diff --git a/Dockerfile b/Dockerfile index 39f4cf9..4a6d532 100644 --- a/Dockerfile +++ b/Dockerfile @@ -59,6 +59,13 @@ RUN python3 /app/code/patch_audio_request_cost.py COPY patch_audio_router_pricing.py /app/code/patch_audio_router_pricing.py RUN python3 /app/code/patch_audio_router_pricing.py +# Audio per-request prices must live in the SHARED cost map, which is built from +# model_prices_and_context_window.json — the per-request helper reads that map, not +# model_info, so a router-only patch left every speech call at $0 (issue #5). +# This patch fails the build rather than warning. +COPY patch_audio_cost_map.py /app/code/patch_audio_cost_map.py +RUN python3 /app/code/patch_audio_cost_map.py + # SECURITY (2026-10-27, member-disclosure finding 4): LiteLLM forwards every # provider response header to callers as `llm_provider-*`, which leaked the # co-op's remaining provider balance (x-credits-remaining) to any member API key. diff --git a/patch_audio_cost_map.py b/patch_audio_cost_map.py new file mode 100644 index 0000000..dfa4fe4 --- /dev/null +++ b/patch_audio_cost_map.py @@ -0,0 +1,64 @@ +"""Put Tinfoil's per-request audio prices in the SHARED cost map, at BUILD time. + +Why this exists (issue #5): the cost calculator's per-request helper reads +``litellm.model_cost`` — the map built from model_prices_and_context_window.json — +and our config's ``input_cost_per_request`` never reaches it. Patching the router +to keep per-deployment pricing on the shared model_info entry was not enough, +because the helper consults the JSON-backed map, not model_info. Result: every +successful voxtral-tts speech call logged cost 0.0 (~$0.22/day of unlogged spend). + +This is the same mechanism as patch_image_cost.py: re-state the price where the +calculator actually looks. It FAILS THE BUILD rather than warning, because a silent +"billed at $0" is exactly the failure mode we are trying to close. + +Prices from the Tinfoil catalogue (2026-11-17): voxtral-tts $0.002/request, +whisper-large-v3-turbo $0.01/request, both $0 per token. +""" +import glob +import json +import sys + +ENTRIES = { + "openai/voxtral-tts": { + "mode": "audio_speech", + "input_cost_per_request": 0.002, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + }, + "openai/whisper-large-v3-turbo": { + "mode": "audio_transcription", + "input_cost_per_request": 0.01, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + }, +} + + +def main() -> int: + files = glob.glob("/app/.venv/lib/python*/site-packages/litellm/" + "model_prices_and_context_window.json") + if not files: + print("[coop-patch] FAIL model_prices_and_context_window.json not found") + return 1 + path = files[0] + with open(path, encoding="utf-8") as handle: + data = json.load(handle) + changed = [] + for key, entry in ENTRIES.items(): + current = data.get(key) or {} + if all(current.get(k) == v for k, v in entry.items()): + continue + merged = {**current, **entry} + data[key] = merged + changed.append(key) + if not changed: + print(f"[coop-patch] audio cost map already correct ({len(ENTRIES)} entries)") + return 0 + with open(path, "w", encoding="utf-8") as handle: + json.dump(data, handle, indent=2) + print("[coop-patch] applied audio cost map: " + ", ".join(changed)) + return 0 + + +if __name__ == "__main__": + sys.exit(main())