fix(mosaic): harden gitea pr wrapper metadata

2026-05-22 11:00:34 -05:00
parent 755df9079e
commit 952fab9443
7 changed files with 266 additions and 29 deletions
--- a/packages/mosaic/framework/tools/git/detect-platform.sh
+++ b/packages/mosaic/framework/tools/git/detect-platform.sh
@@ -92,7 +92,7 @@ get_remote_host() {
 }

 # Resolve a Gitea API token for the given host.
-# Priority: Mosaic credential loader → GITEA_TOKEN env → ~/.git-credentials
+# Priority: Mosaic credential loader → host-matched GITEA_TOKEN env → ~/.git-credentials
 get_gitea_token() {
    local host="$1"
    local script_dir
@@ -103,16 +103,28 @@ get_gitea_token() {
    if [[ -f "$cred_loader" ]]; then
        local token
        token=$(
+            # shellcheck source=/dev/null
            source "$cred_loader"
+            # Host-specific wrapper resolution must not inherit a caller/global GITEA_TOKEN.
+            # load_credentials intentionally preserves existing env vars for interactive use,
+            # but merge/metadata wrappers need the token matching the remote host.
+            unset GITEA_TOKEN GITEA_URL
            case "$host" in
                git.mosaicstack.dev) load_credentials gitea-mosaicstack 2>/dev/null ;;
                git.uscllc.com)      load_credentials gitea-usc 2>/dev/null ;;
                *)
+                    local matched=false
                    for svc in gitea-mosaicstack gitea-usc; do
-                        load_credentials "$svc" 2>/dev/null || continue
-                        [[ "${GITEA_URL:-}" == *"$host"* ]] && break
                        unset GITEA_TOKEN GITEA_URL
+                        load_credentials "$svc" 2>/dev/null || continue
+                        if [[ "${GITEA_URL:-}" == "https://$host" || "${GITEA_URL:-}" == "http://$host" || "${GITEA_URL:-}" == *"//$host" ]]; then
+                            matched=true
+                            break
+                        fi
                    done
+                    if [[ "$matched" != true ]]; then
+                        unset GITEA_TOKEN GITEA_URL
+                    fi
                    ;;
            esac
            echo "${GITEA_TOKEN:-}"
@@ -123,10 +135,12 @@ get_gitea_token() {
        fi
    fi

-    # 2. GITEA_TOKEN env var (may be set by caller)
+    # 2. GITEA_TOKEN env var (only when GITEA_URL, if present, matches the remote host)
    if [[ -n "${GITEA_TOKEN:-}" ]]; then
-        echo "$GITEA_TOKEN"
-        return 0
+        if [[ -z "${GITEA_URL:-}" || "${GITEA_URL:-}" == "https://$host" || "${GITEA_URL:-}" == "http://$host" || "${GITEA_URL:-}" == *"//$host" ]]; then
+            echo "$GITEA_TOKEN"
+            return 0
+        fi
    fi

    # 3. ~/.git-credentials file
--- a/packages/mosaic/framework/tools/git/pr-merge.sh
+++ b/packages/mosaic/framework/tools/git/pr-merge.sh
@@ -1,10 +1,11 @@
 #!/bin/bash
 # pr-merge.sh - Merge pull requests on Gitea or GitHub
-# Usage: pr-merge.sh -n PR_NUMBER [-m squash] [-d] [--skip-queue-guard]
+# Usage: pr-merge.sh -n PR_NUMBER [-m squash] [-d] [--skip-queue-guard] [--dry-run]

 set -e

 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# shellcheck disable=SC1091
 source "$SCRIPT_DIR/detect-platform.sh"

 # Default values
@@ -12,6 +13,7 @@ PR_NUMBER=""
 MERGE_METHOD="squash"
 DELETE_BRANCH=false
 SKIP_QUEUE_GUARD=false
+DRY_RUN=false

 usage() {
    cat <<EOF
@@ -24,6 +26,7 @@ Options:
    -m, --method METHOD     Merge method: squash only (default: squash)
    -d, --delete-branch     Delete the head branch after merge
        --skip-queue-guard  Skip CI queue guard wait before merge
+        --dry-run           Validate metadata/auth/preflight without merging
    -h, --help              Show this help message

 Examples:
@@ -54,6 +57,10 @@ while [[ $# -gt 0 ]]; do
            SKIP_QUEUE_GUARD=true
            shift
            ;;
+        --dry-run)
+            DRY_RUN=true
+            shift
+            ;;
        -h|--help)
            usage
            ;;
@@ -74,7 +81,8 @@ if [[ "$MERGE_METHOD" != "squash" ]]; then
    exit 1
 fi

-BASE_BRANCH="$("$SCRIPT_DIR/pr-metadata.sh" -n "$PR_NUMBER" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("baseRefName") or "").strip())')"
+METADATA_JSON="$("$SCRIPT_DIR/pr-metadata.sh" -n "$PR_NUMBER")"
+BASE_BRANCH="$(printf '%s' "$METADATA_JSON" | python3 -c 'import json, sys; print((json.load(sys.stdin).get("baseRefName") or "").strip())')"
 if [[ "$BASE_BRANCH" != "main" ]]; then
    echo "Error: Mosaic policy allows merges only for PRs targeting 'main' (found '$BASE_BRANCH')." >&2
    exit 1
@@ -94,19 +102,55 @@ REPO=$(get_repo_name)

 case "$PLATFORM" in
    github)
-        CMD="gh pr merge $PR_NUMBER --squash"
-        [[ "$DELETE_BRANCH" == true ]] && CMD="$CMD --delete-branch"
-        eval "$CMD"
+        if [[ "$DRY_RUN" == true ]]; then
+            echo "Dry run: GitHub merge preflight OK for ${OWNER}/${REPO}#${PR_NUMBER} targeting ${BASE_BRANCH}"
+            exit 0
+        fi
+        CMD=(gh pr merge "$PR_NUMBER" --squash)
+        [[ "$DELETE_BRANCH" == true ]] && CMD+=(--delete-branch)
+        "${CMD[@]}"
        ;;
    gitea)
-        CMD="tea pr merge $PR_NUMBER --style squash --repo $OWNER/$REPO --login ${GITEA_LOGIN:-mosaicstack}"
+        HOST=$(get_remote_host) || {
+            echo "Error: Cannot determine host from remote URL" >&2
+            exit 1
+        }
+        TOKEN=$(get_gitea_token "$HOST") || {
+            echo "Error: Could not resolve Gitea API token for ${HOST}" >&2
+            exit 1
+        }
+
+        if [[ "$DRY_RUN" == true ]]; then
+            echo "Dry run: Gitea merge preflight OK for ${OWNER}/${REPO}#${PR_NUMBER} targeting ${BASE_BRANCH} via ${HOST} API"
+            exit 0
+        fi
+
+        RESPONSE_FILE=$(mktemp)
+        trap 'rm -f "$RESPONSE_FILE"' EXIT
+        HTTP_CODE=$(curl -sS \
+            -X POST \
+            -H "Authorization: token $TOKEN" \
+            -H "Content-Type: application/json" \
+            -d '{"Do":"squash"}' \
+            -o "$RESPONSE_FILE" \
+            -w '%{http_code}' \
+            "https://${HOST}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}/merge")
+        RESPONSE_BODY=$(cat "$RESPONSE_FILE")
+        rm -f "$RESPONSE_FILE"
+        trap - EXIT
+
+        if [[ ! "$HTTP_CODE" =~ ^2 ]]; then
+            echo "Error: Gitea PR merge failed for ${OWNER}/${REPO}#${PR_NUMBER} (HTTP ${HTTP_CODE})" >&2
+            if [[ -n "$RESPONSE_BODY" ]]; then
+                printf '%s\n' "$RESPONSE_BODY" >&2
+            fi
+            exit 1
+        fi

        # Delete branch after merge if requested
        if [[ "$DELETE_BRANCH" == true ]]; then
-            echo "Note: Branch deletion after merge may need to be done separately with tea" >&2
+            echo "Note: Branch deletion after merge may need to be done separately with the Gitea API" >&2
        fi
-
-        eval "$CMD"
        ;;
    *)
        echo "Error: Could not detect git platform" >&2
--- a/packages/mosaic/framework/tools/git/pr-metadata.sh
+++ b/packages/mosaic/framework/tools/git/pr-metadata.sh
@@ -5,6 +5,7 @@
 set -e

 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# shellcheck disable=SC1091
 source "$SCRIPT_DIR/detect-platform.sh"

 # Parse arguments
@@ -55,39 +56,51 @@ if [[ "$PLATFORM" == "github" ]]; then
 elif [[ "$PLATFORM" == "gitea" ]]; then
    OWNER=$(get_repo_owner)
    REPO=$(get_repo_name)
-    REMOTE_URL=$(git remote get-url origin 2>/dev/null)
-
-    # Extract host from remote URL
-    if [[ "$REMOTE_URL" == https://* ]]; then
-        HOST=$(echo "$REMOTE_URL" | sed -E 's|https://([^/]+)/.*|\1|')
-    elif [[ "$REMOTE_URL" == git@* ]]; then
-        HOST=$(echo "$REMOTE_URL" | sed -E 's|git@([^:]+):.*|\1|')
-    else
+    HOST=$(get_remote_host) || {
        echo "Error: Cannot determine host from remote URL" >&2
        exit 1
-    fi
+    }

    API_URL="https://${HOST}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}"

    GITEA_API_TOKEN=$(get_gitea_token "$HOST" || true)

+    RESPONSE_FILE=$(mktemp)
+    trap 'rm -f "$RESPONSE_FILE"' EXIT
    if [[ -n "$GITEA_API_TOKEN" ]]; then
-        RAW=$(curl -sS -H "Authorization: token $GITEA_API_TOKEN" "$API_URL")
+        HTTP_CODE=$(curl -sS -H "Authorization: token $GITEA_API_TOKEN" -o "$RESPONSE_FILE" -w '%{http_code}' "$API_URL")
    else
-        RAW=$(curl -sS "$API_URL")
+        HTTP_CODE=$(curl -sS -o "$RESPONSE_FILE" -w '%{http_code}' "$API_URL")
+    fi
+    RAW=$(cat "$RESPONSE_FILE")
+    rm -f "$RESPONSE_FILE"
+    trap - EXIT
+
+    if [[ ! "$HTTP_CODE" =~ ^2 ]]; then
+        echo "Error: Gitea PR metadata request failed for ${OWNER}/${REPO}#${PR_NUMBER} (HTTP ${HTTP_CODE})" >&2
+        exit 1
    fi

    # Normalize Gitea response to match our expected schema
    METADATA=$(echo "$RAW" | python3 -c "
 import json, sys
 data = json.load(sys.stdin)
+if 'message' in data and not data.get('number'):
+    raise SystemExit('Error: Gitea PR metadata response did not contain PR data')
+head = data.get('head') or {}
+head_ref = head.get('ref') or ''
+head_label = head.get('label') or ''
+# Gitea can report closed/merged PR heads as refs/pull/<n>/head; callers need
+# the source branch name equivalent to GitHub headRefName, so prefer label then.
+if head_ref.startswith('refs/pull/') and head_label:
+    head_ref = head_label
 normalized = {
    'number': data.get('number'),
    'title': data.get('title'),
    'body': data.get('body', ''),
    'state': data.get('state'),
    'author': data.get('user', {}).get('login', ''),
-    'headRefName': data.get('head', {}).get('ref', ''),
+    'headRefName': head_ref,
    'baseRefName': data.get('base', {}).get('ref', ''),
    'labels': [l.get('name', '') for l in data.get('labels', [])],
    'assignees': [a.get('login', '') for a in data.get('assignees', [])],
--- a/packages/mosaic/framework/tools/git/tests/pr-gitea-wrapper-regression.sh
+++ b/packages/mosaic/framework/tools/git/tests/pr-gitea-wrapper-regression.sh
@@ -0,0 +1,116 @@
+#!/usr/bin/env bash
+# Regression harness for Gitea PR metadata normalization and merge preflight.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+GIT_TOOLS_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+TEST_ROOT="${TEST_ROOT:-$(pwd)/.test-output/pr-gitea-wrapper-regression}"
+FAKE_BIN="$TEST_ROOT/bin"
+FAKE_REPO="$TEST_ROOT/repo"
+
+rm -rf "$TEST_ROOT"
+mkdir -p "$FAKE_BIN" "$FAKE_REPO" "$TEST_ROOT/state"
+
+cat > "$FAKE_BIN/git" <<'SH'
+#!/usr/bin/env bash
+set -euo pipefail
+if [[ "$*" == "remote get-url origin" ]]; then
+  echo "https://git.uscllc.com/usc/uconnect.git"
+  exit 0
+fi
+echo "unexpected git invocation: $*" >&2
+exit 2
+SH
+chmod +x "$FAKE_BIN/git"
+
+cat > "$FAKE_BIN/curl" <<'SH'
+#!/usr/bin/env bash
+set -euo pipefail
+method="GET"
+out_file=""
+write_format=""
+url=""
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    -X)
+      method="$2"; shift 2 ;;
+    -o)
+      out_file="$2"; shift 2 ;;
+    -w)
+      write_format="$2"; shift 2 ;;
+    -H|-d)
+      shift 2 ;;
+    -s|-S|-f|-k|-sS|-fsS)
+      shift ;;
+    http*)
+      url="$1"; shift ;;
+    *)
+      shift ;;
+  esac
+done
+
+body='{}'
+code="200"
+if [[ "$method" == "GET" && "$url" == *"/api/v1/repos/usc/uconnect/pulls/1908" ]]; then
+  body='{"number":1908,"title":"Test PR","body":"","state":"open","user":{"login":"edith"},"head":{"label":"fix/t_23fa9e1d-portal-health-backend","ref":"refs/pull/1908/head","sha":"abc123"},"base":{"label":"main","ref":"main","sha":"def456"},"labels":[],"assignees":[],"created_at":"2026-05-22T00:00:00Z","updated_at":"2026-05-22T00:00:00Z","html_url":"https://git.uscllc.com/usc/uconnect/pulls/1908","draft":false,"mergeable":true,"diff_url":"https://git.uscllc.com/usc/uconnect/pulls/1908.diff"}'
+elif [[ "$method" == "POST" && "$url" == *"/api/v1/repos/usc/uconnect/pulls/1908/merge" ]]; then
+  echo "$url" > "${TEST_ROOT:?}/state/merge-url"
+  body='{"merged":true}'
+else
+  code="404"
+  body='{"message":"not found"}'
+fi
+
+if [[ -n "$out_file" ]]; then
+  printf '%s' "$body" > "$out_file"
+else
+  printf '%s' "$body"
+fi
+if [[ -n "$write_format" ]]; then
+  printf '%s' "$code"
+fi
+SH
+chmod +x "$FAKE_BIN/curl"
+
+cat > "$FAKE_BIN/tea" <<'SH'
+#!/usr/bin/env bash
+echo "tea must not be invoked by Gitea merge preflight" >&2
+exit 99
+SH
+chmod +x "$FAKE_BIN/tea"
+
+cat > "$TEST_ROOT/credentials.json" <<'JSON'
+{
+  "gitea": {
+    "usc": {"url": "https://git.uscllc.com", "token": "fake-token-usc"},
+    "mosaicstack": {"url": "https://git.mosaicstack.dev", "token": "fake-token-mosaic"}
+  }
+}
+JSON
+
+export PATH="$FAKE_BIN:$PATH"
+export TEST_ROOT
+export MOSAIC_CREDENTIALS_FILE="$TEST_ROOT/credentials.json"
+cd "$FAKE_REPO"
+
+metadata="$("$GIT_TOOLS_DIR/pr-metadata.sh" -n 1908)"
+python3 - "$metadata" <<'PY'
+import json
+import sys
+metadata = json.loads(sys.argv[1])
+assert metadata["baseRefName"] == "main", metadata
+assert metadata["headRefName"] == "fix/t_23fa9e1d-portal-health-backend", metadata
+PY
+
+merge_output="$("$GIT_TOOLS_DIR/pr-merge.sh" -n 1908 -m squash --skip-queue-guard --dry-run 2>&1)"
+if grep -q "mosaicstack\|Login name\|tea must not" <<<"$merge_output"; then
+  echo "$merge_output" >&2
+  exit 1
+fi
+if ! grep -q "Dry run: Gitea merge preflight OK" <<<"$merge_output"; then
+  echo "$merge_output" >&2
+  exit 1
+fi
+
+printf 'Gitea PR metadata and merge preflight regression passed\n'