thethreemagi/bookapp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto-commit: Fix spinning logs — API timeouts + reliable Huey consumer start

Browse Source 
Root causes of indefinite spinning during book create/generate:

1. ai/models.py — ResilientModel.generate_content() had no timeout: a
   stalled Gemini API call would block the thread forever. Now injects
   request_options={"timeout": 180} into every call. Also removed the
   dangerous init_models(force=True) call inside the retry handler, which
   was making a second network call during an existing API failure.

2. ai/setup.py — genai.list_models() calls in get_optimal_model(),
   select_best_models(), and init_models() had no timeout. Added
   request_options={"timeout": 30} to all three calls so model init
   fails fast rather than hanging indefinitely.

3. web/app.py — Huey task consumer only started inside
   `if __name__ == "__main__":`, meaning tasks queued via flask run,
   gunicorn, or other WSGI runners were never executed (status stuck at
   "queued" forever). Moved consumer start to module level with a
   WERKZEUG_RUN_MAIN guard to prevent double-start under the reloader.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mike Wichers
2026-02-21 02:16:39 -05:00
parent 85f1290f02
commit 1f799227d9
3 changed files with 36 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
ai/models.py
View File

@@ -47,6 +47,9 @@ class ResilientModel:
_TOKEN_WARN_LIMIT = 30_000
# Timeout in seconds for all generate_content calls (prevents indefinite hangs)
_GENERATION_TIMEOUT = 180
def generate_content(self, *args, **kwargs):
# Estimate payload size and warn if it exceeds the safe limit
if args:
@@ -64,22 +67,22 @@ class ResilientModel:
max_retries = 3
base_delay = 5
# Inject timeout into request_options without overwriting caller-supplied values
rq_opts = kwargs.pop("request_options", {}) or {}
if isinstance(rq_opts, dict):
rq_opts.setdefault("timeout", self._GENERATION_TIMEOUT)
while True:
try:
return self.model.generate_content(*args, **kwargs)
return self.model.generate_content(*args, **kwargs, request_options=rq_opts)
except Exception as e:
err_str = str(e).lower()
is_retryable = "429" in err_str or "quota" in err_str or "500" in err_str or "503" in err_str or "504" in err_str or "deadline" in err_str or "internal error" in err_str
is_timeout = "timeout" in err_str or "deadline" in err_str or "timed out" in err_str
is_retryable = is_timeout or "429" in err_str or "quota" in err_str or "500" in err_str or "503" in err_str or "504" in err_str or "internal error" in err_str
if is_retryable and retries < max_retries:
delay = base_delay * (2 ** retries)
utils.log("SYSTEM", f"⚠️ Quota error on {self.role} ({self.name}). Retrying in {delay}s...")
utils.log("SYSTEM", f"⚠️ {'Timeout' if is_timeout else 'API error'} on {self.role} ({self.name}). Retrying in {delay}s... ({retries + 1}/{max_retries})")
time.sleep(delay)
if retries == 0:
utils.log("SYSTEM", "Attempting to re-optimize models to find alternative...")
from ai import setup as _setup
_setup.init_models(force=True)
retries += 1
continue
raise e