Register D&D scene chunker

This commit is contained in:
2026-07-04 13:05:39 +00:00
parent 7f83a20fa6
commit 2130414899
7 changed files with 135 additions and 1 deletions

View File

@@ -10,6 +10,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/dnd/scenes"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/generic"
"gitea.maximumdirect.net/eric/notarius/internal/modules/extract/dnd/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/input/seriatim"
@@ -34,6 +35,9 @@ func productionRegistries() (pipeline.Registries, error) {
if err := generic.Register(registries.Chunkers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register generic chunker: %w", err)
}
if err := scenes.Register(registries.Chunkers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register dnd scenes chunker: %w", err)
}
if err := spells.Register(registries.Extractors); err != nil {
return pipeline.Registries{}, fmt.Errorf("register dnd spells extractor: %w", err)
}

View File

@@ -16,6 +16,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/core/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/dnd/scenes"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/generic"
"gitea.maximumdirect.net/eric/notarius/internal/modules/extract/dnd/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/input/seriatim"
@@ -136,6 +137,11 @@ func TestProductionCatalogIncludesDefaultModules(t *testing.T) {
got: func() (pipeline.ModuleSpec, bool) { return catalog.Chunkers.Spec(generic.Key) },
want: generic.ModuleSpec(),
},
{
name: "dnd scenes chunker",
got: func() (pipeline.ModuleSpec, bool) { return catalog.Chunkers.Spec(scenes.Key) },
want: scenes.ModuleSpec(),
},
{
name: "dnd spells extractor",
got: func() (pipeline.ModuleSpec, bool) { return catalog.Extractors.Spec(spells.Key) },
@@ -186,6 +192,21 @@ func TestRunConfigValidateUsesProductionCatalogByDefault(t *testing.T) {
}
}
func TestRunConfigValidateAcceptsDNDScenesChunker(t *testing.T) {
configPath := writeTestConfig(t, mvpConfigYAMLWithChunk("dnd-session", scenes.Key, "dnd/spells"))
var stdout bytes.Buffer
var stderr bytes.Buffer
code := RunWithOptions([]string{"config", "validate", "--config", configPath, "--pipeline", "dnd-session"}, &stdout, &stderr, Options{})
if code != 0 {
t.Fatalf("RunWithOptions() code = %d, stderr=%q", code, stderr.String())
}
if !strings.Contains(stdout.String(), "is valid for pipeline") {
t.Fatalf("stdout = %q, want validation success", stdout.String())
}
}
func TestRunConfigValidateUnknownProductionModuleIncludesContext(t *testing.T) {
configPath := writeTestConfig(t, mvpConfigYAML("dnd-session", "missing/extract"))
var stdout bytes.Buffer
@@ -1220,6 +1241,18 @@ pipelines:
`
}
func mvpConfigYAMLWithChunk(pipelineID string, chunker string, extractor string) string {
return `version: 1
pipelines:
` + pipelineID + `:
input: seriatim
chunk: ` + chunker + `
artifacts:
spells:
extract: ` + extractor + `
`
}
func mvpConfigYAMLForLanes(pipelineID string, laneIDs ...string) string {
var b strings.Builder
b.WriteString("version: 1\n")

View File

@@ -98,6 +98,43 @@ func TestResolveSurfacesMissingCapabilityThroughCatalog(t *testing.T) {
}
}
func TestResolveCanBindSceneChunkerFromCatalog(t *testing.T) {
cfg := validConfig()
profile := cfg.Pipelines["example"]
profile.Chunk = pipeline.Binding("dnd/scenes")
lane := profile.Artifacts["events"]
profile.Artifacts = map[string]pipeline.ArtifactLaneProfile{"events": lane}
cfg.Pipelines["example"] = profile
catalog := fakeCatalog(t,
pipeline.ModuleSpec{
Key: "fake/input",
Stage: pipeline.StageInput,
Provides: []string{"source.transcript"},
},
pipeline.ModuleSpec{
Key: "fake/extract",
Stage: pipeline.StageExtract,
Requires: []string{"chunks", "source.transcript"},
Provides: []string{"artifact"},
},
)
mustRegisterChunker(t, catalog.Chunkers, pipeline.ModuleSpec{
Key: "dnd/scenes",
Stage: pipeline.StageChunk,
Requires: []string{"source.transcript"},
Provides: []string{"chunks", "chunks.scenes"},
})
effective, err := cfg.Resolve(ResolveInput{PipelineID: "example", Catalog: catalog})
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
if got := effective.ResolvedPipeline.Chunk.Module; got != "dnd/scenes" {
t.Fatalf("Chunk.Module = %q, want dnd/scenes", got)
}
}
func TestResolveDigestChangesWhenEffectiveConfigChanges(t *testing.T) {
cfg := validConfig()
first, err := cfg.Resolve(ResolveInput{PipelineID: "example", Catalog: fakeCatalog(t)})