urun-cli 0.6.0__tar.gz → 0.6.1__tar.gz

{urun_cli-0.6.0 → urun_cli-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: urun-cli
-Version: 0.6.0
+Version: 0.6.1
 Summary: End-user CLI for deploying apps to urun
 Project-URL: Homepage, https://urun.sh
 Project-URL: Repository, https://github.com/urun-sh/urun-cli
@@ -371,6 +371,17 @@ Enable a disabled app and bring it back online:
 urun app enable lingbot-handle
 ```
 
+If `urun deploy` or `urun dev --attach` reports that a function was paused
+after repeated startup failures, inspect its runtime logs before overriding
+the safety pause. Then explicitly resume every paused function:
+
+```bash
+urun app enable rapid-clips --force
+```
+
+`--force` may restart a known-crashing function; it does not change the
+platform's automatic pause policy.
+
 Stop a queued, starting, or live session:
 
 ```bash

{urun_cli-0.6.0 → urun_cli-0.6.1}/README.md

@@ -349,6 +349,17 @@ Enable a disabled app and bring it back online:
 urun app enable lingbot-handle
 ```
 
+If `urun deploy` or `urun dev --attach` reports that a function was paused
+after repeated startup failures, inspect its runtime logs before overriding
+the safety pause. Then explicitly resume every paused function:
+
+```bash
+urun app enable rapid-clips --force
+```
+
+`--force` may restart a known-crashing function; it does not change the
+platform's automatic pause policy.
+
 Stop a queued, starting, or live session:
 
 ```bash

{urun_cli-0.6.0 → urun_cli-0.6.1}/pyproject.toml

@@ -10,24 +10,17 @@ build-backend = "hatchling.build"
 
 [project]
 name = "urun-cli"
-# Cut a release for the 11 commits stranded since v0.5.32 (2026-08-20).
+# Cut the paused-function recovery fixes merged after v0.6.0.
 #
 # WHY THIS IS EDITED BY HAND. [tool.semantic_release] below is fully
 # configured -- conventional commit parser, version_toml pointing here, tag
 # format, changelog templates -- but NOTHING invokes it: `grep -rn
 # semantic.release .github/workflows/` matches nothing. release.yaml only
 # READS this value and skips publishing when the matching tag already exists,
-# so the version has been frozen since v0.5.32 was tagged and every merge
-# after it published nothing. CHANGELOG.md stopping at 0.5.4 is the same gap
-# seen from the other end. Wiring semantic-release into CI is the real fix and
-# is deliberately NOT bundled here; this bump is the reversible unblock.
-#
-# 0.6.0 is semantic-release's OWN answer, not a guess:
-#   $ uvx --from python-semantic-release semantic-release --noop version --print
-#   0.6.0
-# (several feat: commits, and major_on_zero = false keeps 0.x on a minor bump)
-# so choosing it leaves the numbering where automation would resume.
-version = "0.6.0"
+# so every merge remains on the already-published version until this value is
+# advanced. Wiring semantic-release into CI remains separate work; this patch
+# bump is the minimal release unblock for the three post-v0.6.0 fixes.
+version = "0.6.1"
 description = "End-user CLI for deploying apps to urun"
 readme = "README.md"
 requires-python = ">=3.11"

{urun_cli-0.6.0 → urun_cli-0.6.1}/src/urun/api.py

@@ -607,6 +607,23 @@ class ApiClient:
         body: dict[str, Any] | None = {"environment": environment} if environment else None
         return self._json("POST", f"/app/{urllib.parse.quote(app, safe='')}/activate", body)
 
+    def set_function_paused(
+        self,
+        app: str,
+        function_name: str,
+        paused: bool,
+        environment: str | None = None,
+    ) -> dict[str, Any]:
+        """Pause or resume one function of an app.
+
+        Hits ``POST /app/<slug>/pause`` with the function name and explicit
+        pause state. The org is derived from the API key.
+        """
+        body: dict[str, Any] = {"paused": paused, "function_name": function_name}
+        if environment:
+            body["environment"] = environment
+        return self._json("POST", f"/app/{urllib.parse.quote(app, safe='')}/pause", body)
+
     def retire_app(self, app: str, environment: str | None = None) -> dict[str, Any]:
         """Retire an app through the CLI edge route (backs ``urun app delete``).
 

{urun_cli-0.6.0 → urun_cli-0.6.1}/src/urun/catalog.py

@@ -115,10 +115,11 @@ ENGINE_DEPS: dict[str, list[str]] = {
         "safetensors",
         "huggingface_hub>=1.5.0,<2.0",
         "opencv-python-headless==4.11.0.86",
-        "nvidia-cuda-nvcc==13.3.73",
-        "nvidia-cuda-crt==13.3.73",
-        "nvidia-cuda-cccl==13.3.3.4.1",
-        "nvidia-cuda-runtime==13.3.29",
+        "nvidia-cuda-nvcc==13.0.88",
+        "nvidia-cuda-crt==13.0.88",
+        "nvidia-cuda-cccl==13.0.85",
+        "nvidia-nvvm==13.0.88",
+        "nvidia-cuda-runtime==13.0.96",
         "numpy<2",
         "pillow>=10.0.0",
         "orjson",
@@ -155,10 +156,11 @@ ENGINE_DEPS: dict[str, list[str]] = {
         "accelerate",
         "safetensors",
         "huggingface_hub>=1.5.0,<2.0",
-        "nvidia-cuda-nvcc==13.3.73",
-        "nvidia-cuda-crt==13.3.73",
-        "nvidia-cuda-cccl==13.3.3.4.1",
-        "nvidia-cuda-runtime==13.3.29",
+        "nvidia-cuda-nvcc==13.0.88",
+        "nvidia-cuda-crt==13.0.88",
+        "nvidia-cuda-cccl==13.0.85",
+        "nvidia-nvvm==13.0.88",
+        "nvidia-cuda-runtime==13.0.96",
         "numpy<2",
         "pillow>=10.0.0",
         "orjson",
@@ -357,10 +359,11 @@ ENGINE_DEPS: dict[str, list[str]] = {
         "safetensors",
         "huggingface_hub>=1.5.0,<2.0",
         "flashinfer_python[cu13]==0.6.14",
-        "nvidia-cuda-nvcc==13.2.78",
-        "nvidia-cuda-crt==13.2.78",
-        "nvidia-cuda-cccl==13.2.75",
-        "nvidia-cuda-runtime==13.2.86",
+        "nvidia-cuda-nvcc==13.0.88",
+        "nvidia-cuda-crt==13.0.88",
+        "nvidia-cuda-cccl==13.0.85",
+        "nvidia-nvvm==13.0.88",
+        "nvidia-cuda-runtime==13.0.96",
         "numpy<2",
         "pillow>=10.0.0",
         "orjson",

{urun_cli-0.6.0 → urun_cli-0.6.1}/src/urun/cli.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import argparse
 import getpass
+import http.client
 import json
 import os
 import re
@@ -1349,10 +1350,20 @@ def add_app_parser(sub: argparse._SubParsersAction) -> None:
         description=(
             "Enable a previously disabled app (the inverse of `urun app "
             "disable`): drive its deployment back to `active` so the control "
-            "plane resumes recreating its runtime StatefulSet."
+            "plane resumes recreating its runtime StatefulSet. Pass --force to "
+            "also resume functions automatically paused after repeated startup "
+            "failures."
         ),
     )
     enable_parser.add_argument("app", help="App slug (as shown by `urun app list`)")
+    enable_parser.add_argument(
+        "--force",
+        action="store_true",
+        help=(
+            "Also resume every paused function. This may restart a function "
+            "the platform paused because it repeatedly failed to start"
+        ),
+    )
     enable_parser.add_argument(
         "--environment",
         "--env",
@@ -2504,9 +2515,18 @@ def deploy_once(args: argparse.Namespace) -> DeployOutcome:
     mark_phase("finalize")
     if final.get("reused") is True:
         # Same-manifest redeploy of an already-built release: the control
-        # plane reuses the existing artifact (nothing to build, nothing to
-        # wait for) and repoints the app onto it.
+        # plane reuses the existing artifact and its function rows. A function
+        # the crash-loop guard paused therefore STAYS paused: unchanged source
+        # cannot silently clear an operational safety decision. Surface that
+        # state and its explicit recovery command before returning success.
         print(f"unchanged — reusing release {mh[:12]}")
+        pause_check_client = ApiClient(
+            api_url,
+            api_key,
+            timeout=DEMO_PREFLIGHT_TIMEOUT_S,
+            backoff=BackoffPolicy(max_attempts=1),
+        )
+        warn_paused_functions(pause_check_client, app_name, environment=environment)
         print(format_phase_timing(phases))
         return DeployOutcome(exit_code=0, manifest_hash=mh, deps=deps, status=dict(final))
     print(f"Deployment {final.get('status', 'queued')}: {mh}")
@@ -4771,8 +4791,16 @@ def app_enable(args: argparse.Namespace) -> int:
     environment = resolve_environment(args)
     client = ApiClient(api_url, api_key)
     response = client.activate_app(args.app, environment=environment)
+    resumed: list[str] = []
+    if getattr(args, "force", False):
+        for function_name in paused_app_functions(client, args.app, environment=environment):
+            client.set_function_paused(args.app, function_name, False, environment=environment)
+            resumed.append(function_name)
     if getattr(args, "json", False):
-        print(json.dumps(response, indent=2, sort_keys=True))
+        result = dict(response)
+        if getattr(args, "force", False):
+            result["functions_resumed"] = resumed
+        print(json.dumps(result, indent=2, sort_keys=True))
         return 0
     app = _app_payload(response)
     slug = _coalesce_str(app.get("app_slug"), args.app)
@@ -4780,19 +4808,75 @@ def app_enable(args: argparse.Namespace) -> int:
         f"Enabled {slug} in {environment} "
         f"(deployment status: {_coalesce_str(app.get('status'), 'active')})."
     )
+    if getattr(args, "force", False):
+        if resumed:
+            print(f"Resumed paused function(s): {', '.join(resumed)}.")
+        else:
+            print("No paused functions needed recovery.")
     return 0
 
 
+def paused_app_functions(client: ApiClient, app_slug: str, *, environment: str) -> list[str]:
+    """Return paused current-release functions from the capacity API."""
+    response = client.list_capacity({"app": app_slug, "environment": environment})
+    rows = response.get("capacity") if isinstance(response, dict) else None
+    if not isinstance(rows, list):
+        raise UrunError("server returned invalid capacity payload")
+    names: set[str] = set()
+    for row in rows:
+        if not isinstance(row, dict):
+            raise UrunError("server returned invalid capacity payload")
+        row_app = string_value(row.get("app_slug"))
+        row_environment = string_value(row.get("environment")) or DEFAULT_ENVIRONMENT
+        if row_app not in {None, app_slug} or row_environment != environment:
+            continue
+        name = string_value(row.get("function_name"))
+        if row.get("paused") is True and name:
+            names.add(name)
+    return sorted(names)
+
+
+def warn_paused_functions(client: ApiClient, app_slug: str, *, environment: str) -> None:
+    """Warn when an unchanged deploy remains function-paused."""
+    try:
+        names = paused_app_functions(client, app_slug, environment=environment)
+    except (UrunError, OSError, http.client.HTTPException) as exc:
+        print(
+            f"Warning: could not check whether {app_slug} has paused functions: {exc}",
+            file=sys.stderr,
+        )
+        return
+    if not names:
+        return
+    print_paused_function_warning(app_slug, names, environment=environment)
+
+
+def print_paused_function_warning(
+    app_slug: str, function_names: list[str], *, environment: str
+) -> None:
+    """Print the shared paused-function explanation and recovery command."""
+    command = shlex.join(["urun", "app", "enable", app_slug, "--force", "--env", environment])
+    joined = ", ".join(function_names)
+    print(
+        f"Warning: {app_slug} has paused function(s): {joined}. The platform may "
+        "have paused them after repeated startup failures. An unchanged deploy "
+        "or frontend attach does not clear that safety state.",
+        file=sys.stderr,
+    )
+    print(
+        f"Review the function logs, then run `{command}` to resume them. This may "
+        "restart a known-crashing function.",
+        file=sys.stderr,
+    )
+
+
 def _confirm_disable(app: str, environment: str) -> bool:
     if not sys.stdin.isatty():
         raise UrunError(
             f"refusing to disable {app} without confirmation; pass --yes (non-interactive)"
         )
-    answer = (
-        input(f"Disable app '{app}' in environment '{environment}'? This stops its runtime. [y/N] ")
-        .strip()
-        .lower()
-    )
+    prompt = f"Disable app '{app}' in environment '{environment}'? This stops its runtime. [y/N] "
+    answer = input(prompt).strip().lower()
     return answer in {"y", "yes"}
 
 

{urun_cli-0.6.0 → urun_cli-0.6.1}/src/urun/frontend_launch.py

@@ -1446,6 +1446,7 @@ def preflight_demo_function(
         _runtime_logs_action,
         _sanitize_table_cell,
         _truncate,
+        print_paused_function_warning,
         string_value,
     )
 
@@ -1510,6 +1511,11 @@ def preflight_demo_function(
 
         row = min(matching_rows, key=selection_key)
         ready_gpu = row.get("ready_gpu_units")
+        paused = row.get("paused") is True
+        if paused:
+            print_paused_function_warning(
+                app_slug, [function_name], environment=selected_environment
+            )
         # ADMISSION BLOCKERS FIRST — they are fatal INDEPENDENTLY of capacity and
         # health. A blocked org cannot start a session even with warm GPUs parked
         # and a perfectly healthy runtime, so this must precede the positive-
@@ -1521,6 +1527,8 @@ def preflight_demo_function(
             raise UrunError(
                 f"cannot demo {app_slug}/{function_name}: {_ready_reason_text(blocking_reason)}"
             )
+        if paused:
+            return
         health = normalize_runtime_health(row.get("runtime_health"))
         if health is None and not isinstance(ready_gpu, int):
             return