Keru/knowledge-genome-orchestrator
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(ingest): Implement 'pi ingest-rework' command

Browse source
This commit is contained in:
Matteo Cherubini 2026-06-30 10:31:37 +02:00
parent c5f113de52
commit 19529531cf
1 changed files with 39 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
deploy/vm101/n8n-pi-wrap
View file

@ -79,7 +79,45 @@ case "$cmd" in
# MECHANICAL step: validate manifest -> index/log/scoped-lint/commit/PR -> 1 JSON line
exec "${HOME}/.pi/agent/skills/ingest/scripts/run-ingest.sh" "${genome}"
;;
"pi changed-raw "*)
"pi ingest-rework "*)
# args: <genome> <raw_path> <feedback_base64> (3 token).
# Feedback in base64 nell'argv: il nodo SSH di n8n non passa stdin, e cosi' i metacaratteri
# della review (apici, newline, $(...)) sono neutralizzati.
args="${cmd#pi ingest-rework }"
genome="${args%% *}"; tmp="${args#* }"
raw_path="${tmp%% *}"; fb_b64="${tmp#* }"
if [ "$genome" = "$args" ] || [ "$raw_path" = "$tmp" ] || [ -z "$fb_b64" ]; then
echo '{"status":"error","reason":"usage: pi ingest-rework <genome> <raw_path> <feedback_b64>"}'; exit 1
fi
case "$genome" in ""|*[!a-z0-9-]*) echo '{"status":"error","reason":"invalid genome"}'; exit 1;; esac
case "$raw_path" in raw/*) : ;; *) echo '{"status":"error","reason":"raw_path must be under raw/"}'; exit 1;; esac
case "$raw_path" in *..*|*//*) echo '{"status":"error","reason":"raw_path traversal"}'; exit 1;; esac
case "$raw_path" in *[!A-Za-z0-9._/-]*) echo '{"status":"error","reason":"raw_path illegal chars"}'; exit 1;; esac
case "$fb_b64" in *[!A-Za-z0-9+/=]*) echo '{"status":"error","reason":"feedback not base64"}'; exit 1;; esac
logger -t n8n-pi-wrap "ok: pi ingest-rework ${genome} ${raw_path}"
feedback="$(printf '%s' "$fb_b64" | base64 -d 2>/dev/null || true)"
# lock per-genoma: serializza con gli ingest normali
exec 9>"/run/lock/kg-ingest-${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}/${genome}" || { echo '{"status":"error","reason":"unknown genome"}'; exit 1; }
[ -f "$raw_path" ] || { echo '{"status":"error","reason":"raw file not found"}'; exit 1; }
: "${KG_LIB_DIR:=${HOME}/knowledge-genome-orchestrator/lib}"
source "${KG_LIB_DIR}/clean-start.sh" 2>/dev/null \
|| { echo '{"status":"error","reason":"clean-start.sh not found"}'; exit 1; }
clean_start || { echo '{"status":"error","reason":"clean-start failed"}'; exit 1; }
log="$(mktemp -t pi-rework.XXXXXX.log)"
INGEST_FEEDBACK="$feedback" \
"${HOME}/.pi/agent/skills/ingest/scripts/ingest-semantic.py" "${genome}" "${raw_path}" \
>"$log" 2>&1 \
|| { echo "{\"status\":\"error\",\"stage\":\"semantic\",\"reason\":\"rework failed\",\"log\":\"${log}\"}"; exit 1; }
exec "${HOME}/.pi/agent/skills/ingest/scripts/run-ingest.sh" "${genome}"
;;
"pi changed-raw "*)
# List raw/ files changed between two commits, one per line (the webhook payload
# does NOT include file lists, so vm101's checkout computes the diff itself).
rest="${cmd#pi changed-raw }"