// api/ — LLM API client (OpenAI-compatible)
//
// Works with any provider that implements the OpenAI chat completions
// API: OpenRouter, vLLM, llama.cpp, Fireworks, Together, etc.
//
// Diagnostics: anomalies always logged to debug panel.
// Set POC_DEBUG=1 for verbose per-turn logging.

pub mod http;
pub(crate) mod parsing;
mod types;
mod openai;

// Public API types — used outside agent::api
pub use types::{Message, MessageContent, ContentPart, ImageUrl, Role, ToolCall, FunctionCall, Usage};

use anyhow::Result;
use std::time::{Duration, Instant};

use self::http::{HttpClient, HttpResponse};

use tokio::sync::mpsc;

use crate::agent::tools::{self as agent_tools, summarize_args, ActiveToolCall};

/// A JoinHandle that aborts its task when dropped.
pub(crate) struct AbortOnDrop(tokio::task::JoinHandle<()>);

impl Drop for AbortOnDrop {
    fn drop(&mut self) {
        self.0.abort();
    }
}

/// Sampling parameters for model generation.
#[derive(Clone, Copy)]
pub(crate) struct SamplingParams {
    pub temperature: f32,
    pub top_p: f32,
    pub top_k: u32,
}

// ─────────────────────────────────────────────────────────────
//  Stream events — yielded by backends, consumed by the runner
// ─────────────────────────────────────────────────────────────

/// Build the tools JSON string from a slice of Tools.
fn tools_to_json_str(tools: &[agent_tools::Tool]) -> String {
    let inner: Vec<String> = tools.iter().map(|t| t.to_json()).collect();
    format!("[{}]", inner.join(","))
}

/// One token from the streaming completions API.
pub(crate) enum StreamToken {
    Token { text: String, id: u32 },
    Done { usage: Option<Usage> },
    Error(String),
}

#[derive(Clone)]
pub struct ApiClient {
    client: HttpClient,
    api_key: String,
    pub model: String,
    base_url: String,
}

impl ApiClient {
    pub fn new(base_url: &str, api_key: &str, model: &str) -> Self {
        let client = HttpClient::builder()
            .connect_timeout(Duration::from_secs(30))
            .timeout(Duration::from_secs(600))
            .build();

        Self {
            client,
            api_key: api_key.to_string(),
            model: model.to_string(),
            base_url: base_url.trim_end_matches('/').to_string(),
        }
    }

    /// Stream a completion with raw token IDs.
    /// Returns (text, token_id) per token via channel.
    pub(crate) fn stream_completion(
        &self,
        prompt_tokens: &[u32],
        sampling: SamplingParams,
        priority: Option<i32>,
    ) -> (mpsc::UnboundedReceiver<StreamToken>, AbortOnDrop) {
        let (tx, rx) = mpsc::unbounded_channel();
        let client = self.client.clone();
        let api_key = self.api_key.clone();
        let model = self.model.clone();
        let prompt_tokens = prompt_tokens.to_vec();
        let base_url = self.base_url.clone();

        let handle = tokio::spawn(async move {
            let result = openai::stream_completions(
                &client, &base_url, &api_key, &model,
                &prompt_tokens, &tx, sampling, priority,
            ).await;
            if let Err(e) = result {
                let _ = tx.send(StreamToken::Error(e.to_string()));
            }
        });

        (rx, AbortOnDrop(handle))
    }

    pub fn base_url(&self) -> &str { &self.base_url }
    pub fn api_key(&self) -> &str { &self.api_key }

}

/// Send an HTTP request and check for errors. Shared by both backends.
pub(crate) async fn send_and_check(
    client: &HttpClient,
    url: &str,
    body: &impl serde::Serialize,
    auth_header: (&str, &str),
    extra_headers: &[(&str, &str)],
    debug_label: &str,
    request_json: Option<&str>,
) -> Result<HttpResponse> {
    let debug = std::env::var("POC_DEBUG").is_ok();
    let start = Instant::now();

    if debug {
        let payload_size = serde_json::to_string(body)
            .map(|s| s.len())
            .unwrap_or(0);
        dbglog!(
            "request: {}K payload, {}",
            payload_size / 1024, debug_label,
        );
    }

    let mut headers: Vec<(&str, &str)> = Vec::with_capacity(extra_headers.len() + 1);
    headers.push(auth_header);
    headers.extend_from_slice(extra_headers);

    let response = client
        .send_json("POST", url, &headers, body)
        .await
        .map_err(|e| {
            let msg = e.to_string();
            let cause = if msg.contains("connect timeout") || msg.contains("TCP connect") {
                "connection refused"
            } else if msg.contains("request timeout") {
                "request timed out"
            } else {
                "request error"
            };
            anyhow::anyhow!("{} ({}): {}", cause, url, msg)
        })?;

    let status = response.status();
    let elapsed = start.elapsed();

    if debug {
        for name in [
            "x-ratelimit-remaining",
            "x-ratelimit-limit",
            "x-request-id",
        ] {
            if let Some(val) = response.header(name) {
                dbglog!("header {}: {}", name, val);
            }
        }
    }

    if !status.is_success() {
        let body = response.text().await.unwrap_or_default();
        dbglog!(
            "HTTP {} after {:.1}s ({}): {}",
            status,
            elapsed.as_secs_f64(),
            url,
            &body[..body.len().min(500)]
        );
        if let Some(json) = request_json {
            let log_dir = dirs::home_dir()
                .unwrap_or_default()
                .join(".consciousness/logs/failed-requests");
            let _ = std::fs::create_dir_all(&log_dir);
            let ts = chrono::Local::now().format("%Y%m%dT%H%M%S");
            let path = log_dir.join(format!("{}.json", ts));
            if std::fs::write(&path, json).is_ok() {
                dbglog!(
                    "saved failed request to {} (HTTP {})", path.display(), status
                );
            }
        }
        anyhow::bail!("HTTP {} ({}): {}", status, url, &body[..body.len().min(1000)]);
    }

    if debug {
        dbglog!(
            "connected in {:.1}s (HTTP {})",
            elapsed.as_secs_f64(),
            status.as_u16()
        );
    }

    Ok(response)
}

/// SSE stream reader. Handles the generic SSE plumbing shared by both
/// backends: chunk reading with timeout, line buffering, `data:` prefix
/// stripping, `[DONE]` detection, JSON parsing, and parse error diagnostics.
/// Yields parsed events as serde_json::Value — each backend handles its
/// own event types.
pub(crate) struct SseReader {
    line_buf: String,
    chunk_timeout: Duration,
    pub stream_start: Instant,
    pub chunks_received: u64,
    pub sse_lines_parsed: u64,
    pub sse_parse_errors: u64,
    debug: bool,
    done: bool,
    /// Serialized request payload — saved to disk on errors for replay debugging.
    pub(crate) request_json: Option<String>,
}

impl SseReader {
    pub(crate) fn new() -> Self {
        Self {
            line_buf: String::new(),
            chunk_timeout: Duration::from_secs(crate::config::get().api_stream_timeout_secs),
            stream_start: Instant::now(),
            chunks_received: 0,
            sse_lines_parsed: 0,
            sse_parse_errors: 0,
            debug: std::env::var("POC_DEBUG").is_ok(),
            done: false,
            request_json: None,
        }
    }

    /// Attach the serialized request payload for error diagnostics.
    /// Save the request payload to disk for replay debugging.
    fn save_failed_request(&self, reason: &str) {
        let Some(ref json) = self.request_json else { return };
        let log_dir = dirs::home_dir()
            .unwrap_or_default()
            .join(".consciousness/logs/failed-requests");
        let _ = std::fs::create_dir_all(&log_dir);
        let ts = chrono::Local::now().format("%Y%m%dT%H%M%S");
        let path = log_dir.join(format!("{}.json", ts));
        if std::fs::write(&path, json).is_ok() {
            dbglog!(
                "saved failed request to {} ({})", path.display(), reason
            );
        }
    }

    /// Read the next SSE event from the response stream.
    /// Returns Ok(Some(value)) for each parsed data line,
    /// Ok(None) when the stream ends or [DONE] is received.
    pub(crate) async fn next_event(
        &mut self,
        response: &mut HttpResponse,
    ) -> Result<Option<serde_json::Value>> {
        loop {
            // Drain complete lines from the buffer before reading more chunks
            while let Some(newline_pos) = self.line_buf.find('\n') {
                let line = self.line_buf[..newline_pos].trim().to_string();
                self.line_buf = self.line_buf[newline_pos + 1..].to_string();

                if line == "data: [DONE]" {
                    self.done = true;
                    return Ok(None);
                }
                if line.is_empty()
                    || line.starts_with("event: ")
                    || !line.starts_with("data: ")
                {
                    continue;
                }

                let json_str = &line[6..];
                self.sse_lines_parsed += 1;

                match serde_json::from_str(json_str) {
                    Ok(v) => return Ok(Some(v)),
                    Err(e) => {
                        self.sse_parse_errors += 1;
                        if self.sse_parse_errors == 1 || self.debug {
                            let preview = if json_str.len() > 200 {
                                format!("{}...", &json_str[..200])
                            } else {
                                json_str.to_string()
                            };
                            dbglog!(
                                "SSE parse error (#{}) {}: {}",
                                self.sse_parse_errors, e, preview
                            );
                        }
                        continue;
                    }
                }
            }

            if self.done {
                return Ok(None);
            }

            // Read more data from the response stream
            match tokio::time::timeout(self.chunk_timeout, response.chunk()).await {
                Ok(Ok(Some(chunk))) => {
                    self.chunks_received += 1;
                    self.line_buf.push_str(&String::from_utf8_lossy(&chunk));
                }
                Ok(Ok(None)) => return Ok(None),
                Ok(Err(e)) => {
                    let buf_preview = if self.line_buf.is_empty() {
                        "(empty)".to_string()
                    } else {
                        let n = self.line_buf.len().min(500);
                        format!("{}B: {}", self.line_buf.len(), &self.line_buf[..n])
                    };
                    let msg = format!(
                        "stream error after {} chunks, {:.1}s, {} sse lines: {} | buf: {}",
                        self.chunks_received,
                        self.stream_start.elapsed().as_secs_f64(),
                        self.sse_lines_parsed,
                        e, buf_preview,
                    );
                    dbglog!("{}", msg);
                    self.save_failed_request(&msg);
                    return Err(e.into());
                }
                Err(_) => {
                    let buf_preview = if self.line_buf.is_empty() {
                        "(empty)".to_string()
                    } else {
                        let n = self.line_buf.len().min(500);
                        format!("{}B: {}", self.line_buf.len(), &self.line_buf[..n])
                    };
                    let msg = format!(
                        "stream timeout: {}s, {} chunks, {} sse lines, {:.1}s elapsed | buf: {}",
                        self.chunk_timeout.as_secs(),
                        self.chunks_received,
                        self.sse_lines_parsed,
                        self.stream_start.elapsed().as_secs_f64(),
                        buf_preview,
                    );
                    dbglog!("{}", msg);
                    self.save_failed_request(&msg);
                    anyhow::bail!(
                        "stream timeout: no data for {}s ({} chunks received)",
                        self.chunk_timeout.as_secs(),
                        self.chunks_received
                    );
                }
            }
        }
    }
}

/// Build a response Message from accumulated content and tool calls.
/// Shared by both backends — the wire format differs but the internal
/// representation is the same.
///
/// If no structured tool calls came from the API but the content
/// contains leaked tool call XML (e.g. `<tool_call>...</tool_call>`
/// from models that emit tool calls as text), parse them out and
/// promote them to structured tool_calls. This way all consumers
/// see tool calls uniformly regardless of backend.
pub(crate) fn build_response_message(
    content: String,
    tool_calls: Vec<ToolCall>,
) -> Message {
    // If the API returned structured tool calls, use them as-is.
    if !tool_calls.is_empty() {
        return Message {
            role: Role::Assistant,
            content: if content.is_empty() { None }
                     else { Some(MessageContent::Text(content)) },
            tool_calls: Some(tool_calls),
            tool_call_id: None,
            name: None,
            timestamp: None,
        };
    }

    // Check for leaked tool calls in content text.
    let leaked = parsing::parse_leaked_tool_calls(&content);
    if !leaked.is_empty() {
        let cleaned = parsing::strip_leaked_artifacts(&content);
        return Message {
            role: Role::Assistant,
            content: if cleaned.trim().is_empty() { None }
                     else { Some(MessageContent::Text(cleaned)) },
            tool_calls: Some(leaked),
            tool_call_id: None,
            name: None,
            timestamp: None,
        };
    }

    Message {
        role: Role::Assistant,
        content: if content.is_empty() { None }
                 else { Some(MessageContent::Text(content)) },
        tool_calls: None,
        tool_call_id: None,
        name: None,
        timestamp: None,
    }
}

/// Log stream diagnostics. Shared by both backends.
pub(crate) fn log_diagnostics(
    content_len: usize,
    tool_count: usize,
    reasoning_chars: usize,
    reasoning_effort: &str,
    finish_reason: &Option<String>,
    chunks_received: u64,
    sse_lines_parsed: u64,
    sse_parse_errors: u64,
    empty_deltas: u64,
    total_elapsed: Duration,
    first_content_at: Option<Duration>,
    usage: &Option<Usage>,
    tools: &[ToolCall],
) {
    let debug = std::env::var("POC_DEBUG").is_ok();

    if reasoning_chars > 0 && reasoning_effort == "none" {
        dbglog!(
            "note: {} chars leaked reasoning (suppressed from display)",
            reasoning_chars
        );
    }
    if content_len == 0 && tool_count == 0 {
        dbglog!(
            "WARNING: empty response (finish: {:?}, chunks: {}, reasoning: {}, \
             parse_errors: {}, empty_deltas: {}, {:.1}s)",
            finish_reason, chunks_received, reasoning_chars,
            sse_parse_errors, empty_deltas, total_elapsed.as_secs_f64()
        );
    }
    if finish_reason.is_none() && chunks_received > 0 {
        dbglog!(
            "WARNING: stream ended without finish_reason ({} chunks, {} content chars)",
            chunks_received, content_len
        );
    }
    if sse_parse_errors > 0 {
        dbglog!(
            "WARNING: {} SSE parse errors out of {} lines",
            sse_parse_errors, sse_lines_parsed
        );
    }

    if debug {
        if let Some(u) = usage {
            dbglog!(
                "tokens: {} prompt + {} completion = {} total",
                u.prompt_tokens, u.completion_tokens, u.total_tokens
            );
        }
        let ttft = first_content_at
            .map(|d| format!("{:.1}s", d.as_secs_f64()))
            .unwrap_or_else(|| "none".to_string());
        dbglog!(
            "stream: {:.1}s total, TTFT={}, {} chunks, {} SSE lines, \
             {} content chars, {} reasoning chars, {} tools, \
             finish={:?}",
            total_elapsed.as_secs_f64(),
            ttft,
            chunks_received,
            sse_lines_parsed,
            content_len,
            reasoning_chars,
            tool_count,
            finish_reason,
        );
        if !tools.is_empty() {
            for (i, tc) in tools.iter().enumerate() {
                dbglog!(
                    "  tool[{}]: {} (id: {}, {} arg chars)",
                    i, tc.function.name, tc.id, tc.function.arguments.len()
                );
            }
        }
    }
}