Feature/delta team/epic r04 (#7)

## Summary

epic r04 - begin refactor

## Change Type

- [x] Cowork feature
- [ ] Bug fix
- [ ] Core AI contribution
- [ ] Test / hardening
- [ ] Performance
- [ ] Documentation

## Related Work

Cowork Task:

Core Repo: http://34.143.229.138/gitea-admin/fsg-ai-core-assets

Core AI Issue:

Core Task:

Related PR:

## Scope

What is intentionally included?

What is intentionally NOT included?

## Validation

- [ ] Unit tests
- [ ] Integration tests
- [ ] Manual verification
- [ ] Regression check

Commands / evidence:

## Security Impact

Permission / credential / network / customer data impact:

## Compatibility

- [ ] No breaking change
- [ ] Breaking change documented

## Reviewer Notes

Anything Cowork reviewers should pay attention to.

---------

Co-authored-by: Anh Tran Nguyen Minh <anhtnm1@fpt.com>
Co-authored-by: Huong Le Thi Thien <huongltt35@fpt.com>
Co-authored-by: Nam Pham Dinh Thanh <nampdt@fpt.com>
Co-authored-by: Vu Dam Tuan <vudt15@fpt.com>
Co-authored-by: Hiep Ha Van <hiephv3@fpt.com>
Co-authored-by: Lam Hoang Van <lamhv7@fpt.com>
Reviewed-on: #7
Co-authored-by: Duy Le Huu <duylh19@fpt.com>

application/workspaces/__init__.py

@@ -0,0 +1,17 @@
+"""Workspace file operations for non-agent-loop callers (EPIC R06, R08)."""
+
+from .ai_edit_output import parse_ai_output, split_code_block
+from .file_preview_helpers import is_probably_text, pptx_available, read_text
+from .file_workspace_service import FileWorkspaceService
+from .graph_index_service import extract_file_contents, pdf_to_markdown
+
+__all__ = [
+    "FileWorkspaceService",
+    "read_text",
+    "is_probably_text",
+    "pptx_available",
+    "split_code_block",
+    "parse_ai_output",
+    "pdf_to_markdown",
+    "extract_file_contents",
+]

application/workspaces/ai_edit_output.py

@@ -0,0 +1,40 @@
+"""Parse an AI file-edit reply into its parts (R08-T12, moved out of
+``ui/folder_tab.py`` — that file's module-level ``_split_code_block``/
+``_parse_ai_output``, lines 1536-1562 of the original 1587-line file). Pure
+string parsing, no Qt — used by ``presentation/folder/ai_file_editor_dialog.py``
+to turn a model's raw reply into a proposed edit.
+"""
+from __future__ import annotations
+
+import re
+from typing import List, Optional, Tuple
+
+
+def split_code_block(text: str) -> Tuple[Optional[str], str]:
+    """Split an AI reply into ``(file_content, summary)``. ``file_content``
+    is the first fenced code block (the edited file); ``summary`` is any
+    prose before it. Returns ``(None, text)`` when there's no code block."""
+    m = re.search(r"```[^\n]*\n(.*?)```", text or "", re.DOTALL)
+    if not m:
+        return None, (text or "")
+    return m.group(1), (text[:m.start()].strip())
+
+
+def parse_ai_output(text: str) -> Tuple[Optional[str], Optional[str], str, List[Tuple[str, str]]]:
+    """Parse an AI edit reply into ``(target, content, summary, image_gens)``.
+    ``FILE: <path>`` names a NEW file to create; ``IMAGE_GEN: <prompt> =>
+    <path>`` lines request generated illustration images (relative paths)."""
+    content, summary = split_code_block(text)
+    target = None
+    m = re.search(r"(?mi)^\s*FILE:\s*(.+?)\s*$", text or "")
+    if m:
+        target = m.group(1).strip().strip("`\"'")
+    image_gens = []
+    for gm in re.finditer(r"(?mi)^\s*IMAGE_GEN:\s*(.+?)\s*=>\s*(\S+)\s*$", text or ""):
+        image_gens.append((gm.group(1).strip(), gm.group(2).strip().strip("`\"'")))
+    # Strip the directive lines out of the shown summary.
+    summary = re.sub(r"(?mi)^\s*(FILE|IMAGE_GEN):\s*.+?$", "", summary).strip()
+    return target, content, summary, image_gens
+
+
+__all__ = ["split_code_block", "parse_ai_output"]

application/workspaces/file_preview_helpers.py

@@ -0,0 +1,62 @@
+"""Pure helpers for previewing a file (R08-T12, moved out of
+``ui/folder_tab.py`` — that file's module-level functions
+``_read_text``/``_is_probably_text``/``_pptx_available``, lines 1519-1533 and
+1565-1587 of the original 1587-line file). No Qt, no widget state — the
+"is this file text? is pptx editing available?" questions the preview
+manager asks before it decides how to render something.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+
+_PPTX_READY = None   # cached: pptx-editing library available (after auto-install)
+
+
+def pptx_available() -> bool:
+    """True when python-pptx is importable. If it's MISSING, auto-download &
+    install it (via deps.ensure_module) so pptx editing 'just works' — cached
+    so the (one-time) install is attempted only once."""
+    global _PPTX_READY
+    if _PPTX_READY is None:
+        try:
+            from cowork_local.core.deps import ensure_module
+
+            _PPTX_READY = ensure_module("pptx", "python-pptx") is not None
+        except Exception:  # noqa: BLE001
+            _PPTX_READY = False
+    return _PPTX_READY
+
+
+def read_text(path: str) -> str:
+    """Đọc tệp dạng văn bản, thay ký tự hỏng thay vì ném lỗi; không đọc được thì
+    trả về chuỗi rỗng.
+    """
+    try:
+        return Path(path).read_text(encoding="utf-8", errors="replace")
+    except OSError as exc:
+        return f"[could not read file: {exc}]"
+
+
+def is_probably_text(path: str) -> bool:
+    """Đoán tệp này có phải văn bản không, bằng cách tìm byte NUL trong phần đầu.
+
+    Đoán sai theo hướng "là văn bản" sẽ hiện một màn hình ký tự rác, nên phép
+    thử cố tình bảo thủ.
+    """
+    try:
+        with open(path, "rb") as f:
+            chunk = f.read(4096)
+    except OSError:
+        return False
+    if b"\x00" in chunk:
+        return False
+    try:
+        chunk.decode("utf-8")
+        return True
+    except UnicodeDecodeError:
+        # Latin-ish text still edits fine via errors="replace"; only reject on
+        # a hard binary signal (NUL above), so most source files pass.
+        return True
+
+
+__all__ = ["pptx_available", "read_text", "is_probably_text"]

application/workspaces/file_workspace_service.py

@@ -0,0 +1,84 @@
+"""FileWorkspaceService - the safe file operations File Explorer and the AI
+File Editor need, outside the agent tool loop (R06-T05).
+
+``ui/folder_tab.py`` (File Explorer) and the AI File Editor dialog need the
+exact same guarantees the agent's tools already have — path containment
+inside the workspace, precise context-anchored edits, syntax warnings on a
+bad Python write — but today that logic only exists wired to a model's tool
+call (``core/tools.py::execute_tool``). A UI action that isn't a tool call
+(browsing the tree, applying an AI-suggested diff from a review dialog) has
+no equivalent entry point of its own.
+
+This service IS that entry point. It reuses ``core/tools.py::execute_tool``
+verbatim - same dispatch table, same ``ToolContext`` containment check, same
+audit-log entry, same Python-syntax warning on write/edit - rather than
+re-implementing any of it, so a fix to one path fixes both. It only adds the
+:class:`~domain.workspaces.workspace_session.WorkspaceSession` seam: which
+workspace root a call is scoped to is decided by the session, not by
+whichever folder a widget happens to have open.
+"""
+from __future__ import annotations
+
+from typing import Any, Dict
+
+
+class FileWorkspaceService:
+    """File operations scoped to one :class:`WorkspaceSession`.
+
+    Read-only by name (``list_tree``/``read_preview``) vs. writing
+    (``write_file``/``apply_edit``) mirrors the same READ/WRITE split
+    ``domain/tools/tool_registry.py`` uses for the agent's own tools - a
+    caller that only wants to browse never accidentally has write access.
+    """
+
+    def __init__(self, session) -> None:  # WorkspaceSession - see module docstring
+        """Nhận một ``WorkspaceSession`` — mọi đường dẫn về sau đều bị nó chặn trong
+        phạm vi cho phép.
+        """
+        self._session = session
+
+    def list_tree(self, rel: str = ".") -> Dict[str, Any]:
+        """Entries at ``rel`` (default: the workspace root)."""
+        return self._execute("list_dir", {"path": rel})
+
+    def read_preview(self, rel: str) -> Dict[str, Any]:
+        """A text file's content (truncated by
+        ``infrastructure/filesystem/file_tools.py::MAX_READ_BYTES``, same as
+        the agent's ``read_file`` tool)."""
+        return self._execute("read_file", {"path": rel})
+
+    def write_file(self, rel: str, content: str) -> Dict[str, Any]:
+        """Create or fully overwrite ``rel``."""
+        return self._execute("write_file", {"path": rel, "content": content})
+
+    def apply_edit(self, rel: str, old_string: str, new_string: str,
+                   replace_all: bool = False) -> Dict[str, Any]:
+        """Replace an exact snippet in an existing file - the same
+        context-anchored algorithm the agent's ``edit_file`` tool uses, so an
+        AI-suggested diff applies with the same precision and the same
+        "old_string not found / ambiguous" failure messages either path
+        would give the caller."""
+        return self._execute("edit_file", {
+            "path": rel, "old_string": old_string, "new_string": new_string,
+            "replace_all": replace_all,
+        })
+
+    # -- internals --------------------------------------------------------- #
+    def _tool_context(self):
+        """A ``ToolContext`` scoped to this session's workspace root.
+        ``flatten_writes=False`` (unlike Cowork's agent context) - File
+        Explorer must preserve whatever subfolder structure the user is
+        actually browsing, not collapse every write into the root."""
+        from cowork_local.infrastructure.filesystem.tool_context import ToolContext
+
+        return ToolContext(self._session.workspace_root, flatten_writes=False)
+
+    def _execute(self, name: str, args: Dict[str, Any]) -> Dict[str, Any]:
+        """Dispatch through ``core/tools.py::execute_tool`` - see the module
+        docstring for why this delegates instead of reimplementing."""
+        from cowork_local.core.tools import execute_tool
+
+        return execute_tool(self._tool_context(), name, args)
+
+
+__all__ = ["FileWorkspaceService"]

application/workspaces/graph_index_service.py

@@ -0,0 +1,91 @@
+"""Temporary file-content extraction for Graph-RAG Q&A (R08-T14, moved out
+of ``ui/structure_graph_view.py`` — that file's module-level
+``_pdf_to_markdown``/``_extract_file_contents``, lines 964-1034 of the
+original 1035-line file). Runs inside the ask worker's job function so the
+answer is synthesized from real file content, not just the graph structure.
+
+Pure Python: no Qt. Best-effort throughout (never raises) — a failed
+extraction degrades to "no content for this file", not a broken Q&A turn.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple
+
+
+def pdf_to_markdown(pdf_path: str, out_dir: str) -> Optional[str]:
+    """Convert a PDF to Markdown with opendataloader-pdf when available
+    (richer structure than a plain text dump). Best-effort — returns None
+    if the package isn't installed or the call fails, so the caller falls
+    back to ``core/doc_extract.py``."""
+    try:
+        import opendataloader_pdf  # optional; auto-installed elsewhere if present
+    except Exception:  # noqa: BLE001
+        try:
+            from cowork_local.core.deps import ensure_module
+            if ensure_module("opendataloader_pdf", "opendataloader-pdf") is None:
+                return None
+            import opendataloader_pdf  # noqa: F811
+        except Exception:  # noqa: BLE001
+            return None
+    out = Path(out_dir)
+    out.mkdir(parents=True, exist_ok=True)
+    for call in (
+        lambda: opendataloader_pdf.convert(input_path=[str(pdf_path)], output_dir=str(out),
+                                           generate_markdown=True),
+        lambda: opendataloader_pdf.convert(input_path=str(pdf_path), output_dir=str(out)),
+        lambda: opendataloader_pdf.convert(str(pdf_path), str(out)),
+    ):
+        try:
+            call()
+            break
+        except TypeError:
+            continue
+        except Exception:  # noqa: BLE001
+            return None
+    mds = list(out.rglob(Path(pdf_path).stem + "*.md")) or list(out.rglob("*.md"))
+    for md in mds:
+        try:
+            return md.read_text(encoding="utf-8", errors="replace")
+        except OSError:
+            continue
+    return None
+
+
+def extract_file_contents(paths: List[str], cache: Dict[str, str], tmp_dir: str,
+                          max_files: int = 15, max_total: int = 120_000
+                          ) -> Tuple[str, Dict[str, str]]:
+    """Read the ACTUAL content of ``paths`` (PDF -> markdown via
+    opendataloader when available, else ``doc_extract`` for office/pdf/
+    text). Returns ``(block, cache)`` — ``block`` is the concatenated
+    content for the prompt (bounded), ``cache`` maps path -> text for
+    reuse. Never raises."""
+    from cowork_local.core import doc_extract
+
+    cache = dict(cache or {})
+    parts, total = [], 0
+    for p in paths[:max_files]:
+        if total >= max_total:
+            break
+        text = cache.get(p)
+        if text is None:
+            try:
+                if Path(p).suffix.lower() == ".pdf":
+                    text = pdf_to_markdown(p, tmp_dir)
+                    if not text:
+                        text, _n = doc_extract.extract_text(p)
+                else:
+                    text, _n = doc_extract.extract_text(p)
+            except Exception:  # noqa: BLE001
+                text = ""
+            cache[p] = text or ""
+        text = cache.get(p) or ""
+        if not text:
+            continue
+        chunk = text[: max(0, max_total - total)]
+        total += len(chunk)
+        parts.append(f'--- {Path(p).name} ({p}) ---\n{chunk}')
+    return ("\n\n".join(parts), cache)
+
+
+__all__ = ["pdf_to_markdown", "extract_file_contents"]