fix: fix mount (#1001)

* docs: document extra_volumes dict format in DockerConf

* feat: accept dict values in extra_volumes to specify bind and mode

* fix: skip invalid PDF reports to prevent infinite loop

* from break to raise self.LoopTerminationError

* format with black

---------

Co-authored-by: Young <[email protected]>

Author: SunsetWolf

rdagent/app/qlib_rd_loop/factor_from_report.py

@@ -105,14 +105,21 @@ def __init__(self, report_folder: str = None):
             self.judge_pdf_data_items = [i for i in Path(report_folder).rglob("*.pdf")]
 
         self.loop_n = min(len(self.judge_pdf_data_items), FACTOR_FROM_REPORT_PROP_SETTING.report_limit)
+        self.shift_report = (
+            0  # some reports does not contain viable factor, so we ship some of them to avoid infinite loop
+        )
 
     async def direct_exp_gen(self, prev_out: dict[str, Any]):
         while True:
             if self.get_unfinished_loop_cnt(self.loop_idx) < RD_AGENT_SETTINGS.get_max_parallel():
-                report_file_path = self.judge_pdf_data_items[self.loop_idx]
+                report_file_path = self.judge_pdf_data_items[self.loop_idx + self.shift_report]
                 logger.info(f"Processing number {self.loop_idx} report: {report_file_path}")
                 exp = extract_hypothesis_and_exp_from_reports(str(report_file_path))
                 if exp is None:
+                    self.shift_report += 1
+                    self.loop_n -= 1
+                    if self.loop_n < 0:  # NOTE: on every step, we self.loop_n -= 1 at first.
+                        raise self.LoopTerminationError("Reach stop criterion and stop loop")
                     continue
                 exp.based_experiments = [QlibFactorExperiment(sub_tasks=[], hypothesis=exp.hypothesis)] + [
                     t[0] for t in self.trace.hist if t[1]

rdagent/utils/env.py

@@ -602,6 +602,10 @@ class DockerConf(EnvConf):
     default_entry: str  # the entry point of the image
 
     extra_volumes: dict = {}
+    """It accept a dict of volumes, which can be either
+    {<host_path>: <container_path>} or
+    {<host_path>: {"bind": <container_path>, "mode": <mode, ro/rw/default is extra_volume_mode>}}
+    """
     extra_volume_mode: str = "ro"  # by default. only the mount_path should be writable, others are changed to read-only
     # Sometime, we need maintain some extra data for the workspace.
     # And the extra data may be shared and the downloading can be time consuming.
@@ -662,7 +666,9 @@ class QlibDockerConf(DockerConf):
     image: str = "local_qlib:latest"
     mount_path: str = "/workspace/qlib_workspace/"
     default_entry: str = "qrun conf.yaml"
-    extra_volumes: dict = {str(Path("~/.qlib/").expanduser().resolve().absolute()): "/root/.qlib/"}
+    extra_volumes: dict = {
+        str(Path("~/.qlib/").expanduser().resolve().absolute()): {"bind": "/root/.qlib/", "mode": "rw"}
+    }
     shm_size: str | None = "16g"
     enable_gpu: bool = True
     enable_cache: bool = False
@@ -854,12 +860,12 @@ def _run_ret_code(
 
         if self.conf.extra_volumes is not None:
             for lp, rp in self.conf.extra_volumes.items():
-                volumes[lp] = {"bind": rp, "mode": self.conf.extra_volume_mode}
+                volumes[lp] = rp if isinstance(rp, dict) else {"bind": rp, "mode": self.conf.extra_volume_mode}
             cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full"
             Path(cache_path).mkdir(parents=True, exist_ok=True)
             volumes[cache_path] = {"bind": T("scenarios.data_science.share:scen.cache_path").r(), "mode": "rw"}
         for lp, rp in running_extra_volume.items():
-            volumes[lp] = {"bind": rp, "mode": self.conf.extra_volume_mode}
+            volumes[lp] = rp if isinstance(rp, dict) else {"bind": rp, "mode": self.conf.extra_volume_mode}
 
         volumes = normalize_volumes(cast(dict[str, str | dict[str, str]], volumes), self.conf.mount_path)