UiPath LLM Client [v1.13.1]

[1.13.1] - 2026-06-09

Fixed

• PlatformSettings now accepts non-JWT access tokens (e.g. opaque UiPath reference tokens) for UIPATH_ACCESS_TOKEN. Previously any token that was not a parseable JWT failed validation with "Invalid access token: expected JWT with at least 2 dot-separated parts". Token introspection is now best-effort: is_token_expired returns False when the token is not a parseable JWT, and the settings validator only extracts client_id when the token is a parseable JWT. Added try_parse_access_token helper in uipath.llm_client.settings.platform.utils.

UiPath LangChain Client [langchain-v1.13.1]

[1.13.1] - 2026-06-09

Fixed

• Picks up the core uipath-llm-client 1.13.1 fix allowing non-JWT access tokens (e.g. opaque UiPath reference tokens) as UIPATH_ACCESS_TOKEN, so LangChain clients built on PlatformSettings no longer fail validation with "Invalid access token: expected JWT with at least 2 dot-separated parts".

UiPath LLM Client [v1.13.0]

[1.13.0] - 2026-05-27

Added

• UiPathRequestTimeoutError (HTTP 408) and UiPathBadGatewayError (HTTP 502) exception classes. Both are registered in _STATUS_CODE_TO_EXCEPTION, re-exported from uipath.llm_client, and inherit from UiPathAPIError for compatibility with existing handlers.

Changed

• Default retry set expanded. _DEFAULT_RETRY_ON_EXCEPTIONS in uipath.llm_client.utils.retry now covers UiPathRequestTimeoutError (408), UiPathRateLimitError (429), UiPathBadGatewayError (502), UiPathServiceUnavailableError (503), UiPathGatewayTimeoutError (504), and UiPathTooManyRequestsError (529) — up from {429, 529}. Applies to every provider client (UiPathOpenAI, UiPathAnthropic*, UiPathGoogle) since they all share the same UiPathHttpxClient-backed retry transport. Retry-After / x-retry-after headers and exponential backoff with jitter behave as before.
• UiPathHttpxClient / UiPathHttpxAsyncClient default max_retries raised from 0 to 3. Callers that pass max_retries=None (or omit it entirely) now get 3 retries by default. Pass max_retries=0 explicitly to opt out — max_retries=0 continues to disable retries, so the opt-out path is unchanged.

UiPath LangChain Client [langchain-v1.13.0]

[1.13.0] - 2026-05-27

Changed

• UiPathBaseLLMClient.max_retries field default raised from 0 to 3. Every LangChain chat and embedding client built on this base (UiPathChat, UiPathChatOpenAI, UiPathAzureChatOpenAI, UiPathChatAnthropic, UiPathChatAnthropicBedrock, UiPathChatBedrock, UiPathChatBedrockConverse, UiPathChatVertexAI, UiPathChatFireworks, UiPathChatLiteLLM, plus the matching embeddings classes) now retries failed requests 3 times by default. Pass max_retries=0 explicitly to disable retries — the opt-out path is unchanged. Combined with the expanded default retry set in uipath-llm-client 1.13.0, every LangChain client now retries on HTTP 408, 429, 502, 503, 504, and 529 out of the box.
• Bumped uipath-llm-client floor to >=1.13.0 to pick up the expanded default retry set and the new UiPathRequestTimeoutError / UiPathBadGatewayError typed exceptions.

UiPath LLM Client [v1.12.2]

[1.12.2] - 2026-05-24

Changed

• Bumped the default Azure OpenAI API version from 2025-03-01-preview to 2025-04-01-preview in the OpenAI passthrough handler's base_api_config.

UiPath LangChain Client [langchain-v1.12.2]

[1.12.2] - 2026-05-24

Changed

• Bumped the default Azure OpenAI API version from 2025-03-01-preview to 2025-04-01-preview on UiPathChatOpenAI, UiPathAzureChatOpenAI, UiPathOpenAIEmbeddings, UiPathAzureOpenAIEmbeddings, UiPathChatFireworks, and UiPathFireworksEmbeddings.
• Bumped uipath-llm-client floor to >=1.12.2 to pick up the matching API version default.

UiPath LangChain Client [langchain-v1.12.1]

[1.12.1] - 2026-05-22

Changed

• get_chat_model once again routes to UiPathChatAnthropicBedrock when api_flavor == ApiFlavor.INVOKE and discovery reports modelFamily == AnthropicClaude. Other INVOKE families still use UiPathChatBedrock, and None/CONVERSE continue to use UiPathChatBedrockConverse.

UiPath LLM Client [v1.11.3]

[1.11.3] - 2026-05-21

Added

• uipath.llm_client.utils.sampling.strip_disabled_fields: eagerly nulls instance attributes whose names appear in disabled_params and whose current values match is_disabled_value. Sibling of strip_disabled_kwargs for the case where vendor SDKs (langchain-anthropic, langchain-aws) read self.<field> rather than per-call **kwargs when building request bodies. Each strip logs a warning that includes the original value so callers can see exactly what was dropped.

UiPath LangChain Client [langchain-v1.12.0]

[1.12.0] - 2026-05-21

Changed

• get_chat_model routes the AWSBEDROCK branch purely by api_flavor: ApiFlavor.INVOKE selects UiPathChatBedrock, while None or ApiFlavor.CONVERSE select UiPathChatBedrockConverse. Model family no longer influences the choice.

Removed

• The AWSBEDROCK branch no longer auto-selects UiPathChatAnthropicBedrock for ANTHROPIC_CLAUDE models. Callers who want that class can pass it via the custom_class kwarg.

UiPath LangChain Client [langchain-v1.11.3]

[1.11.3] - 2026-05-21

Fixed

• UiPathBaseLLMClient.setup_model_info now calls strip_disabled_fields after merging disabled_params, so constructor-set sampling fields (e.g. UiPathChatAnthropicBedrock(model="anthropic.claude-opus-4-7", temperature=0.7)) are nulled on the instance once disabled_params is resolved. Plugs the init-time leak called out as a known follow-up in 1.10.0 — langchain-anthropic and langchain-aws's Bedrock Converse client read self.temperature/self.top_p/etc. when serializing the request body, so the existing kwargs-level strip alone wasn't enough. A warning is logged per stripped field with the original value so the caller can see what was dropped.

Changed

• Bumped uipath-llm-client floor to >=1.11.3 to match the core release exposing strip_disabled_fields.