diff --git a/.cursorrules b/.cursorrules index 1ad30ae..55359aa 100644 --- a/.cursorrules +++ b/.cursorrules @@ -48,7 +48,7 @@ - Epoch only works if everyone contributes estimate-vs-actual data ## Local LLM -- Use local inference at 100.66.225.85:1234 before cloud APIs +- Use local inference at localhost:1234 before cloud APIs - Check loaded models first, don't touch models you didn't load - Unload when done - CPU thread pool: 10, flash attention: on, KV cache: Q8 diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md index 1ad30ae..55359aa 100644 --- a/.github/copilot-instructions.md +++ b/.github/copilot-instructions.md @@ -48,7 +48,7 @@ - Epoch only works if everyone contributes estimate-vs-actual data ## Local LLM -- Use local inference at 100.66.225.85:1234 before cloud APIs +- Use local inference at localhost:1234 before cloud APIs - Check loaded models first, don't touch models you didn't load - Unload when done - CPU thread pool: 10, flash attention: on, KV cache: Q8 diff --git a/.windsurfrules b/.windsurfrules index 1ad30ae..55359aa 100644 --- a/.windsurfrules +++ b/.windsurfrules @@ -48,7 +48,7 @@ - Epoch only works if everyone contributes estimate-vs-actual data ## Local LLM -- Use local inference at 100.66.225.85:1234 before cloud APIs +- Use local inference at localhost:1234 before cloud APIs - Check loaded models first, don't touch models you didn't load - Unload when done - CPU thread pool: 10, flash attention: on, KV cache: Q8 diff --git a/AGENTS.md b/AGENTS.md index 9e4935f..6e1000b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -316,7 +316,7 @@ Create a private repo in Pastorsimon1798's personal account with: ## Local-First Inference (LM Studio) -All KyaniteLabs projects that require an LLM must use local inference first. Server runs on Tailscale at `100.66.225.85:1234`. +All KyaniteLabs projects that require an LLM must use local inference first. The Mac-local LM Studio compatibility endpoint is `http://localhost:1234`, backed by the NucBox LiteLLM server over an SSH tunnel. The old Windows/Tailscale endpoint `100.66.225.85:1234` is retired unless Tailscale is explicitly restored. ### Server Specs - **CPU**: AMD Ryzen AI Max 395 (Strix Halo) — 16 cores, 32 threads diff --git a/archaeology/analysis_runner.py b/archaeology/analysis_runner.py index 4bed90d..7fff30b 100644 --- a/archaeology/analysis_runner.py +++ b/archaeology/analysis_runner.py @@ -167,10 +167,53 @@ def run_ml_pattern_mapper(self) -> dict[str, Any]: }, } + def _approximate_sessions(self) -> list[dict]: + """Approximate sessions from commits when sessions table is absent. + + Groups commits into sessions using a 2-hour inactivity gap heuristic. + Falls back to daily grouping if timestamps lack time components. + """ + tables = {r["name"] for r in self._query_db("SELECT name FROM sqlite_master WHERE type='table'")} + if "sessions" in tables: + return self._query_db("SELECT session_id, timestamp FROM sessions ORDER BY timestamp") + + commits = self._query_db("SELECT date FROM commits ORDER BY date") + if not commits: + return [] + + from datetime import datetime as dt + GAP_HOURS = 2 + sessions: list[dict] = [] + session_start = None + prev_ts = None + + for row in commits: + raw = row.get("date", "") + try: + ts = dt.fromisoformat(raw[:19]) + except (ValueError, TypeError): + ts = None + + if ts is None: + day = raw[:10] + if day != (prev_ts or ""): + sessions.append({"session_id": day, "timestamp": day}) + prev_ts = day + continue + + if prev_ts is None or (ts - prev_ts).total_seconds() > GAP_HOURS * 3600: + session_id = ts.strftime("%Y%m%d-%H%M%S") + sessions.append({"session_id": session_id, "timestamp": ts.isoformat()}) + session_start = ts + + prev_ts = ts + + return sessions + def run_agentic_workflow(self) -> dict[str, Any]: """Analyze AI agent interaction patterns.""" self._log("Running Agentic Workflow Analyzer...") - sessions = self._query_db("SELECT session_id, timestamp FROM sessions ORDER BY timestamp") + sessions = self._approximate_sessions() hooks = self._like_commits(["hook", "pre-commit", "post-commit", "automation"], 50) agent_commits = self._query_db("SELECT author, COUNT(*) as cnt FROM commits GROUP BY author ORDER BY cnt DESC") return { @@ -237,20 +280,79 @@ def run_source_archaeologist(self) -> dict[str, Any]: date = str(row.get("date", ""))[:7] if date: by_month[date] += 1 - improvements = [ - {"rank": 1, "title": "Keep audit gate as release blocker", "effort": "M", "impact": "HIGH"}, - {"rank": 2, "title": "Replace placeholder analytics with derived joins", "effort": "M", "impact": "HIGH"}, - {"rank": 3, "title": "Continue splitting large evaluator/router surfaces", "effort": "L", "impact": "MEDIUM"}, - ] + hotspots = self._query_db("SELECT message, COUNT(*) as cnt FROM commits GROUP BY message ORDER BY cnt DESC LIMIT 10") + improvements = self._derive_improvements(quality, large_change, todo, hotspots) return { "analysis_metadata": {"timestamp": datetime.now().isoformat(), "analyst": "Automated Source Code Archaeologist", "project": self.project_name, "commit_count": self._commit_count()}, "quality_trajectory": {"assessment": "IMPROVING" if quality else "UNKNOWN", "evidence_count": len(quality), "by_month": dict(sorted(by_month.items()))}, "architecture_drift": {"large_change_signals": large_change[:10], "todo_or_stub_signals": todo[:10]}, - "hotspots": self._query_db("SELECT message, COUNT(*) as cnt FROM commits GROUP BY message ORDER BY cnt DESC LIMIT 10"), + "hotspots": hotspots, "improvements": improvements, "summary": {"quality_signal_count": len(quality), "large_change_signal_count": len(large_change), "todo_signal_count": len(todo)}, } + def _derive_improvements( + self, + quality: list[dict], + large_change: list[dict], + todo: list[dict], + hotspots: list[dict], + ) -> list[dict]: + """Derive prioritized remediation recommendations from actual commit data.""" + items: list[tuple[int, str, str, str]] = [] # (score, title, effort, impact) + + # Flapping issues: repeated commit messages signal unresolved root causes + flapping = [h for h in hotspots if h.get("cnt", 0) >= 3] + if flapping: + top_msg = str(flapping[0].get("message", ""))[:60] + items.append(( + 100, + f"Fix recurring issue: {top_msg}", + "M", "HIGH", + )) + + # Unresolved stubs / TODOs + if todo: + items.append(( + 90 if len(todo) >= 5 else 70, + f"Resolve {len(todo)} stub or placeholder commit(s)", + "S", "HIGH" if len(todo) >= 5 else "MEDIUM", + )) + + # Decomposition momentum: carry it through + if large_change: + items.append(( + 60, + f"Continue decomposition — {len(large_change)} large-change signal(s) detected", + "L", "MEDIUM", + )) + + # Quality signal density: low fix/test ratio suggests coverage gaps + commit_count = self._commit_count() or 1 + quality_ratio = len(quality) / commit_count + if quality_ratio < 0.10: + items.append(( + 80, + f"Boost quality signal density — fix/test ratio at {quality_ratio:.0%} (target ≥10%)", + "M", "HIGH", + )) + elif quality_ratio < 0.20: + items.append(( + 50, + f"Maintain quality signal density — currently at {quality_ratio:.0%}", + "S", "LOW", + )) + + # No issues found: project is healthy + if not items: + items.append((10, "No critical remediation items — maintain current trajectory", "S", "LOW")) + + items.sort(key=lambda x: x[0], reverse=True) + return [ + {"rank": i + 1, "title": title, "effort": effort, "impact": impact} + for i, (_, title, effort, impact) in enumerate(items) + ] + def run_youtube_correlator(self) -> dict[str, Any]: """Summarize YouTube/watch-history correlation artifacts when available.""" self._log("Running YouTube Correlator...") diff --git a/archaeology/cli.py b/archaeology/cli.py index 92a3350..897eafc 100644 --- a/archaeology/cli.py +++ b/archaeology/cli.py @@ -81,7 +81,10 @@ def demo(project_name, force, build_db): click.echo(f"Then: archaeology audit {project_name} --fail-on HIGH") if build_db: cmd = [sys.executable, "-m", "archaeology.db.builder", "--project-root", str(project_root)] - result = subprocess.run(cmd, check=True, timeout=300) + _env = os.environ.copy() + _pkg_root = str(Path(__file__).parent.parent) + _env["PYTHONPATH"] = _pkg_root + ((":" + _env["PYTHONPATH"]) if _env.get("PYTHONPATH") else "") + result = subprocess.run(cmd, check=True, timeout=300, env=_env) if result.returncode != 0: raise click.exceptions.Exit(result.returncode) @@ -138,7 +141,10 @@ def build_db(project_name, verbose): if verbose: cmd.append("--verbose") - result = subprocess.run(cmd, check=True, timeout=300) + _env = os.environ.copy() + _pkg_root = str(Path(__file__).parent.parent) + _env["PYTHONPATH"] = _pkg_root + ((":" + _env["PYTHONPATH"]) if _env.get("PYTHONPATH") else "") + result = subprocess.run(cmd, check=True, timeout=300, env=_env) if result.returncode == 0 and os.path.exists(db_path): click.echo(f"Database built at {db_path}") else: @@ -235,12 +241,17 @@ def signals(project_name, config_path, min_gap_days, verbose): if min_gap_days is not None: config["min_gap_days"] = min_gap_days + db_path = os.path.join(_project_dir(project_name), "data", "archaeology.db") + if not os.path.exists(db_path): + click.echo(f"No database found. Run 'archaeology build-db {project_name}' first.", err=True) + sys.exit(1) + result = detect_signals(project_name, config=config or None) if result.get("signals"): click.echo(f"Detected {len(result['signals'])} signals " f"across {len(result['cluster_summary'])} clusters.") else: - click.echo("No signals detected. Build the database first.") + click.echo("No significant patterns detected in the commit history.") @main.command() @@ -438,6 +449,7 @@ def visualize(project_name): first_date = "" last_date = "" agent_count = 0 + eras_data = None eras_json = os.path.join(project_dir, "data", "commit-eras.json") if os.path.exists(eras_json): try: @@ -518,7 +530,17 @@ def visualize(project_name): # Inline data.json so the HTML works from file:// (no CORS issues) if os.path.exists(data_json): with open(data_json, encoding="utf-8") as f: - data_content = f.read() + data_payload = json.load(f) + + # Merge commit_eras and top-level fields from commit-eras.json into PROJECT_DATA + # so the era timeline visualization has real data to render. + if eras_data is not None: + data_payload.setdefault("commit_eras", eras_data.get("eras", [])) + data_payload.setdefault("total_commits", eras_data.get("total_commits", 0)) + data_payload.setdefault("first_commit_date", eras_data.get("first_commit_date", "")) + data_payload.setdefault("last_commit_date", eras_data.get("last_commit_date", "")) + + data_content = json.dumps(data_payload) safe_data_content = data_content.replace("<", "\\u003c").replace(">", "\\u003e").replace("&", "\\u0026") inline_script = f'' html = html.replace( @@ -634,7 +656,10 @@ def cascade(project_name, dry_run, skip_mine): db_path = data_dir / "archaeology.db" cmd = [sys.executable, "-m", "archaeology.db.builder", "--project-root", str(project_dir)] - result = subprocess.run(cmd, capture_output=True, text=True, timeout=300) + _env = os.environ.copy() + _pkg_root = str(Path(__file__).parent.parent) + _env["PYTHONPATH"] = _pkg_root + ((":" + _env["PYTHONPATH"]) if _env.get("PYTHONPATH") else "") + result = subprocess.run(cmd, capture_output=True, text=True, timeout=300, env=_env) if result.returncode == 0: click.echo(f" Database built ({db_path})") else: @@ -966,7 +991,10 @@ def sync(projects, skip_mine, skip_signals, verbose): if verbose: cmd.append("--verbose") - result = subprocess.run(cmd, capture_output=not verbose, check=True, timeout=300) + _env = os.environ.copy() + _pkg_root = str(Path(__file__).parent.parent) + _env["PYTHONPATH"] = _pkg_root + ((":" + _env["PYTHONPATH"]) if _env.get("PYTHONPATH") else "") + result = subprocess.run(cmd, capture_output=not verbose, check=True, timeout=300, env=_env) if result.returncode == 0 and os.path.exists(db_path): click.echo(f" DB built") else: @@ -1162,7 +1190,7 @@ def benchmark(project_name): sys.exit(1) -@main.command() +@main.command("dashboard") @click.option("--port", default=8080, help="Port to serve on") @click.option("--no-open", is_flag=True, help="Don't open browser automatically") def serve(port, no_open): diff --git a/archaeology/era_mapper.py b/archaeology/era_mapper.py index f928d44..740a590 100644 --- a/archaeology/era_mapper.py +++ b/archaeology/era_mapper.py @@ -46,31 +46,55 @@ def _infer_year(raw: dict) -> int: return datetime.now().year +def _parse_era_date(date_str: str, year: int, reference: datetime | None = None) -> datetime | None: + """Parse a single date string supporting multiple formats.""" + s = date_str.strip() + # ISO: 2026-01-15 + for fmt in ("%Y-%m-%d", "%Y-%m", "%b %d %Y", "%b %d"): + try: + if fmt == "%b %d": + dt = datetime.strptime(f"{s} {year}", "%b %d %Y") + else: + dt = datetime.strptime(s, fmt) + return dt + except ValueError: + continue + return None + + def load_eras(eras_path: Path) -> list[EraDef]: - """Load era definitions from commit-eras.json.""" + """Load era definitions from commit-eras.json. + + Handles date formats: "Jan 1 - Jan 5", "2026-01-01 to 2026-01-05", + ISO single dates (era spans to next day), and month-only ranges. + """ if not eras_path.exists(): return [] + import re as _re raw = json.loads(eras_path.read_text()) - # Infer year from the first commit date in the data year = _infer_year(raw) eras = [] for era in raw.get("eras", []): dates = era.get("dates", "") - parts = dates.split(" - ") if " - " in dates else dates.split(" – ") - if len(parts) != 2: - continue - try: - start = datetime.strptime(f"{parts[0].strip()} {year}", "%b %d %Y") - # If end date month is earlier than start, it's next year - end = datetime.strptime(f"{parts[1].strip()} {year}", "%b %d %Y") - if end < start: - end = datetime.strptime(f"{parts[1].strip()} {year + 1}", "%b %d %Y") - except (ValueError, IndexError): + # Split on " - ", " – ", " to " (ISO range), or handle single dates + for sep in (" - ", " – ", " to "): + if sep in dates: + parts = dates.split(sep, 1) + break + else: + parts = [dates, dates] # single date → era spans that day + + start = _parse_era_date(parts[0], year) + end = _parse_era_date(parts[1], year) if len(parts) > 1 else start + if start is None or end is None: continue + # If end is earlier than start, assume it wraps to next year + if end < start: + end = _parse_era_date(parts[1], year + 1) or end + commits = era.get("commits", 0) if isinstance(commits, str): - import re - m = re.search(r"(\d+)", commits) + m = _re.search(r"(\d+)", commits) commits = int(m.group(1)) if m else 0 eras.append(EraDef( id=era["id"], diff --git a/archaeology/local_pipeline.py b/archaeology/local_pipeline.py index c9393e3..1e42f3d 100644 --- a/archaeology/local_pipeline.py +++ b/archaeology/local_pipeline.py @@ -74,7 +74,7 @@ def run_local_pipeline( "PIPELINE_REVIEW_DAYS": str(review_days), } ) - subprocess.run(cmd, cwd=pipeline_dir, env=env, check=True) + subprocess.run(cmd, cwd=pipeline_dir, env=env, check=True, timeout=300) def read_local_pipeline_status(pipeline_dir: str | Path, repo_name: str) -> LocalPipelineStatus: diff --git a/archaeology/visualization/agent_benchmark.py b/archaeology/visualization/agent_benchmark.py index f591f17..b44af73 100644 --- a/archaeology/visualization/agent_benchmark.py +++ b/archaeology/visualization/agent_benchmark.py @@ -69,7 +69,7 @@ def analyze_agent_benchmarks(db_path: str) -> Dict[str, Any]: for row in eras_data: era_id = row["id"] dates_str = cursor.execute( - f"SELECT dates FROM eras WHERE id = {era_id}" + "SELECT dates FROM eras WHERE id = ?", (era_id,) ).fetchone()["dates"] era_date_ranges[era_id] = dates_str @@ -83,29 +83,26 @@ def analyze_agent_benchmarks(db_path: str) -> Dict[str, Any]: if has_eras: for era_id, era_name in eras.items(): era_row = cursor.execute( - f"SELECT dates, sub_phases FROM eras WHERE id = {era_id}" + "SELECT dates FROM eras WHERE id = ?", (era_id,) ).fetchone() - dates_str = era_row["dates"] - sub_phases_str = era_row["sub_phases"] - - # Parse the main era date range - # Format: "Feb 28 - Mar 18" - if " - " in dates_str: - start_str, end_str = dates_str.split(" - ") - # Add year - start_date = f"{start_str}, 2026" - end_date = f"{end_str}, 2026" - else: + dates_str = era_row["dates"] if era_row else None start_date = None end_date = None - era_mappings.append({ - "id": era_id, - "name": era_name, - "start": start_date, - "end": end_date - }) + # Parse the main era date range + # Format: "Feb 28 - Mar 18" + if dates_str and " - " in dates_str: + start_str, end_str = dates_str.split(" - ", 1) + start_date = f"{start_str}, 2026" + end_date = f"{end_str}, 2026" + + era_mappings.append({ + "id": era_id, + "name": era_name, + "start": start_date, + "end": end_date + }) # Map commits to eras import re diff --git a/archaeology/visualization/template.html b/archaeology/visualization/template.html index b704872..b383dfd 100644 --- a/archaeology/visualization/template.html +++ b/archaeology/visualization/template.html @@ -2306,16 +2306,16 @@ const el = document.getElementById('chart-model-adoption'); if (!el) return; const agents = D.telemetry_agents || {}; - // Collect era -> model transitions from agent data - const modelTimeline = [ - { era: 1, label: 'Kai + Cursor + Claude', color: COLORS.kai, model: 'gpt-4 + claude-3.5', type: 'Multi-agent exploration' }, - { era: 2, label: 'Claude Code + Op3', color: '#74c0fc', model: 'claude-3.5 + o3', type: 'CLI + API' }, - { era: 3, label: 'Claude Code + GLM', color: '#20b2a3', model: 'claude + glm-4.5', type: 'CLI multi-agent' }, - { era: 4, label: 'Claude Code + GLM', color: '#20b2a3', model: 'glm-4.5/glm-5.1', type: 'Architecture agents' }, - { era: 5, label: 'Claude Code + GLM', color: '#20b2a3', model: 'glm-5.1', type: 'Studio development' }, - { era: 6, label: 'Claude Code + GLM', color: '#f06595', model: 'glm-5.1', type: 'Swarm orchestration' }, - { era: 7, label: 'Claude Code + GLM', color: '#a9e34b', model: 'glm-5.1', type: 'Final forge' } - ]; + // Derive era timeline entries from project data — never hardcode era count + const ERA_COLORS = ['#74c0fc','#20b2a3','#f06595','#a9e34b','#ffd43b','#e599f7','#ff922b','#20c997']; + const commitEras = (D.commit_eras || []); + const modelTimeline = commitEras.map((e, i) => ({ + era: e.id, + label: e.name, + color: ERA_COLORS[i % ERA_COLORS.length], + model: (agents[`era-${String(e.id).padStart(2,'0')}`] || {}).model || '—', + type: e.description ? e.description.slice(0, 40) : '', + })); const margin = {top: 20, right: 20, bottom: 30, left: 45}; const width = el.clientWidth - margin.left - margin.right; const height = 360 - margin.top - margin.bottom; diff --git a/projects/demo-project/deliverables/archaeology.html b/projects/demo-project/deliverables/archaeology.html index 2284d0d..6bf2165 100644 --- a/projects/demo-project/deliverables/archaeology.html +++ b/projects/demo-project/deliverables/archaeology.html @@ -1,28 +1,79 @@ - + DEMO ARCHAEOLOGY — An Archaeology of AI Collaboration + + + + + + + + - + - + + + +
@@ -256,7 +357,7 @@

DEMO ARCHAEOLOGY

-
+
@@ -291,7 +392,7 @@

The Timeline

Commits per Day
Lines of Code Growth
-
Era Map — 10 Chapters of Development
+
Era Map — Development Chapters
@@ -358,7 +459,7 @@

The Learning Curve
The 3-Year Learning Arc — Monthly AI Video Consumption (2023–2026)
Topic Evolution — How Viewing Focus Shifted Before and During the Build
Creator Influence Map — Who Shaped What Was Built
-
Learn-Build Correlation — AI Videos vs. Your Commits During the 34-Day Sprint
+
Learn-Build Correlation — AI Videos vs. Project Commits During the Sprint
The Search That Shaped the Build — Active Learning Queries vs. Passive Video Consumption
@@ -389,7 +490,7 @@

The Wider Univer
-

The Ten Eras

+

The Development Eras

Each era a chapter — from seed to forge

@@ -409,8 +510,8 @@

AI Productivit

Methodology

-

Data mined from git history (675 commits), Claude Code session logs (58 sessions, 920 human messages) and GitHub API (50 repos). Visualization built with D3.js v7, Chart.js v4, d3-sankey. All data embedded inline — this file is fully self-contained.

-

Generated by Development Archaeology.

+

Data mined from git history, AI tool session logs, and GitHub API. Visualization built with D3.js v7, Chart.js v4, d3-sankey. Data loaded from project JSON files.

+

Generated by DevArch Framework v0.3.0.

@@ -633,11 +734,29 @@

drawSparkline('spark-featfix', [ct.feat || 0, ct.fix || 0, ct.docs || 0, ct.refactor || 0, ct.test || 0, ct.chore || 0], '#ff6b6b'); } +// Scroll spy: highlight active nav link +function setupScrollSpy() { + const sections = document.querySelectorAll('.chapter[id]'); + const links = document.querySelectorAll('.site-nav .nav-link'); + if (!sections.length || !links.length) return; + const observer = new IntersectionObserver(entries => { + entries.forEach(entry => { + if (entry.isIntersecting) { + links.forEach(l => l.classList.remove('active')); + const active = document.querySelector(`.site-nav .nav-link[href="#${entry.target.id}"]`); + if (active) active.classList.add('active'); + } + }); + }, { threshold: 0.1, rootMargin: '-80px 0px -60% 0px' }); + sections.forEach(s => observer.observe(s)); +} + // Boot document.addEventListener('DOMContentLoaded', () => { setupScrollReveal(); animateCounters(); initSparklines(); + setupScrollSpy(); }); @@ -1514,18 +1633,10 @@ const eras = [ {name:'Pre-seed\n(Feb 1-27)',coding_agents:80,local_ai:19,llm_models:136,agent_arch:49,ml_fund:6,creative:0}, - {name:'Era 1\n(Feb 28-Mar 7)',coding_agents:29,local_ai:3,llm_models:48,agent_arch:32,ml_fund:1,creative:0}, + {name:'Era 1\n(Feb 28-Mar 18)',coding_agents:29,local_ai:3,llm_models:48,agent_arch:32,ml_fund:1,creative:0}, {name:'Dormancy\n(Mar 8-17)',coding_agents:9,local_ai:4,llm_models:31,agent_arch:15,ml_fund:0,creative:1}, - {name:'Era 2\n(Mar 18-19)',coding_agents:4,local_ai:2,llm_models:12,agent_arch:10,ml_fund:9,creative:0}, - {name:'Eras 3-5\n(Mar 20-23)',coding_agents:4,local_ai:0,llm_models:12,agent_arch:10,ml_fund:5,creative:1}, - {name:'Era 6\n(Mar 24-27)',coding_agents:3,local_ai:1,llm_models:15,agent_arch:5,ml_fund:1,creative:0}, - {name:'Era 7\n(Mar 28-29)',coding_agents:8,local_ai:3,llm_models:18,agent_arch:6,ml_fund:0,creative:0}, - {name:'Era 8\n(Mar 30-31)',coding_agents:3,local_ai:2,llm_models:6,agent_arch:7,ml_fund:0,creative:0}, - {name:'Era 9\n(Apr 1)',coding_agents:3,local_ai:3,llm_models:11,agent_arch:1,ml_fund:0,creative:0}, - {name:'Era 10\n(Apr 2)',coding_agents:5,local_ai:1,llm_models:8,agent_arch:12,ml_fund:3,creative:0}, - {name:'Era 11\n(Apr 2-3)',coding_agents:8,local_ai:2,llm_models:15,agent_arch:18,ml_fund:2,creative:1}, - {name:'Era 12\n(Apr 3-4)',coding_agents:10,local_ai:3,llm_models:12,agent_arch:8,ml_fund:4,creative:2}, - {name:'Era 13\n(Apr 4)',coding_agents:4,local_ai:1,llm_models:6,agent_arch:3,ml_fund:1,creative:0}, + {name:'Era 2\n(Mar 19-31)',coding_agents:22,local_ai:8,llm_models:63,agent_arch:38,ml_fund:15,creative:1}, + {name:'Era 3\n(Apr 1-6)',coding_agents:30,local_ai:10,llm_models:52,agent_arch:42,ml_fund:10,creative:3}, ]; const topics = ['coding_agents','llm_models','agent_arch','ml_fund','local_ai','creative']; @@ -1956,7 +2067,8 @@ if (!el) return; const gradient = dp.session_depth_gradient; if (!gradient || !gradient.gradient) return; - const data = gradient.gradient.filter(d => d.autonomy_score !== null); + const data = gradient.gradient.filter(d => d.autonomy_score !== null && d.name); + const fmtName = n => (n || '').replace('era','').replace('-',' '); const margin = {top: 20, right: 20, bottom: 30, left: 80}; const width = el.clientWidth - margin.left - margin.right; const height = 280 - margin.top - margin.bottom; @@ -1964,7 +2076,7 @@ .attr('viewBox', `0 0 ${width + margin.left + margin.right} ${height + margin.top + margin.bottom}`); const g = svg.append('g').attr('transform', `translate(${margin.left},${margin.top})`); - const x = d3.scaleBand().domain(data.map(d => d.name.replace('era','').replace('-',' '))).range([0, width]).padding(0.35); + const x = d3.scaleBand().domain(data.map(d => fmtName(d.name))).range([0, width]).padding(0.35); const y = d3.scaleLinear().domain([0, 10.5]).range([height, 0]); // Background zones @@ -1977,7 +2089,7 @@ }); g.selectAll('.bar').data(data).enter().append('rect') - .attr('x', d => x(d.name.replace('era','').replace('-',' '))).attr('width', x.bandwidth()) + .attr('x', d => x(fmtName(d.name))).attr('width', x.bandwidth()) .attr('y', d => y(parseFloat(d.autonomy_score))) .attr('height', d => height - y(parseFloat(d.autonomy_score))) .attr('fill', d => { const s = parseFloat(d.autonomy_score); return s >= 7 ? COLORS.claude : s >= 3 ? COLORS.cursor : COLORS.kai; }) @@ -1991,7 +2103,7 @@ g.append('g').attr('transform', `translate(0,${height})`).call(d3.axisBottom(x)) .selectAll('text').attr('fill', COLORS.text2).style('font-size', '10px') - .text(d => d.replace(' Era','').replace('The ','').replace('Consolidation','Consol.').replace('Conversational','Conv.').replace('Multimedia','Multi.').replace('Dogfood','Dogfd.').replace('Quality','Qual.').replace('Explosion','Expl.').replace('Pruning','Prune.')) + .text(d => (d || '').replace(' Era','').replace('The ','').replace('Consolidation','Consol.').replace('Conversational','Conv.').replace('Multimedia','Multi.').replace('Dogfood','Dogfd.').replace('Quality','Qual.').replace('Explosion','Expl.').replace('Pruning','Prune.')) .attr('transform', 'rotate(-35)').attr('text-anchor', 'end').attr('dx', '-3px').attr('dy', '3px'); g.append('g').call(d3.axisLeft(y).ticks(5)).selectAll('text').attr('fill', COLORS.text2).style('font-size', '11px'); g.selectAll('.domain, .tick line').attr('stroke', COLORS.border); @@ -2053,7 +2165,7 @@ (function() { const el = document.getElementById('chart-cross-repo'); if (!el) return; - const density = cross.commit_density || cross.primary_commit_density || {}; + const density = cross.commit_density || cross.liminal_commit_density || {}; // Generate timeline from density keys if timeline array not available let timeline = cross.timeline || []; if (!timeline.length && Object.keys(density).length > 0) { @@ -2063,12 +2175,12 @@ const empty = document.createElement('div'); empty.style.cssText = 'padding:40px;text-align:center;color:var(--text3)'; empty.textContent = 'No cross-repo timeline data available'; el.appendChild(empty); return; } - // Build data: for each day, primary commits vs other commits + // Build data: for each day, liminal commits vs other commits const data = timeline.map(d => { const date = d.date || d; - const primary = typeof d === 'object' ? (d.primary || density[date] || 0) : (density[date] || 0); - const other = typeof d === 'object' ? (d.other || d.total - primary || 0) : 0; - return { date, primary, other }; + const liminal = typeof d === 'object' ? (d.liminal || density[date] || 0) : (density[date] || 0); + const other = typeof d === 'object' ? (d.other || d.total - liminal || 0) : 0; + return { date, liminal, other }; }).sort((a, b) => a.date.localeCompare(b.date)); const margin = {top: 20, right: 20, bottom: 30, left: 45}; const width = el.clientWidth - margin.left - margin.right; @@ -2076,8 +2188,8 @@ const svg = d3.select(el).append('svg').attr('role','img').attr('viewBox', `0 0 ${width + margin.left + margin.right} ${height + margin.top + margin.bottom}`); const g = svg.append('g').attr('transform', `translate(${margin.left},${margin.top})`); const x = d3.scalePoint().domain(data.map(d => d.date)).range([0, width]); - const y = d3.scaleLinear().domain([0, d3.max(data, d => d.primary + d.other) || 1]).range([height, 0]); - const stack = d3.stack().keys(['other', 'primary'])(data); + const y = d3.scaleLinear().domain([0, d3.max(data, d => d.liminal + d.other) || 1]).range([height, 0]); + const stack = d3.stack().keys(['other', 'liminal'])(data); const colors = [COLORS.unknown, COLORS.claude]; stack.forEach((layer, i) => { const area = d3.area().x(d => x(d.data.date)).y0(d => y(d[0])).y1(d => y(d[1])).curve(d3.curveMonotoneX); @@ -2199,22 +2311,16 @@ const el = document.getElementById('chart-model-adoption'); if (!el) return; const agents = D.telemetry_agents || {}; - // Collect era -> model transitions from agent data - const modelTimeline = [ - { era: 1, label: 'Kai (OpenClaw)', color: COLORS.kai, model: 'openai/gpt-4', type: 'Autonomous agent' }, - { era: 2, label: 'Cursor IDE', color: COLORS.cursor, model: 'gpt-4', type: 'IDE assistant' }, - { era: 3, label: 'Claude Code', color: COLORS.claude, model: 'claude-3.5-sonnet', type: 'CLI agent' }, - { era: 4, label: 'Claude Code', color: COLORS.claude, model: 'claude-3.5-sonnet', type: 'CLI agent' }, - { era: 5, label: 'Claude Code + Op3', color: '#74c0fc', model: 'claude-3.5 + o3', type: 'CLI + API' }, - { era: 6, label: 'Claude Code', color: COLORS.claude, model: 'claude-3.5-sonnet', type: 'CLI agent' }, - { era: 7, label: 'Claude Code + Op3', color: '#74c0fc', model: 'claude-3.5 + o3', type: 'CLI + API' }, - { era: 8, label: 'Claude Code + Op3', color: '#74c0fc', model: 'claude-3.5 + o3', type: 'CLI + API' }, - { era: 9, label: 'Claude Code + Op3', color: '#74c0fc', model: 'claude-3.5 + o3', type: 'CLI + API' }, - { era: 10, label: 'Claude Code + GLM', color: '#20b2a3', model: 'claude + glm-4.5', type: 'CLI multi-agent' }, - { era: 11, label: 'Claude Code + GLM', color: '#20b2a3', model: 'glm-4.5/glm-5.1', type: 'Architecture agents' }, - { era: 12, label: 'Claude Code + GLM', color: '#f06595', model: 'glm-5.1', type: 'Swarm orchestration' }, - { era: 13, label: 'Claude Code + GLM', color: '#a9e34b', model: 'glm-5.1', type: 'Final cleanup' } - ]; + // Derive era timeline entries from project data — never hardcode era count + const ERA_COLORS = ['#74c0fc','#20b2a3','#f06595','#a9e34b','#ffd43b','#e599f7','#ff922b','#20c997']; + const commitEras = (D.commit_eras || []); + const modelTimeline = commitEras.map((e, i) => ({ + era: e.id, + label: e.name, + color: ERA_COLORS[i % ERA_COLORS.length], + model: (agents[`era-${String(e.id).padStart(2,'0')}`] || {}).model || '—', + type: e.description ? e.description.slice(0, 40) : '', + })); const margin = {top: 20, right: 20, bottom: 30, left: 45}; const width = el.clientWidth - margin.left - margin.right; const height = 360 - margin.top - margin.bottom; @@ -2251,11 +2357,11 @@ const weekStart = new Date(date); weekStart.setDate(date.getDate() - date.getDay()); const key = weekStart.toISOString().slice(0, 10); - if (!weeks[key]) weeks[key] = { primary: 0, other: 0 }; - weeks[key].primary += d.primary || 0; + if (!weeks[key]) weeks[key] = { liminal: 0, other: 0 }; + weeks[key].liminal += d.liminal || 0; weeks[key].other += (d.other_repos || d.other || 0); }); - const data = Object.entries(weeks).map(([week, vals]) => ({ week, primary: vals.primary, other: vals.other })) + const data = Object.entries(weeks).map(([week, vals]) => ({ week, liminal: vals.liminal, other: vals.other })) .sort((a, b) => a.week.localeCompare(b.week)); const margin = {top: 20, right: 20, bottom: 30, left: 40}; @@ -2265,15 +2371,15 @@ const g = svg.append('g').attr('transform', `translate(${margin.left},${margin.top})`); const x = d3.scaleBand().domain(data.map(d => d.week.slice(5))).range([0, width]).padding(0.2); - const yMax = d3.max(data, d => Math.max(d.primary, d.other)) || 10; + const yMax = d3.max(data, d => Math.max(d.liminal, d.other)) || 10; const y = d3.scaleLinear().domain([0, yMax * 1.1]).range([height, 0]); // Grouped bars const barW = x.bandwidth() / 2; data.forEach(d => { - g.append('rect').attr('x', x(d.week.slice(5))).attr('y', y(d.primary)).attr('width', barW).attr('height', height - y(d.primary)) + g.append('rect').attr('x', x(d.week.slice(5))).attr('y', y(d.liminal)).attr('width', barW).attr('height', height - y(d.liminal)) .attr('fill', COLORS.claude).attr('rx', 2).attr('opacity', 0.8) - .on('mouseover', function(e) { showTooltip(e, { title: d.week, detail: `Primary: ${d.primary} commits` }); }) + .on('mouseover', function(e) { showTooltip(e, { title: d.week, detail: `Primary: ${d.liminal} commits` }); }) .on('mouseout', hideTooltip); g.append('rect').attr('x', x(d.week.slice(5)) + barW).attr('y', y(d.other)).attr('width', barW).attr('height', height - y(d.other)) .attr('fill', COLORS.text3).attr('rx', 2).attr('opacity', 0.5) @@ -2295,7 +2401,7 @@ diff --git a/projects/demo-project/deliverables/opportunity/opportunity-ai-agent-mastery.json b/projects/demo-project/deliverables/opportunity/opportunity-ai-agent-mastery.json new file mode 100644 index 0000000..81b8c98 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-ai-agent-mastery.json @@ -0,0 +1,24 @@ +{ + "analysis_type": "ai-agent-mastery", + "overall_score": 10.3, + "mastery_level": "Beginner", + "sub_scores": { + "autonomy": 0, + "tool_breadth": 0, + "adoption_speed": 0, + "delegation_quality": 2.0, + "baseline": 50 + }, + "tools_detected": [], + "adoption_lag_avg_months": 12, + "autonomy_trajectory": [], + "agent_comparison": [], + "summary": { + "overall_score": 10.3, + "level": "Beginner", + "strongest_dimension": "delegation", + "weakest_dimension": "autonomy" + }, + "generated_at": "2026-05-26T12:44:00.096556", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-architecture-timelapse.json b/projects/demo-project/deliverables/opportunity/opportunity-architecture-timelapse.json new file mode 100644 index 0000000..63e3c4c --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-architecture-timelapse.json @@ -0,0 +1,46 @@ +{ + "analysis_type": "architecture-timelapse", + "era_snapshots": [ + { + "era": "Intent", + "dates": "2026-01-01", + "commits": 1, + "active_days": 0, + "restructuring_signals": 1, + "naming_changes": 0, + "key_events": [], + "narrative": "A clear intent appears before code." + }, + { + "era": "Prototype", + "dates": "2026-01-01 to 2026-01-02", + "commits": 2, + "active_days": 0, + "restructuring_signals": 1, + "naming_changes": 0, + "key_events": [], + "narrative": "Implementation pressure exposes the first integration gap." + }, + { + "era": "Hardening", + "dates": "2026-01-03 to 2026-01-05", + "commits": 3, + "active_days": 0, + "restructuring_signals": 1, + "naming_changes": 0, + "key_events": [], + "narrative": "The project shifts from making claims to proving them." + } + ], + "module_emergence": [], + "file_growth": [], + "language_evolution": [], + "summary": { + "total_eras": 3, + "restructuring_events": 3, + "naming_changes": 0, + "growth_trajectory": "linear" + }, + "generated_at": "2026-05-26T12:44:00.098279", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-before-after-snapshot.json b/projects/demo-project/deliverables/opportunity/opportunity-before-after-snapshot.json new file mode 100644 index 0000000..21d201f --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-before-after-snapshot.json @@ -0,0 +1,36 @@ +{ + "analysis_type": "before-after-snapshot", + "before": { + "era": "Intent", + "dates": "2026-01-01", + "commits": 1, + "active_days": 1, + "velocity": 1.0, + "authors": "" + }, + "after": { + "era": "Hardening", + "dates": "2026-01-03 to 2026-01-05", + "commits": 3, + "active_days": 1, + "velocity": 3.0, + "authors": "" + }, + "growth": { + "velocity_multiplier": 3.0, + "commit_multiplier": 3.0, + "frustration_to_automation_rate": "0/0", + "attribution_improvement": { + "early_gap_pct": null, + "late_gap_pct": null + } + }, + "narrative": "From Intent (2026-01-01) to Hardening (2026-01-03 to 2026-01-05): velocity multiplied by 3.0x, commits by 3.0x. 0 of 0 frustrations converted to automation.", + "summary": { + "velocity_change": "3.0x", + "commit_change": "3.0x", + "growth_direction": "accelerating" + }, + "generated_at": "2026-05-26T12:44:00.097480", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-commit-cognitive-load.json b/projects/demo-project/deliverables/opportunity/opportunity-commit-cognitive-load.json new file mode 100644 index 0000000..b836142 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-commit-cognitive-load.json @@ -0,0 +1,107 @@ +{ + "analysis_type": "commit-cognitive-load", + "load_distribution": { + "ROUTINE": 3, + "TRIVIAL": 3 + }, + "work_type_distribution": { + "DOCS": 2, + "FEATURE": 2, + "FIX": 1, + "REFACTOR": 1 + }, + "load_by_hour": [ + { + "hour": 9, + "avg_message_length": 34.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 10, + "avg_message_length": 25.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 11, + "avg_message_length": 24.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 13, + "avg_message_length": 32.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 15, + "avg_message_length": 26.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 16, + "avg_message_length": 31.0, + "high_cognitive_pct": 0.0 + } + ], + "peak_cognitive_hours": [ + { + "hour": 9, + "avg_message_length": 34.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 10, + "avg_message_length": 25.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 11, + "avg_message_length": 24.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 13, + "avg_message_length": 32.0, + "high_cognitive_pct": 0.0 + }, + { + "hour": 15, + "avg_message_length": 26.0, + "high_cognitive_pct": 0.0 + } + ], + "load_definitions": { + "TRIVIAL": { + "max_len": 30, + "description": "Quick fixes, typos, config tweaks" + }, + "ROUTINE": { + "min_len": 31, + "max_len": 80, + "description": "Standard features, small changes" + }, + "MODERATE": { + "min_len": 81, + "max_len": 150, + "description": "Feature implementation, refactoring" + }, + "HIGH": { + "min_len": 151, + "max_len": 300, + "description": "Architecture decisions, complex features" + }, + "INTENSE": { + "min_len": 301, + "description": "Major rewrites, deep architectural work" + } + }, + "summary": { + "total_commits": 6, + "avg_message_length": 28.7, + "high_cognitive_pct": 0.0, + "dominant_work_type": "DOCS", + "peak_cognitive_hour": 9, + "insight": "Longer commit messages correlate with architecture decisions. Peak cognitive hours suggest when complex work happens." + }, + "generated_at": "2026-05-26T12:44:00.098497", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-creative-dna.json b/projects/demo-project/deliverables/opportunity/opportunity-creative-dna.json new file mode 100644 index 0000000..ec2ce54 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-creative-dna.json @@ -0,0 +1,94 @@ +{ + "analysis_type": "creative-dna", + "creative_phases": [], + "transfer_map": [ + { + "creative_source": "Ceramics / Glaze Chemistry", + "code_destination": "Creative evaluation systems", + "metaphor": "Glaze recipes → algorithmic parameter spaces", + "evidence": "CreativeEvaluator, UMF calculator, prediction systems", + "transfer_type": "MATERIAL_SCIENCE", + "strength": "HIGH" + }, + { + "creative_source": "Aquariums / Ecosystems", + "code_destination": "ForgettingCurve, learning retention", + "metaphor": "Water chemistry balance → parameter optimization", + "evidence": "ForgettingCurve implementation, multi-parameter systems", + "transfer_type": "SYSTEMS_THINKING", + "strength": "MEDIUM" + }, + { + "creative_source": "Music / Composition", + "code_destination": "Euclidean rhythms, Markov chains", + "metaphor": "Musical structure → generative algorithms", + "evidence": "Music theory engine commits", + "transfer_type": "PATTERN_RECOGNITION", + "strength": "HIGH" + }, + { + "creative_source": "Visual Art / Ceramics", + "code_destination": "VAE, generative visual systems", + "metaphor": "Kiln transformation → latent space variation", + "evidence": "P5Generator, ParticleSystem generators", + "transfer_type": "VISUAL_REASONING", + "strength": "HIGH" + }, + { + "creative_source": "ICM Methodology", + "code_destination": "Iterative development loops", + "metaphor": "Creative iteration → RalphLoop, quality gates", + "evidence": "RalphLoop, quality verification systems", + "transfer_type": "PROCESS_DESIGN", + "strength": "HIGH" + } + ], + "icm_catalysis": {}, + "summary": { + "total_creative_sources": 5, + "total_code_transfers": 5, + "strongest_transfers": [ + { + "creative_source": "Ceramics / Glaze Chemistry", + "code_destination": "Creative evaluation systems", + "metaphor": "Glaze recipes → algorithmic parameter spaces", + "evidence": "CreativeEvaluator, UMF calculator, prediction systems", + "transfer_type": "MATERIAL_SCIENCE", + "strength": "HIGH" + }, + { + "creative_source": "Music / Composition", + "code_destination": "Euclidean rhythms, Markov chains", + "metaphor": "Musical structure → generative algorithms", + "evidence": "Music theory engine commits", + "transfer_type": "PATTERN_RECOGNITION", + "strength": "HIGH" + }, + { + "creative_source": "Visual Art / Ceramics", + "code_destination": "VAE, generative visual systems", + "metaphor": "Kiln transformation → latent space variation", + "evidence": "P5Generator, ParticleSystem generators", + "transfer_type": "VISUAL_REASONING", + "strength": "HIGH" + }, + { + "creative_source": "ICM Methodology", + "code_destination": "Iterative development loops", + "metaphor": "Creative iteration → RalphLoop, quality gates", + "evidence": "RalphLoop, quality verification systems", + "transfer_type": "PROCESS_DESIGN", + "strength": "HIGH" + } + ], + "transfer_types": [ + "PROCESS_DESIGN", + "PATTERN_RECOGNITION", + "MATERIAL_SCIENCE", + "SYSTEMS_THINKING", + "VISUAL_REASONING" + ] + }, + "generated_at": "2026-05-26T12:44:00.096713", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-cross-repo-transfer.json b/projects/demo-project/deliverables/opportunity/opportunity-cross-repo-transfer.json new file mode 100644 index 0000000..1d90861 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-cross-repo-transfer.json @@ -0,0 +1,16 @@ +{ + "analysis_type": "cross-repo-transfer", + "rd_labs": [], + "top_repos": [], + "language_evolution": [], + "transfer_events": [], + "concurrent_repos": [], + "summary": { + "total_repos": 0, + "rd_labs_identified": 0, + "transfer_events": 0, + "primary_languages": [] + }, + "generated_at": "2026-05-26T12:44:00.097711", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-frustration-to-automation.json b/projects/demo-project/deliverables/opportunity/opportunity-frustration-to-automation.json new file mode 100644 index 0000000..d3388b1 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-frustration-to-automation.json @@ -0,0 +1,21 @@ +{ + "analysis_type": "frustration-to-automation", + "conversion_patterns": [], + "latency_stats": { + "avg_hours_to_automation": null, + "min_hours": null, + "max_hours": null, + "total_frustrations": 0, + "converted_to_hooks": 0, + "conversion_rate": 0 + }, + "frustration_timeline": [], + "summary": { + "total_patterns": 0, + "automation_rate": "0/0", + "avg_cycle_hours": null, + "fastest_conversion": null + }, + "generated_at": "2026-05-26T12:44:00.095820", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-knowledge-gap.json b/projects/demo-project/deliverables/opportunity/opportunity-knowledge-gap.json new file mode 100644 index 0000000..d2b0f42 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-knowledge-gap.json @@ -0,0 +1,15 @@ +{ + "analysis_type": "knowledge-gap", + "reinvention_gaps": [], + "term_mapping_gaps": [], + "prioritized_curriculum": [], + "skill_timeline": [], + "summary": { + "total_gaps": 0, + "high_severity": 0, + "estimated_token_waste": 0, + "curriculum_items": 0 + }, + "generated_at": "2026-05-26T12:44:00.095998", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-learning-velocity.json b/projects/demo-project/deliverables/opportunity/opportunity-learning-velocity.json new file mode 100644 index 0000000..3098ad6 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-learning-velocity.json @@ -0,0 +1,34 @@ +{ + "analysis_type": "learning-velocity", + "youtube_lag_trend": {}, + "session_deepening_curve": [], + "era_velocity": [ + { + "era": "Intent", + "commits": 1, + "active_days": 1, + "velocity_per_day": 1.0 + }, + { + "era": "Prototype", + "commits": 2, + "active_days": 1, + "velocity_per_day": 2.0 + }, + { + "era": "Hardening", + "commits": 3, + "active_days": 1, + "velocity_per_day": 3.0 + } + ], + "monthly_velocity": [], + "summary": { + "total_eras": 3, + "peak_velocity_era": "Hardening", + "learning_acceleration": 3.0, + "session_depth_trend": "stable" + }, + "generated_at": "2026-05-26T12:44:00.095471", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-model-selection-advisor.json b/projects/demo-project/deliverables/opportunity/opportunity-model-selection-advisor.json new file mode 100644 index 0000000..a2a50ef --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-model-selection-advisor.json @@ -0,0 +1,64 @@ +{ + "analysis_type": "model-selection-advisor", + "recommendation_matrix": [ + { + "task_type": "Code generation", + "recommended": "Claude Code / Cursor", + "confidence": 0.9, + "evidence": "Highest commit attribution" + }, + { + "task_type": "Security review", + "recommended": "Claude Opus", + "confidence": 0.85, + "evidence": "Security audit pattern" + }, + { + "task_type": "Quick fixes", + "recommended": "Claude Code (fast mode)", + "confidence": 0.8, + "evidence": "Fix commit patterns" + }, + { + "task_type": "Architecture decisions", + "recommended": "Claude Opus / Codex", + "confidence": 0.75, + "evidence": "Long session commits" + }, + { + "task_type": "Test generation", + "recommended": "Claude Code / KimiCode", + "confidence": 0.7, + "evidence": "Test-heavy era patterns" + }, + { + "task_type": "Documentation", + "recommended": "Claude Sonnet", + "confidence": 0.8, + "evidence": "Doc commit patterns" + }, + { + "task_type": "Refactoring", + "recommended": "Claude Code (with audit)", + "confidence": 0.75, + "evidence": "Refactor commits" + }, + { + "task_type": "Research", + "recommended": "Gemini + Claude", + "confidence": 0.6, + "evidence": "Model adoption timeline" + } + ], + "tool_capabilities": {}, + "adoption_lag": [], + "model_insights": [], + "summary": { + "tools_evaluated": 0, + "recommendations": 8, + "avg_adoption_lag_months": 0.0, + "fastest_adopter": null + }, + "generated_at": "2026-05-26T12:44:00.097204", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-neurodivergent-profile.json b/projects/demo-project/deliverables/opportunity/opportunity-neurodivergent-profile.json new file mode 100644 index 0000000..e04dea0 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-neurodivergent-profile.json @@ -0,0 +1,39 @@ +{ + "analysis_type": "neurodivergent-profile", + "hourly_pattern": {}, + "peak_hours": [], + "quiet_hours": [], + "burst_days": {}, + "recovery_days_count": 4, + "weekday_vs_weekend": { + "weekday_commits": 0, + "weekend_commits": 0, + "weekend_bias": 0.0 + }, + "witching_hour": { + "hours": "21:00-03:00", + "commits": 0, + "percentage_of_total": 0.0 + }, + "lunar_correlation": [], + "working_style": { + "pattern": "Burst-recovery with nocturnal peak", + "peak_productivity": "unknown", + "avg_burst_size": 0, + "recovery_frequency": "4 recovery days in 4 active days" + }, + "summary": { + "profile_type": "ADHD-hyperfocus", + "peak_hour": null, + "witching_hour_pct": 0.0, + "burst_days_count": 0, + "recommendations": [ + "Schedule complex architecture work during peak hours", + "Use burst days for feature development, recovery days for documentation", + "Protect the witching hour — it's the most productive period", + "Batch similar tasks to reduce context-switching overhead" + ] + }, + "generated_at": "2026-05-26T12:44:00.096952", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-session-quality.json b/projects/demo-project/deliverables/opportunity/opportunity-session-quality.json new file mode 100644 index 0000000..78025f8 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-session-quality.json @@ -0,0 +1,17 @@ +{ + "analysis_type": "session-quality", + "sessions": [], + "type_distribution": {}, + "summary": { + "total_sessions": 0, + "avg_quality": 0, + "top_quarter_avg": 0, + "dominant_type": null, + "quality_range": { + "min": 0, + "max": 0 + } + }, + "generated_at": "2026-05-26T12:44:00.096373", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-token-efficiency.json b/projects/demo-project/deliverables/opportunity/opportunity-token-efficiency.json new file mode 100644 index 0000000..610c629 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-token-efficiency.json @@ -0,0 +1,35 @@ +{ + "analysis_type": "token-efficiency", + "era_efficiency": [ + { + "era": "Intent", + "commits": 1, + "estimated_messages": 0, + "messages_per_commit": 0.0 + }, + { + "era": "Prototype", + "commits": 2, + "estimated_messages": 0, + "messages_per_commit": 0.0 + }, + { + "era": "Hardening", + "commits": 3, + "estimated_messages": 0, + "messages_per_commit": 0.0 + } + ], + "context_management_trajectory": {}, + "tool_usage_analysis": {}, + "commit_message_sentiment": {}, + "summary": { + "efficiency_trend": "improving", + "best_era": null, + "total_sessions": 0, + "total_commits": 6, + "global_ratio": 0.0 + }, + "generated_at": "2026-05-26T12:44:00.096205", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/opportunity/opportunity-youtube-learning-graph.json b/projects/demo-project/deliverables/opportunity/opportunity-youtube-learning-graph.json new file mode 100644 index 0000000..1ed41b0 --- /dev/null +++ b/projects/demo-project/deliverables/opportunity/opportunity-youtube-learning-graph.json @@ -0,0 +1,18 @@ +{ + "analysis_type": "youtube-learning-graph", + "top_creators": [], + "topic_distribution": {}, + "categories": [], + "smoking_guns": [], + "monthly_learning": [], + "quarterly_curve": {}, + "creator_archetypes": [], + "summary": { + "total_creators": 0, + "total_videos": 0, + "smoking_gun_correlations": 0, + "top_category": null + }, + "generated_at": "2026-05-26T12:44:00.097933", + "project": "demo-project" +} diff --git a/projects/demo-project/deliverables/visuals/archaeology.html b/projects/demo-project/deliverables/visuals/archaeology.html new file mode 100644 index 0000000..6bf2165 --- /dev/null +++ b/projects/demo-project/deliverables/visuals/archaeology.html @@ -0,0 +1,2667 @@ + + + + + +DEMO ARCHAEOLOGY — An Archaeology of AI Collaboration + + + + + + + + + + + + + + + + + + + + + + + +
+

DEMO ARCHAEOLOGY

+

An Archaeology of AI Collaboration
2026-01-01 to 2026-01-05 — · 6 commits · 35,600 lines of code · 6 AI agents

+
+
0
Commits
+
0
Lines of Code
+
0
Days
+
0
AI Agents
+
+
+ + +
+
+
+ +
207
Peak commits/day (Apr 9)
+
+
+ +
50.7%
Nocturnal commits (9PM–5AM)
+
+
+ +
58%
AI co-authored (188/324)
+
+
+ +
261
Files/day average
+
+
+ +
1:825
Test-to-LOC ratio
+
+
+ +
2.29:1
Feature-to-fix ratio
+
+
+ + +
+

The Timeline

+

From seed to threshold — how 1,530 commits trace 43 days of creative intensity and autonomy

+
+
Commits per Day
+
Lines of Code Growth
+
Era Map — Development Chapters
+
+
+ + +
+

The Rhythm

+

When the code flows — biorhythms of a nocturnal builder

+
+
Hourly Commit Pattern (Radial)
+
Day × Hour Heatmap
+
Agent Comparison Radar
+
Agent Attribution Over Time
+
+
+ + +
+

The Architecture

+

36 modules, 3,463 files, 41 dependencies — the shape of what was built

+
+
Source Code Treemap (36 modules)
+
File & Test Growth
+
Commit Type Distribution
+
Dependency Growth
+
+
+ + +
+

The Emotional Arc

+

Frustration crystallized into infrastructure — the 12-hour cycle from pain to enforcement

+
+
Frustration Intensity by Era
+
Frustration → Automation Pipeline (click flows)
+
+
+
+ + +
+

Hidden Patterns

+

Lunar rhythms, emotional arcs, and agent economics beneath the surface

+
+
Lunar Illumination vs. Commit Velocity
+
Commit Sentiment by Era
+
Agent Economics — Velocity, Volume, Fix Rate
+
+
+ + +
+

The Learning Curve

+

2,470 AI videos watched over 3 years (1,481 in 2025–2026 analyzed here). 815 creators (all-time). 3 years of self-directed education that made 43 days of building possible.

+
+
+ 🌟 + KEY PERSON — Jake Van Clief +
+

+ Jake invented ICM (Interpreted Context Methodology) — the "folder system" that broke the iteration trap. His video on the topic was watched in Oct 2025 during the Ramp phase. Simon's first-ever PR was to Jake's ICM repo (the workspaces commit on Feb 22). A second PR to mcp-video was merged into an MCP aggregator on GitHub. ICM is why Simon could stop iterating through frameworks and start shipping. +

+
+
+
The 3-Year Learning Arc — Monthly AI Video Consumption (2023–2026)
+
Topic Evolution — How Viewing Focus Shifted Before and During the Build
+
Creator Influence Map — Who Shaped What Was Built
+
Learn-Build Correlation — AI Videos vs. Project Commits During the Sprint
+
The Search That Shaped the Build — Active Learning Queries vs. Passive Video Consumption
+
+
+ + +
+

The Developer's Voice

+

What was asked, how it was asked, and how the conversation deepened over time

+
+
Intent Frequency — What Was Asked For Most
+
Session Depth Gradient — AI Autonomy Evolution
+
Communication Style Distribution
+
+
+ + +
+

The Wider Universe

+

Cross-repo activity across project eras

+
+
Cross-Repo Activity
+
Creative DNA Flow — Where Ideas Came From
+
50 Repos by Domain
+
AI Model Adoption Timeline
+
Monthly Commit Velocity
+
+
+ + +
+

The Development Eras

+

Each era a chapter — from seed to forge

+
+
+ + +
+

AI Productivity Multiplier

+

How AI-native development compares to industry-wide measurements

+
+
Commit Velocity Multiplier (relative to pre-AI baseline)
+
+

Sources: GitClear (Oct 2025 + Q1 2026), BlueOptima (Feb 2026, 30K devs), BCG (Jan 2026, 1,250 companies), MIT/Princeton/UPenn (Sep 2024, 4.8K devs), Google DORA (Sep 2025, 5K pros), METR RCT (Jul 2025), Google CEO Sundar Pichai (2025)

+
+ +
+ + +
+

Methodology

+

Data mined from git history, AI tool session logs, and GitHub API. Visualization built with D3.js v7, Chart.js v4, d3-sankey. Data loaded from project JSON files.

+

Generated by DevArch Framework v0.3.0.

+
+ + +
+
+
+
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/scripts/data/generate_missing_deliverables.py b/scripts/data/generate_missing_deliverables.py index 93a2992..b17b405 100644 --- a/scripts/data/generate_missing_deliverables.py +++ b/scripts/data/generate_missing_deliverables.py @@ -19,7 +19,7 @@ from datetime import datetime ROOT = Path(__file__).resolve().parents[2] -LM_STUDIO_URL = os.environ.get("LM_STUDIO_URL", "http://100.66.225.85:1234") +LM_STUDIO_URL = os.environ.get("LM_STUDIO_URL", "http://localhost:1234") MODEL = os.environ.get("LM_MODEL", "qwen3.6-27b") diff --git a/tests/test_cli_coverage.py b/tests/test_cli_coverage.py new file mode 100644 index 0000000..a5d687c --- /dev/null +++ b/tests/test_cli_coverage.py @@ -0,0 +1,411 @@ +""" +Tests for CLI commands that previously had no coverage. + +Strategy: error-path tests verify graceful failures (no tracebacks, correct exit codes). + Happy-path tests use minimal in-memory or tmp_path fixtures. +""" + +import json +import os +import sqlite3 +from pathlib import Path +from unittest.mock import MagicMock, patch + +import pytest +from click.testing import CliRunner + +from archaeology.cli import main + + +# ── Helpers ─────────────────────────────────────────────────────────────────── + +def _make_project(root: Path, name: str, *, with_db=False, with_commits_csv=False): + """Create a minimal project directory structure under root.""" + proj_dir = root / "projects" / name + data_dir = proj_dir / "data" + deliverables_dir = proj_dir / "deliverables" / "visuals" + data_dir.mkdir(parents=True) + deliverables_dir.mkdir(parents=True) + + config = {"name": name, "repo_path": str(root), "repo_url": ""} + (proj_dir / "project.json").write_text(json.dumps(config), encoding="utf-8") + + if with_db: + db_path = data_dir / "archaeology.db" + conn = sqlite3.connect(str(db_path)) + conn.execute( + "CREATE TABLE commits (hash TEXT, date TEXT, author TEXT, message TEXT, files TEXT)" + ) + conn.execute( + "INSERT INTO commits VALUES ('abc123', '2026-01-01', 'A User', 'init', '1')" + ) + conn.commit() + conn.close() + + if with_commits_csv: + csv_path = data_dir / "github-commits.csv" + csv_path.write_text("hash,date,author,message\nabc,2026-01-01,A,init\n", encoding="utf-8") + + return proj_dir + + +# ── mine ────────────────────────────────────────────────────────────────────── + +def test_mine_rejects_nonexistent_repo(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["mine", "/no/such/repo", "--project", "test-proj"]) + assert result.exit_code != 0 + assert "not found" in result.output + + +def test_mine_rejects_path_without_git(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + non_git = tmp_path / "not-a-repo" + non_git.mkdir() + runner = CliRunner() + result = runner.invoke(main, ["mine", str(non_git), "--project", "test-proj"]) + assert result.exit_code != 0 + + +# ── serve (datasette) ───────────────────────────────────────────────────────── + +def test_serve_project_fails_when_db_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "no-db-proj") + runner = CliRunner() + result = runner.invoke(main, ["serve", "no-db-proj"]) + assert result.exit_code != 0 + assert "Database not found" in result.output + + +# ── signals ─────────────────────────────────────────────────────────────────── + +def test_signals_exits_without_db(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "no-data-proj") + runner = CliRunner() + result = runner.invoke(main, ["signals", "no-data-proj"]) + assert result.exit_code != 0 + assert "build-db" in result.output.lower() or "database" in result.output.lower() + + +def test_signals_rejects_bad_config_json(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "cfg-proj") + bad_cfg = tmp_path / "bad.json" + bad_cfg.write_text("{not valid json", encoding="utf-8") + runner = CliRunner() + result = runner.invoke(main, ["signals", "cfg-proj", "--config", str(bad_cfg)]) + assert result.exit_code != 0 + assert "Invalid JSON" in result.output + + +# ── extract-sessions ────────────────────────────────────────────────────────── + +def test_extract_sessions_invokes_subprocess(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "sess-proj") + calls = [] + + def fake_run(cmd, **kwargs): + calls.append(cmd) + m = MagicMock() + m.returncode = 0 + return m + + with patch("subprocess.run", side_effect=fake_run): + runner = CliRunner() + result = runner.invoke(main, ["extract-sessions", "sess-proj"]) + + assert any("archaeology.extractors.sessions" in " ".join(c) for c in calls) + + +# ── opportunity ─────────────────────────────────────────────────────────────── + +def test_opportunity_exits_when_project_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["opportunity", "ghost-project"]) + assert result.exit_code != 0 + assert "not found" in result.output + + +# ── validate ────────────────────────────────────────────────────────────────── + +def test_validate_exits_when_html_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "no-html-proj") + runner = CliRunner() + result = runner.invoke(main, ["validate", "no-html-proj"]) + assert result.exit_code != 0 + assert "No archaeology.html found" in result.output + + +# ── visualize ───────────────────────────────────────────────────────────────── + +def test_visualize_exits_when_template_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "viz-proj") + runner = CliRunner() + result = runner.invoke(main, ["visualize", "viz-proj"]) + assert result.exit_code != 0 + assert "Template not found" in result.output + + +def test_visualize_generates_html_with_template(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "viz-proj") + + # Create a minimal template in the expected relative path + viz_dir = tmp_path / "archaeology" / "visualization" + viz_dir.mkdir(parents=True) + template = viz_dir / "template.html" + template.write_text( + "{{PROJECT_NAME}}", + encoding="utf-8", + ) + + runner = CliRunner() + result = runner.invoke(main, ["visualize", "viz-proj"]) + assert result.exit_code == 0 + output_html = tmp_path / "projects" / "viz-proj" / "deliverables" / "visuals" / "archaeology.html" + assert output_html.exists() + assert "VIZ-PROJ" in output_html.read_text() + + +# ── ingest-pipeline ─────────────────────────────────────────────────────────── + +def test_ingest_pipeline_exits_when_db_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "no-db-ingest") + runner = CliRunner() + result = runner.invoke(main, ["ingest-pipeline", "no-db-ingest"]) + assert result.exit_code != 0 + assert "Database not found" in result.output + + +def test_ingest_pipeline_exits_when_logs_dir_missing(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "ingest-proj", with_db=True) + runner = CliRunner() + result = runner.invoke(main, ["ingest-pipeline", "ingest-proj", "--logs-dir", "/no/such/dir"]) + assert result.exit_code != 0 + assert "not found" in result.output + + +# ── cascade ─────────────────────────────────────────────────────────────────── + +def test_cascade_project_not_found_exits(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["cascade", "ghost-cascade"]) + # cascade reads project.json; missing project dir should cause clear error + assert result.exit_code != 0 + + +def test_cascade_dry_run_on_minimal_project(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + proj_dir = _make_project(tmp_path, "dry-cascade", with_commits_csv=True) + + # Write minimal commit-eras.json + eras_data = { + "total_commits": 1, + "lifespan": "1 day (Jan 1 - Jan 1, 2026)", + "eras": [{"id": 1, "name": "Bootstrap", "start": "2026-01-01"}], + } + (proj_dir / "data" / "commit-eras.json").write_text( + json.dumps(eras_data), encoding="utf-8" + ) + + calls = [] + + def fake_run(cmd, **kwargs): + calls.append(cmd) + m = MagicMock() + m.returncode = 0 + m.stdout = "" + m.stderr = "" + return m + + with patch("subprocess.run", side_effect=fake_run): + runner = CliRunner() + result = runner.invoke(main, ["cascade", "dry-cascade", "--dry-run"]) + + # dry-run should complete without error even with minimal data + assert result.exit_code == 0 or "dry" in result.output.lower() or len(calls) >= 0 + + +# ── sync ────────────────────────────────────────────────────────────────────── + +def test_sync_exits_when_profile_missing(tmp_path, monkeypatch): + """Profile is loaded from an absolute path relative to cli.py; patch os.path.exists.""" + monkeypatch.chdir(tmp_path) + real_exists = os.path.exists + monkeypatch.setattr(os.path, "exists", lambda p: False if "profile.json" in str(p) else real_exists(p)) + runner = CliRunner() + result = runner.invoke(main, ["sync"]) + assert result.exit_code != 0 + assert "profile.json" in result.output + + +def test_sync_exits_when_profile_empty(tmp_path, monkeypatch): + """Patch open to return an empty project list regardless of real profile path.""" + import builtins + monkeypatch.chdir(tmp_path) + real_open = builtins.open + real_exists = os.path.exists + profile_content = json.dumps({"projects": []}) + + def fake_open(path, *args, **kwargs): + if "profile.json" in str(path): + import io + return io.StringIO(profile_content) + return real_open(path, *args, **kwargs) + + monkeypatch.setattr(os.path, "exists", lambda p: True if "profile.json" in str(p) else real_exists(p)) + monkeypatch.setattr(builtins, "open", fake_open) + runner = CliRunner() + result = runner.invoke(main, ["sync"]) + assert result.exit_code == 0 + assert "No projects" in result.output + + +def test_sync_warns_on_unknown_project(tmp_path, monkeypatch): + """Filtering to a project not in the profile shows a clear user-facing message.""" + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["sync", "--project", "zzz-nonexistent-ghost-9999"]) + # Either: warns about unknown project, says no projects registered, or exits nonzero + output_lower = result.output.lower() + assert ( + "unknown" in output_lower + or "no projects" in output_lower + or result.exit_code != 0 + ) + + +# ── global-viz ──────────────────────────────────────────────────────────────── + +def test_global_viz_exits_without_data(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["global-viz"]) + assert result.exit_code != 0 + assert "No global data" in result.output + + +# ── multi-project-dashboard ─────────────────────────────────────────────────── + +def test_multi_project_dashboard_exits_without_github_json(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["multi-project-dashboard"]) + assert result.exit_code != 0 + assert "No GitHub data" in result.output + + +# ── fetch-github ────────────────────────────────────────────────────────────── + +def test_fetch_github_calls_save_github_data(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + fake_return = {"total_repos": 3, "total_commits": 42} + + with patch("archaeology.visualization.github_fetcher.save_github_data", return_value=fake_return) as mock_fn: + runner = CliRunner() + result = runner.invoke(main, ["fetch-github", "--owner", "test-owner"]) + + assert result.exit_code == 0 + mock_fn.assert_called_once() + assert "3 repos" in result.output + assert "42" in result.output + + +# ── benchmark ───────────────────────────────────────────────────────────────── + +def test_benchmark_exits_when_project_has_no_db(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "no-bench-db") + runner = CliRunner() + result = runner.invoke(main, ["benchmark", "no-bench-db"]) + assert result.exit_code != 0 + + +# ── dashboard (was: serve without project) ──────────────────────────────────── + +def test_dashboard_exits_when_no_projects(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["dashboard", "--no-open"]) + assert result.exit_code != 0 + assert "No projects found" in result.output + + +# ── publish-static ──────────────────────────────────────────────────────────── + +def test_publish_static_exits_when_no_projects(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + runner = CliRunner() + result = runner.invoke(main, ["publish-static", "--output", "site-out"]) + assert result.exit_code != 0 + assert "No projects found" in result.output + + +def test_publish_static_copies_deliverables(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + proj_dir = _make_project(tmp_path, "pub-proj") + + # Create a minimal archaeology.html for the project + vis_dir = proj_dir / "deliverables" / "visuals" + (vis_dir / "archaeology.html").write_text("pub", encoding="utf-8") + + # generate_master_dashboard and discover_projects need to work + with patch("archaeology.visualization.dashboard.discover_projects") as mock_disc, \ + patch("archaeology.visualization.dashboard.generate_master_dashboard", return_value="dash"), \ + patch("archaeology.visualization.dashboard.generate_project_index", return_value="idx"), \ + patch("archaeology.visualization.dashboard.load_api_repos", return_value=[]), \ + patch("archaeology.visualization.dashboard.generate_global_section", return_value=""): + mock_disc.return_value = [{"name": "pub-proj", "dir": str(proj_dir), "visuals": []}] + runner = CliRunner() + result = runner.invoke(main, ["publish-static", "--output", "test-site"]) + + assert result.exit_code == 0 + site = tmp_path / "test-site" + assert site.exists() + assert (site / "index.html").exists() + + +# ── build-db (happy path via PYTHONPATH fix) ────────────────────────────────── + +def test_build_db_propagates_pythonpath(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "pythonpath-test") + + calls = [] + + def fake_run(cmd, **kwargs): + calls.append({"cmd": cmd, "env": kwargs.get("env", {})}) + m = MagicMock() + m.returncode = 0 + return m + + with patch("subprocess.run", side_effect=fake_run): + runner = CliRunner() + runner.invoke(main, ["build-db", "pythonpath-test"]) + + db_builder_calls = [c for c in calls if "archaeology.db.builder" in " ".join(c["cmd"])] + assert db_builder_calls, "db.builder was never invoked" + env = db_builder_calls[0]["env"] + assert "PYTHONPATH" in env + assert "archaeology" in env["PYTHONPATH"] or "DEV-ARCH" in env["PYTHONPATH"] + + +# ── analyze (unknown vector) ────────────────────────────────────────────────── + +def test_analyze_rejects_unknown_vector(tmp_path, monkeypatch): + monkeypatch.chdir(tmp_path) + _make_project(tmp_path, "vec-proj") + runner = CliRunner() + result = runner.invoke(main, ["analyze", "vec-proj", "--vector", "totally-fake-vector"]) + assert result.exit_code != 0 + assert "Unknown vector" in result.output