feat: eliminate 10k char limit on agent messages

fix: temp fix for SW schema validation

feat: allow invoke to be extended with middleware

fix: terminal chat mode

fix: terminal trace tree view

fix: focus chat input

fix: ignore env vars on auth force

feat: eval runtime factory

This sample does not rely on other models or UiPath dependencies and can run in a standalone manner.
This can be used for quick prototyping and development.

feat(CalculatorSample): adding a sample for a simple calculator

fix: Added more verbose message for authentication failures

fix: pass input_file to context builder

This will allow for programmatic execution of arbitrary functions without having to rely on scripts.

…rds_compatible

refactor(RuntimeUpdates): decouple script runtime from a generic runtime

fix: simplify cli run

fix(job_key): changed job_id to job_key

…n @infer_bindings

feat: initial implementation of list connections

fix: eval logs

fix: move trajectory_span_model

docs: add docs for uipath auth on as

1. Standardization of errors
  1. `UiPathMockResponseGenerationError` to represent errors during generation of mocked response.
  2. `UiPathNoMockFoundError` to represent that the method should not be mocked.
2. Model selection
3. Allow run examples in LLM Mocker.

# Conflicts:
#	pyproject.toml

Akshaya/mocking improvements

fix: remove @infer_bindings from ConnectionsService.retrieve methods

chore: initial version of llms.txt

Similar to ``@tool(args_schema=..`, we now support overriding `input_schema` and `output_schema`
for `@mockable` functions. This will help with dynamic schemas from resources.

…rrides

feat(MockingOverrides): allow schema overrides for mockable

feat: progress on parallelization of eval runs

test: add auth config test for backwards compatibility

feat(Mocking): pass execution trace history into LLM mocker