hud-python 0.6.2__py3-none-any.whl → 0.6.3__py3-none-any.whl

hud/cli/eval.py

@@ -5,6 +5,7 @@ Config Override Order: CLI arguments > .hud_eval.toml > defaults
 
 from __future__ import annotations
 
+import ast
 import asyncio
 import logging
 import os
@@ -665,13 +666,46 @@ def _build_agent(cfg: EvalConfig) -> Any:
     return cast("Any", cfg.agent_type.cls)(config=config)
 
 
+def _python_defines_environment(path: Path) -> bool:
+    """Return True when ``path`` constructs a v6 :class:`~hud.environment.Environment`."""
+    try:
+        tree = ast.parse(path.read_text(encoding="utf-8"))
+    except (OSError, SyntaxError):
+        return False
+    for node in ast.walk(tree):
+        if not isinstance(node, ast.Call):
+            continue
+        callee = node.func
+        callee_name = (
+            callee.id
+            if isinstance(callee, ast.Name)
+            else callee.attr
+            if isinstance(callee, ast.Attribute)
+            else None
+        )
+        if callee_name == "Environment":
+            return True
+    return False
+
+
 def _spawn_target(source: Path) -> Path:
-    """The path the ``LocalRuntime`` provider serves: the source itself for ``.py``
-    files and directories, the surrounding directory for JSON/JSONL data files
-    (the env's ``.py`` source lives next to the tasks file)."""
+    """The path the ``LocalRuntime`` provider serves.
+
+    Directories and env-defining ``.py`` files are served as-is. Task-only
+    sources (``tasks.py`` importing from ``env.py``) resolve to a sibling
+    ``env.py`` or the containing directory. JSON/JSONL data files use the
+    surrounding directory (the env source lives next to the tasks file).
+    """
     resolved = source.resolve()
-    if resolved.is_dir() or resolved.suffix == ".py":
+    if resolved.is_dir():
+        return resolved
+    if resolved.suffix != ".py":
+        return resolved.parent
+    if _python_defines_environment(resolved):
         return resolved
+    env_py = resolved.parent / "env.py"
+    if env_py.is_file():
+        return env_py
     return resolved.parent
 
 

hud/cli/init.py

@@ -76,8 +76,8 @@ def init_command(
         None,
         "--preset",
         "-p",
-        help="Starter preset to download from GitHub (e.g. blank, coding, browser, "
-        "deepresearch, rubrics, remote-browser). Omit for an interactive picker; in a "
+        help="Starter preset to download from GitHub (e.g. blank, browser, "
+        "deepresearch, cua, autonomous-businesses, verilog). Omit for an interactive picker; in a "
         "non-interactive shell, omitting it writes the minimal local scaffold.",
     ),
 ) -> None:
@@ -89,7 +89,7 @@ def init_command(
 
     Examples:
         hud init my-env                  # interactive picker (or local scaffold)
-        hud init my-env --preset coding  # download the coding starter
+        hud init my-env --preset browser  # download the browser starter
         hud init my-env --dir envs       # create ./envs/my-env[/not dim]
     """
     hud_console = HUDConsole()

hud/cli/templates.py

@@ -13,7 +13,7 @@ COPY . .
 
 # Serve the Environment's control channel (tcp JSON-RPC) on 8765.
 EXPOSE 8765
-CMD ["uv", "run", "python", "-m", "hud", "dev", "env:env", "--host", "0.0.0.0", "--port", "8765"]
+CMD ["uv", "run", "hud", "serve", "env:env", "--host", "0.0.0.0", "--port", "8765"]
 """
 
 # fmt: off
@@ -78,7 +78,7 @@ async def count(sentence: str, letter: str):
 
 
 # =============================================================================
-# TEST - run with: python env.py
+# TEST - run with: uv run python env.py
 # =============================================================================
 
 async def test():
@@ -136,7 +136,6 @@ version = "0.1.0"
 requires-python = ">=3.11"
 dependencies = ["hud-python"]
 
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+[tool.uv]
+package = false
 """

hud/cli/tests/test_deploy.py

@@ -48,7 +48,7 @@ class TestResolveEnvironmentName:
 
     def test_entrypoint_disambiguates_subagent(self, tmp_path: Path) -> None:
         (tmp_path / "Dockerfile").write_text(
-            'CMD ["hud", "dev", "env:env", "--port", "8765"]\n', encoding="utf-8"
+            'CMD ["hud", "serve", "env:env", "--port", "8765"]\n', encoding="utf-8"
         )
         (tmp_path / "env.py").write_text('env = Environment("trace-explorer")\n', encoding="utf-8")
         (tmp_path / "verify.py").write_text(

hud/cli/tests/test_eval_config.py

@@ -237,3 +237,32 @@ def test_eval_max_steps_lands_in_agent_config() -> None:
     )
     agent = eval_mod._build_agent(cfg)
     assert agent.config.max_steps == 17
+
+
+def test_spawn_target_serves_single_file_env(tmp_path: Path) -> None:
+    env_py = tmp_path / "tasks.py"
+    env_py.write_text(
+        'from hud import Environment\nenv = Environment(name="demo")\n',
+        encoding="utf-8",
+    )
+    assert eval_mod._spawn_target(env_py) == env_py.resolve()
+
+
+def test_spawn_target_resolves_split_tasks_layout(tmp_path: Path) -> None:
+    (tmp_path / "env.py").write_text(
+        'from hud.environment import Environment\nenv = Environment(name="demo")\n',
+        encoding="utf-8",
+    )
+    tasks_py = tmp_path / "tasks.py"
+    tasks_py.write_text("from env import env\n\ntasks = []\n", encoding="utf-8")
+    assert eval_mod._spawn_target(tasks_py) == (tmp_path / "env.py").resolve()
+
+
+def test_spawn_target_json_uses_parent_directory(tmp_path: Path) -> None:
+    tasks_json = tmp_path / "tasks.json"
+    tasks_json.write_text("[]", encoding="utf-8")
+    assert eval_mod._spawn_target(tasks_json) == tmp_path.resolve()
+
+
+def test_spawn_target_directory_is_served_as_is(tmp_path: Path) -> None:
+    assert eval_mod._spawn_target(tmp_path) == tmp_path.resolve()

hud/cli/tests/test_init.py

@@ -29,6 +29,14 @@ def test_init_scaffolds_a_runnable_package(tmp_path: Path) -> None:
     assert (target / "tasks.py").read_text().startswith('"""')
     assert 'name = "my-cool-env"' in (target / "pyproject.toml").read_text()
 
+    pyproject = (target / "pyproject.toml").read_text()
+    assert "package = false" in pyproject
+    assert "[build-system]" not in pyproject
+
+    dockerfile = (target / "Dockerfile.hud").read_text()
+    assert 'CMD ["uv", "run", "hud", "serve"' in dockerfile
+    assert '"dev"' not in dockerfile
+
 
 def test_init_refuses_to_clobber_nonempty_directory(tmp_path: Path) -> None:
     target = tmp_path / "taken"

hud/eval/job.py

@@ -38,17 +38,20 @@ class Job:
     name: str
     runs: list[Run] = field(default_factory=list)
     group: int = 1
+    #: Platform taskset id this job runs, when it's a synced taskset
+    #: (``Taskset.from_api``). Links the job to that taskset on the platform.
+    taskset_id: str | None = None
 
     @classmethod
-    async def start(cls, name: str, *, group: int = 1) -> Job:
+    async def start(cls, name: str, *, group: int = 1, taskset_id: str | None = None) -> Job:
         """Open a job spanning multiple scheduler calls.
 
         A scheduler call mints its own job by default; pass a started job as
         ``job=`` to ``Task.run`` / ``Taskset.run`` to accumulate every run of a
         longer arc — a training session, a chat conversation — under one id.
         """
-        job = cls(id=uuid.uuid4().hex, name=name, group=group)
-        await job_enter(job.id, name=name, group=group)
+        job = cls(id=uuid.uuid4().hex, name=name, group=group, taskset_id=taskset_id)
+        await job_enter(job.id, name=name, group=group, taskset_id=taskset_id)
         return job
 
     @property
@@ -79,21 +82,42 @@ def _reporting_enabled() -> bool:
     return bool(settings.telemetry_enabled and settings.api_key)
 
 
-async def job_enter(job_id: str, *, name: str, group: int) -> None:
-    """Register a batch job with the platform."""
+async def job_enter(job_id: str, *, name: str, group: int, taskset_id: str | None = None) -> None:
+    """Register a batch job with the platform.
+
+    ``taskset_id`` links the job to a synced taskset (set when running
+    ``Taskset.from_api``); ``None`` for ad-hoc/local tasksets. The platform
+    creates no taskset on its own — remote rollouts carry the scenario inline.
+    """
     if not _reporting_enabled():
         return
-    await _report(f"/trace/job/{job_id}/enter", {"name": name, "group": group})
+    await _report(
+        f"/trace/job/{job_id}/enter",
+        {"name": name, "group": group, "taskset_id": taskset_id},
+    )
     from hud.settings import settings
 
     logger.info("job: %s/jobs/%s", settings.hud_web_url, job_id)
 
 
-async def trace_enter(trace_id: str, *, job_id: str | None, group_id: str | None) -> None:
-    """Report that one rollout started."""
+async def trace_enter(
+    trace_id: str,
+    *,
+    job_id: str | None,
+    group_id: str | None,
+    model: str | None = None,
+) -> None:
+    """Report that one rollout started.
+
+    ``model`` is the model string the agent will sample (when known); the
+    platform resolves it and attributes the trace immediately on enter.
+    """
     if not _reporting_enabled():
         return
-    await _report(f"/trace/{trace_id}/enter", {"job_id": job_id, "group_id": group_id})
+    await _report(
+        f"/trace/{trace_id}/enter",
+        {"job_id": job_id, "group_id": group_id, "model": model},
+    )
 
 
 async def trace_exit(run: Run) -> None:

hud/eval/run.py

@@ -295,8 +295,15 @@ async def rollout(
         job_id = uuid.uuid4().hex
         await job_enter(job_id, name=task.id, group=1)
     trace_id = trace_id or uuid.uuid4().hex
+    # Report the model the agent will sample so the platform attributes the
+    # trace to it on enter. Only LLM tool agents carry an inference-model slug
+    # (``config.model``); robot/other agents have none. Local import avoids an
+    # eval<->agents import cycle.
+    from hud.agents.tool_agent import ToolAgent
+
+    agent_model = agent.config.model if isinstance(agent, ToolAgent) else None
     with set_trace_context(trace_id):
-        await trace_enter(trace_id, job_id=job_id, group_id=group_id)
+        await trace_enter(trace_id, job_id=job_id, group_id=group_id, model=agent_model)
         run: Run | None = None
         _phase = "provisioning"
 

hud/eval/taskset.py

@@ -59,6 +59,17 @@ class Taskset:
         self.origin = origin
         self.tasks: dict[str, Task] = self._index_by_slug(list(tasks))
 
+    @property
+    def api_id(self) -> str | None:
+        """The platform taskset id when loaded via :meth:`from_api`, else None.
+
+        Threaded into the job so a remote run of a synced taskset links to it;
+        ad-hoc/file/module tasksets have none and create no taskset.
+        """
+        if self.origin and self.origin.startswith("api:"):
+            return self.origin[len("api:") :]
+        return None
+
     @classmethod
     def from_file(cls, path: str | Path) -> Taskset:
         """Load a taskset from ``.py`` source, a directory, or JSON/JSONL data.
@@ -242,8 +253,13 @@ class Taskset:
             expanded.extend((task, group_id) for _ in range(group))
 
         if job is None:
-            job = Job(id=uuid.uuid4().hex, name=_job_name(self.name, task_list, group), group=group)
-            await job_enter(job.id, name=job.name, group=group)
+            job = Job(
+                id=uuid.uuid4().hex,
+                name=_job_name(self.name, task_list, group),
+                group=group,
+                taskset_id=self.api_id,
+            )
+            await job_enter(job.id, name=job.name, group=group, taskset_id=self.api_id)
         job_id = job.id
 
         # Placement is chosen once for the batch: HostedRuntime delegates the

hud/version.py

@@ -4,4 +4,4 @@ Version information for the HUD SDK.
 
 from __future__ import annotations
 
-__version__ = "0.6.2"
+__version__ = "0.6.3"

{hud_python-0.6.2.dist-info → hud_python-0.6.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hud-python
-Version: 0.6.2
+Version: 0.6.3
 Summary: SDK for the HUD platform.
 Project-URL: Homepage, https://github.com/hud-evals/hud-python
 Project-URL: Bug Tracker, https://github.com/hud-evals/hud-python/issues

{hud_python-0.6.2.dist-info → hud_python-0.6.3.dist-info}/RECORD

@@ -5,7 +5,7 @@ hud/conftest.py,sha256=HKbHvmFXLPX6KFSJgPFUAM22auclNNdFmHGwilNzg98,1012
 hud/server.py,sha256=NtSHIjBFr9lYvryfXrCa-VhwqnwkRy7n5fp_OuNhNOI,1235
 hud/settings.py,sha256=crfeQArM_8JnwmMdx0fcwL5xCvJMjeofGrGbpn0nW3c,6393
 hud/types.py,sha256=yOBFED8Ii7KA-8EzvmE3CU16LCXVigPnNjjl3kB8aRo,15326
-hud/version.py,sha256=oJ08yq_IrzFrsTHVgSPsBzDrwos8KumqvTVB-J2A0aM,104
+hud/version.py,sha256=Fp9FcgGRmYznsb5parYeGGuY6b_pSnDj5Yz7XEFRzDU,104
 hud/agents/__init__.py,sha256=ISruomRkEw1-cWCncyCgqKeeueYZFeBvFJ62RBIBQI8,4866
 hud/agents/base.py,sha256=WgEOWUmMioXTxYe6cOvbqnbM4n989Z9kFEZIN6xJ3pU,659
 hud/agents/tool_agent.py,sha256=a0xsh2d8IwvmiPGMs9LCzghi61FHt4vMK_9sW8eNFbA,12557
@@ -94,23 +94,23 @@ hud/cli/__main__.py,sha256=fDH7XITyuDITwSDIVwRso06aouADO0CzTHKqp5TOwJE,143
 hud/cli/cancel.py,sha256=MHRdZ6IoFy3iac9NtTT_c91IB_iQbYISsCb7ph7u298,3785
 hud/cli/client.py,sha256=cC23TUTo7w4S63jtk8SWkFWzG9h8Z2AKwYEqaefBWqg,2946
 hud/cli/deploy.py,sha256=QytQKmGY60YKNnQnhv0gXjMl9BVdwsvMRq0yZypVgpY,26082
-hud/cli/eval.py,sha256=GKvncjJ1AhMiBwsCn8jndAP_IdOe14HYC5AMnsAg3PE,33801
-hud/cli/init.py,sha256=6k3svrqeX19VuQ9cRuTTIojq5L5yRS51YscnXRuayRc,6464
+hud/cli/eval.py,sha256=mgXRftSef-6aAr8EkmYumQePGS0djcsUeR2TIDZIKQg,34812
+hud/cli/init.py,sha256=LfxVnuw5rnPCIvCnKWYIkAt6cg2Wxk-DSOM16lbuOvQ,6470
 hud/cli/login.py,sha256=3DhM_FfvfjP-cdfCj596kPo0bE9L3eQdz520X0oWqbc,7961
 hud/cli/models.py,sha256=NInyi2I5x-GFBpcTdjvfTI3f3eWC_U-E-SgWJUxbQz8,8770
 hud/cli/presets.py,sha256=qZmc_GKwdnRNJqxRqrg-MDUhN1Vh1JcDB4nJ94_AXLw,4523
 hud/cli/serve.py,sha256=074y6dGh1yPxr6m8MScKpYPXo2SX38zWbq2uZUrXl9k,3757
 hud/cli/sync.py,sha256=rvbcAM7ZfXOrlxRT3Zpp25Y-UkFbPqTuOzrcHAH1tK4,16927
 hud/cli/task.py,sha256=eYByPZHCqSy1GFiyZOVHNNqDFxvHaSLUGNQZ7o9kdz4,8111
-hud/cli/templates.py,sha256=HpJevrLJ5YQvbNyoDkQfCezT-KFGcdC8wB5OCoT4G-o,4746
+hud/cli/templates.py,sha256=bOu31T9e3IueWvmwU-PFJz869V2EZbZL9ECApfdj-Dk,4691
 hud/cli/tests/__init__.py,sha256=ZrGVkmH7DHXGqOvjOSNGZeMYaFIRB2K8c6hwr8FPJ-8,68
 hud/cli/tests/test_cli_init.py,sha256=e4pHfw4jLt2TY5n_fSTfA7XRcMsu1hKxOK7PNfVRO7U,3002
 hud/cli/tests/test_cli_main.py,sha256=0wMho9p9NcGjp0jLiUtCQh_FYdbMaCJtSY3sBbSgPwA,697
 hud/cli/tests/test_cli_more_wrappers.py,sha256=EEFrqTMg3yknQdmb8hWcHJAbinGAOGyqx3CGdiVX1b8,115
-hud/cli/tests/test_deploy.py,sha256=1b_2iviob4b_RFVun01cwCl3i4FmO2MaCrFs7PfzOSI,13983
+hud/cli/tests/test_deploy.py,sha256=atjacSnfZGf2DVG82Hf1vWswweqDKl6OBxb_Gmddma0,13985
 hud/cli/tests/test_eval_bedrock.py,sha256=UBGakgIV4kzXUj0Jtbr3t05xBss66YPqruKsovUYyoo,1900
-hud/cli/tests/test_eval_config.py,sha256=Cl4kHc6qykaFt_lmsjyzKZRjsoTdomQBgZ5pYKQLMLQ,7932
-hud/cli/tests/test_init.py,sha256=s8ipywnOztV_E4WHuBAqeGGEzcbW2jbIM1RUvEF-yr8,1479
+hud/cli/tests/test_eval_config.py,sha256=A4ViJOap-taGwYckb3CJqc-gSLFCxHt-86tPx8nv_dE,9034
+hud/cli/tests/test_init.py,sha256=KjBMyfbu9N46v8Fv1OUIC5kQTgkB3WLXNkOYUV4p_io,1778
 hud/cli/tests/test_main_module.py,sha256=PyfuSdqI-4Zt-kd16FMj2XHEHrw7SQ75YLJbQPdcIco,1223
 hud/cli/tests/test_sync_export.py,sha256=wd4ICZlNr_7XMw8MfNJuC8v0-lhywsjG7DnZE1zpJek,735
 hud/cli/utils/__init__.py,sha256=L6s0oNzY2LugGp9faodCPnjzM-ZUorUH05-HmYOq5hY,35
@@ -162,12 +162,12 @@ hud/environment/tests/test_tunnel.py,sha256=CDUO3wudYwxRTXhJCFsz3KsSxe10k9tesPd7
 hud/eval/__init__.py,sha256=keLJ4nozyM5soYcqPb1_t821u-xrp0QH0iQo_HS8gr0,2109
 hud/eval/chat.py,sha256=Gu6aDv1UkDAZ8qs41TXLUrFlcX4cav4HHSa7Yyovifw,5853
 hud/eval/file_tracking.py,sha256=MqLNl_lYfp74KCr4ZbwW9yGHmIyJ6GeOgAN9NMhELgs,4278
-hud/eval/job.py,sha256=oBfYHEJtiILd2QV3XZ9_35QSKo9WdgavYXIYkZ9yNhw,4794
-hud/eval/run.py,sha256=P-R4wnMA3YetqVhKBiQDyYIsBCdmzcer5bkoDXVOAbM,16861
+hud/eval/job.py,sha256=QMck-M_0HWtEd56hvfdYaNnStLlIOuNOGBStdcLr2vI,5606
+hud/eval/run.py,sha256=oyuFkT9W47KixTX8cmQMoO65R0QTxgd6sk9_eL02d9k,17276
 hud/eval/runtime.py,sha256=q71caY2XuWYvnKJ3zxB3bBawLU970bg_HwxcbdSD_Ko,40738
 hud/eval/sync.py,sha256=i7kxOoLyX5t6Jf9AoT9IRiDVhAfvY2bPIuYyDdqtc-Y,6469
 hud/eval/task.py,sha256=9xQ_x4AjY26M-sVRH6HhDZpKeofBw1hd8LZ0csBy53k,4617
-hud/eval/taskset.py,sha256=VgAP3xPorTxUnR76D7FRXhuKnOovsCFFMdaJKJgn1eY,11542
+hud/eval/taskset.py,sha256=9KVYxoeMnMHa2syR4fRGh9r1IuKoDVyMe7WEUFvaGxQ,12086
 hud/eval/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hud/eval/tests/test_chat.py,sha256=yQt_dM1UJu-Cw8JS8di102h06ee7QI9CqNA27U66_Qg,4310
 hud/eval/tests/test_docker_provider.py,sha256=1W1xyOzjHti6jfV2eiVnNd5CxKEMAKq8NBgBy-m5ftA,23741
@@ -221,8 +221,8 @@ hud/utils/tests/test_platform.py,sha256=mwhyFkUBvgmHRc43vQ_JgAAW2N9fIaxkQhVo-GB4
 hud/utils/tests/test_requests.py,sha256=ENK6P5xLTuSgWDcCau4zCj_5zPV_EooGwU4P8YYl5Gw,9109
 hud/utils/tests/test_serialization.py,sha256=GY4NiFUJtwLSYQWA0n1zme-Ul4DnBLByHCOOkxn2kLM,819
 hud/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-hud_python-0.6.2.dist-info/METADATA,sha256=3vYSE1DBNZV7N4pIXSiZzbJejgOR196u8V40EpkvX2g,12304
-hud_python-0.6.2.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
-hud_python-0.6.2.dist-info/entry_points.txt,sha256=jJbodNFg1m0-CDofe5AHvB4zKBq7sSdP97-ohaQ3ae4,63
-hud_python-0.6.2.dist-info/licenses/LICENSE,sha256=yIzBheVUf86FC1bztAcr7RYWWNxyd3B-UJQ3uddg1HA,1078
-hud_python-0.6.2.dist-info/RECORD,,
+hud_python-0.6.3.dist-info/METADATA,sha256=SI8xLaheCjc74TPSLvbYoHFDWOlgMzb8b4sdlfQ8fEY,12304
+hud_python-0.6.3.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+hud_python-0.6.3.dist-info/entry_points.txt,sha256=jJbodNFg1m0-CDofe5AHvB4zKBq7sSdP97-ohaQ3ae4,63
+hud_python-0.6.3.dist-info/licenses/LICENSE,sha256=yIzBheVUf86FC1bztAcr7RYWWNxyd3B-UJQ3uddg1HA,1078
+hud_python-0.6.3.dist-info/RECORD,,