v1.1.9

Changed

• Added type checking for chat completion messages
• Made chat.py string consts private to hide from docs
• Updated form_prompt_string to operate on a copy of input messages

v1.1.8

Added

• Add new Claude models: claude-opus-4-0, claude-sonnet-4-0

v1.1.7

• Updated chat.py to handle the Responses API instructions parameter

v1.1.6

• Added chat.py for formatting OpenAI chat messages into prompt strings.

v1.1.5

• Update link in docstring

v1.1.4

Changed

• Update default model to gpt-4.1-mini

v1.1.3

Changed

• Add server side max_timeout
• Add validation check for timeout to be > 0

v1.1.2

Changed

• Update query_ease default criteria
• Add getter functions for _TLM_DEFAULT_MODEL, _DEFAULT_TLM_QUALITY_PRESET, _TLM_DEFAULT_CONTEXT_LIMIT, _TLM_MAX_TOKEN_RANGE.
• Add unit tests for the getter functions.

v1.1.1

Changed

• Improved validation + error messages for TLM's custom_eval_criteria.
• Changed TLMOptions text in docs to have link to TLMOptions class

v1.1.0

Changed

• All .prompt() / .get_trustworthiness_score() / .generate() / .score() methods will now catch any errors and return null values alongside a log of why the exception occurred
• try_ methods are deprecated and will share the same functionality as the "non-try" methods