refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)

* refactor: extract shared utils to break harness→app cross-layer imports

Move _validate_skill_frontmatter to src/skills/validation.py and
CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py.
This eliminates the two reverse dependencies from client.py (harness layer)
into gateway/routers/ (app layer), preparing for the harness/app package split.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: split backend/src into harness (deerflow.*) and app (app.*)

Physically split the monolithic backend/src/ package into two layers:

- **Harness** (`packages/harness/deerflow/`): publishable agent framework
  package with import prefix `deerflow.*`. Contains agents, sandbox, tools,
  models, MCP, skills, config, and all core infrastructure.

- **App** (`app/`): unpublished application code with import prefix `app.*`.
  Contains gateway (FastAPI REST API) and channels (IM integrations).

Key changes:
- Move 13 harness modules to packages/harness/deerflow/ via git mv
- Move gateway + channels to app/ via git mv
- Rename all imports: src.* → deerflow.* (harness) / app.* (app layer)
- Set up uv workspace with deerflow-harness as workspace member
- Update langgraph.json, config.example.yaml, all scripts, Docker files
- Add build-system (hatchling) to harness pyproject.toml
- Add PYTHONPATH=. to gateway startup commands for app.* resolution
- Update ruff.toml with known-first-party for import sorting
- Update all documentation to reflect new directory structure

Boundary rule enforced: harness code never imports from app.
All 429 tests pass. Lint clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* chore: add harness→app boundary check test and update docs

Add test_harness_boundary.py that scans all Python files in
packages/harness/deerflow/ and fails if any `from app.*` or
`import app.*` statement is found. This enforces the architectural
rule that the harness layer never depends on the app layer.

Update CLAUDE.md to document the harness/app split architecture,
import conventions, and the boundary enforcement test.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add config versioning with auto-upgrade on startup

When config.example.yaml schema changes, developers' local config.yaml
files can silently become outdated. This adds a config_version field and
auto-upgrade mechanism so breaking changes (like src.* → deerflow.*
renames) are applied automatically before services start.

- Add config_version: 1 to config.example.yaml
- Add startup version check warning in AppConfig.from_file()
- Add scripts/config-upgrade.sh with migration registry for value replacements
- Add `make config-upgrade` target
- Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services
- Add config error hints in service failure messages

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix comments

* fix: update src.* import in test_sandbox_tools_security to deerflow.*

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: handle empty config and search parent dirs for config.example.yaml

Address Copilot review comments on PR #1131:
- Guard against yaml.safe_load() returning None for empty config files
- Search parent directories for config.example.yaml instead of only
  looking next to config.yaml, fixing detection in common setups

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: correct skills root path depth and config_version type coercion

- loader.py: fix get_skills_root_path() to use 5 parent levels (was 3)
  after harness split, file lives at packages/harness/deerflow/skills/
  so parent×3 resolved to backend/packages/harness/ instead of backend/
- app_config.py: coerce config_version to int() before comparison in
  _check_config_version() to prevent TypeError when YAML stores value
  as string (e.g. config_version: "1")
- tests: add regression tests for both fixes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: update test imports from src.* to deerflow.*/app.* after harness refactor

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

backend/packages/harness/deerflow/skills/loader.py

@@ -0,0 +1,98 @@
+import os
+from pathlib import Path
+
+from .parser import parse_skill_file
+from .types import Skill
+
+
+def get_skills_root_path() -> Path:
+    """
+    Get the root path of the skills directory.
+
+    Returns:
+        Path to the skills directory (deer-flow/skills)
+    """
+    # loader.py lives at packages/harness/deerflow/skills/loader.py — 5 parents up reaches backend/
+    backend_dir = Path(__file__).resolve().parent.parent.parent.parent.parent
+    # skills directory is sibling to backend directory
+    skills_dir = backend_dir.parent / "skills"
+    return skills_dir
+
+
+def load_skills(skills_path: Path | None = None, use_config: bool = True, enabled_only: bool = False) -> list[Skill]:
+    """
+    Load all skills from the skills directory.
+
+    Scans both public and custom skill directories, parsing SKILL.md files
+    to extract metadata. The enabled state is determined by the skills_state_config.json file.
+
+    Args:
+        skills_path: Optional custom path to skills directory.
+                     If not provided and use_config is True, uses path from config.
+                     Otherwise defaults to deer-flow/skills
+        use_config: Whether to load skills path from config (default: True)
+        enabled_only: If True, only return enabled skills (default: False)
+
+    Returns:
+        List of Skill objects, sorted by name
+    """
+    if skills_path is None:
+        if use_config:
+            try:
+                from deerflow.config import get_app_config
+
+                config = get_app_config()
+                skills_path = config.skills.get_skills_path()
+            except Exception:
+                # Fallback to default if config fails
+                skills_path = get_skills_root_path()
+        else:
+            skills_path = get_skills_root_path()
+
+    if not skills_path.exists():
+        return []
+
+    skills = []
+
+    # Scan public and custom directories
+    for category in ["public", "custom"]:
+        category_path = skills_path / category
+        if not category_path.exists() or not category_path.is_dir():
+            continue
+
+        for current_root, dir_names, file_names in os.walk(category_path):
+            # Keep traversal deterministic and skip hidden directories.
+            dir_names[:] = sorted(name for name in dir_names if not name.startswith("."))
+            if "SKILL.md" not in file_names:
+                continue
+
+            skill_file = Path(current_root) / "SKILL.md"
+            relative_path = skill_file.parent.relative_to(category_path)
+
+            skill = parse_skill_file(skill_file, category=category, relative_path=relative_path)
+            if skill:
+                skills.append(skill)
+
+    # Load skills state configuration and update enabled status
+    # NOTE: We use ExtensionsConfig.from_file() instead of get_extensions_config()
+    # to always read the latest configuration from disk. This ensures that changes
+    # made through the Gateway API (which runs in a separate process) are immediately
+    # reflected in the LangGraph Server when loading skills.
+    try:
+        from deerflow.config.extensions_config import ExtensionsConfig
+
+        extensions_config = ExtensionsConfig.from_file()
+        for skill in skills:
+            skill.enabled = extensions_config.is_skill_enabled(skill.name, skill.category)
+    except Exception as e:
+        # If config loading fails, default to all enabled
+        print(f"Warning: Failed to load extensions config: {e}")
+
+    # Filter by enabled status if requested
+    if enabled_only:
+        skills = [skill for skill in skills if skill.enabled]
+
+    # Sort by name for consistent ordering
+    skills.sort(key=lambda s: s.name)
+
+    return skills