feat(tts): add StepFun preset-voice provider, route by URL + voice tag

Add StepFun step-tts-mini / step-tts-2 / stepaudio-2.5-tts as an alternate
TTS provider alongside Xiaomi MiMo. Auto-detected from TTS_BASE_URL host
(contains `stepfun.com` → StepFun; otherwise → MiMo), mirroring how the
image client infers Runware from `*.runware.ai`.

CharacterVoice becomes a discriminated union on `provider`:
- xiaomi: { referenceAudioBase64, mimeType } — unchanged
- stepfun: { voiceId, model, mimeType } — preset voice ID + chosen model

Provision dispatches on the current cfg's base URL; synthesis dispatches
on the voice's own `provider` tag so a session with mixed voices (e.g. a
provider switch mid-development) routes each beat through the correct
protocol. xiaomiSynthesize now guards against being called with a non-
xiaomi voice, surfacing the bug as a clear runtime error instead of a
TypeScript narrow violation at the access site.

StepFun has no voicedesign equivalent — only preset voices + voice
cloning from a reference audio upload. Cloning would require an extra
asset per character, so v1 maps the LLM's Chinese voiceDescription to one
of the 32 published preset IDs via gender + age + tone keyword scoring,
with a deterministic hash spread across the top-3 candidates so multiple
characters with similar descriptions don't collapse onto the identical
preset. lineDelivery is accepted but not yet propagated to StepFun's
voice_label.emotion / .style fields — left as a follow-up.

beat-audio route validation relaxed from `voice.referenceAudioBase64`
(xiaomi-shaped) to `voice.provider` (shape-agnostic), so stepfun voices
pass the gate; provider-specific shape errors still surface from the
synth function.

Observed latency on InfiPlot's dev loop: StepFun step-tts-mini median
~2.3s per beat with 0% timeouts across the test session, vs MiMo's
median ~8s with the long tail tripping the existing 15s synth budget
on roughly 2 of 3 beats. Pricing: step-tts-mini ¥0.9/万字符 (~¥0.14
per typical 50-beat session) vs MiMo TTS currently free under the
Token Plan creator incentive.

AGENTS.md provider matrix updated to describe both providers and the
discriminated-union dispatch.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

lib/types/index.ts

@@ -160,12 +160,24 @@ export type WriterPlan = {
 //  Characters & voices (TTS)
 // ──────────────────────────────────────────────────────────────────────
 
-export type CharacterVoice = {
-  provider: "xiaomi";
-  /** Xiaomi MiMo design output stored as reference audio for later clones. */
-  referenceAudioBase64: string;
-  mimeType: string;
-};
+export type CharacterVoice =
+  | {
+      provider: "xiaomi";
+      /** Xiaomi MiMo design output stored as reference audio for later clones. */
+      referenceAudioBase64: string;
+      mimeType: string;
+    }
+  | {
+      provider: "stepfun";
+      /** StepFun preset voice ID (e.g. "cixingnansheng"). Selected by keyword
+       *  matching against the LLM-written voiceDescription — no network call
+       *  on provision (StepFun has no voicedesign endpoint), so this carries
+       *  only the picked preset, not a clip. */
+      voiceId: string;
+      /** TTS model used at synth time (step-tts-mini / step-tts-2 / stepaudio-2.5-tts). */
+      model: string;
+      mimeType: string;
+    };
 
 export type Character = {
   name: string;