a785b64c6e
update privacy section to reflect multi-provider API usage
2026-04-06 15:28:29 +01:00
066e4ba3ef
fix install requires and privacy section to mention all platforms
2026-04-06 15:27:57 +01:00
b22c3605c4
add codex/opencode/claw always-on install, fix README commands and clustering docs
2026-04-06 15:26:58 +01:00
472d9e1e27
add MIT license and bump to 0.3.0
2026-04-06 15:18:34 +01:00
a74ab7e1b3
ci: add v3 to branch triggers
2026-04-06 15:16:29 +01:00
ba13c7060b
update README and pyproject for v3: multi-platform tagline, v3 badge and curl URL
2026-04-06 15:12:46 +01:00
2d31aa2072
document node deduplication strategy in build.py
2026-04-06 15:10:57 +01:00
58cd072a72
refactor extract.py: LanguageConfig + _extract_generic replaces 10 copy-pasted extractors (2527 → 1588 lines)
2026-04-06 15:08:38 +01:00
5ef4373ed9
fix build() dropping hyperedges when merging multiple extractions
2026-04-06 14:48:00 +01:00
ce7bfe8ff3
add --platform flag to install command with Codex/OpenCode/OpenClaw support
2026-04-06 14:40:17 +01:00
9e8db8ba3f
add platform skill files for Codex, OpenCode, and OpenClaw
2026-04-06 14:40:10 +01:00
1184e7d4d5
fix: use correct Python interpreter for pipx installs
2026-04-06 14:07:42 +01:00
d3c7f950d5
bump version to 0.2.2
2026-04-06 14:04:39 +01:00
5f02b3dfe1
fix graspologic optional, fall back to networkx louvain, add privacy section
2026-04-06 14:02:28 +01:00
5164d972ed
ci: add v2 branch to CI triggers
2026-04-06 01:29:28 +01:00
6dc07e5f99
add PyPI badge, set homepage to PyPI
2026-04-06 01:27:48 +01:00
ccdd465a08
bump version to 0.2.1
2026-04-06 01:26:53 +01:00
90fac738e2
README: explain PreToolUse hook behavior in detail
2026-04-06 01:25:32 +01:00
83c2f4245c
fix obsidian always generating, uninstall early return bug, add missing tests
2026-04-06 01:23:34 +01:00
b37f187767
README: fix CI badge to v2, update curl URL, add how it works, graphify claude install section
2026-04-06 01:16:09 +01:00
6fe4c01bb8
bump version to 0.2.0
2026-04-06 01:06:35 +01:00
a7fc2493f0
v2: confidence scores, hyperedges, rationale extraction, git hooks, Claude Code hooks
...
- confidence_score required on every edge (INFERRED: 0.4-0.9, EXTRACTED: 1.0, AMBIGUOUS: 0.1-0.3)
- semantically_similar_to edges for non-obvious cross-file conceptual links
- hyperedges for 3+ node group relationships - fixed cache and merge pipeline that was silently dropping them
- check_semantic_cache returns 4-tuple including cached_hyperedges
- extract.py: mine the "why" - module/class/function docstrings and rationale comments (# NOTE: # IMPORTANT: # HACK: # WHY: # RATIONALE: # TODO: # FIXME:) as rationale_for nodes
- skill.md: rationale_for in relation schema, doc files extract design rationale
- obsidian output opt-in (--obsidian flag) - default output is graph.html + graph.json + GRAPH_REPORT.md only
- hooks.py: post-checkout hook added alongside post-commit - graph rebuilds on branch switch
- claude install: writes .claude/settings.json PreToolUse hook on Glob/Grep - Claude checks graph before searching raw files
- README updated with all v2 features
2026-04-06 00:58:55 +01:00
494f519bf4
README: highlight multimodal capability upfront
2026-04-05 23:43:59 +01:00
d23ae1774d
v2: hypergraph support - hyperedges in graph.json, shaded regions in HTML, report section
2026-04-05 23:18:25 +01:00
e6fefa8a2c
v2: semantic similarity edges, scored higher in surprising connections
2026-04-05 23:12:47 +01:00
0f11f6a32d
v2: confidence scores on INFERRED edges, avg shown in report
2026-04-05 23:06:07 +01:00
e8b8e2039d
v2: fast --update for code-only changes, parallel AST+semantic, graphify claude install
2026-04-05 23:00:24 +01:00
e4bc87a284
README: clarify any folder works, clean up usage section
2026-04-05 22:48:23 +01:00
0a31c0862b
add git commit hook - auto-rebuilds graph after every commit
2026-04-05 22:40:34 +01:00
2a8b6c16ad
fix test_watch: update import after _run_update renamed to _notify_only
2026-04-05 20:58:23 +01:00
014758f61d
README: clarify --watch auto-sync behavior for code vs docs
2026-04-05 20:20:34 +01:00
5617a7d285
watch: auto-rebuild graph on code changes without LLM, notify on doc/image changes
2026-04-05 20:13:26 +01:00
154919bb64
correct benchmark numbers — token reduction scales with corpus size, small corpora ~1x
2026-04-05 19:44:34 +01:00
3baf316044
add real graphify output (GRAPH_REPORT.md + graph.json) for httpx and mixed-corpus worked examples
2026-04-05 19:39:11 +01:00
0fee55726d
add reproducible worked examples for httpx, karpathy-repos, and mixed-corpus benchmarks
2026-04-05 19:28:05 +01:00
c488808842
Add reproducible worked example with 7 input files and README
2026-04-05 19:19:00 +01:00
546fc0b346
README: add --watch to usage, describe --wiki in What you get
2026-04-05 17:15:35 +01:00
5ae2be8ca7
Update README: add --wiki to usage and output tree
2026-04-05 17:09:02 +01:00
fd2cc8d8a7
Surface all options post-run; wiki-first follow-ups; --update regenerates wiki
2026-04-05 17:07:57 +01:00
ef06d7d8d9
Add --wiki export: agent-crawlable knowledge wiki from graph
2026-04-05 16:54:50 +01:00
93b8ec3cde
Use graph.json for follow-up questions; bump to 0.1.6
2026-04-05 14:46:06 +01:00
e98c1b6297
fix: HTML always generated by default in Step 6, not flag-gated
2026-04-05 14:22:42 +01:00
a4ae70892a
release: 0.1.5
2026-04-05 14:18:47 +01:00
a1be5abb24
refactor: dead imports, node_community helper, split to_html and call_tool
...
- Remove unused shutil (cache.py), sys (ingest.py), inline import os (detect.py)
- Extract _node_community_map() helper - was copy-pasted 8 times across analyze.py + export.py
- Split to_html() 285-line monolith into _html_styles() + _html_script() + thin orchestrator
- Split serve.py call_tool() if/elif chain into per-tool handler functions + dispatch table
- Extract _find_node() helper shared across get_node and get_neighbors handlers
All 231 tests pass.
2026-04-05 14:01:55 +01:00
0061b36c29
fix: 5 skill gaps - graphml usage, manifest timing, graph existence checks, no-viz clarity
...
- Add --graphml to Usage table (was implemented but undocumented there)
- Remove early manifest save from --update merge step (Step 9 owns it; saving early meant failed pipelines left manifest ahead of graph)
- query/path/explain now check graph.json exists before running, with clear "run /graphify first" message
- --no-viz: clarify it skips both Obsidian vault and HTML (was contradictory)
2026-04-05 13:50:07 +01:00
c88528dfa3
perf: larger chunks + code-only fast path + timing estimates
...
- Semantic extraction chunks: 12-15 → 20-25 files (fewer subagent round trips)
- Code-only corpora skip semantic dispatch entirely (AST covers it)
- Print estimated time before extraction so the wait feels intentional
2026-04-05 13:42:11 +01:00
a7f8cab1a9
test: add end-to-end pipeline integration test
...
Covers detect → extract → build → cluster → analyze → report → export
using existing fixtures. AST-only (no LLM calls), catches regressions
in how modules connect, not just individual module behaviour.
2026-04-05 00:42:30 +01:00
fa702bd69f
after pipeline, offer to guide user through the graph
2026-04-05 00:35:47 +01:00
1cd52f191e
shorten README - cut design principles, files section, marketing padding
2026-04-05 00:31:42 +01:00
d7a54d7e14
fix critical install bug, add --graphml to pipeline, update changelog
2026-04-05 00:29:42 +01:00
Safi