q792602257/agentic-mobile-control
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: surface task execution progress across Host Agent and Cloud

Browse Source 
Host Agent now persists step-level execution detail locally (via a real
TaskMetadataStore/Timeline wired into TaskRunner) and reports a bounded
in-progress snapshot piggybacked on lease renewal. Cloud persists that
snapshot per active assignment and exposes it through the existing task
list/detail query path; Cloud Console renders it as a live badge. Host
Agent's local console gains authenticated, read-only task list and
detail/timeline pages (same-origin, server-rendered) with inlined
screenshots.

Also fixes a pre-existing gap in the shared Timeline: the actual
per-step LLM prompt is now recorded instead of the task goal, benefiting
both Runtime and Host Agent consoles. When a host uses the cloud planner
transport, each decide call's prompt and resulting tool decision are
durably logged in a new planner_decision_log table (with bounded
retention) and browsable from Cloud Console; direct-transport hosts
explicitly surface a "not reported" state.

Includes Alembic migrations 0008 (progress columns on scheduled_tasks)
and 0009 (planner_decision_log), bounded Host-Agent-local retention,
dual-backend repository parity, and Vitest + pytest coverage. Task 6.5
(manual end-to-end device verification) remains.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
q792602257
2026-07-14 12:47:49 +08:00
co-authored by Claude Opus 4.6
parent c049c3c1b1
commit ec261d57c2
59 changed files with 3801 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_tool_calling_client.py
+139 -29
View File
@@ -20,7 +20,9 @@ from tests.fakes import PNG_10X20
class FakeMessages:
def __init__(self, *, response: object | None = None, error: Exception | None = None) -> None:
def __init__(
self, *, response: object | None = None, error: Exception | None = None
) -> None:
self.response = response
self.error = error
self.calls: list[dict[str, Any]] = []
@@ -38,7 +40,9 @@ class FakeTransport:
class FakeCompletions:
def __init__(self, *, response: object | None = None, error: Exception | None = None) -> None:
def __init__(
self, *, response: object | None = None, error: Exception | None = None
) -> None:
self.response = response
self.error = error
self.calls: list[dict[str, Any]] = []
@@ -65,9 +69,13 @@ class FakeOpenAITransport:
def test_anthropic_tool_calling_client_sends_forced_single_tool_call_request() -> None:
messages = FakeMessages(
response={"content": [{"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 2}}]}
response={
"content": [{"type": "tool_use", "name": "tap", "input": {"x": 1, "y": 2}}]
}
)
client = AnthropicToolCallingClient(
model="test-model", transport=FakeTransport(messages)
)
client = AnthropicToolCallingClient(model="test-model", transport=FakeTransport(messages))
decision = client.decide(
system_prompt="system",
@@ -77,14 +85,23 @@ def test_anthropic_tool_calling_client_sends_forced_single_tool_call_request() -
timeout=2.5,
)
assert decision == ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
assert decision == ToolCallDecision(
tool_name="tap",
arguments={"x": 1, "y": 2},
system_prompt="system",
user_prompt="user",
)
assert len(messages.calls) == 1
call = messages.calls[0]
assert call["model"] == "test-model"
assert call["timeout"] == 2.5
assert call["tool_choice"] == {"type": "any", "disable_parallel_tool_use": True}
assert call["tools"] == [
{"name": "tap", "description": TAP_SPEC.description, "input_schema": TAP_SPEC.parameters},
{
"name": "tap",
"description": TAP_SPEC.description,
"input_schema": TAP_SPEC.parameters,
},
{
"name": "finish_task",
"description": FINISH_TASK_SPEC.description,
@@ -93,18 +110,28 @@ def test_anthropic_tool_calling_client_sends_forced_single_tool_call_request() -
]
assert call["system"][0]["text"] == "system"
assert call["system"][0]["cache_control"] == {"type": "ephemeral"}
assert call["messages"] == [{"role": "user", "content": [{"type": "text", "text": "user"}]}]
assert call["messages"] == [
{"role": "user", "content": [{"type": "text", "text": "user"}]}
]
def test_anthropic_tool_calling_client_includes_image_block_when_screenshot_present() -> None:
def test_anthropic_tool_calling_client_includes_image_block_when_screenshot_present() -> (
None
):
messages = FakeMessages(
response={
"content": [
{"type": "tool_use", "name": "finish_task", "input": {"success": True, "reason": "done"}}
{
"type": "tool_use",
"name": "finish_task",
"input": {"success": True, "reason": "done"},
}
]
}
)
client = AnthropicToolCallingClient(model="test-model", transport=FakeTransport(messages))
client = AnthropicToolCallingClient(
model="test-model", transport=FakeTransport(messages)
)
client.decide(
system_prompt="system",
@@ -157,10 +184,18 @@ def test_anthropic_tool_calling_client_passes_custom_base_url_to_sdk(
def test_anthropic_tool_calling_client_wraps_transport_errors() -> None:
messages = FakeMessages(error=TimeoutError("timed out"))
client = AnthropicToolCallingClient(model="test-model", transport=FakeTransport(messages))
client = AnthropicToolCallingClient(
model="test-model", transport=FakeTransport(messages)
)
with pytest.raises(ToolCallUnavailable):
client.decide(system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1)
client.decide(
system_prompt="s",
user_prompt="u",
screenshot=None,
tools=[TAP_SPEC],
timeout=1,
)
@pytest.mark.parametrize(
@@ -171,12 +206,22 @@ def test_anthropic_tool_calling_client_wraps_transport_errors() -> None:
{"content": [{"type": "tool_use", "name": "tap", "input": "not-a-dict"}]},
],
)
def test_anthropic_tool_calling_client_wraps_malformed_responses(response: object) -> None:
def test_anthropic_tool_calling_client_wraps_malformed_responses(
response: object,
) -> None:
messages = FakeMessages(response=response)
client = AnthropicToolCallingClient(model="test-model", transport=FakeTransport(messages))
client = AnthropicToolCallingClient(
model="test-model", transport=FakeTransport(messages)
)
with pytest.raises(ToolCallUnavailable):
client.decide(system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1)
client.decide(
system_prompt="s",
user_prompt="u",
screenshot=None,
tools=[TAP_SPEC],
timeout=1,
)
# --- OpenAI --------------------------------------------------------------
@@ -186,11 +231,24 @@ def test_openai_tool_calling_client_sends_forced_single_tool_call_request() -> N
completions = FakeCompletions(
response={
"choices": [
{"message": {"tool_calls": [{"function": {"name": "tap", "arguments": '{"x": 1, "y": 2}'}}]}}
{
"message": {
"tool_calls": [
{
"function": {
"name": "tap",
"arguments": '{"x": 1, "y": 2}',
}
}
]
}
}
]
}
)
client = OpenAIToolCallingClient(model="test-model", transport=FakeOpenAITransport(completions))
client = OpenAIToolCallingClient(
model="test-model", transport=FakeOpenAITransport(completions)
)
decision = client.decide(
system_prompt="system",
@@ -200,7 +258,12 @@ def test_openai_tool_calling_client_sends_forced_single_tool_call_request() -> N
timeout=2.5,
)
assert decision == ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
assert decision == ToolCallDecision(
tool_name="tap",
arguments={"x": 1, "y": 2},
system_prompt="system",
user_prompt="user",
)
assert len(completions.calls) == 1
call = completions.calls[0]
assert call["model"] == "test-model"
@@ -233,7 +296,9 @@ def test_openai_tool_calling_client_sends_forced_single_tool_call_request() -> N
]
def test_openai_tool_calling_client_includes_image_block_when_screenshot_present() -> None:
def test_openai_tool_calling_client_includes_image_block_when_screenshot_present() -> (
None
):
completions = FakeCompletions(
response={
"choices": [
@@ -252,7 +317,9 @@ def test_openai_tool_calling_client_includes_image_block_when_screenshot_present
]
}
)
client = OpenAIToolCallingClient(model="test-model", transport=FakeOpenAITransport(completions))
client = OpenAIToolCallingClient(
model="test-model", transport=FakeOpenAITransport(completions)
)
client.decide(
system_prompt="system",
@@ -275,22 +342,47 @@ def test_openai_tool_calling_client_includes_image_block_when_screenshot_present
def test_openai_tool_calling_client_accepts_arguments_already_as_dict() -> None:
completions = FakeCompletions(
response={
"choices": [{"message": {"tool_calls": [{"function": {"name": "tap", "arguments": {"x": 1, "y": 2}}}]}}]
"choices": [
{
"message": {
"tool_calls": [
{"function": {"name": "tap", "arguments": {"x": 1, "y": 2}}}
]
}
}
]
}
)
client = OpenAIToolCallingClient(model="test-model", transport=FakeOpenAITransport(completions))
client = OpenAIToolCallingClient(
model="test-model", transport=FakeOpenAITransport(completions)
)
decision = client.decide(system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1)
decision = client.decide(
system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1
)
assert decision == ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
assert decision == ToolCallDecision(
tool_name="tap",
arguments={"x": 1, "y": 2},
system_prompt="s",
user_prompt="u",
)
def test_openai_tool_calling_client_wraps_transport_errors() -> None:
completions = FakeCompletions(error=TimeoutError("timed out"))
client = OpenAIToolCallingClient(model="test-model", transport=FakeOpenAITransport(completions))
client = OpenAIToolCallingClient(
model="test-model", transport=FakeOpenAITransport(completions)
)
with pytest.raises(ToolCallUnavailable):
client.decide(system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1)
client.decide(
system_prompt="s",
user_prompt="u",
screenshot=None,
tools=[TAP_SPEC],
timeout=1,
)
@pytest.mark.parametrize(
@@ -298,15 +390,33 @@ def test_openai_tool_calling_client_wraps_transport_errors() -> None:
[
{"choices": []},
{"choices": [{"message": {"tool_calls": []}}]},
{"choices": [{"message": {"tool_calls": [{"function": {"name": "tap", "arguments": "not-json"}}]}}]},
{
"choices": [
{
"message": {
"tool_calls": [
{"function": {"name": "tap", "arguments": "not-json"}}
]
}
}
]
},
],
)
def test_openai_tool_calling_client_wraps_malformed_responses(response: object) -> None:
completions = FakeCompletions(response=response)
client = OpenAIToolCallingClient(model="test-model", transport=FakeOpenAITransport(completions))
client = OpenAIToolCallingClient(
model="test-model", transport=FakeOpenAITransport(completions)
)
with pytest.raises(ToolCallUnavailable):
client.decide(system_prompt="s", user_prompt="u", screenshot=None, tools=[TAP_SPEC], timeout=1)
client.decide(
system_prompt="s",
user_prompt="u",
screenshot=None,
tools=[TAP_SPEC],
timeout=1,
)
# --- build_client ----------------------------------------------------------