commit cf23b4a1cedc854feabfe4fc0e7a7b08b824d3de Author: Adam Moussa <166072409+amoussa1229@users.noreply.github.com> Date: Mon May 11 16:05:38 2026 -0400 Add Front SLA monitor stack Scheduled Lambda polls Front every 15 min on weekdays, checks open conversations for SLA breaches (1hr ack, 1 day action), and sends tiered Slack alerts — DM the assignee, channel broadcast if unassigned, or escalate to Adam. DynamoDB dedup prevents repeat notifications. diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..e30613f --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,11 @@ +version: 2 +updates: + - package-ecosystem: "pip" + directory: "/src/monitor" + schedule: + interval: "weekly" + groups: + minor-and-patch: + update-types: + - "minor" + - "patch" diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml new file mode 100644 index 0000000..3c66f09 --- /dev/null +++ b/.github/workflows/ci.yaml @@ -0,0 +1,10 @@ +name: CI +on: + pull_request: + branches: [main] + +jobs: + ci: + uses: Sea-Haven-Industries/.github/.github/workflows/ci-python-sam.yaml@main + with: + source-dirs: "src" diff --git a/.github/workflows/deploy.yaml b/.github/workflows/deploy.yaml new file mode 100644 index 0000000..6f8a89a --- /dev/null +++ b/.github/workflows/deploy.yaml @@ -0,0 +1,22 @@ +name: Deploy +on: + push: + branches: [main] + +permissions: + id-token: write + contents: read + +concurrency: + group: deploy + cancel-in-progress: false + +jobs: + deploy: + uses: Sea-Haven-Industries/.github/.github/workflows/cd-sam.yaml@main + with: + stack-name: front-sla-monitor + cfn-role-arn: arn:aws:iam::328440206208:role/github-cfn-execution-role + secrets: + deploy-role-arn: ${{ secrets.AWS_DEPLOY_ROLE_ARN }} + parameter-overrides: ${{ secrets.SAM_PARAMETER_OVERRIDES }} diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..bbb6e3b --- /dev/null +++ b/.gitignore @@ -0,0 +1,5 @@ +.aws-sam/ +__pycache__/ +*.pyc +.env +samconfig.toml diff --git a/README.md b/README.md new file mode 100644 index 0000000..bdfbeeb --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +# front-sla-monitor + +Scheduled Lambda that monitors Front conversations for SLA breaches and sends tiered Slack alerts. Runs every 15 minutes on weekdays. + +## SLA Rules + +| Tier | Threshold | Action | +|---|---|---| +| 1 | 1 business hour without reply | Slack DM the assignee, or post to #front-sla-alerts if unassigned | +| 2 | 1 business day without reply | Slack DM Adam | + +Business time counts weekday hours only (Mon-Fri, Eastern time). The SLA clock pauses on Saturday and Sunday. + +## Architecture + +``` +EventBridge (every 15 min, Mon-Fri) + │ + ▼ +Lambda (Python 3.12, arm64) + │ + ├── Secrets Manager → front-sla-monitor/front-api-token + ├── Secrets Manager → front-sla-monitor/slack-bot-token + │ + ├── GET Front API /inboxes → list shared inboxes + ├── GET Front API /inboxes/{id}/conversations → open conversations + │ + ├── DynamoDB (front-sla-alerts) → dedup: skip already-alerted conversations + │ + ├── Tier 1 → Slack DM assignee or #front-sla-alerts + └── Tier 2 → Slack DM Adam +``` + +## AWS Resources + +- **Stack:** `front-sla-monitor` (SAM, us-east-1) +- **Lambda:** `front-sla-monitor` — Python 3.12, arm64, 128 MB, 120s timeout, 60-day log retention +- **DynamoDB:** `front-sla-alerts` — tracks alert history per conversation, 7-day TTL +- **EventBridge:** `cron(0/15 * ? * MON-FRI *)` — every 15 min on weekdays + +## Setup + +### 1. Create the Slack App + +1. Go to https://api.slack.com/apps and create **Front SLA Monitor** +2. Add Bot Token Scopes: `chat:write`, `users:read.email` +3. Install the app to your workspace and copy the Bot User OAuth Token +4. Create the `#front-sla-alerts` channel and invite the bot (`/invite @Front SLA Monitor`) +5. Copy the channel ID (right-click channel name > View channel details) + +### 2. Create a Front API Token + +1. Front > Settings > Developers > API tokens +2. Create a token with conversation read scope +3. Copy the token + +### 3. Store Secrets in AWS + +```bash +aws secretsmanager create-secret \ + --name "front-sla-monitor/front-api-token" \ + --secret-string "YOUR_FRONT_API_TOKEN" \ + --region us-east-1 + +aws secretsmanager create-secret \ + --name "front-sla-monitor/slack-bot-token" \ + --secret-string "xoxb-YOUR-SLACK-BOT-TOKEN" \ + --region us-east-1 +``` + +### 4. Deploy + +```bash +sam build +sam deploy --guided +``` + +Or push to `main` to trigger the GitHub Actions deploy workflow. + +### 5. GitHub Actions Secrets + +| Secret | Value | +|---|---| +| `AWS_DEPLOY_ROLE_ARN` | Org-wide OIDC deploy role (already configured) | +| `SAM_PARAMETER_OVERRIDES` | `FrontApiTokenSecretArn=arn:... SlackBotTokenSecretArn=arn:... SlackAlertChannel=CXXXXXXXXXX` | + +## Manual Testing + +```bash +aws lambda invoke --function-name front-sla-monitor --payload '{}' /dev/stdout --region us-east-1 +``` + +Check logs: + +```bash +aws logs tail /aws/lambda/front-sla-monitor --follow --region us-east-1 +``` + +## Configuration + +| Environment Variable | Default | Description | +|---|---|---| +| `ACK_SLA_MINUTES` | 60 | Business minutes before Tier 1 alert | +| `ACTION_SLA_MINUTES` | 1440 | Business minutes before Tier 2 alert | +| `ADAM_EMAIL` | adam@seahavenind.com | Tier 2 escalation recipient | +| `SLACK_ALERT_CHANNEL` | — | Channel ID for broadcast alerts | diff --git a/samconfig.toml.example b/samconfig.toml.example new file mode 100644 index 0000000..b1d5f38 --- /dev/null +++ b/samconfig.toml.example @@ -0,0 +1,17 @@ +version = 0.1 + +[default.deploy.parameters] +stack_name = "front-sla-monitor" +resolve_s3 = true +s3_prefix = "front-sla-monitor" +region = "us-east-1" +capabilities = "CAPABILITY_IAM" +confirm_changeset = true +parameter_overrides = [ + "FrontApiTokenSecretArn=arn:aws:secretsmanager:us-east-1:ACCOUNT_ID:secret:front-sla-monitor/front-api-token-XXXXXX", + "SlackBotTokenSecretArn=arn:aws:secretsmanager:us-east-1:ACCOUNT_ID:secret:front-sla-monitor/slack-bot-token-XXXXXX", + "SlackAlertChannel=CXXXXXXXXXX", +] + +[default.build.parameters] +use_container = false diff --git a/slack-app-manifest.yaml b/slack-app-manifest.yaml new file mode 100644 index 0000000..8c33177 --- /dev/null +++ b/slack-app-manifest.yaml @@ -0,0 +1,16 @@ +display_information: + name: Front SLA Monitor + description: Monitors Front conversations for SLA breaches and sends tiered Slack alerts + background_color: "#d32f2f" + +features: + bot_user: + display_name: Front SLA Monitor + always_online: true + +oauth_config: + scopes: + bot: + - chat:write + - users:read + - users:read.email diff --git a/src/monitor/app.py b/src/monitor/app.py new file mode 100644 index 0000000..a9dfe37 --- /dev/null +++ b/src/monitor/app.py @@ -0,0 +1,323 @@ +import json +import logging +import os +import time +from datetime import datetime, timedelta, timezone +from urllib import error, parse, request +from zoneinfo import ZoneInfo + +import boto3 + +logger = logging.getLogger() +logger.setLevel(logging.INFO) + +EASTERN = ZoneInfo("America/New_York") +FRONT_BASE = "https://api2.frontapp.com" +SLACK_BASE = "https://slack.com/api" +RATE_LIMIT_DELAY = 0.6 + +_sm = boto3.client("secretsmanager") +_ddb = boto3.resource("dynamodb") +_table = None +_front_token = None +_slack_token = None +_slack_user_cache = {} + + +def _get_table(): + global _table + if _table is None: + _table = _ddb.Table(os.environ["TABLE_NAME"]) + return _table + + +def _get_front_token(): + global _front_token + if _front_token is None: + resp = _sm.get_secret_value(SecretId=os.environ["FRONT_SECRET_NAME"]) + _front_token = resp["SecretString"] + return _front_token + + +def _get_slack_token(): + global _slack_token + if _slack_token is None: + resp = _sm.get_secret_value(SecretId=os.environ["SLACK_SECRET_NAME"]) + _slack_token = resp["SecretString"] + return _slack_token + + +# --------------------------------------------------------------------------- +# Front API +# --------------------------------------------------------------------------- + +def _front_get(url_or_path, params=None): + if url_or_path.startswith("http"): + url = url_or_path + else: + url = f"{FRONT_BASE}{url_or_path}" + if params: + url += "?" + parse.urlencode(params, doseq=True) + + req = request.Request(url, headers={ + "Authorization": f"Bearer {_get_front_token()}", + "Accept": "application/json", + }) + + time.sleep(RATE_LIMIT_DELAY) + + try: + with request.urlopen(req) as resp: + return json.loads(resp.read().decode()) + except error.HTTPError as e: + body = e.read().decode() if e.fp else "" + raise RuntimeError(f"Front GET {url_or_path} failed ({e.code}): {body}") + + +def _front_paginate(path, params=None): + results = [] + data = _front_get(path, params) + results.extend(data.get("_results", [])) + + while data.get("_pagination", {}).get("next"): + data = _front_get(data["_pagination"]["next"]) + results.extend(data.get("_results", [])) + + return results + + +# --------------------------------------------------------------------------- +# Slack API +# --------------------------------------------------------------------------- + +def _slack_post(method, payload): + data = json.dumps(payload).encode() + req = request.Request(f"{SLACK_BASE}/{method}", data=data, headers={ + "Content-Type": "application/json; charset=utf-8", + "Authorization": f"Bearer {_get_slack_token()}", + }) + + try: + with request.urlopen(req) as resp: + result = json.loads(resp.read().decode()) + if not result.get("ok"): + raise RuntimeError(f"Slack {method}: {result.get('error')}") + return result + except error.HTTPError as e: + body = e.read().decode() if e.fp else "" + raise RuntimeError(f"Slack {method} HTTP {e.code}: {body}") + + +def _slack_get(method, params): + url = f"{SLACK_BASE}/{method}?" + parse.urlencode(params) + req = request.Request(url, headers={ + "Authorization": f"Bearer {_get_slack_token()}", + }) + + try: + with request.urlopen(req) as resp: + result = json.loads(resp.read().decode()) + if not result.get("ok"): + raise RuntimeError(f"Slack {method}: {result.get('error')}") + return result + except error.HTTPError as e: + body = e.read().decode() if e.fp else "" + raise RuntimeError(f"Slack {method} HTTP {e.code}: {body}") + + +def _resolve_slack_user(email): + if email in _slack_user_cache: + return _slack_user_cache[email] + try: + result = _slack_get("users.lookupByEmail", {"email": email}) + uid = result["user"]["id"] + _slack_user_cache[email] = uid + return uid + except RuntimeError: + logger.warning("Could not resolve Slack user for %s", email) + return None + + +def _send_slack(channel, blocks, text): + _slack_post("chat.postMessage", { + "channel": channel, + "blocks": blocks, + "text": text, + }) + + +# --------------------------------------------------------------------------- +# Business time calculation (weekdays only, Eastern time) +# --------------------------------------------------------------------------- + +def _business_minutes_elapsed(since_utc, now_utc): + since = since_utc.astimezone(EASTERN) + now = now_utc.astimezone(EASTERN) + + if since >= now: + return 0 + + total = 0.0 + current = since + + while current < now: + if current.weekday() < 5: + end_of_day = (current + timedelta(days=1)).replace( + hour=0, minute=0, second=0, microsecond=0 + ) + day_end = min(end_of_day, now) + total += (day_end - current).total_seconds() / 60 + + current = (current + timedelta(days=1)).replace( + hour=0, minute=0, second=0, microsecond=0 + ) + + return total + + +# --------------------------------------------------------------------------- +# DynamoDB dedup +# --------------------------------------------------------------------------- + +def _already_alerted(conv_id, tier): + resp = _get_table().get_item(Key={"conversationId": conv_id}) + item = resp.get("Item") + if not item: + return False + return f"tier{tier}AlertedAt" in item + + +def _record_alert(conv_id, tier): + now_iso = datetime.now(timezone.utc).isoformat() + ttl_epoch = int(time.time()) + 7 * 86400 + + _get_table().update_item( + Key={"conversationId": conv_id}, + UpdateExpression="SET #ttl = :ttl, #alert = :ts", + ExpressionAttributeNames={ + "#ttl": "ttl", + "#alert": f"tier{tier}AlertedAt", + }, + ExpressionAttributeValues={ + ":ttl": ttl_epoch, + ":ts": now_iso, + }, + ) + + +# --------------------------------------------------------------------------- +# Slack message blocks +# --------------------------------------------------------------------------- + +def _tier1_blocks(conv, assignee_email=None): + subject = conv.get("subject", "No subject") + conv_id = conv.get("id", "") + link = f"https://app.frontapp.com/open/{conv_id}" + msg_at = conv.get("last_message", {}).get("created_at", 0) + ts = datetime.fromtimestamp(msg_at, tz=EASTERN).strftime("%b %d, %I:%M %p ET") + status = f"Assigned to {assignee_email}" if assignee_email else "Unassigned" + + return [ + {"type": "header", "text": {"type": "plain_text", "text": ":warning: SLA Breach: 1-Hour Acknowledgment"}}, + {"type": "section", "text": {"type": "mrkdwn", "text": ( + f"*<{link}|{subject}>*\n" + f"Last inbound: {ts}\n" + f"Status: {status}\n" + f"_No reply for over 1 business hour._" + )}}, + ] + + +def _tier2_blocks(conv): + subject = conv.get("subject", "No subject") + conv_id = conv.get("id", "") + link = f"https://app.frontapp.com/open/{conv_id}" + msg_at = conv.get("last_message", {}).get("created_at", 0) + ts = datetime.fromtimestamp(msg_at, tz=EASTERN).strftime("%b %d, %I:%M %p ET") + assignee = conv.get("assignee") + status = f"Assigned to {assignee['email']}" if assignee else "Unassigned" + + return [ + {"type": "header", "text": {"type": "plain_text", "text": ":rotating_light: SLA Breach: 1-Day Action Required"}}, + {"type": "section", "text": {"type": "mrkdwn", "text": ( + f"*<{link}|{subject}>*\n" + f"Last inbound: {ts}\n" + f"Status: {status}\n" + f"_No reply for over 1 business day. Immediate attention required._" + )}}, + ] + + +# --------------------------------------------------------------------------- +# Handler +# --------------------------------------------------------------------------- + +def handler(event, context): + ack_threshold = int(os.environ["ACK_SLA_MINUTES"]) + action_threshold = int(os.environ["ACTION_SLA_MINUTES"]) + alert_channel = os.environ["SLACK_ALERT_CHANNEL"] + adam_email = os.environ["ADAM_EMAIL"] + + now = datetime.now(timezone.utc) + + inboxes = _front_paginate("/inboxes") + shared = [i for i in inboxes if not i.get("is_private", False)] + logger.info("Found %d shared inboxes", len(shared)) + + tier1_count = 0 + tier2_count = 0 + + for inbox in shared: + inbox_id = inbox["id"] + inbox_name = inbox.get("name", inbox_id) + + try: + conversations = _front_paginate( + f"/inboxes/{inbox_id}/conversations", + params={"q[statuses][]": ["open", "unassigned"]}, + ) + except RuntimeError as e: + logger.error("Failed to fetch conversations for %s: %s", inbox_name, e) + continue + + logger.info("Inbox '%s': %d open conversations", inbox_name, len(conversations)) + + for conv in conversations: + try: + last_msg = conv.get("last_message") + if not last_msg or last_msg.get("type") != "inbound": + continue + + msg_dt = datetime.fromtimestamp(last_msg["created_at"], tz=timezone.utc) + elapsed = _business_minutes_elapsed(msg_dt, now) + conv_id = conv["id"] + assignee = conv.get("assignee") + + if elapsed >= action_threshold and not _already_alerted(conv_id, 2): + adam_uid = _resolve_slack_user(adam_email) + target = adam_uid or alert_channel + _send_slack(target, _tier2_blocks(conv), + f"SLA Breach: {conv.get('subject', '')} - 1 day without reply") + _record_alert(conv_id, 2) + tier2_count += 1 + logger.info("Tier 2 alert: %s", conv_id) + + elif elapsed >= ack_threshold and not _already_alerted(conv_id, 1): + if assignee and assignee.get("email"): + uid = _resolve_slack_user(assignee["email"]) + target = uid or alert_channel + _send_slack(target, _tier1_blocks(conv, assignee["email"]), + f"SLA Breach: {conv.get('subject', '')} - 1 hour without reply") + else: + _send_slack(alert_channel, _tier1_blocks(conv), + f"SLA Breach: {conv.get('subject', '')} - unassigned, 1 hour without reply") + _record_alert(conv_id, 1) + tier1_count += 1 + logger.info("Tier 1 alert: %s", conv_id) + + except Exception: + logger.exception("Error processing conversation %s", conv.get("id", "?")) + + result = {"tier1_alerts": tier1_count, "tier2_alerts": tier2_count} + logger.info("Run complete: %s", result) + return result diff --git a/src/monitor/requirements.txt b/src/monitor/requirements.txt new file mode 100644 index 0000000..e69de29 diff --git a/template.yaml b/template.yaml new file mode 100644 index 0000000..7cd3aa0 --- /dev/null +++ b/template.yaml @@ -0,0 +1,99 @@ +AWSTemplateFormatVersion: '2010-09-09' +Transform: AWS::Serverless-2016-10-31 +Description: Front SLA Monitor - Tiered Slack alerts for conversation SLA breaches + +Parameters: + FrontApiTokenSecretArn: + Type: String + Description: ARN of the Secrets Manager secret containing the Front API token + SlackBotTokenSecretArn: + Type: String + Description: ARN of the Secrets Manager secret containing the Slack bot token + SlackAlertChannel: + Type: String + Description: Slack channel ID for the front-sla-alerts channel + AdamEmail: + Type: String + Default: adam@seahavenind.com + Description: Email address for Tier 2 escalation + AckSlaMinutes: + Type: Number + Default: 60 + Description: Business minutes before Tier 1 alert (1 hour) + ActionSlaMinutes: + Type: Number + Default: 1440 + Description: Business minutes before Tier 2 alert (1 business day) + +Globals: + Function: + Runtime: python3.12 + Timeout: 120 + MemorySize: 128 + Architectures: + - arm64 + +Resources: + AlertsTable: + Type: AWS::DynamoDB::Table + Properties: + TableName: front-sla-alerts + BillingMode: PAY_PER_REQUEST + AttributeDefinitions: + - AttributeName: conversationId + AttributeType: S + KeySchema: + - AttributeName: conversationId + KeyType: HASH + TimeToLiveSpecification: + AttributeName: ttl + Enabled: true + + MonitorLogGroup: + Type: AWS::Logs::LogGroup + Properties: + LogGroupName: /aws/lambda/front-sla-monitor + RetentionInDays: 60 + + MonitorFunction: + Type: AWS::Serverless::Function + DependsOn: MonitorLogGroup + Properties: + FunctionName: front-sla-monitor + Handler: app.handler + CodeUri: src/monitor/ + Environment: + Variables: + FRONT_SECRET_NAME: !Ref FrontApiTokenSecretArn + SLACK_SECRET_NAME: !Ref SlackBotTokenSecretArn + SLACK_ALERT_CHANNEL: !Ref SlackAlertChannel + ADAM_EMAIL: !Ref AdamEmail + TABLE_NAME: !Ref AlertsTable + ACK_SLA_MINUTES: !Ref AckSlaMinutes + ACTION_SLA_MINUTES: !Ref ActionSlaMinutes + Policies: + - DynamoDBCrudPolicy: + TableName: !Ref AlertsTable + - Version: '2012-10-17' + Statement: + - Effect: Allow + Action: + - secretsmanager:GetSecretValue + Resource: + - !Ref FrontApiTokenSecretArn + - !Ref SlackBotTokenSecretArn + Events: + SlaCheck: + Type: Schedule + Properties: + Schedule: cron(0/15 * ? * MON-FRI *) + Description: Check Front conversations for SLA breaches every 15 min on weekdays + Enabled: true + +Outputs: + MonitorFunctionArn: + Description: Front SLA Monitor Lambda ARN + Value: !GetAtt MonitorFunction.Arn + AlertsTableName: + Description: DynamoDB alerts table name + Value: !Ref AlertsTable