eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add merge references and retry config

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-07 19:10:55 +00:00
parent c05ecb58d8
commit bcedf19a08
25 changed files with 466 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
internal/framework/pipeline/references_test.go
View File

@@ -109,17 +109,20 @@ func TestMaterializeReferencesStoresSetsAndProvenanceForAllTargets(t *testing.T)
configDir := t.TempDir()
writeReferenceFile(t, filepath.Join(configDir, "chunk.txt"), []byte("chunk text"))
writeReferenceFile(t, filepath.Join(configDir, "extract.txt"), []byte("extract text"))
writeReferenceFile(t, filepath.Join(configDir, "merge.txt"), []byte("merge text"))
writeReferenceFile(t, filepath.Join(configDir, "normalize.txt"), []byte("normalize text"))
profile := baselineProfile()
profile.References = map[string]string{
"scene_guide": "chunk.txt",
"roster": "extract.txt",
"merge_notes": "merge.txt",
"normalization_notes": "normalize.txt",
}
catalog := referenceCatalogForTargets(t,
[]contracts.ReferenceSlot{{Name: "scene_guide"}},
[]contracts.ReferenceSlot{{Name: "roster"}},
[]contracts.ReferenceSlot{{Name: "merge_notes"}},
[]contracts.ReferenceSlot{{Name: "normalization_notes"}},
)
resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
@@ -145,14 +148,18 @@ func TestMaterializeReferencesStoresSetsAndProvenanceForAllTargets(t *testing.T)
if string(extractItem.Content) != "extract text" {
t.Fatalf("extract content = %q, want extract text", extractItem.Content)
}
mergeItem := materialized.ArtifactLanes[0].MergeReferences.ReferenceSet.Slots["merge_notes"].Items[0]
if string(mergeItem.Content) != "merge text" {
t.Fatalf("merge content = %q, want merge text", mergeItem.Content)
}
normalizeItem := materialized.ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["normalization_notes"].Items[0]
if string(normalizeItem.Content) != "normalize text" {
t.Fatalf("normalize content = %q, want normalize text", normalizeItem.Content)
}
provenance := ReferenceProvenance(materialized)
if len(provenance) != 3 {
t.Fatalf("ReferenceProvenance() = %#v, want three entries", provenance)
if len(provenance) != 4 {
t.Fatalf("ReferenceProvenance() = %#v, want four entries", provenance)
}
if provenance[0].Stage != string(StageChunk) || provenance[0].LaneID != "" || provenance[0].SlotName != "scene_guide" || provenance[0].Digest != chunkItem.Digest {
t.Fatalf("ReferenceProvenance()[0] = %#v, want chunk scene guide provenance", provenance[0])
@@ -160,7 +167,10 @@ func TestMaterializeReferencesStoresSetsAndProvenanceForAllTargets(t *testing.T)
if provenance[1].Stage != string(StageExtract) || provenance[1].LaneID != "events" || provenance[1].SlotName != "roster" || provenance[1].Digest != extractItem.Digest {
t.Fatalf("ReferenceProvenance()[1] = %#v, want extract roster provenance", provenance[1])
}
if provenance[2].Stage != string(StageNormalize) || provenance[2].LaneID != "events" || provenance[2].SlotName != "normalization_notes" || provenance[2].Digest != normalizeItem.Digest {
if provenance[2].Stage != string(StageMerge) || provenance[2].LaneID != "events" || provenance[2].SlotName != "merge_notes" || provenance[2].Digest != mergeItem.Digest {
t.Fatalf("ReferenceProvenance()[2] = %#v, want merge notes provenance", provenance[2])
}
if provenance[3].Stage != string(StageNormalize) || provenance[3].LaneID != "events" || provenance[3].SlotName != "normalization_notes" || provenance[3].Digest != normalizeItem.Digest {
t.Fatalf("ReferenceProvenance()[2] = %#v, want normalize notes provenance", provenance[2])
}
}
@@ -185,7 +195,7 @@ func TestMaterializeReferencesRejectsNonUTF8ContentForChunkTarget(t *testing.T)
writeReferenceFile(t, path, []byte{0xff, 0xfe})
resolved := resolvedPipelineWithTargetReference(t, StageChunk, "", "scene_guide", "bad.txt", contracts.ReferenceBindingSourceConfig, contracts.ReferenceSlot{Name: "scene_guide"})
_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, []contracts.ReferenceSlot{{Name: "scene_guide"}}, nil, nil), ReferenceMaterializationOptions{
_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, []contracts.ReferenceSlot{{Name: "scene_guide"}}, nil, nil, nil), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err == nil || !strings.Contains(err.Error(), "chunk") || !strings.Contains(err.Error(), "UTF-8") || !strings.Contains(err.Error(), "scene_guide") || !strings.Contains(err.Error(), path) {
@@ -309,7 +319,7 @@ func TestMaterializeReferencesRejectsUnacceptedMediaTypeForNormalizeTarget(t *te
slot := contracts.ReferenceSlot{Name: "normalization_notes", AcceptedMediaTypes: []string{"text/markdown"}}
resolved := resolvedPipelineWithTargetReference(t, StageNormalize, "events", "normalization_notes", "notes.json", contracts.ReferenceBindingSourceConfig, slot)
_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, nil, nil, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
_, _, err := MaterializeReferences(resolved, referenceCatalogForTargets(t, nil, nil, nil, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err == nil || !strings.Contains(err.Error(), "normalize") || !strings.Contains(err.Error(), "media type") || !strings.Contains(err.Error(), "application/json") || !strings.Contains(err.Error(), "normalization_notes") {
@@ -353,6 +363,7 @@ func TestMaterializeReferencesWarningScopesIncludeTargetContext(t *testing.T) {
catalog := referenceCatalogForTargets(t,
[]contracts.ReferenceSlot{{Name: "scene_guide"}},
[]contracts.ReferenceSlot{{Name: "roster"}},
nil,
[]contracts.ReferenceSlot{{Name: "normalization_notes"}},
)
resolved, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
@@ -407,6 +418,10 @@ func resolvedPipelineWithTargetReference(t *testing.T, stage ModuleStage, laneID
lane := profile.Artifacts[laneID]
lane.References = map[string]string{slotName: source}
profile.Artifacts[laneID] = lane
case StageMerge:
lane := profile.Artifacts[laneID]
lane.Merge.References = map[string]string{slotName: source}
profile.Artifacts[laneID] = lane
case StageNormalize:
lane := profile.Artifacts[laneID]
lane.Normalize.References = map[string]string{slotName: source}
@@ -425,6 +440,8 @@ func resolvedPipelineWithTargetReference(t *testing.T, stage ModuleStage, laneID
resolved.ChunkReferences.Bindings[0].BindingSource = bindingSource
case StageExtract:
resolved.ArtifactLanes[0].ExtractReferences.Bindings[0].BindingSource = bindingSource
case StageMerge:
resolved.ArtifactLanes[0].MergeReferences.Bindings[0].BindingSource = bindingSource
case StageNormalize:
resolved.ArtifactLanes[0].NormalizeReferences.Bindings[0].BindingSource = bindingSource
}
@@ -441,18 +458,20 @@ func referenceCatalogForStage(t *testing.T, stage ModuleStage, slots []contracts
t.Helper()
switch stage {
case StageChunk:
return referenceCatalogForTargets(t, slots, nil, nil)
return referenceCatalogForTargets(t, slots, nil, nil, nil)
case StageExtract:
return referenceCatalogForTargets(t, nil, slots, nil)
return referenceCatalogForTargets(t, nil, slots, nil, nil)
case StageMerge:
return referenceCatalogForTargets(t, nil, nil, slots, nil)
case StageNormalize:
return referenceCatalogForTargets(t, nil, nil, slots)
return referenceCatalogForTargets(t, nil, nil, nil, slots)
default:
t.Fatalf("unsupported reference target stage %q", stage)
return ModuleCatalog{}
}
}
func referenceCatalogForTargets(t *testing.T, chunkSlots, extractSlots, normalizeSlots []contracts.ReferenceSlot) ModuleCatalog {
func referenceCatalogForTargets(t *testing.T, chunkSlots, extractSlots, mergeSlots, normalizeSlots []contracts.ReferenceSlot) ModuleCatalog {
t.Helper()
return newProfileCatalogWithOverrides(t,
ModuleSpec{
@@ -469,6 +488,13 @@ func referenceCatalogForTargets(t *testing.T, chunkSlots, extractSlots, normaliz
Provides: []string{"candidate"},
ReferenceSlots: extractSlots,
},
ModuleSpec{
Key: "appendorder",
Stage: StageMerge,
Requires: []string{"candidate"},
Provides: []string{"merged"},
ReferenceSlots: mergeSlots,
},
ModuleSpec{
Key: "noop",
Stage: StageNormalize,