2f3fbb3353
agents/*.agent definitions and prompts/ now live under src/subconscious/ alongside the code that uses them. No more intermediate agents/ subdirectory. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
94 lines
3.3 KiB
Rust
94 lines
3.3 KiB
Rust
// Shared JSONL transcript parsing
|
|
//
|
|
// Three agents (enrich, fact_mine, knowledge) all parse Claude Code JSONL
|
|
// transcripts. This module provides the shared core: parse each line, extract
|
|
// message type, text content from string-or-array blocks, timestamp, and
|
|
// user type. Callers filter and transform as needed.
|
|
|
|
use std::fs;
|
|
use std::path::Path;
|
|
|
|
/// A single message extracted from a JSONL transcript.
|
|
pub struct TranscriptMessage {
|
|
/// 1-based line number in the JSONL file.
|
|
pub line: usize,
|
|
/// Raw role: "user" or "assistant".
|
|
pub role: String,
|
|
/// Extracted text content (trimmed, blocks joined with newlines).
|
|
pub text: String,
|
|
/// ISO timestamp from the message, or empty string.
|
|
pub timestamp: String,
|
|
/// For user messages: "external", "internal", etc. None for assistant.
|
|
pub user_type: Option<String>,
|
|
}
|
|
|
|
/// Parse a JSONL transcript into structured messages.
|
|
///
|
|
/// Extracts all user and assistant messages. Content blocks of type "text"
|
|
/// are joined; tool_use, tool_result, thinking blocks are skipped.
|
|
/// System-reminder blocks are filtered out.
|
|
pub fn parse_transcript(path: &Path) -> Result<Vec<TranscriptMessage>, String> {
|
|
let content = fs::read_to_string(path)
|
|
.map_err(|e| format!("read {}: {}", path.display(), e))?;
|
|
|
|
let mut messages = Vec::new();
|
|
for (i, line) in content.lines().enumerate() {
|
|
let Ok(obj) = serde_json::from_str::<serde_json::Value>(line) else { continue };
|
|
|
|
let msg_type = obj.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
|
if msg_type != "user" && msg_type != "assistant" { continue; }
|
|
|
|
let timestamp = obj.get("timestamp")
|
|
.and_then(|v| v.as_str())
|
|
.unwrap_or("")
|
|
.to_string();
|
|
|
|
let user_type = obj.get("userType")
|
|
.and_then(|v| v.as_str())
|
|
.map(|s| s.to_string());
|
|
|
|
let Some(text) = extract_text_content(&obj) else { continue };
|
|
let text = text.trim().to_string();
|
|
if text.is_empty() { continue; }
|
|
|
|
messages.push(TranscriptMessage {
|
|
line: i + 1,
|
|
role: msg_type.to_string(),
|
|
text,
|
|
timestamp,
|
|
user_type,
|
|
});
|
|
}
|
|
|
|
Ok(messages)
|
|
}
|
|
|
|
/// Extract text content from a JSONL message object.
|
|
///
|
|
/// Handles both string content and array-of-blocks content (filtering to
|
|
/// type="text" blocks only). Strips `<system-reminder>` tags.
|
|
fn extract_text_content(obj: &serde_json::Value) -> Option<String> {
|
|
let msg = obj.get("message").unwrap_or(obj);
|
|
let content = msg.get("content")?;
|
|
|
|
let text = match content {
|
|
serde_json::Value::String(s) => s.clone(),
|
|
serde_json::Value::Array(arr) => {
|
|
let texts: Vec<&str> = arr.iter()
|
|
.filter_map(|block| {
|
|
let block_type = block.get("type").and_then(|v| v.as_str())?;
|
|
if block_type != "text" { return None; }
|
|
let t = block.get("text").and_then(|v| v.as_str())?;
|
|
// Skip system-reminder blocks entirely
|
|
if t.contains("<system-reminder>") { return None; }
|
|
Some(t)
|
|
})
|
|
.collect();
|
|
if texts.is_empty() { return None; }
|
|
texts.join("\n")
|
|
}
|
|
_ => return None,
|
|
};
|
|
|
|
Some(text)
|
|
}
|