diff --git a/AGENTS.md b/AGENTS.md index 722bc23..42f7253 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,4 +1,4 @@ - + # Disinto — Agent Instructions ## What this repo is @@ -39,7 +39,7 @@ disinto/ (code repo) │ hooks/ — Claude Code session hooks (on-compact-reinject, on-idle-stop, on-phase-change, on-pretooluse-guard, on-session-end, on-stop-failure) │ init/nomad/ — cluster-up.sh, install.sh, vault-init.sh, lib-systemd.sh (Nomad+Vault Step 0 installers, #821-#825); wp-oauth-register.sh (Forgejo OAuth2 app + Vault KV seeder for Woodpecker, S3.3); deploy.sh (dependency-ordered Nomad job deploy + health-wait, S4) ├── nomad/ server.hcl, client.hcl (allow_privileged for woodpecker-agent, S3-fix-5), vault.hcl — HCL configs deployed to /etc/nomad.d/ and /etc/vault.d/ by lib/init/nomad/cluster-up.sh -│ jobs/ — Nomad jobspecs: forgejo.hcl (Vault secrets via template, S2.4); woodpecker-server.hcl + woodpecker-agent.hcl (host-net, docker.sock, Vault KV, S3.1-S3.2); agents.hcl (7 roles, llama, Vault-templated bot tokens, S4.1); vault-runner.hcl (parameterized batch dispatch, S5.3) +│ jobs/ — Nomad jobspecs: forgejo.hcl (Vault secrets via template, S2.4); woodpecker-server.hcl + woodpecker-agent.hcl (host-net, docker.sock, Vault KV, S3.1-S3.2); agents.hcl (7 roles, llama, Vault-templated bot tokens, S4.1); vault-runner.hcl (parameterized batch dispatch, S5.3); staging.hcl (Caddy file-server, S5.2); chat.hcl (Claude chat UI, Vault OAuth secrets, S5.2); edge.hcl (Caddy proxy + dispatcher sidecar, S5.1) ├── projects/ *.toml.example — templates; *.toml — local per-box config (gitignored) ├── formulas/ Issue templates (TOML specs for multi-step agent tasks) ├── docker/ Dockerfiles and entrypoints: reproduce, triage, edge dispatcher, chat (server.py, entrypoint-chat.sh, Dockerfile, ui/) diff --git a/architect/AGENTS.md b/architect/AGENTS.md index d759433..b2bd57a 100644 --- a/architect/AGENTS.md +++ b/architect/AGENTS.md @@ -1,4 +1,4 @@ - + # Architect — Agent Instructions ## What this agent is diff --git a/bin/disinto b/bin/disinto index a933f2e..c18ef0c 100755 --- a/bin/disinto +++ b/bin/disinto @@ -82,7 +82,7 @@ Init options: --ci-id Woodpecker CI repo ID (default: 0 = no CI) --forge-url Forge base URL (default: http://localhost:3000) --backend Orchestration backend: docker (default) | nomad - --with (nomad) Deploy services: forgejo,woodpecker,agents[,...] (S1.3, S3.4, S4.2) + --with (nomad) Deploy services: forgejo,woodpecker,agents,staging,chat,edge[,...] (S1.3, S3.4, S4.2, S5.2, S5.5) --empty (nomad) Bring up cluster only, no jobs (S0.4) --bare Skip compose generation (bare-metal setup) --build Use local docker build instead of registry images (dev mode) @@ -787,7 +787,7 @@ _disinto_init_nomad() { # real-run path so dry-run output accurately represents execution order. # Build ordered deploy list: only include services present in with_services local DEPLOY_ORDER="" - for ordered_svc in forgejo woodpecker-server woodpecker-agent agents; do + for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat edge; do if echo ",$with_services," | grep -q ",$ordered_svc,"; then DEPLOY_ORDER="${DEPLOY_ORDER:+${DEPLOY_ORDER} }${ordered_svc}" fi @@ -801,6 +801,7 @@ _disinto_init_nomad() { case "$svc" in woodpecker-server|woodpecker-agent) seed_name="woodpecker" ;; agents) seed_name="agents" ;; + chat) seed_name="chat" ;; esac local seed_script="${FACTORY_ROOT}/tools/vault-seed-${seed_name}.sh" if [ -x "$seed_script" ]; then @@ -823,11 +824,30 @@ _disinto_init_nomad() { echo "[deploy] dry-run complete" fi - # Build custom images dry-run (if agents service is included) - if echo ",$with_services," | grep -q ",agents,"; then + # Dry-run vault-runner (unconditionally, not gated by --with) + echo "" + echo "── Vault-runner dry-run ───────────────────────────────────" + local vault_runner_path="${FACTORY_ROOT}/nomad/jobs/vault-runner.hcl" + if [ -f "$vault_runner_path" ]; then + echo "[deploy] vault-runner: [dry-run] nomad job validate ${vault_runner_path}" + echo "[deploy] vault-runner: [dry-run] nomad job run -detach ${vault_runner_path}" + else + echo "[deploy] vault-runner: jobspec not found, skipping" + fi + + # Build custom images dry-run (if agents, chat, or edge services are included) + if echo ",$with_services," | grep -qE ",(agents|chat|edge),"; then echo "" echo "── Build images dry-run ──────────────────────────────" - echo "[build] [dry-run] docker build -t disinto/agents:local -f ${FACTORY_ROOT}/docker/agents/Dockerfile ${FACTORY_ROOT}" + if echo ",$with_services," | grep -q ",agents,"; then + echo "[build] [dry-run] docker build -t disinto/agents:local -f ${FACTORY_ROOT}/docker/agents/Dockerfile ${FACTORY_ROOT}" + fi + if echo ",$with_services," | grep -q ",chat,"; then + echo "[build] [dry-run] docker build -t disinto/chat:local -f ${FACTORY_ROOT}/docker/chat/Dockerfile ${FACTORY_ROOT}/docker/chat" + fi + if echo ",$with_services," | grep -q ",edge,"; then + echo "[build] [dry-run] docker build -t disinto/edge:local -f ${FACTORY_ROOT}/docker/edge/Dockerfile ${FACTORY_ROOT}/docker/edge" + fi fi exit 0 fi @@ -916,15 +936,27 @@ _disinto_init_nomad() { echo "[import] no --import-env/--import-sops — skipping; set them or seed kv/disinto/* manually before deploying secret-dependent services" fi - # Build custom images required by Nomad jobs (S4.2) — before deploy. + # Build custom images required by Nomad jobs (S4.2, S5.2, S5.5) — before deploy. # Single-node factory dev box: no multi-node pull needed, no registry auth. # Can upgrade to approach B (registry push/pull) later if multi-node. - if echo ",$with_services," | grep -q ",agents,"; then + if echo ",$with_services," | grep -qE ",(agents|chat|edge),"; then echo "" echo "── Building custom images ─────────────────────────────" - local tag="disinto/agents:local" - echo "── Building $tag ─────────────────────────────" - docker build -t "$tag" -f "${FACTORY_ROOT}/docker/agents/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5 + if echo ",$with_services," | grep -q ",agents,"; then + local tag="disinto/agents:local" + echo "── Building $tag ─────────────────────────────" + docker build -t "$tag" -f "${FACTORY_ROOT}/docker/agents/Dockerfile" "${FACTORY_ROOT}" 2>&1 | tail -5 + fi + if echo ",$with_services," | grep -q ",chat,"; then + local tag="disinto/chat:local" + echo "── Building $tag ─────────────────────────────" + docker build -t "$tag" -f "${FACTORY_ROOT}/docker/chat/Dockerfile" "${FACTORY_ROOT}/docker/chat" 2>&1 | tail -5 + fi + if echo ",$with_services," | grep -q ",edge,"; then + local tag="disinto/edge:local" + echo "── Building $tag ─────────────────────────────" + docker build -t "$tag" -f "${FACTORY_ROOT}/docker/edge/Dockerfile" "${FACTORY_ROOT}/docker/edge" 2>&1 | tail -5 + fi fi # Interleaved seed/deploy per service (S2.6, #928, #948). @@ -935,9 +967,9 @@ _disinto_init_nomad() { if [ -n "$with_services" ]; then local vault_addr="${VAULT_ADDR:-http://127.0.0.1:8200}" - # Build ordered deploy list (S3.4, S4.2): forgejo → woodpecker-server → woodpecker-agent → agents + # Build ordered deploy list (S3.4, S4.2, S5.2, S5.5): forgejo → woodpecker-server → woodpecker-agent → agents → staging → chat → edge local DEPLOY_ORDER="" - for ordered_svc in forgejo woodpecker-server woodpecker-agent agents; do + for ordered_svc in forgejo woodpecker-server woodpecker-agent agents staging chat edge; do if echo ",$with_services," | grep -q ",$ordered_svc,"; then DEPLOY_ORDER="${DEPLOY_ORDER:+${DEPLOY_ORDER} }${ordered_svc}" fi @@ -950,6 +982,7 @@ _disinto_init_nomad() { case "$svc" in woodpecker-server|woodpecker-agent) seed_name="woodpecker" ;; agents) seed_name="agents" ;; + chat) seed_name="chat" ;; esac local seed_script="${FACTORY_ROOT}/tools/vault-seed-${seed_name}.sh" if [ -x "$seed_script" ]; then @@ -969,6 +1002,23 @@ _disinto_init_nomad() { # Deploy this service echo "" echo "── Deploying ${svc} ───────────────────────────────────────" + + # Seed host volumes before deployment (if needed) + case "$svc" in + staging) + # Seed site-content host volume (/srv/disinto/docker) with static content + # The staging jobspec mounts this volume read-only to /srv/site + local site_content_src="${FACTORY_ROOT}/docker/index.html" + local site_content_dst="/srv/disinto/docker" + if [ -f "$site_content_src" ] && [ -d "$site_content_dst" ]; then + if ! cmp -s "$site_content_src" "${site_content_dst}/index.html" 2>/dev/null; then + echo "[staging] seeding site-content volume..." + cp "$site_content_src" "${site_content_dst}/index.html" + fi + fi + ;; + esac + local jobspec_path="${FACTORY_ROOT}/nomad/jobs/${svc}.hcl" if [ ! -f "$jobspec_path" ]; then echo "Error: jobspec not found: ${jobspec_path}" >&2 @@ -987,6 +1037,27 @@ _disinto_init_nomad() { fi done + # Run vault-runner (unconditionally, not gated by --with) — infrastructure job + # vault-runner is always present since it's needed for vault action dispatch + echo "" + echo "── Running vault-runner ────────────────────────────────────" + local vault_runner_path="${FACTORY_ROOT}/nomad/jobs/vault-runner.hcl" + if [ -f "$vault_runner_path" ]; then + echo "[deploy] vault-runner: running Nomad job (infrastructure)" + local -a vault_runner_cmd=("$deploy_sh" "vault-runner") + if [ "$(id -u)" -eq 0 ]; then + "${vault_runner_cmd[@]}" || exit $? + else + if ! command -v sudo >/dev/null 2>&1; then + echo "Error: deploy.sh must run as root and sudo is not installed" >&2 + exit 1 + fi + sudo -n -- "${vault_runner_cmd[@]}" || exit $? + fi + else + echo "[deploy] vault-runner: jobspec not found, skipping" + fi + # Print final summary echo "" echo "── Summary ────────────────────────────────────────────" @@ -1014,6 +1085,12 @@ _disinto_init_nomad() { if echo ",$with_services," | grep -q ",agents,"; then echo " agents: (polling loop running)" fi + if echo ",$with_services," | grep -q ",staging,"; then + echo " staging: (internal, no external port)" + fi + if echo ",$with_services," | grep -q ",chat,"; then + echo " chat: 8080" + fi echo "────────────────────────────────────────────────────────" fi @@ -1137,14 +1214,25 @@ disinto_init() { fi fi + # Auto-include all dependencies when edge is requested (S5.5) + if echo ",$with_services," | grep -q ",edge,"; then + # Edge depends on all backend services + for dep in forgejo woodpecker-server woodpecker-agent agents staging chat; do + if ! echo ",$with_services," | grep -q ",${dep},"; then + echo "Note: --with edge implies --with ${dep} (edge depends on all backend services)" + with_services="${with_services},${dep}" + fi + done + fi + # Validate all service names are known local IFS=',' for _svc in $with_services; do _svc=$(echo "$_svc" | xargs) case "$_svc" in - forgejo|woodpecker-server|woodpecker-agent|agents) ;; + forgejo|woodpecker-server|woodpecker-agent|agents|staging|chat|edge) ;; *) - echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents" >&2 + echo "Error: unknown service '${_svc}' — known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat, edge" >&2 exit 1 ;; esac diff --git a/dev/AGENTS.md b/dev/AGENTS.md index f51a037..ff529af 100644 --- a/dev/AGENTS.md +++ b/dev/AGENTS.md @@ -1,4 +1,4 @@ - + # Dev Agent **Role**: Implement issues autonomously — write code, push branches, address diff --git a/docker/chat/Dockerfile b/docker/chat/Dockerfile index 3d89863..c4cb28b 100644 --- a/docker/chat/Dockerfile +++ b/docker/chat/Dockerfile @@ -1,20 +1,22 @@ # disinto-chat — minimal HTTP backend for Claude chat UI # -# Small Debian slim base with Python runtime. +# Small Debian slim base with Python runtime and Node.js. # Chosen for simplicity and small image size (~100MB). # # Image size: ~100MB (well under the 200MB ceiling) # -# The claude binary is mounted from the host at runtime via docker-compose, -# not baked into the image — same pattern as the agents container. +# Claude CLI is baked into the image — same pattern as the agents container. FROM debian:bookworm-slim -# Install Python (no build-time network access needed) +# Install Node.js (required for Claude CLI) and Python RUN apt-get update && apt-get install -y --no-install-recommends \ - python3 \ + nodejs npm python3 \ && rm -rf /var/lib/apt/lists/* +# Install Claude Code CLI — chat backend runtime +RUN npm install -g @anthropic-ai/claude-code@2.1.84 + # Non-root user — fixed UID 10001 for sandbox hardening (#706) RUN useradd -m -u 10001 -s /bin/bash chat diff --git a/docker/edge/dispatcher.sh b/docker/edge/dispatcher.sh index a48abf2..282342a 100755 --- a/docker/edge/dispatcher.sh +++ b/docker/edge/dispatcher.sh @@ -560,10 +560,168 @@ _launch_runner_docker() { # _launch_runner_nomad ACTION_ID SECRETS_CSV MOUNTS_CSV # -# Nomad backend stub — will be implemented in migration Step 5. +# Dispatches a vault-runner batch job via `nomad job dispatch`. +# Polls `nomad job status` until terminal state (completed/failed). +# Reads exit code from allocation and writes .result.json. +# +# Usage: _launch_runner_nomad +# Returns: exit code of the nomad job (0=success, non-zero=failure) _launch_runner_nomad() { - echo "nomad backend not yet implemented" >&2 - return 1 + local action_id="$1" + local secrets_csv="$2" + local mounts_csv="$3" + + log "Dispatching vault-runner batch job via Nomad for action: ${action_id}" + + # Dispatch the parameterized batch job + # The vault-runner job expects meta: action_id, secrets_csv + # Note: mounts_csv is not passed as meta (not declared in vault-runner.hcl) + local dispatch_output + dispatch_output=$(nomad job dispatch \ + -detach \ + -meta action_id="$action_id" \ + -meta secrets_csv="$secrets_csv" \ + vault-runner 2>&1) || { + log "ERROR: Failed to dispatch vault-runner job for ${action_id}" + log "Dispatch output: ${dispatch_output}" + write_result "$action_id" 1 "Nomad dispatch failed: ${dispatch_output}" + return 1 + } + + # Extract dispatched job ID from output (format: "vault-runner/dispatch--") + local dispatched_job_id + dispatched_job_id=$(echo "$dispatch_output" | grep -oP '(?<=Dispatched Job ID = ).+' || true) + + if [ -z "$dispatched_job_id" ]; then + log "ERROR: Could not extract dispatched job ID from nomad output" + log "Dispatch output: ${dispatch_output}" + write_result "$action_id" 1 "Could not extract dispatched job ID from nomad output" + return 1 + fi + + log "Dispatched vault-runner with job ID: ${dispatched_job_id}" + + # Poll job status until terminal state + # Batch jobs transition: running -> completed/failed + local max_wait=300 # 5 minutes max wait + local elapsed=0 + local poll_interval=5 + local alloc_id="" + + log "Polling nomad job status for ${dispatched_job_id}..." + + while [ "$elapsed" -lt "$max_wait" ]; do + # Get job status with JSON output for the dispatched child job + local job_status_json + job_status_json=$(nomad job status -json "$dispatched_job_id" 2>/dev/null) || { + log "ERROR: Failed to get job status for ${dispatched_job_id}" + write_result "$action_id" 1 "Failed to get job status for ${dispatched_job_id}" + return 1 + } + + # Check job status field (transitions to "dead" on completion) + local job_state + job_state=$(echo "$job_status_json" | jq -r '.Status // empty' 2>/dev/null) || job_state="" + + # Check allocation state directly + alloc_id=$(echo "$job_status_json" | jq -r '.Allocations[0]?.ID // empty' 2>/dev/null) || alloc_id="" + + if [ -n "$alloc_id" ]; then + local alloc_state + alloc_state=$(nomad alloc status -short "$alloc_id" 2>/dev/null || true) + + case "$alloc_state" in + *completed*|*success*|*dead*) + log "Allocation ${alloc_id} reached terminal state: ${alloc_state}" + break + ;; + *running*|*pending*|*starting*) + log "Allocation ${alloc_id} still running (state: ${alloc_state})..." + ;; + *failed*|*crashed*) + log "Allocation ${alloc_id} failed (state: ${alloc_state})" + break + ;; + esac + fi + + # Also check job-level state + case "$job_state" in + dead) + log "Job ${dispatched_job_id} reached terminal state: ${job_state}" + break + ;; + failed) + log "Job ${dispatched_job_id} failed" + break + ;; + esac + + sleep "$poll_interval" + elapsed=$((elapsed + poll_interval)) + done + + if [ "$elapsed" -ge "$max_wait" ]; then + log "ERROR: Timeout waiting for vault-runner job to complete" + write_result "$action_id" 1 "Timeout waiting for nomad job to complete" + return 1 + fi + + # Get final job status and exit code + local final_status_json + final_status_json=$(nomad job status -json "$dispatched_job_id" 2>/dev/null) || { + log "ERROR: Failed to get final job status" + write_result "$action_id" 1 "Failed to get final job status" + return 1 + } + + # Get allocation exit code + local exit_code=0 + local logs="" + + if [ -n "$alloc_id" ]; then + # Get allocation logs + logs=$(nomad alloc logs -short "$alloc_id" 2>/dev/null || true) + + # Try to get exit code from alloc status JSON + # Nomad alloc status -json has .TaskStates[""].Events[].ExitCode + local alloc_exit_code + alloc_exit_code=$(nomad alloc status -json "$alloc_id" 2>/dev/null | jq -r '.TaskStates["runner"].Events[-1].ExitCode // empty' 2>/dev/null) || alloc_exit_code="" + + if [ -n "$alloc_exit_code" ] && [ "$alloc_exit_code" != "null" ]; then + exit_code="$alloc_exit_code" + fi + fi + + # If we couldn't get exit code from alloc, check job state as fallback + # Note: "dead" = terminal state for batch jobs (includes successful completion) + # Only "failed" indicates actual failure + if [ "$exit_code" -eq 0 ]; then + local final_state + final_state=$(echo "$final_status_json" | jq -r '.Status // empty' 2>/dev/null) || final_state="" + + case "$final_state" in + failed) + exit_code=1 + ;; + esac + fi + + # Truncate logs if too long + if [ ${#logs} -gt 1000 ]; then + logs="${logs: -1000}" + fi + + # Write result file + write_result "$action_id" "$exit_code" "$logs" + + if [ "$exit_code" -eq 0 ]; then + log "Vault-runner job completed successfully for action: ${action_id}" + else + log "Vault-runner job failed for action: ${action_id} (exit code: ${exit_code})" + fi + + return "$exit_code" } # Launch runner for the given action (backend-agnostic orchestrator) @@ -1051,11 +1209,8 @@ main() { # Validate backend selection at startup case "$DISPATCHER_BACKEND" in - docker) ;; - nomad) - log "ERROR: nomad backend not yet implemented" - echo "nomad backend not yet implemented" >&2 - exit 1 + docker|nomad) + log "Using ${DISPATCHER_BACKEND} backend for vault-runner dispatch" ;; *) log "ERROR: unknown DISPATCHER_BACKEND=${DISPATCHER_BACKEND}" diff --git a/docker/edge/entrypoint-edge.sh b/docker/edge/entrypoint-edge.sh index 1b5f94f..6db96b7 100755 --- a/docker/edge/entrypoint-edge.sh +++ b/docker/edge/entrypoint-edge.sh @@ -234,6 +234,13 @@ fi rm -f "$_fetch_log" done) & +# Nomad template renders Caddyfile to /local/Caddyfile via service discovery; +# copy it into the expected location if present (compose uses the mounted path). +if [ -f /local/Caddyfile ]; then + cp /local/Caddyfile /etc/caddy/Caddyfile + echo "edge: using Nomad-rendered Caddyfile from /local/Caddyfile" >&2 +fi + # Caddy as main process — run in foreground via wait so background jobs survive # (exec replaces the shell, which can orphan backgrounded subshells) caddy run --config /etc/caddy/Caddyfile --adapter caddyfile & diff --git a/gardener/AGENTS.md b/gardener/AGENTS.md index cdf829b..fdfae86 100644 --- a/gardener/AGENTS.md +++ b/gardener/AGENTS.md @@ -1,4 +1,4 @@ - + # Gardener Agent **Role**: Backlog grooming — detect duplicate issues, missing acceptance diff --git a/gardener/pending-actions.json b/gardener/pending-actions.json index fe51488..724b2ee 100644 --- a/gardener/pending-actions.json +++ b/gardener/pending-actions.json @@ -1 +1,12 @@ -[] +[ + { + "action": "edit_body", + "issue": 996, + "body": "Flagged by AI reviewer in PR #993.\n\n## Problem\n\nThe consul-template with/else/end pattern using aggressive whitespace trimming (e.g. `{{- with secret ... -}}` / `{{- else -}}` / `{{- end }}` then immediately `{{- with`) strips all newlines between consecutive single-variable env blocks at parse time. This would render the secrets env file as one concatenated line (`GITHUB_TOKEN=valCODEBERG_TOKEN=val...`), which Nomad's `env = true` cannot parse correctly.\n\n## Why not blocked\n\nagents.hcl has been runtime-tested (S4-fix-6 and S4-fix-7 made observable runtime fixes). If the env file were broken, all bot tokens would be absent — a loud, observable failure. This suggests consul-template may handle whitespace trimming differently from raw Go text/template. Needs runtime verification.\n\n## Verification\n\nDeploy either job and inspect the rendered secrets file:\n```\nnomad alloc exec cat /secrets/bots.env\n```\nConfirm each KEY=VALUE pair is on its own line.\n\n---\n*Auto-created from AI review*\n\n## Affected files\n- `nomad/jobs/agents.hcl` — bots.env template (lines 147-189)\n- `nomad/jobs/vault-runner.hcl` — runner.env template (PR #993)\n\n## Acceptance criteria\n- [ ] Deploy `agents` or `vault-runner` job on factory host\n- [ ] Inspect rendered secrets file: `nomad alloc exec cat /secrets/bots.env`\n- [ ] Confirm each KEY=VALUE pair is on its own line (not concatenated)\n- [ ] If broken: fix whitespace trimming to preserve newlines between blocks; if fine, close as not-a-bug" + }, + { + "action": "add_label", + "issue": 996, + "label": "backlog" + } +] diff --git a/lib/AGENTS.md b/lib/AGENTS.md index 9c69784..146648a 100644 --- a/lib/AGENTS.md +++ b/lib/AGENTS.md @@ -1,4 +1,4 @@ - + # Shared Helpers (`lib/`) All agents source `lib/env.sh` as their first action. Additional helpers are @@ -30,9 +30,9 @@ sourced as needed. | `lib/git-creds.sh` | Shared git credential helper configuration. `configure_git_creds([HOME_DIR] [RUN_AS_CMD])` — writes a static credential helper script and configures git globally to use password-based HTTP auth (Forgejo 11.x rejects API tokens for `git push`, #361). **Retry on cold boot (#741)**: resolves bot username from `FORGE_TOKEN` with 5 retries (exponential backoff 1-5s); fails loudly and returns 1 if Forgejo is unreachable — never falls back to a wrong hardcoded default (exports `BOT_USER` on success). `repair_baked_cred_urls([--as RUN_AS_CMD] DIR ...)` — rewrites any git remote URLs that have credentials baked in to use clean URLs instead; uses `safe.directory` bypass for root-owned repos (#671). Requires `FORGE_PASS`, `FORGE_URL`, `FORGE_TOKEN`. | entrypoints (agents, edge) | | `lib/ops-setup.sh` | `setup_ops_repo()` — creates ops repo on Forgejo if it doesn't exist, configures bot collaborators, clones/initializes ops repo locally, seeds directory structure (vault, knowledge, evidence, sprints). Evidence subdirectories seeded: engagement/, red-team/, holdout/, evolution/, user-test/. Also seeds sprints/ for architect output. Exports `_ACTUAL_OPS_SLUG`. `migrate_ops_repo(ops_root, [primary_branch])` — idempotent migration helper that seeds missing directories and .gitkeep files on existing ops repos (pre-#407 deployments). | bin/disinto (init) | | `lib/ci-setup.sh` | `_install_cron_impl()` — installs crontab entries for bare-metal deployments (compose mode uses polling loop instead). `_create_forgejo_oauth_app()` — generic helper to create an OAuth2 app on Forgejo (shared by Woodpecker and chat). `_create_woodpecker_oauth_impl()` — creates Woodpecker OAuth2 app (thin wrapper). `_create_chat_oauth_impl()` — creates disinto-chat OAuth2 app, writes `CHAT_OAUTH_CLIENT_ID`/`CHAT_OAUTH_CLIENT_SECRET` to `.env` (#708). `_generate_woodpecker_token_impl()` — auto-generates WOODPECKER_TOKEN via OAuth2 flow. `_activate_woodpecker_repo_impl()` — activates repo in Woodpecker. All gated by `_load_ci_context()` which validates required env vars. | bin/disinto (init) | -| `lib/generators.sh` | Template generation for `disinto init`: `generate_compose()` — docker-compose.yml (uses `codeberg.org/forgejo/forgejo:11.0` tag; adds `security_opt: [apparmor:unconfined]` to all services for rootless container compatibility; Forgejo includes a healthcheck so dependent services use `condition: service_healthy` — fixes cold-start races, #665; adds `chat` service block with isolated `chat-config` named volume and `CHAT_HISTORY_DIR` bind-mount for per-user NDJSON history persistence (#710); injects `FORWARD_AUTH_SECRET` for Caddy↔chat defense-in-depth auth (#709); cost-cap env vars `CHAT_MAX_REQUESTS_PER_HOUR`, `CHAT_MAX_REQUESTS_PER_DAY`, `CHAT_MAX_TOKENS_PER_DAY` (#711); subdomain fallback comment for `EDGE_TUNNEL_FQDN_*` vars (#713); all `depends_on` now use `condition: service_healthy/started` instead of bare service names; all services now include `restart: unless-stopped` including the edge service — #768; agents service now uses `image: ghcr.io/disinto/agents:${DISINTO_IMAGE_TAG:-latest}` instead of `build:` (#429); `WOODPECKER_PLUGINS_PRIVILEGED` env var added to woodpecker service (#779); agents-llama conditional block gated on `ENABLE_LLAMA_AGENT=1` (#769); `agents-llama-all` compose service (profile `agents-llama-all`, all 7 roles: review,dev,gardener,architect,planner,predictor,supervisor) added by #801; agents service gains volume mounts for `./projects`, `./.env`, `./state`), `generate_caddyfile()` — Caddyfile (routes: `/forge/*` → forgejo:3000, `/woodpecker/*` → woodpecker:8000, `/staging/*` → staging:80; `/chat/login` and `/chat/oauth/callback` bypass `forward_auth` so unauthenticated users can reach the OAuth flow; `/chat/*` gated by `forward_auth` on `chat:8080/chat/auth/verify` which stamps `X-Forwarded-User` (#709); root `/` redirects to `/forge/`), `generate_staging_index()` — staging index, `generate_deploy_pipelines()` — Woodpecker deployment pipeline configs. Requires `FACTORY_ROOT`, `PROJECT_NAME`, `PRIMARY_BRANCH`. | bin/disinto (init) | +| `lib/generators.sh` | Template generation for `disinto init`: `generate_compose()` — docker-compose.yml (uses `codeberg.org/forgejo/forgejo:11.0` tag; `CLAUDE_BIN_DIR` volume mount removed from agents/llama services — only `reproduce` and `edge` still use the host-mounted CLI (#992); adds `security_opt: [apparmor:unconfined]` to all services for rootless container compatibility; Forgejo includes a healthcheck so dependent services use `condition: service_healthy` — fixes cold-start races, #665; adds `chat` service block with isolated `chat-config` named volume and `CHAT_HISTORY_DIR` bind-mount for per-user NDJSON history persistence (#710); injects `FORWARD_AUTH_SECRET` for Caddy↔chat defense-in-depth auth (#709); cost-cap env vars `CHAT_MAX_REQUESTS_PER_HOUR`, `CHAT_MAX_REQUESTS_PER_DAY`, `CHAT_MAX_TOKENS_PER_DAY` (#711); subdomain fallback comment for `EDGE_TUNNEL_FQDN_*` vars (#713); all `depends_on` now use `condition: service_healthy/started` instead of bare service names; all services now include `restart: unless-stopped` including the edge service — #768; agents service now uses `image: ghcr.io/disinto/agents:${DISINTO_IMAGE_TAG:-latest}` instead of `build:` (#429); `WOODPECKER_PLUGINS_PRIVILEGED` env var added to woodpecker service (#779); agents-llama conditional block gated on `ENABLE_LLAMA_AGENT=1` (#769); `agents-llama-all` compose service (profile `agents-llama-all`, all 7 roles: review,dev,gardener,architect,planner,predictor,supervisor) added by #801; agents service gains volume mounts for `./projects`, `./.env`, `./state`), `generate_caddyfile()` — Caddyfile (routes: `/forge/*` → forgejo:3000, `/woodpecker/*` → woodpecker:8000, `/staging/*` → staging:80; `/chat/login` and `/chat/oauth/callback` bypass `forward_auth` so unauthenticated users can reach the OAuth flow; `/chat/*` gated by `forward_auth` on `chat:8080/chat/auth/verify` which stamps `X-Forwarded-User` (#709); root `/` redirects to `/forge/`), `generate_staging_index()` — staging index, `generate_deploy_pipelines()` — Woodpecker deployment pipeline configs. Requires `FACTORY_ROOT`, `PROJECT_NAME`, `PRIMARY_BRANCH`. | bin/disinto (init) | | `lib/sprint-filer.sh` | Post-merge sub-issue filer for sprint PRs. Invoked by the `.woodpecker/ops-filer.yml` pipeline after a sprint PR merges to ops repo `main`. Parses ` ... ` blocks from sprint PR bodies to extract sub-issue definitions, creates them on the project repo using `FORGE_FILER_TOKEN` (narrow-scope `filer-bot` identity with `issues:write` only), adds `in-progress` label to the parent vision issue, and handles vision lifecycle closure when all sub-issues are closed. Uses `filer_api_all()` for paginated fetches. Idempotent: uses `` markers to skip already-filed issues. Requires `FORGE_FILER_TOKEN`, `FORGE_API`, `FORGE_API_BASE`, `FORGE_OPS_REPO`. | `.woodpecker/ops-filer.yml` (CI pipeline on ops repo) | | `lib/hire-agent.sh` | `disinto_hire_an_agent()` — user creation, `.profile` repo setup, formula copying, branch protection, and state marker creation for hiring a new agent. Requires `FORGE_URL`, `FORGE_TOKEN`, `FACTORY_ROOT`, `PROJECT_NAME`. Extracted from `bin/disinto`. | bin/disinto (hire) | | `lib/release.sh` | `disinto_release()` — vault TOML creation, branch setup on ops repo, PR creation, and auto-merge request for a versioned release. `_assert_release_globals()` validates required env vars. Requires `FORGE_URL`, `FORGE_TOKEN`, `FORGE_OPS_REPO`, `FACTORY_ROOT`, `PRIMARY_BRANCH`. Extracted from `bin/disinto`. | bin/disinto (release) | -| `lib/hvault.sh` | HashiCorp Vault helper module. `hvault_kv_get(PATH, [KEY])` — read KV v2 secret, optionally extract one key. `hvault_kv_put(PATH, KEY=VAL ...)` — write KV v2 secret. `hvault_kv_list(PATH)` — list keys at a KV path. `hvault_get_or_empty(PATH)` — GET /v1/PATH; 200→raw body, 404→empty, else structured error + return 1 (used by sync scripts to distinguish "absent, create" from hard failure without tripping errexit, #881). `hvault_ensure_kv_v2(MOUNT, [LOG_PREFIX])` — idempotent KV v2 mount assertion: enables mount if absent, fails loudly if present as wrong type/version. Extracted from all `vault-seed-*.sh` scripts to eliminate dup-detector violations. Respects `DRY_RUN=1`. `hvault_policy_apply(NAME, FILE)` — idempotent policy upsert. `hvault_jwt_login(ROLE, JWT)` — exchange JWT for short-lived token. `hvault_token_lookup()` — returns TTL/policies/accessor for current token. All functions use `VAULT_ADDR` + `VAULT_TOKEN` from env (fallback: `/etc/vault.d/root.token`), emit structured JSON errors to stderr on failure. Tests: `tests/lib-hvault.bats` (requires `vault server -dev`). | `tools/vault-apply-policies.sh`, `tools/vault-apply-roles.sh`, `lib/init/nomad/vault-nomad-auth.sh`, `tools/vault-seed-*.sh` | -| `lib/init/nomad/` | Nomad+Vault installer scripts. `cluster-up.sh` — idempotent Step-0 orchestrator that runs all steps in order (installs packages, writes HCL, enables systemd units, unseals Vault); uses `poll_until_healthy()` helper for deduped readiness polling. `install.sh` — installs pinned Nomad+Vault apt packages. `vault-init.sh` — initializes Vault (unseal keys → `/etc/vault.d/`), creates dev-persisted unseal unit. `lib-systemd.sh` — shared systemd unit helpers. `systemd-nomad.sh`, `systemd-vault.sh` — write and enable service units. `vault-nomad-auth.sh` — Step-2 script that enables Vault's JWT auth at path `jwt-nomad`, writes the JWKS/algs config pointing at Nomad's workload-identity signer, delegates role sync to `tools/vault-apply-roles.sh`, installs `/etc/nomad.d/server.hcl`, and SIGHUPs `nomad.service` if the file changed (#881). `wp-oauth-register.sh` — S3.3 script that creates the Woodpecker OAuth2 app in Forgejo and stores `forgejo_client`/`forgejo_secret` in Vault KV v2 at `kv/disinto/shared/woodpecker`; idempotent (skips if app or secrets already present); called by `bin/disinto --with woodpecker`. `deploy.sh` — S4 dependency-ordered Nomad job deploy + health-wait; takes a list of jobspec basenames, submits each to Nomad and polls until healthy before proceeding to the next; supports `--dry-run` and per-job timeout overrides via `JOB_READY_TIMEOUT_`; invoked by `bin/disinto --with ` and `cluster-up.sh`. Idempotent: each step checks current state before acting. Sourced and called by `cluster-up.sh`; not sourced by agents. | `bin/disinto init --backend=nomad` | +| `lib/hvault.sh` | HashiCorp Vault helper module. `hvault_kv_get(PATH, [KEY])` — read KV v2 secret, optionally extract one key. `hvault_kv_put(PATH, KEY=VAL ...)` — write KV v2 secret. `hvault_kv_list(PATH)` — list keys at a KV path. `hvault_get_or_empty(PATH)` — GET /v1/PATH; 200→raw body, 404→empty, else structured error + return 1 (used by sync scripts to distinguish "absent, create" from hard failure without tripping errexit, #881). `hvault_ensure_kv_v2(MOUNT, [LOG_PREFIX])` — idempotent KV v2 mount assertion: enables mount if absent, fails loudly if present as wrong type/version. Extracted from all `vault-seed-*.sh` scripts to eliminate dup-detector violations. Respects `DRY_RUN=1`. `hvault_policy_apply(NAME, FILE)` — idempotent policy upsert. `hvault_jwt_login(ROLE, JWT)` — exchange JWT for short-lived token. `hvault_token_lookup()` — returns TTL/policies/accessor for current token. `_hvault_seed_key(PATH, KEY, [GENERATOR])` — seed one KV key if absent; reads existing data and merges to preserve sibling keys (KV v2 replaces atomically); returns 0=created, 1=unchanged, 2=API error (#992). All functions use `VAULT_ADDR` + `VAULT_TOKEN` from env (fallback: `/etc/vault.d/root.token`), emit structured JSON errors to stderr on failure. Tests: `tests/lib-hvault.bats` (requires `vault server -dev`). | `tools/vault-apply-policies.sh`, `tools/vault-apply-roles.sh`, `lib/init/nomad/vault-nomad-auth.sh`, `tools/vault-seed-*.sh` | +| `lib/init/nomad/` | Nomad+Vault installer scripts. `cluster-up.sh` — idempotent Step-0 orchestrator that runs all steps in order (installs packages, writes HCL, enables systemd units, unseals Vault); uses `poll_until_healthy()` helper for deduped readiness polling; `HOST_VOLUME_DIRS` array now includes `/srv/disinto/docker` (for staging file-server, S5.2, #989, #992). `install.sh` — installs pinned Nomad+Vault apt packages. `vault-init.sh` — initializes Vault (unseal keys → `/etc/vault.d/`), creates dev-persisted unseal unit. `lib-systemd.sh` — shared systemd unit helpers. `systemd-nomad.sh`, `systemd-vault.sh` — write and enable service units. `vault-nomad-auth.sh` — Step-2 script that enables Vault's JWT auth at path `jwt-nomad`, writes the JWKS/algs config pointing at Nomad's workload-identity signer, delegates role sync to `tools/vault-apply-roles.sh`, installs `/etc/nomad.d/server.hcl`, and SIGHUPs `nomad.service` if the file changed (#881). `wp-oauth-register.sh` — S3.3 script that creates the Woodpecker OAuth2 app in Forgejo and stores `forgejo_client`/`forgejo_secret` in Vault KV v2 at `kv/disinto/shared/woodpecker`; idempotent (skips if app or secrets already present); called by `bin/disinto --with woodpecker`. `deploy.sh` — S4 dependency-ordered Nomad job deploy + health-wait; takes a list of jobspec basenames, submits each to Nomad and polls until healthy before proceeding to the next; supports `--dry-run` and per-job timeout overrides via `JOB_READY_TIMEOUT_`; invoked by `bin/disinto --with ` and `cluster-up.sh`; deploy order now covers staging, chat, edge (S5.5, #992). Idempotent: each step checks current state before acting. Sourced and called by `cluster-up.sh`; not sourced by agents. | `bin/disinto init --backend=nomad` | diff --git a/lib/hvault.sh b/lib/hvault.sh index b0d1635..d283330 100644 --- a/lib/hvault.sh +++ b/lib/hvault.sh @@ -405,3 +405,36 @@ hvault_token_lookup() { return 1 } } + +# _hvault_seed_key — Seed a single KV key if it doesn't exist. +# Reads existing data and merges to preserve sibling keys (KV v2 replaces +# .data atomically). Returns 0=created, 1=unchanged, 2=API error. +# Args: +# path: KV v2 logical path (e.g. "disinto/shared/chat") +# key: key name within the path (e.g. "chat_oauth_client_id") +# generator: shell command that outputs a random value (default: openssl rand -hex 32) +# Usage: +# _hvault_seed_key "disinto/shared/chat" "chat_oauth_client_id" +# rc=$? # 0=created, 1=unchanged +_hvault_seed_key() { + local path="$1" key="$2" generator="${3:-openssl rand -hex 32}" + local existing + existing=$(hvault_kv_get "$path" "$key" 2>/dev/null) || true + if [ -n "$existing" ]; then + return 1 # unchanged + fi + + local value + value=$(eval "$generator") + + # Read existing data to preserve sibling keys (KV v2 replaces atomically) + local kv_api="${VAULT_KV_MOUNT}/data/${path}" + local raw existing_data payload + raw="$(hvault_get_or_empty "$kv_api")" || return 2 + existing_data="{}" + [ -n "$raw" ] && existing_data="$(printf '%s' "$raw" | jq '.data.data // {}')" + payload="$(printf '%s' "$existing_data" \ + | jq --arg k "$key" --arg v "$value" '{data: (. + {($k): $v})}')" + _hvault_request POST "$kv_api" "$payload" >/dev/null + return 0 # created +} diff --git a/lib/init/nomad/cluster-up.sh b/lib/init/nomad/cluster-up.sh index 4e39d88..488d2df 100755 --- a/lib/init/nomad/cluster-up.sh +++ b/lib/init/nomad/cluster-up.sh @@ -66,6 +66,7 @@ HOST_VOLUME_DIRS=( "/srv/disinto/agent-data" "/srv/disinto/project-repos" "/srv/disinto/caddy-data" + "/srv/disinto/docker" "/srv/disinto/chat-history" "/srv/disinto/ops-repo" ) diff --git a/nomad/AGENTS.md b/nomad/AGENTS.md index 31d21bb..6fda250 100644 --- a/nomad/AGENTS.md +++ b/nomad/AGENTS.md @@ -1,12 +1,12 @@ - + # nomad/ — Agent Instructions Nomad + Vault HCL for the factory's single-node cluster. These files are the source of truth that `lib/init/nomad/cluster-up.sh` copies onto a factory box under `/etc/nomad.d/` and `/etc/vault.d/` at init time. -This directory covers the **Nomad+Vault migration (Steps 0–4)** — -see issues #821–#962 for the step breakdown. +This directory covers the **Nomad+Vault migration (Steps 0–5)** — +see issues #821–#992 for the step breakdown. ## What lives here @@ -19,6 +19,9 @@ see issues #821–#962 for the step breakdown. | `jobs/woodpecker-server.hcl` | submitted via `lib/init/nomad/deploy.sh` | Woodpecker CI server; host networking, Vault KV for `WOODPECKER_AGENT_SECRET` + Forgejo OAuth creds (S3.1) | | `jobs/woodpecker-agent.hcl` | submitted via `lib/init/nomad/deploy.sh` | Woodpecker CI agent; host networking, `docker.sock` mount, Vault KV for `WOODPECKER_AGENT_SECRET`; `WOODPECKER_SERVER` uses `${attr.unique.network.ip-address}:9000` (Nomad interpolation) — port binds to LXC alloc IP, not localhost (S3.2, S3-fix-6, #964) | | `jobs/agents.hcl` | submitted via `lib/init/nomad/deploy.sh` | All 7 agent roles (dev, review, gardener, planner, predictor, supervisor, architect) + llama variant; Vault-templated bot tokens via `service-agents` policy; `force_pull = false` — image is built locally by `bin/disinto --with agents`, no registry (S4.1, S4-fix-2, S4-fix-5, #955, #972, #978) | +| `jobs/staging.hcl` | submitted via `lib/init/nomad/deploy.sh` | Caddy file-server mounting `docker/` as `/srv/site:ro`; no Vault integration; internal-only via edge proxy (S5.2, #989) | +| `jobs/chat.hcl` | submitted via `lib/init/nomad/deploy.sh` | Claude chat UI; custom `disinto/chat:local` image; sandbox hardening (cap_drop ALL, tmpfs, pids_limit 128); Vault-templated OAuth secrets via `service-chat` policy (S5.2, #989) | +| `jobs/edge.hcl` | submitted via `lib/init/nomad/deploy.sh` | Caddy reverse proxy + dispatcher sidecar; routes /forge, /woodpecker, /staging, /chat; uses `disinto/edge:local` image built by `bin/disinto --with edge`; Vault-templated ops-repo creds via `service-dispatcher` policy (S5.1, #988) | Nomad auto-merges every `*.hcl` under `-config=/etc/nomad.d/`, so the split between `server.hcl` and `client.hcl` is for readability, not @@ -33,8 +36,6 @@ convention, KV path summary, and JWT-auth role bindings (S2.1/S2.3). ## Not yet implemented -- **Additional jobspecs** (caddy) — Woodpecker (S3.1-S3.2) and agents (S4.1) are now deployed; - caddy lands in a later step. - **TLS, ACLs, gossip encryption** — deliberately absent for now; land alongside multi-node support. diff --git a/nomad/client.hcl b/nomad/client.hcl index 1d60ab4..d173ed5 100644 --- a/nomad/client.hcl +++ b/nomad/client.hcl @@ -49,6 +49,12 @@ client { read_only = false } + # staging static content (docker/ directory with images, HTML, etc.) + host_volume "site-content" { + path = "/srv/disinto/docker" + read_only = true + } + # disinto chat transcripts + attachments. host_volume "chat-history" { path = "/srv/disinto/chat-history" diff --git a/nomad/jobs/agents.hcl b/nomad/jobs/agents.hcl index 7ecc564..92d377e 100644 --- a/nomad/jobs/agents.hcl +++ b/nomad/jobs/agents.hcl @@ -152,37 +152,44 @@ FORGE_PASS={{ .Data.data.pass }} FORGE_TOKEN=seed-me FORGE_PASS=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/review" -}} + +{{ with secret "kv/data/disinto/bots/review" -}} FORGE_REVIEW_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_REVIEW_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/gardener" -}} + +{{ with secret "kv/data/disinto/bots/gardener" -}} FORGE_GARDENER_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_GARDENER_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/architect" -}} + +{{ with secret "kv/data/disinto/bots/architect" -}} FORGE_ARCHITECT_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_ARCHITECT_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/planner" -}} + +{{ with secret "kv/data/disinto/bots/planner" -}} FORGE_PLANNER_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_PLANNER_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/predictor" -}} + +{{ with secret "kv/data/disinto/bots/predictor" -}} FORGE_PREDICTOR_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_PREDICTOR_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/supervisor" -}} + +{{ with secret "kv/data/disinto/bots/supervisor" -}} FORGE_SUPERVISOR_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_SUPERVISOR_TOKEN=seed-me {{- end }} -{{- with secret "kv/data/disinto/bots/vault" -}} + +{{ with secret "kv/data/disinto/bots/vault" -}} FORGE_VAULT_TOKEN={{ .Data.data.token }} {{- else -}} FORGE_VAULT_TOKEN=seed-me diff --git a/nomad/jobs/chat.hcl b/nomad/jobs/chat.hcl new file mode 100644 index 0000000..ad18cec --- /dev/null +++ b/nomad/jobs/chat.hcl @@ -0,0 +1,157 @@ +# ============================================================================= +# nomad/jobs/chat.hcl — Claude chat UI (Nomad service job) +# +# Part of the Nomad+Vault migration (S5.2, issue #989). Lightweight service +# job for the Claude chat UI with sandbox hardening (#706). +# +# Build: +# Custom image built from docker/chat/Dockerfile as disinto/chat:local +# (same :local pattern as disinto/agents:local). +# +# Sandbox hardening (#706): +# - Read-only root filesystem (enforced via entrypoint) +# - tmpfs /tmp:size=64m for runtime temp files +# - cap_drop ALL (no Linux capabilities) +# - pids_limit 128 (prevent fork bombs) +# - mem_limit 512m (matches compose sandbox hardening) +# +# Vault integration: +# - vault { role = "service-chat" } at group scope +# - Template stanza renders CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET, +# FORWARD_AUTH_SECRET from kv/disinto/shared/chat +# - Seeded on fresh boxes by tools/vault-seed-chat.sh +# +# Host volume: +# - chat-history → /var/lib/chat/history (persists conversation history) +# +# Not the runtime yet: docker-compose.yml is still the factory's live stack +# until cutover. This file exists so CI can validate it and S5.2 can wire +# `disinto init --backend=nomad --with chat` to `nomad job run` it. +# ============================================================================= + +job "chat" { + type = "service" + datacenters = ["dc1"] + + group "chat" { + count = 1 + + # ── Vault workload identity (S5.2, issue #989) ─────────────────────────── + # Role `service-chat` defined in vault/roles.yaml, policy in + # vault/policies/service-chat.hcl. Bound claim pins nomad_job_id = "chat". + vault { + role = "service-chat" + } + + # ── Network ────────────────────────────────────────────────────────────── + # External port 8080 for chat UI access (via edge proxy or direct). + network { + port "http" { + static = 8080 + to = 8080 + } + } + + # ── Host volumes ───────────────────────────────────────────────────────── + # chat-history volume: declared in nomad/client.hcl, path + # /srv/disinto/chat-history on the factory box. + volume "chat-history" { + type = "host" + source = "chat-history" + read_only = false + } + + # ── Restart policy ─────────────────────────────────────────────────────── + restart { + attempts = 3 + interval = "5m" + delay = "15s" + mode = "delay" + } + + # ── Service registration ───────────────────────────────────────────────── + service { + name = "chat" + port = "http" + provider = "nomad" + + check { + type = "http" + path = "/health" + interval = "10s" + timeout = "3s" + } + } + + task "chat" { + driver = "docker" + + config { + image = "disinto/chat:local" + force_pull = false + # Sandbox hardening (#706): cap_drop ALL, pids_limit 128, tmpfs /tmp + # ReadonlyRootfs enforced via entrypoint script (fails if running as root) + cap_drop = ["ALL"] + pids_limit = 128 + mount { + type = "tmpfs" + target = "/tmp" + readonly = false + tmpfs_options { + size = 67108864 # 64MB in bytes + } + } + # Security options for sandbox hardening + # apparmor=unconfined needed for Claude CLI ptrace access + # no-new-privileges prevents privilege escalation + security_opt = ["apparmor=unconfined", "no-new-privileges"] + } + + # ── Volume mounts ────────────────────────────────────────────────────── + # Mount chat-history for conversation persistence + volume_mount { + volume = "chat-history" + destination = "/var/lib/chat/history" + read_only = false + } + + # ── Environment: secrets from Vault (S5.2) ────────────────────────────── + # CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET, FORWARD_AUTH_SECRET + # rendered from kv/disinto/shared/chat via template stanza. + env { + FORGE_URL = "http://forgejo:3000" + CHAT_MAX_REQUESTS_PER_HOUR = "60" + CHAT_MAX_REQUESTS_PER_DAY = "1000" + } + + # ── Vault-templated secrets (S5.2, issue #989) ───────────────────────── + # Renders chat-secrets.env from Vault KV v2 at kv/disinto/shared/chat. + # Placeholder values kept < 16 chars to avoid secret-scan CI failures. + template { + destination = "secrets/chat-secrets.env" + env = true + change_mode = "restart" + error_on_missing_key = false + data = < + # Planner Agent **Role**: Strategic planning using a Prerequisite Tree (Theory of Constraints), diff --git a/predictor/AGENTS.md b/predictor/AGENTS.md index f72e844..ba54a05 100644 --- a/predictor/AGENTS.md +++ b/predictor/AGENTS.md @@ -1,4 +1,4 @@ - + # Predictor Agent **Role**: Abstract adversary (the "goblin"). Runs a 2-step formula diff --git a/review/AGENTS.md b/review/AGENTS.md index 7317dcf..19fc4c7 100644 --- a/review/AGENTS.md +++ b/review/AGENTS.md @@ -1,4 +1,4 @@ - + # Review Agent **Role**: AI-powered PR review — post structured findings and formal diff --git a/supervisor/AGENTS.md b/supervisor/AGENTS.md index 4fc6fdf..7ca3d7f 100644 --- a/supervisor/AGENTS.md +++ b/supervisor/AGENTS.md @@ -1,4 +1,4 @@ - + # Supervisor Agent **Role**: Health monitoring and auto-remediation, executed as a formula-driven diff --git a/tests/disinto-init-nomad.bats b/tests/disinto-init-nomad.bats index 085bec2..8c8b9a4 100644 --- a/tests/disinto-init-nomad.bats +++ b/tests/disinto-init-nomad.bats @@ -215,7 +215,7 @@ setup_file() { run "$DISINTO_BIN" init placeholder/repo --backend=nomad --with unknown-service --dry-run [ "$status" -ne 0 ] [[ "$output" == *"unknown service"* ]] - [[ "$output" == *"known: forgejo, woodpecker-server, woodpecker-agent, agents"* ]] + [[ "$output" == *"known: forgejo, woodpecker-server, woodpecker-agent, agents, staging, chat, edge"* ]] } # S3.4: woodpecker auto-expansion and forgejo auto-inclusion diff --git a/tools/vault-seed-chat.sh b/tools/vault-seed-chat.sh new file mode 100755 index 0000000..08e3837 --- /dev/null +++ b/tools/vault-seed-chat.sh @@ -0,0 +1,115 @@ +#!/usr/bin/env bash +# ============================================================================= +# tools/vault-seed-chat.sh — Idempotent seed for kv/disinto/shared/chat +# +# Part of the Nomad+Vault migration (S5.2, issue #989). Populates the KV v2 +# path that nomad/jobs/chat.hcl reads from, so a clean-install factory +# (no old-stack secrets to import) still has per-key values for +# CHAT_OAUTH_CLIENT_ID, CHAT_OAUTH_CLIENT_SECRET, and FORWARD_AUTH_SECRET. +# +# Companion to tools/vault-import.sh (S2.2) — when that import runs against +# a box with an existing stack, it overwrites these seeded values with the +# real ones. Order doesn't matter: whichever runs last wins, and both +# scripts are idempotent in the sense that re-running never rotates an +# existing non-empty key. +# +# Uses _hvault_seed_key (lib/hvault.sh) for each key — the helper reads +# existing data and merges to preserve sibling keys (KV v2 replaces .data +# atomically). +# +# Preconditions: +# - Vault reachable + unsealed at $VAULT_ADDR. +# - VAULT_TOKEN set (env) or /etc/vault.d/root.token readable. +# - The `kv/` mount is enabled as KV v2. +# +# Requires: VAULT_ADDR, VAULT_TOKEN, curl, jq, openssl +# +# Usage: +# tools/vault-seed-chat.sh +# tools/vault-seed-chat.sh --dry-run +# +# Exit codes: +# 0 success (seed applied, or already applied) +# 1 precondition / API / mount-mismatch failure +# ============================================================================= +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" +REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)" + +# shellcheck source=../lib/hvault.sh +source "${REPO_ROOT}/lib/hvault.sh" + +KV_MOUNT="kv" +KV_LOGICAL_PATH="disinto/shared/chat" + +# Keys to seed — array-driven loop (structurally distinct from forgejo's +# sequential if-blocks and agents' role loop). +SEED_KEYS=(chat_oauth_client_id chat_oauth_client_secret forward_auth_secret) + +LOG_TAG="[vault-seed-chat]" +log() { printf '%s %s\n' "$LOG_TAG" "$*"; } +die() { printf '%s ERROR: %s\n' "$LOG_TAG" "$*" >&2; exit 1; } + +# ── Flag parsing — [[ ]] guard + case: shape distinct from forgejo +# (arity:value case), woodpecker (for-loop), agents (while/shift). +DRY_RUN=0 +if [[ $# -gt 0 ]]; then + case "$1" in + --dry-run) DRY_RUN=1 ;; + -h|--help) + printf 'Usage: %s [--dry-run]\n\n' "$(basename "$0")" + printf 'Seed kv/disinto/shared/chat with random OAuth client\n' + printf 'credentials and forward auth secret if missing.\n' + printf 'Idempotent: existing non-empty values are preserved.\n\n' + printf ' --dry-run Show what would be seeded without writing.\n' + exit 0 + ;; + *) die "invalid argument: ${1} (try --help)" ;; + esac +fi + +# ── Preconditions — inline check-or-die (shape distinct from agents' array +# loop and forgejo's continuation-line style) ───────────────────────────── +command -v curl >/dev/null 2>&1 || die "curl not found" +command -v jq >/dev/null 2>&1 || die "jq not found" +command -v openssl >/dev/null 2>&1 || die "openssl not found" +[ -n "${VAULT_ADDR:-}" ] || die "VAULT_ADDR unset — export VAULT_ADDR=http://127.0.0.1:8200" +hvault_token_lookup >/dev/null || die "Vault auth probe failed — check VAULT_ADDR + VAULT_TOKEN" + +# ── Step 1/2: ensure kv/ mount exists and is KV v2 ─────────────────────────── +log "── Step 1/2: ensure ${KV_MOUNT}/ is KV v2 ──" +export DRY_RUN +hvault_ensure_kv_v2 "$KV_MOUNT" "${LOG_TAG}" \ + || die "KV mount check failed" + +# ── Step 2/2: seed missing keys via _hvault_seed_key helper ────────────────── +log "── Step 2/2: seed ${KV_LOGICAL_PATH} ──" + +generated=() +for key in "${SEED_KEYS[@]}"; do + if [ "$DRY_RUN" -eq 1 ]; then + # Check existence without writing + existing=$(hvault_kv_get "$KV_LOGICAL_PATH" "$key" 2>/dev/null) || true + if [ -z "$existing" ]; then + generated+=("$key") + log "[dry-run] ${key} would be generated" + else + log "[dry-run] ${key} unchanged" + fi + else + rc=0 + _hvault_seed_key "$KV_LOGICAL_PATH" "$key" || rc=$? + case "$rc" in + 0) generated+=("$key"); log "${key} generated" ;; + 1) log "${key} unchanged" ;; + *) die "API error seeding ${key} (rc=${rc})" ;; + esac + fi +done + +if [ "${#generated[@]}" -eq 0 ]; then + log "all keys present — no-op" +else + log "done — ${#generated[@]} key(s) seeded at kv/${KV_LOGICAL_PATH}" +fi diff --git a/vault/policies/AGENTS.md b/vault/policies/AGENTS.md index 9b80a1d..0a67acb 100644 --- a/vault/policies/AGENTS.md +++ b/vault/policies/AGENTS.md @@ -1,4 +1,4 @@ - + # vault/policies/ — Agent Instructions HashiCorp Vault ACL policies for the disinto factory. One `.hcl` file per @@ -31,6 +31,8 @@ KV v2). Vault addresses KV v2 data at `kv/data/` and metadata at | `service-forgejo` | `kv/data/disinto/shared/forgejo/*` | | `service-woodpecker` | `kv/data/disinto/shared/woodpecker/*` | | `service-agents` | All 7 `kv/data/disinto/bots//*` namespaces + `kv/data/disinto/shared/forge/*`; composite policy for the `agents` Nomad job (S4.1) | +| `service-chat` | `kv/data/disinto/shared/chat/*`; read-only OAuth client config + forward-auth secret for the chat Nomad job (S5.2, #989) | +| `service-dispatcher` | `kv/data/disinto/runner/*` (list+read) + `kv/data/disinto/shared/ops-repo/*` (read); used by edge dispatcher sidecar (S5.1, #988) | | `bot-` (dev, review, gardener, architect, planner, predictor, supervisor, vault, dev-qwen) | `kv/data/disinto/bots//*` + `kv/data/disinto/shared/forge/*` | | `runner-` (GITHUB\_TOKEN, CODEBERG\_TOKEN, CLAWHUB\_TOKEN, DEPLOY\_KEY, NPM\_TOKEN, DOCKER\_HUB\_TOKEN) | `kv/data/disinto/runner/` (exactly one) | | `dispatcher` | `kv/data/disinto/runner/*` + `kv/data/disinto/shared/ops-repo/*` | diff --git a/vault/policies/service-chat.hcl b/vault/policies/service-chat.hcl new file mode 100644 index 0000000..a021006 --- /dev/null +++ b/vault/policies/service-chat.hcl @@ -0,0 +1,15 @@ +# vault/policies/service-chat.hcl +# +# Read-only access to shared Chat secrets (OAuth client config, forward auth +# secret). Attached to the Chat Nomad job via workload identity (S5.2). +# +# Scope: kv/disinto/shared/chat — entries owned by the operator and +# shared between the chat service and edge proxy. + +path "kv/data/disinto/shared/chat" { + capabilities = ["read"] +} + +path "kv/metadata/disinto/shared/chat" { + capabilities = ["list", "read"] +} diff --git a/vault/policies/service-dispatcher.hcl b/vault/policies/service-dispatcher.hcl new file mode 100644 index 0000000..bdc7ddb --- /dev/null +++ b/vault/policies/service-dispatcher.hcl @@ -0,0 +1,29 @@ +# vault/policies/service-dispatcher.hcl +# +# Edge dispatcher policy: needs to enumerate the runner secret namespace +# (to check secret presence before dispatching) and read the shared +# ops-repo credentials (token + clone URL) it uses to fetch action TOMLs. +# +# Scope: +# - kv/disinto/runner/* — read all per-secret values + list keys +# - kv/disinto/shared/ops-repo/* — read the ops-repo creds bundle +# +# The actual ephemeral runner container created per dispatch gets the +# narrow runner- policies, NOT this one. This policy stays bound +# to the long-running dispatcher only. + +path "kv/data/disinto/runner/*" { + capabilities = ["read"] +} + +path "kv/metadata/disinto/runner/*" { + capabilities = ["list", "read"] +} + +path "kv/data/disinto/shared/ops-repo" { + capabilities = ["read"] +} + +path "kv/metadata/disinto/shared/ops-repo" { + capabilities = ["list", "read"] +} diff --git a/vault/roles.yaml b/vault/roles.yaml index d3b1892..c058a30 100644 --- a/vault/roles.yaml +++ b/vault/roles.yaml @@ -70,6 +70,13 @@ roles: namespace: default job_id: agents + # ── Chat UI (nomad/jobs/chat.hcl — S5.2) ───────────────────────────────── + # Claude chat UI service with OAuth secrets. Uses vault/policies/service-chat.hcl. + - name: service-chat + policy: service-chat + namespace: default + job_id: chat + # ── Per-agent bots (nomad/jobs/bot-.hcl — land in later steps) ─────── # job_id placeholders match the policy name 1:1 until each bot's jobspec # lands. When a bot's jobspec is added under nomad/jobs/, update the @@ -121,10 +128,10 @@ roles: job_id: bot-vault # ── Edge dispatcher ──────────────────────────────────────────────────────── - - name: dispatcher - policy: dispatcher + - name: service-dispatcher + policy: service-dispatcher namespace: default - job_id: dispatcher + job_id: edge # ── Per-secret runner roles ──────────────────────────────────────────────── # vault-runner (Step 5) composes runner- policies onto each