chore: bump version to 1.6.0

Bump both crates (x-media, xmedia-bot) and refresh the lockfile to the
latest semver-compatible releases. No direct dependency or manifest
requirement changed.

.dockerignore

@@ -26,6 +26,10 @@
 *.db
 LICENSE
 README.md
+# Documentation and scratch files: the build only ever reads the manifests,
+# `crates/` and the entrypoint script.
+docs/
+*.md
 data/
 cert/
 nginx-certs/

.github/dependabot.yml

@@ -0,0 +1,32 @@
+version: 2
+
+# Pairs with the `actions-rust-lang/audit` gate in ci.yml: the gate reports
+# advisories in Cargo.lock, this is what actually moves the dependencies.
+# Patch bumps are batched into one PR; minor/major stay separate so they get
+# reviewed and tested individually.
+updates:
+  - package-ecosystem: cargo
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 5
+    groups:
+      cargo-patch:
+        applies-to: version-updates
+        patterns: ['*']
+        update-types: ['patch']
+
+  # The workflow actions are pinned to commit SHAs; that pin is what makes
+  # bumping them a manual chore, so let the bot do it.
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    open-pull-requests-limit: 5
+
+  # The Dockerfile's base images (rust:1-bookworm, debian:bookworm-slim).
+  - package-ecosystem: docker
+    directory: /
+    schedule:
+      interval: monthly
+    open-pull-requests-limit: 3

.github/workflows/ci.yml

@@ -4,14 +4,19 @@ name: CI
 # job that exercises the real source sites and the token-gated pixiv tests.
 #
 # Layering:
-#   test  — fmt + clippy + the full offline unit suite. Runs on every push
-#           and PR, including forks (it needs no secrets).
+#   test  — fmt + clippy + the full offline unit suite + a release-profile
+#           build + cargo-audit dependency gate. Runs on every push and PR,
+#           including forks (it needs no secrets).
 #   live  — the #[ignore]d live-network tests plus the pixiv tests that are
 #           gated on PIXIV_REFRESH_TOKEN. Runs on schedule / manual dispatch
 #           / tag pushes only, because pull requests from forks cannot read
 #           repository secrets. continue-on-error keeps a flaky external site
 #           from blocking, while the run still records the outcome.
 #
+# Every action is pinned to a commit SHA (Dependabot keeps the pins current);
+# `dtolnay/rust-toolchain` deliberately stays on its channel ref, because the
+# ref itself is what selects the toolchain (`@stable` = install stable).
+#
 # Test gating convention (keep in sync with AGENTS.md "Testing & QA"):
 #   - pure unit tests: plain #[test] / #[tokio::test], always run.
 #   - live-network tests: #[ignore = "live network: ..."], only run here.
@@ -27,38 +32,75 @@ on:
     - cron: '0 3 * * 1'
   workflow_dispatch:
 
+permissions:
+  contents: read
+
+# A newer push to the same ref supersedes the older run; without this every
+# intermediate commit of a PR branch keeps a runner busy to completion.
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  # Panicking tests print their backtrace; free when nothing fails.
+  RUST_BACKTRACE: 1
+
 jobs:
   test:
     runs-on: ubuntu-latest
+    # Generous on purpose: the release-profile build below is cold on the very
+    # first run (thin LTO + codegen-units = 1 across every dependency), and a
+    # timeout there would kill the job *before* rust-cache saves its cache —
+    # leaving every later run cold again.
+    timeout-minutes: 45
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
       - uses: dtolnay/rust-toolchain@stable
         with:
           components: clippy, rustfmt
-      - uses: Swatinem/rust-cache@v2
+      - uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2
+      # `--locked` on every cargo invocation: the version bump edits
+      # Cargo.lock by hand (AGENTS.md), so a stale lock must fail here instead
+      # of being silently re-resolved — otherwise CI tests a different
+      # dependency set than the one committed, and than the one the released
+      # image is built from.
       - name: Check formatting
         run: cargo fmt --check
       - name: Lint (deny warnings)
-        run: cargo clippy --workspace --all-targets -- -D warnings
+        run: cargo clippy --workspace --all-targets --locked -- -D warnings
       - name: Run offline tests
-        run: cargo test --workspace
+        run: cargo test --workspace --locked
+      # The release profile (lto/strip/codegen-units=1, overflow checks off)
+      # was otherwise only exercised by the Docker build on master/tag. Same
+      # package the Dockerfile builds; the cache keeps it cheap after the
+      # first run.
+      - name: Build release profile
+        run: cargo build --release --locked -p xmedia-bot
+      # Dependency vulnerability gate: fails the build when a crate in
+      # Cargo.lock has an unfixed security advisory. Unmaintained/unsound
+      # *warnings* (dotenv, proc-macro-error2, anyhow transitive) do not fail
+      # the build by default; the advisory DB is cached across runs.
+      - name: Audit dependencies
+        uses: actions-rust-lang/audit@72c09e02f132669d52284a3323acdb503cfc1a24 # v1
 
   live:
     needs: test
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' || startsWith(github.ref, 'refs/tags/v')
     runs-on: ubuntu-latest
+    timeout-minutes: 30
     continue-on-error: true
     env:
       PIXIV_REFRESH_TOKEN: ${{ secrets.PIXIV_REFRESH_TOKEN }}
       TWITTER_AUTH_TOKEN: ${{ secrets.TWITTER_AUTH_TOKEN }}
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
       - uses: dtolnay/rust-toolchain@stable
-      - uses: Swatinem/rust-cache@v2
-      # Full suite: with the secret present, the pixiv token-gated tests run;
-      # without it they skip themselves. Live tests stay #[ignore]d here.
+      - uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2
+      # Everything network- or secret-gated lives in x-media, and the bot
+      # crate's suite (MockSender + tempdir stores, no network) already ran in
+      # the `test` job — rebuilding it here bought nothing.
       - name: Run token-gated tests
-        run: cargo test --workspace
+        run: cargo test -p x-media --locked
       # The live-network tests, by the "live" name filter (all #[ignore]d).
       - name: Run live-network tests
-        run: cargo test --workspace -- --ignored live
+        run: cargo test -p x-media --locked -- --ignored live

.github/workflows/docker.yml

@@ -1,28 +1,75 @@
 name: Build Docker Image
 
+# Release builds (master / v* tags) plus a build-only check on pull requests
+# that touch anything the image depends on — the Dockerfile's stub-source
+# machinery, the ffmpeg download and the entrypoint are exactly the parts that
+# would otherwise break only at release time.
+#
+# Actions are pinned to commit SHAs (Dependabot keeps the pins current).
+
 on:
   push:
     tags:
       - v*
     branches:
       - master
+  pull_request:
+    paths:
+      - Dockerfile
+      - docker-entrypoint.sh
+      - .dockerignore
+      - Cargo.toml
+      - Cargo.lock
+      - .github/workflows/docker.yml
+      - 'crates/**/Cargo.toml'
 
 env:
   APP_NAME: telegram-twitter-media-bot
   DOCKERHUB_REPO: yoursfunny/telegram-twitter-media-bot
 
+permissions:
+  contents: read
+
+# Serialize runs per ref. Never cancel in progress: a killed run would drop a
+# half-finished image push.
+concurrency:
+  group: docker-${{ github.ref }}
+  cancel-in-progress: false
+
 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
+    timeout-minutes: 10
     outputs:
       build: ${{ steps.check.outputs.build }}
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
         with:
           fetch-depth: 0
+      # A release tag is the version claim: the manifests are bumped by hand,
+      # so `v1.5.1` with `Cargo.toml` still at 1.5.0 would publish an image
+      # whose tag lies about what is inside it (the binary carries no version).
+      - name: Verify the tag matches both crate versions
+        if: startsWith(github.ref, 'refs/tags/v')
+        shell: bash
+        run: |
+          tag="${GITHUB_REF_NAME#v}"
+          status=0
+          for manifest in crates/x-media/Cargo.toml crates/xmedia-bot/Cargo.toml; do
+            # tr -d '\r': a CRLF checkout (core.autocrlf on Windows) would
+            # otherwise yield "1.5.0\r" and false-fail every tag.
+            version="$(sed -n 's/^version = "\(.*\)"/\1/p' "$manifest" | head -1 | tr -d '\r')"
+            if [ "$version" != "$tag" ]; then
+              echo "::error file=$manifest::$manifest is at $version but the tag is v$tag"
+              status=1
+            else
+              echo "$manifest: $version matches v$tag"
+            fi
+          done
+          exit "$status"
       - id: check
         shell: bash
         run: |
@@ -37,10 +84,11 @@ jobs:
     needs: should-build
     if: needs.should-build.outputs.build == 'true'
     runs-on: ubuntu-latest
+    timeout-minutes: 60
     steps:
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@v6
+        uses: docker/metadata-action@dc802804100637a589fabce1cb79ff13a1411302 # v6
         with:
           images: ${{ env.DOCKERHUB_REPO }}
           tags: |
@@ -49,15 +97,15 @@ jobs:
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
             type=sha
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@v4
       -
         name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v4
+        uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069 # v4
+      # Pull requests build the image to prove the Dockerfile still works, but
+      # must not read registry credentials (fork PRs have none).
       -
         name: Login to Docker Hub
-        uses: docker/login-action@v4
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -66,15 +114,26 @@ jobs:
       # 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.
+      # would give every new tag a cold cache on release builds. PR runs only
+      # read it (cache-to is empty) so they cannot evict the release cache.
+      #
+      # FFMPEG_URL/FFMPEG_SHA256 come from repository variables when set, so a
+      # release can pin an exact ffmpeg build (the Dockerfile default follows
+      # the project's `/redirect/latest/` URL, which has no sha256 sidecar).
+      #
+      # Single-arch (amd64) on purpose: adding arm64 means re-adding
+      # `docker/setup-qemu-action`, `platforms: linux/amd64,linux/arm64`, and
+      # parameterizing FFMPEG_URL by $TARGETARCH in the Dockerfile.
       -
         name: Build and push
-        uses: docker/build-push-action@v7
+        uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc # v7
         with:
-          push: true
+          push: ${{ github.event_name != 'pull_request' }}
           build-args: |
             APP_NAME=${{ env.APP_NAME }}
+            FFMPEG_URL=${{ vars.FFMPEG_URL || 'https://ffmpeg.martin-riedl.de/redirect/latest/linux/amd64/release/ffmpeg.zip' }}
+            FFMPEG_SHA256=${{ vars.FFMPEG_SHA256 }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
           cache-from: type=gha,scope=tgxmb-build
-          cache-to: type=gha,mode=max,scope=tgxmb-build
+          cache-to: ${{ github.event_name != 'pull_request' && 'type=gha,mode=max,scope=tgxmb-build' || '' }}

AGENTS.md

@@ -2,11 +2,11 @@
 
 ## 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`).
+Telegram bot (teloxide) that turns post links from X/Twitter, Pixiv, Bluesky, and Misskey (misskey.io) 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 is in Chinese; user-facing bot strings are in English. The project is a Rust port of a Python predecessor (see `queue.rs` comments referencing `utils/task_queue.py`).
 
-Two-crate Cargo workspace (both v1.2.0, edition 2024, resolver 3):
+Two-crate Cargo workspace (both v1.6.0, edition 2024, resolver 3):
 
-- **`crates/x-media`** — library that fetches and normalizes media from the three sites. Pure, no Telegram knowledge.
+- **`crates/x-media`** — library that fetches and normalizes media from the four sites. Pure, no Telegram knowledge.
 - **`crates/xmedia-bot`** — the bot binary: teloxide dispatcher, SQLite-backed chat state, persistent task queue.
 
 ## Architecture & Data Flow
@@ -20,21 +20,29 @@ Telegram update → Dispatcher (polling or axum webhook) → dptree branches
 
 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 → workers lease (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}`.
+Debug command: `/debug <url>` runs the same `x_media::site::fetch` and replies with `debug_report` (`handlers/commands.rs`) — site id, normalized cache key, source URL, title/author/tags, sensitive flag, caption and the media list — nothing is sent, cached or forwarded; the report is capped at 4000 chars and sent with HTML parse mode: raw fields are escaped, and the caption is wrapped in a `<blockquote>` so it renders exactly like the sent media caption (escaped text and links included).
+
+The `/test <url>` command runs the ordinary link pipeline (`urls::url_media`) with `PostSend::Suppressed`: the media is sent and cached like any other link, but the chat's `forward_channel_id`/`edit_before_forward` are ignored, so a test never forwards to the channel and never opens the edit prompt (retries and dead-letter notifications behave as usual). Both commands use a custom `parse_arg_remainder` parser (whole remainder, trimmed) because teloxide's built-in `split` parser takes exactly one space-separated token.
+
+The `x-media` library: `site::fetch(url)` dispatches through the `SITES` registry (per-site `impl Site`, in order twitter → bsky → misskey → pixiv) and returns `Ok(None)` for unmatched URLs. `Fetched { source_url, caption, title, media: Vec<Media>, sensitive, site_id, … }`; `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, command registration (`register_commands`), shared `send::BOT` force-init, queue worker start, pixiv validation, 300 s edit-expiry sweep, dptree handler tree, webhook vs polling dispatch |
+| `crates/x-media/src/site/<twitter\|pixiv\|bsky\|misskey>/` | One directory per site: `mod.rs` (re-exports), `interface.rs` (PATTERN, `enabled()`, `fetch_from_url()`, `cache_key`/`is_retryable`/`media_headers`, unit struct `<Name>Site` implementing `site::Site`, `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`). Misskey targets misskey.io only (`POST /api/notes/show`, 400+`NO_SUCH_NOTE` → NotFound). Twitter's `from_syndication_json` HTML-decodes the API text — syndication and GraphQL `full_text` both arrive pre-escaped (`&gt;` `&lt;` `&amp;` `&#39;`) — so the stored text is raw and the caption escapes exactly once |
+| `crates/xmedia-bot/src/main.rs` | Entry point: env/log init, command registration (`register_commands`), shared `send::BOT` force-init, queue worker start, site login validation (`site::validate_all`), 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; per-URL work flows through a bounded job channel (256) drained by `URL_WORKERS = 8` workers (`start_url_workers`) — backpressure instead of unbounded spawns (teloxide's per-chat workers are sequential — batch-forwards need concurrency) |
+| `crates/xmedia-bot/src/db.rs` | `DbPool`: one shared SQLite connection pool (`POOL_SIZE = 4`, WAL, busy_timeout) for all three tables over `$DATA_DIR/task_queue.db` (default `data/`) — the three stores share it; `open_store` creates file + schema, `with_conn` runs all rusqlite I/O in `spawn_blocking` |
+| `crates/xmedia-bot/src/handlers/` | Handler modules: `mod.rs` (message entry point, `reply`, `log_key`), `commands.rs` (teloxide `BotCommands` enum + command executor, incl. `/test <url>` (send-only) / `/debug <url>` (parse-only) and the admin-only `/bot_dict` state dump), `urls.rs` (URL extraction + bounded job channel (256) drained by `URL_WORKERS = 8` workers (`start_url_workers`) — backpressure instead of unbounded spawns; teloxide's per-chat workers are sequential — batch-forwards need concurrency), `inline.rs`/`callback.rs` (inline queries / edit-before-forward buttons), `statics.rs` (global statics) |
 | `crates/xmedia-bot/src/state.rs` | `ChatStore`: parking_lot `Mutex<HashMap>` cache + SQLite write-through (`chat_state` table) |
 | `crates/xmedia-bot/src/link_cache.rs` | `LinkCache`: SQLite-backed cache (`link_cache` table) of successfully sent posts — raw caption fields + Telegram `file_id`s; repeat links re-send locally (no fetch/upload), TTL + prune, invalidated on permanent send failure |
-| `crates/xmedia-bot/src/queue.rs` | `PersistentTaskQueue`: SQLite-backed queue (`tasks` table), `QUEUE_WORKERS = 4` concurrent workers (lease via `BEGIN IMMEDIATE` + `locked_until` TTL), retry→dead-letter, `Notify::notify_waiters` wakeup, `busy_timeout` on all connections |
-| `crates/xmedia-bot/src/send.rs` | Media senders, upload fallback, error classification, queue task handlers |
+| `crates/xmedia-bot/src/queue.rs` | `PersistentTaskQueue`: SQLite-backed queue (`tasks` table), `QUEUE_WORKERS = 4` concurrent workers (lease via `BEGIN IMMEDIATE` + `locked_until` TTL), retry→dead-letter, `notify_one` worker wakeup plus a separate `Notify` for the 30 s lease-expiry sweep (a shared one let the sweep steal the workers' wakeup permit), `busy_timeout` on all connections |
+| `crates/xmedia-bot/src/ctx.rs` | `AppContext`: the injected collaborators (`sender` + `ChatStore`/`PersistentTaskQueue`/`LinkCache`/`Config`), `from_statics` for production and the `CONTEXT` static the worker closures hold. `test_support::TestStores` backs handler tests with a tempdir store set |
+| `crates/xmedia-bot/src/send/` | `send/mod.rs`: `Task`/`MediaItemPayload` payloads, `SendError`/`Classification`, `send_media_sequence`/`send_animation`/`forward_messages`; `send/input_media.rs`: payload → `InputFile`/`InputMedia` + `build_media_group` (caption on the first item only); `send/upload.rs`: the download-and-reupload fallback (`prepare_upload_item`/`send_batch_via_upload`, photo downscale handoff); `send/post_send.rs`: link-cache write, `KEEP_ALIVE` registry, `settle_task`, `post_send_actions`, `handle_task`/`dead_letter_notify` |
+| `crates/xmedia-bot/src/media_sender.rs` | `MediaSender` trait: the user-flow surface (`send_media_group`/`send_animation`/`copy_messages`/`send_message`/`answer_callback_query`/`edit_message_caption`/`delete_message`/`send_chat_action`) implemented by teloxide `Bot` (per-chat rate-limited) and by a recording `MockSender` in tests. Admin/setup APIs (`get_chat`, `set_my_commands`, …) stay on the concrete `Bot` |
+| `crates/xmedia-bot/src/rate_limit.rs` | Per-chat token bucket (`CAPACITY = 20`, ~20 msg/min refill) paced before sends reach the API so batch forwards don't trip flood control |
 
 ## Development Commands
 
@@ -52,30 +60,30 @@ Docker: `docker build -t tgxmb .` then `docker run --rm -d --name tgxmb --env-fi
 
 ## 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 share the process-wide `send::BOT` (`LazyLock<Bot>`, force-initialized in `main` so a missing token fails at startup).
+- **Errors via `thiserror` derive** (no anyhow): the public, stringified errors — `FetchError` (`Http`/`Json`/`Pixiv`/`Site`/`NotFound`/`Blocked`) and `PixivError` — derive `thiserror::Error` with `#[from]` conversions; `Display`/`source()` come from the derive. The internal control-flow enums — `QueueError` (`Retryable { delay_seconds, payload }` / `Permanent`), `SendError` (Retryable/Permanent), `Classification`, `FallbackError` — carry no `Display` and are handled by direct variant matching. New errors should follow the same split: stringified/public errors derive `thiserror`, internal flow enums stay plain.
+- **Global state via `std::sync::LazyLock` statics**, not DI: `CONFIG`, `CHAT_STORE`, `TASK_QUEUE` in `handlers/statics.rs`; shared reqwest `CLIENT` in `x-media/src/site/mod.rs`. `Bot` is passed/cloned into handlers; queue workers share the process-wide `send::BOT` (`LazyLock<Bot>`, force-initialized in `main` so a missing token fails at startup).
 - **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`.
+- **Site adapter convention**: each site module exports `PATTERN: LazyLock<Regex>`, `enabled() -> bool`, `fetch_from_url(url) -> Result<Fetched, FetchError>`, plus `cache_key`/`is_retryable`/`media_headers`, and a unit struct `<Name>Site` implementing `site::Site`; the central dispatcher (`site/mod.rs`) only iterates the `SITES` registry. Adding a site = new `site/<name>/{mod.rs,interface.rs,model.rs}` + one `Box::new(...)` entry in `SITES` — the bot crate never lists sites (SetFormat whitelist, cache-key site lookup and startup validation all derive from the registry). Async trait methods return `SiteFuture` (a boxed `Pin<Box<dyn Future + Send>>`) because `async fn` in traits is not dyn-compatible.
 - **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`).
+- **Retries**: only `x-media::site::fetch` retries (3 attempts, `1 << attempt` backoff, HTTP errors only); `site::fetch_once` is the same code path with a single attempt, used by inline queries whose answer window is shorter than the backoff. Queue retries are explicit `QueueError::Retryable` with computed delay (`retry_delay_seconds`).
+- Logging via `log` macros (`pretty_env_logger`, level from `RUST_LOG`). Level convention: `info` = lifecycle + per-post business results (`sent`/`forwarded`/`copied`), admin/operator actions and anomalies (fallback, retry enqueue, dead-letter is `error`); `debug` = per-request detail (message/command/URL extraction, `fetching`/`fetched`, batch sends, queue processing, photo processing, inline queries). Full user-submitted URLs and message text only appear at `debug`; at `info` and above links are printed via the normalized cache key (`handlers::log_key`, e.g. `[key=twitter:123...]`) so logs stay short and do not echo user data.
 
 ## 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`; fallback chain; `classify_request_error`; download-and-reupload fallback triggered only by Telegram API errors (`is_media_fetch_failure` / `is_size_error`) |
+| `crates/xmedia-bot/src/handlers/` | `statics.rs` = `CHAT_STORE`/`TASK_QUEUE`/`CONFIG` singletons (open `$DATA_DIR/task_queue.db`, default `data/` **relative to CWD**, dir auto-created); `commands.rs` = command dispatch (incl. `/test <url>` send-only, `/debug <url>` parse-only, and the admin-only `/bot_dict` state dump); `urls.rs` = URL extraction + the per-URL pipeline (`url_media` takes a `PostSend` mode: chat settings vs `/test`'s suppressed actions); `inline.rs` = debounced inline queries; `callback.rs` = edit-before-forward buttons (dptree entry + testable `handle_callback` core) |
+| `crates/xmedia-bot/src/send/` | `mod.rs`: constants `MAX_MEDIA_GROUP = 9`; `classify_request_error`; the senders. `upload.rs`: download-and-reupload fallback triggered only by Telegram API errors (`is_media_fetch_failure` / `is_size_error`). `post_send.rs`: settlement (`settle_task`), cache write, post-send actions, queue handlers. `input_media.rs`: payload → `InputMedia` |
 | `crates/xmedia-bot/src/photo.rs` | Pure-Rust photo processing (no ffmpeg): `png` (image-png) decode/encode + `zune-jpeg` decode + `fast_image_resize` Lanczos3 downscale + `jpeg-encoder`. Photos over Telegram's limits (width + height > 10000 px → `PHOTO_INVALID_DIMENSIONS`; bytes > 10 MiB) are decoded, downscaled keeping the format, PNG bit depth > 24 (RGBA 32-bit / 16-bit per channel) reduced to 24-bit RGB with alpha flattened white (≤24-bit untouched, never upconverted), and transcoded to JPEG only if still over the cap; memory budget guarded, otherwise the item's smaller fallback URL |
 | `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 bump (cargo's freshness is mtime-based and `cargo clean -p` removes 0 files — the touch is what forces the real sources to rebuild while deps stay cached), static ffmpeg from ffmpeg.martin-riedl.de (`FFMPEG_URL` arg, optional `FFMPEG_SHA256` checksum, `unzip -t` integrity check), `debian:bookworm-slim` runtime, entrypoint. Runtime ships **no libssl/libcrypto/CA bundle** — rustls webpki-roots handles all TLS, and the static ffmpeg only processes local files (downloads go through reqwest) |
 | `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 |
+| `.github/workflows/docker.yml` | CI: build+push to Docker Hub on tag `v*`/master, plus a build-only check on PRs touching the build inputs; **no test step**; verifies a release tag matches both crate versions; buildx gha cache (`cache-from` always, `cache-to` except on PRs, scope `tgxmb-build`, `mode=max`) so cargo deps + ffmpeg layers are restored across runs; `FFMPEG_URL`/`FFMPEG_SHA256` come from repo variables when set |
 | `README.md` | Feature docs + command table (Chinese) |
 
 ## Runtime/Tooling Preferences
@@ -83,18 +91,18 @@ Docker: `docker build -t tgxmb .` then `docker run --rm -d --name tgxmb --env-fi
 - **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.
 - **TLS is rustls end-to-end** (no native-tls/openssl in the tree, no libssl in the Docker runtime image): `teloxide` is declared `default-features = false` with `["webhooks-axum", "macros", "rustls", "ctrlc_handler"]` (the removed `default` also carried `native-tls` and `ctrlc_handler` — the latter must stay); x-media's reqwest is `default-features = false` with `["json", "rustls-tls"]` (webpki-roots baked in, so the image ships no CA bundle). One reqwest 0.12.28 in the lock.
-- **Versioning**: bump the version in all three places (`crates/x-media/Cargo.toml`, `crates/xmedia-bot/Cargo.toml`, `Cargo.lock`) and **keep `README.md` and `AGENTS.md` in sync with the code on every bump**, then commit (`chore: bump version to X.Y.Z`), create an annotated tag `vX.Y.Z`, and push branch + tag (the tag push triggers the Docker Hub build).
-- 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), `LINK_CACHE_TTL_SECONDS` (default 604800), `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.
+- **Versioning**: bump the version in all three places (`crates/x-media/Cargo.toml`, `crates/xmedia-bot/Cargo.toml`, `Cargo.lock`) and **keep `README.md`, `README.en.md` and `AGENTS.md` in sync with the code on every bump**, then commit (`chore: bump version to X.Y.Z`), create an annotated tag `vX.Y.Z`, and push branch + tag (the tag push triggers the Docker Hub build). The tag must equal both crate versions: `.github/workflows/docker.yml` verifies that before building, and `--locked` verifies the lock file.
+- 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), `LINK_CACHE_TTL_SECONDS` (default 604800), `DATA_DIR` (default `data`, CWD-relative; the SQLite dir, auto-created), `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_DIR/task_queue.db` (default `data/task_queue.db`, CWD-relative — run from the workspace root, or `/app` in Docker; set `DATA_DIR` to pin state anywhere). 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.
+- Docs are in Chinese (README, AGENTS.md); user-facing bot strings are in English. Keep that split when editing user-facing strings and docs.
 
 ## Testing & QA
 
-- **~80 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).
+- **~135 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`. Test gating convention (enforced by `.github/workflows/ci.yml`): pure unit tests always run; live-network tests carry `#[ignore = "live network: ..."]` (run via `cargo test --workspace -- --ignored live`); token-gated pixiv tests early-return when `PIXIV_REFRESH_TOKEN` is absent **or empty** (an unset GitHub secret arrives as `""` — `is_err()` alone would run them tokenless and fail). Run the full offline suite with `cargo test --workspace`.
+- Live-network tests exist in `site/twitter/interface.rs` (5), `site/bsky/interface.rs` (2), `site/misskey/interface.rs` (1), `site/pixiv/api.rs` (1); `photo.rs` adds one `#[ignore = "heavy: …"]` test. `site/mod.rs` also has a **token-gated but not `#[ignore]`d** pixiv download test (`download_media_pixiv_original_with_referer`): it hits `i.pximg.net` whenever `PIXIV_REFRESH_TOKEN` is set, so a local `cargo test --workspace` is not fully offline and can flake on a pixiv CDN body timeout. Test gating convention (enforced by `.github/workflows/ci.yml`): pure unit tests always run; live-network tests carry `#[ignore = "live network: ..."]` (run via `cargo test --workspace -- --ignored live`); token-gated pixiv tests early-return when `PIXIV_REFRESH_TOKEN` is absent **or empty** (an unset GitHub secret arrives as `""` — `is_err()` alone would run them tokenless and fail). Run the full offline 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** — `.github/workflows/ci.yml` runs `cargo fmt --check` + `cargo clippy --workspace --all-targets -- -D warnings` + `cargo test --workspace` (offline, no secrets, on every push/PR) and a `live` job (schedule/manual/tag only, `PIXIV_REFRESH_TOKEN`/`TWITTER_AUTH_TOKEN` from secrets, `continue-on-error`) for the `#[ignore]`d live + token tests. `.github/workflows/docker.yml` builds/pushes the image only.
-- 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`.
+- **CI** — `.github/workflows/ci.yml` (actions pinned to commit SHAs, `--locked` on every cargo invocation, `concurrency` cancels superseded runs, `RUST_BACKTRACE=1`) runs `cargo fmt --check` + `cargo clippy --workspace --all-targets --locked -- -D warnings` + `cargo test --workspace --locked` + a release-profile `cargo build --release --locked` + an `actions-rust-lang/audit` dependency-vulnerability gate (offline, no secrets, on every push/PR) and a `live` job (schedule/manual/tag only, `-p x-media` since every network/secret-gated test lives there, `continue-on-error`) for the `#[ignore]`d live + token tests. `.github/workflows/docker.yml` builds and pushes the image on master/tag and runs a **build-only check on pull requests touching the build inputs** (`Dockerfile`, entrypoint, manifests, `.dockerignore`); a release tag must match both crate versions or the build stops, and `FFMPEG_URL`/`FFMPEG_SHA256` are taken from repository variables when set (a release can pin an exact ffmpeg build). `.github/dependabot.yml` keeps crates, the pinned actions and the Docker base images current.
+- Untested and hard to test without a mock seam: `main.rs`, `config.rs`, `db.rs`, `handlers/statics.rs`, `media_sender.rs` (holds the `MockSender` itself); in `x-media`: `media.rs`, `lib.rs`, all `model.rs`. The `commands.rs` *executor* needs a real `Bot` (only its pure report builder is tested). Everything else — `handlers/{mod,callback,inline,urls}.rs`, `send/*`, `ctx.rs`, `state.rs`, `queue.rs`, `link_cache.rs`, `rate_limit.rs` — is driven through `TestStores`/`ctx::test_support` and the scripted `MockSender`.
 - No coverage tracking.

Dockerfile

@@ -11,6 +11,8 @@ ARG APP_NAME=telegram-twitter-media-bot
 # 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
+# Arm64 images need this URL swapped for the `linux/arm64` build (currently
+# hardcoded amd64; the workflow builds amd64 only — see docker.yml).
 # Optional sha256 of ffmpeg.zip (pinned releases only): set to verify the
 # download. The mirror publishes .sha256 sidecars next to pinned builds, e.g.
 # https://ffmpeg.martin-riedl.de/download/linux/amd64/<id>_9.0/ffmpeg.zip.sha256
@@ -28,7 +30,7 @@ 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
+    && cargo build --release --locked -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
@@ -51,7 +53,7 @@ RUN wget -q -O /tmp/ffmpeg.zip "$FFMPEG_URL" \
 #    removes 0 files and the stub binary silently ships.)
 COPY crates/ ./crates/
 RUN find crates -type f -name '*.rs' -exec touch {} + \
-    && cargo build --release -p xmedia-bot
+    && cargo build --release --locked -p xmedia-bot
 
 # ---------- runtime stage ----------
 FROM debian:bookworm-slim

README.en.md

@@ -1,6 +1,6 @@
 # TelegramXMediaBot
 
-A Telegram bot that turns post links from X / Twitter, Pixiv, and Bluesky into media messages (images, video, GIF) with the post's title, author, and tags.
+A Telegram bot that turns post links from X / Twitter, Pixiv, Bluesky, and Misskey (misskey.io) into media messages (images, video, GIF) with the post's title, author, and tags.
 
 ## Features
 
@@ -30,7 +30,7 @@ docker build -t tgxmb .
 docker run --rm -d --name tgxmb --env-file .env -v ./data:/app/data tgxmb
 ```
 
-Environment variables: `TELOXIDE_TOKEN` (required), `PIXIV_REFRESH_TOKEN`, `BOT_ADMIN`, `EDIT_MESSAGE_TTL_SECONDS`, `LINK_CACHE_TTL_SECONDS`, `RUST_LOG`, `WEBHOOK*`, `TWITTER_AUTH_TOKEN` (optional).
+Environment variables: `TELOXIDE_TOKEN` (required), `PIXIV_REFRESH_TOKEN`, `BOT_ADMIN`, `EDIT_MESSAGE_TTL_SECONDS`, `LINK_CACHE_TTL_SECONDS`, `RUST_LOG`, `TELOXIDE_PROXY`, `WEBHOOK*`, `TWITTER_AUTH_TOKEN` (optional).
 
 NSFW tweets: the public syndication endpoint does not return sensitive content. Setting `TWITTER_AUTH_TOKEN` (the `auth_token` cookie value of a logged-in x.com session) lets the bot fetch NSFW media in the logged-in state only when it hits a withheld tweet; without it, the bot reports no media.
 
@@ -84,6 +84,7 @@ Telegram only accepts ports 443/80/88/8443.
 | `BOT_ADMIN` | Admin chat IDs, comma-separated; receives start/stop notifications |
 | `EDIT_MESSAGE_TTL_SECONDS` | Edit-before-forward record expiry in seconds, default 86400 |
 | `LINK_CACHE_TTL_SECONDS` | Link-result cache expiry in seconds, default 604800 (7 days) |
+| `DATA_DIR` | Data directory (where the SQLite `task_queue.db` lives), default `data` (relative to the working directory, created automatically) |
 | `RUST_LOG` | Log level |
 | `TELOXIDE_PROXY` | HTTP proxy (e.g. `http://127.0.0.1:10808`); applies to both the Telegram Bot API and site fetches — required on restricted networks (e.g. behind the GFW) |
 | `LOCAL_USER_ID` | UID the container runs as, default 9001 |
@@ -110,9 +111,11 @@ Telegram only accepts ports 443/80/88/8443.
 | `/remove_forward_channel` | Remove the forward channel |
 | `/edit_before_forward` | Toggle "edit before forward": when enabled, the bot posts a prompt after forwarding; replying to it edits the first forwarded message's caption (or taps a template button to apply one) |
 | `/set_template <name>` | Reply to a message containing `[]` to save it as a named template; `[]` is replaced by the original post link when forwarding (used with "edit before forward") |
-| `/set_format <site> <format>` | Customize the caption format for one site. Sites: `twitter` / `bsky` / `pixiv`. Placeholders: `{url}` `{author}` `{author_url}` `{title}` `{tags}` |
+| `/set_format <site> <format>` | Customize the caption format for one site. Sites: `twitter` / `bsky` / `pixiv` / `misskey`. Placeholders: `{url}` `{author}` `{author_url}` `{title}` `{tags}` |
 | `/clear_cache [link]` | Clear the link cache (admin only); with a link only that entry, otherwise everything |
-| `/bot_dict` | Show the current chat state (debugging) |
+| `/bot_dict` | Show the current chat state (debugging; admin only) |
+| `/test <link>` | Parse a link and send its media; no channel forward, no edit-before-forward prompt (send only) |
+| `/debug <link>` | Debug: parse a link and report the parse result only (site, title, author, tags, media list) — no media is sent |
 
 Link processing works only in private chats; commands work in any chat.
 

README.md

@@ -1,6 +1,6 @@
 # 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。
+Telegram 机器人，将 X / Twitter、Pixiv、Bluesky、Misskey (misskey.io) 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
 
@@ -30,7 +30,7 @@ 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`、`LINK_CACHE_TTL_SECONDS`、`RUST_LOG`、`WEBHOOK*`、`TWITTER_AUTH_TOKEN`（可选）。
+环境变量：`TELOXIDE_TOKEN`（必填）、`PIXIV_REFRESH_TOKEN`、`BOT_ADMIN`、`EDIT_MESSAGE_TTL_SECONDS`、`LINK_CACHE_TTL_SECONDS`、`RUST_LOG`、`TELOXIDE_PROXY`、`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。
 
@@ -84,6 +84,7 @@ Telegram 只接受 443/80/88/8443 端口。
 | `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 |
 | `LINK_CACHE_TTL_SECONDS` | 链接结果缓存过期秒数，默认 604800（7 天） |
+| `DATA_DIR` | 数据目录（SQLite 数据库 `task_queue.db` 所在目录），默认 `data`（相对工作目录，会自动创建） |
 | `RUST_LOG` | 日志级别 |
 | `TELOXIDE_PROXY` | HTTP 代理（如 `http://127.0.0.1:10808`）；同时作用于 Telegram Bot API 与站点抓取请求，网络受限环境（如 GFW）必需 |
 | `LOCAL_USER_ID` | 容器内运行用户 UID，默认 9001 |
@@ -110,9 +111,11 @@ Telegram 只接受 443/80/88/8443 端口。
 | `/remove_forward_channel` | 取消转发频道 |
 | `/edit_before_forward` | 开关「转发前编辑」：开启后，转发成功后 bot 会发一条提示消息，回复它可修改第一条转发消息的 caption（或点击模板按钮套用模板） |
 | `/set_template <名称>` | 回复一条含 `[]` 的消息，将其保存为命名模板；转发时 `[]` 会被替换为原帖链接（配合「转发前编辑」使用） |
-| `/set_format <站点> <格式>` | 自定义某站点的 caption 格式。站点：`twitter` / `bsky` / `pixiv`。占位符：`{url}` `{author}` `{author_url}` `{title}` `{tags}` |
+| `/set_format <站点> <格式>` | 自定义某站点的 caption 格式。站点：`twitter` / `bsky` / `pixiv` / `misskey`。占位符：`{url}` `{author}` `{author_url}` `{title}` `{tags}` |
 | `/clear_cache [链接]` | 清空链接缓存（仅管理员）；带链接只清该条，否则清空全部 |
-| `/bot_dict` | 查看当前聊天状态（调试用） |
+| `/bot_dict` | 查看当前聊天状态（调试用；仅管理员） |
+| `/test <链接>` | 解析链接并发送媒体；不转发到频道、不弹转发前编辑提示（仅发送） |
+| `/debug <链接>` | 调试：只解析链接并返回解析结果（站点、标题、作者、标签、媒体列表），不发送任何媒体 |
 
 链接处理仅限私聊；命令在任意聊天可用。
 

crates/x-media/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "x-media"
-version = "1.2.0"
+version = "1.6.0"
 edition = "2024"
 
 [dependencies]
@@ -13,6 +13,7 @@ url = "2.5.2"
 bytes = "1"
 zip = "2"
 tempfile = "3"
+thiserror = "2"
 rand = "0.8"
 log = "0.4"
 tokio = { version = "1.40", features = ["time"] }

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

@@ -1,10 +1,31 @@
 use super::model;
 use crate::media::Media;
-use crate::site::{FetchError, Fetched};
+use crate::site::{FetchError, Fetched, Site, SiteFuture};
 use html_escape::{encode_double_quoted_attribute, encode_text};
 use regex::Regex;
 use std::sync::LazyLock;
 
+/// Registry entry for the bluesky adapter (see [`crate::site::Site`]).
+pub struct BskySite;
+
+impl Site for BskySite {
+    fn id(&self) -> &'static str {
+        "bsky"
+    }
+
+    fn pattern(&self) -> &'static Regex {
+        &PATTERN
+    }
+
+    fn cache_key(&self, url: &str) -> Option<String> {
+        cache_key(url)
+    }
+
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched> {
+        Box::pin(async move { fetch_from_url(url).await })
+    }
+}
+
 pub static PATTERN: LazyLock<Regex> = LazyLock::new(|| {
     Regex::new(r"^(?:https?://)?bsky\.app/profile/([\w.\-:]+)/post/([\w.\-~]+)").unwrap()
 });
@@ -59,6 +80,25 @@ pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
     Ok(fetched)
 }
 
+/// Cache key for a bsky URL: `"bsky:<handle>/<rkey>"`. The prefix is the
+/// site id used for caption-format lookup and link-cache keys.
+pub fn cache_key(url: &str) -> Option<String> {
+    PATTERN
+        .captures(url)
+        .map(|caps| format!("bsky:{}/{}", &caps[1], &caps[2]))
+}
+
+/// Bluesky's fetch-retry policy: transient classes only. Not-found, blocked
+/// and parse failures are permanent.
+pub fn is_retryable(err: &FetchError) -> bool {
+    matches!(err, FetchError::Http(_) | FetchError::Transient(_))
+}
+
+/// bsky media (cdn.bsky.app) needs no extra headers.
+pub fn media_headers(_url: &str) -> Option<Vec<(&'static str, String)>> {
+    None
+}
+
 /// Downloads an HLS playlist (master or media) and remuxes its segments to a
 /// single MP4 via ffmpeg. Returns the MP4 path plus the temp dir that must
 /// stay alive until the file is uploaded. `Ok(None)` when ffmpeg is missing.
@@ -299,6 +339,7 @@ impl From<Post> for Fetched {
             title: post.text.clone(),
             media: post.media,
             sensitive: post.sensitive,
+            site_id: "bsky",
             render_data,
             _keep_alive: None,
         }

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

@@ -1,4 +1,6 @@
 mod interface;
 mod model;
 
-pub use interface::{PATTERN, Post, enabled, fetch_from_url};
+pub use interface::{
+    BskySite, PATTERN, Post, cache_key, enabled, fetch_from_url, is_retryable, media_headers,
+};

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

@@ -0,0 +1,384 @@
+//! Site adapter for misskey.io notes: URL pattern, API fetch and
+//! normalization into [`Fetched`] (see [`crate::site::Site`]).
+
+use super::model;
+use crate::media::Media;
+use crate::site::{FetchError, Fetched, RenderData, Site, SiteFuture};
+use html_escape::{encode_double_quoted_attribute, encode_text};
+use regex::Regex;
+use std::sync::LazyLock;
+
+const API_URL: &str = "https://misskey.io/api/notes/show";
+
+/// Registry entry for the misskey.io adapter (see [`crate::site::Site`]).
+pub struct MisskeySite;
+
+impl Site for MisskeySite {
+    fn id(&self) -> &'static str {
+        "misskey"
+    }
+
+    fn pattern(&self) -> &'static Regex {
+        &PATTERN
+    }
+
+    fn cache_key(&self, url: &str) -> Option<String> {
+        cache_key(url)
+    }
+
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched> {
+        Box::pin(async move { fetch_from_url(url).await })
+    }
+}
+
+pub static PATTERN: LazyLock<Regex> =
+    LazyLock::new(|| Regex::new(r"^(?:https?://)?misskey\.io/notes/([\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 note_id = caps.get(1).ok_or(FetchError::NotFound)?.as_str();
+    let note = fetch(note_id).await?;
+    Ok(note.into())
+}
+
+/// Cache key for a misskey URL: `"misskey:<note id>"`. The prefix is the
+/// site id used for caption-format lookup and link-cache keys.
+pub fn cache_key(url: &str) -> Option<String> {
+    PATTERN
+        .captures(url)
+        .map(|caps| format!("misskey:{}", &caps[1]))
+}
+
+/// Misskey's fetch-retry policy: transient classes only. Not-found, blocked
+/// and parse failures are permanent.
+pub fn is_retryable(err: &FetchError) -> bool {
+    matches!(err, FetchError::Http(_) | FetchError::Transient(_))
+}
+
+/// misskey.io media hosts need no extra headers (verified: direct GET works).
+pub fn media_headers(_url: &str) -> Option<Vec<(&'static str, String)>> {
+    None
+}
+
+/// Fetches a note from misskey.io by id. The API answers client failures
+/// with HTTP 400 + `{"error":{"code":...}}` (NO_SUCH_NOTE → NotFound);
+/// everything else non-success is transient and retried by [`crate::site::fetch`].
+pub async fn fetch(note_id: &str) -> Result<model::Note, FetchError> {
+    let response = crate::site::CLIENT
+        .post(API_URL)
+        .json(&serde_json::json!({ "noteId": note_id }))
+        .send()
+        .await?;
+    let status = response.status();
+    if !status.is_success() {
+        return Err(match status.as_u16() {
+            400 => not_found_or_invalid(response).await,
+            _ => FetchError::Transient(format!("misskey status {status}")),
+        });
+    }
+    response.json().await.map_err(|e| FetchError::Site {
+        site: "misskey",
+        error: Box::new(e),
+    })
+}
+
+/// Maps a 400 response: NO_SUCH_NOTE is permanent NotFound, any other 400 is
+/// a site error (permanent — retrying a rejected request cannot succeed).
+async fn not_found_or_invalid(response: reqwest::Response) -> FetchError {
+    match response.json::<serde_json::Value>().await {
+        Ok(v) if v["error"]["code"] == "NO_SUCH_NOTE" => FetchError::NotFound,
+        _ => FetchError::Site {
+            site: "misskey",
+            error: "note rejected (invalid param or private note)".into(),
+        },
+    }
+}
+
+/// The note whose content matters: a renote shell has no text/files of its
+/// own — the embedded renote carries them.
+fn effective(note: &model::Note) -> &model::Note {
+    match &note.renote {
+        Some(renote) if note.files.is_empty() => renote,
+        _ => note,
+    }
+}
+
+impl From<model::Note> for Fetched {
+    fn from(note: model::Note) -> Self {
+        let note = &note;
+        let content = effective(note);
+        let url = format!("https://misskey.io/notes/{}", note.id);
+        let author = content
+            .user
+            .name
+            .as_deref()
+            .filter(|n| !n.is_empty())
+            .unwrap_or(&content.user.username)
+            .to_string();
+        let author_url = format!("https://misskey.io/@{}", content.user.username);
+        let cw = content.cw.as_deref().unwrap_or_default();
+        // Notes carry hashtags inline in the text (no structured tags array);
+        // a CW note gets the marker prefixed so recipients see the spoiler.
+        let mut title = cw.to_string();
+        if !cw.is_empty() && !title.ends_with(' ') {
+            title.push(' ');
+        }
+        title.push_str(content.text.as_deref().unwrap_or_default().trim());
+        let title = title.trim().to_string();
+
+        let caption = caption(&url, &author_url, &author, &title);
+        let sensitive = content.cw.is_some() || content.files.iter().any(|f| f.is_sensitive);
+        let media: Vec<Media> = content.files.iter().filter_map(media_from_file).collect();
+
+        Fetched {
+            source_url: url.clone(),
+            caption,
+            title: title.clone(),
+            media,
+            sensitive,
+            site_id: "misskey",
+            render_data: Some(RenderData {
+                url,
+                author: encode_text(&author).into_owned(),
+                author_url: author_url.clone(),
+                title: encode_text(&title).into_owned(),
+                tags: String::new(),
+            }),
+            _keep_alive: None,
+        }
+    }
+}
+
+fn caption(url: &str, author_url: &str, author: &str, text: &str) -> String {
+    let url = encode_double_quoted_attribute(url);
+    let author_url = encode_double_quoted_attribute(author_url);
+    let author = encode_text(author);
+    if text.is_empty() {
+        return format!("{url}\n<a href=\"{author_url}\">{author}</a>");
+    }
+    format!(
+        "{url}\n<a href=\"{author_url}\">{author}</a>: {text}",
+        text = encode_text(text),
+    )
+}
+
+/// Maps a Misskey DriveFile to a [`Media`] item; unknown/audio/other types
+/// are skipped (twitter's `_ => {}` precedent). GIF must be matched before
+/// the generic image arm.
+fn media_from_file(file: &model::DriveFile) -> Option<Media> {
+    let title = file.name.clone();
+    match file.mime_type.as_str() {
+        "image/gif" => Some(Media::Animated {
+            title,
+            url: file.url.clone(),
+            thumbnail_url: file.thumbnail_url.clone().unwrap_or_default(),
+        }),
+        mime if mime.starts_with("image/") => Some(Media::Illustration {
+            title,
+            url: file.url.clone(),
+            thumbnail_url: file.thumbnail_url.clone(),
+            fallback_url: None,
+        }),
+        mime if mime.starts_with("video/") => Some(Media::Video {
+            title,
+            url: file.url.clone(),
+            thumbnail_url: file.thumbnail_url.clone().unwrap_or_default(),
+        }),
+        _ => None,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn note_json(json: serde_json::Value) -> model::Note {
+        serde_json::from_value(json).unwrap()
+    }
+
+    fn base_note() -> serde_json::Value {
+        serde_json::json!({
+            "id": "aotihl10lqrs015s",
+            "text": "hello",
+            "user": { "name": "ミロン", "username": "donyan47897", "host": null },
+            "files": []
+        })
+    }
+
+    #[test]
+    fn pattern_matches_misskey_note_urls() {
+        for url in [
+            "https://misskey.io/notes/aotihl10lqrs015s",
+            "http://misskey.io/notes/aotihl10lqrs015s",
+            "misskey.io/notes/aotihl10lqrs015s",
+        ] {
+            assert!(PATTERN.is_match(url), "{url}");
+        }
+        for url in [
+            "https://misskey.io/",
+            "https://misskey.io/@user",
+            "https://misskey.io/notes/",
+            "https://x.com/user/status/123",
+        ] {
+            assert!(!PATTERN.is_match(url), "{url}");
+        }
+    }
+
+    #[test]
+    fn cache_key_normalizes_variants() {
+        assert_eq!(
+            cache_key("https://misskey.io/notes/aotihl10lqrs015s"),
+            Some("misskey:aotihl10lqrs015s".to_string())
+        );
+        assert_eq!(x_media_site_id("misskey:abc"), "misskey");
+    }
+
+    fn x_media_site_id(key: &str) -> &'static str {
+        crate::site::site_id_from_key(key)
+    }
+
+    #[test]
+    fn from_json_image_file() {
+        let mut note = base_note();
+        note["files"] = serde_json::json!([{
+            "type": "image/webp",
+            "url": "https://media.misskeyusercontent.jp/io/a.webp",
+            "thumbnailUrl": "https://media.misskeyusercontent.jp/io/t.webp",
+            "isSensitive": true,
+            "name": "pic.webp"
+        }]);
+        let fetched: Fetched = note_json(note).into();
+        assert_eq!(
+            fetched.source_url,
+            "https://misskey.io/notes/aotihl10lqrs015s"
+        );
+        assert_eq!(fetched.site_id, "misskey");
+        assert_eq!(fetched.title, "hello");
+        assert!(fetched.sensitive);
+        assert_eq!(fetched.media.len(), 1);
+        match &fetched.media[0] {
+            Media::Illustration {
+                title,
+                url,
+                thumbnail_url,
+                fallback_url,
+            } => {
+                assert_eq!(title.as_deref(), Some("pic.webp"));
+                assert_eq!(url, "https://media.misskeyusercontent.jp/io/a.webp");
+                assert_eq!(
+                    thumbnail_url.as_deref(),
+                    Some("https://media.misskeyusercontent.jp/io/t.webp")
+                );
+                assert!(fallback_url.is_none());
+            }
+            other => panic!("expected illustration, got {other:?}"),
+        }
+    }
+
+    #[test]
+    fn from_json_gif_video_and_skip_audio() {
+        let mut note = base_note();
+        note["files"] = serde_json::json!([
+            { "type": "audio/mpeg", "url": "https://m/a.mp3", "isSensitive": false },
+            { "type": "image/gif", "url": "https://m/a.gif", "isSensitive": false },
+            { "type": "video/webm", "url": "https://m/a.webm", "isSensitive": false }
+        ]);
+        let fetched: Fetched = note_json(note).into();
+        assert_eq!(fetched.media.len(), 2);
+        assert!(
+            matches!(&fetched.media[0], Media::Animated { url, .. } if url == "https://m/a.gif")
+        );
+        assert!(matches!(&fetched.media[1], Media::Video { url, .. } if url == "https://m/a.webm"));
+        // No thumbnailUrl → empty string, not a broken URL.
+        match &fetched.media[1] {
+            Media::Video { thumbnail_url, .. } => assert_eq!(thumbnail_url, ""),
+            other => panic!("expected video, got {other:?}"),
+        }
+        assert!(!fetched.sensitive);
+    }
+
+    #[test]
+    fn from_json_cw_marks_sensitive_and_prefixes_title() {
+        let mut note = base_note();
+        note["cw"] = serde_json::json!("spoiler");
+        note["text"] = serde_json::json!("body");
+        let fetched: Fetched = note_json(note).into();
+        assert!(fetched.sensitive);
+        assert_eq!(fetched.title, "spoiler body");
+    }
+
+    #[test]
+    fn from_json_author_falls_back_to_username() {
+        let mut note = base_note();
+        note["user"] = serde_json::json!({ "name": null, "username": "donyan47897", "host": null });
+        let fetched: Fetched = note_json(note).into();
+        assert!(
+            fetched.caption.contains("donyan47897"),
+            "{}",
+            fetched.caption
+        );
+        assert!(fetched.caption.contains("https://misskey.io/@donyan47897"));
+    }
+
+    #[test]
+    fn from_json_renote_uses_embedded_content() {
+        let note = serde_json::json!({
+            "id": "shell0000000000",
+            "text": null,
+            "user": { "name": "shell", "username": "shelluser", "host": null },
+            "files": [],
+            "renote": {
+                "id": "inner000000000",
+                "text": "inner text",
+                "user": { "name": "inner", "username": "inneruser", "host": null },
+                "files": [
+                    { "type": "image/png", "url": "https://m/i.png", "isSensitive": false }
+                ]
+            }
+        });
+        let fetched: Fetched = note_json(note).into();
+        assert_eq!(fetched.title, "inner text");
+        assert_eq!(fetched.media.len(), 1);
+        // The source URL still points at the renote shell the user posted.
+        assert_eq!(
+            fetched.source_url,
+            "https://misskey.io/notes/shell0000000000"
+        );
+    }
+
+    #[test]
+    fn caption_layout_matches_bsky() {
+        let fetched: Fetched = note_json(base_note()).into();
+        assert_eq!(
+            fetched.caption,
+            "https://misskey.io/notes/aotihl10lqrs015s\n<a href=\"https://misskey.io/@donyan47897\">ミロン</a>: hello"
+        );
+    }
+
+    #[test]
+    fn caption_without_text_has_no_dangling_colon() {
+        let mut note = base_note();
+        note["text"] = serde_json::json!(null);
+        let fetched: Fetched = note_json(note).into();
+        assert_eq!(
+            fetched.caption,
+            "https://misskey.io/notes/aotihl10lqrs015s\n<a href=\"https://misskey.io/@donyan47897\">ミロン</a>"
+        );
+    }
+
+    #[tokio::test]
+    #[ignore = "live network: requires outbound HTTPS to misskey.io"]
+    async fn live_fetch_reference_note() {
+        let fetched = fetch_from_url("https://misskey.io/notes/aotihl10lqrs015s")
+            .await
+            .unwrap();
+        assert_eq!(fetched.site_id, "misskey");
+        assert_eq!(fetched.media.len(), 1);
+        assert!(fetched.sensitive);
+        assert!(!fetched.caption.is_empty());
+    }
+}

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

@@ -0,0 +1,6 @@
+mod interface;
+mod model;
+
+pub use interface::{
+    MisskeySite, PATTERN, cache_key, enabled, fetch_from_url, is_retryable, media_headers,
+};

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

@@ -0,0 +1,35 @@
+use serde::Deserialize;
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct Note {
+    pub(crate) id: String,
+    pub(crate) text: Option<String>,
+    #[serde(default)]
+    pub(crate) cw: Option<String>,
+    pub(crate) user: User,
+    #[serde(default)]
+    pub(crate) files: Vec<DriveFile>,
+    /// Embedded original note when this note is a renote; the shell's own
+    /// text/files are usually empty and the content lives here.
+    #[serde(default)]
+    pub(crate) renote: Option<Box<Note>>,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct User {
+    pub(crate) name: Option<String>,
+    pub(crate) username: String,
+}
+
+#[derive(Deserialize, Debug)]
+pub(crate) struct DriveFile {
+    #[serde(rename = "type")]
+    pub(crate) mime_type: String,
+    pub(crate) url: String,
+    #[serde(default, rename = "thumbnailUrl")]
+    pub(crate) thumbnail_url: Option<String>,
+    #[serde(default, rename = "isSensitive")]
+    pub(crate) is_sensitive: bool,
+    #[serde(default)]
+    pub(crate) name: Option<String>,
+}

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

@@ -1,15 +1,20 @@
 //! 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`].
+//! Dispatch order: twitter → bsky → misskey → pixiv. Each site module
+//! exports a `PATTERN`, `enabled()` and `fetch_from_url()`; a future site
+//! plugs in by adding one guarded entry in `SITES`.
 
-use std::fmt;
+use std::future::Future;
+use std::pin::Pin;
 use std::sync::LazyLock;
 use std::sync::atomic::{AtomicBool, Ordering};
 use std::time::Duration;
 
+use regex::Regex;
+use thiserror::Error;
+
 pub mod bsky;
+pub mod misskey;
 pub mod pixiv;
 pub mod twitter;
 
@@ -19,9 +24,9 @@ pub use pixiv::PixivError;
 /// 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}
+    /// 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,
@@ -30,6 +35,10 @@ pub struct Fetched {
     pub media: Vec<crate::media::Media>,
     /// Spoiler flag for all media of this post.
     pub sensitive: bool,
+    /// Site id (`"twitter"` / `"bsky"` / `"pixiv"`): the single source of
+    /// truth for site identity — caption-format lookup, cache-key prefix and
+    /// the SetFormat whitelist all derive from it. Set by the producing site.
+    pub site_id: &'static str,
     /// 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
@@ -37,8 +46,15 @@ pub struct Fetched {
     pub(crate) _keep_alive: Option<tempfile::TempDir>,
 }
 
-/// Pre-escaped values for `{url} {author} {author_url} {title} {tags}`
-/// placeholders in user-supplied caption formats.
+/// Values for the `{url} {author} {author_url} {title} {tags}` placeholders in
+/// user-supplied caption formats, substituted by [`caption_from_fields`] as
+/// HTML text (never as an attribute value).
+///
+/// `author`, `title` and `tags` come from the site API (post text, display
+/// names) and are HTML-escaped at construction. `url` and `author_url` stay
+/// raw: they are canonical URLs the adapter builds from numeric ids and
+/// API-constrained handles/DIDs, so they carry no escapable character — the
+/// bot's `/test` report relies on that when it embeds them.
 #[derive(Debug)]
 pub(crate) struct RenderData {
     pub url: String,
@@ -50,16 +66,10 @@ pub(crate) struct RenderData {
 
 impl Fetched {
     /// The site this post came from (used for per-site format overrides).
+    /// A thin alias over [`Fetched::site_id`] kept for callers that read the
+    /// site off a fetched post.
     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"
-        }
+        self.site_id
     }
 
     /// Renders a user-supplied caption format. The format string is
@@ -162,88 +172,64 @@ pub fn caption_from_fields(
 
 /// Stable per-post cache key derived from any supported URL, so variant
 /// domains (x.com / twitter.com / fxtwitter.com, mobile, `/photo/N`
-/// suffixes) map to the same post. Returns `"twitter:<id>"`,
-/// `"pixiv:<id>"` or `"bsky:<handle>/<rkey>"`.
+/// suffixes) map to the same post. Delegates to each registered site's
+/// `cache_key` (in registry order).
 pub fn cache_key(url: &str) -> Option<String> {
-    if let Some(caps) = twitter::PATTERN.captures(url) {
-        return Some(format!("twitter:{}", &caps[1]));
-    }
-    if let Some(caps) = pixiv::PATTERN.captures(url) {
-        return Some(format!("pixiv:{}", &caps[1]));
-    }
-    if let Some(caps) = bsky::PATTERN.captures(url) {
-        return Some(format!("bsky:{}/{}", &caps[1], &caps[2]));
-    }
-    None
+    SITES.iter().find_map(|site| site.cache_key(url))
 }
 
-#[derive(Debug)]
+/// The site id carried by a cache key (`"twitter:123"` → `"twitter"`).
+/// Unknown prefixes fall back to `"unknown"`. The bot uses this on the
+/// link-cache hit path, where no [`Fetched`] is available — the same value
+/// a fresh fetch would read from [`Fetched::site_id`].
+pub fn site_id_from_key(key: &str) -> &'static str {
+    let prefix = key.split(':').next().unwrap_or("");
+    SITES
+        .iter()
+        .map(|site| site.id())
+        .find(|id| *id == prefix)
+        .unwrap_or("unknown")
+}
+
+#[derive(Debug, Error)]
 pub enum FetchError {
-    Http(reqwest::Error),
-    Json(serde_json::Error),
-    Pixiv(PixivError),
+    #[error("http error: {0}")]
+    Http(#[from] reqwest::Error),
+    #[error("json error: {0}")]
+    Json(#[from] serde_json::Error),
+    #[error("pixiv error: {0}")]
+    Pixiv(#[from] PixivError),
+    /// A site-specific error from a site that keeps its own error type.
+    /// Permanent by default (sites that need retryable site errors convert
+    /// them to [`FetchError::Http`] / [`FetchError::Transient`] before
+    /// returning). Pixiv predates this and keeps the dedicated
+    /// [`FetchError::Pixiv`] variant.
+    #[error("{site} error: {error}")]
+    Site {
+        site: &'static str,
+        #[source]
+        error: Box<dyn std::error::Error + Send + Sync>,
+    },
+    #[error("not found")]
     NotFound,
+    #[error("blocked")]
     Blocked,
     /// The post exists but its content is withheld (twitter NSFW /
     /// age-restricted tweets come back as an empty `{}` from syndication).
+    #[error("content withheld (sensitive)")]
     Sensitive,
     /// A download exceeded the caller's size cap (see [`download_media_limited`]).
+    #[error("media too large")]
     TooLarge,
     /// A transient server-side failure (429 / 5xx); [`fetch`] retries these.
+    #[error("transient: {0}")]
     Transient(String),
     /// A local I/O failure while streaming a download to disk
     /// (see [`download_media_to_file`]).
+    #[error("io error: {0}")]
     Io(std::io::Error),
 }
 
-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)"),
-            FetchError::TooLarge => write!(f, "media too large"),
-            FetchError::Transient(message) => write!(f, "transient: {message}"),
-            FetchError::Io(e) => write!(f, "io error: {e}"),
-        }
-    }
-}
-
-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,
-            FetchError::TooLarge => None,
-            FetchError::Transient(_) => None,
-            FetchError::Io(e) => Some(e),
-        }
-    }
-}
-
-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(|| {
@@ -296,65 +282,174 @@ pub(crate) fn log_once_ffmpeg_missing() {
     }
 }
 
+/// Site adapter: one impl per supported site (twitter / bsky / misskey /
+/// pixiv), registered in `SITES`. All site-specific knowledge — URL pattern,
+/// cache-key format, fetch, retry policy, media-host headers, startup
+/// validation — lives in the site module; the central dispatcher only
+/// iterates the registry.
+///
+/// Async methods return a boxed future (see `SiteFuture`): `async fn` /
+/// RPITIT in traits are not dyn-compatible (verified on rustc 1.95), and
+/// `+ Send` is required since URL/queue workers spawn these futures. The
+/// site structs are stateless unit structs, so the boxed futures never
+/// borrow from `self` beyond the call's scope.
+pub trait Site: Send + Sync {
+    /// Stable site id (`"twitter"` / `"bsky"` / `"misskey"` / `"pixiv"`):
+    /// caption-format lookup, cache-key prefixes and the SetFormat whitelist
+    /// derive from it.
+    fn id(&self) -> &'static str;
+    /// URL pattern; the dispatcher's first match wins (dispatch order).
+    fn pattern(&self) -> &'static Regex;
+    /// Whether the site is usable (env token present, not disabled).
+    fn enabled(&self) -> bool {
+        true
+    }
+    /// Normalized cache key for a URL of this site (`None` when the URL does
+    /// not match this site).
+    fn cache_key(&self, url: &str) -> Option<String>;
+    /// Fetches and normalizes a post.
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched>;
+    /// Retry policy for fetch errors: transient classes only.
+    fn is_retryable(&self, err: &FetchError) -> bool {
+        matches!(err, FetchError::Http(_) | FetchError::Transient(_))
+    }
+    /// Extra headers for downloading this site's media (hotlink protection,
+    /// e.g. pixiv's Referer for pximg.net). Matched on the media URL, not
+    /// the site pattern.
+    fn media_headers(&self, _url: &str) -> Option<Vec<(&'static str, String)>> {
+        None
+    }
+    /// Startup validation (token check etc.); failures are surfaced by
+    /// [`validate_all`]. The default is a no-op.
+    fn validate(&self) -> SiteFuture<'static, (), String> {
+        Box::pin(async { Ok(()) })
+    }
+}
+
+/// A boxed, `Send` future produced by a [`Site`] async method. Boxed so the
+/// trait stays dyn-compatible; `Send` because URL/queue workers `tokio::spawn`
+/// these futures.
+type SiteFuture<'a, T, E = FetchError> = Pin<Box<dyn Future<Output = Result<T, E>> + Send + 'a>>;
+
+/// The one registry of supported sites, in dispatch order (twitter → bsky →
+/// misskey → pixiv). Adding a site = new module + one `Box::new(...)` entry
+/// here; the bot crate never lists sites itself.
+static SITES: LazyLock<Vec<Box<dyn Site>>> = LazyLock::new(|| {
+    vec![
+        Box::new(twitter::TwitterSite),
+        Box::new(bsky::BskySite),
+        Box::new(misskey::MisskeySite),
+        Box::new(pixiv::PixivSite),
+    ]
+});
+
+/// The first enabled site whose pattern matches `url`, in dispatch order.
+fn find_site(url: &str) -> Option<&'static dyn Site> {
+    SITES
+        .iter()
+        .find(|site| site.enabled() && site.pattern().is_match(url))
+        .map(|site| site.as_ref())
+}
+
+/// Every supported site id, in dispatch order. The bot's SetFormat whitelist
+/// derives from this list.
+pub fn site_ids() -> Vec<&'static str> {
+    SITES.iter().map(|site| site.id()).collect()
+}
+
+/// Runs every enabled site's startup validation and returns the failures
+/// (site id + message). The caller logs / notifies; failing sites disable
+/// themselves (pixiv disables on a bad token).
+pub async fn validate_all() -> Vec<(&'static str, String)> {
+    let mut failures = Vec::new();
+    for site in SITES.iter() {
+        if !site.enabled() {
+            continue;
+        }
+        if let Err(e) = site.validate().await {
+            failures.push((site.id(), e));
+        }
+    }
+    failures
+}
+
 /// 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. Retried classes: bare HTTP errors, [`FetchError::Transient`]
-/// (429/5xx from any site), and pixiv errors (its network failures arrive
-/// wrapped as `PixivError`). Non-retried: Json/NotFound/Blocked/Sensitive.
+/// Transient failures are retried: 3 total attempts with 1s then 2s delays.
+/// What counts as transient is the matched site's own policy (`is_retryable`
+/// — e.g. pixiv retries only network errors and 429/5xx). Permanent classes
+/// (not-found, blocked, sensitive, parse failures, pixiv 4xx/auth errors)
+/// are returned immediately; retrying them only wastes attempts against the
+/// source site.
 pub async fn fetch(url: &str) -> Result<Option<Fetched>, FetchError> {
-    for attempt in 0..3u32 {
-        match fetch_once(url).await {
-            Ok(Some(fetched)) => {
-                log::info!(
-                    "fetched {url}: site {} returned {} media",
+    fetch_with_attempts(url, MAX_FETCH_ATTEMPTS).await
+}
+
+/// [`fetch`] without the retry backoff (one attempt). For callers with a
+/// short deadline: an inline query's answer window is measured in seconds, so
+/// the 1s + 2s retry sleeps would outlast the query the answer belongs to.
+pub async fn fetch_once(url: &str) -> Result<Option<Fetched>, FetchError> {
+    fetch_with_attempts(url, 1).await
+}
+
+/// Total attempts of the retried [`fetch`] (3: the initial try plus two).
+const MAX_FETCH_ATTEMPTS: u32 = 3;
+
+async fn fetch_with_attempts(url: &str, attempts: u32) -> Result<Option<Fetched>, FetchError> {
+    let Some(site) = find_site(url) else {
+        return Ok(None);
+    };
+    for attempt in 0..attempts.max(1) {
+        match site.fetch_from_url(url).await {
+            Ok(fetched) => {
+                // Per-request detail: debug only, keyed by the post id.
+                log::debug!(
+                    "fetched [key={}]: site {} returned {} media",
+                    cache_key(url).unwrap_or_else(|| "?".into()),
                     fetched.site_name(),
                     fetched.media.len()
                 );
                 return Ok(Some(fetched));
             }
-            Ok(None) => return Ok(None),
-            Err(e @ (FetchError::Http(_) | FetchError::Transient(_) | FetchError::Pixiv(_))) => {
-                if attempt < 2 {
+            Err(err) => {
+                if site.is_retryable(&err) && attempt + 1 < attempts {
                     tokio::time::sleep(Duration::from_secs(1 << attempt)).await;
                 } else {
-                    return Err(e);
+                    return Err(err);
                 }
             }
-            Err(other) => return Err(other),
         }
     }
     unreachable!("retry loop always returns")
 }
 
-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?));
+/// Applies every site's media-header rule to a download request (pixiv's
+/// `Referer` for pximg.net hotlink protection). Sites contribute via their
+/// `media_headers(url)` — the central download code carries no per-site logic.
+fn apply_media_headers(mut request: reqwest::RequestBuilder, url: &str) -> reqwest::RequestBuilder {
+    for site in SITES.iter() {
+        if let Some(headers) = site.media_headers(url) {
+            for (name, value) in headers {
+                request = request.header(name, value);
+            }
+        }
     }
-    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)
+    request
 }
 
 /// 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.
+/// the file itself and uploads it via multipart. Site-appropriate headers
+/// come from each site's `media_headers` (pixiv image hosts need `Referer`).
 /// 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?.error_for_status()?;
+    let response = apply_media_headers(CLIENT.get(url), url)
+        .send()
+        .await?
+        .error_for_status()?;
     Ok(response.content_length())
 }
 
@@ -363,12 +458,10 @@ pub async fn media_size(url: &str) -> Result<Option<u64>, FetchError> {
 /// crossed (or when a declared Content-Length already exceeds it). Keeps the
 /// bot from buffering arbitrarily large bodies into memory.
 pub async fn download_media_limited(url: &str, max_bytes: u64) -> 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?.error_for_status()?;
+    let response = apply_media_headers(CLIENT.get(url), url)
+        .send()
+        .await?
+        .error_for_status()?;
     if let Some(len) = response.content_length()
         && len > max_bytes
     {
@@ -401,12 +494,10 @@ pub async fn download_media_to_file(
     out: &mut std::fs::File,
 ) -> Result<u64, FetchError> {
     use std::io::Write;
-    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?.error_for_status()?;
+    let response = apply_media_headers(CLIENT.get(url), url)
+        .send()
+        .await?
+        .error_for_status()?;
     if let Some(len) = response.content_length()
         && len > max_bytes
     {
@@ -453,6 +544,43 @@ mod tests {
         assert_eq!(cache_key("https://example.com/not-a-post"), None);
     }
 
+    #[test]
+    fn site_id_from_key_parses_prefix() {
+        assert_eq!(site_id_from_key("twitter:123"), "twitter");
+        assert_eq!(site_id_from_key("pixiv:123"), "pixiv");
+        assert_eq!(site_id_from_key("bsky:handle.example/3lorem"), "bsky");
+        assert_eq!(site_id_from_key("unknown:1"), "unknown");
+        assert_eq!(site_id_from_key("no-colon"), "unknown");
+    }
+
+    #[test]
+    fn registry_lists_all_sites_in_dispatch_order() {
+        assert_eq!(site_ids(), vec!["twitter", "bsky", "misskey", "pixiv"]);
+        // Enabled sites dispatch; unsupported URLs never match.
+        assert!(find_site("https://x.com/u/status/1").is_some());
+        assert!(find_site("https://misskey.io/notes/abc").is_some());
+        assert!(find_site("https://example.com/x").is_none());
+        // Cache keys are pattern-driven, independent of the enabled() gate
+        // (pixiv is disabled in tests without PIXIV_REFRESH_TOKEN).
+        assert_eq!(
+            cache_key("https://www.pixiv.net/artworks/1"),
+            Some("pixiv:1".into())
+        );
+    }
+
+    #[test]
+    fn site_error_variant_displays_and_sources() {
+        use std::error::Error as _;
+        let err = FetchError::Site {
+            site: "example",
+            error: Box::new(std::io::Error::other("boom")),
+        };
+        assert_eq!(err.to_string(), "example error: boom");
+        assert!(err.source().is_some());
+        // Permanent by default: no site's is_retryable matches it.
+        assert!(!twitter::is_retryable(&err));
+    }
+
     #[test]
     fn caption_from_fields_substitutes_and_escapes() {
         // The format string is escaped, the field values are substituted

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

@@ -8,11 +8,11 @@ use super::model::{IllustrationModel, TypeModel, UgoiraMetadataModel};
 use crate::media::Media;
 use crate::site::FetchError;
 use std::env;
-use std::fmt;
 use std::io::Read;
 use std::sync::LazyLock;
 use std::sync::atomic::{AtomicBool, Ordering};
 use std::time::{Duration, SystemTime};
+use thiserror::Error;
 
 const AUTH_TOKEN_URL: &str = "https://oauth.secure.pixiv.net/auth/token";
 const APP_API_URL: &str = "https://app-api.pixiv.net";
@@ -23,48 +23,24 @@ 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)]
+#[derive(Debug, Error)]
 pub enum PixivError {
     /// No refresh token available (PIXIV_REFRESH_TOKEN unset).
+    #[error("pixiv: no authentication")]
     NoAuth,
-    Http(reqwest::Error),
-    Json(serde_json::Error),
+    #[error("pixiv http error: {0}")]
+    Http(#[from] reqwest::Error),
+    #[error("pixiv json error: {0}")]
+    Json(#[from] serde_json::Error),
+    /// Non-2xx HTTP status from the app API. The code lets [`crate::site::fetch`]
+    /// retry only transient classes (429 / 5xx) instead of burning attempts on
+    /// permanent 4xx (bad token, forbidden, not found).
+    #[error("pixiv status {0}")]
+    Status(u16),
+    #[error("pixiv api error: {0}")]
     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,
@@ -137,7 +113,7 @@ impl PixivAPI {
             .send()
             .await?;
         if !response.status().is_success() {
-            return Err(PixivError::Api(format!("status {}", response.status())));
+            return Err(PixivError::Status(response.status().as_u16()));
         }
         let json: serde_json::Value = serde_json::from_str(&response.text().await?)?;
         if json.get("error").is_some() {
@@ -190,7 +166,7 @@ impl PixivAPI {
             .send()
             .await?;
         if !response.status().is_success() {
-            return Err(PixivError::Api(format!("status {}", response.status())));
+            return Err(PixivError::Status(response.status().as_u16()));
         }
         let json: serde_json::Value = serde_json::from_str(&response.text().await?)?;
         if json.get("error").is_some() {

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

@@ -1,6 +1,6 @@
 use super::model::{IllustrationModel, TypeModel};
 use crate::media::Media;
-use crate::site::{FetchError, Fetched};
+use crate::site::{FetchError, Fetched, PixivError, Site, SiteFuture};
 use html_escape::{encode_double_quoted_attribute, encode_text};
 use regex::Regex;
 use std::sync::LazyLock;
@@ -13,6 +13,53 @@ pub fn enabled() -> bool {
     super::api::enabled()
 }
 
+/// Registry entry for the pixiv adapter (see [`crate::site::Site`]).
+pub struct PixivSite;
+
+impl Site for PixivSite {
+    fn id(&self) -> &'static str {
+        "pixiv"
+    }
+
+    fn pattern(&self) -> &'static Regex {
+        &PATTERN
+    }
+
+    fn enabled(&self) -> bool {
+        enabled()
+    }
+
+    fn cache_key(&self, url: &str) -> Option<String> {
+        cache_key(url)
+    }
+
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched> {
+        Box::pin(async move { fetch_from_url(url).await })
+    }
+
+    fn is_retryable(&self, err: &FetchError) -> bool {
+        is_retryable(err)
+    }
+
+    fn media_headers(&self, url: &str) -> Option<Vec<(&'static str, String)>> {
+        media_headers(url)
+    }
+
+    fn validate(&self) -> SiteFuture<'static, (), String> {
+        Box::pin(async {
+            match super::api::validate().await {
+                Ok(()) => Ok(()),
+                Err(e) => {
+                    // Keep the old behavior: a failed login disables pixiv
+                    // for the rest of this process.
+                    super::api::disable();
+                    Err(format!("{e}"))
+                }
+            }
+        })
+    }
+}
+
 pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
     let id = PATTERN
         .captures(url)
@@ -23,6 +70,43 @@ pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
     Ok(super::api::fetch(id).await?.into())
 }
 
+/// Cache key for a pixiv URL: `"pixiv:<id>"`. The prefix is the site id used
+/// for caption-format lookup and link-cache keys.
+pub fn cache_key(url: &str) -> Option<String> {
+    PATTERN
+        .captures(url)
+        .map(|caps| format!("pixiv:{}", &caps[1]))
+}
+
+/// Pixiv's fetch-retry policy: transient classes only — network errors and
+/// HTTP 429/5xx. Permanent 4xx (bad/expired token, forbidden, not found),
+/// API/auth errors, unparseable bodies and missing auth are not retried.
+pub fn is_retryable(err: &FetchError) -> bool {
+    match err {
+        FetchError::Http(_) | FetchError::Transient(_) => true,
+        FetchError::Pixiv(e) => match e {
+            PixivError::Http(_) => true,
+            PixivError::Status(code) if *code == 429 || *code >= 500 => true,
+            PixivError::Status(_)
+            | PixivError::Api(_)
+            | PixivError::Json(_)
+            | PixivError::NoAuth => false,
+        },
+        _ => false,
+    }
+}
+
+/// pximg.net is hotlink-protected: downloads must carry the pixiv Referer.
+/// The match is on the media host, not the site PATTERN — pixiv's PATTERN
+/// only matches `pixiv.net/artworks/...`, never `i.pximg.net`.
+pub fn media_headers(url: &str) -> Option<Vec<(&'static str, String)>> {
+    if url.to_ascii_lowercase().contains("pximg.net") {
+        Some(vec![("Referer", "https://www.pixiv.net/".to_string())])
+    } else {
+        None
+    }
+}
+
 #[derive(Debug)]
 pub struct Illustration {
     id: String,
@@ -142,6 +226,7 @@ impl From<Illustration> for Fetched {
             title: illustration.title.clone(),
             media: illustration.media,
             sensitive: illustration.nsfw,
+            site_id: "pixiv",
             render_data,
             _keep_alive: illustration._keep_alive,
         }
@@ -232,6 +317,43 @@ mod tests {
         }
     }
 
+    #[test]
+    fn is_retryable_classifies_transient_and_permanent() {
+        // Transient: network errors, explicit transient, pixiv 429/5xx.
+        assert!(is_retryable(&FetchError::Transient("429".into())));
+        assert!(is_retryable(&FetchError::Pixiv(PixivError::Status(429))));
+        assert!(is_retryable(&FetchError::Pixiv(PixivError::Status(500))));
+        assert!(is_retryable(&FetchError::Pixiv(PixivError::Status(503))));
+        // Permanent: pixiv 4xx (bad/expired token, forbidden, not found),
+        // api/auth errors, unparseable bodies, not-found/blocked/sensitive.
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Status(400))));
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Status(401))));
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Status(403))));
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Status(404))));
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Api(
+            "invalid_grant".into()
+        ))));
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::NoAuth)));
+        let json_err = serde_json::from_str::<serde_json::Value>("x").unwrap_err();
+        assert!(!is_retryable(&FetchError::Pixiv(PixivError::Json(
+            json_err
+        ))));
+        assert!(!is_retryable(&FetchError::NotFound));
+        assert!(!is_retryable(&FetchError::Blocked));
+        assert!(!is_retryable(&FetchError::Sensitive));
+        assert!(!is_retryable(&FetchError::TooLarge));
+    }
+
+    #[test]
+    fn media_headers_adds_referer_only_for_pximg() {
+        assert_eq!(
+            media_headers("https://i.pximg.net/img-original/img/1.png"),
+            Some(vec![("Referer", "https://www.pixiv.net/".to_string())])
+        );
+        assert_eq!(media_headers("https://www.pixiv.net/artworks/1"), None);
+        assert_eq!(media_headers("https://x.com/u/status/1"), None);
+    }
+
     #[test]
     fn ugoira_yields_empty_media() {
         let v = illust_json(

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

@@ -3,4 +3,7 @@ mod interface;
 mod model;
 
 pub use api::{PixivAPI, PixivError, disable, fetch, validate};
-pub use interface::{Illustration, PATTERN, enabled, fetch_from_url};
+pub use interface::{
+    Illustration, PATTERN, PixivSite, cache_key, enabled, fetch_from_url, is_retryable,
+    media_headers,
+};

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

@@ -1,10 +1,31 @@
 use super::model;
 use crate::media::Media;
-use crate::site::{FetchError, Fetched};
-use html_escape::{encode_double_quoted_attribute, encode_text};
+use crate::site::{FetchError, Fetched, Site, SiteFuture};
+use html_escape::{decode_html_entities, encode_double_quoted_attribute, encode_text};
 use regex::Regex;
 use std::sync::LazyLock;
 
+/// Registry entry for the twitter adapter (see [`crate::site::Site`]).
+pub struct TwitterSite;
+
+impl Site for TwitterSite {
+    fn id(&self) -> &'static str {
+        "twitter"
+    }
+
+    fn pattern(&self) -> &'static Regex {
+        &PATTERN
+    }
+
+    fn cache_key(&self, url: &str) -> Option<String> {
+        cache_key(url)
+    }
+
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched> {
+        Box::pin(async move { fetch_from_url(url).await })
+    }
+}
+
 pub static PATTERN: LazyLock<Regex> = LazyLock::new(|| {
     Regex::new(r"^(?:https?://)?(?:www\.|mobile\.)?(?:x|twitter|fixvx|vxtwitter|fixupx|fxtwitter)\.com/[^.]+/status/(\d+)").unwrap()
 });
@@ -29,13 +50,19 @@ pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
             if super::auth::enabled() {
                 match super::auth::fetch(id).await {
                     Ok(tweet) => Ok(tweet.into()),
+                    // The tweet is genuinely gone (deleted / suspended /
+                    // tombstoned): report it instead of degrading to an
+                    // empty result ("No media found"). Only unexpected
+                    // fallback failures (network, parse) keep the NSFW
+                    // placeholder.
+                    Err(FetchError::NotFound) => Err(FetchError::NotFound),
                     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");
+                log::debug!("tweet {id} is sensitive; set TWITTER_AUTH_TOKEN to fetch NSFW media");
                 Ok(empty_fetched(url))
             }
         }
@@ -43,6 +70,26 @@ pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
     }
 }
 
+/// Cache key for a twitter URL: `"twitter:<id>"`. The prefix is the site id
+/// used for caption-format lookup and link-cache keys.
+pub fn cache_key(url: &str) -> Option<String> {
+    PATTERN
+        .captures(url)
+        .map(|caps| format!("twitter:{}", &caps[1]))
+}
+
+/// Twitter's fetch-retry policy: transient classes only. Not-found, blocked,
+/// sensitive (NSFW withholding) and parse failures are permanent — retrying
+/// them only wastes attempts against the syndication endpoint.
+pub fn is_retryable(err: &FetchError) -> bool {
+    matches!(err, FetchError::Http(_) | FetchError::Transient(_))
+}
+
+/// twimg URLs need no extra headers (no hotlink protection).
+pub fn media_headers(_url: &str) -> Option<Vec<(&'static str, String)>> {
+    None
+}
+
 /// 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 {
@@ -54,13 +101,15 @@ fn empty_fetched(url: &str) -> Fetched {
         title: String::new(),
         media: vec![],
         sensitive: true,
+        site_id: "twitter",
         render_data: None,
         _keep_alive: None,
     }
 }
 
 /// Fetches a tweet from the syndication endpoint. Deleted/blocked tweets
-/// surface as `FetchError::NotFound`.
+/// surface as `FetchError::NotFound`; withheld content (empty tombstone,
+/// age-restricted) as `FetchError::Sensitive`.
 pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
     let id_num = id.parse::<u64>().map_err(|_| FetchError::NotFound)?;
     let response = crate::site::CLIENT
@@ -79,23 +128,46 @@ pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
         };
     }
     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)
-    {
+    // Classify before parsing the tweet (see [`parse_syndication_body`]).
+    parse_syndication_body(&text)?;
+    Tweet::from_syndication_json(&text).map_err(FetchError::Json)
+}
+
+/// Parses and classifies a syndication response body. `Ok` means the body is
+/// a real tweet payload; `Err` carries the permanent error class:
+/// - `NotFound`: an `errors` array (deleted/blocked) or a `TweetTombstone`
+///   **with a reason** — "This Post was deleted by the Post author." /
+///   "This Post is from a suspended account." (the tweet is gone).
+/// - `Sensitive`: content withheld **without a deletion reason** — the empty
+///   `{}` shape or an *empty* `TweetTombstone` (`{"__typename":
+///   "TweetTombstone","tombstone":{}}`). Live tweets in restricted contexts
+///   surface this way; treating them as deleted is a regression (a normal
+///   tweet must not report "deleted"). Age-restricted tombstones route here
+///   too so the logged-in GraphQL fallback can fetch the real tweet.
+/// - `Json`: an unparseable body.
+fn parse_syndication_body(text: &str) -> Result<serde_json::Value, FetchError> {
+    let body: serde_json::Value = serde_json::from_str(text)?;
+    if body.get("errors").is_some() {
         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)
-    {
+    if let Some(tombstone) = body.get("tombstone") {
+        // Only a tombstone with an explicit reason means the tweet is gone;
+        // a missing reason (empty `tombstone: {}`) or an age-restricted
+        // reason means the tweet exists but is withheld.
+        let reason = tombstone
+            .get("text")
+            .and_then(|t| t.get("text"))
+            .and_then(|t| t.as_str())
+            .unwrap_or("");
+        if reason.is_empty() || reason.to_ascii_lowercase().contains("age-restricted") {
+            return Err(FetchError::Sensitive);
+        }
+        return Err(FetchError::NotFound);
+    }
+    if body.get("id_str").is_none() {
         return Err(FetchError::Sensitive);
     }
-    Tweet::from_syndication_json(&text).map_err(FetchError::Json)
+    Ok(body)
 }
 
 /// The syndication token: JS `((id / 1e15) * PI).toString(36)` (the
@@ -167,9 +239,17 @@ impl Tweet {
         // strip the appended media short link, mirroring FxEmbed's linkFixer
         // (no display_text_range arithmetic — see expand_links).
         let text = expand_links(&json.text, &json.entities.urls);
+        // Twitter APIs (syndication AND GraphQL full_text) return the text
+        // pre-escaped for HTML (`&gt;` `&lt;` `&amp;` `&#39;` …): decode it so
+        // the stored text is raw. The caption's own escaping then produces
+        // the rendered form exactly once — without this, `&gt;^ω^&lt;` would
+        // be double-escaped to `&amp;gt;^ω^&amp;lt;` and the sent message
+        // would show literal `&gt;^ω^&lt;`.
+        let text = decode_html_entities(&text).into_owned();
         // `name` is the display name, `screen_name` the handle (Python's
         // vxtwitter mapping: author = display name, author_id = handle).
-        let author = json.user.name;
+        // Display names can carry the same pre-escaped entities.
+        let author = decode_html_entities(&json.user.name).into_owned();
         let author_id = json.user.screen_name;
         let mut media = vec![];
         for item in json.media_details {
@@ -285,6 +365,7 @@ impl From<Tweet> for Fetched {
             title: tweet.text.clone(),
             media: tweet.media,
             sensitive: tweet.sensitive,
+            site_id: "twitter",
             render_data,
             _keep_alive: None,
         }
@@ -336,6 +417,64 @@ mod tests {
         }
     }
 
+    #[test]
+    fn syndication_text_is_unescaped_before_storing() {
+        // Real API shape: the text arrives pre-escaped for HTML — e.g. the
+        // tweet `>^ω^<` comes back as `&gt;^ω^&lt;` (fxtwitter's raw_text for
+        // 2060196388252827954) and apostrophes as `&#39;`. Storing it raw and
+        // escaping once at caption build avoids the double-escape that would
+        // show literal `&gt;`/`&lt;`/`&amp;` in the sent message.
+        let raw = serde_json::json!({
+            "__typename": "Tweet",
+            "id_str": "1",
+            "text": "&gt;^ω^&lt; &amp; more &#39;quoted&#39; https://t.co/abc123",
+            "user": { "name": "O&#39;Brien", "screen_name": "h" },
+            "entities": { "urls": [] },
+            "mediaDetails": []
+        });
+        let tweet = Tweet::from_syndication_json(&raw.to_string()).unwrap();
+        // The appended media short link is stripped, then entities decoded.
+        assert_eq!(tweet.text, ">^ω^< & more 'quoted'");
+        assert_eq!(tweet.author, "O'Brien");
+        let fetched: Fetched = tweet.into();
+        assert_eq!(fetched.title, ">^ω^< & more 'quoted'");
+        // The caption escapes the raw text exactly once (encode_text covers
+        // & < >; apostrophes stay literal — they are harmless in text).
+        assert!(
+            fetched.caption.contains("&gt;^ω^&lt; &amp; more 'quoted'"),
+            "caption: {}",
+            fetched.caption
+        );
+        assert!(
+            !fetched.caption.contains("&amp;gt;"),
+            "double-escaped text: {}",
+            fetched.caption
+        );
+    }
+
+    #[test]
+    fn cache_key_prefixes_tweet_id() {
+        assert_eq!(
+            cache_key("https://x.com/user/status/1234567890"),
+            Some("twitter:1234567890".into())
+        );
+        assert_eq!(cache_key("https://example.com/1"), None);
+    }
+
+    #[test]
+    fn is_retryable_classifies_transient_and_permanent() {
+        // Transient: network errors and explicit transient statuses (the
+        // `Http` arm shares this match arm with `Transient`).
+        assert!(is_retryable(&FetchError::Transient("429".into())));
+        // Permanent: gone, blocked, withheld, oversized, unparseable.
+        assert!(!is_retryable(&FetchError::NotFound));
+        assert!(!is_retryable(&FetchError::Blocked));
+        assert!(!is_retryable(&FetchError::Sensitive));
+        assert!(!is_retryable(&FetchError::TooLarge));
+        let json_err = serde_json::from_str::<serde_json::Value>("x").unwrap_err();
+        assert!(!is_retryable(&FetchError::Json(json_err)));
+    }
+
     #[test]
     fn syndication_json_converts_to_fetched() {
         let raw = fixture(serde_json::json!([
@@ -572,6 +711,77 @@ mod tests {
         assert!(token.starts_with("236.v"), "got {token}");
     }
 
+    #[test]
+    fn syndication_tombstone_maps_to_not_found() {
+        // Deleted tweets answer HTTP 200 with a TweetTombstone carrying a
+        // reason (no `errors`, no `id_str`); they must not fall through to
+        // Sensitive, which would make the bot reply "No media found" for a
+        // deleted tweet.
+        let raw = serde_json::json!({
+            "__typename": "TweetTombstone",
+            "tombstone": {
+                "text": { "rtl": false, "text": "This Post was deleted by the Post author. Learn more" }
+            }
+        });
+        assert!(matches!(
+            parse_syndication_body(&raw.to_string()),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn syndication_empty_tombstone_maps_to_sensitive() {
+        // Regression: live tweets in restricted contexts answer with an
+        // EMPTY tombstone (`{"__typename":"TweetTombstone","tombstone":{}}`)
+        // — no deletion reason. They must not be reported as deleted.
+        let raw = serde_json::json!({ "__typename": "TweetTombstone", "tombstone": {} });
+        assert!(matches!(
+            parse_syndication_body(&raw.to_string()),
+            Err(FetchError::Sensitive)
+        ));
+    }
+
+    #[test]
+    fn syndication_age_restricted_tombstone_maps_to_sensitive() {
+        // An age-restricted tombstone withholds a live tweet; route it to
+        // the logged-in fallback instead of reporting it as gone.
+        let raw = serde_json::json!({
+            "__typename": "TweetTombstone",
+            "tombstone": {
+                "text": { "rtl": false, "text": "Age-restricted adult content" }
+            }
+        });
+        assert!(matches!(
+            parse_syndication_body(&raw.to_string()),
+            Err(FetchError::Sensitive)
+        ));
+    }
+
+    #[test]
+    fn syndication_errors_maps_to_not_found() {
+        // The classic gone shape: {"errors": [...]}.
+        let raw = serde_json::json!({ "errors": [{ "message": "Couldn't find Tweet" }] });
+        assert!(matches!(
+            parse_syndication_body(&raw.to_string()),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn syndication_empty_object_maps_to_sensitive() {
+        // NSFW / age-restricted withholding: an empty `{}`.
+        assert!(matches!(
+            parse_syndication_body("{}"),
+            Err(FetchError::Sensitive)
+        ));
+    }
+
+    #[test]
+    fn syndication_tweet_body_passes() {
+        let raw = fixture(serde_json::json!([]));
+        assert!(parse_syndication_body(&raw.to_string()).is_ok());
+    }
+
     #[tokio::test]
     #[ignore = "live network: requires outbound HTTPS to cdn.syndication.twimg.com"]
     async fn live_fetch_with_photos() {
@@ -596,4 +806,30 @@ mod tests {
             "got {result:?}"
         );
     }
+
+    #[tokio::test]
+    #[ignore = "live network: requires outbound HTTPS to cdn.syndication.twimg.com"]
+    async fn live_fetch_tombstone_deleted_tweet_is_not_found() {
+        // Regression: a real deleted tweet answering with a TweetTombstone
+        // (HTTP 200, no errors/id_str) used to surface as Sensitive and
+        // degrade to an empty result ("No media found").
+        let result = fetch("2085948045967986859").await;
+        assert!(
+            matches!(result, Err(FetchError::NotFound)),
+            "got {result:?}"
+        );
+    }
+
+    #[tokio::test]
+    #[ignore = "live network: requires outbound HTTPS to cdn.syndication.twimg.com"]
+    async fn live_fetch_empty_tombstone_is_sensitive() {
+        // Regression: a LIVE tweet (verified via a third-party API) answers
+        // syndication with an empty TweetTombstone; it must surface as
+        // Sensitive (withheld), never as NotFound (deleted).
+        let result = fetch("2087851366253555752").await;
+        assert!(
+            matches!(result, Err(FetchError::Sensitive)),
+            "got {result:?}"
+        );
+    }
 }

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

@@ -2,4 +2,6 @@ mod auth;
 mod interface;
 mod model;
 
-pub use interface::{PATTERN, Tweet, enabled, fetch_from_url};
+pub use interface::{
+    PATTERN, Tweet, TwitterSite, cache_key, enabled, fetch_from_url, is_retryable, media_headers,
+};

crates/xmedia-bot/Cargo.toml

@@ -1,11 +1,11 @@
 [package]
 name = "xmedia-bot"
-version = "1.2.0"
+version = "1.6.0"
 edition = "2024"
 
 [dependencies]
 teloxide = { version = "0.17", default-features = false, features = ["webhooks-axum", "macros", "rustls", "ctrlc_handler"] }
-tokio = { version = "1.40", features = ["rt-multi-thread", "macros"] }
+tokio = { version = "1.40", features = ["rt-multi-thread", "macros", "time", "sync"] }
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 log = "0.4"
@@ -23,3 +23,6 @@ zune-jpeg = "0.5"
 fast_image_resize = "6"
 jpeg-encoder = "0.7"
 x-media = { path = "../x-media" }
+
+[dev-dependencies]
+tokio = { version = "1.40", features = ["test-util"] }

crates/xmedia-bot/src/ctx.rs

@@ -0,0 +1,118 @@
+//! Runtime context: the collaborators a handler needs, injected as one struct
+//! so tests can substitute a scripted sender and tempdir-backed stores.
+//!
+//! The production context is assembled from the process-wide statics
+//! ([`AppContext::from_statics`]); the spawned worker closures hold
+//! [`CONTEXT`], which is `'static` for that reason.
+
+use crate::config::Config;
+use crate::handlers::{CHAT_STORE, CONFIG, LINK_CACHE, TASK_QUEUE};
+use crate::link_cache::LinkCache;
+use crate::media_sender::MediaSender;
+use crate::queue::PersistentTaskQueue;
+use crate::send::BOT;
+use crate::state::ChatStore;
+use std::sync::LazyLock;
+
+pub struct AppContext<'a> {
+    pub sender: &'a dyn MediaSender,
+    pub chat_store: &'a ChatStore,
+    pub task_queue: &'a PersistentTaskQueue,
+    pub link_cache: &'a LinkCache,
+    pub config: &'a Config,
+}
+
+impl<'a> AppContext<'a> {
+    /// The stores are the process-wide statics; `sender` is whatever the caller
+    /// was handed (the dispatcher's `Bot` clone for update handlers, the shared
+    /// queue `Bot` for the worker loops). Update handlers build their own
+    /// context from the `Bot` they received so the same code path works with an
+    /// injected mock in tests.
+    pub fn from_statics(sender: &'a dyn MediaSender) -> AppContext<'a> {
+        AppContext {
+            sender,
+            chat_store: &CHAT_STORE,
+            task_queue: &TASK_QUEUE,
+            link_cache: &LINK_CACHE,
+            config: &CONFIG,
+        }
+    }
+}
+
+/// The URL/queue workers' context: `'static` because `tokio::spawn`ed closures
+/// and the queue's handler type require it.
+pub static CONTEXT: LazyLock<AppContext<'static>> =
+    LazyLock::new(|| AppContext::from_statics(&*BOT));
+
+/// Test support: a tempdir-backed set of stores plus the context borrowing
+/// them, so a handler test needs one line of setup.
+#[cfg(test)]
+pub(crate) mod test_support {
+    use super::*;
+    use std::sync::Arc;
+
+    pub(crate) struct TestStores {
+        _dir: tempfile::TempDir,
+        pool: Arc<crate::db::DbPool>,
+        chat_store: ChatStore,
+        task_queue: PersistentTaskQueue,
+        link_cache: LinkCache,
+        config: Config,
+    }
+
+    impl TestStores {
+        pub(crate) fn new() -> Self {
+            let dir = tempfile::tempdir().unwrap();
+            let pool = crate::db::open_store(dir.path().join("ctx.db").to_str().unwrap()).unwrap();
+            TestStores {
+                _dir: dir,
+                chat_store: ChatStore::new(Arc::clone(&pool)),
+                task_queue: PersistentTaskQueue::new(Arc::clone(&pool)),
+                link_cache: LinkCache::new(Arc::clone(&pool)),
+                config: Config::load(),
+                pool,
+            }
+        }
+
+        pub(crate) fn ctx<'a>(&'a self, sender: &'a dyn MediaSender) -> AppContext<'a> {
+            AppContext {
+                sender,
+                chat_store: &self.chat_store,
+                task_queue: &self.task_queue,
+                link_cache: &self.link_cache,
+                config: &self.config,
+            }
+        }
+
+        pub(crate) fn chat_store(&self) -> &ChatStore {
+            &self.chat_store
+        }
+
+        pub(crate) fn link_cache(&self) -> &LinkCache {
+            &self.link_cache
+        }
+
+        /// Rows persisted in the task queue: what "queued for retry" looks like
+        /// from the outside.
+        pub(crate) async fn queued_tasks(&self) -> i64 {
+            let pool = Arc::clone(&self.pool);
+            pool.with_conn(|conn| {
+                conn.query_row("SELECT COUNT(*) FROM tasks", [], |row| row.get(0))
+            })
+            .await
+            .unwrap()
+        }
+
+        /// The single queued task payload, for asserting what was rescheduled.
+        pub(crate) async fn queued_payload(&self) -> serde_json::Value {
+            let pool = Arc::clone(&self.pool);
+            let payload: String = pool
+                .with_conn(|conn| {
+                    conn.query_row("SELECT payload FROM tasks LIMIT 1", [], |row| row.get(0))
+                })
+                .await
+                .unwrap();
+            serde_json::from_str(&payload).unwrap()
+        }
+    }
+}

crates/xmedia-bot/src/db.rs

@@ -113,6 +113,45 @@ pub fn open_db(path: &str) -> rusqlite::Result<Connection> {
     Ok(conn)
 }
 
+/// Opens the shared DB file, runs the merged schema for all three tables and
+/// returns a pool for it. One call per process in production (the stores
+/// share the returned pool); tests call it per tempdir.
+pub fn open_store(path: &str) -> rusqlite::Result<Arc<DbPool>> {
+    if let Some(parent) = std::path::Path::new(path).parent()
+        && !parent.as_os_str().is_empty()
+    {
+        std::fs::create_dir_all(parent).map_err(rusqlite_error)?;
+    }
+    let conn = open_db(path)?;
+    schema_init(&conn)?;
+    Ok(Arc::new(DbPool::new(path)))
+}
+
+fn rusqlite_error(e: std::io::Error) -> rusqlite::Error {
+    rusqlite::Error::ToSqlConversionFailure(Box::new(e))
+}
+
+/// Creates the `tasks`, `chat_state` and `link_cache` tables (idempotent).
+/// The three stores used to own their own schema; keeping it in one place
+/// means one initialization for the whole database file.
+///
+/// ⚠️ Schema-change reminder (deferred, see `docs/architecture-refactor.md`
+/// §5): this is a plain `CREATE TABLE IF NOT EXISTS` with no versioning.
+/// Before any column/table change that must migrate existing databases, land
+/// the `PRAGMA user_version` migration chain first (`MIGRATIONS: &[&str]` +
+/// `migrate(conn)`), then restructure this function.
+pub fn schema_init(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); \
+         CREATE INDEX IF NOT EXISTS idx_tasks_pending ON tasks(status, run_after); \
+         CREATE TABLE IF NOT EXISTS chat_state (chat_id TEXT PRIMARY KEY, payload TEXT NOT NULL); \
+         CREATE TABLE IF NOT EXISTS link_cache (url TEXT PRIMARY KEY, payload TEXT NOT NULL, \
+         created_at REAL NOT NULL);",
+    )
+}
+
 /// Unix timestamp in fractional seconds. Shared by the queue, chat store and
 /// link cache (previously four private copies).
 pub fn now_f64() -> f64 {
@@ -121,3 +160,9 @@ pub fn now_f64() -> f64 {
         .map(|d| d.as_secs_f64())
         .unwrap_or(0.0)
 }
+
+/// Unix timestamp in whole seconds. Same clock as [`now_f64`], for fields
+/// that store integer seconds (chat-state expiry, edit prompts).
+pub fn unix_now() -> i64 {
+    now_f64() as i64
+}

crates/xmedia-bot/src/handlers/callback.rs

@@ -0,0 +1,321 @@
+//! Callback query handling: the edit-before-forward prompt's `"forward"` and
+//! `"template|<name>"` buttons.
+//!
+//! [`callback_query_handler`] is the dptree entry; it only pulls the plain
+//! values out of the teloxide update and hands them to [`handle_callback`],
+//! which holds the button logic and is driven directly by tests.
+
+use crate::ctx::AppContext;
+use crate::db::unix_now;
+use crate::send::{self, Task};
+use teloxide::RequestError;
+use teloxide::prelude::*;
+use teloxide::types::{CallbackQuery, CallbackQueryId, MessageId};
+
+/// The `"forward"` button's data.
+const FORWARD: &str = "forward";
+/// Prefix of a template button's data: `"template|<name>"`.
+const TEMPLATE_PREFIX: &str = "template|";
+
+pub async fn callback_query_handler(bot: Bot, query: CallbackQuery) -> Result<(), RequestError> {
+    let Some(message) = &query.message else {
+        return respond(());
+    };
+    let Some(data) = query.data.clone() else {
+        return respond(());
+    };
+    let ctx = AppContext::from_statics(&bot);
+    handle_callback(
+        &ctx,
+        query.id.clone(),
+        message.chat().id.0,
+        message.id().0 as i64,
+        &data,
+    )
+    .await;
+    respond(())
+}
+
+/// Handles one button press on the edit-before-forward prompt.
+async fn handle_callback(
+    ctx: &AppContext<'_>,
+    callback_query_id: CallbackQueryId,
+    chat_id: i64,
+    prompt_message_id: i64,
+    data: &str,
+) {
+    let ttl_secs = ctx.config.edit_message_ttl.as_secs() as i64;
+    let chat_data = ctx.chat_store.get(chat_id).await;
+    let edit = chat_data.edit_message.get(&prompt_message_id).cloned();
+    let Some(edit) = edit else {
+        log::debug!("callback from {chat_id}: no edit record for prompt {prompt_message_id}");
+        let _ = ctx
+            .sender
+            .answer_callback_query(callback_query_id, Some("Expired".to_string()))
+            .await;
+        return;
+    };
+    // Lazy expiry: a stale record (past the TTL, not yet swept) is dropped.
+    if edit.created_at + ttl_secs <= unix_now() {
+        ctx.chat_store
+            .update(chat_id, |data| {
+                data.edit_message.remove(&prompt_message_id);
+            })
+            .await;
+        let _ = ctx
+            .sender
+            .answer_callback_query(callback_query_id, Some("Expired".to_string()))
+            .await;
+        return;
+    }
+
+    log::info!("callback from {chat_id} on prompt {prompt_message_id}: {data}");
+    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),
+                };
+                let (answer, settled) = match send::forward_messages(ctx, &forward_task).await {
+                    Ok(()) => {
+                        log::info!(
+                            "forwarded {} message(s) to channel {channel_id}",
+                            edit.forward_message_ids.len()
+                        );
+                        ("✅ Forwarded".to_string(), true)
+                    }
+                    Err(send::SendError::Retryable {
+                        delay_seconds,
+                        task,
+                    }) => {
+                        log::info!("forward queued for retry in {delay_seconds:.1}s");
+                        send::enqueue_retry(ctx.task_queue, *task, delay_seconds).await;
+                        ("Forward queued for retry.".to_string(), false)
+                    }
+                    Err(send::SendError::Permanent { message, .. }) => {
+                        log::error!("forward failed permanently: {message}");
+                        (format!("Forward failed: {message}"), false)
+                    }
+                };
+                if settled {
+                    // The prompt is done: drop it and its record.
+                    let _ = ctx
+                        .sender
+                        .delete_message(ChatId(chat_id), MessageId(prompt_message_id as i32))
+                        .await;
+                    ctx.chat_store
+                        .update(chat_id, |data| {
+                            data.edit_message.remove(&prompt_message_id);
+                        })
+                        .await;
+                }
+                let _ = ctx
+                    .sender
+                    .answer_callback_query(callback_query_id, Some(answer))
+                    .await;
+            }
+            None => {
+                log::debug!("forward callback without a forward channel set");
+                let _ = ctx
+                    .sender
+                    .answer_callback_query(
+                        callback_query_id,
+                        Some("No forward channel set.".to_string()),
+                    )
+                    .await;
+            }
+        }
+        return;
+    }
+
+    if let Some(name) = data.strip_prefix(TEMPLATE_PREFIX) {
+        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 _ = ctx
+                .sender
+                .edit_message_caption(
+                    ChatId(chat_id),
+                    MessageId(first_forward_id as i32),
+                    template_html,
+                )
+                .await;
+            ctx.chat_store
+                .update(chat_id, |data| {
+                    if let Some(entry) = data.edit_message.get_mut(&prompt_message_id) {
+                        entry.template = name.to_string();
+                    }
+                })
+                .await;
+            log::info!("template '{name}' applied to prompt {prompt_message_id}");
+        }
+        let _ = ctx
+            .sender
+            .answer_callback_query(callback_query_id, None)
+            .await;
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::ctx::test_support::TestStores;
+    use crate::media_sender::test_support::{MockSender, Outcome};
+    use crate::state::EditMessage;
+    use teloxide::ApiError;
+
+    /// The edit-before-forward prompt's message id in these tests.
+    const PROMPT_ID: i64 = 7;
+    /// The message the prompt refers to (the one whose caption is swapped).
+    const FORWARDED_ID: i64 = 9;
+
+    fn api_error() -> RequestError {
+        RequestError::Api(ApiError::Unknown("Bad Request: chat not found".into()))
+    }
+
+    fn callback_id() -> CallbackQueryId {
+        CallbackQueryId("cb-1".to_string())
+    }
+
+    /// Seeds a live prompt record plus a forward channel and a template;
+    /// `created_at` backdates the record for the expiry cases.
+    async fn seed_prompt(ctx: &AppContext<'_>, created_at: i64) {
+        ctx.chat_store
+            .update(1, |data| {
+                data.forward_channel_id = Some(2);
+                data.template
+                    .insert("tpl".to_string(), "<b>[]</b>".to_string());
+                data.edit_message.insert(
+                    PROMPT_ID,
+                    EditMessage {
+                        url: "https://x.com/u/status/1".into(),
+                        chat_id: 1,
+                        forward_message_ids: vec![FORWARDED_ID],
+                        template: String::new(),
+                        created_at,
+                    },
+                );
+            })
+            .await;
+    }
+
+    #[tokio::test]
+    async fn template_button_swaps_the_caption_and_records_the_choice() {
+        let sender = MockSender::scripted(vec![Outcome::EditOk], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, crate::db::unix_now()).await;
+
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "template|tpl").await;
+
+        assert_eq!(
+            sender.calls(),
+            vec!["edit_message_caption", "answer_callback_query"]
+        );
+        // The raw template, including the [] the user edits into.
+        assert_eq!(sender.captions(), vec!["<b>[]</b>"]);
+        assert_eq!(sender.answers(), vec![None]);
+        let data = ctx.chat_store.get(1).await;
+        assert_eq!(data.edit_message[&PROMPT_ID].template, "tpl");
+    }
+
+    #[tokio::test]
+    async fn forward_button_copies_then_clears_the_prompt() {
+        let sender = MockSender::scripted(vec![Outcome::CopyOk], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, crate::db::unix_now()).await;
+
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+
+        assert_eq!(
+            sender.calls(),
+            vec!["copy_messages", "delete_message", "answer_callback_query"]
+        );
+        assert_eq!(sender.answers(), vec![Some("✅ Forwarded".to_string())]);
+        assert!(
+            ctx.chat_store.get(1).await.edit_message.is_empty(),
+            "a settled prompt must drop its record"
+        );
+    }
+
+    #[tokio::test]
+    async fn forward_without_a_channel_is_reported() {
+        let sender = MockSender::scripted(vec![], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, crate::db::unix_now()).await;
+        ctx.chat_store
+            .update(1, |data| data.forward_channel_id = None)
+            .await;
+
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+
+        assert_eq!(sender.calls(), vec!["answer_callback_query"]);
+        assert_eq!(
+            sender.answers(),
+            vec![Some("No forward channel set.".to_string())]
+        );
+    }
+
+    #[tokio::test]
+    async fn retryable_forward_is_queued_and_keeps_the_prompt() {
+        use teloxide::types::Seconds;
+        let sender = MockSender::scripted(vec![Outcome::CopyErr], || {
+            RequestError::RetryAfter(Seconds::from_seconds(7))
+        });
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, crate::db::unix_now()).await;
+
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+
+        assert_eq!(
+            sender.calls(),
+            vec!["copy_messages", "answer_callback_query"]
+        );
+        assert_eq!(
+            sender.answers(),
+            vec![Some("Forward queued for retry.".to_string())]
+        );
+        assert_eq!(stores.queued_tasks().await, 1);
+        // The prompt is not settled: the queued retry still needs the record.
+        assert!(
+            ctx.chat_store
+                .get(1)
+                .await
+                .edit_message
+                .contains_key(&PROMPT_ID)
+        );
+    }
+
+    #[tokio::test]
+    async fn unknown_and_expired_prompts_answer_expired() {
+        let sender = MockSender::scripted(vec![], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+
+        // No record at all.
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+        assert_eq!(sender.answers(), vec![Some("Expired".to_string())]);
+
+        // A record past its TTL (nothing swept it yet) is dropped on use.
+        let stale = crate::db::unix_now() - ctx.config.edit_message_ttl.as_secs() as i64 - 1;
+        seed_prompt(&ctx, stale).await;
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+        assert_eq!(
+            sender.answers(),
+            vec![Some("Expired".to_string()), Some("Expired".to_string())]
+        );
+        assert!(
+            ctx.chat_store.get(1).await.edit_message.is_empty(),
+            "the expired record must be dropped"
+        );
+        assert_eq!(sender.calls(), vec!["answer_callback_query"; 2]);
+    }
+}

crates/xmedia-bot/src/handlers/commands.rs

@@ -0,0 +1,647 @@
+//! Bot command parsing, the `/`-command executor and `setMyCommands`
+//! registration. URL/inline/callback flows live in their own modules.
+
+use super::urls::{PostSend, url_media};
+use super::{CHAT_STORE, CONFIG, LINK_CACHE, log_key, reply, reply_html};
+use crate::ctx::AppContext;
+use teloxide::RequestError;
+use teloxide::prelude::*;
+use teloxide::types::{ChatId, Message, Recipient};
+use teloxide::utils::command::{BotCommands, ParseError};
+
+#[derive(BotCommands, Clone)]
+#[command(
+    rename_rule = "snake_case",
+    description = "Turn X/Pixiv/Bluesky links into media messages"
+)]
+pub(crate) enum Command {
+    #[command(description = "Get started")]
+    Start,
+    #[command(description = "Show command help")]
+    Help,
+    #[command(
+        description = "Set forward channel (@channel or ID)",
+        parse_with = "split"
+    )]
+    SetForwardChannel(String),
+    #[command(description = "Remove forward channel")]
+    RemoveForwardChannel,
+    #[command(description = "Toggle edit-before-forward")]
+    EditBeforeForward,
+    #[command(
+        description = "Reply with [] to save as template",
+        parse_with = "split"
+    )]
+    SetTemplate(String),
+    #[command(description = "Show chat state (debug; admin only)")]
+    BotDict,
+    #[command(description = "Set site caption format", parse_with = "split")]
+    SetFormat(String),
+    #[command(
+        description = "Clear link cache (admin; optional URL, else all)",
+        parse_with = "split"
+    )]
+    ClearCache(String),
+    #[command(
+        description = "Send a link's media (no forwarding)",
+        parse_with = parse_arg_remainder
+    )]
+    Test(String),
+    #[command(
+        description = "Parse a link and report it (debug; nothing sent)",
+        parse_with = parse_arg_remainder
+    )]
+    Debug(String),
+}
+
+/// `/test` and `/debug` argument parser: the whole remainder after the command
+/// name, trimmed. The built-in `split` parser takes exactly one space-separated
+/// token and rejects the rest, so a URL followed by a trailing space (or
+/// pasted text) would silently fall through to the URL flow instead.
+fn parse_arg_remainder(s: String) -> Result<(String,), ParseError> {
+    Ok((s.trim().to_string(),))
+}
+
+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;
+    // The sender must be a channel administrator. Compare against the
+    // sender's user id, NOT the chat id (they only coincide in private
+    // chats, so the old check broke group usage).
+    let Some(sender) = message.from.as_ref() else {
+        return Err(SetForwardChannelError::NotAdmin);
+    };
+    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 == sender.id) {
+                return Err(SetForwardChannelError::NotAdmin);
+            }
+            // The bot itself must be an admin that can post; a missing
+            // bot entry must not pass silently (copy would fail later).
+            let bot_id = match bot.get_me().await {
+                Ok(me) => me.user.id,
+                Err(e) => return Err(SetForwardChannelError::NotBotAdmin(e)),
+            };
+            let bot_ok = admins
+                .iter()
+                .any(|admin| admin.user.id == bot_id && admin.can_post_messages());
+            if !bot_ok {
+                return Err(SetForwardChannelError::NotBotCanPost);
+            }
+        }
+    }
+    Ok(channel_id)
+}
+
+pub(crate) 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) => {
+                    CHAT_STORE
+                        .update(message.chat.id.0, |data| {
+                            data.forward_channel_id = Some(channel_id);
+                        })
+                        .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, message.chat.id.0, message.id, result).await?;
+        }
+        Command::RemoveForwardChannel => {
+            let chat_id = message.chat.id.0;
+            let text = CHAT_STORE
+                .update(chat_id, |data| {
+                    if data.forward_channel_id.is_some() {
+                        data.forward_channel_id = None;
+                        "Remove successfully.".to_string()
+                    } else {
+                        "No channel to remove.".to_string()
+                    }
+                })
+                .await;
+            reply(bot, message.chat.id.0, message.id, text).await?;
+        }
+        Command::EditBeforeForward => {
+            let chat_id = message.chat.id.0;
+            let text = CHAT_STORE
+                .update(chat_id, |data| {
+                    if data.forward_channel_id.is_none() {
+                        "Please enable forward channel first.".to_string()
+                    } else if data.edit_before_forward {
+                        data.edit_before_forward = false;
+                        data.edit_message.clear();
+                        "Disable edit before forward.".to_string()
+                    } else {
+                        data.edit_before_forward = true;
+                        "Enable edit before forward.".to_string()
+                    }
+                })
+                .await;
+            reply(bot, message.chat.id.0, message.id, 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 {
+                        CHAT_STORE
+                            .update(chat_id, |data| {
+                                data.template.insert(
+                                    name,
+                                    html_escape::encode_text(reply_text).into_owned(),
+                                );
+                            })
+                            .await;
+                        "Template set.".to_string()
+                    }
+                }
+            };
+            reply(bot, message.chat.id.0, message.id, text).await?;
+        }
+        Command::BotDict => {
+            // Debug dump of the chat's persisted state: admin only (it echoes
+            // forward-channel ids and templates to whoever asks).
+            let sender_id = message
+                .from
+                .as_ref()
+                .map(|user| user.id.0 as i64)
+                .unwrap_or(-1);
+            if !CONFIG.admin_ids.contains(&sender_id) {
+                reply(bot, message.chat.id.0, message.id, "Admin only.").await?;
+                return Ok(());
+            }
+            let chat_data = CHAT_STORE.get(message.chat.id.0).await;
+            let debug = html_escape::encode_text(&format!("{chat_data:?}")).into_owned();
+            // A chat with many templates/edit records exceeds Telegram's 4096
+            // char message limit; the dump is plain text (no parse mode), so a
+            // plain byte-boundary cut is safe.
+            let end = debug.floor_char_boundary(MAX_DEBUG_DUMP_CHARS.min(debug.len()));
+            let text = if end < debug.len() {
+                format!("{}…", &debug[..end])
+            } else {
+                debug
+            };
+            reply(bot, message.chat.id.0, message.id, 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,
+                        message.chat.id.0,
+                        message.id,
+                        "Usage: /set_format <site> <format>",
+                    )
+                    .await?;
+                    return Ok(());
+                }
+            };
+            if !x_media::site::site_ids().contains(&site) {
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    "Unknown site. Use twitter, bsky, pixiv or misskey.",
+                )
+                .await?;
+                return Ok(());
+            }
+            CHAT_STORE
+                .update(chat_id, |data| {
+                    data.message_format.insert(site.to_string(), format);
+                })
+                .await;
+            reply(bot, message.chat.id.0, message.id, "Format set.").await?;
+        }
+        Command::ClearCache(arg) => {
+            let sender_id = message
+                .from
+                .as_ref()
+                .map(|user| user.id.0 as i64)
+                .unwrap_or(-1);
+            if !CONFIG.admin_ids.contains(&sender_id) {
+                reply(bot, message.chat.id.0, message.id, "Admin only.").await?;
+                return Ok(());
+            }
+            let arg = arg.trim();
+            if arg.is_empty() {
+                let removed = LINK_CACHE.clear(None).await;
+                log::info!("cache cleared by {sender_id}: {removed} entries");
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    format!("Cleared {removed} cached entr{}.", plural(removed)),
+                )
+                .await?;
+            } else {
+                let key = match x_media::site::cache_key(arg) {
+                    Some(key) => key,
+                    None => {
+                        reply(
+                            bot,
+                            message.chat.id.0,
+                            message.id,
+                            "Unrecognized link. Use a twitter/x, pixiv, bsky or misskey post URL.",
+                        )
+                        .await?;
+                        return Ok(());
+                    }
+                };
+                let removed = LINK_CACHE.clear(Some(&key)).await;
+                log::info!("cache entry cleared by {sender_id}: {key} ({removed} rows)");
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    format!(
+                        "Cleared cache for {arg} ({} entr{}).",
+                        removed,
+                        plural(removed)
+                    ),
+                )
+                .await?;
+            }
+        }
+        Command::Test(arg) => {
+            let url = arg.trim();
+            if url.is_empty() {
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    "Usage: /test <post url>",
+                )
+                .await?;
+                return Ok(());
+            }
+            if x_media::site::cache_key(url).is_none() {
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    "No enabled site matches this link (twitter/x, pixiv, bsky or misskey).",
+                )
+                .await?;
+                return Ok(());
+            }
+            // The ordinary link pipeline with the chat's post-send actions
+            // suppressed: the media is sent (and cached) like a normal link,
+            // but nothing is forwarded to the channel and no
+            // edit-before-forward prompt opens. Info level echoes the
+            // normalized key (never the raw URL) per the logging convention.
+            log::info!("test: sending [key={}]", log_key(url));
+            let ctx = AppContext::from_statics(bot);
+            url_media(
+                &ctx,
+                message.chat.id.0,
+                message.id.0 as i64,
+                url,
+                PostSend::Suppressed,
+            )
+            .await;
+        }
+        Command::Debug(arg) => {
+            let url = arg.trim();
+            if url.is_empty() {
+                reply(
+                    bot,
+                    message.chat.id.0,
+                    message.id,
+                    "Usage: /debug <post url>",
+                )
+                .await?;
+                return Ok(());
+            }
+            // Debug tool: report the parse result only — nothing is sent,
+            // cached or forwarded.
+            log::info!("debug: parsing [key={}]", log_key(url));
+            match x_media::site::fetch(url).await {
+                Ok(None) => {
+                    reply(
+                        bot,
+                        message.chat.id.0,
+                        message.id,
+                        "No enabled site matches this link (twitter/x, pixiv, bsky or misskey).",
+                    )
+                    .await?;
+                }
+                Err(e) => {
+                    reply(
+                        bot,
+                        message.chat.id.0,
+                        message.id,
+                        format!("Fetch failed: {e}"),
+                    )
+                    .await?;
+                }
+                Ok(Some(fetched)) => {
+                    let report = debug_report(
+                        url,
+                        fetched.site_name(),
+                        &fetched.source_url,
+                        &fetched.title,
+                        fetched.render_fields(),
+                        fetched.sensitive,
+                        &fetched.caption,
+                        &fetched.media,
+                    );
+                    // HTML report: the caption renders inside a <blockquote>
+                    // exactly as it will appear in the sent media message.
+                    reply_html(bot, message.chat.id.0, message.id, report).await?;
+                }
+            }
+        }
+    }
+    Ok(())
+}
+
+/// `"y"` for one, `"ies"` for anything else — "1 entry" / "2 entries".
+fn plural(n: usize) -> &'static str {
+    if n == 1 { "y" } else { "ies" }
+}
+
+/// Registers the bot's command list with Telegram so clients show it in the
+/// `/` menu (Bot API `setMyCommands`).
+pub async fn register_commands(bot: &Bot) -> Result<(), RequestError> {
+    let commands = Command::bot_commands();
+    bot.set_my_commands(commands.clone()).await?;
+    log::info!("registered {} commands", commands.len());
+    Ok(())
+}
+
+/// Telegram's plain-text message limit is 4096 chars; the report stays under
+/// it even for very large threads (many media lines + a long caption).
+const MAX_DEBUG_REPORT_CHARS: usize = 4000;
+
+/// Cap for the `/bot_dict` debug dump: the state is echoed as one plain-text
+/// message, so it must stay under Telegram's 4096-char limit.
+const MAX_DEBUG_DUMP_CHARS: usize = 3500;
+
+/// Builds the HTML report for the `/debug` command: what the parser produced
+/// for a link (site, canonical URL, title/author/tags, caption and the media
+/// list) — no media is sent and nothing is cached or forwarded. Sent with
+/// HTML parse mode: raw fields are escaped, the pre-escaped render fields are
+/// embedded as-is, and the caption is wrapped in a `<blockquote>` so it shows
+/// exactly as it will render in the sent media message. Fields are passed
+/// individually so the formatter stays a pure function testable without
+/// constructing a `Fetched` (its render fields are `pub(crate)` to the
+/// x-media crate).
+#[allow(clippy::too_many_arguments)]
+fn debug_report(
+    url: &str,
+    site_id: &str,
+    source_url: &str,
+    title: &str,
+    render: Option<(&str, &str, &str, &str)>,
+    sensitive: bool,
+    caption: &str,
+    media: &[x_media::media::Media],
+) -> String {
+    let mut lines = vec![
+        format!("Parse result for {}", html_escape::encode_text(url)),
+        format!("site: {site_id}"),
+        format!(
+            "key: {}",
+            html_escape::encode_text(
+                &x_media::site::cache_key(url).unwrap_or_else(|| "<unsupported>".to_string())
+            )
+        ),
+    ];
+    lines.push(format!(
+        "source_url: {}",
+        html_escape::encode_text(source_url)
+    ));
+    lines.push(format!("title: {}", html_escape::encode_text(title)));
+    if let Some((author, author_url, _title, tags)) = render {
+        // The render fields are already pre-escaped for HTML captions; embed
+        // them as-is so the report renders them exactly like the final
+        // caption. `author_url` is raw and gets escaped here.
+        lines.push(format!("author: {author}"));
+        lines.push(format!(
+            "author_url: {}",
+            html_escape::encode_text(author_url)
+        ));
+        lines.push(format!("tags: {tags}"));
+    }
+    lines.push(format!("sensitive: {sensitive}"));
+    // The caption is wrapped in a <blockquote> so the report (an HTML
+    // message) shows it exactly as it will render in the sent media caption
+    // — escaped text and links included.
+    lines.push(format!(
+        "caption: <blockquote>{}</blockquote>",
+        x_media::site::truncate_caption(caption)
+    ));
+    lines.push(format!("media ({}):", media.len()));
+    for (i, item) in media.iter().enumerate() {
+        let kind = match item {
+            x_media::media::Media::Illustration { .. } => "image",
+            x_media::media::Media::Video { .. } => "video",
+            x_media::media::Media::Animated { .. } => "gif",
+        };
+        lines.push(format!(
+            "  {}. {kind}: {}",
+            i + 1,
+            html_escape::encode_text(item.url())
+        ));
+    }
+    let mut out = lines.join(
+        "
+",
+    );
+    if out.chars().count() > MAX_DEBUG_REPORT_CHARS {
+        let end = out.floor_char_boundary(MAX_DEBUG_REPORT_CHARS - 1);
+        out = format!("{}…", &out[..end]);
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{MAX_DEBUG_REPORT_CHARS, debug_report};
+    use x_media::media::Media;
+
+    #[test]
+    fn debug_report_renders_fields_and_media() {
+        let media = vec![
+            Media::Illustration {
+                title: None,
+                url: "https://cdn.example/1.jpg".into(),
+                thumbnail_url: None,
+                fallback_url: None,
+            },
+            Media::Video {
+                title: None,
+                url: "https://cdn.example/2.mp4".into(),
+                thumbnail_url: "https://cdn.example/2.jpg".into(),
+            },
+        ];
+        let report = debug_report(
+            "https://x.com/u/status/1",
+            "twitter",
+            "https://x.com/u/status/1",
+            "My title",
+            Some(("Author", "https://x.com/u", "My title", "tag1 tag2")),
+            false,
+            "<a href=\"https://x.com/u\">Author</a> · My title",
+            &media,
+        );
+        assert!(report.contains("site: twitter"), "{report}");
+        assert!(report.contains("key: twitter:1"), "{report}");
+        assert!(report.contains("title: My title"), "{report}");
+        assert!(report.contains("author: Author"), "{report}");
+        assert!(report.contains("author_url: https://x.com/u"), "{report}");
+        assert!(report.contains("tags: tag1 tag2"), "{report}");
+        assert!(report.contains("sensitive: false"), "{report}");
+        assert!(report.contains("media (2):"), "{report}");
+        assert!(
+            report.contains("1. image: https://cdn.example/1.jpg"),
+            "{report}"
+        );
+        assert!(
+            report.contains("2. video: https://cdn.example/2.mp4"),
+            "{report}"
+        );
+    }
+
+    #[test]
+    fn debug_report_without_render_data_and_no_media() {
+        let report = debug_report("u", "pixiv", "s", "t", None, true, "c", &[]);
+        assert!(!report.contains("author:"), "{report}");
+        assert!(report.contains("sensitive: true"), "{report}");
+        assert!(report.contains("media (0):"), "{report}");
+    }
+
+    #[test]
+    fn debug_report_wraps_caption_in_blockquote() {
+        // The report is an HTML message: raw fields are escaped, pre-escaped
+        // render fields are embedded as-is, and the caption is wrapped in a
+        // <blockquote> so it shows exactly as it will render in the sent
+        // media caption (escaped text and links included).
+        let report = debug_report(
+            "https://x.com/u/status/1",
+            "twitter",
+            "https://x.com/u/status/1",
+            "A & B <C>",
+            Some((
+                "A &amp; B",
+                "https://x.com/u",
+                "A &amp; B &lt;C&gt;",
+                "#a &amp; #b",
+            )),
+            false,
+            "<a href=\"https://x.com/u\">A &amp; B</a>: C &lt;D&gt; &amp; E",
+            &[],
+        );
+        // Raw fields escaped (they render back to the original text in HTML).
+        assert!(report.contains("title: A &amp; B &lt;C&gt;"), "{report}");
+        assert!(
+            report.contains("source_url: https://x.com/u/status/1"),
+            "{report}"
+        );
+        // Pre-escaped render fields embedded as-is.
+        assert!(report.contains("author: A &amp; B"), "{report}");
+        assert!(report.contains("tags: #a &amp; #b"), "{report}");
+        // Caption wrapped in a blockquote with its HTML preserved.
+        assert!(
+            report.contains(
+                "caption: <blockquote><a href=\"https://x.com/u\">A &amp; B</a>: C &lt;D&gt; &amp; E</blockquote>"
+            ),
+            "{report}"
+        );
+    }
+
+    #[test]
+    fn debug_report_is_capped() {
+        // 200 media lines ≈ 8 KB, comfortably over the cap.
+        let media: Vec<Media> = (0..200)
+            .map(|i| Media::Illustration {
+                title: None,
+                url: format!("https://cdn.example/{i}.jpg"),
+                thumbnail_url: None,
+                fallback_url: None,
+            })
+            .collect();
+        let report = debug_report("u", "twitter", "s", "t", None, false, "c", &media);
+        assert!(report.chars().count() <= MAX_DEBUG_REPORT_CHARS, "{report}");
+        assert!(report.ends_with('…'), "{report}");
+    }
+}

crates/xmedia-bot/src/handlers/inline.rs

@@ -0,0 +1,234 @@
+//! Inline query handling with a keystroke debounce: only a query stable for
+//! [`INLINE_DEBOUNCE`] triggers a fetch, and repeats are served by Telegram's
+//! inline cache instead of re-fetching.
+
+use super::log_key;
+use std::collections::HashMap;
+use std::sync::LazyLock;
+use teloxide::RequestError;
+use teloxide::prelude::*;
+use teloxide::types::{
+    InlineQuery, InlineQueryResult, InlineQueryResultMpeg4Gif, InlineQueryResultPhoto,
+    InlineQueryResultVideo, ParseMode,
+};
+use x_media::media::Media;
+
+/// Debounce window for inline queries: Telegram fires an inline query on
+/// every keystroke, and each prefix of a pasted URL (e.g. `.../status/12`,
+/// `.../status/123`, ...) already matches the site patterns. Without a
+/// debounce every keystroke triggers a fetch (3 attempts!) of a half-typed
+/// post id. Only answer once the query has been stable for this long.
+const INLINE_DEBOUNCE: std::time::Duration = std::time::Duration::from_millis(800);
+
+/// Last seen inline query per user and whether it was already answered.
+/// Guards the debounce timer: a repeat of an answered query is served by
+/// Telegram's inline cache (see `cache_time`), not by another fetch. Keyed by
+/// user id — a single shared slot would let one user's typing burst (or a
+/// different user's query) cancel another user's pending answer.
+struct InlineDebounceState {
+    query: String,
+    answered: bool,
+}
+
+#[derive(Default)]
+struct DebounceStates(HashMap<u64, InlineDebounceState>);
+
+impl DebounceStates {
+    /// Records `query` as the user's newest query. Returns false when it is a
+    /// repeat whose answer already went out (Telegram's inline cache serves
+    /// it; re-fetching would only hit the source site again).
+    fn note(&mut self, user_id: u64, query: &str) -> bool {
+        if let Some(prev) = self.0.get(&user_id)
+            && prev.query == query
+            && prev.answered
+        {
+            return false;
+        }
+        self.0.insert(
+            user_id,
+            InlineDebounceState {
+                query: query.to_string(),
+                answered: false,
+            },
+        );
+        true
+    }
+
+    /// Claims the answer for the user's newest query; false when a newer query
+    /// superseded it or the answer was already claimed.
+    fn claim(&mut self, user_id: u64, query: &str) -> bool {
+        let Some(state) = self.0.get_mut(&user_id) else {
+            return false;
+        };
+        if state.query != query || state.answered {
+            return false;
+        }
+        state.answered = true;
+        true
+    }
+
+    /// Releases a claimed-but-unsent answer so a repeat can retry the fetch.
+    fn release(&mut self, user_id: u64, query: &str) {
+        if let Some(state) = self.0.get_mut(&user_id)
+            && state.query == query
+        {
+            state.answered = false;
+        }
+    }
+}
+
+static INLINE_DEBOUNCE_STATE: LazyLock<parking_lot::Mutex<DebounceStates>> =
+    LazyLock::new(|| parking_lot::Mutex::new(DebounceStates::default()));
+
+pub async fn inline_query_handler(bot: Bot, query: InlineQuery) -> Result<(), RequestError> {
+    if query.query.is_empty() {
+        return respond(());
+    }
+    // Only run a fetch for something that is actually a supported post URL.
+    if x_media::site::cache_key(&query.query).is_none() {
+        return respond(());
+    }
+    // Debounce: record the query and answer only after it has been stable for
+    // INLINE_DEBOUNCE (the timer below). An already-answered repeat of the
+    // same query is left to Telegram's inline cache instead of re-fetching.
+    let user_id = query.from.id.0;
+    if !INLINE_DEBOUNCE_STATE.lock().note(user_id, &query.query) {
+        return respond(());
+    }
+    let query_text = query.query.clone();
+    tokio::spawn(async move {
+        tokio::time::sleep(INLINE_DEBOUNCE).await;
+        // Only the user's last query of a typing burst survives: earlier
+        // timers see the query changed and give up without answering.
+        if !INLINE_DEBOUNCE_STATE.lock().claim(user_id, &query_text) {
+            return;
+        }
+        match answer_inline_query(bot, query).await {
+            Ok(true) => {}
+            // No results produced (or nothing to answer): let a repeat of the
+            // same query retry the fetch.
+            Ok(false) | Err(_) => INLINE_DEBOUNCE_STATE.lock().release(user_id, &query_text),
+        }
+    });
+    respond(())
+}
+
+/// Fetches the post behind an inline query and answers it. The caller has
+/// already applied the debounce. Returns `true` when an answer was sent.
+async fn answer_inline_query(bot: Bot, query: InlineQuery) -> Result<bool, RequestError> {
+    log::debug!(
+        "inline query: {} [key={}]",
+        query.query,
+        log_key(&query.query)
+    );
+    // No retries: the debounce plus a 1s/2s backoff would outlast the inline
+    // query the answer belongs to.
+    match x_media::site::fetch_once(&query.query).await {
+        Ok(Some(fetched)) => {
+            let mut results: Vec<InlineQueryResult> = Vec::new();
+            // Inline results have the same 1024-char caption limit as regular
+            // messages; truncate once here for all items.
+            let caption = x_media::site::truncate_caption(&fetched.caption);
+            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 = 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() {
+                // Explicit cache window: repeats of the same query within 5
+                // minutes are served by Telegram without hitting the bot.
+                bot.answer_inline_query(query.id, results)
+                    .cache_time(300)
+                    .await?;
+                return Ok(true);
+            }
+        }
+        Ok(None) => {}
+        Err(e) => log::error!("inline fetch {}: {e}", query.query),
+    }
+    Ok(false)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::DebounceStates;
+
+    const URL_A: &str = "https://x.com/a/status/1";
+    const URL_B: &str = "https://x.com/b/status/2";
+
+    #[test]
+    fn debounce_state_is_per_user() {
+        let mut states = DebounceStates::default();
+        // Two users query different links: both proceed, and neither timer
+        // cancels the other (a single shared slot dropped one of them).
+        assert!(states.note(1, URL_A));
+        assert!(states.note(2, URL_B));
+        assert!(states.claim(1, URL_A), "user 1's answer was cancelled");
+        assert!(states.claim(2, URL_B), "user 2's answer was cancelled");
+    }
+
+    #[test]
+    fn answered_query_is_suppressed_per_user_only() {
+        let mut states = DebounceStates::default();
+        assert!(states.note(1, URL_A));
+        assert!(states.claim(1, URL_A));
+        // A repeat of the answered query by the same user is left to
+        // Telegram's inline cache.
+        assert!(!states.note(1, URL_A));
+        // Another user pasting the same link still gets an answer.
+        assert!(states.note(2, URL_A));
+        assert!(states.claim(2, URL_A));
+    }
+
+    #[test]
+    fn newer_query_supersedes_and_failed_answer_is_released() {
+        let mut states = DebounceStates::default();
+        assert!(states.note(1, URL_A));
+        assert!(states.note(1, URL_B));
+        // The stale timer for the half-typed query gives up…
+        assert!(!states.claim(1, URL_A));
+        // …and the newest one answers.
+        assert!(states.claim(1, URL_B));
+        // No results → release so a repeat may retry the fetch.
+        states.release(1, URL_B);
+        assert!(states.claim(1, URL_B));
+    }
+}

crates/xmedia-bot/src/handlers/mod.rs

@@ -0,0 +1,274 @@
+//! Update handlers and the per-URL media pipeline.
+//!
+//! Split into per-concern modules: [`commands`] (the `/`-command executor),
+//! [`urls`] (URL extraction + the bounded worker pool + send dispatch),
+//! [`inline`] (debounced inline queries), [`callback`] (edit-before-forward
+//! buttons) and [`statics`] (the shared process-wide stores). This module
+//! holds the message entry point and the helpers the others share.
+
+mod callback;
+mod commands;
+mod inline;
+mod statics;
+mod urls;
+
+pub use callback::callback_query_handler;
+pub use commands::register_commands;
+pub use inline::inline_query_handler;
+pub use statics::{CHAT_STORE, CONFIG, LINK_CACHE, TASK_QUEUE};
+pub use urls::{start_url_workers, stop_url_workers};
+
+use crate::ctx::AppContext;
+use crate::media_sender::MediaSender;
+use commands::{Command, execute_command};
+use teloxide::RequestError;
+use teloxide::prelude::*;
+use teloxide::types::{ChatId, ChatKind, Message, MessageId, ParseMode, ReplyParameters};
+use teloxide::utils::command::BotCommands;
+use urls::{URL_JOBS, extract_urls};
+
+/// Reply to a message by id, keeping the reply decoration even if the
+/// original was already deleted. Returns the reply's message id.
+pub(crate) async fn reply(
+    sender: &dyn MediaSender,
+    chat_id: i64,
+    reply_to: MessageId,
+    text: impl Into<String>,
+) -> Result<i64, RequestError> {
+    sender
+        .send_message(ChatId(chat_id), text.into(), Some(reply_to), None)
+        .await
+}
+
+/// Reply to a message by id with HTML parse mode (same reply decoration as
+/// [`reply`]). Used by `/test`, whose report is an HTML message (the caption
+/// is wrapped in a `<blockquote>` to show it exactly as it will render).
+pub(crate) async fn reply_html(
+    bot: &Bot,
+    chat_id: i64,
+    reply_to: MessageId,
+    text: String,
+) -> Result<i64, RequestError> {
+    // `<Bot as Requester>::` disambiguates from the MediaSender trait's
+    // same-named method (see media_sender.rs).
+    <Bot as Requester>::send_message(bot, ChatId(chat_id), text)
+        .parse_mode(ParseMode::Html)
+        .reply_parameters(ReplyParameters::new(reply_to).allow_sending_without_reply())
+        .await
+        .map(|message| message.id.0 as i64)
+}
+
+/// Log prefix tying the whole lifecycle of one link (fetch → send → cache →
+/// forward) together: the normalized cache key (`twitter:123…`, `pixiv:123`,
+/// `bsky:handle/rkey`) instead of the raw URL, so logs stay short and do not
+/// echo full user-submitted URLs at info level.
+pub fn log_key(url: &str) -> String {
+    x_media::site::cache_key(url).unwrap_or_else(|| "<unsupported>".to_string())
+}
+
+/// 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.
+/// Body of [`message_handler`]'s edit branch, without teloxide update types so
+/// it can be driven by tests.
+async fn edit_message_handler(
+    ctx: &AppContext<'_>,
+    chat_id: i64,
+    reply_to_message_id: i64,
+    text: &str,
+) -> bool {
+    let chat_data = ctx.chat_store.get(chat_id).await;
+    let Some(edit) = chat_data.edit_message.get(&reply_to_message_id) else {
+        return false;
+    };
+    let Some(first_forward_id) = edit.forward_message_ids.first() else {
+        return false;
+    };
+    let link = format!(
+        "<a href=\"{0}\">{1}</a>",
+        html_escape::encode_double_quoted_attribute(&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)
+    };
+    match ctx
+        .sender
+        .edit_message_caption(
+            ChatId(chat_id),
+            MessageId(*first_forward_id as i32),
+            new_text,
+        )
+        .await
+    {
+        Ok(()) => log::info!(
+            "edit-before-forward: caption swapped on message {first_forward_id} for prompt {reply_to_message_id}"
+        ),
+        Err(e) => log::error!("edit_message_caption failed: {e}"),
+    }
+    true
+}
+
+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| {
+            let end = t.floor_char_boundary(120.min(t.len()));
+            &t[..end]
+        })
+        .unwrap_or("<no text>");
+    // Per-request detail: debug only (message text is user data).
+    log::debug!(
+        "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
+        && let Some(reply) = message.reply_to_message()
+        && let Some(text) = message.text()
+        && edit_message_handler(
+            &AppContext::from_statics(&bot),
+            message.chat.id.0,
+            reply.id.0 as i64,
+            text,
+        )
+        .await
+    {
+        return respond(());
+    }
+    if let Some(text) = message.text()
+        && let Ok(command) = Command::parse(text, "")
+    {
+        log::debug!("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() {
+            // Debug only, and echo the normalized keys instead of the raw URLs.
+            let keys: Vec<String> = urls.iter().map(|u| log_key(u)).collect();
+            log::debug!("extracted {} URL(s): {keys:?}", urls.len());
+        }
+        for url in urls {
+            // Clone out of the lock: the parking_lot guard is !Send and must
+            // not be held across the await below.
+            let Some(tx) = URL_JOBS.lock().clone() else {
+                log::warn!("url workers not started; dropping link");
+                break;
+            };
+            // A closed channel means the workers are stopping (shutdown):
+            // report the dropped link instead of losing it silently.
+            if tx.send((message.clone(), url)).await.is_err() {
+                log::warn!("url workers stopped; dropping link");
+                break;
+            }
+        }
+    }
+    respond(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::ctx::test_support::TestStores;
+    use crate::media_sender::test_support::{MockSender, Outcome};
+    use crate::state::EditMessage;
+    use teloxide::ApiError;
+
+    const PROMPT_ID: i64 = 7;
+    const FORWARDED_ID: i64 = 9;
+
+    fn api_error() -> RequestError {
+        RequestError::Api(ApiError::Unknown("Bad Request: message not found".into()))
+    }
+
+    /// Seeds a prompt record; `template` names the chat template used for it
+    /// (empty = none, the caption gets the bare link).
+    async fn seed_prompt(ctx: &AppContext<'_>, template: &str) {
+        ctx.chat_store
+            .update(1, |data| {
+                data.template
+                    .insert("tpl".to_string(), "<b>[]</b>".to_string());
+                data.edit_message.insert(
+                    PROMPT_ID,
+                    EditMessage {
+                        url: "https://x.com/u/status/1".into(),
+                        chat_id: 1,
+                        forward_message_ids: vec![FORWARDED_ID],
+                        template: template.to_string(),
+                        created_at: crate::db::unix_now(),
+                    },
+                );
+            })
+            .await;
+    }
+
+    #[tokio::test]
+    async fn reply_to_a_prompt_swaps_the_caption_through_its_template() {
+        let sender = MockSender::scripted(vec![Outcome::EditOk], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, "tpl").await;
+
+        let consumed = edit_message_handler(&ctx, 1, PROMPT_ID, "new caption").await;
+
+        assert!(consumed, "a reply to the prompt must be consumed");
+        assert_eq!(
+            sender.captions(),
+            vec!["<b><a href=\"https://x.com/u/status/1\">new caption</a></b>"]
+        );
+    }
+
+    #[tokio::test]
+    async fn reply_text_and_url_are_escaped_into_the_caption() {
+        let sender = MockSender::scripted(vec![Outcome::EditOk], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, "").await;
+
+        edit_message_handler(&ctx, 1, PROMPT_ID, "<script>alert(1)</script>").await;
+
+        // No raw markup from user text may reach the HTML caption.
+        assert_eq!(
+            sender.captions(),
+            vec!["<a href=\"https://x.com/u/status/1\">&lt;script&gt;alert(1)&lt;/script&gt;</a>"]
+        );
+    }
+
+    #[tokio::test]
+    async fn a_failed_caption_swap_still_consumes_the_reply() {
+        let sender = MockSender::scripted(vec![Outcome::EditErr], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+        seed_prompt(&ctx, "tpl").await;
+
+        // The edit failed (message deleted etc.); the reply must still be
+        // swallowed instead of being treated as a link to fetch.
+        assert!(edit_message_handler(&ctx, 1, PROMPT_ID, "new caption").await);
+        assert_eq!(sender.calls(), vec!["edit_message_caption"]);
+    }
+
+    #[tokio::test]
+    async fn reply_to_an_unrelated_message_is_not_consumed() {
+        let sender = MockSender::scripted(vec![], api_error);
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&sender);
+
+        // No prompt record for that message id → the reply runs the normal
+        // (URL/command) path instead.
+        assert!(!edit_message_handler(&ctx, 1, PROMPT_ID, "hello").await);
+        assert!(sender.calls().is_empty());
+    }
+}

crates/xmedia-bot/src/handlers/statics.rs

@@ -0,0 +1,38 @@
+//! Process-wide singletons shared by the handler modules: the one SQLite
+//! pool (and the three stores built on it) plus the configuration.
+
+use crate::config::Config;
+use crate::db::{self};
+use crate::link_cache::LinkCache;
+use crate::queue::PersistentTaskQueue;
+use crate::state::ChatStore;
+use std::sync::{Arc, LazyLock};
+
+/// One shared SQLite pool for the three stores (chat state, task queue, link
+/// cache): a single pool bounds concurrent DB work on `data/task_queue.db`
+/// instead of three independent pools competing for the same file. The schema
+/// for all three tables is initialized once, here.
+static DB: LazyLock<Arc<db::DbPool>> = LazyLock::new(|| {
+    let path = db_path();
+    db::open_store(&path.to_string_lossy()).expect("failed to open database")
+});
+
+/// DB file location: `$DATA_DIR/task_queue.db` (default `data`, relative to
+/// the working directory — keeps the docker-compose `./data` mount and local
+/// runs unchanged). The directory is created if missing: SQLite does not
+/// create parent dirs, so the old hardcoded `data/task_queue.db` failed with
+/// a confusing error when started from a directory without `data/`, and a
+/// CWD-relative path is a footgun for systemd / cron deployments — `DATA_DIR`
+/// lets them pin the state anywhere.
+fn db_path() -> std::path::PathBuf {
+    let dir = std::env::var("DATA_DIR").unwrap_or_else(|_| "data".to_string());
+    let dir_path = std::path::Path::new(&dir);
+    std::fs::create_dir_all(dir_path).expect("failed to create data directory");
+    dir_path.join("task_queue.db")
+}
+
+pub static CHAT_STORE: LazyLock<ChatStore> = LazyLock::new(|| ChatStore::new(Arc::clone(&DB)));
+pub static TASK_QUEUE: LazyLock<PersistentTaskQueue> =
+    LazyLock::new(|| PersistentTaskQueue::new(Arc::clone(&DB)));
+pub static LINK_CACHE: LazyLock<LinkCache> = LazyLock::new(|| LinkCache::new(Arc::clone(&DB)));
+pub static CONFIG: LazyLock<Config> = LazyLock::new(Config::load);

crates/xmedia-bot/src/handlers/urls.rs

@@ -0,0 +1,665 @@
+//! URL extraction and the per-URL media pipeline: bounded job channel +
+//! worker pool, link-cache fast path, fetch, task build and send dispatch.
+
+use super::{log_key, reply};
+use crate::ctx::{AppContext, CONTEXT};
+use crate::link_cache::{CachedMediaKind, CachedPost};
+use crate::send::{self, MediaItemPayload, Task};
+use crate::state::ChatData;
+use std::collections::HashSet;
+use std::sync::LazyLock;
+use teloxide::types::{ChatAction, ChatId, Message, MessageEntityKind, MessageId};
+use x_media::media::Media;
+
+/// One URL job: the message + the extracted URL (the sender and stores come
+/// from the shared [`AppContext`], assembled from statics inside the worker).
+type UrlJob = (Message, String);
+/// Bounded channel of URL jobs drained by [`start_url_workers`]. The bound
+/// caps both queued memory and shutdown backlog; a full channel applies
+/// backpressure to the per-chat handler instead of spawning unbounded tasks.
+pub(crate) static URL_JOBS: LazyLock<
+    parking_lot::Mutex<Option<tokio::sync::mpsc::Sender<UrlJob>>>,
+> = LazyLock::new(|| parking_lot::Mutex::new(None));
+/// Set by main's shutdown sequence; workers stop pulling new jobs.
+pub(crate) static URL_STOP: std::sync::atomic::AtomicBool =
+    std::sync::atomic::AtomicBool::new(false);
+
+/// JoinHandles of the URL workers, awaited by [`stop_url_workers`].
+static URL_WORKER_HANDLES: LazyLock<parking_lot::Mutex<Option<Vec<tokio::task::JoinHandle<()>>>>> =
+    LazyLock::new(|| parking_lot::Mutex::new(None));
+
+/// Worker count draining URL jobs; keeps the old 8-permit concurrency cap
+/// while bounding how many jobs can be queued at all.
+const URL_WORKERS: usize = 8;
+
+/// Starts the URL job workers (called once from main after the queue starts).
+/// teloxide dispatches updates to a per-chat worker that handles them
+/// sequentially, so a batch-forward of many messages would otherwise be
+/// processed one at a time (fetch + send each, roughly a second per
+/// message); the workers add throughput, and FIFO order preserves per-message
+/// URL order.
+pub async fn start_url_workers() {
+    let (tx, rx) = tokio::sync::mpsc::channel::<UrlJob>(256);
+    *URL_JOBS.lock() = Some(tx);
+    let rx = std::sync::Arc::new(tokio::sync::Mutex::new(rx));
+    let mut handles = Vec::with_capacity(URL_WORKERS);
+    for _ in 0..URL_WORKERS {
+        let rx = std::sync::Arc::clone(&rx);
+        handles.push(tokio::spawn(async move {
+            while !URL_STOP.load(std::sync::atomic::Ordering::Relaxed) {
+                let job = rx.lock().await.recv().await;
+                match job {
+                    Some((message, url)) => {
+                        url_media(
+                            &CONTEXT,
+                            message.chat.id.0,
+                            message.id.0 as i64,
+                            &url,
+                            PostSend::FromChat,
+                        )
+                        .await
+                    }
+                    None => break,
+                }
+            }
+        }));
+    }
+    *URL_WORKER_HANDLES.lock() = Some(handles);
+}
+
+/// Stops the URL workers: sets the stop flag, drops the job channel (so
+/// workers blocked in \`recv()\` wake with \`None\` and exit) and awaits the
+/// worker tasks. Each worker finishes its in-flight job first; jobs still
+/// queued in the channel are abandoned (the old implementation neither
+/// drained them nor woke blocked workers — it only set a flag checked
+/// between jobs).
+pub async fn stop_url_workers() {
+    URL_STOP.store(true, std::sync::atomic::Ordering::Relaxed);
+    // Dropping the sender makes every worker's recv() return None.
+    *URL_JOBS.lock() = None;
+    // Take the handles first so the lock guard drops before the awaits.
+    let handles = URL_WORKER_HANDLES.lock().take();
+    if let Some(handles) = handles {
+        for handle in handles {
+            let _ = handle.await;
+        }
+    }
+}
+
+/// 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();
+    // Dedup by the normalized post id so variant URLs of the same post
+    // (/status/1 vs /status/1/photo/1) are sent once; unsupported URLs fall
+    // back to exact-string dedup.
+    urls.retain(|url| seen.insert(x_media::site::cache_key(url).unwrap_or_else(|| url.clone())));
+    urls
+}
+
+/// 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://") {
+        // An empty thumbnail string (misskey video/gif files without a
+        // thumbnailUrl) must not reach Telegram; let it generate its own.
+        media
+            .thumbnail_url()
+            .map(str::to_string)
+            .filter(|t| !t.is_empty())
+    } 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,
+            file_id: false,
+        },
+        Media::Video { .. } => MediaItemPayload::Video {
+            media: media.url().to_string(),
+            has_spoiler: sensitive,
+            thumbnail: thumbnail_for(media),
+            fallback_url,
+            file_id: false,
+        },
+        Media::Animated { .. } => MediaItemPayload::Video {
+            media: media.url().to_string(),
+            has_spoiler: sensitive,
+            thumbnail: thumbnail_for(media),
+            fallback_url,
+            file_id: false,
+        },
+    }
+}
+
+/// Sends a task and handles the outcome: post-send actions on success, retry
+/// enqueue on retryable failure, reply + link-cache invalidation on
+/// permanent failure (a stale cached file id must not repeat forever).
+async fn dispatch_send(
+    ctx: &AppContext<'_>,
+    chat_id: i64,
+    reply_to: MessageId,
+    task: &Task,
+    url: &str,
+) {
+    let result = match task {
+        Task::SendAnimation { .. } => send::send_animation(ctx, task).await,
+        Task::SendMediaSequence { .. } => send::send_media_sequence(ctx, task).await,
+        Task::ForwardMessages { .. } => unreachable!(),
+    };
+    match result {
+        Ok(message_ids) => {
+            log::info!(
+                "sent {} message(s) for [key={}]",
+                message_ids.len(),
+                log_key(url)
+            );
+            send::post_send_actions(ctx, task, message_ids).await;
+            send::settle_task(ctx, task, send::Settled::Sent).await;
+        }
+        Err(send::SendError::Retryable {
+            delay_seconds,
+            task,
+        }) => {
+            log::info!(
+                "send for [key={}] failed, queued for retry in {delay_seconds:.1}s",
+                log_key(url)
+            );
+            send::enqueue_retry(ctx.task_queue, *task, delay_seconds).await;
+            let _ = reply(
+                ctx.sender,
+                chat_id,
+                reply_to,
+                "Send failed. Task queued for retry.",
+            )
+            .await;
+        }
+        Err(send::SendError::Permanent {
+            message: err_message,
+            task,
+        }) => {
+            send::settle_task(ctx, &task, send::Settled::Failed).await;
+            log::error!("send for {url} failed permanently: {err_message}");
+            let _ = reply(
+                ctx.sender,
+                chat_id,
+                reply_to,
+                format!("Send failed: {err_message}"),
+            )
+            .await;
+        }
+    }
+}
+
+/// Whether a send also runs the chat's post-send actions. `/test` sends with
+/// them suppressed so a test can never forward to the channel or open the
+/// edit-before-forward prompt; a normal link uses whatever the chat is
+/// configured with.
+#[derive(Clone, Copy, PartialEq, Eq, Debug)]
+pub(crate) enum PostSend {
+    /// Apply the chat's `forward_channel_id` / `edit_before_forward`.
+    FromChat,
+    /// Send only: no channel forward, no edit prompt.
+    Suppressed,
+}
+
+/// Builds the send task from ready-made items, sharing the payload shape
+/// between the fresh-fetch, link-cache and `/test` paths.
+#[allow(clippy::too_many_arguments)]
+fn build_send_task(
+    chat_data: &ChatData,
+    chat_id: i64,
+    reply_to_message_id: i64,
+    source_url: String,
+    caption: String,
+    items: Vec<MediaItemPayload>,
+    cache_data: Option<CachedPost>,
+    post_send: PostSend,
+) -> Task {
+    // Notification ids stay set in both modes: a queued retry that
+    // dead-letters should still tell the chat.
+    let (edit_before_forward, forward_channel_id) = match post_send {
+        PostSend::FromChat => (chat_data.edit_before_forward, chat_data.forward_channel_id),
+        PostSend::Suppressed => (false, None),
+    };
+    if items.len() == 1 && matches!(items[0], MediaItemPayload::Animation { .. }) {
+        Task::SendAnimation {
+            chat_id,
+            reply_to_message_id,
+            caption,
+            animation: items.into_iter().next().unwrap(),
+            source_url,
+            edit_before_forward,
+            forward_channel_id,
+            notify_chat_id: Some(chat_id),
+            notify_message_id: Some(reply_to_message_id),
+            cache_data,
+        }
+    } else {
+        Task::SendMediaSequence {
+            chat_id,
+            reply_to_message_id,
+            caption,
+            // Photos first so a mixed photo+video group starts with a photo
+            // (Telegram's sendMediaGroup rule); order within each kind is kept.
+            media_batches: send::chunk_media_items(send::photos_first(items)),
+            batch_index: 0,
+            sent_message_ids: vec![],
+            source_url,
+            edit_before_forward,
+            forward_channel_id,
+            notify_chat_id: Some(chat_id),
+            notify_message_id: Some(reply_to_message_id),
+            cache_data,
+        }
+    }
+}
+
+/// The per-URL pipeline: link cache → fetch → build → send → post-send.
+///
+/// `post_send` selects whether the chat's forward/edit settings apply: the URL
+/// workers pass [`PostSend::FromChat`], the `/test` command
+/// [`PostSend::Suppressed`]. Everything else (cache write, retry enqueue,
+/// dead-letter notification) is identical.
+pub(crate) async fn url_media(
+    ctx: &AppContext<'_>,
+    chat_id: i64,
+    reply_to_message_id: i64,
+    url: &str,
+    post_send: PostSend,
+) {
+    let reply_to = MessageId(reply_to_message_id as i32);
+    if let Err(e) = ctx
+        .sender
+        .send_chat_action(ChatId(chat_id), ChatAction::Typing)
+        .await
+    {
+        log::error!("send_chat_action failed: {e}");
+    }
+
+    // Link cache: a post sent before is re-sent from Telegram file ids —
+    // no source-site request, no download, no upload. Keyed by the
+    // normalized post id so x.com / fxtwitter / /photo/N variants collide.
+    if let Some(key) = x_media::site::cache_key(url)
+        && let Some(cached) = ctx.link_cache.get(&key, ctx.config.link_cache_ttl).await
+    {
+        log::debug!("link cache hit for {key}");
+        let chat_data = ctx.chat_store.get(chat_id).await;
+        // Cache keys are prefixed with the site id ("twitter:…"), matching
+        // the value a fresh fetch would read from Fetched::site_id.
+        let site = x_media::site::site_id_from_key(&key);
+        let format = chat_data
+            .message_format
+            .get(site)
+            .cloned()
+            .unwrap_or_default();
+        let caption = if format.is_empty() {
+            x_media::site::truncate_caption(&cached.caption)
+        } else {
+            x_media::site::caption_from_fields(
+                &format,
+                "",
+                &cached.url,
+                &cached.author,
+                &cached.author_url,
+                &cached.title,
+                &cached.tags,
+            )
+        };
+        let items: Vec<MediaItemPayload> = cached
+            .media
+            .iter()
+            .map(|m| match m.kind {
+                CachedMediaKind::Photo => MediaItemPayload::Photo {
+                    media: m.file_id.clone(),
+                    has_spoiler: cached.sensitive,
+                    fallback_url: None,
+                    file_id: true,
+                },
+                CachedMediaKind::Video => MediaItemPayload::Video {
+                    media: m.file_id.clone(),
+                    has_spoiler: cached.sensitive,
+                    thumbnail: None,
+                    fallback_url: None,
+                    file_id: true,
+                },
+                CachedMediaKind::Animation => MediaItemPayload::Animation {
+                    media: m.file_id.clone(),
+                    has_spoiler: cached.sensitive,
+                    file_id: true,
+                },
+            })
+            .collect();
+        let task = build_send_task(
+            &chat_data,
+            chat_id,
+            reply_to_message_id,
+            cached.url.clone(),
+            caption,
+            items,
+            Some(cached),
+            post_send,
+        );
+        dispatch_send(ctx, chat_id, reply_to, &task, url).await;
+        return;
+    }
+
+    log::debug!("fetching {url} [key={}]", log_key(url));
+    match x_media::site::fetch(url).await {
+        // Unsupported links are ignored silently (Python parity).
+        Ok(None) => {
+            log::debug!("no site pattern matches {url}; ignoring");
+        }
+        // Retries exhausted: notify the user (Rust-only requirement 3).
+        Err(e) => {
+            log::error!("fetch {url}: {e}");
+            let _ = reply(
+                ctx.sender,
+                chat_id,
+                reply_to,
+                "Failed to fetch media from this link.",
+            )
+            .await;
+        }
+        Ok(Some(mut fetched)) => {
+            if fetched.media.is_empty() {
+                let _ = reply(
+                    ctx.sender,
+                    chat_id,
+                    reply_to,
+                    "No media found or media type is not supported.",
+                )
+                .await;
+                return;
+            }
+            let chat_data = ctx.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);
+            // Raw render data for the link cache; the send fills in the
+            // Telegram file ids and persists the entry.
+            let cache_data = fetched
+                .render_fields()
+                .map(|(author, author_url, title, tags)| CachedPost {
+                    url: fetched.source_url.clone(),
+                    caption: fetched.caption.clone(),
+                    title: title.to_string(),
+                    author: author.to_string(),
+                    author_url: author_url.to_string(),
+                    tags: tags.to_string(),
+                    sensitive: fetched.sensitive,
+                    media: vec![],
+                });
+            let items: Vec<MediaItemPayload> = fetched
+                .media
+                .iter()
+                .map(|media| media_to_payload(media, fetched.sensitive))
+                .collect();
+            let task = build_send_task(
+                &chat_data,
+                chat_id,
+                reply_to_message_id,
+                fetched.source_url.clone(),
+                caption,
+                items,
+                cache_data,
+                post_send,
+            );
+            // Hand the keep-alive temp dir (ugoira / bsky remux MP4) to the
+            // retry registry: a queued retry runs after this function returns
+            // and the fetch's own TempDir is dropped, so without this the
+            // local file would be gone by the time the retry sends it.
+            if let Some(dir) = fetched.take_keep_alive() {
+                send::KEEP_ALIVE.lock().push(dir);
+            }
+            dispatch_send(ctx, chat_id, reply_to, &task, url).await;
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::ctx::test_support::TestStores;
+    use crate::link_cache::CachedMedia;
+    use crate::media_sender::test_support::{MockSender, Outcome};
+    use std::time::Duration;
+    use teloxide::{ApiError, RequestError};
+
+    fn permanent_error() -> RequestError {
+        RequestError::Api(ApiError::Unknown(
+            "Bad Request: message is not modified".into(),
+        ))
+    }
+
+    fn cached_photo_entry() -> CachedPost {
+        CachedPost {
+            url: "https://x.com/u/status/1".into(),
+            caption: "cap".into(),
+            title: "t".into(),
+            author: "a".into(),
+            author_url: "au".into(),
+            tags: "".into(),
+            sensitive: false,
+            media: vec![CachedMedia {
+                kind: CachedMediaKind::Photo,
+                file_id: "file-1".into(),
+            }],
+        }
+    }
+
+    #[tokio::test]
+    async fn cache_hit_sends_file_ids_and_invalidates_on_permanent_failure() {
+        let stores = TestStores::new();
+        let sender = MockSender::scripted(
+            vec![Outcome::GroupErr, Outcome::MessageErr],
+            permanent_error,
+        );
+        let ctx = stores.ctx(&sender);
+        stores
+            .link_cache()
+            .put("twitter:1", &cached_photo_entry())
+            .await;
+
+        url_media(&ctx, 1, 2, "https://x.com/u/status/1", PostSend::FromChat).await;
+
+        // The cached file id went out as a group send; the permanent failure
+        // then triggered the fire-and-forget reply (its mock error is fine).
+        assert_eq!(
+            sender.calls(),
+            vec!["send_chat_action", "send_media_group", "send_message"]
+        );
+        // The stale cache entry was invalidated so the next request re-fetches.
+        assert!(
+            stores
+                .link_cache()
+                .get("twitter:1", Duration::from_secs(3600))
+                .await
+                .is_none()
+        );
+    }
+
+    #[tokio::test]
+    async fn cache_hit_success_keeps_the_cache_entry() {
+        let stores = TestStores::new();
+        let sender = MockSender::scripted(vec![Outcome::GroupOk], permanent_error);
+        let ctx = stores.ctx(&sender);
+        stores
+            .link_cache()
+            .put("twitter:1", &cached_photo_entry())
+            .await;
+
+        url_media(&ctx, 1, 2, "https://x.com/u/status/1", PostSend::FromChat).await;
+
+        assert_eq!(sender.calls(), vec!["send_chat_action", "send_media_group"]);
+        // Success must not evict the entry.
+        assert!(
+            stores
+                .link_cache()
+                .get("twitter:1", Duration::from_secs(3600))
+                .await
+                .is_some()
+        );
+    }
+
+    #[tokio::test]
+    async fn unsupported_url_is_ignored_silently() {
+        let stores = TestStores::new();
+        let sender = MockSender::scripted(vec![], permanent_error);
+        let ctx = stores.ctx(&sender);
+
+        // No cache key → the fetch dispatcher returns Ok(None) without any
+        // network; nothing is sent or replied.
+        url_media(
+            &ctx,
+            1,
+            2,
+            "https://example.com/not-a-post",
+            PostSend::FromChat,
+        )
+        .await;
+        assert_eq!(sender.calls(), vec!["send_chat_action"]);
+    }
+
+    // ── Send modes: the URL flow vs `/test` ─────────────────────────────
+
+    /// A chat that has both post-send actions configured.
+    async fn seed_post_send_settings(ctx: &AppContext<'_>) {
+        ctx.chat_store
+            .update(1, |data| {
+                data.forward_channel_id = Some(2);
+                data.edit_before_forward = true;
+            })
+            .await;
+    }
+
+    #[tokio::test]
+    async fn chat_settings_apply_to_the_normal_link_flow() {
+        let stores = TestStores::new();
+        let sender =
+            MockSender::scripted(vec![Outcome::GroupOk, Outcome::MessageOk], permanent_error);
+        let ctx = stores.ctx(&sender);
+        stores
+            .link_cache()
+            .put("twitter:1", &cached_photo_entry())
+            .await;
+        seed_post_send_settings(&ctx).await;
+
+        url_media(&ctx, 1, 2, "https://x.com/u/status/1", PostSend::FromChat).await;
+
+        // Media group, then the edit prompt (edit-before-forward wins over the
+        // channel forward, which only runs once the prompt is confirmed).
+        assert_eq!(
+            sender.calls(),
+            vec!["send_chat_action", "send_media_group", "send_message"]
+        );
+    }
+
+    #[tokio::test]
+    async fn test_mode_sends_the_media_without_forwarding_or_editing() {
+        let stores = TestStores::new();
+        // Only the group send is scripted: any forward (copy_messages) or edit
+        // prompt (send_message) would panic with "unexpected outcome".
+        let sender = MockSender::scripted(vec![Outcome::GroupOk], permanent_error);
+        let ctx = stores.ctx(&sender);
+        stores
+            .link_cache()
+            .put("twitter:1", &cached_photo_entry())
+            .await;
+        seed_post_send_settings(&ctx).await;
+
+        url_media(&ctx, 1, 2, "https://x.com/u/status/1", PostSend::Suppressed).await;
+
+        assert_eq!(sender.calls(), vec!["send_chat_action", "send_media_group"]);
+        // The send is otherwise ordinary: the post stays cached.
+        assert!(
+            stores
+                .link_cache()
+                .get("twitter:1", Duration::from_secs(3600))
+                .await
+                .is_some()
+        );
+    }
+
+    #[test]
+    fn send_mode_decides_whether_chat_actions_ride_along() {
+        let chat = ChatData {
+            forward_channel_id: Some(2),
+            edit_before_forward: true,
+            ..ChatData::default()
+        };
+
+        let with_chat = build_send_task(
+            &chat,
+            1,
+            2,
+            "https://x.com/u/status/1".into(),
+            "cap".into(),
+            vec![],
+            None,
+            PostSend::FromChat,
+        );
+        let Task::SendMediaSequence {
+            edit_before_forward,
+            forward_channel_id,
+            ..
+        } = with_chat
+        else {
+            panic!("expected a media sequence task");
+        };
+        assert!(edit_before_forward);
+        assert_eq!(forward_channel_id, Some(2));
+
+        let suppressed = build_send_task(
+            &chat,
+            1,
+            2,
+            "https://x.com/u/status/1".into(),
+            "cap".into(),
+            vec![],
+            None,
+            PostSend::Suppressed,
+        );
+        let Task::SendMediaSequence {
+            edit_before_forward,
+            forward_channel_id,
+            notify_chat_id,
+            ..
+        } = suppressed
+        else {
+            panic!("expected a media sequence task");
+        };
+        assert!(!edit_before_forward, "`/test` must not open an edit prompt");
+        assert_eq!(forward_channel_id, None, "`/test` must not forward");
+        // Dead-letter notification still reaches the chat that asked.
+        assert_eq!(notify_chat_id, Some(1));
+    }
+}

crates/xmedia-bot/src/link_cache.rs

@@ -5,12 +5,13 @@
 //! key]. A repeated link is then answered entirely from local state — no
 //! re-fetch of the source site, no re-upload — and no media file is stored
 //! on disk (the file ids point at Telegram's servers). Entries expire after
-//! [`Config::link_cache_ttl`]; a stale entry is dropped lazily on read and
+//! `Config::link_cache_ttl`; a stale entry is dropped lazily on read and
 //! by the periodic prune in `main`.
 
 use crate::db::now_f64;
-use rusqlite::{Connection, params};
+use rusqlite::params;
 use serde::{Deserialize, Serialize};
+use std::sync::Arc;
 use std::time::Duration;
 
 #[derive(Serialize, Deserialize, Clone, Debug, PartialEq)]
@@ -45,24 +46,16 @@ pub struct CachedPost {
 }
 
 /// SQLite-backed cache sharing `data/task_queue.db` with the queue and chat
-/// state (same `open_db` pattern: busy timeout, `spawn_blocking` I/O).
+/// state (same shared pool, see [`crate::db::open_store`]).
 pub struct LinkCache {
-    pool: crate::db::DbPool,
+    pool: Arc<crate::db::DbPool>,
 }
 
 impl LinkCache {
-    pub fn open(db_path: &str) -> Self {
-        if let Ok(conn) = Connection::open(db_path)
-            && let Err(e) = conn.execute_batch(
-                "CREATE TABLE IF NOT EXISTS link_cache (url TEXT PRIMARY KEY, \
-                 payload TEXT NOT NULL, created_at REAL NOT NULL);",
-            )
-        {
-            log::error!("failed to initialize link cache schema: {e}");
-        }
-        Self {
-            pool: crate::db::DbPool::new(db_path),
-        }
+    /// Wraps the shared DB pool (the `link_cache` table lives in the merged
+    /// schema alongside `tasks` and `chat_state`).
+    pub fn new(pool: Arc<crate::db::DbPool>) -> Self {
+        LinkCache { pool }
     }
 
     /// Returns the cached post if present and not expired; a stale entry is
@@ -85,9 +78,15 @@ impl LinkCache {
                     conn.execute("DELETE FROM link_cache WHERE url = ?1", params![key])?;
                     return Ok(None);
                 }
-                Ok(Some(serde_json::from_str::<CachedPost>(&payload).map_err(
-                    |e| rusqlite::Error::ToSqlConversionFailure(Box::new(e)),
-                )?))
+                match serde_json::from_str::<CachedPost>(&payload) {
+                    Ok(post) => Ok(Some(post)),
+                    Err(e) => {
+                        // Unreadable payload (e.g. an older schema): drop it
+                        // instead of re-failing the parse on every later hit.
+                        conn.execute("DELETE FROM link_cache WHERE url = ?1", params![key])?;
+                        Err(rusqlite::Error::ToSqlConversionFailure(Box::new(e)))
+                    }
+                }
             })
             .await;
         match result {
@@ -197,7 +196,9 @@ mod tests {
     #[tokio::test]
     async fn put_get_roundtrip() {
         let dir = tempfile::tempdir().unwrap();
-        let cache = LinkCache::open(dir.path().join("c.db").to_str().unwrap());
+        let cache = LinkCache::new(
+            crate::db::open_store(dir.path().join("c.db").to_str().unwrap()).unwrap(),
+        );
         cache.put("twitter:1", &entry()).await;
         let got = cache.get("twitter:1", Duration::from_secs(3600)).await;
         assert!(got.is_some());
@@ -209,11 +210,13 @@ mod tests {
     #[tokio::test]
     async fn expired_entry_removed_on_read() {
         let dir = tempfile::tempdir().unwrap();
-        let cache = LinkCache::open(dir.path().join("c.db").to_str().unwrap());
+        let cache = LinkCache::new(
+            crate::db::open_store(dir.path().join("c.db").to_str().unwrap()).unwrap(),
+        );
         cache.put("twitter:1", &entry()).await;
         // Force the row into the past so a 1s TTL expires it.
         {
-            let conn = Connection::open(dir.path().join("c.db")).unwrap();
+            let conn = rusqlite::Connection::open(dir.path().join("c.db")).unwrap();
             conn.execute("UPDATE link_cache SET created_at = created_at - 100", [])
                 .unwrap();
         }
@@ -231,10 +234,38 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn unreadable_entry_is_dropped_on_read() {
+        // A payload from an older schema must not be re-parsed on every hit:
+        // the row is removed and the read reports a miss.
+        let dir = tempfile::tempdir().unwrap();
+        let db_path = dir.path().join("c.db");
+        let cache = LinkCache::new(crate::db::open_store(db_path.to_str().unwrap()).unwrap());
+        {
+            let conn = rusqlite::Connection::open(&db_path).unwrap();
+            conn.execute(
+                "INSERT INTO link_cache (url, payload, created_at) VALUES (?1, ?2, ?3)",
+                params!["twitter:1", "{not json", now_f64()],
+            )
+            .unwrap();
+        }
+
+        assert!(
+            cache
+                .get("twitter:1", Duration::from_secs(3600))
+                .await
+                .is_none()
+        );
+        // Dropped, not left behind for the next hit.
+        assert_eq!(cache.clear(None).await, 0, "corrupted row still present");
+    }
+
     #[tokio::test]
     async fn remove_and_prune() {
         let dir = tempfile::tempdir().unwrap();
-        let cache = LinkCache::open(dir.path().join("c.db").to_str().unwrap());
+        let cache = LinkCache::new(
+            crate::db::open_store(dir.path().join("c.db").to_str().unwrap()).unwrap(),
+        );
         cache.put("twitter:1", &entry()).await;
         cache.put("pixiv:2", &entry()).await;
         cache.remove("twitter:1").await;
@@ -251,7 +282,7 @@ mod tests {
                 .is_some()
         );
         {
-            let conn = Connection::open(dir.path().join("c.db")).unwrap();
+            let conn = rusqlite::Connection::open(dir.path().join("c.db")).unwrap();
             conn.execute("UPDATE link_cache SET created_at = created_at - 100", [])
                 .unwrap();
         }
@@ -267,7 +298,9 @@ mod tests {
     #[tokio::test]
     async fn clear_one_entry_or_all() {
         let dir = tempfile::tempdir().unwrap();
-        let cache = LinkCache::open(dir.path().join("c.db").to_str().unwrap());
+        let cache = LinkCache::new(
+            crate::db::open_store(dir.path().join("c.db").to_str().unwrap()).unwrap(),
+        );
         cache.put("twitter:1", &entry()).await;
         cache.put("pixiv:2", &entry()).await;
         // By key: only the matching row is removed.

crates/xmedia-bot/src/main.rs

@@ -8,14 +8,18 @@ use tokio::sync::watch;
 use x_media::site;
 
 mod config;
+mod ctx;
 mod db;
 mod handlers;
 mod link_cache;
+mod media_sender;
 mod photo;
 mod queue;
+mod rate_limit;
 mod send;
 mod state;
 
+use ctx::CONTEXT;
 use handlers::{CHAT_STORE, CONFIG, LINK_CACHE, TASK_QUEUE};
 
 /// Docker `stop` / `compose down` delivers SIGTERM, which teloxide's ctrlc
@@ -59,9 +63,13 @@ async fn main() {
     );
 
     // Queue worker: handles typed tasks, dead-letters failed sends to the
-    // task's chat.
+    // task's chat. Both closures use the shared context (the queue requires
+    // 'static handlers, and the statics are process-wide anyway).
     TASK_QUEUE
-        .start(send::handle_task, send::dead_letter_notify)
+        .start(
+            |payload| send::handle_task(&CONTEXT, payload),
+            |payload, message| send::dead_letter_notify(&CONTEXT, payload, message),
+        )
         .await;
     log::info!("task queue worker started");
 
@@ -69,19 +77,18 @@ async fn main() {
     handlers::start_url_workers().await;
     log::info!("url workers 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();
+    // Site login validation (user request): a failed login notifies the
+    // admin and the site disables itself for this process (pixiv).
+    let failures = site::validate_all().await;
+    if failures.is_empty() {
+        log::info!("site logins validated");
+    } else {
+        for (site_id, message) in &failures {
+            log::error!("{site_id} login failed: {message}");
+            if let Some(admin) = CONFIG.admin_ids.first() {
+                let _ = bot
+                    .send_message(ChatId(*admin), format!("{site_id} login failed: {message}"))
+                    .await;
             }
         }
     }
@@ -107,6 +114,10 @@ async fn main() {
                 if pruned > 0 {
                     log::info!("link cache: pruned {pruned} expired entr(ies)");
                 }
+                let idle_limiters = crate::rate_limit::prune_idle();
+                if idle_limiters > 0 {
+                    log::debug!("rate limiter: dropped {idle_limiters} idle bucket(s)");
+                }
                 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.
@@ -185,7 +196,7 @@ async fn main() {
     const SHUTDOWN_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(30);
     let shutdown = async {
         let _ = stop_tx.send(true);
-        handlers::stop_url_workers();
+        handlers::stop_url_workers().await;
         if let Some(admin) = CONFIG.admin_ids.first() {
             let _ = bot.send_message(ChatId(*admin), "Shutting down...").await;
         }

crates/xmedia-bot/src/media_sender.rs

@@ -0,0 +1,442 @@
+//! Send abstraction: the message-sending surface [`send`](crate::send)
+//! needs, so the send pipeline can be tested with a scripted mock instead of
+//! a live teloxide `Bot`.
+
+use std::future::Future;
+use std::pin::Pin;
+use teloxide::RequestError;
+use teloxide::prelude::Requester;
+use teloxide::prelude::*;
+use teloxide::types::{
+    CallbackQueryId, ChatAction, ChatId, InlineKeyboardMarkup, InputFile, InputMedia, Message,
+    MessageId, ParseMode, ReplyParameters,
+};
+
+/// Boxed, `Send` future returned by a [`MediaSender`] method (`async fn` in
+/// traits is not dyn-compatible).
+type BoxFuture<'a, T> = Pin<Box<dyn Future<Output = T> + Send + 'a>>;
+
+/// The message-sending surface the send pipeline uses. The production
+/// implementation is teloxide's [`Bot`]; tests inject a scripted mock to
+/// cover the fallback and classification logic without touching the
+/// Telegram API.
+pub trait MediaSender: Send + Sync {
+    /// Sends a media group, replying to `reply_to`.
+    fn send_media_group(
+        &self,
+        chat_id: ChatId,
+        reply_to: MessageId,
+        items: Vec<InputMedia>,
+    ) -> BoxFuture<'_, Result<Vec<Message>, RequestError>>;
+
+    /// Sends a lone animation, replying to `reply_to`.
+    fn send_animation<'a>(
+        &'a self,
+        chat_id: ChatId,
+        reply_to: MessageId,
+        caption: &'a str,
+        spoiler: bool,
+        file: InputFile,
+    ) -> BoxFuture<'a, Result<Message, RequestError>>;
+
+    /// Copies messages between chats (forward to channel).
+    fn copy_messages(
+        &self,
+        to: ChatId,
+        from: ChatId,
+        ids: Vec<MessageId>,
+    ) -> BoxFuture<'_, Result<Vec<MessageId>, RequestError>>;
+
+    /// Sends a plain text message, optionally replying to `reply_to` and
+    /// attaching `reply_markup`. Returns the sent message's id: the bot only
+    /// ever needs that (the edit-before-forward prompt's record is keyed by
+    /// it), and returning the whole `Message` would force every test mock to
+    /// construct one.
+    fn send_message(
+        &self,
+        chat_id: ChatId,
+        text: String,
+        reply_to: Option<MessageId>,
+        reply_markup: Option<InlineKeyboardMarkup>,
+    ) -> BoxFuture<'_, Result<i64, RequestError>>;
+
+    /// Answers a callback query, optionally with a toast `text` shown to the
+    /// user who pressed the button.
+    fn answer_callback_query(
+        &self,
+        id: CallbackQueryId,
+        text: Option<String>,
+    ) -> BoxFuture<'_, Result<(), RequestError>>;
+
+    /// Rewrites a message's caption, always with HTML parse mode (every caller
+    /// in this bot renders escaped HTML: templates and edit-before-forward
+    /// links).
+    fn edit_message_caption(
+        &self,
+        chat_id: ChatId,
+        message_id: MessageId,
+        caption: String,
+    ) -> BoxFuture<'_, Result<(), RequestError>>;
+
+    /// Deletes a message (the edit-before-forward prompt after a forward).
+    fn delete_message(
+        &self,
+        chat_id: ChatId,
+        message_id: MessageId,
+    ) -> BoxFuture<'_, Result<(), RequestError>>;
+
+    /// Sets the chat's "typing / uploading …" indicator (cosmetic).
+    fn send_chat_action(
+        &self,
+        chat_id: ChatId,
+        action: ChatAction,
+    ) -> BoxFuture<'_, Result<(), RequestError>>;
+}
+
+impl MediaSender for Bot {
+    fn send_media_group(
+        &self,
+        chat_id: ChatId,
+        reply_to: MessageId,
+        items: Vec<InputMedia>,
+    ) -> BoxFuture<'_, Result<Vec<Message>, RequestError>> {
+        Box::pin(async move {
+            // Pace media sends per chat (one token per item) so bursts do not
+            // trip Telegram's flood control.
+            crate::rate_limit::limiter_for(chat_id.0)
+                .acquire(items.len() as f64)
+                .await;
+            // `<Bot as Requester>::` disambiguates from this trait's same-named
+            // method (teloxide's API lives in the `Requester` trait).
+            <Bot as Requester>::send_media_group(self, chat_id, items)
+                .reply_parameters(ReplyParameters::new(reply_to).allow_sending_without_reply())
+                .await
+        })
+    }
+
+    fn send_animation<'a>(
+        &'a self,
+        chat_id: ChatId,
+        reply_to: MessageId,
+        caption: &'a str,
+        spoiler: bool,
+        file: InputFile,
+    ) -> BoxFuture<'a, Result<Message, RequestError>> {
+        Box::pin(async move {
+            crate::rate_limit::limiter_for(chat_id.0).acquire(1.0).await;
+            let mut request = <Bot as Requester>::send_animation(self, chat_id, file)
+                .caption(caption)
+                .parse_mode(ParseMode::Html)
+                .reply_parameters(ReplyParameters::new(reply_to).allow_sending_without_reply());
+            if spoiler {
+                request = request.has_spoiler(true);
+            }
+            request.await
+        })
+    }
+
+    fn copy_messages(
+        &self,
+        to: ChatId,
+        from: ChatId,
+        ids: Vec<MessageId>,
+    ) -> BoxFuture<'_, Result<Vec<MessageId>, RequestError>> {
+        Box::pin(async move {
+            // Channel forwards are the burstiest path (batch copies); pace
+            // them per message against the channel's budget.
+            crate::rate_limit::limiter_for(to.0)
+                .acquire(ids.len() as f64)
+                .await;
+            <Bot as Requester>::copy_messages(self, to, from, ids).await
+        })
+    }
+
+    fn send_message(
+        &self,
+        chat_id: ChatId,
+        text: String,
+        reply_to: Option<MessageId>,
+        reply_markup: Option<InlineKeyboardMarkup>,
+    ) -> BoxFuture<'_, Result<i64, RequestError>> {
+        Box::pin(async move {
+            let mut request = <Bot as Requester>::send_message(self, chat_id, text);
+            if let Some(reply_to) = reply_to {
+                request = request
+                    .reply_parameters(ReplyParameters::new(reply_to).allow_sending_without_reply());
+            }
+            if let Some(markup) = reply_markup {
+                request = request.reply_markup(markup);
+            }
+            request.await.map(|message| message.id.0 as i64)
+        })
+    }
+
+    fn answer_callback_query(
+        &self,
+        id: CallbackQueryId,
+        text: Option<String>,
+    ) -> BoxFuture<'_, Result<(), RequestError>> {
+        Box::pin(async move {
+            let mut request = <Bot as Requester>::answer_callback_query(self, id);
+            if let Some(text) = text {
+                request = request.text(text);
+            }
+            request.await.map(|_| ())
+        })
+    }
+
+    fn edit_message_caption(
+        &self,
+        chat_id: ChatId,
+        message_id: MessageId,
+        caption: String,
+    ) -> BoxFuture<'_, Result<(), RequestError>> {
+        Box::pin(async move {
+            <Bot as Requester>::edit_message_caption(self, chat_id, message_id)
+                .caption(caption)
+                .parse_mode(ParseMode::Html)
+                .await
+                .map(|_| ())
+        })
+    }
+
+    fn delete_message(
+        &self,
+        chat_id: ChatId,
+        message_id: MessageId,
+    ) -> BoxFuture<'_, Result<(), RequestError>> {
+        Box::pin(async move {
+            <Bot as Requester>::delete_message(self, chat_id, message_id)
+                .await
+                .map(|_| ())
+        })
+    }
+
+    fn send_chat_action(
+        &self,
+        chat_id: ChatId,
+        action: ChatAction,
+    ) -> BoxFuture<'_, Result<(), RequestError>> {
+        Box::pin(async move {
+            // teloxide's `send_chat_action` returns `Result<True, _>` (its
+            // unit marker type); map the success to `()`.
+            <Bot as Requester>::send_chat_action(self, chat_id, action)
+                .await
+                .map(|_| ())
+        })
+    }
+}
+
+/// Test support: a scripted [`MediaSender`] mock (no Telegram API involved).
+#[cfg(test)]
+pub(crate) mod test_support {
+    use super::*;
+    use parking_lot::Mutex;
+
+    /// One scripted outcome, consumed front-to-back; the last entry repeats
+    /// for further calls of the same method kind.
+    #[derive(Clone, Copy, Debug, PartialEq, Eq)]
+    pub(crate) enum Outcome {
+        GroupOk,
+        GroupErr,
+        AnimationErr,
+        CopyOk,
+        CopyErr,
+        /// An error from `send_message` (replies are fire-and-forget, so an
+        /// error is fine for tests).
+        MessageErr,
+        /// A successful `send_message`, returning message id [`MockSender::SENT_ID`].
+        MessageOk,
+        EditOk,
+        EditErr,
+    }
+
+    /// Replays a script and records what was sent, so tests can assert the
+    /// user-visible text a path produced.
+    pub(crate) struct MockSender {
+        script: Mutex<Vec<Outcome>>,
+        cursor: Mutex<usize>,
+        calls: Mutex<Vec<&'static str>>,
+        messages: Mutex<Vec<String>>,
+        captions: Mutex<Vec<String>>,
+        answers: Mutex<Vec<Option<String>>>,
+        /// Builds the error every `*Err` outcome returns (RequestError is not
+        /// cloneable, so the factory recreates it per call).
+        error: Box<dyn Fn() -> RequestError + Send + Sync>,
+    }
+
+    impl MockSender {
+        /// The message id a successful `send_message` reports.
+        pub(crate) const SENT_ID: i64 = 1;
+
+        pub(crate) fn scripted(
+            script: Vec<Outcome>,
+            error: impl Fn() -> RequestError + Send + Sync + 'static,
+        ) -> Self {
+            MockSender {
+                script: Mutex::new(script),
+                cursor: Mutex::new(0),
+                calls: Mutex::new(Vec::new()),
+                messages: Mutex::new(Vec::new()),
+                captions: Mutex::new(Vec::new()),
+                answers: Mutex::new(Vec::new()),
+                error: Box::new(error),
+            }
+        }
+
+        /// Method names in call order (e.g. `["send_media_group",
+        /// "send_media_group"]` proves the fallback re-sent).
+        pub(crate) fn calls(&self) -> Vec<&'static str> {
+            self.calls.lock().clone()
+        }
+
+        /// Texts of the plain messages sent, in order.
+        pub(crate) fn messages(&self) -> Vec<String> {
+            self.messages.lock().clone()
+        }
+
+        /// Captions passed to `edit_message_caption`, in order.
+        pub(crate) fn captions(&self) -> Vec<String> {
+            self.captions.lock().clone()
+        }
+
+        /// Toast texts of the answered callback queries, in order.
+        pub(crate) fn answers(&self) -> Vec<Option<String>> {
+            self.answers.lock().clone()
+        }
+
+        fn next(&self, kind: &'static str) -> Outcome {
+            self.calls.lock().push(kind);
+            let script = self.script.lock();
+            let mut cursor = self.cursor.lock();
+            if script.is_empty() {
+                panic!("mock script exhausted: {kind}");
+            }
+            let idx = (*cursor).min(script.len() - 1);
+            *cursor = idx + 1;
+            script[idx]
+        }
+
+        fn error(&self) -> RequestError {
+            (self.error)()
+        }
+    }
+
+    impl MediaSender for MockSender {
+        fn send_media_group(
+            &self,
+            _chat_id: ChatId,
+            _reply_to: MessageId,
+            _items: Vec<InputMedia>,
+        ) -> BoxFuture<'_, Result<Vec<Message>, RequestError>> {
+            Box::pin(async move {
+                match self.next("send_media_group") {
+                    Outcome::GroupOk => Ok(Vec::new()),
+                    Outcome::GroupErr => Err(self.error()),
+                    other => panic!("unexpected outcome {other:?} for send_media_group"),
+                }
+            })
+        }
+
+        fn send_animation<'a>(
+            &'a self,
+            _chat_id: ChatId,
+            _reply_to: MessageId,
+            _caption: &'a str,
+            _spoiler: bool,
+            _file: InputFile,
+        ) -> BoxFuture<'a, Result<Message, RequestError>> {
+            Box::pin(async move {
+                match self.next("send_animation") {
+                    Outcome::AnimationErr => Err(self.error()),
+                    other => panic!("unexpected outcome {other:?} for send_animation"),
+                }
+            })
+        }
+
+        fn copy_messages(
+            &self,
+            _to: ChatId,
+            _from: ChatId,
+            _ids: Vec<MessageId>,
+        ) -> BoxFuture<'_, Result<Vec<MessageId>, RequestError>> {
+            Box::pin(async move {
+                match self.next("copy_messages") {
+                    Outcome::CopyOk => Ok(vec![MessageId(1)]),
+                    Outcome::CopyErr => Err(self.error()),
+                    other => panic!("unexpected outcome {other:?} for copy_messages"),
+                }
+            })
+        }
+
+        fn send_message(
+            &self,
+            _chat_id: ChatId,
+            text: String,
+            _reply_to: Option<MessageId>,
+            _reply_markup: Option<InlineKeyboardMarkup>,
+        ) -> BoxFuture<'_, Result<i64, RequestError>> {
+            Box::pin(async move {
+                self.messages.lock().push(text);
+                match self.next("send_message") {
+                    Outcome::MessageOk => Ok(MockSender::SENT_ID),
+                    Outcome::MessageErr => Err(self.error()),
+                    other => panic!("unexpected outcome {other:?} for send_message"),
+                }
+            })
+        }
+
+        fn answer_callback_query(
+            &self,
+            _id: CallbackQueryId,
+            text: Option<String>,
+        ) -> BoxFuture<'_, Result<(), RequestError>> {
+            // Always succeeds: the toast is cosmetic, so the script stays
+            // focused on the outcomes a test cares about.
+            Box::pin(async move {
+                self.calls.lock().push("answer_callback_query");
+                self.answers.lock().push(text);
+                Ok(())
+            })
+        }
+
+        fn edit_message_caption(
+            &self,
+            _chat_id: ChatId,
+            _message_id: MessageId,
+            caption: String,
+        ) -> BoxFuture<'_, Result<(), RequestError>> {
+            Box::pin(async move {
+                self.captions.lock().push(caption);
+                match self.next("edit_message_caption") {
+                    Outcome::EditOk => Ok(()),
+                    Outcome::EditErr => Err(self.error()),
+                    other => panic!("unexpected outcome {other:?} for edit_message_caption"),
+                }
+            })
+        }
+
+        fn delete_message(
+            &self,
+            _chat_id: ChatId,
+            _message_id: MessageId,
+        ) -> BoxFuture<'_, Result<(), RequestError>> {
+            // Deletion is fire-and-forget in every caller; always succeeds.
+            Box::pin(async move {
+                self.calls.lock().push("delete_message");
+                Ok(())
+            })
+        }
+
+        fn send_chat_action(
+            &self,
+            _chat_id: ChatId,
+            _action: ChatAction,
+        ) -> BoxFuture<'_, Result<(), RequestError>> {
+            Box::pin(async move {
+                self.calls.lock().push("send_chat_action");
+                Ok(())
+            })
+        }
+    }
+}

crates/xmedia-bot/src/photo.rs

@@ -122,7 +122,7 @@ fn output_channels(color: png::ColorType) -> usize {
 /// white; 16-bit per channel was already stripped to 8-bit at decode.
 fn flatten_rgba_to_rgb(rgba: &[u8]) -> Vec<u8> {
     let mut rgb = Vec::with_capacity(rgba.len() / 4 * 3);
-    for px in rgba.chunks_exact(4) {
+    for px in rgba.as_chunks::<4>().0 {
         let a = px[3] as u32;
         for v in &px[..3] {
             // Over white: C = C*a/255 + 255*(1 - a/255).
@@ -178,7 +178,9 @@ fn encode_jpeg(pix: &PixBuf, w: u32, h: u32) -> Result<Vec<u8>, String> {
         PixBuf::GrayAlpha(v) => {
             // JPEG has no alpha: composite onto white, output as gray.
             let gray: Vec<u8> = v
-                .chunks_exact(2)
+                .as_chunks::<2>()
+                .0
+                .iter()
                 .map(|px| {
                     let (g, a) = (px[0] as u32, px[1] as u32);
                     ((g * a + 255 * (255 - a)) / 255).min(255) as u8
@@ -223,7 +225,7 @@ fn prepare_png(file: NamedTempFile, bytes: &[u8]) -> Result<PhotoPrep, String> {
     if w + h <= PHOTO_MAX_DIMENSION_SUM && !size_over {
         return Ok(PhotoPrep::Upload(file));
     }
-    log::info!(
+    log::debug!(
         "photo {w}x{h} ({_bit_depth:?} {color_type:?}, {} bytes) needs processing",
         bytes.len()
     );
@@ -269,7 +271,7 @@ fn prepare_png(file: NamedTempFile, bytes: &[u8]) -> Result<PhotoPrep, String> {
         let (nw, nh) = target_dims(w, h);
         pix = resize_pix(pix, w, h, nw, nh)?;
         (w, h) = (nw, nh);
-        log::info!("downscaled photo to {w}x{h} (Lanczos3)");
+        log::debug!("downscaled photo to {w}x{h} (Lanczos3)");
     }
 
     let mut png_bytes = Vec::new();
@@ -277,7 +279,7 @@ fn prepare_png(file: NamedTempFile, bytes: &[u8]) -> Result<PhotoPrep, String> {
     if png_bytes.len() as u64 <= MAX_UPLOAD_BYTES {
         return Ok(PhotoPrep::Upload(write_temp(&png_bytes, "png")?));
     }
-    log::info!("PNG still over the upload cap after processing; transcoding to JPEG");
+    log::debug!("PNG still over the upload cap after processing; transcoding to JPEG");
     let jpeg_bytes = encode_jpeg(&pix, w, h)?;
     if jpeg_bytes.len() as u64 <= MAX_UPLOAD_BYTES {
         return Ok(PhotoPrep::Upload(write_temp(&jpeg_bytes, "jpg")?));
@@ -311,7 +313,7 @@ fn prepare_jpeg(file: NamedTempFile, bytes: &[u8]) -> Result<PhotoPrep, String>
         let (nw, nh) = target_dims(w, h);
         pix = resize_pix(pix, w, h, nw, nh)?;
         (w, h) = (nw, nh);
-        log::info!("downscaled jpeg to {w}x{h} (Lanczos3)");
+        log::debug!("downscaled jpeg to {w}x{h} (Lanczos3)");
     }
     let jpeg_bytes = encode_jpeg(&pix, w, h)?;
     if jpeg_bytes.len() as u64 <= MAX_UPLOAD_BYTES {

crates/xmedia-bot/src/queue.rs

@@ -7,7 +7,7 @@
 
 use crate::db::now_f64;
 use parking_lot::Mutex;
-use rusqlite::{Connection, TransactionBehavior, params};
+use rusqlite::{TransactionBehavior, params};
 use serde_json::Value;
 use std::pin::Pin;
 use std::sync::Arc;
@@ -41,7 +41,13 @@ type DeadLetter = dyn Fn(Value, String) -> BoxFuture<'static, ()> + Send + Sync;
 
 pub struct PersistentTaskQueue {
     pool: std::sync::Arc<crate::db::DbPool>,
+    /// Wakes the workers when a row becomes leasable. `notify_one` stores a
+    /// permit, so nothing else may share it: a waiter that is not a worker
+    /// (the sweep) can consume the permit and leave the due row pending until
+    /// the next enqueue.
     notify: Arc<Notify>,
+    /// Wakes the lease-expiry sweep; `stop` is the only producer.
+    sweep_notify: Arc<Notify>,
     stop: Arc<AtomicBool>,
     worker: Mutex<Vec<JoinHandle<()>>>,
     counter: AtomicU64,
@@ -81,35 +87,14 @@ fn scaled_retry_delay(base: f64, attempts: i32) -> f64 {
     (base * 2f64.powi(attempts)).min(300.0)
 }
 
-fn ensure_schema(conn: &rusqlite::Connection) -> rusqlite::Result<()> {
-    conn.execute_batch(
-        "PRAGMA journal_mode=WAL; \
-         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 INDEX IF NOT EXISTS idx_tasks_pending ON tasks(status, run_after);",
-    )
-}
-
 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}");
-        }
+    /// Wraps the shared DB pool; the schema is initialized once by
+    /// [`crate::db::open_store`] (all three stores share the pool).
+    pub fn new(pool: std::sync::Arc<crate::db::DbPool>) -> Self {
         Self {
-            pool: std::sync::Arc::new(crate::db::DbPool::new(db_path)),
+            pool,
             notify: Arc::new(Notify::new()),
+            sweep_notify: Arc::new(Notify::new()),
             stop: Arc::new(AtomicBool::new(false)),
             worker: Mutex::new(Vec::new()),
             counter: AtomicU64::new(0),
@@ -141,12 +126,12 @@ impl PersistentTaskQueue {
             handles.push(tokio::spawn(worker.run_loop_supervised()));
         }
         // Periodic lease-expiry sweep: recovers rows a crashed/panicked
-        // worker left `in_progress` (the lock TTL bounds the wait). Woken by
-        // the same notify as the workers, so enqueue and stop interrupt the
-        // sleep; the first interval tick fires immediately (harmless extra
-        // recovery at startup).
+        // worker left `in_progress` (the lock TTL bounds the wait). Its own
+        // notify (not the workers'): sharing that one let this task consume a
+        // `notify_one` permit meant for a worker, which then slept through a
+        // due row until some later event. Only `stop` wakes it.
         let sweep_pool = std::sync::Arc::clone(&self.pool);
-        let sweep_notify = Arc::clone(&self.notify);
+        let sweep_notify = Arc::clone(&self.sweep_notify);
         let sweep_stop = Arc::clone(&self.stop);
         handles.push(tokio::spawn(async move {
             let mut interval = tokio::time::interval(Duration::from_secs(30));
@@ -172,6 +157,7 @@ impl PersistentTaskQueue {
     pub async fn stop(&self) {
         self.stop.store(true, Ordering::Relaxed);
         self.notify.notify_waiters();
+        self.sweep_notify.notify_waiters();
         let handles = std::mem::take(&mut *self.worker.lock());
         for handle in handles {
             let _ = handle.await;
@@ -188,7 +174,7 @@ impl PersistentTaskQueue {
             self.counter.fetch_add(1, Ordering::Relaxed)
         );
         let payload = payload.to_string();
-        log::info!("enqueued {id} (run_after {run_after:.1})");
+        log::debug!("enqueued {id} (run_after {run_after:.1})");
         self.pool.with_conn(move |conn| {
             conn.execute(
                 "INSERT OR REPLACE INTO tasks (id, payload, run_after, attempts, status, locked_until, created_at) \
@@ -329,6 +315,11 @@ impl QueueWorker {
         }
     }
 
+    /// Processes one leased row, keeping the lease alive while the handler
+    /// runs. Without the heartbeat a task longer than [`LOCK_TTL_SECONDS`]
+    /// (slow download, ugoira encode, rate-limited batch forward) would have
+    /// its lease expire mid-run; the expiry sweep would flip the row back to
+    /// `pending` and another worker would process it again — duplicate sends.
     async fn process(&self, row: LeasedRow) {
         let payload: Value = match serde_json::from_str(&row.payload) {
             Ok(value) => value,
@@ -339,10 +330,11 @@ impl QueueWorker {
                 return;
             }
         };
-        log::info!("processing {} (attempt {})", row.id, row.attempts + 1);
-        match (self.handler)(payload).await {
+        log::debug!("processing {} (attempt {})", row.id, row.attempts + 1);
+        let outcome = self.run_with_lease(&row.id, payload).await;
+        match outcome {
             Ok(()) => {
-                log::info!("task {} completed", row.id);
+                log::debug!("task {} completed", row.id);
                 self.delete_row(&row.id).await;
             }
             Err(QueueError::Retryable {
@@ -356,7 +348,7 @@ impl QueueWorker {
                     (self.dead_letter)(payload, message).await;
                 } else {
                     let delay = scaled_retry_delay(delay_seconds, row.attempts);
-                    log::info!(
+                    log::debug!(
                         "task {} rescheduled in {delay:.1}s (attempt {})",
                         row.id,
                         row.attempts + 1
@@ -373,6 +365,42 @@ impl QueueWorker {
         }
     }
 
+    /// Drives the handler to completion, refreshing the row's `locked_until`
+    /// every 30 s so the expiry sweep never re-leases a still-running task.
+    /// The heartbeat is part of this future, not a separate spawned task: if
+    /// the worker task dies (panic) the heartbeat dies with it and the sweep
+    /// recovers the row exactly as before.
+    async fn run_with_lease(&self, id: &str, payload: Value) -> Result<(), QueueError> {
+        let fut = (self.handler)(payload);
+        tokio::pin!(fut);
+        let mut interval = tokio::time::interval(Duration::from_secs(30));
+        // The first interval tick fires immediately; skip it (the lease was
+        // just set by lease_next).
+        interval.tick().await;
+        let id_owned = id.to_string();
+        loop {
+            tokio::select! {
+                result = &mut fut => return result,
+                _ = interval.tick() => {
+                    let now = now_f64();
+                    let id = id_owned.clone();
+                    let result = self
+                        .pool
+                        .with_conn(move |conn| {
+                            conn.execute(
+                                "UPDATE tasks SET locked_until=?1 WHERE id=?2 AND status='in_progress'",
+                                params![now + LOCK_TTL_SECONDS, id],
+                            )
+                        })
+                        .await;
+                    if let Err(e) = result {
+                        log::error!("queue lease heartbeat failed: {e}");
+                    }
+                }
+            }
+        }
+    }
+
     async fn delete_row(&self, id: &str) {
         let id = id.to_string();
         let result = self
@@ -424,7 +452,8 @@ mod tests {
     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());
+        let pool = crate::db::open_store(path.to_str().unwrap()).unwrap();
+        let queue = PersistentTaskQueue::new(pool);
         (queue, dir)
     }
 
@@ -531,10 +560,11 @@ mod tests {
     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).
+        // Insert a stale leased row directly (lease expired). open_store runs
+        // the schema; the queue below shares the same pool.
+        let pool = crate::db::open_store(path.to_str().unwrap()).unwrap();
         {
-            let conn = Connection::open(&path).unwrap();
-            ensure_schema(&conn).unwrap();
+            let conn = rusqlite::Connection::open(&path).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)",
@@ -542,7 +572,7 @@ mod tests {
             )
             .unwrap();
         }
-        let queue = PersistentTaskQueue::new(path.to_str().unwrap());
+        let queue = PersistentTaskQueue::new(pool);
         let calls = Arc::new(AtomicUsize::new(0));
         let c = calls.clone();
         queue
@@ -578,8 +608,7 @@ mod tests {
         // Insert a stale leased row AFTER startup: without a runtime sweep it
         // would stay `in_progress` forever (only start() used to recover).
         {
-            let conn = Connection::open(queue.pool.path()).unwrap();
-            ensure_schema(&conn).unwrap();
+            let conn = rusqlite::Connection::open(queue.pool.path()).unwrap();
             conn.execute(
                 "INSERT INTO tasks (id, payload, run_after, attempts, status, locked_until, created_at) \
                  VALUES ('task_stale_runtime', '{\"s\":1}', 0, 0, 'in_progress', ?1, 0)",

crates/xmedia-bot/src/rate_limit.rs

@@ -0,0 +1,184 @@
+//! Per-chat token-bucket rate limiting.
+//!
+//! Telegram throttles bots that burst past a chat's message budget
+//! (roughly 20 messages/min for channels/groups); today the bot absorbs
+//! those 429s with queue retries. This limiter smooths the burst *before*
+//! it reaches the API: media sends to a chat consume one token per
+//! message, refilled at [`REFILL_PER_SEC`], so a batch forward paces itself
+//! instead of tripping flood control. The queue retry stays as the safety
+//! net for limits this bucket does not model (global per-bot limits etc.).
+
+use parking_lot::Mutex;
+use std::collections::HashMap;
+use std::sync::Arc;
+use std::sync::LazyLock;
+use std::time::Duration;
+
+/// Burst capacity: how many messages may be sent at once without waiting.
+const CAPACITY: f64 = 20.0;
+/// Sustained refill: ~20 messages per minute.
+const REFILL_PER_SEC: f64 = 20.0 / 60.0;
+
+struct State {
+    /// Current token balance; may go negative (debt from an acquire larger
+    /// than the capacity, repaid by subsequent refills).
+    tokens: f64,
+    last_refill: tokio::time::Instant,
+}
+
+/// A token bucket: at most `CAPACITY` tokens accumulate, refilled at
+/// `REFILL_PER_SEC`. [`TokenBucket::acquire`] consumes `n` tokens, waiting
+/// for the deficit (a single acquire may exceed the capacity and goes into
+/// debt, which the refill repays).
+pub struct TokenBucket {
+    capacity: f64,
+    refill_per_sec: f64,
+    state: Mutex<State>,
+}
+
+impl TokenBucket {
+    fn new(capacity: f64, refill_per_sec: f64) -> Self {
+        TokenBucket {
+            capacity,
+            refill_per_sec,
+            state: Mutex::new(State {
+                tokens: capacity,
+                last_refill: tokio::time::Instant::now(),
+            }),
+        }
+    }
+
+    /// Applies the elapsed refill to `state`. Shared by [`Self::acquire`] and
+    /// the idle check so the two cannot drift apart.
+    fn refill(&self, state: &mut State) {
+        let now = tokio::time::Instant::now();
+        let elapsed = now
+            .saturating_duration_since(state.last_refill)
+            .as_secs_f64();
+        // Refill up to the capacity; a debt (negative balance) is repaid
+        // before any surplus accumulates.
+        state.tokens = (state.tokens + elapsed * self.refill_per_sec).min(self.capacity);
+        state.last_refill = now;
+    }
+
+    /// Waits until `n` tokens are available, consuming them. The wait is
+    /// bounded: the deficit is committed as debt and repaid over time, so a
+    /// large acquire returns once its share of the refill budget has passed.
+    pub async fn acquire(&self, n: f64) {
+        // The parking_lot guard is confined to this block: only the plain
+        // `wait` duration crosses the await (a guard across an await point
+        // would make the future !Send).
+        let wait = {
+            let mut state = self.state.lock();
+            self.refill(&mut state);
+            if state.tokens >= n {
+                state.tokens -= n;
+                return;
+            }
+            // Commit the whole consumption now; the caller proceeds once the
+            // deficit's worth of refill time has passed.
+            let debt = n - state.tokens;
+            state.tokens = -debt;
+            debt / self.refill_per_sec
+        };
+        tokio::time::sleep(Duration::from_secs_f64(wait)).await;
+    }
+
+    /// True when the bucket has refilled to capacity: no debt outstanding, so
+    /// the chat has not sent anything recently.
+    fn is_idle(&self) -> bool {
+        let mut state = self.state.lock();
+        self.refill(&mut state);
+        state.tokens >= self.capacity
+    }
+}
+
+/// One limiter per chat, created on first use. Per-chat so one chat's burst
+/// never throttles another.
+static LIMITERS: LazyLock<Mutex<HashMap<i64, Arc<TokenBucket>>>> =
+    LazyLock::new(|| Mutex::new(HashMap::new()));
+
+/// Returns the shared limiter for a chat, creating it on first use.
+pub fn limiter_for(chat_id: i64) -> Arc<TokenBucket> {
+    LIMITERS
+        .lock()
+        .entry(chat_id)
+        .or_insert_with(|| Arc::new(TokenBucket::new(CAPACITY, REFILL_PER_SEC)))
+        .clone()
+}
+
+/// Drops limiters that are idle (refilled to capacity, so the chat has not
+/// sent recently) and are not still held by an in-flight sender. The map
+/// would otherwise keep one bucket per chat that ever sent media, forever.
+/// Called from the periodic sweep; returns how many were dropped.
+pub fn prune_idle() -> usize {
+    let mut limiters = LIMITERS.lock();
+    let before = limiters.len();
+    // Lock order map → bucket, the only order taken anywhere.
+    limiters.retain(|_, bucket| Arc::strong_count(bucket) > 1 || !bucket.is_idle());
+    before - limiters.len()
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn limiter_for_reuses_the_per_chat_bucket() {
+        let a = limiter_for(1);
+        let b = limiter_for(1);
+        let c = limiter_for(2);
+        assert!(Arc::ptr_eq(&a, &b), "same chat → same bucket");
+        assert!(!Arc::ptr_eq(&a, &c), "different chat → different bucket");
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn burst_is_consumed_instantly_then_refill_waits() {
+        let bucket = TokenBucket::new(3.0, 1.0);
+        // A burst within capacity passes without waiting.
+        bucket.acquire(3.0).await;
+        // The bucket is empty now; one token needs 1s of refill.
+        let start = tokio::time::Instant::now();
+        bucket.acquire(1.0).await;
+        assert!(
+            start.elapsed() >= Duration::from_secs(1),
+            "elapsed {:?}",
+            start.elapsed()
+        );
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn acquire_larger_than_capacity_waits_for_the_deficit() {
+        let bucket = TokenBucket::new(2.0, 1.0);
+        // 5 tokens with a capacity of 2: the 3-token deficit takes 3s.
+        let start = tokio::time::Instant::now();
+        bucket.acquire(5.0).await;
+        assert!(
+            start.elapsed() >= Duration::from_secs(3),
+            "elapsed {:?}",
+            start.elapsed()
+        );
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn prune_idle_drops_full_unheld_buckets_only() {
+        // Held by this task: kept even at full capacity, a sender has it.
+        let held = limiter_for(9_001);
+        assert!(held.is_idle(), "a fresh bucket is full");
+        // Only the map holds this one and it is full → dropped.
+        limiter_for(9_002);
+        // Mid-debt (an acquire larger than the capacity): kept.
+        {
+            let bucket = Arc::new(TokenBucket::new(CAPACITY, REFILL_PER_SEC));
+            bucket.state.lock().tokens = -1.0;
+            LIMITERS.lock().insert(9_003, bucket);
+        }
+
+        assert!(prune_idle() >= 1);
+
+        let limiters = LIMITERS.lock();
+        assert!(limiters.contains_key(&9_001), "held bucket pruned");
+        assert!(!limiters.contains_key(&9_002), "idle unheld bucket kept");
+        assert!(limiters.contains_key(&9_003), "indebted bucket pruned");
+    }
+}

crates/xmedia-bot/src/send/input_media.rs

@@ -0,0 +1,128 @@
+//! Payload → Telegram input types: `InputFile` selection (cached file id /
+//! URL / local path), the per-kind `InputMedia` builders and the media-group
+//! assembly with its caption rule.
+
+use super::MediaItemPayload;
+use teloxide::types::{
+    InputFile, InputMedia, InputMediaAnimation, InputMediaPhoto, InputMediaVideo, ParseMode,
+};
+
+fn parse_media_url(s: &str) -> Result<url::Url, String> {
+    url::Url::parse(s).map_err(|e| format!("invalid media URL: {e}"))
+}
+
+pub(super) fn item_url(item: &MediaItemPayload) -> &str {
+    match item {
+        MediaItemPayload::Photo { media, .. }
+        | MediaItemPayload::Video { media, .. }
+        | MediaItemPayload::Animation { media, .. } => media,
+    }
+}
+
+/// Remote http(s) URLs are handed to Telegram to fetch; everything else
+/// (e.g. a locally encoded ugoira MP4) is uploaded directly.
+pub(super) fn input_file_for(media: &str) -> Result<InputFile, String> {
+    if media.starts_with("http://") || media.starts_with("https://") {
+        Ok(InputFile::url(parse_media_url(media)?))
+    } else if !std::path::Path::new(media).exists() {
+        // A retried task may reference a temp file the original send's
+        // TempDir already cleaned up; fail fast and permanent instead of
+        // burning retries on a file that can never come back.
+        Err(format!("local media file missing: {media}"))
+    } else {
+        Ok(InputFile::file(media))
+    }
+}
+
+impl MediaItemPayload {
+    /// The input for a send: a cached file id goes out as `InputFile::file_id`
+    /// (no fetch, no upload), URLs go to Telegram, anything else is a local
+    /// path (transient upload fallback).
+    fn input_file(&self) -> Result<InputFile, String> {
+        match self {
+            MediaItemPayload::Photo {
+                media,
+                file_id: true,
+                ..
+            }
+            | MediaItemPayload::Video {
+                media,
+                file_id: true,
+                ..
+            }
+            | MediaItemPayload::Animation {
+                media,
+                file_id: true,
+                ..
+            } => Ok(InputFile::file_id(media.clone().into())),
+            _ => input_file_for(item_url(self)),
+        }
+    }
+}
+
+pub(super) fn photo_media(file: InputFile, caption: Option<&str>, spoiler: bool) -> InputMedia {
+    let mut photo = InputMediaPhoto::new(file).parse_mode(ParseMode::Html);
+    if let Some(caption) = caption {
+        photo = photo.caption(caption);
+    }
+    if spoiler {
+        photo = photo.spoiler();
+    }
+    InputMedia::Photo(photo)
+}
+
+pub(super) fn video_media(file: InputFile, caption: Option<&str>, spoiler: bool) -> InputMedia {
+    let mut video = InputMediaVideo::new(file).parse_mode(ParseMode::Html);
+    if let Some(caption) = caption {
+        video = video.caption(caption);
+    }
+    if spoiler {
+        video = video.spoiler();
+    }
+    InputMedia::Video(video)
+}
+
+pub(super) fn animation_media(file: InputFile, caption: Option<&str>, spoiler: bool) -> InputMedia {
+    let mut animation = InputMediaAnimation::new(file).parse_mode(ParseMode::Html);
+    if let Some(caption) = caption {
+        animation = animation.caption(caption);
+    }
+    if spoiler {
+        animation = animation.spoiler();
+    }
+    InputMedia::Animation(animation)
+}
+
+/// Builds a media group from payloads; only the first item of the batch gets
+/// the caption (Telegram rejects captions on later items).
+pub(super) fn build_media_group(
+    batch: &[MediaItemPayload],
+    caption: Option<&str>,
+) -> Result<Vec<InputMedia>, String> {
+    batch
+        .iter()
+        .enumerate()
+        .map(|(i, item)| {
+            let item_caption = if i == 0 { caption } else { None };
+            Ok(match item {
+                MediaItemPayload::Photo { has_spoiler, .. } => {
+                    photo_media(item.input_file()?, item_caption, *has_spoiler)
+                }
+                MediaItemPayload::Video {
+                    has_spoiler,
+                    thumbnail,
+                    ..
+                } => {
+                    let mut video = video_media(item.input_file()?, item_caption, *has_spoiler);
+                    if let (Some(thumb), InputMedia::Video(v)) = (thumbnail, &mut video) {
+                        *v = v.clone().thumbnail(input_file_for(thumb)?);
+                    }
+                    video
+                }
+                MediaItemPayload::Animation { has_spoiler, .. } => {
+                    animation_media(item.input_file()?, item_caption, *has_spoiler)
+                }
+            })
+        })
+        .collect()
+}

crates/xmedia-bot/src/send/post_send.rs

@@ -0,0 +1,366 @@
+//! Everything around a send: the link-cache write that follows one, the
+//! keep-alive registry for locally produced media, task settlement, the
+//! post-send actions (edit prompt / channel forward) and the queue entry
+//! points.
+
+use super::{SendError, Task, forward_messages, send_animation, send_media_sequence};
+use crate::ctx::AppContext;
+use crate::db::{now_f64, unix_now};
+use crate::handlers::log_key;
+use crate::link_cache::{CachedMedia, CachedMediaKind, LinkCache};
+use crate::media_sender::MediaSender;
+use crate::queue::{PersistentTaskQueue, QueueError};
+use crate::state::EditMessage;
+use std::collections::HashMap;
+use std::sync::LazyLock;
+use teloxide::types::{ChatId, InlineKeyboardButton, InlineKeyboardMarkup, Message, MessageId};
+
+/// Persists a successful send under the post's cache key. Only runs for a
+/// fresh (non-resumed) task that carried raw cache data with no file ids yet.
+pub(super) async fn cache_sent_task(ctx: &AppContext<'_>, task: &Task, media: Vec<CachedMedia>) {
+    let Some(cache_data) = task.cache_data() else {
+        return;
+    };
+    if !cache_data.media.is_empty() || media.is_empty() {
+        return;
+    }
+    let mut post = cache_data.clone();
+    post.media = media;
+    if let Some(key) = x_media::site::cache_key(&post.url) {
+        ctx.link_cache.put(&key, &post).await;
+        log::debug!("cached send for [key={}]", log_key(&post.url));
+    }
+}
+
+/// Persists a lone animation send under the post's cache key.
+pub(super) async fn cache_animation_send(ctx: &AppContext<'_>, task: &Task, message: &Message) {
+    if let Some(file_id) = message.animation().map(|a| a.file.id.to_string()) {
+        cache_sent_task(
+            ctx,
+            task,
+            vec![CachedMedia {
+                kind: CachedMediaKind::Animation,
+                file_id,
+            }],
+        )
+        .await;
+    }
+}
+
+/// How a task ended. The two states differ only in whether a link-cache entry
+/// may still be holding the (now unusable) media.
+pub(crate) enum Settled {
+    Sent,
+    Failed,
+}
+
+/// Every path that ends a task's life — sent, permanently failed, or
+/// dead-lettered after the last retry — funnels through here, so the cleanup a
+/// settled task owes cannot be forgotten by a new path: release the keep-alive
+/// temp media (retryable tasks keep it, they will be resent) and drop the
+/// link-cache entry that a failed send's stale file ids would keep poisoning.
+pub(crate) async fn settle_task(ctx: &AppContext<'_>, task: &Task, outcome: Settled) {
+    if matches!(outcome, Settled::Failed) {
+        invalidate_cache(ctx.link_cache, task).await;
+    }
+    release_keep_alive(task);
+}
+
+/// A cached Telegram file id failed permanently (stale/expired); drop the
+/// cache entry so the next request re-fetches instead of repeating it.
+async fn invalidate_cache(cache: &LinkCache, task: &Task) {
+    if task.is_cached_send()
+        && let Some(url) = task.source_url()
+        && let Some(key) = x_media::site::cache_key(url)
+    {
+        log::debug!("removing stale link cache entry for [key={}]", log_key(url));
+        cache.remove(&key).await;
+    }
+}
+
+/// Locally produced media files (ugoira MP4, bsky remux MP4) whose temp dirs
+/// must stay alive while their task may be retried by the queue. The fetch
+/// pipeline hands ownership here via
+/// [`x_media::site::Fetched::take_keep_alive`] before that
+/// [`x_media::site::Fetched`] is dropped; a queued retry runs after that drop,
+/// so without this the local file would be gone by the time the retry sends
+/// it. Entries are removed when the task settles (see [`release_keep_alive`]).
+pub(crate) static KEEP_ALIVE: LazyLock<parking_lot::Mutex<Vec<tempfile::TempDir>>> =
+    LazyLock::new(|| parking_lot::Mutex::new(Vec::new()));
+
+/// Drops the keep-alive temp dirs holding media referenced by `task` (matched
+/// by path prefix). Called once a task settles — sent or permanently failed —
+/// so retry-only temp files do not leak; retryable tasks keep them alive.
+pub(crate) fn release_keep_alive(task: &Task) {
+    let paths = task.local_media_paths();
+    if paths.is_empty() {
+        return;
+    }
+    let mut alive = KEEP_ALIVE.lock();
+    alive.retain(|dir| {
+        let dir_path = dir.path();
+        !paths.iter().any(|p| p.starts_with(dir_path))
+    });
+}
+
+/// One button per template name (column layout), then the confirm button.
+/// Sorted by name: the templates live in a `HashMap`, so an unsorted walk
+/// would reshuffle the buttons between prompts.
+pub(super) fn build_edit_markup(templates: &HashMap<String, String>) -> InlineKeyboardMarkup {
+    let mut names: Vec<&String> = templates.keys().collect();
+    names.sort();
+    let mut rows = Vec::with_capacity(names.len() + 1);
+    for name in names {
+        rows.push(vec![InlineKeyboardButton::callback(
+            name.clone(),
+            format!("template|{name}"),
+        )]);
+    }
+    rows.push(vec![InlineKeyboardButton::callback(
+        "↩️ Confirm",
+        "forward",
+    )]);
+    InlineKeyboardMarkup::new(rows)
+}
+
+/// Notifies a chat about a dead-lettered task (skips when `notify_chat_id` is
+/// absent).
+pub(super) async fn notify_failure(
+    sender: &dyn MediaSender,
+    chat_id: Option<i64>,
+    message_id: Option<i64>,
+    message: &str,
+) {
+    let Some(chat_id) = chat_id else { return };
+    let reply_to = message_id.map(|id| MessageId(id as i32));
+    if let Err(e) = sender
+        .send_message(ChatId(chat_id), message.to_string(), reply_to, None)
+        .await
+    {
+        log::error!("failed to notify about failed task: {e}");
+    }
+}
+
+/// After a successful send: either open the edit-before-forward prompt or
+/// forward to the configured channel (with retry/queue handling).
+pub(crate) async fn post_send_actions(ctx: &AppContext<'_>, task: &Task, message_ids: Vec<i64>) {
+    let (
+        chat_id,
+        reply_to,
+        source_url,
+        edit_before_forward,
+        forward_channel_id,
+        notify_chat_id,
+        notify_message_id,
+    ) = match task {
+        Task::SendMediaSequence {
+            chat_id,
+            reply_to_message_id,
+            source_url,
+            edit_before_forward,
+            forward_channel_id,
+            notify_chat_id,
+            notify_message_id,
+            ..
+        }
+        | Task::SendAnimation {
+            chat_id,
+            reply_to_message_id,
+            source_url,
+            edit_before_forward,
+            forward_channel_id,
+            notify_chat_id,
+            notify_message_id,
+            ..
+        } => (
+            *chat_id,
+            *reply_to_message_id,
+            source_url.clone(),
+            *edit_before_forward,
+            *forward_channel_id,
+            *notify_chat_id,
+            *notify_message_id,
+        ),
+        Task::ForwardMessages { .. } => return,
+    };
+
+    if edit_before_forward {
+        let keyboard = build_edit_markup(&ctx.chat_store.get(chat_id).await.template);
+        let prompt = ctx
+            .sender
+            .send_message(
+                ChatId(chat_id),
+                "Reply to edit message.".to_string(),
+                Some(MessageId(reply_to as i32)),
+                Some(keyboard),
+            )
+            .await;
+        match prompt {
+            Ok(prompt_id) => {
+                log::info!(
+                    "edit-before-forward prompt {prompt_id} opened for {} message(s)",
+                    message_ids.len()
+                );
+                let source_url = source_url.clone();
+                ctx.chat_store
+                    .update(chat_id, move |data| {
+                        data.edit_message.insert(
+                            prompt_id,
+                            EditMessage {
+                                url: source_url,
+                                chat_id,
+                                forward_message_ids: message_ids,
+                                template: String::new(),
+                                created_at: unix_now(),
+                            },
+                        );
+                    })
+                    .await;
+            }
+            Err(e) => log::error!("failed to send edit prompt: {e}"),
+        }
+        return;
+    }
+
+    if let Some(channel_id) = forward_channel_id {
+        log::info!(
+            "forwarding {} message(s) to channel {channel_id}",
+            message_ids.len()
+        );
+        let forward_task = Task::ForwardMessages {
+            from_chat_id: chat_id,
+            to_chat_id: channel_id,
+            message_ids,
+            notify_chat_id,
+            notify_message_id,
+        };
+        match forward_messages(ctx, &forward_task).await {
+            Ok(()) => {}
+            Err(SendError::Retryable {
+                delay_seconds,
+                task,
+            }) => {
+                enqueue_retry(ctx.task_queue, *task, delay_seconds).await;
+            }
+            Err(SendError::Permanent { message, .. }) => {
+                notify_failure(
+                    ctx.sender,
+                    notify_chat_id,
+                    notify_message_id,
+                    &format!("Task failed after retries: {message}"),
+                )
+                .await;
+            }
+        }
+    }
+}
+
+/// Enqueues a task for a later attempt (retry / forward resume). When the
+/// enqueue itself fails the task can never be sent again, so its keep-alive
+/// temp media is released instead of leaking until process exit.
+pub(crate) async fn enqueue_retry(queue: &PersistentTaskQueue, 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) = queue.enqueue(payload, run_after).await {
+        log::error!("failed to enqueue retry: {e}");
+        release_keep_alive(&task);
+    }
+}
+
+/// Queue entry point: parses the stored task and dispatches.
+pub(crate) async fn handle_task(
+    ctx: &AppContext<'_>,
+    payload: serde_json::Value,
+) -> Result<(), QueueError> {
+    let task: Task = match serde_json::from_value(payload.clone()) {
+        Ok(task) => task,
+        Err(e) => {
+            return Err(QueueError::Permanent {
+                message: format!("invalid task payload: {e}"),
+                payload,
+            });
+        }
+    };
+    match task {
+        Task::SendMediaSequence { .. } | Task::SendAnimation { .. } => {
+            let message_ids = match send_media_or_animation(ctx, &task).await {
+                Ok(ids) => ids,
+                Err(SendError::Retryable {
+                    delay_seconds,
+                    task,
+                }) => {
+                    return Err(QueueError::Retryable {
+                        delay_seconds,
+                        payload: serde_json::to_value(task).expect("task serializes"),
+                    });
+                }
+                Err(SendError::Permanent { message, task }) => {
+                    settle_task(ctx, &task, Settled::Failed).await;
+                    return Err(QueueError::Permanent {
+                        message,
+                        payload: serde_json::to_value(task).expect("task serializes"),
+                    });
+                }
+            };
+            // A task only reaches the queue after a failed send, so this
+            // successful run is the first time post_send_actions can fire —
+            // the fresh attempt failed before it ever got here. Run it
+            // unconditionally: `post_send_actions` executes once, after the
+            // whole sequence (every batch) completed, so the channel forward
+            // and the edit-before-forward prompt must not be lost just
+            // because the send needed a retry.
+            post_send_actions(ctx, &task, message_ids).await;
+            settle_task(ctx, &task, Settled::Sent).await;
+            Ok(())
+        }
+        Task::ForwardMessages { .. } => match forward_messages(ctx, &task).await {
+            Ok(()) => Ok(()),
+            Err(SendError::Retryable {
+                delay_seconds,
+                task,
+            }) => Err(QueueError::Retryable {
+                delay_seconds,
+                payload: serde_json::to_value(task).expect("task serializes"),
+            }),
+            Err(SendError::Permanent { message, task }) => {
+                settle_task(ctx, &task, Settled::Failed).await;
+                Err(QueueError::Permanent {
+                    message,
+                    payload: serde_json::to_value(task).expect("task serializes"),
+                })
+            }
+        },
+    }
+}
+
+async fn send_media_or_animation(ctx: &AppContext<'_>, task: &Task) -> Result<Vec<i64>, SendError> {
+    match task {
+        Task::SendMediaSequence { .. } => send_media_sequence(ctx, task).await,
+        Task::SendAnimation { .. } => send_animation(ctx, task).await,
+        Task::ForwardMessages { .. } => unreachable!(),
+    }
+}
+
+/// Dead-letter callback wired to the queue in main: settles the task and
+/// notifies its chat.
+pub(crate) async fn dead_letter_notify(
+    ctx: &AppContext<'_>,
+    payload: serde_json::Value,
+    message: String,
+) {
+    // A dead-lettered task never runs again, and the queue dead-letters retry
+    // exhaustion itself (the handler is not called again), so this is the only
+    // place that sees the final payload.
+    if let Ok(task) = serde_json::from_value::<Task>(payload.clone()) {
+        settle_task(ctx, &task, Settled::Failed).await;
+    }
+    let notify_chat_id = payload.get("notify_chat_id").and_then(|v| v.as_i64());
+    let notify_message_id = payload.get("notify_message_id").and_then(|v| v.as_i64());
+    notify_failure(
+        ctx.sender,
+        notify_chat_id,
+        notify_message_id,
+        &format!("Task failed after retries: {message}"),
+    )
+    .await;
+}

crates/xmedia-bot/src/send/upload.rs

@@ -0,0 +1,345 @@
+//! Download-and-reupload fallback: when Telegram cannot fetch a media URL
+//! itself (hotlink protection), the bot downloads the file, shrinks photos
+//! that exceed Telegram's limits and uploads the batch via multipart.
+
+use super::input_media::{animation_media, input_file_for, item_url, photo_media, video_media};
+use super::{MediaItemPayload, SendError, Task, classify_to_send_error, retry_delay_seconds};
+use crate::media_sender::MediaSender;
+use crate::photo::{self, MAX_UPLOAD_BYTES, PhotoPrep};
+use teloxide::prelude::*;
+use teloxide::types::{ChatId, InputFile, InputMedia, MessageId};
+use tempfile::NamedTempFile;
+use x_media::site::FetchError;
+
+/// Infers a file extension from magic bytes so Telegram detects the mime type
+/// on multipart uploads.
+pub(super) fn sniff_ext(bytes: &[u8]) -> &'static str {
+    if bytes.starts_with(&[0xFF, 0xD8]) {
+        "jpg"
+    } else if bytes.starts_with(b"\x89PNG") {
+        "png"
+    } else if bytes.starts_with(b"RIFF") && bytes.len() >= 12 && &bytes[8..12] == b"WEBP" {
+        "webp"
+    } else if bytes.starts_with(b"GIF8") {
+        "gif"
+    } else if bytes.len() >= 12 && &bytes[4..8] == b"ftyp" {
+        "mp4"
+    } else {
+        "bin"
+    }
+}
+
+pub(super) enum FallbackError {
+    Retryable {
+        delay_seconds: f64,
+    },
+    Permanent {
+        message: String,
+    },
+    /// The downloaded file exceeds the upload cap; the caller falls back to
+    /// the item's smaller URL.
+    MediaTooLarge,
+}
+
+/// Brings a downloaded photo within Telegram's limits via the pure-Rust
+/// chain in [`crate::photo`] (no ffmpeg): dimension cap / upload cap
+/// exceeded photos are decoded, downscaled with Lanczos3, PNG bit depth
+/// reduced (>24-bit → 24-bit RGB, ≤24-bit untouched) and transcoded to JPEG
+/// only if still too big. Anything that cannot be fixed falls back to the
+/// item's smaller URL.
+///
+/// Downloads one media item to a temp file (deleted on drop), returning the
+/// file plus the downloaded bytes (photos keep the bytes for
+/// [`photo::prepare_photo`] — re-reading the file would double the I/O).
+/// Network errors are retryable; size over the upload cap and other download
+/// errors are not.
+async fn download_to_temp(
+    item: &MediaItemPayload,
+) -> Result<(NamedTempFile, bytes::Bytes), FallbackError> {
+    let media_url = match item {
+        MediaItemPayload::Photo { media, .. }
+        | MediaItemPayload::Video { media, .. }
+        | MediaItemPayload::Animation { media, .. } => media,
+    };
+    // Photos are downloaded even over the upload cap so `prepare_photo` can
+    // downscale / transcode them (cap = decode budget); videos/animations
+    // abort as soon as the upload cap is crossed mid-stream.
+    let limit = if matches!(item, MediaItemPayload::Photo { .. }) {
+        photo::MAX_DECODE_BYTES
+    } else {
+        MAX_UPLOAD_BYTES + 1
+    };
+    let bytes = match x_media::site::download_media_limited(media_url, limit).await {
+        Ok(bytes) => bytes,
+        Err(FetchError::Http(_)) => {
+            return Err(FallbackError::Retryable {
+                delay_seconds: retry_delay_seconds(0),
+            });
+        }
+        Err(FetchError::TooLarge) => {
+            return Err(FallbackError::MediaTooLarge);
+        }
+        Err(e) => {
+            return Err(FallbackError::Permanent {
+                message: format!("download failed: {e}"),
+            });
+        }
+    };
+    let ext = sniff_ext(&bytes);
+    let mut file = tempfile::Builder::new()
+        .suffix(&format!(".{ext}"))
+        .tempfile()
+        .map_err(|e| FallbackError::Permanent {
+            message: format!("temp file failed: {e}"),
+        })?;
+    use std::io::Write;
+    file.as_file_mut()
+        .write_all(&bytes)
+        .map_err(|e| FallbackError::Permanent {
+            message: format!("temp file write failed: {e}"),
+        })?;
+    Ok((file, bytes))
+}
+
+/// Builds the media group item from an uploaded file.
+fn media_from_file(
+    item: &MediaItemPayload,
+    path: std::path::PathBuf,
+    caption: Option<&str>,
+    thumbnail: Option<&str>,
+) -> Result<InputMedia, String> {
+    let mut media = match item {
+        MediaItemPayload::Photo { has_spoiler, .. } => {
+            photo_media(InputFile::file(path), caption, *has_spoiler)
+        }
+        MediaItemPayload::Video { has_spoiler, .. } => {
+            video_media(InputFile::file(path), caption, *has_spoiler)
+        }
+        MediaItemPayload::Animation { has_spoiler, .. } => {
+            animation_media(InputFile::file(path), caption, *has_spoiler)
+        }
+    };
+    if let (Some(thumb), InputMedia::Video(v)) = (thumbnail, &mut media) {
+        *v = v.clone().thumbnail(input_file_for(thumb)?);
+    }
+    Ok(media)
+}
+
+/// Builds the media group item from a (smaller) URL.
+fn media_from_url(
+    item: &MediaItemPayload,
+    url: &str,
+    caption: Option<&str>,
+    thumbnail: Option<&str>,
+) -> Result<InputMedia, String> {
+    let mut media = match item {
+        MediaItemPayload::Photo { has_spoiler, .. } => {
+            photo_media(input_file_for(url)?, caption, *has_spoiler)
+        }
+        MediaItemPayload::Video { has_spoiler, .. } => {
+            video_media(input_file_for(url)?, caption, *has_spoiler)
+        }
+        MediaItemPayload::Animation { has_spoiler, .. } => {
+            animation_media(input_file_for(url)?, caption, *has_spoiler)
+        }
+    };
+    if let (Some(thumb), InputMedia::Video(v)) = (thumbnail, &mut media) {
+        *v = v.clone().thumbnail(input_file_for(thumb)?);
+    }
+    Ok(media)
+}
+
+/// One item prepared for the upload fallback: the ready-to-send media plus
+/// the temp file that must stay on disk until the group request completes.
+pub(super) struct PreparedItem {
+    /// Original position in the batch (concurrent prep completes out of order).
+    pub(super) index: usize,
+    pub(super) media: InputMedia,
+    pub(super) keep_alive: Option<NamedTempFile>,
+}
+
+/// Downloads / processes one media item for the upload fallback (see
+/// [`send_batch_via_upload`]). Local files are uploaded directly; oversized
+/// items fall back to their smaller URL; photos are downscaled/transcoded.
+pub(super) async fn prepare_upload_item(
+    item: MediaItemPayload,
+    index: usize,
+    caption: Option<&str>,
+) -> Result<PreparedItem, FallbackError> {
+    // Locally produced files (ugoira / bsky remux MP4): nothing to download
+    // or shrink — upload the file directly. The send is a multipart upload,
+    // so the only remaining failure is an upload-cap error, which is
+    // permanent (a video cannot be re-encoded here).
+    let media_url = item_url(&item);
+    if !media_url.starts_with("http://") && !media_url.starts_with("https://") {
+        let media = media_from_file(
+            &item,
+            std::path::PathBuf::from(media_url),
+            caption,
+            item.thumbnail_url(),
+        )
+        .map_err(|message| FallbackError::Permanent { message })?;
+        return Ok(PreparedItem {
+            index,
+            media,
+            keep_alive: None,
+        });
+    }
+    // Size check before downloading/uploading: over the cap, use the
+    // smaller URL instead of the file. Photos are exempt — they are
+    // downloaded and processed (downscale / PNG→JPEG) before uploading.
+    let too_large = match x_media::site::media_size(media_url).await {
+        Ok(Some(size)) => size > MAX_UPLOAD_BYTES,
+        _ => false,
+    };
+    let too_large = too_large && !matches!(item, MediaItemPayload::Photo { .. });
+    if too_large {
+        let url = item
+            .fallback_url()
+            .ok_or_else(|| FallbackError::Permanent {
+                message: "media too large".into(),
+            })?;
+        let media = media_from_url(&item, url, caption, item.thumbnail_url())
+            .map_err(|message| FallbackError::Permanent { message })?;
+        return Ok(PreparedItem {
+            index,
+            media,
+            keep_alive: None,
+        });
+    }
+    match download_to_temp(&item).await {
+        Ok((file, bytes)) => {
+            if matches!(item, MediaItemPayload::Photo { .. }) {
+                // Telegram rejects photos wider+taller than 10000 px combined
+                // (PHOTO_INVALID_DIMENSIONS): downscale the downloaded file
+                // before uploading; photos that cannot be brought within the
+                // limits degrade to the smaller URL. CPU-heavy work runs off
+                // the async executor thread.
+                let prep = tokio::task::spawn_blocking(move || photo::prepare_photo(file, &bytes))
+                    .await
+                    .map_err(|e| FallbackError::Permanent {
+                        message: format!("photo worker panicked: {e}"),
+                    })?
+                    .map_err(|message| FallbackError::Permanent { message })?;
+                match prep {
+                    PhotoPrep::Upload(upload) => {
+                        let path = upload.path().to_path_buf();
+                        let media = media_from_file(&item, path, caption, item.thumbnail_url())
+                            .map_err(|message| FallbackError::Permanent { message })?;
+                        Ok(PreparedItem {
+                            index,
+                            media,
+                            keep_alive: Some(upload),
+                        })
+                    }
+                    PhotoPrep::UseFallback => {
+                        let url = item.fallback_url().ok_or_else(|| FallbackError::Permanent {
+                            message: "photo dimensions exceed Telegram limits and no smaller variant is available"
+                                .into(),
+                        })?;
+                        let media = media_from_url(&item, url, caption, item.thumbnail_url())
+                            .map_err(|message| FallbackError::Permanent { message })?;
+                        Ok(PreparedItem {
+                            index,
+                            media,
+                            keep_alive: None,
+                        })
+                    }
+                }
+            } else {
+                let path = file.path().to_path_buf();
+                let media = media_from_file(&item, path, caption, item.thumbnail_url())
+                    .map_err(|message| FallbackError::Permanent { message })?;
+                Ok(PreparedItem {
+                    index,
+                    media,
+                    keep_alive: Some(file),
+                })
+            }
+        }
+        Err(FallbackError::MediaTooLarge) => {
+            let url = item
+                .fallback_url()
+                .ok_or_else(|| FallbackError::Permanent {
+                    message: "media too large".into(),
+                })?;
+            let media = media_from_url(&item, url, caption, item.thumbnail_url())
+                .map_err(|message| FallbackError::Permanent { message })?;
+            Ok(PreparedItem {
+                index,
+                media,
+                keep_alive: None,
+            })
+        }
+        Err(e) => Err(e),
+    }
+}
+
+/// Download-and-reupload fallback for one media batch. Files over the upload
+/// cap are not downloaded/uploaded; the item falls back to its smaller URL
+/// (which Telegram fetches itself). Items are prepared concurrently (bounded)
+/// because the downloads are network-bound; the batch is then uploaded in its
+/// original order. Returns the fallback-error without the task attached;
+/// callers wrap it with the updated task state.
+pub(super) async fn send_batch_via_upload(
+    sender: &dyn MediaSender,
+    chat_id: i64,
+    reply_to: i64,
+    batch: &[MediaItemPayload],
+    caption: Option<&str>,
+    task: Task,
+) -> Result<Vec<Message>, SendError> {
+    let sem = std::sync::Arc::new(tokio::sync::Semaphore::new(3));
+    let mut set = tokio::task::JoinSet::new();
+    for (i, item) in batch.iter().enumerate() {
+        let item_caption = if i == 0 {
+            caption.map(str::to_string)
+        } else {
+            None
+        };
+        let item = item.clone();
+        let sem = std::sync::Arc::clone(&sem);
+        set.spawn(async move {
+            let _permit = sem.acquire().await.expect("upload semaphore closed");
+            prepare_upload_item(item, i, item_caption.as_deref()).await
+        });
+    }
+    let mut prepared: Vec<Option<InputMedia>> = (0..batch.len()).map(|_| None).collect();
+    let mut keep_alive: Vec<NamedTempFile> = Vec::new();
+    while let Some(joined) = set.join_next().await {
+        let item = match joined {
+            Ok(Ok(item)) => item,
+            // Dropping the JoinSet aborts the remaining prep tasks; their
+            // temp files are cleaned up on drop (short-circuit like before).
+            Ok(Err(e)) => return Err(SendError::from_fallback(e, task.clone())),
+            Err(e) => {
+                return Err(SendError::Permanent {
+                    message: format!("upload worker panicked: {e}"),
+                    task: Box::new(task),
+                });
+            }
+        };
+        let PreparedItem {
+            index,
+            media,
+            keep_alive: file_opt,
+        } = item;
+        if let Some(file) = file_opt {
+            keep_alive.push(file);
+        }
+        prepared[index] = Some(media);
+    }
+    let items: Vec<InputMedia> = prepared
+        .into_iter()
+        .map(|m| m.expect("every upload item was prepared"))
+        .collect();
+    // `keep_alive` holds the temp files until the group request completes.
+    let result = sender
+        .send_media_group(ChatId(chat_id), MessageId(reply_to as i32), items)
+        .await;
+    drop(keep_alive);
+    match result {
+        Ok(messages) => Ok(messages),
+        Err(e) => Err(classify_to_send_error(&e, task, "upload failed")),
+    }
+}

crates/xmedia-bot/src/state.rs

@@ -1,13 +1,13 @@
 //! Per-chat state with SQLite persistence (table `chat_state` in
 //! `data/task_queue.db`, shared with the task queue).
 
+use crate::db::unix_now;
 use parking_lot::Mutex;
 use rusqlite::params;
 use serde::{Deserialize, Serialize};
 use std::collections::HashMap;
-use std::path::Path;
 use std::sync::Arc;
-use std::time::{Duration, SystemTime, UNIX_EPOCH};
+use std::time::Duration;
 
 #[derive(Serialize, Deserialize, Default, Clone, Debug)]
 pub struct ChatData {
@@ -17,8 +17,8 @@ pub struct ChatData {
     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.
+    /// site name (twitter/bsky/misskey/pixiv) -> user-supplied caption format
+    /// with {url} {author} {author_url} {title} {tags} placeholders.
     pub message_format: HashMap<String, String>,
 }
 
@@ -38,37 +38,19 @@ pub struct ChatStore {
     /// Per-chat async locks serializing get→mutate→set so concurrent handler
     /// tasks (batch-forwards, callbacks) cannot clobber each other's writes.
     locks: Mutex<HashMap<i64, Arc<tokio::sync::Mutex<()>>>>,
-    pool: crate::db::DbPool,
-}
-
-pub fn unix_now() -> i64 {
-    SystemTime::now()
-        .duration_since(UNIX_EPOCH)
-        .map(|d| d.as_secs() as i64)
-        .unwrap_or(0)
+    pool: Arc<crate::db::DbPool>,
 }
 
 impl ChatStore {
-    /// Creates the parent directory and the `chat_state` table (idempotent).
-    /// The shared `tasks` / `link_cache` tables are owned by `queue.rs` and
-    /// `link_cache.rs` respectively.
-    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 = crate::db::open_db(path)?;
-        conn.execute_batch(
-            "CREATE TABLE IF NOT EXISTS chat_state (chat_id TEXT PRIMARY KEY, payload TEXT NOT NULL);",
-        )?;
-        drop(conn);
-        Ok(ChatStore {
+    /// Wraps the shared DB pool (schema initialized once by
+    /// [`crate::db::open_store`]; the `chat_state` table lives in the merged
+    /// schema alongside `tasks` and `link_cache`).
+    pub fn new(pool: Arc<crate::db::DbPool>) -> Self {
+        ChatStore {
             cache: Mutex::new(HashMap::new()),
             locks: Mutex::new(HashMap::new()),
-            pool: crate::db::DbPool::new(path),
-        })
+            pool,
+        }
     }
 
     pub async fn get(&self, chat_id: i64) -> ChatData {
@@ -120,19 +102,22 @@ impl ChatStore {
         }
     }
 
+    /// The per-chat async lock serializing get→mutate→set cycles.
+    fn lock_for(&self, chat_id: i64) -> Arc<tokio::sync::Mutex<()>> {
+        self.locks
+            .lock()
+            .entry(chat_id)
+            .or_insert_with(|| Arc::new(tokio::sync::Mutex::new(())))
+            .clone()
+    }
+
     /// Serializes a get→mutate→set cycle per chat: concurrent handler tasks
     /// (the batch-forward design spawns several per chat) each snapshot the
     /// same `ChatData` and last-writer-wins would silently drop mutations,
     /// e.g. a second `edit_message` record. The per-chat lock makes the
     /// cycle atomic. Returns the closure's result.
     pub async fn update<R>(&self, chat_id: i64, f: impl FnOnce(&mut ChatData) -> R) -> R {
-        let lock = {
-            let mut locks = self.locks.lock();
-            locks
-                .entry(chat_id)
-                .or_insert_with(|| Arc::new(tokio::sync::Mutex::new(())))
-                .clone()
-        };
+        let lock = self.lock_for(chat_id);
         let _guard = lock.lock().await;
         let mut data = self.get(chat_id).await;
         let r = f(&mut data);
@@ -146,43 +131,45 @@ impl ChatStore {
     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();
-        // Chats with no live edit records: evicted from the cache (and their
-        // per-chat lock) so the cache stays bounded to active prompts. The DB
-        // keeps the row; the next get() reloads it.
-        let mut evicted_chats = 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() {
-                    // Persist the pruned row (removes expired records from
-                    // the DB too, not just the cache).
-                    data.edit_message = kept;
-                    out.push((*chat_id, data.clone()));
-                }
-                if data.edit_message.is_empty() {
-                    evicted_chats.push(*chat_id);
-                }
-            }
-            // Lock order: update() takes the per-chat lock before the cache
-            // lock, so prune must not hold the cache lock while taking locks.
-            drop(cache);
-            out
+        // Chats that may have an expired record, from a cache snapshot; the
+        // pruning itself re-reads and writes under the per-chat lock below
+        // (see the eviction note). Takes no lock of its own, so a chat
+        // appearing later is simply picked up by the next sweep.
+        let candidates: Vec<i64> = {
+            let cache = self.cache.lock();
+            cache
+                .iter()
+                .filter(|(_, data)| {
+                    data.edit_message
+                        .values()
+                        .any(|entry| entry.created_at + ttl_secs <= now)
+                })
+                .map(|(chat_id, _)| *chat_id)
+                .collect()
         };
-        for (chat_id, data) in changed {
-            self.set(chat_id, &data).await;
+        let mut removed = Vec::new();
+        let mut evicted_chats = Vec::new();
+        for chat_id in candidates {
+            let lock = self.lock_for(chat_id);
+            let _guard = lock.lock().await;
+            let mut data = self.get(chat_id).await;
+            let before = data.edit_message.len();
+            data.edit_message.retain(|key, entry| {
+                if entry.created_at + ttl_secs > now {
+                    return true;
+                }
+                removed.push((chat_id, *key));
+                false
+            });
+            if data.edit_message.len() != before {
+                self.set(chat_id, &data).await;
+            }
+            // Chats with no live edit records: evicted from the cache (and
+            // their per-chat lock) so the cache stays bounded to active
+            // prompts. The DB keeps the row; the next get() reloads it.
+            if data.edit_message.is_empty() {
+                evicted_chats.push(chat_id);
+            }
         }
         if !evicted_chats.is_empty() {
             let mut cache = self.cache.lock();
@@ -209,9 +196,8 @@ mod tests {
     #[tokio::test]
     async fn concurrent_updates_do_not_lose_edit_records() {
         let dir = tempfile::tempdir().unwrap();
-        let store = std::sync::Arc::new(
-            ChatStore::open(dir.path().join("s.db").to_str().unwrap()).unwrap(),
-        );
+        let pool = crate::db::open_store(dir.path().join("s.db").to_str().unwrap()).unwrap();
+        let store = std::sync::Arc::new(ChatStore::new(pool));
         let mut handles = Vec::new();
         for i in 0..4 {
             let store = Arc::clone(&store);
@@ -242,4 +228,66 @@ mod tests {
             "concurrent get→mutate→set must not drop records"
         );
     }
+
+    fn edit_entry(chat_id: i64, created_at: i64) -> EditMessage {
+        EditMessage {
+            url: "https://x.com/u/status/1".into(),
+            chat_id,
+            forward_message_ids: vec![9],
+            template: String::new(),
+            created_at,
+        }
+    }
+
+    #[tokio::test]
+    async fn prune_removes_only_expired_records() {
+        let dir = tempfile::tempdir().unwrap();
+        let pool = crate::db::open_store(dir.path().join("p.db").to_str().unwrap()).unwrap();
+        let store = ChatStore::new(pool);
+        let now = unix_now();
+        store
+            .update(7, |data| {
+                data.template.insert("t".into(), "[]".into());
+                data.edit_message.insert(1, edit_entry(7, now - 3600));
+                data.edit_message.insert(2, edit_entry(7, now));
+            })
+            .await;
+
+        let removed = store.prune_expired(Duration::from_secs(60)).await;
+
+        assert_eq!(removed, vec![(7, 1)]);
+        let data = store.get(7).await;
+        assert!(data.edit_message.contains_key(&2), "live record pruned");
+        assert_eq!(
+            data.template.get("t").map(String::as_str),
+            Some("[]"),
+            "unrelated state lost by the prune"
+        );
+    }
+
+    #[tokio::test]
+    async fn prune_eviction_keeps_the_persisted_state() {
+        // Every record expires → the chat is evicted from the cache; the
+        // pruned state must already be in the DB when that happens.
+        let dir = tempfile::tempdir().unwrap();
+        let pool = crate::db::open_store(dir.path().join("p.db").to_str().unwrap()).unwrap();
+        let store = ChatStore::new(pool);
+        store
+            .update(8, |data| {
+                data.template.insert("keep".into(), "[]".into());
+                data.edit_message.insert(1, edit_entry(8, 0));
+            })
+            .await;
+
+        let removed = store.prune_expired(Duration::from_secs(60)).await;
+
+        assert_eq!(removed, vec![(8, 1)]);
+        let data = store.get(8).await;
+        assert!(data.edit_message.is_empty());
+        assert_eq!(
+            data.template.get("keep").map(String::as_str),
+            Some("[]"),
+            "eviction dropped state the DB never received"
+        );
+    }
 }

docs/architecture-refactor.md

@@ -0,0 +1,143 @@
+# 架构优化设计：可测试性接缝 + handlers 拆分
+
+> 状态：**阶段 A、B、C 已实施**（A: `c9e72fd`，B: `50206a9` + `ae69d72`，C:
+> rate_limit 提交）；**D 已延迟**——待下次数据库 schema 变化时实施（见 §5）。
+> 目标：把仓库最大的测试空白（`handlers.rs`/`send.rs` 的发送与分派逻辑）补上
+> 可测试接缝，并把 ~1100 行的 handlers 单体拆成模块。
+
+---
+
+## 1. 现状与动机
+
+- `handlers.rs`（~1100 行）混装：命令解析/执行、URL 提取 + 任务通道、inline
+  debounce、callback、edit-before-forward、全部全局静态。
+- 关键路径零测试：`url_media` 的分派、`dispatch_send` 的失败分类、缓存命中路径、
+  edit-before-forward、转发重试——AGENTS.md 自认 "untested: handlers.rs"。
+- 根因：`handlers.rs`/`send.rs` 直接依赖 teloxide `Bot`（具体类型）与全局静态
+  （`CHAT_STORE`/`TASK_QUEUE`/`LINK_CACHE`/`CONFIG`），没有注入点。
+
+## 2. 阶段 A：handlers 拆分（纯组织，零风险，先行）
+
+把 `handlers.rs` 拆为模块（仅移动代码，不改签名）：
+
+```
+handlers/
+  mod.rs       — 入口：message/inline/callback 分发 + 公共类型（UrlJob、log_key）
+  statics.rs   — CHAT_STORE / TASK_QUEUE / LINK_CACHE / DB / CONFIG / URL_JOBS
+  commands.rs  — Command enum + execute_command + set_forward_channel_handler
+  urls.rs      — extract_urls + start/stop_url_workers + url_media + build_send_task + media_to_payload
+  inline.rs    — inline_query_handler + debounce 状态机 + answer_inline_query
+  callback.rs  — callback_query_handler + edit_message_handler
+```
+
+- `mod.rs` 用 `pub use` 重导出，bot 侧引用 `handlers::xxx` 不变。
+- 收益：每个模块独立审阅；后续阶段 B 的接缝改动落在明确的模块内。
+
+## 3. 阶段 B：MediaSender 接缝（核心）
+
+**动机**：`send.rs` 的所有发送入口（`send_media_group`/`send_animation`/
+`copy_messages`）都挂在具体 `Bot` 上；测试无法注入失败/成功。
+
+**设计**：新增 `crates/xmedia-bot/src/media_sender.rs`：
+
+```rust
+/// 发送抽象：生产用 teloxide Bot，测试用记录型 mock。
+/// 方法签名与 teloxide 调用点一一对应，返回 Result 以便注入任意失败。
+pub trait MediaSender: Send + Sync {
+    fn send_media_group(&self, chat_id: ChatId, items: Vec<InputMedia>)
+        -> BoxFuture<'_, Result<Vec<Message>, RequestError>>;
+    fn send_animation(&self, chat_id: ChatId, file: InputFile, caption: Option<&str>, spoiler: bool, reply_to: i64)
+        -> BoxFuture<'_, Result<Message, RequestError>>;
+    fn copy_messages(&self, to: ChatId, from: ChatId, ids: Vec<MessageId>)
+        -> BoxFuture<'_, Result<Vec<MessageId>, RequestError>>;
+    // 按需扩展：edit_message_caption / delete_message / answer_callback_query …
+}
+
+impl MediaSender for Bot { /* 委托现有 teloxide 调用 */ }
+```
+
+配套：`ChatStore`/`LinkCache`/`PersistentTaskQueue` 已是具体类型——给 `send.rs`/
+`url_media` 需要的最小面加 trait（`ChatStoreReader`/`LinkCacheReader` 等），或直接
+注入具体类型（它们已有内存态，测试用真实 tempdir 即可，见阶段 B-注）。
+
+**接入点**：
+- `dispatch_send` / `send_media_sequence` / `send_animation` / `forward_messages` /
+  `post_send_actions` / `notify_failure` 的 `bot: &Bot` 参数改为 `sender: &dyn MediaSender`。
+- `url_media` 由 `url_media(bot, message, url)` 改为 `url_media(sender, store, queue, cache, message, url)`（或聚合为一个 `AppContext` 结构传引用）。
+
+**测试策略**（仓库无 mock 框架，手写 mock）：
+- `MockSender` 记录调用序列、按脚本返回 Ok/Err（覆盖：URL 发送成功、media-fetch
+  失败触发兜底、RetryAfter 触发入队、Permanent 触发缓存失效）。
+- `ChatStore`/`LinkCache` 用真实 tempdir 实例（现有测试已这么做）。
+- 新增测试：`send_media_sequence` 分批续传、`send_animation` 兜底、`url_media`
+  缓存命中 vs 未命中、`dispatch_send` 三分支。
+
+**风险**：中。动 `send.rs`/`handlers.rs` 签名（约 15 处调用点），行为不变。
+**不做**：`main.rs` 的 teloxide 装配不抽象（那是真正的胶水，无测试价值）。
+
+## 4. 阶段 C：主动限流（已实施）
+
+批量转发时的突发会触发 Telegram 频道限速，现在靠 `RetryAfter → 队列重试` 被动
+应对。新增轻量令牌桶（`rate_limit.rs`）：
+
+```rust
+pub struct TokenBucket { capacity, refill_per_sec, state: Mutex<State> }
+impl TokenBucket {
+    pub async fn acquire(&self, n: f64); // 按 n 个 token 等待并消费
+}
+pub fn limiter_for(chat_id: i64) -> Arc<TokenBucket>; // 每频道一个桶
+```
+
+- 默认 `CAPACITY = 20`、`REFILL_PER_SEC = 20/60`（约 20 msg/min）；
+  单次 acquire 可超出容量（记为债务，由后续 refill 偿还）。
+- 挂点：`MediaSender for Bot` 的 `send_media_group`（按 items 数）、
+  `copy_messages`（按 ids 数）、`send_animation`（1 token）前置 `acquire`；
+  MockSender 不受影响（测试不经过限流）。
+- 收益：减少 429 → 重试 → 死信；队列重试仍是全局限速的安全网。
+- 风险：低，独立模块；`tokio::time`（paused-clock 可测）。
+
+## 5. 阶段 D：DB 版本化迁移（**已延迟**）
+
+> ⚠️ **待办提醒**：本阶段**推迟到下次数据库 schema 变化时实施**（给
+> `link_cache`/`chat_state`/`tasks` 加列、改结构等）。当前 `schema_init` 是
+> `CREATE TABLE IF NOT EXISTS`，无版本概念；一旦需要迁移已有线上库，必须先落地
+> 本方案（`PRAGMA user_version` 迁移链）再改 schema。`db.rs` 的 `schema_init`
+> 处已留注释指向这里。
+
+```rust
+// db.rs
+const MIGRATIONS: &[&str] = &[
+    // v1: 初始 schema（tasks / chat_state / link_cache）
+    "CREATE TABLE IF NOT EXISTS tasks (...); ...",
+];
+pub fn migrate(conn: &Connection) -> rusqlite::Result<()> {
+    let v: i64 = conn.query_row("PRAGMA user_version", [], |r| r.get(0))?;
+    for (i, sql) in MIGRATIONS.iter().enumerate().skip(v as usize) {
+        conn.execute_batch(sql)?;
+        conn.pragma_update(None, "user_version", (i + 1) as i64)?;
+    }
+    Ok(())
+}
+```
+
+- 低优先级：schema 未变时无收益；将来加列/改结构时必须有。
+- `open_store` 改用 `migrate` 替换 `schema_init` 调用。
+
+## 6. 明确不做
+
+- **不拆 xmedia-core**：`Task`/队列/发送抽成独立 lib crate 是大工程，除非出现
+  第二个客户端，否则收益不抵成本。
+- **不引入 DI 框架**：仓库惯例是 LazyLock 静态 + 显式传参，保持。
+- **不抽象 main.rs 的 teloxide 装配**。
+
+## 7. 实施记录
+
+| 阶段 | 提交 | 说明 |
+|---|---|---|
+| A | `c9e72fd` | handlers 拆为 `{mod, statics, commands, urls, inline, callback}` |
+| B | `50206a9` | `media_sender.rs`：`trait MediaSender` + `impl for Bot`（`<Bot as Requester>::` 消歧）；send.rs 8 处签名改 `&dyn MediaSender`；`MockSender` 测试覆盖兜底触发与错误分类（+5 测试） |
+| B | `ae69d72` | `AppContext` 注入 `url_media`（sender/store/queue/cache），url_media 全链路测试（缓存命中/失效/成功/不支持 URL，+3 测试） |
+| C | rate_limit 提交 | `rate_limit.rs` 令牌桶 + 每频道注册表；`MediaSender for Bot` 的 group/copy/animation 前置 `acquire`（+3 测试） |
+| D | — | **已延迟**：待下次数据库 schema 变化时实施（见 §5） |
+
+A、B、C 为核心并已实施；D 在 schema 变更时落地。

docs/site-registry-refactor.md

@@ -0,0 +1,241 @@
+# 站点适配器重构方案：让新增站点变成"新模块 + 注册一行"
+
+> 状态：**已实施**（阶段 1-5，提交 `7ca8fd1` / `5e23916` / `bf4e615` / `5679a8c` +
+> 本文档收尾）。目标：把"加一个新站点"从改 8-9 处收敛到 3 处，并让站点身份、
+> 重试策略、下载 header 等站点能力归位到站点模块自身。实施过程中的关键偏差
+> （async 形态）见 §3 的 "async 形态" 段——原生 AFIT 实测不可用于 dyn 分派，
+> 最终采用手写 `BoxFuture`（`SiteFuture` 别名）。
+
+---
+
+## 1. 现状摩擦清单
+
+> ⚠️ 本节记录的是**重构前**的现状：其中的行号、以及 `site/mod.rs` 里的
+> `fetch_once` 分派函数（当时的实现）都已不存在，仅作历史记录。当前形态见
+> `site/mod.rs` 的 `SITES` 注册表——新增站点 = 新模块 + 注册一行。
+
+以现有三站（twitter / bsky / pixiv）为基线，新增第 4 个站点（代号 `example`）
+今天需要触碰的位置：
+
+| # | 位置（当前行号） | 改动 | 必改? |
+|---|---|---|---|
+| 1 | 新目录 `crates/x-media/src/site/example/{mod,interface,model}.rs` | 新模块 | 必改 |
+| 2 | `site/mod.rs:354-365` `fetch_once` | 加一个 `if` 分派分支 | 必改 |
+| 3 | `site/mod.rs:167-178` `cache_key` | 加一个 `if` 分支 + 约定 key 前缀 `"example:..."` | 必改 |
+| 4 | `site/mod.rs:53-63` `site_name()` | 加一个 URL `contains` 嗅探分支 | 必改 |
+| 5 | `handlers.rs:405` `SetFormat` 白名单 | `["twitter","bsky","pixiv"]` 加字符串 | 必改 |
+| 6 | `config.rs` / `main.rs:74-84` | 仿 pixiv 加启动校验（token、`disable()`） | 视站点 |
+| 7 | `site/mod.rs:312-326` `fetch_error_is_retryable` | 若重试策略特殊，改中央分类函数 | 视站点 |
+| 8 | `site/mod.rs:377/391/430` 三个下载函数 | 若媒体有防盗链，加 header（现在是硬编码 pximg 判断） | 视站点 |
+| 9 | `site/mod.rs:16,180-197` `FetchError` | 若错误类型特殊，加嵌套 variant（仿 `Pixiv(PixivError)`） | 视站点 |
+
+**根因**：仓库里没有"站点"这个实体。站点的四类能力——URL 识别（PATTERN +
+cache_key）、抓取、重试策略、下载 header——分别散落在中央 if 链、URL 字符串嗅探、
+魔法字符串 key 和 bot crate 的白名单里。`AGENTS.md` 现行约定 "no trait, no enum
+dispatch" 是刻意的简单性选择；本方案的目标是在**不推翻它精神的前提下**收敛摩擦，
+并在阶段 3 提供完整的 trait 注册表选项。
+
+## 2. 目标架构
+
+```
+crates/x-media/src/site/mod.rs
+  ├─ SITES: LazyLock<Vec<Box<dyn Site>>>      ← 注册表（唯一的"站点列表"）
+  ├─ find_site(url) / fetch(url) / cache_key(url) / site_ids()
+  └─ 通用类型：Fetched { site_id, ... } / FetchError（通用类 + Site 变体）
+        │
+        ├─ site/twitter/{mod,interface,model}.rs  impl Site
+        ├─ site/bsky/…                            impl Site
+        └─ site/pixiv/…                           impl Site  (download_headers: pximg Referer)
+                                                    (validate: token 校验)
+
+crates/xmedia-bot
+  ├─ handlers.rs  SetFormat 白名单 ← x_media::site::ids()（不再写死）
+  ├─ handlers.rs  site 格式查找 ← fetched.site_id（缓存/新鲜两条路径同口径）
+  └─ main.rs      启动校验 ← site::validate_all()（不再特判 pixiv）
+```
+
+## 3. 分阶段迁移
+
+每个阶段是一个独立提交，保持 `cargo fmt` / `cargo clippy -- -D warnings` /
+`cargo test --workspace` 全绿；行为完全不变，只挪代码、不换语义。
+
+### 阶段 1：站点身份单一来源（低风险，推荐先做）
+
+**动机**：同一概念目前有两个来源——缓存命中路径用 `key.split(':').next()`
+（`handlers.rs:639`），新鲜抓取路径用 `fetched.site_name()`（`handlers.rs:724`）；
+`site_name()` 又是对 `source_url` 的 `contains` 字符串嗅探，还有 `"unknown"`
+兜底分支。
+
+**改动**：
+
+1. `site/mod.rs`：`Fetched` 增加字段 `site_id: &'static str`（由各站点的
+   `impl From<SiteStruct> for Fetched` 填充；`empty_fetched` 同步填）。
+   `Fetched::site_name()` 改为 `return self.site_id`（保留方法名，删除
+   `source_url.contains` 嗅探与 `"unknown"` 分支）。
+2. `site/mod.rs`：新增 `pub fn site_id_from_key(key: &str) -> &'static str`
+   （解析 `"example:..."` 前缀，未知前缀返回 `"unknown"`），bot 缓存命中路径改用它，
+   与 `fetched.site_id` 口径统一。
+3. `handlers.rs:405`：`SetFormat` 白名单改为 `x_media::site::ids()`——阶段 1 先实现
+   `ids()` 为 `["twitter","bsky","pixiv"]` 的常量函数（数据源仍集中，行为不变），
+   阶段 3 再改为遍历注册表。
+4. `twitter/interface.rs:48-60` / `bsky` / `pixiv` 的 `From<SiteStruct> for Fetched`
+   各补 `site_id` 字段。
+
+**风险**：低。纯增量字段；`site_name()` 语义不变（测试 `pixiv/interface.rs:355`
+  已断言 `"pixiv"`）。
+**验证**：现有全部单测；`cache_key_normalizes_domain_variants` 等不变。
+**回滚**：revert 该提交。
+
+### 阶段 2：站点能力下沉（不引入 trait，静态分派）
+
+**动机**：把"每个站点自己才知道"的逻辑搬回站点模块，中央只做迭代。这是
+`AGENTS.md` 现有约定（无 trait）与完整注册表之间的折中，可独立交付。
+
+**改动**：每个站点模块新增并 `mod.rs` 重新导出：
+
+```rust
+// site/twitter/interface.rs（bsky/pixiv 同构）
+pub fn cache_key(url: &str) -> Option<String>;   // 用自身 PATTERN，返回 "twitter:<id>"
+pub fn is_retryable(err: &FetchError) -> bool;   // 默认 Http|Transient；pixiv 覆盖 PixivError 分支
+pub fn media_headers(url: &str) -> Option<Vec<(&'static str, String)>>;
+                                                 // pixiv: url 含 "pximg.net" → Referer
+```
+
+`site/mod.rs` 相应改为迭代三站：
+
+- `cache_key`：逐个调 `site::cache_key`，不再自己写 key 格式；
+- `fetch_error_is_retryable`：删除，`fetch()` 重试循环改调 `current_site::is_retryable`
+  （`fetch_once` 已能确定站点，把站点传下去）；
+- `media_size` / `download_media_limited` / `download_media_to_file` 里的
+  `pximg.net → Referer` 硬编码删除，改为遍历 `SITES`（阶段 2 是遍历
+  `[twitter, bsky, pixiv]` 静态列表）取 `media_headers(url)` 合并。
+
+**注意**：Referer 判定依据是媒体 URL 的 host（`pximg.net`），**不是**站点
+PATTERN（pixiv 的 PATTERN 只匹配 `pixiv.net/artworks/...`），所以 `media_headers`
+不能挂在 PATTERN 匹配上，必须按 URL 独立匹配——这正是把它做成独立函数的原因。
+
+**风险**：中。下载函数签名不变，行为必须逐字节不变；新增单元测试覆盖
+`media_headers("https://i.pximg.net/...") == Some(Referer)` 与
+`cache_key` 等价性（对全部既有用例断言新旧结果一致）。
+**回滚**：revert。
+
+### 阶段 3：Site trait + SITES 注册表（完整方案，可选）
+
+**动机**：加站点时 bot crate 与中央分派零改动；站点列表成为唯一注册点。
+
+**新增**（`site/mod.rs`，按实施后的实际形态）：
+
+```rust
+/// Boxed, Send future produced by a Site async method. Boxed so the trait
+/// stays dyn-compatible; Send because URL/queue workers tokio::spawn these.
+type SiteFuture<'a, T, E = FetchError> =
+    Pin<Box<dyn Future<Output = Result<T, E>> + Send + 'a>>;
+
+pub trait Site: Send + Sync {
+    fn id(&self) -> &'static str;
+    fn pattern(&self) -> &'static Regex;
+    fn enabled(&self) -> bool { true }                 // 默认: true
+    fn cache_key(&self, url: &str) -> Option<String>;
+    fn fetch_from_url<'a>(&'a self, url: &'a str) -> SiteFuture<'a, Fetched>;
+    fn is_retryable(&self, err: &FetchError) -> bool;  // 默认: Http|Transient
+    fn media_headers(&self, url: &str) -> Option<Vec<(&'static str, String)>>; // 默认: None
+    fn validate(&self) -> SiteFuture<'static, (), String>;  // 默认: Ok(())
+}
+
+static SITES: LazyLock<Vec<Box<dyn Site>>> = LazyLock::new(|| vec![
+    Box::new(twitter::TwitterSite), Box::new(bsky::BskySite), Box::new(pixiv::PixivSite),
+]);
+```
+
+- `fetch` → `find_site(url)`（注册表中首个 PATTERN 命中且 `enabled()` 的站点，
+  返回 `&'static dyn Site`）→ `site.fetch_from_url(url).await`；
+- `cache_key` / `site_ids()` / `site_id_from_key()` / `apply_media_headers()` /
+  `validate_all()` 全部遍历 `SITES`；`validate_all` 返回失败列表，pixiv 的
+  `Site::validate` 失败时自行 `disable()`；
+- `match_site`/`SiteKind`（阶段 2 的静态分派）与中央 `fetch_error_is_retryable`
+  删除，重试判定走 `site.is_retryable`；
+- `main.rs` 的 pixiv 特判 → `site::validate_all()` + 通用失败通知；
+- 保留各站点的 `PATTERN`/`enabled()`/`fetch_from_url()` 顶层导出（兼容既有
+  测试），trait impl 只是薄壳。
+
+**async 形态**（实施结论）：**原生 AFIT 不可行**。
+
+- 实测（rustc 1.95.0，edition 2024；**1.97.1 复测一致**）：trait 里写
+  `async fn` 报 "method is `async`"（非 dyn 兼容）；写反糖
+  `-> impl Future<...> + Send + '_` 报 "references an `impl Trait` type in its
+  return type"（同样非 dyn 兼容）；纯 RPITIT（无 `+ Send`）也一样。即：
+  **RPITIT/AFIT 目前无法用于 `Vec<Box<dyn Site>>` 注册表**，与早期设计的
+  判断相反。
+- **为什么**：dyn 分派要求调用方在编译期知道返回值大小以分配空间，而
+  `async fn`/RPITIT 返回不透明的 Future——这是"非定长返回值走 dyn"的普遍问题，
+  与 async 无关。Rust 1.75 稳定的 AFIT 只覆盖**静态分派**，dyn 路径被排除；
+  原生 dyn 支持（AFIDT）是 2026-2027 的已接受项目目标，尚未进入 stable。
+  参见 <https://rust-lang.github.io/rust-project-goals/2026/afidt-box.html>。
+- **采用 (a) 手写 `Pin<Box<dyn Future + Send + '_>>`**（`SiteFuture` 别名）：
+  零新依赖、dyn 兼容、future 保证 Send。签名噪音靠别名缓解；生命周期坑因
+  站点是无状态单元结构体 + `'a` 同时约束 `&self` 与 `url` 而完全可控
+  （future 只借用调用域内的 url）。
+- **(b) `async-trait`** 仍是可行备选（语法更干净、同样 box），但新增依赖；
+  本仓库采用 (a) 后无需引入。
+- 若未来 Rust 稳定版落地 AFIDT（调用点 `dyn_box!`），可平滑迁移回原生
+  `async fn`，实现体几乎不动。
+
+**风险**：中。动中央分派，但每站点行为不变；注册表迭代 + `find_site` 补单测
+（`fetch`/`cache_key` 对既有 URL 集合的结果与阶段 2 完全一致）。
+**回滚**：revert。
+
+### 阶段 4：FetchError 泛化（已实施）
+
+**改动**：`FetchError` 新增 `Site { site: &'static str, error: Box<dyn std::error::Error + Send + Sync> }`
+变体（`Display`/`source()` 同步）。**`Pixiv(PixivError)` 变体保留**（未迁移）——
+它已有完整的 `Display`/`source()`/`is_retryable` 处理，替换纯属 churn。`Site`
+变体默认永久性（各站点 `is_retryable` 都不匹配它）；需要可重试站点错误的站点
+应自行转换为 `Http`/`Transient` 再返回。
+
+**风险**：低（纯增量变体）。测试：`site_error_variant_displays_and_sources`。
+
+### 阶段 5：收尾
+
+- 更新 `AGENTS.md` 的 "Site adapter convention" 段：写新约定（注册表 + `impl Site` +
+  每站点 `cache_key`/`is_retryable`/`media_headers`），删除 "no trait" 表述；
+- `examples/fetch.rs` 不变（走 `site::fetch`）；
+- 新增站点 checklist 见 §4。
+
+## 4. 重构后新增站点 checklist
+
+```
+1. crates/x-media/src/site/example/{mod,interface,model}.rs   // 新模块
+2. impl Site for ExampleSite 并注册进 SITES                   // 注册一行
+3. （可选）token 读取 + validate() 实现                         // 启动校验自动生效
+── bot crate 零改动 ──
+```
+
+对比现状的 8-9 处，bot crate 完全不碰：`SetFormat` 白名单、格式查找口径、
+缓存 key、启动校验全部自动跟随注册表。
+
+## 5. 权衡与明确不做的事
+
+- **不做**：Media 类型扩展（`media.rs` + `MediaItemPayload` + `CachedMediaKind` +
+  send.rs 约 10+ 处 match 的 blast radius）——这是"新增媒体类型"的摩擦，与"新增
+  站点"正交，优先级低，保持现状。
+- **不做**：DI/全局注入改造（`CHAT_STORE`/`TASK_QUEUE`/`CONFIG` 的 `LazyLock` 静态
+  模式是仓库惯例，与站点扩展无关）。
+- **不做**：schema 迁移——新站点只产生新的 cache key 前缀与 `message_format` JSON
+  key，`link_cache`/`chat_state` 表结构均无需变化。
+- **代价**：阶段 3 引入 `dyn Site` 与 boxed future 签名（`SiteFuture`，见 §3）；
+  `Send` 约束前移到 trait 边界，站点 impl 的 future 必须 Send（现仅在各
+  `tokio::spawn` 点检查，重构后在 impl 处即报错，提前暴露问题）。
+  若站点数量长期 ≤5 且无新增迹象，阶段 2 的折中方案已够用；本次已按完整方案
+  实施到阶段 4。
+
+## 6. 提交序列（已按此实施）
+
+| 阶段 | 提交 | hash |
+|---|---|---|
+| 1 | `refactor(site): carry site_id on Fetched; unify cache-key site lookup` | `7ca8fd1` |
+| 2 | `refactor(site): move cache_key/is_retryable/media_headers into site modules` | `5e23916` |
+| 3 | `refactor(site): introduce Site trait and SITES registry` | `bf4e615` |
+| 4 | `refactor(site): genericize FetchError::Site` | `5679a8c` |
+| 5 | `docs: update site adapter convention in AGENTS.md` | 本文档收尾提交 |
+
+每阶段独立合入、独立回滚；阶段 2 完成后"加站点"摩擦已收敛，3/4 为深化。