feat(watch,server): thread events over t3 websocket to the gateway hook, t3_answer for pending questions

tests/test_server.py

@@ -125,6 +125,18 @@ class FakeT3:
             thread = self.threads[command["threadId"]]
             thread.pop("_pending_turn", None)
             thread["latestTurn"] = {"turnId": "t", "state": "interrupted"}
+        elif kind == "thread.user-input.respond":
+            self.threads[command["threadId"]]["activities"].append(
+                {
+                    "kind": "user-input.resolved",
+                    "summary": "User input submitted",
+                    "tone": "info",
+                    "payload": {
+                        "requestId": command["requestId"],
+                        "answers": command["answers"],
+                    },
+                }
+            )
         else:
             return httpx.Response(
                 400, json={"code": "invalid_request", "reason": "invalid_command"}
@@ -430,3 +442,150 @@ async def test_wait_returns_on_runtime_failure(
         assert waited["state"] == "starting"
         assert waited["error"] == "Claude runtime stream failed."
         assert waited["waited"] < 1
+
+
+def shell_thread(
+    tid: str, state: str | None, *, user_input: bool = False, error: str | None = None
+) -> dict[str, Any]:
+    return {
+        "id": tid,
+        "latestTurn": {"turnId": "t", "state": state} if state else None,
+        "session": {"status": "stopped" if error else "running", "lastError": error},
+        "hasPendingUserInput": user_input,
+        "hasPendingApprovals": False,
+    }
+
+
+def test_tracker_transitions(tmp_path) -> None:
+    from t3code_mcp.watch import Tracker
+
+    tracker = Tracker(tmp_path / "state.json")
+    tracker.track("t1", "dell", "projects", "do x")
+    assert tracker.apply("dell", shell_thread("t1", None)) == []
+    assert tracker.apply("dell", shell_thread("t1", "running")) == []
+    assert [
+        e.kind
+        for e in tracker.apply("dell", shell_thread("t1", "running", user_input=True))
+    ] == ["question"]
+    assert tracker.apply("dell", shell_thread("t1", "running", user_input=True)) == []
+    assert [e.kind for e in tracker.apply("dell", shell_thread("t1", "completed"))] == [
+        "completed"
+    ]
+    assert tracker.apply("dell", shell_thread("t1", "completed")) == []
+    assert tracker.apply("mac", shell_thread("t1", "running")) == []
+    assert tracker.apply("dell", shell_thread("untracked", "completed")) == []
+    tracker.track("t2", "dell", "projects", "fail")
+    assert [
+        e.kind
+        for e in tracker.apply(
+            "dell", shell_thread("t2", None, error="Claude runtime stream failed.")
+        )
+    ] == ["failed"]
+    reloaded = Tracker(tmp_path / "state.json")
+    assert reloaded.threads["t1"].state == "completed"
+    assert reloaded.threads["t2"].error == "Claude runtime stream failed."
+
+
+async def test_hook_outbox_retries(tmp_path) -> None:
+    from t3code_mcp.watch import Hook, Tracker
+
+    attempts: list[dict[str, Any]] = []
+    fail_first = {"n": 1}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        assert request.headers["authorization"] == "Bearer gw"
+        attempts.append(json.loads(request.content))
+        if fail_first["n"]:
+            fail_first["n"] -= 1
+            return httpx.Response(503, text="down")
+        return httpx.Response(202, json={"job": 1})
+
+    tracker = Tracker(tmp_path / "state.json")
+    hook = Hook(
+        "http://gateway/hooks/t3code",
+        "gw",
+        tracker,
+        transport=httpx.MockTransport(handler),
+    )
+    hook.send({"event": "completed", "thread_id": "t1"})
+    assert Tracker(tmp_path / "state.json").outbox == [
+        {"event": "completed", "thread_id": "t1"}
+    ]
+    assert await hook.deliver_once() is False
+    assert await hook.deliver_once() is True
+    assert tracker.outbox == [] and len(attempts) == 2
+    await hook.aclose()
+
+
+async def test_answer_pending_question(
+    client: Client, fakes: dict[str, FakeT3]
+) -> None:
+    fakes["mac"].polls_until_done = 10_000
+    async with client:
+        started = data(
+            await client.call_tool(
+                "t3_dispatch",
+                {"machine": "mac", "project": "t3-smoke", "prompt": "ask"},
+            )
+        )
+        tid = started["thread_id"]
+        with pytest.raises(ToolError, match="no pending question"):
+            await client.call_tool(
+                "t3_answer", {"thread_id": tid, "answers": {"q1": "yes"}}
+            )
+        fakes["mac"].threads[tid]["activities"].append(
+            {
+                "kind": "user-input.requested",
+                "summary": "User input requested",
+                "tone": "info",
+                "payload": {
+                    "requestId": "req-1",
+                    "questions": [
+                        {
+                            "id": "q1",
+                            "header": "Deploy",
+                            "question": "Deploy now?",
+                            "options": [
+                                {"label": "yes", "description": "go"},
+                                {"label": "no", "description": "wait"},
+                            ],
+                        }
+                    ],
+                },
+            }
+        )
+        view = data(await client.call_tool("t3_thread", {"thread_id": tid}))
+        assert view["question"]["request_id"] == "req-1"
+        assert view["question"]["questions"][0]["options"][0]["label"] == "yes"
+        with pytest.raises(ToolError, match="unknown question ids"):
+            await client.call_tool(
+                "t3_answer", {"thread_id": tid, "answers": {"zz": "yes"}}
+            )
+        answered = data(
+            await client.call_tool(
+                "t3_answer", {"thread_id": tid, "answers": {"q1": "yes"}}
+            )
+        )
+        assert answered["answered"] == ["q1"]
+        cmd = fakes["mac"].commands[-1]
+        assert (
+            cmd["type"] == "thread.user-input.respond"
+            and cmd["requestId"] == "req-1"
+            and cmd["answers"] == {"q1": "yes"}
+        )
+
+
+async def test_dispatch_tracks_thread(client: Client, registry: Registry) -> None:
+    async with client:
+        started = data(
+            await client.call_tool(
+                "t3_dispatch",
+                {"machine": "mac", "project": "t3-smoke", "prompt": "track me"},
+            )
+        )
+    tracked = registry.tracker.threads[started["thread_id"]]
+    assert (tracked.machine, tracked.project, tracked.title) == (
+        "mac",
+        "t3-smoke",
+        "track me",
+    )