mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-14 00:16:38 +00:00
viettranx
82ca0f117b
Post-review cleanup of Phase 4. Closes Finding #9 properly and corrects the Finding #13 documentation lie surfaced in the code-review report. Capability schema: - Replace `AgentOverridable bool` with `AgentOverridableAs string` on ParamSchema. Empty string = not overridable; non-empty = the generic key alias (`"speed"`, `"emotion"`, `"style"`). - Each provider declaration now carries the alias inline, so the generic↔native mapping has a single TS-readable source. Frontend: - Web `tts-override-block.tsx` drops the inline `GENERIC_TO_NATIVE` literal and derives the bidirectional adapter from the filtered capability params (each param self-describes its alias). Adapter tests rewritten around the new shape. - Desktop `AgentDetailPanel.tsx` drops the 45-line inline IIFE in favour of a new `<TtsOverrideFineTune>` component that uses the same alias-based mapping. Backend: - Move `AgentTTSParamsAllowedKeys` + `ValidateAgentTTSParams` to `internal/audio/agent_params_adapter.go`. HTTP `validate.go` and WS `gateway/methods/agents_update.go` both delegate, eliminating the duplicated `{speed, emotion, style}` literal. Cleanup: - Delete orphan i18n keys `MsgTtsParamInvalidJSON` and `MsgTtsParamDependsOn` from `keys.go` + en/vi/zh catalogs (no in-code references; DependsOn is FE-only, JSON parse failures already surface via slog). Documentation: - `prompt-settings-section.tsx` Finding #13 comment rewritten to honestly describe the best-effort merge into a fresh local copy of the cached `otherConfig` prop. Concurrent-tab clobber remains possible — server-side JSON-merge-patch endpoint planned for v2. Tests: 9 backend suites (race), web 217/217, desktop build clean, both Go build tags pass.
89 lines
2.5 KiB
Go
89 lines
2.5 KiB
Go
package openai
|
|
|
|
import "github.com/nextlevelbuilder/goclaw/internal/audio"
|
|
|
|
// openAIModels is the static allowlist of supported OpenAI TTS models.
|
|
var openAIModels = []string{
|
|
"tts-1",
|
|
"tts-1-hd",
|
|
"gpt-4o-mini-tts",
|
|
}
|
|
|
|
// openAIVoices is the full 13-voice catalog. tts-1/tts-1-hd support only 9
|
|
// (ballad/verse/marin/cedar are gpt-4o-mini-tts only), but backend accepts any
|
|
// voice ID — model-compatibility is surfaced as UI help text only.
|
|
var openAIVoices = []audio.VoiceOption{
|
|
{VoiceID: "alloy", Name: "Alloy"},
|
|
{VoiceID: "ash", Name: "Ash"},
|
|
{VoiceID: "ballad", Name: "Ballad"},
|
|
{VoiceID: "coral", Name: "Coral"},
|
|
{VoiceID: "echo", Name: "Echo"},
|
|
{VoiceID: "fable", Name: "Fable"},
|
|
{VoiceID: "onyx", Name: "Onyx"},
|
|
{VoiceID: "nova", Name: "Nova"},
|
|
{VoiceID: "sage", Name: "Sage"},
|
|
{VoiceID: "shimmer", Name: "Shimmer"},
|
|
{VoiceID: "verse", Name: "Verse"},
|
|
{VoiceID: "marin", Name: "Marin"},
|
|
{VoiceID: "cedar", Name: "Cedar"},
|
|
}
|
|
|
|
var (
|
|
speedMin = 0.25
|
|
speedMax = 4.0
|
|
speedStep = 0.05
|
|
)
|
|
|
|
// openAIParams is the enriched param schema for OpenAI TTS.
|
|
// Defaults MUST match the hardcoded values in tts.go (characterization fixture).
|
|
var openAIParams = []audio.ParamSchema{
|
|
{
|
|
Key: "speed",
|
|
Type: audio.ParamTypeRange,
|
|
Label: "Speed",
|
|
Description: "Speech speed multiplier (0.25 = slowest, 4.0 = fastest).",
|
|
Default: 1.0,
|
|
Min: &speedMin,
|
|
Max: &speedMax,
|
|
Step: &speedStep,
|
|
AgentOverridableAs: "speed",
|
|
},
|
|
{
|
|
Key: "response_format",
|
|
Type: audio.ParamTypeEnum,
|
|
Label: "Output Format",
|
|
Default: "mp3",
|
|
Enum: []audio.EnumOption{
|
|
{Value: "mp3", Label: "MP3"},
|
|
{Value: "opus", Label: "Opus"},
|
|
{Value: "aac", Label: "AAC"},
|
|
{Value: "flac", Label: "FLAC"},
|
|
{Value: "wav", Label: "WAV"},
|
|
{Value: "pcm", Label: "PCM"},
|
|
},
|
|
},
|
|
{
|
|
Key: "instructions",
|
|
Type: audio.ParamTypeText,
|
|
Label: "Instructions",
|
|
Description: "System-level style prompt (gpt-4o-mini-tts only). Advanced.",
|
|
Default: "",
|
|
Group: "advanced",
|
|
DependsOn: []audio.Dependency{
|
|
{Field: "model", Op: "eq", Value: "gpt-4o-mini-tts"},
|
|
},
|
|
},
|
|
}
|
|
|
|
// Capabilities returns the full capability schema for the OpenAI TTS provider.
|
|
func (p *Provider) Capabilities() audio.ProviderCapabilities {
|
|
return audio.ProviderCapabilities{
|
|
Provider: "openai",
|
|
DisplayName: "OpenAI TTS",
|
|
RequiresAPIKey: true,
|
|
Models: openAIModels,
|
|
Voices: openAIVoices,
|
|
Params: openAIParams,
|
|
}
|
|
}
|