Short audio responses carry Offset and Duration in 100ns ticks; convert their sum to seconds and price it with the existing azure/speech/azure-stt entry through transcription_cost. Batch calls and responses without an integer duration stay at zero cost
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Adds authenticated /deepgram/v1/listen and /deepgram/listen WebSocket routes that resolve the Deepgram
credential through the pass-through router, inject Authorization: Token upstream, default the model to
nova-3 when the client passes none, and relay audio and transcript frames unchanged. The shared WebSocket
relay no longer assumes the first upstream frame is JSON and forwards every frame as received, keeping
the Vertex AI Live setup handling on Vertex routes only. A Deepgram logging handler bills the call on
Metadata.duration, falling back to the furthest Results start + duration, at the deepgram/<model>
per-second rate from the model cost map
Resolves LIT-7937
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Adds /azure_speech/{endpoint:path}, an authenticated pass-through for the Azure AI Speech REST APIs: short-audio recognition on <region>.stt.speech.microsoft.com and batch transcription on <region>.api.cognitive.microsoft.com. The proxy resolves the subscription key through PassthroughEndpointRouter (AZURE_SPEECH_API_KEY or an Admin UI credential), picks the host from AZURE_SPEECH_REGION or AZURE_SPEECH_API_BASE, injects Ocp-Apim-Subscription-Key, strips the caller's Authorization and subscription-key headers, forwards the raw audio body byte for byte, and records a zero-cost SpendLogs row tagged azure_speech since the price map has no Azure Speech STT entry
Resolves LIT-7939
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
/key/info now serves a deleted key from the archive with status deleted
instead of answering 404, so the delete test's convergence predicate never
settled and the read timed out against a 200 it kept discarding.
The predicate now waits for status deleted through the same
_key_info_everywhere helper the rest of the file uses, and KeyInfo carries
the status field. The chat-rejection assertion after it is unchanged, so
the test still proves the key stops serving.
The bedrock-realtime extra pinned aws-sdk-bedrock-runtime 0.7.x, whose Config and BedrockRuntimeClient surface is gone in 0.11. The handler now resolves AsyncBedrockRuntimeConfig, builds AsyncBedrockRuntimeClient with the awscrt duplex transport, closes the client when the session ends, and tells an absent SDK apart from an installed but unsupported version. Moves the pin to >=0.10.0,<0.12.0 with the awscrt extra
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The Bedrock InvokeModel transformations decided whether to send the
tool-search-tool-2025-10-19 beta from hardcoded model name lists (a pattern
list on the messages path, an "opus-4" substring on the chat path), so Opus 4.8,
Opus 5 and Sonnet 5 never got the beta on the messages path, Opus 5 and Sonnet 5
never got it on the chat path, Opus 4.1 got it without support, and
/v1/model/info reported supports_tool_search as unset for all three.
Both paths now read the model map through one shared helper: the Bedrock
entries for Opus 4.8, Opus 5 and Sonnet 5 carry supports_tool_search
explicitly, and a claude-tool-search fallback rule flags Claude 4.5 and newer
for unmapped ids, inference-profile ARNs and mapped entries with no opinion,
so the next Claude gets the beta with no code change. An explicit false on a
resolved entry still wins.
The keep-or-lower check compares against the budget update_team read, so the write now only lands while the stored max_budget still matches it and answers 409 otherwise. A concurrent proxy admin cut can no longer be overwritten with a higher value.
Forward streaming_transform_mode from guardrail litellm_params into PromptSecurityGuardrail so incremental_diff is reachable from config; the default stays block_only. In incremental_diff the guardrail now returns stream_holdback_chars alongside the rewritten texts so that a value split across streamed chunks (or across an abbreviation period) is never partially released before the vendor rewrite arrives. Each response text gets its own protect call so modified_text maps back to the right choice when n > 1, and custom_guardrail no longer logs a clean response as mask just because the guardrail attached holdback metadata
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
