Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.

#!/usr/bin/env python3
"""Generate and serve a review page for eval results.

Reads the workspace directory, discovers runs (directories with outputs/),
embeds all output data into a self-contained HTML page, and serves it via
a tiny HTTP server. Feedback auto-saves to feedback.json in the workspace.

Usage:
    python generate_review.py <workspace-path> [--port PORT] [--skill-name NAME]
    python generate_review.py <workspace-path> --previous-feedback /path/to/old/feedback.json

No dependencies beyond the Python stdlib are required.
"""

import argparse
import base64
import json
import mimetypes
import os
import re
import signal
import subprocess
import sys
import time
import webbrowser
from functools import partial
from http.server import HTTPServer, BaseHTTPRequestHandler
from pathlib import Path

# Files to exclude from output listings
METADATA_FILES = {"transcript.md", "user_notes.md", "metrics.json"}

# Extensions we render as inline text
TEXT_EXTENSIONS = {
    ".txt", ".md", ".json", ".csv", ".py", ".js", ".ts", ".tsx", ".jsx",
    ".yaml", ".yml", ".xml", ".html", ".css", ".sh", ".rb", ".go", ".rs",
    ".java", ".c", ".cpp", ".h", ".hpp", ".sql", ".r", ".toml",
}

# Extensions we render as inline images
IMAGE_EXTENSIONS = {".png", ".jpg", ".jpeg", ".gif", ".svg", ".webp"}

# MIME type overrides for common types
MIME_OVERRIDES = {
    ".svg": "image/svg+xml",
    ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
    ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    ".pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
}


def get_mime_type(path: Path) -> str:
    ext = path.suffix.lower()
    if ext in MIME_OVERRIDES:
        return MIME_OVERRIDES[ext]
    mime, _ = mimetypes.guess_type(str(path))
    return mime or "application/octet-stream"


def find_runs(workspace: Path) -> list[dict]:
    """Recursively find directories that contain an outputs/ subdirectory."""
    runs: list[dict] = []
    _find_runs_recursive(workspace, workspace, runs)
    runs.sort(key=lambda r: (r.get("eval_id", float("inf")), r["id"]))
    return runs


def _find_runs_recursive(root: Path, current: Path, runs: list[dict]) -> None:
    if not current.is_dir():
        return

    outputs_dir = current / "outputs"
    if outputs_dir.is_dir():
        run = build_run(root, current)
        if run:
            runs.append(run)
        return

    skip = {"node_modules", ".git", "__pycache__", "skill", "inputs"}
    for child in sorted(current.iterdir()):
        if child.is_dir() and child.name not in skip:
            _find_runs_recursive(root, child, runs)


def build_run(root: Path, run_dir: Path) -> dict | None:
    """Build a run dict with prompt, outputs, and grading data."""
    prompt = ""
    eval_id = None

    # Try eval_metadata.json
    for candidate in [run_dir / "eval_metadata.json", run_dir.parent / "eval_metadata.json"]:
        if candidate.exists():
            try:
                metadata = json.loads(candidate.read_text())
                prompt = metadata.get("prompt", "")
                eval_id = metadata.get("eval_id")
            except (json.JSONDecodeError, OSError):
                pass
            if prompt:
                break

    # Fall back to transcript.md
    if not prompt:
        for candidate in [run_dir / "transcript.md", run_dir / "outputs" / "transcript.md"]:
            if candidate.exists():
                try:
                    text = candidate.read_text()
                    match = re.search(r"## Eval Prompt\n\n([\s\S]*?)(?=\n##|$)", text)
                    if match:
                        prompt = match.group(1).strip()
                except OSError:
                    pass
                if prompt:
                    break

    if not prompt:
        prompt = "(No prompt found)"

    run_id = str(run_dir.relative_to(root)).replace("/", "-").replace("\\", "-")

    # Collect output files
    outputs_dir = run_dir / "outputs"
    output_files: list[dict] = []
    if outputs_dir.is_dir():
        for f in sorted(outputs_dir.iterdir()):
            if f.is_file() and f.name not in METADATA_FILES:
                output_files.append(embed_file(f))

    # Load grading if present
    grading = None
    for candidate in [run_dir / "grading.json", run_dir.parent / "grading.json"]:
        if candidate.exists():
            try:
                grading = json.loads(candidate.read_text())
            except (json.JSONDecodeError, OSError):
                pass
            if grading:
                break

    return {
        "id": run_id,
        "prompt": prompt,
        "eval_id": eval_id,
        "outputs": output_files,
        "grading": grading,
    }


def embed_file(path: Path) -> dict:
    """Read a file and return an embedded representation."""
    ext = path.suffix.lower()
    mime = get_mime_type(path)

    if ext in TEXT_EXTENSIONS:
        try:
            content = path.read_text(errors="replace")
        except OSError:
            content = "(Error reading file)"
        return {
            "name": path.name,
            "type": "text",
            "content": content,
        }
    elif ext in IMAGE_EXTENSIONS:
        try:
            raw = path.read_bytes()
            b64 = base64.b64encode(raw).decode("ascii")
        except OSError:
            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
        return {
            "name": path.name,
            "type": "image",
            "mime": mime,
            "data_uri": f"data:{mime};base64,{b64}",
        }
    elif ext == ".pdf":
        try:
            raw = path.read_bytes()
            b64 = base64.b64encode(raw).decode("ascii")
        except OSError:
            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
        return {
            "name": path.name,
            "type": "pdf",
            "data_uri": f"data:{mime};base64,{b64}",
        }
    elif ext == ".xlsx":
        try:
            raw = path.read_bytes()
            b64 = base64.b64encode(raw).decode("ascii")
        except OSError:
            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
        return {
            "name": path.name,
            "type": "xlsx",
            "data_b64": b64,
        }
    else:
        # Binary / unknown — base64 download link
        try:
            raw = path.read_bytes()
            b64 = base64.b64encode(raw).decode("ascii")
        except OSError:
            return {"name": path.name, "type": "error", "content": "(Error reading file)"}
        return {
            "name": path.name,
            "type": "binary",
            "mime": mime,
            "data_uri": f"data:{mime};base64,{b64}",
        }


def load_previous_iteration(workspace: Path) -> dict[str, dict]:
    """Load previous iteration's feedback and outputs.

    Returns a map of run_id -> {"feedback": str, "outputs": list[dict]}.
    """
    result: dict[str, dict] = {}

    # Load feedback
    feedback_map: dict[str, str] = {}
    feedback_path = workspace / "feedback.json"
    if feedback_path.exists():
        try:
            data = json.loads(feedback_path.read_text())
            feedback_map = {
                r["run_id"]: r["feedback"]
                for r in data.get("reviews", [])
                if r.get("feedback", "").strip()
            }
        except (json.JSONDecodeError, OSError, KeyError):
            pass

    # Load runs (to get outputs)
    prev_runs = find_runs(workspace)
    for run in prev_runs:
        result[run["id"]] = {
            "feedback": feedback_map.get(run["id"], ""),
            "outputs": run.get("outputs", []),
        }

    # Also add feedback for run_ids that had feedback but no matching run
    for run_id, fb in feedback_map.items():
        if run_id not in result:
            result[run_id] = {"feedback": fb, "outputs": []}

    return result


def generate_html(
    runs: list[dict],
    skill_name: str,
    previous: dict[str, dict] | None = None,
    benchmark: dict | None = None,
) -> str:
    """Generate the complete standalone HTML page with embedded data."""
    template_path = Path(__file__).parent / "viewer.html"
    template = template_path.read_text()

    # Build previous_feedback and previous_outputs maps for the template
    previous_feedback: dict[str, str] = {}
    previous_outputs: dict[str, list[dict]] = {}
    if previous:
        for run_id, data in previous.items():
            if data.get("feedback"):
                previous_feedback[run_id] = data["feedback"]
            if data.get("outputs"):
                previous_outputs[run_id] = data["outputs"]

    embedded = {
        "skill_name": skill_name,
        "runs": runs,
        "previous_feedback": previous_feedback,
        "previous_outputs": previous_outputs,
    }
    if benchmark:
        embedded["benchmark"] = benchmark

    data_json = json.dumps(embedded)

    return template.replace("/*__EMBEDDED_DATA__*/", f"const EMBEDDED_DATA = {data_json};")


# ---------------------------------------------------------------------------
# HTTP server (stdlib only, zero dependencies)
# ---------------------------------------------------------------------------

def _kill_port(port: int) -> None:
    """Kill any process listening on the given port."""
    try:
        result = subprocess.run(
            ["lsof", "-ti", f":{port}"],
            capture_output=True, text=True, timeout=5,
        )
        for pid_str in result.stdout.strip().split("\n"):
            if pid_str.strip():
                try:
                    os.kill(int(pid_str.strip()), signal.SIGTERM)
                except (ProcessLookupError, ValueError):
                    pass
        if result.stdout.strip():
            time.sleep(0.5)
    except subprocess.TimeoutExpired:
        pass
    except FileNotFoundError:
        print("Note: lsof not found, cannot check if port is in use", file=sys.stderr)

class ReviewHandler(BaseHTTPRequestHandler):
    """Serves the review HTML and handles feedback saves.

    Regenerates the HTML on each page load so that refreshing the browser
    picks up new eval outputs without restarting the server.
    """

    def __init__(
        self,
        workspace: Path,
        skill_name: str,
        feedback_path: Path,
        previous: dict[str, dict],
        benchmark_path: Path | None,
        *args,
        **kwargs,
    ):
        self.workspace = workspace
        self.skill_name = skill_name
        self.feedback_path = feedback_path
        self.previous = previous
        self.benchmark_path = benchmark_path
        super().__init__(*args, **kwargs)

    def do_GET(self) -> None:
        if self.path == "/" or self.path == "/index.html":
            # Regenerate HTML on each request (re-scans workspace for new outputs)
            runs = find_runs(self.workspace)
            benchmark = None
            if self.benchmark_path and self.benchmark_path.exists():
                try:
                    benchmark = json.loads(self.benchmark_path.read_text())
                except (json.JSONDecodeError, OSError):
                    pass
            html = generate_html(runs, self.skill_name, self.previous, benchmark)
            content = html.encode("utf-8")
            self.send_response(200)
            self.send_header("Content-Type", "text/html; charset=utf-8")
            self.send_header("Content-Length", str(len(content)))
            self.end_headers()
            self.wfile.write(content)
        elif self.path == "/api/feedback":
            data = b"{}"
            if self.feedback_path.exists():
                data = self.feedback_path.read_bytes()
            self.send_response(200)
            self.send_header("Content-Type", "application/json")
            self.send_header("Content-Length", str(len(data)))
            self.end_headers()
            self.wfile.write(data)
        else:
            self.send_error(404)

    def do_POST(self) -> None:
        if self.path == "/api/feedback":
            length = int(self.headers.get("Content-Length", 0))
            body = self.rfile.read(length)
            try:
                data = json.loads(body)
                if not isinstance(data, dict) or "reviews" not in data:
                    raise ValueError("Expected JSON object with 'reviews' key")
                self.feedback_path.write_text(json.dumps(data, indent=2) + "\n")
                resp = b'{"ok":true}'
                self.send_response(200)
            except (json.JSONDecodeError, OSError, ValueError) as e:
                resp = json.dumps({"error": str(e)}).encode()
                self.send_response(500)
            self.send_header("Content-Type", "application/json")
            self.send_header("Content-Length", str(len(resp)))
            self.end_headers()
            self.wfile.write(resp)
        else:
            self.send_error(404)

    def log_message(self, format: str, *args: object) -> None:
        # Suppress request logging to keep terminal clean
        pass


def main() -> None:
    parser = argparse.ArgumentParser(description="Generate and serve eval review")
    parser.add_argument("workspace", type=Path, help="Path to workspace directory")
    parser.add_argument("--port", "-p", type=int, default=3117, help="Server port (default: 3117)")
    parser.add_argument("--skill-name", "-n", type=str, default=None, help="Skill name for header")
    parser.add_argument(
        "--previous-workspace", type=Path, default=None,
        help="Path to previous iteration's workspace (shows old outputs and feedback as context)",
    )
    parser.add_argument(
        "--benchmark", type=Path, default=None,
        help="Path to benchmark.json to show in the Benchmark tab",
    )
    parser.add_argument(
        "--static", "-s", type=Path, default=None,
        help="Write standalone HTML to this path instead of starting a server",
    )
    args = parser.parse_args()

    workspace = args.workspace.resolve()
    if not workspace.is_dir():
        print(f"Error: {workspace} is not a directory", file=sys.stderr)
        sys.exit(1)

    runs = find_runs(workspace)
    if not runs:
        print(f"No runs found in {workspace}", file=sys.stderr)
        sys.exit(1)

    skill_name = args.skill_name or workspace.name.replace("-workspace", "")
    feedback_path = workspace / "feedback.json"

    previous: dict[str, dict] = {}
    if args.previous_workspace:
        previous = load_previous_iteration(args.previous_workspace.resolve())

    benchmark_path = args.benchmark.resolve() if args.benchmark else None
    benchmark = None
    if benchmark_path and benchmark_path.exists():
        try:
            benchmark = json.loads(benchmark_path.read_text())
        except (json.JSONDecodeError, OSError):
            pass

    if args.static:
        html = generate_html(runs, skill_name, previous, benchmark)
        args.static.parent.mkdir(parents=True, exist_ok=True)
        args.static.write_text(html)
        print(f"\n  Static viewer written to: {args.static}\n")
        sys.exit(0)

    # Kill any existing process on the target port
    port = args.port
    _kill_port(port)
    handler = partial(ReviewHandler, workspace, skill_name, feedback_path, previous, benchmark_path)
    try:
        server = HTTPServer(("127.0.0.1", port), handler)
    except OSError:
        # Port still in use after kill attempt — find a free one
        server = HTTPServer(("127.0.0.1", 0), handler)
        port = server.server_address[1]

    url = f"http://localhost:{port}"
    print(f"\n  Eval Viewer")
    print(f"  ─────────────────────────────────")
    print(f"  URL:       {url}")
    print(f"  Workspace: {workspace}")
    print(f"  Feedback:  {feedback_path}")
    if previous:
        print(f"  Previous:  {args.previous_workspace} ({len(previous)} runs)")
    if benchmark_path:
        print(f"  Benchmark: {benchmark_path}")
    print(f"\n  Press Ctrl+C to stop.\n")

    webbrowser.open(url)

    try:
        server.serve_forever()
    except KeyboardInterrupt:
        print("\nStopped.")
        server.server_close()


if __name__ == "__main__":
    main()

#!/usr/bin/env python3
"""
Aggregate individual run results into benchmark summary statistics.

Reads grading.json files from run directories and produces:
- run_summary with mean, stddev, min, max for each metric
- delta between with_skill and without_skill configurations

Usage:
    python aggregate_benchmark.py <benchmark_dir>

Example:
    python aggregate_benchmark.py benchmarks/2026-01-15T10-30-00/

The script supports two directory layouts:

    Workspace layout (from skill-creator iterations):
    <benchmark_dir>/
    └── eval-N/
        ├── with_skill/
        │   ├── run-1/grading.json
        │   └── run-2/grading.json
        └── without_skill/
            ├── run-1/grading.json
            └── run-2/grading.json

    Legacy layout (with runs/ subdirectory):
    <benchmark_dir>/
    └── runs/
        └── eval-N/
            ├── with_skill/
            │   └── run-1/grading.json
            └── without_skill/
                └── run-1/grading.json
"""

import argparse
import json
import math
import sys
from datetime import datetime, timezone
from pathlib import Path


def calculate_stats(values: list[float]) -> dict:
    """Calculate mean, stddev, min, max for a list of values."""
    if not values:
        return {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0}

    n = len(values)
    mean = sum(values) / n

    if n > 1:
        variance = sum((x - mean) ** 2 for x in values) / (n - 1)
        stddev = math.sqrt(variance)
    else:
        stddev = 0.0

    return {
        "mean": round(mean, 4),
        "stddev": round(stddev, 4),
        "min": round(min(values), 4),
        "max": round(max(values), 4)
    }


def load_run_results(benchmark_dir: Path) -> dict:
    """
    Load all run results from a benchmark directory.

    Returns dict keyed by config name (e.g. "with_skill"/"without_skill",
    or "new_skill"/"old_skill"), each containing a list of run results.
    """
    # Support both layouts: eval dirs directly under benchmark_dir, or under runs/
    runs_dir = benchmark_dir / "runs"
    if runs_dir.exists():
        search_dir = runs_dir
    elif list(benchmark_dir.glob("eval-*")):
        search_dir = benchmark_dir
    else:
        print(f"No eval directories found in {benchmark_dir} or {benchmark_dir / 'runs'}")
        return {}

    results: dict[str, list] = {}

    for eval_idx, eval_dir in enumerate(sorted(search_dir.glob("eval-*"))):
        metadata_path = eval_dir / "eval_metadata.json"
        if metadata_path.exists():
            try:
                with open(metadata_path) as mf:
                    eval_id = json.load(mf).get("eval_id", eval_idx)
            except (json.JSONDecodeError, OSError):
                eval_id = eval_idx
        else:
            try:
                eval_id = int(eval_dir.name.split("-")[1])
            except ValueError:
                eval_id = eval_idx

        # Discover config directories dynamically rather than hardcoding names
        for config_dir in sorted(eval_dir.iterdir()):
            if not config_dir.is_dir():
                continue
            # Skip non-config directories (inputs, outputs, etc.)
            if not list(config_dir.glob("run-*")):
                continue
            config = config_dir.name
            if config not in results:
                results[config] = []

            for run_dir in sorted(config_dir.glob("run-*")):
                run_number = int(run_dir.name.split("-")[1])
                grading_file = run_dir / "grading.json"

                if not grading_file.exists():
                    print(f"Warning: grading.json not found in {run_dir}")
                    continue

                try:
                    with open(grading_file) as f:
                        grading = json.load(f)
                except json.JSONDecodeError as e:
                    print(f"Warning: Invalid JSON in {grading_file}: {e}")
                    continue

                # Extract metrics
                result = {
                    "eval_id": eval_id,
                    "run_number": run_number,
                    "pass_rate": grading.get("summary", {}).get("pass_rate", 0.0),
                    "passed": grading.get("summary", {}).get("passed", 0),
                    "failed": grading.get("summary", {}).get("failed", 0),
                    "total": grading.get("summary", {}).get("total", 0),
                }

                # Extract timing — check grading.json first, then sibling timing.json
                timing = grading.get("timing", {})
                result["time_seconds"] = timing.get("total_duration_seconds", 0.0)
                timing_file = run_dir / "timing.json"
                if result["time_seconds"] == 0.0 and timing_file.exists():
                    try:
                        with open(timing_file) as tf:
                            timing_data = json.load(tf)
                        result["time_seconds"] = timing_data.get("total_duration_seconds", 0.0)
                        result["tokens"] = timing_data.get("total_tokens", 0)
                    except json.JSONDecodeError:
                        pass

                # Extract metrics if available
                metrics = grading.get("execution_metrics", {})
                result["tool_calls"] = metrics.get("total_tool_calls", 0)
                if not result.get("tokens"):
                    result["tokens"] = metrics.get("output_chars", 0)
                result["errors"] = metrics.get("errors_encountered", 0)

                # Extract expectations — viewer requires fields: text, passed, evidence
                raw_expectations = grading.get("expectations", [])
                for exp in raw_expectations:
                    if "text" not in exp or "passed" not in exp:
                        print(f"Warning: expectation in {grading_file} missing required fields (text, passed, evidence): {exp}")
                result["expectations"] = raw_expectations

                # Extract notes from user_notes_summary
                notes_summary = grading.get("user_notes_summary", {})
                notes = []
                notes.extend(notes_summary.get("uncertainties", []))
                notes.extend(notes_summary.get("needs_review", []))
                notes.extend(notes_summary.get("workarounds", []))
                result["notes"] = notes

                results[config].append(result)

    return results


def aggregate_results(results: dict) -> dict:
    """
    Aggregate run results into summary statistics.

    Returns run_summary with stats for each configuration and delta.
    """
    run_summary = {}
    configs = list(results.keys())

    for config in configs:
        runs = results.get(config, [])

        if not runs:
            run_summary[config] = {
                "pass_rate": {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0},
                "time_seconds": {"mean": 0.0, "stddev": 0.0, "min": 0.0, "max": 0.0},
                "tokens": {"mean": 0, "stddev": 0, "min": 0, "max": 0}
            }
            continue

        pass_rates = [r["pass_rate"] for r in runs]
        times = [r["time_seconds"] for r in runs]
        tokens = [r.get("tokens", 0) for r in runs]

        run_summary[config] = {
            "pass_rate": calculate_stats(pass_rates),
            "time_seconds": calculate_stats(times),
            "tokens": calculate_stats(tokens)
        }

    # Calculate delta between the first two configs (if two exist)
    if len(configs) >= 2:
        primary = run_summary.get(configs[0], {})
        baseline = run_summary.get(configs[1], {})
    else:
        primary = run_summary.get(configs[0], {}) if configs else {}
        baseline = {}

    delta_pass_rate = primary.get("pass_rate", {}).get("mean", 0) - baseline.get("pass_rate", {}).get("mean", 0)
    delta_time = primary.get("time_seconds", {}).get("mean", 0) - baseline.get("time_seconds", {}).get("mean", 0)
    delta_tokens = primary.get("tokens", {}).get("mean", 0) - baseline.get("tokens", {}).get("mean", 0)

    run_summary["delta"] = {
        "pass_rate": f"{delta_pass_rate:+.2f}",
        "time_seconds": f"{delta_time:+.1f}",
        "tokens": f"{delta_tokens:+.0f}"
    }

    return run_summary


def generate_benchmark(benchmark_dir: Path, skill_name: str = "", skill_path: str = "") -> dict:
    """
    Generate complete benchmark.json from run results.
    """
    results = load_run_results(benchmark_dir)
    run_summary = aggregate_results(results)

    # Build runs array for benchmark.json
    runs = []
    for config in results:
        for result in results[config]:
            runs.append({
                "eval_id": result["eval_id"],
                "configuration": config,
                "run_number": result["run_number"],
                "result": {
                    "pass_rate": result["pass_rate"],
                    "passed": result["passed"],
                    "failed": result["failed"],
                    "total": result["total"],
                    "time_seconds": result["time_seconds"],
                    "tokens": result.get("tokens", 0),
                    "tool_calls": result.get("tool_calls", 0),
                    "errors": result.get("errors", 0)
                },
                "expectations": result["expectations"],
                "notes": result["notes"]
            })

    # Determine eval IDs from results
    eval_ids = sorted(set(
        r["eval_id"]
        for config in results.values()
        for r in config
    ))

    benchmark = {
        "metadata": {
            "skill_name": skill_name or "<skill-name>",
            "skill_path": skill_path or "<path/to/skill>",
            "executor_model": "<model-name>",
            "analyzer_model": "<model-name>",
            "timestamp": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
            "evals_run": eval_ids,
            "runs_per_configuration": 3
        },
        "runs": runs,
        "run_summary": run_summary,
        "notes": []  # To be filled by analyzer
    }

    return benchmark


def generate_markdown(benchmark: dict) -> str:
    """Generate human-readable benchmark.md from benchmark data."""
    metadata = benchmark["metadata"]
    run_summary = benchmark["run_summary"]

    # Determine config names (excluding "delta")
    configs = [k for k in run_summary if k != "delta"]
    config_a = configs[0] if len(configs) >= 1 else "config_a"
    config_b = configs[1] if len(configs) >= 2 else "config_b"
    label_a = config_a.replace("_", " ").title()
    label_b = config_b.replace("_", " ").title()

    lines = [
        f"# Skill Benchmark: {metadata['skill_name']}",
        "",
        f"**Model**: {metadata['executor_model']}",
        f"**Date**: {metadata['timestamp']}",
        f"**Evals**: {', '.join(map(str, metadata['evals_run']))} ({metadata['runs_per_configuration']} runs each per configuration)",
        "",
        "## Summary",
        "",
        f"| Metric | {label_a} | {label_b} | Delta |",
        "|--------|------------|---------------|-------|",
    ]

    a_summary = run_summary.get(config_a, {})
    b_summary = run_summary.get(config_b, {})
    delta = run_summary.get("delta", {})

    # Format pass rate
    a_pr = a_summary.get("pass_rate", {})
    b_pr = b_summary.get("pass_rate", {})
    lines.append(f"| Pass Rate | {a_pr.get('mean', 0)*100:.0f}% ± {a_pr.get('stddev', 0)*100:.0f}% | {b_pr.get('mean', 0)*100:.0f}% ± {b_pr.get('stddev', 0)*100:.0f}% | {delta.get('pass_rate', '—')} |")

    # Format time
    a_time = a_summary.get("time_seconds", {})
    b_time = b_summary.get("time_seconds", {})
    lines.append(f"| Time | {a_time.get('mean', 0):.1f}s ± {a_time.get('stddev', 0):.1f}s | {b_time.get('mean', 0):.1f}s ± {b_time.get('stddev', 0):.1f}s | {delta.get('time_seconds', '—')}s |")

    # Format tokens
    a_tokens = a_summary.get("tokens", {})
    b_tokens = b_summary.get("tokens", {})
    lines.append(f"| Tokens | {a_tokens.get('mean', 0):.0f} ± {a_tokens.get('stddev', 0):.0f} | {b_tokens.get('mean', 0):.0f} ± {b_tokens.get('stddev', 0):.0f} | {delta.get('tokens', '—')} |")

    # Notes section
    if benchmark.get("notes"):
        lines.extend([
            "",
            "## Notes",
            ""
        ])
        for note in benchmark["notes"]:
            lines.append(f"- {note}")

    return "\n".join(lines)


def main():
    parser = argparse.ArgumentParser(
        description="Aggregate benchmark run results into summary statistics"
    )
    parser.add_argument(
        "benchmark_dir",
        type=Path,
        help="Path to the benchmark directory"
    )
    parser.add_argument(
        "--skill-name",
        default="",
        help="Name of the skill being benchmarked"
    )
    parser.add_argument(
        "--skill-path",
        default="",
        help="Path to the skill being benchmarked"
    )
    parser.add_argument(
        "--output", "-o",
        type=Path,
        help="Output path for benchmark.json (default: <benchmark_dir>/benchmark.json)"
    )

    args = parser.parse_args()

    if not args.benchmark_dir.exists():
        print(f"Directory not found: {args.benchmark_dir}")
        sys.exit(1)

    # Generate benchmark
    benchmark = generate_benchmark(args.benchmark_dir, args.skill_name, args.skill_path)

    # Determine output paths
    output_json = args.output or (args.benchmark_dir / "benchmark.json")
    output_md = output_json.with_suffix(".md")

    # Write benchmark.json
    with open(output_json, "w") as f:
        json.dump(benchmark, f, indent=2)
    print(f"Generated: {output_json}")

    # Write benchmark.md
    markdown = generate_markdown(benchmark)
    with open(output_md, "w") as f:
        f.write(markdown)
    print(f"Generated: {output_md}")

    # Print summary
    run_summary = benchmark["run_summary"]
    configs = [k for k in run_summary if k != "delta"]
    delta = run_summary.get("delta", {})

    print(f"\nSummary:")
    for config in configs:
        pr = run_summary[config]["pass_rate"]["mean"]
        label = config.replace("_", " ").title()
        print(f"  {label}: {pr*100:.1f}% pass rate")
    print(f"  Delta:         {delta.get('pass_rate', '—')}")


if __name__ == "__main__":
    main()