main
11 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 m4
|
470cf75722 |
merge: bring upstream v0.3.0 (72 commits) into Ai4Sci fork
Merged upstream/main (
|
||
|
Xi Zhang
|
a45563ea7f |
feat(scheduler): optional rubric acceptance checklist for scheduled tasks (#451)
Scheduled tasks gain an optional `rubric`: an acceptance checklist graded after each run by deepagents' RubricMiddleware (LLM-as-a-judge on the auxiliary model) with one revision retry. No `rubric` key = no-op. - cron/schedule.py: create_schedule/run_now carry the rubric in the run input and cron metadata only when non-blank - middleware/scheduler.py: schedule_task gains `rubric`; list marks graded rows - commands/implementation/schedule.py: `/schedule add ... --rubric`, `/schedule run` forwards the stored rubric, list gets a Rubric column - subagents/_factory.py: RubricMiddleware mounted last on the scheduler graph so a needs_revision jump skips the memory lifecycle until the accepted run; grader is read-only (ls + read_file, eviction off), bounded by a 12-call budget, and gets an explicit structured-output strategy on OpenRouter (Gemini JSON mode, Anthropic tool calling); warns at build for anthropic/claude-fable-5.1 via OpenRouter, which grades under neither strategy today - tests: 17 new cases; fix two pre-existing fixture leaks (callable backend stub in test_hitl, import-under-patch in test_async_subagent_factory) |
||
|
m4
|
5a581c78a2 |
feat: add scoped model runtime configuration
Build / build (push) Has been cancelled
Docker / build (push) Has been cancelled
Lint / ruff (push) Has been cancelled
Test / pytest (ubuntu-latest, 3.11) (push) Has been cancelled
Test / pytest (ubuntu-latest, 3.12) (push) Has been cancelled
Test / pytest (windows-latest, 3.11) (push) Has been cancelled
Test / pytest (windows-latest, 3.12) (push) Has been cancelled
Introduce provider, model, and invocation contracts with encrypted configuration persistence. Add web runtime fencing, route fallback, recovery middleware, workspace scoping, and comprehensive tests. |
||
|
dinos
|
01845f4311 |
refactor: route middleware display events through an injected event sink (#343)
* chore: add pytest-asyncio in auto mode * test: migrate channel and stream tests to native async Convert run_async() wrapper tests to plain 'async def test_*' under pytest-asyncio auto mode. collect_events() in stream_v3_fakes becomes a coroutine awaited at every call site. * test: migrate command and model/middleware tests to native async Convert run_async() wrappers (import, alias, and fixture forms) to plain 'async def test_*'. Multi-call tests merge onto one loop as sequential awaits; none asserted on loop identity. * test: migrate TUI, notifier, gateway, and session tests to native async TUI/notifier/gateway files convert run_async wrappers to plain async tests. test_sessions.py's unittest.TestCase classes move to unittest.IsolatedAsyncioTestCase (pytest-asyncio does not await async methods on plain TestCase; converting blindly would have made ~70 tests silently vacuous). Its setUpClass keeps a one-shot asyncio.run() since IsolatedAsyncioTestCase has no async class-level hook. TestLoadingWidget in test_tui_widgets.py drops its TestCase base for the same reason. * test: replace direct asyncio.run() calls with native async tests Convert tests that called asyncio.run() (directly or via a local _run helper) to plain 'async def test_*'; delete the local helpers. * test: drop undeclared anyio markers and delete run_async helper The @pytest.mark.anyio tests relied on anyio being a transitive dep of httpx; auto-mode pytest-asyncio collects them natively. run_async() and its fixture are unreferenced after the migration, so remove them — pytest-asyncio's per-test loop teardown covers the pending-task cancellation the helper existed for (verified: full suite runs with no 'Event loop is closed' errors or destroyed-task warnings). * test: add autouse fixture for watcher cleanup * refactor: remove redundant hasattr calls * refactor: add typed middleware event sink and thread through assembly Add MiddlewareEventSink protocol + NoOpSink in middleware/events.py with a documented any-thread non-blocking contract (contract test uses a deliberately-slow fake sink). Thread an optional `events` parameter through create_cli_agent -> _get_default_middleware -> tool selector / model fallback constructors; subagent stacks are always forced to NoOpSink. * refactor: inject a notifier port into async-watcher and background middleware Add public pre_cancel_watcher() and enqueue_task_notification() to cli/async_notifier.py and a small NotifierPort protocol (middleware/notifier.py) that the module satisfies structurally. AsyncWatcherMiddleware and BackgroundExecutionMiddleware now receive the port by constructor injection at the composition root, deleting the lazy 'from ..cli import async_notifier' imports and the private _watcher_by_thread / _enqueue pokes. * refactor: invert tool-selection ownership onto a frontend event sink The adaptive tool selector now reports on_tool_selection_started / on_tool_selection / on_tool_selection_ended to the injected sink instead of writing four process-global module variables. The frontend sink (stream/sink.py FrontendEventSink) owns the selected/total/active state with consume-once + dedup-vs-last-emitted semantics; stream/tool_selection.py reads that sink object (a ToolSelectionView) rather than reaching into tool_selector's globals. Deleted: the 4 module globals, the cross-module mutations in tool_selection.py, the track_stream_selection flag, the now-vestigial _ToolSelectionTrackerMiddleware, reset_tool_selection_state_for_tests, and the autouse conftest fixture. The sink is threaded from the two interactive frontends through create_runtime_gateways -> LocalGraphGateway (read side) and _load_agent -> create_cli_agent (write side); subagent / headless stacks get NoOpSink. * refactor: route model-fallback narration through the injected event sink Delete the _ui_emit_fn / set_ui_emit module global and the ..stream.console import from model_fallback.py. The fallback middleware now reports through its injected sink: the fallback transition via the structured on_model_fallback (the frontend formats the '-> Falling back to ...' line), and the surrounding narration (primary-failure header, per-attempt outcome, exhaustion, non-fallbackable rejection) via emit_fallback_notice, preserving the exact user-facing text. The TUI binds its _append_system as the sink's fallback display where it used to call set_ui_emit (cleared on exit); the Rich CLI's sink prints to the console. _try_fallbacks / _guard_and_fallback take the sink. * refactor: declare events on the GraphGateway protocol Both gateway implementations now carry an explicit events attribute (LangGraphServerGateway holds None — no frontend renders middleware events across the HTTP boundary), so the four call sites use plain attribute access instead of getattr probing an implicit contract. * refactor: bind fallback display via the closure-scoped concrete sink The App methods used gateway.events (typed as the read-side view) and hasattr-probed for the concrete FrontendEventSink API. The enclosing factory creates that sink two hundred lines up — close over it directly: no probing, fully typed, and it becomes a constructor parameter naturally when the App class is hoisted out of the factory. * fix: end tool selection before fallback handler * fix: keep fallback display errors non-fatal * fix: preserve selector suppression for default streams * fix: restore fallback notice console display * refactor: consolidate fallback narration events * refactor: clean middleware event sink plumbing * fix: type gateway session events * refactor: make all event protocols runtime-checkable MiddlewareEventSink already carried @runtime_checkable (the stream binding guard isinstance-checks it); ToolSelectionView and SessionEvents now match, so mirroring that pattern against any of the three protocols works instead of raising TypeError. * fix(cli): close QuickJS workers after one-shot failures * fix(cli): honor no-thinking in final output * fix(channels): report failed startup accurately * fix(channels): make Telegram cleanup idempotent * fix(tui): skip command sync during exit * fix(channels): preserve startup state during retries * refactor(channels): share pending startup status * refactor(cli): expose channel startup snapshot * fix(tui): move channel startup off event loop * test(channels): release retry gate on assertion failure --------- Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com> |
||
|
dinos
|
f2f010a350 |
feat(memory): observation linking (#307)
* refactor(gateway): create module for launching async/bg agents * refactor(memory): refactor worker launch around source context & output deltas * refactor(gateway): generalize async/bg module * refactor(memory): revamp worker launching * feat(memory): add observation linking * test(memory): remove redundant test branches * fix(memory): make 'supersedes' relation directional * fix(memory): don't create empty project observation dirs * fix(memory): schedule direct observations for linking * fix(cli): wait for observation linker before shutdown * fix(memory): block arbitrary writes to /memories * fix(linker): remove `linked_by` attribute from frontmatter * refactor(linker): rename base relationship to `comlpements` * fix(cli): bump worker wait to 2m * feat(tools): catch malformed tool calls & retry * feat(status): add linking result to statusbar * fix(linker): don't launch linker when observations are disabled * fix(memory): use posix paths * fix(watcher): call abort hook on error status * fix(watcher): delete thread on failed run creation * fix(watcher): preserve url * fix(observation): record session_id, drop unused fields * fix(memory): reject unsupported worker source types * refactor(backends): shared memory backend builder * fix(scheduler): resolve linker inputs outside lock * fix(memory): dont launch workers / record observations without thread_id * feat(memory): include related observations in tool results * fix(memory): skip malformed observation frontmatter * revert(tools): drop tool error handling changes from this PR * fix(memory): serialize observation link writes * fix(memory): queue observations written by aborted workers * fix(memory): track observation linker launch handoff * fix(memory): resolve cross-project related observations * fix(status): avoid recounting reason-only link updates * fix(memory): avoid rereading file for content * fix(linker): use neutral prose for bidirectional reasons * test(memory): coverage for aborted/failed launches * test(memory): cleanup & helpers * feat(linker): add observations index hint |
||
|
dinos
|
b1dccf17ea |
fix(tool-selector): memory tools & state for main agent (#305)
* fix(tool-selector): always include memory tools * fix(tool-selector): only track & show state for main agent * docs: update docstring |
||
|
dinos
|
f356de36a6 | feat: memory retrieval (#281) | ||
|
Xi Zhang
|
63969b596d |
Release/v0.1.4 (#266)
* feat(middleware): reposition code interpreter middleware in the stack * feat(models): add qwen3.7-plus model entry and update context window comment * feat(models): add qwen3.7-max and qwen3.7-plus model entries for DashScope * feat(auxiliary): implement auxiliary model support for background tasks and tool selection - Added auxiliary model configuration to EvoScientistConfig. - Introduced _ensure_auxiliary_chat_model function to manage auxiliary model instances. - Updated onboarding steps to include auxiliary model selection. - Modified middleware to route tool selection to the auxiliary model when applicable. - Enhanced tests to cover auxiliary model functionality and configuration. * feat(steps): update UI backend selection options and descriptions * Refactor code structure for improved readability and maintainability * feat(patches): implement OpenRouter response reasoning item stripping to prevent multi-turn errors * feat: update version to v0.1.4 in badges, README, and pyproject.toml; adjust skill counts in steps.py * feat(config): add auxiliary model and provider environment variables to test setup |
||
|
dinos
|
92d95dee68 |
feat(memory): add observation memory lifecycle (#259)
* feat(memory): add observation memory lifecycle Add file-backed observation memory with deterministic markdown records, structured record_observation tooling, startup indexing, and profile/observation prompt guidance. Launch post-turn and post-subagent EvoMemory workers through LangGraph dev so completed runs can update profile memory, save durable observations, and write subagent execution summaries without blocking the active agent. Wire memory middleware into the main agent, subagents, async graphs, TUI status reporting, worker activity accounting, and observation-aware research prompts, with regression coverage for storage, lifecycle scheduling, graph registration, status display, and stream reset behavior. * fix(cli): sync background agent server on resume Resume flows now need to keep the LangGraph dev background server aligned with the active workspace even when async subagents are disabled. EvoMemory workers use that server too, so gating resume-time sync on enable_async_subagents could leave workers pinned to the launch workspace after resuming a thread from another workspace. Run workspace sync unconditionally for Rich CLI and Textual resume paths, while preserving WorkspaceMismatchError handling so failed sync aborts the resume before mutating the active thread or workspace. Propagate aborted resume callbacks through the command UI so channel-issued /resume commands do not send false success or history output. Channel slash dispatch now treats CommandManager-caught command errors as command errors and skips completion hooks for those failed commands. Add regression coverage for disabled async subagents, callback aborts, and channel command error reporting. * fix(cli): prepare serve resume workspace before adopting Load the resumed workspace agent and sync the background server as a single pre-adoption step. Restore the previous active workspace if preparation fails so serve mode keeps using the old session consistently. * fix(memory): untrack abandoned worker status watches Stop treating watcher shutdown as confirmed worker completion. Terminal worker statuses still count memory deltas, while poll failures or watcher setup failures now remove the active run without crediting partial outputs. * fix(cli): report channel command failures accurately Treat command_error as a None sentinel so empty error strings still fail, and let TUI resumes continue only on non-mismatch background-server sync failures while reporting degraded mode. * fix(stream): clear memory counters for resume streams Reset completed-memory counters for every new agent stream, including Command-based HITL and resume streams, so saved-memory indicators do not leak across turns. * docs(tools): make observation recording guidance conditional Clarify that agents should call record_observation only when the observation tool is available, preserving the existing durability and usefulness criteria. * feat(config): add controls for profile and observation memory Add config flags for profile memory, observation memory, observation writer placement, and background memory workers. Wire the controls through main agents, subagents, EvoMemory middleware, and memory lifecycle workers so observation writes can be assigned to the live agent, subagent worker, both, or neither. Keep turn memory workers profile-only and make prompts reflect the available observation read/write paths. Skip langgraph dev startup when neither async subagents nor memory workers need the background server. Add coverage for config parsing, prompt gating, middleware wiring, and worker tool availability. * test(cli): include memory defaults in serve config stubs * fix(memory): offload async worker launch blocking calls Run the langgraph-dev health check and memory-output snapshot in worker threads from the async EvoMemory launcher so it does not block the event loop. * chore(memory): harden turn worker subagent guardrail * chore(memory): refresh profile context per request * fix(memory): offload async profile file reads * fix(memory): offload async worker completion accounting |
||
|
dinos
|
d348076f40 | Add runtime context middleware (#255) | ||
|
Xi Zhang
|
c407d2e20f |
Fix/async subagent model switch (#217)
* feat(middleware): add ConfigurableModelMiddleware for dynamic model resolution - Introduced ConfigurableModelMiddleware to resolve chat models from RunnableConfig.configurable on each call. - Updated middleware initialization to include ConfigurableModelMiddleware. - Enhanced context editing middleware tests to verify presence of ConfigurableModelMiddleware. - Implemented tests for ConfigurableModelMiddleware to ensure correct model overriding and caching behavior. - Added tests for deepagents model-passthrough patch to verify configuration injection in async tasks. * feat(async-subagent): update middleware handling to prevent deadlocks in async sub-agents * style: Refactor code formatting for improved readability in patches and test files * refactor: streamline middleware construction and improve async handling in ConfigurableModelMiddleware * fix: remove unused request parameter from _read_model_override function * refactor: improve async handling in _ClientProxy and enhance logging in ConfigurableModelMiddleware test: add behavior test to ensure AskUserMiddleware is excluded in async subagent mode |