bump version to 1.0.5

.dockerignore

@@ -24,8 +24,13 @@
 **/secrets.dev.yaml
 **/values.dev.yaml
 *.db
-.python-version
 LICENSE
 README.md
 data/
 cert/
+nginx-certs/
+nginx-vhost.d/
+nginx-html/
+nginx-acme/
+**/target/
+.idea/

.gitattributes

@@ -0,0 +1,2 @@
+# Shell scripts must stay LF: CRLF breaks the shebang inside containers.
+*.sh text eol=lf

.github/workflows/docker.yml

@@ -12,12 +12,35 @@ env:
   DOCKERHUB_REPO: yoursfunny/telegram-twitter-media-bot
 
 jobs:
+  # A tag push and a branch push to the same commit fire two workflow runs;
+  # build only once. Tag runs always build; master runs build only when the
+  # pushed commit is not already tagged (the tag run covers it).
+  should-build:
+    runs-on: ubuntu-latest
+    outputs:
+      build: ${{ steps.check.outputs.build }}
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          fetch-depth: 0
+      - id: check
+        shell: bash
+        run: |
+          if [ "$GITHUB_REF_TYPE" = "branch" ] && git tag --points-at "$GITHUB_SHA" | grep -q .; then
+            echo "commit already tagged; the tag run builds the image"
+            echo "build=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "build=true" >> "$GITHUB_OUTPUT"
+          fi
+
   docker:
+    needs: should-build
+    if: needs.should-build.outputs.build == 'true'
     runs-on: ubuntu-latest
     steps:
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@v6
         with:
           images: ${{ env.DOCKERHUB_REPO }}
           tags: |
@@ -28,22 +51,30 @@ jobs:
             type=sha
       -
         name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v4
       -
         name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v4
       -
         name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
+      # Buildkit cache via the GitHub Actions cache backend (uses the
+      # automatic GITHUB_TOKEN, no extra secrets). mode=max keeps every
+      # stage's layers so the cargo-deps and ffmpeg layers are restored
+      # instead of re-downloaded/recompiled. The scope must be pinned to a
+      # fixed string: the gha backend defaults to the current git ref, which
+      # would give every new tag a cold cache on release builds.
       -
         name: Build and push
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v7
         with:
           push: true
           build-args: |
             APP_NAME=${{ env.APP_NAME }}
           tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha,scope=tgxmb-build
+          cache-to: type=gha,mode=max,scope=tgxmb-build

.gitignore

@@ -2,5 +2,15 @@
 __pycache__/
 cert/
 data/
+nginx-certs/
+nginx-vhost.d/
+nginx-html/
+nginx-acme/
 docker-compose.yml
-x.py
+
+.env
+
+
+# Added by cargo
+
+/target

AGENTS.md

@@ -0,0 +1,97 @@
+# Repository Guidelines
+
+## Project Overview
+
+Telegram bot (teloxide) that turns post links from X/Twitter, Pixiv, and Bluesky into media messages (images, video, GIF) with the post's title, author, and tags. It supports batch media splitting, retry with persistence, inline queries, forward-channel rebinding with caption templates, and Pixiv ugoira→MP4 transcoding. README and user-facing strings are in Chinese. The project is a Rust port of a Python predecessor (see `queue.rs` comments referencing `utils/task_queue.py`).
+
+Two-crate Cargo workspace (both v1.0.3, edition 2024, resolver 3):
+
+- **`crates/x-media`** — library that fetches and normalizes media from the three sites. Pure, no Telegram knowledge.
+- **`crates/xmedia-bot`** — the bot binary: teloxide dispatcher, SQLite-backed chat state, persistent task queue.
+
+## Architecture & Data Flow
+
+```
+Telegram update → Dispatcher (polling or axum webhook) → dptree branches
+  ├─ message    → commands (any chat) / URL links (private chat only)
+  ├─ inline_query → InlineQueryResult Photo/Video/Mpeg4Gif
+  └─ callback_query → "forward" (copy to channel) / "template|<name>" (apply caption template)
+```
+
+Message flow: `message_handler` extracts URLs (from `url`/`text_link` entities, text + caption, deduped) → `x_media::site::fetch(url)` → `Fetched` → builds a `Task` → `send::send_media_sequence` (media groups ≤ 9, caption on first item) or `send::send_animation`. On Telegram URL-fetch failure or size error (`send_batch_via_upload`): download via `x_media::site::download_media` to a temp file (≤ 10 MiB), sniff magic bytes (`sniff_ext`), upload via multipart; oversized items fall back to `fallback_url`. On failure: `enqueue_retry` persists resume-state `Task` into the SQLite queue → single worker leases (120 s lock TTL) → retry with exponential backoff (≤ 30 s, `MAX_RETRIES = 2`) → dead-letter → `notify_failure`. Success → `post_send_actions`: edit-before-forward prompt with inline buttons, or `copy_messages` to the bound forward channel.
+
+The `x-media` library: `site::fetch(url)` dispatches (in order) twitter → bsky → pixiv via per-site regex `PATTERN` and returns `Ok(None)` for unmatched URLs. `Fetched { source_url, caption, title, media: Vec<Media>, sensitive, … }`; `caption_with(format)` substitutes `{url} {author} {author_url} {title} {tags}`.
+
+## Key Directories
+
+| Path | Purpose |
+|---|---|
+| `crates/x-media/src/` | Fetch library. `site/mod.rs` = dispatcher + `Fetched`/`FetchError`/`download_media`/`media_size`; `media.rs` = `Media` enum; `examples/fetch.rs` = end-to-end usage sample |
+| `crates/x-media/src/site/<twitter\|pixiv\|bsky>/` | One directory per site: `mod.rs` (re-exports), `interface.rs` (PATTERN, `enabled()`, `fetch_from_url()`, site struct, `From<SiteStruct> for Fetched`), `model.rs` (serde DTOs). Pixiv adds `api.rs` (auth + transport); twitter adds `auth.rs` (logged-in GraphQL `TweetDetail` fallback for NSFW tweets, gated on `TWITTER_AUTH_TOKEN`) |
+| `crates/xmedia-bot/src/main.rs` | Entry point: env/log init, queue worker start, pixiv validation, 300 s edit-expiry sweep, dptree handler tree, webhook vs polling dispatch |
+| `crates/xmedia-bot/src/config.rs` | Manual env parsing into `Config` |
+| `crates/xmedia-bot/src/handlers.rs` | `Command` enum (teloxide `BotCommands`), message/inline/callback handlers, URL extraction, global statics |
+| `crates/xmedia-bot/src/state.rs` | `ChatStore`: parking_lot `Mutex<HashMap>` cache + SQLite write-through (`chat_state` table) |
+| `crates/xmedia-bot/src/queue.rs` | `PersistentTaskQueue`: SQLite-backed single-worker queue (`tasks` table) |
+| `crates/xmedia-bot/src/send.rs` | Media senders, upload fallback, error classification, queue task handlers |
+
+## Development Commands
+
+```bash
+export TELOXIDE_TOKEN=<token>          # required; PIXIV_REFRESH_TOKEN optional (Pixiv disabled without it)
+cargo run -p xmedia-bot                # run the bot (polling by default)
+cargo run -p x-media --example fetch -- <url>   # test a link through the fetch library
+cargo test --workspace                 # full test suite (no CI test step exists — run locally)
+cargo build --release -p xmedia-bot    # release build (Dockerfile does this)
+cargo clippy --workspace --all-targets # lint (Clippy is the configured IDE linter)
+cargo fmt --check                      # formatting
+```
+
+Docker: `docker build -t tgxmb .` then `docker run --rm -d --name tgxmb --env-file .env -v ./data:/app/data tgxmb`. Runtime requires **ffmpeg** (built into the image).
+
+## Code Conventions & Common Patterns
+
+- **No anyhow/thiserror.** Errors are hand-rolled enums with manual `Display`/`source()`/`From` impls: `QueueError` (`Retryable { delay_seconds, payload }` / `Permanent`), `SendError` (Retryable/Permanent), `FetchError` (`Http`/`Json`/`Pixiv`/`NotFound`/`Blocked`), `PixivError`, `Classification`. New errors should follow this pattern.
+- **Global state via `std::sync::LazyLock` statics**, not DI: `CONFIG`, `CHAT_STORE`, `TASK_QUEUE` in `handlers.rs`; shared reqwest `CLIENT` in `x-media/src/site/mod.rs`. `Bot` is passed/cloned into handlers; queue workers rebuild `Bot::from_env()`.
+- **Async**: tokio multi-thread runtime (`#[tokio::main]` default). All rusqlite I/O inside `tokio::task::spawn_blocking`. Long loops use `tokio::select!` with `tokio::sync::{watch, Notify}` stop/wake channels. No streams.
+- **Blocking sync primitives**: `parking_lot::Mutex` for hot caches, `tokio::sync::Mutex` for async-shared state (pixiv token cache), `AtomicBool` for feature gates.
+- **Site adapter convention** (no trait, no enum dispatch — follow the existing convention): each site module exports `PATTERN: LazyLock<Regex>`, `enabled() -> bool`, `fetch_from_url(url) -> Result<Fetched, FetchError>`; `site/mod.rs` re-exports the site struct and `fetch_once` adds one guarded if-branch. Adding a site = new `site/<name>/{mod.rs,interface.rs,model.rs}` + one branch in `fetch_once`.
+- **Serde**: per-site `model.rs` are pure `Deserialize` DTOs mirroring API JSON; site structs in `interface.rs` have private fields, a `caption()` builder, and `impl From<SiteStruct> for Fetched`. Persisted payloads use internally-tagged enums (`#[serde(tag = "kind")]` / `type`).
+- **Naming**: module-per-concern, snake_case files, `CamelCase` types, `snake_case` fns. `//!` module docs and `///` docs on non-obvious logic (syndication token, ugoira encoding, `display_text_range`).
+- **Retries**: only `x-media::site::fetch` retries (3 attempts, `1 << attempt` backoff, HTTP errors only). Queue retries are explicit `QueueError::Retryable` with computed delay (`retry_delay_seconds`).
+- Logging via `log` macros (`pretty_env_logger`, level from `RUST_LOG`).
+
+## Important Files
+
+| File | Why it matters |
+|---|---|
+| `crates/xmedia-bot/src/main.rs` | Startup sequence, webhook vs polling, graceful shutdown (SIGINT via teloxide ctrlc / SIGTERM via `stop_token` for docker, → sweep stop → admin msg → queue stop) |
+| `crates/xmedia-bot/src/handlers.rs` | `CHAT_STORE`/`TASK_QUEUE`/`CONFIG` singletons (open `data/task_queue.db` **relative to CWD**); command dispatch; URL extraction; retry enqueue |
+| `crates/xmedia-bot/src/send.rs` | Constants `MAX_MEDIA_GROUP = 9`, `MAX_UPLOAD_BYTES = 10 MiB`; fallback chain; `classify_request_error` |
+| `crates/x-media/src/site/mod.rs` | Dispatcher, `Fetched`/`FetchError`, shared `CLIENT`, `download_media` (adds `Referer: https://www.pixiv.net/` for `pximg.net` hotlink protection) |
+| `crates/x-media/src/site/pixiv/api.rs` | OAuth token exchange (hardcoded app client id/secret), access-token cache, ugoira zip→MP4 via ffmpeg in `spawn_blocking` |
+| `Dockerfile` | Multi-stage: cached dep layer via stub sources + `touch *.rs` mtime hack, static ffmpeg from ffmpeg.martin-riedl.de (`FFMPEG_URL` arg, `unzip -t` integrity check), `debian:bookworm-slim` runtime, entrypoint |
+| `docker-entrypoint.sh` | Privilege drop: `useradd` with `LOCAL_USER_ID` (default 9001) + `setpriv` (no gosu on bookworm-slim) |
+| `docker-compose.yml.example` | Deployment env reference (real `docker-compose.yml` is gitignored). Ships nginx-proxy + acme-companion: webhook mode needs TLS termination in front (teloxide's axum listener is HTTP-only; `WEBHOOK_CERT` only feeds `set_webhook`), bot exposes `VIRTUAL_HOST`/`VIRTUAL_PORT` on the shared `proxy` network, no host port; container names `nginx-proxy`/`acme-companion`/`tgxmb`, start order via `depends_on` (proxy → acme → bot) |
+| `.github/workflows/docker.yml` | CI: build+push to Docker Hub on tag `v*`/master; **no test step**; buildx gha cache (`cache-from`/`cache-to`, scope `tgxmb-build`, `mode=max`) so cargo deps + ffmpeg layers are restored across runs |
+| `README.md` | Feature docs + command table (Chinese) |
+
+## Runtime/Tooling Preferences
+
+- **Rust, stable, edition 2024**, workspace resolver 3. No `rust-version`/MSRV pin, no `rust-toolchain.toml` — recent stable is assumed. No nightly features.
+- Package manager: **Cargo** (workspace with path dep `x-media` ← `xmedia-bot`). No `[workspace.package]`/shared deps — each crate lists deps independently.
+- **Two reqwest versions coexist in the lock** (0.12.28 via teloxide, 0.13.3 in x-media) — don't unify casually.
+- Config is **environment-variable driven** (dotenv loads `.env`, gitignored; no `.env.example` exists). Key vars: `TELOXIDE_TOKEN` (required), `PIXIV_REFRESH_TOKEN`, `TWITTER_AUTH_TOKEN` (optional; x.com `auth_token` cookie — enables the logged-in GraphQL fallback that fetches NSFW tweets syndication withholds), `BOT_ADMIN` (comma-separated ids), `EDIT_MESSAGE_TTL_SECONDS` (default 86400), `WEBHOOK`/`WEBHOOK_URL`/`WEBHOOK_LISTEN`/`WEBHOOK_PORT`/`WEBHOOK_CERT`/`WEBHOOK_SECRET_TOKEN` (webhook mode requires URL/listen/port, `.expect`ed; `WEBHOOK_CERT` is Telegram-facing self-signed validation only — TLS must be terminated by a reverse proxy), `RUST_LOG`, `TELOXIDE_PROXY`, `LOCAL_USER_ID` (entrypoint only).
+- SQLite via `rusqlite` with `bundled` feature (no system libsqlite needed). DB file `data/task_queue.db` is CWD-relative — run from the workspace root, or `/app` in Docker. Mount `./data` and `./cert` volumes.
+- `.gitattributes` enforces LF for `*.sh` (CRLF breaks shebangs in containers). `.gitignore`: `.env`, `data/`, `cert/`, `docker-compose.yml`, `/target`, `.idea/`.
+- Docs are in Chinese; user-facing bot strings too. Keep that convention when editing captions/templates/docs.
+
+## Testing & QA
+
+- **~51 tests, all inline `#[cfg(test)] mod tests`** — no `tests/` integration directories. Framework: built-in Rust test + `#[tokio::test]` (dev-deps only in `x-media`: tokio macros/rt-multi-thread, dotenv).
+- No mocking framework anywhere (no mockito/wiremock/mockall). Conventions: pure-function units (regex parsing, serde round-trips, chunking, retry math) tested synchronously; async tests use real dependencies — file-backed SQLite via `tempfile` (`queue.rs::new_queue()` helper), live network fetches.
+- Live-network tests exist in `site/twitter/interface.rs` (3), `site/bsky/interface.rs` (2), `site/pixiv/interface.rs`/`api.rs` (env-gated on `PIXIV_REFRESH_TOKEN`/dotenv, skip by early return). Run the full suite with `cargo test --workspace`.
+- Fixtures are inline `serde_json::json!` builder fns (`fixture()`, `thread_json()`, `illust_json()`), not files. The shared `CLIENT` sets `pool_max_idle_per_host(0)` under `#[cfg(test)]` to avoid cross-runtime `DispatchGone`.
+- **CI runs no tests** — `.github/workflows/docker.yml` only builds/pushes the image; verification is a local responsibility.
+- Untested and hard to test without a mock seam: `handlers.rs` (depends directly on teloxide `Bot`); `main.rs`, `config.rs`, `state.rs`; `media.rs`, `lib.rs`, all `model.rs`.
+- No coverage tracking, no lint gate in CI.

Cargo.toml

@@ -0,0 +1,3 @@
+[workspace]
+members = ["crates/x-media", "crates/xmedia-bot"]
+resolver = "3"

Dockerfile

@@ -1,26 +1,73 @@
-FROM python:3.12-slim-bullseye
+# ---------- build stage ----------
+# rust:1-bookworm (full, not slim) ships the C toolchain needed by
+# rusqlite's bundled SQLite, plus wget/unzip for the ffmpeg download.
+FROM rust:1-bookworm AS builder
+
+ARG APP_NAME=telegram-twitter-media-bot
+# Prebuilt static ffmpeg (glibc-linked, includes libx264) for ugoira MP4
+# encoding. Served from https://ffmpeg.martin-riedl.de (Cloudflare CDN,
+# built on Debian 12 — glibc-compatible with the bookworm-slim runtime).
+# johnvansickle.com throttles datacenter IPs and served garbage from GitHub
+# runners. `/redirect/latest/` floats to the newest release build; each build
+# also ships a .sha256. Swap `amd64` for `arm64` when building arm64 images.
+ARG FFMPEG_URL=https://ffmpeg.martin-riedl.de/redirect/latest/linux/amd64/release/ffmpeg.zip
+
+WORKDIR /build
+
+# 1. Rust dependencies first: only the manifests plus stub sources, so the
+#    expensive dependency fetch + compile lives in a layer invalidated only by
+#    manifest/lock changes.
+COPY Cargo.toml Cargo.lock ./
+COPY crates/x-media/Cargo.toml crates/x-media/Cargo.toml
+COPY crates/xmedia-bot/Cargo.toml crates/xmedia-bot/Cargo.toml
+RUN mkdir -p crates/x-media/src crates/xmedia-bot/src \
+    && printf 'fn main() {}\n' > crates/xmedia-bot/src/main.rs \
+    && : > crates/x-media/src/lib.rs \
+    && cargo build --release -p xmedia-bot
+
+# 2. Static ffmpeg next (cached unless FFMPEG_URL changes), so source edits
+#    never re-download it. The zip contains a single `ffmpeg` binary at the
+#    root. `unzip -t` verifies the archive before extraction so a bad
+#    download fails loudly here instead of a cryptic later error.
+RUN wget -q -O /tmp/ffmpeg.zip "$FFMPEG_URL" \
+    && unzip -tq /tmp/ffmpeg.zip \
+    && unzip -q /tmp/ffmpeg.zip -d /usr/local/bin \
+    && chmod +x /usr/local/bin/ffmpeg \
+    && rm /tmp/ffmpeg.zip \
+    && /usr/local/bin/ffmpeg -version >/dev/null
+
+# 3. Real sources last: only our crates recompile on source changes. The
+#    COPY preserves host mtimes, which predate the stub artifacts from step 1;
+#    cargo's mtime-based freshness check would otherwise treat the stub build
+#    as up-to-date and never compile the real sources. `touch` forces cargo to
+#    see the real files as newer.
+COPY crates/ ./crates/
+RUN find crates -type f -name '*.rs' -exec touch {} + \
+    && cargo build --release -p xmedia-bot
+
+# ---------- runtime stage ----------
+FROM debian:bookworm-slim
+
+# ARG scope is per-stage: re-declare for the label below.
+ARG APP_NAME=telegram-twitter-media-bot
 
 LABEL maintainer="admin@yoursfunny.top"
+LABEL org.opencontainers.image.title="${APP_NAME}"
 
-ENV PYTHONDONTWRITEBYTECODE=1
+# Everything is copied in — no apt in the runtime stage. Privilege dropping is
-ENV PYTHONUNBUFFERED=1
+# done by docker-entrypoint.sh with setpriv (util-linux, already in
-
+# bookworm-slim), so no gosu needed.
-RUN set -eux; \
+COPY --from=builder /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
-	apt-get update; \
+COPY --from=builder /usr/lib/x86_64-linux-gnu/libssl.so.3* /usr/lib/x86_64-linux-gnu/
-	apt-get install -y gosu; \
+COPY --from=builder /usr/lib/x86_64-linux-gnu/libcrypto.so.3* /usr/lib/x86_64-linux-gnu/
-	rm -rf /var/lib/apt/lists/*; \
+COPY --from=builder /usr/local/bin/ffmpeg /usr/local/bin/ffmpeg
-# verify that the binary works
-	gosu nobody true
 
 WORKDIR /app
+COPY --from=builder /build/target/release/xmedia-bot /usr/local/bin/xmedia-bot
+COPY docker-entrypoint.sh /app/docker-entrypoint.sh
+RUN chmod a+x /app/docker-entrypoint.sh
 
-COPY requirements.txt /app
+# State lives in /app/data (SQLite task queue + chat state); mount a volume
-RUN python -m pip install --no-cache-dir --upgrade -r requirements.txt
+# there to keep it across restarts.
-
-COPY . /app
-
-RUN chmod a+x docker-entrypoint.sh
-
 ENTRYPOINT ["/app/docker-entrypoint.sh"]
-
+CMD ["xmedia-bot"]
-CMD ["python", "main.py"]

README.md

@@ -0,0 +1,95 @@
+# TelegramXMediaBot
+
+Telegram 机器人，将 X / Twitter、Pixiv、Bluesky 的帖子链接转换为媒体消息发送，附带帖子标题、作者与标签。
+
+## 功能
+
+- 私聊发送链接后自动抓取并发送图片、视频与 GIF，超量图片自动分批
+- 纯文字帖提示无媒体；不支持的链接静默忽略
+- 支持内联查询（`@机器人 <链接>`）
+- 可绑定转发频道自动转发；支持转发前编辑 caption 与自定义模板
+- 发送失败自动重试并持久化，重试耗尽后通知用户
+- Pixiv ugoira 动图自动转码为 MP4
+
+## 快速开始
+
+```bash
+# 必填：BotFather 的 token；可选：PIXIV_REFRESH_TOKEN（未设置则禁用 Pixiv）
+export TELOXIDE_TOKEN=<token>
+export PIXIV_REFRESH_TOKEN=<token>
+
+cargo run -p xmedia-bot
+```
+
+Docker 部署（参考 `docker-compose.yml.example`）：
+
+```bash
+docker build -t tgxmb .
+docker run --rm -d --name tgxmb --env-file .env -v ./data:/app/data tgxmb
+```
+
+环境变量：`TELOXIDE_TOKEN`（必填）、`PIXIV_REFRESH_TOKEN`、`BOT_ADMIN`、`EDIT_MESSAGE_TTL_SECONDS`、`RUST_LOG`、`WEBHOOK*`、`TWITTER_AUTH_TOKEN`（可选）。
+
+NSFW 推文：公开的 syndication 接口不返回敏感内容。设置 `TWITTER_AUTH_TOKEN`（登录 x.com 后浏览器 Cookie 里的 `auth_token` 值）后，bot 会仅在遇到 NSFW 推文时以登录态获取媒体；未设置则提示无媒体。
+
+### Webhook 部署（需要反向代理）
+
+`docker-compose.yml.example` 内置了 [nginx-proxy](https://github.com/nginx-proxy/nginx-proxy) + [acme-companion](https://github.com/nginx-proxy/acme-companion) 反向代理编排，按部署环境二选一：
+
+**有域名**
+1. DNS A 记录指向服务器
+2. compose 里设 `VIRTUAL_HOST`、`LETSENCRYPT_HOST` 为域名，`WEBHOOK_URL` 设为 `https://域名/`
+3. 证书自动签发与续期，无需手动处理
+
+**只有 IP**
+1. 生成自签证书（PEM 格式，见第 3 步）：
+   `openssl req -x509 -newkey rsa:2048 -nodes -days 365 -keyout nginx-certs/default.key -out nginx-certs/default.crt`
+2. compose 里 nginx-proxy 设 `DEFAULT_HOST`，bot 设 `WEBHOOK_CERT: './cert/cert.pem'`（须与代理所服务的为同一张证书）
+3. 证书必须是 PEM 编码（ASCII BASE64，以 `-----BEGIN CERTIFICATE-----` 开头）—— Telegram 只接受该格式；若现有证书是 DER 二进制，转换：
+   `openssl x509 -in cert.der -inform DER -out cert.pem -outform PEM`
+   （私钥同理：`openssl rsa -in key.der -inform DER -out key.pem -outform PEM`）
+
+Telegram 只接受 443/80/88/8443 端口。
+
+<details>
+<summary>环境变量说明</summary>
+
+| 变量 | 说明 |
+|---|---|
+| `TELOXIDE_TOKEN` | Bot token（必填） |
+| `PIXIV_REFRESH_TOKEN` | Pixiv 刷新令牌；未设置则禁用 Pixiv |
+| `BOT_ADMIN` | 管理员聊天 ID，逗号分隔；接收启动/停止通知 |
+| `EDIT_MESSAGE_TTL_SECONDS` | 转发前编辑记录过期秒数，默认 86400 |
+| `RUST_LOG` | 日志级别 |
+| `LOCAL_USER_ID` | 容器内运行用户 UID，默认 9001 |
+| `VIRTUAL_HOST` | 对外域名或 IP，nginx-proxy 按此路由 |
+| `VIRTUAL_PORT` | bot 容器内监听端口，nginx-proxy 的转发目标 |
+| `LETSENCRYPT_HOST` | 设为域名时由 acme-companion 自动签发/续期证书 |
+| `DEFAULT_HOST` | nginx-proxy 将未知 Host 的请求路由到该 vhost（IP 访问时需要） |
+| `DEFAULT_EMAIL` | acme-companion 证书通知邮箱 |
+| `WEBHOOK` | `true` 启用 webhook 模式（默认轮询） |
+| `WEBHOOK_LISTEN` / `WEBHOOK_PORT` | bot 容器内监听地址/端口 |
+| `WEBHOOK_URL` | 对外公网 HTTPS 地址（`https://域名/`） |
+| `WEBHOOK_CERT` | 自签证书路径（仅 IP 路径需要，须为 PEM 且与代理所服务的一致） |
+| `WEBHOOK_SECRET_TOKEN` | 更新校验令牌（`X-Telegram-Bot-Api-Secret-Token`） |
+
+</details>
+
+## 命令
+
+| 命令 | 说明 |
+|---|---|
+| `/set_forward_channel <频道>` | 设置转发频道 |
+| `/remove_forward_channel` | 取消转发频道 |
+| `/edit_before_forward` | 开关转发前编辑 |
+| `/set_template <名称>` | 将回复的消息（含 `[]`）保存为模板 |
+| `/set_format <站点> <格式>` | 自定义 caption 格式（占位符 `{url}` `{title}` `{tags}` 等） |
+| `/bot_dict` | 查看聊天状态 |
+
+链接处理仅限私聊；命令在任意聊天可用。
+
+## 备注
+
+- 数据持久化于 `data/task_queue.db`，容器部署需挂载该目录
+- 运行环境需安装 ffmpeg（Docker 镜像已内置）
+- 测试：`cargo test --workspace`

common.py

@@ -1,25 +0,0 @@
-import logging
-import os
-import re
-
-BOT_TOKEN = os.getenv("BOT_TOKEN")
-ADMIN = os.getenv("BOT_ADMIN").split(",")
-
-WEBHOOK = os.getenv("WEBHOOK", False)
-if WEBHOOK:
-    WEBHOOK_LISTEN = os.getenv("WEBHOOK_LISTEN", "0.0.0.0")
-    WEBHOOK_PORT = int(os.getenv("WEBHOOK_PORT", 8443))
-    WEBHOOK_URL = os.getenv("WEBHOOK_URL")
-    WEBHOOK_KEY = os.getenv("WEBHOOK_KEY", "cert/private.key")
-    WEBHOOK_CERT = os.getenv("WEBHOOK_CERT", "cert/cert.pem")
-    WEBHOOK_SECRET_TOKEN = os.getenv("WEBHOOK_SECRET_TOKEN")
-
-x_url_regex = re.compile(r"^(?:https?://)(?:www\.|mobile\.|)(?:x|twitter)\.com/(.+)/status/(\d+)")
-x_media_regex = re.compile(r"^(?:https?://)(pbs|video)\.twimg\.com/(.*)")
-x_tco_regex = re.compile(r"(?:https?://)t\.co/.+$", re.M)
-
-logging.basicConfig(
-    level=os.getenv("LOG_LEVEL", "WARNING"),
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-)
-logger = logging.getLogger(__name__)

crates/x-media/Cargo.toml

@@ -0,0 +1,22 @@
+[package]
+name = "x-media"
+version = "1.0.5"
+edition = "2024"
+
+[dependencies]
+reqwest = { version = "0.13", features = ["json", "query", "form"] }
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+regex = "1.12"
+html-escape = "0.2"
+url = "2.5.2"
+bytes = "1"
+zip = "2"
+tempfile = "3"
+rand = "0.8"
+log = "0.4"
+tokio = { version = "1.40", features = ["time"] }
+
+[dev-dependencies]
+tokio = { version = "1.40", features = ["macros", "rt-multi-thread"] }
+dotenv = "0.15"

crates/x-media/examples/fetch.rs

@@ -0,0 +1,10 @@
+use x_media::site;
+
+#[tokio::main]
+async fn main() {
+    let url = std::env::args()
+        .nth(1)
+        .expect("usage: cargo run -p x-media --example fetch -- <url>");
+    let result = site::fetch(&url).await;
+    println!("{result:#?}");
+}

crates/x-media/src/lib.rs

@@ -0,0 +1,2 @@
+pub mod media;
+pub mod site;

crates/x-media/src/media.rs

@@ -0,0 +1,55 @@
+impl Media {
+    pub fn url(&self) -> &str {
+        match self {
+            Media::Illustration { url, .. } => url,
+            Media::Video { url, .. } => url,
+            Media::Animated { url, .. } => url,
+        }
+    }
+
+    pub fn thumbnail_url(&self) -> Option<&str> {
+        match self {
+            Media::Illustration { thumbnail_url, .. } => thumbnail_url.as_deref(),
+            Media::Video { thumbnail_url, .. } => Some(thumbnail_url),
+            Media::Animated { thumbnail_url, .. } => Some(thumbnail_url),
+        }
+    }
+
+    /// A smaller variant of this media's file (used as the fallback when the
+    /// primary URL or upload exceeds Telegram's size limits). None when no
+    /// smaller variant exists (videos, animated gifs).
+    pub fn smaller_url(&self) -> Option<&str> {
+        match self {
+            Media::Illustration {
+                url,
+                fallback_url,
+                thumbnail_url,
+                ..
+            } => fallback_url
+                .as_deref()
+                .or(thumbnail_url.as_deref())
+                .filter(|smaller| *smaller != url),
+            Media::Video { .. } | Media::Animated { .. } => None,
+        }
+    }
+}
+
+#[derive(Debug)]
+pub enum Media {
+    Illustration {
+        title: Option<String>,
+        url: String,
+        thumbnail_url: Option<String>,
+        fallback_url: Option<String>,
+    },
+    Video {
+        title: Option<String>,
+        url: String,
+        thumbnail_url: String,
+    },
+    Animated {
+        title: Option<String>,
+        url: String,
+        thumbnail_url: String,
+    },
+}

crates/x-media/src/site/bsky/interface.rs

@@ -0,0 +1,272 @@
+use super::model;
+use crate::media::Media;
+use crate::site::{FetchError, Fetched};
+use html_escape::encode_text;
+use regex::Regex;
+use std::sync::LazyLock;
+
+pub static PATTERN: LazyLock<Regex> = LazyLock::new(|| {
+    Regex::new(r"bsky\.app/profile/([\w.\-:]+)/post/([\w.\-~]+)").unwrap()
+});
+
+pub fn enabled() -> bool {
+    true
+}
+
+pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
+    let caps = PATTERN.captures(url).ok_or(FetchError::NotFound)?;
+    let handle = caps.get(1).map(|m| m.as_str()).ok_or(FetchError::NotFound)?;
+    let rkey = caps.get(2).map(|m| m.as_str()).ok_or(FetchError::NotFound)?;
+    Ok(fetch(handle, rkey).await?.into())
+}
+
+/// Fetches a post thread by handle or DID (`at://` URIs work for both).
+pub async fn fetch(handle: &str, rkey: &str) -> Result<Post, FetchError> {
+    let response = crate::site::CLIENT
+        .get(API_URL)
+        .query(&[
+            ("uri", format!("at://{handle}/app.bsky.feed.post/{rkey}")),
+            ("depth", "0".to_string()),
+        ])
+        .send()
+        .await?;
+    let text = response.text().await?;
+    Ok(Post::from_json(&text, rkey.to_string())?)
+}
+
+#[derive(Debug)]
+pub struct Post {
+    id: String,
+    author: String,
+    author_id: String,
+    text: String,
+    media: Vec<Media>,
+    sensitive: bool,
+}
+
+impl Post {
+    fn url(&self) -> String {
+        format!("{}/post/{}", self.author_url(), self.id)
+    }
+
+    fn author_url(&self) -> String {
+        format!("https://bsky.app/profile/{}", self.author_id)
+    }
+
+    pub fn caption(&self) -> String {
+        format!(
+            "{url}\n<a href=\"{author_url}\">{author}</a>: {text}",
+            url = self.url(),
+            author_url = self.author_url(),
+            author = encode_text(&self.author),
+            text = encode_text(&self.text),
+        )
+    }
+
+    pub fn from_json(raw_json: &str, id: String) -> Result<Self, FetchError> {
+        let json: serde_json::Value = serde_json::from_str(raw_json).map_err(FetchError::Json)?;
+        let json: model::Info = serde_json::from_value(json).map_err(FetchError::Json)?;
+        match json.thread {
+            model::Thread::Post { post } => {
+                let text = post.record.text;
+                let author = post.author.display_name.unwrap_or_default();
+                let author_id = post.author.handle;
+                let mut media = vec![];
+                if let Some(embed) = post.embed {
+                    match embed {
+                        model::Media::Images { images } => {
+                            media.extend(images.into_iter().map(|image| Media::Illustration {
+                                title: None,
+                                url: image.fullsize,
+                                thumbnail_url: Some(image.thumb),
+                                fallback_url: None,
+                            }));
+                        }
+                        model::Media::Video {
+                            playlist,
+                            thumbnail,
+                        } => {
+                            media.push(Media::Video {
+                                title: None,
+                                url: playlist,
+                                thumbnail_url: thumbnail,
+                            });
+                        }
+                        model::Media::External => {}
+                    }
+                }
+                let sensitive = post
+                    .labels
+                    .iter()
+                    .any(|label| SENSITIVE_LABEL.contains(&label.val.as_str()));
+                Ok(Post {
+                    id,
+                    author,
+                    author_id,
+                    text,
+                    media,
+                    sensitive,
+                })
+            }
+            model::Thread::NotFound => Err(FetchError::NotFound),
+            model::Thread::Blocked => Err(FetchError::Blocked),
+        }
+    }
+}
+
+impl From<Post> for Fetched {
+    fn from(post: Post) -> Self {
+        let url = post.url();
+        let author_url = post.author_url();
+        let render_data = Some(crate::site::RenderData {
+            url: url.clone(),
+            author: encode_text(&post.author).into_owned(),
+            author_url: author_url.clone(),
+            title: encode_text(&post.text).into_owned(),
+            tags: String::new(),
+        });
+        Fetched {
+            source_url: url,
+            caption: post.caption(),
+            title: post.text.clone(),
+            media: post.media,
+            sensitive: post.sensitive,
+            render_data,
+            _keep_alive: None,
+        }
+    }
+}
+
+const API_URL: &str = "https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread";
+const SENSITIVE_LABEL: [&str; 4] = ["sexual", "nudity", "porn", "graphic-media"];
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn thread_json(post_json: serde_json::Value) -> serde_json::Value {
+        serde_json::json!({ "thread": post_json })
+    }
+
+    #[test]
+    fn pattern_matches_handle_and_did() {
+        let cases = [
+            (
+                "https://bsky.app/profile/user.bsky.social/post/3laoveufjv224",
+                "user.bsky.social",
+                "3laoveufjv224",
+            ),
+            (
+                "https://bsky.app/profile/did:plc:abc123def/post/3xxxx",
+                "did:plc:abc123def",
+                "3xxxx",
+            ),
+        ];
+        for (url, handle, rkey) in cases {
+            let caps = PATTERN.captures(url).unwrap_or_else(|| panic!("{url}"));
+            assert_eq!(caps.get(1).unwrap().as_str(), handle);
+            assert_eq!(caps.get(2).unwrap().as_str(), rkey);
+        }
+    }
+
+    #[test]
+    fn pattern_rejects_non_post_urls() {
+        for url in [
+            "https://bsky.app/profile/user.bsky.social",
+            "https://bsky.app/profile/user.bsky.social/posts",
+            "https://x.com/user/status/123",
+        ] {
+            assert!(!PATTERN.is_match(url), "{url}");
+        }
+    }
+
+    #[test]
+    fn from_json_images_with_missing_defaults() {
+        let raw = thread_json(serde_json::json!({
+            "$type": "app.bsky.feed.defs#threadViewPost",
+            "post": {
+                "author": { "handle": "user.bsky.social" },
+                "record": { "$type": "app.bsky.feed.post", "text": "hello <world>" },
+                "embed": {
+                    "$type": "app.bsky.embed.images#view",
+                    "images": [
+                        { "thumb": "https://cdn.bsky.app/img/thumb", "fullsize": "https://cdn.bsky.app/img/full", "alt": "" }
+                    ]
+                }
+            }
+        }));
+        let post = Post::from_json(&raw.to_string(), "3xxxx".into()).unwrap();
+        let fetched: Fetched = post.into();
+        assert_eq!(fetched.source_url, "https://bsky.app/profile/user.bsky.social/post/3xxxx");
+        assert_eq!(fetched.title, "hello <world>");
+        assert_eq!(fetched.media.len(), 1);
+        assert!(!fetched.sensitive);
+        // display_name absent -> empty fallback
+        assert!(
+            fetched.caption.contains("</a>: hello &lt;world&gt;"),
+            "caption: {}",
+            fetched.caption
+        );
+    }
+
+    #[test]
+    fn from_json_sensitive_labels() {
+        let raw = thread_json(serde_json::json!({
+            "$type": "app.bsky.feed.defs#threadViewPost",
+            "post": {
+                "author": { "handle": "u.bsky.social", "displayName": "U" },
+                "record": { "$type": "app.bsky.feed.post", "text": "x" },
+                "labels": [{ "val": "porn" }]
+            }
+        }));
+        let post = Post::from_json(&raw.to_string(), "3xxxx".into()).unwrap();
+        assert!(post.sensitive);
+    }
+
+    #[test]
+    fn from_json_blocked_and_not_found() {
+        let blocked = thread_json(serde_json::json!({
+            "$type": "app.bsky.feed.defs#blockedPost",
+            "blocked": true
+        }));
+        assert!(matches!(
+            Post::from_json(&blocked.to_string(), "3xxxx".into()),
+            Err(FetchError::Blocked)
+        ));
+
+        let not_found = thread_json(serde_json::json!({
+            "$type": "app.bsky.feed.defs#notFoundPost",
+            "notFound": true
+        }));
+        assert!(matches!(
+            Post::from_json(&not_found.to_string(), "3xxxx".into()),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[tokio::test]
+    async fn live_fetch_with_photos() {
+        let fetched = fetch_from_url(
+            "https://bsky.app/profile/asagi0398.bsky.social/post/3mqkhrq5w6k2m",
+        )
+        .await
+        .unwrap();
+        assert_eq!(
+            fetched.source_url,
+            "https://bsky.app/profile/asagi0398.bsky.social/post/3mqkhrq5w6k2m"
+        );
+        assert!(!fetched.caption.is_empty());
+    }
+
+    #[tokio::test]
+    async fn live_fetch_smoke() {
+        let fetched = fetch_from_url("https://bsky.app/profile/fu-futa.bsky.social/post/3laoveufjv224")
+            .await
+            .unwrap();
+        assert_eq!(
+            fetched.source_url,
+            "https://bsky.app/profile/fu-futa.bsky.social/post/3laoveufjv224"
+        );
+        assert!(!fetched.caption.is_empty());
+    }
+}

crates/x-media/src/site/bsky/mod.rs

@@ -0,0 +1,4 @@
+mod interface;
+mod model;
+
+pub use interface::{PATTERN, Post, enabled, fetch_from_url};

crates/x-media/src/site/bsky/model.rs

@@ -0,0 +1,60 @@
+use serde::Deserialize;
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Info {
+    pub(crate) thread: Thread,
+}
+
+#[derive(Deserialize, Debug)]
+#[serde(tag = "$type")]
+pub(crate) enum Thread {
+    #[serde(rename = "app.bsky.feed.defs#threadViewPost")]
+    Post { post: Post },
+    #[serde(rename = "app.bsky.feed.defs#notFoundPost")]
+    NotFound,
+    #[serde(rename = "app.bsky.feed.defs#blockedPost")]
+    Blocked,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Post {
+    pub(crate) author: Author,
+    pub(crate) record: PostRecord,
+    pub(crate) embed: Option<Media>,
+    #[serde(default)]
+    pub(crate) labels: Vec<Label>,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Author {
+    pub(crate) handle: String,
+    #[serde(rename = "displayName", default)]
+    pub(crate) display_name: Option<String>,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct PostRecord {
+    pub(crate) text: String,
+}
+
+#[derive(Deserialize, Debug)]
+#[serde(tag = "$type")]
+pub(crate) enum Media {
+    #[serde(rename = "app.bsky.embed.images#view")]
+    Images { images: Vec<Image> },
+    #[serde(rename = "app.bsky.embed.video#view")]
+    Video { playlist: String, thumbnail: String },
+    #[serde(rename = "app.bsky.embed.external#view")]
+    External,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Image {
+    pub(crate) thumb: String,
+    pub(crate) fullsize: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Label {
+    pub(crate) val: String,
+}

crates/x-media/src/site/mod.rs

@@ -0,0 +1,259 @@
+//! Site fetching dispatcher and unified result types.
+//!
+//! Dispatch order: twitter → bsky → pixiv. Each site module exports a
+//! `PATTERN`, `enabled()` and `fetch_from_url()`; a future site plugs in by
+//! adding one guarded entry in [`fetch_once`].
+
+use std::fmt;
+use std::sync::LazyLock;
+use std::time::Duration;
+
+pub mod bsky;
+pub mod pixiv;
+pub mod twitter;
+
+pub use pixiv::PixivError;
+
+/// The result of fetching a post: canonical URL, HTML caption, raw text,
+/// media list and spoiler flag. Produced by [`fetch`].
+#[derive(Debug)]
+pub struct Fetched {
+    /// Canonical URL: x.com/{author}/status/{id} |
+    /// https://www.pixiv.net/artworks/{id} |
+    /// https://bsky.app/profile/{handle}/post/{rkey}
+    pub source_url: String,
+    /// The exact HTML produced by the site's caption().
+    pub caption: String,
+    /// Raw post text (tweet text / bsky text / pixiv title).
+    pub title: String,
+    pub media: Vec<crate::media::Media>,
+    /// Spoiler flag for all media of this post.
+    pub sensitive: bool,
+    /// Raw values (pre-escaped) for user-customizable caption formats.
+    pub(crate) render_data: Option<RenderData>,
+    /// Keeps temp files (e.g. an encoded ugoira MP4) alive until the caller
+    /// finishes uploading; not part of the public contract.
+    pub(crate) _keep_alive: Option<tempfile::TempDir>,
+}
+
+/// Pre-escaped values for `{url} {author} {author_url} {title} {tags}`
+/// placeholders in user-supplied caption formats.
+#[derive(Debug)]
+pub(crate) struct RenderData {
+    pub url: String,
+    pub author: String,
+    pub author_url: String,
+    pub title: String,
+    pub tags: String,
+}
+
+impl Fetched {
+    /// The site this post came from (used for per-site format overrides).
+    pub fn site_name(&self) -> &'static str {
+        if self.source_url.contains("x.com") || self.source_url.contains("twitter.com") {
+            "twitter"
+        } else if self.source_url.contains("bsky.app") {
+            "bsky"
+        } else if self.source_url.contains("pixiv.net") {
+            "pixiv"
+        } else {
+            "unknown"
+        }
+    }
+
+    /// Renders a user-supplied caption format. The format string is
+    /// HTML-escaped in full, then the (already-escaped) placeholder values
+    /// are substituted — users can structure text but never inject raw HTML
+    /// or attributes. An empty/unknown format falls back to the built-in
+    /// caption.
+    pub fn caption_with(&self, format: &str) -> String {
+        match (&self.render_data, format.is_empty()) {
+            (Some(data), false) => {
+                let escaped = html_escape::encode_text(format).into_owned();
+                escaped
+                    .replace("{url}", &data.url)
+                    .replace("{author}", &data.author)
+                    .replace("{author_url}", &data.author_url)
+                    .replace("{title}", &data.title)
+                    .replace("{tags}", &data.tags)
+            }
+            _ => self.caption.clone(),
+        }
+    }
+}
+
+#[derive(Debug)]
+pub enum FetchError {
+    Http(reqwest::Error),
+    Json(serde_json::Error),
+    Pixiv(PixivError),
+    NotFound,
+    Blocked,
+    /// The post exists but its content is withheld (twitter NSFW /
+    /// age-restricted tweets come back as an empty `{}` from syndication).
+    Sensitive,
+}
+
+impl fmt::Display for FetchError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            FetchError::Http(e) => write!(f, "http error: {e}"),
+            FetchError::Json(e) => write!(f, "json error: {e}"),
+            FetchError::Pixiv(e) => write!(f, "pixiv error: {e}"),
+            FetchError::NotFound => write!(f, "not found"),
+            FetchError::Blocked => write!(f, "blocked"),
+            FetchError::Sensitive => write!(f, "content withheld (sensitive)"),
+        }
+    }
+}
+
+impl std::error::Error for FetchError {
+    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
+        match self {
+            FetchError::Http(e) => Some(e),
+            FetchError::Json(e) => Some(e),
+            FetchError::Pixiv(e) => Some(e),
+            FetchError::NotFound | FetchError::Blocked | FetchError::Sensitive => None,
+        }
+    }
+}
+
+impl From<reqwest::Error> for FetchError {
+    fn from(e: reqwest::Error) -> Self {
+        FetchError::Http(e)
+    }
+}
+
+
+impl From<serde_json::Error> for FetchError {
+    fn from(e: serde_json::Error) -> Self {
+        FetchError::Json(e)
+    }
+}
+
+impl From<PixivError> for FetchError {
+    fn from(e: PixivError) -> Self {
+        FetchError::Pixiv(e)
+    }
+}
+
+/// Shared HTTP client (browser User-Agent) for twitter/bsky fetches and
+/// [`download_media`].
+pub(crate) static CLIENT: LazyLock<reqwest::Client> = LazyLock::new(|| {
+    let builder = reqwest::Client::builder().user_agent("Mozilla/5.0");
+    // Each `#[tokio::test]` runs on its own runtime; the connection pool is
+    // bound to the runtime that created it, so cross-runtime reuse of idle
+    // connections fails with DispatchGone. In test builds every request uses
+    // a fresh connection. Production runs on one runtime and keeps pooling.
+    #[cfg(test)]
+    let builder = builder.pool_max_idle_per_host(0);
+    builder.build().expect("failed to build HTTP client")
+});
+
+/// Fetches a post from its URL. Returns `Ok(None)` when no site pattern
+/// matches (unsupported links are silently ignored by the bot).
+///
+/// Transient network failures are retried: 3 total attempts with 1s then 2s
+/// delays. Non-Http errors (Json/NotFound/Blocked/Pixiv) are not retried.
+pub async fn fetch(url: &str) -> Result<Option<Fetched>, FetchError> {
+    let mut last_http_error = None;
+    for attempt in 0..3u32 {
+        match fetch_once(url).await {
+            Ok(Some(fetched)) => {
+                log::info!(
+                    "fetched {url}: site {} returned {} media",
+                    fetched.site_name(),
+                    fetched.media.len()
+                );
+                return Ok(Some(fetched));
+            }
+            Ok(None) => return Ok(None),
+            Err(FetchError::Http(e)) => {
+                last_http_error = Some(e);
+                if attempt < 2 {
+                    tokio::time::sleep(Duration::from_secs(1 << attempt)).await;
+                }
+            }
+            Err(other) => return Err(other),
+        }
+    }
+    Err(FetchError::Http(
+        last_http_error.expect("retry loop always ran 3 attempts"),
+    ))
+}
+
+async fn fetch_once(url: &str) -> Result<Option<Fetched>, FetchError> {
+    if twitter::enabled() && twitter::PATTERN.is_match(url) {
+        return Ok(Some(twitter::fetch_from_url(url).await?));
+    }
+    if bsky::enabled() && bsky::PATTERN.is_match(url) {
+        return Ok(Some(bsky::fetch_from_url(url).await?));
+    }
+    if pixiv::enabled() && pixiv::PATTERN.is_match(url) {
+        return Ok(Some(pixiv::fetch_from_url(url).await?));
+    }
+    Ok(None)
+}
+
+/// Downloads media bytes for the bot's upload fallback: when Telegram's own
+/// fetch of a media URL is blocked (hotlink protection), the bot downloads
+/// the file itself and uploads it via multipart. Site-appropriate headers:
+/// pixiv image hosts need the `Referer` header.
+/// Returns the Content-Length of a media URL, or `None` when the server does
+/// not report one. Used to check whether a file fits Telegram's size limits
+/// before downloading/uploading it.
+pub async fn media_size(url: &str) -> Result<Option<u64>, FetchError> {
+    let mut request = CLIENT.get(url);
+    let lower = url.to_ascii_lowercase();
+    if lower.contains("pximg.net") {
+        request = request.header("Referer", "https://www.pixiv.net/");
+    }
+    let response = request.send().await?;
+    Ok(response.content_length())
+}
+
+pub async fn download_media(url: &str) -> Result<bytes::Bytes, FetchError> {
+    let mut request = CLIENT.get(url);
+    let lower = url.to_ascii_lowercase();
+    if lower.contains("pximg.net") {
+        request = request.header("Referer", "https://www.pixiv.net/");
+    }
+    let response = request.send().await?;
+    Ok(response.bytes().await?)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[tokio::test]
+    async fn unsupported_url_returns_none() {
+        let result = fetch("https://example.com/some/article").await;
+        assert!(matches!(result, Ok(None)), "got {result:?}");
+    }
+
+    #[tokio::test]
+    async fn unknown_scheme_returns_none() {
+        let result = fetch("not a url at all").await;
+        assert!(matches!(result, Ok(None)), "got {result:?}");
+    }
+
+    #[tokio::test]
+    async fn download_media_pixiv_original_with_referer() {
+        // Proves the Referer header is attached for i.pximg.net: a header-less
+        // GET to a pixiv original URL is rejected with 403.
+        if std::env::var("PIXIV_REFRESH_TOKEN").is_err() {
+            eprintln!("skipping: no PIXIV_REFRESH_TOKEN");
+            return;
+        }
+        let illustration = pixiv::fetch(126839080).await.unwrap();
+        let fetched: Fetched = illustration.into();
+        let url = match fetched.media.first() {
+            Some(crate::media::Media::Illustration { url, .. }) => url.clone(),
+            other => panic!("expected illustration media, got {other:?}"),
+        };
+        assert!(url.contains("i.pximg.net"));
+        let bytes = download_media(&url).await.unwrap();
+        assert!(!bytes.is_empty());
+    }
+}

crates/x-media/src/site/pixiv/api.rs

@@ -0,0 +1,394 @@
+//! Native pixiv app-API client (replaces pixiv3-rs).
+//!
+//! Token exchange against `oauth.secure.pixiv.net` and illust detail against
+//! `app-api.pixiv.net`, deserialized with the kept `model.rs` types.
+
+use super::interface::Illustration;
+use super::model::{IllustrationModel, TypeModel, UgoiraMetadataModel};
+use crate::media::Media;
+use crate::site::FetchError;
+use std::env;
+use std::fmt;
+use std::io::{Cursor, Read};
+use std::sync::atomic::{AtomicBool, Ordering};
+use std::sync::LazyLock;
+use std::time::{Duration, SystemTime};
+
+const AUTH_TOKEN_URL: &str = "https://oauth.secure.pixiv.net/auth/token";
+const APP_API_URL: &str = "https://app-api.pixiv.net";
+const CLIENT_ID: &str = "MOBrBDS8blbauoSck0ZfDbtuzpyT";
+const CLIENT_SECRET: &str = "lsACyCD94FhDUtGTXi3QzcFE2uU1hqtDaKeqrdwj";
+const AUTH_USER_AGENT: &str = "PixivAndroidApp/5.0.234 (Android 11; Pixel 5)";
+const APP_USER_AGENT: &str = "PixivIOSApp/7.13.3 (iOS 14.6; iPhone13,2)";
+/// Token refresh safe margin (seconds).
+const TOKEN_REFRESH_SAFE_MARGIN: u64 = 300;
+
+#[derive(Debug)]
+pub enum PixivError {
+    /// No refresh token available (PIXIV_REFRESH_TOKEN unset).
+    NoAuth,
+    Http(reqwest::Error),
+    Json(serde_json::Error),
+    Api(String),
+}
+
+impl fmt::Display for PixivError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            PixivError::NoAuth => write!(f, "pixiv: no authentication"),
+            PixivError::Http(e) => write!(f, "pixiv http error: {e}"),
+            PixivError::Json(e) => write!(f, "pixiv json error: {e}"),
+            PixivError::Api(message) => write!(f, "pixiv api error: {message}"),
+        }
+    }
+}
+
+impl std::error::Error for PixivError {
+    fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
+        match self {
+            PixivError::Http(e) => Some(e),
+            PixivError::Json(e) => Some(e),
+            _ => None,
+        }
+    }
+}
+
+impl From<reqwest::Error> for PixivError {
+    fn from(e: reqwest::Error) -> Self {
+        PixivError::Http(e)
+    }
+}
+
+impl From<serde_json::Error> for PixivError {
+    fn from(e: serde_json::Error) -> Self {
+        PixivError::Json(e)
+    }
+}
+
+/// Native pixiv app-API client.
+pub struct PixivAPI {
+    refresh_token: String,
+    access_token: tokio::sync::Mutex<Option<(String, SystemTime)>>,
+}
+
+impl PixivAPI {
+    pub fn new(refresh_token: String) -> Self {
+        Self {
+            refresh_token,
+            access_token: tokio::sync::Mutex::new(None),
+        }
+    }
+
+    /// Returns a valid access token, exchanging the refresh token when none
+    /// is cached or it has expired.
+    pub async fn get_access_token(&self) -> Result<String, PixivError> {
+        let mut guard = self.access_token.lock().await;
+        if let Some((token, expires_at)) = guard.as_ref()
+            && *expires_at > SystemTime::now()
+        {
+            return Ok(token.clone());
+        }
+        let response = crate::site::CLIENT
+            .post(AUTH_TOKEN_URL)
+            .form(&[
+                ("client_id", CLIENT_ID),
+                ("client_secret", CLIENT_SECRET),
+                ("grant_type", "refresh_token"),
+                ("include_policy", "true"),
+                ("refresh_token", &self.refresh_token),
+            ])
+            .header("User-Agent", AUTH_USER_AGENT)
+            .send()
+            .await?;
+        let json: serde_json::Value = serde_json::from_str(&response.text().await?)?;
+        let access_token = json
+            .get("access_token")
+            .and_then(|v| v.as_str())
+            .ok_or_else(|| {
+                let message = json
+                    .get("error")
+                    .and_then(|v| v.as_str())
+                    .unwrap_or("invalid token response");
+                PixivError::Api(message.to_string())
+            })?
+            .to_string();
+        let expires_in = json
+            .get("expires_in")
+            .and_then(|v| v.as_u64())
+            .filter(|&sec| sec > 0)
+            .unwrap_or(3600);
+        let expires_at = SystemTime::now()
+            + Duration::from_secs(expires_in.saturating_sub(TOKEN_REFRESH_SAFE_MARGIN));
+        *guard = Some((access_token.clone(), expires_at));
+        Ok(access_token)
+    }
+
+    /// Fetches illust detail from the app API.
+    pub async fn illust_detail(&self, illust_id: u64) -> Result<IllustrationModel, PixivError> {
+        let access_token = self.get_access_token().await?;
+        let response = crate::site::CLIENT
+            .get(format!("{APP_API_URL}/v1/illust/detail?illust_id={illust_id}"))
+            .header("app-os", "ios")
+            .header("app-os-version", "14.6")
+            .header("User-Agent", APP_USER_AGENT)
+            .bearer_auth(access_token)
+            .send()
+            .await?;
+        let json: serde_json::Value = serde_json::from_str(&response.text().await?)?;
+        if json.get("error").is_some() {
+            let message = json
+                .get("message")
+                .and_then(|v| v.as_str())
+                .unwrap_or("illust detail failed");
+            return Err(PixivError::Api(message.to_string()));
+        }
+        let illust = json
+            .get("illust")
+            .ok_or_else(|| PixivError::Api("missing illust in response".to_string()))?;
+        Ok(serde_json::from_value(illust.clone())?)
+    }
+
+    pub async fn fetch(&self, illust_id: u64) -> Result<Illustration, FetchError> {
+        let model = self.illust_detail(illust_id).await?;
+        let mut illustration = Illustration::from_model(&model);
+        if matches!(&model.r#type, TypeModel::Ugoira) {
+            // Real ugoira support: download the frame zip and encode an MP4.
+            // Without ffmpeg (or on encode failure) the post stays
+            // unsupported (empty media, like Python).
+            match self.ugoira_video(illust_id).await {
+                Ok(Some((mp4_path, _keep_alive))) => {
+                    illustration.media.push(Media::Video {
+                        title: None,
+                        url: mp4_path,
+                        thumbnail_url: model.image_urls.medium.clone(),
+                    });
+                    illustration._keep_alive = Some(_keep_alive);
+                }
+                Ok(None) => {}
+                Err(e) => log::error!("ugoira encode failed for {illust_id}: {e}"),
+            }
+        }
+        Ok(illustration)
+    }
+
+    /// Fetches ugoira metadata (frame zip + frame delays) from the app API.
+    pub async fn ugoira_metadata(&self, illust_id: u64) -> Result<UgoiraMetadataModel, PixivError> {
+        let access_token = self.get_access_token().await?;
+        let response = crate::site::CLIENT
+            .get(format!("{APP_API_URL}/v1/ugoira/metadata?illust_id={illust_id}"))
+            .header("app-os", "ios")
+            .header("app-os-version", "14.6")
+            .header("User-Agent", APP_USER_AGENT)
+            .bearer_auth(access_token)
+            .send()
+            .await?;
+        let json: serde_json::Value = serde_json::from_str(&response.text().await?)?;
+        if json.get("error").is_some() {
+            let message = json
+                .get("message")
+                .and_then(|v| v.as_str())
+                .unwrap_or("ugoira metadata failed");
+            return Err(PixivError::Api(message.to_string()));
+        }
+        let metadata = json
+            .get("ugoira_metadata")
+            .ok_or_else(|| PixivError::Api("missing ugoira_metadata".to_string()))?;
+        Ok(serde_json::from_value(metadata.clone())?)
+    }
+
+    /// Downloads the frame zip and encodes one MP4 via ffmpeg. Returns the
+    /// MP4 path plus the temp directory that must stay alive until the file
+    /// is uploaded.
+    async fn ugoira_video(
+        &self,
+        illust_id: u64,
+    ) -> Result<Option<(String, tempfile::TempDir)>, PixivError> {
+        if !ffmpeg_available() {
+            log_once_ffmpeg_missing();
+            return Ok(None);
+        }
+        let metadata = self.ugoira_metadata(illust_id).await?;
+        if metadata.frames.is_empty() {
+            return Ok(None);
+        }
+        let zip_url = metadata
+            .zip_url
+            .clone()
+            .or_else(|| metadata.zip_urls.as_ref().map(|z| z.medium.clone()));
+        let Some(zip_url) = zip_url else {
+            return Ok(None);
+        };
+        let zip_bytes = crate::site::download_media(&zip_url).await.map_err(|e| match e {
+            FetchError::Http(e) => PixivError::Http(e),
+            other => PixivError::Api(format!("frame zip download failed: {other}")),
+        })?;
+        let frame_delays = metadata.frames.iter().map(|f| f.delay).collect::<Vec<_>>();
+        let result = tokio::task::spawn_blocking(
+            move || -> Result<(String, tempfile::TempDir), String> {
+            let frames_dir = tempfile::tempdir().map_err(|e| e.to_string())?;
+            let out_dir = tempfile::tempdir().map_err(|e| e.to_string())?;
+
+            // Extract frames to canonical zero-padded names; pixiv ugoira
+            // frames are uniformly jpg or png per artwork.
+            let mut archive = zip::ZipArchive::new(Cursor::new(zip_bytes))
+                .map_err(|e| format!("unzip: {e}"))?;
+            // pixiv ugoira frames are uniformly jpg or png per artwork; take
+            // the extension from the first entry.
+            let extension = if archive.len() > 0 {
+                let first_name = archive
+                    .by_index(0)
+                    .map_err(|e| e.to_string())?
+                    .name()
+                    .to_string();
+                first_name
+                    .rsplit('.')
+                    .next()
+                    .unwrap_or("jpg")
+                    .to_string()
+            } else {
+                "jpg".to_string()
+            };
+            let mut count = 0usize;
+            for i in 0..archive.len() {
+                let mut entry = archive.by_index(i).map_err(|e| e.to_string())?;
+                let mut bytes = Vec::new();
+                entry.read_to_end(&mut bytes).map_err(|e| e.to_string())?;
+                let path = frames_dir.path().join(format!("img_{count:05}.{extension}"));
+                std::fs::write(&path, bytes).map_err(|e| e.to_string())?;
+                count += 1;
+            }
+            if count == 0 {
+                return Err("empty frame zip".to_string());
+            }
+
+            // Constant rate from the median frame delay (ms).
+            let mut delays = frame_delays;
+            delays.sort_unstable();
+            let median = delays[delays.len() / 2].max(1);
+            let framerate = 1000.0 / median as f64;
+
+            let output = out_dir.path().join("ugoira.mp4");
+            let status = std::process::Command::new("ffmpeg")
+                .args([
+                    "-y",
+                    "-framerate",
+                    &framerate.to_string(),
+                    "-i",
+                    &frames_dir.path().join(format!("img_%05d.{extension}")).to_string_lossy(),
+                    // libx264 needs even dimensions; pixiv ugoira frames can
+                    // be odd-sized (e.g. 277x405).
+                    "-vf",
+                    "scale=trunc(iw/2)*2:trunc(ih/2)*2",
+                    "-c:v",
+                    "libx264",
+                    "-pix_fmt",
+                    "yuv420p",
+                    "-movflags",
+                    "+faststart",
+                    &output.to_string_lossy(),
+                ])
+                .stdout(std::process::Stdio::null())
+                .stderr(std::process::Stdio::null())
+                .status()
+                .map_err(|e| format!("ffmpeg spawn failed: {e}"))?;
+            if !status.success() {
+                return Err(format!("ffmpeg exited with {status}"));
+            }
+            Ok((output.to_string_lossy().into_owned(), out_dir))
+        },
+        )
+        .await
+        .expect("ugoira encode worker panicked");
+        match result {
+            Ok(pair) => Ok(Some(pair)),
+            Err(message) => {
+                log::error!("ugoira encode failed for {illust_id}: {message}");
+                Ok(None)
+            }
+        }
+    }
+}
+
+static FFMPEG_AVAILABLE: LazyLock<bool> = LazyLock::new(|| {
+    std::process::Command::new("ffmpeg")
+        .arg("-version")
+        .stdout(std::process::Stdio::null())
+        .stderr(std::process::Stdio::null())
+        .status()
+        .map(|s| s.success())
+        .unwrap_or(false)
+});
+
+static FFMPEG_MISSING_LOGGED: AtomicBool = AtomicBool::new(false);
+
+fn ffmpeg_available() -> bool {
+    *FFMPEG_AVAILABLE
+}
+
+fn log_once_ffmpeg_missing() {
+    if !FFMPEG_MISSING_LOGGED.swap(true, Ordering::Relaxed) {
+        log::warn!("ffmpeg not found; pixiv ugoira posts stay unsupported");
+    }
+}
+
+/// pixiv3-rs replacement: `None` when `PIXIV_REFRESH_TOKEN` is unset.
+static PIXIV_CLIENT: LazyLock<Option<PixivAPI>> = LazyLock::new(|| {
+    env::var("PIXIV_REFRESH_TOKEN").ok().map(PixivAPI::new)
+});
+
+/// Set at startup when the login validation fails; pixiv stays disabled until
+/// the next process start.
+static DISABLED: AtomicBool = AtomicBool::new(false);
+
+pub fn enabled() -> bool {
+    !DISABLED.load(Ordering::Relaxed) && env::var("PIXIV_REFRESH_TOKEN").is_ok()
+}
+
+/// Permanently disables pixiv until the next process start.
+pub fn disable() {
+    DISABLED.store(true, Ordering::Relaxed);
+}
+
+/// Forces the refresh-token → access-token exchange now, surfacing invalid
+/// tokens and network errors. Called once at bot startup; on failure the bot
+/// calls [`disable`].
+pub async fn validate() -> Result<(), PixivError> {
+    match PIXIV_CLIENT.as_ref() {
+        None => Err(PixivError::NoAuth),
+        Some(client) => {
+            client.get_access_token().await?;
+            Ok(())
+        }
+    }
+}
+
+pub async fn fetch(illust_id: u64) -> Result<Illustration, FetchError> {
+    let client = PIXIV_CLIENT
+        .as_ref()
+        .filter(|_| enabled())
+        .ok_or(FetchError::Pixiv(PixivError::NoAuth))?;
+    client.fetch(illust_id).await
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use dotenv::dotenv;
+
+    #[tokio::test]
+    async fn test_fetch() {
+        dotenv().ok();
+        let result = fetch(126839080).await;
+        assert!(result.is_ok());
+        println!("{:#?}", result);
+    }
+
+    #[tokio::test]
+    async fn validate_with_bogus_token_fails() {
+        dotenv().ok();
+        // A bogus token must surface as Api error (invalid_grant), not panic.
+        let client = PixivAPI::new("bogus_token_for_testing".to_string());
+        let result = client.get_access_token().await;
+        assert!(matches!(result, Err(PixivError::Api(_))), "got {result:?}");
+    }
+}

crates/x-media/src/site/pixiv/interface.rs

@@ -0,0 +1,375 @@
+use super::model::{IllustrationModel, TypeModel};
+use crate::media::Media;
+use crate::site::{FetchError, Fetched};
+use html_escape::encode_text;
+use regex::Regex;
+use std::sync::LazyLock;
+
+pub static PATTERN: LazyLock<Regex> = LazyLock::new(|| {
+    Regex::new(r"(?:www\.)?pixiv\.net/(?:en/)?(?:(?:i|artworks)/|member_illust\.php\?(?:mode=[a-z_]*&)?illust_id=)(\d+)").unwrap()
+});
+
+pub fn enabled() -> bool {
+    super::api::enabled()
+}
+
+pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
+    let id = PATTERN
+        .captures(url)
+        .and_then(|caps| caps.get(1))
+        .map(|m| m.as_str())
+        .ok_or(FetchError::NotFound)?;
+    let id = id.parse::<u64>().map_err(|_| FetchError::NotFound)?;
+    Ok(super::api::fetch(id).await?.into())
+}
+
+#[derive(Debug)]
+pub struct Illustration {
+    id: String,
+    title: String,
+    author: String,
+    author_id: String,
+    tags: Vec<String>,
+    pub(crate) media: Vec<Media>,
+    nsfw: bool,
+    /// Keeps a temp dir (ugoira MP4) alive until the send completes.
+    pub(crate) _keep_alive: Option<tempfile::TempDir>,
+}
+
+impl Illustration {
+    fn url(&self) -> String {
+        format!("https://www.pixiv.net/artworks/{}", self.id)
+    }
+
+    fn author_url(&self) -> String {
+        format!("https://www.pixiv.net/users/{}", self.author_id)
+    }
+
+    pub fn caption(&self) -> String {
+        format!(
+            "<a href=\"{url}\">{title}</a> / <a href=\"{author_url}\">{author}</a>\n{tags}",
+            url = self.url(),
+            title = encode_text(&self.title),
+            author_url = self.author_url(),
+            author = encode_text(&self.author),
+            tags = encode_text(
+                &self
+                    .tags
+                    .iter()
+                    .map(|tag| format!("#{tag}"))
+                    .collect::<Vec<_>>()
+                    .join(" ")
+            ),
+        )
+    }
+
+    pub fn from_model(model: &IllustrationModel) -> Self {
+        let id = model.id.to_string();
+        let title = model.title.clone();
+        let author = model.user.name.clone();
+        let author_id = model.user.id.to_string();
+        let mut tags: Vec<String> = model.tags.iter().map(|tag| tag.name.clone()).collect();
+        // illust_ai_type: 0 = undefined, 1 = not AI, 2 = AI-generated.
+        // Mark AI works with a leading #AI tag (rendered via the `#{tag}`
+        // caption format).
+        if model.illust_ai_type == 2 {
+            tags.insert(0, "AI".to_string());
+        }
+        let mut media = vec![];
+        if matches!(&model.r#type, TypeModel::Ugoira) {
+            // No static images for ugoira; the fetch path encodes an MP4 via
+            // ffmpeg and appends it as a Video item (api.rs). This fallback
+            // keeps media empty when encoding fails or ffmpeg is missing.
+        } else if model.page_count > 1 {
+            media.extend(model.meta_pages.iter().filter_map(|page| {
+                page.image_urls.original.clone().map(|original| Media::Illustration {
+                    title: None,
+                    url: original,
+                    thumbnail_url: Some(page.image_urls.medium.clone()),
+                    fallback_url: Some(page.image_urls.large.clone()),
+                })
+            }));
+        } else if let Some(original) = model
+            .meta_single_page
+            .original_image_url
+            .clone()
+            .or(model.image_urls.original.clone())
+        {
+            media.push(Media::Illustration {
+                title: None,
+                url: original,
+                thumbnail_url: Some(model.image_urls.medium.clone()),
+                fallback_url: Some(model.image_urls.large.clone()),
+            });
+        }
+        let nsfw = model.sanity_level > 5;
+        Self {
+            id,
+            title,
+            author,
+            author_id,
+            tags,
+            media,
+            nsfw,
+            _keep_alive: None,
+        }
+    }
+}
+
+impl From<Illustration> for Fetched {
+    fn from(illustration: Illustration) -> Self {
+        let url = illustration.url();
+        let author_url = illustration.author_url();
+        let tags = illustration
+            .tags
+            .iter()
+            .map(|tag| format!("#{tag}"))
+            .collect::<Vec<_>>()
+            .join(" ");
+        let render_data = Some(crate::site::RenderData {
+            url: url.clone(),
+            author: encode_text(&illustration.author).into_owned(),
+            author_url: author_url.clone(),
+            title: encode_text(&illustration.title).into_owned(),
+            tags: encode_text(&tags).into_owned(),
+        });
+        Fetched {
+            source_url: url,
+            caption: illustration.caption(),
+            title: illustration.title.clone(),
+            media: illustration.media,
+            sensitive: illustration.nsfw,
+            render_data,
+            _keep_alive: illustration._keep_alive,
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use super::super::model::IllustrationModel;
+
+    fn illust_json(
+        type_: &str,
+        page_count: u8,
+        single_original: Option<&str>,
+        image_urls_original: Option<&str>,
+        pages: Vec<(Option<&str>, &str, &str)>,
+        ai_type: i32,
+    ) -> serde_json::Value {
+        let meta_pages: Vec<serde_json::Value> = pages
+            .into_iter()
+            .map(|(original, medium, large)| {
+                serde_json::json!({
+                    "image_urls": {
+                        "medium": medium,
+                        "large": large,
+                        "original": original
+                    }
+                })
+            })
+            .collect();
+        serde_json::json!({
+            "illust": {
+                "id": 123,
+                "title": "Art <title>",
+                "type": type_,
+                "image_urls": {
+                    "medium": "medium.jpg",
+                    "large": "large.jpg",
+                    "original": image_urls_original
+                },
+                "user": { "id": 456, "name": "Artist" },
+                "tags": [{ "name": "tag1" }, { "name": "tag2" }],
+                "page_count": page_count,
+                "sanity_level": 6,
+                "illust_ai_type": ai_type,
+                "meta_single_page": { "original_image_url": single_original },
+                "meta_pages": meta_pages
+            }
+        })
+    }
+
+    fn parse(v: serde_json::Value) -> Illustration {
+        let model: IllustrationModel = serde_json::from_value(v["illust"].clone()).unwrap();
+        Illustration::from_model(&model)
+    }
+
+    #[test]
+    fn pattern_matches_all_forms() {
+        let cases = [
+            ("https://www.pixiv.net/artworks/123456", "123456"),
+            ("https://pixiv.net/artworks/123456", "123456"),
+            ("https://www.pixiv.net/en/artworks/123456", "123456"),
+            ("https://www.pixiv.net/i/123456", "123456"),
+            ("https://www.pixiv.net/member_illust.php?mode=medium&illust_id=123456", "123456"),
+            ("https://www.pixiv.net/en/member_illust.php?illust_id=123456", "123456"),
+        ];
+        for (url, id) in cases {
+            let caps = PATTERN.captures(url).unwrap_or_else(|| panic!("{url}"));
+            assert_eq!(caps.get(1).unwrap().as_str(), id);
+        }
+    }
+
+    #[test]
+    fn pattern_rejects_non_artwork_urls() {
+        for url in [
+            "https://www.pixiv.net/users/123",
+            "https://x.com/user/status/123",
+            "https://bsky.app/profile/u/post/3xxxx",
+        ] {
+            assert!(!PATTERN.is_match(url), "{url}");
+        }
+    }
+
+    #[test]
+    fn ugoira_yields_empty_media() {
+        let v = illust_json("ugoira", 1, Some("https://i.pximg.net/orig.jpg"), None, vec![], 0);
+        let illustration = parse(v);
+        let fetched: Fetched = illustration.into();
+        assert!(fetched.media.is_empty());
+        assert!(fetched.sensitive, "sanity_level 6 > 5");
+        assert_eq!(fetched.title, "Art <title>");
+    }
+
+    #[test]
+    fn single_page_with_single_original() {
+        let v = illust_json(
+            "illust",
+            1,
+            Some("https://i.pximg.net/single.jpg"),
+            None,
+            vec![],
+            0,
+        );
+        let fetched: Fetched = parse(v).into();
+        assert_eq!(fetched.media.len(), 1);
+        match &fetched.media[0] {
+            Media::Illustration { url, .. } => {
+                assert_eq!(url, "https://i.pximg.net/single.jpg")
+            }
+            other => panic!("expected Illustration, got {other:?}"),
+        }
+    }
+
+    #[test]
+    fn single_page_falls_back_to_image_urls_original() {
+        let v = illust_json(
+            "illust",
+            1,
+            None,
+            Some("https://i.pximg.net/fallback.jpg"),
+            vec![],
+            0,
+        );
+        let fetched: Fetched = parse(v).into();
+        assert_eq!(fetched.media.len(), 1);
+        match &fetched.media[0] {
+            Media::Illustration { url, .. } => {
+                assert_eq!(url, "https://i.pximg.net/fallback.jpg")
+            }
+            other => panic!("expected Illustration, got {other:?}"),
+        }
+    }
+
+    #[test]
+    fn single_page_without_any_original_is_empty() {
+        let v = illust_json("illust", 1, None, None, vec![], 0);
+        let fetched: Fetched = parse(v).into();
+        assert!(fetched.media.is_empty());
+    }
+
+    #[test]
+    fn multi_page_skips_pages_without_original() {
+        let v = illust_json(
+            "illust",
+            2,
+            None,
+            None,
+            vec![
+                (None, "m1.jpg", "l1.jpg"),
+                (Some("https://i.pximg.net/p2.jpg"), "m2.jpg", "l2.jpg"),
+            ],
+            0,
+        );
+        let fetched: Fetched = parse(v).into();
+        assert_eq!(fetched.media.len(), 1);
+        match &fetched.media[0] {
+            Media::Illustration { url, thumbnail_url, fallback_url, .. } => {
+                assert_eq!(url, "https://i.pximg.net/p2.jpg");
+                assert_eq!(thumbnail_url.as_deref(), Some("m2.jpg"));
+                assert_eq!(fallback_url.as_deref(), Some("l2.jpg"));
+            }
+            other => panic!("expected Illustration, got {other:?}"),
+        }
+    }
+
+    #[test]
+    fn caption_with_escapes_format_and_substitutes() {
+        let v = illust_json("illust", 1, Some("https://i.pximg.net/o.jpg"), None, vec![], 0);
+        let fetched: Fetched = parse(v).into();
+        // Format string is escaped in full, then placeholders substituted.
+        let out = fetched.caption_with("{title} by {author} <script> {tags}");
+        assert!(
+            out.contains("Art &lt;title&gt; by Artist &lt;script&gt; #tag1 #tag2"),
+            "got: {out}"
+        );
+        assert!(!out.contains("<script>"), "no raw HTML injection: {out}");
+        // {url} and {author_url} carry the site's own URLs.
+        let out = fetched.caption_with("{url} {author_url}");
+        assert_eq!(
+            out,
+            "https://www.pixiv.net/artworks/123 https://www.pixiv.net/users/456"
+        );
+        // Empty format falls back to the built-in caption.
+        assert_eq!(fetched.caption_with(""), fetched.caption);
+        assert_eq!(fetched.site_name(), "pixiv");
+    }
+
+    #[test]
+    fn ai_work_gets_leading_ai_tag() {
+        // illust_ai_type == 2 is the only AI marker.
+        let v = illust_json("illust", 1, Some("https://i.pximg.net/o.jpg"), None, vec![], 2);
+        let fetched: Fetched = parse(v).into();
+        assert!(
+            fetched.caption.contains("#AI #tag1 #tag2"),
+            "caption: {}",
+            fetched.caption
+        );
+        // The {tags} placeholder reflects the tag array too.
+        assert!(fetched.caption_with("{tags}").starts_with("#AI "), "got: {}", fetched.caption_with("{tags}"));
+    }
+
+    #[test]
+    fn non_ai_work_has_no_ai_tag() {
+        // 1 = explicitly not AI, 0 = undefined: neither gets the #AI tag.
+        for ai_type in [0, 1] {
+            let v = illust_json("illust", 1, Some("https://i.pximg.net/o.jpg"), None, vec![], ai_type);
+            let fetched: Fetched = parse(v).into();
+            assert!(
+                !fetched.caption.contains("#AI"),
+                "ai_type={ai_type} got: {}",
+                fetched.caption
+            );
+        }
+    }
+
+    #[test]
+    fn caption_escapes_and_links() {
+        let v = illust_json("illust", 1, Some("https://i.pximg.net/o.jpg"), None, vec![], 0);
+        let fetched: Fetched = parse(v).into();
+        assert!(
+            fetched
+                .caption
+                .contains("<a href=\"https://www.pixiv.net/artworks/123\">Art &lt;title&gt;</a>"),
+            "caption: {}",
+            fetched.caption
+        );
+        assert!(fetched.caption.contains("#tag1 #tag2"));
+        assert_eq!(
+            fetched.source_url,
+            "https://www.pixiv.net/artworks/123"
+        );
+    }
+}

crates/x-media/src/site/pixiv/mod.rs

@@ -0,0 +1,6 @@
+mod api;
+mod interface;
+mod model;
+
+pub use api::{PixivAPI, PixivError, disable, fetch, validate};
+pub use interface::{PATTERN, Illustration, enabled, fetch_from_url};

crates/x-media/src/site/pixiv/model.rs

@@ -0,0 +1,79 @@
+// Model set for the native pixiv app-API client (app-api.pixiv.net).
+
+use serde::Deserialize;
+
+#[derive(Deserialize, Debug)]
+pub struct IllustrationModel {
+    pub id: u64,
+    pub title: String,
+    pub r#type: TypeModel,
+    pub image_urls: ImageUrlsModel,
+    pub user: UserInfoModel,
+    pub tags: Vec<IllustrationTagModel>,
+    pub page_count: u8,
+    pub sanity_level: u8,
+    /// 0 = undefined (unlabeled), 1 = not AI, 2 = AI-generated.
+    pub illust_ai_type: i32,
+    pub meta_single_page: MetaSinglePageModel,
+    pub meta_pages: Vec<MetaPageModel>,
+}
+
+#[derive(Deserialize, Debug)]
+pub enum TypeModel {
+    #[serde(rename = "illust")]
+    Illust,
+    #[serde(rename = "manga")]
+    Manga,
+    #[serde(rename = "ugoira")]
+    Ugoira,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct UserInfoModel {
+    pub id: u64,
+    pub name: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct ImageUrlsModel {
+    pub medium: String,
+    pub large: String,
+    #[serde(default)]
+    pub original: Option<String>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct IllustrationTagModel {
+    pub name: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct MetaSinglePageModel {
+    #[serde(default)]
+    pub original_image_url: Option<String>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct MetaPageModel {
+    pub image_urls: ImageUrlsModel,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct UgoiraMetadataModel {
+    /// Older API shape (`zip_url`); newer responses use `zip_urls.medium`.
+    #[serde(default)]
+    pub zip_url: Option<String>,
+    #[serde(default)]
+    pub zip_urls: Option<UgoiraZipUrlsModel>,
+    pub frames: Vec<UgoiraFrameModel>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct UgoiraZipUrlsModel {
+    pub medium: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct UgoiraFrameModel {
+    pub delay: u32,
+}

crates/x-media/src/site/twitter/auth.rs

@@ -0,0 +1,376 @@
+//! Authenticated fallback for tweets the public syndication endpoint refuses
+//! to serve (NSFW / age-restricted tweets come back as an empty `{}`).
+//!
+//! Mirrors nazurin's web API client ([`web.py`]) and is used *only* when
+//! syndication reports [`FetchError::Sensitive`]: the private GraphQL
+//! `TweetDetail` endpoint, authenticated with a browser session cookie from
+//! `TWITTER_AUTH_TOKEN` (the `auth_token` cookie value of a logged-in x.com
+//! session). A fresh random `ct0` is generated per call; X checks that the
+//! `x-csrf-token` header matches the cookie, not that it issued the value.
+//!
+//! [`web.py`]: https://github.com/y-young/nazurin/blob/master/nazurin/sites/twitter/api/web.py
+//!
+//! # Caveats
+//! - X rotates the GraphQL query id when it rolls the web app; if requests
+//!   start failing, update [`TWEET_DETAIL_QUERY_ID`]. Fresh references from
+//!   the actively maintained FxEmbed/FxEmbed: TweetDetail
+//!   `R9IzzyzQBV87-DOWpcvDmw`, TweetResultByRestId `f2sagi1jweVHFkTUIHzmMQ`
+//!   (the latter is anonymous and surfaces NSFW tweets as
+//!   `reason: NsfwLoggedOut`).
+//! - `x-client-transaction-id` is only required for `SearchTimeline`
+//!   (verified against FxEmbed's `proxy/allowlist.ts`) — TweetDetail works
+//!   without it; no need for the nazurin home-page/JS-bundle derivation.
+
+use std::sync::LazyLock;
+
+use serde_json::{json, Value};
+
+use crate::site::FetchError;
+
+use super::interface::Tweet;
+
+/// `auth_token` cookie of a logged-in x.com session; enables the fallback.
+/// Trimmed: a CRLF `.env` (Windows) leaves a trailing `\r` on the value,
+/// which would make the Cookie header invalid.
+static AUTH_TOKEN: LazyLock<Option<String>> = LazyLock::new(|| {
+    std::env::var("TWITTER_AUTH_TOKEN")
+        .ok()
+        .map(|s| s.trim().to_string())
+        .filter(|s| !s.is_empty())
+});
+
+/// Public "logged in" client token used by the x.com web app.
+const LOGGED_IN_BEARER: &str =
+    "Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA";
+
+/// `TweetDetail` query id (from nazurin; still valid as of 2026-08,
+/// corroborated by the current FxEmbed build — see module caveats).
+const TWEET_DETAIL_QUERY_ID: &str = "_8aYOgEDz35BrBcBal1-_w";
+
+fn variables(id: &str) -> Value {
+    json!({
+        "focalTweetId": id,
+        "with_rux_injections": false,
+        "includePromotedContent": false,
+        "withCommunity": true,
+        "withQuickPromoteEligibilityTweetFields": false,
+        "withBirdwatchNotes": false,
+        "withVoice": true,
+    })
+}
+
+fn features() -> Value {
+    json!({
+        "rweb_video_screen_enabled": false,
+        "profile_label_improvements_pcf_label_in_post_enabled": true,
+        "rweb_tipjar_consumption_enabled": true,
+        "verified_phone_label_enabled": false,
+        "creator_subscriptions_tweet_preview_api_enabled": true,
+        "responsive_web_graphql_timeline_navigation_enabled": true,
+        "responsive_web_graphql_skip_user_profile_image_extensions_enabled": false,
+        "premium_content_api_read_enabled": false,
+        "communities_web_enable_tweet_community_results_fetch": true,
+        "c9s_tweet_anatomy_moderator_badge_enabled": true,
+        "responsive_web_grok_analyze_button_fetch_trends_enabled": false,
+        "responsive_web_grok_analyze_post_followups_enabled": true,
+        "responsive_web_jetfuel_frame": false,
+        "responsive_web_grok_share_attachment_enabled": true,
+        "articles_preview_enabled": true,
+        "responsive_web_edit_tweet_api_enabled": true,
+        "graphql_is_translatable_rweb_tweet_is_translatable_enabled": true,
+        "view_counts_everywhere_api_enabled": true,
+        "longform_notetweets_consumption_enabled": true,
+        "responsive_web_twitter_article_tweet_consumption_enabled": true,
+        "tweet_awards_web_tipping_enabled": false,
+        "responsive_web_grok_show_grok_translated_post": false,
+        "responsive_web_grok_analysis_button_from_backend": true,
+        "creator_subscriptions_quote_tweet_preview_enabled": false,
+        "freedom_of_speech_not_reach_fetch_enabled": true,
+        "standardized_nudges_misinfo": true,
+        "tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled": true,
+        "longform_notetweets_rich_text_read_enabled": true,
+        "longform_notetweets_inline_media_enabled": true,
+        "responsive_web_grok_image_annotation_enabled": true,
+        "responsive_web_enhance_cards_enabled": false,
+    })
+}
+
+/// Whether the authenticated fallback is available.
+pub fn enabled() -> bool {
+    AUTH_TOKEN.is_some()
+}
+
+/// Fetches a tweet as the logged-in user via the private GraphQL API.
+/// Returns the syndication-shaped [`Tweet`] (media included for NSFW posts).
+pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
+    let token = AUTH_TOKEN
+        .as_deref()
+        .ok_or(FetchError::Sensitive)?;
+    // 16 random bytes as 32 hex chars: X rejects ct0 values of any other
+    // length with 403 code 353 ("matching csrf cookie and header").
+    let ct0: String = (0..16)
+        .map(|_| format!("{:02x}", rand::random::<u8>()))
+        .collect();
+
+    let response = crate::site::CLIENT
+        .get(format!(
+            "https://x.com/i/api/graphql/{TWEET_DETAIL_QUERY_ID}/TweetDetail"
+        ))
+        .query(&[
+            ("variables", variables(id).to_string()),
+            ("features", features().to_string()),
+        ])
+        .header("authorization", LOGGED_IN_BEARER)
+        .header("x-csrf-token", &ct0)
+        .header("x-twitter-auth-type", "OAuth2Session")
+        .header("cookie", format!("auth_token={token}; ct0={ct0}"))
+        .header("x-twitter-client-language", "en")
+        .header("x-twitter-active-user", "yes")
+        .header("referer", "https://x.com/")
+        .send()
+        .await?;
+    if !response.status().is_success() {
+        log::warn!("twitter auth fetch {id}: HTTP {}", response.status());
+        return Err(FetchError::NotFound);
+    }
+    let text = response.text().await?;
+    let json: Value = serde_json::from_str(&text)?;
+    let result = parse_tweet_result(&json, id)?;
+    let syndication_shape = to_syndication_shape(&result)
+        .ok_or_else(|| FetchError::Json(serde_json::Error::io(std::io::Error::new(
+            std::io::ErrorKind::InvalidData,
+            "missing tweet fields in GraphQL response",
+        ))))?;
+    Tweet::from_syndication_json(&syndication_shape.to_string()).map_err(FetchError::Json)
+}
+
+/// Locates the tweet for `id` in a `TweetDetail` response and unwraps
+/// visibility wrappers / retweets, mirroring nazurin's `_process_response`.
+fn parse_tweet_result(json: &Value, id: &str) -> Result<Value, FetchError> {
+    if let Some(errors) = json.get("errors").and_then(|e| e.as_array()) {
+        let messages: Vec<&str> = errors
+            .iter()
+            .filter_map(|e| e.get("message").and_then(|m| m.as_str()))
+            .collect();
+        log::warn!("twitter auth fetch {id} failed: {}", messages.join("; "));
+        return Err(FetchError::NotFound);
+    }
+
+    let instructions = json
+        .pointer("/data/threaded_conversation_with_injections_v2/instructions")
+        .and_then(|v| v.as_array())
+        .ok_or(FetchError::NotFound)?;
+    for instruction in instructions {
+        if instruction.get("type").and_then(|t| t.as_str()) != Some("TimelineAddEntries") {
+            continue;
+        }
+        let entries = instruction
+            .get("entries")
+            .and_then(|e| e.as_array())
+            .ok_or(FetchError::NotFound)?;
+        let wanted = format!("tweet-{id}");
+        for entry in entries {
+            if entry.get("entryId").and_then(|i| i.as_str()) == Some(wanted.as_str()) {
+                let result = entry
+                    .pointer("/content/itemContent/tweet_results/result")
+                    .ok_or(FetchError::NotFound)?;
+                return normalize_tweet_result(result);
+            }
+        }
+    }
+    Err(FetchError::NotFound)
+}
+
+/// Unwraps TweetTombstone/TweetUnavailable errors, the
+/// TweetWithVisibilityResults wrapper and retweets, returning the
+/// `{core, legacy, ...}` tweet object.
+fn normalize_tweet_result(result: &Value) -> Result<Value, FetchError> {
+    match result.get("__typename").and_then(|t| t.as_str()) {
+        Some("TweetTombstone") => {
+            let text = result
+                .pointer("/tombstone/text/text")
+                .and_then(|t| t.as_str())
+                .unwrap_or("tweet is unavailable");
+            log::warn!("twitter auth fetch: tombstone: {text}");
+            return Err(FetchError::NotFound);
+        }
+        Some("TweetUnavailable") => {
+            let reason = result
+                .get("reason")
+                .and_then(|r| r.as_str())
+                .unwrap_or("unknown");
+            log::warn!("twitter auth fetch: tweet unavailable: {reason}");
+            return Err(FetchError::NotFound);
+        }
+        _ => {}
+    }
+
+    // TweetWithVisibilityResults (e.g. limited replies) nests the real tweet.
+    let tweet = result.get("tweet").unwrap_or(result);
+    // A retweet's media lives on the original tweet.
+    if let Some(original) = tweet.pointer("/legacy/retweeted_status_result/result") {
+        return Ok(original.clone());
+    }
+    Ok(tweet.clone())
+}
+
+/// Maps a GraphQL `{core, legacy, ...}` tweet onto the syndication JSON
+/// shape [`Tweet::from_syndication_json`] parses, so the existing text /
+/// media handling (t.co expansion, `name=orig`, mp4 variant) is reused.
+fn to_syndication_shape(tweet: &Value) -> Option<Value> {
+    let legacy = tweet.get("legacy")?;
+    let user = tweet.pointer("/core/user_results/result/legacy")?;
+    Some(json!({
+        "id_str": legacy.get("id_str"),
+        "text": legacy.get("full_text"),
+        "user": {
+            "name": user.get("name"),
+            "screen_name": user.get("screen_name"),
+        },
+        "possibly_sensitive": legacy.get("possibly_sensitive"),
+        "display_text_range": legacy.get("display_text_range"),
+        "entities": legacy.get("entities"),
+        "mediaDetails": legacy.pointer("/extended_entities/media"),
+    }))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn tweet_result() -> Value {
+        json!({
+            "__typename": "Tweet",
+            "core": {
+                "user_results": {
+                    "result": {
+                        "legacy": { "name": "Display Name", "screen_name": "nsfw_author" }
+                    }
+                }
+            },
+            "legacy": {
+                "id_str": "2083868672721039569",
+                "full_text": "nsfw content https://t.co/abc123",
+                "display_text_range": [0, 12],
+                "possibly_sensitive": true,
+                "entities": {
+                    "urls": [
+                        { "url": "https://t.co/abc123", "expanded_url": "https://example.com/x" }
+                    ]
+                },
+                "extended_entities": {
+                    "media": [
+                        {
+                            "type": "photo",
+                            "media_url_https": "https://pbs.twimg.com/media/nsfw.jpg",
+                            "original_info": { "width": 1200, "height": 800 }
+                        },
+                        {
+                            "type": "video",
+                            "media_url_https": "https://pbs.twimg.com/thumb.jpg",
+                            "video_info": {
+                                "variants": [
+                                    { "content_type": "application/x-mpegURL", "url": "https://x.com/pl.m3u8" },
+                                    { "content_type": "video/mp4", "url": "https://video.twimg.com/nsfw.mp4" }
+                                ]
+                            }
+                        }
+                    ]
+                }
+            }
+        })
+    }
+
+    fn conversation(tweet: Value) -> Value {
+        json!({
+            "data": {
+                "threaded_conversation_with_injections_v2": {
+                    "instructions": [
+                        { "type": "TimelineAddEntries", "entries": [
+                            { "entryId": "tweet-2083868672721039569",
+                              "content": { "itemContent": { "tweet_results": { "result": tweet } } } }
+                        ]}
+                    ]
+                }
+            }
+        })
+    }
+
+    #[test]
+    fn parses_graphql_tweet_into_fetched() {
+        let json = conversation(tweet_result());
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        let shape = to_syndication_shape(&result).unwrap();
+        let tweet = Tweet::from_syndication_json(&shape.to_string()).unwrap();
+        let fetched: crate::site::Fetched = tweet.into();
+
+        assert!(fetched.sensitive);
+        assert_eq!(fetched.media.len(), 2);
+        match &fetched.media[0] {
+            crate::media::Media::Illustration { url, .. } => {
+                assert_eq!(url, "https://pbs.twimg.com/media/nsfw.jpg?name=orig");
+            }
+            other => panic!("expected illustration, got {other:?}"),
+        }
+        match &fetched.media[1] {
+            crate::media::Media::Video { url, .. } => {
+                assert_eq!(url, "https://video.twimg.com/nsfw.mp4");
+            }
+            other => panic!("expected video, got {other:?}"),
+        }
+        assert_eq!(fetched.source_url, "https://x.com/nsfw_author/status/2083868672721039569");
+        // display_text_range cuts the trailing t.co link.
+        assert_eq!(fetched.title, "nsfw content");
+    }
+
+    #[test]
+    fn unwraps_retweet_to_original() {
+        let original = tweet_result();
+        let mut rt = tweet_result();
+        rt["legacy"]["retweeted_status_result"] = json!({ "result": original });
+        let json = conversation(rt);
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        assert!(result.pointer("/legacy/retweeted_status_result").is_none());
+        assert_eq!(result.pointer("/legacy/id_str").unwrap(), "2083868672721039569");
+    }
+
+    #[test]
+    fn error_response_maps_to_not_found() {
+        let json = json!({ "errors": [{ "message": "NsfwLoggedOut" }] });
+        assert!(matches!(
+            parse_tweet_result(&json, "1"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn missing_entry_maps_to_not_found() {
+        let json = conversation(json!({ "__typename": "Tweet" }));
+        assert!(matches!(
+            parse_tweet_result(&json, "999"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn tombstone_maps_to_not_found() {
+        let tombstone = json!({
+            "__typename": "TweetTombstone",
+            "tombstone": { "text": { "text": "Age-restricted adult content" } }
+        });
+        let json = conversation(tombstone);
+        assert!(matches!(
+            parse_tweet_result(&json, "2083868672721039569"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn visibility_wrapper_unwraps() {
+        let inner = tweet_result();
+        let wrapped = json!({ "__typename": "TweetWithVisibilityResults", "tweet": inner });
+        let json = conversation(wrapped);
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        assert_eq!(result.get("__typename").unwrap(), "Tweet");
+    }
+}

crates/x-media/src/site/twitter/interface.rs

@@ -0,0 +1,552 @@
+use super::model;
+use crate::media::Media;
+use crate::site::{FetchError, Fetched};
+use html_escape::encode_text;
+use regex::Regex;
+use std::sync::LazyLock;
+
+pub static PATTERN: LazyLock<Regex> = LazyLock::new(|| {
+    Regex::new(r"^(?:https?://)?(?:www\.|mobile\.)?(?:x|twitter|fixvx|vxtwitter|fixupx|fxtwitter)\.com/[^.]+/status/(\d+)").unwrap()
+});
+
+pub fn enabled() -> bool {
+    true
+}
+
+pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
+    let id = PATTERN
+        .captures(url)
+        .and_then(|caps| caps.get(1))
+        .map(|m| m.as_str())
+        .ok_or(FetchError::NotFound)?;
+    match fetch(id).await {
+        Ok(tweet) => Ok(tweet.into()),
+        // Syndication withholds NSFW/age-restricted tweets (empty `{}`).
+        // Retry as the logged-in user when TWITTER_AUTH_TOKEN is set;
+        // otherwise degrade to an empty result (the bot replies
+        // "No media found").
+        Err(FetchError::Sensitive) => {
+            if super::auth::enabled() {
+                match super::auth::fetch(id).await {
+                    Ok(tweet) => Ok(tweet.into()),
+                    Err(e) => {
+                        log::warn!("twitter auth fallback failed for {id}: {e}");
+                        Ok(empty_fetched(url))
+                    }
+                }
+            } else {
+                log::info!(
+                    "tweet {id} is sensitive; set TWITTER_AUTH_TOKEN to fetch NSFW media"
+                );
+                Ok(empty_fetched(url))
+            }
+        }
+        Err(e) => Err(e),
+    }
+}
+
+/// A Fetched with no media for withheld tweets: the bot replies
+/// "No media found" and moves on instead of erroring.
+fn empty_fetched(url: &str) -> Fetched {
+    Fetched {
+        source_url: url.to_string(),
+        caption: url.to_string(),
+        title: String::new(),
+        media: vec![],
+        sensitive: true,
+        render_data: None,
+        _keep_alive: None,
+    }
+}
+
+/// Fetches a tweet from the syndication endpoint. Deleted/blocked tweets
+/// surface as `FetchError::NotFound`.
+pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
+    let id_num = id.parse::<u64>().map_err(|_| FetchError::NotFound)?;
+    let response = crate::site::CLIENT
+        .get(format!(
+            "https://cdn.syndication.twimg.com/tweet-result?id={id}&lang=en&token={}",
+            syndication_token(id_num)
+        ))
+        .send()
+        .await?;
+    if !response.status().is_success() {
+        return Err(FetchError::NotFound);
+    }
+    let text = response.text().await?;
+    // Deleted tweets answer with {"errors": [...]} instead of a tweet.
+    if serde_json::from_str::<serde_json::Value>(&text)
+        .map(|v| v.get("errors").is_some())
+        .unwrap_or(false)
+    {
+        return Err(FetchError::NotFound);
+    }
+    // NSFW / age-restricted tweets exist but are served as an empty `{}` —
+    // they surface as FetchError::Sensitive so the caller can retry as a
+    // logged-in user.
+    if serde_json::from_str::<serde_json::Value>(&text)
+        .map(|v| v.get("id_str").is_none())
+        .unwrap_or(false)
+    {
+        return Err(FetchError::Sensitive);
+    }
+    Ok(Tweet::from_syndication_json(&text).map_err(FetchError::Json)?)
+}
+
+/// The syndication token: JS `((id / 1e15) * PI).toString(36)` (the
+/// `replace('0.','')` is a no-op for realistic tweet ids). The endpoint
+/// currently serves public tweets regardless of the token; the formula is
+/// kept for parity with the known-good client behavior.
+fn syndication_token(id: u64) -> String {
+    let value = (id as f64 / 1e15) * std::f64::consts::PI;
+    let integer = value.trunc() as u64;
+    let mut fraction = value.fract();
+    let mut digits = String::new();
+    if integer == 0 {
+        digits.push('0');
+    } else {
+        let mut n = integer;
+        let mut buf = Vec::new();
+        while n > 0 {
+            buf.push(char::from_digit((n % 36) as u32, 36).unwrap());
+            n /= 36;
+        }
+        digits.extend(buf.into_iter().rev());
+    }
+    digits.push('.');
+    for _ in 0..10 {
+        fraction *= 36.0;
+        let digit = fraction.trunc() as u32;
+        digits.push(char::from_digit(digit.min(35), 36).unwrap());
+        fraction -= digit as f64;
+        if fraction == 0.0 {
+            break;
+        }
+    }
+    digits
+}
+
+#[derive(Debug)]
+pub struct Tweet {
+    id: String,
+    text: String,
+    author: String,
+    author_id: String,
+    media: Vec<Media>,
+    sensitive: bool,
+}
+
+impl Tweet {
+    fn url(&self) -> String {
+        format!("{}/status/{}", self.author_url(), self.id)
+    }
+
+    fn author_url(&self) -> String {
+        format!("https://x.com/{}", self.author_id)
+    }
+
+    pub fn caption(&self) -> String {
+        format!(
+            "{url}\n<a href=\"{author_url}\">{author}</a>: {text}",
+            url = self.url(),
+            author_url = self.author_url(),
+            author = encode_text(&self.author),
+            text = encode_text(&self.text),
+        )
+    }
+
+    pub fn from_syndication_json(raw_json: &str) -> Result<Self, serde_json::Error> {
+        let json: model::SyndicationTweet = serde_json::from_str(raw_json)?;
+        let id = json.id_str;
+        // Strip the appended media short link first, then expand the remaining
+        // t.co short links (the user's own URLs) to their real destinations.
+        let text = expand_links(
+            &strip_trailing_short_links(&json.text, json.display_text_range),
+            &json.entities.urls,
+        );
+        // `name` is the display name, `screen_name` the handle (Python's
+        // vxtwitter mapping: author = display name, author_id = handle).
+        let author = json.user.name;
+        let author_id = json.user.screen_name;
+        let mut media = vec![];
+        for item in json.media_details {
+            match item.media_type.as_str() {
+                "photo" => media.push(Media::Illustration {
+                    title: None,
+                    url: original_twimg_url(&item.media_url_https),
+                    thumbnail_url: None,
+                    // The param-less base URL is a reduced-size variant;
+                    // used as the fallback when the original is too large.
+                    fallback_url: Some(item.media_url_https.clone()),
+                }),
+                "video" => media.push(Media::Video {
+                    title: None,
+                    url: mp4_variant(&item),
+                    thumbnail_url: item.media_url_https,
+                }),
+                "animated_gif" => media.push(Media::Animated {
+                    title: None,
+                    url: mp4_variant(&item),
+                    thumbnail_url: item.media_url_https,
+                }),
+                _ => {}
+            }
+        }
+        let sensitive = json.possibly_sensitive.unwrap_or(false);
+        Ok(Self {
+            id,
+            text,
+            author,
+            author_id,
+            media,
+            sensitive,
+        })
+    }
+}
+
+/// The raw syndication `text` ends with the appended media short link
+/// (" https://t.co/wmI8McgXul"). `display_text_range` marks the visible text;
+/// a regex strips any remaining trailing t.co link when the range is absent
+/// or a tweet ends in a URL short link.
+///
+/// X reports these indices in Unicode **code points**, not UTF-16 units
+/// (verified against GraphQL responses containing emoji: cutting an emoji
+/// tweet by UTF-16 units silently drops the character after the emoji).
+fn strip_trailing_short_links(text: &str, display_text_range: Option<[usize; 2]>) -> String {
+    let mut out = match display_text_range {
+        Some([start, end]) if start < end => {
+            text.chars().skip(start).take(end - start).collect()
+        }
+        _ => text.to_string(),
+    };
+    while TRAILING_TCO.is_match(&out) {
+        out = TRAILING_TCO.replace(&out, "").into_owned();
+    }
+    out
+}
+
+/// Trailing Twitter short link, optionally preceded by whitespace.
+static TRAILING_TCO: LazyLock<Regex> = LazyLock::new(|| {
+    Regex::new(r"\s*https?://t\.co/[A-Za-z0-9]+$").unwrap()
+});
+
+/// Replaces every t.co short link that has an entity mapping with its
+/// expanded URL. Short links without a mapping stay untouched.
+fn expand_links(text: &str, urls: &[model::SyndicationEntityUrl]) -> String {
+    let mut out = text.to_string();
+    for entity in urls {
+        if let Some(expanded) = &entity.expanded_url {
+            out = out.replace(&entity.url, expanded);
+        }
+    }
+    out
+}
+
+/// pbs.twimg.com serves a reduced default size without size params; `name=orig`
+/// returns the original file (fxtwitter used to hand out the original
+/// directly, the syndication API does not). Non-twimg URLs pass through
+/// unchanged.
+fn original_twimg_url(url: &str) -> String {
+    if url.starts_with("https://pbs.twimg.com/")
+        && (url.ends_with(".jpg") || url.ends_with(".png"))
+    {
+        format!("{url}?name=orig")
+    } else {
+        url.to_string()
+    }
+}
+
+fn mp4_variant(item: &model::SyndicationMedia) -> String {
+    item.video_info
+        .as_ref()
+        .and_then(|info| {
+            info.variants
+                .iter()
+                .find(|variant| variant.content_type == "video/mp4")
+        })
+        .map(|variant| variant.url.clone())
+        .unwrap_or_else(|| item.media_url_https.clone())
+}
+
+impl From<Tweet> for Fetched {
+    fn from(tweet: Tweet) -> Self {
+        let url = tweet.url();
+        let author_url = tweet.author_url();
+        let render_data = Some(crate::site::RenderData {
+            url: url.clone(),
+            author: encode_text(&tweet.author).into_owned(),
+            author_url: author_url.clone(),
+            title: encode_text(&tweet.text).into_owned(),
+            tags: String::new(),
+        });
+        Fetched {
+            source_url: url,
+            caption: tweet.caption(),
+            title: tweet.text.clone(),
+            media: tweet.media,
+            sensitive: tweet.sensitive,
+            render_data,
+            _keep_alive: None,
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn fixture(media_details: serde_json::Value) -> serde_json::Value {
+        serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "861627479294746624",
+            "text": "a & b <c>",
+            "user": { "name": "Display Name", "screen_name": "author_handle" },
+            "possibly_sensitive": true,
+            "mediaDetails": media_details
+        })
+    }
+
+    #[test]
+    fn pattern_matches_all_domains() {
+        for url in [
+            "https://x.com/user/status/1234567890",
+            "https://twitter.com/user/status/1234567890",
+            "https://mobile.twitter.com/user/status/1234567890",
+            "https://www.x.com/user/status/1234567890",
+            "https://fxtwitter.com/user/status/1234567890",
+            "https://fixupx.com/user/status/1234567890",
+            "https://fixvx.com/user/status/1234567890",
+            "https://vxtwitter.com/user/status/1234567890",
+        ] {
+            let caps = PATTERN.captures(url).unwrap_or_else(|| panic!("{url}"));
+            assert_eq!(caps.get(1).unwrap().as_str(), "1234567890");
+        }
+    }
+
+    #[test]
+    fn pattern_rejects_non_tweet_urls() {
+        for url in [
+            "https://x.com/user",
+            "https://x.com/user/status/abc",
+            "https://bsky.app/profile/u/post/3xxxx",
+            "https://pixiv.net/artworks/123",
+            "https://example.com/x.com/user/status/123",
+        ] {
+            assert!(!PATTERN.is_match(url), "{url}");
+        }
+    }
+
+    #[test]
+    fn syndication_json_converts_to_fetched() {
+        let raw = fixture(serde_json::json!([
+            { "type": "photo", "media_url_https": "https://pbs.twimg.com/media/photo.jpg" },
+            {
+                "type": "video",
+                "media_url_https": "https://pbs.twimg.com/thumb.jpg",
+                "video_info": {
+                    "variants": [
+                        { "content_type": "application/x-mpegURL", "url": "https://x.com/pl.m3u8" },
+                        { "content_type": "video/mp4", "url": "https://video.twimg.com/v.mp4" }
+                    ]
+                }
+            }
+        ]));
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        let fetched: Fetched = tweet.into();
+        assert_eq!(
+            fetched.source_url,
+            "https://x.com/author_handle/status/861627479294746624"
+        );
+        assert_eq!(fetched.title, "a & b <c>");
+        assert!(fetched.sensitive);
+        assert_eq!(fetched.media.len(), 2);
+        match &fetched.media[0] {
+            Media::Illustration { url, .. } => {
+                // Photo URL is rewritten to request the original file.
+                assert_eq!(
+                    url,
+                    "https://pbs.twimg.com/media/photo.jpg?name=orig"
+                );
+            }
+            other => panic!("expected illustration, got {other:?}"),
+        }
+        match &fetched.media[1] {
+            Media::Video { url, thumbnail_url, .. } => {
+                assert_eq!(url, "https://video.twimg.com/v.mp4");
+                assert_eq!(thumbnail_url, "https://pbs.twimg.com/thumb.jpg");
+            }
+            other => panic!("expected video, got {other:?}"),
+        }
+        assert!(
+            fetched
+                .caption
+                .contains("<a href=\"https://x.com/author_handle\">Display Name</a>: a &amp; b &lt;c&gt;"),
+            "caption: {}",
+            fetched.caption
+        );
+    }
+
+    #[test]
+    fn syndication_text_only_has_no_media() {
+        let raw = fixture(serde_json::json!([]));
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        let fetched: Fetched = tweet.into();
+        assert!(fetched.media.is_empty());
+    }
+
+    #[test]
+    fn syndication_gif_maps_to_animated() {
+        let raw = fixture(serde_json::json!([
+            {
+                "type": "animated_gif",
+                "media_url_https": "https://pbs.twimg.com/g.jpg",
+                "video_info": {
+                    "variants": [{ "content_type": "video/mp4", "url": "https://video.twimg.com/g.mp4" }]
+                }
+            }
+        ]));
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert!(matches!(&tweet.media[0], Media::Animated { .. }));
+    }
+
+    #[test]
+    fn syndication_text_strips_trailing_media_short_link() {
+        // Real syndication shape: the media short link sits after the visible
+        // text, and display_text_range marks where it begins.
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": "hello world https://t.co/abc123",
+            "display_text_range": [0, 11],
+            "user": { "name": "N", "screen_name": "h" },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert_eq!(tweet.text, "hello world");
+        assert!(!tweet.caption().contains("t.co"));
+    }
+
+    #[test]
+    fn syndication_text_strips_trailing_short_link_without_range() {
+        // No display_text_range: the regex fallback removes the trailing link.
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": "hello https://t.co/abc123",
+            "user": { "name": "N", "screen_name": "h" },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert_eq!(tweet.text, "hello");
+    }
+
+    #[test]
+    fn syndication_text_expands_url_entities() {
+        // Real FloodSocial shape: the user's own link is a t.co short link in
+        // the text; the entity mapping expands it, the trailing media short
+        // link is stripped.
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": "Test Tweet with @mentionThis $twtr https://t.co/RzmrQ6wAzD #hashtag https://t.co/9r69akA484",
+            "display_text_range": [0, 67],
+            "user": { "name": "N", "screen_name": "h" },
+            "entities": {
+                "urls": [{
+                    "url": "https://t.co/RzmrQ6wAzD",
+                    "expanded_url": "http://bit.ly/2pUk4be",
+                    "display_url": "bit.ly/2pUk4be"
+                }]
+            },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert_eq!(
+            tweet.text,
+            "Test Tweet with @mentionThis $twtr http://bit.ly/2pUk4be #hashtag"
+        );
+        assert!(!tweet.caption().contains("t.co"));
+    }
+
+    #[test]
+    fn syndication_text_keeps_unmapped_short_links() {
+        // No entity mapping for the embedded link: it stays as-is. Only the
+        // trailing media link is stripped.
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": "check https://t.co/abc123 #tag https://t.co/def456",
+            "display_text_range": [0, 30],
+            "user": { "name": "N", "screen_name": "h" },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert_eq!(tweet.text, "check https://t.co/abc123 #tag");
+    }
+
+    #[test]
+    fn syndication_text_utf16_display_range_keeps_multibyte() {
+        // display_text_range is in UTF-16 units; a Japanese text must not be
+        // sliced by UTF-8 bytes.
+        let text = "コミティア落ちたので、明日は行きません。🙏ごめんなさい";
+        let units: Vec<u16> = text.encode_utf16().collect();
+        assert_eq!(units.len(), 28);
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": text,
+            "display_text_range": [0, 28],
+            "user": { "name": "N", "screen_name": "h" },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        assert_eq!(tweet.text, text, "full text kept intact");
+    }
+
+    #[test]
+    fn original_twimg_url_rewrites_photo_urls() {
+        assert_eq!(
+            original_twimg_url("https://pbs.twimg.com/media/C_UdnvPUwAE3Dnn.jpg"),
+            "https://pbs.twimg.com/media/C_UdnvPUwAE3Dnn.jpg?name=orig"
+        );
+        assert_eq!(
+            original_twimg_url("https://pbs.twimg.com/media/abc.png"),
+            "https://pbs.twimg.com/media/abc.png?name=orig"
+        );
+        // Non-twimg URLs (videos, animated gifs) pass through unchanged.
+        assert_eq!(
+            original_twimg_url("https://video.twimg.com/v.mp4"),
+            "https://video.twimg.com/v.mp4"
+        );
+        assert_eq!(
+            original_twimg_url("https://pbs.twimg.com/media/abc.webp"),
+            "https://pbs.twimg.com/media/abc.webp"
+        );
+    }
+
+    #[test]
+    fn syndication_token_matches_js_formula() {
+        // JS: ((861627479294746624 / 1e15) * PI).toString(36) == "236.vrsocvda"
+        let token = syndication_token(861627479294746624);
+        assert!(token.starts_with("236.v"), "got {token}");
+    }
+
+    #[tokio::test]
+    async fn live_fetch_with_photos() {
+        let fetched = fetch("861627479294746624").await.unwrap();
+        assert_eq!(fetched.media.len(), 4);
+    }
+
+    #[tokio::test]
+    async fn live_fetch_text_only() {
+        let fetched = fetch("1992471125734142256").await.unwrap();
+        assert!(fetched.media.is_empty());
+    }
+
+    #[tokio::test]
+    async fn live_fetch_deleted_tweet_is_not_found() {
+        // Deleted tweet: the syndication endpoint answers with errors.
+        let result = fetch("0").await;
+        assert!(matches!(result, Err(FetchError::NotFound)), "got {result:?}");
+    }
+}

crates/x-media/src/site/twitter/mod.rs

@@ -0,0 +1,5 @@
+mod auth;
+mod interface;
+mod model;
+
+pub use interface::{PATTERN, Tweet, enabled, fetch_from_url};

crates/x-media/src/site/twitter/model.rs

@@ -0,0 +1,62 @@
+use serde::Deserialize;
+
+/// Response shape of the syndication endpoint
+/// (`cdn.syndication.twimg.com/tweet-result`).
+#[derive(Deserialize, Debug)]
+pub struct SyndicationTweet {
+    pub id_str: String,
+    pub text: String,
+    pub user: SyndicationUser,
+    #[serde(default)]
+    pub possibly_sensitive: Option<bool>,
+    /// Visible-text span; the raw `text` field has the appended media short
+    /// link after it. Indices are Unicode code points (not UTF-16 units).
+    #[serde(default, rename = "display_text_range")]
+    pub display_text_range: Option<[usize; 2]>,
+    #[serde(default)]
+    pub entities: SyndicationEntities,
+    #[serde(default, rename = "mediaDetails")]
+    pub media_details: Vec<SyndicationMedia>,
+}
+
+#[derive(Deserialize, Debug, Default)]
+pub struct SyndicationEntities {
+    #[serde(default)]
+    pub urls: Vec<SyndicationEntityUrl>,
+}
+
+/// A URL entity: `url` is the t.co short link as it appears in the text,
+/// `expanded_url` the real destination.
+#[derive(Deserialize, Debug)]
+pub struct SyndicationEntityUrl {
+    pub url: String,
+    #[serde(default)]
+    pub expanded_url: Option<String>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct SyndicationUser {
+    pub name: String,
+    pub screen_name: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct SyndicationMedia {
+    #[serde(rename = "type")]
+    pub media_type: String,
+    pub media_url_https: String,
+    #[serde(default)]
+    pub video_info: Option<SyndicationVideoInfo>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct SyndicationVideoInfo {
+    #[serde(default)]
+    pub variants: Vec<SyndicationVariant>,
+}
+
+#[derive(Deserialize, Debug)]
+pub struct SyndicationVariant {
+    pub content_type: String,
+    pub url: String,
+}

crates/xmedia-bot/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "xmedia-bot"
+version = "1.0.5"
+edition = "2024"
+
+[dependencies]
+teloxide = { version = "0.17", features = ["webhooks-axum", "macros"] }
+tokio = { version = "1.40", features = ["rt-multi-thread", "macros"] }
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+log = "0.4"
+pretty_env_logger = "0.5"
+dotenv = "0.15"
+url = "2.5.2"
+regex = "1.12"
+html-escape = "0.2"
+rusqlite = { version = "0.32", features = ["bundled"] }
+rand = "0.8"
+tempfile = "3"
+parking_lot = "0.12"
+x-media = { path = "../x-media" }

crates/xmedia-bot/src/config.rs

@@ -0,0 +1,64 @@
+//! Central env handling. The only other places that read env are
+//! `Bot::from_env` (TELOXIDE_TOKEN) and x-media (PIXIV_REFRESH_TOKEN).
+
+use std::env;
+use std::net::IpAddr;
+use std::time::Duration;
+
+pub struct Config {
+    /// BOT_ADMIN: comma-separated ints; empty when unset.
+    pub admin_ids: Vec<i64>,
+    /// EDIT_MESSAGE_TTL_SECONDS, default 86400 (24h).
+    pub edit_message_ttl: Duration,
+    // Webhook settings (moved out of main; names/defaults unchanged).
+    pub webhook_enabled: bool,
+    pub webhook_url: Option<url::Url>,
+    pub webhook_listen: Option<IpAddr>,
+    pub webhook_port: Option<u16>,
+    pub webhook_cert: Option<String>,
+    pub webhook_secret_token: Option<String>,
+}
+
+impl Config {
+    pub fn load() -> Config {
+        let admin_ids = env::var("BOT_ADMIN")
+        .ok()
+        .map(|s| {
+            s.split(',')
+                .filter_map(|part| part.trim().parse::<i64>().ok())
+                .collect()
+        })
+        .unwrap_or_default();
+
+    let edit_message_ttl = env::var("EDIT_MESSAGE_TTL_SECONDS")
+        .ok()
+        .and_then(|s| s.parse::<u64>().ok())
+        .map(Duration::from_secs)
+        .unwrap_or(Duration::from_secs(86400));
+
+    let webhook_enabled = env::var("WEBHOOK")
+        .is_ok_and(|v| matches!(v.to_lowercase().as_str(), "true" | "yes" | "1"));
+    let webhook_url = env::var("WEBHOOK_URL").ok().and_then(|s| s.parse().ok());
+    let webhook_listen = env::var("WEBHOOK_LISTEN").ok().and_then(|s| s.parse().ok());
+    let webhook_port = env::var("WEBHOOK_PORT").ok().and_then(|s| s.parse().ok());
+    // Empty strings count as unset (e.g. `-e WEBHOOK_CERT=` to disable a
+    // value that would otherwise come from `.env`).
+    let webhook_cert = env::var("WEBHOOK_CERT")
+        .ok()
+        .filter(|s| !s.is_empty());
+    let webhook_secret_token = env::var("WEBHOOK_SECRET_TOKEN")
+        .ok()
+        .filter(|s| !s.is_empty());
+
+        Config {
+            admin_ids,
+            edit_message_ttl,
+            webhook_enabled,
+            webhook_url,
+            webhook_listen,
+            webhook_port,
+            webhook_cert,
+            webhook_secret_token,
+        }
+    }
+}

crates/xmedia-bot/src/handlers.rs

@@ -0,0 +1,651 @@
+use crate::config::Config;
+use crate::queue::PersistentTaskQueue;
+use crate::send::{self, MediaItemPayload, Task};
+use crate::state::{ChatStore, unix_now};
+use std::collections::HashSet;
+use std::sync::LazyLock;
+use teloxide::prelude::*;
+use teloxide::types::{
+    CallbackQuery, ChatAction, ChatId, ChatKind, InlineQuery, InlineQueryResult,
+    InlineQueryResultMpeg4Gif, InlineQueryResultPhoto, InlineQueryResultVideo, Message,
+    MessageEntityKind, MessageId, ParseMode, Recipient, ReplyParameters,
+};
+use teloxide::utils::command::BotCommands;
+use teloxide::RequestError;
+use x_media::media::Media;
+
+pub static CHAT_STORE: LazyLock<ChatStore> = LazyLock::new(|| {
+    ChatStore::open("data/task_queue.db").expect("failed to open chat store")
+});
+pub static TASK_QUEUE: LazyLock<PersistentTaskQueue> =
+    LazyLock::new(|| PersistentTaskQueue::new("data/task_queue.db"));
+pub static CONFIG: LazyLock<Config> = LazyLock::new(Config::load);
+
+#[derive(BotCommands, Clone)]
+#[command(rename_rule = "snake_case", description = "")]
+enum Command {
+    #[command(description = "")]
+    Start,
+    #[command(description = "")]
+    Help,
+    #[command(description = "", parse_with = "split")]
+    SetForwardChannel(String),
+    #[command(description = "")]
+    RemoveForwardChannel,
+    #[command(description = "")]
+    EditBeforeForward,
+    #[command(description = "", parse_with = "split")]
+    SetTemplate(String),
+    #[command(description = "")]
+    BotDict,
+    #[command(description = "", parse_with = "split")]
+    SetFormat(String),
+}
+
+async fn reply<T>(bot: Bot, message: Message, text: T) -> Result<Message, RequestError>
+where
+    T: Into<String>,
+{
+    bot.send_message(message.chat.id, text)
+        .reply_parameters(ReplyParameters::new(message.id).allow_sending_without_reply())
+        .await
+}
+
+fn now_f64() -> f64 {
+    std::time::SystemTime::now()
+        .duration_since(std::time::UNIX_EPOCH)
+        .map(|d| d.as_secs_f64())
+        .unwrap_or(0.0)
+}
+
+/// Extracts URL and text-link entities (text + caption), deduped in order.
+pub fn extract_urls(message: &Message) -> Vec<String> {
+    let mut urls = Vec::new();
+    for entity in message.parse_entities().into_iter().flatten() {
+        match entity.kind() {
+            MessageEntityKind::Url => urls.push(entity.text().to_string()),
+            MessageEntityKind::TextLink { url } => urls.push(url.to_string()),
+            _ => {}
+        }
+    }
+    for entity in message.parse_caption_entities().into_iter().flatten() {
+        match entity.kind() {
+            MessageEntityKind::Url => urls.push(entity.text().to_string()),
+            MessageEntityKind::TextLink { url } => urls.push(url.to_string()),
+            _ => {}
+        }
+    }
+    let mut seen = HashSet::new();
+    urls.retain(|url| seen.insert(url.clone()));
+    urls
+}
+
+/// Edit-before-forward: a reply to the prompt swaps the caption of the first
+/// forwarded message. Returns true when the message was consumed as an edit.
+async fn edit_message_handler(bot: &Bot, message: &Message) -> bool {
+    let Some(reply) = message.reply_to_message() else {
+        return false;
+    };
+    let chat_id = message.chat.id.0;
+    let Some(text) = message.text() else {
+        return false;
+    };
+    let chat_data = CHAT_STORE.get(chat_id).await;
+    let Some(edit) = chat_data.edit_message.get(&(reply.id.0 as i64)) else {
+        return false;
+    };
+    let Some(first_forward_id) = edit.forward_message_ids.first() else {
+        return false;
+    };
+    let link = format!(
+        "<a href=\"{0}\">{1}</a>",
+        edit.url,
+        html_escape::encode_text(text)
+    );
+    let new_text = if edit.template.is_empty() {
+        link
+    } else {
+        chat_data
+            .template
+            .get(&edit.template)
+            .map(|template| template.replace("[]", &link))
+            .unwrap_or(link)
+    };
+    let result = bot
+        .edit_message_caption(ChatId(chat_id), MessageId(*first_forward_id as i32))
+        .caption(new_text)
+        .parse_mode(ParseMode::Html)
+        .await;
+    match result {
+        Ok(_) => log::info!(
+            "edit-before-forward: caption swapped on message {first_forward_id} for prompt {}",
+            reply.id.0
+        ),
+        Err(e) => log::error!("edit_message_caption failed: {e}"),
+    }
+    true
+}
+
+enum SetForwardChannelError {
+    EmptyParameter,
+    NotChannel,
+    NotAdmin,
+    NotBotAdmin(RequestError),
+    NotBotCanPost,
+}
+
+async fn set_forward_channel_handler(
+    bot: &Bot,
+    message: &Message,
+    channel: String,
+) -> Result<i64, SetForwardChannelError> {
+    if channel.is_empty() {
+        return Err(SetForwardChannelError::EmptyParameter);
+    }
+    let channel = match channel.parse::<i64>() {
+        Ok(id) => Recipient::Id(ChatId(id)),
+        Err(_) => Recipient::ChannelUsername(channel),
+    };
+    if let Some(from) = &message.from {
+        log::info!(
+            "Set forward channel for {} ({}) to {}",
+            from.full_name(),
+            message.chat.id,
+            channel
+        );
+    }
+    let chat = match bot.get_chat(channel.clone()).await {
+        Err(e) => {
+            log::error!("Failed to get channel {}: {}", channel, e);
+            return Err(SetForwardChannelError::NotBotAdmin(e));
+        }
+        Ok(chat) => chat,
+    };
+    if !chat.is_channel() {
+        return Err(SetForwardChannelError::NotChannel);
+    }
+    let channel_id = chat.id.0;
+    match bot.get_chat_administrators(channel.clone()).await {
+        Err(e) => {
+            log::error!("Failed to get channel administrators {}: {}", channel, e);
+            return Err(SetForwardChannelError::NotBotAdmin(e));
+        }
+        Ok(admins) => {
+            if !admins.iter().any(|admin| admin.user.id == message.chat.id) {
+                return Err(SetForwardChannelError::NotAdmin);
+            }
+            let bot_id = bot.get_me().await.expect("Failed get bot id").user.id;
+            if let Some(bot_admin) = admins.iter().find(|admin| admin.user.id == bot_id)
+                && !bot_admin.can_post_messages()
+            {
+                return Err(SetForwardChannelError::NotBotCanPost);
+            }
+        }
+    }
+    Ok(channel_id)
+}
+
+async fn execute_command(bot: &Bot, message: &Message, command: Command) -> Result<(), RequestError> {
+    match command {
+        Command::Start => {
+            bot.send_message(message.chat.id, "Hello!").await?;
+        }
+        Command::Help => {
+            bot.send_message(message.chat.id, Command::descriptions().to_string())
+                .await?;
+        }
+        Command::SetForwardChannel(channel) => {
+            let result = match set_forward_channel_handler(bot, message, channel).await {
+                Ok(channel_id) => {
+                    let mut chat_data = CHAT_STORE.get(message.chat.id.0).await;
+                    chat_data.forward_channel_id = Some(channel_id);
+                    CHAT_STORE.set(message.chat.id.0, &chat_data).await;
+                    "Add successfully.".to_string()
+                }
+                Err(SetForwardChannelError::EmptyParameter) => {
+                    "Receive empty parameter.\nYou should enter a channel id or username".to_string()
+                }
+                Err(SetForwardChannelError::NotChannel) => {
+                    "Given id / username is not a channel".to_string()
+                }
+                Err(SetForwardChannelError::NotAdmin) => {
+                    "You are not an administrator of the channel".to_string()
+                }
+                Err(SetForwardChannelError::NotBotAdmin(e)) => {
+                    e.to_string() + "\nPlease add the bot as an admin to the channel"
+                }
+                Err(SetForwardChannelError::NotBotCanPost) => {
+                    "Bot can't post messages to the channel".to_string()
+                }
+            };
+            reply(bot.clone(), message.clone(), result).await?;
+        }
+        Command::RemoveForwardChannel => {
+            let chat_id = message.chat.id.0;
+            let mut chat_data = CHAT_STORE.get(chat_id).await;
+            let text = if chat_data.forward_channel_id.is_some() {
+                chat_data.forward_channel_id = None;
+                CHAT_STORE.set(chat_id, &chat_data).await;
+                "Remove successfully.".to_string()
+            } else {
+                "No channel to remove.".to_string()
+            };
+            reply(bot.clone(), message.clone(), text).await?;
+        }
+        Command::EditBeforeForward => {
+            let chat_id = message.chat.id.0;
+            let mut chat_data = CHAT_STORE.get(chat_id).await;
+            let text = if chat_data.forward_channel_id.is_none() {
+                "Please enable forward channel first.".to_string()
+            } else if chat_data.edit_before_forward {
+                chat_data.edit_before_forward = false;
+                chat_data.edit_message.clear();
+                CHAT_STORE.set(chat_id, &chat_data).await;
+                "Disable edit before forward.".to_string()
+            } else {
+                chat_data.edit_before_forward = true;
+                CHAT_STORE.set(chat_id, &chat_data).await;
+                "Enable edit before forward.".to_string()
+            };
+            reply(bot.clone(), message.clone(), text).await?;
+        }
+        Command::SetTemplate(name) => {
+            let chat_id = message.chat.id.0;
+            let text = match message.reply_to_message() {
+                None => "Please reply to a message to set as template.".to_string(),
+                Some(reply) => {
+                    let reply_text = reply.text().unwrap_or_default();
+                    if !reply_text.contains("[]") {
+                        "Please reply to a message with [] to set as template.".to_string()
+                    } else if name.is_empty() {
+                        "Please provide a name for the template.".to_string()
+                    } else {
+                        let mut chat_data = CHAT_STORE.get(chat_id).await;
+                        chat_data
+                            .template
+                            .insert(name, html_escape::encode_text(reply_text).into_owned());
+                        CHAT_STORE.set(chat_id, &chat_data).await;
+                        "Template set.".to_string()
+                    }
+                }
+            };
+            reply(bot.clone(), message.clone(), text).await?;
+        }
+        Command::BotDict => {
+            let chat_data = CHAT_STORE.get(message.chat.id.0).await;
+            let debug = format!("{chat_data:?}");
+            let text = html_escape::encode_text(&debug).into_owned();
+            reply(bot.clone(), message.clone(), text).await?;
+        }
+        Command::SetFormat(arg) => {
+            let chat_id = message.chat.id.0;
+            let (site, format) = match arg.split_once(char::is_whitespace) {
+                Some((site, format)) if !format.trim().is_empty() => (site.trim(), format.trim().to_string()),
+                _ => {
+                    reply(
+                        bot.clone(),
+                        message.clone(),
+                        "Usage: /set_format <site> <format>",
+                    )
+                    .await?;
+                    return Ok(());
+                }
+            };
+            if !["twitter", "bsky", "pixiv"].contains(&site) {
+                reply(
+                    bot.clone(),
+                    message.clone(),
+                    "Unknown site. Use twitter, bsky or pixiv.",
+                )
+                .await?;
+                return Ok(());
+            }
+            let mut chat_data = CHAT_STORE.get(chat_id).await;
+            chat_data.message_format.insert(site.to_string(), format);
+            CHAT_STORE.set(chat_id, &chat_data).await;
+            reply(bot.clone(), message.clone(), "Format set.").await?;
+        }
+    }
+    Ok(())
+}
+
+/// For locally produced media (encoded ugoira MP4) the thumbnail URL is a
+/// hotlink-protected remote URL Telegram may not fetch; let Telegram generate
+/// its own thumbnail instead.
+fn thumbnail_for(media: &Media) -> Option<String> {
+    let url = media.url();
+    if url.starts_with("http://") || url.starts_with("https://") {
+        media.thumbnail_url().map(str::to_string)
+    } else {
+        None
+    }
+}
+
+fn media_to_payload(media: &Media, sensitive: bool) -> MediaItemPayload {
+    let fallback_url = media.smaller_url().map(str::to_string);
+    match media {
+        // A gif inside a group becomes a video item; a lone gif takes the
+        // animation path (see url_media).
+        Media::Illustration { .. } => MediaItemPayload::Photo {
+            media: media.url().to_string(),
+            has_spoiler: sensitive,
+            fallback_url,
+        },
+        Media::Video { .. } => MediaItemPayload::Video {
+            media: media.url().to_string(),
+            has_spoiler: sensitive,
+            thumbnail: thumbnail_for(media),
+            fallback_url,
+        },
+        Media::Animated { .. } => MediaItemPayload::Video {
+            media: media.url().to_string(),
+            has_spoiler: sensitive,
+            thumbnail: thumbnail_for(media),
+            fallback_url,
+        },
+    }
+}
+
+async fn enqueue_retry(task: Task, delay_seconds: f64) {
+    let payload = serde_json::to_value(task).expect("task serializes");
+    let run_after = now_f64() + delay_seconds;
+    if let Err(e) = TASK_QUEUE.enqueue(payload, run_after).await {
+        log::error!("failed to enqueue retry: {e}");
+    }
+}
+
+async fn url_media(bot: Bot, message: &Message, url: &str) {
+    let chat_id = message.chat.id.0;
+    if let Err(e) = bot.send_chat_action(ChatId(chat_id), ChatAction::Typing).await {
+        log::error!("send_chat_action failed: {e}");
+    }
+    log::info!("fetching {url}");
+    match x_media::site::fetch(url).await {
+        // Unsupported links are ignored silently (Python parity).
+        Ok(None) => {
+            log::info!("no site pattern matches {url}; ignoring");
+        }
+        // Retries exhausted: notify the user (Rust-only requirement 3).
+        Err(e) => {
+            log::error!("fetch {url}: {e}");
+            let _ = reply(bot, message.clone(), "Failed to fetch media from this link.").await;
+        }
+        Ok(Some(fetched)) => {
+            if fetched.media.is_empty() {
+                let _ = reply(
+                    bot,
+                    message.clone(),
+                    "No media found or media type is not supported.",
+                )
+                .await;
+                return;
+            }
+            let chat_data = CHAT_STORE.get(chat_id).await;
+            // Per-site caption format override (empty -> built-in caption).
+            let format = chat_data
+                .message_format
+                .get(fetched.site_name())
+                .cloned()
+                .unwrap_or_default();
+            let caption = fetched.caption_with(&format);
+            let task = if fetched.media.len() == 1
+                && matches!(fetched.media[0], Media::Animated { .. })
+            {
+                Task::SendAnimation {
+                    chat_id,
+                    reply_to_message_id: message.id.0 as i64,
+                    caption: caption.clone(),
+                    animation: MediaItemPayload::Animation {
+                        media: fetched.media[0].url().to_string(),
+                        has_spoiler: fetched.sensitive,
+                    },
+                    source_url: fetched.source_url.clone(),
+                    edit_before_forward: chat_data.edit_before_forward,
+                    forward_channel_id: chat_data.forward_channel_id,
+                    notify_chat_id: Some(chat_id),
+                    notify_message_id: Some(message.id.0 as i64),
+                }
+            } else {
+                let items: Vec<MediaItemPayload> = fetched
+                    .media
+                    .iter()
+                    .map(|media| media_to_payload(media, fetched.sensitive))
+                    .collect();
+                Task::SendMediaSequence {
+                    chat_id,
+                    reply_to_message_id: message.id.0 as i64,
+                    caption: caption.clone(),
+                    media_batches: send::chunk_media_items(items),
+                    batch_index: 0,
+                    sent_message_ids: vec![],
+                    source_url: fetched.source_url.clone(),
+                    edit_before_forward: chat_data.edit_before_forward,
+                    forward_channel_id: chat_data.forward_channel_id,
+                    notify_chat_id: Some(chat_id),
+                    notify_message_id: Some(message.id.0 as i64),
+                }
+            };
+            let result = match &task {
+                Task::SendAnimation { .. } => send::send_animation(&bot, &task).await,
+                Task::SendMediaSequence { .. } => send::send_media_sequence(&bot, &task).await,
+                Task::ForwardMessages { .. } => unreachable!(),
+            };
+            match result {
+                Ok(message_ids) => {
+                    log::info!("sent {} message(s) for {url}", message_ids.len());
+                    send::post_send_actions(&bot, &task, message_ids).await;
+                }
+                Err(send::SendError::Retryable { delay_seconds, task }) => {
+                    log::info!("send for {url} failed, queued for retry in {delay_seconds:.1}s");
+                    enqueue_retry(task, delay_seconds).await;
+                    let _ = reply(bot, message.clone(), "Send failed. Task queued for retry.").await;
+                }
+                Err(send::SendError::Permanent {
+                    message: err_message,
+                    ..
+                }) => {
+                    log::error!("send for {url} failed permanently: {err_message}");
+                    let _ = reply(bot, message.clone(), format!("Send failed: {err_message}")).await;
+                }
+            }
+        }
+    }
+}
+
+pub async fn message_handler(bot: Bot, message: Message) -> Result<(), RequestError> {
+    let is_private = matches!(message.chat.kind, ChatKind::Private(_));
+    let sender = message
+        .from
+        .as_ref()
+        .map(|from| from.full_name())
+        .unwrap_or_else(|| "unknown".to_string());
+    let text_preview = message
+        .text()
+        .map(|t| if t.len() > 120 { &t[..120] } else { t })
+        .unwrap_or("<no text>");
+    log::info!("message from {sender} in {} (private={is_private}): {text_preview}", message.chat.id);
+    // URL/edit flows only run in private chats; commands run in any chat.
+    if is_private && edit_message_handler(&bot, &message).await {
+        return respond(());
+    }
+    if let Some(text) = message.text()
+        && let Ok(command) = Command::parse(text, "")
+    {
+        log::info!("command from {}: {text_preview}", message.chat.id);
+        execute_command(&bot, &message, command).await?;
+        return respond(());
+    }
+    if is_private {
+        let urls = extract_urls(&message);
+        if !urls.is_empty() {
+            log::info!("extracted {} URL(s): {urls:?}", urls.len());
+        }
+        for url in urls {
+            url_media(bot.clone(), &message, &url).await;
+        }
+    }
+    respond(())
+}
+
+pub async fn inline_query_handler(bot: Bot, query: InlineQuery) -> Result<(), RequestError> {
+    if query.query.is_empty() {
+        return respond(());
+    }
+    log::info!("inline query: {}", query.query);
+    match x_media::site::fetch(&query.query).await {
+        Ok(Some(fetched)) => {
+            let mut results: Vec<InlineQueryResult> = Vec::new();
+            for (i, media) in fetched.media.iter().enumerate() {
+                let id = format!("{i}");
+                let Some(url) = url::Url::parse(media.url()).ok() else {
+                    continue;
+                };
+                let thumbnail = media
+                    .thumbnail_url()
+                    .and_then(|t| url::Url::parse(t).ok())
+                    .unwrap_or_else(|| url.clone());
+                let caption = fetched.caption.clone();
+                let result = match media {
+                    Media::Illustration { .. } => {
+                        // Inline photo results have their own (smaller) size
+                        // cap; use the reduced variant when one exists.
+                        let photo_url = media
+                            .smaller_url()
+                            .and_then(|u| url::Url::parse(u).ok())
+                            .unwrap_or_else(|| url.clone());
+                        InlineQueryResult::Photo(
+                            InlineQueryResultPhoto::new(id, photo_url, thumbnail)
+                                .caption(caption)
+                                .parse_mode(ParseMode::Html),
+                        )
+                    }
+                    Media::Video { .. } => InlineQueryResult::Video(
+                        InlineQueryResultVideo::new(
+                            id,
+                            url,
+                            "video/mp4".parse().expect("valid mime"),
+                            thumbnail,
+                            fetched.title.clone(),
+                        )
+                            .caption(caption)
+                            .parse_mode(ParseMode::Html),
+                    ),
+                    Media::Animated { .. } => InlineQueryResult::Mpeg4Gif(
+                        InlineQueryResultMpeg4Gif::new(id, url, thumbnail)
+                            .caption(caption)
+                            .parse_mode(ParseMode::Html),
+                    ),
+                };
+                results.push(result);
+            }
+            if !results.is_empty() {
+                bot.answer_inline_query(query.id, results).await?;
+            }
+        }
+        Ok(None) => {}
+        Err(e) => log::error!("inline fetch {}: {e}", query.query),
+    }
+    respond(())
+}
+
+pub async fn callback_query_handler(bot: Bot, query: CallbackQuery) -> Result<(), RequestError> {
+    let callback_query_id = query.id;
+    let data = query.data.clone();
+    let Some(message) = &query.message else {
+        return respond(());
+    };
+    let chat_id = message.chat().id.0;
+    let prompt_message_id = message.id().0 as i64;
+    let ttl_secs = CONFIG.edit_message_ttl.as_secs() as i64;
+    let mut chat_data = CHAT_STORE.get(chat_id).await;
+    let edit = chat_data.edit_message.get(&prompt_message_id).cloned();
+    let Some(edit) = edit else {
+        log::info!("callback from {}: no edit record for prompt {prompt_message_id}", chat_id);
+        bot.answer_callback_query(callback_query_id)
+            .text("Expired")
+            .await?;
+        return respond(());
+    };
+    // Lazy expiry: a stale record (past the TTL, not yet swept) is dropped.
+    if edit.created_at + ttl_secs <= unix_now() {
+        chat_data.edit_message.remove(&prompt_message_id);
+        CHAT_STORE.set(chat_id, &chat_data).await;
+        bot.answer_callback_query(callback_query_id)
+            .text("Expired")
+            .await?;
+        return respond(());
+    }
+
+    let Some(data) = data else {
+        return respond(());
+    };
+    log::info!("callback from {} on prompt {prompt_message_id}: {data}", chat_id);
+    if data == "forward" {
+        match chat_data.forward_channel_id {
+            Some(channel_id) => {
+                let forward_task = Task::ForwardMessages {
+                    from_chat_id: edit.chat_id,
+                    to_chat_id: channel_id,
+                    message_ids: edit.forward_message_ids.clone(),
+                    notify_chat_id: Some(chat_id),
+                    notify_message_id: Some(prompt_message_id),
+                };
+                match send::forward_messages(&bot, &forward_task).await {
+                    Ok(()) => {
+                        log::info!(
+                            "forwarded {} message(s) to channel {channel_id}",
+                            edit.forward_message_ids.len()
+                        );
+                        bot.answer_callback_query(callback_query_id)
+                            .text("✅ Forwarded")
+                            .await?;
+                        let _ = bot
+                            .delete_message(ChatId(chat_id), MessageId(prompt_message_id as i32))
+                            .await;
+                        chat_data.edit_message.remove(&prompt_message_id);
+                        CHAT_STORE.set(chat_id, &chat_data).await;
+                    }
+                    Err(send::SendError::Retryable { delay_seconds, task }) => {
+                        log::info!("forward queued for retry in {delay_seconds:.1}s");
+                        enqueue_retry(task, delay_seconds).await;
+                        bot.answer_callback_query(callback_query_id)
+                            .text("Forward queued for retry.")
+                            .await?;
+                    }
+                    Err(send::SendError::Permanent { message, .. }) => {
+                        log::error!("forward failed permanently: {message}");
+                        bot.answer_callback_query(callback_query_id)
+                            .text(format!("Forward failed: {message}"))
+                            .await?;
+                    }
+                }
+            }
+            None => {
+                log::info!("forward callback without a forward channel set");
+                bot.answer_callback_query(callback_query_id)
+                    .text("No forward channel set.")
+                    .await?;
+            }
+        }
+        return respond(());
+    }
+    if let Some(name) = data.strip_prefix("template|") {
+        if let Some(template_html) = chat_data.template.get(name).cloned()
+            && let Some(first_forward_id) = edit.forward_message_ids.first().copied()
+        {
+            // Raw template including the [] placeholder (Python parity).
+            let _ = bot
+                .edit_message_caption(ChatId(chat_id), MessageId(first_forward_id as i32))
+                .caption(template_html)
+                .parse_mode(ParseMode::Html)
+                .await;
+            if let Some(entry) = chat_data.edit_message.get_mut(&prompt_message_id) {
+                entry.template = name.to_string();
+            }
+            CHAT_STORE.set(chat_id, &chat_data).await;
+            log::info!("template '{name}' applied to prompt {prompt_message_id}");
+        }
+        bot.answer_callback_query(callback_query_id).await?;
+    }
+    respond(())
+}

crates/xmedia-bot/src/main.rs

@@ -0,0 +1,167 @@
+use dotenv::dotenv;
+use teloxide::dptree::endpoint;
+use teloxide::stop::StopToken;
+use teloxide::types::{ChatId, InputFile, MessageId};
+use teloxide::update_listeners::{self, webhooks, UpdateListener};
+use teloxide::prelude::*;
+use tokio::sync::watch;
+use x_media::site;
+
+mod config;
+mod handlers;
+mod queue;
+mod send;
+mod state;
+
+use handlers::{CHAT_STORE, CONFIG, TASK_QUEUE};
+
+/// Docker `stop` / `compose down` delivers SIGTERM, which teloxide's ctrlc
+/// handler (SIGINT only) never sees — without this the process would die
+/// before the graceful shutdown below (admin notice, queue drain). Stopping
+/// the token unwinds the dispatcher exactly like Ctrl+C does.
+#[cfg(unix)]
+fn spawn_sigterm_handler(stop_token: StopToken) {
+    tokio::spawn(async move {
+        let mut sigterm = tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate())
+            .expect("failed to install SIGTERM handler");
+        sigterm.recv().await;
+        log::info!("SIGTERM received, stopping the dispatcher");
+        stop_token.stop();
+    });
+}
+
+#[cfg(not(unix))]
+fn spawn_sigterm_handler(_stop_token: StopToken) {}
+
+#[tokio::main]
+async fn main() {
+    dotenv().ok();
+    pretty_env_logger::init();
+    log::info!("Starting bot");
+
+    let bot = Bot::from_env();
+
+    log::info!(
+        "config: {} admin(s), edit-message TTL {}s",
+        CONFIG.admin_ids.len(),
+        CONFIG.edit_message_ttl.as_secs()
+    );
+
+    // Queue worker: handles typed tasks, dead-letters failed sends to the
+    // task's chat.
+    TASK_QUEUE
+        .start(send::handle_task, send::dead_letter_notify)
+        .await;
+    log::info!("task queue worker started");
+
+    // Pixiv login validation (user request): a failed login notifies the
+    // admin and disables pixiv for this process.
+    if site::pixiv::enabled() {
+        match site::pixiv::validate().await {
+            Ok(()) => log::info!("pixiv login validated"),
+            Err(e) => {
+                log::error!("pixiv login failed: {e}");
+                if let Some(admin) = CONFIG.admin_ids.first() {
+                    let _ = bot
+                        .send_message(ChatId(*admin), format!("Pixiv login failed: {e}"))
+                        .await;
+                }
+                site::pixiv::disable();
+            }
+        }
+    }
+
+    // Edit-expiry sweep: clears the prompt's buttons once the record expires.
+    log::info!("edit-expiry sweep: every 300s, ttl {}", CONFIG.edit_message_ttl.as_secs());
+    let (stop_tx, stop_rx) = watch::channel(false);
+    {
+        let bot = bot.clone();
+        let mut stop_rx = stop_rx;
+        tokio::spawn(async move {
+            loop {
+                tokio::select! {
+                    _ = stop_rx.changed() => break,
+                    _ = tokio::time::sleep(std::time::Duration::from_secs(300)) => {}
+                }
+                let ttl = CONFIG.edit_message_ttl;
+                let removed = CHAT_STORE.prune_expired(ttl).await;
+                for (chat_id, prompt_message_id) in removed {
+                    // If the prompt was already deleted, this fails with a
+                    // 400 "message to edit not found" — log and ignore.
+                    if let Err(e) = bot
+                        .edit_message_reply_markup(ChatId(chat_id), MessageId(prompt_message_id as i32))
+                        .await
+                    {
+                        log::info!("edit-expiry sweep: prompt message gone: {e}");
+                    }
+                }
+            }
+        });
+    }
+
+    let handler = dptree::entry()
+        .branch(Update::filter_message().branch(endpoint(handlers::message_handler)))
+        .branch(Update::filter_inline_query().branch(endpoint(handlers::inline_query_handler)))
+        .branch(Update::filter_callback_query().branch(endpoint(handlers::callback_query_handler)));
+
+    let mut dispatcher = Dispatcher::builder(bot.clone(), handler)
+        .dependencies(dptree::deps![""])
+        .enable_ctrlc_handler()
+        .build();
+
+    if CONFIG.webhook_enabled {
+        log::info!("running in webhook mode");
+        let url = CONFIG
+            .webhook_url
+            .clone()
+            .expect("WEBHOOK_URL is not set");
+        // `webhooks::axum` calls set_webhook itself (with the full options,
+        // secret token included) — no explicit registration here.
+        let listen = CONFIG.webhook_listen.expect("WEBHOOK_LISTEN is not set");
+        let port = CONFIG.webhook_port.expect("WEBHOOK_PORT is not set");
+        let mut options = webhooks::Options::new((listen, port).into(), url);
+        if let Some(cert) = &CONFIG.webhook_cert {
+            options = options.certificate(InputFile::file(cert));
+        }
+        if let Some(secret) = &CONFIG.webhook_secret_token {
+            options = options.secret_token(secret.clone());
+        }
+
+        let mut listener = webhooks::axum(bot.clone(), options)
+            .await
+            .expect("Failed to create webhook listener");
+        let stop_token = listener.stop_token();
+        spawn_sigterm_handler(stop_token);
+
+        dispatcher
+            .dispatch_with_listener(
+                listener,
+                LoggingErrorHandler::with_custom_text("Error from update listener"),
+            )
+            .await;
+    } else {
+        log::info!("running in polling mode");
+        // Same listener `dispatch()` builds internally — using
+        // `dispatch_with_listener` just exposes its stop token so SIGTERM can
+        // unwind the dispatcher before the graceful shutdown below.
+        let mut listener = update_listeners::polling_default(bot.clone()).await;
+        let stop_token = listener.stop_token();
+        spawn_sigterm_handler(stop_token);
+
+        dispatcher
+            .dispatch_with_listener(
+                listener,
+                LoggingErrorHandler::with_custom_text("Error from update listener"),
+            )
+            .await;
+    }
+
+    // Graceful stop (Ctrl+C / SIGTERM): stop the sweep, notify the admin, drain the queue.
+    log::info!("Stopping bot");
+    let _ = stop_tx.send(true);
+    if let Some(admin) = CONFIG.admin_ids.first() {
+        let _ = bot.send_message(ChatId(*admin), "Shutting down...").await;
+    }
+    TASK_QUEUE.stop().await;
+    log::info!("Bot stopped");
+}

crates/xmedia-bot/src/queue.rs

@@ -0,0 +1,488 @@
+//! Generic persistent task queue backed by SQLite (table `tasks`).
+//!
+//! Concepts kept from the Python `utils/task_queue.py` (untrusted, redesigned):
+//! the table schema, the lease/lock/recovery model, and the retry→dead-letter
+//! flow. The Python dict-mutation hack (attempts inside the payload) is
+//! replaced by dedicated columns.
+
+use parking_lot::Mutex;
+use rusqlite::{params, Connection};
+use serde_json::Value;
+use std::pin::Pin;
+use std::sync::atomic::{AtomicBool, AtomicU64, Ordering};
+use std::sync::Arc;
+use std::time::{Duration, SystemTime, UNIX_EPOCH};
+use tokio::sync::Notify;
+use tokio::task::JoinHandle;
+
+pub const MAX_RETRIES: u32 = 2;
+pub const LOCK_TTL_SECONDS: f64 = 120.0;
+
+/// What a handler returns instead of throwing. The payload it carries is the
+/// (possibly updated) task state to persist for the next attempt.
+pub enum QueueError {
+    /// Reschedule with the given delay; after `MAX_RETRIES` attempts the task
+    /// is dead-lettered instead.
+    Retryable {
+        delay_seconds: f64,
+        payload: Value,
+    },
+    /// Give up now.
+    Permanent {
+        message: String,
+        payload: Value,
+    },
+}
+
+type BoxFuture<'a, T> = Pin<Box<dyn Future<Output = T> + Send + 'a>>;
+type Handler = dyn Fn(Value) -> BoxFuture<'static, Result<(), QueueError>> + Send + Sync;
+type DeadLetter = dyn Fn(Value, String) -> BoxFuture<'static, ()> + Send + Sync;
+
+pub struct PersistentTaskQueue {
+    db_path: String,
+    notify: Arc<Notify>,
+    stop: Arc<AtomicBool>,
+    worker: Mutex<Option<JoinHandle<()>>>,
+    counter: AtomicU64,
+}
+
+struct LeasedRow {
+    id: String,
+    payload: String,
+    attempts: i32,
+}
+
+/// Owned worker state so the spawned loop does not borrow the queue handle.
+struct QueueWorker {
+    db_path: String,
+    notify: Arc<Notify>,
+    stop: Arc<AtomicBool>,
+    handler: Arc<Handler>,
+    dead_letter: Arc<DeadLetter>,
+}
+
+fn now_f64() -> f64 {
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .map(|d| d.as_secs_f64())
+        .unwrap_or(0.0)
+}
+
+fn ensure_schema(conn: &Connection) -> rusqlite::Result<()> {
+    conn.execute_batch(
+        "CREATE TABLE IF NOT EXISTS tasks (id TEXT PRIMARY KEY, payload TEXT NOT NULL, \
+         run_after REAL NOT NULL, attempts INTEGER NOT NULL, status TEXT NOT NULL, \
+         locked_until REAL NOT NULL, created_at REAL NOT NULL);",
+    )
+}
+
+impl PersistentTaskQueue {
+    pub fn new(db_path: &str) -> Self {
+        // Ensure the parent dir and table exist even if only the queue (not
+        // ChatStore) is used — a fresh container without a mounted data dir
+        // must still be able to open the DB.
+        if let Some(parent) = std::path::Path::new(db_path).parent()
+            && !parent.as_os_str().is_empty()
+            && let Err(e) = std::fs::create_dir_all(parent)
+        {
+            log::error!("failed to create queue dir: {e}");
+        }
+        if let Ok(conn) = Connection::open(db_path)
+            && let Err(e) = ensure_schema(&conn)
+        {
+            log::error!("failed to initialize queue schema: {e}");
+        }
+        Self {
+            db_path: db_path.to_string(),
+            notify: Arc::new(Notify::new()),
+            stop: Arc::new(AtomicBool::new(false)),
+            worker: Mutex::new(None),
+            counter: AtomicU64::new(0),
+        }
+    }
+
+    /// Starts the worker loop. Also recovers rows left `in_progress` by a
+    /// previous process (lease expired).
+    pub async fn start<H, F, D, G>(&self, handler: H, dead_letter: D)
+    where
+        H: Fn(Value) -> F + Send + Sync + 'static,
+        F: Future<Output = Result<(), QueueError>> + Send + 'static,
+        D: Fn(Value, String) -> G + Send + Sync + 'static,
+        G: Future<Output = ()> + Send + 'static,
+    {
+        let handler: Arc<Handler> = Arc::new(move |payload| Box::pin(handler(payload)));
+        let dead_letter: Arc<DeadLetter> =
+            Arc::new(move |payload, message| Box::pin(dead_letter(payload, message)));
+        self.recover_stale().await;
+        let worker = QueueWorker {
+            db_path: self.db_path.clone(),
+            notify: Arc::clone(&self.notify),
+            stop: Arc::clone(&self.stop),
+            handler,
+            dead_letter,
+        };
+        let worker = tokio::spawn(worker.run_loop());
+        *self.worker.lock() = Some(worker);
+    }
+
+    pub async fn stop(&self) {
+        self.stop.store(true, Ordering::Relaxed);
+        self.notify.notify_one();
+        if let Some(handle) = self.worker.lock().take() {
+            let _ = handle.await;
+        }
+    }
+
+    /// Persists a task. `run_after` is an absolute unix timestamp (seconds).
+    /// Notifies the worker only after the insert has committed, so the worker
+    /// never wakes to an invisible row.
+    pub async fn enqueue(&self, payload: Value, run_after: f64) -> rusqlite::Result<()> {
+        let id = format!(
+            "task_{}_{}",
+            (now_f64() * 1000.0) as u64,
+            self.counter.fetch_add(1, Ordering::Relaxed)
+        );
+        let payload = payload.to_string();
+        let db_path = self.db_path.clone();
+        log::info!("enqueued {id} (run_after {run_after:.1})");
+        let result = tokio::task::spawn_blocking(move || -> rusqlite::Result<()> {
+            let conn = Connection::open(&db_path)?;
+            conn.execute(
+                "INSERT OR REPLACE INTO tasks (id, payload, run_after, attempts, status, locked_until, created_at) \
+                 VALUES (?1, ?2, ?3, 0, 'pending', 0, ?4)",
+                params![id, payload, run_after, now_f64()],
+            )?;
+            Ok(())
+        })
+        .await
+        .expect("queue insert worker panicked")?;
+        self.notify.notify_one();
+        Ok(result)
+    }
+
+    async fn recover_stale(&self) {
+        let db_path = self.db_path.clone();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<()> {
+            let conn = Connection::open(&db_path)?;
+            conn.execute(
+                "UPDATE tasks SET status='pending', locked_until=0 WHERE status='in_progress' AND locked_until < ?1",
+                params![now_f64()],
+            )?;
+            Ok(())
+        })
+        .await
+        .expect("queue recovery worker panicked")
+        .unwrap_or_else(|e| log::error!("queue recovery failed: {e}"));
+    }
+}
+
+impl QueueWorker {
+    async fn run_loop(self) {
+        while !self.stop.load(Ordering::Relaxed) {
+            match self.lease_next().await {
+                Some(row) => self.process(row).await,
+                None => {
+                    let wait_until = self.earliest_run_after().await;
+                    let notified = self.notify.notified();
+                    tokio::pin!(notified);
+                    match wait_until {
+                        Some(until) => {
+                            let delay = (until - now_f64()).max(0.0);
+                            tokio::select! {
+                                _ = &mut notified => {}
+                                _ = tokio::time::sleep(Duration::from_secs_f64(delay)) => {}
+                            }
+                        }
+                        None => {
+                            notified.await;
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    /// Leases the oldest due row (sets it `in_progress` with a lock TTL).
+    async fn lease_next(&self) -> Option<LeasedRow> {
+        let db_path = self.db_path.clone();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<Option<LeasedRow>> {
+            let mut conn = Connection::open(&db_path)?;
+            let tx = conn.transaction()?;
+            let now = now_f64();
+            let row = tx.query_row(
+                "SELECT id, payload, attempts FROM tasks WHERE status='pending' AND run_after <= ?1 \
+                 ORDER BY run_after LIMIT 1",
+                params![now],
+                |r| {
+                    Ok((
+                        r.get::<_, String>(0)?,
+                        r.get::<_, String>(1)?,
+                        r.get::<_, i32>(2)?,
+                    ))
+                },
+            );
+            let (id, payload, attempts) = match row {
+                Ok(row) => row,
+                Err(rusqlite::Error::QueryReturnedNoRows) => {
+                    tx.commit()?;
+                    return Ok(None);
+                }
+                Err(e) => return Err(e),
+            };
+            tx.execute(
+                "UPDATE tasks SET status='in_progress', locked_until=?1 WHERE id=?2",
+                params![now + LOCK_TTL_SECONDS, id],
+            )?;
+            tx.commit()?;
+            Ok(Some(LeasedRow {
+                id,
+                payload,
+                attempts,
+            }))
+        })
+        .await
+        .expect("queue lease worker panicked")
+        .unwrap_or_else(|e| {
+            log::error!("queue lease failed: {e}");
+            None
+        })
+    }
+
+    async fn earliest_run_after(&self) -> Option<f64> {
+        let db_path = self.db_path.clone();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<Option<f64>> {
+            let conn = Connection::open(&db_path)?;
+            let mut stmt = conn.prepare("SELECT MIN(run_after) FROM tasks WHERE status='pending'")?;
+            let mut rows = stmt.query([])?;
+            match rows.next()? {
+                Some(row) => Ok(row.get::<_, Option<f64>>(0)?),
+                None => Ok(None),
+            }
+        })
+        .await
+        .expect("queue timing worker panicked")
+        .unwrap_or_else(|e| {
+            log::error!("queue timing query failed: {e}");
+            None
+        })
+    }
+
+    async fn process(&self, row: LeasedRow) {
+        let payload: Value = match serde_json::from_str(&row.payload) {
+            Ok(value) => value,
+            Err(e) => {
+                log::error!("queue: unparseable payload for {}: {e}", row.id);
+                self.delete_row(&row.id).await;
+                (self.dead_letter)(Value::Null, format!("invalid stored payload: {e}")).await;
+                return;
+            }
+        };
+        log::info!("processing {} (attempt {})", row.id, row.attempts + 1);
+        match (self.handler)(payload).await {
+            Ok(()) => {
+                log::info!("task {} completed", row.id);
+                self.delete_row(&row.id).await;
+            }
+            Err(QueueError::Retryable {
+                delay_seconds,
+                payload,
+            }) => {
+                if row.attempts as u32 >= MAX_RETRIES {
+                    let message = format!("task failed after {MAX_RETRIES} retries");
+                    log::error!("dead-lettering {}: {message}", row.id);
+                    self.delete_row(&row.id).await;
+                    (self.dead_letter)(payload, message).await;
+                } else {
+                    log::info!(
+                        "task {} rescheduled in {delay_seconds:.1}s (attempt {})",
+                        row.id,
+                        row.attempts + 1
+                    );
+                    self.reschedule(&row.id, payload, delay_seconds, row.attempts + 1)
+                        .await;
+                }
+            }
+            Err(QueueError::Permanent { message, payload }) => {
+                log::error!("dead-lettering {}: {message}", row.id);
+                self.delete_row(&row.id).await;
+                (self.dead_letter)(payload, message).await;
+            }
+        }
+    }
+
+    async fn delete_row(&self, id: &str) {
+        let db_path = self.db_path.clone();
+        let id = id.to_string();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<()> {
+            let conn = Connection::open(&db_path)?;
+            conn.execute("DELETE FROM tasks WHERE id = ?1", params![id])?;
+            Ok(())
+        })
+        .await
+        .expect("queue delete worker panicked")
+        .unwrap_or_else(|e| log::error!("queue delete failed: {e}"));
+    }
+
+    async fn reschedule(&self, id: &str, payload: Value, delay_seconds: f64, attempts: i32) {
+        let db_path = self.db_path.clone();
+        let id = id.to_string();
+        let payload = payload.to_string();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<()> {
+            let conn = Connection::open(&db_path)?;
+            conn.execute(
+                "UPDATE tasks SET payload=?1, run_after=?2, attempts=?3, status='pending', locked_until=0 WHERE id=?4",
+                params![payload, now_f64() + delay_seconds, attempts, id],
+            )?;
+            Ok(())
+        })
+        .await
+        .expect("queue reschedule worker panicked")
+        .unwrap_or_else(|e| log::error!("queue reschedule failed: {e}"));
+        self.notify.notify_one();
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::sync::atomic::{AtomicUsize, Ordering as AtomicOrdering};
+
+    async fn new_queue() -> (PersistentTaskQueue, tempfile::TempDir) {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("queue.db");
+        let queue = PersistentTaskQueue::new(path.to_str().unwrap());
+        (queue, dir)
+    }
+
+    #[tokio::test]
+    async fn enqueue_runs_handler_once() {
+        let (queue, _dir) = new_queue().await;
+        let calls = Arc::new(AtomicUsize::new(0));
+        let calls_worker = calls.clone();
+        queue
+            .start(
+                move |payload| {
+                    assert_eq!(payload["n"], 42);
+                    calls_worker.fetch_add(1, AtomicOrdering::SeqCst);
+                    async { Ok(()) }
+                },
+                |_payload, _message| async {},
+            )
+            .await;
+        queue
+            .enqueue(serde_json::json!({"n": 42}), now_f64())
+            .await
+            .unwrap();
+        tokio::time::sleep(Duration::from_millis(300)).await;
+        assert_eq!(calls.load(AtomicOrdering::SeqCst), 1);
+        queue.stop().await;
+    }
+
+    #[tokio::test]
+    async fn retryable_reschedules_then_dead_letters() {
+        let (queue, _dir) = new_queue().await;
+        let calls = Arc::new(AtomicUsize::new(0));
+        let dead_calls = Arc::new(AtomicUsize::new(0));
+        let c = calls.clone();
+        let d = dead_calls.clone();
+        queue
+            .start(
+                move |payload| {
+                    c.fetch_add(1, AtomicOrdering::SeqCst);
+                    let payload = payload.clone();
+                    async move {
+                        Err(QueueError::Retryable {
+                            delay_seconds: 0.001,
+                            payload,
+                        })
+                    }
+                },
+                move |_payload, _message| {
+                    d.fetch_add(1, AtomicOrdering::SeqCst);
+                    async {}
+                },
+            )
+            .await;
+        queue
+            .enqueue(serde_json::json!({"a": 1}), now_f64())
+            .await
+            .unwrap();
+        tokio::time::sleep(Duration::from_millis(600)).await;
+        assert_eq!(
+            calls.load(AtomicOrdering::SeqCst),
+            MAX_RETRIES as usize + 1,
+            "handler should run once per attempt"
+        );
+        assert_eq!(dead_calls.load(AtomicOrdering::SeqCst), 1);
+        queue.stop().await;
+    }
+
+    #[tokio::test]
+    async fn permanent_error_dead_letters_immediately() {
+        let (queue, _dir) = new_queue().await;
+        let calls = Arc::new(AtomicUsize::new(0));
+        let dead_calls = Arc::new(AtomicUsize::new(0));
+        let c = calls.clone();
+        let d = dead_calls.clone();
+        queue
+            .start(
+                move |payload| {
+                    c.fetch_add(1, AtomicOrdering::SeqCst);
+                    let payload = payload.clone();
+                    async move {
+                        Err(QueueError::Permanent {
+                            message: "nope".into(),
+                            payload,
+                        })
+                    }
+                },
+                move |_payload, message| {
+                    assert_eq!(message, "nope");
+                    d.fetch_add(1, AtomicOrdering::SeqCst);
+                    async {}
+                },
+            )
+            .await;
+        queue
+            .enqueue(serde_json::json!({"a": 1}), now_f64())
+            .await
+            .unwrap();
+        tokio::time::sleep(Duration::from_millis(300)).await;
+        assert_eq!(calls.load(AtomicOrdering::SeqCst), 1);
+        assert_eq!(dead_calls.load(AtomicOrdering::SeqCst), 1);
+        queue.stop().await;
+    }
+
+    #[tokio::test]
+    async fn stale_in_progress_row_is_recovered_on_start() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("queue.db");
+        // Insert a stale leased row directly (lease expired).
+        {
+            let conn = Connection::open(&path).unwrap();
+            ensure_schema(&conn).unwrap();
+            conn.execute(
+                "INSERT INTO tasks (id, payload, run_after, attempts, status, locked_until, created_at) \
+                 VALUES ('task_stale', '{\"s\":1}', 0, 0, 'in_progress', ?1, 0)",
+                params![now_f64() - 10.0],
+            )
+            .unwrap();
+        }
+        let queue = PersistentTaskQueue::new(path.to_str().unwrap());
+        let calls = Arc::new(AtomicUsize::new(0));
+        let c = calls.clone();
+        queue
+            .start(
+                move |payload| {
+                    assert_eq!(payload["s"], 1);
+                    c.fetch_add(1, AtomicOrdering::SeqCst);
+                    async { Ok(()) }
+                },
+                |_payload, _message| async {},
+            )
+            .await;
+        tokio::time::sleep(Duration::from_millis(300)).await;
+        assert_eq!(calls.load(AtomicOrdering::SeqCst), 1);
+        queue.stop().await;
+    }
+}

crates/xmedia-bot/src/state.rs

@@ -0,0 +1,151 @@
+//! Per-chat state with SQLite persistence (table `chat_state` in
+//! `data/task_queue.db`, shared with the task queue).
+
+use parking_lot::Mutex;
+use rusqlite::{params, Connection};
+use serde::{Deserialize, Serialize};
+use std::collections::HashMap;
+use std::path::Path;
+use std::time::{Duration, SystemTime, UNIX_EPOCH};
+
+#[derive(Serialize, Deserialize, Default, Clone, Debug)]
+pub struct ChatData {
+    pub forward_channel_id: Option<i64>,
+    pub edit_before_forward: bool,
+    /// Key: prompt message id.
+    pub edit_message: HashMap<i64, EditMessage>,
+    /// name -> HTML template containing "[]"
+    pub template: HashMap<String, String>,
+    /// site name (twitter/bsky/pixiv) -> user-supplied caption format with
+    /// {url} {author} {author_url} {title} {tags} placeholders.
+    pub message_format: HashMap<String, String>,
+}
+
+#[derive(Serialize, Deserialize, Clone, Debug, Default)]
+pub struct EditMessage {
+    pub url: String,
+    pub chat_id: i64,
+    pub forward_message_ids: Vec<i64>,
+    pub template: String,
+    /// Unix seconds at registration; expiry = created_at + ttl.
+    pub created_at: i64,
+}
+
+pub struct ChatStore {
+    /// In-memory cache; the DB is the source of truth on first access.
+    cache: Mutex<HashMap<i64, ChatData>>,
+    db_path: String,
+}
+
+pub fn unix_now() -> i64 {
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .map(|d| d.as_secs() as i64)
+        .unwrap_or(0)
+}
+
+impl ChatStore {
+    /// Creates the parent directory and both tables (idempotent).
+    pub fn open(path: &str) -> rusqlite::Result<Self> {
+        if let Some(parent) = Path::new(path).parent()
+            && !parent.as_os_str().is_empty()
+        {
+            std::fs::create_dir_all(parent)
+                .map_err(|e| rusqlite::Error::ToSqlConversionFailure(Box::new(e)))?;
+        }
+        let conn = Connection::open(path)?;
+        conn.execute_batch(
+            "CREATE TABLE IF NOT EXISTS tasks (id TEXT PRIMARY KEY, payload TEXT NOT NULL, \
+             run_after REAL NOT NULL, attempts INTEGER NOT NULL, status TEXT NOT NULL, \
+             locked_until REAL NOT NULL, created_at REAL NOT NULL); \
+             CREATE TABLE IF NOT EXISTS chat_state (chat_id TEXT PRIMARY KEY, payload TEXT NOT NULL);",
+        )?;
+        drop(conn);
+        Ok(ChatStore {
+            cache: Mutex::new(HashMap::new()),
+            db_path: path.to_string(),
+        })
+    }
+
+    pub async fn get(&self, chat_id: i64) -> ChatData {
+        if let Some(data) = self.cache.lock().get(&chat_id) {
+            return data.clone();
+        }
+        let db_path = self.db_path.clone();
+        let payload = tokio::task::spawn_blocking(move || -> rusqlite::Result<Option<String>> {
+            let conn = Connection::open(&db_path)?;
+            let mut stmt = conn.prepare("SELECT payload FROM chat_state WHERE chat_id = ?1")?;
+            let mut rows = stmt.query(params![chat_id.to_string()])?;
+            match rows.next()? {
+                Some(row) => Ok(Some(row.get(0)?)),
+                None => Ok(None),
+            }
+        })
+        .await
+        .expect("chat_state worker panicked")
+        .unwrap_or_else(|e| {
+            log::error!("chat_state read failed: {e}");
+            None
+        })
+        .unwrap_or_default();
+        let data: ChatData = serde_json::from_str(&payload).unwrap_or_default();
+        self.cache.lock().insert(chat_id, data.clone());
+        data
+    }
+
+    /// Write-through: update the cache and the DB.
+    pub async fn set(&self, chat_id: i64, data: &ChatData) {
+        self.cache.lock().insert(chat_id, data.clone());
+        let payload = serde_json::to_string(data).expect("chat state serializes");
+        let db_path = self.db_path.clone();
+        tokio::task::spawn_blocking(move || -> rusqlite::Result<()> {
+            let conn = Connection::open(&db_path)?;
+            conn.execute(
+                "INSERT OR REPLACE INTO chat_state (chat_id, payload) VALUES (?1, ?2)",
+                params![chat_id.to_string(), payload],
+            )?;
+            Ok(())
+        })
+        .await
+        .expect("chat_state worker panicked")
+        .unwrap_or_else(|e| log::error!("chat_state write failed: {e}"));
+    }
+
+    /// Removes edit-before-forward records whose `created_at + ttl` is in the
+    /// past. Returns the removed `(chat_id, prompt_message_id)` pairs so the
+    /// caller can clear the prompt's buttons.
+    pub async fn prune_expired(&self, ttl: Duration) -> Vec<(i64, i64)> {
+        let now = unix_now();
+        let ttl_secs = ttl.as_secs() as i64;
+        let mut removed = Vec::new();
+        let changed: Vec<(i64, ChatData)> = {
+            let mut cache = self.cache.lock();
+            let mut out = Vec::new();
+            for (chat_id, data) in cache.iter_mut() {
+                let keys: Vec<i64> = data.edit_message.keys().copied().collect();
+                let mut kept = HashMap::new();
+                for key in keys {
+                    if let Some(entry) = data.edit_message.get(&key) {
+                        if entry.created_at + ttl_secs > now {
+                            kept.insert(key, entry.clone());
+                        } else {
+                            removed.push((*chat_id, key));
+                        }
+                    }
+                }
+                if kept.len() != data.edit_message.len() {
+                    data.edit_message = kept;
+                    out.push((*chat_id, data.clone()));
+                }
+            }
+            out
+        };
+        for (chat_id, data) in changed {
+            self.set(chat_id, &data).await;
+        }
+        if !removed.is_empty() {
+            log::info!("pruned {} expired edit-before-forward record(s)", removed.len());
+        }
+        removed
+    }
+}

docker-compose.yml.example

@@ -1,21 +1,68 @@
 services:
-  tgxmb: image: yoursfunny/telegram-twitter-media-bot: latest
+  nginx-proxy:
+    image: nginxproxy/nginx-proxy:1.11.6-alpine
     restart: always
     ports:
-      - "8443:8443"
+      - '80:80'
+      - '443:443'
+    environment:
+      # Bare-IP access only.
+      # DEFAULT_HOST: 'bot.example.com'
+    volumes:
+      - /var/run/docker.sock:/tmp/docker.sock:ro
+      - ./nginx-certs:/etc/nginx/certs:ro
+      - ./nginx-vhost.d:/etc/nginx/vhost.d:ro
+      - ./nginx-html:/usr/share/nginx/html:ro
+    networks: [proxy]
+    labels:
+      - 'com.github.jrcs.letsencrypt_nginx_proxy_companion.nginx_proxy=true'
+    container_name: nginx-proxy
+
+  acme-companion:
+    image: nginxproxy/acme-companion
+    restart: always
+    environment:
+      DEFAULT_EMAIL: 'admin@yoursfunny.top'
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./nginx-certs:/etc/nginx/certs:rw
+      - ./nginx-vhost.d:/etc/nginx/vhost.d:rw
+      - ./nginx-html:/usr/share/nginx/html:rw
+      - ./nginx-acme:/etc/acme.sh
+    networks: [proxy]
+    container_name: acme-companion
+    depends_on:
+      - nginx-proxy
+
+  tgxmb:
+    image: yoursfunny/telegram-twitter-media-bot:latest
+    restart: always
     environment:
       LOCAL_USER_ID: '1000'
-      BOT_TOKEN: ''
+      TELOXIDE_TOKEN: ''
       BOT_ADMIN: ''
-      WEBHOOK: false
+      PIXIV_REFRESH_TOKEN: ''
-      WEBHOOK_LISTEN: '127.0.0.1'
+      # Optional: x.com session cookie (auth_token) — fetches NSFW tweets
-      WEBHOOK_PORT: 8443
+      # that the public syndication endpoint withholds.
-      WEBHOOK_URL: 'https://example.com'
+      TWITTER_AUTH_TOKEN: ''
-      WEBHOOK_KEY: './cert/private.key'
+      EDIT_MESSAGE_TTL_SECONDS: '86400'
-      WEBHOOK_CERT: './cert/cert.pem'
+      RUST_LOG: 'info'
-      WEBHOOK_SECRET_TOKEN: 'secret-token'
+      VIRTUAL_HOST: 'bot.example.com'
-#      LOG_LEVEL: 'WARNING'
+      VIRTUAL_PORT: '8443'
-volumes:
+      # LETSENCRYPT_HOST: 'bot.example.com'
-      - ./data: /app/data
+      WEBHOOK: 'true'
-#      - ./cert:/app/cert
+      WEBHOOK_LISTEN: '0.0.0.0'
+      WEBHOOK_PORT: '8443'
+      WEBHOOK_URL: 'https://bot.example.com/'
+      # WEBHOOK_CERT: './cert/cert.pem'
+      WEBHOOK_SECRET_TOKEN: ''
+    volumes:
+      - ./data:/app/data
+    networks: [proxy]
+    depends_on:
+      - nginx-proxy
     container_name: tgxmb
+
+networks:
+  proxy:
+    name: proxy

docker-entrypoint.sh

@@ -10,7 +10,9 @@ then
    chown -R `id -u user`:`id -u user` /app > /dev/null 2>&1
 
    export HOME=/home/user
-   exec gosu user "$0" "$@"
+   # setpriv (util-linux, present in bookworm-slim) replaces gosu: drop to the
+   # target user and exec, keeping the process as PID 1.
+   exec setpriv --reuid=`id -u user` --regid=`id -g user` --init-groups "$@"
 fi
 
 exec "$@"

main.py

@@ -1,145 +0,0 @@
-from aiohttp import ClientSession
-from telegram import Update, Chat
-from telegram.constants import ParseMode, ChatAction, ChatType
-from telegram.ext import (
-    Application,
-    ApplicationBuilder,
-    ContextTypes,
-    Defaults,
-    filters,
-    InlineQueryHandler,
-    PicklePersistence,
-    MessageHandler,
-    CommandHandler
-)
-
-import common
-from tweet import TGTweet
-
-
-async def inline_query(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
-    query = update.inline_query.query
-    if query == "":
-        return
-    common.logger.info(f"Query: {query}")
-    async with TGTweet(query) as tweet:
-        result = list(tweet.inline_query_generator)
-        await update.inline_query.answer(result)
-
-
-async def reply_media(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
-    await update.effective_chat.send_action(ChatAction.UPLOAD_PHOTO)
-    # url = update.message.text.split(" ")[0]
-    url = update.message.text
-    common.logger.info(f"Receiving url: {url}")
-    async with TGTweet(url) as tweet:
-        media = list(tweet.pm_media_generator)
-        message_sent = await update.effective_message.reply_media_group(
-            media,
-            caption=tweet.message_text,
-            reply_to_message_id=update.message.message_id
-        )
-    if 'forward_channel_id' in context.user_data:
-        try:
-            await update.effective_chat.copy_messages(
-                chat_id=context.user_data['forward_channel_id'],
-                message_ids=[m.id for m in message_sent],
-            )
-        except Exception as e:
-            await update.effective_message.reply_text(str(e))
-
-
-async def cmd_set_forward_channel(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
-    await update.effective_chat.send_action(ChatAction.TYPING)
-    if not context.args:
-        await update.effective_message.reply_text("Please provide a channel username or id.")
-        return
-    channel = context.args[0]
-    try:
-        channel: Chat = await context.bot.get_chat(channel)
-    except Exception as e:
-        await update.effective_message.reply_text(str(e))
-        return
-    if channel.type != ChatType.CHANNEL:
-        await update.effective_message.reply_text("That is not a channel.")
-        return
-    try:
-        channel_admin = await channel.get_administrators()
-    except Exception as e:
-        await update.effective_message.reply_text(str(e) + "\nPlease add the bot to the channel and set as admin")
-        return
-    user_bot = filter(lambda x: x.user.id == context.bot.id, channel_admin)
-    user_bot = next(user_bot, None)
-    if user_bot.can_post_messages:
-        context.user_data['forward_channel_id'] = channel.id
-        await update.effective_message.reply_text("Add successfully.")
-
-
-async def cmd_remove_forward_channel(update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
-    await update.effective_chat.send_action(ChatAction.TYPING)
-    if 'forward_channel_id' in context.user_data:
-        del context.user_data['forward_channel_id']
-        await update.effective_message.reply_text("Remove successfully.")
-        return
-    await update.effective_message.reply_text("No channel to remove.")
-
-
-async def post_init(application: Application) -> None:
-    # commands = [
-    #     BotCommand('start', CMD_START),
-    # ]
-    # await application.bot.set_my_commands(commands)
-    DESCRIPTION = "A bot to fetch tweets from Twitter."
-    await application.bot.set_my_description(DESCRIPTION)
-    await application.bot.set_my_short_description(DESCRIPTION)
-    TGTweet.set_session(ClientSession())
-
-
-async def post_stop(application: Application) -> None:
-    await application.bot.send_message(common.ADMIN[0], "Shutting down...")
-
-
-async def post_shutdown(application: Application) -> None:
-    await TGTweet.close_session()
-
-
-def main():
-    defaults = Defaults(parse_mode=ParseMode.HTML, allow_sending_without_reply=True)
-    persistence = PicklePersistence(filepath='data/pers.pkl')
-    application = (ApplicationBuilder()
-                   .token(common.BOT_TOKEN)
-                   .defaults(defaults)
-                   .persistence(persistence)
-                   .post_init(post_init)
-                   .post_stop(post_stop)
-                   .post_shutdown(post_shutdown)
-                   .build()
-                   )
-
-    # user_filter = filters.User()
-    # user_filter.add_user_ids(common.admin)
-
-    handlers = [
-        MessageHandler(filters.Regex(common.x_url_regex) & filters.ChatType.PRIVATE, reply_media),
-        InlineQueryHandler(inline_query, common.x_url_regex),
-        CommandHandler("set_forward_channel", cmd_set_forward_channel),
-        CommandHandler("remove_forward_channel", cmd_remove_forward_channel),
-    ]
-
-    application.add_handlers(handlers)
-
-    if common.WEBHOOK:
-        application.run_webhook(
-            listen=common.WEBHOOK_LISTEN,
-            port=common.WEBHOOK_PORT,
-            secret_token=common.WEBHOOK_SECRET_TOKEN,
-            key=common.WEBHOOK_KEY,
-            cert=common.WEBHOOK_CERT,
-            webhook_url=common.WEBHOOK_URL
-        )
-    else:
-        application.run_polling()
-
-
-if __name__ == '__main__':
-    main()

requirements.txt

@@ -1,2 +0,0 @@
-python-telegram-bot[webhooks]~=21.0.1
-aiohttp[speedups]~=3.9.3

tweet.py

@@ -1,237 +0,0 @@
-from typing import Generator
-
-from aiohttp import ClientSession
-from telegram import (
-    InlineQueryResultPhoto,
-    InlineQueryResultVideo,
-    InlineQueryResultMpeg4Gif,
-    InputMediaPhoto,
-    InputMediaVideo,
-    InputMediaAnimation
-)
-
-from common import x_url_regex, x_media_regex, x_tco_regex, logger
-
-twimg_url = 'https://pbs.twimg.com/'
-vx_api_url = 'https://api.vxtwitter.com/{0}/status/{1}'
-
-message_raw_text = """{url}
-<a href="{author_url}">{author}</a>: {text}
-"""
-
-
-async def fetch_json(session: ClientSession, url: str) -> dict:
-    logger.info(f"Fetching {url}")
-    async with session.get(url) as response:
-        assert response.status == 200, f"Failed to fetch {url}, status code {response.status}"
-        return await response.json()
-
-
-class TweetMedia:
-    def __init__(self, url: str, thumb: str, media_type: str):
-        self._url: str = url
-        self._thumb: str = thumb
-        self._type: str = media_type
-
-    def __str__(self):
-        return f"Media[url: {self.url} thumb: {self.thumb} type: {self.type}]"
-
-    @property
-    def _uri(self) -> str | None:
-        match = x_media_regex.match(self._url)
-        if match:
-            return match.group(2).removesuffix('.jpg').removesuffix('.png')
-        return None
-
-    @property
-    def url(self) -> str:
-        match self._type:
-            case "image":
-                return f"{twimg_url}{self._uri}?format=jpg&name=4096x4096"
-            case "video":
-                return self._url
-            case "gif":
-                return self._url
-            case _:
-                return self._url
-
-    @property
-    def thumb(self) -> str:
-        match self._type:
-            case "image":
-                return f"{twimg_url}{self._uri}?format=jpg&name=thumb"
-            case "video":
-                return self._thumb
-            case "gif":
-                return self._thumb
-            case _:
-                return self._thumb
-
-    @property
-    def type(self) -> str:
-        return self._type
-
-
-class Tweet:
-    def __init__(
-            self,
-            tweet_id: str,
-            author: str,
-            author_id: str,
-            text: str,
-            media: list[TweetMedia],
-            sensitive: bool = False
-    ):
-        self._id: str = tweet_id
-        self._author: str = author
-        self._author_id: str = author_id
-        self._text: str = text
-        self._media: list[TweetMedia] = media
-        self._sensitive: bool = sensitive
-
-    @property
-    def id(self) -> str:
-        return self._id
-
-    @property
-    def url(self) -> str:
-        return f"https://twitter.com/{self._author_id}/status/{self._id}"
-
-    @property
-    def author(self) -> str:
-        return self._author
-
-    @property
-    def author_url(self) -> str:
-        return f"https://twitter.com/{self._author_id}"
-
-    @property
-    def text(self) -> str:
-        return self._text
-
-    @property
-    def media(self) -> list[TweetMedia]:
-        return self._media
-
-    @property
-    def sensitive(self) -> bool:
-        return self._sensitive
-
-
-class TGTweet(Tweet):
-    _session: ClientSession
-
-    def __init__(self, url: str):
-        self._url: str = url
-        self._api_param: tuple[str] = self._tweet_id
-        assert self._api_param
-
-    async def __aenter__(self):
-        self._tweet: dict = await self._fetch_tweet(self._api_param)
-        super().__init__(*self._init_properties)
-        return self
-
-    async def __aexit__(self, exc_type, exc_val, exc_tb):
-        pass
-
-    @classmethod
-    def set_session(cls, session: ClientSession) -> None:
-        cls._session = session
-
-    @classmethod
-    async def close_session(cls) -> None:
-        await cls._session.close()
-
-    async def _fetch_tweet(self, api_param: tuple[str]) -> dict:
-        return await fetch_json(self._session, vx_api_url.format(*api_param))
-
-    @property
-    def _tweet_id(self) -> tuple[str] | None:
-        match = x_url_regex.match(self._url)
-        if match:
-            return match.groups()
-        return None
-
-    @property
-    def _tweet_text(self) -> str:
-        match = x_tco_regex.search(self._tweet['text'])
-        return self._tweet['text'][:match.start()].strip(" ") if match else self._tweet['text']
-
-    @property
-    def _tweet_media(self) -> list[TweetMedia]:
-        return [
-            TweetMedia(
-                url=x['url'],
-                thumb=x['thumbnail_url'],
-                media_type=x['type']
-            )
-            for x in self._tweet['media_extended']
-        ]
-
-    @property
-    def _init_properties(self) -> tuple:
-        id = self._tweet['tweetID']
-        author = self._tweet['user_name']
-        author_id = self._tweet['user_screen_name']
-        text = self._tweet_text
-        media = self._tweet_media
-        sensitive = self._tweet['possibly_sensitive']
-        return id, author, author_id, text, media, sensitive
-
-    @property
-    def message_text(self) -> str:
-        return message_raw_text.format(
-            url=self.url,
-            author_url=self.author_url,
-            author=self.author,
-            text=self.text
-        )
-
-    @property
-    def inline_query_generator(self) -> Generator[InlineQueryResultPhoto | InlineQueryResultVideo, None, None]:
-        for i, tweet_media in enumerate(self.media):
-            logger.info(str(tweet_media))
-            if tweet_media.type == "image":
-                yield InlineQueryResultPhoto(
-                    id=str(i),
-                    photo_url=tweet_media.url,
-                    thumbnail_url=tweet_media.thumb,
-                    caption=self.message_text if not i else None
-                )
-            elif tweet_media.type == "video":
-                yield InlineQueryResultVideo(
-                    id=str(i),
-                    video_url=tweet_media.url,
-                    mime_type="video/mp4",
-                    thumbnail_url=tweet_media.thumb,
-                    caption=self.message_text if not i else None
-                )
-            elif tweet_media.type == "gif":
-                yield InlineQueryResultMpeg4Gif(
-                    id=str(i),
-                    mpeg4_url=tweet_media.url,
-                    thumbnail_url=tweet_media.thumb,
-                    caption=self.message_text if not i else None
-                )
-
-    @property
-    def pm_media_generator(self) -> Generator[InputMediaPhoto | InputMediaVideo, None, None]:
-        for tweet_media in self.media:
-            logger.info(str(tweet_media))
-            if tweet_media.type == "image":
-                yield InputMediaPhoto(
-                    media=tweet_media.url,
-                    has_spoiler=self.sensitive
-                )
-            elif tweet_media.type == "video":
-                yield InputMediaVideo(
-                    media=tweet_media.url,
-                    has_spoiler=self.sensitive,
-                    thumbnail=tweet_media.thumb
-                )
-            elif tweet_media.type == "gif":
-                yield InputMediaAnimation(
-                    media=tweet_media.url,
-                    has_spoiler=self.sensitive,
-                    thumbnail=tweet_media.thumb
-                )