fix: prevent deletion of all deployments with pending builds

[woustachemax]

Fixed an issue where attempting to delete all deployments (including those still building/processing) would result in 404 errors and orphaned functions.

Changes:

• Added validation to block deletion when all deployments are selected and any are in 'waiting', 'processing', or 'building' status
• Returns proper error message to display in UI instead of allowing the operation to proceed
• Maintains ability to delete all completed deployments (leaves function in clean "no deployments" state)
• Preserves error tracking for analytics

This prevents the edge case where deleting all deployments while builds are in progress would corrupt the function state.

Summary by CodeRabbit

• Bug Fixes
  • Prevented accidental deletion of all deployments when selected deployments are still processing or pending.

[appwrite]

Console (appwrite/console)

Project ID: 688b7bf400350cbd60e9

Sites (1)

Site	Status	Logs	Preview	QR
console-stage 688b7cf6003b1842c9dc	Failed	Authorize	Preview URL

Tip

Custom domains work with both CNAME for subdomains and NS records for apex domains

[coderabbitai]

Walkthrough

This pull request introduces a complete Docker Compose configuration for Appwrite with Traefik reverse proxy integration and updates the deployment deletion logic in the functions management interface. The docker-compose.yml file defines a multi-service stack including Appwrite core, console, realtime, multiple worker services, MariaDB, Redis, and Traefik as a reverse proxy with TLS support. Additionally, the Svelte component now prevents deletion of all deployments if any selected deployments are in a pending state.

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~60 minutes

• docker-compose.yml: The new configuration file is substantial and declarative but requires validation of:

  • All 40+ service definitions and their correct image versions
  • Environment variable declarations and placeholder values
  • Traefik routing rules, path prefixes, and TLS configurations across multiple services
  • Volume mounting paths and persistence strategy
  • Network topology and service inter-connectivity
  • Restart policies and logging configurations

• table.svelte: The deployment deletion logic requires verification of:

  • Correct detection of pending deployment states (waiting, processing, building)
  • Edge cases where selected deployments include pending items but would leave empty remaining list
  • Error construction and tracking behavior

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the main change: adding validation to prevent deletion of all deployments when pending builds exist, which is the primary objective of the PR.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🧹 Nitpick comments (1)

src/routes/(console)/project-[region]-[project]/functions/function-[function]/table.svelte (1)

66-73: Consider caching regionalConsoleVariables for consistency.

The function calls getEffectiveBuildStatus multiple times with $regionalConsoleVariables inside a loop. Since this is a reactive store value accessed during iteration, if the store updates between checks (unlikely but possible), different deployments might be evaluated with different timeout thresholds.

Consider capturing the store value once before the loop:

 if (remainingDeployments.length === 0) {
     const selectedDeployments = allDeployments.filter(
         (d) => selectedRows.includes(d.$id)
     );
     
+    const consoleVars = $regionalConsoleVariables;
     const hasPendingDeployments = selectedDeployments.some((d) => {
         const effectiveStatus = getEffectiveBuildStatus(
             d.status,
             d.$createdAt,
-            $regionalConsoleVariables
+            consoleVars
         );
         return ['waiting', 'processing', 'building'].includes(effectiveStatus);
     });

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between a6d6223 and 1bfd036.

📒 Files selected for processing (2)

• appwrite/docker-compose.yml (1 hunks)
• src/routes/(console)/project-[region]-[project]/functions/function-[function]/table.svelte (2 hunks)

🔇 Additional comments (2)

src/routes/(console)/project-[region]-[project]/functions/function-[function]/table.svelte (2)

55-82: Validation logic correctly prevents orphaning the function.

The implementation properly addresses the PR objective by blocking deletion when all deployments would be removed and any are in a pending state. The early return prevents API calls and provides a clear error message.

However, note that this validation only triggers when all deployments are selected for deletion. Individual pending deployments or partial selections that include pending deployments can still be deleted through the bulk selection interface. Based on lines 217-230, the single-deployment action menu already prevents deleting individual pending deployments by hiding the delete button for those statuses. This asymmetry is worth documenting.

---

94-97: Explicit return values improve clarity.

The explicit return undefined on success and as Error casting in the catch block improve type safety and make the return contract clearer.

[coderabbitai]

🛠️ Refactor suggestion | 🟠 Major

Docker Compose configuration appears unrelated to PR objectives.

This PR adds a complete 973-line Docker Compose file defining Appwrite infrastructure (Traefik, workers, databases, etc.), but the PR objectives specifically focus on preventing deletion of deployments with pending builds in the console UI.

The deployment deletion fix in table.svelte is a frontend validation change that doesn't require infrastructure modifications. This docker-compose.yml introduces:

• Traefik reverse proxy setup
• 30+ service definitions
• Complete orchestration configuration

These appear to be separate concerns that should be in different PRs for:

1. Easier review and testing
2. Clearer git history
3. Independent deployment/rollback
4. Focused PR objectives

Recommendation: Split this PR into two:

1. Deployment deletion fix (current table.svelte changes)
2. Infrastructure setup (docker-compose.yml)

If this infrastructure is genuinely required for the deployment deletion fix to work, please update the PR description to explain the dependency.

🤖 Prompt for AI Agents

In appwrite/docker-compose.yml around lines 1 to 973, the large Docker Compose
addition is unrelated to the reported UI change (preventing deletion of
deployments with pending builds); remove this file from the current PR by
reverting the commit or unstaging the file (move it to a new branch), and submit
it in a separate focused PR for infrastructure changes; if the compose file is
actually required for testing or reproducing the frontend fix, update the PR
description to explicitly state that dependency and document exactly why it's
needed and how reviewers should use it.