fix(audit): 第五轮审计修复 — 反思LLM分析、语义路由、并行执行、错误中文化
- P2: 反思引擎接入 LLM 深度行为分析 (analyze_patterns_with_llm) - P3-M6: 语义路由 RuntimeLlmIntentDriver 真实 LLM 匹配 - P3-L1: V2 Pipeline execute_parallel 改用 buffer_unordered 真正并行 - P3-S10: Rust 用户可见错误提示统一中文化 累计修复 27 项，完成度 ~72% → ~78%
This commit is contained in:
iven
@@ -402,23 +402,25 @@ pub struct DefaultLlmIntentDriver {
|
||||
model_id: String,
|
||||
}
|
||||
|
||||
impl DefaultLlmIntentDriver {
|
||||
/// Create a new default LLM driver
|
||||
pub fn new(model_id: impl Into<String>) -> Self {
|
||||
Self {
|
||||
model_id: model_id.into(),
|
||||
}
|
||||
/// Runtime LLM driver that wraps zclaw-runtime's LlmDriver for actual LLM calls
|
||||
pub struct RuntimeLlmIntentDriver {
|
||||
driver: std::sync::Arc<dyn zclaw_runtime::driver::LlmDriver>,
|
||||
}
|
||||
|
||||
impl RuntimeLlmIntentDriver {
|
||||
/// Create a new runtime LLM intent driver wrapping an existing LLM driver
|
||||
pub fn new(driver: std::sync::Arc<dyn zclaw_runtime::driver::LlmDriver>) -> Self {
|
||||
Self { driver }
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl LlmIntentDriver for DefaultLlmIntentDriver {
|
||||
impl LlmIntentDriver for RuntimeLlmIntentDriver {
|
||||
async fn semantic_match(
|
||||
&self,
|
||||
user_input: &str,
|
||||
triggers: &[CompiledTrigger],
|
||||
) -> Option<SemanticMatchResult> {
|
||||
// Build prompt for LLM
|
||||
let trigger_descriptions: Vec<String> = triggers
|
||||
.iter()
|
||||
.map(|t| {
|
||||
@@ -430,31 +432,42 @@ impl LlmIntentDriver for DefaultLlmIntentDriver {
|
||||
})
|
||||
.collect();
|
||||
|
||||
let prompt = format!(
|
||||
r#"分析用户输入，匹配合适的 Pipeline。
|
||||
let system_prompt = r#"分析用户输入，匹配合适的 Pipeline。只返回 JSON，不要其他内容。"#
|
||||
.to_string();
|
||||
|
||||
用户输入: {}
|
||||
|
||||
可选 Pipelines:
|
||||
{}
|
||||
|
||||
返回 JSON 格式:
|
||||
{{
|
||||
"pipeline_id": "匹配的 pipeline ID 或 null",
|
||||
"params": {{ "参数名": "值" }},
|
||||
"confidence": 0.0-1.0,
|
||||
"reason": "匹配原因"
|
||||
}}
|
||||
|
||||
只返回 JSON，不要其他内容。"#,
|
||||
let user_msg = format!(
|
||||
"用户输入: {}\n\n可选 Pipelines:\n{}",
|
||||
user_input,
|
||||
trigger_descriptions.join("\n")
|
||||
);
|
||||
|
||||
// In a real implementation, this would call the LLM
|
||||
// For now, we return None to indicate semantic matching is not available
|
||||
let _ = prompt; // Suppress unused warning
|
||||
None
|
||||
let request = zclaw_runtime::driver::CompletionRequest {
|
||||
model: self.driver.provider().to_string(),
|
||||
system: Some(system_prompt),
|
||||
messages: vec![zclaw_types::Message::assistant(user_msg)],
|
||||
max_tokens: Some(512),
|
||||
temperature: Some(0.2),
|
||||
stream: false,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
match self.driver.complete(request).await {
|
||||
Ok(response) => {
|
||||
let text = response.content.iter()
|
||||
.filter_map(|block| match block {
|
||||
zclaw_runtime::driver::ContentBlock::Text { text } => Some(text.as_str()),
|
||||
_ => None,
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.join("");
|
||||
|
||||
parse_semantic_match_response(&text)
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!("[intent] LLM semantic match failed: {}", e);
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn collect_params(
|
||||
@@ -463,7 +476,10 @@ impl LlmIntentDriver for DefaultLlmIntentDriver {
|
||||
missing_params: &[MissingParam],
|
||||
_context: &HashMap<String, serde_json::Value>,
|
||||
) -> HashMap<String, serde_json::Value> {
|
||||
// Build prompt to extract parameters from user input
|
||||
if missing_params.is_empty() {
|
||||
return HashMap::new();
|
||||
}
|
||||
|
||||
let param_descriptions: Vec<String> = missing_params
|
||||
.iter()
|
||||
.map(|p| {
|
||||
@@ -476,30 +492,123 @@ impl LlmIntentDriver for DefaultLlmIntentDriver {
|
||||
})
|
||||
.collect();
|
||||
|
||||
let prompt = format!(
|
||||
r#"从用户输入中提取参数值。
|
||||
let system_prompt = r#"从用户输入中提取参数值。如果无法提取，该参数可以省略。只返回 JSON。"#
|
||||
.to_string();
|
||||
|
||||
用户输入: {}
|
||||
|
||||
需要提取的参数:
|
||||
{}
|
||||
|
||||
返回 JSON 格式:
|
||||
{{
|
||||
"参数名": "提取的值"
|
||||
}}
|
||||
|
||||
如果无法提取，该参数可以省略。只返回 JSON。"#,
|
||||
let user_msg = format!(
|
||||
"用户输入: {}\n\n需要提取的参数:\n{}",
|
||||
user_input,
|
||||
param_descriptions.join("\n")
|
||||
);
|
||||
|
||||
// In a real implementation, this would call the LLM
|
||||
let _ = prompt;
|
||||
HashMap::new()
|
||||
let request = zclaw_runtime::driver::CompletionRequest {
|
||||
model: self.driver.provider().to_string(),
|
||||
system: Some(system_prompt),
|
||||
messages: vec![zclaw_types::Message::assistant(user_msg)],
|
||||
max_tokens: Some(512),
|
||||
temperature: Some(0.1),
|
||||
stream: false,
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
match self.driver.complete(request).await {
|
||||
Ok(response) => {
|
||||
let text = response.content.iter()
|
||||
.filter_map(|block| match block {
|
||||
zclaw_runtime::driver::ContentBlock::Text { text } => Some(text.as_str()),
|
||||
_ => None,
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.join("");
|
||||
|
||||
parse_params_response(&text)
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!("[intent] LLM param extraction failed: {}", e);
|
||||
HashMap::new()
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse semantic match JSON from LLM response
|
||||
fn parse_semantic_match_response(text: &str) -> Option<SemanticMatchResult> {
|
||||
let json_str = extract_json_from_text(text);
|
||||
let parsed: serde_json::Value = serde_json::from_str(&json_str).ok()?;
|
||||
|
||||
let pipeline_id = parsed.get("pipeline_id")?.as_str()?.to_string();
|
||||
let confidence = parsed.get("confidence")?.as_f64()? as f32;
|
||||
|
||||
// Reject low-confidence matches
|
||||
if confidence < 0.5 || pipeline_id.is_empty() {
|
||||
return None;
|
||||
}
|
||||
|
||||
let params = parsed.get("params")
|
||||
.and_then(|v| v.as_object())
|
||||
.map(|obj| {
|
||||
obj.iter()
|
||||
.filter_map(|(k, v)| {
|
||||
let val = match v {
|
||||
serde_json::Value::String(s) => serde_json::Value::String(s.clone()),
|
||||
serde_json::Value::Number(n) => serde_json::Value::Number(n.clone()),
|
||||
other => other.clone(),
|
||||
};
|
||||
Some((k.clone(), val))
|
||||
})
|
||||
.collect()
|
||||
})
|
||||
.unwrap_or_default();
|
||||
|
||||
let reason = parsed.get("reason")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("")
|
||||
.to_string();
|
||||
|
||||
Some(SemanticMatchResult {
|
||||
pipeline_id,
|
||||
params,
|
||||
confidence,
|
||||
reason,
|
||||
})
|
||||
}
|
||||
|
||||
/// Parse params JSON from LLM response
|
||||
fn parse_params_response(text: &str) -> HashMap<String, serde_json::Value> {
|
||||
let json_str = extract_json_from_text(text);
|
||||
if let Ok(parsed) = serde_json::from_str::<serde_json::Value>(&json_str) {
|
||||
if let Some(obj) = parsed.as_object() {
|
||||
return obj.iter()
|
||||
.filter_map(|(k, v)| Some((k.clone(), v.clone())))
|
||||
.collect();
|
||||
}
|
||||
}
|
||||
HashMap::new()
|
||||
}
|
||||
|
||||
/// Extract JSON from LLM response text (handles markdown code blocks)
|
||||
fn extract_json_from_text(text: &str) -> String {
|
||||
let trimmed = text.trim();
|
||||
|
||||
// Try markdown code block
|
||||
if let Some(start) = trimmed.find("```json") {
|
||||
if let Some(content_start) = trimmed[start..].find('\n') {
|
||||
if let Some(end) = trimmed[content_start..].find("```") {
|
||||
return trimmed[content_start + 1..content_start + end].trim().to_string();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Try bare JSON
|
||||
if let Some(start) = trimmed.find('{') {
|
||||
if let Some(end) = trimmed.rfind('}') {
|
||||
return trimmed[start..end + 1].to_string();
|
||||
}
|
||||
}
|
||||
|
||||
trimmed.to_string()
|
||||
}
|
||||
|
||||
/// Intent analysis result (for debugging/logging)
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
|
||||
Reference in New Issue
Block a user