lastlight 0.4.0 → 0.5.1

package/skills/demo/scripts/compose-demo.sh

@@ -9,16 +9,19 @@
 #   compose-demo.sh --output demo.mp4 --title "PR #42 — Add dark mode" \
 #     [--subtitle "..."] [--layout single|side-by-side] \
 #     [--labels "BEFORE (main)" "AFTER (PR)"] [--speed 1.5] \
-#     [--trim START:END] [--target-size-mb 5] [--width 1280] [--height 720] \
-#     [--title-secs 2.5] <clip1.webm> [clip2.webm]
+#     [--trim START:END] [--target-size-mb 10] [--crf 18] \
+#     [--width 1920] [--height 1080] [--title-secs 2.5] <clip1.webm> [clip2.webm]
 #
 # What it does:
 #   1. Normalizes each input clip (optional trim, speed-up, scale+pad to the
-#      panel size, fps/pixfmt/SAR normalize, optional per-panel label).
+#      panel size with lanczos, fps/pixfmt/SAR normalize, optional per-panel
+#      label).
 #   2. Lays out the body: a single panel, or two panels side-by-side (hstack).
 #   3. Prepends a title/subtitle card (solid bg + drawtext).
-#   4. Two-pass H.264 encode targeting --target-size-mb so the mp4 lands under
-#      GitHub's inline-embed limit; yuv420p + +faststart for web streaming.
+#   4. Quality-first H.264 encode: a single-pass CRF encode (sharp for UI
+#      screencasts) that usually lands well under --target-size-mb; only if it
+#      overshoots does it fall back to a size-targeted two-pass ABR encode.
+#      yuv420p + +faststart for web streaming.
 #   5. Prints an ffprobe summary (resolution / duration / size).
 #
 # Prerequisites: ffmpeg, ffprobe (baked into lastlight-sandbox-qa:latest).
@@ -40,9 +43,10 @@ LABEL1=""
 LABEL2=""
 SPEED="1"
 TRIM=""
-TARGET_MB="5"
-WIDTH="1280"
-HEIGHT="720"
+TARGET_MB="10"
+CRF="18"
+WIDTH="1920"
+HEIGHT="1080"
 TITLE_SECS="2.5"
 CLIPS=()
 
@@ -57,6 +61,7 @@ while [[ $# -gt 0 ]]; do
     --speed) SPEED="$2"; shift 2;;
     --trim) TRIM="$2"; shift 2;;
     --target-size-mb) TARGET_MB="$2"; shift 2;;
+    --crf) CRF="$2"; shift 2;;
     --width) WIDTH="$2"; shift 2;;
     --height) HEIGHT="$2"; shift 2;;
     --title-secs) TITLE_SECS="$2"; shift 2;;
@@ -94,11 +99,19 @@ if [[ -n "$FONT" ]]; then FONTARG="fontfile=${FONT}"; else FONTARG="font=Sans";
 # gracefully on a build without it (omit text overlays) rather than failing the
 # whole compose — the demo video is still worth shipping.
 HAS_DRAWTEXT=0
-if ffmpeg -hide_banner -filters 2>/dev/null | grep -q 'drawtext'; then
-  HAS_DRAWTEXT=1
-else
-  echo "compose-demo.sh: warning: this ffmpeg lacks the drawtext filter — title card and labels omitted." >&2
-fi
+# Detect the drawtext filter WITHOUT a pipe. Under `set -o pipefail`, any
+# `ffmpeg -filters | grep -q drawtext` (or even `printf "$var" | grep -q`) is a
+# false-negative trap: `grep -q` exits on the first match and closes the pipe,
+# the writer (still emitting — `drawtext` sits ~16 KB into ~38 KB of output)
+# dies with SIGPIPE (141), and `pipefail` promotes that to the pipeline's exit
+# status, so the `if` wrongly concludes drawtext is absent (~19 of 20 runs).
+# Capture into a variable and match with a pure bash `case` — no subprocess,
+# no pipe, no SIGPIPE.
+FFMPEG_FILTERS="$(ffmpeg -hide_banner -filters 2>/dev/null || true)"
+case "$FFMPEG_FILTERS" in
+  *drawtext*) HAS_DRAWTEXT=1 ;;
+  *) echo "compose-demo.sh: warning: this ffmpeg lacks the drawtext filter — title card and labels omitted." >&2 ;;
+esac
 
 # Panel size: side-by-side splits the width into two equal panels.
 PH="$HEIGHT"
@@ -115,17 +128,19 @@ build_panel() {
     [[ -n "$end" ]] && trim_args+=(-to "$end")
   fi
   local vf="setpts=PTS/${SPEED}"
-  vf+=",scale=${PW}:${PH}:force_original_aspect_ratio=decrease"
+  vf+=",scale=${PW}:${PH}:force_original_aspect_ratio=decrease:flags=lanczos"
   vf+=",pad=${PW}:${PH}:(ow-iw)/2:(oh-ih)/2:color=black"
   vf+=",fps=30,format=yuv420p,setsar=1"
   if [[ -n "$labelfile" && "$HAS_DRAWTEXT" == "1" ]]; then
-    vf+=",drawtext=${FONTARG}:textfile=${labelfile}:x=(w-text_w)/2:y=h-th-24"
-    vf+=":fontsize=26:fontcolor=white:box=1:boxcolor=black@0.55:boxborderw=12"
+    # Anchor labels to the TOP of the panel. At the bottom they're hidden behind
+    # the browser/GitHub video player's control bar (scrubber + play button).
+    vf+=",drawtext=${FONTARG}:textfile=${labelfile}:x=(w-text_w)/2:y=28"
+    vf+=":fontsize=34:fontcolor=white:box=1:boxcolor=black@0.55:boxborderw=14"
   fi
   # `${arr[@]+"${arr[@]}"}` expands to nothing when the array is empty without
   # tripping `set -u` (an empty `"${arr[@]}"` errors on bash < 4.4, e.g. macOS).
   ffmpeg -y -loglevel error ${trim_args[@]+"${trim_args[@]}"} -i "$input" \
-    -vf "$vf" -an -c:v libx264 -crf 20 -preset veryfast "$outfile"
+    -vf "$vf" -an -c:v libx264 -crf "$CRF" -preset medium "$outfile"
 }
 
 # Per-panel labels (side-by-side) written to files to avoid drawtext escaping.
@@ -140,9 +155,16 @@ build_panel "${CLIPS[0]}" "$WORK/panel0.mp4" "$LABELFILE1" 1
 BODY="$WORK/body.mp4"
 if [[ "$LAYOUT" == "side-by-side" ]]; then
   build_panel "${CLIPS[1]}" "$WORK/panel1.mp4" "$LABELFILE2" 1
+  # Pad the shorter panel by freezing its last frame so both stay aligned for the
+  # full body. Without this, hstack lets the shorter side end early and go
+  # blank/black — which reads as "the before didn't render".
+  D0="$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$WORK/panel0.mp4" || echo 0)"
+  D1="$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$WORK/panel1.mp4" || echo 0)"
+  PAD0="$(awk -v a="$D0" -v b="$D1" 'BEGIN{d=b-a; if(d<0)d=0; printf "%.3f", d}')"
+  PAD1="$(awk -v a="$D0" -v b="$D1" 'BEGIN{d=a-b; if(d<0)d=0; printf "%.3f", d}')"
   ffmpeg -y -loglevel error -i "$WORK/panel0.mp4" -i "$WORK/panel1.mp4" \
-    -filter_complex "[0:v][1:v]hstack=inputs=2,format=yuv420p,setsar=1[v]" \
-    -map "[v]" -an -c:v libx264 -crf 20 -preset veryfast "$BODY"
+    -filter_complex "[0:v]tpad=stop_mode=clone:stop_duration=${PAD0}[p0];[1:v]tpad=stop_mode=clone:stop_duration=${PAD1}[p1];[p0][p1]hstack=inputs=2,format=yuv420p,setsar=1[v]" \
+    -map "[v]" -an -c:v libx264 -crf "$CRF" -preset medium "$BODY"
 else
   BODY="$WORK/panel0.mp4"
 fi
@@ -159,25 +181,14 @@ if [[ "$HAS_DRAWTEXT" == "1" ]]; then
   fi
   TITLE_VF+=",format=yuv420p"
   ffmpeg -y -loglevel error -f lavfi -i "color=c=0x101418:s=${WIDTH}x${HEIGHT}:d=${TITLE_SECS}:r=30" \
-    -vf "$TITLE_VF" -c:v libx264 -crf 20 -preset veryfast "$WORK/title.mp4"
+    -vf "$TITLE_VF" -c:v libx264 -crf "$CRF" -preset medium "$WORK/title.mp4"
   TITLE_CLIP="$WORK/title.mp4"
   TITLE_DUR="$TITLE_SECS"
 fi
 
-# ── Stage C: (concat title +) body, two-pass size cap, faststart ─────────────
-BODY_DUR="$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$BODY" || echo 0)"
-TOTAL_DUR="$(awk -v a="$TITLE_DUR" -v b="$BODY_DUR" 'BEGIN{printf "%.3f", a + b}')"
-# Target video bitrate (kbit/s) = target_bytes * 8 / duration / 1000, with a
-# small headroom factor for the muxer; floored so very short clips still encode.
-BR_K="$(awk -v mb="$TARGET_MB" -v d="$TOTAL_DUR" 'BEGIN{
-  if (d <= 0) d = 1;
-  br = (mb * 1024 * 1024 * 8) / d / 1000 * 0.92;
-  if (br < 200) br = 200;
-  printf "%d", br;
-}')"
-
+# ── Stage C: (concat title +) body → final mp4 ───────────────────────────────
 # With a title card: concat it ahead of the body. Without: pass the body
-# through (`null`) so the same two-pass/faststart encode applies either way.
+# through (`null`) so the same encode applies either way.
 if [[ -n "$TITLE_CLIP" ]]; then
   IN_ARGS=(-i "$TITLE_CLIP" -i "$BODY")
   FILTER='[0:v][1:v]concat=n=2:v=1:a=0[v]'
@@ -185,16 +196,43 @@ else
   IN_ARGS=(-i "$BODY")
   FILTER='[0:v]null[v]'
 fi
-PASSLOG="$WORK/ff2pass"
-echo "compose-demo.sh: encoding (${TOTAL_DUR}s, target ${TARGET_MB}MB → ${BR_K}kbit/s, two-pass)…" >&2
-ffmpeg -y -loglevel error "${IN_ARGS[@]}" \
-  -filter_complex "$FILTER" -map "[v]" -an \
-  -c:v libx264 -b:v "${BR_K}k" -pass 1 -passlogfile "$PASSLOG" -preset medium -f mp4 /dev/null
+
+# Quality-first: a single-pass CRF encode (visually crisp for UI screencasts —
+# constant quality, not a starved average bitrate) usually lands well under the
+# size cap. The old always-two-pass-ABR path starved short, near-static clips
+# down to a few tens of KB; CRF spends the bits the content needs.
+echo "compose-demo.sh: encoding (crf ${CRF}, preset slow)…" >&2
 ffmpeg -y -loglevel error "${IN_ARGS[@]}" \
   -filter_complex "$FILTER" -map "[v]" -an \
-  -c:v libx264 -b:v "${BR_K}k" -pass 2 -passlogfile "$PASSLOG" -preset medium \
+  -c:v libx264 -crf "$CRF" -preset slow \
   -pix_fmt yuv420p -movflags +faststart "$OUTPUT"
 
+# Size cap: only if the quality encode overshoots --target-size-mb do we redo it
+# as a size-targeted two-pass ABR encode (keeps it under GitHub's inline limit).
+OUT_BYTES="$(wc -c < "$OUTPUT" | tr -d ' ')"
+CAP_BYTES="$(awk -v mb="$TARGET_MB" 'BEGIN{printf "%d", mb*1024*1024}')"
+if [[ "$OUT_BYTES" -gt "$CAP_BYTES" ]]; then
+  BODY_DUR="$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$BODY" || echo 0)"
+  TOTAL_DUR="$(awk -v a="$TITLE_DUR" -v b="$BODY_DUR" 'BEGIN{printf "%.3f", a + b}')"
+  # Target video bitrate (kbit/s) = target_bytes * 8 / duration / 1000, with a
+  # small headroom factor for the muxer; floored so very short clips still encode.
+  BR_K="$(awk -v mb="$TARGET_MB" -v d="$TOTAL_DUR" 'BEGIN{
+    if (d <= 0) d = 1;
+    br = (mb * 1024 * 1024 * 8) / d / 1000 * 0.92;
+    if (br < 200) br = 200;
+    printf "%d", br;
+  }')"
+  PASSLOG="$WORK/ff2pass"
+  echo "compose-demo.sh: crf encode was $(awk -v b="$OUT_BYTES" 'BEGIN{printf "%.1f", b/1024/1024}')MB > ${TARGET_MB}MB cap — re-encoding size-capped (${TOTAL_DUR}s → ${BR_K}kbit/s, two-pass)…" >&2
+  ffmpeg -y -loglevel error "${IN_ARGS[@]}" \
+    -filter_complex "$FILTER" -map "[v]" -an \
+    -c:v libx264 -b:v "${BR_K}k" -pass 1 -passlogfile "$PASSLOG" -preset medium -f mp4 /dev/null
+  ffmpeg -y -loglevel error "${IN_ARGS[@]}" \
+    -filter_complex "$FILTER" -map "[v]" -an \
+    -c:v libx264 -b:v "${BR_K}k" -pass 2 -passlogfile "$PASSLOG" -preset medium \
+    -pix_fmt yuv420p -movflags +faststart "$OUTPUT"
+fi
+
 # ── Stage D: report ───────────────────────────────────────────────────────────
 RES="$(ffprobe -v error -select_streams v:0 -show_entries stream=width,height -of csv=p=0:s=x "$OUTPUT" || echo '?')"
 DUR="$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$OUTPUT" || echo '?')"

package/workflows/examples/bash-smoke.yaml

@@ -0,0 +1,41 @@
+kind: agent
+name: bash-smoke
+description: "Smoke test for deterministic bash + script phases (run in sandbox)"
+phases:
+  - name: phase_0
+    type: context
+
+  # Deterministic shell command in the sandbox. stdout is captured and exposed
+  # downstream via output_var.
+  - name: emit
+    type: bash
+    command: "echo hello-from-bash"
+    output_var: greeting
+
+  # A second bash phase reads the first phase's output via template substitution
+  # AND via the forwarded LL_OUT_<PHASE> env var.
+  - name: consume
+    type: bash
+    command: "echo template={{phaseOutputs.emit}} ; echo env=$LL_OUT_EMIT"
+
+  # Inline JS via node.
+  - name: js
+    type: script
+    runtime: js
+    script: |
+      console.log("node version:", process.version);
+      console.log("answer:", 6 * 7);
+
+  # Inline Python via uv. The PEP 723 block declares a dependency that uv
+  # resolves from PyPI (pypi.org is on the strict egress allowlist) into a
+  # cached venv. unrestricted_egress is NOT needed for PyPI.
+  - name: py
+    type: script
+    runtime: python
+    timeout_seconds: 120
+    script: |
+      # /// script
+      # dependencies = ["cowsay"]
+      # ///
+      import cowsay
+      cowsay.cow("hello from uv")

package/workflows/prompts/demo.md

@@ -44,11 +44,33 @@ so `doctor` should pass.
 
 ## Workspace + run the app
 
-You are already inside the **{{repo}}** repo at branch {{branch}} — the harness
-pre-cloned it and your cwd is the repo root (no `cd`). Follow the `building`
-skill to install dependencies and start the dev-server in the background; poll
-with `curl` until it answers on `localhost:<port>`. For a before/after demo,
-run each branch in turn and record the same scripted interaction against each.
+You are already inside the **{{repo}}** repo — the harness pre-cloned it and your
+cwd is the repo root (no `cd`){{#if baseBranch}}, **checked out at the PR head
+branch `{{branch}}`**, so the workspace already holds the PR's code: this checkout
+*is* your "after" state{{/if}}. Follow the `building` skill to install
+dependencies and start the dev-server in the background; poll with `curl` until
+it answers on `localhost:<port>`.
+
+{{#if baseBranch}}**This is a PR → record a `side-by-side` before/after.** Record
+the **after** first, straight from the current checkout (`{{branch}}`) — do not
+re-checkout for it. Then record the **before** from the base branch
+`{{baseBranch}}`. The pre-clone is shallow + single-branch, so the base isn't
+present locally yet — fetch it explicitly by ref (never trust an ambiguously
+named local branch):
+
+```
+git fetch --depth 1 origin {{baseBranch}}
+git checkout -B {{baseBranch}}-base FETCH_HEAD
+```
+
+Re-run `building`'s install + restart the dev-server after switching. When you
+composite, the **first** clip is the left/BEFORE panel and the **second** is the
+right/AFTER panel.
+
+**Verify before you ship:** the disambiguating change must actually appear in the
+*after* recording and be absent from the *before* (use the driver's `text`/
+`assertText` to read it on both). If both states look identical, your checkout is
+wrong — STOP and fix it; do not ship a side-by-side that proves nothing.{{/if}}
 
 ## Capture and compose
 

package/workflows/qa-test.yaml

@@ -76,7 +76,7 @@ phases:
   # workflow-level `final_message`. Pure composition — no skills, no repo work.
   - name: synthesize
     label: Summary
-    depends_on: [qa_test]
+    depends_on: [qa_test, qa_browser]
     prompt: prompts/qa-synth.md
     model: "{{models.qa-test}}"
     variant: "{{variants.qa-test}}"

package/workflows/verify.yaml

@@ -74,7 +74,7 @@ phases:
   # workflow-level `final_message`. Pure composition — no skills, no repo work.
   - name: synthesize
     label: Summary
-    depends_on: [verify]
+    depends_on: [verify, verify_browser]
     prompt: prompts/verify-synth.md
     model: "{{models.verify}}"
     variant: "{{variants.verify}}"