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

Added chunking logic to modules and added corresponding regression tests

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-12 12:25:14 -05:00
parent fb59cb21b9
commit cad172a758
14 changed files with 235 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
internal/modules/glossary/module.go
View File

@@ -4,6 +4,7 @@ import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
@@ -49,7 +50,12 @@ func (m *Module) Validators() []contracts.Validator {
}
func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
messages, err := BuildProposalMessages(req.WorkingTranscript, req.Glossary)
sectionTranscript := transcriptForSection(req.WorkingTranscript, req.Section)
sectionIndex := 0
if req.Section != nil {
sectionIndex = req.Section.Index
}
messages, err := BuildProposalMessages(sectionTranscript, req.Glossary, sectionIndex)
if err != nil {
return nil, err
}
@@ -74,3 +80,16 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
}
return generated.Corrections, nil
}
func transcriptForSection(transcript *schema.Transcript, section *contracts.SectionMetadata) *schema.Transcript {
if section == nil || transcript == nil {
return transcript
}
segments := make([]schema.Segment, 0, len(transcript.Segments))
for _, seg := range transcript.Segments {
if seg.ID >= section.StartSegmentID && seg.ID <= section.EndSegmentID {
segments = append(segments, seg)
}
}
return &schema.Transcript{Segments: segments}
}

3
internal/modules/glossary/module_test.go
View File

@@ -61,7 +61,7 @@ func tinyGlossary() *schema.Glossary {
}
func TestBuildProposalMessagesContainsGlossaryContextAndConstraints(t *testing.T) {
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary())
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0)
if err != nil {
t.Fatalf("BuildProposalMessages error: %v", err)
}
@@ -72,6 +72,7 @@ func TestBuildProposalMessagesContainsGlossaryContextAndConstraints(t *testing.T
for _, want := range []string{
"Glossary:",
"Transcript section:",
`"section_index": 0`,
`"Aliases":`,
`"Jester"`,
`"Category": "faction"`,

4
internal/modules/glossary/prompt.go
View File

@@ -22,14 +22,14 @@ type promptTranscriptSection struct {
Segments []promptSegment `json:"segments"`
}
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary) ([]contracts.LLMMessage, error) {
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
glossaryJSON, err := json.MarshalIndent(glossary, "", " ")
if err != nil {
return nil, fmt.Errorf("marshal glossary prompt context: %w", err)
}
sectionPayload := promptTranscriptSection{
SectionIndex: 0,
SectionIndex: sectionIndex,
Segments: make([]promptSegment, 0),
}
if transcript != nil {

21
internal/modules/grammar/module.go
View File

@@ -4,6 +4,7 @@ import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
@@ -49,7 +50,12 @@ func (m *Module) Validators() []contracts.Validator {
}
func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
messages, err := BuildProposalMessages(req.WorkingTranscript, req.Glossary)
sectionTranscript := transcriptForSection(req.WorkingTranscript, req.Section)
sectionIndex := 0
if req.Section != nil {
sectionIndex = req.Section.Index
}
messages, err := BuildProposalMessages(sectionTranscript, req.Glossary, sectionIndex)
if err != nil {
return nil, err
}
@@ -74,3 +80,16 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
}
return generated.Corrections, nil
}
func transcriptForSection(transcript *schema.Transcript, section *contracts.SectionMetadata) *schema.Transcript {
if section == nil || transcript == nil {
return transcript
}
segments := make([]schema.Segment, 0, len(transcript.Segments))
for _, seg := range transcript.Segments {
if seg.ID >= section.StartSegmentID && seg.ID <= section.EndSegmentID {
segments = append(segments, seg)
}
}
return &schema.Transcript{Segments: segments}
}

3
internal/modules/grammar/module_test.go
View File

@@ -71,7 +71,7 @@ func tinyGlossary() *schema.Glossary {
}
func TestBuildProposalMessagesConstraints(t *testing.T) {
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary())
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0)
if err != nil {
t.Fatalf("BuildProposalMessages error: %v", err)
}
@@ -82,6 +82,7 @@ func TestBuildProposalMessagesConstraints(t *testing.T) {
for _, want := range []string{
"Transcript section:",
"Protected glossary/context:",
`"section_index": 0`,
"punctuation, capitalization, spacing, and article cleanup only",
"Do not make word substitutions",
"Do not return speaker, start, or end fields",

4
internal/modules/grammar/prompt.go
View File

@@ -24,14 +24,14 @@ type promptTranscriptSection struct {
// BuildProposalMessages mirrors the Python grammar-module prompt intent:
// punctuation/capitalization/spacing cleanup only, with strict meaning guards.
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary) ([]contracts.LLMMessage, error) {
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
glossaryJSON, err := json.MarshalIndent(glossary, "", " ")
if err != nil {
return nil, fmt.Errorf("marshal glossary prompt context: %w", err)
}
sectionPayload := promptTranscriptSection{
SectionIndex: 0,
SectionIndex: sectionIndex,
Segments: make([]promptSegment, 0),
}
if transcript != nil {

21
internal/modules/homophones/module.go
View File

@@ -4,6 +4,7 @@ import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
@@ -49,7 +50,12 @@ func (m *Module) Validators() []contracts.Validator {
}
func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
messages, err := BuildProposalMessages(req.WorkingTranscript, req.Glossary)
sectionTranscript := transcriptForSection(req.WorkingTranscript, req.Section)
sectionIndex := 0
if req.Section != nil {
sectionIndex = req.Section.Index
}
messages, err := BuildProposalMessages(sectionTranscript, req.Glossary, sectionIndex)
if err != nil {
return nil, err
}
@@ -74,3 +80,16 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
}
return generated.Corrections, nil
}
func transcriptForSection(transcript *schema.Transcript, section *contracts.SectionMetadata) *schema.Transcript {
if section == nil || transcript == nil {
return transcript
}
segments := make([]schema.Segment, 0, len(transcript.Segments))
for _, seg := range transcript.Segments {
if seg.ID >= section.StartSegmentID && seg.ID <= section.EndSegmentID {
segments = append(segments, seg)
}
}
return &schema.Transcript{Segments: segments}
}

3
internal/modules/homophones/module_test.go
View File

@@ -62,7 +62,7 @@ func tinyGlossary() *schema.Glossary {
}
func TestBuildProposalMessagesContainsContextAndConservativeConstraints(t *testing.T) {
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary())
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0)
if err != nil {
t.Fatalf("BuildProposalMessages error: %v", err)
}
@@ -73,6 +73,7 @@ func TestBuildProposalMessagesContainsContextAndConservativeConstraints(t *testi
for _, want := range []string{
"Protected glossary/context:",
"Transcript section:",
`"section_index": 0`,
`"Aliases":`,
`"Category": "faction"`,
`"Summary": "Guild members"`,

4
internal/modules/homophones/prompt.go
View File

@@ -24,14 +24,14 @@ type promptTranscriptSection struct {
// BuildProposalMessages mirrors the Python homophones-module prompt intent:
// conservative homophone and mistranscription correction only.
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary) ([]contracts.LLMMessage, error) {
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
glossaryJSON, err := json.MarshalIndent(glossary, "", " ")
if err != nil {
return nil, fmt.Errorf("marshal glossary prompt context: %w", err)
}
sectionPayload := promptTranscriptSection{
SectionIndex: 0,
SectionIndex: sectionIndex,
Segments: make([]promptSegment, 0),
}
if transcript != nil {

21
internal/modules/spoken_word/module.go
View File

@@ -4,6 +4,7 @@ import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
@@ -49,7 +50,12 @@ func (m *Module) Validators() []contracts.Validator {
}
func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
messages, err := BuildProposalMessages(req.WorkingTranscript, req.Glossary)
sectionTranscript := transcriptForSection(req.WorkingTranscript, req.Section)
sectionIndex := 0
if req.Section != nil {
sectionIndex = req.Section.Index
}
messages, err := BuildProposalMessages(sectionTranscript, req.Glossary, sectionIndex)
if err != nil {
return nil, err
}
@@ -74,3 +80,16 @@ func (m *Module) Propose(ctx context.Context, req contracts.ProposalRequest) ([]
}
return generated.Corrections, nil
}
func transcriptForSection(transcript *schema.Transcript, section *contracts.SectionMetadata) *schema.Transcript {
if section == nil || transcript == nil {
return transcript
}
segments := make([]schema.Segment, 0, len(transcript.Segments))
for _, seg := range transcript.Segments {
if seg.ID >= section.StartSegmentID && seg.ID <= section.EndSegmentID {
segments = append(segments, seg)
}
}
return &schema.Transcript{Segments: segments}
}

3
internal/modules/spoken_word/module_test.go
View File

@@ -62,7 +62,7 @@ func tinyGlossary() *schema.Glossary {
}
func TestBuildProposalMessagesContainsContextAndMeaningGuardrails(t *testing.T) {
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary())
msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0)
if err != nil {
t.Fatalf("BuildProposalMessages error: %v", err)
}
@@ -73,6 +73,7 @@ func TestBuildProposalMessagesContainsContextAndMeaningGuardrails(t *testing.T)
for _, want := range []string{
"Protected glossary/context:",
"Transcript section:",
`"section_index": 0`,
`"Aliases":`,
`"Category": "faction"`,
`"Summary": "Guild members"`,

4
internal/modules/spoken_word/prompt.go
View File

@@ -24,14 +24,14 @@ type promptTranscriptSection struct {
// BuildProposalMessages mirrors the Python spoken_word-module prompt intent:
// conservative dysfluency cleanup with strict semantic preservation.
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary) ([]contracts.LLMMessage, error) {
func BuildProposalMessages(transcript *schema.Transcript, glossary *schema.Glossary, sectionIndex int) ([]contracts.LLMMessage, error) {
glossaryJSON, err := json.MarshalIndent(glossary, "", " ")
if err != nil {
return nil, fmt.Errorf("marshal glossary prompt context: %w", err)
}
sectionPayload := promptTranscriptSection{
SectionIndex: 0,
SectionIndex: sectionIndex,
Segments: make([]promptSegment, 0),
}
if transcript != nil {