Release version 0.1.1 [skip ci]

docs/deployment/GITEA_CD.md

@@ -363,3 +363,16 @@ the audit client's normal HTTP freshness rules. It is not a permanent offline
 snapshot or a cross-job cache. Raw network exceptions are omitted because proxy
 URLs may contain credentials. Logs identify the advisory host and whether the
 complete audit succeeded.
+
+### Production image retention
+
+After a deployment passes verification and its success journal is saved, Frame Flow
+removes obsolete `release-<commit>-<owner>` and `rollback-<owner>` images from the
+configured production image repository. It retains the running version and the
+previous deployment baseline for one-step rollback. Images referenced by any
+container (including stopped containers), images with unrelated tags, and CI
+images are protected. Retention does not prune build cache, volumes, or data.
+Failed deployments do not run retention; cleanup failure produces a warning and
+never rolls back a successfully verified deployment. Historical deployment
+journals remain available for audit, but only the latest rollback image is
+retained locally; older releases require rebuilding before use.

pigway_frame_flow/api/app.py

@@ -124,7 +124,7 @@ def create_app(settings=None, start_worker=True):
     app = FastAPI(
         title="Pigway Frame Flow API",
         docs_url=None,
-        version="0.1.0",
+        version="0.1.1",
         lifespan=lifespan,
         responses=error_responses,
     )
@@ -1000,7 +1000,7 @@ def create_app(settings=None, start_worker=True):
     )
     def settings_view():
         return SettingsView(
-            version="0.1.0",
+            version="0.1.1",
             mock=settings.mock,
             write_enabled=settings.write_enabled,
             api_key_configured=bool(settings.api_key)

pigway_frame_flow/display/service.py

@@ -50,6 +50,7 @@ class DisplayService:
         self.retention = Retention(self)
         self.cloud_library = CloudLibrary(self)
         self.expiration_checked: dict[str, float] = {}
+        self.unknown_checked: dict[str, float] = {}
         # A killed write cannot be replayed safely; pre-write work can resume.
         db.execute(
             "UPDATE operations SET status='UNKNOWN', updated_at=? WHERE write_started=1 AND status IN ('UPLOADING','RENDERING')",
@@ -689,6 +690,31 @@ class DisplayService:
         )
 
     def sync(self):
+        # Late acknowledgements only resolve a known display target. Never replay
+        # writes or infer success from gallery presence alone.
+        for op in self.db.all(
+            "SELECT * FROM operations WHERE status='UNKNOWN' AND action='display' AND write_started=1"
+        ):
+            expected = json.loads(op["result"] or "{}").get("image_id")
+            if not expected:
+                continue
+            checked = time.monotonic()
+            if checked - self.unknown_checked.get(op["id"], float("-inf")) < 60:
+                continue
+            self.unknown_checked[op["id"]] = checked
+            try:
+                device = self.registry.get(op["device_id"]).device(refresh=True)
+                if (
+                    device.current_content.id == expected
+                    and device.current_content.synced
+                ):
+                    self.update(op["id"], "COMPLETED")
+                    self.cloud_library.confirm(op["id"])
+                    self.db.history(op, "COMPLETED")
+                    self.db.event("operation.completed", {"operation_id": op["id"]})
+                    self.unknown_checked.pop(op["id"], None)
+            except FlowError:
+                pass
         for op in self.db.all("SELECT * FROM operations WHERE status='SYNCING'"):
             try:
                 device = self.registry.get(op["device_id"]).device()
@@ -824,6 +850,9 @@ class DisplayService:
                     {"image_id": device.current_content.id},
                 )
                 resolved = True
+                if confirmed and op["action"] == "display":
+                    self.cloud_library.confirm(id)
+                    self.db.event("operation.completed", {"operation_id": id})
                 self.db.history(
                     dict(
                         id=id,

pigway_frame_flow/models.py

@@ -336,7 +336,7 @@ class SettingsView(BaseModel):
 
 class Health(BaseModel):
     status: str
-    version: str = "0.1.0"
+    version: str = "0.1.1"
 
 
 class Readiness(BaseModel):
@@ -366,7 +366,7 @@ class RestoreRequest(StrictModel):
 
 class Version(BaseModel):
     product: str = "Pigway Frame Flow"
-    version: str = "0.1.0"
+    version: str = "0.1.1"
     api_version: str = "v1"
     commit: str = "development"
     build_time: str = "unknown"

pigway_frame_flow/scheduler/engine.py

@@ -269,6 +269,9 @@ class Scheduler:
     def run(self):
         while not self.stop_event.is_set():
             try:
+                # Resolve late sync before submitting due jobs: a write lock
+                # otherwise makes tick fail before reconciliation can run.
+                self.service.sync()
                 self.tick()
                 self.service.expire()
                 self.service.cloud_library.sweep()

pigway_frame_flow/web/index.html

@@ -1,3 +1,3 @@
 <!doctype html>
 <html lang="zh-CN"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><meta name="color-scheme" content="light dark"><title>Pigway Frame Flow</title><link rel="stylesheet" href="/ui/style.css"></head>
-<body><aside class="sidebar"><a class="brand" href="/"><span class="brand-icon">F<span>↗</span></span><span>Frame Flow<small>Pigway · Smart Frame Automation</small></span></a><nav id="nav"></nav><div class="sidebar-bottom"><small>Version 0.1.0</small></div></aside><div class="workspace"><header><div><span class="eyebrow">PIGWAY FRAME FLOW</span><h1 id="page-title"></h1></div><div class="toolbar"><select id="device" aria-label="Device"></select><button id="lang" class="icon-button" aria-label="Change language">EN</button><button id="theme" class="icon-button" aria-label="Change theme">◐</button></div></header><main id="main"></main><footer id="footer"></footer></div><div id="toast" role="status" aria-live="polite"></div><dialog id="modal"><div id="modal-content"></div></dialog><script src="/ui/i18n.js"></script><script src="/ui/features.js"></script><script src="/ui/extensions.js"></script><script src="/ui/app.js"></script></body></html>
+<body><aside class="sidebar"><a class="brand" href="/"><span class="brand-icon">F<span>↗</span></span><span>Frame Flow<small>Pigway · Smart Frame Automation</small></span></a><nav id="nav"></nav><div class="sidebar-bottom"><small>Version 0.1.1</small></div></aside><div class="workspace"><header><div><span class="eyebrow">PIGWAY FRAME FLOW</span><h1 id="page-title"></h1></div><div class="toolbar"><select id="device" aria-label="Device"></select><button id="lang" class="icon-button" aria-label="Change language">EN</button><button id="theme" class="icon-button" aria-label="Change theme">◐</button></div></header><main id="main"></main><footer id="footer"></footer></div><div id="toast" role="status" aria-live="polite"></div><dialog id="modal"><div id="modal-content"></div></dialog><script src="/ui/i18n.js"></script><script src="/ui/features.js"></script><script src="/ui/extensions.js"></script><script src="/ui/app.js"></script></body></html>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pigway-frame-flow"
-version = "0.1.0"
+version = "0.1.1"
 requires-python = ">=3.12"
 dependencies = ["paho-mqtt==2.1.0", "python-dateutil==2.9.0.post0", "fastapi==0.142.2", "uvicorn==0.54.0", "pillow==12.3.0", "requests==2.34.2", "croniter==6.2.4", "python-multipart==0.0.32", "pyyaml==6.0.3"]
 [project.optional-dependencies]

scripts/production-deploy.py

@@ -723,6 +723,50 @@ class Deploy:
         text = re.sub(r"https?://[^\s\"'<>]+", "[REDACTED-URL]", text)
         print("Scoped container logs (redacted):", text, flush=True)
 
+    def cleanup_images(self):
+        """Retain container references and the verified deployment's rollback baseline."""
+        try:
+            protected = {self.state["previous_image"]}
+            container_ids = self.run("ps", "-aq").stdout.decode().split()
+            if container_ids:
+                containers = json.loads(self.run("inspect", *container_ids).stdout)
+                protected.update(container["Image"] for container in containers)
+            repo = self.env["PROD_IMAGE_REPO"]
+            image_ids = (
+                self.run("image", "ls", "--no-trunc", "-q", repo)
+                .stdout.decode()
+                .split()
+            )
+            if not image_ids:
+                return
+            images = json.loads(
+                self.run("image", "inspect", *sorted(set(image_ids))).stdout
+            )
+            removed = 0
+            for image in images:
+                tags = image.get("RepoTags") or []
+                # Shared images and unrelated tags are never cleanup targets.
+                if image["Id"] in protected or not tags:
+                    continue
+                if not all(
+                    re.fullmatch(
+                        re.escape(repo)
+                        + r":(?:release-[0-9a-f]{40}-[0-9a-f]{8}|rollback-[0-9a-f]{32})",
+                        tag,
+                    )
+                    for tag in tags
+                ):
+                    continue
+                result = self.run("image", "rm", *tags, check=False)
+                if result.returncode:
+                    print("IMAGE RETENTION: referenced image retained", flush=True)
+                else:
+                    removed += 1
+            print(f"IMAGE RETENTION: removed {removed} obsolete images", flush=True)
+        except Exception:
+            # Cleanup failure must never roll back an already verified deployment.
+            print("IMAGE RETENTION WARNING: cleanup deferred", flush=True)
+
     def deploy(self):
         previous = self.preflight()
         self.lock()
@@ -769,6 +813,7 @@ class Deploy:
             self.state["status"] = "success"
             self.state_io(self.state)
             print("DEPLOY VERIFIED", flush=True)
+            self.cleanup_images()
         except BaseException as exc:
             print("DEPLOY FAILED:", type(exc).__name__, flush=True)
             self.diagnostics()

tests/test_display.py

@@ -152,3 +152,55 @@ def test_offline(service):
     id = submit(service)
     service.process_one()
     assert service.operation(id)["error"]["code"] == "DEVICE_OFFLINE"
+
+
+def test_late_sync_resolves_unknown_without_upload_retry(service, monkeypatch):
+    id = submit(service)
+    service.process_one()
+    service.update(id, "UNKNOWN")
+    driver = service.registry.get("living-room")
+    calls = []
+    device = driver.device
+    monkeypatch.setattr(driver, "device", lambda **kw: calls.append(kw) or device(**kw))
+    service.sync()
+    assert service.operation(id)["status"] == "COMPLETED"
+    assert driver.client.uploads == 1
+    assert calls == [{"refresh": True}]
+    assert not service.blocked("living-room")
+    assert service.db.one(
+        "SELECT confirmed_at FROM managed_cloud_uploads WHERE operation_id=?", (id,)
+    )["confirmed_at"]
+
+
+def test_unknown_wrong_target_stays_locked_and_queries_at_most_once_per_minute(
+    service, monkeypatch
+):
+    id = submit(service)
+    service.process_one()
+    service.update(id, "UNKNOWN")
+    driver = service.registry.get("living-room")
+    driver.client.display(1)
+    driver.invalidate()
+    calls = []
+    device = driver.device
+    monkeypatch.setattr(driver, "device", lambda **kw: calls.append(kw) or device(**kw))
+    service.sync()
+    service.sync()
+    assert service.operation(id)["status"] == "UNKNOWN"
+    assert service.blocked("living-room")
+    assert driver.client.uploads == 1
+    assert len(calls) == 1
+
+
+def test_unknown_matching_image_without_sync_stays_locked(service, monkeypatch):
+    id = submit(service)
+    service.process_one()
+    service.update(id, "UNKNOWN")
+    driver = service.registry.get("living-room")
+    device = driver.device()
+    device.current_content.synced = False
+    monkeypatch.setattr(driver, "device", lambda **kw: device)
+    service.sync()
+    assert service.operation(id)["status"] == "UNKNOWN"
+    assert service.blocked("living-room")
+    assert driver.client.uploads == 1

tests/test_production_deploy.py

@@ -111,6 +111,10 @@ def test_deploy_rolls_back_exact_baseline_without_deleting_data(
     monkeypatch.setattr(
         tool, "state_io", lambda state: saved.append(json.loads(json.dumps(state)))
     )
+    cleanup = []
+    monkeypatch.setattr(
+        tool, "cleanup_images", lambda: cleanup.append(saved[-1]["status"])
+    )
     verifies = []
 
     def verify(config):
@@ -125,11 +129,13 @@ def test_deploy_rolls_back_exact_baseline_without_deleting_data(
     if failure:
         with pytest.raises(RuntimeError):
             tool.deploy()
+        assert cleanup == []
         assert activated == [new, old]
         assert saved[0]["previous"] == old
         assert ("unlock" in calls) is (failure != "rollback")
     else:
         tool.deploy()
+        assert cleanup == ["success"]
         assert activated == [new]
         assert saved[-1]["status"] == "success"
     assert not any(
@@ -243,3 +249,53 @@ def test_lock_conflict_never_activates_production(tool, monkeypatch):
     monkeypatch.setattr(tool, "run", fail)
     with pytest.raises(RuntimeError):
         tool.deploy()
+
+
+def test_image_retention_protects_containers_rollback_and_other_tags(tool, monkeypatch):
+    tool.state = {"previous_image": "previous"}
+    release = "pigway-frame-flow:release-" + "a" * 40 + "-" + "b" * 8
+    rollback = "pigway-frame-flow:rollback-" + "c" * 32
+    images = [
+        {"Id": "current", "RepoTags": [release]},
+        {"Id": "previous", "RepoTags": [rollback]},
+        {"Id": "stopped", "RepoTags": [release]},
+        {"Id": "obsolete", "RepoTags": [release, rollback]},
+        {"Id": "shared", "RepoTags": [release, "other:latest"]},
+        {"Id": "ci", "RepoTags": ["ffci-fixture:latest"]},
+    ]
+    calls = []
+
+    def run(*args, **kwargs):
+        calls.append(args)
+        if args == ("ps", "-aq"):
+            data = "container1 container2"
+        elif args[0] == "inspect":
+            data = json.dumps([{"Image": "current"}, {"Image": "stopped"}])
+        elif args[:2] == ("image", "ls"):
+            data = "current previous stopped obsolete shared ci"
+        elif args[:2] == ("image", "inspect"):
+            data = json.dumps(images)
+        else:
+            data = ""
+        return SimpleNamespace(stdout=data.encode(), returncode=0)
+
+    monkeypatch.setattr(tool, "run", run)
+    tool.cleanup_images()
+    assert [c for c in calls if c[:2] == ("image", "rm")] == [
+        ("image", "rm", release, rollback)
+    ]
+
+
+def test_image_retention_failure_does_not_fail_verified_deploy(
+    tool, monkeypatch, capsys
+):
+    tool.state = {"previous_image": "previous"}
+
+    def unavailable(*args, **kwargs):
+        raise RuntimeError("private diagnostic")
+
+    monkeypatch.setattr(tool, "run", unavailable)
+    tool.cleanup_images()
+    output = capsys.readouterr().out
+    assert "cleanup deferred" in output
+    assert "private diagnostic" not in output

tests/test_scheduler.py

@@ -75,3 +75,21 @@ def test_playlist(app, service):
 def test_invalid_cron():
     with pytest.raises(FlowError):
         next_run(Schedule(type="cron", cron="* * * * * *"))
+
+
+def test_worker_checks_late_sync_before_due_tasks(app, service, monkeypatch):
+    scheduler = app.state.scheduler
+    calls = []
+    monkeypatch.setattr(service, "sync", lambda: calls.append("sync"))
+
+    def tick():
+        calls.append("tick")
+        scheduler.stop_event.set()
+
+    monkeypatch.setattr(scheduler, "tick", tick)
+    monkeypatch.setattr(service, "expire", lambda: None)
+    monkeypatch.setattr(service.cloud_library, "sweep", lambda: None)
+    monkeypatch.setattr(service.local_retention, "sweep", lambda: None)
+    monkeypatch.setattr(service, "process_one", lambda: False)
+    scheduler.run()
+    assert calls[:2] == ["sync", "tick"]