fix(sdk): harden runtime lifecycle and JSON-RPC

Keep DeepSeekHarness.run() reusable, but make ownership of its lazy
runtime process explicit. Document the context-manager/close contract and
update every construction example to use a context manager so repeated runs
remain valid without encouraging leaked subprocesses.

Contain notification predicate failures at the subscription boundary. Remove
only the subscriber whose callback raised, deliver that exception through its
queue, and continue dispatching to healthy subscribers so arbitrary callback
code cannot terminate the shared reader thread or strand later requests.

Enforce one in-flight prompt per server session with an atomic activePrompt
guard. Route overlap through the existing -32603 handler-error response and
clear the guard in finally, preserving parallel prompts across sessions and
sequential reuse without changing JSON-RPC request or notification shapes.

Use StringDecoder for line framing so a UTF-8 code point split across Buffer
chunks is not corrupted. Add a queued-write flush barrier, and make memoized
shutdown await it before disposal and exit while retaining exactly-once
cleanup when shutdown calls race or flushing fails.

Cover callback isolation, same-session exclusion, cross-session concurrency,
split multibyte input, delayed writes, racing shutdown, and flush failure with
deterministic tests.

python/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-README.md: d9403733b7daff9b3e8dbf21e1bc0c68d61b88a7
-README.zh.md: 28859e43b7332a8ef4c3cf199b97860447a011a8
+README.md: 35ed645ce0e4d5e4c88c8aae2fe33d94aea79b3e
+README.zh.md: bddb709114df2e46bbea6e6faeb660bffa30df2b

python/README.md

@@ -37,7 +37,8 @@ For an interactive check (needs `DEEPSEEK_API_KEY` in the environment or the rep
 
 ```python
 from deepseek_harness import DeepSeekHarness
-print(DeepSeekHarness().run("say hi").final_response)   # auto-resolution picks the bundled exe
+with DeepSeekHarness() as harness:
+    print(harness.run("say hi").final_response)   # auto-resolution picks the bundled exe
 ```
 
 ## Running the SDK against the Node source (no executable)

python/README.zh.md

@@ -37,7 +37,8 @@ uv run --project python/sdk pytest                                            #
 
 ```python
 from deepseek_harness import DeepSeekHarness
-print(DeepSeekHarness().run("say hi").final_response)   # auto-resolution picks the bundled exe
+with DeepSeekHarness() as harness:
+    print(harness.run("say hi").final_response)   # auto-resolution picks the bundled exe
 ```
 
 ## 对着 Node 源码运行 SDK（不用可执行文件）

python/sdk/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-README.md: 1916086324e18ce79ea572f3c85115fda3b4ab91
-README.zh.md: 380ed1726f2b541cd66403edb68a2629071e18f0
+README.md: 60540376c5fd85b0852e204bc8bad3f01c849de5
+README.zh.md: 7148a45c8f4bd22aaa28fc15ac9cd589cba13dfb

python/sdk/README.md

@@ -13,9 +13,12 @@ Installing `deepseek-harness` installs the exact same-version `deepseek-harness-
 ```py
 from deepseek_harness import DeepSeekHarness
 
-result = DeepSeekHarness().run("Say hi.")
+with DeepSeekHarness() as harness:
+    result = harness.run("Say hi.")
 ```
 
+`DeepSeekHarness` keeps its lazily started runtime subprocess for reuse across calls. Use it as a context manager, as above, or call `close()` explicitly when finished.
+
 By default, the SDK launches the bundled single-file `dsh-jsonrpc-agent` executable from the `deepseek-harness-runtime-bin` package and injects that package's default configuration (the stdio JSON-RPC server, agent core, preloaded DeepSeek adapter, JSONL session persistence, local bash) via `DSH_CORDIS_CONFIG`. To run a plugin composition of your own, keep the `@deepseek-ai/dsh-jsonrpc` entry in the config and pass the Cordis config path.
 
 ```py

python/sdk/README.zh.md

@@ -9,9 +9,12 @@
 ```py
 from deepseek_harness import DeepSeekHarness
 
-result = DeepSeekHarness().run("Say hi.")
+with DeepSeekHarness() as harness:
+    result = harness.run("Say hi.")
 ```
 
+`DeepSeekHarness` 会保留延迟启动的运行时子进程，以供多次调用复用。请像上例一样将其用作上下文管理器，或在用完后显式调用 `close()`。
+
 默认情况下，SDK 启动 `deepseek-harness-runtime-bin` 包内置的单文件 `dsh-jsonrpc-agent` 可执行程序，并通过 `DSH_CORDIS_CONFIG` 注入该包的默认配置（stdio JSON-RPC 服务器、agent core、预载的 DeepSeek 适配器、JSONL 会话持久化、本地 bash）。要运行自己用插件组合需要在配置里保留 `@deepseek-ai/dsh-jsonrpc` 条目，并传入 Cordis 配置路径。
 
 ```py

python/sdk/src/deepseek_harness/api.py

@@ -43,7 +43,12 @@ class TurnResult:
 
 
 class DeepSeekHarness:
-    """Synchronous high-level SDK for running DeepSeek Harness agent turns."""
+    """Reusable synchronous SDK for running DeepSeek Harness agent turns.
+
+    The runtime subprocess starts lazily and remains owned by this instance
+    across calls to :meth:`run`. Use the instance as a context manager, or call
+    :meth:`close` explicitly when finished, so the subprocess is always reaped.
+    """
 
     def __init__(self, config: DeepSeekHarnessConfig | None = None, **kwargs: object) -> None:
         if config is not None and kwargs:

python/sdk/src/deepseek_harness/client.py

@@ -350,10 +350,19 @@ class HarnessClient:
             params = message.get("params")
             notification = Notification(method=method, payload=params if isinstance(params, dict) else {})
             with self._lock:
-                subscribers = list(self._notification_subscribers.values())
+                subscribers = list(self._notification_subscribers.items())
             delivered = False
-            for subscriber, predicate in subscribers:
-                if predicate is None or predicate(notification):
+            for subscription_id, (subscriber, predicate) in subscribers:
+                try:
+                    matches = predicate is None or predicate(notification)
+                except BaseException as exc:
+                    with self._lock:
+                        current = self._notification_subscribers.get(subscription_id)
+                        if current is not None and current[0] is subscriber:
+                            self._notification_subscribers.pop(subscription_id, None)
+                    subscriber.put(exc)
+                    continue
+                if matches:
                     subscriber.put(notification)
                     delivered = True
             if not delivered:

python/sdk/tests/test_client.py

@@ -356,6 +356,48 @@ def test_client_keeps_unmatched_notifications_available_globally_while_subscribe
         assert notification.payload["sessionId"] == "other"
 
 
+def test_client_contains_notification_filter_failure_to_its_subscription(tmp_path: Path) -> None:
+    script = tmp_path / "fake_bridge.py"
+    script.write_text(
+        """
+import json
+import sys
+
+for line in sys.stdin:
+    msg = json.loads(line)
+    method = msg.get("method")
+    if method == "initialize":
+        print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
+    elif method in {"emit-first", "emit-second"}:
+        print(json.dumps({"jsonrpc": "2.0", "method": "tick", "params": {"source": method}}), flush=True)
+    elif method == "session/prompt":
+        print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"accepted": True}}), flush=True)
+    elif method == "shutdown":
+        print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
+        break
+""".strip()
+    )
+
+    def broken_filter(_notification: object) -> bool:
+        raise RuntimeError("bad notification filter")
+
+    with HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) as client:
+        client.initialize(cwd="/workspace", model="dsagent")
+        with (
+            client.subscribe_notifications(broken_filter) as broken,
+            client.subscribe_notifications(lambda notification: notification.method == "tick") as healthy,
+        ):
+            client.notify("emit-first")
+            with pytest.raises(RuntimeError, match="bad notification filter"):
+                broken.next()
+            assert healthy.next().payload == {"source": "emit-first"}
+            assert client._notifications.qsize() == 0
+
+            client.session_prompt("main", [{"type": "text", "text": "reader still works"}])
+            client.notify("emit-second")
+            assert healthy.next().payload == {"source": "emit-second"}
+
+
 def test_client_rejects_unaccepted_session_prompt_response(tmp_path: Path) -> None:
     script = tmp_path / "fake_bridge.py"
     script.write_text(