refactor: Integrate shared clean_start into ingest preparation

deploy/vm101/n8n-pi-wrap

@@ -42,20 +42,25 @@ case "$cmd" in
    esac
 
    logger -t n8n-pi-wrap "ok: pi ingest ${genome} ${raw_path}"
+
+   # Per-genome lock: serialize writes; never two concurrent ingests on the same genome.
+   exec 9>"/run/lock/kg-ingest-${genome}.lock" 2>/dev/null || exec 9>"/tmp/kg-ingest-${genome}.lock"
+   if ! flock -n 9; then
+     echo '{"status":"busy","reason":"another ingest is running for this genome","genome":"'"$genome"'"}'
+     exit 0
+   fi
+
    set -a; . "${HOME}/.config/knowledge-genome.env"; set +a
    cd "${GENOMES_ROOT}/${genome}" || { echo '{"status":"error","reason":"unknown genome"}'; exit 1; }
 
    # The raw file must actually exist under the genome's raw/ dir.
    [ -f "$raw_path" ] || { echo '{"status":"error","reason":"raw file not found"}'; exit 1; }
 
-   # Clean start on the configured base (develop), pinned to the remote. Destroys only
+   # Clean start on the configured base (single source of truth in lib/clean-start.sh).
-   # vm101's scratch checkout (never a shared branch, never a force-push) — this is by design.
+   : "${KG_LIB_DIR:=${HOME}/knowledge-genome-orchestrator/lib}"
-   # `clean -fd` also removes leftover UNTRACKED files (e.g. wiki/sources/* or a stale
+   source "${KG_LIB_DIR}/clean-start.sh" 2>/dev/null \
-   # .ingest-manifest.json from a half-finished previous run) that `reset --hard` won't touch.
+     || { echo '{"status":"error","reason":"clean-start.sh not found"}'; exit 1; }
-   git fetch -q origin \
+   clean_start || { echo '{"status":"error","reason":"clean-start failed"}'; exit 1; }
-     && git switch -q "${INGEST_BASE:-main}" 2>/dev/null \
-     && git reset -q --hard "origin/${INGEST_BASE:-main}" \
-     && git clean -q -fd
 
    # SEMANTIC step: dedicated script drives pi to WRITE wiki pages + manifest.
    # (NOT `pi -p "/skill:ingest ..."`, which makes the model reply in chat and write nothing.)

skills/ingest/scripts/pending-raw.sh

@@ -12,11 +12,11 @@ genome="${1:?usage: pending-raw.sh <genome>}"
 base_dir="${GENOMES_ROOT:-${HOME}/genomes}"
 cd "${base_dir}/${genome}" 2>/dev/null || { echo '{"status":"error","reason":"unknown genome"}'; exit 1; }
 
-# Clean start on the configured base (Step 3 will extract this to lib/clean-start.sh).
+# Clean start on the configured base (single source of truth in lib/clean-start.sh).
-git fetch -q origin \
+: "${KG_LIB_DIR:=${HOME}/knowledge-genome-orchestrator/lib}"
-  && git switch -q "${INGEST_BASE:-main}" 2>/dev/null \
+source "${KG_LIB_DIR}/clean-start.sh" 2>/dev/null \
-  && git reset -q --hard "origin/${INGEST_BASE:-main}" \
+  || { echo '{"status":"error","reason":"clean-start.sh not found"}'; exit 1; }
-  && git clean -q -fd
+clean_start || { echo '{"status":"error","reason":"clean-start failed"}'; exit 1; }
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 SLUG="${SCRIPT_DIR}/slug.sh"

tests/pending-raw.bats

@@ -5,6 +5,7 @@ setup() {
   export PENDING="${SKILL_SCRIPTS}/pending-raw.sh"
   export GENOMES_ROOT="${BATS_TEST_TMPDIR}"
   export INGEST_BASE="main"
+  export KG_LIB_DIR="${LIB_DIR}"
 
   g_src="$(make_fixture_genome)"
   export g_name="fixture-genome"