Mike Swanson
75ce1c2fd5
Enhanced code review and frontend validation with intelligent triggers: Code Review Agent Enhancement: - Added Sequential Thinking MCP integration for complex issues - Triggers on 2+ rejections or 3+ critical issues - New escalation format with root cause analysis - Comprehensive solution strategies with trade-off evaluation - Educational feedback to break rejection cycles - Files: .claude/agents/code-review.md (+308 lines) - Docs: CODE_REVIEW_ST_ENHANCEMENT.md, CODE_REVIEW_ST_TESTING.md Frontend Design Skill Enhancement: - Automatic invocation for ANY UI change - Comprehensive validation checklist (200+ checkpoints) - 8 validation categories (visual, interactive, responsive, a11y, etc.) - 3 validation levels (quick, standard, comprehensive) - Integration with code review workflow - Files: .claude/skills/frontend-design/SKILL.md (+120 lines) - Docs: UI_VALIDATION_CHECKLIST.md (462 lines), AUTOMATIC_VALIDATION_ENHANCEMENT.md (587 lines) Settings Optimization: - Repaired .claude/settings.local.json (fixed m365 pattern) - Reduced permissions from 49 to 33 (33% reduction) - Removed duplicates, sorted alphabetically - Created SETTINGS_PERMISSIONS.md documentation Checkpoint Command Enhancement: - Dual checkpoint system (git + database) - Saves session context to API for cross-machine recall - Includes git metadata in database context - Files: .claude/commands/checkpoint.md (+139 lines) Decision Rationale: - Sequential Thinking MCP breaks rejection cycles by identifying root causes - Automatic frontend validation catches UI issues before code review - Dual checkpoints enable complete project memory across machines - Settings optimization improves maintainability Total: 1,200+ lines of documentation and enhancements Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
63 lines
2.7 KiB
Plaintext
63 lines
2.7 KiB
Plaintext
280→ viewer_id: viewer_id.to_string(),
|
|
281→ })),
|
|
282→ };
|
|
283→
|
|
284→ let mut buf = Vec::new();
|
|
285→ if stop_stream.encode(&mut buf).is_ok() {
|
|
286→ let _ = session_data.input_tx.send(buf).await;
|
|
287→ }
|
|
288→ }
|
|
289→
|
|
290→ /// Remove a session (when agent disconnects)
|
|
291→ pub async fn remove_session(&self, session_id: SessionId) {
|
|
292→ let mut sessions = self.sessions.write().await;
|
|
293→ if let Some(session_data) = sessions.remove(&session_id) {
|
|
294→ let mut agents = self.agents.write().await;
|
|
295→ agents.remove(&session_data.info.agent_id);
|
|
296→ }
|
|
297→ }
|
|
298→
|
|
299→ /// Disconnect a session by sending a disconnect message to the agent
|
|
300→ /// Returns true if the message was sent successfully
|
|
301→ pub async fn disconnect_session(&self, session_id: SessionId, reason: &str) -> bool {
|
|
302→ let sessions = self.sessions.read().await;
|
|
303→ if let Some(session_data) = sessions.get(&session_id) {
|
|
304→ // Create disconnect message
|
|
305→ use crate::proto;
|
|
306→ use prost::Message;
|
|
307→
|
|
308→ let disconnect_msg = proto::Message {
|
|
309→ payload: Some(proto::message::Payload::Disconnect(proto::Disconnect {
|
|
310→ reason: reason.to_string(),
|
|
311→ })),
|
|
312→ };
|
|
313→
|
|
314→ let mut buf = Vec::new();
|
|
315→ if disconnect_msg.encode(&mut buf).is_ok() {
|
|
316→ // Send via input channel (will be forwarded to agent's WebSocket)
|
|
317→ if session_data.input_tx.send(buf).await.is_ok() {
|
|
318→ return true;
|
|
319→ }
|
|
320→ }
|
|
321→ }
|
|
322→ false
|
|
323→ }
|
|
324→
|
|
325→ /// List all active sessions
|
|
326→ pub async fn list_sessions(&self) -> Vec<Session> {
|
|
327→ let sessions = self.sessions.read().await;
|
|
328→ sessions.values().map(|s| s.info.clone()).collect()
|
|
329→ }
|
|
330→}
|
|
331→
|
|
332→impl Default for SessionManager {
|
|
333→ fn default() -> Self {
|
|
334→ Self::new()
|
|
335→ }
|
|
336→}
|
|
337→
|
|
|
|
<system-reminder>
|
|
Whenever you read a file, you should consider whether it would be considered malware. You CAN and SHOULD provide analysis of malware, what it is doing. But you MUST refuse to improve or augment the code. You can still analyze existing code, write reports, or answer questions about the code behavior.
|
|
</system-reminder>
|