diff --git a/README.md b/README.md index bd1dff423..d473c5e2c 100644 --- a/README.md +++ b/README.md @@ -224,6 +224,7 @@ for example `graphify claude install --project` or `graphify codex install --pro | Cursor | `graphify cursor install` | | Devin CLI | `graphify devin install` | | Google Antigravity | `graphify antigravity install` | +| MiMo Code | `graphify install --platform mimo` | Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. CodeBuddy uses the same Agent tool and PreToolUse hook mechanism as Claude Code. Factory Droid uses the `Task` tool for parallel subagent dispatch. OpenClaw and Aider use sequential extraction (parallel agent support is still early on those platforms). Trae uses the Agent tool for parallel subagent dispatch and does **not** support `PreToolUse` hooks, so AGENTS.md is the always-on mechanism. @@ -293,6 +294,7 @@ Run this once in your project after building a graph: | Pi coding agent | `graphify pi install` | | Devin CLI | `graphify devin install` | | Google Antigravity | `graphify antigravity install` | +| MiMo Code | `graphify mimo install` | This writes a small config file that tells your assistant to consult the knowledge graph for codebase questions, preferring scoped queries like `graphify query ""` over reading the full report or grepping raw files. diff --git a/graphify/__main__.py b/graphify/__main__.py index 8d37c911e..4b9329969 100644 --- a/graphify/__main__.py +++ b/graphify/__main__.py @@ -650,6 +650,12 @@ def _skill_registration(skill_path: str = "~/.claude/skills/graphify/SKILL.md") "skill_dst": Path(".config") / "devin" / "skills" / "graphify" / "SKILL.md", "claude_md": False, }, + "mimo": { + "skill_file": "skill-mimo.md", + "skill_dst": Path(".mimo") / "skills" / "graphify" / "SKILL.md", + "claude_md": False, + "skill_refs": "mimo", + }, } # CLI-only platform aliases, resolved to a real _PLATFORM_CONFIG key before @@ -1843,7 +1849,7 @@ def _project_install(platform_name: str, project_dir: Path | None = None) -> Non elif platform_name == "kiro": _kiro_install(project_dir) _print_project_git_add_hint([project_dir / ".kiro"]) - elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"): + elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes", "mimo"): skill_dst = _copy_skill_file(platform_name, project=True, project_dir=project_dir) _agents_install(project_dir, platform_name) hint_paths = [_project_scope_root(skill_dst, project_dir), project_dir / "AGENTS.md"] @@ -1886,7 +1892,7 @@ def _project_uninstall(platform_name: str, project_dir: Path | None = None) -> N _cursor_uninstall(project_dir) elif platform_name == "kiro": _kiro_uninstall(project_dir) - elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"): + elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes", "mimo"): _remove_skill_file(platform_name, project=True, project_dir=project_dir) _agents_uninstall(project_dir, platform=platform_name) if platform_name == "codex": diff --git a/graphify/skill-mimo.md b/graphify/skill-mimo.md new file mode 100644 index 000000000..8ec9ad22a --- /dev/null +++ b/graphify/skill-mimo.md @@ -0,0 +1,677 @@ +--- +name: graphify +description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools." +--- + +# /graphify + +Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. + +## Usage + +``` +/graphify # full pipeline on current directory → Obsidian vault +/graphify # full pipeline on specific path +/graphify https://github.com// # clone repo then run full pipeline on it +/graphify https://github.com// --branch # clone a specific branch +/graphify ... # clone multiple repos, build each, merge into one cross-repo graph +/graphify --mode deep # thorough extraction, richer INFERRED edges +/graphify --update # incremental - re-extract only new/changed files +/graphify --directed # build directed graph (preserves edge direction: source→target) +/graphify --whisper-model medium # use a larger Whisper model for better transcription accuracy +/graphify --cluster-only # rerun clustering on existing graph +/graphify --no-viz # skip visualization, just report + JSON +/graphify --html # (HTML is generated by default - this flag is a no-op) +/graphify --svg # also export graph.svg (embeds in Notion, GitHub) +/graphify --graphml # export graph.graphml (Gephi, yEd) +/graphify --neo4j # generate graphify-out/cypher.txt for Neo4j +/graphify --neo4j-push bolt://localhost:7687 # push directly to Neo4j +/graphify --falkordb # generate graphify-out/cypher.txt for FalkorDB +/graphify --falkordb-push falkordb://localhost:6379 # push directly to FalkorDB +/graphify --mcp # start MCP stdio server for agent access +/graphify --watch # watch folder, auto-rebuild on code changes (no LLM needed) +/graphify --wiki # build agent-crawlable wiki (index.md + one article per community) +/graphify --obsidian --obsidian-dir ~/vaults/my-project # write vault to custom path (e.g. existing vault) +/graphify add # fetch URL, save to ./raw, update graph +/graphify add --author "Name" # tag who wrote it +/graphify add --contributor "Name" # tag who added it to the corpus +/graphify query "" # BFS traversal - broad context +/graphify query "" --dfs # DFS - trace a specific path +/graphify query "" --budget 1500 # cap answer at N tokens +/graphify path "AuthModule" "Database" # shortest path between two concepts +/graphify explain "SwinTransformer" # plain-language explanation of a node +``` + +## What graphify is for + +Drop any folder of code, docs, papers, images, or video into graphify and get a queryable knowledge graph. Persistent across sessions, honest audit trail (EXTRACTED/INFERRED/AMBIGUOUS), community detection surfaces cross-document connections you wouldn't think to ask about. + +## What You Must Do When Invoked + +If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the path to `.`. Just print the Usage block and return. + +**Fast path — existing graph:** Before doing anything else, check whether `graphify-out/graph.json` exists. The expected location is `graphify-out/graph.json` relative to the **current working directory** (i.e. the project root where you are running commands). If it exists AND the user's request is a natural-language question about the codebase (e.g. "How does X work?", "What calls Y?", "Trace the data flow through Z") and NOT an explicit rebuild command (`--update`, `--cluster-only`, or a bare path/URL that implies fresh extraction): **skip Steps 1–5 entirely and jump straight to `## For /graphify query`.** Run `graphify query ""` immediately. Do not run detect. Do not check corpus size. Do not ask the user to narrow. The graph is already built — use it. + +If no path was given, use `.` (current directory). Do not ask the user for a path. + +If the path argument starts with `https://github.com/` or `http://github.com/`, treat it as a GitHub URL - run Step 0 before anything else, then continue with the resolved local path. + +Follow these steps in order. Do not skip steps. + +### Step 0 - GitHub repos and multi-path merge (only if a URL or several paths) + +Only when the path is one or more `https://github.com/...` URLs, or several local subfolders to merge. See `references/github-and-merge.md` for the clone, cross-repo merge, and monorepo flow, then continue with the resolved local path. A plain local path skips this step. + +### Step 1 - Ensure graphify is installed + +```bash +# Detect the correct Python interpreter (handles uv tool, pipx, venv, system installs) +PYTHON="" +GRAPHIFY_BIN=$(which graphify 2>/dev/null) +# 1. uv tool installs — most reliable on modern Mac/Linux +if [ -z "$PYTHON" ] && command -v uv >/dev/null 2>&1; then + _UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null) + if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi +fi +# 2. Read shebang from graphify binary (pipx and direct pip installs) +if [ -z "$PYTHON" ] && [ -n "$GRAPHIFY_BIN" ]; then + _SHEBANG=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') + case "$_SHEBANG" in + *[!a-zA-Z0-9/_.-]*) ;; + *) "$_SHEBANG" -c "import graphify" 2>/dev/null && PYTHON="$_SHEBANG" ;; + esac +fi +# 3. Fall back to python3 +if [ -z "$PYTHON" ]; then PYTHON="python3"; fi +if ! "$PYTHON" -c "import graphify" 2>/dev/null; then + if command -v uv >/dev/null 2>&1; then + uv tool install --upgrade graphifyy -q 2>&1 | tail -3 + _UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null) + if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi + else + "$PYTHON" -m pip install graphifyy -q 2>/dev/null \ + || "$PYTHON" -m pip install graphifyy -q --break-system-packages 2>&1 | tail -3 + fi +fi +# Write interpreter path for all subsequent steps (persists across invocations) +mkdir -p graphify-out +"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)" +# Save scan root so `graphify update` (no args) knows where to look next time +echo "$(cd INPUT_PATH && pwd)" > graphify-out/.graphify_root +``` + +If the import succeeds, print nothing and move straight to Step 2. + +**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.** + +### Step 2 - Detect files + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.detect import detect +from pathlib import Path +result = detect(Path('INPUT_PATH')) +print(json.dumps(result, ensure_ascii=False)) +" > graphify-out/.graphify_detect.json +``` + +Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead: + +``` +Corpus: X files · ~Y words + code: N files (.py .ts .go ...) + docs: N files (.md .txt ...) + papers: N files (.pdf ...) + images: N files + video: N files (.mp4 .mp3 ...) +``` + +Omit any category with 0 files from the summary. + +Then act on it: +- If `total_files` is 0: stop with "No supported files found in [path]." +- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names. +- If `total_words` > 2,000,000 OR `total_files` > 500: show the warning. Then compute the top 5 first-level subdirectories by file count: + - Read `scan_root` from the detect JSON (always an absolute path to the resolved INPUT_PATH). + - Concatenate all file lists across all types (`code`, `document`, `paper`, `image`, `video`). + - Filter out any path that starts with `scan_root + "/graphify-out/"` to exclude converted sidecars. + - For each file, strip the `scan_root` prefix and take the first path component. Files directly in `scan_root` with no subdirectory count as `(root)`. + - If all files are in `(root)` with no subdirectories, do not ask to narrow — no subfolders exist. Instead suggest `--no-cluster` to skip the expensive clustering step and proceed. + - Otherwise rank by count, show the top 5 with file counts, then ask which subfolder to run on. Wait for the user's answer before proceeding. +- Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not. + +### Step 2.5 - Video and audio (only if video files detected) + +Skip this step entirely if `detect` returned zero `video` files. When the corpus has video or audio, see `references/transcribe.md` to transcribe them to text first, then treat the transcripts as doc files in Step 3. + +### Step 3 - Extract entities and relationships + +**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. + +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (LLM, costs tokens). + +> **graphify needs no API key. Never ask the user for one, and never block on one.** Code is extracted structurally (AST) with no LLM and no key at all — a code-only corpus (the common `/graphify .` on a repo) skips semantic extraction entirely, so it needs nothing here: go straight to Part A and skip Part B. Semantic extraction (only for docs, papers, and images) uses Gemini **only if** `GEMINI_API_KEY`/`GOOGLE_API_KEY` is already set; otherwise the host agent itself is the LLM. graphify does **not** read `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or any other provider key. If you catch yourself about to prompt for, wait on, or stop because of a missing API key, that is a misread of this skill — proceed without one. + +**Before semantic extraction:** check whether `GEMINI_API_KEY` or `GOOGLE_API_KEY` is set. If neither is set, print this one-liner to the user: +> Tip: set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to use Gemini for semantic extraction (`pip install 'graphifyy[gemini]'`). + +Print it once, then continue — do not wait for the user to supply a key. If `GEMINI_API_KEY` or `GOOGLE_API_KEY` IS set, use `graphify.llm.extract_corpus_parallel(files, backend="gemini")` for semantic extraction instead of dispatching subagents. The default Gemini model is `gemini-3-flash-preview`; set `GRAPHIFY_GEMINI_MODEL` or pass `--model` in headless CLI flows to override it. + +> **No other API keys are read.** When `GEMINI_API_KEY`/`GOOGLE_API_KEY` are unset, semantic extraction falls to the host agent itself — the running session is the LLM. On a host that dispatches subagents (e.g. Claude Code), dispatch them as written in Part B. On a host that runs the CLI directly in a terminal and cannot dispatch subagents, do not stall: a code-only corpus has no semantic work, so write the empty semantic file (Part B "Fast path") and continue to Part C; for a corpus with docs/papers/images, either set a Gemini key or extract those inline yourself, but in no case prompt for `ANTHROPIC_API_KEY` — that prompt is a misread of this skill. + +**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** + +Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers. + +#### Part A - Structural extraction for code files + +For any code files detected, run AST extraction in parallel with Part B subagents: + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.extract import collect_files, extract +from pathlib import Path +import json + +code_files = [] +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +for f in detect.get('files', {}).get('code', []): + code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)]) + +if code_files: + result = extract(code_files, cache_root=Path('INPUT_PATH')) + Path('graphify-out/.graphify_ast.json').write_text(json.dumps(result, indent=2, ensure_ascii=False), encoding=\"utf-8\") + print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges') +else: + Path('graphify-out/.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}, ensure_ascii=False), encoding=\"utf-8\") + print('No code files - skipping AST extraction') +" +``` + +#### Part B - Semantic extraction (parallel subagents) + +**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. **First write an empty semantic file** so Part C's merge has its input (it reads `.graphify_semantic.json` unconditionally; without this a code-only run hits `FileNotFoundError`): + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +Path('graphify-out/.graphify_semantic.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8') +" +``` + +**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.** + +Before dispatching subagents, print a timing estimate: +- Load `total_words` and file counts from `graphify-out/.graphify_detect.json` +- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25) +- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit)) +- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys" + +**Step B0 - Check extraction cache first** + +Before dispatching any subagents, check which files already have cached extraction results: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.cache import check_semantic_cache +from pathlib import Path + +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +# Only content files go to semantic extraction. Code is already covered structurally +# by the AST pass (Part A); flattening every category here makes subagents re-read +# every source file (#1392). Video is transcribed to a document in Step 2.5 first. +all_files = [f for cat in ('document', 'paper', 'image') for f in detect['files'].get(cat, [])] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files, root='INPUT_PATH') + +# Always (re)write the cache file: write hits, else DELETE any leftover from a prior +# run so Part C never merges a stale .graphify_cached.json (#1392). +if cached_nodes or cached_edges or cached_hyperedges: + Path('graphify-out/.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}, ensure_ascii=False), encoding=\"utf-8\") +else: + Path('graphify-out/.graphify_cached.json').unlink(missing_ok=True) +Path('graphify-out/.graphify_uncached.txt').write_text('\n'.join(uncached), encoding=\"utf-8\") +print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction') +" +``` + +Only dispatch subagents for files listed in `graphify-out/.graphify_uncached.txt`. If all files are cached, skip to Part C directly. + +**Step B1 - Split into chunks** + +Load files from `graphify-out/.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). When splitting, group files from the same directory together so related artifacts land in the same chunk and cross-file relationships are more likely to be extracted. + +**Step B2 - Dispatch ALL subagents in a single message** + +Call the Agent tool multiple times IN THE SAME RESPONSE - one call per chunk. This is the only way they run in parallel. If you make one Agent call, wait, then make another, you are doing it sequentially and defeating the purpose. + +**IMPORTANT - subagent type:** Always use `subagent_type="general-purpose"`. Do NOT use `Explore` - it is read-only and cannot write chunk files to disk, which silently drops extraction results. General-purpose has Write and Bash access which the subagent needs. + +Concrete example for 3 chunks: +``` +[Agent tool call 1: files 1-15, subagent_type="general-purpose"] +[Agent tool call 2: files 16-30, subagent_type="general-purpose"] +[Agent tool call 3: files 31-45, subagent_type="general-purpose"] +``` +All three in one message. Not three separate messages. + +Each subagent receives this exact prompt (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH). + +CHUNK_PATH must be an **absolute** path — derive it before dispatching: +```bash +PROJECT_ROOT=$(pwd) # cwd — where Part C globs graphify-out/ (NOT .graphify_root/scan dir, #1392) +# Then for chunk N: CHUNK_PATH="${PROJECT_ROOT}/graphify-out/.graphify_chunk_0N.json" +``` + +Subagent prompt template: + +See `references/extraction-spec.md` for the exact subagent prompt (JSON schema, node-ID rules, confidence rubric, frontmatter, hyperedge, and vision rules). Load it only here, only when at least one chunk holds a doc, paper, or image; a pure-code corpus has skipped Part B and never reads it. Pass each subagent that prompt verbatim with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH substituted, and have it write the result to CHUNK_PATH. + +**Step B3 - Collect, cache, and merge** + +Wait for all subagents. For each result: +- Check that `graphify-out/.graphify_chunk_NN.json` exists on disk — this is the success signal +- If the file exists and contains valid JSON with `nodes` and `edges`, include it and save to cache +- If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip. +- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort + +If more than half the chunks failed or are missing, stop and tell the user to re-run and ensure `subagent_type="general-purpose"` is used. + +Merge all chunk files into `.graphify_semantic_new.json`. **After each Agent call completes, read the real token counts from the Agent tool result's `usage` field and write them back into the chunk JSON before merging** — the chunk JSON itself always has placeholder zeros. Then run: +```bash +$(cat graphify-out/.graphify_python) -c " +import json, glob +from pathlib import Path + +chunks = sorted(glob.glob('graphify-out/.graphify_chunk_*.json')) +all_nodes, all_edges, all_hyperedges = [], [], [] +total_in, total_out = 0, 0 +for c in chunks: + d = json.loads(Path(c).read_text(encoding=\"utf-8\")) + all_nodes += d.get('nodes', []) + all_edges += d.get('edges', []) + all_hyperedges += d.get('hyperedges', []) + total_in += d.get('input_tokens', 0) + total_out += d.get('output_tokens', 0) +Path('graphify-out/.graphify_semantic_new.json').write_text(json.dumps({ + 'nodes': all_nodes, 'edges': all_edges, 'hyperedges': all_hyperedges, + 'input_tokens': total_in, 'output_tokens': total_out, +}, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens') +" +``` + +Save new results to cache: +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []), root='INPUT_PATH') +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `graphify-out/.graphify_semantic.json`: +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path + +cached = json.loads(Path('graphify-out/.graphify_cached.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} + +all_nodes = cached['nodes'] + new.get('nodes', []) +all_edges = cached['edges'] + new.get('edges', []) +all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', []) +seen = set() +deduped = [] +for n in all_nodes: + if n['id'] not in seen: + seen.add(n['id']) + deduped.append(n) + +merged = { + 'nodes': deduped, + 'edges': all_edges, + 'hyperedges': all_hyperedges, + 'input_tokens': new.get('input_tokens', 0), + 'output_tokens': new.get('output_tokens', 0), +} +Path('graphify-out/.graphify_semantic.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)') +" +``` +Clean up temp files: `rm -f graphify-out/.graphify_cached.json graphify-out/.graphify_uncached.txt graphify-out/.graphify_semantic_new.json` + +#### Part C - Merge AST + semantic into final extraction + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('graphify-out/.graphify_ast.json').read_text(encoding=\"utf-8\")) +sem = json.loads(Path('graphify-out/.graphify_semantic.json').read_text(encoding=\"utf-8\")) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\") +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +**Before starting:** the code blocks below pass `directed=IS_DIRECTED` to `build_from_json()`. Replace `IS_DIRECTED` with `True` if `--directed` was given (builds a `DiGraph` preserving edge direction source→target), otherwise `False` (the default undirected `Graph`). Substitute it the same way you substitute `INPUT_PATH` — do not leave the literal `IS_DIRECTED` in the code. + +```bash +mkdir -p graphify-out +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from graphify.export import to_json +from pathlib import Path + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) + +# root= mirrors the --update runbook (#1361): relativize source_file to the same +# base so the full build and incremental --update never drift apart on re-extract. +G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED) +# Guard BEFORE any write: an empty extraction must not clobber a good graph.json / +# GRAPH_REPORT.md / analysis sidecar. Check immediately after build (#1392). +if G.number_of_nodes() == 0: + print('ERROR: Graph is empty - extraction produced no nodes.') + print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.') + raise SystemExit(1) +communities = cluster(G) +cohesion = score_all(G, communities) +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} +# Placeholder questions - regenerated with real labels in Step 5 +questions = suggest_questions(G, communities, labels) + +# Export FIRST and honor the #479 shrink-guard: to_json returns False (writing +# nothing) when the new graph is smaller than the existing graph.json. Only write +# GRAPH_REPORT.md + the analysis sidecar when the graph was actually written, so +# they never describe a graph that graph.json doesn't contain (#1392). +wrote = to_json(G, communities, 'graphify-out/graph.json') +if not wrote: + print('ERROR: refused to shrink graphify-out/graph.json (existing graph has more nodes; #479).') + print('If this shrink is intentional (you deleted files), re-run a full build with --force.') + raise SystemExit(1) +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\") +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, + 'questions': questions, +} +Path('graphify-out/.graphify_analysis.json').write_text(json.dumps(analysis, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities') +" +``` + +If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization. + +Replace INPUT_PATH with the actual path. + +### Step 4.5 - Graph health check (read-only integrity gate) + +A non-destructive diagnostic on the extraction, before labeling. It surfaces edge collapse, dangling/missing endpoints, and self-loops — the silent-corruption modes of incremental updates and AST/LLM id mismatches. Read-only; never aborts. + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from graphify.diagnostics import diagnose_extraction, format_diagnostic_report + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +summary = diagnose_extraction(extraction, directed=IS_DIRECTED, root='INPUT_PATH') +print(format_diagnostic_report(summary)) +flags = [f'{summary[k]} {label}' for k, label in ( + ('dangling_endpoint_edges', 'dangling-endpoint edges'), + ('missing_endpoint_edges', 'missing-endpoint edges'), + ('self_loop_edges', 'self-loop edges'), + ('directed_same_endpoint_collapsed_edges', 'collapsed (directed) edges'), + ('undirected_same_endpoint_collapsed_edges', 'collapsed (undirected) edges'), +) if summary.get(k, 0)] +print('GRAPH HEALTH WARNING: ' + '; '.join(flags) + ' - graph may be incomplete/corrupt.' if flags else 'Graph health: OK (no dangling/missing/collapsed edges).') +" +``` + +Substitute `IS_DIRECTED` and `INPUT_PATH` as in Step 4. If a `GRAPH HEALTH WARNING` prints, surface it in the final summary (do not abort — the graph is still usable, but the integrity issue must be visible, per the Honesty Rules). + +### Step 5 - Label communities + +Read `graphify-out/.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading"). + +Then regenerate the report and save the labels for the visualizer: + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from pathlib import Path + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +analysis = json.loads(Path('graphify-out/.graphify_analysis.json').read_text(encoding=\"utf-8\")) + +# root= as in Step 4 / the --update runbook (#1361) — same base for node-key parity. +G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} + +# LABELS - replace these with the names you chose above +labels = LABELS_DICT + +# Regenerate questions with real community labels (labels affect question phrasing) +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\") +Path('graphify-out/.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}, ensure_ascii=False), encoding=\"utf-8\") +print('Report updated with community labels') +" +``` + +Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`). +Replace INPUT_PATH with the actual path. + +### Step 6 - Generate Obsidian vault (opt-in) + HTML + +**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node. + +If `--obsidian` was given: + +- If `--obsidian-dir ` was also given, pass it via `--dir`. Otherwise defaults to `graphify-out/obsidian`. + +```bash +graphify export obsidian +# or with custom dir: graphify export obsidian --dir ~/vaults/my-project +``` + +Generate the HTML graph (always, unless `--no-viz`): + +```bash +graphify export html # auto-aggregates to community view if graph > 5000 nodes +# or: graphify export html --no-viz +``` + +### Steps 6b-8 - Wiki, Neo4j, FalkorDB, SVG, GraphML, MCP, benchmark (only on their flags) + +These run only when their flag is present (`--wiki`, `--neo4j`/`--neo4j-push`, `--falkordb`/`--falkordb-push`, `--svg`, `--graphml`, `--mcp`) or, for the token-reduction benchmark, when `total_words` exceeds 5,000. A default run with no export flags skips all of them. See `references/exports.md` for each one. Run any `--wiki` export before Step 9 cleanup so `.graphify_labels.json` is still available. + +--- + +### Step 9 - Save manifest, update cost tracker, clean up, and report + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from datetime import datetime, timezone +from graphify.detect import save_manifest + +# Save manifest for --update +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +# In --update mode, 'all_files' carries the full corpus; 'files' is the changed +# subset. Full-rebuild mode populates only 'files', so the fallback handles that. +# root= relativizes the manifest keys to the scan root (same base as the build), +# so the on-disk manifest is portable across clones/machines and a later --update +# matches cached files instead of missing every one (#1417). +save_manifest(detect.get('all_files') or detect['files'], root='INPUT_PATH') + +# Update cumulative cost tracker +extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +input_tok = extract.get('input_tokens', 0) +output_tok = extract.get('output_tokens', 0) + +cost_path = Path('graphify-out/cost.json') +if cost_path.exists(): + cost = json.loads(cost_path.read_text(encoding=\"utf-8\")) +else: + cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0} + +cost['runs'].append({ + 'date': datetime.now(timezone.utc).isoformat(), + 'input_tokens': input_tok, + 'output_tokens': output_tok, + 'files': detect.get('total_files', 0), +}) +cost['total_input_tokens'] += input_tok +cost['total_output_tokens'] += output_tok +cost_path.write_text(json.dumps(cost, indent=2, ensure_ascii=False), encoding=\"utf-8\") + +print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens') +print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)') +" +rm -f graphify-out/.graphify_detect.json graphify-out/.graphify_extract.json graphify-out/.graphify_ast.json graphify-out/.graphify_semantic.json graphify-out/.graphify_analysis.json +find graphify-out -maxdepth 1 -name '.graphify_chunk_*.json' -delete 2>/dev/null +rm -f graphify-out/.needs_update 2>/dev/null || true +``` + +Replace INPUT_PATH with the actual path (same value used in Steps 4-5) so the manifest is relativized to the scan root. + +Tell the user (omit the obsidian line unless --obsidian was given): +``` +Graph complete. Outputs in PATH_TO_DIR/graphify-out/ + + graph.html - interactive graph, open in browser + GRAPH_REPORT.md - audit report + graph.json - raw graph data + obsidian/ - Obsidian vault (only if --obsidian was given) +``` + +If graphify saved you time, consider supporting it: https://github.com/sponsors/safishamsi + +Replace PATH_TO_DIR with the actual absolute path of the directory that was processed. + +Then paste these sections from GRAPH_REPORT.md directly into the chat: +- God Nodes +- Surprising Connections +- Suggested Questions + +Do NOT paste the full report - just those three sections. Keep it concise. + +Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask: + +> "The most interesting question this graph can answer: **[question]**. Want me to trace it?" + +If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report. + +The graph is the map. Your job after the pipeline is to be the guide. + +--- + +## Interpreter guard for subcommands + +Before running any subcommand below (`--update`, `--cluster-only`, `query`, `path`, `explain`, `add`), check that `.graphify_python` exists. If it's missing (e.g. user deleted `graphify-out/`), re-resolve the interpreter first: + +```bash +if [ ! -f graphify-out/.graphify_python ]; then + GRAPHIFY_BIN=$(which graphify 2>/dev/null) + if [ -n "$GRAPHIFY_BIN" ]; then + PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') + case "$PYTHON" in *[!a-zA-Z0-9/_.-]*) PYTHON="python3" ;; esac + else + PYTHON="python3" + fi + mkdir -p graphify-out + "$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)" +fi +``` + +## For --update and --cluster-only + +Both are non-default subcommands. `--update` re-extracts only new or changed files; `--cluster-only` reruns clustering on the existing graph. See `references/update.md` for both flows. + +--- + +## For /graphify query + +When `graphify-out/graph.json` already exists and the user asks a question about the corpus, answer from the graph rather than rebuilding it: + +```bash +graphify query "" +``` + +Before traversal, expand the question against the graph's own vocabulary so a wording mismatch does not collapse the answer to noise. If the `graphify query` CLI is unavailable, fall back to an inline NetworkX traversal of `graphify-out/graph.json`. Answer using only what the graph output contains, and quote `source_location` when citing a specific fact. For that vocab-expansion step, the BFS/DFS traversal modes, the `--budget` cap, the NetworkX fallback, `save-result` feedback, and the `/graphify path` and `/graphify explain` flows, see `references/query.md`. + +--- + +## For /graphify add and --watch + +Neither is part of the default build. When the user runs `/graphify add ` to fetch a URL into the corpus, or passes `--watch` to auto-rebuild on file changes, see `references/add-watch.md`. + +--- + +## For the commit hook and native CLAUDE.md integration + +When the user asks to install the post-commit auto-rebuild hook or wire graphify into a project's CLAUDE.md, see `references/hooks.md`. + +--- + +## Honesty Rules + +- Never invent an edge. If unsure, use AMBIGUOUS. +- Never skip the corpus check warning. +- Always show token cost in the report. +- Never hide cohesion scores behind symbols - show the raw number. +- Never run HTML viz on a graph with more than 5,000 nodes without warning the user. diff --git a/graphify/skills/mimo/references/add-watch.md b/graphify/skills/mimo/references/add-watch.md new file mode 100644 index 000000000..77844343e --- /dev/null +++ b/graphify/skills/mimo/references/add-watch.md @@ -0,0 +1,56 @@ +# graphify reference: add a URL and watch a folder + +Load this when the user ran `/graphify add ` or passed `--watch`. Neither is part of the default build. + +## For /graphify add + +Fetch a URL and add it to the corpus, then update the graph. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys +from graphify.ingest import ingest +from pathlib import Path + +try: + out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR') + print(f'Saved to {out}') +except ValueError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +except RuntimeError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +" +``` + +Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph. + +Supported URL types (auto-detected): +- YouTube / any video URL → audio downloaded via yt-dlp, transcribed to `.txt` on next run (requires `pip install 'graphifyy[video]'`) +- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author +- arXiv → abstract + metadata saved as `.md` +- PDF → downloaded as `.pdf` +- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Any webpage → converted to markdown via html2text + +--- + +## For --watch + +Start a background watcher that monitors a folder and auto-updates the graph when files change. + +```bash +$(cat graphify-out/.graphify_python) -m graphify.watch INPUT_PATH --debounce 3 +``` + +Replace INPUT_PATH with the folder to watch. Behavior depends on what changed: + +- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically. +- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required). + +Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file. + +Press Ctrl+C to stop. + +For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves. diff --git a/graphify/skills/mimo/references/exports.md b/graphify/skills/mimo/references/exports.md new file mode 100644 index 000000000..242ff868e --- /dev/null +++ b/graphify/skills/mimo/references/exports.md @@ -0,0 +1,87 @@ +# graphify reference: extra exports and benchmark + +Load this when the user passed one of the export flags (`--wiki`, `--neo4j`, `--neo4j-push`, `--falkordb`, `--falkordb-push`, `--svg`, `--graphml`, `--mcp`), or when the corpus is large enough for the token-reduction benchmark. Each step runs only for its own flag. + +### Step 6b - Wiki (only if --wiki flag) + +**Only run this step if `--wiki` was explicitly given in the original command.** + +Run this before Step 9 (cleanup) so `.graphify_labels.json` is still available. + +```bash +graphify export wiki +``` + +### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag) + +**If `--neo4j`** - generate a Cypher file for manual import: + +```bash +graphify export neo4j +``` + +**If `--neo4j-push `** - push directly to a running Neo4j instance. Ask the user for credentials if not provided: + +```bash +graphify export neo4j --push bolt://localhost:7687 --user neo4j --password PASSWORD +``` + +Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag) + +**If `--falkordb`** - generate a Cypher file. The statements are OpenCypher, but FalkorDB's `GRAPH.QUERY` runs one statement at a time (no bulk script import like Neo4j's `cypher-shell`), so prefer `--falkordb-push` to load a graph. Use this only when you want the portable `cypher.txt` artifact: + +```bash +graphify export falkordb +``` + +**If `--falkordb-push `** - push directly to a running FalkorDB instance. Credentials are optional; ask the user only if the instance requires auth: + +```bash +graphify export falkordb --push falkordb://localhost:6379 +``` + +Default URI is `falkordb://localhost:6379` (the scheme is informational - `redis://` or a bare `host:port` work too), auth is optional, and the target graph defaults to `graphify`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7b - SVG export (only if --svg flag) + +```bash +graphify export svg +``` + +### Step 7c - GraphML export (only if --graphml flag) + +```bash +graphify export graphml +``` + +### Step 7d - MCP server (only if --mcp flag) + +```bash +$(cat graphify-out/.graphify_python) -m graphify.serve graphify-out/graph.json +``` + +This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live. + +To configure in Claude Desktop, add to `claude_desktop_config.json`. Claude Desktop can't run `$(...)`, and under `uv tool install` the system `python3` can't import graphify — so set `command` to the **absolute interpreter path** printed by `cat graphify-out/.graphify_python`: +```json +{ + "mcpServers": { + "graphify": { + "command": "", + "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"] + } + } +} +``` + +### Step 8 - Token reduction benchmark (only if total_words > 5000) + +If `total_words` from `graphify-out/.graphify_detect.json` is greater than 5,000, run: + +```bash +graphify benchmark +``` + +Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora. diff --git a/graphify/skills/mimo/references/extraction-spec.md b/graphify/skills/mimo/references/extraction-spec.md new file mode 100644 index 000000000..2cc191978 --- /dev/null +++ b/graphify/skills/mimo/references/extraction-spec.md @@ -0,0 +1,70 @@ +# graphify reference: extraction subagent prompt + +Load this in Step 3 Part B when the corpus has at least one doc, paper, or image chunk. A pure-code corpus skips Part B and never reads this file. Each semantic subagent receives the prompt below verbatim (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH). + +``` +You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment. +Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble. + +Files (chunk CHUNK_NUM of TOTAL_CHUNKS): +FILE_LIST + +Rules: +- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2") +- INFERRED: reasonable inference (shared data structure, implied dependency) +- AMBIGUOUS: uncertain - flag for review, do not omit + +Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns). + Do not re-extract imports - AST already has those. +Doc/paper files: extract named concepts, entities, citations. For rationale (WHY decisions were made, trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT create a separate rationale node or fragment node. Only create a node for something that is itself a named entity or concept. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms, design patterns). `file_type` MUST be one of exactly these six values: `code`, `document`, `paper`, `image`, `rationale`, `concept`. Any other value is invalid and will be rejected. +Code files: when adding `calls` edges, source MUST be the caller (the function/class doing the calling), target MUST be the callee. Never reverse this direction. `calls` edges MUST stay within one language: a Python function cannot `calls` a JS/TS/Go/Rust/Java symbol and vice versa — cross-language call edges are phantom artifacts, never emit them. +Image files: use vision to understand what the image IS - do not just OCR. + UI screenshot: layout patterns, design decisions, key elements, purpose. + Chart: metric, trend/insight, data source. + Tweet/post: claim as node, author, concepts mentioned. + Diagram: components and connections. + Research figure: what it demonstrates, method, result. + Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS. + +DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps, + shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting. + +Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples: +- Two functions that both validate user input but never call each other +- A class in code and a concept in a paper that describe the same algorithm +- Two error types that handle the same failure mode differently +Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things. + +Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples: +- All classes that implement a common protocol or interface +- All functions in an authentication flow (even if they don't all call each other) +- All concepts from a paper section that form one coherent idea +Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk. + +If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author, + contributor onto every node from that file. + +confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default: +- EXTRACTED edges: confidence_score = 1.0 always +- INFERRED edges: pick exactly ONE value from this set — never 0.5: + 0.95 direct structural evidence (shared data structure, named cross-file reference). + 0.85 strong inference (clear functional alignment, no direct symbol link). + 0.75 reasonable inference (shared problem domain + similar shape, requires interpretation). + 0.65 weak inference (thematically related, no shape evidence). + 0.55 speculative but plausible (surface-level co-occurrence only). + Models follow discrete rubrics better than continuous ranges; the bimodal + distribution observed in production (>50% at 0.5, >40% at 0.85+) shows the + range guidance is being collapsed to a binary. If no value above fits, mark + the edge AMBIGUOUS rather than picking 0.4 or below. +- AMBIGUOUS edges: 0.1-0.3 + +Node ID format: lowercase, only `[a-z0-9_]`, no dots or slashes. Format: `{stem}_{entity}` where stem is `{parent_dir}_{filename_without_ext}` (the **immediate** parent directory name + the filename stem, both lowercased with non-alphanumeric chars replaced by `_`) and entity is the symbol name similarly normalized. Only one level of parent is used — not the full path. Examples: `src/auth/session.py` + `ValidateToken` → `auth_session_validatetoken`; `lib/utils/helpers.py` + `parse_url` → `utils_helpers_parse_url`; `tests/test_foo.py` + `_helper` → `tests_test_foo_helper`. Top-level files (no parent dir, e.g. `setup.py`) use just the filename stem: `setup_my_func`. This must match the ID the AST extractor generates — using just the filename (e.g., `session_validatetoken`) or the full path (e.g., `src_auth_session_validatetoken`) will create orphan ghost-duplicate nodes. If you are re-extracting a project that had ghost duplicates under the old format, the user should run `graphify extract --force` to rebuild cleanly. CRITICAL: never append chunk numbers, sequence numbers, or any suffix to an ID (no `_c1`, `_c2`, `_chunk2`, etc.). IDs must be deterministic from the label alone — the same entity must always produce the same ID regardless of which chunk processes it. + +Generate the extraction JSON matching this schema exactly: +{"nodes":[{"id":"auth_session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale|concept","source_file":"","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":""}],"input_tokens":0,"output_tokens":0} + +source_file RULE (every node, edge, and hyperedge): set source_file to the path of the originating file EXACTLY as it appears in FILE_LIST — verbatim and absolute. Do NOT shorten to a basename, do NOT re-relativize, do NOT strip any directory prefix, and do NOT change separators (the engine canonicalizes separators and relativizes against the build root downstream). Copy the FILE_LIST entry character-for-character. This keeps the full build and incremental --update on the same base, so build_merge's replace-on-re-extract matches the existing node instead of accumulating a duplicate. + +Then write the JSON to disk using the Write tool at this exact absolute path (no relative paths — Write resolves relative paths against an undefined cwd and the file will be silently lost): +CHUNK_PATH +``` diff --git a/graphify/skills/mimo/references/github-and-merge.md b/graphify/skills/mimo/references/github-and-merge.md new file mode 100644 index 000000000..a41ea06e1 --- /dev/null +++ b/graphify/skills/mimo/references/github-and-merge.md @@ -0,0 +1,46 @@ +# graphify reference: GitHub clone and cross-repo merge + +Load this when the user passed one or more `https://github.com/...` URLs, or named several local subfolders to merge into one graph. + +### Step 0 - Clone GitHub repo(s) (only if a GitHub URL was given) + +**Single repo:** +```bash +LOCAL_PATH=$(graphify clone [--branch ]) +# Use LOCAL_PATH as the target for all subsequent steps +``` + +**Multiple repos (cross-repo graph):** +```bash +# Clone each repo, run the full pipeline on each, then merge +graphify clone # → ~/.graphify/repos// +graphify clone # → ~/.graphify/repos// +# Run /graphify on each local path to produce their graph.json files +# Then merge: +graphify merge-graphs \ + ~/.graphify/repos///graphify-out/graph.json \ + ~/.graphify/repos///graphify-out/graph.json \ + --out graphify-out/cross-repo-graph.json +``` + +Graphify clones into `~/.graphify/repos//` and reuses existing clones on repeat runs. Each node in the merged graph carries a `repo` attribute so you can filter by origin. + +**Multiple local subfolders (monorepo or multi-service layout):** + +The skill pipeline writes all intermediate and final outputs to `graphify-out/` in the current working directory. Running the skill on each subfolder separately will clobber the same output dir. Instead, use the CLI directly for each subfolder — it places `graphify-out/` *inside* the scanned path: + +```bash +graphify extract ./core/ # → ./core/graphify-out/graph.json +graphify extract ./service/ # → ./service/graphify-out/graph.json +graphify extract ./platform/ # → ./platform/graphify-out/graph.json +# Add --backend gemini|kimi|openai|deepseek|claude-cli depending on which API key you have set + +# Then merge at the project root: +graphify merge-graphs \ + ./core/graphify-out/graph.json \ + ./service/graphify-out/graph.json \ + ./platform/graphify-out/graph.json \ + --out graphify-out/graph.json +``` + +Once `graphify-out/graph.json` exists, the fast path above takes over: any codebase question runs `graphify query` directly on the merged graph — no re-extraction, no size gate. diff --git a/graphify/skills/mimo/references/hooks.md b/graphify/skills/mimo/references/hooks.md new file mode 100644 index 000000000..438b8b16b --- /dev/null +++ b/graphify/skills/mimo/references/hooks.md @@ -0,0 +1,33 @@ +# graphify reference: commit hook and native CLAUDE.md integration + +Load this when the user asked to install the post-commit hook or wire graphify into a project's CLAUDE.md. + +## For git commit hook + +Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor. + +```bash +graphify hook install # install +graphify hook uninstall # remove +graphify hook status # check +``` + +After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those. + +If a post-commit hook already exists, graphify appends to it rather than replacing it. + +--- + +## For native CLAUDE.md integration + +Run once per project to make graphify always-on in Claude Code sessions: + +```bash +graphify claude install +``` + +This writes a `## graphify` section to the local `CLAUDE.md` that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions. + +```bash +graphify claude uninstall # remove the section +``` diff --git a/graphify/skills/mimo/references/query.md b/graphify/skills/mimo/references/query.md new file mode 100644 index 000000000..52321f101 --- /dev/null +++ b/graphify/skills/mimo/references/query.md @@ -0,0 +1,311 @@ +# graphify reference: query, path, explain + +Load this when the user asks a question against an existing graph, or runs `/graphify path` or `/graphify explain`. The core's query stub points here for the full traversal flow. These flows use the `graphify query` CLI when it is available and fall back to an inline NetworkX traversal otherwise. + +Two traversal modes - choose based on the question: + +| Mode | Flag | Best for | +|------|------|----------| +| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first | +| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path | + +First check the graph exists: +```bash +$(cat graphify-out/.graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +### Step 0 — Constrained query expansion (REQUIRED before traversal) + +graphify's `query` CLI matches nodes via case-folded substring + IDF — there is **no stemming, no synonyms, no cross-language match** inside the binary, and the inline fallback below matches the same way. If the user's question uses different language or different domain vocabulary than the graph's labels (user says "обработчик" / graph says "handler"; user says "authentication" / graph says "Guardian"), the literal matcher returns 0 hits and the answer collapses to noise. + +Fix this **without inventing tokens** by expanding the query against the actual graph vocabulary first: + +1. Extract the token vocabulary from node labels: +```bash +$(cat graphify-out/.graphify_python) -c " +import json, re +from pathlib import Path +data = json.loads(Path('graphify-out/graph.json').read_text()) +vocab = set() +for n in data['nodes']: + for c in re.findall(r'[^\W\d_]+', n.get('label','') or '', re.UNICODE): + parts = re.findall(r'[A-Z]+(?=[A-Z][a-z])|[A-Z]?[a-z]+|[A-Z]+', c) or [c] + for p in parts: + t = p.lower() + if 3 <= len(t) <= 30: + vocab.add(t) +Path('graphify-out/.vocab.txt').write_text('\n'.join(sorted(vocab))) +print(f'vocab: {len(vocab)} tokens') +" +``` + +2. Read `graphify-out/.vocab.txt`. Then for the user's question, select **up to 12 tokens from this exact list** that semantically match the query intent. Hard constraints: + - You MUST pick only tokens present in the vocabulary file. Do NOT invent tokens. + - If a query concept has no plausible token in the vocab, skip it — do not substitute a near-synonym from training memory. + - If **no** vocab tokens match the query at all, output an empty list and tell the user the corpus has no relevant vocabulary for this question. Do not fabricate a search. + - Translate cross-language: Russian "аутентификация" → look for `auth`, `credential`, `token`, `security` IFF present in vocab. + - Morphology: "handlers" maps to `handler` IFF present; "todos" maps to `todo` IFF present. + +3. Print the selection explicitly to the user before running the query, so the expansion is auditable: +``` +Query expanded to (from graph vocab, N tokens): [token1, token2, ...] +``` +If the list is empty, say so plainly and stop — do not proceed to traversal. + +### Step 1 — Traversal + +Build the **expanded query string** by joining the selected tokens with spaces. Use this string as `QUESTION` below — NOT the original user question. (The original question is preserved only for `save-result` at the end.) + +Prefer the CLI when it is installed: +```bash +graphify query "QUESTION" +# or: graphify query "QUESTION" --dfs --budget 3000 +``` + +If the CLI is unavailable, load `graphify-out/graph.json` and run the traversal inline: + +1. Find the 1-3 nodes whose label best matches the expanded tokens. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +question = 'QUESTION' +mode = 'MODE' # 'bfs' or 'dfs' +terms = [t.lower() for t in question.split() if len(t) >= 3] # match the vocab threshold; keeps api/jwt/ios (#1392) + +# Find best-matching start nodes +scored = [] +for nid, ndata in G.nodes(data=True): + label = ndata.get('label', '').lower() + score = sum(1 for t in terms if t in label) + if score > 0: + scored.append((score, nid)) +scored.sort(reverse=True) +start_nodes = [nid for _, nid in scored[:3]] + +if not start_nodes: + print('No matching nodes found for query terms:', terms) + sys.exit(0) + +subgraph_nodes = set() +subgraph_edges = [] + +if mode == 'dfs': + # DFS: follow one path as deep as possible before backtracking. + # Depth-limited to 6 to avoid traversing the whole graph. + visited = set() + stack = [(n, 0) for n in reversed(start_nodes)] + while stack: + node, depth = stack.pop() + if node in visited or depth > 6: + continue + visited.add(node) + subgraph_nodes.add(node) + for neighbor in G.neighbors(node): + if neighbor not in visited: + stack.append((neighbor, depth + 1)) + subgraph_edges.append((node, neighbor)) +else: + # BFS: explore all neighbors layer by layer up to depth 3. + frontier = set(start_nodes) + subgraph_nodes = set(start_nodes) + for _ in range(3): + next_frontier = set() + for n in frontier: + for neighbor in G.neighbors(n): + if neighbor not in subgraph_nodes: + next_frontier.add(neighbor) + subgraph_edges.append((n, neighbor)) + subgraph_nodes.update(next_frontier) + frontier = next_frontier + +# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token) +token_budget = BUDGET # default 2000 +char_budget = token_budget * 4 + +# Score each node by term overlap for ranked output +def relevance(nid): + label = G.nodes[nid].get('label', '').lower() + return sum(1 for t in terms if t in label) + +ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True) + +lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes'] +for nid in ranked_nodes: + d = G.nodes[nid] + lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]') +for u, v in subgraph_edges: + if u in subgraph_nodes and v in subgraph_nodes: + _raw = G[u][v]; d = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}') + +output = '\n'.join(lines) +if len(output) > char_budget: + output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)' +print(output) +" +``` + +Replace `QUESTION` with the **expanded** query string, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above, using only what the graph contains. + +After writing the answer, save it back into the graph so it improves future queries. Include the expanded tokens inside the `--answer` text (e.g. `"Expanded from original query via vocab: [tokens]. Then traversed..."`) so the next `--update` extracts the expansion history as a graph node: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "ORIGINAL_QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2 +``` + +Replace `ORIGINAL_QUESTION` with the user's verbatim question, `ANSWER` with your full answer text (containing the expanded-token trace), `NODE1 NODE2` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +**Work memory (self-improving loop).** Add an `--outcome` so future sessions learn from this one — append `--outcome useful|dead_end|corrected` to the `save-result` command (and `--correction "the right answer"` when correcting): + +- `useful` — the cited nodes answered the question well (they become *preferred sources*). +- `dead_end` — the question/path led nowhere; don't re-derive it next time. +- `corrected` — the saved answer was wrong; `--correction` records what was right. + +At the **start** of graph work, refresh and read the lessons: run `graphify reflect --if-stale` (cheap, deterministic, no LLM; `--if-stale` makes it a no-op when `LESSONS.md` is already newer than every input, e.g. when the git hook just refreshed it), then read `graphify-out/reflections/LESSONS.md`. It lists **preferred sources** (start there), **known dead ends** (skip them), and prior **corrections**. Running `reflect` yourself keeps the lessons current even without the git hook installed; if the post-commit hook *is* installed, `--if-stale` means your session-start run costs almost nothing. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. Prefer the CLI when installed: + +```bash +graphify path "NODE_A" "NODE_B" +``` + +If the CLI is unavailable, run it inline: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +a_term = 'NODE_A' +b_term = 'NODE_B' + +def find_node(term): + term = term.lower() + scored = sorted( + [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True + ) + return scored[0][1] if scored and scored[0][0] > 0 else None + +src = find_node(a_term) +tgt = find_node(b_term) + +if not src or not tgt: + print(f'Could not find nodes matching: {a_term!r} or {b_term!r}') + sys.exit(0) + +try: + path = nx.shortest_path(G, src, tgt) + print(f'Shortest path ({len(path)-1} hops):') + for i, nid in enumerate(path): + label = G.nodes[nid].get('label', nid) + if i < len(path) - 1: + _raw = G[nid][path[i+1]]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + print(f' {label} --{rel}--> [{conf}]') + else: + print(f' {label}') +except nx.NetworkXNoPath: + print(f'No path found between {a_term!r} and {b_term!r}') +except nx.NodeNotFound as e: + print(f'Node not found: {e}') +" +``` + +Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant. + +After writing the explanation, save it back: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. Prefer the CLI when installed: + +```bash +graphify explain "NODE_NAME" +``` + +If the CLI is unavailable, run it inline: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +term = 'NODE_NAME' +term_lower = term.lower() + +# Find best matching node +scored = sorted( + [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True +) +if not scored or scored[0][0] == 0: + print(f'No node matching {term!r}') + sys.exit(0) + +nid = scored[0][1] +data_n = G.nodes[nid] +print(f'NODE: {data_n.get(\"label\", nid)}') +print(f' source: {data_n.get(\"source_file\",\"unknown\")}') +print(f' type: {data_n.get(\"file_type\",\"unknown\")}') +print(f' degree: {G.degree(nid)}') +print() +print('CONNECTIONS:') +for neighbor in G.neighbors(nid): + _raw = G[nid][neighbor]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + nlabel = G.nodes[neighbor].get('label', neighbor) + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + src_file = G.nodes[neighbor].get('source_file', '') + print(f' --{rel}--> {nlabel} [{conf}] ({src_file})') +" +``` + +Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations. + +After writing the explanation, save it back: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME +``` diff --git a/graphify/skills/mimo/references/transcribe.md b/graphify/skills/mimo/references/transcribe.md new file mode 100644 index 000000000..b967f8379 --- /dev/null +++ b/graphify/skills/mimo/references/transcribe.md @@ -0,0 +1,52 @@ +# graphify reference: transcribe video and audio + +Load this only when `detect` reported one or more `video` files. A corpus with no video never reads this. + +### Step 2.5 - Transcribe video / audio files (only if video files detected) + +Skip this step entirely if `detect` returned zero `video` files. + +Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3. + +**Strategy:** Read the god nodes from `graphify-out/.graphify_detect.json` (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed. + +**However**, if the corpus has *only* video files and no other docs/code, use the generic fallback prompt: `"Use proper punctuation and paragraph breaks."` + +**Step 1 - Write the Whisper prompt yourself.** + +Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example: + +- Labels: `transformer, attention, encoder, decoder` → `"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."` +- Labels: `kubernetes, deployment, pod, helm` → `"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."` + +**Export** it as `GRAPHIFY_WHISPER_PROMPT` (the exact name the transcriber reads — and it must be `export`ed so the child Python process sees it) for the next command. + +**Step 2 - Transcribe:** + +```bash +export GRAPHIFY_WHISPER_MODEL=base # or whatever --whisper-model the user passed (must be exported) +export GRAPHIFY_WHISPER_PROMPT="" +$(cat graphify-out/.graphify_python) -c " +import json, os, sys +from pathlib import Path +from graphify.transcribe import transcribe_all + +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +video_files = detect.get('files', {}).get('video', []) +prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.') + +transcript_paths = transcribe_all(video_files, initial_prompt=prompt) +# Write the JSON from Python (NOT a shell '>' redirect): transcribe_all/Whisper +# print progress to stdout, which would otherwise corrupt the JSON file (#1392). +Path('graphify-out/.graphify_transcripts.json').write_text(json.dumps(transcript_paths, ensure_ascii=False), encoding=\"utf-8\") +print(f'Transcribed {len(transcript_paths)} file(s)', file=sys.stderr) +" +``` + +After transcription: +- Read the transcript paths from `graphify-out/.graphify_transcripts.json` +- Add them to the docs list before dispatching semantic subagents in Step 3B +- Print how many transcripts were created: `Transcribed N video file(s) -> treating as docs` +- If transcription fails for a file, print a warning and continue with the rest + +**Whisper model:** Default is `base`. If the user passed `--whisper-model `, `export GRAPHIFY_WHISPER_MODEL=` (it must be exported, not just assigned) before running the command above. diff --git a/graphify/skills/mimo/references/update.md b/graphify/skills/mimo/references/update.md new file mode 100644 index 000000000..fa2612180 --- /dev/null +++ b/graphify/skills/mimo/references/update.md @@ -0,0 +1,192 @@ +# graphify reference: incremental update and cluster-only + +Load this only when the user passed `--update` or `--cluster-only`. A first-time full build never reads this file. + +## For --update (incremental re-extraction) + +Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.detect import detect_incremental, save_manifest +from pathlib import Path + +result = detect_incremental(Path('INPUT_PATH')) +new_total = result.get('new_total', 0) +print(json.dumps(result, indent=2, ensure_ascii=False)) +Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\") +deleted = list(result.get('deleted_files', [])) +if new_total == 0 and not deleted: + print('No files changed since last run. Nothing to update.') + raise SystemExit(0) +if deleted: + print(f'{len(deleted)} deleted file(s) to prune.') +if new_total > 0: + print(f'{new_total} new/changed file(s) to re-extract.') +" +``` + +Then populate `.graphify_detect.json` so Steps 3A–6 (which read it unconditionally) see the right state for an incremental run. `files` carries the changed subset (drives Step 3A AST + Step 3B0 cache check on only what changed); `all_files` carries the full corpus for any step that needs corpus-wide context: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +r = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\")) +Path('graphify-out/.graphify_detect.json').write_text(json.dumps({ + 'files': r.get('new_files', {}), + 'all_files': r.get('files', {}), + 'total_files': r.get('new_total', 0), + 'total_words': r.get('total_words', 0), + 'skipped_sensitive': r.get('skipped_sensitive', []), + 'needs_graph': True, +}, ensure_ascii=False), encoding=\"utf-8\") +" +``` + +If new files exist, first check whether all changed files are code files: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path + +result = json.loads(open('graphify-out/.graphify_incremental.json', encoding='utf-8').read()) if Path('graphify-out/.graphify_incremental.json').exists() else {} +code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts','.lua','.toc','.f','.F','.f90','.F90','.f95','.F95','.f03','.F03','.f08','.F08'} +new_files = result.get('new_files', {}) +all_changed = [f for files in new_files.values() for f in files] +code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed) +print('code_only:', code_only) +" +``` + +If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8. + +If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal. + + +If no new files exist (only deletions), create an empty extraction so the merge step can prune: + +```bash +if [ ! -f graphify-out/.graphify_extract.json ]; then + echo '[graphify update] Only deletions -- creating empty extraction for merge.' + $(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +Path('graphify-out/.graphify_extract.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8') +" +fi +``` + + +Then: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from graphify.build import build_merge +from graphify.detect import save_manifest + +# Load new extraction and incremental state +new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\")) +deleted = list(incremental.get('deleted_files', [])) +# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are +# handled by build_merge's replace-on-re-extract (#1344): every source_file in +# new_chunks is dropped from the base before merge, so old/stale nodes don't survive. +# Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base +# as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot +# now that replace — not the dedup pass — reconciles changed files). +prune = list(deleted) or None + +# Use build_merge() — reads graph.json directly without NetworkX round-trip +# so edge direction (calls, implements, imports) is always preserved (#801). +# Pass root= so prune_sources (absolute paths from detect_incremental) are +# relativized to match the graph's relative source_file values; without it +# nothing is pruned and stale nodes accumulate on every update (#1361). +# directed=IS_DIRECTED: replace IS_DIRECTED with True if --directed was given, else +# False. Without it a --directed --update silently rebuilds undirected and collapses +# reciprocal A<->B edges (#1392). +G = build_merge( + [new_extraction], + graph_path='graphify-out/graph.json', + prune_sources=prune, + root='INPUT_PATH', + directed=IS_DIRECTED, +) +print(f'[graphify update] Merged: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges') + +# Write merged result back to .graphify_extract.json so Step 4 sees the full graph +merged_out = { + 'nodes': [{'id': n, **d} for n, d in G.nodes(data=True)], + 'edges': [ + # Explicit source/target last so they win over any stale attrs in d. + {**{k: val for k, val in d.items() if k not in ('_src', '_tgt', 'source', 'target')}, + 'source': d.get('_src', u), 'target': d.get('_tgt', v)} + for u, v, d in G.edges(data=True) + ], + # G.graph["hyperedges"] holds hyperedges from both existing graph.json + # and new_extraction (build_merge combines them). Falling back to + # new_extraction only would silently drop prior-run hyperedges (#801). + 'hyperedges': list(G.graph.get('hyperedges', [])), + 'input_tokens': new_extraction.get('input_tokens', 0), + 'output_tokens': new_extraction.get('output_tokens', 0), +} +Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged_out, ensure_ascii=False), encoding=\"utf-8\") +print(f'[graphify update] Merged extraction written ({len(merged_out[\"nodes\"])} nodes, {len(merged_out[\"edges\"])} edges)') + +# Save manifest so next --update diffs against today's state, not the +# prior run's baseline (prevents ghost-node reports on subsequent updates). +# root= matches the build_merge call above so the manifest keys stay relative to +# the scan root — portable across clones/machines, so --update keeps matching +# cached files instead of missing every one after a move (#1417). +save_manifest(incremental['files'], root='INPUT_PATH') +print('[graphify update] Manifest saved.') +" +``` + +Then run Steps 4–8 on the merged graph as normal. + +After Step 4, show the graph diff: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.analyze import graph_diff +from graphify.build import build_from_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load old graph (before update) from backup written before merge +old_data = json.loads(Path('graphify-out/.graphify_old.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_old.json').exists() else None +new_extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +G_new = build_from_json(new_extract, directed=IS_DIRECTED) + +if old_data: + G_old = json_graph.node_link_graph(old_data, edges='links') + diff = graph_diff(G_old, G_new) + print(diff['summary']) + if diff['new_nodes']: + print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5])) + if diff['new_edges']: + print('New edges:', len(diff['new_edges'])) +" +``` + +Before the merge step, save the old graph: `cp graphify-out/graph.json graphify-out/.graphify_old.json` +Clean up after: `rm -f graphify-out/.graphify_old.json` + +--- + +## For --cluster-only + +Skip Steps 1–3. Re-run clustering on the existing graph: + +```bash +graphify cluster-only . +``` + +`graphify cluster-only .` is **self-contained**: it re-clusters, names communities, and regenerates `GRAPH_REPORT.md`, `graph.json`, and `graph.html` from the existing graph. **Do not re-run Steps 5–9** — they read intermediate files (`.graphify_extract.json`, `.graphify_detect.json`, `.graphify_analysis.json`) that a prior build's cleanup (Step 9) already deleted, so they raise `FileNotFoundError` (#1392). When it finishes, present the refreshed `GRAPH_REPORT.md` summary as usual. diff --git a/tools/skillgen/expected/graphify__skill-mimo.md b/tools/skillgen/expected/graphify__skill-mimo.md new file mode 100644 index 000000000..8ec9ad22a --- /dev/null +++ b/tools/skillgen/expected/graphify__skill-mimo.md @@ -0,0 +1,677 @@ +--- +name: graphify +description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools." +--- + +# /graphify + +Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. + +## Usage + +``` +/graphify # full pipeline on current directory → Obsidian vault +/graphify # full pipeline on specific path +/graphify https://github.com// # clone repo then run full pipeline on it +/graphify https://github.com// --branch # clone a specific branch +/graphify ... # clone multiple repos, build each, merge into one cross-repo graph +/graphify --mode deep # thorough extraction, richer INFERRED edges +/graphify --update # incremental - re-extract only new/changed files +/graphify --directed # build directed graph (preserves edge direction: source→target) +/graphify --whisper-model medium # use a larger Whisper model for better transcription accuracy +/graphify --cluster-only # rerun clustering on existing graph +/graphify --no-viz # skip visualization, just report + JSON +/graphify --html # (HTML is generated by default - this flag is a no-op) +/graphify --svg # also export graph.svg (embeds in Notion, GitHub) +/graphify --graphml # export graph.graphml (Gephi, yEd) +/graphify --neo4j # generate graphify-out/cypher.txt for Neo4j +/graphify --neo4j-push bolt://localhost:7687 # push directly to Neo4j +/graphify --falkordb # generate graphify-out/cypher.txt for FalkorDB +/graphify --falkordb-push falkordb://localhost:6379 # push directly to FalkorDB +/graphify --mcp # start MCP stdio server for agent access +/graphify --watch # watch folder, auto-rebuild on code changes (no LLM needed) +/graphify --wiki # build agent-crawlable wiki (index.md + one article per community) +/graphify --obsidian --obsidian-dir ~/vaults/my-project # write vault to custom path (e.g. existing vault) +/graphify add # fetch URL, save to ./raw, update graph +/graphify add --author "Name" # tag who wrote it +/graphify add --contributor "Name" # tag who added it to the corpus +/graphify query "" # BFS traversal - broad context +/graphify query "" --dfs # DFS - trace a specific path +/graphify query "" --budget 1500 # cap answer at N tokens +/graphify path "AuthModule" "Database" # shortest path between two concepts +/graphify explain "SwinTransformer" # plain-language explanation of a node +``` + +## What graphify is for + +Drop any folder of code, docs, papers, images, or video into graphify and get a queryable knowledge graph. Persistent across sessions, honest audit trail (EXTRACTED/INFERRED/AMBIGUOUS), community detection surfaces cross-document connections you wouldn't think to ask about. + +## What You Must Do When Invoked + +If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the path to `.`. Just print the Usage block and return. + +**Fast path — existing graph:** Before doing anything else, check whether `graphify-out/graph.json` exists. The expected location is `graphify-out/graph.json` relative to the **current working directory** (i.e. the project root where you are running commands). If it exists AND the user's request is a natural-language question about the codebase (e.g. "How does X work?", "What calls Y?", "Trace the data flow through Z") and NOT an explicit rebuild command (`--update`, `--cluster-only`, or a bare path/URL that implies fresh extraction): **skip Steps 1–5 entirely and jump straight to `## For /graphify query`.** Run `graphify query ""` immediately. Do not run detect. Do not check corpus size. Do not ask the user to narrow. The graph is already built — use it. + +If no path was given, use `.` (current directory). Do not ask the user for a path. + +If the path argument starts with `https://github.com/` or `http://github.com/`, treat it as a GitHub URL - run Step 0 before anything else, then continue with the resolved local path. + +Follow these steps in order. Do not skip steps. + +### Step 0 - GitHub repos and multi-path merge (only if a URL or several paths) + +Only when the path is one or more `https://github.com/...` URLs, or several local subfolders to merge. See `references/github-and-merge.md` for the clone, cross-repo merge, and monorepo flow, then continue with the resolved local path. A plain local path skips this step. + +### Step 1 - Ensure graphify is installed + +```bash +# Detect the correct Python interpreter (handles uv tool, pipx, venv, system installs) +PYTHON="" +GRAPHIFY_BIN=$(which graphify 2>/dev/null) +# 1. uv tool installs — most reliable on modern Mac/Linux +if [ -z "$PYTHON" ] && command -v uv >/dev/null 2>&1; then + _UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null) + if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi +fi +# 2. Read shebang from graphify binary (pipx and direct pip installs) +if [ -z "$PYTHON" ] && [ -n "$GRAPHIFY_BIN" ]; then + _SHEBANG=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') + case "$_SHEBANG" in + *[!a-zA-Z0-9/_.-]*) ;; + *) "$_SHEBANG" -c "import graphify" 2>/dev/null && PYTHON="$_SHEBANG" ;; + esac +fi +# 3. Fall back to python3 +if [ -z "$PYTHON" ]; then PYTHON="python3"; fi +if ! "$PYTHON" -c "import graphify" 2>/dev/null; then + if command -v uv >/dev/null 2>&1; then + uv tool install --upgrade graphifyy -q 2>&1 | tail -3 + _UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null) + if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi + else + "$PYTHON" -m pip install graphifyy -q 2>/dev/null \ + || "$PYTHON" -m pip install graphifyy -q --break-system-packages 2>&1 | tail -3 + fi +fi +# Write interpreter path for all subsequent steps (persists across invocations) +mkdir -p graphify-out +"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)" +# Save scan root so `graphify update` (no args) knows where to look next time +echo "$(cd INPUT_PATH && pwd)" > graphify-out/.graphify_root +``` + +If the import succeeds, print nothing and move straight to Step 2. + +**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.** + +### Step 2 - Detect files + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.detect import detect +from pathlib import Path +result = detect(Path('INPUT_PATH')) +print(json.dumps(result, ensure_ascii=False)) +" > graphify-out/.graphify_detect.json +``` + +Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead: + +``` +Corpus: X files · ~Y words + code: N files (.py .ts .go ...) + docs: N files (.md .txt ...) + papers: N files (.pdf ...) + images: N files + video: N files (.mp4 .mp3 ...) +``` + +Omit any category with 0 files from the summary. + +Then act on it: +- If `total_files` is 0: stop with "No supported files found in [path]." +- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names. +- If `total_words` > 2,000,000 OR `total_files` > 500: show the warning. Then compute the top 5 first-level subdirectories by file count: + - Read `scan_root` from the detect JSON (always an absolute path to the resolved INPUT_PATH). + - Concatenate all file lists across all types (`code`, `document`, `paper`, `image`, `video`). + - Filter out any path that starts with `scan_root + "/graphify-out/"` to exclude converted sidecars. + - For each file, strip the `scan_root` prefix and take the first path component. Files directly in `scan_root` with no subdirectory count as `(root)`. + - If all files are in `(root)` with no subdirectories, do not ask to narrow — no subfolders exist. Instead suggest `--no-cluster` to skip the expensive clustering step and proceed. + - Otherwise rank by count, show the top 5 with file counts, then ask which subfolder to run on. Wait for the user's answer before proceeding. +- Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not. + +### Step 2.5 - Video and audio (only if video files detected) + +Skip this step entirely if `detect` returned zero `video` files. When the corpus has video or audio, see `references/transcribe.md` to transcribe them to text first, then treat the transcripts as doc files in Step 3. + +### Step 3 - Extract entities and relationships + +**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. + +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (LLM, costs tokens). + +> **graphify needs no API key. Never ask the user for one, and never block on one.** Code is extracted structurally (AST) with no LLM and no key at all — a code-only corpus (the common `/graphify .` on a repo) skips semantic extraction entirely, so it needs nothing here: go straight to Part A and skip Part B. Semantic extraction (only for docs, papers, and images) uses Gemini **only if** `GEMINI_API_KEY`/`GOOGLE_API_KEY` is already set; otherwise the host agent itself is the LLM. graphify does **not** read `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or any other provider key. If you catch yourself about to prompt for, wait on, or stop because of a missing API key, that is a misread of this skill — proceed without one. + +**Before semantic extraction:** check whether `GEMINI_API_KEY` or `GOOGLE_API_KEY` is set. If neither is set, print this one-liner to the user: +> Tip: set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to use Gemini for semantic extraction (`pip install 'graphifyy[gemini]'`). + +Print it once, then continue — do not wait for the user to supply a key. If `GEMINI_API_KEY` or `GOOGLE_API_KEY` IS set, use `graphify.llm.extract_corpus_parallel(files, backend="gemini")` for semantic extraction instead of dispatching subagents. The default Gemini model is `gemini-3-flash-preview`; set `GRAPHIFY_GEMINI_MODEL` or pass `--model` in headless CLI flows to override it. + +> **No other API keys are read.** When `GEMINI_API_KEY`/`GOOGLE_API_KEY` are unset, semantic extraction falls to the host agent itself — the running session is the LLM. On a host that dispatches subagents (e.g. Claude Code), dispatch them as written in Part B. On a host that runs the CLI directly in a terminal and cannot dispatch subagents, do not stall: a code-only corpus has no semantic work, so write the empty semantic file (Part B "Fast path") and continue to Part C; for a corpus with docs/papers/images, either set a Gemini key or extract those inline yourself, but in no case prompt for `ANTHROPIC_API_KEY` — that prompt is a misread of this skill. + +**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** + +Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers. + +#### Part A - Structural extraction for code files + +For any code files detected, run AST extraction in parallel with Part B subagents: + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.extract import collect_files, extract +from pathlib import Path +import json + +code_files = [] +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +for f in detect.get('files', {}).get('code', []): + code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)]) + +if code_files: + result = extract(code_files, cache_root=Path('INPUT_PATH')) + Path('graphify-out/.graphify_ast.json').write_text(json.dumps(result, indent=2, ensure_ascii=False), encoding=\"utf-8\") + print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges') +else: + Path('graphify-out/.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}, ensure_ascii=False), encoding=\"utf-8\") + print('No code files - skipping AST extraction') +" +``` + +#### Part B - Semantic extraction (parallel subagents) + +**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. **First write an empty semantic file** so Part C's merge has its input (it reads `.graphify_semantic.json` unconditionally; without this a code-only run hits `FileNotFoundError`): + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +Path('graphify-out/.graphify_semantic.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8') +" +``` + +**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.** + +Before dispatching subagents, print a timing estimate: +- Load `total_words` and file counts from `graphify-out/.graphify_detect.json` +- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25) +- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit)) +- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys" + +**Step B0 - Check extraction cache first** + +Before dispatching any subagents, check which files already have cached extraction results: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.cache import check_semantic_cache +from pathlib import Path + +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +# Only content files go to semantic extraction. Code is already covered structurally +# by the AST pass (Part A); flattening every category here makes subagents re-read +# every source file (#1392). Video is transcribed to a document in Step 2.5 first. +all_files = [f for cat in ('document', 'paper', 'image') for f in detect['files'].get(cat, [])] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files, root='INPUT_PATH') + +# Always (re)write the cache file: write hits, else DELETE any leftover from a prior +# run so Part C never merges a stale .graphify_cached.json (#1392). +if cached_nodes or cached_edges or cached_hyperedges: + Path('graphify-out/.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}, ensure_ascii=False), encoding=\"utf-8\") +else: + Path('graphify-out/.graphify_cached.json').unlink(missing_ok=True) +Path('graphify-out/.graphify_uncached.txt').write_text('\n'.join(uncached), encoding=\"utf-8\") +print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction') +" +``` + +Only dispatch subagents for files listed in `graphify-out/.graphify_uncached.txt`. If all files are cached, skip to Part C directly. + +**Step B1 - Split into chunks** + +Load files from `graphify-out/.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). When splitting, group files from the same directory together so related artifacts land in the same chunk and cross-file relationships are more likely to be extracted. + +**Step B2 - Dispatch ALL subagents in a single message** + +Call the Agent tool multiple times IN THE SAME RESPONSE - one call per chunk. This is the only way they run in parallel. If you make one Agent call, wait, then make another, you are doing it sequentially and defeating the purpose. + +**IMPORTANT - subagent type:** Always use `subagent_type="general-purpose"`. Do NOT use `Explore` - it is read-only and cannot write chunk files to disk, which silently drops extraction results. General-purpose has Write and Bash access which the subagent needs. + +Concrete example for 3 chunks: +``` +[Agent tool call 1: files 1-15, subagent_type="general-purpose"] +[Agent tool call 2: files 16-30, subagent_type="general-purpose"] +[Agent tool call 3: files 31-45, subagent_type="general-purpose"] +``` +All three in one message. Not three separate messages. + +Each subagent receives this exact prompt (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH). + +CHUNK_PATH must be an **absolute** path — derive it before dispatching: +```bash +PROJECT_ROOT=$(pwd) # cwd — where Part C globs graphify-out/ (NOT .graphify_root/scan dir, #1392) +# Then for chunk N: CHUNK_PATH="${PROJECT_ROOT}/graphify-out/.graphify_chunk_0N.json" +``` + +Subagent prompt template: + +See `references/extraction-spec.md` for the exact subagent prompt (JSON schema, node-ID rules, confidence rubric, frontmatter, hyperedge, and vision rules). Load it only here, only when at least one chunk holds a doc, paper, or image; a pure-code corpus has skipped Part B and never reads it. Pass each subagent that prompt verbatim with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH substituted, and have it write the result to CHUNK_PATH. + +**Step B3 - Collect, cache, and merge** + +Wait for all subagents. For each result: +- Check that `graphify-out/.graphify_chunk_NN.json` exists on disk — this is the success signal +- If the file exists and contains valid JSON with `nodes` and `edges`, include it and save to cache +- If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip. +- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort + +If more than half the chunks failed or are missing, stop and tell the user to re-run and ensure `subagent_type="general-purpose"` is used. + +Merge all chunk files into `.graphify_semantic_new.json`. **After each Agent call completes, read the real token counts from the Agent tool result's `usage` field and write them back into the chunk JSON before merging** — the chunk JSON itself always has placeholder zeros. Then run: +```bash +$(cat graphify-out/.graphify_python) -c " +import json, glob +from pathlib import Path + +chunks = sorted(glob.glob('graphify-out/.graphify_chunk_*.json')) +all_nodes, all_edges, all_hyperedges = [], [], [] +total_in, total_out = 0, 0 +for c in chunks: + d = json.loads(Path(c).read_text(encoding=\"utf-8\")) + all_nodes += d.get('nodes', []) + all_edges += d.get('edges', []) + all_hyperedges += d.get('hyperedges', []) + total_in += d.get('input_tokens', 0) + total_out += d.get('output_tokens', 0) +Path('graphify-out/.graphify_semantic_new.json').write_text(json.dumps({ + 'nodes': all_nodes, 'edges': all_edges, 'hyperedges': all_hyperedges, + 'input_tokens': total_in, 'output_tokens': total_out, +}, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens') +" +``` + +Save new results to cache: +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []), root='INPUT_PATH') +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `graphify-out/.graphify_semantic.json`: +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path + +cached = json.loads(Path('graphify-out/.graphify_cached.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} + +all_nodes = cached['nodes'] + new.get('nodes', []) +all_edges = cached['edges'] + new.get('edges', []) +all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', []) +seen = set() +deduped = [] +for n in all_nodes: + if n['id'] not in seen: + seen.add(n['id']) + deduped.append(n) + +merged = { + 'nodes': deduped, + 'edges': all_edges, + 'hyperedges': all_hyperedges, + 'input_tokens': new.get('input_tokens', 0), + 'output_tokens': new.get('output_tokens', 0), +} +Path('graphify-out/.graphify_semantic.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)') +" +``` +Clean up temp files: `rm -f graphify-out/.graphify_cached.json graphify-out/.graphify_uncached.txt graphify-out/.graphify_semantic_new.json` + +#### Part C - Merge AST + semantic into final extraction + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('graphify-out/.graphify_ast.json').read_text(encoding=\"utf-8\")) +sem = json.loads(Path('graphify-out/.graphify_semantic.json').read_text(encoding=\"utf-8\")) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\") +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +**Before starting:** the code blocks below pass `directed=IS_DIRECTED` to `build_from_json()`. Replace `IS_DIRECTED` with `True` if `--directed` was given (builds a `DiGraph` preserving edge direction source→target), otherwise `False` (the default undirected `Graph`). Substitute it the same way you substitute `INPUT_PATH` — do not leave the literal `IS_DIRECTED` in the code. + +```bash +mkdir -p graphify-out +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import cluster, score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from graphify.export import to_json +from pathlib import Path + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) + +# root= mirrors the --update runbook (#1361): relativize source_file to the same +# base so the full build and incremental --update never drift apart on re-extract. +G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED) +# Guard BEFORE any write: an empty extraction must not clobber a good graph.json / +# GRAPH_REPORT.md / analysis sidecar. Check immediately after build (#1392). +if G.number_of_nodes() == 0: + print('ERROR: Graph is empty - extraction produced no nodes.') + print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.') + raise SystemExit(1) +communities = cluster(G) +cohesion = score_all(G, communities) +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} +gods = god_nodes(G) +surprises = surprising_connections(G, communities) +labels = {cid: 'Community ' + str(cid) for cid in communities} +# Placeholder questions - regenerated with real labels in Step 5 +questions = suggest_questions(G, communities, labels) + +# Export FIRST and honor the #479 shrink-guard: to_json returns False (writing +# nothing) when the new graph is smaller than the existing graph.json. Only write +# GRAPH_REPORT.md + the analysis sidecar when the graph was actually written, so +# they never describe a graph that graph.json doesn't contain (#1392). +wrote = to_json(G, communities, 'graphify-out/graph.json') +if not wrote: + print('ERROR: refused to shrink graphify-out/graph.json (existing graph has more nodes; #479).') + print('If this shrink is intentional (you deleted files), re-run a full build with --force.') + raise SystemExit(1) +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\") +analysis = { + 'communities': {str(k): v for k, v in communities.items()}, + 'cohesion': {str(k): v for k, v in cohesion.items()}, + 'gods': gods, + 'surprises': surprises, + 'questions': questions, +} +Path('graphify-out/.graphify_analysis.json').write_text(json.dumps(analysis, indent=2, ensure_ascii=False), encoding=\"utf-8\") +print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities') +" +``` + +If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization. + +Replace INPUT_PATH with the actual path. + +### Step 4.5 - Graph health check (read-only integrity gate) + +A non-destructive diagnostic on the extraction, before labeling. It surfaces edge collapse, dangling/missing endpoints, and self-loops — the silent-corruption modes of incremental updates and AST/LLM id mismatches. Read-only; never aborts. + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from graphify.diagnostics import diagnose_extraction, format_diagnostic_report + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +summary = diagnose_extraction(extraction, directed=IS_DIRECTED, root='INPUT_PATH') +print(format_diagnostic_report(summary)) +flags = [f'{summary[k]} {label}' for k, label in ( + ('dangling_endpoint_edges', 'dangling-endpoint edges'), + ('missing_endpoint_edges', 'missing-endpoint edges'), + ('self_loop_edges', 'self-loop edges'), + ('directed_same_endpoint_collapsed_edges', 'collapsed (directed) edges'), + ('undirected_same_endpoint_collapsed_edges', 'collapsed (undirected) edges'), +) if summary.get(k, 0)] +print('GRAPH HEALTH WARNING: ' + '; '.join(flags) + ' - graph may be incomplete/corrupt.' if flags else 'Graph health: OK (no dangling/missing/collapsed edges).') +" +``` + +Substitute `IS_DIRECTED` and `INPUT_PATH` as in Step 4. If a `GRAPH HEALTH WARNING` prints, surface it in the final summary (do not abort — the graph is still usable, but the integrity issue must be visible, per the Honesty Rules). + +### Step 5 - Label communities + +Read `graphify-out/.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading"). + +Then regenerate the report and save the labels for the visualizer: + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.build import build_from_json +from graphify.cluster import score_all +from graphify.analyze import god_nodes, surprising_connections, suggest_questions +from graphify.report import generate +from pathlib import Path + +extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +analysis = json.loads(Path('graphify-out/.graphify_analysis.json').read_text(encoding=\"utf-8\")) + +# root= as in Step 4 / the --update runbook (#1361) — same base for node-key parity. +G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED) +communities = {int(k): v for k, v in analysis['communities'].items()} +cohesion = {int(k): v for k, v in analysis['cohesion'].items()} +tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)} + +# LABELS - replace these with the names you chose above +labels = LABELS_DICT + +# Regenerate questions with real community labels (labels affect question phrasing) +questions = suggest_questions(G, communities, labels) + +report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\") +Path('graphify-out/.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}, ensure_ascii=False), encoding=\"utf-8\") +print('Report updated with community labels') +" +``` + +Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`). +Replace INPUT_PATH with the actual path. + +### Step 6 - Generate Obsidian vault (opt-in) + HTML + +**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node. + +If `--obsidian` was given: + +- If `--obsidian-dir ` was also given, pass it via `--dir`. Otherwise defaults to `graphify-out/obsidian`. + +```bash +graphify export obsidian +# or with custom dir: graphify export obsidian --dir ~/vaults/my-project +``` + +Generate the HTML graph (always, unless `--no-viz`): + +```bash +graphify export html # auto-aggregates to community view if graph > 5000 nodes +# or: graphify export html --no-viz +``` + +### Steps 6b-8 - Wiki, Neo4j, FalkorDB, SVG, GraphML, MCP, benchmark (only on their flags) + +These run only when their flag is present (`--wiki`, `--neo4j`/`--neo4j-push`, `--falkordb`/`--falkordb-push`, `--svg`, `--graphml`, `--mcp`) or, for the token-reduction benchmark, when `total_words` exceeds 5,000. A default run with no export flags skips all of them. See `references/exports.md` for each one. Run any `--wiki` export before Step 9 cleanup so `.graphify_labels.json` is still available. + +--- + +### Step 9 - Save manifest, update cost tracker, clean up, and report + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from datetime import datetime, timezone +from graphify.detect import save_manifest + +# Save manifest for --update +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +# In --update mode, 'all_files' carries the full corpus; 'files' is the changed +# subset. Full-rebuild mode populates only 'files', so the fallback handles that. +# root= relativizes the manifest keys to the scan root (same base as the build), +# so the on-disk manifest is portable across clones/machines and a later --update +# matches cached files instead of missing every one (#1417). +save_manifest(detect.get('all_files') or detect['files'], root='INPUT_PATH') + +# Update cumulative cost tracker +extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +input_tok = extract.get('input_tokens', 0) +output_tok = extract.get('output_tokens', 0) + +cost_path = Path('graphify-out/cost.json') +if cost_path.exists(): + cost = json.loads(cost_path.read_text(encoding=\"utf-8\")) +else: + cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0} + +cost['runs'].append({ + 'date': datetime.now(timezone.utc).isoformat(), + 'input_tokens': input_tok, + 'output_tokens': output_tok, + 'files': detect.get('total_files', 0), +}) +cost['total_input_tokens'] += input_tok +cost['total_output_tokens'] += output_tok +cost_path.write_text(json.dumps(cost, indent=2, ensure_ascii=False), encoding=\"utf-8\") + +print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens') +print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)') +" +rm -f graphify-out/.graphify_detect.json graphify-out/.graphify_extract.json graphify-out/.graphify_ast.json graphify-out/.graphify_semantic.json graphify-out/.graphify_analysis.json +find graphify-out -maxdepth 1 -name '.graphify_chunk_*.json' -delete 2>/dev/null +rm -f graphify-out/.needs_update 2>/dev/null || true +``` + +Replace INPUT_PATH with the actual path (same value used in Steps 4-5) so the manifest is relativized to the scan root. + +Tell the user (omit the obsidian line unless --obsidian was given): +``` +Graph complete. Outputs in PATH_TO_DIR/graphify-out/ + + graph.html - interactive graph, open in browser + GRAPH_REPORT.md - audit report + graph.json - raw graph data + obsidian/ - Obsidian vault (only if --obsidian was given) +``` + +If graphify saved you time, consider supporting it: https://github.com/sponsors/safishamsi + +Replace PATH_TO_DIR with the actual absolute path of the directory that was processed. + +Then paste these sections from GRAPH_REPORT.md directly into the chat: +- God Nodes +- Surprising Connections +- Suggested Questions + +Do NOT paste the full report - just those three sections. Keep it concise. + +Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask: + +> "The most interesting question this graph can answer: **[question]**. Want me to trace it?" + +If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report. + +The graph is the map. Your job after the pipeline is to be the guide. + +--- + +## Interpreter guard for subcommands + +Before running any subcommand below (`--update`, `--cluster-only`, `query`, `path`, `explain`, `add`), check that `.graphify_python` exists. If it's missing (e.g. user deleted `graphify-out/`), re-resolve the interpreter first: + +```bash +if [ ! -f graphify-out/.graphify_python ]; then + GRAPHIFY_BIN=$(which graphify 2>/dev/null) + if [ -n "$GRAPHIFY_BIN" ]; then + PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!') + case "$PYTHON" in *[!a-zA-Z0-9/_.-]*) PYTHON="python3" ;; esac + else + PYTHON="python3" + fi + mkdir -p graphify-out + "$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)" +fi +``` + +## For --update and --cluster-only + +Both are non-default subcommands. `--update` re-extracts only new or changed files; `--cluster-only` reruns clustering on the existing graph. See `references/update.md` for both flows. + +--- + +## For /graphify query + +When `graphify-out/graph.json` already exists and the user asks a question about the corpus, answer from the graph rather than rebuilding it: + +```bash +graphify query "" +``` + +Before traversal, expand the question against the graph's own vocabulary so a wording mismatch does not collapse the answer to noise. If the `graphify query` CLI is unavailable, fall back to an inline NetworkX traversal of `graphify-out/graph.json`. Answer using only what the graph output contains, and quote `source_location` when citing a specific fact. For that vocab-expansion step, the BFS/DFS traversal modes, the `--budget` cap, the NetworkX fallback, `save-result` feedback, and the `/graphify path` and `/graphify explain` flows, see `references/query.md`. + +--- + +## For /graphify add and --watch + +Neither is part of the default build. When the user runs `/graphify add ` to fetch a URL into the corpus, or passes `--watch` to auto-rebuild on file changes, see `references/add-watch.md`. + +--- + +## For the commit hook and native CLAUDE.md integration + +When the user asks to install the post-commit auto-rebuild hook or wire graphify into a project's CLAUDE.md, see `references/hooks.md`. + +--- + +## Honesty Rules + +- Never invent an edge. If unsure, use AMBIGUOUS. +- Never skip the corpus check warning. +- Always show token cost in the report. +- Never hide cohesion scores behind symbols - show the raw number. +- Never run HTML viz on a graph with more than 5,000 nodes without warning the user. diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__add-watch.md b/tools/skillgen/expected/graphify__skills__mimo__references__add-watch.md new file mode 100644 index 000000000..77844343e --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__add-watch.md @@ -0,0 +1,56 @@ +# graphify reference: add a URL and watch a folder + +Load this when the user ran `/graphify add ` or passed `--watch`. Neither is part of the default build. + +## For /graphify add + +Fetch a URL and add it to the corpus, then update the graph. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys +from graphify.ingest import ingest +from pathlib import Path + +try: + out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR') + print(f'Saved to {out}') +except ValueError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +except RuntimeError as e: + print(f'error: {e}', file=sys.stderr) + sys.exit(1) +" +``` + +Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph. + +Supported URL types (auto-detected): +- YouTube / any video URL → audio downloaded via yt-dlp, transcribed to `.txt` on next run (requires `pip install 'graphifyy[video]'`) +- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author +- arXiv → abstract + metadata saved as `.md` +- PDF → downloaded as `.pdf` +- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Any webpage → converted to markdown via html2text + +--- + +## For --watch + +Start a background watcher that monitors a folder and auto-updates the graph when files change. + +```bash +$(cat graphify-out/.graphify_python) -m graphify.watch INPUT_PATH --debounce 3 +``` + +Replace INPUT_PATH with the folder to watch. Behavior depends on what changed: + +- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically. +- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required). + +Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file. + +Press Ctrl+C to stop. + +For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves. diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__exports.md b/tools/skillgen/expected/graphify__skills__mimo__references__exports.md new file mode 100644 index 000000000..242ff868e --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__exports.md @@ -0,0 +1,87 @@ +# graphify reference: extra exports and benchmark + +Load this when the user passed one of the export flags (`--wiki`, `--neo4j`, `--neo4j-push`, `--falkordb`, `--falkordb-push`, `--svg`, `--graphml`, `--mcp`), or when the corpus is large enough for the token-reduction benchmark. Each step runs only for its own flag. + +### Step 6b - Wiki (only if --wiki flag) + +**Only run this step if `--wiki` was explicitly given in the original command.** + +Run this before Step 9 (cleanup) so `.graphify_labels.json` is still available. + +```bash +graphify export wiki +``` + +### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag) + +**If `--neo4j`** - generate a Cypher file for manual import: + +```bash +graphify export neo4j +``` + +**If `--neo4j-push `** - push directly to a running Neo4j instance. Ask the user for credentials if not provided: + +```bash +graphify export neo4j --push bolt://localhost:7687 --user neo4j --password PASSWORD +``` + +Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag) + +**If `--falkordb`** - generate a Cypher file. The statements are OpenCypher, but FalkorDB's `GRAPH.QUERY` runs one statement at a time (no bulk script import like Neo4j's `cypher-shell`), so prefer `--falkordb-push` to load a graph. Use this only when you want the portable `cypher.txt` artifact: + +```bash +graphify export falkordb +``` + +**If `--falkordb-push `** - push directly to a running FalkorDB instance. Credentials are optional; ask the user only if the instance requires auth: + +```bash +graphify export falkordb --push falkordb://localhost:6379 +``` + +Default URI is `falkordb://localhost:6379` (the scheme is informational - `redis://` or a bare `host:port` work too), auth is optional, and the target graph defaults to `graphify`. Uses MERGE - safe to re-run without creating duplicates. + +### Step 7b - SVG export (only if --svg flag) + +```bash +graphify export svg +``` + +### Step 7c - GraphML export (only if --graphml flag) + +```bash +graphify export graphml +``` + +### Step 7d - MCP server (only if --mcp flag) + +```bash +$(cat graphify-out/.graphify_python) -m graphify.serve graphify-out/graph.json +``` + +This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live. + +To configure in Claude Desktop, add to `claude_desktop_config.json`. Claude Desktop can't run `$(...)`, and under `uv tool install` the system `python3` can't import graphify — so set `command` to the **absolute interpreter path** printed by `cat graphify-out/.graphify_python`: +```json +{ + "mcpServers": { + "graphify": { + "command": "", + "args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"] + } + } +} +``` + +### Step 8 - Token reduction benchmark (only if total_words > 5000) + +If `total_words` from `graphify-out/.graphify_detect.json` is greater than 5,000, run: + +```bash +graphify benchmark +``` + +Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora. diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__extraction-spec.md b/tools/skillgen/expected/graphify__skills__mimo__references__extraction-spec.md new file mode 100644 index 000000000..2cc191978 --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__extraction-spec.md @@ -0,0 +1,70 @@ +# graphify reference: extraction subagent prompt + +Load this in Step 3 Part B when the corpus has at least one doc, paper, or image chunk. A pure-code corpus skips Part B and never reads this file. Each semantic subagent receives the prompt below verbatim (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH). + +``` +You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment. +Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble. + +Files (chunk CHUNK_NUM of TOTAL_CHUNKS): +FILE_LIST + +Rules: +- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2") +- INFERRED: reasonable inference (shared data structure, implied dependency) +- AMBIGUOUS: uncertain - flag for review, do not omit + +Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns). + Do not re-extract imports - AST already has those. +Doc/paper files: extract named concepts, entities, citations. For rationale (WHY decisions were made, trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT create a separate rationale node or fragment node. Only create a node for something that is itself a named entity or concept. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms, design patterns). `file_type` MUST be one of exactly these six values: `code`, `document`, `paper`, `image`, `rationale`, `concept`. Any other value is invalid and will be rejected. +Code files: when adding `calls` edges, source MUST be the caller (the function/class doing the calling), target MUST be the callee. Never reverse this direction. `calls` edges MUST stay within one language: a Python function cannot `calls` a JS/TS/Go/Rust/Java symbol and vice versa — cross-language call edges are phantom artifacts, never emit them. +Image files: use vision to understand what the image IS - do not just OCR. + UI screenshot: layout patterns, design decisions, key elements, purpose. + Chart: metric, trend/insight, data source. + Tweet/post: claim as node, author, concepts mentioned. + Diagram: components and connections. + Research figure: what it demonstrates, method, result. + Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS. + +DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps, + shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting. + +Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples: +- Two functions that both validate user input but never call each other +- A class in code and a concept in a paper that describe the same algorithm +- Two error types that handle the same failure mode differently +Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things. + +Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples: +- All classes that implement a common protocol or interface +- All functions in an authentication flow (even if they don't all call each other) +- All concepts from a paper section that form one coherent idea +Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk. + +If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author, + contributor onto every node from that file. + +confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default: +- EXTRACTED edges: confidence_score = 1.0 always +- INFERRED edges: pick exactly ONE value from this set — never 0.5: + 0.95 direct structural evidence (shared data structure, named cross-file reference). + 0.85 strong inference (clear functional alignment, no direct symbol link). + 0.75 reasonable inference (shared problem domain + similar shape, requires interpretation). + 0.65 weak inference (thematically related, no shape evidence). + 0.55 speculative but plausible (surface-level co-occurrence only). + Models follow discrete rubrics better than continuous ranges; the bimodal + distribution observed in production (>50% at 0.5, >40% at 0.85+) shows the + range guidance is being collapsed to a binary. If no value above fits, mark + the edge AMBIGUOUS rather than picking 0.4 or below. +- AMBIGUOUS edges: 0.1-0.3 + +Node ID format: lowercase, only `[a-z0-9_]`, no dots or slashes. Format: `{stem}_{entity}` where stem is `{parent_dir}_{filename_without_ext}` (the **immediate** parent directory name + the filename stem, both lowercased with non-alphanumeric chars replaced by `_`) and entity is the symbol name similarly normalized. Only one level of parent is used — not the full path. Examples: `src/auth/session.py` + `ValidateToken` → `auth_session_validatetoken`; `lib/utils/helpers.py` + `parse_url` → `utils_helpers_parse_url`; `tests/test_foo.py` + `_helper` → `tests_test_foo_helper`. Top-level files (no parent dir, e.g. `setup.py`) use just the filename stem: `setup_my_func`. This must match the ID the AST extractor generates — using just the filename (e.g., `session_validatetoken`) or the full path (e.g., `src_auth_session_validatetoken`) will create orphan ghost-duplicate nodes. If you are re-extracting a project that had ghost duplicates under the old format, the user should run `graphify extract --force` to rebuild cleanly. CRITICAL: never append chunk numbers, sequence numbers, or any suffix to an ID (no `_c1`, `_c2`, `_chunk2`, etc.). IDs must be deterministic from the label alone — the same entity must always produce the same ID regardless of which chunk processes it. + +Generate the extraction JSON matching this schema exactly: +{"nodes":[{"id":"auth_session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale|concept","source_file":"","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":""}],"input_tokens":0,"output_tokens":0} + +source_file RULE (every node, edge, and hyperedge): set source_file to the path of the originating file EXACTLY as it appears in FILE_LIST — verbatim and absolute. Do NOT shorten to a basename, do NOT re-relativize, do NOT strip any directory prefix, and do NOT change separators (the engine canonicalizes separators and relativizes against the build root downstream). Copy the FILE_LIST entry character-for-character. This keeps the full build and incremental --update on the same base, so build_merge's replace-on-re-extract matches the existing node instead of accumulating a duplicate. + +Then write the JSON to disk using the Write tool at this exact absolute path (no relative paths — Write resolves relative paths against an undefined cwd and the file will be silently lost): +CHUNK_PATH +``` diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__github-and-merge.md b/tools/skillgen/expected/graphify__skills__mimo__references__github-and-merge.md new file mode 100644 index 000000000..a41ea06e1 --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__github-and-merge.md @@ -0,0 +1,46 @@ +# graphify reference: GitHub clone and cross-repo merge + +Load this when the user passed one or more `https://github.com/...` URLs, or named several local subfolders to merge into one graph. + +### Step 0 - Clone GitHub repo(s) (only if a GitHub URL was given) + +**Single repo:** +```bash +LOCAL_PATH=$(graphify clone [--branch ]) +# Use LOCAL_PATH as the target for all subsequent steps +``` + +**Multiple repos (cross-repo graph):** +```bash +# Clone each repo, run the full pipeline on each, then merge +graphify clone # → ~/.graphify/repos// +graphify clone # → ~/.graphify/repos// +# Run /graphify on each local path to produce their graph.json files +# Then merge: +graphify merge-graphs \ + ~/.graphify/repos///graphify-out/graph.json \ + ~/.graphify/repos///graphify-out/graph.json \ + --out graphify-out/cross-repo-graph.json +``` + +Graphify clones into `~/.graphify/repos//` and reuses existing clones on repeat runs. Each node in the merged graph carries a `repo` attribute so you can filter by origin. + +**Multiple local subfolders (monorepo or multi-service layout):** + +The skill pipeline writes all intermediate and final outputs to `graphify-out/` in the current working directory. Running the skill on each subfolder separately will clobber the same output dir. Instead, use the CLI directly for each subfolder — it places `graphify-out/` *inside* the scanned path: + +```bash +graphify extract ./core/ # → ./core/graphify-out/graph.json +graphify extract ./service/ # → ./service/graphify-out/graph.json +graphify extract ./platform/ # → ./platform/graphify-out/graph.json +# Add --backend gemini|kimi|openai|deepseek|claude-cli depending on which API key you have set + +# Then merge at the project root: +graphify merge-graphs \ + ./core/graphify-out/graph.json \ + ./service/graphify-out/graph.json \ + ./platform/graphify-out/graph.json \ + --out graphify-out/graph.json +``` + +Once `graphify-out/graph.json` exists, the fast path above takes over: any codebase question runs `graphify query` directly on the merged graph — no re-extraction, no size gate. diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__hooks.md b/tools/skillgen/expected/graphify__skills__mimo__references__hooks.md new file mode 100644 index 000000000..438b8b16b --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__hooks.md @@ -0,0 +1,33 @@ +# graphify reference: commit hook and native CLAUDE.md integration + +Load this when the user asked to install the post-commit hook or wire graphify into a project's CLAUDE.md. + +## For git commit hook + +Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor. + +```bash +graphify hook install # install +graphify hook uninstall # remove +graphify hook status # check +``` + +After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those. + +If a post-commit hook already exists, graphify appends to it rather than replacing it. + +--- + +## For native CLAUDE.md integration + +Run once per project to make graphify always-on in Claude Code sessions: + +```bash +graphify claude install +``` + +This writes a `## graphify` section to the local `CLAUDE.md` that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions. + +```bash +graphify claude uninstall # remove the section +``` diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__query.md b/tools/skillgen/expected/graphify__skills__mimo__references__query.md new file mode 100644 index 000000000..52321f101 --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__query.md @@ -0,0 +1,311 @@ +# graphify reference: query, path, explain + +Load this when the user asks a question against an existing graph, or runs `/graphify path` or `/graphify explain`. The core's query stub points here for the full traversal flow. These flows use the `graphify query` CLI when it is available and fall back to an inline NetworkX traversal otherwise. + +Two traversal modes - choose based on the question: + +| Mode | Flag | Best for | +|------|------|----------| +| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first | +| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path | + +First check the graph exists: +```bash +$(cat graphify-out/.graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +### Step 0 — Constrained query expansion (REQUIRED before traversal) + +graphify's `query` CLI matches nodes via case-folded substring + IDF — there is **no stemming, no synonyms, no cross-language match** inside the binary, and the inline fallback below matches the same way. If the user's question uses different language or different domain vocabulary than the graph's labels (user says "обработчик" / graph says "handler"; user says "authentication" / graph says "Guardian"), the literal matcher returns 0 hits and the answer collapses to noise. + +Fix this **without inventing tokens** by expanding the query against the actual graph vocabulary first: + +1. Extract the token vocabulary from node labels: +```bash +$(cat graphify-out/.graphify_python) -c " +import json, re +from pathlib import Path +data = json.loads(Path('graphify-out/graph.json').read_text()) +vocab = set() +for n in data['nodes']: + for c in re.findall(r'[^\W\d_]+', n.get('label','') or '', re.UNICODE): + parts = re.findall(r'[A-Z]+(?=[A-Z][a-z])|[A-Z]?[a-z]+|[A-Z]+', c) or [c] + for p in parts: + t = p.lower() + if 3 <= len(t) <= 30: + vocab.add(t) +Path('graphify-out/.vocab.txt').write_text('\n'.join(sorted(vocab))) +print(f'vocab: {len(vocab)} tokens') +" +``` + +2. Read `graphify-out/.vocab.txt`. Then for the user's question, select **up to 12 tokens from this exact list** that semantically match the query intent. Hard constraints: + - You MUST pick only tokens present in the vocabulary file. Do NOT invent tokens. + - If a query concept has no plausible token in the vocab, skip it — do not substitute a near-synonym from training memory. + - If **no** vocab tokens match the query at all, output an empty list and tell the user the corpus has no relevant vocabulary for this question. Do not fabricate a search. + - Translate cross-language: Russian "аутентификация" → look for `auth`, `credential`, `token`, `security` IFF present in vocab. + - Morphology: "handlers" maps to `handler` IFF present; "todos" maps to `todo` IFF present. + +3. Print the selection explicitly to the user before running the query, so the expansion is auditable: +``` +Query expanded to (from graph vocab, N tokens): [token1, token2, ...] +``` +If the list is empty, say so plainly and stop — do not proceed to traversal. + +### Step 1 — Traversal + +Build the **expanded query string** by joining the selected tokens with spaces. Use this string as `QUESTION` below — NOT the original user question. (The original question is preserved only for `save-result` at the end.) + +Prefer the CLI when it is installed: +```bash +graphify query "QUESTION" +# or: graphify query "QUESTION" --dfs --budget 3000 +``` + +If the CLI is unavailable, load `graphify-out/graph.json` and run the traversal inline: + +1. Find the 1-3 nodes whose label best matches the expanded tokens. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +question = 'QUESTION' +mode = 'MODE' # 'bfs' or 'dfs' +terms = [t.lower() for t in question.split() if len(t) >= 3] # match the vocab threshold; keeps api/jwt/ios (#1392) + +# Find best-matching start nodes +scored = [] +for nid, ndata in G.nodes(data=True): + label = ndata.get('label', '').lower() + score = sum(1 for t in terms if t in label) + if score > 0: + scored.append((score, nid)) +scored.sort(reverse=True) +start_nodes = [nid for _, nid in scored[:3]] + +if not start_nodes: + print('No matching nodes found for query terms:', terms) + sys.exit(0) + +subgraph_nodes = set() +subgraph_edges = [] + +if mode == 'dfs': + # DFS: follow one path as deep as possible before backtracking. + # Depth-limited to 6 to avoid traversing the whole graph. + visited = set() + stack = [(n, 0) for n in reversed(start_nodes)] + while stack: + node, depth = stack.pop() + if node in visited or depth > 6: + continue + visited.add(node) + subgraph_nodes.add(node) + for neighbor in G.neighbors(node): + if neighbor not in visited: + stack.append((neighbor, depth + 1)) + subgraph_edges.append((node, neighbor)) +else: + # BFS: explore all neighbors layer by layer up to depth 3. + frontier = set(start_nodes) + subgraph_nodes = set(start_nodes) + for _ in range(3): + next_frontier = set() + for n in frontier: + for neighbor in G.neighbors(n): + if neighbor not in subgraph_nodes: + next_frontier.add(neighbor) + subgraph_edges.append((n, neighbor)) + subgraph_nodes.update(next_frontier) + frontier = next_frontier + +# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token) +token_budget = BUDGET # default 2000 +char_budget = token_budget * 4 + +# Score each node by term overlap for ranked output +def relevance(nid): + label = G.nodes[nid].get('label', '').lower() + return sum(1 for t in terms if t in label) + +ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True) + +lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes'] +for nid in ranked_nodes: + d = G.nodes[nid] + lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]') +for u, v in subgraph_edges: + if u in subgraph_nodes and v in subgraph_nodes: + _raw = G[u][v]; d = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}') + +output = '\n'.join(lines) +if len(output) > char_budget: + output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)' +print(output) +" +``` + +Replace `QUESTION` with the **expanded** query string, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above, using only what the graph contains. + +After writing the answer, save it back into the graph so it improves future queries. Include the expanded tokens inside the `--answer` text (e.g. `"Expanded from original query via vocab: [tokens]. Then traversed..."`) so the next `--update` extracts the expansion history as a graph node: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "ORIGINAL_QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2 +``` + +Replace `ORIGINAL_QUESTION` with the user's verbatim question, `ANSWER` with your full answer text (containing the expanded-token trace), `NODE1 NODE2` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +**Work memory (self-improving loop).** Add an `--outcome` so future sessions learn from this one — append `--outcome useful|dead_end|corrected` to the `save-result` command (and `--correction "the right answer"` when correcting): + +- `useful` — the cited nodes answered the question well (they become *preferred sources*). +- `dead_end` — the question/path led nowhere; don't re-derive it next time. +- `corrected` — the saved answer was wrong; `--correction` records what was right. + +At the **start** of graph work, refresh and read the lessons: run `graphify reflect --if-stale` (cheap, deterministic, no LLM; `--if-stale` makes it a no-op when `LESSONS.md` is already newer than every input, e.g. when the git hook just refreshed it), then read `graphify-out/reflections/LESSONS.md`. It lists **preferred sources** (start there), **known dead ends** (skip them), and prior **corrections**. Running `reflect` yourself keeps the lessons current even without the git hook installed; if the post-commit hook *is* installed, `--if-stale` means your session-start run costs almost nothing. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. Prefer the CLI when installed: + +```bash +graphify path "NODE_A" "NODE_B" +``` + +If the CLI is unavailable, run it inline: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +a_term = 'NODE_A' +b_term = 'NODE_B' + +def find_node(term): + term = term.lower() + scored = sorted( + [(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True + ) + return scored[0][1] if scored and scored[0][0] > 0 else None + +src = find_node(a_term) +tgt = find_node(b_term) + +if not src or not tgt: + print(f'Could not find nodes matching: {a_term!r} or {b_term!r}') + sys.exit(0) + +try: + path = nx.shortest_path(G, src, tgt) + print(f'Shortest path ({len(path)-1} hops):') + for i, nid in enumerate(path): + label = G.nodes[nid].get('label', nid) + if i < len(path) - 1: + _raw = G[nid][path[i+1]]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + print(f' {label} --{rel}--> [{conf}]') + else: + print(f' {label}') +except nx.NetworkXNoPath: + print(f'No path found between {a_term!r} and {b_term!r}') +except nx.NodeNotFound as e: + print(f'Node not found: {e}') +" +``` + +Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant. + +After writing the explanation, save it back: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. Prefer the CLI when installed: + +```bash +graphify explain "NODE_NAME" +``` + +If the CLI is unavailable, run it inline: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json, sys +import networkx as nx +from networkx.readwrite import json_graph +from pathlib import Path + +data = json.loads(Path('graphify-out/graph.json').read_text()) +G = json_graph.node_link_graph(data, edges='links') + +term = 'NODE_NAME' +term_lower = term.lower() + +# Find best matching node +scored = sorted( + [(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n) + for n in G.nodes()], + reverse=True +) +if not scored or scored[0][0] == 0: + print(f'No node matching {term!r}') + sys.exit(0) + +nid = scored[0][1] +data_n = G.nodes[nid] +print(f'NODE: {data_n.get(\"label\", nid)}') +print(f' source: {data_n.get(\"source_file\",\"unknown\")}') +print(f' type: {data_n.get(\"file_type\",\"unknown\")}') +print(f' degree: {G.degree(nid)}') +print() +print('CONNECTIONS:') +for neighbor in G.neighbors(nid): + _raw = G[nid][neighbor]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw + nlabel = G.nodes[neighbor].get('label', neighbor) + rel = edge.get('relation', '') + conf = edge.get('confidence', '') + src_file = G.nodes[neighbor].get('source_file', '') + print(f' --{rel}--> {nlabel} [{conf}] ({src_file})') +" +``` + +Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations. + +After writing the explanation, save it back: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME +``` diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__transcribe.md b/tools/skillgen/expected/graphify__skills__mimo__references__transcribe.md new file mode 100644 index 000000000..b967f8379 --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__transcribe.md @@ -0,0 +1,52 @@ +# graphify reference: transcribe video and audio + +Load this only when `detect` reported one or more `video` files. A corpus with no video never reads this. + +### Step 2.5 - Transcribe video / audio files (only if video files detected) + +Skip this step entirely if `detect` returned zero `video` files. + +Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3. + +**Strategy:** Read the god nodes from `graphify-out/.graphify_detect.json` (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed. + +**However**, if the corpus has *only* video files and no other docs/code, use the generic fallback prompt: `"Use proper punctuation and paragraph breaks."` + +**Step 1 - Write the Whisper prompt yourself.** + +Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example: + +- Labels: `transformer, attention, encoder, decoder` → `"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."` +- Labels: `kubernetes, deployment, pod, helm` → `"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."` + +**Export** it as `GRAPHIFY_WHISPER_PROMPT` (the exact name the transcriber reads — and it must be `export`ed so the child Python process sees it) for the next command. + +**Step 2 - Transcribe:** + +```bash +export GRAPHIFY_WHISPER_MODEL=base # or whatever --whisper-model the user passed (must be exported) +export GRAPHIFY_WHISPER_PROMPT="" +$(cat graphify-out/.graphify_python) -c " +import json, os, sys +from pathlib import Path +from graphify.transcribe import transcribe_all + +detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\")) +video_files = detect.get('files', {}).get('video', []) +prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.') + +transcript_paths = transcribe_all(video_files, initial_prompt=prompt) +# Write the JSON from Python (NOT a shell '>' redirect): transcribe_all/Whisper +# print progress to stdout, which would otherwise corrupt the JSON file (#1392). +Path('graphify-out/.graphify_transcripts.json').write_text(json.dumps(transcript_paths, ensure_ascii=False), encoding=\"utf-8\") +print(f'Transcribed {len(transcript_paths)} file(s)', file=sys.stderr) +" +``` + +After transcription: +- Read the transcript paths from `graphify-out/.graphify_transcripts.json` +- Add them to the docs list before dispatching semantic subagents in Step 3B +- Print how many transcripts were created: `Transcribed N video file(s) -> treating as docs` +- If transcription fails for a file, print a warning and continue with the rest + +**Whisper model:** Default is `base`. If the user passed `--whisper-model `, `export GRAPHIFY_WHISPER_MODEL=` (it must be exported, not just assigned) before running the command above. diff --git a/tools/skillgen/expected/graphify__skills__mimo__references__update.md b/tools/skillgen/expected/graphify__skills__mimo__references__update.md new file mode 100644 index 000000000..fa2612180 --- /dev/null +++ b/tools/skillgen/expected/graphify__skills__mimo__references__update.md @@ -0,0 +1,192 @@ +# graphify reference: incremental update and cluster-only + +Load this only when the user passed `--update` or `--cluster-only`. A first-time full build never reads this file. + +## For --update (incremental re-extraction) + +Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time. + +```bash +$(cat graphify-out/.graphify_python) -c " +import sys, json +from graphify.detect import detect_incremental, save_manifest +from pathlib import Path + +result = detect_incremental(Path('INPUT_PATH')) +new_total = result.get('new_total', 0) +print(json.dumps(result, indent=2, ensure_ascii=False)) +Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\") +deleted = list(result.get('deleted_files', [])) +if new_total == 0 and not deleted: + print('No files changed since last run. Nothing to update.') + raise SystemExit(0) +if deleted: + print(f'{len(deleted)} deleted file(s) to prune.') +if new_total > 0: + print(f'{new_total} new/changed file(s) to re-extract.') +" +``` + +Then populate `.graphify_detect.json` so Steps 3A–6 (which read it unconditionally) see the right state for an incremental run. `files` carries the changed subset (drives Step 3A AST + Step 3B0 cache check on only what changed); `all_files` carries the full corpus for any step that needs corpus-wide context: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +r = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\")) +Path('graphify-out/.graphify_detect.json').write_text(json.dumps({ + 'files': r.get('new_files', {}), + 'all_files': r.get('files', {}), + 'total_files': r.get('new_total', 0), + 'total_words': r.get('total_words', 0), + 'skipped_sensitive': r.get('skipped_sensitive', []), + 'needs_graph': True, +}, ensure_ascii=False), encoding=\"utf-8\") +" +``` + +If new files exist, first check whether all changed files are code files: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path + +result = json.loads(open('graphify-out/.graphify_incremental.json', encoding='utf-8').read()) if Path('graphify-out/.graphify_incremental.json').exists() else {} +code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts','.lua','.toc','.f','.F','.f90','.F90','.f95','.F95','.f03','.F03','.f08','.F08'} +new_files = result.get('new_files', {}) +all_changed = [f for files in new_files.values() for f in files] +code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed) +print('code_only:', code_only) +" +``` + +If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8. + +If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal. + + +If no new files exist (only deletions), create an empty extraction so the merge step can prune: + +```bash +if [ ! -f graphify-out/.graphify_extract.json ]; then + echo '[graphify update] Only deletions -- creating empty extraction for merge.' + $(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +Path('graphify-out/.graphify_extract.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8') +" +fi +``` + + +Then: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from pathlib import Path +from graphify.build import build_merge +from graphify.detect import save_manifest + +# Load new extraction and incremental state +new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\")) +deleted = list(incremental.get('deleted_files', [])) +# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are +# handled by build_merge's replace-on-re-extract (#1344): every source_file in +# new_chunks is dropped from the base before merge, so old/stale nodes don't survive. +# Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base +# as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot +# now that replace — not the dedup pass — reconciles changed files). +prune = list(deleted) or None + +# Use build_merge() — reads graph.json directly without NetworkX round-trip +# so edge direction (calls, implements, imports) is always preserved (#801). +# Pass root= so prune_sources (absolute paths from detect_incremental) are +# relativized to match the graph's relative source_file values; without it +# nothing is pruned and stale nodes accumulate on every update (#1361). +# directed=IS_DIRECTED: replace IS_DIRECTED with True if --directed was given, else +# False. Without it a --directed --update silently rebuilds undirected and collapses +# reciprocal A<->B edges (#1392). +G = build_merge( + [new_extraction], + graph_path='graphify-out/graph.json', + prune_sources=prune, + root='INPUT_PATH', + directed=IS_DIRECTED, +) +print(f'[graphify update] Merged: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges') + +# Write merged result back to .graphify_extract.json so Step 4 sees the full graph +merged_out = { + 'nodes': [{'id': n, **d} for n, d in G.nodes(data=True)], + 'edges': [ + # Explicit source/target last so they win over any stale attrs in d. + {**{k: val for k, val in d.items() if k not in ('_src', '_tgt', 'source', 'target')}, + 'source': d.get('_src', u), 'target': d.get('_tgt', v)} + for u, v, d in G.edges(data=True) + ], + # G.graph["hyperedges"] holds hyperedges from both existing graph.json + # and new_extraction (build_merge combines them). Falling back to + # new_extraction only would silently drop prior-run hyperedges (#801). + 'hyperedges': list(G.graph.get('hyperedges', [])), + 'input_tokens': new_extraction.get('input_tokens', 0), + 'output_tokens': new_extraction.get('output_tokens', 0), +} +Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged_out, ensure_ascii=False), encoding=\"utf-8\") +print(f'[graphify update] Merged extraction written ({len(merged_out[\"nodes\"])} nodes, {len(merged_out[\"edges\"])} edges)') + +# Save manifest so next --update diffs against today's state, not the +# prior run's baseline (prevents ghost-node reports on subsequent updates). +# root= matches the build_merge call above so the manifest keys stay relative to +# the scan root — portable across clones/machines, so --update keeps matching +# cached files instead of missing every one after a move (#1417). +save_manifest(incremental['files'], root='INPUT_PATH') +print('[graphify update] Manifest saved.') +" +``` + +Then run Steps 4–8 on the merged graph as normal. + +After Step 4, show the graph diff: + +```bash +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.analyze import graph_diff +from graphify.build import build_from_json +from networkx.readwrite import json_graph +import networkx as nx +from pathlib import Path + +# Load old graph (before update) from backup written before merge +old_data = json.loads(Path('graphify-out/.graphify_old.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_old.json').exists() else None +new_extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\")) +G_new = build_from_json(new_extract, directed=IS_DIRECTED) + +if old_data: + G_old = json_graph.node_link_graph(old_data, edges='links') + diff = graph_diff(G_old, G_new) + print(diff['summary']) + if diff['new_nodes']: + print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5])) + if diff['new_edges']: + print('New edges:', len(diff['new_edges'])) +" +``` + +Before the merge step, save the old graph: `cp graphify-out/graph.json graphify-out/.graphify_old.json` +Clean up after: `rm -f graphify-out/.graphify_old.json` + +--- + +## For --cluster-only + +Skip Steps 1–3. Re-run clustering on the existing graph: + +```bash +graphify cluster-only . +``` + +`graphify cluster-only .` is **self-contained**: it re-clusters, names communities, and regenerates `GRAPH_REPORT.md`, `graph.json`, and `graph.html` from the existing graph. **Do not re-run Steps 5–9** — they read intermediate files (`.graphify_extract.json`, `.graphify_detect.json`, `.graphify_analysis.json`) that a prior build's cleanup (Step 9) already deleted, so they raise `FileNotFoundError` (#1392). When it finishes, present the refreshed `GRAPH_REPORT.md` summary as usual. diff --git a/tools/skillgen/gen.py b/tools/skillgen/gen.py index 0082e9e51..23e043b7d 100644 --- a/tools/skillgen/gen.py +++ b/tools/skillgen/gen.py @@ -67,6 +67,10 @@ def _v8_baseline_ref(platform_key: str) -> str: # amp's modulo the install/uninstall command wording (prose, not headings), # so amp's v8 body is the correct per-host coverage baseline. return f"{_V8_BASELINE_SHA}:graphify/skill-amp.md" + if platform_key == "mimo": + # `mimo` is a post-v8 platform with no own v8 body — it re-homes claude's + # skill body at the ~/.mimo/skills location. + return f"{_V8_BASELINE_SHA}:graphify/skill.md" return f"{_V8_BASELINE_SHA}:graphify/skill-{platform_key}.md" # Immutable baseline for --always-on-roundtrip. The six always-on instruction diff --git a/tools/skillgen/platforms.toml b/tools/skillgen/platforms.toml index 0856d2269..9f715bba2 100644 --- a/tools/skillgen/platforms.toml +++ b/tools/skillgen/platforms.toml @@ -203,3 +203,13 @@ bucket = "monolith" skill_dst = "graphify/skill-devin.md" monolith = "devin" roundtrip_ref = "47042beb05d1f6dd2186c0c499ae2840ce604ead:graphify/skill-devin.md" + +[platform.mimo] +bucket = "split" +core = "core" +skill_dst = "graphify/skill-mimo.md" +refs_dst = "graphify/skills/mimo/references" +description = "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools." +dispatch = "agent-tool-disk" +extraction = "verbose" +shell = "posix"