7e11e9676dcb4b650719577add29bf5afd5c398a
10
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 huongltt35
|
f8e22f5f5b | merge: merge origin/gamma/refactor and origin/feature/teamhoa/r05-r06 into feature/delta-team/epic-R04 | ||
  duylh19andClaude Opus 5
|
3665135c38 |
feat(R04): run every Cowork turn through ConversationApplicationService
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> |
||
|
duylh19andClaude Opus 5
|
19e6b4deb2 |
feat(R04): add the immutable turn snapshot and typed agent event stream
R04-T01 — `domain/agents/conversation_execution_request.py`: a frozen
snapshot of everything one chat turn needs. Turn inputs previously lived in a
closure plus a 15-key ctx dict inside `ui/chat_panel.py::_start_turn`, and the
worker thread kept reading the widget back while it ran, so every later click
was visible to work already in flight. The request also owns the prompt
composition rules (instruction prefix separator, session notes, model-switch
review note) that were inline in that closure.
R04-T02 — `domain/agents/agent_event.py`: 13 frozen event types replacing the
untyped `{"type": ...}` dicts, whose only specification was the 130-line
if/elif chain in `_on_event`. Each event serialises back to the exact legacy
dict, so the presentation layer is untouched; `agent_event_codec.py` parses the
other way and is a temporary shim, isolated so R08 can delete it in one move.
`assistant_done` is deliberately NOT the end of a turn (it fires once per
provider call), so it maps to AssistantMessageCompletedEvent while the new
TurnCompletedEvent reports the turn itself.
R04-T03 (part) — `domain/agents/agent_result.py`: one named outcome for a
finished turn, replacing the message list / 3-tuple / reconstructed-from-side-
effects trio the three callers each read differently.
Verification: 66 tests. Beyond the unit tests,
`tests/integration/test_agent_event_bridge.py` runs the REAL `run_cowork` loop
offline and asserts every dict it emits is recognised and round-trips
byte-for-byte — a guard against an event type nobody modelled or a key whose
meaning silently drifted.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
||
 anhtnm1andClaude Opus 5
|
f61c5474b0 |
feat(R03): unify model routing and centralise the provider catalogue
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>
|
||
 vudt15andClaude Sonnet 5
|
cf542b7416 |
feat(R06): workspace session snapshot, atomic persistence, history-dir race fix
EPIC R06 (Team Hoa) - workspace/filesystem isolation, no cross-project
mutable state.
R06-T01 domain/workspaces/workspace_session.py
WorkspaceSession - project_id/workspace_root/sandbox_dir/allowed_paths
frozen snapshot + is_allowed(path), same "capture once at submit time"
shape as R04's ConversationExecutionRequest.
R06-T02 infrastructure/persistence/json/{atomic_write,workspace_repository_impl,conversation_repository_impl}.py
Real bug fixed: core/projects.py::save_project and core/history.py's
save_conversation/rename_conversation/set_pinned did a plain
path.write_text(json.dumps(...)) - two syscalls, no atomicity. A crash
between them leaves a half-written file that load_project/load_conversation
then silently treat as "missing". All four now write through
atomic_write.write_json (temp file + os.replace). WorkspaceRepository/
ConversationRepository are thin object-shaped facades over the same
(now-atomic) functions, for future application-layer callers.
NOTE: atomic_write.py is deliberately NOT named atomic_json_file.py -
R02-T01 (Team Nam) claims that filename for the same purpose app-wide;
see the checklist for the consolidation TODO.
R06-T03 infrastructure/filesystem/execution_workspace.py
ExecutionWorkspace names the output_dir/scratch_dir split that already
exists (core/chat_agent.py's flat workspace_root/.scratch) - does not
move anything.
R06-T04 ui/chat_panel.py
The actual race: ChatPanel._persist_session (saves a BACKGROUND turn's
conversation) resolved its save directory via a live
self.ctx.config.history_dir() read at save time. ui/workspace_tab.py::
_load_current mutates that same config field on every project switch, so
a turn still running when the user switched projects got saved into the
NEW project's history folder. Fixed by adding "home_history_dir" to the
per-turn ctx dict (same "home_*" snapshot convention already used for
session id/messages/title), captured at submit time. Verified with a real
offscreen-Qt test, not just a unit double:
tests/integration/test_history_dir_race.py.
R06-T05 application/workspaces/file_workspace_service.py
FileWorkspaceService - the File Explorer / AI Editor entry point for the
same safe read/write/edit operations the agent tool loop has, by calling
core/tools.py::execute_tool directly (same dispatch, same ToolContext
containment, same audit log) rather than reimplementing any of it.
New tests: tests/unit/test_workspace_session.py,
test_atomic_write_and_repositories.py, test_execution_workspace.py,
test_file_workspace_service.py, tests/integration/test_history_dir_race.py
(29 new tests, incl. 2 real offscreen-Qt integration tests).
Suite: 283 passed, 4 pre-existing failures unrelated to R05/R06 (see
checklist). check_imports: PASS. All new files < 400 LOC.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
||
|
vudt15andClaude Sonnet 5
|
ae4fe72b2e |
feat(R05): tool capability registry, unified policy gateway, MCP lifecycle manager
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>
|
||
|
huongltt35
|
10739f19aa | breakdown folder tree for epic R01 | ||
|
anhtnm1andClaude Opus 5
|
a53163ebaf |
feat(R04): immutable turn snapshot, typed agent events, conversation service
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> |
||
|
anhtnm1andClaude Opus 5
|
96bec976e7 |
feat(R03): unify provider catalogue, routing decisions and usage telemetry
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
|
bbc09f628a |
feat(R01): architecture foundation, offline fakes and characterization net
EPIC R01 (Team Duy) - safety net before the parallel refactor starts.
R01-T01 docs/architecture/ADR-001-layered-architecture.md
4-tier boundaries, allowed dependency directions, invariants I1-I6 and
the strangler-fig migration strategy.
R01-T02 tests/fakes/{fake_provider,fake_tool_executor}.py
Scripted, offline Provider and extra-tool executor doubles.
R01-T03 scripts/check_imports.py
AST-based Clean Architecture Guard (CASAN Check 3). Also covers relative
imports and function-local imports; ASCII-only output for cp932 consoles.
R01-T04 tests/characterization/test_run_cowork.py
13 snapshot tests pinning run_cowork's current observable contract before
EPIC R04 moves its orchestration into application/.
R01-T05 docs/architecture/dormant-code.md
Import-graph scan: 43 unimported modules verified down to 6 genuinely
dormant items (~1887 LOC); the rest run via subprocess/CLI entry points.
tests/conftest.py binds `cowork_local` to THIS checkout by absolute path -
previously sys.path discovery could import a sibling checkout and the suite
would silently test the wrong code.
Suite: 104 passed, 1.08s (2 pre-existing failures in test_config_security.py
remain - config.py still ships a hardcoded default password, EPIC R02/Team Nam).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|