {}", self.api_key))
.header("Content-Type", "application/json")
.json(&or_req)
.send()
.await
.map_err(|e| format!("openrouter request failed: {e}"))?;
let status = resp.status();
let body = resp.text().await.unwrap_or_default();
if !status.is_success() {
return Err(format!("openrouter error ({}): {}", status, body));
}
let or_resp: OpenRouterChatResponse = serde_json::from_str(&body)
.map_err(|e| format!("openrouter parse error: {e}"))?;
let choice = or_resp.choices.into_iter().next()
.ok_or("no completion choice returned")?;
let usage = or_resp.usage;
Ok(GenerateResponse {
text: choice.message.content,
model: or_resp.model,
tokens_evaluated: usage.prompt_tokens.map(|n| n as u64),
tokens_generated: usage.completion_tokens.map(|n| n as u64),
})
}
async fn embed(&self, _req: EmbedRequest) -> Result<EmbedResponse, String> {
Err("openrouter: embed not implemented".into())
}
async fn health(&self) -> Result<serde_json::Value, String> {
// OpenRouter doesn't have a dedicated health endpoint,
// so we just return a healthy response if the client works.
Ok(serde_json::json!({
"status": "ok",
"provider": "openrouter",
}))
}
}