skypilot-nightly 1.0.0.dev20250305__tar.gz → 1.0.0.dev20250307__tar.gz

{skypilot_nightly-1.0.0.dev20250305/skypilot_nightly.egg-info → skypilot_nightly-1.0.0.dev20250307}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: skypilot-nightly
-Version: 1.0.0.dev20250305
+Version: 1.0.0.dev20250307
 Summary: SkyPilot: An intercloud broker for the clouds
 Author: SkyPilot Team
 License: Apache 2.0

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/__init__.py

@@ -5,7 +5,7 @@ from typing import Optional
 import urllib.request
 
 # Replaced with the current commit when building the wheels.
-_SKYPILOT_COMMIT_SHA = '296a22e868b9bdf1faccbe3effbfb858a5a05905'
+_SKYPILOT_COMMIT_SHA = 'f6a65c2ea0ac00976d06e47c46e8df1297cb70a2'
 
 
 def _get_git_commit():
@@ -35,7 +35,7 @@ def _get_git_commit():
 
 
 __commit__ = _get_git_commit()
-__version__ = '1.0.0.dev20250305'
+__version__ = '1.0.0.dev20250307'
 __root_dir__ = os.path.dirname(os.path.abspath(__file__))
 
 

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/backends/wheel_utils.py

@@ -17,7 +17,7 @@ import re
 import shutil
 import subprocess
 import tempfile
-from typing import Tuple
+from typing import Optional, Tuple
 
 import filelock
 from packaging import version
@@ -149,16 +149,29 @@ def build_sky_wheel() -> Tuple[pathlib.Path, str]:
         - wheel_hash: The wheel content hash.
     """
 
-    def _get_latest_modification_time(path: pathlib.Path) -> float:
+    def _get_latest_modification_time(path: pathlib.Path) -> Optional[float]:
+        max_time = -1.
         if not path.exists():
-            return -1.
-        try:
-            return max(
-                os.path.getmtime(os.path.join(root, f))
-                for root, dirs, files in os.walk(path)
-                for f in (*dirs, *files))
-        except ValueError:
-            return -1.
+            return max_time
+        for root, dirs, files in os.walk(path):
+            # Prune __pycache__ directories to prevent walking into them and
+            # exclude them from processing
+            if '__pycache__' in dirs:
+                dirs.remove('__pycache__')
+            # Filter out .pyc files
+            filtered_files = [f for f in files if not f.endswith('.pyc')]
+            # Process remaining directories and files
+            for entry in (*dirs, *filtered_files):
+                entry_path = os.path.join(root, entry)
+                try:
+                    mtime = os.path.getmtime(entry_path)
+                    if mtime > max_time:
+                        max_time = mtime
+                except OSError:
+                    # Handle cases where file might have been deleted after
+                    # listing
+                    return None
+        return max_time
 
     # This lock prevents that the wheel is updated while being copied.
     # Although the current caller already uses a lock, we still lock it here
@@ -170,10 +183,12 @@ def build_sky_wheel() -> Tuple[pathlib.Path, str]:
         last_modification_time = _get_latest_modification_time(SKY_PACKAGE_PATH)
         last_wheel_modification_time = _get_latest_modification_time(WHEEL_DIR)
 
-        # Only build wheels if the wheel is outdated or wheel does not exist
-        # for the requested version.
-        if (last_wheel_modification_time < last_modification_time) or not any(
-                WHEEL_DIR.glob(f'**/{_WHEEL_PATTERN}')):
+        # Only build wheels if the wheel is outdated, wheel does not exist
+        # for the requested version, or files were deleted during checking.
+        if ((last_modification_time is None or
+             last_wheel_modification_time is None) or
+            (last_wheel_modification_time < last_modification_time) or
+                not any(WHEEL_DIR.glob(f'**/{_WHEEL_PATTERN}'))):
             if not WHEEL_DIR.exists():
                 WHEEL_DIR.mkdir(parents=True, exist_ok=True)
             latest_wheel = _build_sky_wheel()

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/cli.py

@@ -1874,7 +1874,7 @@ def status(verbose: bool, refresh: bool, ip: bool, endpoints: bool,
                 num_in_progress_jobs, msg = _handle_jobs_queue_request(
                     managed_jobs_queue_request_id,
                     show_all=False,
-                    show_user=False,
+                    show_user=all_users,
                     limit_num_jobs_to_show=not all,
                     is_called_by_user=False)
             except KeyboardInterrupt:

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/client/cli.py

@@ -1874,7 +1874,7 @@ def status(verbose: bool, refresh: bool, ip: bool, endpoints: bool,
                 num_in_progress_jobs, msg = _handle_jobs_queue_request(
                     managed_jobs_queue_request_id,
                     show_all=False,
-                    show_user=False,
+                    show_user=all_users,
                     limit_num_jobs_to_show=not all,
                     is_called_by_user=False)
             except KeyboardInterrupt:

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/clouds/service_catalog/data_fetchers/fetch_vast.py

@@ -9,8 +9,8 @@ import collections
 import csv
 import json
 import math
+import os
 import re
-import sys
 from typing import Any, Dict, List
 
 from sky.adaptors import vast
@@ -38,6 +38,10 @@ def dot_get(d: dict, key: str) -> Any:
 
 if __name__ == '__main__':
     seen = set()
+    # InstanceList is the buffered list to emit to
+    # the CSV
+    csvList = []
+
     # InstanceType and gpuInfo are basically just stubs
     # so that the dictwriter is happy without weird
     # code.
@@ -47,8 +51,6 @@ if __name__ == '__main__':
                    ('cpu_ram', 'MemoryGiB'), ('gpu_name', 'GpuInfo'),
                    ('search.totalHour', 'Price'), ('min_bid', 'SpotPrice'),
                    ('geolocation', 'Region'))
-    writer = csv.DictWriter(sys.stdout, fieldnames=[x[1] for x in mapped_keys])
-    writer.writeheader()
 
     # Vast has a wide variety of machines, some of
     # which will have less diskspace and network
@@ -141,7 +143,15 @@ if __name__ == '__main__':
                 printstub = f'{stub}#print'
                 if printstub not in seen:
                     instance['SpotPrice'] = f'{maxBid:.2f}'
-                    writer.writerow(instance)
+                    csvList.append(instance)
                     seen.add(printstub)
             else:
                 seen.add(stub)
+
+    os.makedirs('vast', exist_ok=True)
+    with open('vast/vms.csv', 'w', newline='', encoding='utf-8') as csvfile:
+        writer = csv.DictWriter(csvfile, fieldnames=[x[1] for x in mapped_keys])
+        writer.writeheader()
+
+        for instance in csvList:
+            writer.writerow(instance)

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/jobs/server/core.py

@@ -157,6 +157,7 @@ def launch(
             'modified_catalogs':
                 service_catalog_common.get_modified_catalog_file_mounts(),
             'dashboard_setup_cmd': managed_job_constants.DASHBOARD_SETUP_CMD,
+            'dashboard_user_id': common.SERVER_ID,
             **controller_utils.shared_controller_vars_to_fill(
                 controller_utils.Controllers.JOBS_CONTROLLER,
                 remote_user_config_path=remote_user_config_path,
@@ -305,10 +306,9 @@ def _maybe_restart_controller(
     with rich_utils.safe_status(
             ux_utils.spinner_message('Starting dashboard...')):
         runner = handle.get_command_runners()[0]
-        user_hash = common_utils.get_user_hash()
         runner.run(
             f'export '
-            f'{skylet_constants.USER_ID_ENV_VAR}={user_hash!r}; '
+            f'{skylet_constants.USER_ID_ENV_VAR}={common.SERVER_ID!r}; '
             f'{managed_job_constants.DASHBOARD_SETUP_CMD}',
             stream_logs=True,
         )
@@ -341,6 +341,8 @@ def queue(refresh: bool,
                 'status': (sky.jobs.ManagedJobStatus) of the job,
                 'cluster_resources': (str) resources of the cluster,
                 'region': (str) region of the cluster,
+                'user_name': (Optional[str]) job creator's user name,
+                'user_hash': (str) job creator's user hash,
             }
         ]
     Raises:

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/jobs/server/server.py

@@ -159,6 +159,9 @@ async def dashboard(request: fastapi.Request,
             except Exception as e:  # pylint: disable=broad-except
                 # We catch all exceptions to gracefully handle unknown
                 # errors and retry or raise an HTTPException to the client.
+                # Assume an exception indicates that the dashboard connection
+                # is stale - remove it so that a new one is created.
+                dashboard_utils.remove_dashboard_session(user_hash)
                 msg = (
                     f'Dashboard connection attempt {attempt + 1} failed with '
                     f'{common_utils.format_exception(e, use_bracket=True)}')

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/jobs/utils.py

@@ -735,6 +735,10 @@ def stream_logs_by_id(job_id: int, follow: bool = True) -> Tuple[str, int]:
         managed_job_status = managed_job_state.get_status(job_id)
         assert managed_job_status is not None, job_id
 
+    if not follow and not managed_job_status.is_terminal():
+        # The job is not in terminal state and we are not following,
+        # just return.
+        return '', exceptions.JobExitCode.SUCCEEDED
     logger.info(
         ux_utils.finishing_message(f'Managed job finished: {job_id} '
                                    f'(status: {managed_job_status.value}).'))
@@ -914,6 +918,10 @@ def load_managed_job_queue(payload: str) -> List[Dict[str, Any]]:
     jobs = message_utils.decode_payload(payload)
     for job in jobs:
         job['status'] = managed_job_state.ManagedJobStatus(job['status'])
+        if 'user_hash' in job and job['user_hash'] is not None:
+            # Skip jobs that do not have user_hash info.
+            # TODO(cooperc): Remove check before 0.12.0.
+            job['user_name'] = global_user_state.get_user(job['user_hash']).name
     return jobs
 
 
@@ -1043,16 +1051,21 @@ def format_job_table(
     def get_user_column_values(task: Dict[str, Any]) -> List[str]:
         user_values: List[str] = []
         if show_user:
+            user_name = '-'  # default value
+
+            task_user_name = task.get('user_name', None)
+            task_user_hash = task.get('user_hash', None)
+            if task_user_name is not None:
+                user_name = task_user_name
+            elif task_user_hash is not None:
+                # Fallback to the user hash if we are somehow missing the name.
+                user_name = task_user_hash
 
-            user_name = '-'
-            user_hash = task.get('user_hash', None)
-            if user_hash:
-                user = global_user_state.get_user(user_hash)
-                user_name = user.name if user.name else '-'
             user_values = [user_name]
 
             if show_all:
-                user_values.append(user_hash if user_hash is not None else '-')
+                user_values.append(
+                    task_user_hash if task_user_hash is not None else '-')
 
         return user_values
 

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/server/server.py

@@ -45,6 +45,7 @@ from sky.utils import admin_policy_utils
 from sky.utils import common as common_lib
 from sky.utils import common_utils
 from sky.utils import dag_utils
+from sky.utils import env_options
 from sky.utils import status_lib
 
 # pylint: disable=ungrouped-imports
@@ -65,6 +66,10 @@ def _add_timestamp_prefix_for_server_logs() -> None:
     # Add date prefix to the log message printed by loggers under
     # server.
     stream_handler = logging.StreamHandler(sys.stdout)
+    if env_options.Options.SHOW_DEBUG_INFO.get():
+        stream_handler.setLevel(logging.DEBUG)
+    else:
+        stream_handler.setLevel(logging.INFO)
     stream_handler.flush = sys.stdout.flush  # type: ignore
     stream_handler.setFormatter(sky_logging.FORMATTER)
     server_logger.addHandler(stream_handler)

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/templates/jobs-controller.yaml.j2

@@ -39,9 +39,7 @@ setup: |
   After=network.target
 
   [Service]
-  Environment="PATH={{ sky_python_env_path }}:\$PATH"
-  Environment="SKYPILOT_USER_ID={{controller_envs.SKYPILOT_USER_ID}}"
-  Environment="SKYPILOT_USER={{controller_envs.SKYPILOT_USER}}"
+  Environment="SKYPILOT_USER_ID={{ dashboard_user_id }}"
   Restart=always
   StandardOutput=append:/home/$USER/.sky/job-dashboard.log
   StandardError=append:/home/$USER/.sky/job-dashboard.log
@@ -51,6 +49,7 @@ setup: |
   WantedBy=default.target
   EOF
 
+  export SKYPILOT_USER_ID="{{ dashboard_user_id }}"
   {{ dashboard_setup_cmd }}
 
 run: |

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/utils/command_runner.py

@@ -531,8 +531,8 @@ class SSHCommandRunner(CommandRunner):
         if port_forward is not None:
             for local, remote in port_forward:
                 logger.info(
-                    f'Forwarding port {local} to port {remote} on localhost.')
-                ssh += ['-NL', f'{remote}:localhost:{local}']
+                    f'Forwarding local port {local} to remote port {remote}.')
+                ssh += ['-NL', f'{local}:localhost:{remote}']
         if self._docker_ssh_proxy_command is not None:
             docker_ssh_proxy_command = self._docker_ssh_proxy_command(ssh)
         else:

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307}/sky/utils/rich_utils.py

@@ -230,15 +230,53 @@ def decode_rich_status(
     decoding_status = None
     try:
         last_line = ''
+        # Buffer to store incomplete UTF-8 bytes between chunks
+        undecoded_buffer = b''
+
         # Iterate over the response content in chunks. We do not use iter_lines
         # because it will strip the trailing newline characters, causing the
         # progress bar ending with `\r` becomes a pyramid.
-        for encoded_msg in response.iter_content(chunk_size=None):
-            if encoded_msg is None:
+        for chunk in response.iter_content(chunk_size=None):
+            if chunk is None:
                 return
-            encoded_msg = encoded_msg.decode('utf-8')
+
+            # Append the new chunk to any leftover bytes from previous iteration
+            current_bytes = undecoded_buffer + chunk
+            undecoded_buffer = b''
+
+            # Try to decode the combined bytes
+            try:
+                encoded_msg = current_bytes.decode('utf-8')
+            except UnicodeDecodeError as e:
+                # Check if this is potentially an incomplete sequence at the end
+                if e.start > 0:
+                    # Decode the valid part
+                    encoded_msg = current_bytes[:e.start].decode('utf-8')
+
+                    # Check if the remaining bytes are likely a partial char
+                    # or actually invalid UTF-8
+                    remaining_bytes = current_bytes[e.start:]
+                    if len(remaining_bytes) < 4:  # Max UTF-8 char is 4 bytes
+                        # Likely incomplete - save for next chunk
+                        undecoded_buffer = remaining_bytes
+                    else:
+                        # Likely invalid - replace with replacement character
+                        encoded_msg += remaining_bytes.decode('utf-8',
+                                                              errors='replace')
+                        undecoded_buffer = b''
+                else:
+                    # Error at the very beginning of the buffer - invalid UTF-8
+                    encoded_msg = current_bytes.decode('utf-8',
+                                                       errors='replace')
+                    undecoded_buffer = b''
+
             lines = encoded_msg.splitlines(keepends=True)
 
+            # Skip processing if lines is empty to avoid IndexError
+            if not lines:
+                continue
+
+            # Append any leftover text from previous chunk to first line
             lines[0] = last_line + lines[0]
             last_line = lines[-1]
             # If the last line is not ended with `\r` or `\n` (with ending

{skypilot_nightly-1.0.0.dev20250305 → skypilot_nightly-1.0.0.dev20250307/skypilot_nightly.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: skypilot-nightly
-Version: 1.0.0.dev20250305
+Version: 1.0.0.dev20250307
 Summary: SkyPilot: An intercloud broker for the clouds
 Author: SkyPilot Team
 License: Apache 2.0