hmo
57377e9dd3
Error investigation (from restored monitoring) found 2 root causes: 1. 'Blocked: script path resolves outside scripts dir' (5+ cron jobs): Jul 17 symlink refactor replaced real scripts with symlinks; the hermes cron scheduler's security check (Path.resolve + relative_to) rejects symlink escape. ALL no_agent script jobs blocked since Jul 17 23:12. FIX: converted 102 symlinks to hardlinks (same inode, resolve() stays inside scripts_dir, single-source still works). Permanent structural fix. 2. HTTP 429 on default profile (知识研究/梦境循环/wiki-self-growth/ evolution-pulse/大脑任务执行): default gateway used ocg-key1 (weekly 100%). FIX: switched default profile to ocg-key6 + added missing provider block. LLM verified working (3.1s). auto_heal extended to actually cover these automatically next time: - PROFILES registry: zhiwei (8643, system svc) + default (8642, user svc) - current_provider/switch_key/_scan_agent_log parameterized by profile - health() now reports llm_provider_default (agent.log scan) - auto_heal: per-profile 429 detection -> best_key -> switch_key(profile) - _ensure_provider_block: injects missing provider credentials from zhiwei config (single source of truth) into target config
45 lines
1.7 KiB
Python
45 lines
1.7 KiB
Python
import json
|
|
|
|
d = json.load(open('/tmp/mofin_health.json'))
|
|
|
|
print("generated_at:", d.get('generated_at'))
|
|
print()
|
|
|
|
# 1. Pipelines with error/warn status
|
|
print("=== PIPELINES (error/warn) ===")
|
|
for p in d.get('pipelines', []):
|
|
if p.get('status') in ('error', 'fail', 'warn'):
|
|
print(f"[{p['status']}] {p.get('name') or p.get('script')} | profile={p.get('profile')} | type={p.get('type')} | schedule={p.get('schedule')} | last_run={p.get('last_run')}")
|
|
|
|
print()
|
|
print("=== FEATURE TREE (non-ok nodes) ===")
|
|
def walk(n, path=''):
|
|
label = n.get('label', '?')
|
|
p = f"{path}/{label}"
|
|
if n.get('status') not in ('ok', None):
|
|
print(f"[{n.get('status')}] {p}")
|
|
for pipe in n.get('pipes', []):
|
|
if pipe.get('status') != 'ok':
|
|
print(f" pipe: [{pipe.get('status')}] {pipe.get('name') or pipe.get('script')} | last_run={pipe.get('last_run')}")
|
|
for c in n.get('children', []):
|
|
walk(c, p)
|
|
walk(d.get('feature_tree', {}))
|
|
|
|
print()
|
|
print("=== DATA ENTITIES (orphan/write_only) ===")
|
|
for e in d.get('entities', []):
|
|
if e.get('flow_status') in ('orphan', 'write_only'):
|
|
print(f"[{e['flow_status']}] {e['name']} | rows={e.get('rows')} | writers={e.get('writers')} | readers={e.get('readers')} | {e.get('desc','')[:60]}")
|
|
|
|
print()
|
|
print("=== ARCHITECTURE violations ===")
|
|
arch = d.get('architecture', {})
|
|
print("violation_count:", arch.get('violation_count'))
|
|
for v in (arch.get('price_api_violations') or [])[:10]:
|
|
print(f" {v.get('script')} L{v.get('line')}")
|
|
|
|
print()
|
|
print("=== JSON files with warn ===")
|
|
for j in d.get('json_files', []):
|
|
if j.get('warn'):
|
|
print(f"[warn] {j['name']} | {j.get('desc','')[:60]} | readers={j.get('readers')}") |