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

Add transcript description prompt context

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-13 12:13:32 +00:00
parent de99467ede
commit ebbd2c8a63
27 changed files with 542 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
internal/core/config/config.go
View File

@@ -14,22 +14,23 @@ const (
)
const (
DefaultModulesCSV = "glossary,homophones,glossary,spoken_word,grammar"
DefaultPrimaryModel = "openrouter/google/gemma-4-31b-it"
DefaultPrimaryBaseURL = "https://openrouter.ai/api/v1"
DefaultPrimaryLLMTimeoutSeconds = 600
DefaultMaxRetries = 3
DefaultLLMConcurrency = 1
DefaultValidationMaxPromptTokens = 2048
DefaultMaxSectionTokens = 8192
DefaultMinSectionTokens = 2048
DefaultConfidenceThreshold = 0.8
DefaultNormalizeMaxSegmentGap = 4.0
DefaultNormalizeEllipsisGap = 3.5
DefaultNormalizeMaxSegmentDuration = 60.0
DefaultNormalizeMaxSegmentTokens = 2048
DefaultWorkDir = "/tmp/audita"
DefaultWorkDirRetention WorkDirRetention = WorkDirRetentionAuto
DefaultModulesCSV = "glossary,homophones,glossary,spoken_word,grammar"
DefaultPrimaryModel = "openrouter/google/gemma-4-31b-it"
DefaultPrimaryBaseURL = "https://openrouter.ai/api/v1"
DefaultPrimaryLLMTimeoutSeconds = 600
DefaultMaxRetries = 3
DefaultLLMConcurrency = 1
DefaultValidationMaxPromptTokens = 2048
DefaultMaxSectionTokens = 8192
DefaultMinSectionTokens = 2048
DefaultConfidenceThreshold = 0.8
DefaultNormalizeMaxSegmentGap = 4.0
DefaultNormalizeEllipsisGap = 3.5
DefaultNormalizeMaxSegmentDuration = 60.0
DefaultNormalizeMaxSegmentTokens = 2048
DefaultTranscriptDescriptionMaxChars = 500
DefaultWorkDir = "/tmp/audita"
DefaultWorkDirRetention WorkDirRetention = WorkDirRetentionAuto
)
type Config struct {
@@ -45,6 +46,7 @@ type Config struct {
TargetSections *int
Thresholds ConfidenceThresholds
Normalization NormalizationConfig
TranscriptDescription string
WorkDir string
WorkDirRetention WorkDirRetention
}

26
internal/core/config/config_test.go
View File

@@ -51,6 +51,9 @@ func TestDefaultConfigValues(t *testing.T) {
if cfg.WorkDir != DefaultWorkDir {
t.Fatalf("unexpected default work dir: %q", cfg.WorkDir)
}
if cfg.TranscriptDescription != "" {
t.Fatalf("expected default transcript description to be empty, got %q", cfg.TranscriptDescription)
}
if cfg.WorkDirRetention != DefaultWorkDirRetention {
t.Fatalf("unexpected default work dir retention: %q", cfg.WorkDirRetention)
}
@@ -214,6 +217,29 @@ func TestApplyCLIOverridesPrecedence(t *testing.T) {
}
}
func TestApplyCLIOverridesTrimsTranscriptDescription(t *testing.T) {
cfg := Default()
description := " background context about speakers "
if err := cfg.ApplyCLIOverrides(CLIOverrides{TranscriptDescription: &description}); err != nil {
t.Fatalf("ApplyCLIOverrides failed: %v", err)
}
if cfg.TranscriptDescription != "background context about speakers" {
t.Fatalf("unexpected transcript description trim result: %q", cfg.TranscriptDescription)
}
}
func TestValidationRejectsOverlyLongTranscriptDescription(t *testing.T) {
cfg := Default()
cfg.TranscriptDescription = strings.Repeat("a", DefaultTranscriptDescriptionMaxChars+1)
err := cfg.Validate()
if err == nil {
t.Fatalf("expected transcript description length validation error")
}
if !strings.Contains(err.Error(), "transcript description must be 500 characters or fewer") {
t.Fatalf("unexpected validation error: %v", err)
}
}
func TestApplyCLIOverridesLegacyLLMConcurrencyAlias(t *testing.T) {
cfg := Default()
aliasConcurrency := 6

9
internal/core/config/flags.go
View File

@@ -1,6 +1,9 @@
package config
import "fmt"
import (
"fmt"
"strings"
)
type CLIOverrides struct {
ModulesCSV *string
@@ -30,6 +33,7 @@ type CLIOverrides struct {
NormalizeEllipsisGap *float64
NormalizeMaxSegmentDuration *float64
NormalizeMaxSegmentTokens *int
TranscriptDescription *string
WorkDir *string
WorkDirRetention *string
}
@@ -135,6 +139,9 @@ func (c *Config) ApplyCLIOverrides(overrides CLIOverrides) error {
if overrides.NormalizeMaxSegmentTokens != nil {
c.Normalization.MaxSegmentTokens = *overrides.NormalizeMaxSegmentTokens
}
if overrides.TranscriptDescription != nil {
c.TranscriptDescription = strings.TrimSpace(*overrides.TranscriptDescription)
}
if overrides.WorkDir != nil {
c.WorkDir = *overrides.WorkDir
}

3
internal/core/config/validation.go
View File

@@ -88,6 +88,9 @@ func (c Config) Validate() error {
if c.Normalization.MaxSegmentTokens <= 0 {
issues = append(issues, "normalize max segment tokens must be greater than zero")
}
if len(strings.TrimSpace(c.TranscriptDescription)) > DefaultTranscriptDescriptionMaxChars {
issues = append(issues, fmt.Sprintf("transcript description must be %d characters or fewer", DefaultTranscriptDescriptionMaxChars))
}
if strings.TrimSpace(c.WorkDir) == "" {
issues = append(issues, "work dir must not be empty")

17
internal/core/diagnostics/run_dir.go
View File

@@ -48,14 +48,15 @@ func ShouldRetainRunDirectory(input RetentionDecisionInput) bool {
// 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"`
ReportJSONPath string `json:"report_json_path,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"`
GlossaryPath string `json:"glossary_path"`
OutputPath string `json:"output_path,omitempty"`
ReportJSONPath string `json:"report_json_path,omitempty"`
TranscriptDescription string `json:"transcript_description,omitempty"`
Modules []string `json:"modules"`
RunID string `json:"run_id"`
StartedAt time.Time `json:"started_at"`
}
// NewRunDirectory creates a new run directory under the configured work dir