conversation application service, AtomicJsonFile fix) vào sau khi tách 6
widget UI Co4E (N3)
Đã kiểm trước khi merge: ui/co4e_tab.py và ui/routing_toggle.py đều bị 2
bên cùng đụng, nhưng ở vùng dòng khác nhau hoàn toàn (bên kia sửa
_apply_co4e_routing/RoutingToggle cho R03-T05, N3 chỉ đụng phần dựng
sidebar/canvas/chat) — không có xung đột logic thật.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Lane N3 (Co4E Studio) — dùng bộ workflow refactor-god-file, mỗi bước có
characterization test trước khi tách, hậu kiểm ranh giới tầng sau mỗi bước:
- skills_list_panel.py / agent_list_panel.py — 2 khu vực sidebar
- co4e_canvas_widget.py + canvas_items.py + canvas_interaction_mixin.py —
Co4ECanvas tách 3 file (vượt 400 dòng nếu đứng một mình)
- node_property_panel.py + node_property_actions_mixin.py +
step_config_section.py — StepConfigPanel, cùng lý do
- co4e_run_control_widget.py — RunsPagePanel (trang Flow Status)
- co4e_chat_view.py — ChatPanel + _ChatInput + helper autocomplete
- palette_list.py — _PaletteList dời khỏi ui/co4e_tab.py, hết import ngược
presentation -> ui (agent/skills panel giờ import top-level)
ui/co4e_tab.py giảm 2089 -> 1878 dòng, chỉ còn phần wiring + business logic
(Co4ERunManager/AgentWorker chưa đổi — nằm ngoài phạm vi này, xem docstring
presentation/co4e/co4e_tab.py). ui/co4e_canvas.py và ui/co4e_config_panel.py
còn lại là compat shim re-export, không đổi API cho bên gọi.
Thêm tests/test_co4e_integration.py — dựng thật Co4ETab qua build_co4e_tab(),
lái luồng qua nhiều panel trong cùng instance (thêm node, mở/gập chat, chuyển
trang Flow Status rồi quay lại không mất state canvas) — bắt lỗi wiring
xuyên-panel mà characterization test từng panel riêng không thấy được.
Đã xác minh: pytest 348 passed/1 skipped, tools/check_co4e.py sạch, không
file nào >400 dòng, domain/application không import PySide6, và so pixel
before/after (git worktree tại HEAD cũ) ra 0/1.125.000 pixel khác biệt.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
R04-T03 — the turn lifecycle, extracted from `core/chat_agent.py::run_cowork`
into `application/conversations/`. The 260-line body mixed the lifecycle (step
budget, cancel checks, guard -> preview -> gate -> execute ordering, sandbox
tidy-up) with the machinery doing each step, and reaching any of it meant
standing up a Qt widget and a worker thread. It is now a plain object driven
through two Protocols and six callables (`turn_runtime.py`), with the concrete
`core/*` wiring confined to `core_runtime_adapter.py` — the same shape R03 used
for routing. Faithful port, not an improvement pass: where the original had a
quirk (the step-ceiling note only merges into the answer when the last message
is the assistant's) the quirk is preserved and commented.
R04-T04 — `ui/cowork_tab.py::build_job` no longer calls run_cowork. It captures
the widget's state at submit time, builds the request via the new
`cowork_turn_request.py` and executes it. `execute(..., messages=...)` hands the
widget's own list over because `_reattach_running_turn` replays from it WHILE
the worker appends and `_finalize_turn` slices it afterwards — a private list
would break both silently.
R04-T05 — `core/task_executors.py`'s cowork branch shares the same engine. All
five unattended-run behaviours stay put (plan reminder, history_ready, History
autosave per assistant message, timeout notice, plan_incomplete_reason), and
`_unattended_prompt` now expresses the load-bearing prefix order in one
readable call instead of three successive rebindings.
Verification: 74 new tests (364 passed, 1 skipped overall; check_imports PASS).
The two that matter most:
- `test_conversation_service_parity.py` runs the same scripted turn through
run_cowork AND the service and compares the event stream, the resulting
conversation and the advertised tool list across 7 scenarios;
- `test_task_executor_turn.py` was written BEFORE the migration and passed 8/8
against the old code, then unchanged against the new.
Known: `ui/cowork_tab.py` (416 -> 455) and `core/task_executors.py` (476 -> 524)
stay above the 400-LOC limit. Both were already over it before this change;
bringing them under needs the R08 / R07 decompositions.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
EPIC R03 (Team Duy) — Model Providers & Routing. All six tasks done.
R03-T02 — Provider catalogue
domain/models/provider_descriptor.py ProviderDescriptor (frozen), WireProtocol, AuthKind
infrastructure/providers/provider_registry.py
thread-safe registry: id/alias lookup, dynamic
lookup by model id, adapter selection by protocol
providers/factory.py drops its own _REGISTRY table and delegates to the
registry, still raising ProviderError for callers
R03-T03 — RoutingApplicationService (pure Python, 4 modes)
application/model_routing/routing_models.py
RoutingMode (off/auto/manual/fallback),
RoutingRequest (immutable snapshot), RouteEvaluation,
RoutingOutcome
application/model_routing/routing_application_service.py
the single decision flow, reached through two narrow
ports plus a caller-supplied confirm callback, so no
Qt import is needed
application/model_routing/core_routing_adapter.py
binds the ports to core/routing and AppContext
Fallback is a new resilience mode: keep the selected model while it can serve the turn,
re-route only when it cannot. Wired end to end through config.py, state.py,
ui/routing_toggle.py and i18n.py (EN/JA/VI).
R03-T04 / T05 — Remove the duplicated routing flow
ui/chat_panel.py (#L638), ui/co4e_tab.py, ui/folder_tab.py each drop ~35 lines of copied
logic and call the shared service; the widgets now only build a RoutingRequest, host the
Manual-mode modal and render the outcome.
R03-T06 — Token usage as an event
infrastructure/telemetry/usage_sink.py UsageEvent + UsageEventSink protocol, with tracker,
in-memory and composite sinks
providers/openai_compat.py, providers/anthropic.py
publish a UsageEvent instead of writing to the
usage tracker themselves
core/usage_tracker.py adds current_context() so a sink can borrow and
restore a thread's attribution
R03-T01 — Contract tests
tests/contracts/test_providers.py parametrises over every provider in the registry: chat()
signature, canonical assistant message, normalised tool calls, response closed, tool schema
translation, ProviderError, list_models/test_connection, one UsageEvent per turn.
Test infrastructure fix (required to verify any of the above): tests/conftest.py used to put
the repository's PARENT directory on sys.path, so `import cowork_local.*` resolved against
whichever sibling folder happened to carry that name — on a dev machine, an unrelated older
checkout. The suite reported green while exercising different code. The conftest now binds
this checkout to the cowork_local name in sys.modules.
Verification
pytest tests/ 236 passed in ~1.8s (102 before this change)
scripts/check_imports.py PASS, 0 forbidden imports in domain/ and application/
new production files largest is 288 lines, all under the 400 LOC ceiling
new tests 134 (50 contract, 70 unit, 14 integration), all offline
scripts/run_quality_gate.py does not exist yet (R10-T02), so DoD item 7 was covered by
check_imports.py plus the full suite.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
lamhv7andClaude Sonnet 5
duylh19andClaude Opus 5
anhtnm1andClaude Opus 5
