Add parallel Placement pipeline for routing-first topology plans.

Ship a free, analysis-independent job that writes placement_plan.json (domains/satellites, no mm) with API, SSE progress, and a minimal project UI.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/pinscopex/functional_groups.py

@@ -132,6 +132,12 @@ def build_functional_groups(
     return FunctionalGroupsReport(objective="routing", domains=domains, groups=groups)
 
 
+# Alias used by the dedicated Placement pipeline (same topology artifact).
+build_placement_plan = build_functional_groups
+PlacementPlan = FunctionalGroupsReport
+
+
+
 def load_capacitance_farads(comp: Component) -> float | None:
     """Crystal CL from SimpleComponentSpecs.values, if present."""
     specs = comp.specs

backend/pipeline_worker.py

@@ -101,8 +101,11 @@ async def _run() -> None:
         await pipeline_svc.run_regen_pipeline(
             storage, user_id, project_id, stages,
         )
+    elif mode == "placement":
+        from backend.services import placement_pipeline as placement_svc
+        await placement_svc.run_placement_pipeline(storage, user_id, project_id)
     else:
-        raise SystemExit(f"unknown MODE={mode!r}; expected 'run' or 'regen'")
+        raise SystemExit(f"unknown MODE={mode!r}; expected 'run', 'regen', or 'placement'")
 
 
 def main() -> None:

backend/routers/pipeline.py

@@ -492,9 +492,204 @@ async def status(project_id: str, request: Request):
         "summary": meta.summary,
         "pipeline_state": meta.pipeline_state,
         "running": meta.status in (proj_svc.STATUS_RUNNING, proj_svc.STATUS_QUEUED),
+        "placement_status": meta.placement_status,
+        "placement_state": meta.placement_state,
+        "placement_running": (meta.placement_status or "draft") in ("queued", "running"),
     }
 
 
+# ---------------------------------------------------------------------------
+# Placement pipeline (parallel — topology only, no LLM / no credits)
+# ---------------------------------------------------------------------------
+
+
+_PLACEMENT_START_OK = frozenset({"draft", "complete", "error", "cancelled"})
+_PLACEMENT_SSE_TERMINAL = frozenset({
+    "placement_complete",
+    "placement_error",
+    "placement_cancelled",
+})
+
+
+@router.post("/pipeline/{project_id}/placement/start", status_code=202)
+async def start_placement(project_id: str, request: Request):
+    """Enqueue the Placement topology pipeline (free, no analysis status change)."""
+    from backend.services.placement_pipeline import analysis_busy, placement_busy
+
+    storage = get_storage(request)
+    owner_user_id, meta = await resolve_or_404(request, project_id)
+    if not meta.has_bom or not meta.has_netlist:
+        raise HTTPException(400, "Upload BOM and netlist before starting placement")
+    if analysis_busy(meta):
+        raise HTTPException(409, "Analysis pipeline is running; wait or cancel it first")
+    if placement_busy(meta):
+        raise HTTPException(409, "Placement pipeline already running or queued")
+    if (meta.placement_status or "draft") not in _PLACEMENT_START_OK:
+        raise HTTPException(
+            409,
+            f"Cannot start placement from placement_status={meta.placement_status}",
+        )
+
+    proj_svc.update_project(
+        storage, owner_user_id, project_id,
+        placement_status="queued",
+        placement_cancel_requested=False,
+        placement_state=None,
+        placement_execution_name=None,
+    )
+    # Clear before enqueue so the placement SSE client never stops on a
+    # leftover analysis ``pipeline_complete`` in the shared event log.
+    try:
+        event_bridge.GCSEventBroker(storage, owner_user_id).clear_history(project_id)
+    except Exception:
+        logger.exception("failed to clear events before placement start for %s", project_id)
+
+    try:
+        execution_name = job_runner.enqueue_placement_pipeline(
+            project_id, owner_user_id,
+        )
+    except Exception:
+        logger.exception("enqueue_placement_pipeline failed for %s", project_id)
+        proj_svc.update_project(
+            storage, owner_user_id, project_id,
+            placement_status="error",
+            placement_state={"error": "Failed to enqueue placement worker"},
+        )
+        raise HTTPException(503, "Failed to enqueue placement worker; please retry")
+
+    proj_svc.update_project(
+        storage, owner_user_id, project_id,
+        placement_execution_name=execution_name,
+    )
+    return {"status": "started", "project_id": project_id}
+
+
+@router.post("/pipeline/{project_id}/placement/cancel")
+async def cancel_placement(project_id: str, request: Request):
+    """Soft-cancel the Placement pipeline via ``placement_cancel_requested``."""
+    from backend.services.placement_pipeline import placement_busy
+
+    storage = get_storage(request)
+    owner_user_id, meta = await resolve_or_404(request, project_id)
+    if not placement_busy(meta):
+        raise HTTPException(
+            409,
+            f"Placement is not running (placement_status={meta.placement_status})",
+        )
+    proj_svc.update_project(
+        storage, owner_user_id, project_id,
+        placement_cancel_requested=True,
+    )
+    return {"status": "cancel_requested", "project_id": project_id}
+
+
+@router.get("/pipeline/{project_id}/placement/plan")
+async def get_placement_plan(project_id: str, request: Request):
+    """Return ``placement_plan.json`` (F1 topology — no coordinates)."""
+    storage = get_storage(request)
+    owner_user_id, _ = await resolve_or_404(request, project_id)
+    key = f"{proj_svc.project_prefix(owner_user_id, project_id)}/placement_plan.json"
+    if not storage.exists(key):
+        # Fallback for plans written only as functional_groups during analysis.
+        key = f"{proj_svc.project_prefix(owner_user_id, project_id)}/functional_groups.json"
+    if not storage.exists(key):
+        raise HTTPException(404, "Placement plan not found — run placement first")
+    return storage.read_json(key)
+
+
+@router.get("/pipeline/{project_id}/placement/events")
+async def placement_events(project_id: str, request: Request):
+    """SSE stream for Placement pipeline progress (watches placement_* only)."""
+    owner_user_id, meta = await resolve_or_404(request, project_id)
+    storage = get_storage(request)
+
+    async def event_generator():
+        execution_name = meta.placement_execution_name
+        crash_detected: dict[str, str | None] = {"reason": None}
+
+        async def watch_status() -> None:
+            poll_interval = 2.0
+            saw_active = (meta.placement_status or "draft") in ("queued", "running")
+            while True:
+                await asyncio.sleep(poll_interval)
+                try:
+                    cur = proj_svc.get_project(storage, owner_user_id, project_id)
+                except Exception:
+                    continue
+                if cur is None:
+                    continue
+                pst = cur.placement_status or "draft"
+                if pst in ("queued", "running"):
+                    saw_active = True
+                elif saw_active and pst in ("complete", "error", "cancelled"):
+                    # Worker wrote terminal status; if SSE missed the event,
+                    # surface a synthetic terminal after a short grace.
+                    crash_detected["reason"] = f"placement_status={pst} (terminal)"
+                    return
+                if execution_name:
+                    try:
+                        state = job_runner.get_execution_state(execution_name)
+                    except Exception:
+                        state = "unknown"
+                    if state in _EXEC_TERMINAL and (
+                        saw_active or pst in ("queued", "running")
+                    ):
+                        crash_detected["reason"] = f"execution state={state}"
+                        return
+
+        watcher = asyncio.create_task(watch_status())
+        try:
+            async for msg in event_bridge.tail_events(
+                storage, owner_user_id, project_id,
+                terminal_events=_PLACEMENT_SSE_TERMINAL,
+            ):
+                if crash_detected["reason"] is not None:
+                    break
+                ev = msg["event"]
+                # Skip leftover analysis events if the log was not cleared yet.
+                if not (
+                    ev.startswith("placement_")
+                    or ev == "heartbeat"
+                ):
+                    continue
+                yield {
+                    "event": ev,
+                    "data": json.dumps(msg.get("data", {})),
+                }
+                if ev in _PLACEMENT_SSE_TERMINAL:
+                    return
+
+            if crash_detected["reason"] is not None:
+                cur = proj_svc.get_project(storage, owner_user_id, project_id)
+                err = None
+                if cur and cur.placement_state:
+                    err = cur.placement_state.get("error")
+                yield {
+                    "event": "placement_error",
+                    "data": json.dumps({
+                        "error": err or crash_detected["reason"]
+                        or "placement worker terminated without a terminal event",
+                        "synthetic": True,
+                    }),
+                }
+        finally:
+            watcher.cancel()
+            try:
+                await watcher
+            except (asyncio.CancelledError, Exception):
+                pass
+
+    return EventSourceResponse(
+        event_generator(),
+        ping=15,
+        headers={
+            "Cache-Control": "no-cache, no-transform",
+            "X-Accel-Buffering": "no",
+            "Connection": "keep-alive",
+        },
+    )
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------

backend/services/event_bridge.py

@@ -46,6 +46,9 @@ TERMINAL_EVENTS = frozenset({
     "pipeline_error",
     "pipeline_cancelled",
     "pipeline_paused",
+    "placement_complete",
+    "placement_error",
+    "placement_cancelled",
 })
 
 
@@ -131,19 +134,19 @@ async def tail_events(
     *,
     poll_interval: float = 0.5,
     heartbeat_interval: float = 15.0,
+    terminal_events: frozenset[str] | None = None,
 ) -> AsyncIterator[dict]:
     """Yield events from the GCS-backed event log in order.
 
-    Stops yielding after a terminal event (``pipeline_complete``,
-    ``pipeline_error``, ``pipeline_cancelled``). Emits a
-    ``{"event": "heartbeat", "data": {}}`` synthetic event roughly every
-    ``heartbeat_interval`` seconds when no real events arrive, matching
-    the behaviour of the in-memory broker's SSE loop.
+    Stops yielding after a terminal event (default ``TERMINAL_EVENTS``).
+    Emits a ``{"event": "heartbeat", "data": {}}`` synthetic event roughly
+    every ``heartbeat_interval`` seconds when no real events arrive.
 
     The caller is expected to handle disconnects/cancellations and
     secondary terminal-detection (``meta.status``, Cloud Run execution
     state) on top of this iterator.
     """
+    stop_on = terminal_events if terminal_events is not None else TERMINAL_EVENTS
     prefix = _events_prefix(user_id, project_id)
     last_seen_key: str | None = None
     last_emit_ts = 0.0
@@ -166,7 +169,7 @@ async def tail_events(
             emitted_any = True
             last_seen_key = key
             last_emit_ts = asyncio.get_event_loop().time()
-            if msg.get("event") in TERMINAL_EVENTS:
+            if msg.get("event") in stop_on:
                 return
 
         now = asyncio.get_event_loop().time()

backend/services/job_runner.py

@@ -58,8 +58,11 @@ def _spawn_local_subprocess(
     free: bool,
     mode: str = "run",
     regen_stages: list[str] | None = None,
+    proc_key: str | None = None,
+    execution_name: str | None = None,
 ) -> str:
-    name = _local_execution_name(project_id)
+    key = proc_key or project_id
+    name = execution_name or _local_execution_name(project_id)
     env = os.environ.copy()
     env["PROJECT_ID"] = project_id
     env["USER_ID"] = user_id
@@ -74,17 +77,20 @@ def _spawn_local_subprocess(
         env=env,
         stdin=subprocess.DEVNULL,
     )
-    _write_pid(project_id, proc.pid)
+    _write_pid(key, proc.pid)
     with _local_procs_lock:
-        # Reap any old proc for the same project before tracking the new one.
-        prior = _local_procs.pop(project_id, None)
+        # Reap any old proc for the same key before tracking the new one.
+        prior = _local_procs.pop(key, None)
         if prior is not None:
             try:
                 prior.terminate()
             except Exception:
                 pass
-        _local_procs[project_id] = proc
-    logger.info("dev: spawned worker subprocess pid=%s for %s", proc.pid, project_id)
+        _local_procs[key] = proc
+    logger.info(
+        "dev: spawned worker subprocess pid=%s for %s mode=%s",
+        proc.pid, project_id, mode,
+    )
     return name
 
 
@@ -341,6 +347,9 @@ def get_execution_state(execution_name: str | None) -> ExecutionState:
     if execution_name.startswith("local/projects/"):
         project_id = execution_name.split("/", 2)[-1]
         return _local_state(project_id)
+    if execution_name.startswith("local/placement/"):
+        project_id = execution_name.split("/", 2)[-1]
+        return _local_state(f"placement:{project_id}")
     return _cloud_run_state(execution_name)
 
 
@@ -356,4 +365,21 @@ def cancel_execution(execution_name: str | None) -> None:
         project_id = execution_name.split("/", 2)[-1]
         _local_cancel(project_id)
         return
+    if execution_name.startswith("local/placement/"):
+        project_id = execution_name.split("/", 2)[-1]
+        _local_cancel(f"placement:{project_id}")
+        return
     _cloud_run_cancel(execution_name)
+
+
+def enqueue_placement_pipeline(project_id: str, user_id: str) -> str:
+    """Dispatch the parallel Placement pipeline (topology plan, no LLM)."""
+    if use_cloud_run_jobs():
+        return _enqueue_cloud_run_job(
+            project_id, user_id, resume=False, free=True, mode="placement",
+        )
+    return _spawn_local_subprocess(
+        project_id, user_id, resume=False, free=True, mode="placement",
+        proc_key=f"placement:{project_id}",
+        execution_name=f"local/placement/{project_id}",
+    )

backend/services/pipeline.py

@@ -259,6 +259,8 @@ class PipelineWorkspace:
             self._upload_file("design_graph.json")
             self._upload_file("layout_graph.json")
             self._upload_file("impedance_nets.json")
+            self._upload_file("functional_groups.json")
+            self._upload_file("placement_plan.json")
             self._upload_file("bom_summary.json")
             self._upload_file("derating.json")
             self._upload_file("report.json")

backend/services/placement_pipeline.py

@@ -0,0 +1,200 @@
+"""Placement pipeline — parallel to analysis, topology only (no LLM / no mm).
+
+Stages: ensure_graph → classify → write_plan.
+Writes ``placement_plan.json`` (+ refreshes ``functional_groups.json``).
+Uses ``placement_status`` so analysis ``status`` is untouched.
+"""
+
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+
+from backend.pinscopex.functional_groups import build_placement_plan
+from backend.pinscopex.graph import build_graph
+from backend.pinscopex.models import ComponentConstraints, DesignGraph
+from backend.services import projects as proj_svc
+from backend.services.pipeline import PipelineWorkspace, broker
+from backend.services.storage import StorageBackend
+
+logger = logging.getLogger(__name__)
+
+_PLACEMENT_ACTIVE = frozenset({"queued", "running"})
+_ANALYSIS_BUSY = frozenset({
+    proj_svc.STATUS_QUEUED,
+    proj_svc.STATUS_RUNNING,
+})
+
+
+def _load_constraints_map(extracted_dir: Path) -> dict[str, ComponentConstraints]:
+    """Load per-MPN extractions without importing the Anthropic review path."""
+    result: dict[str, ComponentConstraints] = {}
+    if not extracted_dir.is_dir():
+        return result
+    for f in extracted_dir.glob("*.json"):
+        try:
+            c = ComponentConstraints.model_validate_json(
+                f.read_text(encoding="utf-8"),
+            )
+        except Exception:
+            logger.exception("skipping bad extraction %s", f)
+            continue
+        result[c.mpn] = c
+    return result
+
+
+def _publish(project_id: str, event: str, data: dict) -> None:
+    broker.publish(project_id, event, data)
+
+
+def _step(project_id: str, stage: str, status: str, detail: str = "") -> None:
+    payload: dict = {"stage": stage, "status": status}
+    if detail:
+        payload["detail"] = detail
+    _publish(project_id, "placement_step_update", payload)
+
+
+async def run_placement_pipeline(
+    storage: StorageBackend, user_id: str, project_id: str,
+) -> None:
+    """Run the placement topology pipeline (no extraction / review)."""
+    meta = proj_svc.get_project(storage, user_id, project_id)
+    if not meta:
+        raise ValueError(f"Project {project_id} not found")
+
+    # Boot: queued → running on placement_status only.
+    if meta.placement_status not in _PLACEMENT_ACTIVE:
+        logger.warning(
+            "placement worker booted with placement_status=%s for %s; exiting",
+            meta.placement_status, project_id,
+        )
+        return
+
+    proj_svc.update_project(
+        storage, user_id, project_id,
+        placement_status="running",
+        placement_cancel_requested=False,
+        placement_state=None,
+    )
+
+    try:
+        async with PipelineWorkspace(storage, user_id, project_id) as ws:
+            if _cancelled(storage, user_id, project_id):
+                _finish_cancelled(storage, user_id, project_id)
+                return
+
+            graph = await _ensure_graph(ws, meta, project_id)
+            if _cancelled(storage, user_id, project_id):
+                _finish_cancelled(storage, user_id, project_id)
+                return
+
+            _step(project_id, "classify", "running", "domains and satellite roles")
+            extracted_dir = ws.local_path("extracted")
+            cmap = _load_constraints_map(extracted_dir)
+            plan = build_placement_plan(graph, cmap)
+            _step(
+                project_id, "classify", "complete",
+                f"{len(plan.domains)} domains, {len(plan.groups)} IC groups",
+            )
+
+            if _cancelled(storage, user_id, project_id):
+                _finish_cancelled(storage, user_id, project_id)
+                return
+
+            _step(project_id, "write_plan", "running")
+            plan_path = ws.local_path("placement_plan.json")
+            plan_json = plan.model_dump_json(indent=2) + "\n"
+            plan_path.write_text(plan_json)
+            # Keep functional_groups.json in sync for consumers that already read it.
+            fg_path = ws.local_path("functional_groups.json")
+            fg_path.write_text(plan_json)
+            ws._upload_file("placement_plan.json")
+            ws._upload_file("functional_groups.json")
+            _step(project_id, "write_plan", "complete", "placement_plan.json")
+
+        proj_svc.update_project(
+            storage, user_id, project_id,
+            placement_status="complete",
+            placement_state={
+                "domains": len(plan.domains),
+                "groups": len(plan.groups),
+            },
+            placement_cancel_requested=False,
+        )
+        _publish(project_id, "placement_complete", {
+            "domains": len(plan.domains),
+            "groups": len(plan.groups),
+        })
+    except Exception as e:
+        logger.exception("placement pipeline failed for %s", project_id)
+        proj_svc.update_project(
+            storage, user_id, project_id,
+            placement_status="error",
+            placement_state={"error": str(e)},
+        )
+        _publish(project_id, "placement_error", {"error": str(e)})
+
+
+async def _ensure_graph(ws: PipelineWorkspace, meta, project_id: str) -> DesignGraph:
+    """Reuse design_graph.json when present; otherwise graph_build only."""
+    graph_path = ws.local_path("design_graph.json")
+    if graph_path.is_file():
+        _step(project_id, "ensure_graph", "running", "reusing design_graph.json")
+        graph = DesignGraph.model_validate_json(graph_path.read_text(encoding="utf-8"))
+        _step(
+            project_id, "ensure_graph", "complete",
+            f"{len(graph.components)} components (cached)",
+        )
+        return graph
+
+    _step(project_id, "ensure_graph", "running", "building design graph")
+    bom_path = ws.local_path("uploads/bom.csv")
+    netlist_path = ws.netlist_local_path()
+    if not bom_path.is_file() or not Path(netlist_path).is_file():
+        raise FileNotFoundError("Missing BOM or netlist for placement graph_build")
+
+    col_map = meta.bom_columns or {}
+    graph = build_graph(
+        str(netlist_path),
+        str(bom_path),
+        str(ws.local_path("extracted")),
+        str(ws.local_path("patterns")),
+        str(ws.local_path("models")),
+        reference_col=col_map.get("reference", "Reference"),
+        mpn_col=col_map.get("mpn", "Manufacturer Part Number"),
+        include_subdesigns=(
+            set(meta.netlist_subdesigns)
+            if meta.netlist_subdesigns is not None
+            else None
+        ),
+        pcb_path=ws.local_path("uploads/pcb.kicad_pcb"),
+    )
+    graph_path.write_text(graph.model_dump_json(indent=2) + "\n")
+    ws._upload_file("design_graph.json")
+    _step(
+        project_id, "ensure_graph", "complete",
+        f"{len(graph.components)} components, {len(graph.nets)} nets",
+    )
+    return graph
+
+
+def _cancelled(storage: StorageBackend, user_id: str, project_id: str) -> bool:
+    meta = proj_svc.get_project(storage, user_id, project_id)
+    return bool(meta and meta.placement_cancel_requested)
+
+
+def _finish_cancelled(storage: StorageBackend, user_id: str, project_id: str) -> None:
+    proj_svc.update_project(
+        storage, user_id, project_id,
+        placement_status="cancelled",
+        placement_cancel_requested=False,
+    )
+    _publish(project_id, "placement_cancelled", {})
+
+
+def placement_busy(meta: proj_svc.ProjectMeta) -> bool:
+    return (meta.placement_status or "draft") in _PLACEMENT_ACTIVE
+
+
+def analysis_busy(meta: proj_svc.ProjectMeta) -> bool:
+    return meta.status in _ANALYSIS_BUSY

backend/services/projects.py

@@ -132,6 +132,13 @@ class ProjectMeta(BaseModel):
     # gate (inside _charge_for_logs) and exits cleanly.
     cancel_requested: bool = False
 
+    # Placement pipeline (parallel to analysis — does not overwrite status).
+    # draft | queued | running | complete | error | cancelled
+    placement_status: str = "draft"
+    placement_state: dict[str, Any] | None = None
+    placement_execution_name: str | None = None
+    placement_cancel_requested: bool = False
+
 
 def completed_review_refs_for_retry(
     storage: StorageBackend, user_id: str, project_id: str,