Merge remote-tracking branch 'origin/main' into pi-hf-sandbox-backend

Author: sergiopaniego

src/openenv/cli/commands/collect.py

@@ -86,34 +86,35 @@ def _resolve_api_key(provider: str) -> str:
     )
 
 
+def _extract_legal_actions(messages: list[dict[str, Any]]) -> list[int]:
+    for message in reversed(messages):
+        content = message.get("content") or ""
+        if not isinstance(content, str):
+            continue
+        try:
+            payload = json.loads(content)
+        except (json.JSONDecodeError, ValueError):
+            payload = None
+        if isinstance(payload, dict) and "legal_actions" in payload:
+            legal = payload["legal_actions"]
+            if isinstance(legal, list):
+                return [int(a) for a in legal]
+        match = re.search(r"Legal actions:\s*\[([^\]]*)\]", content)
+        if match:
+            raw = match.group(1).strip()
+            if not raw:
+                return []
+            return [int(x) for x in raw.split(",")]
+    return []
+
+
 def _build_scripted_model_step():
     """Default teacher: pick the first legal action from the latest observation.
 
     Matches the scripted teacher in ``examples/ttt_collect_demo.py``. Lets
     users smoke-test the CLI without any API key configured.
     """
 
-    def _extract_legal_actions(messages: list[dict[str, Any]]) -> list[int]:
-        for message in reversed(messages):
-            content = message.get("content") or ""
-            if not isinstance(content, str):
-                continue
-            try:
-                payload = json.loads(content)
-            except (json.JSONDecodeError, ValueError):
-                payload = None
-            if isinstance(payload, dict) and "legal_actions" in payload:
-                legal = payload["legal_actions"]
-                if isinstance(legal, list):
-                    return [int(a) for a in legal]
-            match = re.search(r"Legal actions:\s*\[([^\]]*)\]", content)
-            if match:
-                raw = match.group(1).strip()
-                if not raw:
-                    return []
-                return [int(x) for x in raw.split(",")]
-        return []
-
     def model_step(messages, tools, sampling):
         del sampling
         legal = _extract_legal_actions(messages)

src/openenv/cli/importers/base.py

@@ -257,6 +257,42 @@ def qualified_name(self) -> str:
         return f"{self.module_path}:{self.class_name}"
 
 
+@dataclass(frozen=True)
+class ImportPackageContext:
+    """Shared details produced while scaffolding an imported environment package."""
+
+    class_name_prefix: str
+    vendor_dir: str
+
+
+def prepare_import_package(
+    source: Path, destination: Path, env_name: str
+) -> ImportPackageContext:
+    from openenv.cli.commands.init import (
+        _copy_template_directory,
+        _create_template_replacements,
+    )
+
+    replacements = _create_template_replacements(env_name)
+    _copy_template_directory(
+        "openenv.cli.templates.openenv_env",
+        "",
+        destination,
+        replacements,
+        env_name,
+    )
+
+    vendor_dir = safe_vendor_dir_name(source)
+    vendor_path = destination / "vendor" / vendor_dir
+    copy_source_tree(source, vendor_path)
+    ensure_vendor_package(vendor_path)
+
+    return ImportPackageContext(
+        class_name_prefix=replacements["__ENV_CLASS_NAME__"],
+        vendor_dir=vendor_dir,
+    )
+
+
 class EnvironmentImporter(Protocol):
     source_type: str
 

src/openenv/cli/importers/ors.py

@@ -8,13 +8,11 @@
 from .base import (
     append_dependency_files,
     collect_source_dependencies,
-    copy_source_tree,
     DetectedEnvironment,
-    ensure_vendor_package,
     iter_python_files,
     module_path,
+    prepare_import_package,
     render_importer_template,
-    safe_vendor_dir_name,
     write_text,
 )
 
@@ -209,39 +207,20 @@ def generate(
         env_name: str,
         detected: DetectedEnvironment,
     ) -> None:
-        from openenv.cli.commands.init import (
-            _copy_template_directory,
-            _create_template_replacements,
-        )
-
-        replacements = _create_template_replacements(env_name)
-        _copy_template_directory(
-            "openenv.cli.templates.openenv_env",
-            "",
-            destination,
-            replacements,
-            env_name,
-        )
-
-        vendor_dir = safe_vendor_dir_name(source)
-        vendor_path = destination / "vendor" / vendor_dir
-        copy_source_tree(source, vendor_path)
-        ensure_vendor_package(vendor_path)
-
-        prefix = replacements["__ENV_CLASS_NAME__"]
+        package = prepare_import_package(source, destination, env_name)
         write_text(
             destination / "server" / f"{env_name}_environment.py",
             _wrapper_source(
                 env_name=env_name,
-                class_name_prefix=prefix,
+                class_name_prefix=package.class_name_prefix,
                 source_module=detected.module_path,
                 source_class=detected.class_name,
-                vendor_dir=vendor_dir,
+                vendor_dir=package.vendor_dir,
             ),
         )
         write_text(
             destination / "server" / "app.py",
-            _app_source(env_name=env_name, class_name_prefix=prefix),
+            _app_source(env_name=env_name, class_name_prefix=package.class_name_prefix),
         )
         dependencies = collect_source_dependencies(source)
         for dependency in detect_ors_dependencies(source):

src/openenv/cli/importers/verifiers.py

@@ -8,13 +8,11 @@
 from .base import (
     append_dependency_files,
     collect_source_dependencies,
-    copy_source_tree,
     DetectedEnvironment,
-    ensure_vendor_package,
     iter_python_files,
     module_path,
+    prepare_import_package,
     render_importer_template,
-    safe_vendor_dir_name,
     write_text,
 )
 
@@ -110,38 +108,19 @@ def generate(
         env_name: str,
         detected: DetectedEnvironment,
     ) -> None:
-        from openenv.cli.commands.init import (
-            _copy_template_directory,
-            _create_template_replacements,
-        )
-
-        replacements = _create_template_replacements(env_name)
-        _copy_template_directory(
-            "openenv.cli.templates.openenv_env",
-            "",
-            destination,
-            replacements,
-            env_name,
-        )
-
-        vendor_dir = safe_vendor_dir_name(source)
-        vendor_path = destination / "vendor" / vendor_dir
-        copy_source_tree(source, vendor_path)
-        ensure_vendor_package(vendor_path)
-
-        prefix = replacements["__ENV_CLASS_NAME__"]
+        package = prepare_import_package(source, destination, env_name)
         write_text(
             destination / "server" / f"{env_name}_environment.py",
             _wrapper_source(
                 env_name=env_name,
-                class_name_prefix=prefix,
+                class_name_prefix=package.class_name_prefix,
                 source_module=detected.module_path,
-                vendor_dir=vendor_dir,
+                vendor_dir=package.vendor_dir,
             ),
         )
         write_text(
             destination / "server" / "app.py",
-            _app_source(env_name=env_name, class_name_prefix=prefix),
+            _app_source(env_name=env_name, class_name_prefix=package.class_name_prefix),
         )
         dependencies = collect_source_dependencies(source)
         if "verifiers>=0.1.14" not in dependencies:

src/openenv/core/containers/runtime/_server_config.py

@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Shared helpers for reading environment server configuration."""
+
+from __future__ import annotations
+
+import json
+import re
+
+import yaml
+
+
+def parse_openenv_app_field(yaml_content: str) -> str | None:
+    """Extract the top-level ``app`` value from raw ``openenv.yaml`` content."""
+    try:
+        data = yaml.safe_load(yaml_content) or {}
+    except Exception:
+        return None
+
+    if not isinstance(data, dict):
+        return None
+
+    value = data.get("app")
+    if isinstance(value, str):
+        value = value.strip()
+        return value if value else None
+    return None
+
+
+def parse_dockerfile_cmd(dockerfile_content: str) -> str | None:
+    """Extract the server command from the last Dockerfile ``CMD``."""
+    last_cmd: str | None = None
+    for line in dockerfile_content.splitlines():
+        stripped = line.strip()
+        if stripped.startswith("#"):
+            continue
+        match = re.match(r"CMD\s+(.+)", stripped, flags=re.IGNORECASE)
+        if match:
+            last_cmd = match.group(1).strip()
+
+    if last_cmd is None:
+        return None
+
+    if last_cmd.startswith("["):
+        try:
+            parts = json.loads(last_cmd)
+            if isinstance(parts, list) and all(isinstance(p, str) for p in parts):
+                return " ".join(parts)
+        except (json.JSONDecodeError, TypeError):
+            # Invalid exec-form JSON falls back to the raw CMD below.
+            pass
+
+    return last_cmd if last_cmd else None

src/openenv/core/containers/runtime/daytona_provider.py

@@ -8,14 +8,12 @@
 
 from __future__ import annotations
 
-import json
 import os
 import shlex
 import time
 from typing import Any, Callable, Dict, Optional
 
-import yaml
-
+from ._server_config import parse_dockerfile_cmd, parse_openenv_app_field
 from .providers import ContainerProvider
 
 
@@ -149,19 +147,7 @@ def _parse_app_field(yaml_content: str) -> Optional[str]:
 
         Uses PyYAML to handle comments, quotes, and nested keys correctly.
         """
-        try:
-            data = yaml.safe_load(yaml_content) or {}
-        except Exception:
-            return None
-
-        if not isinstance(data, dict):
-            return None
-
-        value = data.get("app")
-        if isinstance(value, str):
-            value = value.strip()
-            return value if value else None
-        return None
+        return parse_openenv_app_field(yaml_content)
 
     @staticmethod
     def _parse_dockerfile_cmd(dockerfile_content: str) -> Optional[str]:
@@ -176,32 +162,7 @@ def _parse_dockerfile_cmd(dockerfile_content: str) -> Optional[str]:
         Returns:
             The command as a single string, or ``None`` if no ``CMD`` found.
         """
-        import re
-
-        last_cmd: Optional[str] = None
-        for line in dockerfile_content.splitlines():
-            stripped = line.strip()
-            # Skip comments
-            if stripped.startswith("#"):
-                continue
-            match = re.match(r"CMD\s+(.+)", stripped, flags=re.IGNORECASE)
-            if match:
-                last_cmd = match.group(1).strip()
-
-        if last_cmd is None:
-            return None
-
-        # Exec form: CMD ["executable", "param1", ...]
-        if last_cmd.startswith("["):
-            try:
-                parts = json.loads(last_cmd)
-                if isinstance(parts, list) and all(isinstance(p, str) for p in parts):
-                    return " ".join(parts)
-            except (json.JSONDecodeError, TypeError):
-                pass
-
-        # Shell form: CMD executable param1 ...
-        return last_cmd if last_cmd else None
+        return parse_dockerfile_cmd(dockerfile_content)
 
     @staticmethod
     def strip_buildkit_syntax(dockerfile_content: str) -> str: