0.13.0

What's Changed

• ✅ Add Chat Completions Streaming integration tests by @declark1 in #417
• 🐛 Bugfix: Allow int/string stop_reasons by @RobGeada in #453
• 📦 Upgrade mocktail to 0.3.0, update tests to use new MockServer constructors by @declark1 in #455
• ❇️ Add Chat Completions Streaming support for continuous_usage_stats by @declark1 in #456
• 🚚 Rename ChatCompletionBatcher to CompletionBatcher by @declark1 in #458
• ❇️ Add completions streaming support by @mdevino in #457
• 🚚 Rename openai detection types by @declark1 in #459
• 👷 Update builder layer to use UBI 9 minimal by @evaline-ju in #461
• ♻️ Refactor detector clients to single DetectorClient by @declark1 in #462
• ♻️ Update DetectorConfig to support multiple detector types by @declark1 in #463
• 📦 Release 0.13.0 by @mdevino in #465

New Contributors

• @RobGeada made their first contribution in #453

Full Changelog: 0.12.0...0.13.0

0.12.0

What's Changed

• 🐛 Update OpenAI openAPI spec location by @evaline-ju in #433
• 🐛 Update OpenAI openAPI spec location for standalone chat by @evaline-ju in #434
• 📝✨ API update to support detections on vLLM /completions by @evaline-ju in #435
• fix: OpenAiClient streaming error handling by @declark1 in #436
• fix: send [DONE] after all error messages by @declark1 in #437
• Rename chat_completions config to openai by @mdevino in #438
• Completions endpoint - unary text_contents detection by @mdevino in #446
• Invoke vLLM /tokenize endpoint on completions input detection by @mdevino in #448
• Upgrade dependencies for release 0.12.0 by @mdevino in #451

Full Changelog: 0.11.2...0.12.0

0.11.2 - Fix chat completion streaming

What's Changed

• Upgrade dependencies by @mdevino in #430
• fix: send chat completion chunk with finish reason, set role on chat completion chunks by @declark1 in #431
• fix: only send non-empty choice text to detection input channel by @declark1 in #432

Full Changelog: 0.11.1...0.11.2

0.11.1 - Tool call fix

What's Changed

• 🔧 Update config key and comments by @evaline-ju in #420
• Add Mateus in CODEOWNERS by @gkumbhat in #421
• Test s390x build by @mdevino in #423
• Update Dockerfile.s390x for tls issue by @Sanketha-Cr in #419
• Add Dockerfile.ppc64le by @varad-ahirwadkar in #424
• Fix rust version for amd64 build by @mdevino in #425
• Use rust:1 on dockerfiles by @mdevino in #426
• fix: make ToolCall and FunctionCall fields optional by @declark1 in #427

New Contributors

• @varad-ahirwadkar made their first contribution in #424

Full Changelog: 0.11.0...0.11.1

0.11.0 - Chat completion update and rename

What's Changed

• 📦 Add dashmap dependency by @declark1 in #405
• ✨ (BETA) Add Chat Completions streaming support by @declark1 in #391
• 📦 Upgrade open telemetry by @mdevino in #403
• ✨ Add retry on eager by @gkumbhat in #393
• 📦 Upgrade tonic to 0.13.1 by @mdevino in #407
• 📦 Added Dockerfile.amd64, Dockerfile.s390x and removed Dockerfile by @Sanketha-Cr in #399
• 🐛 Fix OpenAiClient error handling for streaming by @declark1 in #410
• 🔊 Drop warning for empty choice content by @declark1 in #411
• 📦 Upgrade open telemetry crates to 0.30 by @mdevino in #408
• 🐛 Empty choice warning by @mdevino in #402
• ♻️ server::Error refactor by @declark1 in #412
• 🐛 Update SseStream and error integration test cases by @declark1 in #413
• 🚩 OrchestratorConfig: deprecate chat_generation in favor of chat_completions by @mdevino in #414
• 📦 Upgrade dependencies by @mdevino in #415

Full Changelog: 0.10.0...0.11.0

0.10.0

What's Changed

• 🐛 Stream content tests and error handling fix by @mdevino in #350
• ✅ Integration tests for /api/v2/chat/completions-detection by @pmcjr in #360
• 📦 Bump openssl from 0.10.71 to 0.10.72 by @dependabot in #361
• 📦 Update Rust to 1.86 by @mdevino in #364
• 📦 Bump tokio from 1.44.1 to 1.44.2 by @dependabot in #365
• ✅ Single detector tests by @mdevino in #362
• ♻️ Task handlers by @declark1 in #355
• ➖ Drop faux by @mdevino in #374
• 🔥 Chunker client cleanup by @evaline-ju in #376
• 🦺 Guardrails request config validation by @mdevino in #371
• ✅ No detectors tests by @mdevino in #373
• ♻️ Refactor ChatCompletionsRequest by @declark1 in #375
• ✅ Tests cleanup by @mdevino in #379
• 🐛 Fix DetectionBatchStream by @declark1 in #381
• 👷 To support s390x by @Sanketha-Cr in #369
• ✨ Chat completions batcher by @evaline-ju in #380
• 🥅 Handle unsupported media type errors by @evaline-ju in #386
• 🐛 Allow input detection on whole input for streaming text generation endpoint by @evaline-ju in #388
• ♻️ server cleanups by @declark1 in #387
• 🧑‍💻 OpenAiClient updates & completions implementation by @declark1 in #390
• ✅ Implement re-try logic for TestOrchestratorServer port binding by @mdevino in #392
• 🚸 Batcher simplifications by @declark1 in #394
• 🦺 Validate message content on chat completions endpoint by @mdevino in #383
• 📦 Update Rust to 1.87.0 and dependencies by @mdevino in #404

New Contributors

• @Sanketha-Cr made their first contribution in #369

Full Changelog: 0.9.4...0.10.0

0.9.4

What's Changed

• 🛂 Add code of conduct by @spzala in #309
• 🐛 Accumulate DetectionResults for detections with same message_index in chat completions api by @swith004 in #310
• ⬆️ Bump hickory-proto from 0.24.2 to 0.24.3 by @dependabot in #300
• ⬆️ Bump openssl from 0.10.68 to 0.10.70 by @dependabot in #291
• ♻️ pre-refactor: A few type and organization tweaks by @declark1 in #325
• 🐛 process stream-content requests as ndjson (w/jsonlines) by @swith004 in #327
• 🐛 Use jsonlines as response in stream-content by @swith004 in #329
• ♻️ pre-refactor: Add orchestrator.types module with common types by @declark1 in #326
• ✅ Integration tests for input detection cases in /api/v1/task/server-streaming-classification-with-text-generation by @mdevino in #312
• ♻️ Refactor TestOrchestratorServerBuilder and TestOrchestratorServer to avoid mock server ownership by @declark1 in #333
• ✅ Integration tests for /api/v2/text/detection/content by @mdevino in #314
• 📝 ADR and API updates for additional detector fields by @evaline-ju in #334
• reverted response_stream processing and message json conversion for stream content detection by @swith004 in #336
• 📝 API update - add tools to chat detections by @evaline-ju in #335
• ♻️ Update existing integration tests to new mocktail API, add tests for /api/v2/text/detection/generated by @mdevino in #318
• ✅ Integration tests for input detections in /api/v2/text/detection/context/ by @mdevino in #319
• ✅ Integration tests for /api/v2/text/detection/chat by @mdevino in #320
• ✅ Integration tests for /api/v1/task/classification-with-text-generation by @pmcjr in #340
• ✅ Output streaming integration tests by @mdevino in #342
• ✅ Generation with detection integration tests by @mdevino in #345
• pre-refactor: Add common.tasks and common.clients modules by @declark1 in #337
• 👷 Update CI checks by @mdevino in #346
• 📦 Update rust version by @mdevino in #347
• ✨ Add tools to standalone chat detection by @evaline-ju in #351
• ✨ Add metadata object by @gkumbhat in #353
• 👷 Healthcheck command for Dockerfile by @evaline-ju in #356

New Contributors

• @spzala made their first contribution in #309
• @dependabot made their first contribution in #300

Full Changelog: 0.9.3...0.9.4

0.9.3 - Output detection, CI improvements and DNS interval config

What's Changed

• 👷 removed most of the warnings from Dockerfile when running docker build by @resoluteCoder in #301
• 👷 added arg statement to each layer in Dockerfile by @resoluteCoder in #303
• ❇️ output detection for chat completions by @resoluteCoder in #288
• 🔧 Make grpc dns probe interval configurable per client by @gkumbhat in #306

Full Changelog: 0.9.2...0.9.3

0.9.2

What's Changed

• Add Role enum to openai module by @swith004 in #287
• Revert ":wrench: Assume http2 for grpc clients (#284)" by @evaline-ju in #293
• Add error handling for unknown fields for chat completion detection request by @swith004 in #296

Full Changelog: 0.9.1...0.9.2

0.9.1 - Fix http2 negotiation, error handling improvements and input detection on chat

What's Changed

• ✨ Add chat content detector (input detection only) by @gkumbhat in #276
• 🔧 Assume http2 for grpc clients by @evaline-ju in #284
• 🥅 Add error handling for unknown fields in orchestrator request by @swith004 in #285
• 🔧 Add header on detector requests by @evaline-ju in #283

Full Changelog: 0.9.0...0.9.1