49 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
tobi	d2d57bc431	Merge pull request 'feat: kOREInference — Algorithm 4 iDRegEx with MDL scoring + ensemble integration' (#1) from feature/kore-inference into main	2026-07-01 14:08:18 +00:00
tobjend	90d8c69aa7	fix: broken y-axis bar chart for readability	2026-07-01 16:05:49 +02:00
tobjend	2562519718	fix: grouped bar chart with Without Dervish vs With Dervish	2026-07-01 16:04:55 +02:00
tobjend	ce4088e705	fix: chart bars use Dervish purple #853E91	2026-07-01 16:03:20 +02:00
tobjend	d96e99d84f	docs: xkcd-style chart	2026-07-01 16:02:14 +02:00
tobjend	b34e39d4b9	feat: replace single-chart Helm with cross-project convention (15 charts, 6 publishers)	2026-07-01 16:00:04 +02:00
tobjend	fbdb39bf7c	docs: syntax highlighting tags in SHOWCASE.md	2026-07-01 15:48:36 +02:00
tobjend	bc81bbdce1	docs: extra blank line above coffee button	2026-07-01 15:42:14 +02:00
tobjend	bb193d000f	docs: bump logo 180→216px	2026-07-01 15:41:55 +02:00
tobjend	4969819dbb	docs: center logo, move coffee button below nav links	2026-07-01 15:41:35 +02:00
tobjend	a70024397f	chore: ignore examples/	2026-07-01 15:40:02 +02:00
tobjend	929a50c95d	docs: add Buy Me a Coffee button	2026-07-01 15:37:09 +02:00
tobjend	0be1a7fd79	docs: badges row, nav links, language tags on code blocks	2026-07-01 15:24:00 +02:00
tobjend	5e0674bf77	docs: fix Go lint description (both optional), format outliers in SHOWCASE usage	2026-07-01 15:21:55 +02:00
tobjend	0886e5f3bc	docs: update README and SHOWCASE for kOREInference + core/outlier analysis	2026-07-01 15:18:32 +02:00
tobjend	036a84cc76	docs: add min_coverage to MCP tool + README, include core in output	2026-07-01 15:16:24 +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	dc559a4aee	fix badge position; purge remaining German user-reference comments	2026-07-01 13:28:55 +02:00
tobjend	6b60e0131f	clean up agent-betraying comments; fix stale test names	2026-07-01 13:26:03 +02:00
tobjend	dcfd8b054e	remove pull:true (image cached now)	2026-07-01 13:23:29 +02:00
tobjend	79c6a0734c	force pull of dervish-ci:latest	2026-07-01 13:22:39 +02:00
tobjend	701c5649c7	use pre-built dervish-ci image with pytest; no pip install in pipeline	2026-07-01 13:20:56 +02:00
tobjend	6191427983	fix pipeline: editable install; add CI badge to README	2026-07-01 13:19:11 +02:00
tobjend	416527c209	add Woodpecker CI: run tests on push/pull/manual	2026-07-01 13:15:53 +02:00
tobjend	b8cc40177c	remove redundant infer_grammar tool; update docs to single-tool MCP	2026-07-01 13:15:19 +02:00
tobjend	ed495d3477	gif 65%	2026-07-01 11:52:51 +02:00
tobjend	2b7541a8b1	gif 50% bigger than 37.5% = 56.25%	2026-07-01 11:40:09 +02:00
tobjend	0c91e11d4b	gif back to 75%	2026-07-01 11:39:53 +02:00
tobi	07ac315751	Update README.md	2026-07-01 09:33:02 +00:00
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	c8a49f0149	scale PNG logo to 150%	2026-07-01 11:21:02 +02:00
tobjend	923ecfd231	half the gif display size	2026-07-01 11:20:24 +02:00
tobjend	9d71763b27	restore original dervish.gif below explanation; add new logo left-aligned, smaller	2026-07-01 11:18:13 +02:00
tobjend	64c3313da9	replace logo with dervis_logo.png; add to SHOWCASE.md and blog_post.md	2026-07-01 11:16:21 +02:00
tobjend	67369f31a8	remove context-cost chart (too blatant)	2026-07-01 11:06:39 +02:00
tobjend	17b5c271ec	deduplicate: replace detailed Real-world Results with summary table linking to SHOWCASE.md	2026-07-01 11:05:26 +02:00
tobjend	b05c3ee116	rename to Dervish MCP; expand description with token-savings framing; add xkcd-style bar charts; link papers to actual URLs	2026-07-01 11:05:03 +02:00
tobjend	6d1c033267	remove Terraform showcase (everything-optional grammar isn't useful); fix GHA scope claim	2026-07-01 10:42:08 +02:00
tobjend	d7477344a6	move format-specific adapters to examples/, purge format-specific MCP tools	2026-07-01 10:36:14 +02:00
tobjend	25d844d1f9	purge Portainer references, format-specific tools, and Domain Adapters section; make showcases concrete with extracted types	2026-07-01 10:36:04 +02:00
tobjend	097dfc9954	Rename to Dervish, add animated logo to README	2026-07-01 10:19:08 +02:00
tobjend	a8a8bddb37	Move MCP server to top of README — it's the primary interface ... Restructure: MCP Server first (with agent workflow example), then Why grammar inference / showcases, then Quick Start, then details. This matches how users actually interact with the project: via MCP tools.	2026-07-01 10:18:10 +02:00
tobjend	9f5bde22d5	Remove bugs section (implementation bugs, not paper bugs), remove Docker Compose (private data), add Portainer templates, fix geerlingguy claim precision ... Blog post: remove 'The bugs we found' section (all 4 bugs were from our implementation, not the paper algorithms). Replace company data references in MCP section with Galaxy example. Update ensemble dynamics table with public datasets. README: replace Docker Compose with Portainer templates in 'Why grammar inference?' table, Real-world Results, and Domain Adapters. SHOWCASE: replace Docker Compose with Portainer templates. All claims verified: no public documentation of geerlingguy module ordering convention exists.	2026-07-01 10:15:22 +02:00
tobjend	547376894c	Update README and SHOWCASE with real-world dataset evaluations ... README: - Replace outdated company benchmarks with public showcases - Add Algorithm Selection Guide - Add 'When each algorithm wins' table - Add 'Why grammar inference?' table with value prop for LLMs - Add 'What doesn't work' section documenting failed approaches - Update all domain adapter examples with public results - Clean up outdated references (companyweb roles, hashistack terraform) SHOWCASE: - Add Helm (kube-prometheus-stack) with iDRegEx minimal core - Add Docker Compose per-project patterns - Add GitHub Actions cross-project Go lint pattern - Add Terraform modules with vocabulary analysis - Add 'What doesn't work' section - Explain WHY each dataset helps an LLM	2026-07-01 10:04:10 +02:00
tobjend	0e2aec582b	Grammar inference engine: CRX + iDRegEx ensemble with MDL scoring, MCP server, showcase, and blog post ... - Ensemble inference (infer_ensemble) runs both CRX and iDRegEx, picks best by MDL - CRX: CRX algorithm for wide coverage (accepts all sequences, large vocabulary) - iDRegEx: iDRegEx for minimal core grammar (tightest common pattern) - MDL scoring: fixed model_cost to count alphabet symbol occurrences, fixed dispatch order in _count_words_fast - Fixed _match_tokens: rewritten as _match_possible with proper backtracking - Fixed _parse_parts disjunction: children use _parse_flat_symbol to avoid dot-splitting - MCP server: infer_best_grammar and infer_grammar tools - Added prefer parameter (crx/idregex) to skip ensemble - 28 passing tests - SHOWCASE.md with Geerlingguy Galaxy demonstration - blog_post.md with full technical deep-dive	2026-07-01 09:51:41 +02:00
tobjend	a1567bffbe	Add bin/mcp-server wrapper script for robust path resolution ... Avoids module shadowing when CWD contains another bex package.	2026-07-01 08:06:17 +02:00
tobjend	adc52c99ec	Add MCP server: grammar inference via FastMCP ... - bex/mcp_server.py: FastMCP server with 3 tools: * infer_grammar(sequences, method='crx'|'idregex') * infer_yaml_grammar(yaml_dir, pattern, method) * infer_ansible_role_grammar(roles_dir) - pyproject.toml: add bex-mcp console_scripts entry point	2026-07-01 08:03:10 +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