feat(ci): add wiki-search integration test#2536
Draft
mikasenghaas wants to merge 5 commits into
Draft
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PrimeIntellect/Qwen3-0.6B is not in MODEL_RENDERER_MAP so it falls back to DefaultRenderer, which has supports_tools=False unless tool_parser is explicitly set. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
hermes is the vLLM server-side parser name; the renderer uses qwen3. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ero-adv filter - max_turns=2: caps sequential API calls per rollout (embedding + judge) - rollouts_per_example=4: 8 unique examples per batch, better reward variance - zero_advantage enforce=false: avoids retry cycles when all rewards tie - max_completion_tokens=512: cap completion length Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
wiki-searchintegration test to the CI matrix to cover tool call environments, which are currently untestedconfigs/ci/integration/wiki_search.toml: 5 steps, batch size 32,PrimeIntellect/Qwen3-0.6B, withtool_call_parser = "hermes"vmrunner job in.github/workflows/gpu_tests.yamlalongsidealphabet_sortNotes
PrimeIntellect/Qwen3-0.6Bis not inMODEL_RENDERER_MAPin the renderers submodule, so it falls back toDefaultRendererwhich hassupports_tools=Falseunlesstool_parseris explicitly set. The CI config therefore sets both[orchestrator.renderer] tool_parser = "hermes"(renderer-side) and[inference.model] tool_call_parser = "hermes"(vLLM server-side).