mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-08-28 05:25:04 +00:00
Some checks are pending
Pre-commit / run (ubuntu-latest) (push) Waiting to run
Tests ReMe / Unit Tests - py3.13 (push) Waiting to run
Tests ReMe / Unit Tests - py3.11 (push) Waiting to run
Tests ReMe / Unit Tests - py3.12 (push) Waiting to run
Windows Smoke / CLI smoke - py3.11 (push) Waiting to run
* feat: add ssh proxy * feat: add ssh proxy * feat: add ssh proxy * feat: add ssh proxy * feat: add prompt * feat: add agent wrapper * feat: add agent wrapper * feat: add agent wrapper * feat: add tushare skill * feat: add tushare skill * feat: add tushare skill * feat: add none stream * chore(deps): update dependency versions in pyproject.toml - Bump claude-agent-sdk from 0.2.123 to 0.2.126 - Upgrade pre-commit to version 4.6.1 or higher - Upgrade pytest to version 9.1.1 or higher * feat(agent_wrapper): add session compaction support and unify session commands - Introduce compact_session method to BaseAgentWrapper and implement it in AsAgentWrapper, CcAgentWrapper, and CodexAgentWrapper - Add session_command module with SessionCommandResult dataclass and handle_session_command function for /clear and /compact commands - Update __init__.py exports to include session_command handlers - Modify DingTalkWaitStep to handle session commands via handle_session_command function - Remove streaming mode from DingTalkWaitStep and simplify reply handling to final Markdown replies only - Add unit tests for session compaction methods and session command handling across wrappers and DingTalk integration - Clean up and remove obsolete streaming and card rendering code from DingTalk wait step - Adjust daily_cookbook.yaml to remove stream and card_update_interval config entries for DingTalk wait step * feat(auto_fin): add Auto Fin simulated portfolio cookbook workflow - Add comprehensive Auto Fin schema exports for multiple models and enums - Implement base class and helpers for Auto Fin analysis steps - Create file, state, and formatting utilities for Auto Fin with atomic file writes and locking - Define Auto Fin pipeline with four analysis agents: backtest, event, portfolio, and US correlation - Register Auto Fin package in cookbook workflows and schema initialization - Add detailed documentation in markdown describing the system design, workflow, and data contracts * feat(outbound_proxy): add application-scoped outbound HTTP proxy components - Introduce BaseOutboundProxy and OutboundProxyEndpoint as core contracts - Implement FixedHttpOutboundProxy for external HTTP proxy integration - Add SshHttpOutboundProxy providing SSH-backed local HTTP proxy tunnels - Register outbound proxy components in component registry and enumeration - Update components package to include outbound_proxy module - Add dependency on pproxy for SSH HTTP proxy bridging - Include comprehensive unit tests covering proxy lifecycle, validation, environment merging, error handling, readiness, and monitoring mechanisms * refactor(network): replace SSH proxy with explicit HTTP outbound proxy - Remove SSH proxy helper implementation and references in codebase - Add support for explicit HTTP proxy URL in arXiv and HuggingFace clients - Modify clients to use async context manager for consistent resource handling - Update daily paper steps to forward outbound proxy configuration explicitly - Change tests to cover new proxy usage model and remove SSH proxy mocks - Add outbound proxy component configuration in daily_cookbook.yaml - Ensure proxy URL usage disables environment trust in HTTP clients - Fix app context component enum access to be defensive against missing keys * feat(agent_wrapper): add managed proxy support for command environments - Introduce BaseOutboundProxy binding in BaseAgentWrapper for outbound proxy management - Add bash_environment and command_proxy_environment properties to apply proxy settings - Update WorkspaceBackend instantiation in AsAgentWrapper to use bash_environment - Inject managed proxy export commands into Claude Code Bash commands via hooks - Enhance CodexAgentWrapper to include managed proxy in shell environment policy - Modify daily_cookbook.yaml steps to specify outbound_proxy as default where needed - Add comprehensive unit tests verifying managed proxy injection and environment isolation - Ensure subprocess_environment remains unchanged while proxy is applied selectively to commands * refactor(memory): replace search job_tools with memory in daily cookbook config - Change workspace_dir default from .reme to reme_workspace - Replace search job_tools with memory across multiple components and jobs - Update descriptions to reflect long-term memory retrieval instead of search - Modify system prompts to instruct using memory for retrieving notes - Adjust unit tests to verify memory job_tools and job presence instead of search - Ensure consistency in configuration and tests for memory backend usage * refactor(config): rename memory to memory_search in daily cookbook config - Change all occurrences of "memory" to "memory_search" in job_tools and job definitions - Update related system prompts to reflect the new memory_search terminology - Modify unit tests to assert the presence of memory_search instead of memory - Ensure consistency across skills, job tools, and backend configurations in multiple components * feat(auto_fin): add deterministic quantitative research and ranking fusion - Introduce new schema models: EtfScore, RankingMetrics, ExtremeAnalysis, DimensionRanking, and FusionRanking to represent deterministic research outputs - Add ranking data to event, backtest, us_correlation, and portfolio analysis outputs - Implement ranking_section renderer to format Top20 scores and diagnostics in Markdown - Develop AutoFinQuantStep for deterministic ETF ranking using TuShare data, Polars, and a custom extremely randomized tree ensemble - Integrate quantitative rankings into backtest and portfolio analysis steps and reports - Extend auto_fin pipeline with new quant_enabled and quant_required config options - Enforce ranking constraints like unique codes, contiguous ranks, and normalized fusion weights - Update analysis YAMLs with rules limiting data freshness, universe, and ranking usage - Incorporate ranking outputs into all major markdown report bodies in Auto Fin pipeline - Add concurrency-limited asynchronous TuShare client to fetch required market data - Introduce cross-sectional rank correlation and NDCG metrics for ranking quality evaluation * feat(auto_fin): implement stage-wise notification and reporting for analysis pipeline - Refactor notification config in daily_cookbook.yaml to support dispatch steps - Update AutoFinNotificationStep to deduplicate notifications per run stage - Add _notify_stage method in pipeline to send notifications for each analysis stage - Implement persistence and notification for event, backtest, US correlation, and portfolio stages - Modify pipeline flow to persist reports and notify after each stage completion - Adjust metadata to track notifications and errors per stage - Update tests to verify stage-wise notification sending and deduplication - Remove older combined report persistence in favor of modular stage handling * feat(auto_fin): add outbound proxy support for Tushare API usage - Introduce BaseOutboundProxy reference in AutoFinPipelineStep and AutoFinQuantStep - Update TushareResearchClient and trade calendar fetch to accept and use proxy URL - Create _ProxiedTushareApi adapter to route Tushare requests via explicit HTTP proxy - Modify create_tushare_api utility to optionally return proxied API client - Add unit tests covering proxy forwarding and client behavior with managed proxies - Ensure proxy usage respects explicit proxy URL over environment fallback - Integrate outbound proxy into data fetching and quantitative research steps * feat(auto_fin): enforce checkpoint time validation and add state models - Introduce AnalysisState base class and specific states for event, backtest, and US correlation analyses - Replace analysis output types with corresponding state classes in run schemas - Add require_checkpoint_reached method to validate decision_at/data_cutoff against current time - Enforce checkpoint time checks before analysis steps in event, backtest, portfolio, and quant analyses - Refactor quant data loading to include adjustment factors and apply price adjustments without fallback - Update analysis YAML docs to require real-time checkpoint validation and forbid using future data - Improve portfolio run serialization by excluding redundant legacy fields and nested proposed actions - Add helper to extract readable sections from persisted checkpoint documents - Fix event analysis output validation to reject events and sources with future timestamps * feat(auto_fin): auto-select latest reached checkpoint if none specified - Extend checkpoint config to accept empty string for auto selection - Add static method to compute latest checkpoint reached by current time - Modify pipeline step to auto-select checkpoint based on trade calendar and time - Adjust force flag default depending on whether checkpoint is explicit or auto - Log details when checkpoint is auto-selected to improve observability - Add comprehensive tests for auto checkpoint selection logic and edge cases - Remove deprecated default and required constraints from force parameter in config * refactor(auto_fin): unify datetime comparison with compare_datetimes utility - Replace direct datetime comparisons with compare_datetimes function calls - Use cmp_to_key with compare_datetimes for sorting datetime tuples and lists - Update validation logic in backtest, event, analysis, and ledger modules for consistent datetime handling - Add unit tests to verify handling of naive and aware datetime comparisons in event and backtest validations - Ensure marked_at and interval_end timestamps are set and compared consistently using compare_datetimes - Improve correctness of ordering and conditional checks related to timestamps throughout auto_fin steps and ledger code * feat(auto_fin): add datetime comparison helper for mixed timezone data - Implement compare_datetimes function to handle naive and aware datetimes - Ensure naive datetime is interpreted in the known timezone of the counterpart - Facilitate comparisons between legacy and timezone-aware Auto Fin data - Add module docstring explaining purpose of the helpers * docs(auto_fin): enforce unique ETF representative per sub-theme in analysis rules - Update backtest.yaml to recommend or highlight only one ETF per sub-theme for ETF analyses - Modify event.yaml to map only one representative ETF per sub-theme, avoiding duplicate recommendations - Revise portfolio.yaml to restrict holdings/buys to a single ETF per sub-theme, preventing repeated buys of highly overlapping ETFs - Adjust us_correlation.yaml to retain only one representative A-share ETF per sub-theme for mapping or recommendation - Add test to verify presence of new sub-theme uniqueness guidance in step prompts * feat(auto_fin): separate draft model and include deterministic fusion ranking - Introduce _PortfolioProposalDraft pydantic model for agent-authored fields before ranking - Discard any "fusion_ranking" data from draft to prevent conflicts with canonical ranking - Modify AutoFinPortfolioStep to receive draft, enrich with fusion_ranking, and produce final output - Update tests to use _PortfolioProposalDraft and validate deterministic fusion ranking propagation - Add async test verifying fusion ranking is correctly set in portfolio output with no errors * refactor(auto_fin): rewrite and simplify Auto Fin schema and steps - Remove legacy Auto Fin analysis step modules and helpers - Replace complex ranking and portfolio models with simplified current-news models - Update schema to focus on news-case workflow with new domain models - Remove A-share decision checkpoints and backtest details from schema - Simplify recommendation and decision output structures - Clean up deprecated state and utility functions - Update Auto Fin steps initialization to new pipeline steps only - Improve uniqueness validation for themes and ETFs in research plan * feat(auto_fin): implement full local cache and analysis workflow for Auto Fin - Add AutoFinDataStep to prepare and cache daily TuShare data with lookback - Add AutoFinAnalysisStep to analyze cached data and generate Markdown report - Implement detailed time window, ETF filtering, and historical case validation - Introduce YAML prompts for planning and decision-making steps - Update .gitignore to include reme_workspace/ - Clean up config and import structure for auto_fin steps - Remove old pipeline.py and consolidate functionality into new modules - Use polars for efficient CSV reading and data processing - Ensure atomic writes and strict JSON serialization for cache files - Enforce rules on news timing, ETF universe, and historical case usage * fix(auto_fin): restrict news data source to '财联社' in analysis and cache - Update analysis templates to specify current news as from '财联社' only - Modify news fetching functions to filter by source '财联社' - Add validation method to check cached news source correctness - Update news caching logic to exclude non-'财联社' news - Enhance unit tests with multiple sources to ensure filtering works - Confirm news API calls include source filter parameter as '财联社' * refactor(auto_fin): convert I/O methods to asynchronous implementations - Change _news, _dataset, and _theme_data methods to async for improved concurrency - Move JSONL and CSV reading operations to asynchronous wrappers using asyncio.to_thread - Remove synchronous _read_jsonl and _read_csv functions, integrate them as static async class methods - Update cache validation methods to async, awaiting I/O operations accordingly - Adjust usage of dataset and news retrieval in analysis step to await asynchronous methods - Add async unit test to validate JSONL reading with unicode line separators - Preserve existing functionality while enabling non-blocking file and data access * fix(nx_file_graph): defer networkx import and improve dependency handling - Move networkx import inside NxFileGraph constructor for lazy loading - Raise ImportError with original exception context if networkx is missing - Remove module-level fallback assignment of nx to None - Expand test to block loading of multiple optional core dependencies eagerly - Change exception type in test from ModuleNotFoundError to AssertionError - Update test comments to reflect broader optional dependency checks * feat(embedding_store): add quota retry delay mechanism for embedding requests - Introduce quota_retry_delay parameter to configure wait time before retry on quota exhaustion - Implement detection of insufficient quota errors in LocalEmbeddingStore without external SDK - Add retry logic with custom delay when quota is insufficient during embedding requests - Update configuration to set max_retries and quota_retry_delay defaults for embedding store - Add unit tests covering quota exhaustion retry behavior with delay and opt-in control - Ensure existing retry behavior remains unchanged if quota_retry_delay is not set * feat(auto_fin): add detailed logging to analysis and data fetching steps - Add _preview static method for bounded diagnostic output in analysis.py - Log prompt start, completion, errors, and validation details in _reply method - Add info logs for major processing steps in execute method of analysis.py - Add debug and info logs for cache validation, data fetching, and pagination in data.py - Log conditions for skipping reports and cache plans in data.py execute method - Log download summaries and cache writes for news and ETF data - Improve error logging with exception details in cache validation functions - Ensure all logs include context such as record counts, paths, and parameters * refactor(auto_fin): overhaul Auto Fin workflow and schema contracts - Replace old Auto Fin schema models with comprehensive new data classes - Remove legacy Auto Fin analysis step in favor of modular agent-based steps - Introduce AutoFinAgentStep for validating structured agent replies - Simplify data cleaning and JSONL writing utilities for news cache - Remove synchronous and asynchronous dataset methods from analysis step - Redefine Auto Fin analysis configuration for 360-day news retention and multi-step pipeline - Remove embedded analysis prompt templates and replace with agent-driven logic - Update __init__.py exports to match new step implementations and remove deprecated classes - Improve error handling and validation in agent step reply processing - Clean up redundant imports and unused code in analysis and data preparation modules * feat(auto_fin): add detailed logging for analysis and data processing steps - Add timing logs to measure agent prompt processing duration in analysis.py - Log news cache hits and news write paths with record counts in data.py - Include detailed info logs for news download start and completion in data.py - Add start, progress, and completion logs with topic and event counts in history.py - Log start and completion of merge step including path and ETF count in merge.py - Add start and done logs with window and news counts in topic.py * feat(auto_fin): enhance schema and steps with detailed ETF and event modeling - Replace and add multiple AutoFin schema classes to support detailed ETF selection, historical research, market analysis, forecast models, and report output with validation - Implement Shanghai timezone normalization and strict validation in schema models - Remove deprecated AutoFin analysis agent step and consolidate reply handling in base step - Introduce AutoFinStep base class with shared helpers for prompt handling, data fetching, logging, and JSONL file operations - Add AutoFinDataStep to manage daily news data complete with schedule validation, caching, and source validation logic - Update cookbook configuration to customize auto_fin step parameters and simplify outbound proxy settings - Refactor imports and clean unused code for better maintainability * feat(auto_fin): introduce detailed historical event resolution and market similarity analysis - Add AutoFinHistoricalEventReference and AutoFinHistoricalSimilarity models for refined event referencing and similarity judgment - Implement validation to ensure non-empty critical fields and uniqueness of historical news IDs - Develop method to resolve Agent-selected historical event references from workspace files with strict path and existence checks - Enrich historical events with market entry and future returns data after resolution - Redesign market step to calculate similarity-weighted ETF forecasts based on matched historical event similarities - Enforce validation on matched historical events for uniqueness and proper weight summation - Simplify merge step output to final Markdown report without YAML frontmatter and redundant fields - Update user instructions for history search, market, and merge steps to reflect new data structures and responsibilities - Adjust test suite to cover new schema and step behavior changes, including enhanced validation and JSON output formats * feat(auto_fin): add new cron jobs and output analysis jsonl - Add new cron jobs auto_fin_1145_cron and auto_fin_1800_cron with auto_fin_steps - Change auto_fin_0930_cron schedule to run Monday to Sunday - Extend merge step to write analysis data to auto_fin_analysis.jsonl - Update unit tests to verify new cron jobs and their steps configuration * fix(auto_fin): improve atomic file write and refresh daily index - Change temporary file naming to include UUID for uniqueness and hidden prefix - Replace atomic write method from using Path.replace to os.replace with safe unlink - Add import and use os.replace for safer file replace operation - Refresh daily index after writing auto finance markdown and JSONL files - Import and call refresh_day_index in merge step to update file index asynchronously * docs(cookbook): add optional SSH proxy configuration in README files - Introduce optional SSH proxy setup in auto-fin and daily_paper cookbooks - Provide instructions to enable outbound proxy via `daily_cookbook.yaml` and environment variables - Add `REME_PROXY_IP` and `REME_PROXY_ACCOUNT` environment variables descriptions in multiple README files - Update English and Chinese README and README_ZH documents with proxy details - Maintain consistent formatting of environment variable tables across documents * fix(file_io): include schema_version in hidden metadata keys - Added "schema_version" to _INDEX_HIDDEN_METADATA_KEYS in _daily_index.py - Updated _render_notes_block to always include additional keys regardless of schema_version fix(deps): move pproxy dependency to later in pyproject.toml - Removed pproxy from early dependencies list - Added pproxy back near the end of dependency list for better ordering fix(outbound_proxy): require pproxy package for ssh_http proxy - Added importlib.util check for pproxy package presence - Raise RuntimeError if pproxy is not installed when using SSH HTTP outbound proxy - Improved error message suggests installing reme-ai with 'core' extra * docs(readme): update News section with new Cookbook workflows - Clarify introduction of optional Cookbooks with Daily Paper and Auto Fin workflows - Update English README to reflect both paper discovery and file-native ETF event research - Revise Chinese README to include financial news and historical market data research capability - Maintain announcement of paper acceptance at Findings of ACL 2026 * feat(auto_fin): add calculation results to final Markdown output - Implement _calculation_results to summarize forecast for each ETF analyzed - Include program-calculated results in the JSON input for the Markdown report - Update YAML template to incorporate calculation results and adjust recommendation rules - Refine recommendation logic to rely on event impact judgments combined with calculation outputs - Modify tests to verify presence of calculation results and updated report content and format * up prompt * fix(keyword_index): ignore non-indexable chunks during keyword sync - Add is_indexable method to base and BM25 keyword index classes to check text tokenizability - Update local file store to exclude non-indexable chunks from expected document IDs to prevent rebuild - Fix JSONL chunker to correctly handle Unicode line separator U+2028 inside JSON strings without splitting - Add test to ensure non-empty but non-indexable chunk does not trigger keyword index rebuild - Add test to verify U+2028 character does not cause incorrect JSONL record splitting
233 lines
8.1 KiB
Python
233 lines
8.1 KiB
Python
"""Focused tests for the DingTalk background agent bridge."""
|
|
|
|
# pylint: disable=missing-function-docstring,protected-access
|
|
|
|
import asyncio
|
|
from types import SimpleNamespace
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
from reme.components import ApplicationContext, R
|
|
from reme.components.agent_wrapper.base_agent_wrapper import BaseAgentWrapper
|
|
from reme.config.config_parser import _load_config
|
|
from reme.enumeration import ComponentEnum
|
|
from reme.steps.cookbook.dingtalk.wait import DingTalkWaitStep, _session_key
|
|
|
|
|
|
class _AgentWrapper(BaseAgentWrapper):
|
|
def __init__(self, **kwargs):
|
|
super().__init__(**kwargs)
|
|
self.reply_calls = []
|
|
self.compact_calls = []
|
|
self.result_text = "回答"
|
|
self.is_error = False
|
|
|
|
async def compact_session(self, session_id):
|
|
self.compact_calls.append(session_id)
|
|
|
|
async def reply(self, inputs, **kwargs):
|
|
self.reply_calls.append((inputs, kwargs))
|
|
session_id = kwargs.get("resume") or "session-1"
|
|
return {
|
|
"session_id": session_id,
|
|
"last_message": {"is_error": self.is_error},
|
|
"result": self.result_text,
|
|
}
|
|
|
|
|
|
class _Handler:
|
|
def __init__(self):
|
|
self.replies = []
|
|
self.markdown_replies = []
|
|
self.markdown_result = {"errcode": 0}
|
|
|
|
def reply_text(self, text, _message):
|
|
self.replies.append(text)
|
|
|
|
def reply_markdown(self, title, text, _message):
|
|
self.markdown_replies.append((title, text))
|
|
return self.markdown_result
|
|
|
|
|
|
class _WebSocket:
|
|
def __init__(self, messages=()):
|
|
self.messages = list(messages)
|
|
self.closed = asyncio.Event()
|
|
|
|
async def __aenter__(self):
|
|
return self
|
|
|
|
async def __aexit__(self, *_args):
|
|
await self.close()
|
|
|
|
def __aiter__(self):
|
|
return self
|
|
|
|
async def __anext__(self):
|
|
if self.messages:
|
|
return self.messages.pop(0)
|
|
await self.closed.wait()
|
|
raise StopAsyncIteration
|
|
|
|
async def close(self):
|
|
self.closed.set()
|
|
|
|
|
|
class _StreamClient:
|
|
TAG_DISCONNECT = "disconnect"
|
|
|
|
def __init__(self, route_result=""):
|
|
self.route_result = route_result
|
|
self.websocket = None
|
|
|
|
def pre_start(self):
|
|
return None
|
|
|
|
def open_connection(self):
|
|
return {"endpoint": "wss://example.test/connect", "ticket": "ticket"}
|
|
|
|
async def keepalive(self, _websocket):
|
|
await asyncio.Event().wait()
|
|
|
|
async def route_message(self, _message):
|
|
return self.route_result
|
|
|
|
|
|
def _message(text="hello", sender="user-1", conversation="cid-1", conversation_type="1"):
|
|
return SimpleNamespace(
|
|
text=SimpleNamespace(content=text),
|
|
sender_staff_id=sender,
|
|
conversation_id=conversation,
|
|
conversation_type=conversation_type,
|
|
)
|
|
|
|
|
|
def test_session_key_uses_conversation_type_id_and_sender():
|
|
assert _session_key(_message()) == "1:cid-1:user-1"
|
|
assert _session_key(_message(sender="user-2")) == "1:cid-1:user-2"
|
|
assert _session_key(_message(conversation="cid-2", conversation_type="2")) == "2:cid-2:user-1"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_final_reply_resumes_session_and_clear_only_removes_combined_key(
|
|
tmp_path,
|
|
):
|
|
app_context = ApplicationContext(workspace_dir=str(tmp_path))
|
|
wrapper = _AgentWrapper(app_context=app_context)
|
|
step = DingTalkWaitStep(app_context=app_context, agent_wrapper=wrapper)
|
|
step.logger = MagicMock()
|
|
handler = _Handler()
|
|
sessions = {}
|
|
message = _message()
|
|
key = _session_key(message)
|
|
|
|
await step._handle_message(message, key, sessions, handler)
|
|
await step._handle_message(message, key, sessions, handler)
|
|
|
|
assert sessions == {key: "session-1"}
|
|
assert wrapper.reply_calls == [("hello", {}), ("hello", {"resume": "session-1"})]
|
|
assert handler.markdown_replies == [("ReMe Agent", "回答"), ("ReMe Agent", "回答")]
|
|
|
|
await step._handle_message(_message(text="/compact"), key, sessions, handler)
|
|
assert wrapper.compact_calls == ["session-1"]
|
|
assert sessions[key] == "session-1"
|
|
assert handler.replies[-1] == "✅ Conversation compaction requested."
|
|
|
|
other_key = _session_key(_message(sender="user-2"))
|
|
sessions[other_key] = "session-2"
|
|
await step._handle_message(_message(text="/clear"), key, sessions, handler)
|
|
assert sessions == {other_key: "session-2"}
|
|
assert handler.replies[-1] == "✅ Conversation cleared. The next message will start a new session."
|
|
|
|
logs = "\n".join(call.args[0] for call in step.logger.info.call_args_list)
|
|
assert "received DingTalk text" in logs
|
|
assert "completed DingTalk reply" in logs
|
|
assert "handled session command" in logs
|
|
assert "conversation_type='1' conversation_id='cid-1' sender_staff_id='user-1'" in logs
|
|
assert all(value not in logs for value in ("hello", "session-1"))
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_final_reply_rejects_empty_agent_reply_and_dingtalk_send_failure(
|
|
tmp_path,
|
|
):
|
|
app_context = ApplicationContext(workspace_dir=str(tmp_path))
|
|
wrapper = _AgentWrapper(app_context=app_context)
|
|
step = DingTalkWaitStep(app_context=app_context, agent_wrapper=wrapper)
|
|
step.logger = MagicMock()
|
|
handler = _Handler()
|
|
message = _message()
|
|
key = _session_key(message)
|
|
|
|
wrapper.result_text = " "
|
|
with pytest.raises(ValueError, match="空回复"):
|
|
await step._handle_message(message, key, {}, handler)
|
|
|
|
wrapper.result_text = "回答"
|
|
handler.markdown_result = None
|
|
with pytest.raises(RuntimeError, match="发送钉钉 Markdown 回复失败"):
|
|
await step._handle_message(message, key, {}, handler)
|
|
|
|
|
|
def test_daily_cookbook_registers_one_step_background_wait_job(monkeypatch):
|
|
for name in ("DINGTALK_APP_KEY", "DINGTALK_APP_SECRET", "DINGTALK_ROBOT_CODE"):
|
|
monkeypatch.delenv(name, raising=False)
|
|
config = _load_config("daily_cookbook")
|
|
job = config["jobs"]["dingtalk_wait"]
|
|
assert job["backend"] == "background"
|
|
assert job["steps"] == [
|
|
{
|
|
"backend": "dingtalk_wait_step",
|
|
"agent_wrapper": "dingtalk_wait",
|
|
"app_key": "",
|
|
"app_secret": "",
|
|
"robot_code": "",
|
|
"worker_count": 4,
|
|
},
|
|
]
|
|
dingtalk_wait = config["components"]["agent_wrapper"]["dingtalk_wait"]
|
|
assert dingtalk_wait["skills"] == ["tushare-data"]
|
|
assert dingtalk_wait["job_tools"] == ["memory_search"]
|
|
assert dingtalk_wait["system_prompt"] == {
|
|
"type": "preset",
|
|
"preset": "claude_code",
|
|
"append": (
|
|
"Daily-paper Markdown is stored under the ReMe workspace. Detailed notes, including historical notes, "
|
|
"are at daily/YYYY-MM-DD/paper-<arxiv-id>.md; daily briefs are at "
|
|
"daily/YYYY-MM-DD/daily-paper-brief.md. Use memory_search to retrieve relevant long-term notes "
|
|
"across dates."
|
|
),
|
|
}
|
|
assert R.get(ComponentEnum.STEP, "dingtalk_wait_step") is DingTalkWaitStep
|
|
|
|
|
|
def test_daily_cookbook_passes_dingtalk_environment_to_step(monkeypatch):
|
|
monkeypatch.setenv("DINGTALK_APP_KEY", "app-key")
|
|
monkeypatch.setenv("DINGTALK_APP_SECRET", "app-secret")
|
|
monkeypatch.setenv("DINGTALK_ROBOT_CODE", "robot-code")
|
|
step = _load_config("daily_cookbook")["jobs"]["dingtalk_wait"]["steps"][0]
|
|
assert (step["app_key"], step["app_secret"], step["robot_code"]) == (
|
|
"app-key",
|
|
"app-secret",
|
|
"robot-code",
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_client_closes_when_background_stop_is_set(monkeypatch):
|
|
websocket = _WebSocket()
|
|
monkeypatch.setattr("websockets.connect", lambda _uri: websocket)
|
|
stop_event = asyncio.Event()
|
|
task = asyncio.create_task(DingTalkWaitStep._run_client(_StreamClient(), stop_event))
|
|
stop_event.set()
|
|
await asyncio.wait_for(task, timeout=1)
|
|
assert websocket.closed.is_set()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_client_restarts_after_server_disconnect(monkeypatch):
|
|
websocket = _WebSocket(["{}"])
|
|
monkeypatch.setattr("websockets.connect", lambda _uri: websocket)
|
|
with pytest.raises(ConnectionError, match="WebSocket closed"):
|
|
await DingTalkWaitStep._run_client(_StreamClient("disconnect"), asyncio.Event())
|