feat(capabilities): add QuestionCapability and migrate BackgroundTaskCapability from xeno-agent - #345
Closed
Million-mo wants to merge 7 commits into
Closed
feat(capabilities): add QuestionCapability and migrate BackgroundTaskCapability from xeno-agent#345Million-mo wants to merge 7 commits into
Million-mo wants to merge 7 commits into
Conversation
…support Move question tools into a proper AbstractCapability that accepts args.schemas and args.enabled_tools, mirroring BackgroundTaskCapability. Replaces the bare QuestionTools entry point so consumers can customize LLM-facing parameter descriptions via YAML schema files without writing their own capability wrapper.
Move 51 question tool unit tests (40 for question_for_user + 11 for ask_followup_question) from xeno-agent to agentpool. Tests now import from agentpool_toolsets.builtin.question_tools instead of xeno_agent. Two assertions adjusted to match agentpool's actual implementation: - Error message regex: 'questionnaire' → 'questions' (agentpool naming) - ask_followup_question metadata: dropped suggestion_attributes check (agentpool's _format_followup_response doesn't emit this field) Also add RUF001 per-file ignore for CJK fullwidth punctuation in test data.
Add a 'question' tool to QuestionCapability that replicates the legacy
QuestionTool behavior (simple prompt + optional response_schema via MCP
Elicit). This unifies all user-interaction tools under one capability:
- question_for_user: XML multi-question questionnaire
- ask_followup_question: single question with <suggest> options
- question: simplest single-question (replaces QuestionTool)
Mark QuestionToolConfig (tools: [{type: question}]) as deprecated,
directing users to capabilities: [{type: question}].
Add 3 new tests covering the question tool: default-enabled, enabled
alone, enabled via schemas.
…gent Migrate the complete BackgroundTaskCapability implementation to agentpool: - capability.py: full lifecycle management (task, background_output, background_cancel, steer_task tools) - manager.py: BackgroundTaskManager with concurrent task execution, cleanup, and session isolation - notification.py: NotificationBatcher for debounced completion notifications - types.py: BackgroundTask, SessionTaskState dataclasses - utils/tool_schema.py: YAML schema loading and LLM-facing schema override Includes 277 tests (unit + integration + resource provider) covering lifecycle, concurrency, error propagation, notification batching, history isolation, and cancellation regression. Config schema files (task.yaml, background_output.yaml, background_cancel.yaml, steer_task.yaml) provide default LLM-facing parameter descriptions. Entry point 'background_task' registered in pyproject.toml.
Three CI failures fixed:
1. ruff format: question.py ternary expression reformatted
2. mypy (16 errors → 0):
- tool_schema.py: cast yaml.safe_load/json.loads results to
OpenAIFunctionDefinition, construct TypedDict with explicit
key-value pairs instead of ** unpacking
- question.py: add ToolResult return annotations to tool wrappers
- manager.py: re-read task_model.status into locals after await
to prevent mypy narrowing from concurrent status changes
- capability.py: type session_pool as SessionPool | None,
fix delivered bool assignment from followup() str|None return,
remove dead config.type == 'team' comparison (agents dict never
contains team configs), rename shadowed task_model variable
3. Flaky tests (8 failures): replace fixed asyncio.sleep(0.8) with
_wait_until_called() polling helper in 3 test files. The fixed
sleep was too tight under CI load — debounce timers fire late
when the event loop is busy with parallel workers.
…cationBatcher Root cause: loop.call_later callbacks run in a separate contextvars context where anyio's sniffio async-library detection fails with AsyncLibraryNotFoundError. This prevented _schedule_flush from calling tg.start_soon, so _flush never executed and deliver_callback was never invoked — all 25 batcher tests + 8 notification tests failed in CI. Fix: replace anyio.create_task_group/start_soon with asyncio.ensure_future for scheduling flush coroutines. Keep anyio.CancelScope and anyio.fail_after for timeout protection (these don't require sniffio context). Track flush tasks in a set[asyncio.Task] and cancel/await them in shutdown. Also restore source_type team detection by checking config.type via str() cast (mypy-safe for AnyAgentConfig union that doesn't include team types at the type level, but mocks provide type='team' at runtime).
Million-mo
changed the title
Collaborator
Author
|
/oc |
Collaborator
|
@Million-mo 保留一个 question 就行了吧。ask_followup_question实际是为了对齐以前版本（不怎么用了）；question 是 agentpool 的能力吧，没有适配 multi-question 的情况。其中相当于把 question 升级为 question_for_user，统一改为 question？ |
Collaborator
|
是不是留一个 task 就行，（实际实现是 background task 的功能）？ |
Collaborator
Author
|
分析了一下 核心重叠：创建子会话、delegation depth 守卫、sync 流式收集、async fire-and-forget 写文件 — 这些路径结构上几乎一样。 BackgroundTaskCapability 独有（无法塞进 SubagentTools）：
这些功能依赖 SubagentTools 独有：
如果要合并，正确方向是把 SubagentTools 的独有功能（team 执行、list_available_nodes、runtime registry）移植到 BackgroundTaskCapability 里，然后退役 SubagentTools。这是一个较大的重构，建议作为单独的 PR。 这个 PR 先保持两者分离，question 合并已经按你的建议做了（删掉 |
Merge ask_followup_question, question_for_user, and question into one unified question tool per reviewer feedback. The question_for_user implementation (richest, supports multi-question XML with enum/multi/ input types) is retained as the canonical implementation, renamed to question. ask_followup_question (legacy compat) and the simple question tool are removed. Changes: - question_tools.py: remove ask_followup_question + _format_followup_response, rename question_for_user to question - question.py: simplify QuestionCapability to expose only question - Update all tests, docs, and tool name references
Collaborator
|
@Million-mo list_available_node 没有意义，这是历史遗留代码，在最早的 agentpool 中没有办法注入 agent list，所以提供个工具。在最新的一些实践中，直接就注入到 system prompt 中了，所以这个工具并没有太大存在必要。 |
Million-mo
added a commit
that referenced
this pull request
Aug 4, 2026
- src/agentpool_toolsets/builtin/subagent_tools.py: remove list_available_nodes method + create_tool registration - src/agentpool_config/toolsets.py: SubagentToolName Literal now only accepts 'task'; docstring updated - tests/toolsets/test_tool_filtering.py: update assertions - tests/toolsets/builtin/test_as_capability.py: update assertions - tests/servers/acp_server/test_claude_acp_toolset_integration.py: update assertion - tests/tools/test_runcontext.py: remove prompt referencing list_available_nodes (test was already xfail) - docs/how-to/advanced/acp-integration.md: update docs - docs/how-to/servers/mcp-server.md: update docs The tool was legacy code; Leoyzen noted agents list is now injected directly into system prompt.
6 tasks
Million-mo
added a commit
that referenced
this pull request
Aug 4, 2026
…Capability from xeno-agent (#346) * feat(capabilities): add QuestionCapability with YAML schema override support Move question tools into a proper AbstractCapability that accepts args.schemas and args.enabled_tools, mirroring BackgroundTaskCapability. Replaces the bare QuestionTools entry point so consumers can customize LLM-facing parameter descriptions via YAML schema files without writing their own capability wrapper. * test(question): migrate question tool tests from xeno-agent Move 51 question tool unit tests (40 for question_for_user + 11 for ask_followup_question) from xeno-agent to agentpool. Tests now import from agentpool_toolsets.builtin.question_tools instead of xeno_agent. Two assertions adjusted to match agentpool's actual implementation: - Error message regex: 'questionnaire' → 'questions' (agentpool naming) - ask_followup_question metadata: dropped suggestion_attributes check (agentpool's _format_followup_response doesn't emit this field) Also add RUF001 per-file ignore for CJK fullwidth punctuation in test data. * feat(question): merge simple question tool into QuestionCapability Add a 'question' tool to QuestionCapability that replicates the legacy QuestionTool behavior (simple prompt + optional response_schema via MCP Elicit). This unifies all user-interaction tools under one capability: - question_for_user: XML multi-question questionnaire - ask_followup_question: single question with <suggest> options - question: simplest single-question (replaces QuestionTool) Mark QuestionToolConfig (tools: [{type: question}]) as deprecated, directing users to capabilities: [{type: question}]. Add 3 new tests covering the question tool: default-enabled, enabled alone, enabled via schemas. * feat(capabilities): add BackgroundTaskCapability migrated from xeno-agent Migrate the complete BackgroundTaskCapability implementation to agentpool: - capability.py: full lifecycle management (task, background_output, background_cancel, steer_task tools) - manager.py: BackgroundTaskManager with concurrent task execution, cleanup, and session isolation - notification.py: NotificationBatcher for debounced completion notifications - types.py: BackgroundTask, SessionTaskState dataclasses - utils/tool_schema.py: YAML schema loading and LLM-facing schema override Includes 277 tests (unit + integration + resource provider) covering lifecycle, concurrency, error propagation, notification batching, history isolation, and cancellation regression. Config schema files (task.yaml, background_output.yaml, background_cancel.yaml, steer_task.yaml) provide default LLM-facing parameter descriptions. Entry point 'background_task' registered in pyproject.toml. * fix(ci): resolve ruff format, mypy, and flaky test failures Three CI failures fixed: 1. ruff format: question.py ternary expression reformatted 2. mypy (16 errors → 0): - tool_schema.py: cast yaml.safe_load/json.loads results to OpenAIFunctionDefinition, construct TypedDict with explicit key-value pairs instead of ** unpacking - question.py: add ToolResult return annotations to tool wrappers - manager.py: re-read task_model.status into locals after await to prevent mypy narrowing from concurrent status changes - capability.py: type session_pool as SessionPool | None, fix delivered bool assignment from followup() str|None return, remove dead config.type == 'team' comparison (agents dict never contains team configs), rename shadowed task_model variable 3. Flaky tests (8 failures): replace fixed asyncio.sleep(0.8) with _wait_until_called() polling helper in 3 test files. The fixed sleep was too tight under CI load — debounce timers fire late when the event loop is busy with parallel workers. * fix(ci): replace anyio TaskGroup with asyncio.ensure_future in NotificationBatcher Root cause: loop.call_later callbacks run in a separate contextvars context where anyio's sniffio async-library detection fails with AsyncLibraryNotFoundError. This prevented _schedule_flush from calling tg.start_soon, so _flush never executed and deliver_callback was never invoked — all 25 batcher tests + 8 notification tests failed in CI. Fix: replace anyio.create_task_group/start_soon with asyncio.ensure_future for scheduling flush coroutines. Keep anyio.CancelScope and anyio.fail_after for timeout protection (these don't require sniffio context). Track flush tasks in a set[asyncio.Task] and cancel/await them in shutdown. Also restore source_type team detection by checking config.type via str() cast (mypy-safe for AnyAgentConfig union that doesn't include team types at the type level, but mocks provide type='team' at runtime). * refactor(question): unify question tools into single question tool Merge ask_followup_question, question_for_user, and question into one unified question tool per reviewer feedback. The question_for_user implementation (richest, supports multi-question XML with enum/multi/ input types) is retained as the canonical implementation, renamed to question. ask_followup_question (legacy compat) and the simple question tool are removed. Changes: - question_tools.py: remove ask_followup_question + _format_followup_response, rename question_for_user to question - question.py: simplify QuestionCapability to expose only question - Update all tests, docs, and tool name references * fix(review): address opencode-agent review findings #1 tool_call_id: QuestionCapability._question already uses replace() to propagate tool_name/tool_call_id/tool_input — verified with L2 test. #2 telemetry: add @logfire.instrument to QuestionCapability._question; background_task modules already instrumented. #3 state cleanup: after_run() evicts _session_states and _ephemeral_states, shuts down batcher and task manager. #5 queued cancel: pending cancel path fires on_completed before completion_event.set(). #6 flush exception: _flush catches broad Exception, marks delivered regardless of success/failure. #7 timeout message: CancelledError handler checks task.status == 'timed_out' before choosing message. #8 private API: guard pydantic_ai._agent_graph import with try/except and helpful error message. #9 L2 test: add test_question_tool_propagates_tool_call_id_to_agent_context. #10 error contract: _build_definition raises ValueError with descriptive message for missing name or non-dict input. Nit: remove DEBUG_TASK_MGR prefix, type coro as Coroutine, fix test names. * chore: remove list_available_nodes tool (legacy, Leoyzen feedback #345) - src/agentpool_toolsets/builtin/subagent_tools.py: remove list_available_nodes method + create_tool registration - src/agentpool_config/toolsets.py: SubagentToolName Literal now only accepts 'task'; docstring updated - tests/toolsets/test_tool_filtering.py: update assertions - tests/toolsets/builtin/test_as_capability.py: update assertions - tests/servers/acp_server/test_claude_acp_toolset_integration.py: update assertion - tests/tools/test_runcontext.py: remove prompt referencing list_available_nodes (test was already xfail) - docs/how-to/advanced/acp-integration.md: update docs - docs/how-to/servers/mcp-server.md: update docs The tool was legacy code; Leoyzen noted agents list is now injected directly into system prompt. * fix: ruff format toolsets.py (single-entry Literal syntax)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Migrate
questionandbackground_taskcapabilities from xeno-agent into agentpool as built-inAbstractCapabilitysubclasses with YAML schema override support.QuestionCapability (
src/agentpool/capabilities/question.py)question_for_user,ask_followup_question, andquestiontoolsschemas: dict[str, str]for YAML schema file paths (resolved relative toCONFIG_DIR)enabled_tools: list[str]to control which tools are exposedagentpool_toolsets.builtin.question_tools.QuestionToolsquestiontool replaces the legacyQuestionToolfromtool_impls/question/questionentry point inpyproject.tomlBackgroundTaskCapability (
src/agentpool/capabilities/background_task/)task,background_output,background_cancel,steer_taskBackgroundTaskManager— concurrency gating, timeout, cleanup, blocking-waiter trackingNotificationBatcher— debounced batched completion notifications viafollowup()config/tools/(task.yaml, background_output.yaml, etc.)background_taskentry point inpyproject.tomlUtility:
src/agentpool/utils/tool_schema.pyload_tool_schema()— load OpenAIFunctionDefinition from YAML/JSON filesapply_params_schema()— override tool function_schema with YAML parametersBug fixes included
anyio.create_task_group/start_soonwithasyncio.ensure_futurebecauseloop.call_latercallbacks run outside anyio sniffio context, causingAsyncLibraryNotFoundErroron Ubuntu CIasyncio.sleep(0.8)with_wait_until_called()polling helper in 3 test filesCommits
feat(capabilities): add QuestionCapability with YAML schema override supporttest(question): migrate question tool tests from xeno-agent— 51 testsfeat(question): merge simple question tool into QuestionCapabilityfeat(capabilities): add BackgroundTaskCapability migrated from xeno-agent— 277 testsfix(ci): resolve ruff format, mypy, and flaky test failuresfix(ci): replace anyio TaskGroup with asyncio.ensure_future in NotificationBatcherTest Plan
uv run ruff checkpassesuv run ruff format --checkpassesuv run --no-group docs mypy src/— 0 errorsuv run pytest -m unit— 4867 passed (4 pre-existing failures unrelated)uv run pytest -m "not unit and not integration..."— 324 passed