Support server health check by http://localhost:<port>/v1/system/healthz (#10150)

### What problem does this PR solve?

Support server health check. Solved issue: #10106

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Billy Bao
2025-09-19 11:11:07 +08:00
committed by GitHub
parent a04c5247ab
commit a24547aa66
5 changed files with 153 additions and 122 deletions

View File

@ -48,31 +48,16 @@ def check_storage() -> tuple[bool, dict]:
return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
def check_chat() -> tuple[bool, dict]:
st = timer()
try:
cfg = getattr(settings, "CHAT_CFG", None)
ok = bool(cfg and cfg.get("factory"))
return ok, {"elapsed": f"{(timer() - st) * 1000.0:.1f}"}
except Exception as e:
return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
def run_health_checks() -> tuple[dict, bool]:
result: dict[str, str | dict] = {}
db_ok, db_meta = check_db()
chat_ok, chat_meta = check_chat()
result["db"] = _ok_nok(db_ok)
if not db_ok:
result.setdefault("_meta", {})["db"] = db_meta
result["chat"] = _ok_nok(chat_ok)
if not chat_ok:
result.setdefault("_meta", {})["chat"] = chat_meta
# Optional probes (do not change minimal contract but exposed for observability)
try:
redis_ok, redis_meta = check_redis()
result["redis"] = _ok_nok(redis_ok)
@ -97,7 +82,8 @@ def run_health_checks() -> tuple[dict, bool]:
except Exception:
result["storage"] = "nok"
all_ok = (result.get("db") == "ok") and (result.get("chat") == "ok")
all_ok = (result.get("db") == "ok") and (result.get("redis") == "ok") and (result.get("doc_engine") == "ok") and (result.get("storage") == "ok")
result["status"] = "ok" if all_ok else "nok"
return result, all_ok