mirror of
https://github.com/unslothai/unsloth.git
synced 2026-07-10 00:08:58 +00:00
264f1a04f8
Boot `unsloth run --disable-tools` against a small GGUF and drive each supported coding agent (claude, codex, hermes, openclaw, opencode, pi) through its documented `unsloth connect <agent> --no-launch` recipe, so the connect flow in unsloth_cli/commands/connect.py stays exercised end to end and regressions surface as a failing check. Per-agent matrix, three jobs: - connection: assert a non-empty, error-free reply to a trivial prompt - file-edit: a two-turn create-and-run hello.py test (dispatch/schedule only, skipped on pull_request) - prompt-cache: verify llama.cpp prefix-cache reuse across requests The GitHub-hosted runners are CPU-only, so each request is trimmed to the smallest prompt that still drives the recipe: claude with --tools to drop unused tool schemas (--allowedTools only gates permission, it does not shrink the prompt), hermes with an empty platform_toolsets.cli, and openclaw with a minimal agent definition. hermes and openclaw run a multi-turn tool loop in file-edit that a CPU runner cannot finish in time, so those two cells are best-effort; their endpoint wiring is still hard-gated by the connection job. A preflight step HTTP-checks each agent's API dialect before install so a server-side contract regression is reported separately from agent or guide drift. |
||
|---|---|---|
| .. | ||
| agent-guides-drive.sh | ||
| agent-guides-install.sh | ||
| assert-llama-loads.sh | ||
| assert-prompt-cache.sh | ||
| ci-connect-prompt.txt | ||
| ci-min-system-prompt.txt | ||
| hf-download-with-retry.sh | ||
| serve-unsloth-run.sh | ||