Keep checkpoints aligned with PromptKit profiles

This commit is contained in:
2026-07-28 13:36:01 -05:00
parent f1a6574013
commit de046a8f13
14 changed files with 308 additions and 399 deletions

View File

@@ -20,6 +20,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/chunkmap"
"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/dnd"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/chunk/scenes"
@@ -390,6 +391,14 @@ func TestProductionLLMClientFactoriesBuildOfflineRuntime(t *testing.T) {
if len(manifests) != 0 {
t.Fatalf("eager profile manifests = %#v, want none", manifests)
}
fingerprintProvider, ok := client.(llm.CheckpointFingerprintProvider)
if !ok {
t.Fatalf("production LLM client %T does not provide one profile-source checkpoint fingerprint", client)
}
fingerprints, err := fingerprintProvider.LLMCheckpointFingerprints()
if err != nil || len(fingerprints) != 1 {
t.Fatalf("production LLM checkpoint fingerprints = %#v, error = %v, want one profile-source identity", fingerprints, err)
}
if _, ok := client.(contracts.LLMProfileManifestProvider); !ok {
t.Fatalf("production LLM client %T does not provide profile manifests", client)
}

View File

@@ -23,6 +23,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/chunkplan"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
frameworkdebug "gitea.maximumdirect.net/eric/notarius/internal/framework/debug"
frameworkllm "gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
@@ -367,6 +368,13 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, fmt.Errorf("create LLM client for profile %q: %w", factoryProfileID, err))
}
var llmFingerprints []checkpoint.Fingerprint
if effective.Config.Cache.Checkpoints.Enabled {
llmFingerprints, err = llmCheckpointFingerprints(llmClient)
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, fmt.Errorf("prepare LLM checkpoint identity: %w", err))
}
}
llmClient = pipeline.WithDebugLLMRecording(llmClient, debugRecorder)
prepared, err := pipeline.Prepare(effective.ResolvedPipeline, registries, pipeline.ModuleDependencies{LLM: llmClient})
if err != nil {
@@ -380,7 +388,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, err)
}
checkpointRecorder, checkpointLoader, err := checkpointHandlersForRun(effective.Config.Cache.Checkpoints, opts, effective.ResolvedPipeline, prepared.CheckpointFingerprints(), rawInput, only, llmProfiles, strings.TrimSpace(*llmProfile), strings.TrimSpace(sessionID.value), *resume)
checkpointRecorder, checkpointLoader, err := checkpointHandlersForRun(effective.Config.Cache.Checkpoints, opts, effective.ResolvedPipeline, prepared.CheckpointFingerprints(), llmFingerprints, rawInput, only, llmProfiles, strings.TrimSpace(*llmProfile), strings.TrimSpace(sessionID.value), *resume)
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, err)
}
@@ -481,6 +489,7 @@ func checkpointHandlersForRun(
opts Options,
resolved pipeline.ResolvedPipeline,
componentFingerprints []pipeline.CheckpointFingerprint,
llmFingerprints []checkpoint.Fingerprint,
rawInput []byte,
only []string,
llmProfiles []artifacts.LLMProfileManifest,
@@ -495,13 +504,17 @@ func checkpointHandlersForRun(
return pipeline.NoopCheckpointRecorder(), pipeline.NoopCheckpointLoader(), nil
}
identity, err := checkpoint.NewIdentity(checkpoint.IdentityInput{
Pipeline: resolved,
InputKey: resolved.Input.Module,
RawInputDigest: rawInputDigest(rawInput),
SelectedLanes: only,
RuntimeOverrides: runtimeOverrideFingerprints(llmProfileOverride, sessionID),
References: pipeline.ReferenceProvenance(resolved),
ProvenanceFingerprints: append(llmProfileFingerprints(llmProfiles), checkpointIdentityFingerprints(componentFingerprints)...),
Pipeline: resolved,
InputKey: resolved.Input.Module,
RawInputDigest: rawInputDigest(rawInput),
SelectedLanes: only,
RuntimeOverrides: runtimeOverrideFingerprints(llmProfileOverride, sessionID),
References: pipeline.ReferenceProvenance(resolved),
ProvenanceFingerprints: combineCheckpointFingerprints(
llmProfileFingerprints(llmProfiles),
llmFingerprints,
checkpointIdentityFingerprints(componentFingerprints),
),
})
if err != nil {
return nil, nil, fmt.Errorf("create checkpoint identity: %w", err)
@@ -527,6 +540,30 @@ func checkpointHandlersForRun(
return recorder, loader, nil
}
func llmCheckpointFingerprints(client contracts.StructuredLLMClient) ([]checkpoint.Fingerprint, error) {
provider, ok := client.(frameworkllm.CheckpointFingerprintProvider)
if !ok {
return nil, nil
}
values, err := provider.LLMCheckpointFingerprints()
if err != nil {
return nil, err
}
out := make([]checkpoint.Fingerprint, 0, len(values))
for _, value := range values {
out = append(out, checkpoint.Fingerprint{Name: value.Name, Value: value.Value})
}
return out, nil
}
func combineCheckpointFingerprints(sources ...[]checkpoint.Fingerprint) []checkpoint.Fingerprint {
var out []checkpoint.Fingerprint
for _, source := range sources {
out = append(out, source...)
}
return out
}
func recomputePolicy(resolved pipeline.ResolvedPipeline, requestedStep string) (pipeline.CheckpointExecutionPolicy, error) {
requestedStep = strings.TrimSpace(requestedStep)
if requestedStep == "" {

View File

@@ -214,8 +214,9 @@ func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t
t.Fatal(err)
}
fingerprints := prepared.CheckpointFingerprints()
llmFingerprints := []checkpoint.Fingerprint{{Name: "promptkit_profile_source", Value: "sha256:profile-source-one"}}
settings := config.CheckpointCacheConfig{Enabled: true, Directory: t.TempDir()}
recorder, _, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, []byte("same input"), nil, nil, "", "", false)
recorder, _, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, llmFingerprints, []byte("same input"), nil, nil, "", "", false)
if err != nil {
t.Fatal(err)
}
@@ -241,7 +242,7 @@ func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t
t.Fatal(err)
}
_, sameLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, []byte("same input"), nil, nil, "", "", true)
_, sameLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, llmFingerprints, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
@@ -253,7 +254,7 @@ func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t
}
changed := replaceCheckpointFingerprintValue(t, fingerprints, normalizeSpellCatalogFingerprintName(), "sha256:changed-effective-catalog")
assertOnlyCheckpointFingerprintChanged(t, fingerprints, changed, normalizeSpellCatalogFingerprintName())
_, changedLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changed, []byte("same input"), nil, nil, "", "", true)
_, changedLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changed, llmFingerprints, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
@@ -265,13 +266,25 @@ func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t
}
changedMapping := replaceCheckpointFingerprintValue(t, fingerprints, extractSpellMappingFingerprintName(), "dnd.spells.extract_mapping.v3")
assertOnlyCheckpointFingerprintChanged(t, fingerprints, changedMapping, extractSpellMappingFingerprintName())
_, mappingLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changedMapping, []byte("same input"), nil, nil, "", "", true)
_, mappingLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changedMapping, llmFingerprints, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
if _, decision := mappingLoader.Source(materialized.Input.Module); decision.Reused {
t.Fatalf("changed mapping policy decision = %#v, want cold miss", decision)
}
changedLLMFingerprints := []checkpoint.Fingerprint{{Name: "promptkit_profile_source", Value: "sha256:profile-source-two"}}
_, profileLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, changedLLMFingerprints, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
if _, decision := profileLoader.Source(materialized.Input.Module); decision.Reused {
t.Fatalf("changed PromptKit profile source decision = %#v, want cold miss", decision)
}
if _, decision := profileLoader.Normalize("spells", spellnormalize.Key, normalizeDependencies); decision.Reused {
t.Fatalf("changed PromptKit profile normalize decision = %#v, want cold miss", decision)
}
}
func normalizeSpellCatalogFingerprintName() string {