diff --git a/helpers.py b/helpers.py
index 3ec6a87..7a3e9bc 100644
--- a/helpers.py
+++ b/helpers.py
@@ -1,6 +1,7 @@
from __future__ import annotations
import os
+import re
from typing import Any
@@ -33,13 +34,39 @@ def summarize_error(body: Any, fallback: str) -> str:
if isinstance(err, dict):
msg = err.get("message")
if isinstance(msg, str) and msg.strip():
- return msg.strip()
+ return _compact_error_text(msg)
msg = body.get("message")
if isinstance(msg, str) and msg.strip():
- return msg.strip()
+ return _compact_error_text(msg)
- return fallback
+ return _compact_error_text(fallback)
+
+
+def _compact_error_text(text: str, limit: int = 240) -> str:
+ clean = text.strip()
+ if not clean:
+ return "Unknown provider error"
+
+ lower = clean.lower()
+ if "\s*([^<]+?)\s*", clean, flags=re.IGNORECASE | re.DOTALL)
+ title = re.sub(r"\s+", " ", title_match.group(1)).strip() if title_match else "HTML error page"
+ code_match = re.search(r"(?:error code\s*)?([45]\d{2})", clean, flags=re.IGNORECASE)
+ code = code_match.group(1) if code_match else None
+ phrase = "Bad gateway" if "bad gateway" in lower else title
+ if "cloudflare" in lower or "openrouter.ai" in lower:
+ if code:
+ return f"Cloudflare/OpenRouter returned HTTP {code} {phrase}"
+ return f"Cloudflare/OpenRouter returned {phrase}"
+ if code:
+ return f"Provider returned HTTP {code} HTML error page: {title}"
+ return f"Provider returned HTML error page: {title}"
+
+ clean = re.sub(r"\s+", " ", clean)
+ if len(clean) > limit:
+ return clean[: limit - 1].rstrip() + "…"
+ return clean
def build_transcript_block(display_name: str, transcript: str) -> str:
diff --git a/openrouter_client.py b/openrouter_client.py
index 88b0451..5ac631b 100644
--- a/openrouter_client.py
+++ b/openrouter_client.py
@@ -19,10 +19,15 @@ load_dotenv()
logger = logging.getLogger(__name__)
OPENROUTER_BASE = "https://openrouter.ai/api/v1"
+OPENAI_BASE = "https://api.openai.com/v1"
TRANSCRIPTION_MODELS = [
"openai/gpt-4o-mini-transcribe",
"openai/whisper-large-v3",
]
+DIRECT_OPENAI_TRANSCRIPTION_MODELS = [
+ "gpt-4o-mini-transcribe",
+ "whisper-1",
+]
TRANSCRIPTION_CHUNK_SECONDS = 600
MAX_TRANSCRIPTION_FILE_BYTES = 25 * 1024 * 1024
SUMMARY_TRANSCRIPT_CHAR_LIMIT = 12000
@@ -32,6 +37,10 @@ def _api_key() -> str:
return os.getenv("OPENROUTER_API_KEY", "")
+def _openai_api_key() -> str:
+ return os.getenv("OPENAI_API_KEY", "")
+
+
def _auth_headers() -> dict[str, str]:
api_key = _api_key()
if not api_key:
@@ -177,7 +186,7 @@ async def _split_audio_for_transcription(audio_path: str) -> list[str]:
return chunk_paths
-async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers: dict[str, str]) -> str:
+async def _transcribe_chunk_with_openrouter(client: httpx.AsyncClient, audio_path: str, headers: dict[str, str]) -> str:
failures: list[str] = []
for model in TRANSCRIPTION_MODELS:
resp = await client.post(
@@ -193,7 +202,7 @@ async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers:
suffix = f"; generation_id={generation_id}" if generation_id else ""
failures.append(f"{model}: HTTP {resp.status_code}: {detail}{suffix}")
logger.warning(
- "Transcription model failed: model=%s chunk=%s status=%s detail=%s generation_id=%s",
+ "Transcription model failed: provider=openrouter model=%s chunk=%s status=%s detail=%s generation_id=%s",
model,
Path(audio_path).name,
resp.status_code,
@@ -206,7 +215,7 @@ async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers:
text = data.get("text", "")
if text.strip():
logger.info(
- "Transcription chunk completed: chunk=%s model=%s transcript_chars=%s",
+ "Transcription chunk completed: provider=openrouter chunk=%s model=%s transcript_chars=%s",
Path(audio_path).name,
model,
len(text.strip()),
@@ -215,7 +224,7 @@ async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers:
failures.append(f"{model}: returned empty text")
logger.warning(
- "Transcription model returned empty text: model=%s chunk=%s",
+ "Transcription model returned empty text: provider=openrouter model=%s chunk=%s",
model,
Path(audio_path).name,
)
@@ -223,6 +232,83 @@ async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers:
raise RuntimeError("OpenRouter transcription failed across all models: " + " | ".join(failures))
+async def _transcribe_chunk_with_openai(client: httpx.AsyncClient, audio_path: str) -> str:
+ api_key = _openai_api_key()
+ if not api_key:
+ raise RuntimeError("OPENAI_API_KEY not set")
+
+ failures: list[str] = []
+ headers = {"Authorization": f"Bearer {api_key}"}
+ for model in DIRECT_OPENAI_TRANSCRIPTION_MODELS:
+ with open(audio_path, "rb") as audio_file:
+ files = {"file": (Path(audio_path).name, audio_file, "audio/wav")}
+ data = {"model": model}
+ resp = await client.post(
+ f"{OPENAI_BASE}/audio/transcriptions",
+ headers=headers,
+ data=data,
+ files=files,
+ )
+ try:
+ resp.raise_for_status()
+ except httpx.HTTPStatusError:
+ detail = summarize_error(_safe_json(resp), fallback=resp.text)
+ request_id = resp.headers.get("x-request-id")
+ suffix = f"; request_id={request_id}" if request_id else ""
+ failures.append(f"{model}: HTTP {resp.status_code}: {detail}{suffix}")
+ logger.warning(
+ "Transcription model failed: provider=openai model=%s chunk=%s status=%s detail=%s request_id=%s",
+ model,
+ Path(audio_path).name,
+ resp.status_code,
+ detail,
+ request_id,
+ )
+ continue
+
+ data = resp.json()
+ text = data.get("text", "")
+ if text.strip():
+ logger.info(
+ "Transcription chunk completed: provider=openai chunk=%s model=%s transcript_chars=%s",
+ Path(audio_path).name,
+ model,
+ len(text.strip()),
+ )
+ return text.strip()
+
+ failures.append(f"{model}: returned empty text")
+ logger.warning(
+ "Transcription model returned empty text: provider=openai model=%s chunk=%s",
+ model,
+ Path(audio_path).name,
+ )
+
+ raise RuntimeError("Direct OpenAI transcription failed across all models: " + " | ".join(failures))
+
+
+async def _transcribe_chunk(client: httpx.AsyncClient, audio_path: str, headers: dict[str, str]) -> str:
+ failures: list[str] = []
+ try:
+ return await _transcribe_chunk_with_openrouter(client, audio_path, headers)
+ except RuntimeError as exc:
+ failures.append(str(exc))
+ logger.warning(
+ "OpenRouter transcription provider failed for chunk=%s; checking direct OpenAI fallback",
+ Path(audio_path).name,
+ )
+
+ if _openai_api_key():
+ try:
+ return await _transcribe_chunk_with_openai(client, audio_path)
+ except RuntimeError as exc:
+ failures.append(str(exc))
+ else:
+ failures.append("direct OpenAI fallback skipped: OPENAI_API_KEY not set")
+
+ raise RuntimeError("Transcription failed across providers: " + " | ".join(failures))
+
+
async def transcribe(audio_path: str) -> str:
"""Send audio to OpenRouter STT models and return transcript text."""
logger.info(
diff --git a/tests/test_helpers.py b/tests/test_helpers.py
index 96720d8..f1775cc 100644
--- a/tests/test_helpers.py
+++ b/tests/test_helpers.py
@@ -33,6 +33,23 @@ def test_summarize_error_falls_back_to_string():
assert summarize_error({"unexpected": True}, fallback="fallback") == "fallback"
+def test_summarize_error_compacts_cloudflare_html():
+ html = """
+
+ openrouter.ai | 502: Bad gateway
+ Bad gateway
Error code 502
+ """
+
+ assert summarize_error(None, fallback=html) == "Cloudflare/OpenRouter returned HTTP 502 Bad gateway"
+
+
+def test_summarize_error_truncates_long_plain_text():
+ message = summarize_error(None, fallback="x" * 600)
+
+ assert len(message) < 260
+ assert message.endswith("…")
+
+
def test_build_transcript_block_labels_transcript():
block = build_transcript_block("Chris", "Discussed deadlines")
assert block == "[Chris]\nDiscussed deadlines"
diff --git a/tests/test_openrouter_client.py b/tests/test_openrouter_client.py
index a3c271b..8ab081f 100644
--- a/tests/test_openrouter_client.py
+++ b/tests/test_openrouter_client.py
@@ -16,6 +16,7 @@ from openrouter_client import (
_chunk_text,
_combined_summary_prompt,
_summary_prompt,
+ _transcribe_chunk,
summarize,
transcribe,
)
@@ -136,3 +137,48 @@ def test_combined_summary_prompt_requires_requested_sections():
assert "## Action Items" in prompt
assert "## Decisions" in prompt
assert "all dev team members' reports" in prompt
+
+
+def test_transcribe_chunk_falls_back_to_direct_openai_when_openrouter_fails(tmp_path: Path, monkeypatch):
+ audio = tmp_path / "chunk-000.wav"
+ audio.write_bytes(b"audio")
+ calls = []
+
+ async def fake_openrouter(_client, audio_path: str, _headers: dict[str, str]) -> str:
+ calls.append(("openrouter", Path(audio_path).name))
+ raise RuntimeError("OpenRouter transcription failed across all models: Cloudflare 502")
+
+ async def fake_openai(_client, audio_path: str) -> str:
+ calls.append(("openai", Path(audio_path).name))
+ return "direct provider transcript"
+
+ monkeypatch.setattr(openrouter_client, "_transcribe_chunk_with_openrouter", fake_openrouter)
+ monkeypatch.setattr(openrouter_client, "_transcribe_chunk_with_openai", fake_openai)
+ monkeypatch.setattr(openrouter_client, "_openai_api_key", lambda: "sk-test")
+
+ result = asyncio.run(_transcribe_chunk(object(), str(audio), {"Authorization": "Bearer test"}))
+
+ assert result == "direct provider transcript"
+ assert calls == [("openrouter", "chunk-000.wav"), ("openai", "chunk-000.wav")]
+
+
+def test_transcribe_chunk_reports_provider_fallback_when_all_providers_fail(tmp_path: Path, monkeypatch):
+ audio = tmp_path / "chunk-000.wav"
+ audio.write_bytes(b"audio")
+
+ async def fake_openrouter(_client, _audio_path: str, _headers: dict[str, str]) -> str:
+ raise RuntimeError("OpenRouter transcription failed across all models: Cloudflare 502")
+
+ monkeypatch.setattr(openrouter_client, "_transcribe_chunk_with_openrouter", fake_openrouter)
+ monkeypatch.setattr(openrouter_client, "_openai_api_key", lambda: "")
+
+ try:
+ asyncio.run(_transcribe_chunk(object(), str(audio), {"Authorization": "Bearer test"}))
+ except RuntimeError as exc:
+ message = str(exc)
+ else:
+ raise AssertionError("Expected transcription failure")
+
+ assert "Transcription failed across providers" in message
+ assert "OpenRouter transcription failed" in message
+ assert "direct OpenAI fallback skipped" in message