SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(litellm-health): retry single-host model probes once at a longer timeout #121

Merged
abiba-bot merged 2 commits from fix/litellm-health-retry-timeout-20260919 into master 2026-09-19 10:57:40 +00:00
Conversation 0 Commits 2 Files Changed 1
+7 -2
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit aee2de25ac - Show all commits
scripts/litellm-health-check.py
+7 -2
View File
@@ -124,8 +124,10 @@ def check_model_probes():
data='{"model":"' + model + '","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
timeout=30)
first_kind = None # Track first attempt's failure kind
if code == 000 and failure_kind:
# Retry once with longer timeout (45s) before declaring failure
first_kind = failure_kind
time.sleep(1)
code, failure_kind = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
method="POST",
@@ -134,8 +136,11 @@ def check_model_probes():
timeout=45)
if code == 000 and failure_kind:
# Both attempts failed - report with duration
results.append((model, False, "probe-failed: " + model + " " + failure_kind + " (timeout after retry, 45s)"))
# Both attempts failed - report both kinds
if first_kind:
results.append((model, False, "probe-failed: " + model + " " + first_kind + " then " + failure_kind + " (2 attempts)"))
else:
results.append((model, False, "probe-failed: " + model + " " + failure_kind))
elif code == 200:
results.append((model, True, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=" + model + ")"))
elif code in (401, 403):