Vendor lm15 with ogg, opus, flac, aac, aiff, webm and mpeg input_audio

dspy/_vendor/lm15-provenance.txt

@@ -1,5 +1,5 @@
 source=https://github.com/cmpnd-ai/lm15-python.git
 version=1.0.0rc3
-commit=55fce2e61a04ed3193acfeb8797b7c58d1b55398
+commit=b0bffc13bc4a12e115e4c2e92fbba40ca8f3450c
 contract=b721ce4f03877d72a91431b3a5ce653ffc0b3e38
-split=63b6bb319f38ad1d31060138da54cb8ac8718711
+split=6a745c84e83a58aa4ed1237132d940f78ce65c35

dspy/_vendor/lm15/providers/openai_chat.py

@@ -246,7 +246,13 @@ def _response_format_to_chat(format_config: dict[str, Any]) -> dict[str, Any]:
 
 _INGEST_GROQ_BUILTIN_INVERSE: dict[str, str] = {wire: name for name, wire in _GROQ_BUILTIN_MAP.items()}
 
-_INGEST_AUDIO_MEDIA_TYPES: dict[str, str] = {"wav": "audio/wav", "mp3": "audio/mpeg"}
+# MAP-12 rule 4: OpenAI's server takes wav and mp3, Gemini's any audio type,
+# and DSPy writes the MIME subtype (mpeg for .mp3). Each format reads as its
+# true media type; a builder with no audio slot raises at send (MAP-10).
+_INGEST_AUDIO_MEDIA_TYPES: dict[str, str] = {
+    "wav": "audio/wav", "mp3": "audio/mpeg", "mpeg": "audio/mpeg", "ogg": "audio/ogg", "opus": "audio/opus",
+    "flac": "audio/flac", "aac": "audio/aac", "aiff": "audio/aiff", "webm": "audio/webm",
+}
 
 
 def _ingest_unsupported(provider: str, what: str, why: str) -> UnsupportedFeatureError:

tests/clients/test_lm15_audio_formats.py

@@ -0,0 +1,29 @@
+import json
+
+import dspy
+import dspy.clients.execution as execution
+from dspy._vendor.lm15.testing import FakeResponse, FakeTransport
+from dspy.lm15 import RouterConfig
+
+
+def test_ogg_audio_reaches_gemini_inline_with_its_media_type(monkeypatch):
+    reply = {
+        "candidates": [{"content": {"role": "model", "parts": [{"text": "[[ ## text ## ]]\nhej\n\n[[ ## completed ## ]]"}]},
+                        "finishReason": "STOP"}],
+        "usageMetadata": {"promptTokenCount": 1, "candidatesTokenCount": 1, "totalTokenCount": 2},
+    }
+    transport = FakeTransport([FakeResponse(status=200, body=json.dumps(reply).encode())])
+    monkeypatch.setattr(execution, "RouterConfig", lambda **kwargs: RouterConfig(
+        **{**{k: v for k, v in kwargs.items() if k != "timeouts"}, "api_keys": {"gemini": "fake"}, "transport": transport},
+    ))
+
+    class Transcribe(dspy.Signature):
+        audio: dspy.Audio = dspy.InputField()
+        text: str = dspy.OutputField()
+
+    with dspy.context(lm=dspy.LM("gemini/gemini-3.8-flash", cache=False), adapter=dspy.ChatAdapter()):
+        result = dspy.Predict(Transcribe)(audio=dspy.Audio(data="T2dnUw==", audio_format="ogg"))
+
+    assert result.text == "hej"
+    parts = json.loads(transport.requests[0].body)["contents"][-1]["parts"]
+    assert {"inlineData": {"mimeType": "audio/ogg", "data": "T2dnUw=="}} in parts