chore: release main

.release-please-manifest.json

@@ -1,6 +1,6 @@
 {
-  "packages/sdk/server-ai": "0.18.0",
-  "packages/ai-providers/server-ai-langchain": "0.5.0",
-  "packages/ai-providers/server-ai-openai": "0.4.0",
+  "packages/sdk/server-ai": "0.19.0",
+  "packages/ai-providers/server-ai-langchain": "0.6.0",
+  "packages/ai-providers/server-ai-openai": "0.5.0",
   "packages/optimization": "0.1.0"
 }

packages/ai-providers/server-ai-langchain/CHANGELOG.md

@@ -2,6 +2,26 @@
 
 All notable changes to the LaunchDarkly Python AI LangChain provider package will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org).
 
+## [0.6.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-langchain-0.5.0...launchdarkly-server-sdk-ai-langchain-0.6.0) (2026-05-05)
+
+
+### ⚠ BREAKING CHANGES
+
+* `LangChainModelRunner.invoke_model()` and `invoke_structured_model()` have been removed. Use the unified `run(input, output_type=...)` method instead, which returns `RunnerResult` in place of `ModelResponse` / `StructuredResponse`.
+
+
+### Features
+
+* Add judge evaluation support to agent graphs ([#142](https://github.com/launchdarkly/python-server-sdk-ai/issues/142)) ([3d5a6a9](https://github.com/launchdarkly/python-server-sdk-ai/commit/3d5a6a91a87c7475a83a7e440cd4b71337cfd56f))
+* Migrate LangGraph runner to AgentGraphRunnerResult; clean up legacy shape detection ([#156](https://github.com/launchdarkly/python-server-sdk-ai/issues/156)) ([efa8e00](https://github.com/launchdarkly/python-server-sdk-ai/commit/efa8e00103d3870d379167769ae38f438b019ec4))
+* Support conversation history directly in AI Provider model runners ([#166](https://github.com/launchdarkly/python-server-sdk-ai/issues/166)) ([4bb3e78](https://github.com/launchdarkly/python-server-sdk-ai/commit/4bb3e7813f7c087302ba8446dea6a4a41f012c2e))
+* Update LangChain runners to implement Runner protocol returning RunnerResult ([#150](https://github.com/launchdarkly/python-server-sdk-ai/issues/150)) ([62a8e25](https://github.com/launchdarkly/python-server-sdk-ai/commit/62a8e252f4389884fa2f6a90e325db4a8f79376a))
+
+
+### Bug Fixes
+
+* build judge input as string; strip legacy judge config messages ([#165](https://github.com/launchdarkly/python-server-sdk-ai/issues/165)) ([e6942a6](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6942a6e2d4db17ae1fa6191521f8ac4fb48f30d))
+
 ## [0.5.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-langchain-0.4.1...launchdarkly-server-sdk-ai-langchain-0.5.0) (2026-04-21)
 
 

packages/ai-providers/server-ai-langchain/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "launchdarkly-server-sdk-ai-langchain"
-version = "0.5.0"
+version = "0.6.0"
 description = "LaunchDarkly AI SDK LangChain Provider"
 authors = [{name = "LaunchDarkly", email = "dev@launchdarkly.com"}]
 license = {text = "Apache-2.0"}
@@ -20,7 +20,7 @@ classifiers = [
     "Topic :: Software Development :: Libraries",
 ]
 dependencies = [
-    "launchdarkly-server-sdk-ai>=0.18.0",
+    "launchdarkly-server-sdk-ai>=0.19.0",
     "langchain-core>=1.0.0",
     "langchain>=1.0.0",
 ]

packages/ai-providers/server-ai-openai/CHANGELOG.md

@@ -2,6 +2,26 @@
 
 All notable changes to the LaunchDarkly Python AI OpenAI provider package will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org).
 
+## [0.5.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-openai-0.4.0...launchdarkly-server-sdk-ai-openai-0.5.0) (2026-05-05)
+
+
+### ⚠ BREAKING CHANGES
+
+* `OpenAIModelRunner` no longer exposes `invoke_model()` or `invoke_structured_model()`. It now implements the unified `Runner` protocol — use `run(input: str)` instead. The return type is `RunnerResult` (replacing `ModelResponse` / `StructuredResponse`). ([#149](https://github.com/launchdarkly/python-server-sdk-ai/issues/149))
+
+
+### Features
+
+* Add judge evaluation support to agent graphs ([#142](https://github.com/launchdarkly/python-server-sdk-ai/issues/142)) ([3d5a6a9](https://github.com/launchdarkly/python-server-sdk-ai/commit/3d5a6a91a87c7475a83a7e440cd4b71337cfd56f))
+* Support conversation history directly in AI Provider model runners ([#166](https://github.com/launchdarkly/python-server-sdk-ai/issues/166)) ([4bb3e78](https://github.com/launchdarkly/python-server-sdk-ai/commit/4bb3e7813f7c087302ba8446dea6a4a41f012c2e))
+* Update OpenAI graph runner to return AgentGraphRunnerResult with GraphMetrics ([#155](https://github.com/launchdarkly/python-server-sdk-ai/issues/155)) ([388b7af](https://github.com/launchdarkly/python-server-sdk-ai/commit/388b7af70c23180607764a0fc4783ae4d0cd096d))
+* Update OpenAI runners to implement Runner protocol returning RunnerResult ([#149](https://github.com/launchdarkly/python-server-sdk-ai/issues/149)) ([382e662](https://github.com/launchdarkly/python-server-sdk-ai/commit/382e662af00b224f7269397beea94c70c2872b9a))
+
+
+### Bug Fixes
+
+* build judge input as string; strip legacy judge config messages ([#165](https://github.com/launchdarkly/python-server-sdk-ai/issues/165)) ([e6942a6](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6942a6e2d4db17ae1fa6191521f8ac4fb48f30d))
+
 ## [0.4.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-openai-0.3.0...launchdarkly-server-sdk-ai-openai-0.4.0) (2026-04-21)
 
 

packages/ai-providers/server-ai-openai/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "launchdarkly-server-sdk-ai-openai"
-version = "0.4.0"
+version = "0.5.0"
 description = "LaunchDarkly AI SDK OpenAI Provider"
 authors = [{name = "LaunchDarkly", email = "dev@launchdarkly.com"}]
 license = {text = "Apache-2.0"}
@@ -20,7 +20,7 @@ classifiers = [
     "Topic :: Software Development :: Libraries",
 ]
 dependencies = [
-    "launchdarkly-server-sdk-ai>=0.18.0",
+    "launchdarkly-server-sdk-ai>=0.19.0",
     "openai>=1.0.0",
 ]
 

packages/sdk/server-ai/CHANGELOG.md

@@ -2,6 +2,46 @@
 
 All notable changes to the LaunchDarkly Python AI package will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org).
 
+## [0.19.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-0.18.0...launchdarkly-server-sdk-ai-0.19.0) (2026-05-05)
+
+
+### ⚠ BREAKING CHANGES
+
+* StructuredResponse replaced by RunnerResult with new "parsed" property
+* AgentResult replaced by RunnerResult and Managed Result
+* Removed ModelRunner and AgentRunner protocols
+* Removed invoke_model, invoke_structured_model from AIProvider base class.
+* ModelResponse was replaced by RunnerResult
+* Add ManagedResult, RunnerResult, and Runner protocol; rename invoke() to run() ([#148](https://github.com/launchdarkly/python-server-sdk-ai/issues/148))
+* Swap track_metrics_of parameter order to match spec ([#144](https://github.com/launchdarkly/python-server-sdk-ai/issues/144))
+
+### Features
+
+* Add evaluations support to ManagedAgent.run() ([#153](https://github.com/launchdarkly/python-server-sdk-ai/issues/153)) ([442f46a](https://github.com/launchdarkly/python-server-sdk-ai/commit/442f46aa65996a4b986e9421a3348180a43b520e))
+* Add judge evaluation support to agent graphs ([#142](https://github.com/launchdarkly/python-server-sdk-ai/issues/142)) ([3d5a6a9](https://github.com/launchdarkly/python-server-sdk-ai/commit/3d5a6a91a87c7475a83a7e440cd4b71337cfd56f))
+* Add ManagedGraphResult, GraphMetricSummary, and AgentGraphRunnerResult types ([#151](https://github.com/launchdarkly/python-server-sdk-ai/issues/151)) ([301e24c](https://github.com/launchdarkly/python-server-sdk-ai/commit/301e24c3f84168ba8f4fed2a172c0391b3017c29))
+* Add ManagedResult, RunnerResult, and Runner protocol; rename invoke() to run() ([#148](https://github.com/launchdarkly/python-server-sdk-ai/issues/148)) ([88d4ddc](https://github.com/launchdarkly/python-server-sdk-ai/commit/88d4ddce26c17fbf5509802367156e50a66d0a68))
+* Add root-level tools map with customParameters to AI Config types ([#141](https://github.com/launchdarkly/python-server-sdk-ai/issues/141)) ([f17c535](https://github.com/launchdarkly/python-server-sdk-ai/commit/f17c53571e707a46c695f0955163776a2999f49a))
+* bake sampling_rate into Judge at construction; simplify Evaluator to List[Judge] ([#159](https://github.com/launchdarkly/python-server-sdk-ai/issues/159)) ([86c79e6](https://github.com/launchdarkly/python-server-sdk-ai/commit/86c79e6a65c88cf9f59e8ed8ca4d29897b5ce059))
+* Update LangChain runners to implement Runner protocol returning RunnerResult ([#150](https://github.com/launchdarkly/python-server-sdk-ai/issues/150)) ([62a8e25](https://github.com/launchdarkly/python-server-sdk-ai/commit/62a8e252f4389884fa2f6a90e325db4a8f79376a))
+
+
+### Bug Fixes
+
+* Add runtime DeprecationWarnings to deprecated methods ([#145](https://github.com/launchdarkly/python-server-sdk-ai/issues/145)) ([2189b81](https://github.com/launchdarkly/python-server-sdk-ai/commit/2189b812df257e122d7c7001158a219d34d9e3d0))
+* AgentResult replaced by RunnerResult and Managed Result ([fbb0b4b](https://github.com/launchdarkly/python-server-sdk-ai/commit/fbb0b4b45090144e3cb14d3966ed46a2884518fb))
+* build judge input as string; strip legacy judge config messages ([#165](https://github.com/launchdarkly/python-server-sdk-ai/issues/165)) ([e6942a6](https://github.com/launchdarkly/python-server-sdk-ai/commit/e6942a6e2d4db17ae1fa6191521f8ac4fb48f30d))
+* Fall back to model.parameters.tools when root tools absent ([#146](https://github.com/launchdarkly/python-server-sdk-ai/issues/146)) ([2c30d75](https://github.com/launchdarkly/python-server-sdk-ai/commit/2c30d75a7df83207e8ff13bcb1af30e001554e8a))
+* Graph tracking refactor — ManagedAgentGraph drives tracking for new runner shape ([#154](https://github.com/launchdarkly/python-server-sdk-ai/issues/154)) ([20a5020](https://github.com/launchdarkly/python-server-sdk-ai/commit/20a50206a58b3aa1c0d256955a3dfda59a1e20f6))
+* ModelResponse was replaced by RunnerResult ([fbb0b4b](https://github.com/launchdarkly/python-server-sdk-ai/commit/fbb0b4b45090144e3cb14d3966ed46a2884518fb))
+* parse model.parameters.tools as list ([#160](https://github.com/launchdarkly/python-server-sdk-ai/issues/160)) ([fb53e99](https://github.com/launchdarkly/python-server-sdk-ai/commit/fb53e99ea66634ee79867494535a28d3eac37646))
+* reference correct PyPI package names in provider load error messages ([#164](https://github.com/launchdarkly/python-server-sdk-ai/issues/164)) ([48761c9](https://github.com/launchdarkly/python-server-sdk-ai/commit/48761c998d58aa8ca2f8bbbe8a886e395d3a431a))
+* Removed invoke_model, invoke_structured_model from AIProvider base class. ([fbb0b4b](https://github.com/launchdarkly/python-server-sdk-ai/commit/fbb0b4b45090144e3cb14d3966ed46a2884518fb))
+* Removed ModelRunner and AgentRunner protocols ([fbb0b4b](https://github.com/launchdarkly/python-server-sdk-ai/commit/fbb0b4b45090144e3cb14d3966ed46a2884518fb))
+* Replace done_callback with coroutine chain for judge tracking ([#147](https://github.com/launchdarkly/python-server-sdk-ai/issues/147)) ([1e1f36b](https://github.com/launchdarkly/python-server-sdk-ai/commit/1e1f36b08ba28dafa4eb7b1dc8e192ef6a0891ad))
+* StructuredResponse replaced by RunnerResult with new "parsed" property ([fbb0b4b](https://github.com/launchdarkly/python-server-sdk-ai/commit/fbb0b4b45090144e3cb14d3966ed46a2884518fb))
+* Swap track_metrics_of parameter order to match spec ([#144](https://github.com/launchdarkly/python-server-sdk-ai/issues/144)) ([53db736](https://github.com/launchdarkly/python-server-sdk-ai/commit/53db736e71fbdcb0cd83e4ed20ce1b8c1084db78))
+
 ## [0.18.0](https://github.com/launchdarkly/python-server-sdk-ai/compare/launchdarkly-server-sdk-ai-0.17.0...launchdarkly-server-sdk-ai-0.18.0) (2026-04-21)
 
 

packages/sdk/server-ai/PROVENANCE.md

@@ -9,7 +9,7 @@ To verify build provenance attestations, we recommend using the [GitHub CLI `att
 <!-- x-release-please-start-version -->
 ```
 # Set the version of the library to verify
-VERSION=0.18.0
+VERSION=0.19.0
 ```
 <!-- x-release-please-end -->
 

packages/sdk/server-ai/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "launchdarkly-server-sdk-ai"
-version = "0.18.0"  # x-release-please-version
+version = "0.19.0"  # x-release-please-version
 description = "LaunchDarkly SDK for AI"
 authors = [{name = "LaunchDarkly", email = "dev@launchdarkly.com"}]
 license = {text = "Apache-2.0"}

packages/sdk/server-ai/src/ldai/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.18.0"  # x-release-please-version
+__version__ = "0.19.0"  # x-release-please-version
 
 from ldclient import log