feat: profile-gated workspace-maintenance service and connector override generator (P2)

2026-08-11 18:40:11 +02:00
parent 17f2e48463
commit c5f65d0f15
9 changed files with 156 additions and 19 deletions
@@ -55,6 +55,60 @@ services:
    networks:
      - thothii

+  workspace-maintenance:
+    image: thothii-core:local
+    profiles: [workspace-maintenance]
+    pull_policy: never
+    entrypoint: ["/usr/bin/tini", "--", "/app/docker/workspace-maintenance-entrypoint.sh"]
+    environment:
+      THT_HARNESS_DIR: /app/harness
+      THT_BIN: /opt/venv/bin/tht
+      THT_DATA_ROOT: /data
+      THT_WORKSPACE_REGISTRY_ROOT: /data/workspace-registry
+      THT_WORKSPACE_GIT_REMOTE: ${THT_WORKSPACE_GIT_REMOTE:?set THT_WORKSPACE_GIT_REMOTE}
+      THT_WORKSPACE_GIT_BRANCH: ${THT_WORKSPACE_GIT_BRANCH:-main}
+      THT_WORKSPACE_INSTALLATION_ID: ${THT_WORKSPACE_INSTALLATION_ID:-local}
+      THT_WORKSPACE_SECRET_ROOTS: /run/secrets
+      THT_SECRETS_FILE: /run/secrets/thothii.secrets
+      THT_DB_NAME: ${THT_DB_NAME:-}
+      THT_DWH_REST_URL: ${THT_DWH_REST_URL:-}
+      THT_LLM_URL: ${THT_LLM_URL:-}
+      THT_INTERNAL_QDRANT_URL: http://qdrant:6333
+      THT_INTERNAL_EMBEDDING_URL: http://embedding:11434
+      THT_INTERNAL_EMBEDDING_MODEL: qwen3-embedding:0.6b
+      THT_INTERNAL_EMBEDDING_DIMENSIONS: "1024"
+      HOME: /tmp/thoth
+      AWS_ACCESS_KEY_ID: ""
+      AWS_SECRET_ACCESS_KEY: ""
+      AWS_SESSION_TOKEN: ""
+      AWS_PROFILE: ""
+      AWS_DEFAULT_PROFILE: ""
+      AWS_CONFIG_FILE: /dev/null
+      AWS_SHARED_CREDENTIALS_FILE: /dev/null
+    volumes:
+      - type: volume
+        source: workspace-registry
+        target: /data/workspace-registry
+        read_only: true
+      - type: volume
+        source: sessions
+        target: /data/sessions
+    secrets:
+      - source: thothii_secrets
+        target: thothii.secrets
+    user: "10001:10001"
+    read_only: true
+    tmpfs:
+      - /tmp:rw,noexec,nosuid,nodev,size=64m,mode=1777
+      - /var/tmp:rw,noexec,nosuid,nodev,size=32m,mode=1777
+    cap_drop:
+      - ALL
+    security_opt:
+      - no-new-privileges:true
+    restart: "no"
+    networks:
+      - thothii
+
  frontend:
    build:
      context: .
@@ -1,5 +1,6 @@
 # Select this override only for an HTTPS Git remote. The separate CA mount keeps TLS validation
 # explicit; neither host-only source file nor its contents belongs in the base Compose contract.
+# Active-snapshot workspace-maintenance operations intentionally receive no Git credential mounts.
 x-thoth-git-transport: https

 services:
@@ -1,5 +1,6 @@
 # Select this override only for an SSH Git remote. The host-only source files must be absolute,
 # normalized paths; strict host-key checking is mandatory for registry pull and publish.
+# Active-snapshot workspace-maintenance operations intentionally receive no Git credential mounts.
 x-thoth-git-transport: ssh

 services:
@@ -11,3 +11,8 @@ services:
    ports:
      - "127.0.0.1:${THOTH_HTTP_PORT:-8080}:8080"
    restart: "no"
+
+  workspace-maintenance:
+    environment:
+      THT_WORKSPACE_INSTALLATION_ID: local
+    restart: "no"
@@ -1,3 +1,5 @@
+# Retired for operator use: this profile remains only as a non-public engine-fixture path.
+# It exercises the legacy preprocessing fixtures and must not become a second operator interface.
 services:
  preprocess-evidence:
    image: thothii-core:local
@@ -35,3 +35,18 @@ services:
    ports:
      - "${THOTH_SERVER_BIND:-127.0.0.1}:${THOTH_HTTP_PORT:-8080}:8080"
    restart: unless-stopped
+
+
+  workspace-maintenance:
+    environment:
+      THT_DATA_ROOT: /data
+      THT_WORKSPACE_INSTALLATION_ID: server
+    volumes: !override
+      - type: bind
+        source: ${THT_DATA_ROOT:?set THT_DATA_ROOT}/sessions
+        target: /data/sessions
+      - type: bind
+        source: ${THT_WORKSPACE_REGISTRY_ROOT:?set THT_WORKSPACE_REGISTRY_ROOT}
+        target: /data/workspace-registry
+        read_only: true
+    restart: "no"
@@ -33,10 +33,16 @@ LABEL org.opencontainers.image.title="thothii-core" \
      io.thothii.pi.version="${PI_VERSION}"

 # Runtime tools
-RUN apt-get update && apt-get install -y --no-install-recommends \
-        curl ca-certificates ripgrep fd-find tini git openssh-client \
-    && rm -rf /var/lib/apt/lists/* \
-    && ln -s /usr/bin/fdfind /usr/local/bin/fd
+RUN set -eux; \
+    runtime_packages="curl ca-certificates ripgrep fd-find tini git openssh-client"; \
+    if ! command -v flock >/dev/null 2>&1; then \
+        runtime_packages="$runtime_packages util-linux"; \
+    fi; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends $runtime_packages; \
+    rm -rf /var/lib/apt/lists/*; \
+    command -v flock >/dev/null 2>&1; \
+    ln -s /usr/bin/fdfind /usr/local/bin/fd

 # Node 22 + npm copiati dall'immagine ufficiale (stesso Debian bookworm → binario compatibile)
 COPY --from=node-runtime /usr/local/bin/node /usr/local/bin/node
@@ -91,10 +97,10 @@ ENV PATH="/opt/venv/bin:/usr/local/bin:$PATH" \
    HOME=/home/thoth

 COPY scripts/verify-line-endings.sh /usr/local/bin/verify-line-endings
-COPY docker/core-entrypoint.sh docker/session-migrate.sh docker/ensure-pi-trust.mjs docker/embedding-model-init.sh /app/docker/
+COPY docker/core-entrypoint.sh docker/workspace-maintenance-entrypoint.sh docker/session-migrate.sh docker/ensure-pi-trust.mjs docker/embedding-model-init.sh /app/docker/
 COPY docker/smoke/core-smoke.sh /app/docker/smoke/core-smoke.sh
 RUN /usr/local/bin/verify-line-endings /app/docker \
- && chmod +x /app/docker/core-entrypoint.sh /app/docker/session-migrate.sh /app/docker/embedding-model-init.sh /app/docker/smoke/core-smoke.sh
+ && chmod +x /app/docker/core-entrypoint.sh /app/docker/workspace-maintenance-entrypoint.sh /app/docker/session-migrate.sh /app/docker/embedding-model-init.sh /app/docker/smoke/core-smoke.sh

 WORKDIR /app/backend
 USER thoth
@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+exec node /app/backend/dist/workspace-maintenance.js "$@"
@@ -3,7 +3,10 @@
 set -euo pipefail

 usage() {
-  echo "usage: $0 --bindings-env <workspace-bindings.env> --operator-env <operator.env> --output <override.yaml>" >&2
+  cat >&2 <<'EOF'
+usage: $0 --bindings-env <workspace-bindings.env> --operator-env <operator.env> --output <override.yaml> \
+  [--service <core|workspace-maintenance>]... [--role <all|dwh|evidence>]...
+EOF
  exit 2
 }

@@ -40,20 +43,59 @@ read_env_value() {
  printf '%s' "$result"
 }

+binding_matches_roles() {
+  local name="$1" role
+  for role in "${roles[@]}"; do
+    case "$role" in
+      all) return 0 ;;
+      dwh)
+        [[ "$name" == *"_DWH_"* ]] && return 0
+        ;;
+      evidence)
+        [[ "$name" == *"_EVIDENCE_"* ]] && return 0
+        ;;
+      *)
+        echo "unsupported role filter: $role" >&2
+        exit 2
+        ;;
+    esac
+  done
+  return 1
+}
+
 bindings_env=""
 operator_env=""
 output=""
+services=()
+roles=()
 while (($#)); do
  case "$1" in
    --bindings-env) bindings_env="${2:-}"; shift 2 ;;
    --operator-env) operator_env="${2:-}"; shift 2 ;;
    --output) output="${2:-}"; shift 2 ;;
+    --service) services+=("${2:-}"); shift 2 ;;
+    --role)
+      roles+=("$(printf '%s' "${2:-}" | tr '[:upper:]' '[:lower:]')")
+      shift 2
+      ;;
    *) usage ;;
  esac
 done

 [[ -f "$bindings_env" && -f "$operator_env" && -n "$output" ]] || usage
 [[ ! -e "$output" ]] || { echo "refusing to overwrite connector override: $output" >&2; exit 2; }
+((${#services[@]})) || services=(core)
+((${#roles[@]})) || roles=(all)
+
+for service in "${services[@]}"; do
+  case "$service" in
+    core|workspace-maintenance) ;;
+    *)
+      echo "unsupported service target: $service" >&2
+      exit 2
+      ;;
+  esac
+done

 names=()
 targets=()
@@ -64,6 +106,7 @@ while IFS=$'\t' read -r name target; do
    echo "retired semantic secret binding is not supported: ${name%_FILE}_SOURCE" >&2
    exit 2
  fi
+  binding_matches_roles "$name" || continue
  [[ "$target" =~ ^/run/secrets/[A-Za-z0-9][A-Za-z0-9_.-]*$ && "$target" != *..* ]] || {
    echo "invalid connector secret target for $name: $target" >&2
    exit 2
@@ -101,20 +144,25 @@ done < <(
  ' "$bindings_env"
 )

-((${#names[@]})) || { echo "no THT_WS_*_FILE connector bindings found in $bindings_env" >&2; exit 2; }
+((${#names[@]})) || {
+  echo "no THT_WS_*_FILE connector bindings matched the selected roles in $bindings_env" >&2
+  exit 2
+}

 {
  printf '%s\n' '# Generated by scripts/generate-connector-secrets-override.sh; keep this file untracked.'
-  printf '%s\n' \
-    'services:' \
-    '  core:' \
-    '    env_file:' \
-    '      - path: ${THT_WORKSPACE_BINDINGS_ENV_FILE:?set THT_WORKSPACE_BINDINGS_ENV_FILE}' \
-    '        required: true' \
-    '    secrets:'
-  for ((index = 0; index < ${#names[@]}; index += 1)); do
-    printf '      - source: connector_secret_%d\n' "$((index + 1))"
-    printf '        target: %s\n' "${targets[index]}"
+  printf '%s\n' 'services:'
+  for service in "${services[@]}"; do
+    printf '  %s:\n' "$service"
+    printf '%s\n' \
+      '    env_file:' \
+      '      - path: ${THT_WORKSPACE_BINDINGS_ENV_FILE:?set THT_WORKSPACE_BINDINGS_ENV_FILE}' \
+      '        required: true' \
+      '    secrets:'
+    for ((index = 0; index < ${#names[@]}; index += 1)); do
+      printf '      - source: connector_secret_%d\n' "$((index + 1))"
+      printf '        target: %s\n' "${targets[index]}"
+    done
  done
  printf '%s\n' '' 'secrets:'
  for ((index = 0; index < ${#names[@]}; index += 1)); do
@@ -123,4 +171,5 @@ done < <(
  done
 } >"$output"

-printf 'generated %s connector secret mount(s) at %s\n' "${#names[@]}" "$output"
+printf 'generated %s connector secret mount(s) for %s at %s\n' \
+  "${#names[@]}" "$(IFS=,; printf '%s' "${services[*]}")" "$output"