eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Record chunking metadata in process runs

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-11 12:47:31 +00:00
parent 12fd541669
commit b997e7c97c
6 changed files with 598 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
internal/core/reporting/report.go
View File

@@ -8,27 +8,40 @@ import (
)
type ProcessReport struct {
Phase string `json:"phase"`
Status string `json:"status"`
Operation string `json:"operation"`
TranscriptPath string `json:"transcript_path"`
GlossaryPath string `json:"glossary_path"`
OutputPath string `json:"output_path,omitempty"`
Modules []string `json:"modules"`
StartedAt time.Time `json:"started_at"`
CompletedAt *time.Time `json:"completed_at,omitempty"`
ErrorMessage string `json:"error_message,omitempty"`
ErrorPhase string `json:"error_phase,omitempty"`
InputSegmentCount *int `json:"input_segment_count,omitempty"`
NormalizedSegmentCount *int `json:"normalized_segment_count,omitempty"`
NormalizationMerges *int `json:"normalization_merges,omitempty"`
NormalizationIDReassignments *int `json:"normalization_id_reassignments,omitempty"`
NormalizationSkipped struct {
DifferentSpeakers *int `json:"different_speakers,omitempty"`
GapTooLarge *int `json:"gap_too_large,omitempty"`
DurationExceeded *int `json:"duration_exceeded,omitempty"`
TokenLimitExceeded *int `json:"token_limit_exceeded,omitempty"`
} `json:"normalization_skipped,omitempty"`
Phase string `json:"phase"`
Status string `json:"status"`
Operation string `json:"operation"`
TranscriptPath string `json:"transcript_path"`
GlossaryPath string `json:"glossary_path"`
OutputPath string `json:"output_path,omitempty"`
Modules []string `json:"modules"`
StartedAt time.Time `json:"started_at"`
CompletedAt *time.Time `json:"completed_at,omitempty"`
ErrorMessage string `json:"error_message,omitempty"`
ErrorPhase string `json:"error_phase,omitempty"`
InputSegmentCount *int `json:"input_segment_count,omitempty"`
NormalizedSegmentCount *int `json:"normalized_segment_count,omitempty"`
NormalizationMerges *int `json:"normalization_merges,omitempty"`
NormalizationIDReassignments *int `json:"normalization_id_reassignments,omitempty"`
NormalizationSkipped NormalizationSkipped `json:"normalization_skipped,omitempty"`
Chunking *ChunkingSummary `json:"chunking,omitempty"`
}
type NormalizationSkipped struct {
DifferentSpeakers *int `json:"different_speakers,omitempty"`
GapTooLarge *int `json:"gap_too_large,omitempty"`
DurationExceeded *int `json:"duration_exceeded,omitempty"`
TokenLimitExceeded *int `json:"token_limit_exceeded,omitempty"`
}
type ChunkingSummary 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"`
}
func WriteProcessReport(path string, report ProcessReport) error {