nyrn
/
openclaw
mirror of https://github.com/openclaw/openclaw.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

refactor: require legacy config migration on read

This commit is contained in:
Peter Steinberger 2026-03-26 23:22:35 +00:00
parent cad83db8b2
commit 01bcbcf8d5
No known key found for this signature in database
18 changed files with 276 additions and 359 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@ -21,6 +21,7 @@ Docs: https://docs.openclaw.ai
- Agents/compaction: surface safeguard-specific cancel reasons and relabel benign manual `/compact` no-op cases as skipped instead of failed. (#51072) Thanks @afurm.
- Plugins/CLI backends: move bundled Claude CLI, Codex CLI, and Gemini CLI inference defaults onto the plugin surface, add bundled Gemini CLI backend support, and replace `gateway run --claude-cli-logs` with generic `--cli-backend-logs` while keeping the old flag as a compatibility alias.
- Plugins/startup: auto-load bundled provider and CLI-backend plugins from explicit config refs, so bundled Claude CLI, Codex CLI, and Gemini CLI message-provider setups no longer need manual `plugins.allow` entries.
- Config/TTS: auto-migrate legacy speech config on normal reads and secret resolution, keep legacy diagnostics for Doctor, and remove regular-mode runtime fallback for old bundled `tts.<provider>` API-key shapes.
### Fixes

108
docs/tools/tts.md
View File

@ -15,7 +15,7 @@ It works anywhere OpenClaw can send audio.
## Supported services
- **ElevenLabs** (primary or fallback provider)
- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`, default when no API keys)
- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`)
- **OpenAI** (primary or fallback provider; also used for summaries)
### Microsoft speech notes
@ -38,9 +38,7 @@ If you want OpenAI or ElevenLabs:
- `ELEVENLABS_API_KEY` (or `XI_API_KEY`)
- `OPENAI_API_KEY`
Microsoft speech does **not** require an API key. If no API keys are found,
OpenClaw defaults to Microsoft (unless disabled via
`messages.tts.microsoft.enabled=false` or `messages.tts.edge.enabled=false`).
Microsoft speech does **not** require an API key.
If multiple providers are configured, the selected provider is used first and the others are fallback options.
Auto-summary uses the configured `summaryModel` (or `agents.defaults.model.primary`),
@ -60,8 +58,8 @@ so that provider must also be authenticated if you enable summaries.
No. Auto‑TTS is **off** by default. Enable it in config with
`messages.tts.auto` or per session with `/tts always` (alias: `/tts on`).
Microsoft speech **is** enabled by default once TTS is on, and is used automatically
when no OpenAI or ElevenLabs API keys are available.
When `messages.tts.provider` is unset, OpenClaw picks the first configured
speech provider in registry auto-select order.
## Config
@ -93,26 +91,28 @@ Full schema is in [Gateway configuration](/gateway/configuration).
modelOverrides: {
enabled: true,
},
openai: {
apiKey: "openai_api_key",
baseUrl: "https://api.openai.com/v1",
model: "gpt-4o-mini-tts",
voice: "alloy",
},
elevenlabs: {
apiKey: "elevenlabs_api_key",
baseUrl: "https://api.elevenlabs.io",
voiceId: "voice_id",
modelId: "eleven_multilingual_v2",
seed: 42,
applyTextNormalization: "auto",
languageCode: "en",
voiceSettings: {
stability: 0.5,
similarityBoost: 0.75,
style: 0.0,
useSpeakerBoost: true,
speed: 1.0,
providers: {
openai: {
apiKey: "openai_api_key",
baseUrl: "https://api.openai.com/v1",
model: "gpt-4o-mini-tts",
voice: "alloy",
},
elevenlabs: {
apiKey: "elevenlabs_api_key",
baseUrl: "https://api.elevenlabs.io",
voiceId: "voice_id",
modelId: "eleven_multilingual_v2",
seed: 42,
applyTextNormalization: "auto",
languageCode: "en",
voiceSettings: {
stability: 0.5,
similarityBoost: 0.75,
style: 0.0,
useSpeakerBoost: true,
speed: 1.0,
},
},
},
},
@ -128,13 +128,15 @@ Full schema is in [Gateway configuration](/gateway/configuration).
tts: {
auto: "always",
provider: "microsoft",
microsoft: {
enabled: true,
voice: "en-US-MichelleNeural",
lang: "en-US",
outputFormat: "audio-24khz-48kbitrate-mono-mp3",
rate: "+10%",
pitch: "-5%",
providers: {
microsoft: {
enabled: true,
voice: "en-US-MichelleNeural",
lang: "en-US",
outputFormat: "audio-24khz-48kbitrate-mono-mp3",
rate: "+10%",
pitch: "-5%",
},
},
},
},
@ -147,8 +149,10 @@ Full schema is in [Gateway configuration](/gateway/configuration).
{
messages: {
tts: {
microsoft: {
enabled: false,
providers: {
microsoft: {
enabled: false,
},
},
},
},
@ -208,37 +212,37 @@ Then run:
- `enabled`: legacy toggle (doctor migrates this to `auto`).
- `mode`: `"final"` (default) or `"all"` (includes tool/block replies).
- `provider`: speech provider id such as `"elevenlabs"`, `"microsoft"`, or `"openai"` (fallback is automatic).
- If `provider` is **unset**, OpenClaw prefers `openai` (if key), then `elevenlabs` (if key),
otherwise `microsoft`.
- If `provider` is **unset**, OpenClaw uses the first configured speech provider in registry auto-select order.
- Legacy `provider: "edge"` still works and is normalized to `microsoft`.
- `summaryModel`: optional cheap model for auto-summary; defaults to `agents.defaults.model.primary`.
- Accepts `provider/model` or a configured model alias.
- `modelOverrides`: allow the model to emit TTS directives (on by default).
- `allowProvider` defaults to `false` (provider switching is opt-in).
- `providers.<id>`: provider-owned settings keyed by speech provider id.
- `maxTextLength`: hard cap for TTS input (chars). `/tts audio` fails if exceeded.
- `timeoutMs`: request timeout (ms).
- `prefsPath`: override the local prefs JSON path (provider/limit/summary).
- `apiKey` values fall back to env vars (`ELEVENLABS_API_KEY`/`XI_API_KEY`, `OPENAI_API_KEY`).
- `elevenlabs.baseUrl`: override ElevenLabs API base URL.
- `openai.baseUrl`: override the OpenAI TTS endpoint.
- Resolution order: `messages.tts.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
- `providers.elevenlabs.baseUrl`: override ElevenLabs API base URL.
- `providers.openai.baseUrl`: override the OpenAI TTS endpoint.
- Resolution order: `messages.tts.providers.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
- Non-default values are treated as OpenAI-compatible TTS endpoints, so custom model and voice names are accepted.
- `elevenlabs.voiceSettings`:
- `providers.elevenlabs.voiceSettings`:
- `stability`, `similarityBoost`, `style`: `0..1`
- `useSpeakerBoost`: `true|false`
- `speed`: `0.5..2.0` (1.0 = normal)
- `elevenlabs.applyTextNormalization`: `auto|on|off`
- `elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
- `elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
- `microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
- `microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
- `microsoft.lang`: language code (e.g. `en-US`).
- `microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
- `providers.elevenlabs.applyTextNormalization`: `auto|on|off`
- `providers.elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
- `providers.elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
- `providers.microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
- `providers.microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
- `providers.microsoft.lang`: language code (e.g. `en-US`).
- `providers.microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
- See Microsoft Speech output formats for valid values; not all formats are supported by the bundled Edge-backed transport.
- `microsoft.rate` / `microsoft.pitch` / `microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
- `microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
- `microsoft.proxy`: proxy URL for Microsoft speech requests.
- `microsoft.timeoutMs`: request timeout override (ms).
- `providers.microsoft.rate` / `providers.microsoft.pitch` / `providers.microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
- `providers.microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
- `providers.microsoft.proxy`: proxy URL for Microsoft speech requests.
- `providers.microsoft.timeoutMs`: request timeout override (ms).
- `edge.*`: legacy alias for the same Microsoft settings.
## Model-driven overrides (default on)

108
docs/tts.md
View File

@ -15,7 +15,7 @@ It works anywhere OpenClaw can send audio.
## Supported services
- **ElevenLabs** (primary or fallback provider)
- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`, default when no API keys)
- **Microsoft** (primary or fallback provider; current bundled implementation uses `node-edge-tts`)
- **OpenAI** (primary or fallback provider; also used for summaries)
### Microsoft speech notes
@ -38,9 +38,7 @@ If you want OpenAI or ElevenLabs:
- `ELEVENLABS_API_KEY` (or `XI_API_KEY`)
- `OPENAI_API_KEY`
Microsoft speech does **not** require an API key. If no API keys are found,
OpenClaw defaults to Microsoft (unless disabled via
`messages.tts.microsoft.enabled=false` or `messages.tts.edge.enabled=false`).
Microsoft speech does **not** require an API key.
If multiple providers are configured, the selected provider is used first and the others are fallback options.
Auto-summary uses the configured `summaryModel` (or `agents.defaults.model.primary`),
@ -60,8 +58,8 @@ so that provider must also be authenticated if you enable summaries.
No. Auto‑TTS is **off** by default. Enable it in config with
`messages.tts.auto` or per session with `/tts always` (alias: `/tts on`).
Microsoft speech **is** enabled by default once TTS is on, and is used automatically
when no OpenAI or ElevenLabs API keys are available.
When `messages.tts.provider` is unset, OpenClaw picks the first configured
speech provider in registry auto-select order.
## Config
@ -93,26 +91,28 @@ Full schema is in [Gateway configuration](/gateway/configuration).
modelOverrides: {
enabled: true,
},
openai: {
apiKey: "openai_api_key",
baseUrl: "https://api.openai.com/v1",
model: "gpt-4o-mini-tts",
voice: "alloy",
},
elevenlabs: {
apiKey: "elevenlabs_api_key",
baseUrl: "https://api.elevenlabs.io",
voiceId: "voice_id",
modelId: "eleven_multilingual_v2",
seed: 42,
applyTextNormalization: "auto",
languageCode: "en",
voiceSettings: {
stability: 0.5,
similarityBoost: 0.75,
style: 0.0,
useSpeakerBoost: true,
speed: 1.0,
providers: {
openai: {
apiKey: "openai_api_key",
baseUrl: "https://api.openai.com/v1",
model: "gpt-4o-mini-tts",
voice: "alloy",
},
elevenlabs: {
apiKey: "elevenlabs_api_key",
baseUrl: "https://api.elevenlabs.io",
voiceId: "voice_id",
modelId: "eleven_multilingual_v2",
seed: 42,
applyTextNormalization: "auto",
languageCode: "en",
voiceSettings: {
stability: 0.5,
similarityBoost: 0.75,
style: 0.0,
useSpeakerBoost: true,
speed: 1.0,
},
},
},
},
@ -128,13 +128,15 @@ Full schema is in [Gateway configuration](/gateway/configuration).
tts: {
auto: "always",
provider: "microsoft",
microsoft: {
enabled: true,
voice: "en-US-MichelleNeural",
lang: "en-US",
outputFormat: "audio-24khz-48kbitrate-mono-mp3",
rate: "+10%",
pitch: "-5%",
providers: {
microsoft: {
enabled: true,
voice: "en-US-MichelleNeural",
lang: "en-US",
outputFormat: "audio-24khz-48kbitrate-mono-mp3",
rate: "+10%",
pitch: "-5%",
},
},
},
},
@ -147,8 +149,10 @@ Full schema is in [Gateway configuration](/gateway/configuration).
{
messages: {
tts: {
microsoft: {
enabled: false,
providers: {
microsoft: {
enabled: false,
},
},
},
},
@ -208,37 +212,37 @@ Then run:
- `enabled`: legacy toggle (doctor migrates this to `auto`).
- `mode`: `"final"` (default) or `"all"` (includes tool/block replies).
- `provider`: speech provider id such as `"elevenlabs"`, `"microsoft"`, or `"openai"` (fallback is automatic).
- If `provider` is **unset**, OpenClaw prefers `openai` (if key), then `elevenlabs` (if key),
otherwise `microsoft`.
- If `provider` is **unset**, OpenClaw uses the first configured speech provider in registry auto-select order.
- Legacy `provider: "edge"` still works and is normalized to `microsoft`.
- `summaryModel`: optional cheap model for auto-summary; defaults to `agents.defaults.model.primary`.
- Accepts `provider/model` or a configured model alias.
- `modelOverrides`: allow the model to emit TTS directives (on by default).
- `allowProvider` defaults to `false` (provider switching is opt-in).
- `providers.<id>`: provider-owned settings keyed by speech provider id.
- `maxTextLength`: hard cap for TTS input (chars). `/tts audio` fails if exceeded.
- `timeoutMs`: request timeout (ms).
- `prefsPath`: override the local prefs JSON path (provider/limit/summary).
- `apiKey` values fall back to env vars (`ELEVENLABS_API_KEY`/`XI_API_KEY`, `OPENAI_API_KEY`).
- `elevenlabs.baseUrl`: override ElevenLabs API base URL.
- `openai.baseUrl`: override the OpenAI TTS endpoint.
- Resolution order: `messages.tts.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
- `providers.elevenlabs.baseUrl`: override ElevenLabs API base URL.
- `providers.openai.baseUrl`: override the OpenAI TTS endpoint.
- Resolution order: `messages.tts.providers.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
- Non-default values are treated as OpenAI-compatible TTS endpoints, so custom model and voice names are accepted.
- `elevenlabs.voiceSettings`:
- `providers.elevenlabs.voiceSettings`:
- `stability`, `similarityBoost`, `style`: `0..1`
- `useSpeakerBoost`: `true|false`
- `speed`: `0.5..2.0` (1.0 = normal)
- `elevenlabs.applyTextNormalization`: `auto|on|off`
- `elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
- `elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
- `microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
- `microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
- `microsoft.lang`: language code (e.g. `en-US`).
- `microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
- `providers.elevenlabs.applyTextNormalization`: `auto|on|off`
- `providers.elevenlabs.languageCode`: 2-letter ISO 639-1 (e.g. `en`, `de`)
- `providers.elevenlabs.seed`: integer `0..4294967295` (best-effort determinism)
- `providers.microsoft.enabled`: allow Microsoft speech usage (default `true`; no API key).
- `providers.microsoft.voice`: Microsoft neural voice name (e.g. `en-US-MichelleNeural`).
- `providers.microsoft.lang`: language code (e.g. `en-US`).
- `providers.microsoft.outputFormat`: Microsoft output format (e.g. `audio-24khz-48kbitrate-mono-mp3`).
- See Microsoft Speech output formats for valid values; not all formats are supported by the bundled Edge-backed transport.
- `microsoft.rate` / `microsoft.pitch` / `microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
- `microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
- `microsoft.proxy`: proxy URL for Microsoft speech requests.
- `microsoft.timeoutMs`: request timeout override (ms).
- `providers.microsoft.rate` / `providers.microsoft.pitch` / `providers.microsoft.volume`: percent strings (e.g. `+10%`, `-5%`).
- `providers.microsoft.saveSubtitles`: write JSON subtitles alongside the audio file.
- `providers.microsoft.proxy`: proxy URL for Microsoft speech requests.
- `providers.microsoft.timeoutMs`: request timeout override (ms).
- `edge.*`: legacy alias for the same Microsoft settings.
## Model-driven overrides (default on)

5
src/commands/doctor-legacy-config.migrations.test.ts
View File

@ -523,7 +523,6 @@ describe("normalizeCompatibilityConfigValues", () => {
});
expect(res.config.talk).toEqual({
provider: "elevenlabs",
providers: {
elevenlabs: {
voiceId: "voice-123",
@ -545,9 +544,7 @@ describe("normalizeCompatibilityConfigValues", () => {
interruptOnSpeech: false,
silenceTimeoutMs: 1500,
});
expect(res.changes).toEqual([
"Moved legacy talk flat fields → talk.provider/talk.providers.elevenlabs.",
]);
expect(res.changes).toEqual(["Moved legacy talk flat fields → talk.providers.elevenlabs."]);
});
it("normalizes talk provider ids without overriding explicit provider config", () => {

6
src/commands/doctor-legacy-config.ts
View File

@ -11,7 +11,7 @@ import {
resolveTelegramPreviewStreamMode,
} from "../config/discord-preview-streaming.js";
import { migrateLegacyWebSearchConfig } from "../config/legacy-web-search.js";
import { DEFAULT_TALK_PROVIDER, normalizeTalkSection } from "../config/talk.js";
import { LEGACY_TALK_PROVIDER_ID, normalizeTalkSection } from "../config/talk.js";
import { DEFAULT_GOOGLE_API_BASE_URL } from "../infra/google-api-base-url.js";
import { DEFAULT_ACCOUNT_ID } from "../routing/session-key.js";
@ -651,9 +651,7 @@ export function normalizeCompatibilityConfigValues(cfg: OpenClawConfig): {
return;
}
changes.push(
`Moved legacy talk flat fields → talk.provider/talk.providers.${DEFAULT_TALK_PROVIDER}.`,
);
changes.push(`Moved legacy talk flat fields → talk.providers.${LEGACY_TALK_PROVIDER_ID}.`);
};
const normalizeLegacyCrossContextMessageConfig = () => {

4
src/config/config-misc.test.ts
View File

@ -482,7 +482,7 @@ describe("config strict validation", () => {
const snap = await readConfigFileSnapshot();
expect(snap.valid).toBe(false);
expect(snap.valid).toBe(true);
expect(snap.legacyIssues).not.toHaveLength(0);
});
});
@ -517,7 +517,7 @@ describe("config strict validation", () => {
});
const snap = await readConfigFileSnapshot();
expect(snap.valid).toBe(false);
expect(snap.valid).toBe(true);
expect(snap.legacyIssues.some((issue) => issue.path === "gateway.bind")).toBe(true);
});
});

8
src/config/config.legacy-config-detection.accepts-imessage-dmpolicy.test.ts
View File

@ -68,7 +68,7 @@ function expectRoutingAllowFromLegacySnapshot(
ctx: { snapshot: ConfigSnapshot; parsed: unknown },
expectedAllowFrom: string[],
) {
expect(ctx.snapshot.valid).toBe(false);
expect(ctx.snapshot.valid).toBe(true);
expect(ctx.snapshot.legacyIssues.some((issue) => issue.path === "routing.allowFrom")).toBe(true);
const parsed = ctx.parsed as {
routing?: { allowFrom?: string[] };
@ -269,7 +269,7 @@ describe("legacy config detection", () => {
await withSnapshotForConfig(
{ memorySearch: { provider: "local", fallback: "none" } },
async (ctx) => {
expect(ctx.snapshot.valid).toBe(false);
expect(ctx.snapshot.valid).toBe(true);
expect(ctx.snapshot.legacyIssues.some((issue) => issue.path === "memorySearch")).toBe(true);
},
);
@ -278,14 +278,14 @@ describe("legacy config detection", () => {
await withSnapshotForConfig(
{ heartbeat: { model: "anthropic/claude-3-5-haiku-20241022", every: "30m" } },
async (ctx) => {
expect(ctx.snapshot.valid).toBe(false);
expect(ctx.snapshot.valid).toBe(true);
expect(ctx.snapshot.legacyIssues.some((issue) => issue.path === "heartbeat")).toBe(true);
},
);
});
it("flags legacy provider sections in snapshot", async () => {
await withSnapshotForConfig({ whatsapp: { allowFrom: ["+1555"] } }, async (ctx) => {
expect(ctx.snapshot.valid).toBe(false);
expect(ctx.snapshot.valid).toBe(true);
expect(ctx.snapshot.legacyIssues.some((issue) => issue.path === "whatsapp")).toBe(true);
const parsed = ctx.parsed as {

7
src/config/defaults.ts
View File

@ -3,7 +3,7 @@ import { normalizeProviderId, parseModelRef } from "../agents/model-selection.js
import { DEFAULT_AGENT_MAX_CONCURRENT, DEFAULT_SUBAGENT_MAX_CONCURRENT } from "./agent-limits.js";
import { resolveAgentModelPrimaryValue } from "./model-input.js";
import {
DEFAULT_TALK_PROVIDER,
LEGACY_TALK_PROVIDER_ID,
normalizeTalkConfig,
resolveActiveTalkProviderConfig,
resolveTalkApiKey,
@ -204,7 +204,7 @@ export function applyTalkApiKey(config: OpenClawConfig): OpenClawConfig {
const talk = normalized.talk;
const active = resolveActiveTalkProviderConfig(talk);
if (active?.provider && active.provider !== DEFAULT_TALK_PROVIDER) {
if (!active || active.provider !== LEGACY_TALK_PROVIDER_ID) {
return normalized;
}
@ -214,7 +214,7 @@ export function applyTalkApiKey(config: OpenClawConfig): OpenClawConfig {
return normalized;
}
const providerId = active?.provider ?? DEFAULT_TALK_PROVIDER;
const providerId = active.provider;
const providers = { ...talk?.providers };
const providerConfig = { ...providers[providerId], apiKey: resolved };
providers[providerId] = providerConfig;
@ -222,7 +222,6 @@ export function applyTalkApiKey(config: OpenClawConfig): OpenClawConfig {
const nextTalk = {
...talk,
apiKey: resolved,
provider: talk?.provider ?? providerId,
providers,
};

60
src/config/io.ts
View File

@ -41,6 +41,7 @@ import {
readConfigIncludeFileWithGuards,
resolveConfigIncludes,
} from "./includes.js";
import { migrateLegacyConfig } from "./legacy-migrate.js";
import { findLegacyConfigIssues } from "./legacy.js";
import { applyMergePatch } from "./merge-patch.js";
import { normalizeExecSafeBinProfilesInConfig } from "./normalize-exec-safe-bin.js";
@ -1185,6 +1186,11 @@ type ConfigReadResolution = {
envWarnings: EnvSubstitutionWarning[];
};
type LegacyMigrationResolution = {
effectiveConfigRaw: unknown;
sourceLegacyIssues: LegacyConfigIssue[];
};
function resolveConfigIncludesForRead(
parsed: unknown,
configPath: string,
@ -1225,6 +1231,21 @@ function resolveConfigForRead(
};
}
function resolveLegacyConfigForRead(
resolvedConfigRaw: unknown,
sourceRaw: unknown,
): LegacyMigrationResolution {
const sourceLegacyIssues = findLegacyConfigIssues(resolvedConfigRaw, sourceRaw);
if (sourceLegacyIssues.length === 0) {
return { effectiveConfigRaw: resolvedConfigRaw, sourceLegacyIssues };
}
const migrated = migrateLegacyConfig(resolvedConfigRaw);
return {
effectiveConfigRaw: migrated.config ?? resolvedConfigRaw,
sourceLegacyIssues,
};
}
type ReadConfigFileSnapshotInternalResult = {
snapshot: ConfigFileSnapshot;
envSnapshotForRestore?: Record<string, string | undefined>;
@ -1275,13 +1296,15 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
deps.env,
);
const resolvedConfig = readResolution.resolvedConfigRaw;
const legacyResolution = resolveLegacyConfigForRead(resolvedConfig, parsed);
const effectiveConfigRaw = legacyResolution.effectiveConfigRaw;
for (const w of readResolution.envWarnings) {
deps.logger.warn(
`Config (${configPath}): missing env var "${w.varName}" at ${w.configPath} — feature using this value will be unavailable`,
);
}
warnOnConfigMiskeys(resolvedConfig, deps.logger);
if (typeof resolvedConfig !== "object" || resolvedConfig === null) {
warnOnConfigMiskeys(effectiveConfigRaw, deps.logger);
if (typeof effectiveConfigRaw !== "object" || effectiveConfigRaw === null) {
observeLoadConfigSnapshot({
path: configPath,
exists: true,
@ -1293,31 +1316,31 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
hash,
issues: [],
warnings: [],
legacyIssues: [],
legacyIssues: legacyResolution.sourceLegacyIssues,
});
return {};
}
const preValidationDuplicates = findDuplicateAgentDirs(resolvedConfig as OpenClawConfig, {
const preValidationDuplicates = findDuplicateAgentDirs(effectiveConfigRaw as OpenClawConfig, {
env: deps.env,
homedir: deps.homedir,
});
if (preValidationDuplicates.length > 0) {
throw new DuplicateAgentDirError(preValidationDuplicates);
}
const validated = validateConfigObjectWithPlugins(resolvedConfig, { env: deps.env });
const validated = validateConfigObjectWithPlugins(effectiveConfigRaw, { env: deps.env });
if (!validated.ok) {
observeLoadConfigSnapshot({
path: configPath,
exists: true,
raw,
parsed,
resolved: coerceConfig(resolvedConfig),
resolved: coerceConfig(effectiveConfigRaw),
valid: false,
config: coerceConfig(resolvedConfig),
config: coerceConfig(effectiveConfigRaw),
hash,
issues: validated.issues,
warnings: validated.warnings,
legacyIssues: findLegacyConfigIssues(resolvedConfig, parsed),
legacyIssues: legacyResolution.sourceLegacyIssues,
});
const details = validated.issues
.map(
@ -1362,13 +1385,13 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
exists: true,
raw,
parsed,
resolved: coerceConfig(resolvedConfig),
resolved: coerceConfig(effectiveConfigRaw),
valid: true,
config: cfg,
hash,
issues: [],
warnings: validated.warnings,
legacyIssues: findLegacyConfigIssues(resolvedConfig, parsed),
legacyIssues: legacyResolution.sourceLegacyIssues,
});
const duplicates = findDuplicateAgentDirs(cfg, {
@ -1536,11 +1559,10 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
}));
const resolvedConfigRaw = readResolution.resolvedConfigRaw;
// Detect legacy keys on resolved config, but only mark source-literal legacy
// entries (for auto-migration) when they are present in the parsed source.
const legacyIssues = findLegacyConfigIssues(resolvedConfigRaw, parsedRes.parsed);
const legacyResolution = resolveLegacyConfigForRead(resolvedConfigRaw, parsedRes.parsed);
const effectiveConfigRaw = legacyResolution.effectiveConfigRaw;
const validated = validateConfigObjectWithPlugins(resolvedConfigRaw, { env: deps.env });
const validated = validateConfigObjectWithPlugins(effectiveConfigRaw, { env: deps.env });
if (!validated.ok) {
return await finalizeReadConfigSnapshotInternalResult(deps, {
snapshot: {
@ -1548,13 +1570,13 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
exists: true,
raw,
parsed: parsedRes.parsed,
resolved: coerceConfig(resolvedConfigRaw),
resolved: coerceConfig(effectiveConfigRaw),
valid: false,
config: coerceConfig(resolvedConfigRaw),
config: coerceConfig(effectiveConfigRaw),
hash,
issues: validated.issues,
warnings: [...validated.warnings, ...envVarWarnings],
legacyIssues,
legacyIssues: legacyResolution.sourceLegacyIssues,
},
});
}
@ -1580,13 +1602,13 @@ export function createConfigIO(overrides: ConfigIoDeps = {}) {
parsed: parsedRes.parsed,
// Use resolvedConfigRaw (after $include and ${ENV} substitution but BEFORE runtime defaults)
// for config set/unset operations (issue #6070)
resolved: coerceConfig(resolvedConfigRaw),
resolved: coerceConfig(effectiveConfigRaw),
valid: true,
config: snapshotConfig,
hash,
issues: [],
warnings: [...validated.warnings, ...envVarWarnings],
legacyIssues,
legacyIssues: legacyResolution.sourceLegacyIssues,
},
envSnapshotForRestore: readResolution.envSnapshotForRestore,
});

3
src/config/talk.normalize.test.ts
View File

@ -36,7 +36,6 @@ describe("talk normalization", () => {
});
expect(normalized).toEqual({
provider: "elevenlabs",
providers: {
elevenlabs: {
voiceId: "voice-123",
@ -149,7 +148,7 @@ describe("talk normalization", () => {
async (configPath) => {
const io = createConfigIO({ configPath });
const snapshot = await io.readConfigFileSnapshot();
expect(snapshot.config.talk?.provider).toBe("elevenlabs");
expect(snapshot.config.talk?.provider).toBeUndefined();
expect(snapshot.config.talk?.providers?.elevenlabs?.voiceId).toBe("voice-123");
expect(snapshot.config.talk?.providers?.elevenlabs?.apiKey).toBe(elevenLabsApiKey);
expect(snapshot.config.talk?.apiKey).toBe(elevenLabsApiKey);

10
src/config/talk.ts
View File

@ -16,7 +16,7 @@ type TalkApiKeyDeps = {
path?: typeof path;
};
export const DEFAULT_TALK_PROVIDER = "elevenlabs";
export const LEGACY_TALK_PROVIDER_ID = "elevenlabs";
function isPlainObject(value: unknown): value is Record<string, unknown> {
return typeof value === "object" && value !== null && !Array.isArray(value);
@ -225,19 +225,13 @@ export function normalizeTalkSection(value: TalkConfig | undefined): TalkConfig
}
if (provider) {
normalized.provider = provider;
} else if (providers) {
const ids = Object.keys(providers);
if (ids.length === 1) {
normalized.provider = ids[0];
}
}
return Object.keys(normalized).length > 0 ? normalized : undefined;
}
const legacyProviderConfig = legacyProviderConfigFromTalk(source);
if (legacyProviderConfig) {
normalized.provider = DEFAULT_TALK_PROVIDER;
normalized.providers = { [DEFAULT_TALK_PROVIDER]: legacyProviderConfig };
normalized.providers = { [LEGACY_TALK_PROVIDER_ID]: legacyProviderConfig };
}
return Object.keys(normalized).length > 0 ? normalized : undefined;
}

41
src/config/types.tts.ts
View File

@ -27,22 +27,8 @@ export type TtsModelOverrideConfig = {
export type TtsProviderConfigMap = Record<string, Record<string, unknown>>;
export type TtsConfig = {
/** Auto-TTS mode (preferred). */
auto?: TtsAutoMode;
/** Legacy: enable auto-TTS when `auto` is not set. */
enabled?: boolean;
/** Apply TTS to final replies only or to all replies (tool/block/final). */
mode?: TtsMode;
/** Primary TTS provider (fallbacks are automatic). */
provider?: TtsProvider;
/** Optional model override for TTS auto-summary (provider/model or alias). */
summaryModel?: string;
/** Allow the model to override TTS parameters. */
modelOverrides?: TtsModelOverrideConfig;
/** Provider-specific TTS settings keyed by speech provider id. */
providers?: TtsProviderConfigMap;
/** ElevenLabs configuration. */
export type LegacyTtsConfigCompat = {
/** Legacy ElevenLabs configuration. Prefer providers.elevenlabs. */
elevenlabs?: {
apiKey?: SecretInput;
baseUrl?: string;
@ -59,7 +45,7 @@ export type TtsConfig = {
speed?: number;
};
};
/** OpenAI configuration. */
/** Legacy OpenAI configuration. Prefer providers.openai. */
openai?: {
apiKey?: SecretInput;
baseUrl?: string;
@ -70,7 +56,7 @@ export type TtsConfig = {
/** System-level instructions for the TTS model (gpt-4o-mini-tts only). */
instructions?: string;
};
/** Legacy alias for Microsoft speech configuration. */
/** Legacy alias for Microsoft speech configuration. Prefer providers.microsoft. */
edge?: {
/** Explicitly allow Microsoft speech usage (no API key required). */
enabled?: boolean;
@ -84,7 +70,7 @@ export type TtsConfig = {
proxy?: string;
timeoutMs?: number;
};
/** Preferred alias for Microsoft speech configuration. */
/** Legacy Microsoft speech configuration. Prefer providers.microsoft. */
microsoft?: {
enabled?: boolean;
voice?: string;
@ -97,6 +83,23 @@ export type TtsConfig = {
proxy?: string;
timeoutMs?: number;
};
};
export type TtsConfig = LegacyTtsConfigCompat & {
/** Auto-TTS mode (preferred). */
auto?: TtsAutoMode;
/** Legacy: enable auto-TTS when `auto` is not set. */
enabled?: boolean;
/** Apply TTS to final replies only or to all replies (tool/block/final). */
mode?: TtsMode;
/** Primary TTS provider (fallbacks are automatic). */
provider?: TtsProvider;
/** Optional model override for TTS auto-summary (provider/model or alias). */
summaryModel?: string;
/** Allow the model to override TTS parameters. */
modelOverrides?: TtsModelOverrideConfig;
/** Provider-specific TTS settings keyed by speech provider id. */
providers?: TtsProviderConfigMap;
/** Optional path for local TTS user preferences JSON. */
prefsPath?: string;
/** Hard cap for text sent to TTS (chars). */

21
src/secrets/runtime-config-collectors-tts.ts
View File

@ -54,25 +54,4 @@ export function collectTtsApiKeyAssignments(params: {
}
return;
}
// Legacy compatibility until migrated configs have been rewritten on disk.
const legacyProviders = ["elevenlabs", "openai"] as const;
for (const providerId of legacyProviders) {
const providerConfig = params.tts[providerId];
if (!isRecord(providerConfig)) {
continue;
}
collectSecretInputAssignment({
value: providerConfig.apiKey,
path: `${params.pathPrefix}.${providerId}.apiKey`,
expected: "string",
defaults: params.defaults,
context: params.context,
active: params.active,
inactiveReason: params.inactiveReason,
apply: (value) => {
providerConfig.apiKey = value;
},
});
}
}

101
src/secrets/runtime.test.ts
View File

@ -1949,20 +1949,22 @@ describe("secrets runtime snapshot", () => {
loadAuthStore: () => ({ version: 1, profiles: {} }),
});
expect(snapshot.config.channels?.discord?.voice?.tts?.openai?.apiKey).toEqual({
expect(snapshot.config.channels?.discord?.voice?.tts?.providers?.openai?.apiKey).toEqual({
source: "env",
provider: "default",
id: "MISSING_DISCORD_VOICE_TTS_OPENAI",
});
expect(snapshot.config.channels?.discord?.accounts?.work?.voice?.tts?.openai?.apiKey).toEqual({
expect(
snapshot.config.channels?.discord?.accounts?.work?.voice?.tts?.providers?.openai?.apiKey,
).toEqual({
source: "env",
provider: "default",
id: "MISSING_DISCORD_WORK_VOICE_TTS_OPENAI",
});
expect(snapshot.warnings.map((warning) => warning.path)).toEqual(
expect.arrayContaining([
"channels.discord.voice.tts.openai.apiKey",
"channels.discord.accounts.work.voice.tts.openai.apiKey",
"channels.discord.voice.tts.providers.openai.apiKey",
"channels.discord.accounts.work.voice.tts.providers.openai.apiKey",
]),
);
});
@ -1974,8 +1976,10 @@ describe("secrets runtime snapshot", () => {
discord: {
voice: {
tts: {
openai: {
apiKey: { source: "env", provider: "default", id: "DISCORD_BASE_TTS_OPENAI" },
providers: {
openai: {
apiKey: { source: "env", provider: "default", id: "DISCORD_BASE_TTS_OPENAI" },
},
},
},
},
@ -1990,11 +1994,13 @@ describe("secrets runtime snapshot", () => {
enabled: true,
voice: {
tts: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_OVERRIDE_TTS_OPENAI",
providers: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_OVERRIDE_TTS_OPENAI",
},
},
},
},
@ -2004,11 +2010,13 @@ describe("secrets runtime snapshot", () => {
enabled: false,
voice: {
tts: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_DISABLED_OVERRIDE_TTS_OPENAI",
providers: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_DISABLED_OVERRIDE_TTS_OPENAI",
},
},
},
},
@ -2034,13 +2042,17 @@ describe("secrets runtime snapshot", () => {
loadAuthStore: () => ({ version: 1, profiles: {} }),
});
expect(snapshot.config.channels?.discord?.voice?.tts?.openai?.apiKey).toBe("base-tts-openai");
expect(snapshot.config.channels?.discord?.voice?.tts?.providers?.openai?.apiKey).toBe(
"base-tts-openai",
);
expect(snapshot.config.channels?.discord?.pluralkit?.token).toBe("base-pk-token");
expect(
snapshot.config.channels?.discord?.accounts?.enabledOverride?.voice?.tts?.openai?.apiKey,
snapshot.config.channels?.discord?.accounts?.enabledOverride?.voice?.tts?.providers?.openai
?.apiKey,
).toBe("enabled-override-tts-openai");
expect(
snapshot.config.channels?.discord?.accounts?.disabledOverride?.voice?.tts?.openai?.apiKey,
snapshot.config.channels?.discord?.accounts?.disabledOverride?.voice?.tts?.providers?.openai
?.apiKey,
).toEqual({
source: "env",
provider: "default",
@ -2055,7 +2067,7 @@ describe("secrets runtime snapshot", () => {
);
expect(snapshot.warnings.map((warning) => warning.path)).toEqual(
expect.arrayContaining([
"channels.discord.accounts.disabledOverride.voice.tts.openai.apiKey",
"channels.discord.accounts.disabledOverride.voice.tts.providers.openai.apiKey",
"channels.discord.accounts.disabledOverride.pluralkit.token",
]),
);
@ -2068,11 +2080,13 @@ describe("secrets runtime snapshot", () => {
discord: {
voice: {
tts: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_UNUSED_BASE_TTS_OPENAI",
providers: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_UNUSED_BASE_TTS_OPENAI",
},
},
},
},
@ -2082,11 +2096,13 @@ describe("secrets runtime snapshot", () => {
enabled: true,
voice: {
tts: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_ONLY_TTS_OPENAI",
providers: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_ONLY_TTS_OPENAI",
},
},
},
},
@ -2107,15 +2123,16 @@ describe("secrets runtime snapshot", () => {
});
expect(
snapshot.config.channels?.discord?.accounts?.enabledOverride?.voice?.tts?.openai?.apiKey,
snapshot.config.channels?.discord?.accounts?.enabledOverride?.voice?.tts?.providers?.openai
?.apiKey,
).toBe("enabled-only-tts-openai");
expect(snapshot.config.channels?.discord?.voice?.tts?.openai?.apiKey).toEqual({
expect(snapshot.config.channels?.discord?.voice?.tts?.providers?.openai?.apiKey).toEqual({
source: "env",
provider: "default",
id: "DISCORD_UNUSED_BASE_TTS_OPENAI",
});
expect(snapshot.warnings.map((warning) => warning.path)).toContain(
"channels.discord.voice.tts.openai.apiKey",
"channels.discord.voice.tts.providers.openai.apiKey",
);
});
@ -2127,8 +2144,10 @@ describe("secrets runtime snapshot", () => {
discord: {
voice: {
tts: {
openai: {
apiKey: { source: "env", provider: "default", id: "DISCORD_BASE_TTS_OK" },
providers: {
openai: {
apiKey: { source: "env", provider: "default", id: "DISCORD_BASE_TTS_OK" },
},
},
},
},
@ -2137,11 +2156,13 @@ describe("secrets runtime snapshot", () => {
enabled: true,
voice: {
tts: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_OVERRIDE_TTS_MISSING",
providers: {
openai: {
apiKey: {
source: "env",
provider: "default",
id: "DISCORD_ENABLED_OVERRIDE_TTS_MISSING",
},
},
},
},

5
src/secrets/runtime.ts
View File

@ -12,6 +12,7 @@ import {
setRuntimeConfigSnapshot,
type OpenClawConfig,
} from "../config/config.js";
import { migrateLegacyConfig } from "../config/legacy-migrate.js";
import { resolveUserPath } from "../utils.js";
import {
collectCommandSecretAssignmentsFromSnapshot,
@ -139,7 +140,9 @@ export async function prepareSecretsRuntimeSnapshot(params: {
}): Promise<PreparedSecretsRuntimeSnapshot> {
const runtimeEnv = mergeSecretsRuntimeEnv(params.env);
const sourceConfig = structuredClone(params.config);
const resolvedConfig = structuredClone(params.config);
const resolvedConfig = structuredClone(
migrateLegacyConfig(params.config).config ?? params.config,
);
const context = createResolverContext({
sourceConfig,
env: runtimeEnv,

45
src/tts/directives.ts
View File

@ -4,7 +4,6 @@ import { listSpeechProviders } from "./provider-registry.js";
import type {
SpeechModelOverridePolicy,
SpeechProviderConfig,
SpeechProviderOverrides,
TtsDirectiveOverrides,
TtsDirectiveParseResult,
} from "./provider-types.js";
@ -13,7 +12,6 @@ type ParseTtsDirectiveOptions = {
cfg?: OpenClawConfig;
providers?: readonly SpeechProviderPlugin[];
providerConfigs?: Record<string, SpeechProviderConfig>;
openaiBaseUrl?: string;
};
function buildProviderOrder(left: SpeechProviderPlugin, right: SpeechProviderPlugin): number {
@ -36,49 +34,18 @@ function resolveDirectiveProviderConfig(
provider: SpeechProviderPlugin,
options?: ParseTtsDirectiveOptions,
): SpeechProviderConfig | undefined {
const explicit = options?.providerConfigs?.[provider.id];
if (explicit) {
return explicit;
}
if (provider.id === "openai" && options?.openaiBaseUrl) {
return { baseUrl: options.openaiBaseUrl };
}
return undefined;
}
function mergeProviderOverrides(
target: TtsDirectiveOverrides,
providerId: string,
next: SpeechProviderOverrides,
): void {
target.providerOverrides = {
...target.providerOverrides,
[providerId]: {
...target.providerOverrides?.[providerId],
...next,
},
};
}
function resolveLegacyOptions(
optionsOrOpenaiBaseUrl?: ParseTtsDirectiveOptions | string,
): ParseTtsDirectiveOptions | undefined {
if (typeof optionsOrOpenaiBaseUrl === "string") {
return { openaiBaseUrl: optionsOrOpenaiBaseUrl };
}
return optionsOrOpenaiBaseUrl;
return options?.providerConfigs?.[provider.id];
}
export function parseTtsDirectives(
text: string,
policy: SpeechModelOverridePolicy,
optionsOrOpenaiBaseUrl?: ParseTtsDirectiveOptions | string,
options?: ParseTtsDirectiveOptions,
): TtsDirectiveParseResult {
if (!policy.enabled) {
return { cleanedText: text, overrides: {}, warnings: [], hasDirective: false };
}
const options = resolveLegacyOptions(optionsOrOpenaiBaseUrl);
const providers = resolveDirectiveProviders(options);
const overrides: TtsDirectiveOverrides = {};
const warnings: string[] = [];
@ -135,7 +102,13 @@ export function parseTtsDirectives(
}
handled = true;
if (parsed.overrides) {
mergeProviderOverrides(overrides, provider.id, parsed.overrides);
overrides.providerOverrides = {
...overrides.providerOverrides,
[provider.id]: {
...overrides.providerOverrides?.[provider.id],
...parsed.overrides,
},
};
}
if (parsed.warnings?.length) {
warnings.push(...parsed.warnings);

76
src/tts/tts.test.ts
View File

@ -86,7 +86,6 @@ const {
parseTtsDirectives,
resolveModelOverridePolicy,
summarizeText,
resolveOutputFormat,
getResolvedSpeechProviderConfig,
} = _test;
@ -234,65 +233,6 @@ describe("tts", () => {
});
});
describe("resolveOutputFormat", () => {
it("selects opus for opus channels (telegram/feishu/whatsapp/matrix) and mp3 for others", () => {
const cases = [
{
channel: "telegram",
expected: {
openai: "opus",
elevenlabs: "opus_48000_64",
extension: ".opus",
voiceCompatible: true,
},
},
{
channel: "feishu",
expected: {
openai: "opus",
elevenlabs: "opus_48000_64",
extension: ".opus",
voiceCompatible: true,
},
},
{
channel: "whatsapp",
expected: {
openai: "opus",
elevenlabs: "opus_48000_64",
extension: ".opus",
voiceCompatible: true,
},
},
{
channel: "matrix",
expected: {
openai: "opus",
elevenlabs: "opus_48000_64",
extension: ".opus",
voiceCompatible: true,
},
},
{
channel: "discord",
expected: {
openai: "mp3",
elevenlabs: "mp3_44100_128",
extension: ".mp3",
voiceCompatible: false,
},
},
] as const;
for (const testCase of cases) {
const output = resolveOutputFormat(testCase.channel);
expect(output.openai, testCase.channel).toBe(testCase.expected.openai);
expect(output.elevenlabs, testCase.channel).toBe(testCase.expected.elevenlabs);
expect(output.extension, testCase.channel).toBe(testCase.expected.extension);
expect(output.voiceCompatible, testCase.channel).toBe(testCase.expected.voiceCompatible);
}
});
});
describe("resolveEdgeOutputFormat", () => {
const baseCfg: OpenClawConfig = {
agents: { defaults: { model: { primary: "openai/gpt-4o-mini" } } },
@ -383,9 +323,11 @@ describe("tts", () => {
it("accepts custom voices and models when openaiBaseUrl is a non-default endpoint", () => {
const policy = resolveModelOverridePolicy({ enabled: true });
const input = "Hello [[tts:voice=kokoro-chinese model=kokoro-v1]] world";
const customBaseUrl = "http://localhost:8880/v1";
const result = parseTtsDirectives(input, policy, customBaseUrl);
const result = parseTtsDirectives(input, policy, {
providerConfigs: {
openai: { baseUrl: "http://localhost:8880/v1" },
},
});
const openaiOverrides = result.overrides.providerOverrides?.openai as
| { voice?: string; model?: string }
| undefined;
@ -398,9 +340,11 @@ describe("tts", () => {
it("rejects unknown voices and models when openaiBaseUrl is the default OpenAI endpoint", () => {
const policy = resolveModelOverridePolicy({ enabled: true });
const input = "Hello [[tts:voice=kokoro-chinese model=kokoro-v1]] world";
const defaultBaseUrl = "https://api.openai.com/v1";
const result = parseTtsDirectives(input, policy, defaultBaseUrl);
const result = parseTtsDirectives(input, policy, {
providerConfigs: {
openai: { baseUrl: "https://api.openai.com/v1" },
},
});
const openaiOverrides = result.overrides.providerOverrides?.openai as
| { voice?: string }
| undefined;

26
src/tts/tts.ts
View File

@ -48,22 +48,6 @@ const DEFAULT_TTS_MAX_LENGTH = 1500;
const DEFAULT_TTS_SUMMARIZE = true;
const DEFAULT_MAX_TEXT_LENGTH = 4096;
const OPUS_OUTPUT = {
openai: "opus" as const,
// ElevenLabs output formats use codec_sample_rate_bitrate naming.
// Opus @ 48kHz/64kbps is a good voice message tradeoff.
elevenlabs: "opus_48000_64",
extension: ".opus",
voiceCompatible: true,
};
const DEFAULT_OUTPUT = {
openai: "mp3" as const,
elevenlabs: "mp3_44100_128",
extension: ".mp3",
voiceCompatible: false,
};
export type ResolvedTtsConfig = {
auto: TtsAutoMode;
mode: TtsMode;
@ -418,16 +402,9 @@ export function setLastTtsAttempt(entry: TtsStatusEntry | undefined): void {
lastTtsAttempt = entry;
}
/** Channels that require opus audio */
/** Channels that require voice-note-compatible audio */
const OPUS_CHANNELS = new Set(["telegram", "feishu", "whatsapp", "matrix"]);
function resolveOutputFormat(channelId?: string | null) {
if (channelId && OPUS_CHANNELS.has(channelId)) {
return OPUS_OUTPUT;
}
return DEFAULT_OUTPUT;
}
function resolveChannelId(channel: string | undefined): ChannelId | null {
return channel ? normalizeChannelId(channel) : null;
}
@ -876,6 +853,5 @@ export const _test = {
parseTtsDirectives,
resolveModelOverridePolicy,
summarizeText,
resolveOutputFormat,
getResolvedSpeechProviderConfig,
};