refactor(backend): revert selective COPY, keep cleanup approach

Address review feedback: keep COPY --from=builder /app /app to avoid
maintenance burden of selective copies. The builder cleanup step still
removes __pycache__, test dirs, pip/poetry caches for size reduction.

Added clarifying comment about --only main referencing the development
docs (dev deps are installed locally, not in production images).

autogpt_platform/backend/Dockerfile

@@ -37,13 +37,15 @@ ENV POETRY_VIRTUALENVS_CREATE=true
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 ENV PATH=/opt/poetry/bin:$PATH
 
-RUN pip3 install poetry --break-system-packages
+RUN pip3 install --no-cache-dir poetry --break-system-packages
 
 # Copy and install dependencies
 COPY autogpt_platform/autogpt_libs /app/autogpt_platform/autogpt_libs
 COPY autogpt_platform/backend/poetry.lock autogpt_platform/backend/pyproject.toml /app/autogpt_platform/backend/
 WORKDIR /app/autogpt_platform/backend
-RUN poetry install --no-ansi --no-root
+# Production image only needs runtime deps; dev deps (pytest, black, ruff, etc.)
+# are installed locally via `poetry install --with dev` per the development docs
+RUN poetry install --no-ansi --no-root --only main
 
 # Generate Prisma client
 COPY autogpt_platform/backend/schema.prisma ./
@@ -51,6 +53,15 @@ COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/parti
 COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
 RUN poetry run prisma generate && poetry run gen-prisma-stub
 
+# Clean up build artifacts and caches to reduce layer size
+# Note: setuptools is kept as it's a direct dependency (used by aioclamd via pkg_resources)
+RUN find /app -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true; \
+    find /app -type d -name tests -exec rm -rf {} + 2>/dev/null || true; \
+    find /app -type d -name test -exec rm -rf {} + 2>/dev/null || true; \
+    rm -rf /app/autogpt_platform/backend/.venv/lib/python*/site-packages/pip* \
+           /root/.cache/pip \
+           /root/.cache/pypoetry
+
 FROM debian:13-slim AS server_dependencies
 
 WORKDIR /app
@@ -68,7 +79,7 @@ RUN apt-get update && apt-get install -y \
     python3-pip \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy only necessary files from builder
+# Copy built artifacts from builder (cleaned of caches, __pycache__, and test dirs)
 COPY --from=builder /app /app
 COPY --from=builder /usr/local/lib/python3* /usr/local/lib/python3*
 COPY --from=builder /usr/local/bin/poetry /usr/local/bin/poetry
@@ -81,9 +92,7 @@ COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-pyth
 
 ENV PATH="/app/autogpt_platform/backend/.venv/bin:$PATH"
 
-RUN mkdir -p /app/autogpt_platform/autogpt_libs
-RUN mkdir -p /app/autogpt_platform/backend
-
+# Copy fresh source from context (overwrites builder's copy with latest source)
 COPY autogpt_platform/autogpt_libs /app/autogpt_platform/autogpt_libs
 
 COPY autogpt_platform/backend/poetry.lock autogpt_platform/backend/pyproject.toml /app/autogpt_platform/backend/

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/core.py

@@ -14,7 +14,6 @@ from backend.data.graph import (
     create_graph,
     get_graph,
     get_graph_all_versions,
-    get_store_listed_graphs,
 )
 from backend.util.exceptions import DatabaseError, NotFoundError
 
@@ -267,18 +266,18 @@ async def get_library_agents_for_generation(
 async def search_marketplace_agents_for_generation(
     search_query: str,
     max_results: int = 10,
-) -> list[LibraryAgentSummary]:
+) -> list[MarketplaceAgentSummary]:
     """Search marketplace agents formatted for Agent Generator.
 
-    Fetches marketplace agents and their full schemas so they can be used
-    as sub-agents in generated workflows.
+    Note: This returns basic agent info. Full input/output schemas would require
+    additional graph fetches and is a potential future enhancement.
 
     Args:
         search_query: Search term to find relevant public agents
         max_results: Maximum number of agents to return (default 10)
 
     Returns:
-        List of LibraryAgentSummary with full input/output schemas
+        List of MarketplaceAgentSummary (without detailed schemas for now)
     """
     try:
         response = await store_db.get_store_agents(
@@ -287,31 +286,17 @@ async def search_marketplace_agents_for_generation(
             page_size=max_results,
         )
 
-        agents_with_graphs = [
-            agent for agent in response.agents if agent.agent_graph_id
-        ]
-
-        if not agents_with_graphs:
-            return []
-
-        graph_ids = [agent.agent_graph_id for agent in agents_with_graphs]
-        graphs = await get_store_listed_graphs(*graph_ids)
-
-        results: list[LibraryAgentSummary] = []
-        for agent in agents_with_graphs:
-            graph_id = agent.agent_graph_id
-            if graph_id and graph_id in graphs:
-                graph = graphs[graph_id]
-                results.append(
-                    LibraryAgentSummary(
-                        graph_id=graph.id,
-                        graph_version=graph.version,
-                        name=agent.agent_name,
-                        description=agent.description,
-                        input_schema=graph.input_schema,
-                        output_schema=graph.output_schema,
-                    )
+        results: list[MarketplaceAgentSummary] = []
+        for agent in response.agents:
+            results.append(
+                MarketplaceAgentSummary(
+                    name=agent.agent_name,
+                    description=agent.description,
+                    sub_heading=agent.sub_heading,
+                    creator=agent.creator,
+                    is_marketplace_agent=True,
                 )
+            )
         return results
     except Exception as e:
         logger.warning(f"Failed to search marketplace agents: {e}")
@@ -342,7 +327,8 @@ async def get_all_relevant_agents_for_generation(
         max_marketplace_results: Max marketplace agents to return (default 10)
 
     Returns:
-        List of AgentSummary with full schemas (both library and marketplace agents)
+        List of AgentSummary, library agents first (with full schemas),
+        then marketplace agents (basic info only)
     """
     agents: list[AgentSummary] = []
     seen_graph_ids: set[str] = set()
@@ -379,11 +365,16 @@ async def get_all_relevant_agents_for_generation(
             search_query=search_query,
             max_results=max_marketplace_results,
         )
+        library_names: set[str] = set()
+        for a in agents:
+            name = a.get("name")
+            if name and isinstance(name, str):
+                library_names.add(name.lower())
         for agent in marketplace_agents:
-            graph_id = agent.get("graph_id")
-            if graph_id and graph_id not in seen_graph_ids:
-                agents.append(agent)
-                seen_graph_ids.add(graph_id)
+            agent_name = agent.get("name")
+            if agent_name and isinstance(agent_name, str):
+                if agent_name.lower() not in library_names:
+                    agents.append(agent)
 
     return agents
 

autogpt_platform/backend/backend/api/features/store/db.py

@@ -112,7 +112,6 @@ async def get_store_agents(
                             description=agent["description"],
                             runs=agent["runs"],
                             rating=agent["rating"],
-                            agent_graph_id=agent.get("agentGraphId", ""),
                         )
                         store_agents.append(store_agent)
                     except Exception as e:
@@ -171,7 +170,6 @@ async def get_store_agents(
                         description=agent.description,
                         runs=agent.runs,
                         rating=agent.rating,
-                        agent_graph_id=agent.agentGraphId,
                     )
                     # Add to the list only if creation was successful
                     store_agents.append(store_agent)

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -600,7 +600,6 @@ async def hybrid_search(
                 sa.featured,
                 sa.is_available,
                 sa.updated_at,
-                sa."agentGraphId",
                 -- Searchable text for BM25 reranking
                 COALESCE(sa.agent_name, '') || ' ' || COALESCE(sa.sub_heading, '') || ' ' || COALESCE(sa.description, '') as searchable_text,
                 -- Semantic score
@@ -660,7 +659,6 @@ async def hybrid_search(
                 featured,
                 is_available,
                 updated_at,
-                "agentGraphId",
                 searchable_text,
                 semantic_score,
                 lexical_score,

autogpt_platform/backend/backend/api/features/store/model.py

@@ -38,7 +38,6 @@ class StoreAgent(pydantic.BaseModel):
     description: str
     runs: int
     rating: float
-    agent_graph_id: str
 
 
 class StoreAgentsResponse(pydantic.BaseModel):

autogpt_platform/backend/backend/api/features/store/model_test.py

@@ -26,13 +26,11 @@ def test_store_agent():
         description="Test description",
         runs=50,
         rating=4.5,
-        agent_graph_id="test-graph-id",
     )
     assert agent.slug == "test-agent"
     assert agent.agent_name == "Test Agent"
     assert agent.runs == 50
     assert agent.rating == 4.5
-    assert agent.agent_graph_id == "test-graph-id"
 
 
 def test_store_agents_response():
@@ -48,7 +46,6 @@ def test_store_agents_response():
                 description="Test description",
                 runs=50,
                 rating=4.5,
-                agent_graph_id="test-graph-id",
             )
         ],
         pagination=store_model.Pagination(

autogpt_platform/backend/backend/api/features/store/routes_test.py

@@ -82,7 +82,6 @@ def test_get_agents_featured(
                 description="Featured agent description",
                 runs=100,
                 rating=4.5,
-                agent_graph_id="test-graph-1",
             )
         ],
         pagination=store_model.Pagination(
@@ -128,7 +127,6 @@ def test_get_agents_by_creator(
                 description="Creator agent description",
                 runs=50,
                 rating=4.0,
-                agent_graph_id="test-graph-2",
             )
         ],
         pagination=store_model.Pagination(
@@ -174,7 +172,6 @@ def test_get_agents_sorted(
                 description="Top agent description",
                 runs=1000,
                 rating=5.0,
-                agent_graph_id="test-graph-3",
             )
         ],
         pagination=store_model.Pagination(
@@ -220,7 +217,6 @@ def test_get_agents_search(
                 description="Specific search term description",
                 runs=75,
                 rating=4.2,
-                agent_graph_id="test-graph-search",
             )
         ],
         pagination=store_model.Pagination(
@@ -266,7 +262,6 @@ def test_get_agents_category(
                 description="Category agent description",
                 runs=60,
                 rating=4.1,
-                agent_graph_id="test-graph-category",
             )
         ],
         pagination=store_model.Pagination(
@@ -311,7 +306,6 @@ def test_get_agents_pagination(
                 description=f"Agent {i} description",
                 runs=i * 10,
                 rating=4.0,
-                agent_graph_id="test-graph-2",
             )
             for i in range(5)
         ],

autogpt_platform/backend/backend/api/features/store/test_cache_delete.py

@@ -33,7 +33,6 @@ class TestCacheDeletion:
                     description="Test description",
                     runs=100,
                     rating=4.5,
-                    agent_graph_id="test-graph-id",
                 )
             ],
             pagination=Pagination(

autogpt_platform/backend/backend/data/graph.py

@@ -1028,39 +1028,6 @@ async def get_graph(
     return GraphModel.from_db(graph, for_export)
 
 
-async def get_store_listed_graphs(*graph_ids: str) -> dict[str, GraphModel]:
-    """Batch-fetch multiple store-listed graphs by their IDs.
-
-    Only returns graphs that have approved store listings (publicly available).
-    Does not require permission checks since store-listed graphs are public.
-
-    Args:
-        *graph_ids: Variable number of graph IDs to fetch
-
-    Returns:
-        Dict mapping graph_id to GraphModel for graphs with approved store listings
-    """
-    if not graph_ids:
-        return {}
-
-    store_listings = await StoreListingVersion.prisma().find_many(
-        where={
-            "agentGraphId": {"in": list(graph_ids)},
-            "submissionStatus": SubmissionStatus.APPROVED,
-            "isDeleted": False,
-        },
-        include={"AgentGraph": {"include": AGENT_GRAPH_INCLUDE}},
-        distinct=["agentGraphId"],
-        order={"agentGraphVersion": "desc"},
-    )
-
-    return {
-        listing.agentGraphId: GraphModel.from_db(listing.AgentGraph)
-        for listing in store_listings
-        if listing.AgentGraph
-    }
-
-
 async def get_graph_as_admin(
     graph_id: str,
     version: int | None = None,

autogpt_platform/backend/backend/executor/scheduler.py

@@ -193,11 +193,9 @@ async def _handle_graph_validation_error(args: "GraphExecutionJobArgs") -> None:
             user_id=args.user_id,
         )
     else:
-        logger.warning(
-            f"Old scheduled job for graph {args.graph_id} (user {args.user_id}) "
-            f"has no schedule_id, attempting targeted cleanup"
+        logger.error(
+            f"Unable to unschedule graph: {args.graph_id} as this is an old job with no associated schedule_id please remove manually"
         )
-        await _cleanup_old_schedules_without_id(args.graph_id, args.user_id)
 
 
 async def _handle_graph_not_available(
@@ -240,35 +238,6 @@ async def _cleanup_orphaned_schedules_for_graph(graph_id: str, user_id: str) ->
             )
 
 
-async def _cleanup_old_schedules_without_id(graph_id: str, user_id: str) -> None:
-    """Remove only schedules that have no schedule_id in their job args.
-
-    Unlike _cleanup_orphaned_schedules_for_graph (which removes ALL schedules
-    for a graph), this only targets legacy jobs created before schedule_id was
-    added to GraphExecutionJobArgs, preserving any valid newer schedules.
-    """
-    scheduler_client = get_scheduler_client()
-    schedules = await scheduler_client.get_execution_schedules(
-        graph_id=graph_id, user_id=user_id
-    )
-
-    for schedule in schedules:
-        if schedule.schedule_id is not None:
-            continue
-        try:
-            await scheduler_client.delete_schedule(
-                schedule_id=schedule.id, user_id=user_id
-            )
-            logger.info(
-                f"Cleaned up old schedule {schedule.id} (no schedule_id) "
-                f"for graph {graph_id}"
-            )
-        except Exception:
-            logger.exception(
-                f"Failed to delete old schedule {schedule.id} for graph {graph_id}"
-            )
-
-
 def cleanup_expired_files():
     """Clean up expired files from cloud storage."""
     # Wait for completion

autogpt_platform/backend/backend/integrations/webhooks/utils_test.py

@@ -1,39 +0,0 @@
-from urllib.parse import urlparse
-
-import fastapi
-from fastapi.routing import APIRoute
-
-from backend.api.features.integrations.router import router as integrations_router
-from backend.integrations.providers import ProviderName
-from backend.integrations.webhooks import utils as webhooks_utils
-
-
-def test_webhook_ingress_url_matches_route(monkeypatch) -> None:
-    app = fastapi.FastAPI()
-    app.include_router(integrations_router, prefix="/api/integrations")
-
-    provider = ProviderName.GITHUB
-    webhook_id = "webhook_123"
-    base_url = "https://example.com"
-
-    monkeypatch.setattr(webhooks_utils.app_config, "platform_base_url", base_url)
-
-    route = next(
-        route
-        for route in integrations_router.routes
-        if isinstance(route, APIRoute)
-        and route.path == "/{provider}/webhooks/{webhook_id}/ingress"
-        and "POST" in route.methods
-    )
-    expected_path = f"/api/integrations{route.path}".format(
-        provider=provider.value,
-        webhook_id=webhook_id,
-    )
-    actual_url = urlparse(webhooks_utils.webhook_ingress_url(provider, webhook_id))
-    expected_base = urlparse(base_url)
-
-    assert (actual_url.scheme, actual_url.netloc) == (
-        expected_base.scheme,
-        expected_base.netloc,
-    )
-    assert actual_url.path == expected_path

autogpt_platform/backend/snapshots/agts_by_creator

@@ -9,8 +9,7 @@
       "sub_heading": "Creator agent subheading",
       "description": "Creator agent description",
       "runs": 50,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     }
   ],
   "pagination": {

autogpt_platform/backend/snapshots/agts_category

@@ -9,8 +9,7 @@
       "sub_heading": "Category agent subheading",
       "description": "Category agent description",
       "runs": 60,
-      "rating": 4.1,
-      "agent_graph_id": "test-graph-category"
+      "rating": 4.1
     }
   ],
   "pagination": {

autogpt_platform/backend/snapshots/agts_pagination

@@ -9,8 +9,7 @@
       "sub_heading": "Agent 0 subheading",
       "description": "Agent 0 description",
       "runs": 0,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     },
     {
       "slug": "agent-1",
@@ -21,8 +20,7 @@
       "sub_heading": "Agent 1 subheading",
       "description": "Agent 1 description",
       "runs": 10,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     },
     {
       "slug": "agent-2",
@@ -33,8 +31,7 @@
       "sub_heading": "Agent 2 subheading",
       "description": "Agent 2 description",
       "runs": 20,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     },
     {
       "slug": "agent-3",
@@ -45,8 +42,7 @@
       "sub_heading": "Agent 3 subheading",
       "description": "Agent 3 description",
       "runs": 30,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     },
     {
       "slug": "agent-4",
@@ -57,8 +53,7 @@
       "sub_heading": "Agent 4 subheading",
       "description": "Agent 4 description",
       "runs": 40,
-      "rating": 4.0,
-      "agent_graph_id": "test-graph-2"
+      "rating": 4.0
     }
   ],
   "pagination": {

autogpt_platform/backend/snapshots/agts_search

@@ -9,8 +9,7 @@
       "sub_heading": "Search agent subheading",
       "description": "Specific search term description",
       "runs": 75,
-      "rating": 4.2,
-      "agent_graph_id": "test-graph-search"
+      "rating": 4.2
     }
   ],
   "pagination": {

autogpt_platform/backend/snapshots/agts_sorted

@@ -9,8 +9,7 @@
       "sub_heading": "Top agent subheading",
       "description": "Top agent description",
       "runs": 1000,
-      "rating": 5.0,
-      "agent_graph_id": "test-graph-3"
+      "rating": 5.0
     }
   ],
   "pagination": {

autogpt_platform/backend/snapshots/feat_agts

@@ -9,8 +9,7 @@
       "sub_heading": "Featured agent subheading",
       "description": "Featured agent description",
       "runs": 100,
-      "rating": 4.5,
-      "agent_graph_id": "test-graph-1"
+      "rating": 4.5
     }
   ],
   "pagination": {

autogpt_platform/backend/test/agent_generator/test_library_agents.py

@@ -134,28 +134,15 @@ class TestSearchMarketplaceAgentsForGeneration:
                 description="A public agent",
                 sub_heading="Does something useful",
                 creator="creator-1",
-                agent_graph_id="graph-123",
             )
         ]
 
-        mock_graph = MagicMock()
-        mock_graph.id = "graph-123"
-        mock_graph.version = 1
-        mock_graph.input_schema = {"type": "object"}
-        mock_graph.output_schema = {"type": "object"}
-
-        with (
-            patch(
-                "backend.api.features.store.db.get_store_agents",
-                new_callable=AsyncMock,
-                return_value=mock_response,
-            ) as mock_search,
-            patch(
-                "backend.api.features.chat.tools.agent_generator.core.get_store_listed_graphs",
-                new_callable=AsyncMock,
-                return_value={"graph-123": mock_graph},
-            ),
-        ):
+        # The store_db is dynamically imported, so patch the import path
+        with patch(
+            "backend.api.features.store.db.get_store_agents",
+            new_callable=AsyncMock,
+            return_value=mock_response,
+        ) as mock_search:
             result = await core.search_marketplace_agents_for_generation(
                 search_query="automation",
                 max_results=10,
@@ -169,7 +156,7 @@ class TestSearchMarketplaceAgentsForGeneration:
 
         assert len(result) == 1
         assert result[0]["name"] == "Public Agent"
-        assert result[0]["graph_id"] == "graph-123"
+        assert result[0]["is_marketplace_agent"] is True
 
     @pytest.mark.asyncio
     async def test_handles_marketplace_error_gracefully(self):
@@ -206,12 +193,11 @@ class TestGetAllRelevantAgentsForGeneration:
 
         marketplace_agents = [
             {
-                "graph_id": "market-456",
-                "graph_version": 1,
                 "name": "Market Agent",
                 "description": "From marketplace",
-                "input_schema": {},
-                "output_schema": {},
+                "sub_heading": "Sub heading",
+                "creator": "creator-1",
+                "is_marketplace_agent": True,
             }
         ]
 
@@ -239,11 +225,11 @@ class TestGetAllRelevantAgentsForGeneration:
         assert result[1]["name"] == "Market Agent"
 
     @pytest.mark.asyncio
-    async def test_deduplicates_by_graph_id(self):
-        """Test that marketplace agents with same graph_id as library are excluded."""
+    async def test_deduplicates_by_name(self):
+        """Test that marketplace agents with same name as library are excluded."""
         library_agents = [
             {
-                "graph_id": "shared-123",
+                "graph_id": "lib-123",
                 "graph_version": 1,
                 "name": "Shared Agent",
                 "description": "From library",
@@ -254,20 +240,18 @@ class TestGetAllRelevantAgentsForGeneration:
 
         marketplace_agents = [
             {
-                "graph_id": "shared-123",  # Same graph_id, should be deduplicated
-                "graph_version": 1,
-                "name": "Shared Agent",
+                "name": "Shared Agent",  # Same name, should be deduplicated
                 "description": "From marketplace",
-                "input_schema": {},
-                "output_schema": {},
+                "sub_heading": "Sub heading",
+                "creator": "creator-1",
+                "is_marketplace_agent": True,
             },
             {
-                "graph_id": "unique-456",
-                "graph_version": 1,
                 "name": "Unique Agent",
                 "description": "Only in marketplace",
-                "input_schema": {},
-                "output_schema": {},
+                "sub_heading": "Sub heading",
+                "creator": "creator-2",
+                "is_marketplace_agent": True,
             },
         ]
 
@@ -289,7 +273,7 @@ class TestGetAllRelevantAgentsForGeneration:
                     include_marketplace=True,
                 )
 
-        # Shared Agent from marketplace should be excluded by graph_id
+        # Shared Agent from marketplace should be excluded
         assert len(result) == 2
         names = [a["name"] for a in result]
         assert "Shared Agent" in names

autogpt_platform/frontend/src/app/api/openapi.json

@@ -9833,8 +9833,7 @@
           "sub_heading": { "type": "string", "title": "Sub Heading" },
           "description": { "type": "string", "title": "Description" },
           "runs": { "type": "integer", "title": "Runs" },
-          "rating": { "type": "number", "title": "Rating" },
-          "agent_graph_id": { "type": "string", "title": "Agent Graph Id" }
+          "rating": { "type": "number", "title": "Rating" }
         },
         "type": "object",
         "required": [
@@ -9846,8 +9845,7 @@
           "sub_heading",
           "description",
           "runs",
-          "rating",
-          "agent_graph_id"
+          "rating"
         ],
         "title": "StoreAgent"
       },