Files
QuiCommit/src/llm/anthropic.rs

656 lines
20 KiB
Rust

use super::thinking::ThinkingStateManager;
use super::{LlmProvider, create_http_client};
use anyhow::{Context, Result, bail};
use async_trait::async_trait;
use serde::{Deserialize, Serialize};
use std::sync::Arc;
use std::time::Duration;
/// Anthropic Claude API client
pub struct AnthropicClient {
api_key: String,
model: String,
client: reqwest::Client,
thinking_enabled: bool,
thinking_budget_tokens: u32,
max_tokens: u32,
temperature: f32,
top_p: Option<f32>,
thinking_state: Option<Arc<ThinkingStateManager>>,
}
#[derive(Debug, Serialize)]
struct MessagesRequest {
model: String,
max_tokens: u32,
#[serde(skip_serializing_if = "Option::is_none")]
temperature: Option<f32>,
#[serde(skip_serializing_if = "Option::is_none")]
top_p: Option<f32>,
messages: Vec<AnthropicMessage>,
#[serde(skip_serializing_if = "Option::is_none")]
system: Option<Vec<SystemContent>>,
#[serde(skip_serializing_if = "Option::is_none")]
thinking: Option<ThinkingConfig>,
stream: bool,
}
#[derive(Debug, Serialize, Clone)]
struct SystemContent {
#[serde(rename = "type")]
content_type: String,
text: String,
}
#[derive(Debug, Serialize)]
struct ThinkingConfig {
#[serde(rename = "type")]
thinking_type: String,
#[serde(skip_serializing_if = "Option::is_none")]
budget_tokens: Option<u32>,
}
#[derive(Debug, Serialize, Deserialize, Clone)]
struct AnthropicMessage {
role: String,
content: AnthropicContent,
}
#[derive(Debug, Serialize, Deserialize, Clone)]
#[serde(untagged)]
enum AnthropicContent {
Text(String),
Blocks(Vec<ContentBlock>),
}
#[derive(Debug, Serialize, Deserialize, Clone)]
struct ContentBlock {
#[serde(rename = "type")]
content_type: String,
#[serde(skip_serializing_if = "Option::is_none")]
text: Option<String>,
}
#[derive(Debug, Deserialize)]
struct MessagesResponse {
content: Vec<ResponseContentBlock>,
}
#[derive(Debug, Deserialize)]
struct ResponseContentBlock {
#[serde(rename = "type")]
content_type: String,
text: String,
}
#[derive(Debug, Deserialize)]
struct ErrorResponse {
error: AnthropicError,
}
#[derive(Debug, Deserialize)]
struct AnthropicError {
#[serde(rename = "type")]
error_type: String,
message: String,
}
// --- Streaming SSE event structures ---
#[derive(Debug, Deserialize)]
struct SseEvent {
#[serde(rename = "type")]
event_type: String,
#[serde(default)]
message: Option<SseMessage>,
#[serde(default)]
index: Option<u32>,
#[serde(default)]
content_block: Option<SseContentBlock>,
#[serde(default)]
delta: Option<SseDelta>,
#[serde(default)]
usage: Option<SseUsage>,
}
#[derive(Debug, Deserialize)]
struct SseMessage {
#[serde(default)]
content: Option<Vec<SseContentBlock>>,
}
#[derive(Debug, Deserialize)]
struct SseContentBlock {
#[serde(rename = "type")]
content_type: String,
#[serde(default)]
thinking: Option<String>,
#[serde(default)]
text: Option<String>,
}
#[derive(Debug, Deserialize)]
struct SseDelta {
#[serde(rename = "type")]
delta_type: Option<String>,
#[serde(default)]
thinking: Option<String>,
#[serde(default)]
text: Option<String>,
}
#[derive(Debug, Deserialize)]
struct SseUsage {
#[serde(default)]
output_tokens: Option<u32>,
}
impl AnthropicClient {
pub fn new(api_key: &str, model: &str) -> Result<Self> {
let client = create_http_client(Duration::from_secs(60))?;
Ok(Self {
api_key: api_key.to_string(),
model: model.to_string(),
client,
thinking_enabled: false,
thinking_budget_tokens: 1024,
max_tokens: 500,
temperature: 0.7,
top_p: None,
thinking_state: None,
})
}
pub fn with_timeout(mut self, timeout: Duration) -> Result<Self> {
self.client = create_http_client(timeout)?;
Ok(self)
}
pub fn with_thinking(mut self, enabled: bool) -> Self {
self.thinking_enabled = enabled;
self
}
pub fn with_thinking_budget_tokens(mut self, budget_tokens: u32) -> Self {
self.thinking_budget_tokens = budget_tokens;
self
}
pub fn with_max_tokens(mut self, max_tokens: u32) -> Self {
self.max_tokens = max_tokens;
self
}
pub fn with_temperature(mut self, temperature: f32) -> Self {
self.temperature = temperature;
self
}
pub fn with_top_p(mut self, top_p: f32) -> Self {
self.top_p = Some(top_p);
self
}
pub fn with_thinking_state(mut self, state: Arc<ThinkingStateManager>) -> Self {
self.thinking_state = Some(state);
self
}
pub async fn list_models(&self) -> Result<Vec<String>> {
Ok(ANTHROPIC_MODELS.iter().map(|&m| m.to_string()).collect())
}
pub async fn validate_key(&self) -> Result<bool> {
let url = "https://api.anthropic.com/v1/messages";
let request = MessagesRequest {
model: self.model.clone(),
max_tokens: 5,
temperature: Some(0.0),
top_p: None,
messages: vec![AnthropicMessage {
role: "user".to_string(),
content: AnthropicContent::Text("Hi".to_string()),
}],
system: None,
thinking: None,
stream: false,
};
let response = self
.client
.post(url)
.header("x-api-key", &self.api_key)
.header("anthropic-version", "2023-06-01")
.header("Content-Type", "application/json")
.json(&request)
.send()
.await;
match response {
Ok(resp) => {
if resp.status().is_success() {
Ok(true)
} else {
let status = resp.status();
if status.as_u16() == 401 {
Ok(false)
} else {
let text = resp.text().await.unwrap_or_default();
bail!("Anthropic API error: {} - {}", status, text)
}
}
}
Err(e) => Err(e.into()),
}
}
}
#[async_trait]
impl LlmProvider for AnthropicClient {
async fn generate(&self, prompt: &str) -> Result<String> {
let messages = vec![AnthropicMessage {
role: "user".to_string(),
content: AnthropicContent::Text(prompt.to_string()),
}];
self.messages_request_with_retry(messages, None).await
}
async fn generate_with_system(&self, system: &str, user: &str) -> Result<String> {
let messages = vec![AnthropicMessage {
role: "user".to_string(),
content: AnthropicContent::Text(user.to_string()),
}];
let system = if system.is_empty() {
None
} else {
Some(vec![SystemContent {
content_type: "text".to_string(),
text: system.to_string(),
}])
};
self.messages_request_with_retry(messages, system).await
}
async fn is_available(&self) -> bool {
self.validate_key().await.unwrap_or(false)
}
fn name(&self) -> &str {
"anthropic"
}
}
impl AnthropicClient {
async fn messages_request_with_retry(
&self,
messages: Vec<AnthropicMessage>,
system: Option<Vec<SystemContent>>,
) -> Result<String> {
let mut last_error = None;
for attempt in 1..=3 {
match self
.messages_request(messages.clone(), system.clone())
.await
{
Ok(result) => return Ok(result),
Err(e) => {
let err_msg = e.to_string();
let is_retryable = err_msg.contains("timeout")
|| err_msg.contains("connection")
|| err_msg.contains("temporary")
|| err_msg.contains("5")
&& (err_msg.contains("500")
|| err_msg.contains("502")
|| err_msg.contains("503")
|| err_msg.contains("504"));
if !is_retryable || attempt == 3 {
last_error = Some(e);
break;
}
tokio::time::sleep(Duration::from_millis(500 * 2u64.pow(attempt - 1))).await;
}
}
}
Err(last_error.unwrap_or_else(|| anyhow::anyhow!("Request failed after retries")))
}
async fn messages_request(
&self,
messages: Vec<AnthropicMessage>,
system: Option<Vec<SystemContent>>,
) -> Result<String> {
if self.thinking_enabled {
self.streaming_messages_request(messages, system).await
} else {
self.non_streaming_messages_request(messages, system).await
}
}
async fn non_streaming_messages_request(
&self,
messages: Vec<AnthropicMessage>,
system: Option<Vec<SystemContent>>,
) -> Result<String> {
let url = "https://api.anthropic.com/v1/messages";
let temperature = if self.temperature == 0.0 {
None
} else {
Some(self.temperature)
};
let request = MessagesRequest {
model: self.model.clone(),
max_tokens: self.max_tokens,
temperature,
top_p: self.top_p,
messages,
system,
thinking: Some(ThinkingConfig {
thinking_type: "disabled".to_string(),
budget_tokens: None,
}),
stream: false,
};
let response = self
.client
.post(url)
.header("x-api-key", &self.api_key)
.header("anthropic-version", "2023-06-01")
.header("Content-Type", "application/json")
.json(&request)
.send()
.await
.context("Failed to send request to Anthropic")?;
let status = response.status();
if !status.is_success() {
let text = response.text().await.unwrap_or_default();
if let Ok(error) = serde_json::from_str::<ErrorResponse>(&text) {
bail!(
"Anthropic API error: {} ({})",
error.error.message,
error.error.error_type
);
}
bail!("Anthropic API error: {} - {}", status, text);
}
let result: MessagesResponse = response
.json()
.await
.context("Failed to parse Anthropic response")?;
result
.content
.into_iter()
.find(|c| c.content_type == "text")
.map(|c| c.text.trim().to_string())
.filter(|s| !s.is_empty())
.ok_or_else(|| anyhow::anyhow!("No text response from Anthropic"))
}
/// Streaming request for thinking mode, filters thinking content blocks
async fn streaming_messages_request(
&self,
messages: Vec<AnthropicMessage>,
system: Option<Vec<SystemContent>>,
) -> Result<String> {
let url = "https://api.anthropic.com/v1/messages";
let thinking = ThinkingConfig {
thinking_type: "enabled".to_string(),
budget_tokens: Some(self.thinking_budget_tokens),
};
// max_tokens must exceed budget_tokens
let max_tokens = (self.max_tokens).max(self.thinking_budget_tokens + 100);
let request = MessagesRequest {
model: self.model.clone(),
max_tokens,
temperature: None, // must be omitted for thinking mode
top_p: None,
messages,
system,
thinking: Some(thinking),
stream: true,
};
let response = self
.client
.post(url)
.header("x-api-key", &self.api_key)
.header("anthropic-version", "2023-06-01")
.header("Content-Type", "application/json")
.header("Accept", "text/event-stream")
.json(&request)
.send()
.await
.context("Failed to send streaming request to Anthropic")?;
let status = response.status();
if !status.is_success() {
let text = response.text().await.unwrap_or_default();
if let Ok(error) = serde_json::from_str::<ErrorResponse>(&text) {
bail!(
"Anthropic API error: {} ({})",
error.error.message,
error.error.error_type
);
}
bail!("Anthropic API error: {} - {}", status, text);
}
let mut content_buffer = String::new();
let mut in_thinking = false;
let mut has_reasoning = false;
let mut has_content = false;
let thinking_state = self.thinking_state.as_ref();
let mut byte_stream = response.bytes_stream();
let mut line_buffer = String::new();
use futures_util::StreamExt;
while let Some(chunk) = byte_stream.next().await {
let chunk = chunk.context("Failed to read streaming response chunk")?;
let chunk_str =
String::from_utf8(chunk.to_vec()).context("Invalid UTF-8 in stream chunk")?;
line_buffer.push_str(&chunk_str);
while let Some(line_end) = line_buffer.find('\n') {
let line = line_buffer[..line_end].trim().to_string();
line_buffer = line_buffer[line_end + 1..].to_string();
if line.is_empty() {
continue;
}
// Parse SSE event line
if let Some(data) = line.strip_prefix("data: ") {
if let Ok(event) = serde_json::from_str::<SseEvent>(data) {
match event.event_type.as_str() {
"content_block_start" => {
if let Some(ref block) = event.content_block {
if block.content_type == "thinking" {
in_thinking = true;
if !has_reasoning {
has_reasoning = true;
if let Some(state) = thinking_state {
state.start_thinking();
}
}
}
}
}
"content_block_delta" => {
if let Some(ref delta) = event.delta {
// Thinking delta - ignore content but track state
if delta.thinking.is_some() {
continue;
}
// Text delta - collect
if in_thinking && delta.text.is_some() {
// Transition from thinking to text
if let Some(state) = thinking_state {
state.end_thinking();
}
in_thinking = false;
}
if let Some(ref text) = delta.text
&& !text.is_empty()
{
has_content = true;
content_buffer.push_str(text);
}
}
}
"content_block_stop" => {
if in_thinking {
if let Some(state) = thinking_state {
state.end_thinking();
}
in_thinking = false;
}
}
_ => {}
}
}
}
}
}
// Ensure thinking state is ended
if let Some(state) = thinking_state {
state.end_thinking();
}
let result = content_buffer.trim().to_string();
if result.is_empty() {
if has_reasoning && !has_content {
bail!(
"Anthropic returned thinking content but no final answer. \
The model may have entered an incomplete thinking state. \
Please try again or disable thinking mode."
);
}
bail!(
"No response from Anthropic. \
If thinking mode is enabled, try disabling it or ensure the model supports it."
);
}
Ok(result)
}
}
/// Available Anthropic models (Claude 4 series with extended thinking)
pub const ANTHROPIC_MODELS: &[&str] = &[
"claude-opus-4-7",
"claude-sonnet-4-6",
"claude-haiku-4-5",
// Legacy models
"claude-3-opus-20240229",
"claude-3-sonnet-20240229",
"claude-3-haiku-20240307",
"claude-2.1",
"claude-2.0",
"claude-instant-1.2",
];
pub fn is_valid_model(model: &str) -> bool {
ANTHROPIC_MODELS.contains(&model)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_model_validation_claude4() {
assert!(is_valid_model("claude-opus-4-7"));
assert!(is_valid_model("claude-sonnet-4-6"));
assert!(is_valid_model("claude-haiku-4-5"));
assert!(is_valid_model("claude-3-sonnet-20240229"));
assert!(!is_valid_model("invalid-model"));
}
#[test]
fn test_thinking_config_serialization() {
let config = ThinkingConfig {
thinking_type: "enabled".to_string(),
budget_tokens: Some(2048),
};
let json = serde_json::to_string(&config).unwrap();
assert!(json.contains(r#""type":"enabled""#));
assert!(json.contains(r#""budget_tokens":2048"#));
}
#[test]
fn test_thinking_config_disabled_serialization() {
let config = ThinkingConfig {
thinking_type: "disabled".to_string(),
budget_tokens: None,
};
let json = serde_json::to_string(&config).unwrap();
assert_eq!(json, r#"{"type":"disabled"}"#);
}
#[test]
fn test_system_content_serialization() {
let content = SystemContent {
content_type: "text".to_string(),
text: "You are helpful.".to_string(),
};
let json = serde_json::to_string(&content).unwrap();
assert!(json.contains(r#""type":"text""#));
}
#[test]
fn test_sse_event_parsing_content_block_start() {
let json = r#"{"type":"content_block_start","index":0,"content_block":{"type":"thinking","thinking":""}}"#;
let event: SseEvent = serde_json::from_str(json).unwrap();
assert_eq!(event.event_type, "content_block_start");
assert_eq!(event.content_block.unwrap().content_type, "thinking");
}
#[test]
fn test_sse_event_parsing_text_delta() {
let json = r#"{"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}"#;
let event: SseEvent = serde_json::from_str(json).unwrap();
assert_eq!(event.event_type, "content_block_delta");
assert_eq!(event.delta.unwrap().text, Some("Hello".to_string()));
}
#[test]
fn test_anthropic_content_text() {
let msg = AnthropicMessage {
role: "user".to_string(),
content: AnthropicContent::Text("Hello".to_string()),
};
let json = serde_json::to_string(&msg).unwrap();
assert!(json.contains(r#""content":"Hello""#));
}
}