hyperstudy 0.2.0__tar.gz → 0.2.2__tar.gz

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/.github/workflows/sync-release-notes.yml

@@ -53,15 +53,11 @@ jobs:
           # Remove leading whitespace from heredoc
           sed -i 's/^          //' "$FILE"
 
-      - name: Create PR to hyperstudy-docs
-        uses: peter-evans/create-pull-request@v6
-        with:
-          path: docs-repo
-          token: ${{ secrets.DOCS_REPO_TOKEN }}
-          title: "docs: Python SDK ${{ steps.release.outputs.tag }} release notes"
-          branch: "python-sdk-release-${{ steps.release.outputs.tag }}"
-          commit-message: "Add Python SDK ${{ steps.release.outputs.tag }} release notes"
-          body: |
-            Auto-generated release notes for Python SDK ${{ steps.release.outputs.tag }}.
-
-            Source: ${{ github.event.release.html_url }}
+      - name: Commit and push
+        run: |
+          cd docs-repo
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add docs/release-notes/
+          git commit -m "Add Python SDK ${{ steps.release.outputs.tag }} release notes" || exit 0
+          git push

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hyperstudy
-Version: 0.2.0
+Version: 0.2.2
 Summary: Python SDK for the HyperStudy experiment platform API
 Project-URL: Homepage, https://hyperstudy.io
 Project-URL: Documentation, https://docs.hyperstudy.io/developers/python-sdk

hyperstudy-0.2.2/docs/superpowers/specs/2026-04-10-recording-downloads-design.md

@@ -0,0 +1,128 @@
+# Recording Downloads via Python SDK
+
+## Problem
+
+The Python SDK's `get_recordings()` returns metadata only. Users need the actual audio/video files for offline analysis (ML models, manual review, archival). Currently they must manually extract `downloadUrl` from each record and fetch files themselves.
+
+## Decision: SDK-only, no backend changes
+
+The V3 API already returns signed GCS download URLs (7-day expiry) in the recording metadata. The SDK will fetch metadata and download files in the same call, so URL expiry is not a practical concern. This matches how the frontend downloads recordings.
+
+## API Surface
+
+### `download_recordings()` — Bulk download
+
+```python
+df = hs.download_recordings(
+    "exp_abc123",
+    output_dir="./data/recordings",
+    scope="experiment",           # "experiment" | "room" | "participant"
+    deployment_id=None,           # optional filter
+    room_id=None,                 # optional filter
+    recording_type=None,          # "audio" | "video" | None (both)
+    progress=True,                # tqdm progress bar
+    skip_existing=True,           # skip files already on disk with matching size
+)
+```
+
+**Returns**: `pandas.DataFrame` with all recording metadata columns plus:
+- `local_path` — absolute path to the downloaded file on disk
+- `download_status` — `"downloaded"`, `"skipped"`, or `"failed"`
+
+**Side effects**:
+- Writes media files to `output_dir`
+- Writes `recordings_metadata.csv` to `output_dir`
+
+### `download_recording()` — Single recording
+
+```python
+path = hs.download_recording(
+    recording,                    # dict from get_recordings(output="dict")
+    output_dir="./data/recordings",
+)
+```
+
+**Returns**: `pathlib.Path` to downloaded file.
+
+## Directory Structure
+
+```
+output_dir/
+  recordings_metadata.csv
+  user1_video_EG_abc123.mp4
+  user1_audio_EG_def456.webm
+  user2_video_EG_ghi789.mp4
+```
+
+**Filename pattern**: `{participantName}_{recordingType}_{recordingId}.{ext}`
+
+- `participantName`: from recording metadata, sanitized for filesystem safety
+- `recordingType`: `"video"` or `"audio"` from `metadata.type`
+- `recordingId`: egressId or recordingId
+- `ext`: from `format` field, falling back to `mp4` (video) or `webm` (audio)
+
+## Internal Design
+
+### Download flow (`download_recordings`)
+
+1. Call `self.get_recordings(scope_id, scope=scope, output="dict")` to get metadata
+2. Filter by `recording_type` if specified (via `metadata.type`)
+3. Create `output_dir` via `os.makedirs(exist_ok=True)`
+4. For each recording:
+   - Build filename using pattern above
+   - If `skip_existing=True` and file exists with size matching `fileSize` metadata, mark as `"skipped"`
+   - Otherwise, fetch from `downloadUrl` (fallback: `url`) using streaming HTTP GET
+   - Write to disk in 8KB chunks
+   - Mark as `"downloaded"` or `"failed"` (with warning logged)
+5. Build DataFrame from metadata, add `local_path` and `download_status` columns
+6. Write `recordings_metadata.csv` to `output_dir`
+7. Return DataFrame
+
+### Streaming downloads
+
+Use `requests.get(url, stream=True)` with chunked iteration to avoid loading large video files into memory. The SDK's existing `HttpTransport` handles JSON responses only, so file downloads use a standalone `requests.get()` — the signed GCS URLs don't need API key auth.
+
+### Error handling
+
+- Per-file failure tolerance: if one recording fails (404, timeout, network error), log a warning, set `download_status="failed"`, continue with remaining files
+- If the metadata API call itself fails, raise normally (same as `get_recordings()`)
+- Invalid/missing `downloadUrl`: set `download_status="failed"`, log warning
+
+### Skip-existing logic
+
+Compare `os.path.getsize(local_path)` against `fileSize` from metadata. If `fileSize` is `None` (metadata missing), fall back to checking file existence only (any existing file is considered complete).
+
+## File Layout
+
+| File | Change |
+|------|--------|
+| `src/hyperstudy/_downloads.py` | **New.** `build_filename()`, `download_file()` streaming helper |
+| `src/hyperstudy/client.py` | Add `download_recordings()` and `download_recording()` methods |
+| `tests/test_downloads.py` | **New.** Unit tests for filename building, skip logic, status tracking |
+| `tests/test_client.py` | Integration test: mock API + GCS, verify files + DataFrame |
+| `tests/fixtures/sparse_ratings_response.json` | Already exists (from prior work) |
+
+## Testing
+
+### Unit tests (`tests/test_downloads.py`)
+- `test_build_filename` — video, audio, missing fields, filesystem-unsafe characters
+- `test_build_filename_dedup` — duplicate names get numeric suffix
+- `test_skip_existing_matching_size` — file with correct size is skipped
+- `test_skip_existing_wrong_size` — file with wrong size is re-downloaded
+
+### Integration tests (`tests/test_client.py`)
+- `test_download_recordings` — mock API + GCS fetch, verify files on disk, CSV sidecar, DataFrame with `local_path` + `download_status`
+- `test_download_recordings_filter_type` — `recording_type="audio"` only downloads audio
+- `test_download_recording_single` — single recording download
+
+### Mocking strategy
+- V3 API: `responses` library (existing pattern)
+- GCS signed URL: also `responses` (it's just an HTTP GET to a URL)
+- File I/O: real writes to `pytest` `tmp_path`
+
+## No Backend Changes Required
+
+The existing V3 API endpoints return all necessary data:
+- `GET /api/v3/data/recordings/{scope}/{scopeId}` returns metadata with `downloadUrl`
+- Signed GCS URLs are valid for 7 days
+- SDK downloads immediately after fetching metadata, so expiry is not an issue

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hyperstudy"
-version = "0.2.0"
+version = "0.2.2"
 description = "Python SDK for the HyperStudy experiment platform API"
 readme = "README.md"
 license = "MIT"

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/src/hyperstudy/__init__.py

@@ -19,7 +19,7 @@ from .exceptions import (
     ValidationError,
 )
 
-__version__ = "0.2.0"
+__version__ = "0.2.2"
 
 __all__ = [
     "HyperStudy",

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/src/hyperstudy/_dataframe.py

@@ -6,6 +6,51 @@ from typing import Any
 
 import pandas as pd
 
+# Nested dict fields to flatten into top-level columns.
+# Mapping of {field_name: prefix} — sub-keys become ``{prefix}_{sub_key}``.
+FLATTEN_FIELDS: dict[str, str] = {
+    "sparseRatingData": "sparseRatingData",
+    "metadata": "metadata",
+}
+
+
+def _flatten_nested_dicts(
+    data: list[dict[str, Any]],
+    fields: dict[str, str] | None = None,
+) -> list[dict[str, Any]]:
+    """Promote sub-keys of nested dict fields to top-level keys.
+
+    For each *field* present in a record whose value is a ``dict``, every
+    sub-key is copied to ``{prefix}_{sub_key}``.  The original nested dict
+    is preserved for backward compatibility.
+
+    Records where the target field is ``None`` or missing are left
+    untouched — downstream DataFrame construction fills those columns
+    with ``NaN`` / ``null``.
+    """
+    if not data:
+        return data
+
+    fields = fields if fields is not None else FLATTEN_FIELDS
+
+    # Quick check on first record — skip work when no target fields exist.
+    sample = data[0]
+    targets = [f for f in fields if f in sample and isinstance(sample[f], dict)]
+    if not targets:
+        return data
+
+    out: list[dict[str, Any]] = []
+    for record in data:
+        record = dict(record)  # shallow copy to avoid mutating caller's data
+        for field in targets:
+            nested = record.get(field)
+            if isinstance(nested, dict):
+                prefix = fields[field]
+                for sub_key, sub_val in nested.items():
+                    record[f"{prefix}_{sub_key}"] = sub_val
+        out.append(record)
+    return out
+
 
 def _post_process(df: pd.DataFrame) -> pd.DataFrame:
     """Shared post-processing for pandas DataFrames.
@@ -32,6 +77,7 @@ def to_pandas(data: list[dict[str, Any]]) -> pd.DataFrame:
     """Convert API response data to a pandas DataFrame with post-processing."""
     if not data:
         return pd.DataFrame()
+    data = _flatten_nested_dicts(data)
     df = pd.DataFrame(data)
     return _post_process(df)
 
@@ -51,6 +97,7 @@ def to_polars(data: list[dict[str, Any]]):
     if not data:
         return pl.DataFrame()
 
+    data = _flatten_nested_dicts(data)
     df = pl.DataFrame(data)
 
     # Parse timestamps

hyperstudy-0.2.2/src/hyperstudy/_downloads.py

@@ -0,0 +1,50 @@
+"""Helpers for downloading recording files from signed URLs."""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+from typing import Any
+
+import requests
+
+_CHUNK_SIZE = 65536  # 64 KB — good balance for large video files
+_UNSAFE_RE = re.compile(r"[^\w\-]")
+
+
+def get_download_url(recording: dict[str, Any]) -> str | None:
+    """Return the best download URL from a recording dict, or ``None``."""
+    return recording.get("downloadUrl") or recording.get("url") or None
+
+
+def build_filename(recording: dict[str, Any]) -> str:
+    """Build a filesystem-safe filename from recording metadata.
+
+    Pattern: ``{participantName}_{type}_{recordingId}.{ext}``
+    """
+    name = recording.get("participantName") or recording.get("participantId") or "unknown"
+    name = _UNSAFE_RE.sub("_", name)
+
+    meta = recording.get("metadata") or {}
+    rec_type = meta.get("type") or "recording"
+
+    rec_id = recording.get("recordingId") or recording.get("egressId") or "unknown"
+
+    fmt = recording.get("format")
+    if not fmt:
+        fmt = "webm" if rec_type == "audio" else "mp4"
+
+    return f"{name}_{rec_type}_{rec_id}.{fmt}"
+
+
+def download_file(url: str, dest: Path, timeout: int = 300) -> int:
+    """Stream-download *url* to *dest* and return bytes written."""
+    resp = requests.get(url, stream=True, timeout=timeout)
+    resp.raise_for_status()
+
+    written = 0
+    with open(dest, "wb") as fh:
+        for chunk in resp.iter_content(chunk_size=_CHUNK_SIZE):
+            fh.write(chunk)
+            written += len(chunk)
+    return written

{hyperstudy-0.2.0 → hyperstudy-0.2.2}/src/hyperstudy/client.py

@@ -2,9 +2,14 @@
 
 from __future__ import annotations
 
+import warnings
+from pathlib import Path
 from typing import Any
 
+from tqdm.auto import tqdm
+
 from ._dataframe import to_pandas, to_polars
+from ._downloads import build_filename, download_file, get_download_url
 from ._http import HttpTransport
 from ._pagination import fetch_all_pages
 from ._types import Scope
@@ -55,6 +60,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -71,6 +77,7 @@ class HyperStudy(ExperimentMixin):
         Args:
             scope_id: ID of the experiment, room, or participant.
             scope: ``"experiment"``, ``"room"``, or ``"participant"``.
+            deployment_id: Filter by deployment (experiment scope only).
             room_id: Required when ``scope="participant"``.
             start_time: ISO 8601 start filter.
             end_time: ISO 8601 end filter.
@@ -84,7 +91,7 @@ class HyperStudy(ExperimentMixin):
         """
         return self._fetch_data(
             "events", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             category=category, sort=sort, order=order,
             limit=limit, offset=offset,
@@ -96,6 +103,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         limit: int | None = None,
         offset: int = 0,
@@ -105,7 +113,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch video/audio recording metadata."""
         return self._fetch_data(
             "recordings", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             limit=limit, offset=offset,
             output=output, progress=progress,
         )
@@ -115,6 +123,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -128,7 +137,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch text chat messages."""
         return self._fetch_data(
             "chat", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -140,6 +149,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -153,7 +163,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch LiveKit video chat connection data."""
         return self._fetch_data(
             "videochat", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -165,6 +175,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -182,7 +193,7 @@ class HyperStudy(ExperimentMixin):
             extra["aggregationWindow"] = aggregation_window
         return self._fetch_data(
             "sync", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -196,6 +207,7 @@ class HyperStudy(ExperimentMixin):
         *,
         kind: str = "continuous",
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -214,7 +226,7 @@ class HyperStudy(ExperimentMixin):
         """
         return self._fetch_data(
             f"ratings/{kind}", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -226,6 +238,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         limit: int | None = None,
         offset: int = 0,
@@ -235,7 +248,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch component response data."""
         return self._fetch_data(
             "components", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             limit=limit, offset=offset,
             output=output, progress=progress,
         )
@@ -245,6 +258,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         limit: int | None = None,
         offset: int = 0,
@@ -254,7 +268,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch participant data."""
         return self._fetch_data(
             "participants", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             limit=limit, offset=offset,
             output=output, progress=progress,
         )
@@ -264,6 +278,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         limit: int | None = None,
         offset: int = 0,
         output: str = "pandas",
@@ -272,7 +287,7 @@ class HyperStudy(ExperimentMixin):
         """Fetch room/session data."""
         return self._fetch_data(
             "rooms", scope_id,
-            scope=scope,
+            scope=scope, deployment_id=deployment_id,
             limit=limit, offset=offset,
             output=output, progress=progress,
         )
@@ -286,6 +301,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -303,7 +319,7 @@ class HyperStudy(ExperimentMixin):
         """
         return self._fetch_data(
             "events", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             category="questionnaire", sort=sort, order=order,
             limit=limit, offset=offset,
@@ -315,6 +331,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -332,7 +349,7 @@ class HyperStudy(ExperimentMixin):
         """
         return self._fetch_and_filter(
             "instructions.", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -344,6 +361,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -361,7 +379,7 @@ class HyperStudy(ExperimentMixin):
         """
         return self._fetch_and_filter(
             "consent.", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             sort=sort, order=order,
             limit=limit, offset=offset,
@@ -453,6 +471,125 @@ class HyperStudy(ExperimentMixin):
             "consent": self.get_consent(participant_id, **common),
         }
 
+    # ------------------------------------------------------------------
+    # Recording downloads
+    # ------------------------------------------------------------------
+
+    def download_recording(
+        self,
+        recording: dict[str, Any],
+        output_dir: str = ".",
+    ) -> Path:
+        """Download a single recording file to disk.
+
+        Args:
+            recording: A recording dict (from ``get_recordings(output="dict")``).
+            output_dir: Directory to save the file.
+
+        Returns:
+            Path to the downloaded file.
+        """
+        url = get_download_url(recording)
+        if not url:
+            raise ValueError("Recording has no downloadUrl or url field")
+
+        dest_dir = Path(output_dir)
+        dest_dir.mkdir(parents=True, exist_ok=True)
+
+        filename = build_filename(recording)
+        dest = dest_dir / filename
+        download_file(url, dest)
+        return dest
+
+    def download_recordings(
+        self,
+        scope_id: str,
+        *,
+        output_dir: str,
+        scope: str = "experiment",
+        deployment_id: str | None = None,
+        room_id: str | None = None,
+        recording_type: str | None = None,
+        progress: bool = True,
+        skip_existing: bool = True,
+    ):
+        """Download recording files to disk.
+
+        Fetches recording metadata, downloads each file from its signed
+        URL, writes a ``recordings_metadata.csv`` sidecar, and returns a
+        DataFrame with a ``local_path`` column.
+
+        Args:
+            scope_id: Experiment, room, or participant ID.
+            output_dir: Directory to save files.
+            scope: ``"experiment"``, ``"room"``, or ``"participant"``.
+            deployment_id: Filter by deployment (experiment scope only).
+            room_id: Filter by room.
+            recording_type: ``"audio"``, ``"video"``, or ``None`` (both).
+            progress: Show progress bar.
+            skip_existing: Skip files already on disk with matching size.
+
+        Returns:
+            pandas DataFrame with recording metadata plus ``local_path``
+            and ``download_status`` columns.
+        """
+        recordings = self.get_recordings(
+            scope_id,
+            scope=scope,
+            deployment_id=deployment_id,
+            room_id=room_id,
+            output="dict",
+        )
+
+        if recording_type:
+            recordings = [
+                r for r in recordings
+                if (r.get("metadata") or {}).get("type") == recording_type
+            ]
+
+        dest_dir = Path(output_dir)
+        dest_dir.mkdir(parents=True, exist_ok=True)
+
+        local_paths: list[str | None] = []
+        statuses: list[str] = []
+
+        for rec in tqdm(recordings, desc="Downloading recordings", disable=not progress):
+            filename = build_filename(rec)
+            dest = dest_dir / filename
+
+            url = get_download_url(rec)
+            if not url:
+                local_paths.append(None)
+                statuses.append("failed")
+                warnings.warn(f"Recording {rec.get('recordingId')} has no download URL")
+                continue
+
+            if skip_existing and dest.exists():
+                expected_size = rec.get("fileSize")
+                if expected_size is None or dest.stat().st_size == expected_size:
+                    local_paths.append(str(dest.resolve()))
+                    statuses.append("skipped")
+                    continue
+
+            try:
+                download_file(url, dest)
+                local_paths.append(str(dest.resolve()))
+                statuses.append("downloaded")
+            except Exception as exc:
+                local_paths.append(None)
+                statuses.append("failed")
+                warnings.warn(
+                    f"Failed to download recording {rec.get('recordingId')}: {exc}"
+                )
+
+        df = to_pandas(recordings)
+        if not df.empty:
+            df["local_path"] = local_paths
+            df["download_status"] = statuses
+            df.to_csv(dest_dir / "recordings_metadata.csv", index=False)
+
+        return df
+
     # ------------------------------------------------------------------
     # Internal helpers
     # ------------------------------------------------------------------
@@ -463,6 +600,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -482,7 +620,7 @@ class HyperStudy(ExperimentMixin):
         # Always fetch as dicts so we can filter before conversion
         raw = self._fetch_data(
             "events", scope_id,
-            scope=scope, room_id=room_id,
+            scope=scope, deployment_id=deployment_id, room_id=room_id,
             start_time=start_time, end_time=end_time,
             category="pre_experiment", sort=sort, order=order,
             limit=limit, offset=offset,
@@ -500,6 +638,7 @@ class HyperStudy(ExperimentMixin):
         scope_id: str,
         *,
         scope: str = "experiment",
+        deployment_id: str | None = None,
         room_id: str | None = None,
         start_time: str | None = None,
         end_time: str | None = None,
@@ -517,6 +656,8 @@ class HyperStudy(ExperimentMixin):
         path = f"data/{data_type}/{scope_val.value}/{scope_id}"
 
         params: dict[str, Any] = {"offset": offset}
+        if deployment_id:
+            params["deploymentId"] = deployment_id
         if room_id:
             params["roomId"] = room_id
         if start_time: