Releasesby GlyphPromptfoo 0.123.0
0.123.0 (2026-09-10) ⚠ BREAKING CHANGES providers: default GPT-5.6+ to Responses ( #10803 ) Features assertions: grade native audio with llm-rubric ( #10814 ) ( 39c4fb5 ) providers: add Claude Fable and Mythos 5.1 ( #10601 ) ( ac6ba5b ) providers: add GPT-6 Astra support ( #10625 ) ( cd4c68b ) providers: add grok-4.6, grok-imagine-image-2.0, and...
Also shipped Sep 10, 2026Promptfoo in September 2026 →
BigQuery conversational analytics adds ML.CORRELATION in preview
Conversational analytics can now use ML.CORRELATION to calculate statistical correlations between a target column and one or more metric columns in a table.
BigQuery ML.METRICS evaluates predictions without a stored model
The preview ML.METRICS function computes classification or regression evaluation metrics on any table or query with actual and predicted values, with no need to create or reference a stored model.
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data. This feature is in Preview .
BigQuery Data Engineering Agent integrates with BigQuery Graph
The Data Engineering Agent now uses BigQuery Graph for extra context between source and destination schemas, improving schema mapping accuracy in data engineering pipelines. It is generally available.
Using dbt artifacts for Slim CI and defer to production in dbt Projects on Snowflake (General availability)
Slim CI, defer to production, failed-execution recovery, and concurrent execution are now generally available for dbt Projects on Snowflake. Reuse dbt artifacts from recent production executions to accelerate development, streamline CI/CD workflows, and recover from failed production runs without maintaining a separate artifact store.
External secret providers (Preview)
External secret providers are now in preview. If your organization already keeps API keys, database passwords, and similar values in AWS Secrets Manager, Azure Key Vault, or Google Cloud Secret Manager, Snowflake can read those values when a query needs them, so you don't have to maintain a second copy in a Snowflake secret .
More from PromptfooEvery Promptfoo release →
Promptfoo 0.123.1
0.123.1 (2026-09-18) Features bedrock: refresh auth across HTTP adapters ( #10123 ) ( 9d3f063 ) providers: add Gemini 3.8 and Vertex Live ( #10956 ) ( 1417f22 ) providers: add GPT-Live voice sessions ( #10891 ) ( 316a334 ) providers: add OpenAI Agents API ( #10892 ) ( ad3bee3 ) providers: add portable HTTP config schemas ( #10968 ) ( fcd0604 ) providers...
Promptfoo 0.122.2
0.122.2 (2026-08-28) Features auth: support configurable Cloud auth header name ( #10375 ) ( 997cb56 ) providers: add Codex Security SDK provider ( #10467 ) ( df8a5ab )
Promptfoo 0.122.1
0.122.1 (2026-08-26) Features eval: distinguish scan footprint from incurred token usage ( #10497 ) ( 8df8ef0 ) providers: add Gemini 3.7 Flash and Flash-Lite ( #10389 ) ( bc6b189 ) redteam: account for multi-turn attacker and grading tokens ( #10407 ) ( 33cc8bc ) redteam: report generation, target, attacker, and grading tokens ( #10408 ) ( 0891e4e )...
Promptfoo 0.124.0
0.124.0 (2026-10-06) ⚠ BREAKING CHANGES providers: remove hosted ChatKit provider providers: make WatsonX SDKs opt-in deps: make Langfuse SDK opt-in deps: make Slack SDK opt-in providers: make OpenAI Agents an explicit install providers: make Codex Security SDK opt-in providers: make browser SDKs explicit installs deps: make local Transformers opt-in...
Promptfoo 0.124.1
0.124.1 (2026-10-08) Features assertions: record cost without a threshold (037f1f6) providers: add OpenAI Decisions support (2dbf3ec) providers: expose catalog text-token pricing (3ecce2e) Bug Fixes assertions: preserve async expression grading (1df3eb8) assertions: preserve keyword-property grading (a2da804) assertions: preserve regex operands after yield...
Promptfoo 0.122.0
0.122.0 (2026-08-04) ⚠ BREAKING CHANGES drop Node.js 20 support ( #10260 ) Bug Fixes deps: keep the Shai-Hulud compromised versions unreachable ( #10301 ) ( db2a066 ) deps: patch undici in code-scan-action and guard both lockfiles ( #10278 ) ( 15bf41f ) deps: pin socket.io-parser above the packet-decoder DoS ( #10279 ) ( d0f2a83 ) deps: repair Biome and...
Promptfoo 0.121.20
0.121.20 (2026-07-30) Features providers: add Claude Opus 5 support ( #10210 ) ( ff84f13 ) providers: add current Azure, Claude, and Gemini models ( #10128 ) ( 5c216a1 ) providers: add Kimi K3 support to Moonshot provider ( #10132 ) ( a1168b6 ) websocket: support URL templating ( #10171 ) ( a9aaced ) Bug Fixes assertions: default conversation-relevance...
Promptfoo 0.125.0
This release adds support for rouge-l and rouge-s assertions, trace span filtering, and Gemini media models. It also introduces a safe mode to disable inline JavaScript execution during evaluations.