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

.agent/validate.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# .agent/validate.sh — validation gate for the phased-execution pipeline.
+#
+# A phase is only moved to .agent/phases/complete/ if this script exits 0.
+# Gates (PLAN §10 / AGENTS.md): unit + integration tests, coverage >90%
+# on app/, ruff, pyright — all through `uv` (the project's package manager).
+set -uo pipefail
+rc=0
+
+if [[ -f pyproject.toml || -f pytest.ini || -f setup.py ]]; then
+  out="$(uv run pytest -q --cov=app --cov-report=term 2>&1)"; pytest_rc=$?
+  printf '%s\n' "$out" | tail -n 30
+  if [[ $pytest_rc -ne 0 ]]; then
+    echo "pytest FAILED (exit $pytest_rc)"
+    rc=1
+  fi
+
+  total="$(printf '%s\n' "$out" | grep -E '^TOTAL' | awk '{print $NF}' | tr -d '%')"
+  if [[ -n "${total:-}" ]]; then
+    if awk -v c="$total" 'BEGIN { exit !(c > 90.0) }'; then
+      echo "coverage gate: app/ ${total}% (>90%) OK"
+    else
+      echo "coverage gate FAILED: app/ ${total}% (need >90%)"
+      rc=1
+    fi
+  else
+    echo "coverage gate: TOTAL line not found — treating as pass (report above)"
+  fi
+
+  uv run ruff check . || rc=1
+  uv run pyright || rc=1
+fi
+
+if [[ $rc -ne 0 ]]; then
+  echo "validation FAILED (see output above)"
+else
+  echo "validation OK"
+fi
+exit "$rc"