Update trajectory dataset organization

README.md

@@ -28,7 +28,7 @@ new in the Space.
 | --- | --- |
 | `black-yt/ResearchHarness` | Main open-source runtime, CLI, API server, frontend, docs, tests, and benchmark adapters. |
 | `InternScience/ResearchHarness` | Hugging Face Space app that hosts the browser frontend with managed temporary workspaces. |
-| `CoCoOne/ResearchHarness-Data` | Hugging Face dataset receiving collected hosted-run trajectory PRs. |
+| `InternScience/ResearchHarness-Data` | Hugging Face dataset receiving collected hosted-run trajectory PRs. |
 
 Maintenance rule:
 
@@ -108,7 +108,7 @@ Configure these as Hugging Face Space secrets before starting the app:
 | `SERPER_KEY` | WebSearch / ScholarSearch key from <https://serper.dev/>. |
 | `JINA_KEY` | WebFetch key from <https://jina.ai/>. |
 | `MINERU_TOKEN` | ReadPDF key from <https://mineru.net/>. |
-| `HF_TOKEN` | Hugging Face token with write access to `CoCoOne/ResearchHarness-Data`. |
+| `HF_TOKEN` | Hugging Face token with write access to `InternScience/ResearchHarness-Data`. |
 
 ## Optional Runtime Variables
 
@@ -121,7 +121,7 @@ Configure these as Hugging Face Space secrets before starting the app:
 | `WEBFETCH_TIMEOUT_SECONDS` | `180` | Overall timeout for one WebFetch tool call. |
 | `WEBFETCH_MAX_CHARS` | `30000` | Hard maximum characters returned by one URL-only WebFetch call. |
 | `RH_COLLECTION_ENABLED` | `true` | Automatically collect completed hosted runs. |
-| `RH_COLLECTION_DATASET_REPO` | `CoCoOne/ResearchHarness-Data` | Dataset repo that receives trajectory PRs. |
+| `RH_COLLECTION_DATASET_REPO` | `InternScience/ResearchHarness-Data` | Dataset repo that receives trajectory PRs. |
 | `RH_COLLECTION_BATCH_SIZE` | `5` | Create one dataset PR after this many collected runs. |
 | `RH_COLLECTION_MAX_BUNDLE_BYTES` | `20971520` | Drop a single run bundle if it exceeds this byte limit. |
 | `PORT` | `7860` | Port used by Hugging Face Docker Spaces. |

app.py

@@ -39,7 +39,7 @@ def configure_space() -> None:
         cleanup_max_runs=_int_env("RH_SPACE_MAX_RUNS", 40),
         cleanup_interval_seconds=_int_env("RH_SPACE_CLEANUP_INTERVAL_SECONDS", 15 * 60),
         collection_enabled=_bool_env("RH_COLLECTION_ENABLED", True),
-        collection_dataset_repo=os.getenv("RH_COLLECTION_DATASET_REPO", "CoCoOne/ResearchHarness-Data"),
+        collection_dataset_repo=os.getenv("RH_COLLECTION_DATASET_REPO", "InternScience/ResearchHarness-Data"),
         collection_batch_size=_int_env("RH_COLLECTION_BATCH_SIZE", 5),
         collection_max_bundle_bytes=_int_env("RH_COLLECTION_MAX_BUNDLE_BYTES", 20 * 1024 * 1024),
     )

check_space_runtime.py

@@ -19,7 +19,7 @@ def main() -> int:
             cleanup_max_runs=2,
             cleanup_interval_seconds=60,
             collection_enabled=True,
-            collection_dataset_repo="CoCoOne/ResearchHarness-Data",
+            collection_dataset_repo="InternScience/ResearchHarness-Data",
             collection_batch_size=5,
             collection_max_bundle_bytes=1024 * 1024,
         )

frontend/local_server.py

@@ -44,7 +44,7 @@ FRONTEND_CLEANUP_RETENTION_SECONDS = 6 * 60 * 60
 FRONTEND_CLEANUP_MAX_RUNS = 40
 FRONTEND_CLEANUP_INTERVAL_SECONDS = 15 * 60
 FRONTEND_COLLECTION_ENABLED = True
-FRONTEND_COLLECTION_DATASET_REPO = "CoCoOne/ResearchHarness-Data"
+FRONTEND_COLLECTION_DATASET_REPO = "InternScience/ResearchHarness-Data"
 FRONTEND_COLLECTION_BATCH_SIZE = 5
 FRONTEND_COLLECTION_MAX_BUNDLE_BYTES = 20 * 1024 * 1024
 _CLEANUP_THREAD_STARTED = False