Bugfix/unify prompt exhibit header
* Remove dead prompt_exhibit_header overrides and legacy get_exhibit_pages
Investigation (AST call tree analysis) proved both were dead code:
1. get_exhibit_pages() in preprocessing_funcs.py had ZERO callers in the
entire codebase. It was superseded by get_exhibit_pages_new() which is
the only live path (called by preprocess.one_to_n_exhibit_chunking).
2. Client prompt_exhibit_header overrides (2-arg) in bcbs_promise and
clover prompt_calls.py were dead for two independent reasons:
a) Their only consumer (get_exhibit_pages) has zero callers
b) The live consumer (get_exhibit_pages_new) calls with 3 args —
if the resolver returned the client 2-arg function, Python would
raise TypeError. The SaaS 3-arg version was always running.
Verification:
- Programmatic AST call tree (local_scripts/call_tree_analysis.py)
confirms zero callers and signature mismatch
- Resolver test confirms all clients resolve to SaaS 3-arg implementation
- Full unit suite: 1077 passed, 0 failures
- E2E: BCBS P…
* Merged dev into bugfix/unify_prompt_exhibit_header
* Add dev dependencies for local code index
Add tree-sitter, lancedb, and tiktoken as dev dependencies for a local
codebase indexing system. The index provides hybrid search (symbol table,
call graph, semantic embeddings, BM25) for token-efficient code exploration.
The index lives in a gitignored .index/ folder — each developer builds
their own locally.
Approved-by: Katon Minhas
Bugfix/row count
* Updated lesser of statements filter; Updated lesser of prompt related to GLOBAL and STANDALONE
* Updated validate reimbursement prompt
* Update lesser of check prompt related to GLOBAL assignment
* Restructured VALIDATE_REIMBURSEMENTS_PROMPT
* Updated reimbursement primary; validate reimbursement prompt
* Updated reimb primary prompt and validate reimb prompt
* Code cleaned up. Updated unittest cases
* Updated validate reimbursement prompt
* Added logging
* Update on validate reimbursement prompt; Code clean up
* Fix Black version conflict in dependencies
* Add Black back to dependencies
* Apply black formatting and update uv.lock
* Resolve conflict
* Merge branch 'DEV' into bugfix/row_count
Approved-by: Katon Minhas
Feature/chc client
* Add CHC client pipeline with Claims Coding/Editing Determinations extraction
- Add CHC client to pipelines with regex-based extraction
- Create extraction/claims_coding_funcs.py for section extraction
- Add chc_prompts.json with non_prompt field type
- Add CHC_PROMPTS_PATH to config
- Add tests for extraction function (11 test cases)
* Add black[jupyter] for code formatting
* Format testing notebook with black
* Remove unused prompt field from chc_prompts.json
* Merged main into feature/chc-client
Approved-by: Katon Minhas
Feature/lesser table caching refactor hybrid
* chore: Remove unused duplicate main.py from shared pipeline
* fix: Correct crosswalk paths in aarete_derived.py
* chore: Remove unused documentation files from fieldExtraction
* docs: Add documentation files to documentation folder
* docs: Update README with uv setup, expanded project structure, and branching conventions
* docs: Add uv installation steps with Ubuntu/WSL emphasis
* Enable prompt caching for all remaining LLM calls
- Add _INSTRUCTION() functions for: EXHIBIT_HEADER, EXHIBIT_LINKAGE,
EXHIBIT_TITLE_MATCH, DATE_FIX, DERIVED_TERM_DATE, CHECK_PROVIDER_NAME_MATCH,
SPECIAL_CASE_ASSIGNMENT
- Update all invoke_claude() calls in saas and clover pipelines to use
cache=True with corresponding _INSTRUCTION() functions
- Add new instructions to get_cacheable_instructions() for cache warming
- Update tests for new instruction functions
Functions now using caching:
- prompt_exhibit_level
- prompt_exhibit_lesser (EXHIBIT_LEVEL_LESSER_OF)
- prompt_fee_schedule_breakout
- prompt_grouper_breakout
- prompt_special_case_assignment
- prompt_exhibit_linkage
- prompt_exhibit_header
- prompt_smart_chunked (ONE_TO_ONE templates)
- prompt_date_fix
- prompt_derived_term_date
- prompt_exhibit_title_match
- provider_name_match_check
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Reorder
* feat: Add bcbs_promise client pipeline with OFFSET_TERM extraction
- Add new bcbs_promise client with HSC-based OFFSET_TERM field extraction
- Extract full paragraph text of offset/recoupment provisions from contracts
- Derive OFFSET_INDICATOR (Y/N) from OFFSET_TERM presence
- Fix reorder_columns to preserve extra columns not in COLUMN_ORDER
- Update QC/QA output path to outputs/qc_qa/
* fix: Update dev deps and test assertions for QC/QA output path
- Add pytest/pytest-mock to dev dependencies for mypy type checking
- Update test assertions to expect outputs/qc_qa instead of qa_qc_output
* style: Apply black formatting to prompt_templates.py
* Merge main, move scripts
* Archive some scripts
* update py version
* remove .py version file
* Remove ASCII characters
* Restore testbed code
* restore tracking
* Update testbed metrics
* Enable prompt caching for CODE_LAST_CHECK, FILL_BILL_TYPE, DUAL_LOB_CHECK, and GROUPER_BREAKOUT
- Add CODE_LAST_CHECK_INSTRUCTION() for service specificity classification
- Add FILL_BILL_TYPE_INSTRUCTION() for bill type code determination
- Add DUAL_LOB_CHECK_INSTRUCTION() for Medicare/Medicaid classification
- Update code_funcs.py to use caching for CODE_LAST_CHECK, FILL_BILL_TYPE, GROUPER_BREAKOUT
- Update postprocessing_funcs.py to use caching for DUAL_LOB_CHECK
- Add new instructions to get_cacheable_instructions() for cache warming
- Add unit tests for new instruction functions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix postprocessing_funcs to remove invalid columns
* Merge branch 'main' into feature/lesser-table-caching-refactor-hybrid
* Revert prompt caching changes from aed1b73c
* update formatting
* Update imports
Approved-by: Sha Brown
Approved-by: Praneel Panchigar
Siddhant Medar