feat(R08): split ScheduleTaskTab, FolderTab, DashboardTab, StructureGraphView

Team Hoa, EPIC R08 (UI/Application Separation) - Team Hoa scope only
(R08-T11 -> T14; R08-T01->T10 belong to Team Duy/Team Nam).

- R08-T11: ui/schedule_task_tab.py (795 lines) -> presentation/scheduling/
  {kanban_board_widget,calendar_view_widget,ai_task_creator_dialog,
  ai_task_import_dialog,run_history_dialog}.py + schedule_task_tab.py
  shell. Kanban CRUD/drag-drop now goes through
  application/scheduling/task_application_service.py (R07-T04) instead of
  ~30 lines of inline if/elif per drag target.
- R08-T12: ui/folder_tab.py (1587 lines, the largest of the four) ->
  presentation/folder/{workspace_file_tree,document_preview_manager,
  code_editor,office_document_renderer,ai_file_editor_dialog,
  ai_edit_model_resolver,ai_edit_pipeline}.py + folder_tab.py shell.
  Closes the R06-T05 loop: FileWorkspaceService existed since R06 with
  zero production call sites (confirmed by grep); every plain-text write
  (save/create/write_content) now goes through it, gaining path
  containment and a Python-syntax warning the original code never had.
  Pure helpers (_read_text, _is_probably_text, _pptx_available,
  _split_code_block, _parse_ai_output) moved to
  application/workspaces/{file_preview_helpers,ai_edit_output}.py.
- R08-T13: ui/dashboard_tab.py (437 lines) -> presentation/dashboard/
  {token_usage_card_widget,usage_chart_widget,habits_widget}.py +
  dashboard_tab.py shell, backed by a new
  application/monitoring/dashboard_query_service.py (pricing/period/
  summary queries the three widgets used to each recompute separately).
  Directory-ownership note left in the checklist for Team Nam.
- R08-T14: ui/structure_graph_view.py (1035 lines) ->
  presentation/graph/{graph_scene_items,graph_renderer,
  graph_messages_view,graph_qa_widget}.py + structure_graph_view.py
  shell. Extraction helpers (_pdf_to_markdown, _extract_file_contents)
  moved to application/workspaces/graph_index_service.py (pure Python).
  Renderer and Q&A panel talk only through signals
  (node_selected/graph_rendered/raw_json_ready/project_changed) - neither
  imports the other.
- presentation/shared/web_engine_support.py: HAS_WEB_ENGINE, previously
  duplicated (folder_tab imported it FROM structure_graph_view.py) - now
  one shared flag instead of one screen importing another screen's module.

All four old ui/*.py files deleted; app.py and ui/workspace_tab.py updated
to the new import paths (each god-file only had 1-2 real construction
sites, so import sites were updated directly rather than kept as a
strangler-fig shim - unlike core/tools.py at R05, which had dozens).

pytest: 377 pass (+94 vs the R07 baseline of 328; same 4 pre-existing
failures as the R05/R06 baseline, unrelated to this work).
scripts/check_imports.py: PASS. python -c "import cowork_local.app": OK.
Every new file < 400 lines (largest: graph_renderer.py, 391).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

presentation/folder/ai_edit_model_resolver.py

@@ -0,0 +1,248 @@
+"""AiEditModelResolver — model picker + Auto Model Routing + image-model
+discovery for the AI-Edit panel (R08-T12, extracted from
+``ui/folder_tab.py::FolderTab``, lines 802-1036/911-961 of the original
+1587-line file: ``refresh_ai_models``, ``_scan_all_image_models``,
+``_ai_provider``, ``_ai_apply_routing``, ``_confirm_routing_switch``,
+``_ai_image_model``, ``_maybe_suggest_image_model``,
+``_suggest_cross_provider_image``).
+
+A plain (non-Qt-widget) helper composed BY
+``ai_file_editor_dialog.py::AiFileEditorDialog`` — this is genuinely a
+distinct concern (which provider/model answers THIS run) from the panel's
+send/plan/edit orchestration, and splitting it out is also what keeps
+``ai_file_editor_dialog.py`` under the 400-line cap.
+"""
+from __future__ import annotations
+
+from typing import Any, List, Optional, Tuple
+
+from cowork_local.core.worker import AgentWorker
+from cowork_local.i18n import tr
+
+
+class AiEditModelResolver:
+    """Owns the AI-edit model combo's contents and every "which provider/
+    model should THIS run use" decision — independent of the Cowork/Settings
+    agent, exactly like the original panel's own picker was.
+
+    Args:
+        ctx: ``AppContext``.
+        model_combo: the ``QComboBox`` populated by :meth:`refresh`.
+        on_status: ``(text) -> None`` — posts a status line into the AI
+            chat (production passes ``ai_chat.add_status``).
+        confirm_switch: ``(self, decision, timeout) -> bool`` — the Qt
+            confirm dialog for Manual routing mode (kept as a callback so
+            this class never imports a dialog itself).
+    """
+
+    def __init__(self, ctx, model_combo, on_status, confirm_switch) -> None:
+        self.ctx = ctx
+        self._combo = model_combo
+        self._on_status = on_status
+        self._confirm_switch = confirm_switch
+        self._models: List[str] = []
+        self._models_provider = ""
+        self._all_image_models: List[Tuple[str, str]] = []   # [(provider_key, model)]
+        self._img_scan_worker = None
+        self._pending_img_suggest = False
+        self._routed_provider: Optional[str] = None
+        self._routed_model: Optional[str] = None
+
+    @property
+    def models(self) -> List[str]:
+        return self._models
+
+    @property
+    def models_provider(self) -> str:
+        return self._models_provider
+
+    @property
+    def routed_provider(self) -> Optional[str]:
+        """The provider :meth:`apply_routing` switched to for the current
+        run, or ``None`` when it didn't switch (routing off/declined)."""
+        return self._routed_provider
+
+    @property
+    def routed_model(self) -> Optional[str]:
+        return self._routed_model
+
+    def should_refresh(self) -> bool:
+        """True on first open, or when the active provider changed since
+        the model list was last loaded — a stale list would resolve a pick
+        to the wrong/default model at the new endpoint."""
+        return self._combo.count() <= 1 or self._models_provider != self.ctx.config.active_provider
+
+    def refresh(self) -> None:
+        """Fetch the active provider's model list (background) into the
+        picker. Also proactively scans ALL providers for image-capable
+        models so a suggestion is ready the moment one is needed."""
+        name = self.ctx.config.active_provider
+        setting_model = self.ctx.config.provider_conf(name).get("model", "")
+
+        def job(worker):
+            prov = self.ctx.build_provider_for(name)
+            try:
+                models = list(getattr(prov, "list_models", lambda: [])() or [])
+            except Exception:  # noqa: BLE001
+                models = []
+            return {"models": models}
+
+        def done(res):
+            fetched = list(res.get("models", []))
+            # Always offer the Settings-configured model as an explicit
+            # choice, even when the provider can't list models.
+            self._models = list(dict.fromkeys(
+                ([setting_model] if setting_model else []) + [m for m in fetched if m]))
+            self._models_provider = name
+            cur = self._combo.currentData()
+            self._combo.blockSignals(True)
+            self._combo.clear()
+            self._combo.addItem(tr("folder.ai_model_auto"), None)
+            for m in self._models:
+                self._combo.addItem(m, m)
+            idx = self._combo.findData(cur)
+            self._combo.setCurrentIndex(idx if idx >= 0 else 0)
+            self._combo.blockSignals(False)
+
+        w = AgentWorker(job)
+        w.finished_ok.connect(done)
+        self._models_worker = w
+        w.start()
+        self._scan_all_image_models()
+
+    def _scan_all_image_models(self, then_suggest: bool = False) -> None:
+        if self._img_scan_worker is not None:
+            if then_suggest:
+                self._pending_img_suggest = True
+            return
+        providers = dict(self.ctx.config.data.get("providers", {}))
+        candidates = [k for k, c in providers.items()
+                      if (c.get("base_url") or c.get("api_key"))]
+
+        def job(worker):
+            from cowork_local.core import image_gen
+            found = []
+            for key in candidates:
+                try:
+                    prov = self.ctx.build_provider_for(key)
+                    models = list(getattr(prov, "list_models", lambda: [])() or [])
+                except Exception:  # noqa: BLE001 - a broken provider must not block the scan
+                    models = []
+                for m in models:
+                    if image_gen.looks_like_image_model(m):
+                        found.append((key, m))
+            return {"found": found}
+
+        def done(res):
+            self._img_scan_worker = None
+            self._all_image_models = list(res.get("found", []))
+            if self._pending_img_suggest:
+                self._pending_img_suggest = False
+                self._suggest_cross_provider_image()
+
+        w = AgentWorker(job)
+        w.finished_ok.connect(done)
+        w.failed.connect(self._on_image_scan_failed)
+        self._img_scan_worker = w
+        if then_suggest:
+            self._pending_img_suggest = True
+        w.start()
+
+    def _on_image_scan_failed(self, _err) -> None:
+        self._img_scan_worker = None
+
+    def provider(self) -> Any:
+        """Build a provider using the model chosen in the picker ('(auto)'
+        -> the active provider's default), or an Auto/Manual routing
+        override set by :meth:`apply_routing` for the current run."""
+        if self._routed_provider or self._routed_model:
+            provider = self._routed_provider or self.ctx.config.active_provider
+            return self.ctx.build_provider_for(provider, self._routed_model or None)
+        model = self._combo.currentData()
+        return self.ctx.build_provider_for(self.ctx.config.active_provider, model or None)
+
+    def apply_routing(self, instruction: str) -> None:
+        """Auto Model Routing for the AI-Edit surface (always a CODING
+        task). Sets the routing override :meth:`provider` honours."""
+        from cowork_local.core.routing.models import TaskType
+
+        self._routed_provider = None
+        self._routed_model = None
+        cur_provider = self.ctx.config.active_provider
+        picked = self._combo.currentData()
+        cur_model = picked or self.ctx.config.provider_conf(cur_provider).get("model", "")
+        decision = self.ctx.routing_application().route_turn(
+            "ai_edit", instruction, cur_provider, cur_model,
+            task_type=TaskType.CODING, confirm=self._confirm_switch,
+        )
+        if not decision.switched:
+            return
+        self._routed_provider, self._routed_model = decision.target()
+        self._on_status(tr(
+            "routing.switched_notice",
+            model=decision.model, task=decision.task_type,
+            gain=f"{decision.score_gain:.2f}"))
+
+    _IMAGE_WORDS = ("image", "picture", "photo", "illustration", "icon", "logo", "diagram",
+                    "ảnh", "hình", "minh họa", "biểu tượng", "画像", "イラスト")
+
+    def maybe_suggest_image_model(self, instruction: str) -> None:
+        """If the request looks image-related, suggest a suitable image
+        model BEFORE running — active provider first, then ALL providers."""
+        from cowork_local.core import image_gen
+        low = (instruction or "").lower()
+        if not any(w in low for w in self._IMAGE_WORDS):
+            return
+        picked = self._combo.currentData()
+        if picked and image_gen.looks_like_image_model(picked):
+            return
+        local = image_gen.suggest_image_model(self._models)
+        if local:
+            self._on_status(tr("folder.ai_image_suggest", model=local))
+            return
+        if self._all_image_models:
+            self._suggest_cross_provider_image()
+        elif self._img_scan_worker is not None:
+            self._pending_img_suggest = True
+        else:
+            self._scan_all_image_models(then_suggest=True)
+
+    def _suggest_cross_provider_image(self) -> None:
+        from cowork_local.config import PROVIDER_LABELS
+        if not self._all_image_models:
+            picked = self._combo.currentData()
+            if picked:
+                self._on_status(tr("folder.ai_image_use_selected", model=picked))
+            else:
+                self._on_status(tr("folder.ai_image_none"))
+            return
+        seen, lines = set(), []
+        for key, model in self._all_image_models:
+            tag = (key, model)
+            if tag in seen:
+                continue
+            seen.add(tag)
+            lines.append(f"• {model}  ({PROVIDER_LABELS.get(key, key)})")
+            if len(lines) >= 5:
+                break
+        self._on_status(tr("folder.ai_image_suggest_all") + "\n" + "\n".join(lines))
+
+    def image_model(self) -> Tuple[Optional[str], Optional[str], Optional[str]]:
+        """Resolve ``(model, base_url, api_key)`` for image generation,
+        searching ALL providers — see the module docstring for priority
+        order (picked model if image-capable -> active provider's image
+        model -> any other provider's -> fall back to the picked model)."""
+        from cowork_local.core import image_gen
+        picked = self._combo.currentData()
+        if picked and image_gen.looks_like_image_model(picked):
+            return picked, None, None
+        local = image_gen.suggest_image_model(self._models)
+        if local:
+            return local, None, None
+        for key, model in self._all_image_models:
+            conf = self.ctx.config.provider_conf(key)
+            return model, (conf.get("base_url") or None), (conf.get("api_key") or None)
+        return (picked or None), None, None
+
+
+__all__ = ["AiEditModelResolver"]