Merge branch 'ci/lint' into 'main'

osisdie · osisdie · commit b203ac84ed20 · 2026-03-13T03:30:25.000Z
ci: add ci and lint

See merge request nwpie/vibe/ai-claude-loop!5
diff --git a/.env.example b/.env.example
@@ -17,4 +17,4 @@ B2_APP_KEY=
 B2_BUCKET_NAME=
 
 # Whishper from HugginfFace inference API
-HF_TOKEN=
+HF_TOKEN=
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -0,0 +1,19 @@
+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - uses: pre-commit/action@v3.0.1
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
@@ -0,0 +1,15 @@
+stages:
+  - lint
+
+lint:
+  stage: lint
+  image: python:3.12-slim
+  before_script:
+    - apt-get update -qq && apt-get install -y -qq git >/dev/null
+    - pip install --quiet pre-commit
+  script:
+    - pre-commit run --all-files
+  cache:
+    key: pre-commit
+    paths:
+      - ~/.cache/pre-commit
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,25 @@
+# See https://pre-commit.com for more information
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-json
+      - id: check-added-large-files
+        args: ['--maxkb=10000']
+      - id: check-merge-conflict
+      - id: detect-private-key
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.10
+    hooks:
+      - id: ruff
+        args: ['--fix']
+      - id: ruff-format
+
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
diff --git a/docs/example.ingest/digest-yt.md b/docs/example.ingest/digest-yt.md
@@ -15,4 +15,4 @@
 
 
 
-Compiled from @AIDailyBrief by Claude Code :zap:
+Compiled from @AIDailyBrief by Claude Code :zap:
diff --git a/scripts/slack_notify.sh b/scripts/slack_notify.sh
@@ -103,7 +103,7 @@ slack_send() {
       local payload resp ok
       payload=$(printf '{"channel":"%s","text":"%s"}' \
         "$SLACK_CHANNEL_ID" \
-        "$(echo "$msg" | sed 's/"/\\"/g')")
+        "${msg//\"/\\\"}")
 
       resp=$(curl -s -X POST \
         -H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
@@ -122,7 +122,7 @@ slack_send() {
 
     webhook)
       local payload
-      payload=$(printf '{"text":"%s"}' "$(echo "$msg" | sed 's/"/\\"/g')")
+      payload=$(printf '{"text":"%s"}' "${msg//\"/\\\"}")
       curl -s -X POST \
         -H 'Content-type: application/json' \
         -d "$payload" \
@@ -144,19 +144,21 @@ slack_send() {
 # Returns: 0 on success (sets _SLACK_LAST_THREAD_TS), 1 on failure
 slack_ask() {
   local question="${1:?Usage: slack_ask \"question\"}"
-  local req_id="REQ-$(date +%s)"
+  local req_id
+  req_id="REQ-$(date +%s)"
   local project_name
   project_name=$(basename "$(pwd)")
 
   case "${_SLACK_MODE:-}" in
     bot)
-      local msg payload resp ok ts
+      local msg payload resp ok
+      # shellcheck disable=SC2016 # %s placeholders are printf args, not shell expansions
       msg=$(printf ':question: *[%s] Approval Request*\n`[%s]`\n\n%s\n\n_Reply in this thread to respond._' \
         "$project_name" "$req_id" "$question")
 
       payload=$(printf '{"channel":"%s","text":"%s","unfurl_links":false}' \
         "$SLACK_CHANNEL_ID" \
-        "$(echo "$msg" | sed 's/"/\\"/g')")
+        "${msg//\"/\\\"}")
 
       resp=$(curl -s -X POST \
         -H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
@@ -180,7 +182,7 @@ slack_ask() {
       local msg payload
       msg=$(printf '[%s] Approval Request [%s]: %s (webhook mode — reply not monitored)' \
         "$project_name" "$req_id" "$question")
-      payload=$(printf '{"text":"%s"}' "$(echo "$msg" | sed 's/"/\\"/g')")
+      payload=$(printf '{"text":"%s"}' "${msg//\"/\\\"}")
       curl -s -X POST \
         -H 'Content-type: application/json' \
         -d "$payload" \
@@ -224,7 +226,7 @@ slack_wait_reply() {
   echo "[slack] Waiting for reply (timeout: ${timeout}s, polling every ${interval}s)..." >&2
 
   while (( elapsed < timeout )); do
-    local resp replies reply_text reply_user
+    local resp reply_text
     resp=$(curl -s -H "Authorization: Bearer ${SLACK_BOT_TOKEN}" \
       "https://slack.com/api/conversations.replies?channel=${SLACK_CHANNEL_ID}&ts=${_SLACK_LAST_THREAD_TS}" \
       2>/dev/null)
diff --git a/scripts/yt/build_html.py b/scripts/yt/build_html.py
@@ -103,6 +103,7 @@ def build_html(md_path: Path, title: str = "", lang: str = "en") -> str:
     if not title:
         first_line = md_text.split("\n")[0]
         import re
+
         title = re.sub(r"^#+\s*", "", first_line).strip() or md_path.stem
 
     lang_attr = "zh-Hant" if "zh" in lang else "en"
diff --git a/scripts/yt/fetch_recent_videos.py b/scripts/yt/fetch_recent_videos.py
@@ -26,8 +26,10 @@ def fetch_channel_videos(channel_url: str, max_items: int = 10) -> list[dict]:
     """
     cmd = [
         "yt-dlp",
-        "--playlist-items", f"1:{max_items}",
-        "--print", "%(id)s\t%(title)s\t%(upload_date)s\t%(modified_date)s\t%(thumbnail)s",
+        "--playlist-items",
+        f"1:{max_items}",
+        "--print",
+        "%(id)s\t%(title)s\t%(upload_date)s\t%(modified_date)s\t%(thumbnail)s",
         "--skip-download",
         f"{channel_url}/videos",
     ]
@@ -51,8 +53,9 @@ def fetch_channel_videos(channel_url: str, max_items: int = 10) -> list[dict]:
                 "title": parts[1],
                 "upload_date": upload,
                 "modified_date": modified,
-                "thumbnail": parts[4] if len(parts) >= 5 and parts[4] != "NA"
-                    else f"https://i.ytimg.com/vi/{vid_id}/hqdefault.jpg",
+                "thumbnail": parts[4]
+                if len(parts) >= 5 and parts[4] != "NA"
+                else f"https://i.ytimg.com/vi/{vid_id}/hqdefault.jpg",
             }
             videos.append(vid)
     return videos
diff --git a/scripts/yt/get_transcript.py b/scripts/yt/get_transcript.py
@@ -21,6 +21,7 @@
 # Try to load .env
 try:
     from dotenv import load_dotenv
+
     load_dotenv()
 except ImportError:
     pass
@@ -34,23 +35,41 @@ def download_subtitles(video_url: str, out_dir: Path, lang: str = "en") -> Path
     # Try manual subs first
     subprocess.run(
         [
-            "yt-dlp", "--write-subs", "--sub-lang", lang,
-            "--sub-format", "srt", "--skip-download",
-            "-o", str(out_dir / "video"), video_url,
+            "yt-dlp",
+            "--write-subs",
+            "--sub-lang",
+            lang,
+            "--sub-format",
+            "srt",
+            "--skip-download",
+            "-o",
+            str(out_dir / "video"),
+            video_url,
         ],
-        capture_output=True, text=True, timeout=60,
+        capture_output=True,
+        text=True,
+        timeout=60,
     )
     if srt_path.exists() and srt_path.stat().st_size > 0:
         return srt_path
 
     # Try auto-generated subs
     subprocess.run(
         [
-            "yt-dlp", "--write-auto-subs", "--sub-lang", lang,
-            "--sub-format", "srt", "--skip-download",
-            "-o", str(out_dir / "video"), video_url,
+            "yt-dlp",
+            "--write-auto-subs",
+            "--sub-lang",
+            lang,
+            "--sub-format",
+            "srt",
+            "--skip-download",
+            "-o",
+            str(out_dir / "video"),
+            video_url,
         ],
-        capture_output=True, text=True, timeout=60,
+        capture_output=True,
+        text=True,
+        timeout=60,
     )
     if srt_path.exists() and srt_path.stat().st_size > 0:
         return srt_path
@@ -85,11 +104,19 @@ def whisper_transcribe_hf(video_url: str, out_dir: Path) -> str | None:
     audio_path = out_dir / "audio.m4a"
     subprocess.run(
         [
-            "yt-dlp", "-f", "worstaudio[ext=m4a]/worstaudio",
-            "--extract-audio", "--audio-format", "m4a",
-            "-o", str(audio_path), video_url,
+            "yt-dlp",
+            "-f",
+            "worstaudio[ext=m4a]/worstaudio",
+            "--extract-audio",
+            "--audio-format",
+            "m4a",
+            "-o",
+            str(audio_path),
+            video_url,
         ],
-        capture_output=True, text=True, timeout=300,
+        capture_output=True,
+        text=True,
+        timeout=300,
     )
     if not audio_path.exists():
         # Check for alternative extensions
@@ -103,15 +130,28 @@ def whisper_transcribe_hf(video_url: str, out_dir: Path) -> str | None:
     # Convert to wav for HF API
     wav_path = out_dir / "audio.wav"
     subprocess.run(
-        ["ffmpeg", "-i", str(audio_path), "-ar", "16000", "-ac", "1", "-y", str(wav_path)],
-        capture_output=True, text=True, timeout=300,
+        [
+            "ffmpeg",
+            "-i",
+            str(audio_path),
+            "-ar",
+            "16000",
+            "-ac",
+            "1",
+            "-y",
+            str(wav_path),
+        ],
+        capture_output=True,
+        text=True,
+        timeout=300,
     )
     if not wav_path.exists():
         print("FFmpeg conversion failed", file=sys.stderr)
         return None
 
     try:
         from huggingface_hub import InferenceClient
+
         client = InferenceClient(token=hf_token)
         result = client.automatic_speech_recognition(
             str(wav_path),
diff --git a/scripts/yt/upload_b2.py b/scripts/yt/upload_b2.py
@@ -20,6 +20,7 @@
 # Try to load .env
 try:
     from dotenv import load_dotenv
+
     load_dotenv()
 except ImportError:
     pass
@@ -32,7 +33,9 @@ def _b2_cmd() -> list[str]:
     # b2 v1.3.8 installed in system python without a CLI entrypoint
     for py in ["/usr/bin/python3", "python3", "python"]:
         if shutil.which(py):
-            r = subprocess.run([py, "-m", "b2", "version"], capture_output=True, text=True)
+            r = subprocess.run(
+                [py, "-m", "b2", "version"], capture_output=True, text=True
+            )
             if r.returncode == 0:
                 return [py, "-m", "b2"]
     return ["b2"]  # let it fail with a clear error
@@ -48,7 +51,9 @@ def authorize_b2() -> bool:
 
     result = subprocess.run(
         [*_b2_cmd(), "authorize-account", key_id, app_key],
-        capture_output=True, text=True, timeout=30,
+        capture_output=True,
+        text=True,
+        timeout=30,
     )
     if result.returncode != 0:
         print(f"b2 authorize-account failed: {result.stderr[:300]}", file=sys.stderr)
@@ -65,7 +70,9 @@ def upload_file(local_path: Path, b2_path: str, duration: int = 604800) -> str |
 
     result = subprocess.run(
         [*_b2_cmd(), "upload-file", bucket, str(local_path), b2_path],
-        capture_output=True, text=True, timeout=120,
+        capture_output=True,
+        text=True,
+        timeout=120,
     )
     if result.returncode != 0:
         print(f"b2 upload-file failed: {result.stderr[:300]}", file=sys.stderr)
@@ -75,17 +82,26 @@ def upload_file(local_path: Path, b2_path: str, duration: int = 604800) -> str |
     return _get_presigned_url(bucket, b2_path, duration)
 
 
-def _get_presigned_url(
-    bucket: str, b2_path: str, duration: int = 604800
-) -> str | None:
+def _get_presigned_url(bucket: str, b2_path: str, duration: int = 604800) -> str | None:
     """Get a presigned download URL. Default duration: 7 days (604800s)."""
     result = subprocess.run(
-        [*_b2_cmd(), "get-download-url-with-auth", "--duration", str(duration),
-         bucket, b2_path],
-        capture_output=True, text=True, timeout=30,
+        [
+            *_b2_cmd(),
+            "get-download-url-with-auth",
+            "--duration",
+            str(duration),
+            bucket,
+            b2_path,
+        ],
+        capture_output=True,
+        text=True,
+        timeout=30,
     )
     if result.returncode != 0:
-        print(f"b2 get-download-url-with-auth failed: {result.stderr[:300]}", file=sys.stderr)
+        print(
+            f"b2 get-download-url-with-auth failed: {result.stderr[:300]}",
+            file=sys.stderr,
+        )
         # Fallback to direct URL (will 401 on private buckets)
         return f"https://f005.backblazeb2.com/file/{bucket}/{b2_path}"
 
@@ -115,7 +131,7 @@ def main():
 
     b2_path = f"{args.prefix}/{local_path.name}"
 
-    print(f"Authorizing B2...", file=sys.stderr)
+    print("Authorizing B2...", file=sys.stderr)
     if not authorize_b2():
         sys.exit(1)
 

Original file line number	Diff line number	Diff line change
`@@ -15,4 +15,4 @@`
`15`	`15`
`16`	`16`
`17`	`17`
`18`		`-Compiled from @AIDailyBrief by Claude Code :zap:`
	`18`	`+Compiled from @AIDailyBrief by Claude Code :zap:`