Overview

7 days30 days

Latest CI Pipeline Executions

Fuzzy

Succeeded
feat/llmgateway-adapter
8014624f 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 smakosh
Succeeded
feat/llmgateway-adapter
8014624f Merge 6b263baa9e121bfd4c002dfa0b02399b00331042 into f7c67a85bb7dabaed4c80fc01ffc8a03fe9375a0
by Ismail Gha...
Succeeded
feat/llmgateway-adapter
58c65616 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 smakosh
Succeeded
feat/llmgateway-adapter
58c65616 Merge 4e79a73caaf3428f1584e9f2bbadb0ee20f287ac into 22b5b7d12321daa2e93faa6277bf225575ca2a5e
by Ismail Gha...
Succeeded
feat/llmgateway-adapter
57259f8e chore(agents): require docs, pr-description, and ponytail skills (#1162) * chore(agents): require the docs skill before touching docs Check in the docs skill for Claude, Grok, and Codex. AGENTS.md and CLAUDE.md now require loading it before planning, writing, or editing docs/. * chore(agents): add pr-description skill and require it on PRs Agents must load pr-description before gh pr create and after an agent push on an open PR. The skill writes the title and body from the diff, and tries browser screenshots when the PR has UI. * ci: apply automated fixes * chore(agents): clarify docs skill gates and fence languages Hard-gate skip paths continue in the same turn. The tone gate sits before Phase 2. Example fences use a text language id. * chore(agents): remove screenshot capture from pr-description The skill no longer captures, commits, or embeds PR screenshots. * ci: apply automated fixes * chore(agents): require the ponytail skill before writing code Claude, Grok, and Codex must load ponytail before they plan or edit application code, tests, or examples. Repo quality gates, E2E, docs, and pr-description still apply. * ci: apply automated fixes --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
by Alem Tuzlak
Failed
feat/llmgateway-adapter
57259f8e Merge 3b126fbf5ce7d3d9332ae8813dfd2bcdb5ad6666 into 9ac4a38a99f6c74f96399ec2225ead532c369f76
by Ismail Gha...
Succeeded
feat/llmgateway-adapter
d8633d3b Merge 70ad50d77eeea04a28ef85dc1316916354fdc63f into c092231d974bc1f5869d4abc56b5bc54c84245d1
by Ismail Gha...
Succeeded
feat/llmgateway-adapter
d8633d3b 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
by smakosh
Succeeded
feat/llmgateway-adapter
a4a4ad71 refactor(code-mode)!: rename Code Mode "skills" to "snippets" (#1114) * refactor(code-mode)!: rename Code Mode "skills" to "snippets" Disambiguates Code Mode's runtime code library from the agent/provider "skills" systems (the SKILL.md packaging feature). Breaking rename of the package, its public API, and the Code Mode wire contract. - Package: `@tanstack/ai-code-mode-skills` -> `@tanstack/ai-code-mode-snippets` (dir `packages/ai-code-mode-skills` -> `packages/ai-code-mode-snippets`) - API: `codeModeWithSkills`->`codeModeWithSnippets`, `snippetsToTools`, `snippetsToBindings`, `selectRelevantSnippets`, `createSnippetManagementTools`, `createSnippetsSystemPrompt`, `generateSnippetTypes`, `createFile/MemorySnippetStorage`, all `Snippet*` types/options - Runtime tools: `search_snippets`/`get_snippet`/`register_snippet`; sandbox binding prefix `snippet_` - Wire contract (`@tanstack/ai`): events `code_mode:snippet_*`, `snippet:registered`; types `CodeModeSnippet*Event`/`SnippetRegisteredEvent` - Sandbox hook (`@tanstack/ai-code-mode`): `createCodeModeTool` option `getSkillBindings` -> `getSnippetBindings` - Updated example `ts-code-mode-web`, docs, and reference docs Agent/provider skills (packages/*/skills, SKILL.md, provider skills-wire) are intentionally untouched. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: apply automated fixes * docs/test: address CodeRabbit review (rename-related fixes) - Rename leftover test-cli id `SKL` -> `SNP` (skill abbreviation) - Fix inaccurate "client-side" execution claim in provider-skills.md and ai-core/tool-calling SKILL.md (snippets run in a local isolate, not necessarily client-side) - Package README: correct `registry` -> `toolsRegistry` return field; add `text` language to bare fence - code-mode-with-snippets.md: add `text` language to two bare fences (MD040) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(code-mode-snippets): reject path traversal in snippet names `createFileSnippetStorage` used the LLM-supplied snippet name directly as an on-disk path segment (`join(directory, name)`) in get/save/delete, so a name like `../../x` could read, write, or delete files outside the storage directory. Snippet names are already identifier-shaped (they double as `snippet_<name>` sandbox tool names), so names are now validated against `/^[A-Za-z0-9_-]+$/`: save/delete throw and get returns null for unsafe names. Addresses a CodeRabbit finding (pre-existing under the old skills storage). Adds regression tests covering traversal attempts and ordinary names. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci: apply automated fixes --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
by Jack Herri...
Succeeded
feat/llmgateway-adapter
a4a4ad71 Merge 2d3f7d63a4eb75f1f28bc28f729c76173a4a392b into 0fb826321c9ba7bd5d8ba0062be2a00b6178726d
by Ismail Gha...