feat(rag): index markdown KB — chunker, embed client, delta importer, Sources page

Phase 02 (story: import documents):

- fence-aware markdown chunker (heading sections, 200-char overlap,
  heading anchor on every chunk, 1200-char hard cap, fence blocks
  kept atomic and split under the cap)
- LLMClient over aipi (LiteLLM) reusing the openai client's httpx
  transport to send a clean {model, input} payload — the openai SDK
  injects encoding_format, which aipi's openai_like group rejects;
  token-budget batching + halving retry for the endpoint's
  ~1024-token per-request input cap
- two-phase per-file upsert importer: sha256 delta (unchanged skip),
  atomic commit, A9 exclusion walk, per-source prune, per-file error
  tolerance (rollback + log + continue, non-zero CLI exit), adaptive
  re-chunk at half target for URL-dense files the endpoint rejects
- scripts/import_docs CLI (repeatable --source, --prune, --limit,
  defaults ~/Homelab + ~/Deployments)
- GET /api/docs with per-doc chunk counts; Sources page wired to the
  real endpoint (stat cards, full-width a11y table, designed empty
  state, DOM-built rows — no innerHTML)
- tests: 63 passed (chunker/llm/importer units, docs API + importer
  integration), story E2E 3/3 (real endpoints, in-thread import);
  app/ coverage 98%
- real KB imported: 672 docs / 8969 chunks in ~3m, idempotent
  re-run (672 unchanged, 0 batches)
- harness: .agent/validate.sh now gates through uv (pytest +
  coverage >90% + ruff + pyright) instead of system python3

app/api/docs.py

@@ -0,0 +1,47 @@
+"""GET /api/docs — the indexed document list (feeds the Sources page)."""
+from __future__ import annotations
+
+from fastapi import APIRouter, Depends
+from sqlalchemy import func, select
+from sqlalchemy.orm import Session
+
+from app.db import get_db
+from app.models import Chunk, Document
+from app.schemas import DocList, DocSummary
+
+router = APIRouter(tags=["kb"])
+
+
+@router.get("/docs", response_model=DocList)
+def list_documents(db: Session = Depends(get_db)) -> DocList:  # noqa: B008
+    """All indexed documents with per-document chunk counts.
+
+    An empty list means the knowledge base has not been imported yet —
+    the Sources page renders its designed empty state in that case.
+    """
+    rows = db.execute(
+        select(
+            Document.id,
+            Document.source,
+            Document.path,
+            Document.title,
+            func.count(Chunk.id).label("chunks"),
+            Document.indexed_at,
+        )
+        .outerjoin(Chunk, Chunk.document_id == Document.id)
+        .group_by(Document.id, Document.source, Document.path, Document.title, Document.indexed_at)
+        .order_by(Document.source, Document.path)
+    ).all()
+    return DocList(
+        documents=[
+            DocSummary(
+                id=str(row.id),
+                source=row.source,
+                path=row.path,
+                title=row.title,
+                chunks=row.chunks,
+                indexed_at=row.indexed_at.isoformat(),
+            )
+            for row in rows
+        ]
+    )