From d70b878b71d40d56523a7bcc6f183694378f0887 Mon Sep 17 00:00:00 2001
From: James Pine <ijamespine@me.com>
Date: Thu, 19 Mar 2026 19:32:49 -0700
Subject: [PATCH] fix: tighten kokoro profile handling

---
 .../Generation/EngineModelSelector.tsx        |  21 +-
 .../components/VoiceProfiles/ProfileForm.tsx  |  61 ++-
 .../components/VoiceProfiles/ProfileList.tsx  |   2 +-
 backend/database/migrations.py                |  13 +-
 backend/routes/profiles.py                    |  15 +-
 backend/services/profiles.py                  | 169 ++++---
 docs/plans/API_REFACTOR_PLAN.md               | 428 ++++++++++++++++++
 7 files changed, 618 insertions(+), 91 deletions(-)
 create mode 100644 docs/plans/API_REFACTOR_PLAN.md

diff --git a/app/src/components/Generation/EngineModelSelector.tsx b/app/src/components/Generation/EngineModelSelector.tsx
index 1dfd4e9b..80fd82af 100644
--- a/app/src/components/Generation/EngineModelSelector.tsx
+++ b/app/src/components/Generation/EngineModelSelector.tsx
@@ -1,3 +1,4 @@
+import { useEffect } from 'react';
 import type { UseFormReturn } from 'react-hook-form';
 import { FormControl } from '@/components/ui/form';
 import {
@@ -41,12 +42,9 @@ const ENGLISH_ONLY_ENGINES = new Set(['luxtts', 'chatterbox_turbo']);
 /** Engines that support cloned (reference audio) profiles. */
 const CLONING_ENGINES = new Set(['qwen', 'luxtts', 'chatterbox', 'chatterbox_turbo', 'tada']);
 
-/**
- * All engine options are always available. The profile grid already
- * filters by engine, so the dropdown doesn't need to restrict options.
- */
-function getAvailableOptions(_selectedProfile?: VoiceProfileResponse | null) {
-  return ENGINE_OPTIONS;
+function getAvailableOptions(selectedProfile?: VoiceProfileResponse | null) {
+  if (!selectedProfile) return ENGINE_OPTIONS;
+  return ENGINE_OPTIONS.filter((opt) => isProfileCompatibleWithEngine(selectedProfile, opt.engine));
 }
 
 function getSelectValue(engine: string, modelSize?: string): string {
@@ -108,12 +106,13 @@ export function EngineModelSelector({ form, compact, selectedProfile }: EngineMo
   const selectValue = getSelectValue(engine, modelSize);
   const availableOptions = getAvailableOptions(selectedProfile);
 
-  // If current engine isn't in available options, auto-switch to first available
   const currentEngineAvailable = availableOptions.some((opt) => opt.value === selectValue);
-  if (!currentEngineAvailable && availableOptions.length > 0) {
-    // Defer to avoid setting state during render
-    setTimeout(() => handleEngineChange(form, availableOptions[0].value), 0);
-  }
+
+  useEffect(() => {
+    if (!currentEngineAvailable && availableOptions.length > 0) {
+      handleEngineChange(form, availableOptions[0].value);
+    }
+  }, [availableOptions, currentEngineAvailable, form]);
 
   const itemClass = compact ? 'text-xs text-muted-foreground' : undefined;
   const triggerClass = compact
diff --git a/app/src/components/VoiceProfiles/ProfileForm.tsx b/app/src/components/VoiceProfiles/ProfileForm.tsx
index d3f53eac..0c4987b5 100644
--- a/app/src/components/VoiceProfiles/ProfileForm.tsx
+++ b/app/src/components/VoiceProfiles/ProfileForm.tsx
@@ -43,6 +43,7 @@ import {
   useAddSample,
   useCreateProfile,
   useDeleteAvatar,
+  useDeleteProfile,
   useProfile,
   useUpdateProfile,
   useUploadAvatar,
@@ -59,6 +60,15 @@ import { AudioSampleUpload } from './AudioSampleUpload';
 import { SampleList } from './SampleList';
 
 const MAX_AUDIO_DURATION_SECONDS = 30;
+const PRESET_ONLY_ENGINES = new Set(['kokoro']);
+const DEFAULT_ENGINE_OPTIONS = [
+  { value: 'qwen', label: 'Qwen3-TTS' },
+  { value: 'luxtts', label: 'LuxTTS' },
+  { value: 'chatterbox', label: 'Chatterbox' },
+  { value: 'chatterbox_turbo', label: 'Chatterbox Turbo' },
+  { value: 'tada', label: 'TADA' },
+  { value: 'kokoro', label: 'Kokoro 82M' },
+] as const;
 
 const baseProfileSchema = z.object({
   name: z.string().min(1, 'Name is required').max(100),
@@ -119,6 +129,7 @@ export function ProfileForm() {
   const createProfile = useCreateProfile();
   const updateProfile = useUpdateProfile();
   const addSample = useAddSample();
+  const deleteProfile = useDeleteProfile();
   const uploadAvatar = useUploadAvatar();
   const deleteAvatar = useDeleteAvatar();
   const transcribe = useTranscription();
@@ -259,6 +270,12 @@ export function ProfileForm() {
         (!isCreating && editingProfile?.voice_type === 'preset')),
   });
   const presetVoices = presetVoicesData?.voices ?? [];
+  const isSampleBasedProfile = isCreating
+    ? voiceSource === 'clone'
+    : editingProfile?.voice_type !== 'preset';
+  const availableDefaultEngines = DEFAULT_ENGINE_OPTIONS.filter(
+    (option) => !isSampleBasedProfile || !PRESET_ONLY_ENGINES.has(option.value),
+  );
 
   // Show recording errors
   useEffect(() => {
@@ -348,6 +365,15 @@ export function ProfileForm() {
     }
   }, [editingProfile, profileFormDraft, open, form]);
 
+  useEffect(() => {
+    if (
+      defaultEngine &&
+      !availableDefaultEngines.some((option) => option.value === defaultEngine)
+    ) {
+      setDefaultEngine('');
+    }
+  }, [availableDefaultEngines, defaultEngine]);
+
   async function handleTranscribe() {
     const file = form.getValues('sampleFile');
     if (!file) {
@@ -638,12 +664,32 @@ export function ProfileForm() {
             description: `"${data.name}" has been created with a sample.`,
           });
         } catch (sampleError) {
-          // Profile was created but sample failed - still show error
+          let rollbackSucceeded = false;
+          try {
+            await deleteProfile.mutateAsync(profile.id);
+            rollbackSucceeded = true;
+          } catch (rollbackError) {
+            toast({
+              title: 'Rollback failed',
+              description:
+                rollbackError instanceof Error
+                  ? rollbackError.message
+                  : 'Created profile could not be removed after sample upload failure.',
+              variant: 'destructive',
+            });
+          }
+
           toast({
             title: 'Failed to add sample',
-            description: `Profile "${data.name}" was created, but failed to add sample: ${sampleError instanceof Error ? sampleError.message : 'Unknown error'}`,
+            description:
+              sampleError instanceof Error
+                ? `${sampleError.message}${rollbackSucceeded ? ' The profile was rolled back.' : ''}`
+                : rollbackSucceeded
+                  ? 'Failed to add sample. The profile was rolled back.'
+                  : 'Failed to add sample.',
             variant: 'destructive',
           });
+          return;
         }
       }
 
@@ -1140,12 +1186,11 @@ export function ProfileForm() {
                       </FormControl>
                       <SelectContent>
                         <SelectItem value="_none">No preference</SelectItem>
-                        <SelectItem value="qwen">Qwen3-TTS</SelectItem>
-                        <SelectItem value="luxtts">LuxTTS</SelectItem>
-                        <SelectItem value="chatterbox">Chatterbox</SelectItem>
-                        <SelectItem value="chatterbox_turbo">Chatterbox Turbo</SelectItem>
-                        <SelectItem value="tada">TADA</SelectItem>
-                        <SelectItem value="kokoro">Kokoro 82M</SelectItem>
+                        {availableDefaultEngines.map((option) => (
+                          <SelectItem key={option.value} value={option.value}>
+                            {option.label}
+                          </SelectItem>
+                        ))}
                       </SelectContent>
                     </Select>
                     <p className="text-xs text-muted-foreground">
diff --git a/app/src/components/VoiceProfiles/ProfileList.tsx b/app/src/components/VoiceProfiles/ProfileList.tsx
index 97dde233..606f4a2e 100644
--- a/app/src/components/VoiceProfiles/ProfileList.tsx
+++ b/app/src/components/VoiceProfiles/ProfileList.tsx
@@ -63,7 +63,7 @@ export function ProfileList() {
                 No {ENGINE_NAMES[selectedEngine] ?? selectedEngine} voices created yet.
               </p>
               <p className="text-sm text-muted-foreground mb-4">
-                The default voice will be used. Create a profile to choose a specific voice.
+                Create a profile to choose a specific voice before generating.
               </p>
               <Button onClick={() => setDialogOpen(true)}>
                 <Sparkles className="mr-2 h-4 w-4" />
diff --git a/backend/database/migrations.py b/backend/database/migrations.py
index 9c00fa8f..f4cc5ada 100644
--- a/backend/database/migrations.py
+++ b/backend/database/migrations.py
@@ -191,11 +191,12 @@ def _resolve_relative_paths(engine, tables: set[str]) -> None:
     Idempotent: absolute paths are left untouched.
 
     Strategy: paths like "data/generations/abc.wav" are rebased onto the
-    configured data directory.  If the path starts with "data/", strip that
-    prefix and prepend get_data_dir().  Otherwise, try resolving relative to
-    CWD as a fallback.
+    configured data directory. If the path starts with "data/", strip that
+    prefix and prepend get_data_dir(). Otherwise, join the relative path
+    directly under get_data_dir().
     """
     from pathlib import Path
+
     from ..config import get_data_dir
 
     data_dir = get_data_dir()
@@ -229,11 +230,7 @@ def _resolve_relative_paths(engine, tables: set[str]) -> None:
                 else:
                     rebased = data_dir / p
 
-                if rebased.exists():
-                    resolved = rebased
-                else:
-                    # Fallback: resolve relative to CWD
-                    resolved = p.resolve()
+                resolved = rebased.resolve()
 
                 if resolved.exists():
                     conn.execute(
diff --git a/backend/routes/profiles.py b/backend/routes/profiles.py
index 92552e79..a13b02fc 100644
--- a/backend/routes/profiles.py
+++ b/backend/routes/profiles.py
@@ -7,13 +7,12 @@ import tempfile
 import uuid
 from datetime import datetime
 from pathlib import Path
-from typing import Optional
 
 from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile
 from fastapi.responses import FileResponse, StreamingResponse
 from sqlalchemy.orm import Session
 
-from .. import config, models
+from .. import models
 from ..app import safe_content_disposition
 from ..database import VoiceProfile as DBVoiceProfile, get_db
 from ..services import channels, export_import, profiles
@@ -131,13 +130,15 @@ async def seed_preset_profiles_route(
             if existing:
                 continue
 
-            # Skip name collisions
-            if db.query(DBVoiceProfile).filter_by(name=profile_name).first():
-                continue
+            unique_name = profile_name
+            suffix = 2
+            while db.query(DBVoiceProfile).filter_by(name=unique_name).first():
+                unique_name = f"{profile_name} {suffix}"
+                suffix += 1
 
             profile = DBVoiceProfile(
                 id=str(uuid.uuid4()),
-                name=profile_name,
+                name=unique_name,
                 description=f"Kokoro preset voice — {display_name} ({gender})",
                 language=lang,
                 voice_type="preset",
@@ -394,8 +395,6 @@ async def update_profile_effects(
     db: Session = Depends(get_db),
 ):
     """Set or clear the default effects chain for a voice profile."""
-    import json as _json
-
     profile = db.query(DBVoiceProfile).filter_by(id=profile_id).first()
     if not profile:
         raise HTTPException(status_code=404, detail="Profile not found")
diff --git a/backend/services/profiles.py b/backend/services/profiles.py
index 32fa3bb9..16ea7b57 100644
--- a/backend/services/profiles.py
+++ b/backend/services/profiles.py
@@ -1,36 +1,30 @@
-"""
-Voice profile management module.
-"""
+"""Voice profile management module."""
 
+import json as _json
 import logging
-from typing import List, Optional
-from datetime import datetime
-import uuid
 import shutil
+import uuid
+from datetime import datetime
 from pathlib import Path
+
+from sqlalchemy import func
 from sqlalchemy.orm import Session
-from sqlalchemy import func, select
+
+from .. import config
+from ..database import Generation as DBGeneration, ProfileSample as DBProfileSample, VoiceProfile as DBVoiceProfile
+from ..models import (
+    EffectConfig,
+    ProfileSampleResponse,
+    VoiceProfileCreate,
+    VoiceProfileResponse,
+)
+from ..utils.audio import save_audio, validate_and_load_reference_audio
+from ..utils.cache import _get_cache_dir, clear_profile_cache
+from ..utils.images import process_avatar, validate_image
 
 logger = logging.getLogger(__name__)
 
-from ..models import (
-    VoiceProfileCreate,
-    VoiceProfileResponse,
-    ProfileSampleCreate,
-    ProfileSampleResponse,
-)
-from ..database import (
-    VoiceProfile as DBVoiceProfile,
-    ProfileSample as DBProfileSample,
-    Generation as DBGeneration,
-)
-from ..models import EffectConfig
-from ..utils.audio import validate_reference_audio, validate_and_load_reference_audio, load_audio, save_audio
-from ..utils.images import validate_image, process_avatar
-from ..utils.cache import _get_cache_dir, clear_profile_cache
-from .tts import get_tts_model
-from .. import config
-import json as _json
+CLONING_ENGINES = {"qwen", "luxtts", "chatterbox", "chatterbox_turbo", "tada"}
 
 
 def _profile_to_response(
@@ -67,6 +61,37 @@ def _profile_to_response(
     )
 
 
+def _validate_profile_fields(
+    *,
+    voice_type: str,
+    preset_engine: str | None,
+    preset_voice_id: str | None,
+    design_prompt: str | None,
+    default_engine: str | None,
+) -> str | None:
+    if voice_type == "preset":
+        if not preset_engine or not preset_voice_id:
+            return "Preset profiles require both preset_engine and preset_voice_id"
+        if default_engine and default_engine != preset_engine:
+            return "Preset profiles must use their preset_engine as default_engine"
+        return None
+
+    if voice_type == "designed":
+        if not design_prompt or not design_prompt.strip():
+            return "Designed profiles require a design_prompt"
+        if preset_engine or preset_voice_id:
+            return "Designed profiles cannot set preset_engine or preset_voice_id"
+        return None
+
+    if preset_engine or preset_voice_id:
+        return "Cloned profiles cannot set preset_engine or preset_voice_id"
+    if design_prompt:
+        return "Cloned profiles cannot set design_prompt"
+    if default_engine and default_engine not in CLONING_ENGINES:
+        return f"Cloned profiles cannot use default engine '{default_engine}'"
+    return None
+
+
 async def create_profile(
     data: VoiceProfileCreate,
     db: Session,
@@ -94,6 +119,16 @@ async def create_profile(
     if voice_type == "preset" and data.preset_engine and not default_engine:
         default_engine = data.preset_engine
 
+    validation_error = _validate_profile_fields(
+        voice_type=voice_type,
+        preset_engine=data.preset_engine,
+        preset_voice_id=data.preset_voice_id,
+        design_prompt=data.design_prompt,
+        default_engine=default_engine,
+    )
+    if validation_error:
+        raise ValueError(validation_error)
+
     db_profile = DBVoiceProfile(
         id=str(uuid.uuid4()),
         name=data.name,
@@ -180,7 +215,7 @@ async def add_profile_sample(
 async def get_profile(
     profile_id: str,
     db: Session,
-) -> Optional[VoiceProfileResponse]:
+) -> VoiceProfileResponse | None:
     """
     Get a voice profile by ID.
 
@@ -201,7 +236,7 @@ async def get_profile(
 async def get_profile_samples(
     profile_id: str,
     db: Session,
-) -> List[ProfileSampleResponse]:
+) -> list[ProfileSampleResponse]:
     """
     Get all samples for a profile.
 
@@ -216,7 +251,7 @@ async def get_profile_samples(
     return [ProfileSampleResponse.model_validate(s) for s in samples]
 
 
-async def list_profiles(db: Session) -> List[VoiceProfileResponse]:
+async def list_profiles(db: Session) -> list[VoiceProfileResponse]:
     """
     List all voice profiles with generation and sample counts.
 
@@ -257,7 +292,7 @@ async def update_profile(
     profile_id: str,
     data: VoiceProfileCreate,
     db: Session,
-) -> Optional[VoiceProfileResponse]:
+) -> VoiceProfileResponse | None:
     """
     Update a voice profile.
 
@@ -281,6 +316,22 @@ async def update_profile(
         if existing_profile:
             raise ValueError(f"A profile with the name '{data.name}' already exists. Please choose a different name.")
 
+    voice_type = getattr(profile, "voice_type", None) or "cloned"
+    preset_engine = getattr(profile, "preset_engine", None)
+    preset_voice_id = getattr(profile, "preset_voice_id", None)
+    design_prompt = getattr(profile, "design_prompt", None)
+    default_engine = data.default_engine if data.default_engine is not None else getattr(profile, "default_engine", None)
+
+    validation_error = _validate_profile_fields(
+        voice_type=voice_type,
+        preset_engine=preset_engine,
+        preset_voice_id=preset_voice_id,
+        design_prompt=design_prompt,
+        default_engine=default_engine,
+    )
+    if validation_error:
+        raise ValueError(validation_error)
+
     profile.name = data.name
     profile.description = data.description
     profile.language = data.language
@@ -366,7 +417,7 @@ async def update_profile_sample(
     sample_id: str,
     reference_text: str,
     db: Session,
-) -> Optional[ProfileSampleResponse]:
+) -> ProfileSampleResponse | None:
     """
     Update a profile sample's reference text.
 
@@ -428,6 +479,12 @@ async def create_voice_prompt_for_profile(
 
     # ── Preset profiles: return engine-specific voice reference ──
     if voice_type == "preset":
+        if not profile.preset_engine or not profile.preset_voice_id:
+            raise ValueError(f"Preset profile {profile_id} is missing preset engine metadata")
+        if profile.preset_engine != engine:
+            raise ValueError(
+                f"Preset profile {profile_id} only supports engine '{profile.preset_engine}', not '{engine}'"
+            )
         return {
             "voice_type": "preset",
             "preset_engine": profile.preset_engine,
@@ -436,11 +493,16 @@ async def create_voice_prompt_for_profile(
 
     # ── Designed profiles: return text description (future) ──
     if voice_type == "designed":
+        if not profile.design_prompt or not profile.design_prompt.strip():
+            raise ValueError(f"Designed profile {profile_id} is missing design_prompt")
         return {
             "voice_type": "designed",
             "design_prompt": profile.design_prompt,
         }
 
+    if engine not in CLONING_ENGINES:
+        raise ValueError(f"Engine '{engine}' does not support cloned voice profiles")
+
     # ── Cloned profiles: create from audio samples ──
     samples = db.query(DBProfileSample).filter_by(profile_id=profile_id).all()
 
@@ -457,34 +519,34 @@ async def create_voice_prompt_for_profile(
             use_cache=use_cache,
         )
         return voice_prompt
-    else:
-        audio_paths = [s.audio_path for s in samples]
-        reference_texts = [s.reference_text for s in samples]
 
-        combined_audio, combined_text = await tts_model.combine_voice_prompts(
-            audio_paths,
-            reference_texts,
-        )
+    audio_paths = [s.audio_path for s in samples]
+    reference_texts = [s.reference_text for s in samples]
 
-        # Save combined audio to cache directory (persistent)
-        # Create a hash of sample IDs to identify this specific combination
-        import hashlib
+    combined_audio, combined_text = await tts_model.combine_voice_prompts(
+        audio_paths,
+        reference_texts,
+    )
 
-        sample_ids_str = "-".join(sorted([s.id for s in samples]))
-        combination_hash = hashlib.md5(sample_ids_str.encode()).hexdigest()[:12]
+    # Save combined audio to cache directory (persistent)
+    # Create a hash of sample IDs to identify this specific combination
+    import hashlib
 
-        cache_dir = _get_cache_dir()
-        cache_dir.mkdir(parents=True, exist_ok=True)
-        combined_path = cache_dir / f"combined_{profile_id}_{combination_hash}.wav"
+    sample_ids_str = "-".join(sorted([s.id for s in samples]))
+    combination_hash = hashlib.md5(sample_ids_str.encode()).hexdigest()[:12]
 
-        save_audio(combined_audio, str(combined_path), 24000)
+    cache_dir = _get_cache_dir()
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    combined_path = cache_dir / f"combined_{profile_id}_{combination_hash}.wav"
 
-        voice_prompt, _ = await tts_model.create_voice_prompt(
-            str(combined_path),
-            combined_text,
-            use_cache=use_cache,
-        )
-        return voice_prompt
+    save_audio(combined_audio, str(combined_path), 24000)
+
+    voice_prompt, _ = await tts_model.create_voice_prompt(
+        str(combined_path),
+        combined_text,
+        use_cache=use_cache,
+    )
+    return voice_prompt
 
 
 async def upload_avatar(
@@ -571,6 +633,3 @@ async def delete_avatar(
     db.commit()
 
     return True
-
-
-
diff --git a/docs/plans/API_REFACTOR_PLAN.md b/docs/plans/API_REFACTOR_PLAN.md
new file mode 100644
index 00000000..019f0482
--- /dev/null
+++ b/docs/plans/API_REFACTOR_PLAN.md
@@ -0,0 +1,428 @@
+# Voicebox API Refactor Plan
+
+Date: 2026-03-19
+Status: Proposed
+Scope: Backend HTTP API structure, schemas, docs, and compatibility strategy
+
+## Goals
+
+- Make the API easier to understand and automate against.
+- Improve endpoint consistency without breaking the desktop app or existing local integrations.
+- Align generated docs and checked-in OpenAPI artifacts with the actual backend.
+- Separate app-facing resources from internal or operational actions.
+- Create a migration path toward a cleaner `v2` resource model while preserving `v1` routes during transition.
+
+## Non-Goals
+
+- Rewriting backend business logic or generation internals.
+- Introducing authentication for all deployment modes in the first pass.
+- Changing storage models or database schema unless required for API correctness.
+- Removing current routes immediately.
+
+## Current Pain Points
+
+- Mixed endpoint styles: resource-oriented (`/profiles`) and command-oriented (`/generate`, `/tasks/clear`) coexist.
+- Related generation resources are split across multiple namespaces: `/generate`, `/history`, `/audio`, `/effects`, and `/generations/.../versions`.
+- Response payloads vary widely: typed models, raw dicts with `message`, booleans, and `HTTPException(detail=...)` payloads.
+- Some async flows use exception-shaped `202` responses instead of first-class task contracts.
+- Checked-in OpenAPI output can drift from actual backend models.
+- Operational endpoints such as `/shutdown` are exposed in the same surface as user workflows.
+
+## Guiding Principles
+
+1. Prefer additive changes before destructive changes.
+2. Keep `v1` behavior working until the app and docs fully migrate.
+3. Add compatibility shims close to the routing layer, not deep in services.
+4. Treat OpenAPI as a release artifact that must be kept in sync.
+5. Standardize public contracts before renaming everything.
+
+## Target API Shape
+
+This is the intended end state, not the immediate first milestone.
+
+### Core Resources
+
+- `/profiles`
+- `/profiles/{profile_id}/samples`
+- `/profiles/{profile_id}/avatar`
+- `/profiles/{profile_id}/effects`
+- `/generations`
+- `/generations/{generation_id}`
+- `/generations/{generation_id}/status`
+- `/generations/{generation_id}/audio`
+- `/generations/{generation_id}/versions`
+- `/generations/{generation_id}/versions/{version_id}`
+- `/generations/{generation_id}/versions/{version_id}/audio`
+- `/stories`
+- `/stories/{story_id}/items`
+- `/effects/presets`
+- `/models`
+- `/models/{model_name}`
+- `/tasks`
+
+### Operational or Internal Endpoints
+
+Move under an explicit namespace and disable where appropriate:
+
+- `/admin/shutdown`
+- `/admin/watchdog/disable`
+- `/admin/cache/clear`
+- `/admin/tasks/clear`
+
+### Response Contract Direction
+
+- Resource reads and writes return typed resource models.
+- Delete and action endpoints return small typed action result models.
+- Errors use a consistent structure.
+- Async actions return explicit task metadata instead of overloading `detail`.
+
+## Migration Strategy Overview
+
+The refactor is split into six phases. Phases 1-3 are the highest impact and safest to ship first.
+
+| Phase | Focus | Est. Duration | Risk | Backward Compatibility |
+| --- | --- | --- | --- | --- |
+| 1 | Documentation and contract correctness | 2-3 days | Low | Full |
+| 2 | Response and error consistency | 3-5 days | Low-Medium | Full |
+| 3 | Router structure and internal organization | 3-4 days | Low | Full |
+| 4 | Additive `v2` resource endpoints | 1-2 weeks | Medium | Full |
+| 5 | Client migration and deprecation rollout | 1 week | Medium | Full during rollout |
+| 6 | Cleanup and optional removals | 1-2 releases | Medium-High | Partial after notice |
+
+## Phase 1: Fix Contract Drift First
+
+Priority: Highest
+Outcome: The documented API matches the running backend.
+
+### Problems Addressed
+
+- `docs/openapi.json` can become stale.
+- Generated API reference pages may describe outdated request bodies.
+- App metadata still frames the backend too narrowly.
+
+### Implementation Steps
+
+1. Update FastAPI app metadata in `backend/app.py`.
+   - Replace the old Qwen-specific description with a multi-engine Voicebox API description.
+   - Add tags metadata for major domains if desired.
+2. Regenerate OpenAPI from the running app using the existing docs script flow.
+3. Compare `backend/models.py` to the checked-in schema.
+   - Verify `GenerationRequest`, effects endpoints, stories endpoints, and model endpoints.
+4. Regenerate or refresh API reference pages under `docs/content/docs/api-reference/`.
+5. Add a CI check that fails if `docs/openapi.json` is out of date.
+6. Add a short maintainer note describing when schema regeneration is required.
+
+### Backward Compatibility
+
+- No route changes.
+- No payload changes.
+- Safe to release immediately.
+
+### Success Criteria
+
+- `docs/openapi.json` matches the live app.
+- Generated docs include all currently supported generate parameters.
+- No frontend code changes required.
+
+## Phase 2: Standardize Responses and Errors
+
+Priority: High
+Outcome: Clients can handle responses predictably.
+
+### Problems Addressed
+
+- Delete endpoints return ad hoc message dicts.
+- Toggle endpoints return special one-off payloads.
+- `202` async responses are encoded as `HTTPException(detail=...)` in some places.
+
+### Implementation Steps
+
+1. Add shared response models in `backend/models.py`.
+   - `ActionResult`
+   - `DeleteResult`
+   - `ToggleFavoriteResponse`
+   - `AcceptedTaskResponse`
+   - `ApiError`
+2. Convert routes that currently return raw dicts to explicit `response_model`s.
+   - `DELETE /profiles/{profile_id}`
+   - `DELETE /history/{generation_id}`
+   - `DELETE /stories/{story_id}`
+   - `POST /tasks/clear`
+   - `POST /cache/clear`
+   - similar endpoints across routes
+3. Replace exception-shaped `202` responses in `transcription.py` with an explicit accepted response body.
+   - Return `JSONResponse(status_code=202, content=...)` or typed FastAPI response model.
+4. Add a global exception handler for known API errors if helpful.
+   - Normalize `ValueError` to `400` with a consistent error body.
+   - Preserve FastAPI validation errors for now, or wrap them in a consistent top-level shape in a later pass.
+5. Document the stable error contract in the docs.
+
+### Migration Strategy
+
+- Keep field names inside successful payloads compatible where possible.
+- For existing dict responses, preserve the current keys while introducing typed models with the same shape.
+- For `202` flows, support both old and new client handling for one release if needed.
+
+### Timeline Estimate
+
+- 3-5 engineering days including tests and docs refresh.
+
+### Success Criteria
+
+- All mutation endpoints declare response models.
+- Clients can programmatically distinguish success, accepted, and error cases without special casing `detail` payloads.
+
+## Phase 3: Normalize Router Structure Internally
+
+Priority: High
+Outcome: The backend becomes easier to maintain before public path changes begin.
+
+### Problems Addressed
+
+- Route files hardcode full paths and are all mounted at root.
+- There is no consistent use of router prefixes or tags.
+- Route grouping in code does not cleanly express the public API shape.
+
+### Implementation Steps
+
+1. Add prefixes and tags to routers.
+   - `profiles`: `prefix="/profiles"`
+   - `generations`: `prefix="/generate"` for now or split additive aliases carefully
+   - `history`: `prefix="/history"`
+   - `effects`: `prefix="/effects"`
+   - and so on
+2. Convert route declarations to relative paths within each router.
+3. Introduce a small route compatibility layer for routes that are likely to move later.
+   - Example: helper functions that can be mounted under both old and new paths.
+4. Add explicit route tags so Swagger/OpenAPI groups are coherent.
+5. Document the intended public ownership of each namespace.
+
+### Backward Compatibility
+
+- No public path changes yet if existing paths are preserved through prefixes and aliases.
+- Mostly internal refactoring.
+
+### Timeline Estimate
+
+- 3-4 engineering days.
+
+### Success Criteria
+
+- All route modules use prefixes and tags.
+- Route registration in `backend/routes/__init__.py` becomes simpler.
+- OpenAPI groups read cleanly by domain.
+
+## Phase 4: Introduce Additive `v2` Resource Endpoints
+
+Priority: High
+Outcome: A cleaner API exists without breaking the current one.
+
+### Problems Addressed
+
+- Generation-related resources are fragmented.
+- Sample and audio endpoints are not consistently modeled as resources.
+- Command-style naming makes the API harder to reason about.
+
+### New Endpoints to Add
+
+These should be introduced alongside current endpoints, not as replacements.
+
+- `POST /generations` -> alias for current `/generate`
+- `GET /generations` -> alias for current `/history`
+- `GET /generations/{id}` -> alias for current `/history/{id}`
+- `POST /generations/{id}/retry` -> alias for current `/generate/{id}/retry`
+- `POST /generations/{id}/regenerate` -> alias for current `/generate/{id}/regenerate`
+- `GET /generations/{id}/status` -> alias for current `/generate/{id}/status`
+- `POST /generations/stream` -> alias for current `/generate/stream`
+- `GET /generations/{id}/audio` -> alias for current `/audio/{generation_id}`
+- `GET /generations/{id}/export` -> alias for current `/history/{generation_id}/export`
+- `GET /generations/{id}/export-audio` -> alias for current `/history/{generation_id}/export-audio`
+- `GET /profiles/{profile_id}/samples/{sample_id}` or `GET /samples/{sample_id}` as a consciously chosen model
+- `PUT /profiles/{profile_id}/samples/{sample_id}` -> alias for current sample update route
+- `DELETE /profiles/{profile_id}/samples/{sample_id}` -> alias for current sample delete route
+
+### Implementation Steps
+
+1. Create new handler entry points that call the existing service functions.
+2. Keep old handlers in place, but mark them deprecated in OpenAPI.
+3. Add `summary` and `description` text clarifying preferred routes.
+4. Update frontend and docs examples to use new endpoints first.
+5. Add tests proving both old and new paths return equivalent responses.
+
+### Migration Strategy
+
+- Old paths remain functional for at least one stable release cycle.
+- New docs and client examples use `v2-style` resource routes immediately.
+- Include deprecation headers where feasible, for example:
+  - `Deprecation: true`
+  - `Sunset: <date>`
+  - `Link: <new-doc-url>; rel="successor-version"`
+
+### Timeline Estimate
+
+- 1-2 weeks depending on test coverage and frontend updates.
+
+### Success Criteria
+
+- All major generation workflows are accessible through resource-oriented routes.
+- Old routes still work unchanged.
+
+## Phase 5: Migrate First-Party Clients and Publish Deprecations
+
+Priority: Medium
+Outcome: Voicebox itself stops depending on legacy paths.
+
+### Problems Addressed
+
+- The desktop app and docs may continue to reinforce old route shapes.
+- Third-party consumers need a visible migration path.
+
+### Implementation Steps
+
+1. Update `app/src/lib/api/client.ts` to use the new preferred endpoints.
+2. Regenerate or refresh any generated API clients.
+3. Update docs examples, tutorials, and code snippets to use preferred routes only.
+4. Add a changelog entry describing the migration path.
+5. Add runtime deprecation logging for legacy route usage in development mode.
+6. If feasible, expose a small `/health` or `/meta` field showing API version and deprecation window.
+
+### Migration Strategy
+
+- Keep old endpoints available but clearly documented as legacy.
+- Publish a mapping table from old route to new route.
+- Do not change request or response payloads during the same phase unless necessary.
+
+### Timeline Estimate
+
+- About 1 week including docs and app verification.
+
+### Success Criteria
+
+- First-party app no longer depends on legacy route names.
+- Docs do not advertise deprecated paths as the primary interface.
+
+## Phase 6: Cleanup, Namespace Hardening, and Optional Breaking Changes
+
+Priority: Medium
+Outcome: The API surface is cleaner and safer for remote or Docker use.
+
+### Problems Addressed
+
+- Internal/admin endpoints are mixed into the public API.
+- Legacy aliases increase maintenance cost forever if never retired.
+
+### Implementation Steps
+
+1. Move operational endpoints under `/admin` or `/internal`.
+   - `/shutdown`
+   - `/watchdog/disable`
+   - `/tasks/clear`
+   - `/cache/clear`
+2. Gate these endpoints behind configuration for non-local deployments.
+   - Example: `VOICEBOX_ENABLE_ADMIN_API=true`
+3. Decide whether to remove or keep legacy aliases.
+   - If removing, do so only after a published deprecation window.
+4. Remove deprecated docs pages and old examples.
+5. Tighten route-level tests to prevent accidental reintroduction of legacy patterns.
+
+### Migration Strategy
+
+- For desktop-only local use, aliases may remain indefinitely if removal cost outweighs benefit.
+- For published remote API guidance, hide admin endpoints from default docs even if they still exist.
+
+### Timeline Estimate
+
+- 1-2 releases after the additive migration is complete.
+
+### Success Criteria
+
+- Public docs expose a coherent resource API.
+- Operational endpoints are clearly separate or disabled in remote contexts.
+
+## Cross-Cutting Work Items
+
+These should happen throughout the migration, not only in a single phase.
+
+### Testing
+
+- Add route equivalence tests for old and new paths.
+- Add schema snapshot tests for OpenAPI generation.
+- Add response-shape tests for common mutations and async workflows.
+- Add contract tests for `202 Accepted` flows.
+
+### Documentation
+
+- Maintain an old-to-new endpoint mapping table.
+- Add per-endpoint examples for create profile, generate, apply effects, transcribe, and stories operations.
+- Explicitly document which endpoints are app-facing vs admin-facing.
+
+### Observability
+
+- Add warning logs when deprecated endpoints are used.
+- Track usage counts in development or optional telemetry-free local logs.
+
+### Release Management
+
+- Mention API changes in `CHANGELOG.md`.
+- Ensure docs and app updates ship in the same release as new preferred routes.
+
+## Recommended Execution Order
+
+If engineering time is limited, implement in this exact order:
+
+1. Fix OpenAPI and docs drift.
+2. Standardize response models and accepted-task responses.
+3. Add router prefixes and tags internally.
+4. Add `/generations` aliases and sample path aliases.
+5. Migrate the first-party app to preferred routes.
+6. Deprecate or hide legacy/admin routes.
+
+## Old-to-New Route Mapping
+
+| Current Route | Preferred Route |
+| --- | --- |
+| `POST /generate` | `POST /generations` |
+| `POST /generate/stream` | `POST /generations/stream` |
+| `POST /generate/{id}/retry` | `POST /generations/{id}/retry` |
+| `POST /generate/{id}/regenerate` | `POST /generations/{id}/regenerate` |
+| `GET /generate/{id}/status` | `GET /generations/{id}/status` |
+| `GET /history` | `GET /generations` |
+| `GET /history/{id}` | `GET /generations/{id}` |
+| `GET /audio/{id}` | `GET /generations/{id}/audio` |
+| `GET /history/{id}/export` | `GET /generations/{id}/export` |
+| `GET /history/{id}/export-audio` | `GET /generations/{id}/export-audio` |
+| `PUT /profiles/samples/{sample_id}` | `PUT /profiles/{profile_id}/samples/{sample_id}` |
+| `DELETE /profiles/samples/{sample_id}` | `DELETE /profiles/{profile_id}/samples/{sample_id}` |
+| `POST /tasks/clear` | `POST /admin/tasks/clear` |
+| `POST /cache/clear` | `POST /admin/cache/clear` |
+| `POST /shutdown` | `POST /admin/shutdown` |
+| `POST /watchdog/disable` | `POST /admin/watchdog/disable` |
+
+## Risks and Mitigations
+
+### Risk: App regressions during endpoint migration
+
+- Mitigation: Add new routes before changing client usage.
+- Mitigation: Keep payloads identical while paths change.
+
+### Risk: Docs still drift after cleanup
+
+- Mitigation: Add CI enforcement and a release checklist step.
+
+### Risk: Third-party local scripts break on removal
+
+- Mitigation: Prefer indefinite aliases for one-person local workflows unless maintenance becomes painful.
+
+### Risk: Admin endpoints remain dangerous in remote mode
+
+- Mitigation: Hide and gate them before promoting remote deployment more broadly.
+
+## Definition of Done
+
+The refactor can be considered complete when all of the following are true:
+
+- OpenAPI, checked-in docs, and backend models match.
+- The preferred public API is resource-oriented and documented consistently.
+- The Voicebox app uses preferred routes exclusively.
+- Legacy routes are either deprecated with a timeline or intentionally retained as compatibility aliases.
+- Operational endpoints are clearly separated from the public app API.