diff --git a/.codex-after-desktop.png b/.codex-after-desktop.png new file mode 100644 index 0000000..d3eec52 Binary files /dev/null and b/.codex-after-desktop.png differ diff --git a/.codex-after-handoff.png b/.codex-after-handoff.png new file mode 100644 index 0000000..50b4dbd Binary files /dev/null and b/.codex-after-handoff.png differ diff --git a/.codex-bridge-target.png b/.codex-bridge-target.png new file mode 100644 index 0000000..6a074bb Binary files /dev/null and b/.codex-bridge-target.png differ diff --git a/.codex-final-handoff-centered.png b/.codex-final-handoff-centered.png new file mode 100644 index 0000000..280426b Binary files /dev/null and b/.codex-final-handoff-centered.png differ diff --git a/.codex-final-scroll-check.png b/.codex-final-scroll-check.png new file mode 100644 index 0000000..0aed1e1 Binary files /dev/null and b/.codex-final-scroll-check.png differ diff --git a/.codex-final-wheel-check.png b/.codex-final-wheel-check.png new file mode 100644 index 0000000..84e156b Binary files /dev/null and b/.codex-final-wheel-check.png differ diff --git a/.codex-handoff-desktop.png b/.codex-handoff-desktop.png new file mode 100644 index 0000000..21d0d70 Binary files /dev/null and b/.codex-handoff-desktop.png differ diff --git a/.codex-handoff-target.png b/.codex-handoff-target.png new file mode 100644 index 0000000..4b4e728 Binary files /dev/null and b/.codex-handoff-target.png differ diff --git a/.codex-handoff-wheel.png b/.codex-handoff-wheel.png new file mode 100644 index 0000000..3f33f21 Binary files /dev/null and b/.codex-handoff-wheel.png differ diff --git a/.codex-hub-handoff-final.png b/.codex-hub-handoff-final.png new file mode 100644 index 0000000..cac99a0 Binary files /dev/null and b/.codex-hub-handoff-final.png differ diff --git a/.codex-hub-handoff.png b/.codex-hub-handoff.png new file mode 100644 index 0000000..87de973 Binary files /dev/null and b/.codex-hub-handoff.png differ diff --git a/.codex-remap-bridge.png b/.codex-remap-bridge.png new file mode 100644 index 0000000..c488ec4 Binary files /dev/null and b/.codex-remap-bridge.png differ diff --git a/.codex/hooks.json b/.codex/hooks.json new file mode 100644 index 0000000..58307b7 --- /dev/null +++ b/.codex/hooks.json @@ -0,0 +1,15 @@ +{ + "hooks": { + "PreToolUse": [ + { + "matcher": "Bash", + "hooks": [ + { + "type": "command", + "command": "/home/user/.local/bin/graphify hook-check" + } + ] + } + ] + } +} \ No newline at end of file diff --git a/.codex/skills/graphify/.graphify_version b/.codex/skills/graphify/.graphify_version new file mode 100644 index 0000000..43b284f --- /dev/null +++ b/.codex/skills/graphify/.graphify_version @@ -0,0 +1 @@ +0.8.37 \ No newline at end of file diff --git a/.codex/skills/graphify/SKILL.md b/.codex/skills/graphify/SKILL.md new file mode 100644 index 0000000..9f8253f --- /dev/null +++ b/.codex/skills/graphify/SKILL.md @@ -0,0 +1,612 @@ +--- +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 --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). + +**Before dispatching subagents:** 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. 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 Claude 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.** If `GEMINI_API_KEY`/`GOOGLE_API_KEY` are unset, fall straight through to Claude Code subagent dispatch (Part B below) — the host session itself is the LLM. graphify does **not** read `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or any other provider key from the environment. If a host agent prompts the user for `ANTHROPIC_API_KEY` to run extraction, that prompt is a misread of this skill — ignore it and dispatch subagents as written. + +**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('.')) + 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. + +**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\")) +all_files = [f for files in detect['files'].values() for f in files] + +cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files) + +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\") +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 (Codex)** + +> **Codex platform:** Uses `spawn_agent` + `wait_agent` + `close_agent` instead of the Agent tool. +> Requires `multi_agent = true` under `[features]` in `~/.codex/config.toml`. +> If `spawn_agent` is unavailable, tell the user to add that config and restart Codex. + +Call `spawn_agent` once per chunk — ALL in the same response so they run in parallel. Build the message by wrapping the extraction prompt in task-delegation framing: + +``` +spawn_agent(agent_type="worker", message="Your task is to perform the following. Follow the instructions below exactly.\n\n\n[extraction prompt, with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted]\n\n\nExecute this now. Output ONLY the structured JSON response.") +``` + +After all agents are dispatched, collect results sequentially in memory: +``` +result = wait_agent(handle); close_agent(handle) # repeat per handle +``` + +Parse each result as JSON. Accumulate nodes/edges/hyperedges across all results and write to `graphify-out/.graphify_semantic_new.json`. Codex collects in memory, so there are no per-chunk files on disk; the disk-based success checks in Step B3 do not apply — a chunk that returns invalid JSON is the failure signal instead. + +Subagent prompt template: + +See `references/extraction-spec.md` for the compact subagent prompt (rules, node-ID format, confidence rubric, hyperedge and vision rules, JSON schema). 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 agent that prompt verbatim with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, and DEEP_MODE substituted, and have it return the JSON inline. + +**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 +$(cat graphify-out/.graphify_python) -c " +import json +from graphify.cache import save_semantic_cache +from pathlib import Path + +new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]} +saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', [])) +print(f'Cached {saved} files') +" +``` + +Merge cached + new results into `graphify-out/.graphify_semantic.json`: +```bash +$(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 +$(cat graphify-out/.graphify_python) -c " +import sys, json +from pathlib import Path + +ast = json.loads(Path('graphify-out/.graphify_ast.json').read_text(encoding=\"utf-8\")) +sem = json.loads(Path('graphify-out/.graphify_semantic.json').read_text(encoding=\"utf-8\")) + +# Merge: AST nodes first, semantic nodes deduplicated by id +seen = {n['id'] for n in ast['nodes']} +merged_nodes = list(ast['nodes']) +for n in sem['nodes']: + if n['id'] not in seen: + merged_nodes.append(n) + seen.add(n['id']) + +merged_edges = ast['edges'] + sem['edges'] +merged_hyperedges = sem.get('hyperedges', []) +merged = { + 'nodes': merged_nodes, + 'edges': merged_edges, + 'hyperedges': merged_hyperedges, + 'input_tokens': sem.get('input_tokens', 0), + 'output_tokens': sem.get('output_tokens', 0), +} +Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\") +total = len(merged_nodes) +edges = len(merged_edges) +print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)') +" +``` + +### Step 4 - Build graph, cluster, analyze, generate outputs + +**Before starting:** note whether `--directed` was given. If so, pass `directed=True` to `build_from_json()` in the code block below. This builds a `DiGraph` that preserves edge direction (source→target) instead of the default undirected `Graph`. + +```bash +mkdir -p graphify-out +$(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\")) + +G = build_from_json(extraction) +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) + +report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.', suggested_questions=questions) +Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\") +to_json(G, communities, 'graphify-out/graph.json') + +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\") +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) +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 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\")) + +G = build_from_json(extraction) +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, '.', 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, SVG, GraphML, MCP, benchmark (only on their flags) + +These run only when their flag is present (`--wiki`, `--neo4j`/`--neo4j-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. +save_manifest(detect.get('all_files') or detect['files']) + +# 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 +``` + +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 "" +``` + +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 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/.codex/skills/graphify/references/add-watch.md b/.codex/skills/graphify/references/add-watch.md new file mode 100644 index 0000000..78b6870 --- /dev/null +++ b/.codex/skills/graphify/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 +python3 -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/.codex/skills/graphify/references/exports.md b/.codex/skills/graphify/references/exports.md new file mode 100644 index 0000000..3750ff2 --- /dev/null +++ b/.codex/skills/graphify/references/exports.md @@ -0,0 +1,71 @@ +# graphify reference: extra exports and benchmark + +Load this when the user passed one of the export flags (`--wiki`, `--neo4j`, `--neo4j-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 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 +python3 -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`: +```json +{ + "mcpServers": { + "graphify": { + "command": "python3", + "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/.codex/skills/graphify/references/extraction-spec.md b/.codex/skills/graphify/references/extraction-spec.md new file mode 100644 index 0000000..231da82 --- /dev/null +++ b/.codex/skills/graphify/references/extraction-spec.md @@ -0,0 +1,29 @@ +# graphify reference: extraction subagent prompt (compact) + +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, and DEEP_MODE). + +``` +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) +- INFERRED: reasonable inference (shared structure, implied dependency) +- AMBIGUOUS: uncertain — flag it, do not omit +- Code files: semantic edges AST cannot find. Do not re-extract imports. When adding `calls` edges: source is the caller, target is the callee, never reversed; keep `calls` within one language. +- Doc/paper files: named concepts, entities, citations. Store rationale (WHY decisions were made) as a `rationale` attribute on the relevant node, not as a separate node. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms) and `file_type:"concept"` for named concepts. `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. +- Image files: use vision — understand what the image IS, not just OCR +- DEEP_MODE (if --mode deep): be aggressive with INFERRED edges — indirect deps, shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting. +- Semantic similarity: if two concepts solve the same problem or represent the same idea without a structural link (no import, call, or citation), add a `semantically_similar_to` edge marked INFERRED with confidence_score 0.6-0.95. Non-obvious cross-file links only. +- Hyperedges: if 3+ nodes share a concept, flow, or pattern not captured by pairwise edges, add a hyperedge to a top-level `hyperedges` array. Use sparingly. Max 3 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 = 1.0 always. INFERRED: pick exactly ONE of 0.95 (direct structural evidence), 0.85 (strong inference), 0.75 (reasonable inference), 0.65 (weak inference), 0.55 (speculative but plausible) — never 0.5; if none fit, mark the edge AMBIGUOUS. AMBIGUOUS = 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 + the filename stem, both lowercased with non-alphanumeric chars replaced by `_`) and entity is the symbol name similarly normalized. Only one level of parent. `src/auth/session.py` + `ValidateToken` → `auth_session_validatetoken`. Top-level files use just the filename stem. This must match the AST extractor's ID. Never append chunk or sequence suffixes — IDs must be deterministic from the label alone. + +Output exactly this JSON (no other text): +{"nodes":[{"id":"session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale|concept","source_file":"relative/path","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":"relative/path","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":"relative/path"}],"input_tokens":0,"output_tokens":0} +``` diff --git a/.codex/skills/graphify/references/github-and-merge.md b/.codex/skills/graphify/references/github-and-merge.md new file mode 100644 index 0000000..a41ea06 --- /dev/null +++ b/.codex/skills/graphify/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/.codex/skills/graphify/references/hooks.md b/.codex/skills/graphify/references/hooks.md new file mode 100644 index 0000000..438b8b1 --- /dev/null +++ b/.codex/skills/graphify/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/.codex/skills/graphify/references/query.md b/.codex/skills/graphify/references/query.md new file mode 100644 index 0000000..25b826f --- /dev/null +++ b/.codex/skills/graphify/references/query.md @@ -0,0 +1,249 @@ +# 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 +$(cat graphify-out/.graphify_python) -c " +from pathlib import Path +if not Path('graphify-out/graph.json').exists(): + print('ERROR: No graph found. Run /graphify first to build the graph.') + raise SystemExit(1) +" +``` +If it fails, stop and tell the user to run `/graphify ` first. + +Prefer the CLI when it is installed: +```bash +graphify query "QUESTION" +# or: graphify query "QUESTION" --dfs --budget 3000 +``` + +If the CLI is unavailable, load `graphify-out/graph.json` and run the traversal inline: + +1. Find the 1-3 nodes whose label best matches key terms in the question. +2. Run the appropriate traversal from each starting node. +3. Read the subgraph - node labels, edge relations, confidence tags, source locations. +4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact. +5. If the graph lacks enough information, say so - do not hallucinate edges. + +```bash +$(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] + +# 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 user's actual question, `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. + +After writing the answer, save it back into the graph so it improves future queries: + +```bash +$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2 +``` + +Replace `QUESTION` with the user's verbatim question, `ANSWER` with your full answer text, and the node list with the labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph. + +--- + +## For /graphify path + +Find the shortest path between two named concepts in the graph. + +```bash +$(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 +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B +``` + +--- + +## For /graphify explain + +Give a plain-language explanation of a single node - everything connected to it. + +```bash +$(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 +$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME +``` diff --git a/.codex/skills/graphify/references/transcribe.md b/.codex/skills/graphify/references/transcribe.md new file mode 100644 index 0000000..d9cc698 --- /dev/null +++ b/.codex/skills/graphify/references/transcribe.md @@ -0,0 +1,48 @@ +# graphify reference: transcribe video and audio + +Load this only when `detect` reported one or more `video` files. A corpus with no video never reads this. + +### Step 2.5 - Transcribe video / audio files (only if video files detected) + +Skip this step entirely if `detect` returned zero `video` files. + +Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3. + +**Strategy:** Read the god nodes from `graphify-out/.graphify_detect.json` (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed. + +**However**, if the corpus has *only* video files and no other docs/code, use the generic fallback prompt: `"Use proper punctuation and paragraph breaks."` + +**Step 1 - Write the Whisper prompt yourself.** + +Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example: + +- Labels: `transformer, attention, encoder, decoder` → `"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."` +- Labels: `kubernetes, deployment, pod, helm` → `"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."` + +Set it as `WHISPER_PROMPT` to use in the next command. + +**Step 2 - Transcribe:** + +```bash +GRAPHIFY_WHISPER_MODEL=base # or whatever --whisper-model the user passed +$(cat graphify-out/.graphify_python) -c " +import json, os +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) +print(json.dumps(transcript_paths, ensure_ascii=False)) +" > graphify-out/.graphify_transcripts.json +``` + +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 `, set `GRAPHIFY_WHISPER_MODEL=` in the environment before running the command above. diff --git a/.codex/skills/graphify/references/update.md b/.codex/skills/graphify/references/update.md new file mode 100644 index 0000000..d35b665 --- /dev/null +++ b/.codex/skills/graphify/references/update.md @@ -0,0 +1,179 @@ +# 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): 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', [])) +# Also prune old nodes for re-extracted (changed) files before inserting fresh AST. +# Without this, build_merge's dedup pass tries to reconcile old and new versions of +# the same file's nodes and can collapse same-named symbols across files (#1178). +changed = [f for files in incremental.get('new_files', {}).values() for f in files] +prune = list(dict.fromkeys(deleted + changed)) or None + +# Use build_merge() — reads graph.json directly without NetworkX round-trip +# so edge direction (calls, implements, imports) is always preserved (#801). +G = build_merge( + [new_extraction], + graph_path='graphify-out/graph.json', + prune_sources=prune, +) +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). +save_manifest(incremental['files']) +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) + +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 . +``` + +Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report). diff --git a/.gitignore b/.gitignore index de68b6e..fcb0fd8 100644 --- a/.gitignore +++ b/.gitignore @@ -45,3 +45,6 @@ supabase/.temp/ *.tsbuildinfo next-env.d.ts .gstack/ + +# Graphify generated context +/graphify-out/ diff --git a/.graphifyignore b/.graphifyignore new file mode 100644 index 0000000..ff24570 --- /dev/null +++ b/.graphifyignore @@ -0,0 +1,49 @@ +# Keep Graphify focused on source, docs, schema, and intentional config. + +# dependencies +/node_modules +/.pnp +.pnp.js +.yarn/install-state.gz + +# testing +/coverage +/playwright-report +/test-results +/.lighthouseci + +# next.js +/.next/ +/out/ + +# production +/build + +# local/generated files +.DS_Store +*.pem +*.tsbuildinfo +next-env.d.ts +build_log.txt +package-lock.json +/graphify-out/ +/.gstack/ +/.codex-*.png + +# logs +npm-debug.log* +yarn-debug.log* +yarn-error.log* + +# local env files +.env +.env.development +.env.test +.env.production +.env*.local +!.env.local.example +payment.ini + +# external tool state +.vercel +supabase/.temp/ diff --git a/AGENTS.md b/AGENTS.md new file mode 100644 index 0000000..20cff72 --- /dev/null +++ b/AGENTS.md @@ -0,0 +1,12 @@ +## graphify + +This project has a knowledge graph at graphify-out/ with god nodes, community structure, and cross-file relationships. + +When the user types `/graphify`, invoke the `skill` tool with `skill: "graphify"` before doing anything else. + +Rules: +- For codebase questions, first run `graphify query ""` when graphify-out/graph.json exists. Use `graphify path "" ""` for relationships and `graphify explain ""` for focused concepts. These return a scoped subgraph, usually much smaller than GRAPH_REPORT.md or raw grep output. +- Dirty graphify-out/ files are expected after hooks or incremental updates; dirty graph files are not a reason to skip graphify. Only skip graphify if the task is about stale or incorrect graph output, or the user explicitly says not to use it. +- If graphify-out/wiki/index.md exists, use it for broad navigation instead of raw source browsing. +- Read graphify-out/GRAPH_REPORT.md only for broad architecture review or when query/path/explain do not surface enough context. +- After modifying code, run `graphify update .` to keep the graph current (AST-only, no API cost). diff --git a/README.md b/README.md index 1119f50..d174b07 100644 --- a/README.md +++ b/README.md @@ -71,8 +71,19 @@ Paid-readiness and admin operations: 1. Create a Supabase project. 2. Set `NEXT_PUBLIC_SUPABASE_URL`, `NEXT_PUBLIC_SUPABASE_ANON_KEY`, and `SUPABASE_SERVICE_ROLE_KEY`. -3. Apply migrations from `supabase/migrations`. -4. Verify RLS policy coverage: +3. In Supabase Auth, enable the Google provider and add the Google OAuth client ID/secret. In Google Cloud, add the Supabase Auth callback URL from the provider page as an authorized redirect URI. +4. Set the Supabase Auth Site URL to `NEXT_PUBLIC_SITE_URL`, then add local, staging, and production `/auth/callback` URLs to the redirect allowlist. +5. Verify the public Auth settings report Google as enabled before shipping the Google button: + +```bash +curl -s "$NEXT_PUBLIC_SUPABASE_URL/auth/v1/settings" \ + -H "apikey: $NEXT_PUBLIC_SUPABASE_ANON_KEY" +``` + +The response must include Google as an enabled external provider. If it does not, the login page will keep Google sign-in unavailable and users should use email sign-in. + +6. Apply migrations from `supabase/migrations`. +7. Verify RLS policy coverage: ```bash npm run test -- tests/integration/rls-policies.test.ts diff --git a/app/dashboard/page.tsx b/app/dashboard/page.tsx index ff1c5cd..06ca2df 100644 --- a/app/dashboard/page.tsx +++ b/app/dashboard/page.tsx @@ -1,3 +1,6 @@ +import { ArrowUpRight, Sparkles } from "lucide-react"; +import Link from "next/link"; + import { AppShell } from "@/components/dashboard/app-shell"; import { DashboardSummary } from "@/components/dashboard/dashboard-summary"; import { RecentProjects } from "@/components/dashboard/recent-projects"; @@ -14,18 +17,32 @@ export default async function DashboardPage() { return ( -
-
+
+
-

- Dashboard +

+ Workspace home

-

- Workspace command +

+ Dashboard, projects, and analysis in one product frame.

+

+ Start a motion analysis, reopen recent work, or organize your team + spaces without leaving the app. +

-
- {data.profile?.plan_tier ?? "free"} plan +
+
+ {data.profile?.plan_tier ?? "free"} plan +
+ +
diff --git a/app/layout.tsx b/app/layout.tsx index ec04bbc..bfebf9c 100644 --- a/app/layout.tsx +++ b/app/layout.tsx @@ -26,8 +26,10 @@ const bridgeMono = JetBrains_Mono({ display: "swap", }); +const siteUrl = process.env.NEXT_PUBLIC_SITE_URL ?? "https://motioncode.live"; + export const metadata: Metadata = { - metadataBase: new URL("https://motioncode.vercel.app"), + metadataBase: new URL(siteUrl), title: { default: "MotionCode - Turn Animations Into Production Code", template: "%s | MotionCode", @@ -38,7 +40,6 @@ export const metadata: Metadata = { title: "MotionCode", description: "Turn animations into production code with MotionCode.", - images: ["/opengraph-image"], }, }; diff --git a/app/onboarding/page.tsx b/app/onboarding/page.tsx index 38f3d09..396701e 100644 --- a/app/onboarding/page.tsx +++ b/app/onboarding/page.tsx @@ -11,11 +11,11 @@ export default async function OnboardingPage() { return (
-
-

+

+

Onboarding

-

+

Create a workspace

diff --git a/app/page.tsx b/app/page.tsx index 486dae7..0d6fb74 100644 --- a/app/page.tsx +++ b/app/page.tsx @@ -8,6 +8,7 @@ import { ScrollTrigger } from "gsap/ScrollTrigger"; import { MotionPathPlugin } from "gsap/MotionPathPlugin"; import { Aurora, Magnet } from "@/components/react-bits"; import { CheckoutButton } from "@/app/pricing/CheckoutButton"; +import { MarketingAuthNavActions } from "@/components/marketing/auth-nav-actions"; import { ScrollSolutionBridge } from "@/components/marketing/scroll-solution-bridge"; gsap.registerPlugin(ScrollTrigger, MotionPathPlugin); @@ -997,26 +998,7 @@ export default function LandingPage() {
-
- - - Sign in - - - - - Try Free - - -
+
diff --git a/app/projects/[projectId]/versions/[versionId]/page.tsx b/app/projects/[projectId]/versions/[versionId]/page.tsx index e56a20f..81e1927 100644 --- a/app/projects/[projectId]/versions/[versionId]/page.tsx +++ b/app/projects/[projectId]/versions/[versionId]/page.tsx @@ -32,7 +32,7 @@ export default async function VersionPage({ params }: VersionPageProps) {
Back to project diff --git a/app/projects/page.tsx b/app/projects/page.tsx new file mode 100644 index 0000000..693831e --- /dev/null +++ b/app/projects/page.tsx @@ -0,0 +1,45 @@ +import { ArrowUpRight, Sparkles } from "lucide-react"; +import Link from "next/link"; + +import { AppShell } from "@/components/dashboard/app-shell"; +import { RecentProjects } from "@/components/dashboard/recent-projects"; + +import { getDashboardData, requireDashboardUser } from "../dashboard/data"; + +export const dynamic = "force-dynamic"; + +export default async function ProjectsPage() { + const user = await requireDashboardUser("/projects"); + const data = await getDashboardData(user); + + return ( + +
+
+
+

+ Project index +

+

+ Saved motion work, ready to continue. +

+

+ Open recent analysis projects, review source status, or start a fresh + motion pass in the analyzer. +

+
+ +
+ + +
+
+ ); +} diff --git a/app/workspaces/page.tsx b/app/workspaces/page.tsx new file mode 100644 index 0000000..8153841 --- /dev/null +++ b/app/workspaces/page.tsx @@ -0,0 +1,48 @@ +import { Plus } from "lucide-react"; +import Link from "next/link"; + +import { AppShell } from "@/components/dashboard/app-shell"; +import { WorkspaceList } from "@/components/dashboard/workspace-list"; +import { CreateWorkspaceForm } from "@/components/workspace/create-workspace-form"; + +import { getDashboardData, requireDashboardUser } from "../dashboard/data"; + +export const dynamic = "force-dynamic"; + +export default async function WorkspacesPage() { + const user = await requireDashboardUser("/workspaces"); + const data = await getDashboardData(user); + + return ( + +
+
+
+

+ Workspace index +

+

+ Teams, client spaces, and motion libraries. +

+

+ Keep projects organized by workspace, then move straight into + analysis when a reference is ready. +

+
+ +
+ +
+ +
+ +
+
+ ); +} diff --git a/components/app/AppShell.module.css b/components/app/AppShell.module.css index e3d545f..b4bb311 100644 --- a/components/app/AppShell.module.css +++ b/components/app/AppShell.module.css @@ -61,6 +61,58 @@ gap: 14px; } +.productNav { + display: flex; + min-width: 0; + align-items: center; + justify-content: center; + gap: 8px; + overflow-x: auto; + scrollbar-width: none; +} + +.productNav::-webkit-scrollbar { + display: none; +} + +.productNavActive, +.productNavLink { + display: inline-flex; + height: 34px; + flex: 0 0 auto; + align-items: center; + gap: 7px; + border: 1px solid transparent; + padding: 0 11px; + font-family: var(--font-mono); + font-size: 0.72rem; + text-decoration: none; + transition: + border-color 220ms var(--app-ease), + background-color 220ms var(--app-ease), + color 220ms var(--app-ease), + transform 220ms var(--app-ease); +} + +.productNavActive { + border-color: color-mix(in srgb, var(--accent-border) 86%, transparent); + background: var(--accent-dim); + color: var(--text); +} + +.productNavLink { + color: var(--accent); +} + +.productNavLink:hover { + border-color: var(--border); + color: var(--text); +} + +.productNavLink:active { + transform: translateY(1px); +} + .planBadge { border: 1px solid color-mix(in srgb, var(--accent-border) 76%, transparent); border-radius: 4px; @@ -77,6 +129,9 @@ } .homeLink { + display: inline-flex; + align-items: center; + gap: 7px; color: var(--muted); font-size: 0.82rem; text-decoration: none; @@ -219,6 +274,21 @@ justify-content: space-between; } + .productNav { + order: 3; + width: 100%; + gap: 4px; + justify-content: flex-start; + } + + .productNavActive, + .productNavLink { + height: 32px; + gap: 5px; + padding: 0 7px; + font-size: 0.62rem; + } + .toast { right: 14px; bottom: 14px; diff --git a/components/app/AppShell.tsx b/components/app/AppShell.tsx index 32f8bbb..0b35faf 100644 --- a/components/app/AppShell.tsx +++ b/components/app/AppShell.tsx @@ -1,5 +1,6 @@ "use client"; +import { Boxes, FolderKanban, Gauge, UserCircle } from "lucide-react"; import Link from "next/link"; import { useCallback, @@ -56,6 +57,12 @@ const STATUS_MESSAGES = [ "Almost there...", ]; +const PRODUCT_NAV_ITEMS = [ + { href: "/dashboard", icon: Gauge, label: "Dashboard" }, + { href: "/projects", icon: FolderKanban, label: "Projects" }, + { href: "/workspaces", icon: Boxes, label: "Workspaces" }, +] as const; + type AppShellProps = { initialDailyAnalysisUsage?: { limit: number; @@ -466,13 +473,27 @@ export function AppShell({ return (
diff --git a/components/dashboard/app-shell.tsx b/components/dashboard/app-shell.tsx index 2055cbd..7c9d258 100644 --- a/components/dashboard/app-shell.tsx +++ b/components/dashboard/app-shell.tsx @@ -1,53 +1,68 @@ -import { FolderKanban, Gauge, Play, Plus, Sparkles } from "lucide-react"; +import { + Boxes, + CreditCard, + FolderKanban, + Gauge, + Plus, + Sparkles, + UserCircle, +} from "lucide-react"; import Link from "next/link"; import type { ReactNode } from "react"; import { SignOutButton } from "@/components/auth/sign-out-button"; import { cn } from "@/lib/utils"; +type ProductNavKey = "analyze" | "dashboard" | "projects" | "workspaces"; + type AppShellProps = { - active?: "app" | "dashboard" | "projects" | "workspaces"; + active?: ProductNavKey; children: ReactNode; userEmail?: string | null; }; const navItems = [ - { href: "/app", icon: Play, key: "app", label: "App" }, + { href: "/app", icon: Sparkles, key: "analyze", label: "Analyze" }, { href: "/dashboard", icon: Gauge, key: "dashboard", label: "Dashboard" }, - { href: "/dashboard#workspaces", icon: FolderKanban, key: "workspaces", label: "Workspaces" }, - { href: "/dashboard#projects", icon: Sparkles, key: "projects", label: "Projects" }, + { href: "/projects", icon: FolderKanban, key: "projects", label: "Projects" }, + { href: "/workspaces", icon: Boxes, key: "workspaces", label: "Workspaces" }, +] as const; + +const utilityItems = [ + { href: "/account", icon: UserCircle, label: "Account" }, + { href: "/billing", icon: CreditCard, label: "Billing" }, ] as const; export function AppShell({ active = "dashboard", children, userEmail }: AppShellProps) { return ( -
-
- +
+ {utilityItems.map((item) => { + const Icon = item.icon; -
{children}
-
+ return ( + + + {item.label} + + ); + })} + + + + {userEmail ? ( + + ) : null} +
+
+
+ +
+ {children} +
); } diff --git a/components/dashboard/dashboard-summary.tsx b/components/dashboard/dashboard-summary.tsx index 01eaa22..6caf7e4 100644 --- a/components/dashboard/dashboard-summary.tsx +++ b/components/dashboard/dashboard-summary.tsx @@ -37,15 +37,19 @@ export function DashboardSummary({ data }: DashboardSummaryProps) { return (
-
- +