Merged in feature/further-phase-1-and-2-fixes (pull request #624)

Sonnet 4 and model aliasing

* Add EXHIBIT_HEADER_MARKERS for improved document header recognition in table handling

* Refactor EXHIBIT_HEADER_MARKERS definition for improved clarity and organization

* remove unused page span tracking code; add unit tests for new functionality

* remove debugging logs from combine_continuous_tables function

* Refactor logging setup and update test file configuration in investment field testing notebook

* Merge remote-tracking branch 'origin/main' into feature/further-phase-1-and-2-fixes

* Merge remote-tracking branch 'origin/main' into feature/further-phase-1-and-2-fixes

* Refactor model ID handling and add support for model aliases in llm_utils

* Update model IDs to use alias in LLM invocation functions in one_to_n_funcs

* change pre-and-post-processing to new model alias method

* Update model ID references to use 'sonnet_latest' in LLM invocation functions

* Update LLM invocation functions to use 'sonnet_latest' model ID

* Update LLM invocation functions to use 'sonnet_latest' and 'haiku_latest' model IDs

* update invoke_claude function docstring

* Fix caller frame to address mypy error


Approved-by: Katon Minhas

fieldExtraction/src/utils/string_utils.py

@@ -214,7 +214,7 @@ def secondary_string_to_dict(dict_string: str, filename: str) -> dict:
             try:
                 prompt = preprocessing_prompts.FIX_JSON(dict_substring)
                 dict_substring = llm_utils.invoke_claude(
-                    prompt, config.MODEL_ID_CLAUDE3_HAIKU, filename
+                    prompt, "haiku_latest", filename
                 )
                 result_dict = json.loads(dict_substring)
             except Exception as e: