Skip to content

Improve BlazorJob application#3

Closed
QuenumGerald wants to merge 3 commits into
mainfrom
claude/improve-blazerjob-LNqE4
Closed

Improve BlazorJob application#3
QuenumGerald wants to merge 3 commits into
mainfrom
claude/improve-blazerjob-LNqE4

Conversation

@QuenumGerald

Copy link
Copy Markdown
Owner
  • Ajout de la décrémentation automatique de retriesLeft lors des échecs
  • Implémentation du backoff exponentiel (1s, 2s, 4s, 8s...)
  • Mise à jour du champ lastError dans la base de données
  • Replanification automatique des tâches avec le délai de backoff
  • Marquage des tâches comme 'failed' après épuisement des retries
  • Appel du callback onEnd avec les statistiques correctes
  • Ajout d'un test complet pour valider la logique de retry

Le test confirme que :

  • Les tâches sont replanifiées avec le bon délai
  • retriesLeft est correctement décrémenté
  • lastError est bien sauvegardé
  • Les statistiques finales sont exactes

claude and others added 3 commits January 15, 2026 07:12
- Ajout de la décrémentation automatique de retriesLeft lors des échecs
- Implémentation du backoff exponentiel (1s, 2s, 4s, 8s...)
- Mise à jour du champ lastError dans la base de données
- Replanification automatique des tâches avec le délai de backoff
- Marquage des tâches comme 'failed' après épuisement des retries
- Appel du callback onEnd avec les statistiques correctes
- Ajout d'un test complet pour valider la logique de retry

Le test confirme que :
- Les tâches sont replanifiées avec le bon délai
- retriesLeft est correctement décrémenté
- lastError est bien sauvegardé
- Les statistiques finales sont exactes
…bhook

- Ajout de trois stratégies de retry : exponential (défaut), linear, et fixed
- Configuration personnalisable du délai de base (delayMs) et délai maximum (maxDelayMs)
- Notifications webhook lors de chaque tentative de retry avec détails (attemptNumber, retriesLeft, nextRetryAt)
- Notifications webhook améliorées pour les échecs définitifs avec totalAttempts
- Ajout des types RetryStrategy et RetryConfig
- Extension
- Added comparison table highlighting key differences (infrastructure, setup, performance, scaling)
- Documented when to choose BlazerJob (zero dependencies, simple deployment, <5k tasks/s)
- Documented when to choose BullMQ (high throughput, distributed architecture, >10k tasks/s)
- Emphasized BlazerJob's philosophy: simplicity and zero dependencies vs BullMQ's scalability focus
- Added blockchain-native features as BlazerJob advantage

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4bf44b4d35

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/index.ts
Comment on lines +217 to +221
// Décrémenter retriesLeft
const newRetriesLeft = Math.max(0, task.retriesLeft - 1);

if (newRetriesLeft > 0) {
// Récupérer la configuration de retry

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Retry count is off by one

The retry decision is based on newRetriesLeft > 0, but newRetriesLeft is already decremented. That means a task configured with retriesLeft = 1 never retries (the first failure sets newRetriesLeft to 0 and falls into the permanent-failure path). More generally, a task configured for N retries will only get N-1 retries. Given the documented semantics (“number of retry attempts”), this causes fewer attempts than configured; consider checking task.retriesLeft > 0 before decrementing or adjusting the condition so a task with 1 retry actually gets one retry.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants