add time estimation for image gen

allow selection between portrait, landscape, square canvas types
Various test fixes
2026-08-17 12:29:26 -04:00 · 2026-08-17 12:19:31 -04:00 · 2026-08-17 11:35:40 -04:00
13 changed files with 648 additions and 41 deletions
@@ -0,0 +1,36 @@
+# AGENTS.md
+
+Single Python package `vibe_bot`: a Discord bot (discord.py, `!` prefix) with SQLite RAG chat history, Kokoro TTS, and image gen/edit via OpenAI-compatible APIs. Python 3.13, managed with uv. Everything lives in `vibe_bot/`.
+
+## Commands
+
+- Setup: `uv sync --extra dev` — plain `uv sync` already installs the `dev` dependency group (ruff, pyright); the `dev` extra adds black/debugpy/mypy
+- Run bot: `uv run python -m vibe_bot.main` — this logs the real bot into Discord with the token from `.env`; don't run it as a smoke test
+- Tests: `uv run pytest vibe_bot/tests/ -v`; single test: `uv run pytest vibe_bot/tests/test_main.py::test_name`
+- Checks: `uv run ruff check vibe_bot/`, `uv run mypy vibe_bot/` (strict), `uv run pyright vibe_bot/` (strict), `uv run black --check vibe_bot/`
+- Container: `./build.sh` (podman). CI (`.gitea/workflows/build-push.yml`, Gitea) only builds/pushes the image on main/release — lint and tests are not gated; run them locally
+
+## Setup requirements
+
+- A repo-root `.env` is required even to run tests: `config.py` calls `load_dotenv()` and raises `RuntimeError` at import time if any required var is missing. Placeholder values suffice for the mocked suite. Never commit it.
+- PortAudio is a required system library (kokoro-tts → sounddevice). Without it, ~60 tests in `test_main`/`test_tts` error at import time. On this host: `sudo dnf install portaudio` (the Containerfile installs `portaudio19-dev`).
+- TTS needs `kokoro-v1.0.onnx` and `voices-v1.0.bin` in the repo root (baked into the container image). The bot runs without them; only `!speak` degrades.
+
+## Test suite gotchas
+
+- Baseline: everything passes except `test_llama_wrapper.py::test_chat_completion_think` and `::test_chat_completion_instruct`. Those two are unmocked live calls to the real `CHAT_ENDPOINT` from `.env` and fail without network access to that API.
+- `test_config.py` hardcodes `sys.path.insert(0, "/var/home/ducoterra/Projects/vibe_discord_bots")` (a stale repo path). The test only passes because pytest's cwd fallback finds the package — run tests from the repo root.
+- If `uv run <tool>` suddenly fails with `ModuleNotFoundError` or "bad interpreter", the `.venv` shebangs are stale from a repo move: `rm -rf .venv && uv sync --extra dev`.
+
+## Code map
+
+- `main.py` — entrypoint. The bot is created at module import (module-level `commands.Bot(...)`), `bot.run()` only under `__main__`. Custom-bot "commands" (`!<bot_name> ...`) are matched in `on_message` against the database, not registered with `bot.command`.
+- `config.py` — env loading + import-time validation, voice catalog.
+- `database.py` — `ChatDatabase` (embeddings stored as float32 blobs, cosine-similarity RAG, schema auto-migrates on startup) and `CustomBotManager`.
+- `llama_wrapper.py` — thin OpenAI-compatible clients for chat / image gen / image edit / embeddings, each with its own endpoint, key, and model.
+- `tools.py` — `get_channel_members` is a no-op LangChain `@tool` stub used only for name/description/schema; the real implementation is `get_channel_members_impl(channel)`, wired into the tool executor in `main.py`.
+
+## Style
+
+- All four checks (ruff, mypy strict, pyright strict, black) are declared gates and currently pass; keep new code clean under all of them.
+- ruff is a dev dependency (installed via `uv add --dev`) with config in `pyproject.toml`; it runs with the default ruleset of the locked version.
@@ -123,6 +123,9 @@ IMAGE_GEN_ENDPOINT_KEY=your_api_key
 IMAGE_EDIT_ENDPOINT_KEY=your_api_key
 IMAGE_GEN_MODEL=gen
 IMAGE_EDIT_MODEL=edit
+IMAGE_GEN_SIZE_SQUARE=1024x1024
+IMAGE_GEN_SIZE_PORTRAIT=1024x1536
+IMAGE_GEN_SIZE_LANDSCAPE=1536x1024

 # Embedding API (required)
 EMBEDDING_ENDPOINT=https://your-api.com/v1
@@ -269,6 +272,9 @@ uv run black --check vibe_bot/
 | `CHAT_MODEL`            | *(required)*       | Model name for chat completions       |
 | `IMAGE_GEN_ENDPOINT`    | *(required)*       | Image generation API URL              |
 | `IMAGE_EDIT_ENDPOINT`   | *(required)*       | Image editing API URL                 |
+| `IMAGE_GEN_SIZE_SQUARE`   | `1024x1024`        | Square canvas size for image generation     |
+| `IMAGE_GEN_SIZE_PORTRAIT` | `1024x1536`        | Portrait (tall) canvas size for image generation |
+| `IMAGE_GEN_SIZE_LANDSCAPE`| `1536x1024`        | Landscape (wide) canvas size for image generation |
 | `EMBEDDING_ENDPOINT`    | *(required)*       | Embedding API URL                     |
 | `EMBEDDING_MODEL`       | *(required)*       | Model name for text embeddings        |
 | `MAX_COMPLETION_TOKENS` | `1000`             | Max tokens in LLM responses           |
@@ -21,7 +21,6 @@ dependencies = [

 [project.optional-dependencies]
 dev = [
-    "pyright>=1.1.398",
    "mypy>=1.17.0",
    "black>=25.1.0",
    "debugpy>=1.8.0",
@@ -56,7 +55,17 @@ reportPrivateUsage = false
 line-length = 88
 target-version = ["py313"]

+[tool.ruff]
+line-length = 88
+target-version = "py313"
+
 [tool.pytest.ini_options]
 filterwarnings = [
    "ignore::pytest.PytestUnraisableExceptionWarning",
 ]
+
+[dependency-groups]
+dev = [
+    "pyright>=1.1.409",
+    "ruff>=0.16.3",
+]
@@ -2015,6 +2015,31 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d0/02/fa464cdfbe6b26e0600b62c528b72d8608f5cc49f96b8d6e38c95d60c676/rpds_py-0.30.0-cp314-cp314t-win_amd64.whl", hash = "sha256:27f4b0e92de5bfbc6f86e43959e6edd1425c33b5e69aab0984a72047f2bcf1e3", size = 226532, upload-time = "2025-11-30T20:24:14.634Z" },
 ]

+[[package]]
+name = "ruff"
+version = "0.16.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/61/b3/3213589383f8f1b3938781bd1278713f6d18621a14992b3e81fefb8a5ef9/ruff-0.16.3.tar.gz", hash = "sha256:e76d33a347661a84b5be6d043d0347fdc745dfdcf825a8f4fed64b5e26eebdf2", size = 4891904, upload-time = "2026-08-13T15:17:13.381Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/bf/96/493770daebd68c0a67f1549fdf519f53be51fc435186c0585bcc272fd76c/ruff-0.16.3-py3-none-linux_armv6l.whl", hash = "sha256:0c5710e247a58a4521e66e124ba9a74655b414f61ba3a2e9e3811e11098f48f7", size = 10902799, upload-time = "2026-08-13T15:16:27.382Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/e6/2becf3942fddc29a29b8df47691d456fb1085391a694f74d84513251418c/ruff-0.16.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:fe155130631a2471fd2e14a7a664a4dfbd7194b8229c3d7b2a40b21178639081", size = 11135539, upload-time = "2026-08-13T15:16:30.87Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/1e/4b8b72f0d006dbf19326aa99f9ca0ee2ff374187c4d301cf529a51aa06fe/ruff-0.16.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e2ed719e14aa64d895c2ee922594a90a43c861a93f0575a95ff8c47cdbd13eb9", size = 10475095, upload-time = "2026-08-13T15:16:33.259Z" },
+    { url = "https://files.pythonhosted.org/packages/92/32/2201fa49ba1f6c101ee321e83f051ac7a4b8d07b0ef6b4d3f2772b302275/ruff-0.16.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9e0b1da805eb043654645d74d5de1e5ce2edc686e40790d2b86f56d71cc06a84", size = 10668771, upload-time = "2026-08-13T15:16:35.65Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/66/4afc5c8363bd04d45effce1b7c8713ca037d7a6740b7451a2403a6e3a972/ruff-0.16.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a37bdea0bbe21780f590bf437d6412c8c4e1b6cd010f91a65c2c40c5e5f5f870", size = 10699568, upload-time = "2026-08-13T15:16:38.195Z" },
+    { url = "https://files.pythonhosted.org/packages/53/fd/c67d246bf36bf1698551c56de39e95cd07f70e64433e0098e6267d77061b/ruff-0.16.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:09571e6d1288ed9be475207a3ac04ada404f1cd898104be0f6ab8d7df438575b", size = 11499365, upload-time = "2026-08-13T15:16:40.623Z" },
+    { url = "https://files.pythonhosted.org/packages/67/0b/00ecbceb99a263af7b12f6f05ac3c92bc47b905e91adc3f207a836e3bc01/ruff-0.16.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2c18c5a101eb540010638cc1ff3c84944d3adb3df62b8d98ca8f22ba484d3413", size = 12311728, upload-time = "2026-08-13T15:16:43.564Z" },
+    { url = "https://files.pythonhosted.org/packages/54/b2/b7b3bb54f4d3f7db504e476ad4ab8de530dceebe2c061384b2757ee419e8/ruff-0.16.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8457c44f15033c85ddbb77b15d451df9e24e4bd03b628396dd3610cedc3b8f82", size = 11699896, upload-time = "2026-08-13T15:16:46.209Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/30/4c468429ac195addc5ee1b717b6ab1b66632786737ca3b2ed3443fb0c26a/ruff-0.16.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:294b95c4ae0cda9388525c2047778aa758d6b8d4bb876fd4e9eaa3ebc92343eb", size = 11058736, upload-time = "2026-08-13T15:16:48.823Z" },
+    { url = "https://files.pythonhosted.org/packages/43/67/7a113cdaddf24b64d7f75b1242a99d04c82fcef4f6921fdbb832beaffb5f/ruff-0.16.3-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:3d0c7c40c87c2a820509c31ba007968da6e1306468c067b2d82fbfdbcd0e8474", size = 11586911, upload-time = "2026-08-13T15:16:51.913Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/c1/2e66f24c0f3ead25a5e660111778685e505e5da353c82802bf49f0cbe7b9/ruff-0.16.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:9f738c0fdfa8eed0b2ce7fb27ee7258208a92a68d7949e62aa15164bc7b389da", size = 10954265, upload-time = "2026-08-13T15:16:54.763Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/ba/4cee23bf52cba9a058d3726de623624daf50ef9638868edd86f4126157f6/ruff-0.16.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:fb785f0be25abe69d320415cd4f833b59e17ba7613d9ba6a958023b6bceb0a50", size = 10709886, upload-time = "2026-08-13T15:16:57.339Z" },
+    { url = "https://files.pythonhosted.org/packages/82/df/7da7194fa5d9dc0a285f7e6fa5a4722e7c63faac0b45b614ded9314363a1/ruff-0.16.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:c5536e3acfbf9563085aa2be7b13c629c3077e902afc5b941ac44024dbb9f506", size = 11210392, upload-time = "2026-08-13T15:17:00.171Z" },
+    { url = "https://files.pythonhosted.org/packages/35/85/7795f6e817af050e7517bf3e7aa9b061cce70ef33d280aad902c956c1ecf/ruff-0.16.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a2d85c02f9b8e165d85e6779184d38c4132de12603dab59c51c28e22584f9e4d", size = 11626910, upload-time = "2026-08-13T15:17:03.299Z" },
+    { url = "https://files.pythonhosted.org/packages/78/9b/475b927cf27a5cbbda3c7bafb69ed6ff77e1d7923d5d85f17c2749d7ae32/ruff-0.16.3-py3-none-win32.whl", hash = "sha256:388cdf2166642bd9b13d52b5932d3170f34f8abed7e8d9a855f1d84b83645a0a", size = 10931415, upload-time = "2026-08-13T15:17:05.726Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/99/e2a2bfc4fbf0a1e8a916bc9ebe6fe6c58cc34c28e0ffc6ce281d572d1c2e/ruff-0.16.3-py3-none-win_amd64.whl", hash = "sha256:e80a7d69ca2a6d1c4d352ec91458cdca6e56c83cdbcabd93e4abe1e53591d948", size = 11445993, upload-time = "2026-08-13T15:17:08.353Z" },
+    { url = "https://files.pythonhosted.org/packages/69/3e/4132e539aed78c148854d4997a2685b0ed4dc4e87110b59ce528564e184e/ruff-0.16.3-py3-none-win_arm64.whl", hash = "sha256:b8ca152da82c1acc1fa8d5874b15951935f0eef46f10e6954c83859011b6178a", size = 11399302, upload-time = "2026-08-13T15:17:10.908Z" },
+]
+
 [[package]]
 name = "scikit-learn"
 version = "1.8.0"
@@ -2461,7 +2486,12 @@ dev = [
    { name = "black" },
    { name = "debugpy" },
    { name = "mypy" },
+]
+
+[package.dev-dependencies]
+dev = [
    { name = "pyright" },
+    { name = "ruff" },
 ]

 [package.metadata]
@@ -2476,7 +2506,6 @@ requires-dist = [
    { name = "mypy", marker = "extra == 'dev'", specifier = ">=1.17.0" },
    { name = "numpy", specifier = ">=1.24.0" },
    { name = "openai", specifier = ">=2.24.0" },
-    { name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.398" },
    { name = "pytest", specifier = ">=9.0.2" },
    { name = "pytest-env", specifier = ">=1.5.0" },
    { name = "python-dotenv", specifier = ">=1.2.2" },
@@ -2485,6 +2514,12 @@ requires-dist = [
 ]
 provides-extras = ["dev"]

+[package.metadata.requires-dev]
+dev = [
+    { name = "pyright", specifier = ">=1.1.409" },
+    { name = "ruff", specifier = ">=0.16.3" },
+]
+
 [[package]]
 name = "xxhash"
 version = "3.7.0"
@@ -38,7 +38,9 @@ EMBEDDING_ENDPOINT_KEY: str = os.getenv("EMBEDDING_ENDPOINT_KEY", "placeholder")
 CHAT_MODEL: str = os.getenv("CHAT_MODEL", "")
 COMPLETION_MODEL: str = os.getenv("COMPLETION_MODEL", "")
 IMAGE_GEN_MODEL: str = os.getenv("IMAGE_GEN_MODEL", "")
-IMAGE_GEN_SIZE: str = os.getenv("IMAGE_GEN_SIZE", "1024x1024")
+IMAGE_GEN_SIZE_SQUARE: str = os.getenv("IMAGE_GEN_SIZE_SQUARE", "1024x1024")
+IMAGE_GEN_SIZE_PORTRAIT: str = os.getenv("IMAGE_GEN_SIZE_PORTRAIT", "1024x1536")
+IMAGE_GEN_SIZE_LANDSCAPE: str = os.getenv("IMAGE_GEN_SIZE_LANDSCAPE", "1536x1024")
 IMAGE_EDIT_MODEL: str = os.getenv("IMAGE_EDIT_MODEL", "")
 EMBEDDING_MODEL: str = os.getenv("EMBEDDING_MODEL", "")

@@ -30,6 +30,11 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)

+# Moving-average window (most recent generations) for the time estimate.
+IMAGE_GEN_TIME_WINDOW = 10
+# Maximum number of generation times retained in the database.
+IMAGE_GEN_TIME_LIMIT = 100
+

 class ChatDatabase:
    """SQLite database with RAG support for storing chat history
@@ -118,6 +123,19 @@ class ChatDatabase:
        )
        logger.info("idx_user_id index created successfully")

+        # Create image generation timing table
+        logger.info("Creating image_generation_times table if not exists")
+        cursor.execute(
+            """
+            CREATE TABLE IF NOT EXISTS image_generation_times (
+                id INTEGER PRIMARY KEY AUTOINCREMENT,
+                duration_seconds REAL NOT NULL,
+                generated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+            )
+        """,
+        )
+        logger.info("image_generation_times table initialized successfully")
+
        conn.commit()
        logger.info("Database initialization completed successfully")
        conn.close()
@@ -497,6 +515,85 @@ class ChatDatabase:
        conn.commit()
        conn.close()

+    def record_image_generation_time(self, duration_seconds: float) -> bool:
+        """Record how long an image generation took.
+
+        Args:
+            duration_seconds: Wall-clock seconds the generation took.
+
+        """
+        logger.info("Recording image generation time: %.2fs", duration_seconds)
+        conn = sqlite3.connect(self.db_path)
+        cursor = conn.cursor()
+
+        try:
+            cursor.execute(
+                """
+                INSERT INTO image_generation_times (duration_seconds)
+                VALUES (?)
+            """,
+                (duration_seconds,),
+            )
+
+            # Cap the table so it doesn't grow unbounded.
+            cursor.execute(
+                """
+                DELETE FROM image_generation_times
+                WHERE id NOT IN (
+                    SELECT id FROM image_generation_times
+                    ORDER BY id DESC
+                    LIMIT ?
+                )
+            """,
+                (IMAGE_GEN_TIME_LIMIT,),
+            )
+
+            conn.commit()
+        except Exception:
+            logger.exception("Error recording image generation time")
+            conn.rollback()
+            return False
+        else:
+            return True
+        finally:
+            conn.close()
+
+    def get_image_generation_time_estimate(self) -> float | None:
+        """Get a moving-average estimate of image generation time.
+
+        Returns:
+            The average duration in seconds over the most recent generations,
+            or None if there is no generation history yet.
+
+        """
+        logger.debug("Computing moving-average image generation time estimate")
+        conn = sqlite3.connect(self.db_path)
+        cursor = conn.cursor()
+
+        try:
+            cursor.execute(
+                """
+                SELECT AVG(duration_seconds)
+                FROM (
+                    SELECT duration_seconds
+                    FROM image_generation_times
+                    ORDER BY id DESC
+                    LIMIT ?
+                )
+            """,
+                (IMAGE_GEN_TIME_WINDOW,),
+            )
+            row = cursor.fetchone()
+        except Exception:
+            logger.exception("Error reading image generation times")
+            return None
+        finally:
+            conn.close()
+
+        if row is None or row[0] is None:
+            return None
+        return float(row[0])
+

 # Global database instance
 _chat_db: ChatDatabase | None = None
@@ -504,7 +601,7 @@ _chat_db: ChatDatabase | None = None

 def get_database() -> ChatDatabase:
    """Get or create the global database instance."""
-    global _chat_db  # noqa: PLW0603
+    global _chat_db
    if _chat_db is None:
        _chat_db = ChatDatabase()
    return _chat_db
@@ -7,7 +7,8 @@ Allows custom endpoints for each of the above supported functions.
 from __future__ import annotations

 import json
-from typing import TYPE_CHECKING, Awaitable, Callable, cast
+from collections.abc import Awaitable, Callable
+from typing import TYPE_CHECKING, cast

 import openai
 import requests
@@ -4,6 +4,8 @@ from __future__ import annotations

 import base64
 import logging
+import re
+import time
 from io import BytesIO
 from typing import TYPE_CHECKING

@@ -13,7 +15,6 @@ from discord import Message
 from discord.ext import commands

 from vibe_bot import llama_wrapper, tts
-from vibe_bot.tts import DEFAULT_LANG
 from vibe_bot.config import (
    CHAT_ENDPOINT,
    CHAT_ENDPOINT_KEY,
@@ -25,7 +26,9 @@ from vibe_bot.config import (
    IMAGE_GEN_ENDPOINT,
    IMAGE_GEN_ENDPOINT_KEY,
    IMAGE_GEN_MODEL,
-    IMAGE_GEN_SIZE,
+    IMAGE_GEN_SIZE_LANDSCAPE,
+    IMAGE_GEN_SIZE_PORTRAIT,
+    IMAGE_GEN_SIZE_SQUARE,
    MAX_COMPLETION_TOKENS,
    TTS_MODEL_PATH,
    TTS_SPEED,
@@ -35,6 +38,7 @@ from vibe_bot.config import (
 )
 from vibe_bot.database import CustomBotManager, get_database
 from vibe_bot.tools import get_channel_members, get_channel_members_impl
+from vibe_bot.tts import DEFAULT_LANG

 if TYPE_CHECKING:
    from discord.ext.commands import Bot
@@ -102,6 +106,75 @@ MIN_BOT_NAME_LENGTH = 2
 MAX_BOT_NAME_LENGTH = 50
 MIN_PERSONALITY_LENGTH = 10

+# Image layout (canvas orientation) selection for doodlebob.
+DEFAULT_IMAGE_LAYOUT = "square"
+VALID_IMAGE_LAYOUTS = ("portrait", "landscape", "square")
+LAYOUT_SIZES: dict[str, str] = {
+    "portrait": IMAGE_GEN_SIZE_PORTRAIT,
+    "landscape": IMAGE_GEN_SIZE_LANDSCAPE,
+    "square": IMAGE_GEN_SIZE_SQUARE,
+}
+
+IMAGE_LAYOUT_SYSTEM_PROMPT = (
+    "You decide the aspect ratio (layout) of an image that will be generated "
+    "from a user's request. Choose exactly ONE layout from these three options:\n"
+    "- portrait: a tall, vertical image (taller than wide). Use for subjects that "
+    "are taller than they are wide, such as a single standing person or animal, "
+    "a full-body character, a tall building, a skyscraper, a tree, a rocket, or "
+    "any vertical composition.\n"
+    "- landscape: a wide, horizontal image (wider than tall). Use for scenes that "
+    "are wider than they are tall, such as wide landscapes, panoramas, cityscapes, "
+    "seas and horizons, battle or group scenes spread out horizontally, or any "
+    "horizontal composition.\n"
+    "- square: an image that is as wide as it is tall. Use for balanced subjects, "
+    "close-ups, faces, single objects, logos, emblems, or whenever no strong tall "
+    "or wide orientation is implied.\n"
+    "Rules:\n"
+    "- Base your choice ONLY on the orientation the content implies.\n"
+    "- Respond with ONLY the single word portrait, landscape, or square.\n"
+    "- Do NOT include any other text, punctuation, explanation, or reasoning.\n"
+)
+
+
+def parse_image_layout(response: str) -> str:
+    """Parse an LLM response into a valid image layout.
+
+    Args:
+        response: The raw LLM response text.
+
+    Returns:
+        One of "portrait", "landscape", or "square". Falls back to "square"
+        when the response is empty or does not contain a valid layout.
+
+    """
+    text = response.strip().lower()
+    for layout in VALID_IMAGE_LAYOUTS:
+        if re.search(rf"\b{layout}\b", text):
+            return layout
+    return DEFAULT_IMAGE_LAYOUT
+
+
+def select_image_layout(user_message: str) -> str:
+    """Ask the LLM to pick an image layout for the given content.
+
+    Args:
+        user_message: The user's original image request.
+
+    Returns:
+        One of "portrait", "landscape", or "square". Falls back to "square"
+        when the LLM returns an empty or malformed response.
+
+    """
+    response = llama_wrapper.chat_completion_instruct(
+        system_prompt=IMAGE_LAYOUT_SYSTEM_PROMPT,
+        user_prompt=user_message,
+        openai_url=CHAT_ENDPOINT,
+        openai_api_key=CHAT_ENDPOINT_KEY,
+        model=CHAT_MODEL,
+        max_tokens=MAX_COMPLETION_TOKENS,
+    )
+    return parse_image_layout(response)
+

@bot.event
 async def on_ready() -> None:
@@ -713,11 +786,18 @@ async def doodlebob(ctx: CommandsContext[Bot], *, message: str) -> None:
        ctx.author.name,
        message[:100],
    )
-    await ctx.send(f"**Doodlebob erasing {message[:100]}...**")
+    await ctx.send("**Doodlebob shopping for a canvas...**")
+
+    # Let the LLM pick the canvas orientation based on the content.
+    layout = select_image_layout(message)
+    logger.info("Doodlebob selected layout %r for %s", layout, ctx.author.name)
+    await ctx.send(f"**Doodlebob selected {layout}**")

    system_prompt = (
        "Given the following message, convert it to a detailed image generation "
        "prompt that will be passed directly into an image generation model. "
+        f"The final image will use a {layout} canvas, so compose the scene to "
+        f"fit that orientation. "
        "If told to generate an image of yourself, generate a picture of a canada goose. "
        "If told to generate a picture of 'me', 'myself', or some other self "
        "reference, generate a picture of a canada goose. Only respond with a valid image "
@@ -740,25 +820,36 @@ async def doodlebob(ctx: CommandsContext[Bot], *, message: str) -> None:
        return

    # Alert the user we're generating the image
+    db = get_database()
+    estimated_seconds = db.get_image_generation_time_estimate()
    await ctx.send(f"**Doodlebob calling drone strike on {image_prompt[:100]}...**")
+    if estimated_seconds is not None:
+        await ctx.send(f"**Drone ETA: ~{estimated_seconds:.0f} seconds**")

+    start_time = time.monotonic()
    image_b64 = llama_wrapper.image_generation(
        prompt=image_prompt,
        openai_url=IMAGE_GEN_ENDPOINT,
        openai_api_key=IMAGE_GEN_ENDPOINT_KEY,
        model=IMAGE_GEN_MODEL,
-        size=IMAGE_GEN_SIZE,
+        size=LAYOUT_SIZES[layout],
    )
+    elapsed_seconds = time.monotonic() - start_time

    if not image_b64:
        logger.warning("Image generation returned empty response.")
        await ctx.send("Failed to generate image. The server may be busy.")
        return

+    db.record_image_generation_time(elapsed_seconds)
+
    try:
        edited_image_data = BytesIO(base64.b64decode(image_b64))
        send_img = discord.File(edited_image_data, filename="image.png")
        await ctx.send(file=send_img)
+        await ctx.send(
+            f"**Strike complete. Image generated in {elapsed_seconds:.1f} seconds.**",
+        )
    except Exception:
        logger.exception("Failed to decode image data")
        await ctx.send("Failed to process the generated image.")
@@ -771,7 +862,7 @@ async def retcon(ctx: CommandsContext[Bot], *, message: str) -> None:
    for discord_image in ctx.message.attachments:
        image_url = discord_image.url
        try:
-            response = requests.get(image_url, timeout=30)
+            response = requests.get(image_url, timeout=30)  # noqa: ASYNC210
            image_data = response.content
        except requests.RequestException as e:
            logger.warning("Failed to download image from %s: %s", image_url, e)
@@ -103,7 +103,7 @@ def custom_bot_manager(temp_db_path: str) -> CustomBotManager:
    from vibe_bot.database import CustomBotManager

    manager = CustomBotManager(db_path=temp_db_path)
-    return manager  # noqa: RET504
+    return manager


@pytest.fixture
@@ -123,8 +123,8 @@ def mock_kokoro_tts() -> Generator[dict[str, Any]]:
            return_value=mock_kokoro_instance,
        ),
        patch("vibe_bot.tts.chunk_text", mock_chunk),
+        patch("vibe_bot.tts.process_chunk_sequential", mock_process),
    ):
-        with patch("vibe_bot.tts.process_chunk_sequential", mock_process):
        yield {
            "Kokoro": mock_kokoro,
            "chunk_text": mock_chunk,
@@ -148,9 +148,11 @@ def mock_discord() -> Generator[dict[str, MagicMock]]:
    mock_bot_instance.user.name = "test-bot"
    mock_bot_instance.user.id = "123456789"

-    with patch("vibe_bot.main.discord") as mock_discord_module:
-        with patch("vibe_bot.main.commands", MagicMock()):
-            with patch("vibe_bot.main.commands.Bot", mock_bot_class):
+    with (
+        patch("vibe_bot.main.discord") as mock_discord_module,
+        patch("vibe_bot.main.commands", MagicMock()),
+        patch("vibe_bot.main.commands.Bot", mock_bot_class),
+    ):
        mock_bot_class.return_value = mock_bot_instance
        mock_discord_module.Intents = mock_intents
        mock_discord_module.Message = MagicMock
@@ -167,8 +169,10 @@ def mock_tts_engine() -> Generator[MagicMock]:
    """Provide a mock TTSEngine."""
    mock_engine = MagicMock()
    mock_engine.generate_audio.return_value = MagicMock()
-    with patch("vibe_bot.main.tts_engine", mock_engine):
-        with patch("vibe_bot.main.tts.TTSEngine", return_value=mock_engine):
+    with (
+        patch("vibe_bot.main.tts_engine", mock_engine),
+        patch("vibe_bot.main.tts.TTSEngine", return_value=mock_engine),
+    ):
        yield mock_engine


@@ -68,7 +68,7 @@ assert vibe_bot.config.TTS_SPEED == 1.0
 print("OK")
 """

-    result = subprocess.run(  # noqa: PLW1510, S603
+    result = subprocess.run(  # noqa: PLW1510
        [sys.executable, "-c", code],
        capture_output=True,
        text=True,
@@ -99,7 +99,7 @@ except Exception as e:
    print(f"OTHER: {{type(e).__name__}}: {{e}}")
 """

-    result = subprocess.run(  # noqa: PLW1510, S603
+    result = subprocess.run(  # noqa: PLW1510
        [sys.executable, "-c", code],
        capture_output=True,
        text=True,
@@ -194,6 +194,76 @@ def test_clear_all_messages(
    assert len(messages) == 0


+def test_image_generation_time_estimate_empty(chat_db: ChatDatabase) -> None:
+    """Test the estimate is None before any generations are recorded."""
+    assert chat_db.get_image_generation_time_estimate() is None
+
+
+def test_record_and_get_image_generation_time_estimate(
+    chat_db: ChatDatabase,
+) -> None:
+    """Test recorded generation times produce an average estimate."""
+    assert chat_db.record_image_generation_time(10.0) is True
+    assert chat_db.record_image_generation_time(20.0) is True
+
+    estimate = chat_db.get_image_generation_time_estimate()
+    assert estimate == pytest.approx(15.0)
+
+
+def test_image_generation_estimate_uses_recent_window(
+    chat_db: ChatDatabase,
+) -> None:
+    """Test only the most recent window of generations feeds the estimate."""
+    from vibe_bot.database import IMAGE_GEN_TIME_WINDOW
+
+    chat_db.record_image_generation_time(1000.0)
+    for _ in range(IMAGE_GEN_TIME_WINDOW):
+        chat_db.record_image_generation_time(10.0)
+
+    estimate = chat_db.get_image_generation_time_estimate()
+    assert estimate == pytest.approx(10.0)
+
+
+def test_image_generation_times_capped(chat_db: ChatDatabase) -> None:
+    """Test the generation time table keeps only the most recent entries."""
+    import sqlite3
+
+    from vibe_bot.database import IMAGE_GEN_TIME_LIMIT
+
+    total = IMAGE_GEN_TIME_LIMIT + 5
+    for i in range(total):
+        chat_db.record_image_generation_time(float(i))
+
+    conn = sqlite3.connect(chat_db.db_path)
+    cursor = conn.cursor()
+    cursor.execute("SELECT COUNT(*) FROM image_generation_times")
+    count = cursor.fetchone()[0]
+    cursor.execute("SELECT MIN(id) FROM image_generation_times")
+    min_id = cursor.fetchone()[0]
+    cursor.execute("SELECT MAX(id) FROM image_generation_times")
+    max_id = cursor.fetchone()[0]
+    conn.close()
+
+    assert count == IMAGE_GEN_TIME_LIMIT
+    assert min_id == 6
+    assert max_id == total
+
+
+def test_image_generation_estimate_after_capping(
+    chat_db: ChatDatabase,
+) -> None:
+    """Test the estimate is computed from the retained recent rows."""
+    from vibe_bot.database import IMAGE_GEN_TIME_LIMIT
+
+    total = IMAGE_GEN_TIME_LIMIT + 5
+    for i in range(total):
+        chat_db.record_image_generation_time(float(i))
+
+    # Rows 95.0 through 104.0 are the ten most recent retained generations.
+    estimate = chat_db.get_image_generation_time_estimate()
+    assert estimate == pytest.approx(99.5)
+
+
 def test_get_user_history(
    chat_db: ChatDatabase,
    mock_embedding: MagicMock,
@@ -484,3 +554,4 @@ def test_database_init_creates_tables(temp_db_path: str) -> None:
    assert "chat_messages" in tables
    assert "message_embeddings" in tables
    assert "custom_bots" in tables
+    assert "image_generation_times" in tables
@@ -2,6 +2,7 @@

 from __future__ import annotations

+from datetime import UTC
 from unittest.mock import AsyncMock, MagicMock, patch

 import pytest
@@ -44,8 +45,8 @@ def mock_ctx_with_member() -> MagicMock:
    ctx.author.activities = [mock_activity]
    from datetime import datetime

-    ctx.author.joined_at = datetime(2024, 1, 15)
-    ctx.author.created_at = datetime(2023, 6, 1)
+    ctx.author.joined_at = datetime(2024, 1, 15, tzinfo=UTC)
+    ctx.author.created_at = datetime(2023, 6, 1, tzinfo=UTC)
    ctx.channel.id = "channel-1"
    ctx.guild.id = "guild-1"
    ctx.message.id = "msg-1"
@@ -481,7 +482,6 @@ def test_speak_plain_with_mock_tts(
    asyncio.run(main_module._speak_plain(mock_ctx, "hello world", mock_tts_engine))

    from vibe_bot.config import TTS_SPEED, TTS_VOICE
-
    from vibe_bot.tts import DEFAULT_LANG

    mock_tts_engine.generate_audio.assert_called_once_with(
@@ -961,3 +961,254 @@ def test_debug_tools(mock_ctx: MagicMock) -> None:
    assert "LLM Tools" in call_args
    assert "get_channel_members" in call_args
    assert "members" in call_args.lower()
+
+
+# ---------------------------------------------------------------------------
+# Image layout selection (doodlebob)
+# ---------------------------------------------------------------------------
+
+LAYOUT_TEST_SIZES = {
+    "portrait": "1024x1536",
+    "landscape": "1536x1024",
+    "square": "1024x1024",
+}
+
+
+def _sent_texts(mock_ctx: MagicMock) -> list[str]:
+    """Collect positional (text) arguments sent via ctx.send."""
+    return [c.args[0] for c in mock_ctx.send.call_args_list if c.args]
+
+
+@pytest.mark.parametrize(
+    ("response", "expected"),
+    [
+        ("portrait", "portrait"),
+        ("landscape", "landscape"),
+        ("square", "square"),
+        ("  Portrait  ", "portrait"),
+        ("LANDSCAPE", "landscape"),
+        ("square.", "square"),
+        ("I would use portrait.", "portrait"),
+        ("This scene is best as landscape.", "landscape"),
+        ("A square composition works here.", "square"),
+    ],
+)
+def test_parse_image_layout_valid(response: str, expected: str) -> None:
+    """Test that valid LLM layout responses parse to the right layout."""
+    import vibe_bot.main as main_module
+
+    assert main_module.parse_image_layout(response) == expected
+
+
+@pytest.mark.parametrize(
+    "response",
+    [
+        "",
+        "   ",
+        "banana",
+        "1024x1024",
+        "tall and wide",
+        "squareness",  # word boundary should prevent a match on "square"
+    ],
+)
+def test_parse_image_layout_defaults_to_square(response: str) -> None:
+    """Test that empty or malformed responses fall back to square."""
+    import vibe_bot.main as main_module
+
+    assert main_module.parse_image_layout(response) == "square"
+
+
+def test_doodlebob_selects_portrait(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """Test doodlebob picks portrait and passes the portrait size."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "portrait",  # layout selection
+        "a tall portrait of a lighthouse",  # prompt rewrite
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = None
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a tall lighthouse"))
+
+    # Layout selection is the first instruct call, using the layout prompt.
+    layout_call = mock_llama_wrapper.chat_completion_instruct.call_args_list[0]
+    assert layout_call.kwargs["system_prompt"] == main_module.IMAGE_LAYOUT_SYSTEM_PROMPT
+    assert layout_call.kwargs["user_prompt"] == "a tall lighthouse"
+
+    mock_llama_wrapper.image_generation.assert_called_once()
+    assert mock_llama_wrapper.image_generation.call_args.kwargs["size"] == "1024x1536"
+
+    sent = _sent_texts(mock_ctx)
+    assert any("shopping for a canvas" in m for m in sent)
+    assert any("selected portrait" in m for m in sent)
+    assert any("drone strike" in m for m in sent)
+
+
+def test_doodlebob_selects_landscape(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """Test doodlebob picks landscape and passes the landscape size."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "landscape",
+        "a wide panoramic coastline",
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = None
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="wide coastline"))
+
+    assert mock_llama_wrapper.image_generation.call_args.kwargs["size"] == "1536x1024"
+
+
+def test_doodlebob_malformed_layout_defaults_square(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """Test a malformed layout response falls back to the square size."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "banana",  # malformed layout
+        "a balanced composition",
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = None
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a logo"))
+
+    assert mock_llama_wrapper.image_generation.call_args.kwargs["size"] == "1024x1024"
+    sent = _sent_texts(mock_ctx)
+    assert any("selected square" in m for m in sent)
+
+
+def test_doodlebob_empty_layout_defaults_square(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """Test an empty layout response (LLM failure) falls back to square."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "",  # empty layout response
+        "a balanced composition",
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = None
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a logo"))
+
+    assert mock_llama_wrapper.image_generation.call_args.kwargs["size"] == "1024x1024"
+
+
+def test_doodlebob_reports_estimate_and_elapsed(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """Doodlebob posts an ETA from history and the final elapsed time."""
+    import asyncio
+    import re
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "square",
+        "a test scene",
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = 12.34
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a scene"))
+
+    mock_database.record_image_generation_time.assert_called_once()
+    recorded = mock_database.record_image_generation_time.call_args[0][0]
+    assert isinstance(recorded, float)
+    assert recorded >= 0.0
+
+    sent = _sent_texts(mock_ctx)
+    assert any("drone strike" in m for m in sent)
+    assert any("~12 seconds" in m for m in sent)
+    assert any(re.search(r"generated in \d+\.\d+ seconds", m) for m in sent)
+
+
+def test_doodlebob_no_estimate_without_history(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """No ETA is posted when there is no generation history yet."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "square",
+        "a test scene",
+    ]
+    mock_llama_wrapper.image_generation.return_value = "aW1hZ2U="
+    mock_database.get_image_generation_time_estimate.return_value = None
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a scene"))
+
+    sent = _sent_texts(mock_ctx)
+    assert any("drone strike" in m for m in sent)
+    assert not any("ETA" in m for m in sent)
+    mock_database.record_image_generation_time.assert_called_once()
+
+
+def test_doodlebob_failed_generation_not_recorded(
+    mock_ctx: MagicMock,
+    mock_llama_wrapper: MagicMock,
+    mock_base64: MagicMock,
+    mock_database: MagicMock,
+) -> None:
+    """A failed generation records no time and reports no elapsed seconds."""
+    import asyncio
+
+    import vibe_bot.main as main_module
+
+    mock_llama_wrapper.chat_completion_instruct.side_effect = [
+        "square",
+        "a test scene",
+    ]
+    mock_llama_wrapper.image_generation.return_value = ""
+    mock_database.get_image_generation_time_estimate.return_value = 8.0
+
+    with patch.object(main_module, "LAYOUT_SIZES", LAYOUT_TEST_SIZES):
+        asyncio.run(main_module.doodlebob(mock_ctx, message="a scene"))
+
+    mock_database.record_image_generation_time.assert_not_called()
+    sent = _sent_texts(mock_ctx)
+    assert any("Failed to generate image" in m for m in sent)
+    assert not any("generated in" in m for m in sent)
@@ -8,6 +8,10 @@ import numpy as np
 import pytest


+class ChunkProcessingError(Exception):
+    """Simulates a chunk processing failure in the fake Kokoro processor."""
+
+
 def test_tts_engine_init(mock_kokoro_tts: MagicMock) -> None:
    """Test TTSEngine initialization."""
    from vibe_bot.tts import TTSEngine
@@ -91,7 +95,7 @@ def test_generate_audio_chunk_failure(mock_kokoro_tts: MagicMock) -> None:
        lang: str,
    ) -> tuple[np.ndarray, int]:
        if chunk == "bad chunk":
-            raise Exception("processing error")
+            raise ChunkProcessingError("processing error")
        return np.array([0.1, 0.2], dtype=np.float32), 24000

    mock_kokoro_tts["chunk_text"].return_value = [
Author	SHA1	Message	Date
ducoterra	b740d00b5d	add time estimation for image gen Build and Push Container / build-and-push (push) Successful in 1m11s Details	2026-08-17 12:29:26 -04:00
ducoterra	a73a10fdb6	allow selection between portrait, landscape, square canvas types	2026-08-17 12:19:31 -04:00
ducoterra	5518f07234	Various test fixes	2026-08-17 11:35:40 -04:00