steve
9c0ac1d60b
- Transcribe: sanitize the caller-supplied multipart filename (CR/LF would inject Content-Disposition headers; upload metadata is untrusted), always send the required model/response_format fields, parse MIME parameters before extension matching, and give audio/opus its own .opus extension. - doRaw: a response larger than maxResponseBytes is now an error, not a silent truncation. - Shared plumbing: requireBaseURL() + newRequest() helpers replace the 7x-duplicated guard/error string and the triplicated request building across doJSON/doRaw/Health. - Health: non-2xx now returns *llm.APIError (package convention, programmatically distinguishable from transport failure) instead of a one-off unexported error type. - Speak: reject negative Speed; speechMIME no longer accepts video/* Content-Types. - image.go: Generate/Edit share one sdWire validate+map helper. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj
45 lines
1.3 KiB
Go
45 lines
1.3 KiB
Go
package llamaswap
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
|
|
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
|
|
)
|
|
|
|
// Health reports whether the llama-swap instance is reachable (GET
|
|
// {base}/health, which answers "OK" without touching any model). A nil error
|
|
// means the proxy itself is up — it says nothing about how long a subsequent
|
|
// request will take (a cold model swap can still block for minutes). Bound
|
|
// the probe with a short context deadline; the client has no timeout by
|
|
// design.
|
|
//
|
|
// Failure taxonomy matches the rest of the package: transport failures wrap
|
|
// the raw net error; a reachable-but-unhealthy status comes back as
|
|
// *llm.APIError, so callers can errors.As-distinguish the two.
|
|
func (p *Provider) Health(ctx context.Context) error {
|
|
if err := p.requireBaseURL(); err != nil {
|
|
return err
|
|
}
|
|
req, err := p.newRequest(ctx, http.MethodGet, "/health", "", nil)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
resp, err := p.client.Do(req)
|
|
if err != nil {
|
|
return fmt.Errorf("llama-swap: health probe: %w", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
_, _ = io.Copy(io.Discard, io.LimitReader(resp.Body, 1<<10))
|
|
if resp.StatusCode/100 != 2 {
|
|
return &llm.APIError{
|
|
Provider: p.name,
|
|
Status: resp.StatusCode,
|
|
Message: "health endpoint returned a non-2xx status",
|
|
}
|
|
}
|
|
return nil
|
|
}
|