Overview

7 days30 days

Latest CI Pipeline Executions

Fuzzy

Succeeded
fix/stream-to-text-run-error
ac1098d2 feat: add LLM Gateway provider adapter (#1016) * feat: add @tanstack/ai-llmgateway adapter New provider adapter for LLM Gateway (llmgateway.io) — an open-source, self-hostable AI gateway routing one OpenAI-compatible endpoint to hundreds of models. Built on @tanstack/openai-base driven by the OpenAI SDK with a baseURL override (same pattern as ai-grok/ai-groq), with curated flagship model metadata, open-ended model ids (provider/model pinning supported), reasoning_content delta extraction, and summarize factories. Claude-Session: https://claude.ai/code/session_01PuLomtAzhhxAa692JW6eFU * test: wire llmgateway into e2e provider matrix Adds the llmgateway provider to the feature-support matrix, test-matrix iteration order, chat/summarize adapter factories, and the e2e app's dependencies. Covers chat, tools (parallel/approval), structured output (incl. native streaming), multimodal, multi-turn, and summarize — 19 specs, all passing against aimock. Claude-Session: https://claude.ai/code/session_01PuLomtAzhhxAa692JW6eFU * docs: add LLM Gateway adapter page Claude-Session: https://claude.ai/code/session_01PuLomtAzhhxAa692JW6eFU * fix: forward summarize maxLength as max_tokens Address review findings on the LLM Gateway adapter: - packages/ai: register `llmgateway` in the summarize wrapper's provider-native token-key map. The adapter constructs ChatStreamSummarizeAdapter with name 'llmgateway', which was not in MAX_TOKENS_KEY_BY_ADAPTER, so summarize({ maxLength }) was dropped before reaching the wire and logged a warning saying a first-party adapter was unrecognised. LLM Gateway's OpenAI-compatible Chat Completions surface reads `max_tokens` (it does not accept `max_completion_tokens`). - Add a regression test asserting the mocked request carries the cap, plus the harness hook it needs: the summarize wrapper builds its own text adapter internally, so the mock client is applied to the wrapper's inner adapter. - e2e: add llmgateway to the `reasoning` feature set so the adapter's extractReasoning override (delta.reasoning_content) is covered. - Preserve the original error as `cause` in getLLMGatewayApiKeyFromEnv. - Changeset: drop the pricing/context-window claim (that metadata is module-local, not exported) and cover the @tanstack/ai patch. - docs/config.json: refresh updatedAt on the two edited docs pages. Claude-Session: https://claude.ai/code/session_019Cghg44NaR9ER2XWPo1qrW * fix(ai-llmgateway): align dep versions with the workspace Bump vite to ^8.2.1 and @vitest/coverage-v8 to 4.1.10 to match every other package (fixes the sherif multiple-dependency-versions errors), and use workspace:^ for published dependencies per repo convention. Claude-Session: https://claude.ai/code/session_017MciDnFFB5JLiXUS2t96GW
by Ismail Gha...
Succeeded
fix/stream-to-text-run-error
ac1098d2 Merge be1636e7303ad280359dd132f144fe1762c295dd into d34b6c01fbc9ed83e5dc9bd2725eb05f6b03bfd4
by Jan Kubica
Succeeded
fix/stream-to-text-run-error
0c65943d fix: propagate non-streaming run errors
by jan-kubica
Succeeded
fix/stream-to-text-run-error
0c65943d Merge 0ff9643cd693f5f0abb71a17b44aa6bcf56e91f2 into f7c67a85bb7dabaed4c80fc01ffc8a03fe9375a0
by Jan Kubica