238 lines
9.0 KiB
Go
238 lines
9.0 KiB
Go
package server
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
|
|
"git.a-wan.net/alan/pipelines/internal/opencode"
|
|
"git.a-wan.net/alan/pipelines/internal/pipeline"
|
|
"git.a-wan.net/alan/pipelines/internal/protocol"
|
|
"git.a-wan.net/alan/pipelines/internal/stage"
|
|
)
|
|
|
|
// sessionExportBody is a minimal native export envelope with a user and an
|
|
// assistant turn, used by the fake CLI below.
|
|
const sessionExportBody = `{"info":{"id":"ses_run"},"messages":[` +
|
|
`{"info":{"id":"m1","role":"user"},"text":"do the task"},` +
|
|
`{"info":{"id":"m2","role":"assistant"},"parts":[` +
|
|
`{"type":"text","text":"done"},` +
|
|
`{"type":"tool","name":"shell","state":{"status":"completed","input":{"cmd":"ls"},"content":[{"type":"text","text":"output here"}]}}]}]}`
|
|
|
|
// sessionExportCLI isolates both the authenticated V2 API and legacy CLI.
|
|
// Neither export transport may fall through to the operator's real service.
|
|
func sessionExportCLI(t *testing.T) {
|
|
t.Helper()
|
|
path := filepath.Join(t.TempDir(), "opencode")
|
|
script := "#!/bin/sh\n" +
|
|
"[ \"$1\" = export ] && shift || { [ \"$1\" = session ] && [ \"$2\" = export ] && shift 2 || exit 8; }\n" +
|
|
"[ \"$1\" = ses_run ] || exit 9\n" +
|
|
"cat <<'EOF'\n" + sessionExportBody + "\nEOF\n"
|
|
if err := os.WriteFile(path, []byte(script), 0700); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
t.Setenv("PIPELINES_OPENCODE", path)
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
user, password, ok := r.BasicAuth()
|
|
if !ok || user != "opencode" || password != "fixture-password" {
|
|
w.WriteHeader(http.StatusUnauthorized)
|
|
return
|
|
}
|
|
if r.Method != "GET" || r.URL.Path != "/api/experimental/session/ses_run/export" || r.URL.Query().Get("sanitize") != "false" {
|
|
t.Errorf("unexpected export operation: %s %s", r.Method, r.URL.Path)
|
|
w.WriteHeader(http.StatusNotFound)
|
|
return
|
|
}
|
|
w.Header().Set("Content-Type", "application/json")
|
|
fmt.Fprint(w, `{"data":`+sessionExportBody+`}`)
|
|
}))
|
|
t.Cleanup(srv.Close)
|
|
passwordPath := filepath.Join(t.TempDir(), "password")
|
|
if err := os.WriteFile(passwordPath, []byte("fixture-password"), 0600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
t.Setenv(opencode.EndpointEnvKey, srv.URL)
|
|
t.Setenv(opencode.EndpointPasswordFileEnvKey, passwordPath)
|
|
t.Setenv(opencode.EndpointUsernameEnvKey, "")
|
|
}
|
|
|
|
// sessionExportRunner runs one stage that records a session for the run, so the
|
|
// runner's post-stage export has an owner to read. The export seam is supplied by
|
|
// the caller; ready gates the stage until the test has captured the run id.
|
|
func sessionExportRunner(t *testing.T, backend string, seam func(stage.SessionExportRequest) (stage.SessionExportResult, error)) (*runHandler, *pipeline.Store, int64) {
|
|
t.Helper()
|
|
ctx, cancel := context.WithCancel(context.Background())
|
|
t.Cleanup(cancel)
|
|
store, err := pipeline.Open(filepath.Join(t.TempDir(), "session.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
t.Cleanup(func() { store.Close() })
|
|
if _, err := store.Submit(ctx, "session-export", pipeline.Template([]string{"one"}, true)); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
items, err := store.List(ctx)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
handler := Handler(ctx, store).(*runHandler)
|
|
t.Cleanup(func() { cancel(); WaitRuns(handler) })
|
|
handler.runner.artifactsRoot = t.TempDir()
|
|
if seam != nil {
|
|
handler.runner.exportSession = func(_ context.Context, request stage.SessionExportRequest) (stage.SessionExportResult, error) {
|
|
return seam(request)
|
|
}
|
|
}
|
|
ready := make(chan struct{})
|
|
var runID int64
|
|
handler.runner.execute = func(ctx context.Context, _ stage.Definition, _ stage.Values) (stage.Result, error) {
|
|
<-ready
|
|
if err := handler.runner.store.RunSession(ctx, runID, 1, "ses_run", false, backend, ""); err != nil {
|
|
return stage.Result{}, err
|
|
}
|
|
return stage.Result{Outcome: "success", Output: stage.Values{"summary": "done"}}, nil
|
|
}
|
|
run, err := handler.runner.start(protocol.Message{PipelineID: items[0].ID, Version: 1, RequestKey: "session", Workspace: t.TempDir(), Input: map[string]any{"prompt": "task"}})
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
runID = run.ID
|
|
close(ready)
|
|
handler.runner.wg.Wait()
|
|
return handler, store, run.ID
|
|
}
|
|
|
|
// TestRunnerExportsTheHTMLSessionIntoArtifactsAndServesIt proves the real export
|
|
// path writes the one html session file into the step's artifacts directory,
|
|
// lists it with an artifact URL and serves it 200, without changing the step's
|
|
// status, outcome or target, and produces no legacy session.md.
|
|
func TestRunnerExportsTheHTMLSessionIntoArtifactsAndServesIt(t *testing.T) {
|
|
sessionExportCLI(t)
|
|
handler, store, runID := sessionExportRunner(t, "v2", nil)
|
|
detail, err := store.GetRun(context.Background(), runID)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if detail.Status != "succeeded" || len(detail.Steps) != 1 {
|
|
t.Fatalf("unexpected run: %+v", detail)
|
|
}
|
|
step := detail.Steps[0]
|
|
if step.Status != "completed" || step.Outcome != "success" {
|
|
t.Fatalf("export changed the stage result: %+v", step)
|
|
}
|
|
if len(step.Transcript) > 32<<10 || strings.Contains(step.Transcript, "do the task") || strings.Contains(step.Transcript, "session.md") {
|
|
t.Fatalf("transcript was changed by the export: %q", step.Transcript)
|
|
}
|
|
if step.SessionExport == nil || step.SessionExport.SessionID != "ses_run" || step.SessionExport.Source != "native_export" {
|
|
t.Fatalf("export evidence missing: %+v", step.SessionExport)
|
|
}
|
|
if step.SessionExport.HTML != "session.html" || step.SessionExport.Messages != 2 || step.SessionExport.HTMLBytes == 0 {
|
|
t.Fatalf("export evidence wrong: %+v", step.SessionExport)
|
|
}
|
|
if _, ok := artifactNamed(step.Artifacts, stage.SessionMarkdownFile); ok {
|
|
t.Fatalf("legacy session.md must not be produced: %+v", step.Artifacts)
|
|
}
|
|
artifact, ok := artifactNamed(step.Artifacts, "session.html")
|
|
if !ok {
|
|
t.Fatalf("session.html not in the artifact listing: %+v", step.Artifacts)
|
|
}
|
|
wantURL := fmt.Sprintf("/artifacts/%d/1/session.html", runID)
|
|
if artifact.URL != wantURL || artifact.SizeBytes == 0 {
|
|
t.Fatalf("session.html listing wrong: %+v", artifact)
|
|
}
|
|
|
|
srv := httptest.NewServer(handler)
|
|
defer srv.Close()
|
|
resp, err := http.Get(srv.URL + wantURL)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
body, _ := io.ReadAll(resp.Body)
|
|
resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK || len(body) == 0 {
|
|
t.Fatalf("session.html served %d (%d bytes)", resp.StatusCode, len(body))
|
|
}
|
|
if contentType := resp.Header.Get("Content-Type"); !strings.HasPrefix(contentType, "text/html") {
|
|
t.Fatalf("session.html content type = %q", contentType)
|
|
}
|
|
if !strings.Contains(string(body), "output here") {
|
|
t.Fatal("served html missing tool output")
|
|
}
|
|
}
|
|
|
|
// TestRunnerSessionExportFailureTruncationAndUnavailableHarness proves the three
|
|
// non-success exports block success without replacing the completed computation.
|
|
func TestRunnerSessionExportFailureTruncationAndUnavailableHarness(t *testing.T) {
|
|
cases := []struct {
|
|
name string
|
|
backend string
|
|
seam func(stage.SessionExportRequest) (stage.SessionExportResult, error)
|
|
wantSrc string
|
|
wantDiag string
|
|
wantTrunc bool
|
|
}{
|
|
{
|
|
name: "failure",
|
|
backend: "v2",
|
|
seam: func(stage.SessionExportRequest) (stage.SessionExportResult, error) {
|
|
return stage.SessionExportResult{}, errors.New("native session export failed")
|
|
},
|
|
wantSrc: "native_export",
|
|
wantDiag: "native session export failed",
|
|
},
|
|
{
|
|
name: "truncated",
|
|
backend: "v2",
|
|
seam: func(stage.SessionExportRequest) (stage.SessionExportResult, error) {
|
|
return stage.SessionExportResult{Source: "native_export", Truncated: true, Messages: 3}, nil
|
|
},
|
|
wantSrc: "native_export",
|
|
wantTrunc: true,
|
|
},
|
|
{
|
|
name: "unavailable",
|
|
backend: "pi",
|
|
seam: nil,
|
|
wantSrc: "unavailable",
|
|
wantDiag: "harness has no native export path",
|
|
},
|
|
}
|
|
for _, tc := range cases {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
handler, store, runID := sessionExportRunner(t, tc.backend, tc.seam)
|
|
detail, err := store.GetRun(context.Background(), runID)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if detail.Status != "waiting" || detail.ExportPendingSequence != 1 || detail.FinishedAt != "" || detail.Output["summary"] != "done" {
|
|
t.Fatalf("export gate did not preserve and block computation: %+v", detail)
|
|
}
|
|
step := detail.Steps[0]
|
|
if step.Status != "completed" || step.Outcome != "success" {
|
|
t.Fatalf("export changed the stage result: %+v", step)
|
|
}
|
|
if step.SessionExport == nil || step.SessionExport.Source != tc.wantSrc {
|
|
t.Fatalf("export evidence wrong: %+v", step.SessionExport)
|
|
}
|
|
if tc.wantDiag != "" && !strings.Contains(step.SessionExport.Diagnostic, tc.wantDiag) {
|
|
t.Fatalf("diagnostic %q missing %q", step.SessionExport.Diagnostic, tc.wantDiag)
|
|
}
|
|
if step.SessionExport.Truncated != tc.wantTrunc {
|
|
t.Fatalf("truncated = %v, want %v", step.SessionExport.Truncated, tc.wantTrunc)
|
|
}
|
|
if tc.wantSrc == "unavailable" {
|
|
if artifacts, _, _ := handler.runner.scanArtifacts(runID, 1, filepath.Join(handler.runner.artifactsRoot, fmt.Sprint(runID), "1")); len(artifacts) != 0 {
|
|
t.Fatalf("unavailable harness wrote files: %+v", artifacts)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|