fix(replay): recover failed archives and release deleted sessions

src/k1link/sessions/preparation.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 import os
 import queue
 import threading
@@ -20,6 +21,8 @@ from .recording import (
     SessionRecordingMaterializer,
 )
 
+LOGGER = logging.getLogger(__name__)
+
 PreparationState = Literal[
     "queued",
     "validating",
@@ -582,6 +585,12 @@ class SessionRecordingPreparationManager:
                     except Exception:
                         # The public status intentionally does not expose paths,
                         # broker payloads or exporter internals.
+                        LOGGER.exception(
+                            "recording preparation materialization failed: "
+                            "session_id=%s preparation_id=%s",
+                            job.command.session_id,
+                            job.preparation_id,
+                        )
                         with self._guard:
                             if job.cancel_event.is_set():
                                 self._transition_locked(job, "cancelled", job.progress)
@@ -616,6 +625,12 @@ class SessionRecordingPreparationManager:
                                 recording_end_seconds=(recording.timeline_end_ns / 1_000_000_000),
                             )
                         except Exception:
+                            LOGGER.exception(
+                                "recording preparation finalization failed: "
+                                "session_id=%s preparation_id=%s",
+                                job.command.session_id,
+                                job.preparation_id,
+                            )
                             with self._guard:
                                 if job.cancel_event.is_set():
                                     self._transition_locked(job, "cancelled", job.progress)

src/k1link/web/session_api.py

@@ -372,8 +372,10 @@ def build_session_router(
         try:
             store.get_session(session_id)
             recorded_artifacts = store.list_recorded_media(session_id)
-        except SessionNotFoundError as exc:
-            raise HTTPException(status_code=404, detail=str(exc)) from exc
+        except SessionNotFoundError:
+            # DELETE is idempotent. Multiple mounted catalogs or another
+            # operator tab may have already removed the exact session.
+            return Response(status_code=204)
         except ValueError as exc:
             raise HTTPException(
                 status_code=422,
@@ -427,8 +429,10 @@ def build_session_router(
                 (artifact.artifact_id for artifact in recorded_artifacts),
             )
             await run_in_threadpool(store.delete_session, session_id)
-        except SessionNotFoundError as exc:
-            raise HTTPException(status_code=404, detail=str(exc)) from exc
+        except SessionNotFoundError:
+            # A concurrent idempotent delete won the race after both callers
+            # resolved the catalog row.
+            return Response(status_code=204)
         except (OSError, SessionIntegrityError) as exc:
             raise HTTPException(
                 status_code=409,
@@ -469,7 +473,12 @@ def build_session_router(
                         recording_preparation_manager.restore_published,
                         command,
                     )
-                if snapshot is None:
+                if snapshot is None or snapshot.state in {"failed", "cancelled"}:
+                    # A terminal preparation describes one attempt, not the
+                    # durable session. A fresh POST /replay is explicit retry
+                    # intent and must replace that attempt. This also recovers
+                    # the camera-finalization race where the RRD is already
+                    # published but the media archive seals moments later.
                     snapshot = recording_preparation_manager.enqueue(
                         command,
                         retry_failed=True,