Merge pull request #18 from madhura68/feat/per-job-log-symlink

feat(logs): per-job log-symlink jobs/<job_id>.log (IDEA-063)

bin/log-cleanup.sh

@@ -18,4 +18,9 @@ find "${AGENT_LOG_DIR}" -type f \
     \( -name '*.log' -o -name '*.log.gz' -o -name '*.txt' -o -name '*.json' \) \
     -mtime "+${AGENT_LOG_HARD_DELETE_DAYS}" -delete 2>/dev/null || true
 
+# Prune dangling per-job symlinks: jobs/<job_id>.log -> runs/<ts>.log waarvan
+# het doel door rotatie is gegzipt of verwijderd. De -type f hierboven raakt
+# symlinks niet, dus broken links worden hier expliciet opgeruimd (-xtype l).
+find "${AGENT_LOG_DIR}/jobs" -maxdepth 1 -xtype l -delete 2>/dev/null || true
+
 find "${AGENT_LOG_DIR}/jobs" -mindepth 1 -type d -empty -delete 2>/dev/null || true

bin/run-agent.sh

@@ -68,7 +68,9 @@ while true; do
     # claimt zelf via tryClaimJob, leest JobConfig (PBI-67), bouwt de
     # juiste Claude CLI-args, spawnt 'claude', wacht, sluit af.
     set +e
-    tsx /opt/agent/bin/run-one-job.ts > "${run_log}" 2>&1
+    # RUN_LOG laat run-one-job.ts een jobs/<job_id>.log symlink leggen naar
+    # dit run-log, zodat de output van een job op job-id vindbaar is.
+    RUN_LOG="${run_log}" tsx /opt/agent/bin/run-one-job.ts > "${run_log}" 2>&1
     exit_code=$?
     set -e
 

bin/run-one-job.ts

@@ -22,7 +22,8 @@
 //   3  = TOKEN_EXPIRED detected → run-agent.sh schrijft TOKEN_EXPIRED marker
 
 import { spawn, spawnSync } from 'node:child_process'
-import { mkdirSync, rmSync, writeFileSync } from 'node:fs'
+import { mkdirSync, rmSync, symlinkSync, writeFileSync } from 'node:fs'
+import { basename, join } from 'node:path'
 
 import { Client as PgClient } from 'pg'
 
@@ -196,6 +197,25 @@ async function main(): Promise<number> {
 
     log(`claimed job_id=${jobId}`)
 
+    // Per-job log: symlink jobs/<jobId>.log -> the runs/<timestamp>.log of
+    // this iteration. runs/ files are timestamp-named, so without this a job's
+    // output is only findable by grepping. run-agent.sh passes the run-log
+    // path via RUN_LOG. Relative target so it survives the host bind-mount.
+    // Best-effort — never fail the job over a log convenience. Dangling links
+    // (after the runs/ file is gzipped/deleted) are pruned by log-cleanup.sh.
+    const runLog = process.env.RUN_LOG
+    if (runLog) {
+      try {
+        const jobsDir = join(process.env.AGENT_LOG_DIR ?? '/var/log/agent', 'jobs')
+        mkdirSync(jobsDir, { recursive: true })
+        const linkPath = join(jobsDir, `${jobId}.log`)
+        rmSync(linkPath, { force: true })
+        symlinkSync(join('..', 'runs', basename(runLog)), linkPath)
+      } catch (err) {
+        log(`per-job log symlink skipped for ${jobId}: ${(err as Error).message}`)
+      }
+    }
+
     // 3. Resolve full context.
     let ctx: Awaited<ReturnType<typeof getFullJobContext>> = null
     try {