Commit Graph

15 Commits

Author SHA1 Message Date
Safi 6a549e42d5 fix: four bugs — affected direction, hook root, glob fish/zsh, manifest drift (#1174 #1173 #1172 #1163)
#1174: affected.py load_graph now forces directed=True before
node_link_graph, matching the identical fix in serve.py and __main__.py.
Undirected graphs (directed:false in graph.json) were causing in_edges
to fall back to a direction-blind scan, missing true callers and
reporting false positives. Regression test added.

#1173: post-commit and post-checkout hook bodies now read
graphify-out/.graphify_root before calling _rebuild_code, falling back
to Path('.') if absent. A scoped build (graphify src/) no longer gets
silently expanded to the full repo on the next commit. Tests added.

#1172: Step 9 cleanup split into rm -f for fixed files and
find -maxdepth 1 -delete for the chunk glob. Under fish/zsh an
unmatched glob aborts the entire rm -f line, leaving temp files on disk.
Fixed in the three skillgen source fragments and regenerated.

#1163: detect_incremental type guard on stored mtime — if the manifest
contains a dict-valued mtime (schema drift from older versions), coerce
to None rather than propagating a non-numeric into comparisons.
Regression test added.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 12:40:44 +01:00
Soham Patankar fbe1e9977f feat(skills): progressive-disclosure split for all platforms (generator + drift fence) (#1121)
All-platform progressive-disclosure skill split + generator (addresses #1106).

Splits each platform's skill into a lean core (~615 lines, full default pipeline inline) + on-demand references/, generated from a single source via tools/skillgen with a CI/pre-commit drift gate. 13 hosts split, aider/devin stay monoliths. Also fixes the stale bare-path bugs across the previously hand-maintained variants and moves the always-on blocks into packaged markdown.

Verified: all 5 generator guards pass, byte-verbatim load-bearing slices, lean cores self-sufficient on the default path across all 13 split hosts, references gated to non-default branches, description preserves the graphify-out-query-first clause. Supersedes #1119 (Claude-first subset).

Known follow-up applied on top: harden _always_on() against a missing packaged file so a partial install can't brick the CLI.
2026-06-02 20:48:13 +01:00
Safi c2de9fa72f add uv-aware install detection to all skill files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-28 17:07:24 +01:00
Safi 299b6baa26 v0.8.4: SQL FK/trigger extraction, deletion pruning fixes, community label normalization
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-15 15:31:22 +01:00
Safi 23f598f3a0 fix MultiGraph crash, hollow LLM response retry, and skill --help (#796, #795, #792)
#796: add edge_data()/edge_datas() helpers in build.py that tolerate
MultiGraph/MultiDiGraph; replace all G.edges[u,v] 2-tuple call sites in
__main__.py, serve.py, wiki.py, export.py, analyze.py, benchmark.py;
fix same pattern in 10 skill file inline heredocs

#795: all 12 skill files now short-circuit on /graphify --help or -h
and print the Usage block without running any pipeline steps

#792 (hollow response): add _response_is_hollow() predicate in llm.py;
when Ollama (or any backend) returns empty/null/whitespace content or a
parsed result with no nodes/edges, rewrite finish_reason="length" so
_extract_with_adaptive_retry bisects the chunk instead of silently
dropping it; applied to _call_openai_compat, _call_claude, _call_bedrock

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-09 21:17:25 +01:00
Arjun Pramanik a15cb36dfc fix(skills): rewrite YAML descriptions from pipeline-only to trigger-oriented (#774)
10 skill-*.md files had descriptions that only described what graphify does (input->pipeline->output), not when agents should use it. This meant skills never loaded proactively on codebase questions.

Changed to hybrid descriptions that retain the pipeline summary but add trigger conditions: 'Use when user asks any question about a codebase, project content, architecture, or file relationships'.
2026-05-07 20:07:49 +01:00
Safi 005a36608a fix 7 bugs: cluster-only --graph, _is_sensitive boundaries, max_tokens 16384, prune message clarity, svelte stub source_file, svelte static imports, manifest on full rebuild + pi skill YAML fix
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-05 16:00:08 +01:00
Safi d819827ea2 fix #655 #656 #657 #658: cache dir crash, sanitize_label None, rationale file_type, token counting
#655 and #656 already fixed in cache.py and security.py.
#657: add rationale to file_type schema in all 12 skill variants; warn against inventing concept.
#658: add explicit chunk-merge step with token summation before save_semantic_cache.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-02 17:10:20 +01:00
Safi 4563b043f2 Fix 6 bugs: ID collisions, path portability, alias resolution, HTML controls, desync guard, rationale prompt
- #550: _file_stem() includes parent dir to prevent node ID collisions for same-named files
- #555: extract() relativizes source_file paths before returning for cross-machine portability
- #562: to_json() returns bool; _rebuild_code() writes report/html only if json succeeded
- #563: skill prompts store rationale as node attribute, not separate node; enforce calls direction
- #566: Show All / Hide All buttons added to HTML community panel
- #575: _import_js() resolves tsconfig.json compilerOptions.paths aliases before external fallback

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 21:44:22 +01:00
Safi 9c3d0fa517 Fix chunk temp files not cleaned up after graph build
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-21 22:21:37 +01:00
Safi 1dd4c41413 Remove Claude-specific language from platform skill files (0.4.8)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-12 21:18:20 +01:00
Safi cede5b6ca6 Fix #188: collect_files() now respects .graphifyignore; fix #195: skill.md requires general-purpose subagent type for extraction dispatch
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 18:41:48 +01:00
Safi 2a7d2f4fdc Remove Anthropic API call from transcribe.py - agent generates Whisper prompt itself
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 15:55:22 +01:00
Safi cf5d721bee Add video/audio corpus support with yt-dlp download and Whisper transcription
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 15:40:18 +01:00
Safi 9c829d7a2e release 0.3.25: Aider + Copilot CLI, directed graphs, frontmatter cache, graphifyignore parent discovery, MCP fixes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 00:56:22 +01:00