eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Remove retired reporting and diagnostic code

Browse Source
This commit is contained in:
Eric Rakestraw
2026-11-10 20:26:43 +00:00
parent a0e45c8f92
commit 9a52c8c246
21 changed files with 59 additions and 706 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
internal/core/chunking/summary.go
View File

@@ -1,84 +0,0 @@
package chunking
// Summary provides a concise overview of chunking results for reports
type Summary struct {
ChunkCount int `json:"chunk_count"`
MinEstimatedTokens int `json:"min_estimated_chunk_tokens"`
MaxEstimatedTokens int `json:"max_estimated_chunk_tokens"`
TotalEstimatedTokens int `json:"total_estimated_transcript_tokens"`
TargetSections *int `json:"target_sections,omitempty"`
MaxSectionTokens int `json:"max_section_tokens"`
MinSectionTokens int `json:"min_section_tokens"`
}
// ChunkSummary represents a single chunk's metadata for diagnostics
type ChunkSummary struct {
Index int `json:"index"`
StartSegmentID int `json:"start_segment_id"`
EndSegmentID int `json:"end_segment_id"`
EstimatedTokens int `json:"estimated_tokens"`
SegmentCount int `json:"segment_count"`
}
// DetailedSummary provides per-chunk details for diagnostics
type DetailedSummary struct {
Summary `json:",inline"`
Chunks []ChunkSummary `json:"chunks"`
}
// ComputeSummary creates a Summary from sections and config
func ComputeSummary(sections []Section, config ChunkingConfig) Summary {
if len(sections) == 0 {
return Summary{
ChunkCount: 0,
MaxSectionTokens: config.MaxSectionTokens,
MinSectionTokens: config.MinSectionTokens,
TargetSections: config.TargetSections,
}
}
minTokens := sections[0].EstimatedTokens
maxTokens := sections[0].EstimatedTokens
totalTokens := 0
for _, sec := range sections {
if sec.EstimatedTokens < minTokens {
minTokens = sec.EstimatedTokens
}
if sec.EstimatedTokens > maxTokens {
maxTokens = sec.EstimatedTokens
}
totalTokens += sec.EstimatedTokens
}
return Summary{
ChunkCount: len(sections),
MinEstimatedTokens: minTokens,
MaxEstimatedTokens: maxTokens,
TotalEstimatedTokens: totalTokens,
TargetSections: config.TargetSections,
MaxSectionTokens: config.MaxSectionTokens,
MinSectionTokens: config.MinSectionTokens,
}
}
// ComputeDetailedSummary creates a DetailedSummary from sections and config
func ComputeDetailedSummary(sections []Section, config ChunkingConfig) DetailedSummary {
summary := ComputeSummary(sections, config)
chunks := make([]ChunkSummary, len(sections))
for i, sec := range sections {
chunks[i] = ChunkSummary{
Index: sec.Index,
StartSegmentID: sec.StartSegmentID,
EndSegmentID: sec.EndSegmentID,
EstimatedTokens: sec.EstimatedTokens,
SegmentCount: len(sec.Segments),
}
}
return DetailedSummary{
Summary: summary,
Chunks: chunks,
}
}

148
internal/core/chunking/summary_test.go
View File

@@ -1,148 +0,0 @@
package chunking
import (
"testing"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/schema"
)
func TestComputeSummary(t *testing.T) {
config := ChunkingConfig{
MaxSectionTokens: 100,
MinSectionTokens: 10,
}
sections := []Section{
{Index: 0, EstimatedTokens: 30, StartSegmentID: 1, EndSegmentID: 2},
{Index: 1, EstimatedTokens: 50, StartSegmentID: 3, EndSegmentID: 4},
{Index: 2, EstimatedTokens: 20, StartSegmentID: 5, EndSegmentID: 5},
}
summary := ComputeSummary(sections, config)
if summary.ChunkCount != 3 {
t.Errorf("expected chunk_count=3, got %d", summary.ChunkCount)
}
if summary.MinEstimatedTokens != 20 {
t.Errorf("expected min_estimated_tokens=20, got %d", summary.MinEstimatedTokens)
}
if summary.MaxEstimatedTokens != 50 {
t.Errorf("expected max_estimated_tokens=50, got %d", summary.MaxEstimatedTokens)
}
if summary.TotalEstimatedTokens != 100 {
t.Errorf("expected total_estimated_tokens=100, got %d", summary.TotalEstimatedTokens)
}
if summary.MaxSectionTokens != 100 {
t.Errorf("expected max_section_tokens=100, got %d", summary.MaxSectionTokens)
}
if summary.MinSectionTokens != 10 {
t.Errorf("expected min_section_tokens=10, got %d", summary.MinSectionTokens)
}
if summary.TargetSections != nil {
t.Errorf("expected target_sections=nil, got %v", summary.TargetSections)
}
}
func TestComputeSummaryWithTarget(t *testing.T) {
target := 5
config := ChunkingConfig{
MaxSectionTokens: 100,
MinSectionTokens: 10,
TargetSections: &target,
}
sections := []Section{
{Index: 0, EstimatedTokens: 30, StartSegmentID: 1, EndSegmentID: 2},
}
summary := ComputeSummary(sections, config)
if summary.TargetSections == nil || *summary.TargetSections != 5 {
t.Errorf("expected target_sections=5, got %v", summary.TargetSections)
}
}
func TestComputeSummaryEmptySections(t *testing.T) {
config := ChunkingConfig{
MaxSectionTokens: 100,
MinSectionTokens: 10,
}
sections := []Section{}
summary := ComputeSummary(sections, config)
if summary.ChunkCount != 0 {
t.Errorf("expected chunk_count=0, got %d", summary.ChunkCount)
}
if summary.MinEstimatedTokens != 0 {
t.Errorf("expected min_estimated_tokens=0 for empty, got %d", summary.MinEstimatedTokens)
}
if summary.MaxSectionTokens != 100 {
t.Errorf("expected max_section_tokens preserved, got %d", summary.MaxSectionTokens)
}
}
func TestComputeDetailedSummary(t *testing.T) {
config := ChunkingConfig{
MaxSectionTokens: 100,
MinSectionTokens: 10,
}
sections := []Section{
{
Index: 0,
EstimatedTokens: 30,
StartSegmentID: 1,
EndSegmentID: 2,
Segments: make([]schema.Segment, 2), // 2 segments
},
{
Index: 1,
EstimatedTokens: 50,
StartSegmentID: 3,
EndSegmentID: 5,
Segments: make([]schema.Segment, 3), // 3 segments
},
}
detailed := ComputeDetailedSummary(sections, config)
if detailed.ChunkCount != 2 {
t.Errorf("expected chunk_count=2, got %d", detailed.ChunkCount)
}
if len(detailed.Chunks) != 2 {
t.Fatalf("expected 2 chunk entries, got %d", len(detailed.Chunks))
}
// Check first chunk
if detailed.Chunks[0].Index != 0 {
t.Errorf("expected chunk[0].index=0, got %d", detailed.Chunks[0].Index)
}
if detailed.Chunks[0].StartSegmentID != 1 {
t.Errorf("expected chunk[0].start_segment_id=1, got %d", detailed.Chunks[0].StartSegmentID)
}
if detailed.Chunks[0].EndSegmentID != 2 {
t.Errorf("expected chunk[0].end_segment_id=2, got %d", detailed.Chunks[0].EndSegmentID)
}
if detailed.Chunks[0].EstimatedTokens != 30 {
t.Errorf("expected chunk[0].estimated_tokens=30, got %d", detailed.Chunks[0].EstimatedTokens)
}
if detailed.Chunks[0].SegmentCount != 2 {
t.Errorf("expected chunk[0].segment_count=2, got %d", detailed.Chunks[0].SegmentCount)
}
// Check second chunk
if detailed.Chunks[1].Index != 1 {
t.Errorf("expected chunk[1].index=1, got %d", detailed.Chunks[1].Index)
}
if detailed.Chunks[1].StartSegmentID != 3 {
t.Errorf("expected chunk[1].start_segment_id=3, got %d", detailed.Chunks[1].StartSegmentID)
}
if detailed.Chunks[1].EndSegmentID != 5 {
t.Errorf("expected chunk[1].end_segment_id=5, got %d", detailed.Chunks[1].EndSegmentID)
}
if detailed.Chunks[1].SegmentCount != 3 {
t.Errorf("expected chunk[1].segment_count=3, got %d", detailed.Chunks[1].SegmentCount)
}
}

5
internal/core/diagnostics/artifacts.go
View File

@@ -5,13 +5,8 @@ const (
ArtifactParsedSourceTranscript = "source-transcript-parsed.json"
ArtifactNormalizedTranscript = "normalized-transcript.json"
ArtifactNormalizationSummary = "normalization-summary.json"
ArtifactChunkingSummary = "chunking-summary.json"
ArtifactUtilizationSummary = "utilization-diagnostics.json"
ArtifactLLMExecution = "llm-execution.json"
ArtifactSelectedProfiles = "selected-profiles.yaml"
ArtifactConfigOrigins = "config-origins.yaml"
ArtifactCorrectionLedger = "correction-ledger.json"
ArtifactInvocationMetadata = "invocation.json"
ArtifactEffectiveConfig = "effective-config.redacted.yaml"
ArtifactErrorLog = "error.log"
)

40
internal/core/diagnostics/run_dir.go
View File

@@ -8,7 +8,6 @@ import (
"strings"
"time"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/chunking"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/normalization"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/redaction"
"gitea.maximumdirect.net/eric/audita/v3/internal/core/schema"
@@ -23,18 +22,13 @@ type RunDirectory struct {
// InvocationMetadata captures non-secret invocation details for diagnostics.
type InvocationMetadata struct {
Operation string `json:"operation"`
TranscriptPath string `json:"transcript_path"`
GlossaryPath string `json:"glossary_path"`
OutputPath string `json:"output_path,omitempty"`
ConfigPath string `json:"config_path,omitempty"`
ConfigSource string `json:"config_source,omitempty"`
Overlay string `json:"overlay,omitempty"`
ConfigVersion *int `json:"config_version,omitempty"`
TranscriptDescription string `json:"transcript_description,omitempty"`
Modules []string `json:"modules"`
RunID string `json:"run_id"`
StartedAt time.Time `json:"started_at"`
Operation string `json:"operation"`
TranscriptPath string `json:"transcript_path"`
OutputPath string `json:"output_path,omitempty"`
Overlay string `json:"overlay,omitempty"`
ConfigVersion *int `json:"config_version,omitempty"`
RunID string `json:"run_id"`
StartedAt time.Time `json:"started_at"`
}
// NewRunDirectory creates a new run directory under the configured work dir
@@ -158,26 +152,6 @@ func (r *RunDirectory) WriteNormalizationSummary(summary *normalization.Normaliz
return nil
}
// WriteErrorLog writes an error log on failure
func (r *RunDirectory) WriteErrorLog(errorMessage string) error {
errorPath := filepath.Join(r.path, ArtifactErrorLog)
return os.WriteFile(errorPath, []byte(r.redactor.String(errorMessage)+"\n"), 0o644)
}
// WriteChunkingSummary writes the chunking summary artifact
func (r *RunDirectory) WriteChunkingSummary(summary *chunking.DetailedSummary) error {
summaryPath := filepath.Join(r.path, ArtifactChunkingSummary)
bytes, err := r.redactor.JSON(summary)
if err != nil {
return fmt.Errorf("failed to marshal chunking summary: %w", err)
}
bytes = append(bytes, '\n')
if err := os.WriteFile(summaryPath, bytes, 0o644); err != nil {
return fmt.Errorf("failed to write chunking summary: %w", err)
}
return nil
}
func (r *RunDirectory) WriteJSONArtifact(name string, payload any) error {
artifactPath := filepath.Join(r.path, name)
bytes, err := r.redactor.JSON(payload)

34
internal/core/reporting/llm.go
View File

@@ -22,37 +22,3 @@ type LLMSummary struct {
StructuralRepairs uint64 `json:"structural_repairs"`
Usage LLMUsage `json:"usage"`
}
type BackendUtilization struct {
Concurrency *int `json:"concurrency,omitempty"`
QueueCapacity *int `json:"queue_capacity,omitempty"`
LLMSummary
CapacityWaitMS int64 `json:"capacity_wait_ms"`
GenerationMS int64 `json:"generation_ms"`
RetryDelayMS int64 `json:"retry_delay_ms"`
LogicalWallMS int64 `json:"logical_wall_ms"`
}
type UtilizationDiagnostics struct {
Backends map[string]BackendUtilization `json:"backends"`
RunWallTimeMS int64 `json:"run_wall_time_ms"`
Modules []ModuleUtilization `json:"modules,omitempty"`
Validators []ValidatorUtilization `json:"validators,omitempty"`
}
type ModuleUtilization struct {
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`
ProposalLLMCalls uint64 `json:"proposal_llm_calls"`
ValidationLLMCalls uint64 `json:"validation_llm_calls"`
ModuleWallTimeMS int64 `json:"module_wall_time_ms"`
}
type ValidatorUtilization struct {
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`
ValidatorKey string `json:"validator_key"`
LLMBacked bool `json:"llm_backed"`
Calls int `json:"calls"`
ElapsedMS int64 `json:"elapsed_ms"`
}

1
internal/core/reporting/markdown.go
View File

@@ -39,7 +39,6 @@ func Markdown(snapshot Snapshot, secrets ...string) []byte {
fmt.Fprintf(&b, "Proposal responses: %s; with filtering: %s\n\n",
showCount(snapshot.Summary.ProposalResponses), showCount(snapshot.Summary.ProposalResponsesWithFiltering))
fmt.Fprintf(&b, "Transcript input: %s \n", safe(snapshot.TranscriptPath))
fmt.Fprintf(&b, "Glossary input: %s \n", safe(snapshot.GlossaryPath))
output := snapshot.OutputPath
if output == "" {
output = "stdout"

4
internal/core/reporting/markdown_test.go
View File

@@ -14,7 +14,7 @@ func TestMarkdownFixedLayoutAndCounts(t *testing.T) {
one, two, three, four, zero := 1, 2, 3, 4, 0
snapshot := Snapshot{
RunID: "run-123", Status: StatusCompleted, StartedAt: time.Date(2026, 9, 24, 10, 0, 0, 0, time.UTC),
TranscriptPath: "in|put.json", GlossaryPath: "glossary`secret`.yaml", OutputPath: "out\nfile.json",
TranscriptPath: "in|put`secret`.json", OutputPath: "out\nfile.json",
StageNames: []string{"grammar_1", "grammar_2"},
WorkUnits: []WorkUnit{
{StageIndex: 0, ModuleInstance: "grammar_1", ChunkIndex: 0, StartSegmentID: 1, EndSegmentID: 2, State: "completed", ErrorCount: 1, RecoveryCount: 1, CorrectionsApplied: 1},
@@ -45,7 +45,7 @@ func TestMarkdownFixedLayoutAndCounts(t *testing.T) {
if rows := markdownTableRows(text); !reflect.DeepEqual(rows, wantRows) {
t.Fatalf("matrices: got %v; want %v", rows, wantRows)
}
for _, fragment := range []string{"in\\|put.json", "out<br>file.json", "glossary\\`[REDACTED]\\`.yaml", "`transport_failed`: 1", "`output_repaired`: 2", "`proposals_filtered`: 1", "`service_recovered`: 1"} {
for _, fragment := range []string{"in\\|put\\`[REDACTED]\\`.json", "out<br>file.json", "`transport_failed`: 1", "`output_repaired`: 2", "`proposals_filtered`: 1", "`service_recovered`: 1"} {
if !strings.Contains(text, fragment) {
t.Fatalf("missing %q in:\n%s", fragment, text)
}

1
internal/core/reporting/report.go
View File

@@ -136,7 +136,6 @@ type Snapshot struct {
StartedAt time.Time
CompletedAt *time.Time
TranscriptPath string
GlossaryPath string
OutputPath string
StageNames []string
WorkUnits []WorkUnit