pearmut 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

pearmut/app.py

@@ -280,6 +280,79 @@ async def _reset_task(request: ResetTaskRequest):
     return response
 
 
+class PurgeCampaignRequest(BaseModel):
+    campaign_id: str
+    token: str
+
+
+@app.post("/purge-campaign")
+async def _purge_campaign(request: PurgeCampaignRequest):
+    global progress_data, tasks_data
+    
+    campaign_id = request.campaign_id
+    token = request.token
+
+    if campaign_id not in progress_data:
+        return JSONResponse(content="Unknown campaign ID", status_code=400)
+    if token != tasks_data[campaign_id]["token"]:
+        return JSONResponse(content="Invalid token", status_code=400)
+
+    # Unlink assets if they exist
+    destination = tasks_data[campaign_id].get("info", {}).get("assets", {}).get("destination")
+    if destination:
+        symlink_path = f"{ROOT}/data/{destination}".rstrip("/")
+        if os.path.islink(symlink_path):
+            os.remove(symlink_path)
+    
+    # Remove task file
+    task_file = f"{ROOT}/data/tasks/{campaign_id}.json"
+    if os.path.exists(task_file):
+        os.remove(task_file)
+    
+    # Remove output file
+    output_file = f"{ROOT}/data/outputs/{campaign_id}.jsonl"
+    if os.path.exists(output_file):
+        os.remove(output_file)
+    
+    # Remove from in-memory data structures
+    del tasks_data[campaign_id]
+    del progress_data[campaign_id]
+    
+    # Save updated progress data
+    save_progress_data(progress_data)
+    
+    return JSONResponse(content="ok", status_code=200)
+
+
+class AddCampaignRequest(BaseModel):
+    campaign_data: dict[str, Any]
+
+
+@app.post("/add-campaign")
+async def _add_campaign(request: AddCampaignRequest):
+    global progress_data, tasks_data
+    
+    from .cli import _add_single_campaign
+    
+    try:
+        server = f"{os.environ.get('PEARMUT_SERVER_URL', 'http://localhost:8001')}"
+        _add_single_campaign(request.campaign_data, overwrite=False, server=server)
+        
+        campaign_id = request.campaign_data['campaign_id']
+        with open(f"{ROOT}/data/tasks/{campaign_id}.json", "r") as f:
+            tasks_data[campaign_id] = json.load(f)
+        
+        progress_data = load_progress_data(warn=None)
+        
+        return JSONResponse(content={
+            "status": "ok",
+            "campaign_id": campaign_id,
+            "token": tasks_data[campaign_id]["token"]
+        }, status_code=200)
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=400)
+
+
 @app.get("/download-annotations")
 async def _download_annotations(
     campaign_id: list[str] = Query(),

pearmut/assignment.py

@@ -1,10 +1,12 @@
 import collections
+import copy
 import random
 import statistics
 from typing import Any
 
 from fastapi.responses import JSONResponse
 
+from .constants import PROTOCOL_INSTRUCTIONS
 from .utils import (
     RESET_MARKER,
     check_validation_threshold,
@@ -14,6 +16,15 @@ from .utils import (
 )
 
 
+def _get_instructions(tasks_data: dict, campaign_id: str) -> str:
+    """Get instructions: custom if provided, else protocol default, else empty."""
+    campaign_info = tasks_data[campaign_id]["info"]
+    if "instructions" in campaign_info:
+        return campaign_info["instructions"]
+    return PROTOCOL_INSTRUCTIONS.get(campaign_info.get("protocol", ""), "")
+
+
+
 def _completed_response(
     tasks_data: dict,
     progress_data: dict,
@@ -132,11 +143,12 @@ def get_i_item_taskbased(
             "time": user_progress["time"],
             "info": {
                 "item_i": item_i,
+                "instructions": _get_instructions(data_all, campaign_id),
             }
             | {
                 k: v
                 for k, v in data_all[campaign_id]["info"].items()
-                if k.startswith("protocol")
+                if k in {"protocol", "sliders"}
             },
             "payload": data_all[campaign_id]["data"][user_id][item_i],
         }
@@ -178,11 +190,12 @@ def get_i_item_singlestream(
             "time": user_progress["time"],
             "info": {
                 "item_i": item_i,
+                "instructions": _get_instructions(data_all, campaign_id),
             }
             | {
                 k: v
                 for k, v in data_all[campaign_id]["info"].items()
-                if k.startswith("protocol")
+                if k in {"protocol", "sliders"}
             },
             "payload": data_all[campaign_id]["data"][item_i],
         }
@@ -224,11 +237,12 @@ def get_next_item_taskbased(
             "time": user_progress["time"],
             "info": {
                 "item_i": item_i,
+                "instructions": _get_instructions(data_all, campaign_id),
             }
             | {
                 k: v
                 for k, v in data_all[campaign_id]["info"].items()
-                if k.startswith("protocol")
+                if k in {"protocol", "sliders"}
             },
             "payload": data_all[campaign_id]["data"][user_id][item_i],
         }
@@ -279,11 +293,12 @@ def get_next_item_singlestream(
             "progress": progress,
             "info": {
                 "item_i": item_i,
+                "instructions": _get_instructions(data_all, campaign_id),
             }
             | {
                 k: v
                 for k, v in data_all[campaign_id]["info"].items()
-                if k.startswith("protocol")
+                if k in {"protocol", "sliders"}
             },
             "payload": data_all[campaign_id]["data"][item_i],
         }
@@ -439,11 +454,12 @@ def get_next_item_dynamic(
             "progress": user_progress["progress"],
             "info": {
                 "item_i": item_i,
+                "instructions": _get_instructions(tasks_data, campaign_id),
             }
             | {
                 k: v
                 for k, v in campaign_data["info"].items()
-                if k.startswith("protocol")
+                if k in {"protocol", "sliders"}
             },
             "payload": pruned_item,
         },
@@ -459,6 +475,26 @@ def _reset_user_time(progress_data: dict, campaign_id: str, user_id: str) -> Non
     progress_data[campaign_id][user_id]["validations"] = {}
 
 
+def _get_user_annotated_items(campaign_id: str, user_id: str) -> set[int]:
+    """
+    Get the set of item indices that a specific user has annotated.
+    
+    Args:
+        campaign_id: The campaign identifier
+        user_id: The user identifier
+        
+    Returns:
+        Set of item indices (item_i) that the user has annotated
+    """
+    log = get_db_log(campaign_id)
+    user_items = set()
+    for entry in log:
+        if entry.get("user_id") == user_id and entry.get("annotation") != RESET_MARKER:
+            if (item_i := entry.get("item_i")) is not None:
+                user_items.add(item_i)
+    return user_items
+
+
 def reset_task(
     campaign_id: str,
     user_id: str,
@@ -482,29 +518,46 @@ def reset_task(
         _reset_user_time(progress_data, campaign_id, user_id)
         return JSONResponse(content="ok", status_code=200)
     elif assignment == "single-stream":
-        # Save reset markers for all items (shared pool)
-        num_items = len(tasks_data[campaign_id]["data"])
-        for item_i in range(num_items):
+        # Find all items that this user has annotated
+        user_items = _get_user_annotated_items(campaign_id, user_id)
+        
+        # Save reset markers only for items this user has touched
+        for item_i in user_items:
             save_db_payload(
                 campaign_id,
-                {"user_id": None, "item_i": item_i, "annotation": RESET_MARKER},
+                {"user_id": user_id, "item_i": item_i, "annotation": RESET_MARKER},
             )
-        # for single-stream reset all progress
+        
+        # Reset only the touched items in all users' progress (shared pool)
         for uid in progress_data[campaign_id]:
-            progress_data[campaign_id][uid]["progress"] = [False] * num_items
+            for item_i in user_items:
+                progress_data[campaign_id][uid]["progress"][item_i] = False
+        
+        # Reset only the specified user's time
         _reset_user_time(progress_data, campaign_id, user_id)
         return JSONResponse(content="ok", status_code=200)
     elif assignment == "dynamic":
-        # Save reset markers for all items (shared pool like single-stream)
-        num_items = len(tasks_data[campaign_id]["data"])
-        for item_i in range(num_items):
+        # Find all items that this user has annotated
+        user_items = _get_user_annotated_items(campaign_id, user_id)
+        
+        # Save reset markers only for items this user has touched
+        for item_i in user_items:
             save_db_payload(
                 campaign_id,
-                {"user_id": None, "item_i": item_i, "annotation": RESET_MARKER},
+                {"user_id": user_id, "item_i": item_i, "annotation": RESET_MARKER},
             )
-        # for dynamic reset all progress (use sets to track models)
+
+        progress_data_user = copy.deepcopy(progress_data[campaign_id][user_id]["progress"])
+        
+        # Reset only the touched items in all users' progress (shared pool, use lists to track models)
         for uid in progress_data[campaign_id]:
-            progress_data[campaign_id][uid]["progress"] = [[] for _ in range(num_items)]
+            for item_i in user_items:
+                progress_data[campaign_id][uid]["progress"][item_i] = [
+                    x for x in progress_data[campaign_id][uid]["progress"][item_i]
+                    if x not in progress_data_user[item_i]
+                ]
+        
+        # Reset only the specified user's time
         _reset_user_time(progress_data, campaign_id, user_id)
         return JSONResponse(content="ok", status_code=200)
     else: