feat(launcher): prune old run logs (L-2)

src/agents/launcher.py

@@ -16,6 +16,62 @@ from ..plane_sync import notify_stage_change as plane_notify_stage, add_comment
 logger = logging.getLogger("orchestrator.launcher")
 
 
+def prune_run_logs(runs_dir, keep_days=30, keep_max=500, active_paths=None):
+    """L-2: best-effort rotation of per-run logs (<runs_dir>/*.log).
+
+    A log file is removed if it is older than keep_days OR it is not within the
+    keep_max most-recent logs (whichever condition is met first). Only *.log
+    files directly inside runs_dir are considered; non-.log files and
+    subdirectories are never touched. Files whose path is in active_paths (the
+    currently running log) are always kept.
+
+    Returns the number of files removed. Never raises: any error is logged and
+    swallowed so log rotation can never bring the app down.
+    """
+    removed = 0
+    try:
+        active = set()
+        for ap in (active_paths or []):
+            try:
+                active.add(os.path.realpath(ap))
+            except Exception:
+                active.add(ap)
+
+        if not os.path.isdir(runs_dir):
+            return 0
+
+        logs = []
+        for name in os.listdir(runs_dir):
+            if not name.endswith(".log"):
+                continue
+            path = os.path.join(runs_dir, name)
+            if not os.path.isfile(path):
+                continue
+            if os.path.realpath(path) in active:
+                continue
+            try:
+                mtime = os.path.getmtime(path)
+            except OSError:
+                continue
+            logs.append((path, mtime))
+
+        logs.sort(key=lambda t: t[1], reverse=True)
+
+        cutoff = time.time() - keep_days * 86400
+        for idx, (path, mtime) in enumerate(logs):
+            too_old = mtime < cutoff
+            over_max = idx >= keep_max
+            if too_old or over_max:
+                try:
+                    os.remove(path)
+                    removed += 1
+                except OSError as e:
+                    logger.warning(f"prune_run_logs: failed to remove {path}: {e}")
+    except Exception as e:
+        logger.warning(f"prune_run_logs failed for {runs_dir}: {e}")
+    return removed
+
+
 class AgentLauncher:
     """Launch Claude CLI agents directly (binary mounted into container)."""
 

src/config.py

@@ -66,6 +66,15 @@ class Settings(BaseSettings):
     agent_kill_grace_seconds: int = 20
     agent_timeout_overrides_json: str = ""
 
+    # L-2: run-log rotation. Old per-run logs in <data>/runs/*.log are pruned at
+    # app startup (best-effort). A *.log is removed if it is older than
+    # log_keep_days OR not within the log_keep_max most-recent logs (whichever
+    # hits first). Only *.log files are touched; the active run log is skipped.
+    #   log_keep_days -> max age in days (env ORCH_LOG_KEEP_DAYS).
+    #   log_keep_max  -> max number of newest logs to retain (env ORCH_LOG_KEEP_MAX).
+    log_keep_days: int = 30
+    log_keep_max: int = 500
+
 
     # Telegram notifications
     telegram_bot_token: str = ""

src/main.py

@@ -60,6 +60,22 @@ async def lifespan(app: FastAPI):
     if requeued:
         log.warning(f"Queue-recovery: requeued {requeued} running job(s) after restart")
 
+    # L-2: rotate old per-run logs at startup (best-effort; never fatal).
+    try:
+        import os as _os
+        from .config import settings as _settings
+        from .agents.launcher import prune_run_logs
+        _runs_dir = _os.path.join(_os.path.dirname(_settings.db_path), "runs")
+        _removed = prune_run_logs(
+            _runs_dir,
+            keep_days=_settings.log_keep_days,
+            keep_max=_settings.log_keep_max,
+        )
+        if _removed:
+            log.info(f"Log rotation: pruned {_removed} old run log(s) from {_runs_dir}")
+    except Exception as e:
+        log.warning(f"Log rotation skipped: {e}")
+
     # Start the background job-queue worker (ORCH-1).
     from .queue_worker import worker
     worker.start()