MythEclipse/zesdex
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: enhance safety filters for shell commands by normalizing ANSI-C quoting

Browse Source
This commit is contained in:
asepharyana
2026-07-13 04:10:08 +07:00
parent a080957c26
commit d09e440e7e
14 changed files with 383 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/app/runtime/shortsend.rs
+42 -19
View File
@@ -7,15 +7,24 @@ use crate::dto::chat::message::ChatMessage;
/// sending to the LLM.
///
/// Flow: trigger based on token estimate. If `token_estimate` exceeds
/// `MAX_WIRE_TOKENS * 0.8`, we shape. We also apply hysteresis so it doesn't
/// flutter.
/// the threshold, we shape. When `prev_shaped` is true, the threshold is
/// raised (95%) to avoid fluttering — compaction only re-triggers when
/// the context is genuinely full again. When `prev_shaped` is false, the
/// threshold is lower (85%) so compaction starts proactively.
///
/// Why: hysteresis prevents repeated compaction on every turn when the
/// token count hovers near the boundary.
///
/// Return: `true` if shaping should be applied.
pub fn should_shape(token_estimate: usize, max_wire_tokens: usize, prev_shaped: bool) -> bool {
let threshold = if prev_shaped {
(max_wire_tokens as f32 * 0.85) as usize
// Higher threshold when already shaped — defer re-shaping until
// the buffer is genuinely full again (95%).
(max_wire_tokens as f32 * 0.95) as usize
} else {
(max_wire_tokens as f32 * 0.90) as usize
// Lower threshold when not yet shaped — trigger shaping sooner
// (85%) to avoid hitting the context window limit.
(max_wire_tokens as f32 * 0.85) as usize
};
token_estimate >= threshold
}
@@ -59,7 +68,10 @@ pub fn shape_messages(
// Iterate backwards from the most recent to oldest
for m in msgs_to_eval.into_iter().rev() {
let text = m.content.as_deref().unwrap_or("");
let msg_tokens = text.len() / 4;
// Estimate tokens: ~1 token per 3 bytes for mixed content (code,
// prose, multi-byte). Conservative enough to stay under provider
// limits while avoiding premature compaction.
let msg_tokens = text.len() / 3;
if current_tokens + msg_tokens <= target_tokens {
current_tokens += msg_tokens;
@@ -80,22 +92,33 @@ pub fn shape_messages(
if !dropped_msgs.is_empty() {
let mut summary_text = "[prior conversation compacted]".to_string();
if let Some(llm) = client {
let prompt = format!(
"Summarize the following dropped conversation history briefly. Focus on main goals, decisions made, and files modified, so the context is preserved for future turns. Keep it concise.\n\nHistory:\n{}",
dropped_msgs.iter()
.map(|m| format!("[{}]: {}", if m.role == crate::dto::chat::message::Role::User { "User" } else { "Assistant" }, m.content.as_deref().unwrap_or("")))
.collect::<Vec<_>>()
.join("\n\n")
);
let req_msgs = vec![ChatMessage::user(prompt)];
if let Ok(resp) = llm.chat_with_tools_non_streaming(&req_msgs, None) {
if let Some(content) = resp.0.content {
summary_text = format!("[Summary of compacted prior conversation:\n{}\n]", content);
if let Some(llm) = client {
let prompt = format!(
"Summarize the following dropped conversation history briefly. Focus on main goals, decisions made, and files modified, so the context is preserved for future turns. Keep it concise.\n\nHistory:\n{}",
dropped_msgs.iter()
.map(|m| format!("[{}]: {}", if m.role == crate::dto::chat::message::Role::User { "User" } else { "Assistant" }, m.content.as_deref().unwrap_or("")))
.collect::<Vec<_>>()
.join("\n\n")
);
let req_msgs = vec![ChatMessage::user(prompt)];
match llm.chat_with_tools_non_streaming(&req_msgs, None) {
Ok(resp) => {
if let Some(content) = resp.0.content {
summary_text = format!("[Summary of compacted prior conversation:\n{}\n]", content);
}
}
Err(e) => {
tracing::warn!(
"[shortsend] LLM summarization failed: {}. \
Prior conversation history is lost — no summary available. \
This means the model will lose context about earlier parts of \
the conversation.",
e,
);
}
}
}
}
result.push(ChatMessage::system(summary_text));
}