Merge branch 'main' into fix-gemini-toolbehaviour

Author: simllll

.changeset/modern-views-fry.md

@@ -0,0 +1,5 @@
+---
+'@livekit/agents': patch
+---
+
+Added SessionReport and onSessionEnd callback

.github/pull_request_template.md

@@ -12,6 +12,7 @@
 - [ ] **AI-generated code reviewed**: Removed unnecessary comments and ensured code quality
 - [ ] **Changes explained**: All changes are properly documented and justified above
 - [ ] **Scope appropriate**: All changes relate to the PR title, or explanations provided for why they're included
+- [ ] **Video demo**: A small video demo showing changes works as expected and did not break any existing functionality using [Agent Playground](https://agents-playground.livekit.io/#cam=0&mic=1&screen=1&video=1&audio=1&chat=1&theme_color=green) (if applicable) 
 
 ## Testing
 <!-- Describe how you tested these changes -->

.gitignore

@@ -189,4 +189,8 @@ docs
 # vscode workspace config
 agents-js.code-workspace
 
-examples/src/test_*.ts
+examples/src/test_*.ts
+
+# Ignore all markdown files except root README
+*.md
+!README.md

REUSE.toml

@@ -36,3 +36,9 @@ SPDX-License-Identifier = "CC-BY-NC-SA-4.0"
 path = ["**/.gitattributes", "**.wav", "**/__snapshots__/**"]
 SPDX-FileCopyrightText = "2024 LiveKit, Inc."
 SPDX-License-Identifier = "Apache-2.0"
+
+# audio resources
+[[annotations]]
+path = ["agents/resources/*.ogg", "agents/resources/NOTICE"]
+SPDX-FileCopyrightText = "2024 LiveKit, Inc."
+SPDX-License-Identifier = "Apache-2.0"

agents/CHANGELOG.md

@@ -1,5 +1,53 @@
 # @livekit/agents
 
+## 1.0.18
+
+### Patch Changes
+
+- bump openai to 6.x - [#813](https://github.com/livekit/agents-js/pull/813) ([@toubatbrian](https://github.com/toubatbrian))
+
+- Emit away events for User - [#801](https://github.com/livekit/agents-js/pull/801) ([@paulheinrichs-jb](https://github.com/paulheinrichs-jb))
+
+- Support openai half-duplex mode (audio in -> text out -> custom TTS model) - [#814](https://github.com/livekit/agents-js/pull/814) ([@toubatbrian](https://github.com/toubatbrian))
+
+- Support strict tool schema for openai-competible model - [#816](https://github.com/livekit/agents-js/pull/816) ([@toubatbrian](https://github.com/toubatbrian))
+
+## 1.0.17
+
+### Patch Changes
+
+- handle APIError in STT & TTS retry mechanism and prevent ERR_UNHANDLED_ERROR - [#804](https://github.com/livekit/agents-js/pull/804) ([@toubatbrian](https://github.com/toubatbrian))
+
+## 1.0.16
+
+### Patch Changes
+
+- Add preemptive generation - [#798](https://github.com/livekit/agents-js/pull/798) ([@toubatbrian](https://github.com/toubatbrian))
+
+- Rename Worker to AgentServer - [#713](https://github.com/livekit/agents-js/pull/713) ([@Shubhrakanti](https://github.com/Shubhrakanti))
+
+## 1.0.15
+
+### Patch Changes
+
+- Fix race condition causing "Writer is not bound to a WritableStream" error in Silero VAD - [#786](https://github.com/livekit/agents-js/pull/786) ([@toubatbrian](https://github.com/toubatbrian))
+
+- Support Zod V4 tool schema and backward competible to V3 - [#792](https://github.com/livekit/agents-js/pull/792) ([@toubatbrian](https://github.com/toubatbrian))
+
+## 1.0.14
+
+### Patch Changes
+
+- Fix ffmpeg dependency cannot found issue - [#793](https://github.com/livekit/agents-js/pull/793) ([@toubatbrian](https://github.com/toubatbrian))
+
+## 1.0.13
+
+### Patch Changes
+
+- Add utility to play local audio file to livekit - [#788](https://github.com/livekit/agents-js/pull/788) ([@toubatbrian](https://github.com/toubatbrian))
+
+- Add BackgroundAudio support - [#789](https://github.com/livekit/agents-js/pull/789) ([@toubatbrian](https://github.com/toubatbrian))
+
 ## 1.0.12
 
 ### Patch Changes

agents/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@livekit/agents",
-  "version": "1.0.12",
+  "version": "1.0.18",
   "description": "LiveKit Agents - Node.js",
   "main": "dist/index.js",
   "require": "dist/index.cjs",
@@ -22,6 +22,7 @@
   "files": [
     "dist",
     "src",
+    "resources",
     "README.md"
   ],
   "scripts": {
@@ -34,34 +35,45 @@
     "api:update": "api-extractor run --local --typescript-compiler-folder ../node_modules/typescript --verbose"
   },
   "devDependencies": {
-    "@livekit/rtc-node": "^0.13.12",
+    "@livekit/rtc-node": "^0.13.13",
     "@microsoft/api-extractor": "^7.35.0",
+    "@types/fluent-ffmpeg": "^2.1.28",
     "@types/json-schema": "^7.0.15",
     "@types/node": "^22.5.5",
     "@types/ws": "^8.5.10",
     "tsup": "^8.4.0",
-    "typescript": "^5.0.0"
+    "typescript": "^5.0.0",
+    "zod": "^3.25.76"
   },
   "dependencies": {
+    "@ffmpeg-installer/ffmpeg": "^1.1.0",
     "@livekit/mutex": "^1.1.1",
-    "@livekit/protocol": "^1.41.0",
+    "@livekit/protocol": "^1.43.0",
     "@livekit/typed-emitter": "^3.0.0",
+    "@opentelemetry/api": "^1.9.0",
+    "@opentelemetry/exporter-trace-otlp-http": "^0.54.0",
+    "@opentelemetry/otlp-exporter-base": "^0.208.0",
+    "@opentelemetry/resources": "^1.28.0",
+    "@opentelemetry/sdk-trace-base": "^1.28.0",
+    "@opentelemetry/sdk-trace-node": "^1.28.0",
+    "@opentelemetry/semantic-conventions": "^1.28.0",
     "@types/pidusage": "^2.0.5",
     "commander": "^12.0.0",
+    "fluent-ffmpeg": "^2.1.3",
     "heap-js": "^2.6.0",
     "json-schema": "^0.4.0",
-    "openai": "^4.91.1",
-    "livekit-server-sdk": "^2.13.3",
+    "livekit-server-sdk": "^2.14.1",
+    "openai": "^6.8.1",
     "pidusage": "^4.0.1",
     "pino": "^8.19.0",
     "pino-pretty": "^11.0.0",
     "sharp": "0.34.3",
     "uuid": "^11.1.0",
-    "ws": "^8.16.0",
-    "zod": "^3.23.8",
+    "ws": "^8.18.0",
     "zod-to-json-schema": "^3.24.6"
   },
   "peerDependencies": {
-    "@livekit/rtc-node": "^0.13.12"
+    "@livekit/rtc-node": "^0.13.12",
+    "zod": "^3.25.76 || ^4.1.8"
   }
 }

agents/resources/NOTICE

@@ -0,0 +1,2 @@
+keyboard-typing.ogg by Anton -- https://freesound.org/s/137/ -- License: Attribution 4.0
+keyboard-typing2.opg by Anton -- https://freesound.org/s/137/ -- License: Attribution 4.0