duylh19andClaude Opus 5
3665135c38
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>
Cowork Local
Cowork Local is the internal AI cowork desktop platform owned by the Cowork Team. It provides the Cowork runtime, workspace and agent experiences, MCP/connectors, security controls, and model routing foundation.
The Cowork Team owns this product and its stable branch. The FSG AI Core Team contributes selected reusable capabilities through branches and Pull Requests; it is not the owner or final merger of this repository.
Quick start
The imported application is a Python/PySide6 package. Run it from the directory that contains cowork_local:
python -m cowork_local
The source snapshot does not include a complete runtime dependency manifest. Use the Cowork Team's supported runtime environment until that packaging contract is documented. The reliable automated test surface currently checked by CI is:
python -m pip install -r cowork_local/requirements-test.txt
python -m pytest cowork_local/tests -q
When already inside this repository, run python -m pytest tests -q.
Configuration and runtime data live under ~/.cowork_local/. Provider keys and local unlock codes must be supplied through environment variables or an approved secret manager; see .env.example.
Contributing
Start with START_CONTRIBUTING.md, then read CONTRIBUTING.md. Core AI task execution remains in fsg-ai-core-assets; source changes are reviewed as Pull Requests in this repository.
Security concerns should follow SECURITY.md. Ownership and completion rules are documented under docs/governance/.