fix: Move ensureWorkerRunning to start of hooks to prevent race condition

All hooks now call ensureWorkerRunning() BEFORE querying the database. This
ensures the worker's orphaned session cleanup runs before hooks check for
active sessions, preventing 404 errors when hooks try to use sessions that
don't exist in worker memory after a restart.

Hook order now:
1. ensureWorkerRunning() - starts worker, runs cleanup
2. Query DB - cleanup already marked orphaned sessions as failed
3. Use session - only valid sessions are processed

Fixed in:
- new-hook: Line 26, before DB queries
- save-hook: Line 37, before DB queries
- summary-hook: Line 24, before DB queries
- cleanup-hook: Line 50, before DB queries

This prevents the race condition where hooks would read session status before
cleanup ran, then get 404 from worker after cleanup marked sessions failed.
This commit is contained in:
Alex Newman
2025-10-19 02:01:11 -04:00
parent daf368e343
commit f849a69506
8 changed files with 54 additions and 52 deletions
+3 -3
View File
@@ -1,7 +1,7 @@
#!/usr/bin/env node
import F from"better-sqlite3";import{join as a,dirname as U,basename as q}from"path";import{homedir as R}from"os";import{existsSync as z,mkdirSync as w}from"fs";import{fileURLToPath as X}from"url";function M(){return typeof __dirname<"u"?__dirname:U(X(import.meta.url))}var P=M(),d=process.env.CLAUDE_MEM_DATA_DIR||a(R(),".claude-mem"),u=process.env.CLAUDE_CONFIG_DIR||a(R(),".claude"),ee=a(d,"archives"),se=a(d,"logs"),te=a(d,"trash"),re=a(d,"backups"),ne=a(d,"settings.json"),I=a(d,"claude-mem.db"),oe=a(u,"settings.json"),ie=a(u,"commands"),ae=a(u,"CLAUDE.md");function O(o){w(o,{recursive:!0})}function L(){return a(P,"..","..")}var _=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(_||{}),T=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=_[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,t){return`obs-${e}-${t}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let t=Object.keys(e);return t.length===0?"{}":t.length<=3?JSON.stringify(e):`{${t.length} keys: ${t.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,t){if(!t)return e;try{let s=typeof t=="string"?JSON.parse(t):t;if(e==="Bash"&&s.command){let r=s.command.length>50?s.command.substring(0,50)+"...":s.command;return`${e}(${r})`}if(e==="Read"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}if(e==="Edit"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}if(e==="Write"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,t,s,r,n){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),p=_[e].padEnd(5),c=t.padEnd(6),E="";r?.correlationId?E=`[${r.correlationId}] `:r?.sessionId&&(E=`[session-${r.sessionId}] `);let m="";n!=null&&(this.level===0&&typeof n=="object"?m=`
`+JSON.stringify(n,null,2):m=" "+this.formatData(n));let h="";if(r){let{sessionId:$,sdkSessionId:B,correlationId:G,...f}=r;Object.keys(f).length>0&&(h=` {${Object.entries(f).map(([y,x])=>`${y}=${x}`).join(", ")}}`)}let N=`[${i}] [${p}] [${c}] ${E}${s}${h}${m}`;e===3?console.error(N):console.log(N)}debug(e,t,s,r){this.log(0,e,t,s,r)}info(e,t,s,r){this.log(1,e,t,s,r)}warn(e,t,s,r){this.log(2,e,t,s,r)}error(e,t,s,r){this.log(3,e,t,s,r)}dataIn(e,t,s,r){this.info(e,`\u2192 ${t}`,s,r)}dataOut(e,t,s,r){this.info(e,`\u2190 ${t}`,s,r)}success(e,t,s,r){this.info(e,`\u2713 ${t}`,s,r)}failure(e,t,s,r){this.error(e,`\u2717 ${t}`,s,r)}timing(e,t,s,r){this.info(e,`\u23F1 ${t}`,r,{duration:`${s}ms`})}},v=new T;var l=class{db;constructor(){O(d),this.db=new F(I),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable()}initializeSchema(){try{this.db.exec(`
${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let t=Object.keys(e);return t.length===0?"{}":t.length<=3?JSON.stringify(e):`{${t.length} keys: ${t.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,t){if(!t)return e;try{let s=typeof t=="string"?JSON.parse(t):t;if(e==="Bash"&&s.command){let r=s.command.length>50?s.command.substring(0,50)+"...":s.command;return`${e}(${r})`}if(e==="Read"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}if(e==="Edit"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}if(e==="Write"&&s.file_path){let r=s.file_path.split("/").pop()||s.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,t,s,r,n){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),p=_[e].padEnd(5),c=t.padEnd(6),m="";r?.correlationId?m=`[${r.correlationId}] `:r?.sessionId&&(m=`[session-${r.sessionId}] `);let E="";n!=null&&(this.level===0&&typeof n=="object"?E=`
`+JSON.stringify(n,null,2):E=" "+this.formatData(n));let h="";if(r){let{sessionId:$,sdkSessionId:B,correlationId:G,...f}=r;Object.keys(f).length>0&&(h=` {${Object.entries(f).map(([y,x])=>`${y}=${x}`).join(", ")}}`)}let N=`[${i}] [${p}] [${c}] ${m}${s}${h}${E}`;e===3?console.error(N):console.log(N)}debug(e,t,s,r){this.log(0,e,t,s,r)}info(e,t,s,r){this.log(1,e,t,s,r)}warn(e,t,s,r){this.log(2,e,t,s,r)}error(e,t,s,r){this.log(3,e,t,s,r)}dataIn(e,t,s,r){this.info(e,`\u2192 ${t}`,s,r)}dataOut(e,t,s,r){this.info(e,`\u2190 ${t}`,s,r)}success(e,t,s,r){this.info(e,`\u2713 ${t}`,s,r)}failure(e,t,s,r){this.error(e,`\u2717 ${t}`,s,r)}timing(e,t,s,r){this.info(e,`\u23F1 ${t}`,r,{duration:`${s}ms`})}},v=new T;var l=class{db;constructor(){O(d),this.db=new F(I),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable()}initializeSchema(){try{this.db.exec(`
CREATE TABLE IF NOT EXISTS schema_versions (
id INTEGER PRIMARY KEY,
version INTEGER UNIQUE NOT NULL,
@@ -240,4 +240,4 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let t=Obje
SET status = 'failed', completed_at = ?, completed_at_epoch = ?
WHERE status = 'active'
`).run(e.toISOString(),t).changes}close(){this.db.close()}};import g from"path";import{existsSync as S}from"fs";import{spawn as H}from"child_process";var W=parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10),j=`http://127.0.0.1:${W}/health`;async function A(){try{return(await fetch(j,{signal:AbortSignal.timeout(500)})).ok}catch{return!1}}async function k(){try{if(await A())return!0;console.error("[claude-mem] Worker not responding, starting...");let o=L(),e=g.join(o,"plugin","scripts","worker-service.cjs");if(!S(e))return console.error(`[claude-mem] Worker service not found at ${e}`),!1;let t=g.join(o,"ecosystem.config.cjs"),s=g.join(o,"node_modules",".bin","pm2");if(!S(s))throw new Error(`PM2 binary not found at ${s}. This is a bundled dependency - try running: npm install`);if(!S(t))throw new Error(`PM2 ecosystem config not found at ${t}. Plugin installation may be corrupted.`);let r=H(s,["start",t],{detached:!0,stdio:"ignore",cwd:o});r.on("error",n=>{throw new Error(`Failed to spawn PM2: ${n.message}`)}),r.unref(),console.error("[claude-mem] Worker started with PM2");for(let n=0;n<3;n++)if(await new Promise(i=>setTimeout(i,500)),await A())return console.error("[claude-mem] Worker is healthy"),!0;return console.error("[claude-mem] Worker failed to become healthy after startup"),!1}catch(o){return console.error(`[claude-mem] Failed to start worker: ${o.message}`),!1}}async function C(o){try{console.error("[claude-mem cleanup] Hook fired",{input:o?{session_id:o.session_id,cwd:o.cwd,reason:o.reason}:null}),o||(console.log("No input provided - this script is designed to run as a Claude Code SessionEnd hook"),console.log(`
Expected input format:`),console.log(JSON.stringify({session_id:"string",cwd:"string",transcript_path:"string",hook_event_name:"SessionEnd",reason:"exit"},null,2)),process.exit(0));let{session_id:e,reason:t}=o;console.error("[claude-mem cleanup] Searching for active SDK session",{session_id:e,reason:t});let s=new l,r=s.findActiveSDKSession(e);if(r||(console.error("[claude-mem cleanup] No active SDK session found",{session_id:e}),s.close(),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)),console.error("[claude-mem cleanup] Active SDK session found",{session_id:r.id,sdk_session_id:r.sdk_session_id,project:r.project,worker_port:r.worker_port}),r.worker_port)try{if(!await k())console.error("[claude-mem cleanup] Worker not available - skipping HTTP cleanup");else{let i=await fetch(`http://127.0.0.1:${r.worker_port}/sessions/${r.id}`,{method:"DELETE",signal:AbortSignal.timeout(5e3)});i.ok?console.error("[claude-mem cleanup] Session deleted successfully via HTTP"):console.error("[claude-mem cleanup] Failed to delete session:",await i.text())}}catch(n){console.error("[claude-mem cleanup] HTTP DELETE error:",n.message)}else console.error("[claude-mem cleanup] No worker port, cannot send DELETE request");try{s.markSessionFailed(r.id),console.error("[claude-mem cleanup] Session marked as failed in database")}catch(n){console.error("[claude-mem cleanup] Failed to mark session as failed:",n)}s.close(),console.error("[claude-mem cleanup] Cleanup completed successfully"),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}catch(e){console.error("[claude-mem cleanup] Unexpected error in hook",{error:e.message,stack:e.stack,name:e.name}),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}}import{stdin as D}from"process";var b="";D.on("data",o=>b+=o);D.on("end",async()=>{try{let o=b.trim()?JSON.parse(b):void 0;await C(o)}catch(o){console.error(`[claude-mem cleanup-hook error: ${o.message}]`),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}});
Expected input format:`),console.log(JSON.stringify({session_id:"string",cwd:"string",transcript_path:"string",hook_event_name:"SessionEnd",reason:"exit"},null,2)),process.exit(0));let{session_id:e,reason:t}=o;console.error("[claude-mem cleanup] Searching for active SDK session",{session_id:e,reason:t});let s=await k();s||console.error("[claude-mem cleanup] Worker not available - skipping HTTP cleanup");let r=new l,n=r.findActiveSDKSession(e);if(n||(console.error("[claude-mem cleanup] No active SDK session found",{session_id:e}),r.close(),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)),console.error("[claude-mem cleanup] Active SDK session found",{session_id:n.id,sdk_session_id:n.sdk_session_id,project:n.project,worker_port:n.worker_port}),n.worker_port&&s)try{let i=await fetch(`http://127.0.0.1:${n.worker_port}/sessions/${n.id}`,{method:"DELETE",signal:AbortSignal.timeout(5e3)});i.ok?console.error("[claude-mem cleanup] Session deleted successfully via HTTP"):console.error("[claude-mem cleanup] Failed to delete session:",await i.text())}catch(i){console.error("[claude-mem cleanup] HTTP DELETE error:",i.message)}else console.error("[claude-mem cleanup] No worker available or no worker port, skipping HTTP cleanup");try{r.markSessionFailed(n.id),console.error("[claude-mem cleanup] Session marked as failed in database")}catch(i){console.error("[claude-mem cleanup] Failed to mark session as failed:",i)}r.close(),console.error("[claude-mem cleanup] Cleanup completed successfully"),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}catch(e){console.error("[claude-mem cleanup] Unexpected error in hook",{error:e.message,stack:e.stack,name:e.name}),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}}import{stdin as D}from"process";var b="";D.on("data",o=>b+=o);D.on("end",async()=>{try{let o=b.trim()?JSON.parse(b):void 0;await C(o)}catch(o){console.error(`[claude-mem cleanup-hook error: ${o.message}]`),console.log('{"continue": true, "suppressOutput": true}'),process.exit(0)}});