fix(preprocess): enforce local vector startup chain
This commit is contained in:
@@ -33,3 +33,17 @@ The cleanup boundary now begins immediately after snapshot materialization. Resu
|
||||
validation and `JobSpec` construction are guarded by the same release routine as `run_job`, so
|
||||
corrupt/mismatched resume state or constructor failure clears the pipeline holder, removes the
|
||||
private directory, and restores the snapshot registry to its prior state before propagating.
|
||||
|
||||
## Shipped preprocessing startup contract
|
||||
|
||||
Local-vector preprocessing now uses a dedicated Compose override. Both one-shot jobs depend on a
|
||||
successfully completed `vector-migrate`, whose transitive chain waits for database health and role
|
||||
reconciliation. The generic preprocessing overlay remains independently renderable and contains no
|
||||
local-vector services or password secrets. README commands include the local override and build the
|
||||
job image before running.
|
||||
|
||||
The real clean-project smoke no longer injects dependencies or manually starts, reconciles, or
|
||||
migrates PostgreSQL. Its first shipped `compose run preprocess-evidence` demonstrably creates the
|
||||
database, waits for health, runs reconciliation and migration, then runs the Evidence job. Unchanged
|
||||
rerun, changed-source publish, DWH preprocessing, ACTIVE verification, and injected-failure cleanup
|
||||
all pass through the same shipped dependency path.
|
||||
|
||||
@@ -62,23 +62,13 @@ runtime):
|
||||
|
||||
```sh
|
||||
docker compose -f compose.yaml -f deploy/compose.local-vector.yaml \
|
||||
-f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml \
|
||||
--profile local-vector --profile preprocess build preprocess-evidence
|
||||
-f deploy/compose.preprocess.yaml --profile local-vector --profile preprocess \
|
||||
run --rm preprocess-evidence
|
||||
docker compose -f compose.yaml -f deploy/compose.local-vector.yaml \
|
||||
-f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml \
|
||||
--profile local-vector --profile preprocess run --rm preprocess-evidence
|
||||
docker compose -f compose.yaml -f deploy/compose.local-vector.yaml \
|
||||
-f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml \
|
||||
--profile local-vector --profile preprocess build preprocess-dwh
|
||||
docker compose -f compose.yaml -f deploy/compose.local-vector.yaml \
|
||||
-f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml \
|
||||
--profile local-vector --profile preprocess run --rm preprocess-dwh
|
||||
-f deploy/compose.preprocess.yaml --profile local-vector --profile preprocess \
|
||||
run --rm preprocess-dwh
|
||||
```
|
||||
|
||||
The local preprocessing override makes each job wait for the vector database health check,
|
||||
role reconciliation, and a successful migration. These commands are safe on a clean Compose
|
||||
project; no separate database startup or migration command is required.
|
||||
|
||||
S3 Evidence uses the optional `tht[s3]` dependency and canonical `s3://bucket/key` provenance.
|
||||
AWS endpoints are used when no custom URL is supplied. Every custom endpoint is an explicit egress
|
||||
trust-boundary opt-in and uses path-style addressing; private and HTTP endpoints require additional
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
services:
|
||||
preprocess-evidence:
|
||||
environment:
|
||||
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
|
||||
THT_VECTOR_WRITER_PASSWORD_FILE: /run/secrets/vector_writer_password
|
||||
secrets: [vector_reader_password, vector_writer_password]
|
||||
depends_on:
|
||||
vector-migrate: {condition: service_completed_successfully}
|
||||
|
||||
preprocess-dwh:
|
||||
environment:
|
||||
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
|
||||
secrets: [vector_reader_password]
|
||||
depends_on:
|
||||
vector-migrate: {condition: service_completed_successfully}
|
||||
|
||||
secrets:
|
||||
vector_reader_password:
|
||||
file: ${THT_VECTOR_READER_PASSWORD_SECRET_FILE:?set THT_VECTOR_READER_PASSWORD_SECRET_FILE}
|
||||
vector_writer_password:
|
||||
file: ${THT_VECTOR_WRITER_PASSWORD_SECRET_FILE:?set THT_VECTOR_WRITER_PASSWORD_SECRET_FILE}
|
||||
@@ -10,9 +10,6 @@ services:
|
||||
environment:
|
||||
THT_DATA_ROOT: /data
|
||||
THT_OLLAMA_URL: "${THT_OLLAMA_URL:-http://host.docker.internal:11434}"
|
||||
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
|
||||
THT_VECTOR_WRITER_PASSWORD_FILE: /run/secrets/vector_writer_password
|
||||
secrets: [vector_reader_password, vector_writer_password]
|
||||
volumes:
|
||||
- thoth_data:/data
|
||||
- ./deploy/workspaces:/app/harness/workspaces:ro
|
||||
@@ -28,15 +25,7 @@ services:
|
||||
command: ["mkdir -p /data/workspaces/preprocess-dwh && exec /app/docker/core-entrypoint.sh preprocess dwh --steps introspect --json -c /app/harness/workspaces/preprocess-dwh.yaml"]
|
||||
environment:
|
||||
THT_DATA_ROOT: /data
|
||||
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
|
||||
secrets: [vector_reader_password]
|
||||
volumes:
|
||||
- thoth_data:/data
|
||||
- ./deploy/workspaces:/app/harness/workspaces:ro
|
||||
restart: "no"
|
||||
|
||||
secrets:
|
||||
vector_reader_password:
|
||||
file: ${THT_VECTOR_READER_PASSWORD_SECRET_FILE:?set THT_VECTOR_READER_PASSWORD_SECRET_FILE}
|
||||
vector_writer_password:
|
||||
file: ${THT_VECTOR_WRITER_PASSWORD_SECRET_FILE:?set THT_VECTOR_WRITER_PASSWORD_SECRET_FILE}
|
||||
|
||||
@@ -79,18 +79,11 @@ services:
|
||||
volumes:
|
||||
- $tmp/source:/data/source:ro
|
||||
depends_on:
|
||||
vector-migrate: {condition: service_completed_successfully}
|
||||
mock-embeddings: {condition: service_started}
|
||||
preprocess-dwh:
|
||||
depends_on:
|
||||
vector-migrate: {condition: service_completed_successfully}
|
||||
YAML
|
||||
|
||||
compose="docker compose -f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f $tmp/smoke.yaml --project-name $project --profile local-vector --profile preprocess"
|
||||
compose="docker compose -f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml -f $tmp/smoke.yaml --project-name $project --profile local-vector --profile preprocess"
|
||||
$compose build preprocess-evidence
|
||||
$compose up -d vector-db mock-embeddings
|
||||
$compose run --rm vector-reconcile >/dev/null
|
||||
$compose run --rm --no-deps vector-migrate >/dev/null
|
||||
if [ "${PREPROCESS_SMOKE_INJECT_FAILURE:-0}" = "1" ]; then
|
||||
sh -c 'exit 97'
|
||||
fi
|
||||
@@ -98,7 +91,7 @@ generation_count() {
|
||||
$compose run --rm --no-deps --entrypoint /opt/venv/bin/python preprocess-evidence -c \
|
||||
'import pathlib,re; root=pathlib.Path("/data/workspaces/preprocess-evidence/corpus"); print(sum(1 for p in root.iterdir() if p.is_dir() and re.fullmatch(r"gen-[0-9a-f]{32}",p.name)) if root.exists() else 0)'
|
||||
}
|
||||
before=$(generation_count)
|
||||
before=0
|
||||
first=$($compose run --rm preprocess-evidence)
|
||||
after_first=$(generation_count)
|
||||
second=$($compose run --rm preprocess-evidence)
|
||||
|
||||
Executable
+43
@@ -0,0 +1,43 @@
|
||||
#!/bin/sh
|
||||
set -eu
|
||||
|
||||
cd "$(dirname "$0")/.."
|
||||
|
||||
export THT_VECTOR_BOOTSTRAP_PASSWORD_SECRET_FILE=${THT_VECTOR_BOOTSTRAP_PASSWORD_SECRET_FILE:-/tmp/vector-bootstrap}
|
||||
export THT_VECTOR_MIGRATOR_PASSWORD_SECRET_FILE=${THT_VECTOR_MIGRATOR_PASSWORD_SECRET_FILE:-/tmp/vector-migrator}
|
||||
export THT_VECTOR_READER_PASSWORD_SECRET_FILE=${THT_VECTOR_READER_PASSWORD_SECRET_FILE:-/tmp/vector-reader}
|
||||
export THT_VECTOR_WRITER_PASSWORD_SECRET_FILE=${THT_VECTOR_WRITER_PASSWORD_SECRET_FILE:-/tmp/vector-writer}
|
||||
|
||||
local_files="-f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml"
|
||||
local_json=$(docker compose $local_files --profile local-vector --profile preprocess config --format json)
|
||||
|
||||
printf '%s' "$local_json" | python3 -c '
|
||||
import json, sys
|
||||
|
||||
config = json.load(sys.stdin)
|
||||
services = config["services"]
|
||||
for name in ("preprocess-evidence", "preprocess-dwh"):
|
||||
dependency = services[name].get("depends_on", {}).get("vector-migrate")
|
||||
assert dependency is not None, f"{name} does not depend on vector-migrate"
|
||||
assert dependency["condition"] == "service_completed_successfully", dependency
|
||||
'
|
||||
|
||||
external_json=$(docker compose \
|
||||
-f compose.yaml -f deploy/compose.preprocess.yaml \
|
||||
--profile preprocess config --format json)
|
||||
|
||||
printf '%s' "$external_json" | python3 -c '
|
||||
import json, sys
|
||||
|
||||
config = json.load(sys.stdin)
|
||||
services = config["services"]
|
||||
assert "vector-db" not in services
|
||||
assert "vector-migrate" not in services
|
||||
assert "vector-reconcile" not in services
|
||||
for name in ("preprocess-evidence", "preprocess-dwh"):
|
||||
service = services[name]
|
||||
assert "depends_on" not in service
|
||||
assert not service.get("secrets"), service.get("secrets")
|
||||
'
|
||||
|
||||
echo "preprocess compose config: ok"
|
||||
Reference in New Issue
Block a user