Hồi quy đã vá
-------------
F-12 Kéo–thả hoặc dán tệp vào ô chat ném NameError. R08 tách `_Input` sang
`chat_input_box.py` nhưng để `_paths_from_mime()` ở lại
`composer_widget.py`, nên hai hàm sự kiện Qt gọi một cái tên không tồn
tại. Bốn hàm dùng chung chuyển sang `composer_mime.py` — module thứ ba
là chỗ duy nhất không lặp lại được lỗi này. Đo lại: cả thả lẫn dán đều
gắn 1 tệp, khớp bản trước refactor.
F-01 Đổi provider thì bộ chọn model AI-Edit không làm gì. Hook cũ kiểm
`folder.ai_model_combo`, thuộc tính R08-T12 đã dời sang
`ai_panel.resolver`. Làm mới vô điều kiện, đúng như tab cũ: lần lấy đầu
tiên hỏng thì đổi provider chính là lúc phải thử lại.
F-07 Hàng chọn kỳ của Dashboard bị đẩy xuống dưới các thẻ số liệu. Hàng này
lọc CẢ BA thẻ con chứ không riêng biểu đồ, nên để nó nằm dưới là bắt
người dùng đọc con số trước khi thấy con số đó tính cho kỳ nào. Kèm
theo: `TokenUsageCardWidget` bị bỏ sót `setContentsMargins(0,0,0,0)`
mà hai thẻ con còn lại đã có, đẩy cả hàng thẻ lệch 9px.
`check_layout_geometry` nay khớp TỪNG BYTE với bản trước refactor.
F-11 Hai lớp khai trùng tên phương thức; Python giữ bản sau nên bản đầu là
mã chết. `co4e_tab.py::showEvent` bản đầu gọi `_narrow_guard.attach()`
và không bao giờ chạy.
Tách file (F-09)
----------------
Bốn file chạm trần 400 dòng, mỗi lần cắt ra một trách nhiệm thật:
graph_renderer.py -> graph_scene_builder.py + graph_export.py
co4e_workflow_service.py -> co4e_run_history.py
json_config_repository.py -> config_sections.py
agents_admin_tab.py -> shared/agent_kind_visuals.py
File cuối còn xoá 3 bản sao của hàm đã có trong `shared/formatters.py`,
giống hệt đến từng dòng — nay định dạng thời gian và avatar không lệch nhau
giữa các bảng Giám sát nữa.
Docstring
---------
41,6% -> 100% (3.478/3.478 định nghĩa production), kể cả module dormant và
phương thức dunder. Toàn bộ phần bổ sung viết bằng tiếng Việt; comment tiếng
Anh có sẵn giữ nguyên — dịch ngược là một đợt riêng.
Seam chưa nối dây (F-05)
------------------------
9 seam mang nhãn `SEAM · dựng <ngày>` kèm hai câu: được nối khi nào, và để
dormant thì hỏng gì. Ngày lấy từ lịch sử git, không phải hạn tự đặt. Gate O
đọc nhãn đó và nhắc khi quá 30 ngày.
859 test xanh · 4/4 cổng CASAN · 19/24 checker khớp từng byte bản cũ.
Co-Authored-By: Claude Opus 5 (1M context) <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 R05 (Team Hoa) - one security/approval path for every tool call.
R05-T01 domain/tools/{tool_descriptor,tool_registry}.py
ToolCapability (READ/WRITE/EXECUTE/NETWORK, composable) + ToolDescriptor +
ToolRegistry, replacing three independently-maintained gating lists
(core/tools.py::WRITE_TOOLS, code_agent.py's WRITE_TOOLS|MS365_WRITE_TOOLS,
chat_agent.py's literal ("run_command","install_package") tuple) with one
capability lookup.
R05-T02 infrastructure/filesystem/{file_tools,command_tools,fetch_tools,tool_context}.py
core/tools.py's execute_tool if/elif chain split into per-concern modules.
core/tools.py is now a strangler-fig shim: re-exports ToolContext/ToolError,
dispatches through a {name: handler} dict built from the split modules.
core/tools.py: 566 -> 291 lines.
R05-T03 application/conversations/tool_policy_gateway.py
ToolPolicyGateway.allow(name, gate, payload) - capability-driven ALLOW vs
ask-the-gate decision. Wired into both chat_agent.py::run_cowork and
code_agent.py::run_code, replacing their separate hand-rolled checks.
Verified equivalent to the old hardcoded sets by test.
R05-T04 (behavior change, not just refactor)
MCP/connector tools (core/mcp_client.py, core/ext_connectors.py) reached
chat_agent.py via extra_executor(name, args) with NO permission check at
all. They are now tagged with a conservative default capability
(WRITE|EXECUTE|NETWORK - no MCP tool self-declares risk) and routed through
the SAME ToolPolicyGateway as built-ins. When "confirm before running
commands" is on, MCP/connector calls now prompt like run_command already
did - a real gap closed, and a user-visible change worth calling out.
R05-T05 infrastructure/mcp/mcp_source_manager.py
McpToolSourceManager extracts the connection cache/lock/start-or-skip
lifecycle out of state.py::AppContext (_mcp_connections/_conn_lock) into a
standalone, directly-testable class. AppContext.build_mcp_tools and
_ms365_builtin_connection now call ensure()/stop(); _ext_connections
(unified Connectors) is out of scope for this task and keeps its own lock.
New tests: tests/unit/test_tool_registry_and_policy.py,
test_code_agent_tool_policy.py, test_cowork_extra_tool_policy.py,
test_mcp_source_manager.py (26 new tests).
Suite: 254 passed, 4 pre-existing failures unrelated to R05 (2 EPIC R02
config-security, 2 environment-dependent routing tests - see checklist).
check_imports: PASS. All new files < 400 LOC.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
EPIC R04 (Team Duy) - the turn lifecycle leaves the widget.
R04-T01 domain/agents/conversation_execution_request.py
Frozen snapshot of one turn, captured on the UI thread at submit time. The
job closure used to read widget/workspace state from inside the worker
thread, so a turn could run on a mix of submit-time and later state
depending on thread timing.
R04-T02 domain/agents/agent_event.py
13 frozen event types replacing untyped emit() dicts, with a two-way bridge
so existing widgets keep consuming the legacy shape until EPIC R08. Adds
TurnCompletedEvent - the end-of-turn signal the engine never had, which is
why a cancelled turn and a failed turn look identical to the UI today.
R04-T03 application/conversations/conversation_application_service.py
Runs a turn from a request and reports typed events. Never raises across the
worker boundary; TurnResult.raise_if_failed() preserves the existing
exception-based failure path. begin_turn()/execute_turn() expose the live
message list for callers that autosave history mid-run.
R04-T04 ui/cowork_tab.py::build_job -> snapshot + service.
R04-T05 core/task_executors.py::_run_agent -> same service (was a second,
slightly different assembly of the same call).
Caught while wiring the bridge: the first event vocabulary had no "notice"
event, so Agent Security warnings and auto-compaction notices would have been
silently swallowed. Added NoticeEvent plus a test that scans the engine sources
for emit() tags and fails when one has no typed counterpart.
New: tests/integration/ - real offscreen CoworkTab running a scripted turn end
to end (7 tests), including a characterisation of the extra provider call Agent
Security spends reviewing each request.
Suite: 225 passed, 2.74s. check_imports: PASS. All new files < 400 LOC.
2 pre-existing failures remain in test_config_security.py (EPIC R02/Team Nam).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
EPIC R03 (Team Duy) - one provider catalogue, one routing flow, one usage seam.
R03-T01 tests/contracts/test_providers.py
29 contract tests every provider must satisfy: canonical assistant message,
streamed text == returned content, reasoning never joins the answer, parsed
tool arguments, ProviderError for every failure. Real adapters exercised
offline by stubbing Provider._request.
R03-T02 domain/models/provider_descriptor.py
infrastructure/providers/provider_registry.py
Provider facts declared once (was split across providers/factory.py,
DEFAULT_CONFIG and PROVIDER_LABELS). ProviderRegistry.build() also stamps the
descriptor id onto the instance, so ollama/github_copilot/codex usage is no
longer all attributed to "openai_compat", and never mutates the caller config.
R03-T03 application/model_routing/routing_application_service.py
Pure-Python routing policy with four modes: Off, Auto, Manual and the new
Fallback (switch only AFTER the current model fails). Depends on a RoutingPort
protocol; production wires the existing core.routing engine underneath.
R03-T04/T05 ui/chat_panel.py, ui/co4e_tab.py, ui/folder_tab.py
Three near-identical routing copies (~40 lines each) replaced by a call to
ctx.routing_application() plus a confirm callback. Mode vocabulary now lives
in one place (normalize_mode/is_valid_mode) instead of four literal tuples.
R03-T06 infrastructure/telemetry/usage_sink.py
Token usage extracted from both providers into UsageEvent + UsageEventSink.
Estimation pinned against core.usage_tracker so no recorded number changes.
Also fixes a deadlock introduced while wiring AppContext: routing_application()
held _routing_lock and called routing(), which takes the same non-reentrant lock.
Suite: 186 passed, 1.22s. check_imports: PASS. All new files < 400 LOC.
2 pre-existing failures remain in test_config_security.py (EPIC R02/Team Nam).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
anhtnm1andClaude Opus 5
huongltt35
duylh19andClaude Opus 5
vudt15andClaude Sonnet 5