978 lines
27 KiB
Go
978 lines
27 KiB
Go
package config
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestLoadAndValidate(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
pipelineYAML string
|
|
sessionYAML string
|
|
wantLoadErr string
|
|
wantValidate string
|
|
checkDefault bool
|
|
wantRoot string
|
|
}{
|
|
{
|
|
name: "valid minimal config",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
analyzer:
|
|
timeout: 20m
|
|
notification:
|
|
timeout: 15s
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
checkDefault: true,
|
|
wantRoot: "/tmp/narratio",
|
|
},
|
|
{
|
|
name: "seriatim and audita sections can be omitted",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
analyzer:
|
|
timeout: 20m
|
|
notification:
|
|
timeout: 15s
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
checkDefault: true,
|
|
wantRoot: "/tmp/narratio",
|
|
},
|
|
{
|
|
name: "workspace root defaults when omitted",
|
|
pipelineYAML: `whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
analyzer:
|
|
timeout: 20m
|
|
notification:
|
|
timeout: 15s
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
checkDefault: true,
|
|
wantRoot: DefaultWorkspaceRoot,
|
|
},
|
|
{
|
|
name: "unknown pipeline field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
bogus: true
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "pipeline file",
|
|
},
|
|
{
|
|
name: "unknown whisperx field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
bogus: true
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "unknown secrets field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
secrets:
|
|
bogus: true
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "empty secrets env_dir fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
secrets:
|
|
env_dir: " "
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.secrets.env_dir must be non-empty when pipeline.secrets is configured",
|
|
},
|
|
{
|
|
name: "unknown session field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
unknown_field: true
|
|
`,
|
|
wantLoadErr: "session file",
|
|
},
|
|
{
|
|
name: "missing required field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: ""
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "session config \"session.yml\" invalid: session.session_id is required",
|
|
},
|
|
{
|
|
name: "missing transcribe_url fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.transcribe_url is required",
|
|
},
|
|
{
|
|
name: "invalid transcribe_url fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: ://
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.transcribe_url must be a valid URL",
|
|
},
|
|
{
|
|
name: "invalid timeout fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
timeout: definitely-not-a-duration
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.timeout must be a valid duration",
|
|
},
|
|
{
|
|
name: "invalid retry_delay fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
retry_delay: not-a-duration
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.retry_delay must be a valid duration",
|
|
},
|
|
{
|
|
name: "negative retries fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
retries: -1
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.retries must be >= 0",
|
|
},
|
|
{
|
|
name: "invalid concurrency fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
concurrency: 0
|
|
seriatim:
|
|
binary: seriatim
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.whisperx.concurrency must be > 0",
|
|
},
|
|
{
|
|
name: "unknown seriatim field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
bogus: true
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "unknown seriatim env field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
env:
|
|
unknown_knob: 1.0
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "missing seriatim binary uses default",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
timeout: 10m
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
},
|
|
{
|
|
name: "invalid seriatim timeout fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
timeout: not-a-duration
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.timeout must be a valid duration",
|
|
},
|
|
{
|
|
name: "invalid seriatim output schema fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
output_schema: invalid-schema
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.output_schema must be one of: seriatim-minimal, seriatim-intermediate, seriatim-full",
|
|
},
|
|
{
|
|
name: "negative seriatim coalesce gap fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
coalesce_gap: -0.1
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.coalesce_gap must be >= 0",
|
|
},
|
|
{
|
|
name: "invalid seriatim env float fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
env:
|
|
overlap_word_run_gap: 0
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.seriatim.env.overlap_word_run_gap must be > 0 when provided",
|
|
},
|
|
{
|
|
name: "unknown audita field fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
bogus: true
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "missing audita binary uses default",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
timeout: 3h
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
},
|
|
{
|
|
name: "invalid audita timeout fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
timeout: bad-timeout
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.timeout must be a valid duration",
|
|
},
|
|
{
|
|
name: "empty audita modules is valid override",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
modules: []
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
},
|
|
{
|
|
name: "empty audita module item fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
modules:
|
|
- glossary
|
|
- ""
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.modules[1] must be non-empty",
|
|
},
|
|
{
|
|
name: "invalid audita module item fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
modules:
|
|
- glossary
|
|
- bad_module
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.modules[1] must be one of: glossary, homophones, spoken_word, grammar",
|
|
},
|
|
{
|
|
name: "invalid audita base_url fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
base_url: ://
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.base_url must be a valid URL",
|
|
},
|
|
{
|
|
name: "legacy audita llm_concurrency field fails strict decode",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
llm_concurrency: 1
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantLoadErr: "strict decode failed",
|
|
},
|
|
{
|
|
name: "invalid audita total_llm_concurrency fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
total_llm_concurrency: 0
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.total_llm_concurrency must be > 0",
|
|
},
|
|
{
|
|
name: "invalid audita proposal_llm_concurrency fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
proposal_llm_concurrency: 0
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.proposal_llm_concurrency must be > 0",
|
|
},
|
|
{
|
|
name: "invalid audita validation_llm_concurrency fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
validation_llm_concurrency: 0
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.validation_llm_concurrency must be > 0",
|
|
},
|
|
{
|
|
name: "invalid audita output_schema fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
output_schema: bad
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.output_schema must be one of: bare-segments, audita-v1",
|
|
},
|
|
{
|
|
name: "invalid audita work_dir_retention fails",
|
|
pipelineYAML: `workspace:
|
|
root: /tmp/narratio
|
|
whisperx:
|
|
transcribe_url: https://transcription.ai.rakestrawhome.com/transcribe
|
|
seriatim:
|
|
binary: seriatim
|
|
audita:
|
|
binary: audita
|
|
work_dir_retention: sometimes
|
|
`,
|
|
sessionYAML: `session_id: 2026-05-03
|
|
inputs:
|
|
audio_dir: ./audio
|
|
speakers_file: ./speakers.yml
|
|
autocorrect_file: ./autocorrect.yml
|
|
glossary_file: ./glossary.yml
|
|
`,
|
|
wantValidate: "pipeline config \"pipeline.yml\" invalid: pipeline.audita.work_dir_retention must be one of: always, auto, never",
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
pipelinePath, sessionPath := writeConfigFiles(t, tt.pipelineYAML, tt.sessionYAML)
|
|
|
|
cfg, err := Load(pipelinePath, sessionPath)
|
|
if tt.wantLoadErr != "" {
|
|
if err == nil {
|
|
t.Fatalf("expected load error containing %q, got nil", tt.wantLoadErr)
|
|
}
|
|
if !strings.Contains(err.Error(), tt.wantLoadErr) {
|
|
t.Fatalf("load error = %q, want to contain %q", err.Error(), tt.wantLoadErr)
|
|
}
|
|
if !strings.Contains(err.Error(), "strict decode failed") {
|
|
t.Fatalf("load error = %q, want strict decode context", err.Error())
|
|
}
|
|
return
|
|
}
|
|
|
|
if err != nil {
|
|
t.Fatalf("Load() error = %v", err)
|
|
}
|
|
if cfg.PipelinePath != pipelinePath {
|
|
t.Fatalf("PipelinePath = %q, want %q", cfg.PipelinePath, pipelinePath)
|
|
}
|
|
if cfg.SessionPath != sessionPath {
|
|
t.Fatalf("SessionPath = %q, want %q", cfg.SessionPath, sessionPath)
|
|
}
|
|
if tt.checkDefault {
|
|
if tt.wantRoot != "" && cfg.Pipeline.Workspace.Root != tt.wantRoot {
|
|
t.Fatalf("workspace.root = %q, want %q", cfg.Pipeline.Workspace.Root, tt.wantRoot)
|
|
}
|
|
if cfg.Pipeline.WhisperX.Language != "en" {
|
|
t.Fatalf("whisperx.language = %q, want %q", cfg.Pipeline.WhisperX.Language, "en")
|
|
}
|
|
if cfg.Pipeline.WhisperX.Timeout != "30m" {
|
|
t.Fatalf("whisperx.timeout = %q, want %q", cfg.Pipeline.WhisperX.Timeout, "30m")
|
|
}
|
|
if cfg.Pipeline.WhisperX.RetryDelay != "2s" {
|
|
t.Fatalf("whisperx.retry_delay = %q, want %q", cfg.Pipeline.WhisperX.RetryDelay, "2s")
|
|
}
|
|
if cfg.Pipeline.WhisperX.Retries == nil || *cfg.Pipeline.WhisperX.Retries != 3 {
|
|
t.Fatalf("whisperx.retries = %v, want 3", cfg.Pipeline.WhisperX.Retries)
|
|
}
|
|
if cfg.Pipeline.WhisperX.Concurrency == nil || *cfg.Pipeline.WhisperX.Concurrency != 2 {
|
|
t.Fatalf("whisperx.concurrency = %v, want 2", cfg.Pipeline.WhisperX.Concurrency)
|
|
}
|
|
if cfg.Pipeline.Seriatim.Timeout != "10m" {
|
|
t.Fatalf("seriatim.timeout = %q, want %q", cfg.Pipeline.Seriatim.Timeout, "10m")
|
|
}
|
|
if cfg.Pipeline.Seriatim.Binary != "seriatim" {
|
|
t.Fatalf("seriatim.binary = %q, want %q", cfg.Pipeline.Seriatim.Binary, "seriatim")
|
|
}
|
|
if cfg.Pipeline.Seriatim.OutputSchema != "seriatim-intermediate" {
|
|
t.Fatalf("seriatim.output_schema = %q, want %q", cfg.Pipeline.Seriatim.OutputSchema, "seriatim-intermediate")
|
|
}
|
|
if cfg.Pipeline.Seriatim.CoalesceGap == nil || *cfg.Pipeline.Seriatim.CoalesceGap != 3.0 {
|
|
t.Fatalf("seriatim.coalesce_gap = %v, want 3.0", cfg.Pipeline.Seriatim.CoalesceGap)
|
|
}
|
|
if cfg.Pipeline.Seriatim.Report == nil || *cfg.Pipeline.Seriatim.Report != true {
|
|
t.Fatalf("seriatim.report = %v, want true", cfg.Pipeline.Seriatim.Report)
|
|
}
|
|
if cfg.Pipeline.Audita.Timeout != "3h" {
|
|
t.Fatalf("audita.timeout = %q, want %q", cfg.Pipeline.Audita.Timeout, "3h")
|
|
}
|
|
if cfg.Pipeline.Audita.Binary != "audita" {
|
|
t.Fatalf("audita.binary = %q, want %q", cfg.Pipeline.Audita.Binary, "audita")
|
|
}
|
|
if cfg.Pipeline.Audita.LLMAPIKeyEnv != "" {
|
|
t.Fatalf("audita.llm_api_key_env = %q, want empty by default", cfg.Pipeline.Audita.LLMAPIKeyEnv)
|
|
}
|
|
if cfg.Pipeline.Audita.Modules != nil {
|
|
t.Fatalf("audita.modules = %#v, want nil default (optional override)", cfg.Pipeline.Audita.Modules)
|
|
}
|
|
if cfg.Pipeline.Audita.BaseURL != "" {
|
|
t.Fatalf("audita.base_url = %q, want empty default", cfg.Pipeline.Audita.BaseURL)
|
|
}
|
|
if cfg.Pipeline.Audita.Model != "" {
|
|
t.Fatalf("audita.model = %q, want empty default", cfg.Pipeline.Audita.Model)
|
|
}
|
|
if cfg.Pipeline.Audita.ValidationModel != "" {
|
|
t.Fatalf("audita.validation_model = %q, want empty default", cfg.Pipeline.Audita.ValidationModel)
|
|
}
|
|
if cfg.Pipeline.Audita.TotalLLMConcurrency != nil {
|
|
t.Fatalf("audita.total_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.TotalLLMConcurrency)
|
|
}
|
|
if cfg.Pipeline.Audita.ProposalLLMConcurrency != nil {
|
|
t.Fatalf("audita.proposal_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ProposalLLMConcurrency)
|
|
}
|
|
if cfg.Pipeline.Audita.ValidationLLMConcurrency != nil {
|
|
t.Fatalf("audita.validation_llm_concurrency = %v, want nil default", cfg.Pipeline.Audita.ValidationLLMConcurrency)
|
|
}
|
|
if cfg.Pipeline.Audita.Report == nil || *cfg.Pipeline.Audita.Report != true {
|
|
t.Fatalf("audita.report = %v, want true", cfg.Pipeline.Audita.Report)
|
|
}
|
|
if cfg.Pipeline.Normalize == nil {
|
|
t.Fatal("normalize config should be present via defaults")
|
|
}
|
|
if cfg.Pipeline.Normalize.OutputPath != "transcripts/normalized.json" {
|
|
t.Fatalf("normalize.output_path = %q, want %q", cfg.Pipeline.Normalize.OutputPath, "transcripts/normalized.json")
|
|
}
|
|
if cfg.Pipeline.Normalize.OutputSchema != "seriatim-intermediate" {
|
|
t.Fatalf("normalize.output_schema = %q, want %q", cfg.Pipeline.Normalize.OutputSchema, "seriatim-intermediate")
|
|
}
|
|
if cfg.Pipeline.Normalize.Report == nil || *cfg.Pipeline.Normalize.Report != true {
|
|
t.Fatalf("normalize.report = %v, want true", cfg.Pipeline.Normalize.Report)
|
|
}
|
|
}
|
|
|
|
err = Validate(cfg)
|
|
if tt.wantValidate != "" {
|
|
if err == nil {
|
|
t.Fatalf("expected validation error containing %q, got nil", tt.wantValidate)
|
|
}
|
|
if !strings.Contains(err.Error(), tt.wantValidate) {
|
|
t.Fatalf("validation error = %q, want to contain %q", err.Error(), tt.wantValidate)
|
|
}
|
|
return
|
|
}
|
|
if err != nil {
|
|
t.Fatalf("Validate() error = %v", err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestValidateMissingAudioSource(t *testing.T) {
|
|
retries := 3
|
|
concurrency := 2
|
|
cfg := &Config{
|
|
Pipeline: &PipelineConfig{
|
|
Workspace: WorkspaceConfig{Root: "/tmp/narratio"},
|
|
WhisperX: WhisperXConfig{
|
|
TranscribeURL: "https://transcription.ai.rakestrawhome.com/transcribe",
|
|
Language: "en",
|
|
Timeout: "30m",
|
|
Retries: &retries,
|
|
RetryDelay: "2s",
|
|
Concurrency: &concurrency,
|
|
},
|
|
Seriatim: SeriatimConfig{
|
|
Binary: "seriatim",
|
|
Timeout: "10m",
|
|
OutputSchema: "seriatim-intermediate",
|
|
CoalesceGap: float64Ptr(3.0),
|
|
Report: boolPtr(true),
|
|
},
|
|
Audita: AuditaConfig{
|
|
Binary: "audita",
|
|
Timeout: "3h",
|
|
LLMAPIKeyEnv: "AUDITA_LLM_API_KEY",
|
|
Modules: []string{"glossary", "homophones"},
|
|
BaseURL: "https://openrouter.ai/api/v1",
|
|
Model: "openrouter/google/gemma-4-31b-it",
|
|
TotalLLMConcurrency: intPtr(1),
|
|
ProposalLLMConcurrency: intPtr(1),
|
|
ValidationModel: "",
|
|
ValidationLLMConcurrency: intPtr(1),
|
|
Report: boolPtr(true),
|
|
},
|
|
},
|
|
Session: &SessionConfig{
|
|
SessionID: "2026-05-03",
|
|
Campaign: "sample-campaign",
|
|
Inputs: SessionInputsConfig{
|
|
SpeakersFile: "speakers.yml",
|
|
AutocorrectFile: "autocorrect.yml",
|
|
GlossaryFile: "glossary.yml",
|
|
},
|
|
},
|
|
}
|
|
|
|
err := Validate(cfg)
|
|
if err == nil {
|
|
t.Fatal("expected validation error, got nil")
|
|
}
|
|
if !strings.Contains(err.Error(), "audio_dir, at least one audio_files entry, or audio_s3") {
|
|
t.Fatalf("error = %q, want audio source guidance", err.Error())
|
|
}
|
|
if !strings.Contains(err.Error(), "session config") {
|
|
t.Fatalf("error = %q, want session config context", err.Error())
|
|
}
|
|
}
|
|
|
|
func TestExamplesLoadAndValidate(t *testing.T) {
|
|
examplesDir := filepath.Join("..", "..", "docs", "examples")
|
|
tests := []struct {
|
|
name string
|
|
pipelineFile string
|
|
sessionFile string
|
|
sessionOpts SessionLoadOptions
|
|
}{
|
|
{
|
|
name: "minimal pipeline with local audio session",
|
|
pipelineFile: "pipeline.minimal.yml",
|
|
sessionFile: "session.local-audio.yml",
|
|
},
|
|
{
|
|
name: "production pipeline with s3 audio session",
|
|
pipelineFile: "pipeline.production.yml",
|
|
sessionFile: "session.s3-audio.yml",
|
|
},
|
|
{
|
|
name: "full annotated pipeline with local audio session",
|
|
pipelineFile: "pipeline.full.annotated.yml",
|
|
sessionFile: "session.local-audio.yml",
|
|
},
|
|
{
|
|
name: "template session renders with session_id option",
|
|
pipelineFile: "pipeline.minimal.yml",
|
|
sessionFile: "session.template.yml",
|
|
sessionOpts: SessionLoadOptions{
|
|
SessionID: "2026-05-03",
|
|
},
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
pipelinePath := filepath.Join(examplesDir, tt.pipelineFile)
|
|
sessionPath := filepath.Join(examplesDir, tt.sessionFile)
|
|
|
|
var (
|
|
cfg *Config
|
|
err error
|
|
)
|
|
if strings.TrimSpace(tt.sessionOpts.SessionID) == "" {
|
|
cfg, err = Load(pipelinePath, sessionPath)
|
|
} else {
|
|
cfg, err = LoadWithSessionOptions(pipelinePath, sessionPath, tt.sessionOpts)
|
|
}
|
|
if err != nil {
|
|
t.Fatalf("load example config error = %v", err)
|
|
}
|
|
if err := Validate(cfg); err != nil {
|
|
t.Fatalf("validate example config error = %v", err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func writeConfigFiles(t *testing.T, pipelineYAML, sessionYAML string) (string, string) {
|
|
t.Helper()
|
|
if !strings.Contains(pipelineYAML, "\naudita:") && !strings.HasPrefix(pipelineYAML, "audita:") {
|
|
if !strings.HasSuffix(pipelineYAML, "\n") {
|
|
pipelineYAML += "\n"
|
|
}
|
|
pipelineYAML += "audita:\n binary: audita\n"
|
|
}
|
|
if !strings.Contains(sessionYAML, "\ncampaign:") && !strings.HasPrefix(sessionYAML, "campaign:") {
|
|
if !strings.HasSuffix(sessionYAML, "\n") {
|
|
sessionYAML += "\n"
|
|
}
|
|
sessionYAML += "campaign: sample-campaign\n"
|
|
}
|
|
|
|
dir := t.TempDir()
|
|
pipelinePath := filepath.Join(dir, "pipeline.yml")
|
|
sessionPath := filepath.Join(dir, "session.yml")
|
|
|
|
if err := os.WriteFile(pipelinePath, []byte(pipelineYAML), 0o644); err != nil {
|
|
t.Fatalf("write pipeline.yml: %v", err)
|
|
}
|
|
if err := os.WriteFile(sessionPath, []byte(sessionYAML), 0o644); err != nil {
|
|
t.Fatalf("write session.yml: %v", err)
|
|
}
|
|
|
|
return pipelinePath, sessionPath
|
|
}
|