feat: enhance profile path resolution and add example profiles for better project adaptability

scripts/aiw/indexer.py

@@ -12,6 +12,7 @@ import argparse
 import hashlib
 import json
 import re
+import sys
 import time
 from dataclasses import dataclass
 from datetime import datetime, timezone
@@ -20,11 +21,13 @@ from typing import Any
 
 
 ROOT = Path(__file__).resolve().parents[2]
-INDEX_ROOT = ROOT / ".aiw" / "indexes"
 DEFAULT_PROFILE = "fidelity"
 MAX_CHARS = 1800
 OVERLAP_CHARS = 180
 
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+import profile as aiw_profile  # noqa: E402
+
 
 @dataclass(frozen=True)
 class Chunk:
@@ -37,15 +40,15 @@ class Chunk:
 
 
 def project_knowledge_dir(profile: str) -> Path:
-    profile_base = ROOT / "profiles" / profile
-    candidate = profile_base / "project-knowledge"
-    if candidate.exists():
-        return candidate
-    return ROOT / "project-knowledge"
+    return aiw_profile.knowledge_dir(profile, root=ROOT)
 
 
 def index_dir(profile: str) -> Path:
-    return INDEX_ROOT / profile
+    return aiw_profile.index_dir(profile, root=ROOT)
+
+
+def rel(path: Path) -> str:
+    return aiw_profile.relative_to_root(path, root=ROOT)
 
 
 def index_path(profile: str) -> Path:
@@ -120,13 +123,13 @@ def build_chunks(profile: str) -> list[Chunk]:
     chunks: list[Chunk] = []
     for path in iter_markdown_files(base):
         raw = path.read_text(encoding="utf-8", errors="replace")
-        rel = str(path.relative_to(ROOT))
+        rel_path = rel(path)
         digest = hashlib.sha256(raw.encode("utf-8", errors="replace")).hexdigest()
         mtime = path.stat().st_mtime
         for section_index, (heading, section) in enumerate(split_sections(raw)):
             for chunk_index, chunk in enumerate(chunk_text(section)):
-                chunk_digest = hashlib.sha256(f"{rel}\n{section_index}\n{chunk_index}\n{chunk}".encode("utf-8")).hexdigest()[:16]
-                chunks.append(Chunk(chunk_id=chunk_digest, path=rel, heading=heading, text=chunk, mtime=mtime, sha256=digest))
+                chunk_digest = hashlib.sha256(f"{rel_path}\n{section_index}\n{chunk_index}\n{chunk}".encode("utf-8")).hexdigest()[:16]
+                chunks.append(Chunk(chunk_id=chunk_digest, path=rel_path, heading=heading, text=chunk, mtime=mtime, sha256=digest))
     return chunks
 
 
@@ -140,14 +143,14 @@ def write_index(profile: str) -> dict[str, Any]:
     files = sorted({chunk.path for chunk in chunks})
     manifest = {
         "profile": profile,
-        "source": str(project_knowledge_dir(profile).relative_to(ROOT)),
+        "source": rel(project_knowledge_dir(profile)),
         "canonical": False,
         "derived_from": "project-knowledge",
         "index_type": "lexical-markdown-chunks",
         "created_at": datetime.now(timezone.utc).isoformat(),
         "file_count": len(files),
         "chunk_count": len(chunks),
-        "index_path": str(index_path(profile).relative_to(ROOT)),
+        "index_path": rel(index_path(profile)),
     }
     manifest_path(profile).write_text(json.dumps(manifest, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8")
     return manifest
@@ -225,7 +228,7 @@ def search_index(profile: str, query: str, limit: int = 10) -> dict[str, Any]:
 def status(profile: str) -> dict[str, Any]:
     manifest_file = manifest_path(profile)
     if not manifest_file.is_file():
-        return {"profile": profile, "indexed": False, "index_path": str(index_path(profile).relative_to(ROOT))}
+        return {"profile": profile, "indexed": False, "index_path": rel(index_path(profile))}
     manifest = json.loads(manifest_file.read_text(encoding="utf-8"))
     path = index_path(profile)
     manifest["indexed"] = path.is_file()