Reuse valid workspace checkpoints on request

This commit is contained in:
2026-07-08 03:02:50 +00:00
parent 1d3a444df8
commit ae9c2e1d5e
14 changed files with 1406 additions and 290 deletions

View File

@@ -80,6 +80,149 @@ func TestWorkspaceRecorderWritesSuccessfulCheckpointFiles(t *testing.T) {
}
}
func TestWorkspaceLoaderReusesSuccessfulCheckpointFiles(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
loader := &WorkspaceLoader{root: root}
doc := &source.SourceDocument{
ID: "source-1",
Kind: "document",
Format: "text/plain",
Digest: "sha256:source",
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello"}},
}
chunks := []contracts.SourceChunk{
{
ID: "chunk-1",
SourceID: "source-1",
Index: 0,
StartUnitID: 1,
EndUnitID: 1,
Content: []byte("chunk content"),
MediaType: "text/plain",
Units: doc.Units,
},
}
extractOutput := contracts.ExtractOutput{
LaneID: "spells",
ExtractorKey: "dnd/spells",
SourceID: doc.ID,
ChunkID: "chunk-1",
Payload: contracts.RawPayload{
Content: []byte(`{"spell":"cure wounds"}`),
MediaType: "application/json",
},
}
mergeOutput := contracts.MergeOutput{
LaneID: "spells",
MergerKey: "appendorder",
SourceID: doc.ID,
Payload: contracts.RawPayload{
Content: []byte(`{"merged":true}`),
MediaType: "application/json",
},
}
normalizeOutput := contracts.NormalizeOutput{
LaneID: "spells",
NormalizerKey: "noop",
SourceID: doc.ID,
Payload: contracts.RawPayload{
Content: []byte(`{"normalized":true}`),
MediaType: "application/json",
},
}
if err := recorder.SourceSucceeded("seriatim", doc); err != nil {
t.Fatalf("SourceSucceeded: %v", err)
}
if err := recorder.ChunkSucceeded("generic", doc.Digest, chunks, nil); err != nil {
t.Fatalf("ChunkSucceeded: %v", err)
}
extractDeps := []pipeline.CheckpointFingerprint{{Name: "chunks", Value: "sha256:chunks"}}
if err := recorder.ExtractSucceeded("spells", "dnd/spells", extractDeps, []contracts.ExtractOutput{extractOutput}, nil, nil); err != nil {
t.Fatalf("ExtractSucceeded: %v", err)
}
mergeDeps := rawOutputDigests([]contracts.RawPayload{extractOutput.Payload})
if err := recorder.MergeSucceeded("spells", "appendorder", mergeDeps, mergeOutput, nil); err != nil {
t.Fatalf("MergeSucceeded: %v", err)
}
normalizeDeps := rawOutputDigests([]contracts.RawPayload{mergeOutput.Payload})
if err := recorder.NormalizeSucceeded("spells", "noop", normalizeDeps, normalizeOutput, nil); err != nil {
t.Fatalf("NormalizeSucceeded: %v", err)
}
sourceCheckpoint, decision := loader.Source("seriatim")
if !decision.Reused || sourceCheckpoint.Document.ID != "source-1" {
t.Fatalf("source decision = %#v checkpoint=%#v, want reused", decision, sourceCheckpoint)
}
chunkCheckpoint, decision := loader.Chunk("generic", doc.Digest)
if !decision.Reused || len(chunkCheckpoint.Chunks) != 1 || string(chunkCheckpoint.Chunks[0].Content) != "chunk content" {
t.Fatalf("chunk decision = %#v checkpoint=%#v, want reused", decision, chunkCheckpoint)
}
extractCheckpoint, decision := loader.Extract("spells", "dnd/spells", extractDeps)
if !decision.Reused || len(extractCheckpoint.Outputs) != 1 || string(extractCheckpoint.Outputs[0].Payload.Content) != `{"spell":"cure wounds"}` {
t.Fatalf("extract decision = %#v checkpoint=%#v, want reused", decision, extractCheckpoint)
}
mergeCheckpoint, decision := loader.Merge("spells", "appendorder", mergeDeps)
if !decision.Reused || string(mergeCheckpoint.Output.Payload.Content) != `{"merged":true}` {
t.Fatalf("merge decision = %#v checkpoint=%#v, want reused", decision, mergeCheckpoint)
}
normalizeCheckpoint, decision := loader.Normalize("spells", "noop", normalizeDeps)
if !decision.Reused || string(normalizeCheckpoint.Output.Payload.Content) != `{"normalized":true}` {
t.Fatalf("normalize decision = %#v checkpoint=%#v, want reused", decision, normalizeCheckpoint)
}
}
func TestWorkspaceLoaderInvalidatesMissingCorruptAndMismatchedCheckpoints(t *testing.T) {
t.Run("missing", func(t *testing.T) {
loader := &WorkspaceLoader{root: t.TempDir()}
if _, decision := loader.Source("seriatim"); decision.Reused || !strings.Contains(decision.Reason, "missing") {
t.Fatalf("decision = %#v, want missing invalidation", decision)
}
})
t.Run("dependency mismatch", func(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
chunks := []contracts.SourceChunk{{
ID: "chunk-1",
SourceID: "source-1",
Content: []byte("chunk content"),
MediaType: "text/plain",
}}
if err := recorder.ChunkSucceeded("generic", "sha256:source-a", chunks, nil); err != nil {
t.Fatalf("ChunkSucceeded: %v", err)
}
loader := &WorkspaceLoader{root: root}
if _, decision := loader.Chunk("generic", "sha256:source-b"); decision.Reused || !strings.Contains(decision.Reason, "dependency") {
t.Fatalf("decision = %#v, want dependency invalidation", decision)
}
})
t.Run("corrupt payload", func(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
chunks := []contracts.SourceChunk{{
ID: "chunk-1",
SourceID: "source-1",
Content: []byte("chunk content"),
MediaType: "text/plain",
}}
if err := recorder.ChunkSucceeded("generic", "sha256:source", chunks, nil); err != nil {
t.Fatalf("ChunkSucceeded: %v", err)
}
payloadPath := filepath.Join(root, "chunk", "chunks.json")
data := strings.ReplaceAll(string(readFile(t, payloadPath)), contentDigest([]byte("chunk content")), "sha256:bad")
if err := os.WriteFile(payloadPath, []byte(data), 0o644); err != nil {
t.Fatalf("corrupt chunk payload: %v", err)
}
loader := &WorkspaceLoader{root: root}
if _, decision := loader.Chunk("generic", "sha256:source"); decision.Reused || !strings.Contains(decision.Reason, "invalid") {
t.Fatalf("decision = %#v, want corrupt payload invalidation", decision)
}
})
}
func TestWorkspaceRecorderRecordsRejectedExtractOutputs(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
@@ -181,15 +324,21 @@ func assertManifestStatus(t *testing.T, path string, want coreworkspace.StageSta
func readJSON(t *testing.T, path string, out any) {
t.Helper()
data, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read %q: %v", path, err)
}
data := readFile(t, path)
if err := json.Unmarshal(data, out); err != nil {
t.Fatalf("decode %q: %v", path, err)
}
}
func readFile(t *testing.T, path string) []byte {
t.Helper()
data, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read %q: %v", path, err)
}
return data
}
type assertErr string
func (e assertErr) Error() string { return string(e) }