@olives/devos 2.1.0

package/.agents/skills/skill-creator/scripts/run_loop.py

@@ -0,0 +1,328 @@
+#!/usr/bin/env python3
+"""Run the eval + improve loop until all pass or max iterations reached.
+
+Combines run_eval.py and improve_description.py in a loop, tracking history
+and returning the best description found. Supports train/test split to prevent
+overfitting.
+"""
+
+import argparse
+import json
+import random
+import sys
+import tempfile
+import time
+import webbrowser
+from pathlib import Path
+
+from scripts.generate_report import generate_html
+from scripts.improve_description import improve_description
+from scripts.run_eval import find_project_root, run_eval
+from scripts.utils import parse_skill_md
+
+
+def split_eval_set(eval_set: list[dict], holdout: float, seed: int = 42) -> tuple[list[dict], list[dict]]:
+    """Split eval set into train and test sets, stratified by should_trigger."""
+    random.seed(seed)
+
+    # Separate by should_trigger
+    trigger = [e for e in eval_set if e["should_trigger"]]
+    no_trigger = [e for e in eval_set if not e["should_trigger"]]
+
+    # Shuffle each group
+    random.shuffle(trigger)
+    random.shuffle(no_trigger)
+
+    # Calculate split points
+    n_trigger_test = max(1, int(len(trigger) * holdout))
+    n_no_trigger_test = max(1, int(len(no_trigger) * holdout))
+
+    # Split
+    test_set = trigger[:n_trigger_test] + no_trigger[:n_no_trigger_test]
+    train_set = trigger[n_trigger_test:] + no_trigger[n_no_trigger_test:]
+
+    return train_set, test_set
+
+
+def run_loop(
+    eval_set: list[dict],
+    skill_path: Path,
+    description_override: str | None,
+    num_workers: int,
+    timeout: int,
+    max_iterations: int,
+    runs_per_query: int,
+    trigger_threshold: float,
+    holdout: float,
+    model: str,
+    verbose: bool,
+    live_report_path: Path | None = None,
+    log_dir: Path | None = None,
+) -> dict:
+    """Run the eval + improvement loop."""
+    project_root = find_project_root()
+    name, original_description, content = parse_skill_md(skill_path)
+    current_description = description_override or original_description
+
+    # Split into train/test if holdout > 0
+    if holdout > 0:
+        train_set, test_set = split_eval_set(eval_set, holdout)
+        if verbose:
+            print(f"Split: {len(train_set)} train, {len(test_set)} test (holdout={holdout})", file=sys.stderr)
+    else:
+        train_set = eval_set
+        test_set = []
+
+    history = []
+    exit_reason = "unknown"
+
+    for iteration in range(1, max_iterations + 1):
+        if verbose:
+            print(f"\n{'='*60}", file=sys.stderr)
+            print(f"Iteration {iteration}/{max_iterations}", file=sys.stderr)
+            print(f"Description: {current_description}", file=sys.stderr)
+            print(f"{'='*60}", file=sys.stderr)
+
+        # Evaluate train + test together in one batch for parallelism
+        all_queries = train_set + test_set
+        t0 = time.time()
+        all_results = run_eval(
+            eval_set=all_queries,
+            skill_name=name,
+            description=current_description,
+            num_workers=num_workers,
+            timeout=timeout,
+            project_root=project_root,
+            runs_per_query=runs_per_query,
+            trigger_threshold=trigger_threshold,
+            model=model,
+        )
+        eval_elapsed = time.time() - t0
+
+        # Split results back into train/test by matching queries
+        train_queries_set = {q["query"] for q in train_set}
+        train_result_list = [r for r in all_results["results"] if r["query"] in train_queries_set]
+        test_result_list = [r for r in all_results["results"] if r["query"] not in train_queries_set]
+
+        train_passed = sum(1 for r in train_result_list if r["pass"])
+        train_total = len(train_result_list)
+        train_summary = {"passed": train_passed, "failed": train_total - train_passed, "total": train_total}
+        train_results = {"results": train_result_list, "summary": train_summary}
+
+        if test_set:
+            test_passed = sum(1 for r in test_result_list if r["pass"])
+            test_total = len(test_result_list)
+            test_summary = {"passed": test_passed, "failed": test_total - test_passed, "total": test_total}
+            test_results = {"results": test_result_list, "summary": test_summary}
+        else:
+            test_results = None
+            test_summary = None
+
+        history.append({
+            "iteration": iteration,
+            "description": current_description,
+            "train_passed": train_summary["passed"],
+            "train_failed": train_summary["failed"],
+            "train_total": train_summary["total"],
+            "train_results": train_results["results"],
+            "test_passed": test_summary["passed"] if test_summary else None,
+            "test_failed": test_summary["failed"] if test_summary else None,
+            "test_total": test_summary["total"] if test_summary else None,
+            "test_results": test_results["results"] if test_results else None,
+            # For backward compat with report generator
+            "passed": train_summary["passed"],
+            "failed": train_summary["failed"],
+            "total": train_summary["total"],
+            "results": train_results["results"],
+        })
+
+        # Write live report if path provided
+        if live_report_path:
+            partial_output = {
+                "original_description": original_description,
+                "best_description": current_description,
+                "best_score": "in progress",
+                "iterations_run": len(history),
+                "holdout": holdout,
+                "train_size": len(train_set),
+                "test_size": len(test_set),
+                "history": history,
+            }
+            live_report_path.write_text(generate_html(partial_output, auto_refresh=True, skill_name=name))
+
+        if verbose:
+            def print_eval_stats(label, results, elapsed):
+                pos = [r for r in results if r["should_trigger"]]
+                neg = [r for r in results if not r["should_trigger"]]
+                tp = sum(r["triggers"] for r in pos)
+                pos_runs = sum(r["runs"] for r in pos)
+                fn = pos_runs - tp
+                fp = sum(r["triggers"] for r in neg)
+                neg_runs = sum(r["runs"] for r in neg)
+                tn = neg_runs - fp
+                total = tp + tn + fp + fn
+                precision = tp / (tp + fp) if (tp + fp) > 0 else 1.0
+                recall = tp / (tp + fn) if (tp + fn) > 0 else 1.0
+                accuracy = (tp + tn) / total if total > 0 else 0.0
+                print(f"{label}: {tp+tn}/{total} correct, precision={precision:.0%} recall={recall:.0%} accuracy={accuracy:.0%} ({elapsed:.1f}s)", file=sys.stderr)
+                for r in results:
+                    status = "PASS" if r["pass"] else "FAIL"
+                    rate_str = f"{r['triggers']}/{r['runs']}"
+                    print(f"  [{status}] rate={rate_str} expected={r['should_trigger']}: {r['query'][:60]}", file=sys.stderr)
+
+            print_eval_stats("Train", train_results["results"], eval_elapsed)
+            if test_summary:
+                print_eval_stats("Test ", test_results["results"], 0)
+
+        if train_summary["failed"] == 0:
+            exit_reason = f"all_passed (iteration {iteration})"
+            if verbose:
+                print(f"\nAll train queries passed on iteration {iteration}!", file=sys.stderr)
+            break
+
+        if iteration == max_iterations:
+            exit_reason = f"max_iterations ({max_iterations})"
+            if verbose:
+                print(f"\nMax iterations reached ({max_iterations}).", file=sys.stderr)
+            break
+
+        # Improve the description based on train results
+        if verbose:
+            print(f"\nImproving description...", file=sys.stderr)
+
+        t0 = time.time()
+        # Strip test scores from history so improvement model can't see them
+        blinded_history = [
+            {k: v for k, v in h.items() if not k.startswith("test_")}
+            for h in history
+        ]
+        new_description = improve_description(
+            skill_name=name,
+            skill_content=content,
+            current_description=current_description,
+            eval_results=train_results,
+            history=blinded_history,
+            model=model,
+            log_dir=log_dir,
+            iteration=iteration,
+        )
+        improve_elapsed = time.time() - t0
+
+        if verbose:
+            print(f"Proposed ({improve_elapsed:.1f}s): {new_description}", file=sys.stderr)
+
+        current_description = new_description
+
+    # Find the best iteration by TEST score (or train if no test set)
+    if test_set:
+        best = max(history, key=lambda h: h["test_passed"] or 0)
+        best_score = f"{best['test_passed']}/{best['test_total']}"
+    else:
+        best = max(history, key=lambda h: h["train_passed"])
+        best_score = f"{best['train_passed']}/{best['train_total']}"
+
+    if verbose:
+        print(f"\nExit reason: {exit_reason}", file=sys.stderr)
+        print(f"Best score: {best_score} (iteration {best['iteration']})", file=sys.stderr)
+
+    return {
+        "exit_reason": exit_reason,
+        "original_description": original_description,
+        "best_description": best["description"],
+        "best_score": best_score,
+        "best_train_score": f"{best['train_passed']}/{best['train_total']}",
+        "best_test_score": f"{best['test_passed']}/{best['test_total']}" if test_set else None,
+        "final_description": current_description,
+        "iterations_run": len(history),
+        "holdout": holdout,
+        "train_size": len(train_set),
+        "test_size": len(test_set),
+        "history": history,
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Run eval + improve loop")
+    parser.add_argument("--eval-set", required=True, help="Path to eval set JSON file")
+    parser.add_argument("--skill-path", required=True, help="Path to skill directory")
+    parser.add_argument("--description", default=None, help="Override starting description")
+    parser.add_argument("--num-workers", type=int, default=10, help="Number of parallel workers")
+    parser.add_argument("--timeout", type=int, default=30, help="Timeout per query in seconds")
+    parser.add_argument("--max-iterations", type=int, default=5, help="Max improvement iterations")
+    parser.add_argument("--runs-per-query", type=int, default=3, help="Number of runs per query")
+    parser.add_argument("--trigger-threshold", type=float, default=0.5, help="Trigger rate threshold")
+    parser.add_argument("--holdout", type=float, default=0.4, help="Fraction of eval set to hold out for testing (0 to disable)")
+    parser.add_argument("--model", required=True, help="Model for improvement")
+    parser.add_argument("--verbose", action="store_true", help="Print progress to stderr")
+    parser.add_argument("--report", default="auto", help="Generate HTML report at this path (default: 'auto' for temp file, 'none' to disable)")
+    parser.add_argument("--results-dir", default=None, help="Save all outputs (results.json, report.html, log.txt) to a timestamped subdirectory here")
+    args = parser.parse_args()
+
+    eval_set = json.loads(Path(args.eval_set).read_text())
+    skill_path = Path(args.skill_path)
+
+    if not (skill_path / "SKILL.md").exists():
+        print(f"Error: No SKILL.md found at {skill_path}", file=sys.stderr)
+        sys.exit(1)
+
+    name, _, _ = parse_skill_md(skill_path)
+
+    # Set up live report path
+    if args.report != "none":
+        if args.report == "auto":
+            timestamp = time.strftime("%Y%m%d_%H%M%S")
+            live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{timestamp}.html"
+        else:
+            live_report_path = Path(args.report)
+        # Open the report immediately so the user can watch
+        live_report_path.write_text("<html><body><h1>Starting optimization loop...</h1><meta http-equiv='refresh' content='5'></body></html>")
+        webbrowser.open(str(live_report_path))
+    else:
+        live_report_path = None
+
+    # Determine output directory (create before run_loop so logs can be written)
+    if args.results_dir:
+        timestamp = time.strftime("%Y-%m-%d_%H%M%S")
+        results_dir = Path(args.results_dir) / timestamp
+        results_dir.mkdir(parents=True, exist_ok=True)
+    else:
+        results_dir = None
+
+    log_dir = results_dir / "logs" if results_dir else None
+
+    output = run_loop(
+        eval_set=eval_set,
+        skill_path=skill_path,
+        description_override=args.description,
+        num_workers=args.num_workers,
+        timeout=args.timeout,
+        max_iterations=args.max_iterations,
+        runs_per_query=args.runs_per_query,
+        trigger_threshold=args.trigger_threshold,
+        holdout=args.holdout,
+        model=args.model,
+        verbose=args.verbose,
+        live_report_path=live_report_path,
+        log_dir=log_dir,
+    )
+
+    # Save JSON output
+    json_output = json.dumps(output, indent=2)
+    print(json_output)
+    if results_dir:
+        (results_dir / "results.json").write_text(json_output)
+
+    # Write final HTML report (without auto-refresh)
+    if live_report_path:
+        live_report_path.write_text(generate_html(output, auto_refresh=False, skill_name=name))
+        print(f"\nReport: {live_report_path}", file=sys.stderr)
+
+    if results_dir and live_report_path:
+        (results_dir / "report.html").write_text(generate_html(output, auto_refresh=False, skill_name=name))
+
+    if results_dir:
+        print(f"Results saved to: {results_dir}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

package/.agents/skills/skill-creator/scripts/utils.py

@@ -0,0 +1,47 @@
+"""Shared utilities for skill-creator scripts."""
+
+from pathlib import Path
+
+
+
+def parse_skill_md(skill_path: Path) -> tuple[str, str, str]:
+    """Parse a SKILL.md file, returning (name, description, full_content)."""
+    content = (skill_path / "SKILL.md").read_text()
+    lines = content.split("\n")
+
+    if lines[0].strip() != "---":
+        raise ValueError("SKILL.md missing frontmatter (no opening ---)")
+
+    end_idx = None
+    for i, line in enumerate(lines[1:], start=1):
+        if line.strip() == "---":
+            end_idx = i
+            break
+
+    if end_idx is None:
+        raise ValueError("SKILL.md missing frontmatter (no closing ---)")
+
+    name = ""
+    description = ""
+    frontmatter_lines = lines[1:end_idx]
+    i = 0
+    while i < len(frontmatter_lines):
+        line = frontmatter_lines[i]
+        if line.startswith("name:"):
+            name = line[len("name:"):].strip().strip('"').strip("'")
+        elif line.startswith("description:"):
+            value = line[len("description:"):].strip()
+            # Handle YAML multiline indicators (>, |, >-, |-)
+            if value in (">", "|", ">-", "|-"):
+                continuation_lines: list[str] = []
+                i += 1
+                while i < len(frontmatter_lines) and (frontmatter_lines[i].startswith("  ") or frontmatter_lines[i].startswith("\t")):
+                    continuation_lines.append(frontmatter_lines[i].strip())
+                    i += 1
+                description = " ".join(continuation_lines)
+                continue
+            else:
+                description = value.strip('"').strip("'")
+        i += 1
+
+    return name, description, content

package/.agents/skills/stacks/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: stacks
+description: Stack-specific coding standards. Contains standards for Next.js, Laravel, Django, Express, FastAPI, and React Native. Copy the relevant stack file into your project root.
+---
+
+# Stack-Specific Coding Standards
+
+This directory contains coding standards for supported technology stacks.
+
+## Available Stacks
+
+- `nextjs.md` — Next.js 15 + TypeScript + Supabase + Vercel
+- `laravel.md` — Laravel 12 + PHP + MySQL + cPanel
+- `django.md` — Django + DRF + Celery + Redis
+- `express.md` — Express.js + TypeScript + Node
+- `fastapi.md` — FastAPI + Python + SQLAlchemy
+- `react-native.md` — React Native + Expo Router + Zustand
+
+## Usage
+
+Copy the relevant stack file into your project root as your coding standards reference. If no stack file matches your project, fall back to the universal standards in the root `CODING_STANDARDS.md`.

package/.agents/skills/stacks/django.md

@@ -0,0 +1,187 @@
+---
+name: django-stack
+description: Stack-specific coding standards for Django. Append this to the universal CLAUDE.md when working on a Django project.
+---
+
+# CLAUDE.md — Django Stack Context
+
+> Append this to the universal `skills/CLAUDE.md` when working on a Django project.
+
+---
+
+## Stack
+
+- **Framework:** Django (current stable) with Django REST Framework (DRF)
+- **Language:** Python (current stable)
+- **Auth:** djangorestframework-simplejwt or dj-rest-auth
+- **Database:** PostgreSQL
+- **Task Queue:** Celery + Redis
+- **Testing:** pytest + pytest-django
+- **Type Checking:** mypy (strict)
+- **Linting:** Ruff
+- **Formatting:** Black
+
+---
+
+## Project Structure
+
+```
+project_name/
+├── config/                  ← Django settings (split by environment)
+│   ├── settings/
+│   │   ├── base.py
+│   │   ├── development.py
+│   │   └── production.py
+│   ├── urls.py
+│   └── wsgi.py
+├── apps/                    ← Django apps (one per domain)
+│   ├── users/
+│   │   ├── models.py
+│   │   ├── serializers.py
+│   │   ├── views.py
+│   │   ├── urls.py
+│   │   ├── services.py      ← Business logic
+│   │   └── tests/
+│   └── [feature]/
+├── common/                  ← Shared utilities, mixins, base classes
+│   ├── exceptions.py
+│   ├── pagination.py
+│   └── permissions.py
+├── requirements/
+│   ├── base.txt
+│   ├── development.txt
+│   └── production.txt
+└── manage.py
+```
+
+---
+
+## Architecture Rules
+
+### Views Must Be Thin
+Views handle HTTP only — request parsing, calling services, returning responses. No business logic.
+
+```python
+# ✅ Correct
+class UserRegistrationView(CreateAPIView):
+    serializer_class = UserRegistrationSerializer
+
+    def perform_create(self, serializer):
+        user_service.register_user(serializer.validated_data)
+
+# ❌ Wrong — business logic in view
+class UserRegistrationView(CreateAPIView):
+    def create(self, request):
+        user = User.objects.create_user(...)
+        send_welcome_email.delay(user.id)
+        Profile.objects.create(user=user)
+        # ...
+```
+
+### Services
+Business logic lives in `services.py` files. Services are plain Python functions or classes — no Django magic.
+
+```python
+# apps/users/services.py
+def register_user(data: dict) -> User:
+    user = User.objects.create_user(
+        email=data['email'],
+        password=data['password'],
+    )
+    send_welcome_email.delay(user.id)
+    return user
+```
+
+### Serializers
+- Serializers are for input validation and output shaping only
+- Do not put business logic in `create()` or `update()` — call a service
+- Always define `fields` explicitly — never use `fields = '__all__'`
+
+### Models
+- Use `verbose_name` and `verbose_name_plural` on every model
+- Define `__str__` on every model
+- Use `created_at` and `updated_at` (via abstract base model) on every model
+- Never do computation in model `save()` — use signals or services sparingly
+
+---
+
+## Coding Conventions
+
+```python
+# ✅ Base model for timestamps
+from django.db import models
+
+class TimeStampedModel(models.Model):
+    created_at = models.DateTimeField(auto_now_add=True)
+    updated_at = models.DateTimeField(auto_now=True)
+
+    class Meta:
+        abstract = True
+
+# ✅ Type annotations everywhere
+def get_user_by_email(email: str) -> User | None:
+    return User.objects.filter(email=email).first()
+```
+
+### Naming
+| Type | Convention | Example |
+|------|-----------|---------|
+| Models | PascalCase | `UserProfile` |
+| Views | PascalCase + View | `UserListView` |
+| Serializers | PascalCase + Serializer | `UserCreateSerializer` |
+| Services | snake_case functions | `register_user()` |
+| URLs | kebab-case | `user-profile/` |
+| Variables / functions | snake_case | `get_active_users()` |
+
+---
+
+## Forbidden Patterns
+
+```python
+# ❌ Business logic in views or serializers
+# ❌ fields = '__all__' in serializers
+# ❌ Raw SQL when ORM can handle it
+# ❌ print() statements in production code
+# ❌ Catching bare exceptions: except Exception: pass
+# ❌ Mutable default arguments: def fn(items=[])
+# ❌ Blocking operations in views (use Celery)
+# ❌ Importing from settings directly in apps — use django.conf.settings
+```
+
+---
+
+## Testing
+
+```bash
+pytest                          # Run all tests
+pytest --cov=apps --cov-report=html   # Coverage
+mypy .                          # Type checking
+ruff check .                    # Linting
+black --check .                 # Format check
+```
+
+- Every view must have a test
+- Use `pytest.mark.django_db` only on tests that need DB access
+- Use `mixer` or `factory_boy` for test data — never hardcode
+- Separate test files per class: `tests/test_views.py`, `tests/test_services.py`
+
+---
+
+## Environment Variables Required
+
+```bash
+DJANGO_SECRET_KEY=
+DJANGO_DEBUG=False
+DJANGO_ALLOWED_HOSTS=
+
+DATABASE_URL=postgresql://user:password@host:5432/dbname
+
+REDIS_URL=redis://localhost:6379/0
+
+EMAIL_HOST=
+EMAIL_PORT=587
+EMAIL_HOST_USER=
+EMAIL_HOST_PASSWORD=
+DEFAULT_FROM_EMAIL=
+```
+

package/.agents/skills/stacks/express.md

@@ -0,0 +1,16 @@
+---
+name: express-stack
+description: Stack standard for Express.js, TypeScript, Node
+---
+# Express.js Stack Standard
+
+## Tech Stack
+- Framework: Express.js
+- Language: TypeScript
+- Node: LTS (20+)
+
+## Standards
+- **Architecture:** Use Controller-Service-Repository pattern.
+- **Error Handling:** Centralized async error handling middleware.
+- **Validation:** Use Zod or Joi for request validation middleware.
+- **Security:** Helmet, CORS, Rate Limiting must be configured.

package/.agents/skills/stacks/fastapi.md

@@ -0,0 +1,17 @@
+---
+name: fastapi-stack
+description: Stack standard for FastAPI, Python, SQLAlchemy
+---
+# FastAPI Stack Standard
+
+## Tech Stack
+- Framework: FastAPI
+- Language: Python 3.11+
+- ORM: SQLAlchemy 2.0
+- Validation: Pydantic V2
+
+## Standards
+- **Structure:** Use a modular router setup (e.g., `routers/`, `services/`, `models/`, `schemas/`).
+- **Typing:** Strict Python type hints required everywhere.
+- **Async:** Use `async def` for endpoints and async database drivers (e.g., `asyncpg`).
+- **Dependencies:** Use FastAPI's Dependency Injection for database sessions and auth.

package/.agents/skills/stacks/laravel.md

@@ -0,0 +1,18 @@
+---
+name: laravel-stack
+description: Stack standard for Laravel 12, MySQL, cPanel
+---
+# Laravel 12 Stack Standard
+
+## Tech Stack
+- Framework: Laravel 12
+- Language: PHP 8.2+
+- Database: MySQL
+- Hosting: cPanel
+
+## Standards
+- **Architecture:** Use strict MVC or Action/Domain patterns. Avoid logic in routes or controllers; push to services/actions.
+- **Database:** Use Eloquent ORM. Always create migrations and seeders for new tables.
+- **Security:** Use CSRF protection, parameter binding (built into Eloquent), and strict validation via FormRequests.
+- **Deployment (cPanel):** Ensure `public/` is mapped correctly. Configure `.htaccess` for routing. Run `php artisan optimize` on deploy.
+- **Testing:** Write tests using Pest or PHPUnit.

package/.agents/skills/stacks/nextjs.md

@@ -0,0 +1,20 @@
+---
+name: nextjs-stack
+description: Stack standard for Next.js 15, Supabase, Vercel
+---
+# Next.js 15 Stack Standard
+
+## Tech Stack
+- Framework: Next.js 15 (App Router)
+- Language: TypeScript (Strict)
+- Database/Auth: Supabase
+- Hosting: Vercel
+- Styling: Tailwind CSS / shadcn/ui
+
+## Standards
+- **App Router:** Use App Router exclusively. No `pages/` directory.
+- **Server Components:** Default to Server Components. Only use `"use client"` when state, effects, or DOM events are needed.
+- **Data Fetching:** Fetch data in Server Components natively. Use Supabase SSR package for auth and data.
+- **Server Actions:** Use Server Actions for mutations instead of API Routes.
+- **Auth:** Supabase Auth with RLS (Row Level Security) on all tables.
+- **Deployment:** Deploy strictly to Vercel. Ensure `vercel.json` and build scripts are properly configured.