cosyvoice: warn that \instruct\ is Chinese-only; XML tags for EN

Verified empirically (gitea #7): the neosun wrapper's \`instruct\`
field routes through CosyVoice's inference_instruct2 which expects
a Chinese template. English directives produce Chinese-phonemed
speech of the directive itself — the model is stuck in Chinese
context regardless of the directive language.

XML inline tags (<angry>, <sad>, etc.) bypass that path entirely
and work cleanly for English emotion control.

README updated:
  - Added Gotcha section entry explaining the instruct trap with
    the specific failure mode and the byte-identical-response
    evidence
  - Smoke-test recipes (steps 4 + 5) reworked to use <angry>...</angry>
    in the input instead of an English instruct value
  - "Emotion / style control" table now marks instruct as Chinese-
    only with ⚠️ and XML tags as ✅

stacks/cosyvoice/README.md

@@ -113,6 +113,20 @@ ssh irv-ml1 '
 - **Model choice.** `cosyvoice-v3` is default and best; `cosyvoice-v2`
   is available as a fallback if you have voices tuned against the
   v2 model's idiosyncrasies.
+- **The `instruct` field is Chinese-context-only — DON'T use it
+  for English emotion control.** Verified empirically 2026-04-24:
+  any value in `instruct` (English, Chinese, or empty hints inside
+  it) routes through CosyVoice's `inference_instruct2` which expects
+  a directive in the upstream Chinese template
+  (`You are a helpful assistant. <directive>请用…<|endofprompt|>`).
+  English values like `instruct: "speak with cold contempt"` cause
+  the model to *vocalize the instruction text itself* — you'll hear
+  Chinese-flavored phonemes reading the English directive instead
+  of your `input`. Workaround: **use the XML inline tags** (`<angry>`,
+  `<sad>`, `<surprised>`, `<fearful>`, `<fast>`, `<slow>`,
+  `<whisper>`, `<shout>`, `<peppa>`, `<robot>`) for English emotion
+  control. They're parsed as control tokens, not content. See
+  upstream issue [reference TBD].
 
 ## Smoke test (full clone → synthesize)
 
@@ -131,29 +145,31 @@ curl -X POST http://10.100.79.3:8190/v1/voices/create \
   -F "text=<paste from glados_25s.txt>"
 # → {"voice_id": "<id>", "name": "glados", ...}
 
-# 4. Synthesize via OpenAI-compat endpoint (single-shot)
+# 4. Synthesize via OpenAI-compat endpoint (single-shot).
+#    For English emotion control, use the XML inline tag — NOT the
+#    `instruct` field (that's Chinese-context only; see Gotchas).
 curl -X POST http://10.100.79.3:8190/v1/audio/speech \
   -H 'Content-Type: application/json' \
   -d '{
     "model": "cosyvoice-v3",
     "voice": "<voice_id>",
-    "input": "Hello. I did not ask for visitors today.",
-    "instruct": "speak with a flat, menacing calm",
+    "input": "<angry>I did not ask for visitors today.</angry>",
     "response_format": "wav",
     "speed": 1.0
   }' \
   -o out.wav
 
 # 5. Or synthesize via native endpoint with streaming — curl writes
-#    audio chunks to the file as they arrive (~150 ms TTFB)
+#    audio chunks to the file as they arrive (~150 ms TTFB).
+#    `instruct_text` here has the same Chinese-only caveat as the
+#    OpenAI path's `instruct` — leave it empty for English work.
 curl -N -X POST http://10.100.79.3:8190/api/tts \
-  -F "text=Hello. I did not ask for visitors today." \
+  -F "text=<angry>I did not ask for visitors today.</angry>" \
   -F "voice=<voice_id>" \
   -F "mode=zero_shot" \
-  -F "instruct_text=speak with a flat, menacing calm" \
   -F "speed=1.0" \
   -F "stream=true" \
-  -o out_stream.wav
+  -o out_stream.pcm
 ```
 
 Field naming differs between the two synthesis endpoints:
@@ -170,16 +186,21 @@ Field naming differs between the two synthesis endpoints:
 
 ## Emotion / style control
 
-Two syntaxes, combine freely:
+**For English content, use XML inline tags. Do not use the `instruct`
+field** — see the Gotcha above; `instruct` routes through CosyVoice's
+Chinese-context inference path and English values get spoken aloud
+instead of treated as direction.
 
-| Syntax | Where | Example |
-|---|---|---|
-| XML tags in the text | inline in `input` / `text` | `<angry>You're late.</angry>` |
-| Natural-language directive | `instruct` / `instruct_text` | `"speak with a flat, menacing calm"` |
+| Syntax | Where | Example | English-safe? |
+|---|---|---|---|
+| XML tags in the text | inline in `input` / `text` | `<angry>You're late.</angry>` | ✅ |
+| Natural-language directive | `instruct` / `instruct_text` | `"用愤怒的语气说"` (Chinese) | ⚠️ Chinese only |
 
 Tag vocabulary includes `<angry>`, `<sad>`, `<surprised>`,
 `<fearful>`, `<fast>`, `<slow>`, `<whisper>`, `<shout>`, plus
-character/style tags like `<peppa>`, `<robot>`.
+character/style tags like `<peppa>`, `<robot>`. Tags can be nested
+or applied at sentence granularity (the model accepts paragraph-
+length input with multiple tagged segments).
 
 ## Version bump