🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
TypeScript analyticsautogenevaluationlangchainlarge-language-modelsllama-indexllmllm-evaluationllm-observabilityllmopsmonitoringobservabilityopen-sourceopenaiplaygroundprompt-engineeringprompt-managementself-hostedycombinator
chore(pricing): document Jev 1.14.0 matchPattern coverage in audit skill (#18835)
langfuse-bot747daf9a57f7
diff --git a/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md b/.agents/skills/add-model-price/references/provider-sources-and-price-keys.mdindex 9ff4bac769..aeb6f10993 100644--- a/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md+++ b/.agents/skills/add-model-price/references/provider-sources-and-price-keys.md@@ -1176,6 +1176,17 @@ json_literal = "<price_per_mtok>e-6"`types.ts` is not one of the selectable arrays the audit may edit; report anewly released Jev version that should become selectable as unresolved.+- **Jev 1.14.0 found, no pricing-file change needed (confirmed October 15+ 2026)** — `https://docs.typesafe.ai/models` now lists `jev-1.14.0` alongside+ `jev-1.13.0`, priced identically ($42/Btok = $0.042/MTok input, output free).+ `jev-preview` now points to `jev-1.14.0`; `jev-latest` still points to+ `jev-1.13.0`. The existing `jev` entry's matchPattern+ (`(?i)^(~?typesafe(-ai)?\/)?jev(-[0-9]+(\.[0-9]+)*(-[0-9]{8})?|-latest|-preview)?$`)+ already accepts `jev-1.14.0` (its `[0-9]+(\.[0-9]+)*` segment matches+ `1.14.0`) and the price is unchanged, so no pricing-file edit was required.+ This confirms the generic version-number matchPattern design handles new+ dotted Jev point releases without per-version entries, as intended.+- **Claude Sonnet 5.5 cache-read price corrected to 0.05x (found October 13 2026)** —Anthropic's pricing page cache-hits footnote changed from listing only Claude Opus 5.5(and separately Fable 5.1/Mythos 5.1) at a non-standard multiplier to now also including