package sourcecheck import ( "context" "fmt" "net/http" "strings" "time" "gitea.mynodes.xyz/ilker/llmgw/internal/safedial" ) // Check asks whether a model's weights are actually there. // // A source that does not resolve is caught today by a replica failing to start, // minutes later, on a node — and the error names the node rather than the typo. // Asking now turns that into a sentence while the operator still has the file // open. // // Only URLs. A path is checked on the node that will use it, by the node, which // is the only machine whose answer means anything; a bare model id is resolved // by the engine and is not this function's business. // // A package of its own rather than a helper in the CLI, because the admin page // adds models too and was not checking anything. Two ways in that disagree // about whether the weights exist is the kind of difference nobody finds until // a replica fails on a node, hours later, naming the node. func Check(ctx context.Context, source string) (size int64, err error) { url, ok := HTTPSource(source) if !ok { return 0, nil } ctx, cancel := context.WithTimeout(ctx, 15*time.Second) defer cancel() req, err := http.NewRequestWithContext(ctx, http.MethodHead, url, nil) if err != nil { return 0, err } // Not anything link-local: instance metadata answering a HEAD would be // read through this, by whoever can add a model. resp, err := safedial.Client(safedial.ControlPlane, 0).Do(req) if err != nil { return 0, fmt.Errorf("cannot reach %s: %w", url, err) } defer resp.Body.Close() if resp.StatusCode != http.StatusOK { return 0, fmt.Errorf("%s answered %s", url, resp.Status) } // Absent when the server does not send it, which is not an error: a // resumable fetch does not need the length in advance, and refusing here // would reject a mirror that is merely terse. Go reports that as -1; // normalised to 0 so callers have one spelling of "unknown". if resp.ContentLength < 0 { return 0, nil } return resp.ContentLength, nil } // HTTPSource returns the URL to check, and whether there is one. // // hf: is expanded the way the fetcher expands it, so the check asks about the // same file the download will ask for rather than about a string that looks // similar. func HTTPSource(source string) (string, bool) { switch { case strings.HasPrefix(source, "http://"), strings.HasPrefix(source, "https://"): return source, true case strings.HasPrefix(source, "hf:"): rest := strings.TrimPrefix(source, "hf:") parts := strings.SplitN(rest, "/", 3) if len(parts) != 3 { // A repository rather than a file. vLLM and SGLang download those // themselves, so there is nothing here to check. return "", false } return fmt.Sprintf("https://huggingface.co/%s/%s/resolve/main/%s", parts[0], parts[1], parts[2]), true default: return "", false } }