Fix strategy scheduling and crawler limits

Co-Authored-By: Claude <noreply@anthropic.com>

app/clients/modelhub.py

@@ -142,7 +142,7 @@ class ModelHubClient:
             message = body.get("message", "")
             if code == 0 and message == "ok":
                 result = "success"
-            elif code == 40000 and "正在验证中" in message:
+            elif "请勿重复提交" in message or "已经被验证成功" in message or "正在验证中" in message:
                 result = "conflict"
             elif code == 60007:
                 result = "queue_full"

app/scheduler/downloader.py

@@ -22,6 +22,8 @@ class Downloader:
                 active_self_slot=active,
                 next_poll_at=future_seconds(self.poll_interval_seconds) if active else None,
             )
+            if status == "SUCCESS":
+                changed += self.repo.mark_waiting_download_tasks_ready(download["model_id"], download["source"])
             changed += 1
         return changed
 

app/scheduler/loop.py

@@ -92,8 +92,6 @@ class StrategyLoop:
         released = self.submitter.release_queue_full_backoff()
         ready = self.mark_ready_tasks()
         submitted = self.submitter.submit_due()
-        started_downloads = 0
-        if submitted == 0 and ready == 0:
         started_downloads = self.downloader.maybe_start_self_downloads()
         return {
             "crawled_not_adapted": crawler_stats["not_adapted"],

app/settings.py

@@ -81,11 +81,11 @@ class Settings:
     target_task_level: str = "文本生成"
     modelhub_page_size: int = 100
     crawler_refresh_seconds: int = 3600
-    crawler_max_pages: int = 0
+    crawler_max_pages: int = 400
 
     enable_download_success_crawler: bool = True
     download_success_page_size: int = 50
-    download_success_max_pages: int = 0
+    download_success_max_pages: int = 100
 
     config_file_loaded: str = ""
 
@@ -140,10 +140,10 @@ def load_settings(require_secrets: bool = True) -> Settings:
         target_task_level=str(_value(config, "TARGET_TASK_LEVEL", "文本生成")),
         modelhub_page_size=_int_value(config, "MODELHUB_PAGE_SIZE", 100),
         crawler_refresh_seconds=_int_value(config, "CRAWLER_REFRESH_SECONDS", 3600),
-        crawler_max_pages=_int_value(config, "CRAWLER_MAX_PAGES", 0),
+        crawler_max_pages=_int_value(config, "CRAWLER_MAX_PAGES", 400),
         enable_download_success_crawler=_bool_value(config, "ENABLE_DOWNLOAD_SUCCESS_CRAWLER", True),
         download_success_page_size=_int_value(config, "DOWNLOAD_SUCCESS_PAGE_SIZE", 50),
-        download_success_max_pages=_int_value(config, "DOWNLOAD_SUCCESS_MAX_PAGES", 0),
+        download_success_max_pages=_int_value(config, "DOWNLOAD_SUCCESS_MAX_PAGES", 100),
         config_file_loaded=loaded_path,
     )
     if require_secrets:

app/storage/repositories.py

@@ -233,6 +233,25 @@ class Repository:
         )
         return list(cursor.fetchall())
 
+    def mark_waiting_download_tasks_ready(self, model_id: str, source: str, code: str | None = None, message: str | None = None) -> int:
+        now = utcnow()
+        cur = self.conn.execute(
+            """
+            UPDATE tasks SET
+                status = 'ready_to_submit',
+                last_error_code = ?,
+                last_error_message = ?,
+                next_attempt_at = NULL,
+                updated_at = ?
+            WHERE model_id = ?
+              AND status = 'waiting_download'
+            """,
+            (code, message, now, model_id),
+        )
+        self.conn.commit()
+        self.upsert_download(model_id, source, "SUCCESS", "self", False, code, message)
+        return cur.rowcount
+
     def record_submission_attempt(
         self,
         task_id: int,