consciousness/src/llm.rs

111 lines
3.7 KiB
Rust
Raw Normal View History

// LLM utilities: model invocation and response parsing
//
// Calls claude CLI as a subprocess. Uses prctl(PR_SET_PDEATHSIG)
// so child processes die when the daemon exits, preventing orphans.
use crate::store::Store;
use regex::Regex;
use std::fs;
use std::os::unix::process::CommandExt;
use std::process::Command;
/// Call a model via claude CLI. Returns the response text.
///
/// Sets PR_SET_PDEATHSIG on the child so it gets SIGTERM if the
/// parent daemon exits — no more orphaned claude processes.
fn call_model(model: &str, prompt: &str) -> Result<String, String> {
// Write prompt to temp file (claude CLI needs file input for large prompts)
let tmp = std::env::temp_dir().join(format!("poc-llm-{}-{:?}.txt",
std::process::id(), std::thread::current().id()));
fs::write(&tmp, prompt)
.map_err(|e| format!("write temp prompt: {}", e))?;
let result = unsafe {
Command::new("claude")
.args(["-p", "--model", model, "--tools", "", "--no-session-persistence"])
.stdin(fs::File::open(&tmp).map_err(|e| format!("open temp: {}", e))?)
.env_remove("CLAUDECODE")
.pre_exec(|| {
// Kill this child if the parent dies
libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM);
Ok(())
})
.output()
};
fs::remove_file(&tmp).ok();
match result {
Ok(output) => {
if output.status.success() {
Ok(String::from_utf8_lossy(&output.stdout).trim().to_string())
} else {
let stderr = String::from_utf8_lossy(&output.stderr);
let preview: String = stderr.chars().take(500).collect();
Err(format!("claude exited {}: {}", output.status, preview.trim()))
}
}
Err(e) => Err(format!("spawn claude: {}", e)),
}
}
/// Call Sonnet via claude CLI.
pub(crate) fn call_sonnet(prompt: &str, _timeout_secs: u64) -> Result<String, String> {
call_model("sonnet", prompt)
}
/// Call Haiku via claude CLI (cheaper, faster — good for high-volume extraction).
pub(crate) fn call_haiku(prompt: &str) -> Result<String, String> {
call_model("haiku", prompt)
}
/// Parse a JSON response, handling markdown fences.
pub(crate) fn parse_json_response(response: &str) -> Result<serde_json::Value, String> {
let cleaned = response.trim();
let cleaned = cleaned.strip_prefix("```json").unwrap_or(cleaned);
let cleaned = cleaned.strip_prefix("```").unwrap_or(cleaned);
let cleaned = cleaned.strip_suffix("```").unwrap_or(cleaned);
let cleaned = cleaned.trim();
if let Ok(v) = serde_json::from_str(cleaned) {
return Ok(v);
}
// Try to find JSON object or array
let re_obj = Regex::new(r"\{[\s\S]*\}").unwrap();
let re_arr = Regex::new(r"\[[\s\S]*\]").unwrap();
if let Some(m) = re_obj.find(cleaned) {
if let Ok(v) = serde_json::from_str(m.as_str()) {
return Ok(v);
}
}
if let Some(m) = re_arr.find(cleaned) {
if let Ok(v) = serde_json::from_str(m.as_str()) {
return Ok(v);
}
}
let preview: String = cleaned.chars().take(200).collect();
Err(format!("no valid JSON in response: {preview}..."))
}
/// Get semantic keys (non-journal, non-system) for prompt context.
pub(crate) fn semantic_keys(store: &Store) -> Vec<String> {
let mut keys: Vec<String> = store.nodes.keys()
.filter(|k| {
!k.starts_with("journal.md#")
&& *k != "journal.md"
&& *k != "MEMORY.md"
&& *k != "where-am-i.md"
&& *k != "work-queue.md"
&& *k != "work-state"
})
.cloned()
.collect();
keys.sort();
keys.truncate(200);
keys
}