Merge pull request #1 from madhura68/feat/gh-token-clone-bootstrap

feat(bootstrap): GH_TOKEN clone-on-start for Scrum4Me + scrum4me-mcp

.env.example

@@ -22,6 +22,28 @@ CLAUDE_CODE_OAUTH_TOKEN=sk-ant-oat01-vervang-mij
 # Als deze ge-revoked wordt: rebuild + redeploy (zie README).
 SCRUM4ME_TOKEN=vervang-mij
 
+# ----- GitHub credentials -----------------------------------
+# Personal Access Token (fine-grained) met:
+#   - Repository access op madhura68/Scrum4Me + madhura68/scrum4me-mcp
+#   - Permissions: Contents (read/write), Pull requests (read/write),
+#                  Metadata (read)
+#
+# Gebruikt voor:
+#   1. Pre-clone van de repos in /home/agent/Projects/<name>/ bij
+#      container-start (entrypoint.sh)
+#   2. `git push` van agent feature-branches via HTTPS
+#   3. `gh pr create` (auto_pr=true) — gh CLI leest GH_TOKEN uit env
+#
+# Genereer op github.com → Settings → Developer settings →
+# Personal access tokens → Fine-grained tokens.
+GH_TOKEN=ghp_vervang-mij
+
+# Lijst (komma-gescheiden) van repos om vooraf te clonen naar
+# ~agent/Projects/<name>. resolveRepoRoot in scrum4me-mcp valt
+# automatisch terug op die conventie. Voeg meer toe als je nieuwe
+# producten/repos toevoegt aan Scrum4Me.
+GH_PRECLONE_REPOS=madhura68/Scrum4Me,madhura68/scrum4me-mcp
+
 # ----- Scrum4Me database ------------------------------------
 # Beide URLs uit het Neon-dashboard. DATABASE_URL is pooled,
 # DIRECT_URL is unpooled — scrum4me-mcp gebruikt DATABASE_URL

Dockerfile

@@ -12,10 +12,24 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
         ca-certificates curl git tini gosu jq xz-utils \
         build-essential python3 \
         tzdata logrotate \
+        gnupg \
     && ln -fs /usr/share/zoneinfo/$TZ /etc/localtime \
     && dpkg-reconfigure --frontend=noninteractive tzdata \
     && rm -rf /var/lib/apt/lists/*
 
+# ----- gh CLI ------------------------------------------------------------
+# Required for auto_pr (`gh pr create`) and authenticates via the GH_TOKEN
+# env-var that is also used by the git credential helper for HTTPS.
+RUN install -m 0755 -d /etc/apt/keyrings \
+    && curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg \
+       | gpg --dearmor -o /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+    && chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+    && echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" \
+       > /etc/apt/sources.list.d/github-cli.list \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends gh \
+    && rm -rf /var/lib/apt/lists/*
+
 # ----- node 22 LTS -------------------------------------------------------
 # Voor zowel Claude Code (de native installer heeft geen node nodig, maar
 # scrum4me-mcp draait op tsx) als de health-server.
@@ -56,6 +70,7 @@ ARG AGENT_GID=1000
 RUN groupadd -g ${AGENT_GID} agent \
     && useradd  -u ${AGENT_UID} -g ${AGENT_GID} -m -s /bin/bash agent \
     && mkdir -p /var/cache/repos /var/cache/npm /var/log/agent /var/run/agent \
+    && mkdir -p /home/agent/Projects /home/agent/.scrum4me-agent-worktrees \
     && chown -R agent:agent /var/cache /var/log/agent /var/run/agent /home/agent
 
 # ----- runner files ------------------------------------------------------

README.md

@@ -71,6 +71,13 @@ fouten.
 #    b. SCRUM4ME_TOKEN           →  log in als de dedicated agent-user in
 #                                   Scrum4Me, /settings/tokens, label "NAS-runner"
 #    c. DATABASE_URL/DIRECT_URL  →  Neon dashboard
+#    d. GH_TOKEN                 →  github.com → Settings → Developer settings →
+#                                   Personal access tokens → Fine-grained.
+#                                   Repository access op madhura68/Scrum4Me +
+#                                   madhura68/scrum4me-mcp; Permissions:
+#                                   Contents (RW), Pull requests (RW),
+#                                   Metadata (R). Wordt gebruikt voor clone,
+#                                   push en `gh pr create` (auto_pr).
 
 # 2. Repo op de NAS plaatsen
 ssh admin@nas
@@ -126,10 +133,30 @@ laatste heartbeat ouder is dan 5 minuten.
 
 ## Filesystem-grenzen
 
-De agent-user heeft geen SSH-keys, geen `~/.gitconfig` met push-credentials,
+De agent-user heeft geen SSH-keys en geen toegang tot andere shares dan
-en geen toegang tot andere shares dan `/share/Agent/*`. Commits worden
+`/share/Agent/*`. Wel een `~/.git-credentials` met de `GH_TOKEN` voor
-lokaal in de per-job clone gemaakt; pushen gebeurt door jou op je
+HTTPS-clone/push (zie volgende sectie) — die token is scoped tot de twee
-werkstation na review (CLAUDE.md regel: *"`git push` is altijd expliciet"*).
+configured repos en mag worden gerouleerd door rebuild + redeploy.
+
+## Repo bootstrap (clone-on-start)
+
+Bij elke container-start runt `bin/repo-bootstrap.sh` (als de
+`agent`-user, ná drop-privileges) en zet zo'n setup neer:
+
+1. Configureert git's credential-helper met `GH_TOKEN` zodat
+   `git clone`/`push` naar `https://github.com/...` zonder prompt werkt.
+2. Voor elke repo in `GH_PRECLONE_REPOS` (komma-gescheiden owner/name):
+   - Bestaat `~/Projects/<name>/.git` al? → `git fetch origin --prune`
+   - Anders → fresh `git clone`
+
+Daarna vindt scrum4me-mcp's `resolveRepoRoot` (in `wait_for_job`) de
+clone via z'n convention-fallback `~/Projects/<name>/.git`. Worktrees
+voor jobs landen vervolgens onder `~/.scrum4me-agent-worktrees/<jobId>/`
+zodat de hoofd-clone niet wordt aangeraakt.
+
+Push gaat over dezelfde token: `git push -u origin feat/story-<id>`
+slaagt zonder prompt. `gh pr create` (voor producten met `auto_pr=true`)
+gebruikt dezelfde `GH_TOKEN` via de `gh` CLI's standaard env-detect.
 
 ## Bekende grenzen
 

bin/entrypoint.sh

@@ -61,6 +61,15 @@ gosu agent /bin/bash -c 'cat > "${AGENT_STATE_DIR}/state.json"' <<EOF
 }
 EOF
 
-# ----- 3. drop privileges en start daemon-loop --------------------------
+# ----- 3. drop privileges, bootstrap repos, start daemon-loop -----------
-log "dropping to agent user and starting run-agent.sh"
+# repo-bootstrap.sh runs as agent (NOT root) so that the cloned repos
+# are owned by the agent user and live under ~agent/Projects/<name> —
+# that is exactly where scrum4me-mcp's resolveRepoRoot looks via its
+# convention fallback.
+log "dropping to agent user and bootstrapping repos"
+gosu agent /opt/agent/bin/repo-bootstrap.sh \
+    >> "${AGENT_LOG_DIR}/repo-bootstrap.log" 2>&1 \
+    || log "WARN: repo-bootstrap returned non-zero (continuing)"
+
+log "starting run-agent.sh"
 exec gosu agent /opt/agent/bin/run-agent.sh

bin/repo-bootstrap.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+# repo-bootstrap.sh — pre-clone repos into ~agent/Projects so that
+# scrum4me-mcp's `wait_for_job` finds a working repoRoot via the
+# convention-fallback `~/Projects/<name>/.git`.
+#
+# Idempotent:
+#   - Sets up git credential helper using GH_TOKEN (HTTPS auth)
+#   - For each entry in GH_PRECLONE_REPOS (comma-separated owner/name list):
+#       * If ~/Projects/<name> exists → `git fetch origin --prune`
+#       * Otherwise → fresh `git clone`
+#
+# Runs as the agent user (called from entrypoint.sh after `gosu agent …`).
+
+set -uo pipefail
+
+source /opt/agent/bin/_lib.sh
+
+: "${GH_TOKEN:=}"
+: "${GH_PRECLONE_REPOS:=}"
+
+if [[ -z "$GH_TOKEN" ]]; then
+    log "GH_TOKEN not set — skipping clone bootstrap. wait_for_job will fail until repos exist."
+    return 0 2>/dev/null || exit 0
+fi
+
+if [[ -z "$GH_PRECLONE_REPOS" ]]; then
+    log "GH_PRECLONE_REPOS empty — nothing to clone."
+    return 0 2>/dev/null || exit 0
+fi
+
+# ----- 1. configure git credential helper for HTTPS clone/push -----------
+mkdir -p "$HOME"
+git config --global credential.helper store
+CREDS_FILE="$HOME/.git-credentials"
+if [[ ! -f "$CREDS_FILE" ]] || ! grep -q "oauth2:${GH_TOKEN}@github.com" "$CREDS_FILE" 2>/dev/null; then
+    printf 'https://oauth2:%s@github.com\n' "$GH_TOKEN" > "$CREDS_FILE"
+    chmod 600 "$CREDS_FILE"
+    log "git credentials helper configured at ${CREDS_FILE}"
+fi
+
+# Prevent the token from leaking into commit-author of automated commits.
+git config --global user.name "${GIT_AUTHOR_NAME:-Scrum4Me Agent}"
+git config --global user.email "${GIT_AUTHOR_EMAIL:-agent@scrum4me.local}"
+
+# ----- 2. clone-or-fetch each repo --------------------------------------
+mkdir -p "$HOME/Projects"
+
+IFS=',' read -ra REPOS <<< "$GH_PRECLONE_REPOS"
+for repo in "${REPOS[@]}"; do
+    repo=$(echo "$repo" | tr -d '[:space:]')
+    [[ -z "$repo" ]] && continue
+
+    name=$(basename "$repo")
+    target="$HOME/Projects/$name"
+
+    if [[ -d "$target/.git" ]]; then
+        log "fetching ${repo} into ${target}"
+        git -C "$target" fetch origin --prune --quiet \
+            || log "WARN: fetch failed for ${repo} (continuing)"
+    else
+        log "cloning ${repo} into ${target}"
+        rm -rf "$target"
+        git clone --quiet "https://github.com/${repo}.git" "$target" \
+            || { log "ERROR: clone failed for ${repo}"; continue; }
+    fi
+done
+
+log "repo-bootstrap done"