Author SHA1 Message Date
steve abf8a514ba Merge pull request 'fix(gif): stop making agents discover the API by failing (closes mort#1522)' (#4) from fix/1522-gifsmith-api-discoverable into main 2026-07-26 18:26:44 +00:00
steve 1992efd322 Merge pull request 'fix(gif): make the contact sheet an actual contact sheet (closes mort#1519)' (#3) from fix/1519-contact-sheet-time-samples into main 2026-07-26 18:25:44 +00:00
steveandClaude Opus 5 9eb3ec49dd fix(gif): stop making agents discover the API by failing
Closes mort#1522.

23% of all code_exec calls across two production runs (9 of 39) failed on
gifsmith API misuse, hitting 7 of 14 workers. The recovery was always the same
shape: another round trip spent printing gifsmith's own source — or, in one
case, running `dir(gifsmith)` — to learn what the module contains.

Three distinct causes, three fixes.

**Unguessable re-exports → `__all__`, plus the two that were missing.** The
module exported SOME matplotlib artists and not others, and the only way to find
out which was to fail: two workers wrote `from gifsmith import PathPatch` and
got an ImportError while `FancyBboxPatch` beside it worked. `PathPatch` and
`Path` are now exported, on the rule "the drawing vocabulary, whole". `__all__`
states the surface — and it also fixes what made self-service expensive:
`dir(gifsmith)` returned 24 names of which nine were incidental imports (glob,
os, shutil, subprocess, sys, traceback...), several being things a scene author
should never touch. SKILL.md now carries the same list, so the question should
not arise.

**Near-miss constructor kwargs → an error that names the miss.** `background=`
is accepted as an alias for `bg` (it is the obvious synonym, and an agent
reached for it). `force=` is rejected with the reason it was tempting —
`render(force="mp4")` really does take it, which makes it read like an
Animation-level setting. Anything else gets a difflib near-match and the valid
list. Both failures were one round trip each, and both are the kind a message
fixes for free.

**Scenes fail at render time → dry-run every scene at t=0 first.** A NameError
in scene 4 used to surface only after scenes 0-3 were fully rendered, and with
a streaming pipe open, after frames had gone into the encoder. Two workers lost
a whole render each to `RuntimeError: every scene failed`, learning one broken
name per attempt. One frame per scene now reports EVERY broken scene in a single
pass, before any scratch dir or ffmpeg pipe exists. Per-scene isolation is
preserved exactly: a scene that fails the dry run is marked and skipped rather
than re-run to fail identically, the others still ship, and only an
all-scenes-broken program raises early — which is precisely the case that was
paying for a full setup to learn nothing.

Verified against the production failures: `Animation(background=…)` now works,
`Animation(force=…)` explains itself, `Animation(backgrnd=…)` suggests
`background`, every name in `__all__` resolves, no incidental import leaks into
it, and the dry run marks exactly the broken scenes while leaving the good ones
untouched.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
2026-07-26 12:12:00 -04:00
steveandClaude Opus 5 c1b2d41cc5 fix(gif): make the contact sheet an actual contact sheet
Closes mort#1519.

`_contact_sheet` built one tile per SCENE, and a single-scene animation — the
common case — short-circuited to `tiles[0][1].first_frame.save(path)`, a bare
frame. The harness then printed "still: … (contact sheet)" next to it.

Every single-scene worker across two production runs corrected that claim
unprompted, in the vision model's own words: "this is a single frame (not a
contact sheet)", "there is exactly 1 distinct panel/tile", "a single static
illustration, not an animation contact sheet" — ten of them. One worked out why
its critic could not see the brine tear it had animated, then proved it with a
pixel count, having already spent three full re-renders and 690 seconds on it.
It was the last of nine parallel workers to finish, holding the whole fan-out
open.

The sheet is now sampled across TIME: nine tiles by default, spread over the
whole animation, each labelled with its `t`. One scene gets all nine time
points; many scenes still get one tile each, as before, so nothing regresses
for the multi-scene case that already worked.

Two details that matter more than they look:

**Never sample t=1.0.** A loop is built to return to its starting state, so its
closing frame is the one instant guaranteed to show none of the motion. That is
exactly the frame the tear had faded out of.

**Label every tile with its t.** Without it the critic cannot tell "the tear is
missing" from "the tear is missing at t=0.75", and only the second is
actionable. The SKILL.md critique step now says so directly: check the other
tiles before re-rendering.

Reconciling the discrepancy the issue raised: the body said the still is the
t≈1.0 frame (backed by a pixel count on a live render), the code reads
`first_frame`. At HEAD it is NEITHER — `if sc.first_frame is None and
k >= n // 2` captures the MIDDLE frame, and that line arrived with the harness
in 7906a1a. The t≈1.0 observation therefore came from an older deployed pack.
It does not change the fix: one time point is one time point, whichever one it
is, and the single-scene short-circuit was the real defect.

Also: a failed scene now drops its samples along with its partial frames, so
the sheet can't advertise a scene that never shipped. Thumbnails are downscaled
at capture rather than held full-size — nine 640x480 RGB copies is ~8 MiB held
for the whole render, and the sheet shrinks them anyway.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
2026-07-26 12:09:28 -04:00
steve 7dee907d44 fix(gif): stop emitting GIFs Discord can't decode; stop dropping 44% of frames (#2)
Fixes mort#1510. Verified end-to-end: the rebuilt file plays correctly in Discord where the original flashes, and is smaller (1210 KB -> 918 KB).
2026-07-25 21:10:54 +00:00
2 changed files with 190 additions and 21 deletions
+20 -4
View File
@@ -76,9 +76,18 @@ bottom of this skill) as `{"name": "gifsmith.py", "file_id": "<that id>"}`, then
write ONE `code_exec` call:
```python
# gifsmith re-exports the drawing vocabulary, so this one import is enough:
# gifsmith re-exports the drawing vocabulary, so this one import is enough.
# The COMPLETE importable list (there is nothing else — don't guess, and don't
# spend a call on dir(gifsmith)):
# Animation
# Arc Circle Ellipse FancyBboxPatch PathPatch Path Polygon Rectangle Wedge
# Image ImageDraw ImageFont (PIL, for mode="pil")
# np plt (numpy / pyplot, for anything else)
# GIF_MAX_SECONDS GIF_MAX_BYTES
from gifsmith import Animation, Circle, Ellipse, Rectangle, Polygon, Wedge, np
anim = Animation(width=640, height=480, fps=15) # canvas locked here
# Animation() takes ONLY width, height, fps, dpi, bg (background= also works).
# Everything about the output — format, size, audio — is set on render().
# ---- cast: defined ONCE, called from every scene ----
def draw_steve(ax, x, y, rage=0.0):
@@ -149,9 +158,16 @@ gifsicle are already in the sandbox.
## 5. Self-critique (AT MOST 3 render passes)
Before delivering, LOOK at what you made: call `image_describe` on the
**`still.png` file_id** — the harness already built it as a labelled contact
sheet, one tile per scene. Ask specifically about subject size, caption
readability and whether the depicted action matches the request. Then answer:
**`still.png` file_id** — the harness already built it as a contact sheet of
frames sampled evenly ACROSS the animation, each tile labelled with its `t`
(0.00 = first frame). Ask specifically about subject size, caption readability
and whether the depicted action matches the request.
**A thing missing from one tile is not a thing missing from the animation.**
The tiles are time points, so a transient — a tear rolling, a blink, a wipe —
appears in some and not others. If the critique says something is absent, check
the other tiles for it before re-rendering; that mistake once cost a worker
three full re-renders chasing a tear that was there all along. Then answer:
1. Does it depict what was asked — every named character, prop and action?
2. Is the subject **big enough to read** (≥ ⅓ frame height)?
+170 -17
View File
@@ -37,6 +37,7 @@ fix just that scene. It also writes /workspace/still.png: a labelled contact
sheet, one tile per scene, for the critique pass.
"""
import difflib
import glob
import math
import os
@@ -52,10 +53,34 @@ from PIL import Image, ImageDraw, ImageFont # noqa: E402
# Re-exported so one import line covers the whole drawing vocabulary — a missing
# `from matplotlib.patches import ...` is otherwise a NameError that costs a pass.
#
# PathPatch and Path are here because agents assumed they already were: two
# separate workers wrote `from gifsmith import PathPatch` and got an ImportError,
# because the module exported SOME matplotlib artists and not others with no way
# to tell which from outside. The rule now is "the drawing vocabulary, whole".
from matplotlib.patches import ( # noqa: E402,F401
Arc, Circle, Ellipse, FancyBboxPatch, Polygon, Rectangle, Wedge)
Arc, Circle, Ellipse, FancyBboxPatch, PathPatch, Polygon, Rectangle, Wedge)
from matplotlib.path import Path # noqa: E402,F401
import numpy as np # noqa: E402,F401
# The public surface, stated rather than discovered. Without this, `dir(gifsmith)`
# returned 24 names of which nine were incidental imports (glob, os, shutil,
# subprocess, sys, traceback...) — several of them things a scene author should
# never touch — and a worker spent a whole code_exec call running exactly that
# to find out what it could import. Keep in sync when adding a re-export.
__all__ = [
"Animation",
# matplotlib artists (mode="mpl")
"Arc", "Circle", "Ellipse", "FancyBboxPatch", "PathPatch", "Path",
"Polygon", "Rectangle", "Wedge",
# PIL (mode="pil")
"Image", "ImageDraw", "ImageFont",
# the two libraries themselves, for anything not re-exported above
"np", "plt",
# caps a scene author may want to read
"GIF_MAX_SECONDS", "GIF_MAX_BYTES",
]
# A GIF longer than this balloons past what's worth shipping as a GIF.
GIF_MAX_SECONDS = 20
# Keep a GIF comfortably under Discord's ~10 MiB inline limit.
@@ -67,6 +92,11 @@ GIF_MAX_BYTES = 9 * 1024 * 1024
# turns a borderline short piece into an MP4.
PNG_BYTES_PER_PIXEL = 0.29
# Contact-sheet budget. Nine tiles is a 3x3 grid that vision models read
# reliably; spread across TIME for one scene, across scenes for many.
CONTACT_SHEET_MAX_TILES = 9
CONTACT_TILE_W = 300
_FONT_CANDIDATES = [
"/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf",
"/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
@@ -110,13 +140,44 @@ class _Scene:
self.mode, self.hold = mode, float(hold)
self.frames = 0
self.error = None
self.first_frame = None
# (t, thumbnail) pairs for the contact sheet. Thumbnails, not full
# frames: nine 640x480 RGB copies is ~8 MiB of RAM held for the whole
# render, and the sheet downscales them anyway.
self.samples = []
class Animation:
"""Collects scenes, renders them to a locked-size frame sequence, encodes."""
def __init__(self, width=640, height=480, fps=15, dpi=100, bg="white"):
def __init__(self, width=640, height=480, fps=15, dpi=100, bg="white", **kwargs):
# `background` is accepted as an alias for `bg` because it is the obvious
# synonym and agents reached for it; `force` is rejected loudly because
# `render(force="mp4")` DOES take it, which makes it read like an
# Animation-level setting. Both were real failures, one code_exec round
# trip each, and both are the kind a better message fixes for free.
if "background" in kwargs:
bg = kwargs.pop("background")
if kwargs:
valid = ["width", "height", "fps", "dpi", "bg (or background)"]
bad = sorted(kwargs)
hints = []
for k in bad:
near = difflib.get_close_matches(
k, ["width", "height", "fps", "dpi", "bg", "background"], n=1, cutoff=0.6)
if near:
hints.append(f"{k!r} — did you mean {near[0]!r}?")
elif k == "force":
hints.append("'force' belongs to render(force='mp4'/'gif'), "
"not to Animation()")
else:
hints.append(repr(k))
raise TypeError(
"Animation() got unexpected keyword argument(s): "
+ "; ".join(hints)
+ ". Valid: " + ", ".join(valid)
+ ". Everything about the OUTPUT (format, size, audio) is set on "
"render(), not here.")
# H.264 needs even dimensions; lock them here so the encoder never fails.
self.width = int(width) // 2 * 2
self.height = int(height) // 2 * 2
@@ -209,10 +270,46 @@ class Animation:
# ------------------------------------------------------------------- render
def _dry_run_scenes(self):
"""Render every scene ONCE at t=0 before the real pass.
Scene functions fail at render time, not definition time, so a NameError
in scene 4 used to surface only after scenes 0-3 had been fully rendered
— and, when the pipe was open, after frames had already gone into the
encoder. Two production workers lost a whole render each to
`RuntimeError: every scene failed`, learning about one broken name per
attempt.
One frame per scene costs almost nothing and reports EVERY broken scene
in a single pass. A scene that fails here is marked and skipped by the
real loop rather than re-run to fail identically; if they ALL fail there
is nothing to encode, so say so now instead of after the setup.
"""
for i, sc in enumerate(self._scenes):
try:
(self._render_pil if sc.mode == "pil" else self._render_mpl)(sc, 0.0)
except Exception: # noqa: BLE001
sc.error = traceback.format_exc(limit=6)
print(f"[gifsmith] SCENE {i} ({sc.title!r}) FAILED its t=0 dry "
f"run — skipped, other scenes continue:\n{sc.error}",
file=sys.stderr, flush=True)
broken = [i for i, sc in enumerate(self._scenes) if sc.error]
if broken and len(broken) == len(self._scenes):
raise RuntimeError(
"every scene failed before rendering started — see the "
f"{len(broken)} traceback(s) above. They usually share ONE "
"cause: a helper called with a keyword it does not take, or a "
"name that differs by a character. Fix it and re-run the whole "
"program in a fresh code_exec call, remembering gifsmith.py in "
"files_in. Nothing was encoded and no GPU time was spent.")
return broken
def render(self, long_edge=None, force=None, audio=None):
if not self._scenes:
raise RuntimeError("no scenes registered — decorate at least one "
"function with @anim.scene(...)")
# Before ANY setup: no scratch dir, no ffmpeg pipe, no frames.
self._dry_run_scenes()
self._scratch, free_mb = _pick_scratch()
long_edge = long_edge or max(self.width, self.height)
@@ -241,20 +338,33 @@ class Animation:
print(f"[gifsmith] {len(self._scenes)} scene(s), {total_s:.1f}s at "
f"{self.fps}fps, canvas {self.width}x{self.height}", flush=True)
# Tile budget for the contact sheet, spread across the scenes. One scene
# gets the whole budget in TIME, which is the case that was broken: a
# loop's interesting content is by construction not at any single
# instant.
per_scene = max(1, CONTACT_SHEET_MAX_TILES // len(self._scenes))
for i, sc in enumerate(self._scenes):
if sc.error:
continue # already reported by the dry run; don't fail it twice
start = self._count
n = max(1, int(round(sc.seconds * self.fps)))
try:
want = self._sample_frames(n, per_scene)
for k in range(n):
t = k / max(n - 1, 1)
img = (self._render_pil if sc.mode == "pil" else self._render_mpl)(sc, t)
if sc.first_frame is None and k >= n // 2:
sc.first_frame = img.copy()
if k in want:
sc.samples.append((t, img.resize(
(CONTACT_TILE_W, self._tile_h()), Image.LANCZOS)))
self._emit(img)
for _ in range(int(round(sc.hold * self.fps))):
self._emit(img)
except Exception: # noqa: BLE001
sc.error = traceback.format_exc(limit=6)
# Its partial frames are dropped below; its samples must go too,
# or the sheet advertises a scene that never shipped.
sc.samples = []
if not self._streaming:
# Drop this scene's partial frames so it can't ship half-drawn.
# (Streamed frames are already in the encoder — a broken scene
@@ -292,15 +402,19 @@ class Animation:
os.remove(leftover)
shutil.rmtree(self._scratch, ignore_errors=True)
raise
self._contact_sheet()
sheet_tiles = self._contact_sheet() or 0
broken = [f"{i}:{s.title!r}" for i, s in enumerate(self._scenes) if s.error]
print(f"[gifsmith] {self._count} frames, scratch "
+ ("streamed (0 MiB on disk)" if self._streaming
else f"peak {self._peak_mb:.1f} MiB"))
print(f"[gifsmith] scene errors: {', '.join(broken) if broken else 'none'}")
print(f"[gifsmith] ART {art}")
print("[gifsmith] still: /workspace/still.png (contact sheet — call "
"image_describe on ITS file_id from files_out)")
ts = ", ".join(f"{t:.2f}" for sc in self._scenes for (t, _th) in sc.samples)
print(f"[gifsmith] still: /workspace/still.png — {sheet_tiles} frames "
f"sampled across the animation at t={ts} (each tile is labelled "
"with its t). Call image_describe on ITS file_id from files_out; "
"if something is missing from one tile, check whether it is "
"present in another before re-rendering.")
shutil.rmtree(self._scratch, ignore_errors=True)
return art
@@ -411,25 +525,64 @@ class Animation:
# ------------------------------------------------------------- critique aid
def _tile_h(self):
return max(1, round(self.height * CONTACT_TILE_W / self.width))
@staticmethod
def _sample_frames(n, count):
"""Frame indices to keep for the contact sheet, spread evenly over the
scene: t = 0, 1/count, ... (count-1)/count.
A scene with very few frames yields fewer samples than asked for, since
distinct t values collide onto the same frame index; the sheet simply
has fewer tiles, which is the honest outcome.
Deliberately NOT ending at t=1.0. A loop is built to return to its
starting state, so its last frame is the one instant guaranteed to show
none of the motion — which is exactly how a worker spent three
re-renders chasing a tear its critic could not see, because the still
was the frame after the tear had faded."""
if n <= 1:
return {0}
count = max(1, min(count, n))
return {min(n - 1, round(j / count * (n - 1))) for j in range(count)}
def _contact_sheet(self, path="/workspace/still.png"):
tiles = [(i, s) for i, s in enumerate(self._scenes) if s.first_frame is not None]
"""A grid sampled across TIME, one labelled tile per sample.
It used to be one frame per SCENE, and a single-scene animation — the
common case — short-circuited to a bare frame save. Every single-scene
worker in two production runs told us so unprompted, in the words of
the vision model: "this is a single frame (not a contact sheet)". The
critique loop was being fed one time point out of ~84 and asked to
judge motion.
"""
tiles = [(i, sc, t, thumb)
for i, sc in enumerate(self._scenes)
for (t, thumb) in sc.samples]
if not tiles:
return
if len(tiles) == 1:
tiles[0][1].first_frame.save(path)
return
cols = min(3, len(tiles))
rows = math.ceil(len(tiles) / cols)
tw = 300
th = max(1, round(self.height * tw / self.width))
tw, th = CONTACT_TILE_W, self._tile_h()
sheet = Image.new("RGB", (cols * tw, rows * (th + 20)), (20, 20, 24))
d = ImageDraw.Draw(sheet)
f = self.font(14)
for k, (i, sc) in enumerate(tiles):
multi = len(self._scenes) > 1
for k, (i, sc, t, thumb) in enumerate(tiles):
x, y = (k % cols) * tw, (k // cols) * (th + 20)
sheet.paste(sc.first_frame.resize((tw, th), Image.LANCZOS), (x, y + 20))
d.text((x + 4, y + 3), f"scene {i}: {sc.title[:38]}", fill=(235, 235, 240), font=f)
sheet.paste(thumb, (x, y + 20))
# The t label is the point: it tells the critic WHEN it is looking,
# so "the tear is missing" can be read as "missing at t=0.75"
# rather than as a fault in the drawing.
label = f"t={t:.2f}"
if multi:
label = f"scene {i} {label}: {sc.title[:26]}"
elif sc.title:
label = f"{label} {sc.title[:30]}"
d.text((x + 4, y + 3), label, fill=(235, 235, 240), font=f)
sheet.save(path)
return len(tiles)
def _run(cmd):