| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073 |
- from __future__ import annotations
- import json
- import inspect
- import sys
- import threading
- import time
- from pathlib import Path
- import pytest
- from deepseek_harness import DeepSeekHarness, HarnessClient, HarnessConfig, Notification, RunResult, SdkProtocolError
- from deepseek_harness.errors import JsonRpcError
- def test_high_level_sdk_runs_turn_and_collects_final_response(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.py"
- env_dump = tmp_path / "env.json"
- init_dump = tmp_path / "init.json"
- script.write_text(
- """
- import json
- import os
- import sys
- env_dump = os.environ["ENV_DUMP"]
- json.dump({
- "DEEPSEEK_API_KEY": os.environ.get("DEEPSEEK_API_KEY"),
- "DEEPSEEK_BASE_URL": os.environ.get("DEEPSEEK_BASE_URL"),
- "DSH_CWD": os.environ.get("DSH_CWD"),
- "DSH_SESSION_ROOT": os.environ.get("DSH_SESSION_ROOT"),
- "DSH_CORDIS_CONFIG": os.environ.get("DSH_CORDIS_CONFIG"),
- }, open(env_dump, "w"))
- for line in sys.stdin:
- msg = json.loads(line)
- method = msg.get("method")
- if method == "initialize":
- json.dump(msg.get("params"), open(os.environ["INIT_DUMP"], "w"))
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-runtime"}}}), flush=True)
- elif method == "session/prompt":
- params = msg.get("params") or {}
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {
- "sessionId": params["sessionId"],
- "event": {
- "type": "assistant/message",
- "data": {
- "message": {
- "role": "assistant",
- "content": [{"type": "text", "text": "hello from runtime"}],
- },
- },
- },
- },
- }), flush=True)
- print(json.dumps({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {
- "sessionId": params["sessionId"],
- "event": {
- "type": "turn/end",
- "data": {"turn": 1, "reason": {"kind": "completed"}},
- },
- },
- }), flush=True)
- print(json.dumps({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {
- "sessionId": params["sessionId"],
- "event": {
- "type": "turn/end",
- "data": {"turn": 2, "reason": {"kind": "max-tokens"}},
- },
- },
- }), flush=True)
- print(json.dumps({
- "jsonrpc": "2.0",
- "method": "session.status",
- "params": {"sessionId": params["sessionId"], "status": "idle"},
- }), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(
- model="deepseek-v4-flash",
- reasoning_effort="max",
- max_tokens=4096,
- cwd=str(tmp_path),
- _launch_args=(sys.executable, str(script)),
- env={
- "ENV_DUMP": str(env_dump),
- "INIT_DUMP": str(init_dump),
- "DEEPSEEK_API_KEY": "env-key",
- "DEEPSEEK_BASE_URL": "http://127.0.0.1:4321",
- },
- ) as harness:
- result = harness.run("say hello", session_id="main")
- assert result.final_response == "hello from runtime"
- assert result.finish_reason == "max-tokens"
- assert result.events[-1]["type"] == "turn/end"
- dumped_env = json.loads(env_dump.read_text())
- assert dumped_env["DEEPSEEK_API_KEY"] == "env-key"
- assert dumped_env["DEEPSEEK_BASE_URL"] == "http://127.0.0.1:4321"
- assert dumped_env["DSH_CWD"] is None
- assert dumped_env["DSH_SESSION_ROOT"] is None
- assert dumped_env["DSH_CORDIS_CONFIG"] is None
- assert json.loads(init_dump.read_text()) == {
- "cwd": str(tmp_path),
- "provider": "deepseek-official",
- "model": "deepseek-v4-flash",
- "reasoningEffort": "max",
- "maxTokens": 4096,
- }
- def test_session_run_invokes_notification_callback_before_returning(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "main", "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": "main", "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": "main", "childSessionId": "child"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": "main", "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- seen: list[str] = []
- with DeepSeekHarness(
- _launch_args=(sys.executable, str(script)),
- cwd=str(tmp_path),
- ) as harness:
- session = harness.start_session("main")
- result = session.run(
- "spawn a helper",
- on_notification=lambda notification: seen.append(notification.method),
- )
- assert seen == ["session.event", "session.status", "subagent.started", "session.status"]
- assert result.finish_reason is None
- def test_high_level_sdk_rejects_turn_end_without_reason_kind(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- params = msg.get("params") or {}
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "turn/end", "data": {"turn": 1, "reason": {}}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(
- _launch_args=(sys.executable, str(script)),
- cwd=str(tmp_path),
- ) as harness:
- with pytest.raises(
- SdkProtocolError,
- match=r"turn/end event requires a string data\.reason\.kind",
- ):
- harness.run("reject malformed turn ending", session_id="main")
- def test_relative_cwd_is_absolute_in_process_environment_and_wire(
- tmp_path: Path, monkeypatch: pytest.MonkeyPatch
- ) -> None:
- script = tmp_path / "capture_cwd.py"
- capture = tmp_path / "cwd.json"
- script.write_text(
- """
- import json
- import os
- import sys
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- json.dump({"process": os.getcwd(), "environment": os.environ.get("DSH_CWD"), "wire": msg["params"]["cwd"]}, open(os.environ["CAPTURE"], "w"))
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-runtime"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- monkeypatch.chdir(tmp_path)
- with DeepSeekHarness(
- cwd=".",
- runtime_cwd=".",
- _launch_args=(sys.executable, str(script)),
- env={"CAPTURE": str(capture)},
- ):
- pass
- expected = str(tmp_path.resolve())
- assert json.loads(capture.read_text()) == {
- "process": expected,
- "environment": None,
- "wire": expected,
- }
- def test_session_run_includes_subagent_finished_for_parent_session(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "main", "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": "main", "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": "main", "childSessionId": "child"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.finished", "params": {"parentSessionId": "main", "childSessionId": "child", "status": "ok", "stopReason": "completed"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": "main", "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(
- _launch_args=(sys.executable, str(script)),
- cwd=str(tmp_path),
- ) as harness:
- result = harness.run("spawn a helper", session_id="main")
- assert [notification.method for notification in result.notifications] == [
- "session.event",
- "session.status",
- "subagent.started",
- "subagent.finished",
- "session.status",
- ]
- def test_session_run_collects_nested_subagent_tree_without_polluting_root_events(
- tmp_path: Path,
- ) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- root = (msg.get("params") or {})["sessionId"]
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": root, "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": root, "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": root, "childSessionId": "child"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "child", "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "child response"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.started", "params": {"parentSessionId": "child", "childSessionId": "grandchild"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "grandchild", "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "grandchild response"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.finished", "params": {"parentSessionId": "child", "childSessionId": "grandchild", "status": "ok"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "subagent.finished", "params": {"parentSessionId": root, "childSessionId": "child", "status": "ok"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": root, "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "root response"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": root, "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- seen: list[str] = []
- with DeepSeekHarness(
- _launch_args=(sys.executable, str(script)),
- cwd=str(tmp_path),
- ) as harness:
- result = harness.run(
- "delegate recursively",
- session_id="main",
- on_notification=lambda notification: seen.append(notification.method),
- )
- assert harness.client._notifications.qsize() == 0
- assert result.final_response == "root response"
- assert [event["data"]["content"][0]["text"] for event in result.events if event["type"] == "assistant/message"] == ["root response"]
- assert [notification.method for notification in result.notifications] == [
- "session.event",
- "session.status",
- "subagent.started",
- "session.event",
- "subagent.started",
- "session.event",
- "subagent.finished",
- "subagent.finished",
- "session.event",
- "session.status",
- ]
- assert seen == [notification.method for notification in result.notifications]
- def test_session_run_ignores_notifications_for_other_sessions(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- params = msg.get("params") or {}
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": "other", "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "wrong session"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": "other", "status": "idle"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "right session"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(
- _launch_args=(sys.executable, str(script)),
- cwd=str(tmp_path),
- ) as harness:
- result = harness.run("stay in your lane", session_id="main")
- assert result.final_response == "right session"
- assert [notification.payload.get("sessionId") for notification in result.notifications] == ["main"] * 4
- def test_high_level_session_run_does_not_accumulate_global_notifications(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- params = msg.get("params") or {}
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": "message-1"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": params["sessionId"], "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "ok"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": params["sessionId"], "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(_launch_args=(sys.executable, str(script)), cwd=str(tmp_path)) as harness:
- result = harness.run("one turn", session_id="main")
- assert harness.client._notifications.qsize() == 0
- def test_session_run_waits_for_late_idle_without_replaying_stale_notifications(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.py"
- script.write_text(
- """
- import json
- import sys
- import time
- turn = 0
- 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-runtime"}}}), flush=True)
- elif method == "session/prompt":
- turn += 1
- params = msg.get("params") or {}
- session_id = params["sessionId"]
- message_id = f"message-{turn}"
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": session_id, "event": {"type": "agent/inbox/spliced", "data": {"target": "next-turn", "start": 0, "inserted": [{"id": message_id}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": session_id, "status": "running"}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": message_id}}), flush=True)
- if turn == 1:
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": session_id, "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "first"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": session_id, "status": "idle"}}), flush=True)
- else:
- time.sleep(0.05)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.event", "params": {"sessionId": session_id, "event": {"type": "assistant/message", "data": {"content": [{"type": "text", "text": "second"}]}}}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "method": "session.status", "params": {"sessionId": session_id, "status": "idle"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with DeepSeekHarness(_launch_args=(sys.executable, str(script)), cwd=str(tmp_path)) as harness:
- first = harness.run("first turn", session_id="main")
- second = harness.run("second turn", session_id="main")
- assert first.final_response == "first"
- assert second.final_response == "second"
- assert [notification.payload.get("sessionId") for notification in second.notifications] == ["main"] * 4
- def test_client_starts_subprocess_sends_requests_and_routes_notifications(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 == "session/prompt":
- params = msg.get("params") or {}
- print(json.dumps({"jsonrpc": "2.0", "method": "llm/request", "params": {"requestId": "req-1", "sessionId": params["sessionId"], "model": "dsagent", "messages": []}}), flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"messageId": "message-1"}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with HarnessClient(_launch_args=(sys.executable, str(script))) as client:
- init = client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- assert init.serverInfo.name == "fake-dsh"
- client.session_prompt("main", [{"type": "text", "text": "fix it"}])
- notification = client.next_notification()
- assert notification.method == "llm/request"
- assert notification.payload["requestId"] == "req-1"
- assert notification.payload["sessionId"] == "main"
- def test_client_keeps_unmatched_notifications_available_globally_while_subscribed() -> None:
- client = HarnessClient()
- with client.subscribe_session_notifications("main"):
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {"sessionId": "other", "event": {"type": "assistant/message"}},
- })
- assert client._notifications.qsize() == 1
- notification = client._notifications.get_nowait()
- assert not isinstance(notification, BaseException)
- assert notification.method == "session.event"
- assert notification.payload["sessionId"] == "other"
- def test_session_subscription_keeps_descendant_relationships_across_subscriptions() -> None:
- client = HarnessClient()
- with client.subscribe_session_notifications("main") as first:
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "subagent.started",
- "params": {"parentSessionId": "main", "childSessionId": "child"},
- })
- assert first.next().payload["childSessionId"] == "child"
- with client.subscribe_session_notifications("main") as second:
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "subagent.started",
- "params": {"parentSessionId": "child", "childSessionId": "grandchild"},
- })
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {"sessionId": "grandchild", "event": {"type": "assistant/message"}},
- })
- assert second.next().payload["childSessionId"] == "grandchild"
- assert second.next().payload["sessionId"] == "grandchild"
- assert client._notifications.qsize() == 0
- def test_session_subscription_preserves_reused_child_ancestry_after_late_finish() -> None:
- client = HarnessClient()
- old_seen: list[Notification] = []
- new_seen: list[Notification] = []
- with (
- client.subscribe_session_notifications("old-parent") as old_subscription,
- client.subscribe_session_notifications("new-parent") as new_subscription,
- ):
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "subagent.started",
- "params": {"parentSessionId": "old-parent", "childSessionId": "reused-child"},
- })
- old_subscription.drain(old_seen.append)
- new_subscription.drain(new_seen.append)
- assert [notification.method for notification in old_seen] == ["subagent.started"]
- assert new_seen == []
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "subagent.started",
- "params": {"parentSessionId": "new-parent", "childSessionId": "reused-child"},
- })
- old_subscription.drain(old_seen.append)
- new_subscription.drain(new_seen.append)
- assert [notification.method for notification in new_seen] == ["subagent.started"]
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "subagent.finished",
- "params": {"parentSessionId": "old-parent", "childSessionId": "reused-child"},
- })
- old_subscription.drain(old_seen.append)
- new_subscription.drain(new_seen.append)
- assert [notification.method for notification in old_seen] == [
- "subagent.started",
- "subagent.finished",
- ]
- assert [notification.method for notification in new_seen] == ["subagent.started"]
- client._handle_message({
- "jsonrpc": "2.0",
- "method": "session.event",
- "params": {"sessionId": "reused-child", "event": {"type": "assistant/message"}},
- })
- old_subscription.drain(old_seen.append)
- new_subscription.drain(new_seen.append)
- assert [notification.method for notification in old_seen] == [
- "subagent.started",
- "subagent.finished",
- ]
- assert [notification.method for notification in new_seen] == [
- "subagent.started",
- "session.event",
- ]
- assert client._notifications.qsize() == 0
- 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": {"messageId": "message-1"}}), 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(_launch_args=(sys.executable, str(script))) as client:
- client.initialize(provider="deepseek-official", 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(
- """
- 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 == "session/prompt":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"accepted": False}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with HarnessClient(_launch_args=(sys.executable, str(script))) as client:
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- with pytest.raises(ValueError):
- client.session_prompt("main", [{"type": "text", "text": "fix it"}])
- def test_client_routes_bridge_requests_and_sends_responses(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)
- print(json.dumps({"jsonrpc": "2.0", "id": "bridge-req-1", "method": "llm.request", "params": {"requestId": "req-1", "sessionId": "main", "model": "dsagent", "messages": []}}), flush=True)
- elif "id" in msg and "method" not in msg:
- print(json.dumps({"jsonrpc": "2.0", "method": "response/seen", "params": {"result": msg.get("result")}}), flush=True)
- elif method == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with HarnessClient(_launch_args=(sys.executable, str(script))) as client:
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- request = client.next_request()
- assert request.id == "bridge-req-1"
- assert request.method == "llm.request"
- assert request.payload["requestId"] == "req-1"
- client.respond(request.id, {"content_blocks": [{"type": "text", "text": "done"}]})
- notification = client.next_notification()
- assert notification.method == "response/seen"
- assert notification.payload["result"]["content_blocks"][0]["text"] == "done"
- def test_client_ignores_non_json_stdout_lines(tmp_path: Path) -> None:
- script = tmp_path / "fake_bridge.py"
- script.write_text(
- """
- import json
- import sys
- print("node warning: experimental loader", flush=True)
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with HarnessClient(_launch_args=(sys.executable, str(script))) as client:
- init = client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- assert init.serverInfo.name == "fake-dsh"
- def test_client_request_times_out_when_bridge_does_not_respond(tmp_path: Path) -> None:
- script = tmp_path / "fake_bridge.py"
- script.write_text(
- """
- import sys
- import time
- print("bridge is still starting", file=sys.stderr, flush=True)
- time.sleep(60)
- """.strip()
- )
- with HarnessClient(
- HarnessConfig(
- profile="web",
- initialize_timeout_seconds=0.1,
- ),
- _launch_args=(sys.executable, str(script)),
- ) as client:
- start = time.monotonic()
- try:
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- except TimeoutError as exc:
- assert time.monotonic() - start < 2
- assert "bridge is still starting" in str(exc)
- assert "profile 'web'" in str(exc)
- else:
- raise AssertionError("initialize should time out")
- def test_client_close_times_out_when_shutdown_does_not_respond(tmp_path: Path) -> None:
- script = tmp_path / "fake_bridge.py"
- script.write_text(
- """
- import json
- import signal
- import sys
- import time
- signal.signal(signal.SIGTERM, signal.SIG_IGN)
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- time.sleep(60)
- """.strip()
- )
- client = HarnessClient(
- HarnessConfig(
- shutdown_timeout_seconds=0.1,
- ),
- _launch_args=(sys.executable, str(script)),
- )
- client.start()
- proc = client._proc
- assert proc is not None
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- start = time.monotonic()
- client.close()
- assert time.monotonic() - start < 2
- assert proc.poll() is not None
- assert client._proc is None
- def test_client_close_allows_eof_quiescence_after_shutdown_response(tmp_path: Path) -> None:
- script = tmp_path / "fake_runtime.py"
- marker = tmp_path / "quiesced.txt"
- script.write_text(
- """
- import json
- import os
- from pathlib import Path
- import sys
- import time
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- time.sleep(0.05)
- Path(os.environ["QUIESCED_MARKER"]).write_text("quiesced")
- """.strip()
- )
- client = HarnessClient(
- HarnessConfig(
- env={"QUIESCED_MARKER": str(marker)},
- shutdown_timeout_seconds=1,
- ),
- _launch_args=(sys.executable, str(script)),
- )
- client.start()
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- client.close()
- assert marker.read_text() == "quiesced"
- def test_initialize_failure_reaps_started_runtime(tmp_path: Path) -> None:
- script = tmp_path / "rejecting_runtime.py"
- script.write_text(
- """
- import json
- import sys
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print("initialize diagnostic", file=sys.stderr, flush=True)
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "error": {"code": -32000, "message": "bad initialize"}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- client = HarnessClient(_launch_args=(sys.executable, str(script)))
- client.start()
- proc = client._proc
- assert proc is not None
- with pytest.raises(JsonRpcError, match="bad initialize") as excinfo:
- client.initialize(provider="deepseek-official", cwd=".", model="dsagent")
- assert excinfo.value.code == -32000
- assert "initialize diagnostic" in str(excinfo.value)
- assert proc.wait(timeout=1) is not None
- assert client._proc is None
- def test_public_signatures_omit_unsupported_wire_parameters() -> None:
- from deepseek_harness import DeepSeekHarnessConfig, Session
- assert "session_root" not in inspect.signature(HarnessClient.initialize).parameters
- assert "system_prompt" not in inspect.signature(HarnessClient.initialize).parameters
- assert "profile" not in inspect.signature(HarnessClient.session_prompt).parameters
- assert "profile" not in inspect.signature(DeepSeekHarness.run).parameters
- assert "profile" not in inspect.signature(Session.run).parameters
- assert "system_prompt" not in DeepSeekHarnessConfig.__dataclass_fields__
- assert "max_tokens" in DeepSeekHarnessConfig.__dataclass_fields__
- assert "reasoning_effort" in DeepSeekHarnessConfig.__dataclass_fields__
- assert "max_tokens" in inspect.signature(HarnessClient.initialize).parameters
- assert "reasoning_effort" in inspect.signature(HarnessClient.initialize).parameters
- assert "client_name" not in HarnessConfig.__dataclass_fields__
- assert "client_version" not in HarnessConfig.__dataclass_fields__
- assert {"dsh_bin", "profile", "patches", "dsh_home"} <= set(
- DeepSeekHarnessConfig.__dataclass_fields__
- )
- assert {"dsh_bin", "profile", "patches", "dsh_home"} <= set(
- HarnessConfig.__dataclass_fields__
- )
- assert "initialize_timeout_seconds" in DeepSeekHarnessConfig.__dataclass_fields__
- assert "initialize_timeout_seconds" in HarnessConfig.__dataclass_fields__
- assert DeepSeekHarnessConfig().initialize_timeout_seconds == 30.0
- assert HarnessConfig().initialize_timeout_seconds == 30.0
- for removed in ("cordis", "session_root", "runtime_bin", "bridge_bin", "launch_args_override"):
- assert removed not in DeepSeekHarnessConfig.__dataclass_fields__
- assert removed not in HarnessConfig.__dataclass_fields__
- assert "_launch_args" not in HarnessConfig.__dataclass_fields__
- assert "session_root" not in RunResult.__dataclass_fields__
- def test_client_close_is_idempotent_before_and_after_start(tmp_path: Path) -> None:
- HarnessClient().close()
- script = tmp_path / "fake_bridge.py"
- script.write_text(
- """
- import json
- import sys
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- client = HarnessClient(_launch_args=(sys.executable, str(script)))
- client.start()
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- client.close()
- client.close()
- def test_runtime_closed_error_includes_stderr_tail(tmp_path: Path) -> None:
- script = tmp_path / "crashing_runtime.py"
- script.write_text(
- """
- import sys
- print("fatal bridge exploded", file=sys.stderr, flush=True)
- sys.exit(42)
- """.strip()
- )
- with HarnessClient(
- HarnessConfig(
- request_timeout_seconds=2,
- ),
- _launch_args=(sys.executable, str(script)),
- ) as client:
- with pytest.raises(Exception, match="fatal bridge exploded"):
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- def test_client_serializes_concurrent_writes(tmp_path: Path) -> None:
- script = tmp_path / "fake_bridge.py"
- output = tmp_path / "seen.jsonl"
- script.write_text(
- """
- import json
- import os
- import sys
- with open(os.environ["SEEN"], "w") as seen:
- for line in sys.stdin:
- seen.write(line)
- seen.flush()
- msg = json.loads(line)
- if "id" in msg and msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-dsh"}}}), flush=True)
- elif "id" in msg and msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- with HarnessClient(
- HarnessConfig(
- env={"SEEN": str(output)},
- ),
- _launch_args=(sys.executable, str(script)),
- ) as client:
- client.initialize(provider="deepseek-official", cwd="/workspace", model="dsagent")
- threads = [
- threading.Thread(target=client.notify, args=(f"notice-{index}", {"index": index}))
- for index in range(50)
- ]
- for thread in threads:
- thread.start()
- for thread in threads:
- thread.join()
- for line in output.read_text().splitlines():
- json.loads(line)
- def _install_fake_bundled_dsh(
- tmp_path: Path, monkeypatch: pytest.MonkeyPatch
- ) -> None:
- """Install a fake runtime package that records dsh argv and serves lifecycle calls."""
- runtime = tmp_path / "dsh.py"
- runtime.write_text(
- """
- import json
- import os
- import sys
- json.dump({
- "argv": sys.argv[1:],
- "DSH_HOME": os.environ.get("DSH_HOME"),
- "DSH_CORDIS_CONFIG": os.environ.get("DSH_CORDIS_CONFIG"),
- }, open(os.environ["ENV_DUMP"], "w"))
- for line in sys.stdin:
- msg = json.loads(line)
- if msg.get("method") == "initialize":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "bundled-runtime"}}}), flush=True)
- elif msg.get("method") == "shutdown":
- print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {}}), flush=True)
- break
- """.strip()
- )
- module_dir = tmp_path / "deepseek_harness_runtime"
- module_dir.mkdir()
- (module_dir / "__init__.py").write_text(
- f"""
- def resolve_bundled_launch_args(mode=None):
- return ({sys.executable!r}, {str(runtime)!r})
- """.strip()
- )
- monkeypatch.syspath_prepend(str(tmp_path))
- monkeypatch.delitem(sys.modules, "deepseek_harness_runtime", raising=False)
- def test_client_default_launch_uses_bundled_dsh_sdk_profile_and_explicit_home(
- tmp_path: Path, monkeypatch: pytest.MonkeyPatch
- ) -> None:
- env_dump = tmp_path / "env.json"
- home = tmp_path / "home"
- patch = tmp_path / "sdk.patch.yml"
- patch.write_text("[]\n")
- _install_fake_bundled_dsh(tmp_path, monkeypatch)
- monkeypatch.chdir(tmp_path)
- monkeypatch.setenv("DSH_HOME", str(tmp_path / "ambient-home"))
- monkeypatch.delenv("DSH_CORDIS_CONFIG", raising=False)
- with HarnessClient(HarnessConfig(
- profile="sdk",
- patches=("sdk.patch.yml",),
- dsh_home=str(home),
- env={"ENV_DUMP": str(env_dump), "DSH_HOME": str(tmp_path / "env-home")},
- )) as client:
- init = client.initialize(provider="deepseek-official", cwd="/workspace", model="deepseek-v4-pro")
- assert init.serverInfo.name == "bundled-runtime"
- assert json.loads(env_dump.read_text()) == {
- "argv": ["--profile", "sdk", "--patch", str(patch)],
- "DSH_HOME": str(home),
- "DSH_CORDIS_CONFIG": None,
- }
- def test_client_accepts_explicit_environment_dsh_home(
- tmp_path: Path, monkeypatch: pytest.MonkeyPatch
- ) -> None:
- env_dump = tmp_path / "env.json"
- home = tmp_path / "environment-home"
- _install_fake_bundled_dsh(tmp_path, monkeypatch)
- with HarnessClient(
- HarnessConfig(profile="custom", env={"ENV_DUMP": str(env_dump), "DSH_HOME": str(home)})
- ) as client:
- client.initialize(provider="deepseek-official", cwd="/workspace", model="deepseek-v4-pro")
- assert json.loads(env_dump.read_text()) == {
- "argv": ["--profile", "custom"],
- "DSH_HOME": str(home),
- "DSH_CORDIS_CONFIG": None,
- }
- def test_client_rejects_an_implicit_default_dsh_home(
- tmp_path: Path, monkeypatch: pytest.MonkeyPatch
- ) -> None:
- _install_fake_bundled_dsh(tmp_path, monkeypatch)
- monkeypatch.delenv("DSH_HOME", raising=False)
- with pytest.raises(ValueError, match="explicit dsh_home or non-empty DSH_HOME"):
- HarnessClient(HarnessConfig(env={})).start()
- def test_client_reports_missing_bundled_runtime_dependency(monkeypatch: pytest.MonkeyPatch) -> None:
- monkeypatch.delitem(sys.modules, "deepseek_harness_runtime", raising=False)
- monkeypatch.setattr(sys, "path", [])
- with pytest.raises(FileNotFoundError, match="Install deepseek-harness-runtime-bin"):
- HarnessClient(HarnessConfig(dsh_home="/explicit/home")).start()
|