LoginSign Up
← Back to all sparks
P

Promptfoo

AI-ASSISTANTS
Velocity5.0

Open-source LLM evaluation, testing and red-teaming toolkit

www.promptfoo.dev ↗

Promptfoo's feed has gone quiet except for small fixes to its code-scan action.

llm-evaluationred-teaminggithub-actionsprovider-coveragecode-scanning
◆Current state
The newest entries are code-scan GitHub Action patches: 0.2.1 updates type definitions and 0.2.2 mints the OIDC token after the CLI installs. The main evaluator's last visible release, 0.121.20 in July, added Claude Opus 5, Kimi K3 and websocket URL templating, following a run of releases that tracked each new frontier model.
◆Where it's heading
The evaluator's rhythm is provider coverage plus red-team strategies, and the code-scan action is maintained on its own track. The feed shows no evaluator release since July, which may be a feed gap rather than a pause.
◆Prediction
If the evaluator is still shipping, the next visible entry will likely add the latest frontier models; the feed doesn't show whether it stopped.

◆Recent moves

  1. 1mo ago

    Code-scan action 0.2.2 fixes OIDC token ordering

    A one-line fix that mints the OIDC token after the CLI installs. Ordering repair in the code-scan action.

    View source ↗
  2. 1mo ago

    Code-scan action 0.2.1 updates type definitions

    A dependency update for type definitions in the code-scan action. No behaviour change.

    View source ↗
  3. 2mo ago

    Code-scan action drops Node 20 and hardens its supply chain

    The code-scan action drops Node.js 20 as a declared breaking change and patches undici alongside supply-chain hardening. Nothing new for evaluation users, but anyone pinning the action on an older runner has to move.

    View source ↗
  4. 3mo ago

    Promptfoo adds Claude Opus 5, Kimi K3 and websocket URL templating

    Claude Opus 5, Kimi K3 and refreshed Azure and Gemini catalogues arrive together, with websocket URL templating the one non-provider feature. The usual shape of a promptfoo release.

    View source ↗
  5. 4mo ago

    Promptfoo adds GPT-5.6, Grok 4.5 and an Open Interpreter provider

    GPT-5.6 on Bedrock and GA, Grok 4.5, an Open Interpreter provider and a new red-team goblin strategy. Token-usage accounting gets proper helpers for the first time.

    View source ↗
  6. 4mo ago

    Promptfoo adds per-test repeat and broad Bedrock model coverage

    Per-test repeat and broad Bedrock coverage — evaluation ergonomics alongside the standing provider expansion.

    View source ↗