Skip to content

Feature/voice profile and refactors #58

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ericksonlopes merged 5 commits into from
Apr 7, 2026
Merged

Feature/voice profile and refactors #58

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
80a0a29
fix(api): improve voice profile upload validation and fix failing tes…
ericksonlopes Apr 7, 2026
a7cd10b
feat(db): add status and error messages to content sources
ericksonlopes Apr 7, 2026
5330207
refactor(api): enhance subject and source routing logic and coverage
ericksonlopes Apr 7, 2026
bb82cc7
refactor: update dependencies, index services, and background worker …
ericksonlopes Apr 7, 2026
360a982
feat(voice): add status management and improve test coverage for voic…
ericksonlopes Apr 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 10 additions & 30 deletions alembic/versions/04e0f5f5f0af_add_status_message_and_error_message_to_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,7 @@ def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("chunk_index", schema=None) as batch_op:
batch_op.alter_column(
"id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False)
batch_op.alter_column(
"content_source_id",
existing_type=sa.NUMERIC(),
Expand All @@ -48,9 +46,7 @@ def upgrade() -> None:
with op.batch_alter_table("content_sources", schema=None) as batch_op:
batch_op.add_column(sa.Column("status_message", sa.Text(), nullable=True))
batch_op.add_column(sa.Column("error_message", sa.Text(), nullable=True))
batch_op.alter_column(
"id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False)
batch_op.alter_column(
"subject_id",
existing_type=sa.NUMERIC(),
Expand All @@ -66,14 +62,10 @@ def upgrade() -> None:
existing_nullable=True,
)
batch_op.drop_index(batch_op.f("ix_diarizations_title"))
batch_op.create_index(
batch_op.f("ix_diarizations_name"), ["name"], unique=False
)
batch_op.create_index(batch_op.f("ix_diarizations_name"), ["name"], unique=False)

with op.batch_alter_table("ingestion_jobs", schema=None) as batch_op:
batch_op.alter_column(
"id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False)
batch_op.alter_column(
"content_source_id",
existing_type=sa.NUMERIC(),
Expand All @@ -88,9 +80,7 @@ def upgrade() -> None:
)

with op.batch_alter_table("knowledge_subjects", schema=None) as batch_op:
batch_op.alter_column(
"id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.NUMERIC(), type_=sa.UUID(), existing_nullable=False)

# ### end Alembic commands ###

Expand All @@ -99,9 +89,7 @@ def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("knowledge_subjects", schema=None) as batch_op:
batch_op.alter_column(
"id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False)

with op.batch_alter_table("ingestion_jobs", schema=None) as batch_op:
batch_op.alter_column(
Expand All @@ -116,15 +104,11 @@ def downgrade() -> None:
type_=sa.NUMERIC(),
existing_nullable=True,
)
batch_op.alter_column(
"id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False)

with op.batch_alter_table("diarizations", schema=None) as batch_op:
batch_op.drop_index(batch_op.f("ix_diarizations_name"))
batch_op.create_index(
batch_op.f("ix_diarizations_title"), ["name"], unique=False
)
batch_op.create_index(batch_op.f("ix_diarizations_title"), ["name"], unique=False)
batch_op.alter_column(
"subject_id",
existing_type=sa.UUID(),
Expand All @@ -139,9 +123,7 @@ def downgrade() -> None:
type_=sa.NUMERIC(),
existing_nullable=True,
)
batch_op.alter_column(
"id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False)
batch_op.drop_column("error_message")
batch_op.drop_column("status_message")

Expand All @@ -164,8 +146,6 @@ def downgrade() -> None:
type_=sa.NUMERIC(),
existing_nullable=False,
)
batch_op.alter_column(
"id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False
)
batch_op.alter_column("id", existing_type=sa.UUID(), type_=sa.NUMERIC(), existing_nullable=False)

# ### end Alembic commands ###
4 changes: 1 addition & 3 deletions alembic/versions/0ce7f69147eb_update_unique_constraint_on_content_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,7 @@ def upgrade() -> None:
"""Upgrade schema."""
# Using batch mode for SQLite compatibility
with op.batch_alter_table("content_sources", schema=None) as batch_op:
batch_op.drop_constraint(
op.f("uq_content_source_external_source"), type_="unique"
)
batch_op.drop_constraint(op.f("uq_content_source_external_source"), type_="unique")
batch_op.create_unique_constraint(
"uq_content_source_external_source_per_subject",
["external_source", "subject_id"],
Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/4e8d4e04a288_add_external_source_to_ingestion_jobs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,9 +21,7 @@

def upgrade() -> None:
"""Upgrade schema."""
op.add_column(
"ingestion_jobs", sa.Column("external_source", sa.Text(), nullable=True)
)
op.add_column("ingestion_jobs", sa.Column("external_source", sa.Text(), nullable=True))


def downgrade() -> None:
Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/50420d500c2e_add_token_columns_to_content_source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,7 @@
def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.add_column(
"content_sources", sa.Column("total_tokens", sa.Integer(), nullable=True)
)
op.add_column("content_sources", sa.Column("total_tokens", sa.Integer(), nullable=True))
op.add_column(
"content_sources",
sa.Column("max_tokens_per_chunk", sa.Integer(), nullable=True),
Expand Down
8 changes: 2 additions & 6 deletions alembic/versions/5736075a22d0_add_vector_store_type_to_job_and_chunk_.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,17 +28,13 @@ def upgrade() -> None:
columns_chunk = [c["name"] for c in insp.get_columns("chunk_index")]
if "vector_store_type" not in columns_chunk:
with op.batch_alter_table("chunk_index", schema=None) as batch_op:
batch_op.add_column(
sa.Column("vector_store_type", sa.Text(), nullable=True)
)
batch_op.add_column(sa.Column("vector_store_type", sa.Text(), nullable=True))

# ingestion_jobs
columns_jobs = [c["name"] for c in insp.get_columns("ingestion_jobs")]
if "vector_store_type" not in columns_jobs:
with op.batch_alter_table("ingestion_jobs", schema=None) as batch_op:
batch_op.add_column(
sa.Column("vector_store_type", sa.Text(), nullable=True)
)
batch_op.add_column(sa.Column("vector_store_type", sa.Text(), nullable=True))


def downgrade() -> None:
Expand Down
36 changes: 9 additions & 27 deletions alembic/versions/5ff7984a3bcc_optimize_sql_models_indexes_and_audit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,12 +33,8 @@ def upgrade() -> None:
)
)
batch_op.create_index("ix_chunk_index_chunk_id", ["chunk_id"], unique=False)
batch_op.create_index(
"ix_chunk_index_content_source_id", ["content_source_id"], unique=False
)
batch_op.create_index(
op.f("ix_chunk_index_created_at"), ["created_at"], unique=False
)
batch_op.create_index("ix_chunk_index_content_source_id", ["content_source_id"], unique=False)
batch_op.create_index(op.f("ix_chunk_index_created_at"), ["created_at"], unique=False)
batch_op.create_index("ix_chunk_index_job_id", ["job_id"], unique=False)

with op.batch_alter_table("content_sources", schema=None) as batch_op:
Expand All @@ -50,24 +46,16 @@ def upgrade() -> None:
nullable=False,
)
)
batch_op.create_index(
op.f("ix_content_sources_created_at"), ["created_at"], unique=False
)
batch_op.create_index(op.f("ix_content_sources_created_at"), ["created_at"], unique=False)
batch_op.create_index(
op.f("ix_content_sources_processing_status"),
["processing_status"],
unique=False,
)
batch_op.create_index(
"ix_content_sources_source_type", ["source_type"], unique=False
)
batch_op.create_index("ix_content_sources_source_type", ["source_type"], unique=False)
batch_op.create_index("ix_content_sources_status", ["status"], unique=False)
batch_op.create_index(
"ix_content_sources_subject_id", ["subject_id"], unique=False
)
batch_op.create_unique_constraint(
"uq_content_source_external_source", ["external_source"]
)
batch_op.create_index("ix_content_sources_subject_id", ["subject_id"], unique=False)
batch_op.create_unique_constraint("uq_content_source_external_source", ["external_source"])

with op.batch_alter_table("ingestion_jobs", schema=None) as batch_op:
batch_op.add_column(
Expand All @@ -78,12 +66,8 @@ def upgrade() -> None:
nullable=False,
)
)
batch_op.create_index(
"ix_ingestion_jobs_content_source_id", ["content_source_id"], unique=False
)
batch_op.create_index(
op.f("ix_ingestion_jobs_started_at"), ["started_at"], unique=False
)
batch_op.create_index("ix_ingestion_jobs_content_source_id", ["content_source_id"], unique=False)
batch_op.create_index(op.f("ix_ingestion_jobs_started_at"), ["started_at"], unique=False)
batch_op.create_index("ix_ingestion_jobs_status", ["status"], unique=False)

with op.batch_alter_table("knowledge_subjects", schema=None) as batch_op:
Expand All @@ -105,9 +89,7 @@ def downgrade() -> None:
with op.batch_alter_table("ingestion_jobs", schema=None) as batch_op:
batch_op.drop_index("ix_ingestion_jobs_status")
batch_op.drop_index(op.f("ix_ingestion_jobs_started_at"))
batch_op.create_index(
"ix_ingestion_jobs_content_source_id", ["content_source_id"], unique=False
)
batch_op.create_index("ix_ingestion_jobs_content_source_id", ["content_source_id"], unique=False)
batch_op.drop_column("updated_at")

with op.batch_alter_table("content_sources", schema=None) as batch_op:
Expand Down
8 changes: 2 additions & 6 deletions alembic/versions/6e53bc32edfe_add_subject_id_to_diarization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,12 +24,8 @@ def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("diarizations", schema=None) as batch_op:
batch_op.add_column(sa.Column("subject_id", sa.UUID(), nullable=True))
batch_op.create_index(
batch_op.f("ix_diarizations_subject_id"), ["subject_id"], unique=False
)
batch_op.create_foreign_key(
"fk_diarization_subject", "knowledge_subjects", ["subject_id"], ["id"]
)
batch_op.create_index(batch_op.f("ix_diarizations_subject_id"), ["subject_id"], unique=False)
batch_op.create_foreign_key("fk_diarization_subject", "knowledge_subjects", ["subject_id"], ["id"])

# ### end Alembic commands ###

Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/72f69987a221_rename_diarization_title_to_name.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,7 @@
def upgrade() -> None:
"""Upgrade schema."""
with op.batch_alter_table("diarizations", schema=None) as batch_op:
batch_op.alter_column(
"title", new_column_name="name", existing_type=sa.String()
)
batch_op.alter_column("title", new_column_name="name", existing_type=sa.String())


def downgrade() -> None:
Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/73f13c5ff10a_add_metadata_to_chunk_index.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,9 +39,7 @@ def upgrade() -> None:
# Check for FK
fks = insp.get_foreign_keys("chunk_index")
has_fk = any(
fk["referred_table"] == "knowledge_subjects"
and "subject_id" in fk["constrained_columns"]
for fk in fks
fk["referred_table"] == "knowledge_subjects" and "subject_id" in fk["constrained_columns"] for fk in fks
)
if not has_fk:
batch_op.create_foreign_key(
Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/946d88fe08b1_add_source_metadata_to_content_source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,7 @@
def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.add_column(
"content_sources", sa.Column("source_metadata", sa.JSON(), nullable=True)
)
op.add_column("content_sources", sa.Column("source_metadata", sa.JSON(), nullable=True))
# ### end Alembic commands ###


Expand Down
12 changes: 3 additions & 9 deletions alembic/versions/bd01964d9b26_created_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,7 @@ def upgrade() -> None:
sa.Column("language", sa.Text(), nullable=True),
sa.Column("embedding_model", sa.Text(), nullable=True),
sa.Column("dimensions", sa.Integer(), nullable=True),
sa.Column(
"status", sa.Text(), server_default=sa.text("'active'"), nullable=False
),
sa.Column("status", sa.Text(), server_default=sa.text("'active'"), nullable=False),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
Expand Down Expand Up @@ -103,9 +101,7 @@ def upgrade() -> None:
sa.Column("chunk_id", sa.Text(), nullable=False),
sa.Column("chars", sa.Integer(), server_default=sa.text("0"), nullable=False),
sa.Column("language", sa.Text(), nullable=True),
sa.Column(
"version_number", sa.Integer(), server_default=sa.text("1"), nullable=False
),
sa.Column("version_number", sa.Integer(), server_default=sa.text("1"), nullable=False),
sa.Column(
"created_at",
sa.DateTime(timezone=True),
Expand All @@ -118,9 +114,7 @@ def upgrade() -> None:
initially="IMMEDIATE",
deferrable=True,
),
sa.ForeignKeyConstraint(
["job_id"], ["ingestion_jobs.id"], initially="IMMEDIATE", deferrable=True
),
sa.ForeignKeyConstraint(["job_id"], ["ingestion_jobs.id"], initially="IMMEDIATE", deferrable=True),
sa.PrimaryKeyConstraint("id"),
if_not_exists=True,
)
Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/c16fab000f02_add_user_table.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,9 +34,7 @@ def upgrade() -> None:
if_not_exists=True,
)
with op.batch_alter_table("users", schema=None) as batch_op:
batch_op.create_index(
batch_op.f("ix_users_email"), ["email"], unique=True, if_not_exists=True
)
batch_op.create_index(batch_op.f("ix_users_email"), ["email"], unique=True, if_not_exists=True)

# ### end Alembic commands ###

Expand Down
4 changes: 1 addition & 3 deletions alembic/versions/c48798b08031_add_voice_samples_table.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,4 @@ def downgrade() -> None:
sa.PrimaryKeyConstraint("id"),
)
with op.batch_alter_table("voice_samples", schema=None) as batch_op:
batch_op.create_index(
batch_op.f("ix_voice_samples_voice_id"), ["voice_id"], unique=False
)
batch_op.create_index(batch_op.f("ix_voice_samples_voice_id"), ["voice_id"], unique=False)
4 changes: 1 addition & 3 deletions alembic/versions/f120b614600a_add_diarizations_and_voices_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,9 +56,7 @@ def upgrade() -> None:
if_not_exists=True,
)
with op.batch_alter_table("voices", schema=None) as batch_op:
batch_op.create_index(
batch_op.f("ix_voices_name"), ["name"], unique=True, if_not_exists=True
)
batch_op.create_index(batch_op.f("ix_voices_name"), ["name"], unique=True, if_not_exists=True)


def downgrade() -> None:
Expand Down
37 changes: 32 additions & 5 deletions frontend/src/components/DiarizationView.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,13 @@ export function DiarizationView() {
loadJobs(true).then(updatedJobs => {
const updated = updatedJobs.find(j => j.id === activeJob.id);
if (updated && updated.status !== activeJob.status) {
if (updated.status === 'awaiting_verification' || updated.status === 'completed' || updated.status === 'failed') {
// If user is already in identification/result, don't reset the
// local speakers state on transient status changes (e.g. voice
// training flipping the job to TRAINING → COMPLETED). Only
// open/reset the job when we were still waiting on the initial
// diarization run.
const inIdentification = step === 'identification' || step === 'result';
if (!inIdentification && (updated.status === 'awaiting_verification' || updated.status === 'completed' || updated.status === 'failed')) {
handleOpenJob(updated);
} else {
setActiveJob(updated);
Expand All @@ -111,7 +117,18 @@ export function DiarizationView() {
}
}
}
}, [lastEvent, loadJobs, activeJob, addToast, t]);

// Voice training finished in background → clear per-speaker processing flag
if (lastEvent.type === 'voice' && lastEvent.action === 'train' && lastEvent.name) {
const finishedName = lastEvent.name as string;
setSpeakers(prev => prev.map(s =>
s.trainingStatus === 'processing' && s.assigned === finishedName
? { ...s, trainingStatus: undefined, confidence: Math.max(s.confidence, 95) }
: s
));
refreshVoices();
}
}, [lastEvent, loadJobs, activeJob, addToast, t, step, refreshVoices]);


// -- HANDLERS --
Expand Down Expand Up @@ -497,9 +514,19 @@ export function DiarizationView() {
speaker={trainingSpeaker}
diarizationId={activeJob?.id || ''}
onClose={() => setTrainingSpeaker(null)}
onTrained={() => {
refreshVoices();
handleRecognizeSpeakers();
onTrained={(name) => {
// Mark this speaker as "processing" and optimistically assign the
// new name so the UI reflects the in-flight training job. The
// button will switch to "Reinforce" once the backend publishes
// the voice/train completion event.
const targetId = trainingSpeaker?.id;
if (targetId) {
setSpeakers(prev => prev.map(s =>
s.id === targetId
? { ...s, assigned: name, trainingStatus: 'processing' }
: s
));
}
}}
/>
</div>
Expand Down
Loading
Loading