replica-omnisciente/.aurelio/mirrors/sync-mirrors.yaml

# Mirror Pipeline — single source of truth
#
# Declares how upstream sources (GitHub, Jira, Confluence) replicate into the
# self-hosted mirrors (Forgejo, Plane, Outline). All downstream surfaces derive
# from this file via scripts/sync-mirrors.py.
#
# ONE place to edit. mirrors/dist/*.json are GENERATED (do not edit).
#
# Direction: upstream → mirror (read-only by default; write-back is a future
# toggle per-target). The agent fleet operates on the mirrors; the originals
# stay authoritative.
#
# Regenerate after editing:
#   python3 scripts/sync-mirrors.py --write-in-place   # regenerate dist/
#   python3 scripts/sync-mirrors.py --check            # CI guard: exit 1 if stale
#   python3 scripts/sync-mirrors.py --sync             # run all mirror syncs
#   python3 scripts/sync-mirrors.py --sync forgejo     # one target
#
# Auth: tokens are NEVER in this file. They live in the environment (.env or
# shell env), referenced by the `token_env` key. Fetch from Vaultwarden.

version: 1

# ── Global defaults ────────────────────────────────────────────────────────
defaults:
  # Sync cadence (minutes). Overridden by cron job schedule.
  interval_minutes: 15
  # Fail the whole run if any single source errors? false = log + continue.
  fail_fast: false
  # User-agent for upstream API calls.
  user_agent: "replica-omnisciente-mirror/1.0"

# ── Mirror targets ─────────────────────────────────────────────────────────
# Each target is a self-hosted service that RECEIVES data from one or more
# upstream sources. A target may have multiple sources (e.g. Forgejo mirrors
# both GitHub orgs and individual repos).

targets:

  # ── Forgejo: code mirror (GitHub → Forgejo) ────────────────────────────
  forgejo:
    kind: git-mirror
    label: "Forgejo (code mirror)"
    endpoint: https://code.portugalfuturista.org
    # Forgejo API token (admin or org-owner scope). ENV var name only.
    token_env: FORGEJO_MIRROR_TOKEN
    # Default owner/org for mirrored repos if the upstream org doesn't exist.
    default_owner: SavearthTech
    # Mirror interval in Forgejo's own scheduler (for native push mirrors).
    native_interval: 8h
    sources:
      - id: savearthtech-github
        label: "SavearthTech GitHub org"
        type: github-org
        # GitHub org name to mirror ALL public+private repos from.
        org: SavearthTech
        # GitHub PAT (classic, read scope on repo + org). ENV var name only.
        token_env: GITHUB_MIRROR_TOKEN
        # Clone over SSH for private repos (key must be in agent).
        clone_transport: https
        # Include forked repos? false = skip forks.
        include_forks: false
        # Map GitHub topics → Forgejo labels (optional).
        topic_labels: true
        status: declared

      - id: savearth-personal-github
        label: "Personal Savearth repos (fabiorafaelcoutada)"
        type: github-user
        user: fabiorafaelcoutada
        token_env: GITHUB_MIRROR_TOKEN
        # Only mirror repos matching these patterns (glob).
        include_patterns:
          - "savearth*"
          - "aws-iot-core*"
          - "hardware-devices*"
          - "agent-firmware*"
        exclude_patterns:
          - "*.github.io"
        clone_transport: https
        status: declared

  # ── Plane: issue tracker mirror (Jira → Plane) ─────────────────────────
  plane:
    kind: issue-mirror
    label: "Plane (issue tracker mirror)"
    endpoint: https://plane.portugalfuturista.org
    token_env: PLANE_API_TOKEN
    # Plane workspace slug (in the URL). Create if it doesn't exist.
    workspace_slug: savearth
    sources:
      - id: savearth-jira
        label: "Savearth Jira Cloud"
        type: jira-cloud
        # Jira Cloud base URL (e.g. https://savearth.atlassian.net).
        # Leave null if Savearth doesn't use Jira Cloud — the pipeline will
        # skip this source and report it.
        endpoint: null
        token_env: JIRA_API_TOKEN
        # Jira user email (for API token auth). ENV var name only.
        email_env: JIRA_USER_EMAIL
        # Jira projects to mirror (keys, e.g. SAVE, IOT, HW). null = all.
        projects: null
        # Map Jira → Plane fields. Plane uses: name, description_html,
        # state (group), priority (urgency), assignee, labels, cycle.
        field_map:
          summary: name
          description: description_html
          status: state
          priority: priority
          assignee: assignee
          labels: labels
          issuetype: type
        status: declared

  # ── Outline: documentation mirror (Confluence → Outline) ───────────────
  outline:
    kind: doc-mirror
    label: "Outline (documentation mirror)"
    endpoint: https://docs.portugalfuturista.org
    token_env: OUTLINE_API_TOKEN
    # Outline collection to mirror into (created if absent).
    collection_name: Savearth Mirror
    sources:
      - id: savearth-confluence
        label: "Savearth Confluence Cloud"
        type: confluence-cloud
        # Confluence Cloud base URL (e.g. https://savearth.atlassian.net/wiki).
        endpoint: null
        token_env: CONFLUENCE_API_TOKEN
        email_env: CONFLUENCE_USER_EMAIL
        # Space keys to mirror (e.g. SAVE, ENG, HW). null = all.
        spaces: null
        # Convert Confluence storage format → Markdown for Outline.
        format: markdown
        # Include attachments? (binary download + re-upload to Outline).
        include_attachments: true
        status: declared

# ── RL feedback loop ──────────────────────────────────────────────────────
# Mirror sync outcomes feed into the RL trajectory pipeline as reward signals.
# When an agent operates on a mirror and the sync detects drift (upstream
# changed but mirror lagged, or an agent's change diverged from upstream),
# that becomes a negative reward signal for the agent's trajectory.
#
# See scripts/sync-mirrors.py --emit-trajectory-rewards and the
# rl-agent-trajectory-training skill for the consumption side.
rl_feedback:
  enabled: true
  # Where to write reward signals (trajectory.jsonl format, appended).
  output: .aurelio/brain/trajectory-rewards/mirror-sync.jsonl
  # Reward shaping: how much each signal type contributes.
  signals:
    # Agent worked on a mirror that was in sync with upstream (positive).
    sync_hit: 0.1
    # Agent worked on a mirror that had drifted from upstream (negative).
    sync_miss: -0.2
    # Agent's mirror change was overwritten by an upstream sync (negative).
    upstream_overwrite: -0.5