lakehouse/crates/aibridge/src/client.rs

use reqwest::Client;
use serde::{Deserialize, Serialize};
use std::time::Duration;

/// HTTP client for the Python AI sidecar.
#[derive(Clone)]
pub struct AiClient {
    client: Client,
    base_url: String,
}

// -- Request/Response types --

#[derive(Serialize, Deserialize)]
pub struct EmbedRequest {
    pub texts: Vec<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub model: Option<String>,
}

#[derive(Deserialize, Serialize, Clone)]
pub struct EmbedResponse {
    pub embeddings: Vec<Vec<f64>>,
    pub model: String,
    pub dimensions: usize,
}

#[derive(Clone, Serialize, Deserialize)]
pub struct GenerateRequest {
    pub prompt: String,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub model: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub system: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub temperature: Option<f64>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_tokens: Option<u32>,
    /// Phase 21 — per-call opt-out of hidden reasoning. Thinking models
    /// (qwen3.5, gpt-oss, etc) burn tokens on reasoning before the
    /// visible response starts; setting this to `false` on hot-path
    /// JSON emitters avoids empty returns when the budget is tight.
    /// Sidecar forwards this to Ollama's `think` parameter; if the
    /// sidecar drops an unknown field the request still succeeds.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub think: Option<bool>,
}

#[derive(Deserialize, Serialize, Clone)]
pub struct GenerateResponse {
    pub text: String,
    pub model: String,
    pub tokens_evaluated: Option<u64>,
    pub tokens_generated: Option<u64>,
}

#[derive(Serialize, Deserialize)]
pub struct RerankRequest {
    pub query: String,
    pub documents: Vec<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub model: Option<String>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub top_k: Option<usize>,
}

#[derive(Deserialize, Serialize, Clone)]
pub struct ScoredDocument {
    pub index: usize,
    pub text: String,
    pub score: f64,
}

#[derive(Deserialize, Serialize, Clone)]
pub struct RerankResponse {
    pub results: Vec<ScoredDocument>,
    pub model: String,
}

impl AiClient {
    pub fn new(base_url: &str) -> Self {
        let client = Client::builder()
            .timeout(Duration::from_secs(120))
            .build()
            .expect("failed to build HTTP client");
        Self {
            client,
            base_url: base_url.trim_end_matches('/').to_string(),
        }
    }

    pub async fn health(&self) -> Result<serde_json::Value, String> {
        let resp = self.client
            .get(format!("{}/health", self.base_url))
            .send()
            .await
            .map_err(|e| format!("sidecar unreachable: {e}"))?;
        resp.json().await.map_err(|e| format!("invalid response: {e}"))
    }

    pub async fn embed(&self, req: EmbedRequest) -> Result<EmbedResponse, String> {
        let resp = self.client
            .post(format!("{}/embed", self.base_url))
            .json(&req)
            .send()
            .await
            .map_err(|e| format!("embed request failed: {e}"))?;

        if !resp.status().is_success() {
            let text = resp.text().await.unwrap_or_default();
            return Err(format!("embed error ({}): {text}", text.len()));
        }
        resp.json().await.map_err(|e| format!("embed parse error: {e}"))
    }

    pub async fn generate(&self, req: GenerateRequest) -> Result<GenerateResponse, String> {
        let resp = self.client
            .post(format!("{}/generate", self.base_url))
            .json(&req)
            .send()
            .await
            .map_err(|e| format!("generate request failed: {e}"))?;

        if !resp.status().is_success() {
            let text = resp.text().await.unwrap_or_default();
            return Err(format!("generate error: {text}"));
        }
        resp.json().await.map_err(|e| format!("generate parse error: {e}"))
    }

    pub async fn rerank(&self, req: RerankRequest) -> Result<RerankResponse, String> {
        let resp = self.client
            .post(format!("{}/rerank", self.base_url))
            .json(&req)
            .send()
            .await
            .map_err(|e| format!("rerank request failed: {e}"))?;

        if !resp.status().is_success() {
            let text = resp.text().await.unwrap_or_default();
            return Err(format!("rerank error: {text}"));
        }
        resp.json().await.map_err(|e| format!("rerank parse error: {e}"))
    }

    /// Force Ollama to unload the named model from VRAM (keep_alive=0).
    /// Used for predictable profile swaps — without this, Ollama holds a
    /// model for its configured TTL (default 5min) and the previous
    /// profile's model can linger in VRAM next to the new one.
    pub async fn unload_model(&self, model: &str) -> Result<serde_json::Value, String> {
        let resp = self.client
            .post(format!("{}/admin/unload", self.base_url))
            .json(&serde_json::json!({ "model": model }))
            .send().await
            .map_err(|e| format!("unload request failed: {e}"))?;
        if !resp.status().is_success() {
            let text = resp.text().await.unwrap_or_default();
            return Err(format!("unload error: {text}"));
        }
        resp.json().await.map_err(|e| format!("unload parse error: {e}"))
    }

    /// Ask Ollama to load the named model into VRAM proactively. Makes
    /// the first real request after profile activation fast (no cold-load
    /// latency).
    pub async fn preload_model(&self, model: &str) -> Result<serde_json::Value, String> {
        let resp = self.client
            .post(format!("{}/admin/preload", self.base_url))
            .json(&serde_json::json!({ "model": model }))
            .send().await
            .map_err(|e| format!("preload request failed: {e}"))?;
        if !resp.status().is_success() {
            let text = resp.text().await.unwrap_or_default();
            return Err(format!("preload error: {text}"));
        }
        resp.json().await.map_err(|e| format!("preload parse error: {e}"))
    }

    /// GPU + loaded-model snapshot from the sidecar. Combines nvidia-smi
    /// output (if available) with Ollama's /api/ps.
    pub async fn vram_snapshot(&self) -> Result<serde_json::Value, String> {
        let resp = self.client
            .get(format!("{}/admin/vram", self.base_url))
            .send().await
            .map_err(|e| format!("vram request failed: {e}"))?;
        resp.json().await.map_err(|e| format!("vram parse error: {e}"))
    }
}