chore: require uipath-platform>=0.2.19

resolve_coded_agenthub_config lands in uipath-platform 0.2.19 (0.2.18 is already
published without it), so floor-pin >=0.2.19 to guarantee the helper is present.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Author: al3xanndru

CHANGELOG.md

@@ -6,7 +6,7 @@ All notable changes to `uipath_llm_client` (core package) will be documented in
 
 ### Changed
 - `PlatformBaseSettings.agenthub_config` now defaults to `codedagentsplayground` for design-time runs (local, Studio Web, or a debug session) instead of `None`, so coded-agent LLM calls draw the `CodedAgents.Playground` licensing pool. A deployed run — a real Orchestrator job that is neither a Studio Web project nor rooted to a debug session — still resolves to `None` (→ `AgentHub.LLM`). Callers that pass an explicit `agenthub_config` (low-code agents, evaluators via `get_chat_model(agenthub_config=...)`) override this default via `model_copy` and are unaffected; an explicit empty string is left as an opt-out. Setting `UIPATH_AGENTHUB_CONFIG` still wins over the computed default.
-- The design-time-vs-deployed decision uses the shared `resolve_coded_agenthub_config` helper from `uipath.platform` (bumped floor to `uipath-platform>=0.2.18`) so all coded frameworks (langchain / llamaindex / openai-agents) classify runs identically.
+- The design-time-vs-deployed decision uses the shared `resolve_coded_agenthub_config` helper from `uipath.platform` (bumped floor to `uipath-platform>=0.2.19`) so all coded frameworks (langchain / llamaindex / openai-agents) classify runs identically.
 
 ## [1.17.1] - 2026-07-17
 

pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
     "tenacity>=9.1.4,<10.0.0",
     "pydantic>=2.12.5,<3.0.0",
     "pydantic-settings>=2.14.0,<3.0.0",
-    "uipath-platform>=0.2.18,<1.0.0",
+    "uipath-platform>=0.2.19,<1.0.0",
 ]
 
 authors = [