Compare commits

...
2 Commits
Author SHA1 Message Date
Richard Zink b1fa54a7b6 Release v202611-00010 2026-11-09 20:21:42 +01:00
Richard ZinkandClaude Opus 5.5 e8e455b779 Store chat images separately; JPEG for large PNGs; gzip/brotli responses
Images of messages (pasted images, screenshots, generated images) were base64
inside the message JSON, so opening a chat downloaded all of them at once
(66 MB for a chat with 120 screenshots). They now live in a `blobs` table,
addressed by SHA-256; messages keep a reference (blob, size). The UI loads
them from /api/blobs/<hash> lazily with an immutable cache header, the runner
fills the bytes in before model requests, JSON exports stay self-contained.

- Store::add_message moves inline images out; large opaque PNGs become JPEG
  (q85) when smaller. Older chats are converted once at start-up in the
  background, unused images are removed (also after deleting a chat) and the
  database is vacuumed when that frees 32 MB or more.
- Responses are compressed with gzip/brotli (not images, SSE streams or
  binary downloads).

Example (copy of production): chat load 66 MB -> 1.5 MB (370 KB brotli),
database 90 MB -> 27 MB.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 20:21:24 +01:00
28 changed files with 475 additions and 32 deletions

No files matched your search

+12
View File
@@ -3,6 +3,18 @@
All notable changes to CodeCraft. Versions follow [Semantic Versioning](https://semver.org/);
until 1.0, minor versions may contain breaking changes.
## [v202611-00010] – 2026-11-09
### Changed
- **Chats with many images load much faster:** images (screenshots, generated images, pasted
images) are stored separately instead of inside the messages and load on demand when they
scroll into view, cached by the browser. Large PNGs without transparency are stored as JPEG.
Older chats are converted once on the first start; the database usually shrinks a lot.
Example: a chat with 120 screenshots loads 1.5 MB instead of 66 MB.
- **Compressed responses:** the API and the web UI are sent with gzip/brotli (not images,
downloads or live streams).
## [v202611-00009] – 2026-11-09
### Fixed
Generated
+67
View File
@@ -52,6 +52,21 @@ dependencies = [
"memchr",
]
[[package]]
name = "alloc-no-stdlib"
version = "3.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2fb6cfd47bf496ff64095c20eaba0c201404ee38714d4142fcfa1dc334fcc7a"
[[package]]
name = "alloc-stdlib"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b5c1865780388bfa186411ab5f247819487fc4864c6e9c3106611fa347586e1"
dependencies = [
"alloc-no-stdlib",
]
[[package]]
name = "allocator-api2"
version = "0.2.21"
@@ -153,6 +168,18 @@ dependencies = [
"password-hash",
]
[[package]]
name = "async-compression"
version = "0.4.52"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ad47a740fb906fffdd891e8b6d5fde2511600f7bfaebd68939fa08a14999459"
dependencies = [
"compression-codecs",
"compression-core",
"pin-project-lite",
"tokio",
]
[[package]]
name = "async-trait"
version = "0.1.92"
@@ -363,6 +390,27 @@ dependencies = [
"hybrid-array",
]
[[package]]
name = "brotli"
version = "9.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "627b7cfb0578f0eafce087a90fcd40add1231900b69e4d4de2d456260a4f5d81"
dependencies = [
"alloc-no-stdlib",
"alloc-stdlib",
"brotli-decompressor",
]
[[package]]
name = "brotli-decompressor"
version = "6.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "75c74c9c51b9140663e196b5fb88bc94c334d7a497c8311cb759d8557874747f"
dependencies = [
"alloc-no-stdlib",
"alloc-stdlib",
]
[[package]]
name = "bstr"
version = "1.13.1"
@@ -682,6 +730,24 @@ dependencies = [
"static_assertions",
]
[[package]]
name = "compression-codecs"
version = "0.4.47"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84f840cff84d10085260e460023934d0af699e71212b09b2a41452e8bd9cda43"
dependencies = [
"brotli",
"compression-core",
"flate2",
"memchr",
]
[[package]]
name = "compression-core"
version = "0.4.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2ebdda89edc534bf8d5dd2857562633b6495557e5846552ade994b99ed13c36a"
[[package]]
name = "const-oid"
version = "0.10.2"
@@ -4035,6 +4101,7 @@ version = "0.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08a05a66a4fdd61cbbe0a1d755ffe0ca6aba159dd4820936a0ff8a8278245b9c"
dependencies = [
"async-compression",
"bitflags 2.13.2",
"bytes",
"futures-core",
+1 -1
View File
@@ -11,7 +11,7 @@
</p>
<p align="center">
<img alt="Version v202611-00009" src="https://img.shields.io/badge/version-v202611--00009-d69e2e?style=flat-square">
<img alt="Version v202611-00010" src="https://img.shields.io/badge/version-v202611--00010-d69e2e?style=flat-square">
<img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-689d6a?style=flat-square">
<img alt="Rust backend" src="https://img.shields.io/badge/backend-Rust-b7410e?style=flat-square&logo=rust">
<img alt="React PWA" src="https://img.shields.io/badge/frontend-React%20PWA-2d81ff?style=flat-square&logo=react">
+2 -2
View File
@@ -421,7 +421,7 @@ impl App {
_ => None,
};
if let (Some(mt), Ok(bytes)) = (mt, std::fs::read(&path)) {
self.images.push(ImageData { media_type: mt.into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
self.images.push(ImageData { blob: None, size: None, media_type: mt.into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
}
}
}
@@ -840,7 +840,7 @@ impl App {
for (cmd, args) in tries {
if let Ok(out) = std::process::Command::new(cmd).args(*args).stderr(std::process::Stdio::null()).output() {
if out.status.success() && out.stdout.starts_with(b"\x89PNG") {
self.images.push(ImageData { media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(&out.stdout) });
self.images.push(ImageData { blob: None, size: None, media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(&out.stdout) });
self.status = format!("image {} attached", self.images.len());
return;
}
+1 -1
View File
@@ -408,7 +408,7 @@ pub async fn run(ctx: &Ctx, name: &str, input: &Value) -> Result<Output> {
return Ok(Output {
content: format!("Image {} ({} bytes)", rel(&ctx.cwd, &path), bytes.len()),
is_error: false,
images: vec![ImageData { media_type: mt.into(), data: base64::engine::general_purpose::STANDARD.encode(&bytes) }],
images: vec![ImageData { blob: None, size: None, media_type: mt.into(), data: base64::engine::general_purpose::STANDARD.encode(&bytes) }],
diff: None,
});
}
+16 -2
View File
@@ -10,11 +10,25 @@ pub enum Role {
Assistant,
}
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq)]
pub struct ImageData {
pub media_type: String,
/// Base64-encoded bytes.
/// Base64-encoded bytes. Empty when the image is stored separately (`blob`).
#[serde(default, skip_serializing_if = "String::is_empty")]
pub data: String,
/// Server only: SHA-256 of the bytes in the image store; the UI loads
/// /api/blobs/<blob> and the server fills `data` in before a model request.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub blob: Option<String>,
/// Size in bytes of a stored image (shown in the UI without fetching it).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub size: Option<u64>,
}
impl ImageData {
pub fn new(media_type: impl Into<String>, data: String) -> Self {
Self { media_type: media_type.into(), data, blob: None, size: None }
}
}
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
+1 -1
View File
@@ -38,7 +38,7 @@ tokio-tungstenite = "0.29"
tokio-util = "0.7"
toml = "1"
toml_edit = "0.25"
tower-http = { version = "0.7", features = ["fs", "cors", "trace"] }
tower-http = { version = "0.7", features = ["fs", "cors", "trace", "compression-gzip", "compression-br"] }
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
uuid = { version = "1", features = ["v4", "v7"] }
+39 -1
View File
@@ -80,6 +80,7 @@ pub fn router(app: AppState) -> Router {
.route("/sessions/{id}/worktree", get(worktree_status).post(worktree_action))
.route("/sessions/{id}/tabs", get(session_tabs).put(put_file_tabs))
.route("/sessions/{id}/export", get(export_session))
.route("/blobs/{hash}", get(get_blob))
.route("/sessions/{id}", get(get_session).patch(update_session).delete(delete_session))
.route("/sessions/{id}/prompt", post(prompt))
.route("/sessions/{id}/abort", post(abort))
@@ -181,9 +182,21 @@ pub fn router(app: AppState) -> Router {
.route("/cli/install.sh", get(cli_install_script))
.route("/cli/download/{target}", get(cli_download))
.fallback_service(static_files)
.layer(compression())
.with_state(app)
}
/// gzip/brotli for JSON, HTML, JS and CSS. Images and SSE streams are left alone (default
/// predicate), and so are binary downloads (already compressed or large).
fn compression() -> tower_http::compression::CompressionLayer<impl tower_http::compression::Predicate + Clone> {
use tower_http::compression::predicate::{DefaultPredicate, NotForContentType, Predicate};
let predicate = DefaultPredicate::new()
.and(NotForContentType::const_new("application/octet-stream"))
.and(NotForContentType::const_new("application/zip"))
.and(NotForContentType::const_new("application/gzip"));
tower_http::compression::CompressionLayer::new().compress_when(predicate)
}
fn cli_dir() -> PathBuf {
std::env::var("CODECRAFT_CLI_DIR").map(PathBuf::from).unwrap_or_else(|_| PathBuf::from("/app/cli"))
}
@@ -744,7 +757,8 @@ struct ExportQ {
/// Download a session as Markdown (default) or JSON.
async fn export_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<ExportQ>) -> Result<axum::response::Response, ApiError> {
let s = readable(&app, &user, &id)?;
let messages = app.store.messages(&id)?;
// JSON exports are self-contained: images inline instead of store references.
let messages = if q.format == "json" { app.store.messages_for_model(&id)? } else { app.store.messages(&id)? };
let base: String = s.title.chars().map(|c| if c.is_alphanumeric() || c == '-' { c } else { '_' }).collect::<String>().trim_matches('_').to_string();
let base = if base.is_empty() { format!("session-{}", &id[..8.min(id.len())]) } else { base };
let (body, mime, ext) = if q.format == "json" {
@@ -879,9 +893,33 @@ async fn delete_session(Extension(user): Extension<User>, State(app): State<AppS
crate::shells::kill_session(&app, &id);
app.terminals.kill_session(&id);
app.store.delete_session(&id)?;
// Images only this session used.
let a = app.clone();
tokio::task::spawn_blocking(move || {
if let Err(e) = a.store.gc_blobs() {
tracing::warn!("image cleanup: {e:#}");
}
});
Ok(Json(json!({"ok": true})))
}
/// An image of a chat message (see blobs.rs). Addressed by the SHA-256 of its bytes,
/// so it never changes and the browser may keep it.
async fn get_blob(Extension(_user): Extension<User>, State(app): State<AppState>, Path(hash): Path<String>) -> Result<axum::response::Response, ApiError> {
if !crate::blobs::is_hash(&hash) {
return Err(not_found("image"));
}
let (mime, bytes) = app.store.blob(&hash)?.ok_or_else(|| not_found("image"))?;
Ok((
[
(axum::http::header::CONTENT_TYPE, mime),
(axum::http::header::CACHE_CONTROL, "private, max-age=31536000, immutable".to_string()),
],
bytes,
)
.into_response())
}
#[derive(Deserialize)]
struct PromptBody {
text: String,
+23
View File
@@ -131,9 +131,32 @@ impl App {
});
crate::auth::bootstrap(&app)?;
app.clone().start_mcp();
app.clone().start_image_migration();
Ok(app)
}
/// Move inline images of older chats to the image store, drop unused images and
/// shrink the database file (in the background; chats load meanwhile as before).
fn start_image_migration(self: Arc<Self>) {
tokio::task::spawn_blocking(move || {
match self.store.migrate_inline_images() {
Ok(0) => {}
Ok(n) => tracing::info!("moved {n} images of older chats to the image store"),
Err(e) => tracing::warn!("moving images to the image store: {e:#}"),
}
match self.store.gc_blobs() {
Ok(0) => {}
Ok(n) => tracing::info!("removed {n} unused images"),
Err(e) => tracing::warn!("image cleanup: {e:#}"),
}
match self.store.vacuum_if_worthwhile() {
Ok(true) => tracing::info!("database compacted"),
Ok(false) => {}
Err(e) => tracing::warn!("database compaction: {e:#}"),
}
});
}
fn start_mcp(self: Arc<Self>) {
let servers = self.config().mcp.clone();
let mcp = self.mcp.clone();
+134
View File
@@ -0,0 +1,134 @@
//! Images of chat messages are stored in the `blobs` table instead of as base64 inside the
//! message JSON. A chat then loads without its images; the UI fetches them on demand from
//! /api/blobs/<hash> (cached by the browser), and the runner puts the bytes back in before
//! a model request. Large PNGs without transparency are stored as JPEG.
use crate::types::{ImageData, Message, Part};
use base64::Engine;
use sha2::{Digest, Sha256};
const B64: base64::engine::GeneralPurpose = base64::engine::general_purpose::STANDARD;
/// PNGs above this size are re-encoded as JPEG when that is smaller and loses no transparency.
const RECOMPRESS_ABOVE: usize = 100 * 1024;
const JPEG_QUALITY: u8 = 85;
/// An image to put into the store.
pub struct Blob {
pub hash: String,
pub media_type: String,
pub bytes: Vec<u8>,
}
/// Call `f` for every image of a message (pasted images and tool results).
pub fn for_each_image(m: &mut Message, mut f: impl FnMut(&mut ImageData)) {
for part in &mut m.parts {
match part {
Part::Image { image } => f(image),
Part::ToolResult { images, .. } => images.iter_mut().for_each(&mut f),
_ => {}
}
}
}
/// Move the inline images of `m` out: each becomes a reference (`blob`, `size`, no
/// `data`). Returns the blobs to store. Images that already are references stay as they are.
pub fn externalize(m: &mut Message) -> Vec<Blob> {
let mut out = Vec::new();
for_each_image(m, |img| {
if img.data.is_empty() {
return;
}
let Ok(raw) = B64.decode(img.data.as_bytes()) else { return };
let (media_type, bytes) = compact(&img.media_type, raw);
let hash = hash(&bytes);
img.media_type = media_type.clone();
img.data.clear();
img.blob = Some(hash.clone());
img.size = Some(bytes.len() as u64);
out.push(Blob { hash, media_type, bytes });
});
out
}
/// Whether `s` looks like a blob hash (64 lowercase hex digits).
pub fn is_hash(s: &str) -> bool {
s.len() == 64 && s.bytes().all(|b| b.is_ascii_digit() || (b'a'..=b'f').contains(&b))
}
fn hash(bytes: &[u8]) -> String {
Sha256::digest(bytes).iter().map(|b| format!("{b:02x}")).collect()
}
/// Re-encode a large opaque PNG as JPEG if that is smaller; anything else is kept.
fn compact(media_type: &str, raw: Vec<u8>) -> (String, Vec<u8>) {
if media_type != "image/png" || raw.len() <= RECOMPRESS_ABOVE {
return (media_type.to_string(), raw);
}
let Ok(img) = image::load_from_memory_with_format(&raw, image::ImageFormat::Png) else {
return (media_type.to_string(), raw);
};
if img.color().has_alpha() && img.to_rgba8().pixels().any(|p| p.0[3] != 255) {
return (media_type.to_string(), raw);
}
let mut jpeg = Vec::new();
let enc = image::codecs::jpeg::JpegEncoder::new_with_quality(&mut jpeg, JPEG_QUALITY);
if img.to_rgb8().write_with_encoder(enc).is_err() || jpeg.len() >= raw.len() {
return (media_type.to_string(), raw);
}
("image/jpeg".to_string(), jpeg)
}
#[cfg(test)]
mod tests {
use super::*;
use crate::types::Role;
fn png(w: u32, h: u32, alpha: u8) -> Vec<u8> {
// Noise, so the PNG is large and JPEG wins.
let img = image::RgbaImage::from_fn(w, h, |x, y| {
let v = (x.wrapping_mul(7919) ^ y.wrapping_mul(104_729)).wrapping_mul(2_654_435_761) >> 24;
image::Rgba([v as u8, (v >> 1) as u8, (v >> 2) as u8, alpha])
});
let mut buf = Vec::new();
img.write_to(&mut std::io::Cursor::new(&mut buf), image::ImageFormat::Png).unwrap();
buf
}
fn message(img: ImageData) -> Message {
let mut m = Message { id: "m1".into(), role: Role::User, parts: vec![], model: None, usage: None, created_at: 0 };
m.parts.push(Part::ToolResult { call_id: "c".into(), name: "browser".into(), content: String::new(), images: vec![img], is_error: false, meta: None });
m
}
#[test]
fn large_opaque_png_becomes_a_jpeg_reference() {
let raw = png(400, 400, 255);
let mut m = message(ImageData::new("image/png", B64.encode(&raw)));
let blobs = externalize(&mut m);
assert_eq!(blobs.len(), 1);
assert_eq!(blobs[0].media_type, "image/jpeg");
assert!(blobs[0].bytes.len() < raw.len());
let Part::ToolResult { images, .. } = &m.parts[0] else { panic!() };
assert!(images[0].data.is_empty());
assert_eq!(images[0].blob.as_deref(), Some(blobs[0].hash.as_str()));
assert_eq!(images[0].size, Some(blobs[0].bytes.len() as u64));
assert!(is_hash(&blobs[0].hash));
// Already a reference: nothing to do.
assert!(externalize(&mut m).is_empty());
}
#[test]
fn transparent_and_small_pngs_stay_png() {
let mut m = message(ImageData::new("image/png", B64.encode(png(400, 400, 128))));
assert_eq!(externalize(&mut m)[0].media_type, "image/png");
let mut m = message(ImageData::new("image/png", B64.encode(png(8, 8, 255))));
assert_eq!(externalize(&mut m)[0].media_type, "image/png");
}
#[test]
fn serialized_reference_has_no_data() {
let img = ImageData { media_type: "image/jpeg".into(), data: String::new(), blob: Some("ab".into()), size: Some(3) };
assert_eq!(serde_json::to_value(&img).unwrap(), serde_json::json!({"media_type": "image/jpeg", "blob": "ab", "size": 3}));
}
}
+1 -1
View File
@@ -129,7 +129,7 @@ async fn render_page(pdf: &str, page: u32) -> Result<ImageData> {
let img = img.resize(1568, 1568, image::imageops::FilterType::Triangle);
let mut buf = Vec::new();
img.write_to(&mut std::io::Cursor::new(&mut buf), image::ImageFormat::Png)?;
Ok(ImageData { media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(buf) })
Ok(ImageData { blob: None, size: None, media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(buf) })
}
fn spreadsheet(path: &Path, sheet: Option<&str>) -> Result<String> {
+1 -1
View File
@@ -258,7 +258,7 @@ fn preview_for_model(path: &Path) -> Option<ImageData> {
let img = img.resize(1024, 1024, image::imageops::FilterType::Triangle);
let mut buf = Vec::new();
img.write_to(&mut std::io::Cursor::new(&mut buf), image::ImageFormat::Png).ok()?;
Some(ImageData { media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(buf) })
Some(ImageData { blob: None, size: None, media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(buf) })
}
pub struct GenerateImage;
+1
View File
@@ -4,6 +4,7 @@ mod api;
mod app;
mod auth;
mod backup;
mod blobs;
mod cli_api;
mod budget;
mod config;
+2
View File
@@ -212,6 +212,8 @@ impl McpServer {
match c["type"].as_str().unwrap_or_default() {
"text" => texts.push(c["text"].as_str().unwrap_or_default().to_string()),
"image" => out.images.push(ImageData {
blob: None,
size: None,
media_type: c["mimeType"].as_str().unwrap_or("image/png").into(),
data: c["data"].as_str().unwrap_or_default().into(),
}),
+3 -3
View File
@@ -291,7 +291,7 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
let owner = session.owner_id.as_deref().and_then(|id| app.store.user(id).ok().flatten());
let tools = available_tools(&app, &agent, owner.as_ref());
let history = active_history(app.store.messages(session_id)?);
let history = active_history(app.store.messages_for_model(session_id)?);
let req = ChatRequest {
system: prompts::with_chat_instructions(prompts::system_prompt(&app, &agent, &root, &cwd, &model_spec, &session.permission_mode, owner.as_ref()), &session.instructions),
messages: history,
@@ -1126,7 +1126,7 @@ async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent,
model.effort = Some("medium".into());
app.emit(Event::Waiting { session_id: session.id.clone(), reason: Some(format!("review:{round}/{rounds}")) });
let result = async {
let history = active_history(app.store.messages(&session.id)?);
let history = active_history(app.store.messages_for_model(&session.id)?);
// The user's request: the last user message with text that is not feedback/tool output.
let req_idx = history
.iter()
@@ -1251,7 +1251,7 @@ pub async fn compact(app: Arc<App>, session_id: &str, cancel: CancellationToken,
async fn compact_inner(app: Arc<App>, session_id: &str, cancel: CancellationToken, auto: Option<(u64, u64)>) -> Result<()> {
let session = app.session(session_id)?;
let history = active_history(app.store.messages(session_id)?);
let history = active_history(app.store.messages_for_model(session_id)?);
if history.is_empty() {
return Ok(());
}
+129 -2
View File
@@ -1,6 +1,6 @@
//! SQLite persistence for sessions and messages.
use crate::types::{Message, Part, Session, now_ms};
use crate::types::{ImageData, Message, Part, Session, now_ms};
use serde::Serialize;
use serde_json::{Value, json};
use anyhow::Result;
@@ -90,6 +90,13 @@ impl Store {
created_at INTEGER NOT NULL
);
CREATE INDEX IF NOT EXISTS images_user ON images(user_id, created_at);
-- Images of messages, referenced by hash from the message JSON (see blobs.rs).
CREATE TABLE IF NOT EXISTS blobs (
hash TEXT PRIMARY KEY,
media_type TEXT NOT NULL,
data BLOB NOT NULL,
created_at INTEGER NOT NULL
);
CREATE TABLE IF NOT EXISTS queue (
id TEXT PRIMARY KEY,
session_id TEXT NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
@@ -274,12 +281,21 @@ impl Store {
}
pub fn add_message(&self, session_id: &str, m: &Message) -> Result<()> {
// Images go to the blob table (encoded before taking the lock).
let mut m = m.clone();
let blobs = crate::blobs::externalize(&mut m);
let conn = self.conn.lock().unwrap();
for b in &blobs {
conn.execute(
"INSERT OR IGNORE INTO blobs (hash, media_type, data, created_at) VALUES (?1, ?2, ?3, ?4)",
params![b.hash, b.media_type, b.bytes, now_ms()],
)?;
}
conn.execute(
"INSERT INTO messages (id, session_id, seq, data) VALUES (?1, ?2,
(SELECT COALESCE(MAX(seq), 0) + 1 FROM messages WHERE session_id = ?2), ?3)
ON CONFLICT(id) DO UPDATE SET data = excluded.data",
params![m.id, session_id, serde_json::to_string(m)?],
params![m.id, session_id, serde_json::to_string(&m)?],
)?;
conn.execute(
"UPDATE sessions SET updated_at = ?2 WHERE id = ?1",
@@ -300,6 +316,103 @@ impl Store {
Ok(out)
}
/// Messages with the bytes of their images filled in – for model requests and exports.
pub fn messages_for_model(&self, session_id: &str) -> Result<Vec<Message>> {
let mut out = self.messages(session_id)?;
let conn = self.conn.lock().unwrap();
let mut cache: std::collections::HashMap<String, String> = std::collections::HashMap::new();
for m in &mut out {
crate::blobs::for_each_image(m, |img| fill_image(&conn, &mut cache, img));
}
Ok(out)
}
/// Fill in the bytes of one image reference (no-op for inline images).
pub fn resolve_image(&self, img: &ImageData) -> ImageData {
let mut img = img.clone();
let conn = self.conn.lock().unwrap();
fill_image(&conn, &mut std::collections::HashMap::new(), &mut img);
img
}
/// One stored image: (media type, bytes).
pub fn blob(&self, hash: &str) -> Result<Option<(String, Vec<u8>)>> {
let conn = self.conn.lock().unwrap();
Ok(conn
.query_row("SELECT media_type, data FROM blobs WHERE hash = ?1", [hash], |r| Ok((r.get(0)?, r.get(1)?)))
.optional()?)
}
/// Move inline images of older messages to the blob table (once, after the update
/// that introduced it). Does not touch `updated_at` of the sessions.
pub fn migrate_inline_images(&self) -> Result<usize> {
let ids: Vec<String> = {
let conn = self.conn.lock().unwrap();
let mut stmt = conn.prepare("SELECT id FROM messages WHERE data LIKE '%\"media_type\"%\"data\":\"%'")?;
let rows = stmt.query_map([], |r| r.get(0))?.collect::<rusqlite::Result<Vec<String>>>()?;
rows
};
let mut moved = 0;
for id in ids {
let data: Option<String> = {
let conn = self.conn.lock().unwrap();
conn.query_row("SELECT data FROM messages WHERE id = ?1", [&id], |r| r.get(0)).optional()?
};
let Some(data) = data else { continue };
let Ok(mut m) = serde_json::from_str::<Message>(&data) else { continue };
let blobs = crate::blobs::externalize(&mut m);
if blobs.is_empty() {
continue;
}
let conn = self.conn.lock().unwrap();
for b in &blobs {
conn.execute(
"INSERT OR IGNORE INTO blobs (hash, media_type, data, created_at) VALUES (?1, ?2, ?3, ?4)",
params![b.hash, b.media_type, b.bytes, now_ms()],
)?;
}
conn.execute("UPDATE messages SET data = ?2 WHERE id = ?1", params![id, serde_json::to_string(&m)?])?;
moved += blobs.len();
}
Ok(moved)
}
/// Delete images no message refers to any more (deleted or truncated sessions).
pub fn gc_blobs(&self) -> Result<usize> {
let conn = self.conn.lock().unwrap();
let mut used = std::collections::HashSet::new();
let mut stmt = conn.prepare("SELECT data FROM messages WHERE data LIKE '%\"blob\":\"%'")?;
let mut rows = stmt.query([])?;
while let Some(row) = rows.next()? {
let data: String = row.get(0)?;
for (i, _) in data.match_indices("\"blob\":\"") {
if let Some(h) = data.get(i + 8..i + 72) {
used.insert(h.to_string());
}
}
}
drop(rows);
drop(stmt);
let all: Vec<String> = conn.prepare("SELECT hash FROM blobs")?.query_map([], |r| r.get(0))?.collect::<rusqlite::Result<_>>()?;
let mut removed = 0;
for h in all.iter().filter(|h| !used.contains(*h)) {
removed += conn.execute("DELETE FROM blobs WHERE hash = ?1", [h])?;
}
Ok(removed)
}
/// Give the space of deleted data back to the file system when it is worth it.
pub fn vacuum_if_worthwhile(&self) -> Result<bool> {
let conn = self.conn.lock().unwrap();
let free: i64 = conn.query_row("PRAGMA freelist_count", [], |r| r.get(0))?;
let page: i64 = conn.query_row("PRAGMA page_size", [], |r| r.get(0))?;
if free * page < 32 * 1024 * 1024 {
return Ok(false);
}
conn.execute_batch("VACUUM")?;
Ok(true)
}
/// Remove all messages after (and including) the given one – used for "edit & resend".
pub fn truncate_from(&self, session_id: &str, message_id: &str) -> Result<()> {
let conn = self.conn.lock().unwrap();
@@ -312,6 +425,20 @@ impl Store {
}
}
/// Put the bytes of a stored image into `img.data`.
fn fill_image(conn: &Connection, cache: &mut std::collections::HashMap<String, String>, img: &mut ImageData) {
use base64::Engine;
let Some(hash) = img.blob.clone().filter(|_| img.data.is_empty()) else { return };
if !cache.contains_key(&hash) {
let Ok(bytes) = conn.query_row("SELECT data FROM blobs WHERE hash = ?1", [&hash], |r| r.get::<_, Vec<u8>>(0)) else {
tracing::warn!("image {hash} is missing in the store");
return;
};
cache.insert(hash.clone(), base64::engine::general_purpose::STANDARD.encode(bytes));
}
img.data = cache[&hash].clone();
}
/// One model request, as recorded for statistics.
#[derive(Debug, Clone, Serialize)]
pub struct UsageRecord {
+4 -4
View File
@@ -354,13 +354,13 @@ async fn handle_update(app: &Arc<App>, user_id: &str, bot: &Bot, u: &Value) -> R
let mut notes = Vec::new();
if let Some(photo) = m["photo"].as_array().and_then(|p| p.last()) {
let (bytes, _) = bot.download(photo["file_id"].as_str().unwrap_or("")).await?;
images.push(ImageData { media_type: "image/jpeg".into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
images.push(ImageData { blob: None, size: None, media_type: "image/jpeg".into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
}
if let Some(doc) = m.get("document") {
let mime = doc["mime_type"].as_str().unwrap_or("");
let (bytes, path) = bot.download(doc["file_id"].as_str().unwrap_or("")).await?;
if mime.starts_with("image/") && bytes.len() < 10 * 1024 * 1024 {
images.push(ImageData { media_type: mime.into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
images.push(ImageData { blob: None, size: None, media_type: mime.into(), data: base64::engine::general_purpose::STANDARD.encode(bytes) });
} else {
let name = doc["file_name"].as_str().map(String::from).unwrap_or_else(|| path.rsplit('/').next().unwrap_or("file").to_string());
let rel = save_upload(&session, &name, &bytes)?;
@@ -876,7 +876,7 @@ async fn listen(app: Arc<App>) {
}
#[allow(clippy::too_many_arguments)]
async fn on_event(_app: &App, bot: &Bot, chat: i64, de: bool, session: &Session, is_current: bool, ev: &Event, progress: &mut HashMap<String, Progress>) -> Result<()> {
async fn on_event(app: &App, bot: &Bot, chat: i64, de: bool, session: &Session, is_current: bool, ev: &Event, progress: &mut HashMap<String, Progress>) -> Result<()> {
let sid = session.id.clone();
match ev {
// Approvals and questions of every own session: the agent waits for them.
@@ -947,7 +947,7 @@ async fn on_event(_app: &App, bot: &Bot, chat: i64, de: bool, session: &Session,
for part in &message.parts {
if let Part::ToolResult { images, name, .. } = part {
for img in images {
let _ = bot.send_photo(chat, img, Some(name)).await;
let _ = bot.send_photo(chat, &app.store.resolve_image(img), Some(name)).await;
}
}
}
+1 -1
View File
@@ -186,7 +186,7 @@ impl Tool for OpenScad {
continue;
}
if let Ok(bytes) = std::fs::read(&out) {
images.push(ImageData { media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(&bytes) });
images.push(ImageData { blob: None, size: None, media_type: "image/png".into(), data: base64::engine::general_purpose::STANDARD.encode(&bytes) });
files.push(out);
}
}
+2
View File
@@ -27,6 +27,8 @@ pub(crate) fn png_for_model(img: &image::DynamicImage) -> Result<ImageData> {
let mut buf = Vec::new();
img.write_to(&mut Cursor::new(&mut buf), ImageFormat::Png)?;
Ok(ImageData {
blob: None,
size: None,
media_type: "image/png".into(),
data: base64::engine::general_purpose::STANDARD.encode(&buf),
})
+2
View File
@@ -107,6 +107,8 @@ impl Tool for Read {
return Ok(ToolOutput {
content: format!("Image {} ({} bytes)", rel(ctx, &path), bytes.len()),
images: vec![ImageData {
blob: None,
size: None,
media_type: mt.into(),
data: base64::engine::general_purpose::STANDARD.encode(&bytes),
}],
+3 -3
View File
@@ -1,6 +1,6 @@
import { takePrefill } from "../share";
import { Icon } from "./Icon";
import { base64Size, FileChip, FileFigure, fileType } from "./FileFigure";
import { FileChip, FileFigure, fileType, imageSize, imageSrc } from "./FileFigure";
import { useEffect, useLayoutEffect, useMemo, useRef, useState } from "react";
import { del, get, patch, post } from "../api";
import { useModels } from "../hooks";
@@ -471,8 +471,8 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
{imgs.length > 0 && (
<div className="user-files">
{imgs.map((p, i) => (
<FileFigure key={i} name={`image-${i + 1}.${fileType(undefined, p.image.media_type).toLowerCase()}`} mime={p.image.media_type} size={base64Size(p.image.data)}>
<img src={`data:${p.image.media_type};base64,${p.image.data}`} alt="" />
<FileFigure key={i} name={`image-${i + 1}.${fileType(undefined, p.image.media_type).toLowerCase()}`} mime={p.image.media_type} size={imageSize(p.image)}>
<img src={imageSrc(p.image)} alt="" loading="lazy" decoding="async" />
</FileFigure>
))}
</div>
+2 -2
View File
@@ -1,6 +1,6 @@
import { TemplatePicker } from "./TemplatePicker";
import { Icon } from "./Icon";
import { formatSize } from "./FileFigure";
import { formatSize, imageSrc } from "./FileFigure";
import { uploadFile } from "../api";
import { useEffect, useMemo, useRef, useState } from "react";
import { useAgents, useFetch, useModels } from "../hooks";
@@ -257,7 +257,7 @@ export function Composer({
)}
{images.map((img, i) => (
<div className="att" key={i}>
<img src={`data:${img.media_type};base64,${img.data}`} alt="" />
<img src={imageSrc(img)} alt="" />
<button onClick={() => setImages((cur) => cur.filter((_, j) => j !== i))} aria-label={t("common.remove")}>
<Icon name="close" />
</button>
+11
View File
@@ -1,5 +1,6 @@
import { Icon } from "./Icon";
import { useEffect, useState, type ReactNode } from "react";
import type { ImageData } from "../types";
/** Human-readable file size. */
export function formatSize(n: number) {
@@ -32,6 +33,16 @@ export function basename(p: string) {
}
/** Bytes of a base64 payload. */
/** URL of an image of a message: inline (data URL) or from the image store. */
export function imageSrc(img: ImageData) {
return img.data ? `data:${img.media_type};base64,${img.data}` : `/api/blobs/${img.blob}`;
}
/** Size in bytes of an image of a message. */
export function imageSize(img: ImageData) {
return img.data ? base64Size(img.data) : img.size;
}
export function base64Size(b64: string) {
const pad = b64.endsWith("==") ? 2 : b64.endsWith("=") ? 1 : 0;
return Math.floor((b64.length * 3) / 4) - pad;
+2 -2
View File
@@ -5,7 +5,7 @@ import { useAgents, useFetch } from "../hooks";
import { useT, type Key } from "../i18n";
import type { ImageData } from "../types";
import { readImage } from "./Composer";
import { formatSize } from "./FileFigure";
import { formatSize, imageSrc } from "./FileFigure";
import { ModelSelect } from "./ModelSelect";
import { takePrefill } from "../share";
@@ -478,7 +478,7 @@ export function NewSession({ onMenu, onCreated }: { onMenu: () => void; onCreate
<div className="attachments">
{images.map((img, i) => (
<div className="att" key={`i${i}`}>
<img src={`data:${img.media_type};base64,${img.data}`} alt="" />
<img src={imageSrc(img)} alt="" />
<button onClick={() => setImages((c) => c.filter((_, j) => j !== i))} aria-label={t("common.remove")}>
<Icon name="close" />
</button>
+2 -1
View File
@@ -3,6 +3,7 @@ import { del, post } from "../api";
import { useT } from "../i18n";
import { useStore } from "../store";
import type { QueueItem } from "../types";
import { imageSrc } from "./FileFigure";
import { confirmDialog, promptDialog, toast } from "../dialogs";
const EMPTY: QueueItem[] = [];
@@ -30,7 +31,7 @@ export function QueueList({ sessionId, busy }: { sessionId: string; busy: boolea
{it.source === "background" && <span className="chip">{t("tool.background")}</span>}
<span className="queue-text">{it.source === "background" ? t("queue.backgroundResult") : text || "—"}</span>
{images.map((p, i) => (
<img key={i} src={`data:${p.image.media_type};base64,${p.image.data}`} alt="" />
<img key={i} src={imageSrc(p.image)} alt="" />
))}
{it.source !== "background" && (
<button
+3 -3
View File
@@ -1,5 +1,5 @@
import { Icon } from "./Icon";
import { base64Size, FileFigure } from "./FileFigure";
import { FileFigure, imageSize, imageSrc } from "./FileFigure";
import { useT } from "../i18n";
import { navigate } from "../router";
import { useStore } from "../store";
@@ -166,8 +166,8 @@ export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; r
</div>
) : (
result?.images?.map((img, i) => (
<FileFigure key={i} name={typeof call.input?.path === "string" ? call.input.path : undefined} mime={img.media_type} size={base64Size(img.data)}>
<img src={`data:${img.media_type};base64,${img.data}`} alt="" />
<FileFigure key={i} name={typeof call.input?.path === "string" ? call.input.path : undefined} mime={img.media_type} size={imageSize(img)}>
<img src={imageSrc(img)} alt="" loading="lazy" decoding="async" />
</FileFigure>
))
)}
+6 -1
View File
@@ -2,7 +2,12 @@
export interface ImageData {
media_type: string;
data: string;
/** Base64 bytes; absent when the server stores the image separately (blob). */
data?: string;
/** SHA-256 of a stored image: GET /api/blobs/<blob>. */
blob?: string;
/** Size in bytes of a stored image. */
size?: number;
}
export type Part =
+4
View File
@@ -3,6 +3,10 @@
* under "unreleased"; scripts/release.sh renames the key to the release version.
*/
export const WHATS_NEW: Record<string, { en: string[]; de: string[] }> = {
"202611-00010": {
en: ["Chats with many images (screenshots, generated images) open much faster – images load when they scroll into view"],
de: ["Chats mit vielen Bildern (Screenshots, generierte Bilder) öffnen viel schneller – Bilder laden erst beim Hinscrollen"],
},
"202611-00008": {
en: ["Instructions per chat: ⋯ → Instructions for this chat (Telegram: /prompt)"],
de: ["Anweisungen pro Chat: ⋯ → Anweisungen für diesen Chat (Telegram: /prompt)"],