14 commits

Author	SHA1	Message	Date
tobjend	011df391c2	feat: implement SORE → GBNF converter ... - Recursive descent parser for SORE syntax (+, ?, *, |, ., parens) - AST intermediate representation (_Literal, _Concat, _Alt, _Plus, _Optional, _Star) - to_gbnf(sore) → full GBNF rule string - to_gbnf_with_rules(sore, name) → named rule for composition - 15 tests covering all SORE operators and nesting patterns	2026-07-12 00:31:47 +02:00
tobjend	b516b2985d	feat: implement Reduce algorithm (Algorithm 4, TODS 2010) ... - bex/reduce.py: Faithful implementation of Reduce with support-weighted SOA edit distance, adjunction, iterative merging, and Minimize - experiments/context_eval.py: Multi-codebase support (RAGSAK + Flask), Reduce experiments with thresholds 0.05-0.4 - tests/test_reduce.py: 24 tests covering all Reduce components - Flask cloned to external_refs/flask for cross-validation Results: - RAGSAK: 12.0% coverage (First 3 symbols) - Flask: 10.7% coverage (First 3 symbols) - Reduce has minimal impact (1-2 merges per codebase at ε=0.3) - Coverage ceiling appears to be ~10-12% for prefix-based grouping	2026-07-12 00:11:38 +02:00
tobjend	dfb56a083a	WIP: language size scoring + diversity threshold (step 1 pending)	2026-07-11 22:56:42 +02:00
tobjend	710da56916	drop kORE from default ensemble, add --kore flag to opt in ... - Remove kORE from top-level imports, _ALGORITHMS, and infer_ensemble body - Add include_kore=False parameter, runs kORE only when opted in - Add --kore CLI flag threaded through all pipeline layers - Remove koreinference from --prefer choices - Keep kore.py module in repo for reference/future use - Update tests: remove test_prefer_koreinference, update algorithm assertions	2026-07-04 02:58:07 +02:00
tobjend	e3ad256321	feat: add --slice package (per-directory grouping), --include/--exclude, --verbose, drop root group inference, run full ensemble on all groups	2026-07-04 02:43:03 +02:00
tobjend	fd574da53d	feat: language-agnostic import/arg/package extraction ... - Add _classify_arg_node, _find_arglist_node, _iterate_arg_nodes, extract_arg_info, _summarize_arg_info (no per-language branches) - _find_arglist_node: drop call_suffix from fallback list - _iterate_arg_nodes: generic named-child iterator only - Add IMPORT_PATTERNS + _extract_imports (regex-based, all languages) - Add _file_to_package / _top_packages (pure relpath from project root) - Add --json output format for prompt injection - analyze_clusters returns 4-tuple with meta (files, imports, arg_patterns, packages)	2026-07-03 22:41:04 +02:00
tobjend	73b94af959	feat: cluster methods by n-gram patterns before inference ... - _extract_call_tokens filters to call-like captures only - cluster_methods groups sequences by shared 3-gram call patterns - analyze_clusters runs per-cluster CRX/iDRegEx/kORE inference - Lists 17 convention clusters for RAGSAK test code - iDRegEx and kOREInference now produce ordered grammars per cluster - (other) cluster captures diverse conventions as CRX vocabulary - min-cluster-size (default 3) and ngram-size (default 3) CLI flags	2026-07-03 21:41:46 +02:00
tobjend	2620b6e49f	feat: method-level sequence extraction via child_by_field_name('body') ... - _find_method_bodies uses tree-sitter's universal body field (9/10 grammars) - Kotlin fallback: scan children for body-like types - preprocess_by_method groups highlight captures by enclosing method body - Returns per-method sequences for k-ORE ordering analysis - analyze.py infer() now uses preprocess_by_method - Document findings in ANALYSIS.md - 97 tests pass	2026-07-03 21:34:25 +02:00
tobjend	0c7703f63b	feat: universal tag-preprocessor orchestrator with frequency filter ... - Rename bex/tag-preprocessor/ to bex/tag_preprocessor/ (valid Python package) - Add analyze.py: scan_directory, frequency_filter, infer, analyze_directory - Frequency filter removes symbols below min_coverage threshold (Phase 1.0 step 4) - infer() wires preprocess → frequency_filter → ensemble (Phase 1.0 step 5) - --dir CLI mode for running full pipeline on directories (Phase 1.0 step 6) - 9 new tests (test_analyze.py), all 94 tests pass	2026-07-03 20:58:18 +02:00
tobjend	9045769d57	feat: core+outlier analysis via min_coverage parameter, 6 new tests	2026-07-01 15:09:10 +02:00
tobjend	edd6d9d4dd	feat: implement kOREInference (Algorithm 4) with MDL scoring, add to ensemble, 79 tests	2026-07-01 14:50:09 +02:00
tobjend	6b60e0131f	clean up agent-betraying comments; fix stale test names	2026-07-01 13:26:03 +02:00
tobjend	6bf7a681ce	purge make_charts.py, examples/, full-text papers, blog_post (moved to ~/Desktop/kesai/); translate German CLI to English	2026-07-01 11:28:42 +02:00
tobjend	7c00c6713d	Initial commit: BEX-based grammar inference engine ... - CRX: direct CHARE inference (Algorithm 7, TODS 2010) - iDRegEx: k-ORE inference (Algorithm 4, arXiv 2010) - RWR₀: SORE repair (Algorithm 6, TODS 2010) - rwr²: k-ORE extraction (Algorithm 3, arXiv 2010) - SOA, k-OA, iKoa, 2T-INF, Baum-Welch - Ansible role grammar adapter - Generic YAML key-path converter - 28 tests, all passing	2026-07-01 08:01:16 +02:00