sessionreel 0.1.0__py3-none-any.whl

sessionreel/__init__.py

@@ -0,0 +1,7 @@
+"""sessionreel: turn a coding-agent session log into a short recap video."""
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("sessionreel")
+except PackageNotFoundError:  # running from a source checkout
+    __version__ = "0.0.0+dev"

sessionreel/board.py

@@ -0,0 +1,101 @@
+"""Checks a storyboard must pass before any frame is drawn.
+
+A storyboard is plain JSON that people and agents edit between `plan` and `render`, so the
+renderer cannot trust it: `validate` normalises its shape (clear errors instead of tracebacks),
+`reredact` runs the redactor over every string again (idempotent — placeholders do not re-match),
+and `caption_claims` flags numbers in captions that the scene's own data does not contain.
+"""
+from __future__ import annotations
+
+import copy
+import math
+import re
+from typing import Any
+
+from .redact import Redactor
+
+KINDS = {"title", "prompt", "montage", "terminal", "diff", "ship", "say", "stats", "end"}
+MAX_SECONDS = 30.0
+
+
+class BoardError(ValueError):
+    pass
+
+
+def _str(v: Any) -> str:
+    return "" if v is None else str(v)
+
+
+def validate(board: Any) -> dict:
+    """Return a cleaned copy of `board` or raise BoardError naming the first problem."""
+    if not isinstance(board, dict):
+        raise BoardError("storyboard must be a JSON object")
+    scenes = board.get("scenes")
+    if not isinstance(scenes, list):
+        raise BoardError("storyboard has no 'scenes' list")
+    out = copy.deepcopy(board)
+    clean: list[dict] = []
+    for i, sc in enumerate(scenes):
+        if not isinstance(sc, dict):
+            raise BoardError(f"scene {i} is not an object")
+        kind = sc.get("kind")
+        if kind not in KINDS:
+            raise BoardError(f"scene {i}: unknown kind {kind!r} (expected one of {', '.join(sorted(KINDS))})")
+        sc = dict(sc)
+        try:
+            secs = float(sc.get("seconds", 3))
+        except (TypeError, ValueError):
+            raise BoardError(f"scene {i} ({kind}): seconds must be a number, got {sc.get('seconds')!r}") from None
+        if not math.isfinite(secs) or secs <= 0:
+            raise BoardError(f"scene {i} ({kind}): seconds must be a positive number, got {secs!r}")
+        sc["seconds"] = min(secs, MAX_SECONDS)
+        for key in ("caption", "fact", "text", "command", "file", "message", "badge", "status",
+                    "project", "title", "date", "model", "branch", "duration"):
+            if key in sc:
+                sc[key] = _str(sc[key])
+        for key in ("output", "lines", "files"):
+            if key in sc:
+                if not isinstance(sc[key], list):
+                    raise BoardError(f"scene {i} ({kind}): {key} must be a list of strings")
+                sc[key] = [_str(x) for x in sc[key]]
+        if kind == "stats":
+            items = sc.get("items", [])
+            if not isinstance(items, list) or not all(isinstance(it, (list, tuple)) and len(it) == 2 for it in items):
+                raise BoardError(f"scene {i} (stats): items must be a list of [label, value] pairs")
+            sc["items"] = [[_str(a), _str(b)] for a, b in items]
+        for key in ("added", "removed"):
+            if key in sc:
+                try:
+                    sc[key] = int(sc[key])
+                except (TypeError, ValueError):
+                    raise BoardError(f"scene {i} ({kind}): {key} must be an integer") from None
+        clean.append(sc)
+    out["scenes"] = clean
+    return out
+
+
+def reredact(board: dict, redactor: Redactor | None = None) -> tuple[dict, dict[str, int]]:
+    """Run redaction over every string in every scene. Returns the board and what changed."""
+    r = redactor or Redactor()
+    scenes = r.value(board["scenes"])
+    return {**board, "scenes": scenes}, dict(r.counts)
+
+
+_NUM = re.compile(r"\d[\d,.]*")
+
+
+def caption_claims(board: dict) -> list[str]:
+    """Numbers in a caption that appear nowhere in that scene's data or its template fact."""
+    warnings: list[str] = []
+    for i, sc in enumerate(board.get("scenes", [])):
+        cap = sc.get("caption", "")
+        if not cap or cap == sc.get("fact"):
+            continue
+        support = " ".join(_str(v) if not isinstance(v, list) else " ".join(map(_str, v))
+                           for k, v in sc.items() if k != "caption")
+        known = {n.strip(".,").replace(",", "") for n in _NUM.findall(support)}
+        for n in _NUM.findall(cap):
+            n = n.strip(".,").replace(",", "")
+            if n and n not in known:
+                warnings.append(f"scene {i} ({sc.get('kind')}): caption says {n!r}, which is not in the scene data")
+    return warnings

sessionreel/cli.py

@@ -0,0 +1,193 @@
+"""sessionreel command line."""
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sys
+import time
+from importlib import resources
+from pathlib import Path
+
+from . import __version__, ingest, redact, render, story
+
+
+def _eprint(*a: object) -> None:
+    print(*a, file=sys.stderr)
+
+
+def _progress(done: int, total: int) -> None:
+    if done == total or done % 15 == 0:
+        bar = int(28 * done / max(1, total))
+        sys.stderr.write(f"\r  rendering [{'█' * bar}{'·' * (28 - bar)}] {done}/{total} frames")
+        if done == total:
+            sys.stderr.write("\n")
+        sys.stderr.flush()
+
+
+def _resolve(ref: str | None) -> Path:
+    if ref:
+        return ingest.find_session(ref)
+    found = ingest.current_session()
+    if found is None:
+        raise FileNotFoundError(
+            f"no Claude Code sessions for {os.getcwd()} (or its parents) under {ingest.projects_root()}\n"
+            "  run `sessionreel list` to see all sessions, or pass a session id / .jsonl path")
+    return found
+
+
+def _plan(args: argparse.Namespace) -> dict:
+    path = _resolve(args.session)
+    sess = ingest.load(path)
+    redact.redact_session(sess, extra=args.redact or ())
+    board = story.build(sess, lang=args.lang, whole=args.whole,
+                        project_name=getattr(args, "project", None), show_branch=not getattr(args, "no_branch", False))
+    n = sum(board["redactions"].values())
+    ask = next((s["text"] for s in board["scenes"] if s["kind"] == "prompt"), "")
+    what = ", ".join(f"{v} {k}" for k, v in sorted(board["redactions"].items(), key=lambda kv: -kv[1]))
+    _eprint(f"  session  {path.stem}  ({len(sess.events)} events"
+            + (f", {sess.skipped_lines} malformed lines skipped" if sess.skipped_lines else "") + ")")
+    if ask:
+        _eprint(f"  ask      {ask[:90]}{'…' if len(ask) > 90 else ''}")
+    _eprint(f"  story    {' → '.join(s['kind'] for s in board['scenes'])}"
+            + ("" if board["arc"] else "   (no red→green arc found; built from the largest edits)"))
+    _eprint(f"  redacted {n} item{'s' if n != 1 else ''}" + (f" ({what})" if what else ""))
+    return board
+
+
+def _render(board: dict, args: argparse.Namespace) -> Path:
+    from .board import caption_claims, reredact, validate
+    board = validate(board)
+    board, changed = reredact(board)
+    if changed:
+        _eprint(f"  redacted {sum(changed.values())} more item(s) found in the storyboard ({', '.join(changed)})")
+    for w in caption_claims(board):
+        _eprint(f"  warning  {w}")
+    out = Path(args.output)
+    audio = None
+    if args.voice is not None:
+        from . import voice
+        board, audio = voice.narrate(board, voice=args.voice or None)
+    t0 = time.time()
+    render.render(board, out, fmt=args.format, audio=audio, progress=_progress)
+    secs = sum(float(s.get("seconds", 3)) for s in board["scenes"])
+    _eprint(f"  wrote    {out}  ({secs:.0f}s video, {out.stat().st_size / 1e6:.1f} MB, {time.time() - t0:.0f}s to render)")
+    if args.gif:
+        gif = render.to_gif(out, out.with_suffix(".gif"))
+        _eprint(f"  wrote    {gif}  ({gif.stat().st_size / 1e6:.1f} MB)")
+    return out
+
+
+def cmd_make(args: argparse.Namespace) -> int:
+    board = _plan(args)
+    _render(board, args)
+    return 0
+
+
+def cmd_plan(args: argparse.Namespace) -> int:
+    board = _plan(args)
+    text = json.dumps(board, ensure_ascii=False, indent=2)
+    if args.output == "-":
+        print(text)
+    else:
+        Path(args.output).write_text(text + "\n", encoding="utf-8")
+        _eprint(f"  wrote    {args.output}  — edit captions, then: sessionreel render {args.output}")
+    return 0
+
+
+def cmd_render(args: argparse.Namespace) -> int:
+    board = json.loads(Path(args.storyboard).read_text(encoding="utf-8"))
+    if board.get("version") != story.STORYBOARD_VERSION:
+        _eprint(f"  storyboard version {board.get('version')} is not supported by this sessionreel ({__version__})")
+        return 2
+    _render(board, args)
+    return 0
+
+
+def cmd_list(args: argparse.Namespace) -> int:
+    files = ingest.session_files(cwd=os.getcwd() if args.here else None)[: args.limit]
+    if not files:
+        _eprint(f"  no sessions under {ingest.projects_root()}")
+        return 1
+    home = str(Path.home())
+    for f in files:
+        sess = ingest.load(f)
+        when = time.strftime("%Y-%m-%d %H:%M", time.localtime(f.stat().st_mtime))
+        cwd = sess.cwd.replace(home, "~") if sess.cwd else "?"
+        mins = int(story.active_seconds(sess.events) // 60)
+        print(f"{f.stem[:8]}  {when}  {mins:>4}m  {len(sess.prompts):>3} prompts  {len(sess.tools):>4} tools  {cwd}")
+    return 0
+
+
+def cmd_demo(args: argparse.Namespace) -> int:
+    args.session = str(resources.files("sessionreel").joinpath("demo", "demo-session.jsonl"))
+    return cmd_make(args)
+
+
+def build_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(
+        prog="sessionreel",
+        description="Turn a Claude Code session into a short recap video. Local, redacted, no API key.",
+    )
+    p.add_argument("--version", action="version", version=f"sessionreel {__version__}")
+    sub = p.add_subparsers(dest="cmd")
+
+    def story_opts(sp: argparse.ArgumentParser) -> None:
+        sp.add_argument("session", nargs="?", help="session id, id prefix or .jsonl path (default: latest here)")
+        sp.add_argument("--lang", choices=sorted(story.T), default="en", help="caption language")
+        sp.add_argument("--whole", action="store_true", help="tell the whole session, not just the episode around the fix")
+        sp.add_argument("--redact", action="append", metavar="REGEX", help="extra pattern to redact (repeatable)")
+        sp.add_argument("--project", metavar="NAME", help="name shown on every frame instead of the directory name")
+        sp.add_argument("--no-branch", action="store_true", help="do not show the git branch")
+
+    def video_opts(sp: argparse.ArgumentParser, default_out: str = "reel.mp4") -> None:
+        sp.add_argument("-o", "--output", default=default_out)
+        sp.add_argument("--format", choices=sorted(render.FORMATS), default="square")
+        sp.add_argument("--voice", nargs="?", const="", default=None, metavar="NAME",
+                        help="narrate captions with the OS voice (optionally a voice name)")
+        sp.add_argument("--gif", action="store_true", help="also write a GIF next to the mp4")
+
+    mk = sub.add_parser("make", help="session → mp4 (default command)")
+    story_opts(mk)
+    video_opts(mk)
+    mk.set_defaults(fn=cmd_make)
+
+    pl = sub.add_parser("plan", help="session → editable storyboard.json")
+    story_opts(pl)
+    pl.add_argument("-o", "--output", default="storyboard.json", help="path, or - for stdout")
+    pl.set_defaults(fn=cmd_plan)
+
+    rd = sub.add_parser("render", help="storyboard.json → mp4")
+    rd.add_argument("storyboard")
+    video_opts(rd)
+    rd.set_defaults(fn=cmd_render)
+
+    ls = sub.add_parser("list", help="recent sessions")
+    ls.add_argument("--here", action="store_true", help="only sessions for the current directory")
+    ls.add_argument("-n", "--limit", type=int, default=20)
+    ls.set_defaults(fn=cmd_list)
+
+    dm = sub.add_parser("demo", help="render the bundled sample session (no logs needed)")
+    dm.add_argument("--lang", choices=sorted(story.T), default="en")
+    video_opts(dm, "sessionreel-demo.mp4")
+    dm.set_defaults(fn=cmd_demo, whole=False, redact=None, project=None, no_branch=False)
+    return p
+
+
+def main(argv: list[str] | None = None) -> int:
+    argv = sys.argv[1:] if argv is None else argv
+    parser = build_parser()
+    if not argv or argv[0] not in {"make", "plan", "render", "list", "demo", "-h", "--help", "--version"}:
+        argv = ["make", *argv]
+    args = parser.parse_args(argv)
+    try:
+        return args.fn(args)
+    except (FileNotFoundError, ValueError, RuntimeError, OSError, json.JSONDecodeError) as e:
+        _eprint(f"sessionreel: {e}")
+        return 1
+    except KeyboardInterrupt:
+        return 130
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

sessionreel/demo/demo-session.jsonl

@@ -0,0 +1,25 @@
+{"type": "ai-title", "aiTitle": "Unicode titles produce empty slugs", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001"}
+{"parentUuid": null, "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "72acfd2f-7482-4fdc-a3f1-c2c764cc7afc", "timestamp": "2026-09-18T14:02:11Z", "message": {"role": "user", "content": "Titles with accents or emoji come out as broken slugs — \"Crème brûlée 🍮\" becomes \"cr-me-br-l-e\". Fix slugify so it produces \"creme-brulee\", cap slugs at 80 chars, and add tests."}}
+{"parentUuid": "72acfd2f-7482-4fdc-a3f1-c2c764cc7afc", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "db7b1b2f-7827-4ef8-908a-f85fdc9535db", "timestamp": "2026-09-18T14:02:15Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "text", "text": "I'll look at how slugs are built and what the tests cover first."}], "usage": {"input_tokens": 6, "cache_creation_input_tokens": 2100, "cache_read_input_tokens": 31000, "output_tokens": 180}}}
+{"parentUuid": "db7b1b2f-7827-4ef8-908a-f85fdc9535db", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "5926dc4d-f3de-4731-b3f5-97611cdd5910", "timestamp": "2026-09-18T14:02:20Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_e4987968ed914b69b42e1f81", "name": "Read", "input": {"file_path": "/home/dev/slugkit/slugkit/slug.py"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "5926dc4d-f3de-4731-b3f5-97611cdd5910", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "6310dfe0-48de-4a3b-9ada-02a0c2ae149f", "timestamp": "2026-09-18T14:02:22Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_e4987968ed914b69b42e1f81", "type": "tool_result", "content": "import re\n\n\ndef slugify(title: str) -> str:\n    \"\"\"Lowercase, keep a-z0-9, join words with '-'.\"\"\"\n    words = re.findall(r\"[a-z0-9]+\", title.lower())\n    return \"-\".join(words)\n", "is_error": false}]}}
+{"parentUuid": "6310dfe0-48de-4a3b-9ada-02a0c2ae149f", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "8cf3b5ab-9691-4a02-8e5f-b5a5e155dde4", "timestamp": "2026-09-18T14:02:27Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_ee00f0f96c7445b78df7e9dd", "name": "Grep", "input": {"pattern": "slugify\\(", "path": "/home/dev/slugkit"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "8cf3b5ab-9691-4a02-8e5f-b5a5e155dde4", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "972acd37-17ce-47e9-aac8-8e50230e96c3", "timestamp": "2026-09-18T14:02:29Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_ee00f0f96c7445b78df7e9dd", "type": "tool_result", "content": "slugkit/slug.py\nslugkit/posts.py\nslugkit/feed.py\ntests/test_slug.py", "is_error": false}]}}
+{"parentUuid": "972acd37-17ce-47e9-aac8-8e50230e96c3", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "4ef38ca9-3398-42d2-941a-0f546d0309db", "timestamp": "2026-09-18T14:02:34Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_1eeabb0fc4e344129403c1dc", "name": "Read", "input": {"file_path": "/home/dev/slugkit/slugkit/posts.py"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "4ef38ca9-3398-42d2-941a-0f546d0309db", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "4628f880-f74a-4792-bc63-d8ba78f623a9", "timestamp": "2026-09-18T14:02:36Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_1eeabb0fc4e344129403c1dc", "type": "tool_result", "content": "from .slug import slugify\n...", "is_error": false}]}}
+{"parentUuid": "4628f880-f74a-4792-bc63-d8ba78f623a9", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "0cd11491-21df-488b-bf48-379f99069811", "timestamp": "2026-09-18T14:02:41Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_120cce50341b4d16bf5bb118", "name": "Read", "input": {"file_path": "/home/dev/slugkit/tests/test_slug.py"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "0cd11491-21df-488b-bf48-379f99069811", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "5f19650e-1e3f-4ba3-ad36-fe20a7482f6d", "timestamp": "2026-09-18T14:02:43Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_120cce50341b4d16bf5bb118", "type": "tool_result", "content": "def test_basic(): ...", "is_error": false}]}}
+{"parentUuid": "5f19650e-1e3f-4ba3-ad36-fe20a7482f6d", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "d8e21392-7966-4f56-972f-7ad755a267cb", "timestamp": "2026-09-18T14:02:48Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_e9ddc3d9bd144b919c460c96", "name": "Read", "input": {"file_path": "/home/dev/slugkit/pyproject.toml"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "d8e21392-7966-4f56-972f-7ad755a267cb", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "318366d2-a5e9-47d2-802d-c7fad6e7c391", "timestamp": "2026-09-18T14:02:50Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_e9ddc3d9bd144b919c460c96", "type": "tool_result", "content": "[project]\nname = \"slugkit\"", "is_error": false}]}}
+{"parentUuid": "318366d2-a5e9-47d2-802d-c7fad6e7c391", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "3cf5b1fe-4c72-4e7f-a34a-e40bf435141b", "timestamp": "2026-09-18T14:02:59Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_537f9b8411a24b07a132a244", "name": "Edit", "input": {"file_path": "/home/dev/slugkit/tests/test_slug.py", "old_string": "def test_basic():", "new_string": "def test_accents():\n    assert slugify(\"Crème brûlée 🍮\") == \"creme-brulee\"\n\n\ndef test_max_len():\n    assert len(slugify(\"word \" * 40)) <= 80\n\n\ndef test_basic():"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "3cf5b1fe-4c72-4e7f-a34a-e40bf435141b", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "b02e5ee3-a7e3-4e43-854b-f52fa3965b44", "timestamp": "2026-09-18T14:03:01Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_537f9b8411a24b07a132a244", "type": "tool_result", "content": "The file tests/test_slug.py has been updated.", "is_error": false}]}, "toolUseResult": {"filePath": "/home/dev/slugkit/tests/test_slug.py", "structuredPatch": [{"oldStart": 1, "oldLines": 3, "newStart": 1, "newLines": 11, "lines": [" from slugkit.slug import slugify", "+", "+", "+def test_accents():", "+    assert slugify(\"Crème brûlée 🍮\") == \"creme-brulee\"", "+", "+", "+def test_max_len():", "+    assert len(slugify(\"word \" * 40)) <= 80", " ", " "]}]}}
+{"parentUuid": "b02e5ee3-a7e3-4e43-854b-f52fa3965b44", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "bbead3f9-a6c8-43b9-98ef-806d2d2580f4", "timestamp": "2026-09-18T14:03:15Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_f575db7dcbef41228716d19f", "name": "Bash", "input": {"command": "cd /home/dev/slugkit && python -m pytest -q", "description": "Run tests"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "bbead3f9-a6c8-43b9-98ef-806d2d2580f4", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "17cb27ba-2866-4a3b-9be4-21320117bc30", "timestamp": "2026-09-18T14:03:17Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_f575db7dcbef41228716d19f", "type": "tool_result", "content": "Exit code 1\n..F.F.........                                                   [100%]\n=================================== FAILURES ===================================\n________________________________ test_accents _________________________________\n>       assert slugify(\"Crème brûlée 🍮\") == \"creme-brulee\"\nE       AssertionError: assert 'cr-me-br-l-e' == 'creme-brulee'\n________________________________ test_max_len _________________________________\nE       assert 199 <= 80\n=========================== short test summary info ============================\nFAILED tests/test_slug.py::test_accents - AssertionError\nFAILED tests/test_slug.py::test_max_len - assert 199 <= 80\n2 failed, 12 passed in 0.31s", "is_error": true}]}}
+{"parentUuid": "17cb27ba-2866-4a3b-9be4-21320117bc30", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "8b9fa0cf-2791-47be-b6e2-41e59fba9621", "timestamp": "2026-09-18T14:03:21Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "text", "text": "Two failures, as expected: accented letters are dropped instead of folded, and there is no length cap. Normalising to NFKD and encoding to ASCII folds é→e and drops the emoji."}], "usage": {"input_tokens": 6, "cache_creation_input_tokens": 2100, "cache_read_input_tokens": 31000, "output_tokens": 180}}}
+{"parentUuid": "8b9fa0cf-2791-47be-b6e2-41e59fba9621", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "ef99cae3-cd36-4292-9925-dbcd8b9ef4a1", "timestamp": "2026-09-18T14:03:42Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_e3e03248803c49ab9521cf24", "name": "Edit", "input": {"file_path": "/home/dev/slugkit/slugkit/slug.py", "old_string": "import re\n\n\ndef slugify(title: str) -> str:\n    \"\"\"Lowercase, keep a-z0-9, join words with '-'.\"\"\"\n    words = re.findall(r\"[a-z0-9]+\", title.lower())\n    return \"-\".join(words)\n", "new_string": "import re\nimport unicodedata\n\n\ndef slugify(title: str, max_len: int = 80) -> str:\n    \"\"\"ASCII slug: strip accents, drop symbols and emoji, join words with '-'.\"\"\"\n    text = unicodedata.normalize(\"NFKD\", title)\n    text = text.encode(\"ascii\", \"ignore\").decode(\"ascii\")\n    words = re.findall(r\"[a-z0-9]+\", text.lower())\n    return \"-\".join(words)[:max_len].rstrip(\"-\")\n"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "ef99cae3-cd36-4292-9925-dbcd8b9ef4a1", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "0deb9e41-898a-46ae-b721-a5c4325f9063", "timestamp": "2026-09-18T14:03:44Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_e3e03248803c49ab9521cf24", "type": "tool_result", "content": "The file slugkit/slug.py has been updated.", "is_error": false}]}, "toolUseResult": {"filePath": "/home/dev/slugkit/slugkit/slug.py", "structuredPatch": [{"oldStart": 1, "oldLines": 8, "newStart": 1, "newLines": 11, "lines": [" import re", "+import unicodedata", " ", " ", "-def slugify(title: str) -> str:", "-    \"\"\"Lowercase, keep a-z0-9, join words with '-'.\"\"\"", "-    words = re.findall(r\"[a-z0-9]+\", title.lower())", "-    return \"-\".join(words)", "+def slugify(title: str, max_len: int = 80) -> str:", "+    \"\"\"ASCII slug: strip accents, drop symbols and emoji, join words with '-'.\"\"\"", "+    text = unicodedata.normalize(\"NFKD\", title)", "+    text = text.encode(\"ascii\", \"ignore\").decode(\"ascii\")", "+    words = re.findall(r\"[a-z0-9]+\", text.lower())", "+    return \"-\".join(words)[:max_len].rstrip(\"-\")", " "]}]}}
+{"parentUuid": "0deb9e41-898a-46ae-b721-a5c4325f9063", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "2755f14f-5fe0-4396-9edb-90b8c4ed30f5", "timestamp": "2026-09-18T14:03:56Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_867fd826f46a4126ac85342b", "name": "Bash", "input": {"command": "cd /home/dev/slugkit && python -m pytest -q", "description": "Run tests"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "2755f14f-5fe0-4396-9edb-90b8c4ed30f5", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "9d8e2ffe-cd19-450b-a5c2-e62718c5d99d", "timestamp": "2026-09-18T14:03:58Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_867fd826f46a4126ac85342b", "type": "tool_result", "content": "..............                                                   [100%]\n14 passed in 0.27s", "is_error": false}]}}
+{"parentUuid": "9d8e2ffe-cd19-450b-a5c2-e62718c5d99d", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "92e963d0-f683-4fd8-ae5a-4df0135eea6a", "timestamp": "2026-09-18T14:04:06Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "tool_use", "id": "toolu_7fcddb74f9304f6b8f9ef07a", "name": "Bash", "input": {"command": "cd /home/dev/slugkit && git add -A && git commit -q -m \"slugify: fold accents, drop emoji, cap at 80 chars\" && git push -q", "description": "Commit and push"}}], "usage": {"input_tokens": 4, "cache_creation_input_tokens": 900, "cache_read_input_tokens": 33000, "output_tokens": 220}}}
+{"parentUuid": "92e963d0-f683-4fd8-ae5a-4df0135eea6a", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "user", "uuid": "b8dbc652-6557-48c1-ac3d-8a66f0bd24f1", "timestamp": "2026-09-18T14:04:08Z", "message": {"role": "user", "content": [{"tool_use_id": "toolu_7fcddb74f9304f6b8f9ef07a", "type": "tool_result", "content": "", "is_error": false}]}}
+{"parentUuid": "b8dbc652-6557-48c1-ac3d-8a66f0bd24f1", "isSidechain": false, "userType": "external", "cwd": "/home/dev/slugkit", "sessionId": "5e55a0d0-de40-4c1e-9d3e-000000000001", "version": "2.1.270", "gitBranch": "fix/unicode-slugs", "type": "assistant", "uuid": "52dca5ee-d8de-4c15-a93f-646783fcd3e3", "timestamp": "2026-09-18T14:04:12Z", "message": {"model": "claude-opus-5", "role": "assistant", "type": "message", "content": [{"type": "text", "text": "Fixed. `slugify(\"Crème brûlée 🍮\")` now returns `creme-brulee`: titles are NFKD-normalised and folded to ASCII, symbols and emoji are dropped, and slugs are capped at 80 characters. Two new tests cover it; all 14 pass."}], "usage": {"input_tokens": 6, "cache_creation_input_tokens": 2100, "cache_read_input_tokens": 31000, "output_tokens": 180}}}

sessionreel/fonts/OFL-Inter.txt

@@ -0,0 +1,92 @@
+Copyright (c) 2016 The Inter Project Authors (https://github.com/rsms/inter)
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded,
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION AND CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

sessionreel/fonts/OFL-JetBrainsMono.txt

@@ -0,0 +1,93 @@
+Copyright 2020 The JetBrains Mono Project Authors (https://github.com/JetBrains/JetBrainsMono)
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+https://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.