Release v202611-00022

Palette from the Tintenblau desktop theme (colors.toml, neovim.lua, zed.json):
ink blue with cream text, paper with dark ink. Also in the terminal client's
palettes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

CHANGELOG.md

@@ -3,6 +3,112 @@
 All notable changes to CodeCraft. Versions follow [Semantic Versioning](https://semver.org/);
 until 1.0, minor versions may contain breaking changes.
 
+## [v202611-00022] – 2026-11-11
+
+### Added
+
+- **Theme "Tintenblau"** (dark: ink blue with cream text; light: paper with dark ink), from the
+  Tintenblau desktop theme; also in the terminal client.
+
+## [v202611-00021] – 2026-11-11
+
+### Added
+
+- **Commits of agents name the model:** every `git commit` an agent makes gets the trailer
+  `Co-Authored-By: <model> (<provider>) via CodeCraft` (a git wrapper in the agent shell, also in
+  the sandbox; your own commits stay unchanged). The text is set under *Settings → General*
+  (`server.commit_trailer`, `{model}`, `{provider}`, `{model_id}`; empty = off).
+
+## [v202611-00020] – 2026-11-11
+
+### Added
+
+- **Reverse engineering outside craft:** *Settings → Agents & commands* can give any mode the
+  `binary_info` and `decompile` (Ghidra) tools; the clean-room rule stays a craft rule.
+- **Raw firmware in `decompile`:** optional `processor` (Ghidra language id, e.g.
+  `ARM:LE:32:Cortex`) and `base_address` for images without a file format (.bin, converted .hex).
+- **Skill "reverse-engineering":** how to identify, decompile and explore programs and firmware
+  (processor table for common chips, HEX conversion, notes in `analysis/`).
+
+## [v202611-00019] – 2026-11-11
+
+### Added
+
+- **Search in a chat:** the magnifier in the chat's top bar searches all of it (messages, tool
+  output) on the server; a hit loads its part of the chat and marks the message.
+- **Media of a chat:** *⋯ → Media* shows every image, video and audio file of the chat and its
+  subagents – generated images, screenshots, files the agent wrote, media in answers, your
+  attachments – filterable, large view, "show in chat" jumps to the message.
+
+### Changed
+
+- **Long chats stay fast:** a chat opens with its messages since the last summary (at most 200);
+  older ones load when scrolling up, the history before a summary on request. Finished turns
+  fold into one line ("42 steps · 3 files", the answer stays visible). Typing, streaming and
+  status changes no longer re-render the whole history, and tool output is only built when a
+  card is opened. Measured with a chat of 5,900 messages: opening 9 s → 0.7 s (phone-like
+  CPU: 22 s → 1 s), typing 440 ms → 25 ms per key.
+
+## [v202611-00018] – 2026-11-10
+
+### Added
+
+- **Enforced reviews:** when a review is configured for a mode, every todo the agent marks
+  completed is reviewed; with findings the todo is reopened and the agent has to fix them and
+  complete it again (up to the configured rounds per todo). Ending the turn with open todos sends
+  the agent back to work as long as it makes progress – for unattended runs, e.g. overnight
+  (such modes may take up to 2,000 steps per turn). The chat shows passed reviews and these
+  reminders; *Settings → Modes* can switch it off per mode (then only one review at the end of a
+  turn, as before).
+- **Max input per model:** providers that limit the input below the context window (e.g. 272k of
+  400k) are taken into account; fetched from the model catalogue, editable in the provider settings.
+
+### Fixed
+
+- **Context overflow instead of compaction** (e.g. DeepSeek V4.1 Flash with 384k max output):
+  requests asked for the model's full max output, and providers count input + output against the
+  window, so long chats failed before automatic compaction kicked in. The output budget is now what
+  the window leaves, the chat is compacted when no reasonable room for an answer is left, and a
+  "context too long" error compacts and retries once instead of stopping. A turn that hits the
+  step limit now says so.
+
+## [v202611-00017] – 2026-11-10
+
+### Added
+
+- **Markdown in your messages:** your messages are shown formatted like the model's answers
+  (headings, lists, tables, code blocks, quotes, bold/italic); single line breaks stay as typed.
+  The eye button next to the text field shows a preview of the formatted message before sending.
+
+## [v202611-00016] – 2026-11-10
+
+### Fixed
+
+- **Phone: page stayed shifted after the keyboard closed** – the top bar (menu) was out of
+  reach. On Android the keyboard now shrinks the page instead of shifting it
+  (`interactive-widget=resizes-content`; the chat stays at its latest message); browsers that
+  still shift the page (iOS Safari) get it scrolled back once the keyboard closes.
+
+## [v202611-00015] – 2026-11-10
+
+### Fixed
+
+- **Generated images missing on other devices:** when an agent moved or renamed a generated
+  image afterwards (e.g. sorted it into subfolders), the gallery pointed to the old file – only
+  the device that had it in its browser cache still showed it. Now:
+  - generated images are also kept in the image store and shown from there when the file is gone
+    (existing images get their copy on the first start);
+  - their entries follow moves and renames: after an agent's `mv`/`rename`, when moved with the
+    file manager, and on the next view (found by file name, or by content when renamed);
+  - in the chat, an image that cannot be found falls back to the preview the model saw.
+
+## [v202611-00014] – 2026-11-10
+
+### Added
+
+- **New folder in the folder picker:** creating an automation or a chat, *New folder* creates a
+  subfolder of the shown folder and selects it.
+
 ## [v202611-00013] – 2026-11-10
 
 ### Added

Dockerfile

@@ -96,6 +96,8 @@ COPY --from=cli /out /app/cli
 # Used with a mounted /var/run/docker.sock (see docs/MOVING.md, --docker-sock).
 COPY --from=dockercli /docker /usr/local/bin/docker
 COPY server/ghidra /app/ghidra
+# git for agent shells: commits get the co-author trailer of the model (server.commit_trailer).
+COPY --chmod=755 docker/git-coauthor /usr/local/lib/codecraft/bin/git
 COPY server/resources /app/resources
 # The agent's home lives on the data volume: tools it installs in user space
 # (pip --user, pipx, rustup, npm -g, downloaded binaries) survive rebuilds.

README.md

@@ -11,7 +11,7 @@
 </p>
 
 <p align="center">
-  <img alt="Version v202611-00013" src="https://img.shields.io/badge/version-v202611--00013-d69e2e?style=flat-square">
+  <img alt="Version v202611-00022" src="https://img.shields.io/badge/version-v202611--00022-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">
@@ -296,6 +296,7 @@ in turn are based on:
 | Coffee | Dark, Latte | [megabyte0x/omarchy-coffee-theme](https://github.com/megabyte0x/omarchy-coffee-theme) | MIT |
 | Solarized | Dark, Light | [Solarized by Ethan Schoonover](https://ethanschoonover.com/solarized/) | MIT |
 | Tokyo Night | Night, Day | [folke/tokyonight.nvim](https://github.com/folke/tokyonight.nvim) | Apache-2.0 |
+| Tintenblau | Dark, Light | original (zink/tintenblau desktop theme) | private |
 
 Further standard themes (palettes re-created from the published colour specifications):
 

cli/src/palettes.json

@@ -701,6 +701,60 @@
 "syntax-type": "#b58900",
 "syntax-variable": "#586e75"
 },
+"tintenblau-dark": {
+"accent": "#7aa0cc",
+"accent2": "#d4b46a",
+"aqua": "#96b4bc",
+"bg0": "#232a44",
+"bg1": "#2b3352",
+"bg2": "#353e60",
+"bg3": "#4a5478",
+"blue": "#7aa0cc",
+"fg0": "#f5efe3",
+"fg1": "#eae4d6",
+"fg2": "#d6d0c2",
+"fg3": "#bdcfd4",
+"green": "#96b4bc",
+"muted": "#8e96b4",
+"on-accent": "#232a44",
+"purple": "#c896b2",
+"red": "#d47a6a",
+"syntax-comment": "#8e96b4",
+"syntax-function": "#7aa0cc",
+"syntax-keyword": "#c896b2",
+"syntax-meta": "#baa0c4",
+"syntax-number": "#96b4bc",
+"syntax-string": "#d47a6a",
+"syntax-type": "#d4b46a",
+"syntax-variable": "#eae4d6"
+},
+"tintenblau-light": {
+"accent": "#2a3f6f",
+"accent2": "#6a4a2c",
+"aqua": "#3a5a6a",
+"bg0": "#f0ead9",
+"bg1": "#e6dfd0",
+"bg2": "#dbd3c1",
+"bg3": "#c9c0ac",
+"blue": "#3a5a8a",
+"fg0": "#0f1628",
+"fg1": "#1e2a4a",
+"fg2": "#3a3f5a",
+"fg3": "#5e5a6a",
+"green": "#4a5a3a",
+"muted": "#8a8694",
+"on-accent": "#f0ead9",
+"purple": "#5a4a72",
+"red": "#8a3028",
+"syntax-comment": "#8a8694",
+"syntax-function": "#3a5a6a",
+"syntax-keyword": "#2a3f6f",
+"syntax-meta": "#4a5a3a",
+"syntax-number": "#5a4a72",
+"syntax-string": "#8a3028",
+"syntax-type": "#6a4a2c",
+"syntax-variable": "#1e2a4a"
+},
 "tokyonight-dark": {
 "accent": "#7aa2f7",
 "accent2": "#ff9e64",

core/src/config.rs

@@ -64,6 +64,9 @@ pub struct ModelConfig {
     pub context: Option<u64>,
     #[serde(default)]
     pub max_output: Option<u64>,
+    /// Input limit when the provider sets one below the context window (e.g. 272k of 400k).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub max_input: Option<u64>,
     #[serde(default)]
     pub reasoning: bool,
     #[serde(default)]

docker/git-coauthor

@@ -0,0 +1,21 @@
+#!/bin/bash
+# git for the shells of CodeCraft agents: `git commit` gets the co-author trailer from
+# $CODECRAFT_COMMIT_TRAILER (model, provider, CodeCraft). Everything else goes to the real
+# git unchanged. Git itself skips the trailer when the message already ends with it.
+real=${CODECRAFT_REAL_GIT:-/usr/bin/git}
+[[ -n $CODECRAFT_COMMIT_TRAILER ]] || exec "$real" "$@"
+# The subcommand comes after git's global options (-C dir, -c key=value, --git-dir=…).
+i=1
+while (( i <= $# )); do
+  case ${!i} in
+    -C | -c | --git-dir | --work-tree | --namespace | --exec-path | --config-env) i=$((i + 2)) ;;
+    --) break ;;
+    -*) i=$((i + 1)) ;;
+    *) break ;;
+  esac
+done
+if (( i <= $# )) && [[ ${!i} == commit ]]; then
+  # Right after "commit", so it stays an option even before "-- <paths>".
+  exec "$real" "${@:1:i}" --trailer "$CODECRAFT_COMMIT_TRAILER" "${@:i+1}"
+fi
+exec "$real" "$@"

server/resources/skills/reverse-engineering/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: reverse-engineering
+description: Analyse programs and firmware – identify the format, inspect with binary_info, decompile with Ghidra (decompile tool, also raw firmware with processor/base address), explore the output and write down findings. For file formats, protocols, bugs and interoperability.
+---
+# Reverse engineering of programs and firmware
+
+You analyse a binary to understand how it works – a file format, a protocol, an algorithm,
+a bug, or how to talk to a device. Work from cheap to expensive and write down what you learn.
+
+Only analyse binaries the user owns or may analyse (their own builds, their devices, programs
+for interoperability). Decompiled code is third-party material: never commit it and never paste
+it into the user's source – describe behaviour in your own words.
+
+## 1. Identify
+- `file <path>` – format, architecture, stripped or not.
+- Executables and libraries (PE .exe/.dll, ELF, Mach-O): `binary_info` – sections, imports,
+  exports, strings. Imports and strings tell a lot (file names, error messages, protocol
+  keywords, library names) before any decompiling.
+- Archives and update packages: unpack first (`unzip`, `7z x`), then identify the parts.
+- Intel HEX / S-record firmware: convert to a raw image –
+  `objcopy -I ihex -O binary fw.hex fw.bin` (the lowest address in the HEX file is the base
+  address). An ELF from the firmware's build (e.g. `zephyr.elf`, `firmware.elf`) is far better
+  than a raw image: symbols and addresses are included – look for it first.
+- Raw images: look for clues with `strings -n 6 fw.bin | head -200` and
+  `python3 -c` one-liners (vector table, magic numbers, embedded file systems).
+
+## 2. Raw firmware: processor and load address
+`decompile` needs both for images without a file format:
+
+| Chip family | `processor` | typical `base_address` |
+|---|---|---|
+| ARM Cortex-M (STM32, nRF52, RP2040, SAMD) | `ARM:LE:32:Cortex` | STM32 `0x08000000`, nRF52 `0x00000000`, RP2040 `0x10000000` |
+| ARM Cortex-A / ARMv7 | `ARM:LE:32:v7` | from the bootloader / datasheet |
+| AArch64 | `AARCH64:LE:64:v8A` | |
+| ESP32 (Xtensa) | `Xtensa:LE:32:default` | per segment (use the ELF if possible) |
+| AVR (Arduino) | `AVR8:LE:16:atmega256` or `AVR8:LE:16:default` | `0x0` |
+| MIPS (routers) | `MIPS:BE:32:default` or `MIPS:LE:32:default` | e.g. `0x80000000` |
+
+Cortex-M check: the first word of the image is the initial stack pointer (0x2000xxxx = RAM),
+the second the reset vector – it points just behind the base address. If the decompiled output
+is mostly garbage, the processor or base address is wrong: fix it and run again (results are
+cached per file *and* processor/address).
+
+## 3. Decompile
+- `decompile` with the path (plus `processor`/`base_address` for raw images). Large programs:
+  start with `max_functions` (e.g. 2000), widen when needed.
+- Output in `.codecraft/decompiled/<name>/`: `functions.tsv` (address, name, size, file,
+  signature), `functions/*.c`, `strings.tsv`, `imports.tsv`, `exports.tsv`.
+
+## 4. Explore
+- Start from what you know: a string, an import or an export.
+  `grep -l "SetCommState" .codecraft/decompiled/<name>/functions` finds the functions that use it.
+- Follow the calls by reading the functions; note addresses (`FUN_00401a30`) as you go.
+- Broad searches through thousands of functions: delegate them to an `explore` subagent with a
+  precise question and let it report file:line.
+- File formats: compare the reading/writing code with a sample file (`python3` to dump the bytes)
+  until every field is explained.
+
+## 5. Write it down
+Keep findings in `analysis/notes.md` (create it; it is not committed): structure of the
+program, important functions with addresses, data structures, file formats and protocols with
+field tables, open questions. Make sure `.gitignore` excludes `analysis/`, `original/` and
+`.codecraft/decompiled/`. At the end, report what you found and how sure you are – mark guesses
+as guesses.

server/src/api.rs

@@ -81,6 +81,9 @@ pub fn router(app: AppState) -> Router {
         .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}/messages", get(session_messages))
+        .route("/sessions/{id}/search", get(search_in_session))
+        .route("/sessions/{id}/media", get(session_media))
         .route("/sessions/{id}", get(get_session).patch(update_session).delete(delete_session))
         .route("/sessions/{id}/prompt", post(prompt))
         .route("/sessions/{id}/abort", post(abort))
@@ -813,14 +816,81 @@ async fn export_session(Extension(user): Extension<User>, State(app): State<AppS
         .into_response())
 }
 
-async fn get_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> ApiResult {
+#[derive(Deserialize)]
+struct WindowQ {
+    /// Only the end of the chat (from the last summary on, at most this many messages);
+    /// without it, all messages (terminal client).
+    limit: Option<i64>,
+    before: Option<String>,
+    after: Option<String>,
+    around: Option<String>,
+    /// Loading older messages stops at a summary (the history before it on request).
+    #[serde(default)]
+    stop_at_summary: bool,
+}
+
+impl WindowQ {
+    fn window(&self) -> Option<crate::store::MessageWindow> {
+        use crate::store::MessageWindow as W;
+        let limit = self.limit.unwrap_or(200).clamp(1, 1000);
+        Some(match (&self.before, &self.after, &self.around) {
+            (Some(id), _, _) => W::Before { id: id.clone(), limit, stop_at_summary: self.stop_at_summary },
+            (_, Some(id), _) => W::After { id: id.clone(), limit },
+            (_, _, Some(id)) => W::Around { id: id.clone(), limit },
+            _ if self.limit.is_some() => W::Tail { limit },
+            _ => return None,
+        })
+    }
+}
+
+async fn get_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<WindowQ>) -> ApiResult {
     let s = readable(&app, &user, &id)?;
-    let messages = app.store.messages(&id)?;
     let busy = app.is_busy(&id);
     let can_write = app.access(&user, &id) == Access::Full;
     let queue = app.store.queue_list(&id)?;
     let step = app.with_runtime(&id, |r| r.step.clone());
-    Ok(Json(json!({"session": s, "messages": messages, "busy": busy, "can_write": can_write, "queue": queue, "step": step})))
+    let mut out = json!({"session": s, "busy": busy, "can_write": can_write, "queue": queue, "step": step});
+    match q.window() {
+        Some(w) => {
+            let (messages, older, newer) = app.store.messages_window(&id, &w)?;
+            out["messages"] = json!(messages);
+            out["has_older"] = json!(older);
+            out["has_newer"] = json!(newer);
+        }
+        None => out["messages"] = json!(app.store.messages(&id)?),
+    }
+    Ok(Json(out))
+}
+
+/// More messages of a chat: before / after / around a message.
+async fn session_messages(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<WindowQ>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    let w = q.window().ok_or_else(|| ApiError(StatusCode::BAD_REQUEST, "before, after, around or limit is required".into()))?;
+    let (messages, older, newer) = app.store.messages_window(&id, &w).map_err(|e| ApiError(StatusCode::NOT_FOUND, format!("{e:#}")))?;
+    Ok(Json(json!({"messages": messages, "has_older": older, "has_newer": newer})))
+}
+
+/// Images, videos and audio files shown in a chat (all of it, with subagents).
+async fn session_media(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    let a = app.clone();
+    let items = tokio::task::spawn_blocking(move || crate::media::collect(&a, &id)).await.map_err(|e| ApiError(StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))??;
+    Ok(Json(json!(items)))
+}
+
+/// Search within one chat (all of it, not only the loaded part).
+async fn search_in_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<SearchQ>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    if q.q.trim().chars().count() < 2 {
+        return Ok(Json(json!([])));
+    }
+    let hits: Vec<Value> = app
+        .store
+        .search_messages(&id, q.q.trim(), 100)?
+        .into_iter()
+        .map(|(mid, role, at, snippet)| json!({"id": mid, "role": role, "created_at": at, "snippet": snippet}))
+        .collect();
+    Ok(Json(json!(hits)))
 }
 
 #[derive(Deserialize)]
@@ -1563,13 +1633,26 @@ fn own_image(app: &App, user: &User, id: &str) -> Result<crate::store::ImageReco
 
 async fn image_file(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> Result<Response, ApiError> {
     let img = own_image(&app, &user, &id)?;
-    let bytes = tokio::fs::read(&img.path).await.map_err(|_| not_found("image file"))?;
-    let ctype = match std::path::Path::new(&img.path).extension().and_then(|e| e.to_str()) {
+    let ctype_of = |p: &str| match std::path::Path::new(p).extension().and_then(|e| e.to_str()).map(|e| e.to_ascii_lowercase()).as_deref() {
         Some("jpg") | Some("jpeg") => "image/jpeg",
         Some("webp") => "image/webp",
         _ => "image/png",
     };
-    Ok(([(axum::http::header::CONTENT_TYPE, ctype), (axum::http::header::CACHE_CONTROL, "private, max-age=86400")], bytes).into_response())
+    let respond = |ctype: String, bytes: Vec<u8>| ([(axum::http::header::CONTENT_TYPE, ctype), (axum::http::header::CACHE_CONTROL, "private, max-age=86400".to_string())], bytes).into_response();
+    if let Ok(bytes) = tokio::fs::read(&img.path).await {
+        return Ok(respond(ctype_of(&img.path).into(), bytes));
+    }
+    // The file was moved or renamed (agents tidy up folders): with a copy in the image store,
+    // answer from there and look for the file in the background; otherwise look now.
+    if let Some((mime, bytes)) = img.blob.as_deref().map(|h| app.store.blob(h)).transpose()?.flatten() {
+        let a = app.clone();
+        tokio::task::spawn_blocking(move || crate::images::relocate(&a, &img));
+        return Ok(respond(mime, bytes));
+    }
+    let a = app.clone();
+    let found = tokio::task::spawn_blocking(move || crate::images::relocate(&a, &img)).await.ok().flatten().ok_or_else(|| not_found("image file"))?;
+    let bytes = tokio::fs::read(&found).await.map_err(|_| not_found("image file"))?;
+    Ok(respond(ctype_of(&found.display().to_string()).into(), bytes))
 }
 
 async fn delete_image(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> ApiResult {

server/src/app.rs

@@ -144,6 +144,11 @@ impl App {
                 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 crate::images::backfill_copies(&self) {
+                Ok(0) => {}
+                Ok(n) => tracing::info!("kept copies of {n} generated images in the image store"),
+                Err(e) => tracing::warn!("copies of generated images: {e:#}"),
+            }
             match self.store.gc_blobs() {
                 Ok(0) => {}
                 Ok(n) => tracing::info!("removed {n} unused images"),

server/src/blobs.rs

@@ -56,7 +56,8 @@ 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 {
+/// Address of `bytes` in the image store (SHA-256, hex).
+pub fn hash(bytes: &[u8]) -> String {
     Sha256::digest(bytes).iter().map(|b| format!("{b:02x}")).collect()
 }
 

server/src/budget.rs

@@ -409,6 +409,7 @@ fn opencode_model(m: &Value) -> Value {
         "id": m["id"],
         "context": m["limit"]["context"],
         "max_output": m["limit"]["output"],
+        "max_input": m["limit"]["input"],
         "vision": images,
         "reasoning": m["capabilities"]["reasoning"]["supported"].as_bool().unwrap_or(false),
         "input_price": input["price"],

server/src/config.rs

@@ -307,8 +307,13 @@ pub struct ServerConfig {
     /// Bearer token for GET /metrics (Prometheus); empty = /metrics disabled.
     #[serde(skip_serializing_if = "String::is_empty")]
     pub metrics_token: String,
+    /// Trailer added to every git commit an agent makes ({model}, {provider}, {model_id});
+    /// empty = off.
+    pub commit_trailer: String,
 }
 
+pub const DEFAULT_COMMIT_TRAILER: &str = "Co-Authored-By: {model} ({provider}) via CodeCraft";
+
 impl Default for ServerConfig {
     fn default() -> Self {
         Self {
@@ -327,6 +332,7 @@ impl Default for ServerConfig {
             max_upload_mb: 500,
             update_url: "https://git.familie-zink.org/api/v1/repos/zink/codecraft/releases/latest".into(),
             metrics_token: String::new(),
+            commit_trailer: DEFAULT_COMMIT_TRAILER.into(),
         }
     }
 }
@@ -398,6 +404,10 @@ pub struct AgentConfig {
     /// Review loop after each turn of this mode.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub refine: Option<RefineConfig>,
+    /// Reverse engineering tools (binary_info, decompile with Ghidra) in this mode;
+    /// craft has them anyway (deep mode).
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub reverse_tools: Option<bool>,
 }
 
 /// Refinement loop: after the agent finishes, a reviewer checks the result
@@ -413,6 +423,9 @@ pub struct RefineConfig {
     /// Review criteria; empty = the mode's defaults.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub criteria: Option<String>,
+    /// Also review every todo the agent marks completed (reopened when findings come back).
+    #[serde(default = "yes")]
+    pub after_todos: bool,
 }
 
 #[derive(Debug, Clone, Deserialize, Serialize)]

server/src/files.rs

@@ -353,6 +353,10 @@ pub async fn move_or_copy(Extension(user): Extension<User>, State(app): State<Ap
     }
     let (f, t) = (from.clone(), to.clone());
     tokio::task::spawn_blocking(move || if b.copy { copy_recursive(&f, &t) } else { std::fs::rename(&f, &t) }).await??;
+    if !b.copy {
+        // Generated images in the moved file or folder keep their entries.
+        app.store.move_image_paths(&from.display().to_string(), &to.display().to_string())?;
+    }
     Ok(Json(json!({"ok": true, "path": to})))
 }
 

server/src/images.rs

@@ -213,6 +213,8 @@ pub async fn generate(app: &App, req: GenerateRequest) -> Result<Vec<ImageRecord
         let name = if images.len() > 1 { format!("{stamp}-{base}-{}.{ext}", i + 1) } else { format!("{stamp}-{base}.{ext}") };
         let path = req.dir.join(name);
         tokio::fs::write(&path, &bytes).await?;
+        // A copy in the image store keeps it viewable when the file is moved or deleted.
+        let blob = app.store.put_blob(&ctype, &bytes).map_err(|e| tracing::warn!("image copy: {e:#}")).ok();
         let rec = ImageRecord {
             id: new_id(),
             user_id: req.user_id.clone(),
@@ -223,6 +225,7 @@ pub async fn generate(app: &App, req: GenerateRequest) -> Result<Vec<ImageRecord
             width: img["width"].as_i64().unwrap_or(0),
             height: img["height"].as_i64().unwrap_or(0),
             created_at: now_ms(),
+            blob,
         };
         app.store.add_image(&rec)?;
         records.push(rec);
@@ -252,6 +255,98 @@ pub async fn generate(app: &App, req: GenerateRequest) -> Result<Vec<ImageRecord
     Ok(records)
 }
 
+/// A generated image whose file is gone: the same file name below its original folder
+/// (or the folder above it), e.g. after an agent sorted the images into subfolders.
+/// Only inside `roots`; looks at a few thousand entries at most.
+pub fn find_moved(path: &Path, roots: &[PathBuf]) -> Option<PathBuf> {
+    let name = path.file_name()?;
+    search_near(path, roots, |p, _| p.file_name() == Some(name))
+}
+
+/// Like `find_moved`, but by content: an image file with the same bytes (renamed).
+pub fn find_by_content(path: &Path, roots: &[PathBuf], hash: &str, size: u64) -> Option<PathBuf> {
+    search_near(path, roots, |p, len| {
+        let ext = p.extension().and_then(|e| e.to_str()).map(|e| e.to_ascii_lowercase());
+        len == size && matches!(ext.as_deref(), Some("png" | "jpg" | "jpeg" | "webp")) && std::fs::read(p).is_ok_and(|b| crate::blobs::hash(&b) == hash)
+    })
+}
+
+/// Files below the folder of `path` and the folder above it (3 levels, hidden folders
+/// skipped, inside `roots`) for which `matches(path, size)` holds.
+fn search_near(path: &Path, roots: &[PathBuf], matches: impl Fn(&Path, u64) -> bool) -> Option<PathBuf> {
+    let dir = path.parent()?;
+    let mut budget = 5000usize;
+    for base in [Some(dir), dir.parent()].into_iter().flatten() {
+        if !roots.iter().any(|r| base.starts_with(r)) {
+            continue;
+        }
+        let mut stack = vec![(base.to_path_buf(), 0usize)];
+        while let Some((d, depth)) = stack.pop() {
+            let Ok(entries) = std::fs::read_dir(&d) else { continue };
+            for e in entries.flatten() {
+                if budget == 0 {
+                    return None;
+                }
+                budget -= 1;
+                let p = e.path();
+                let Ok(ft) = e.file_type() else { continue };
+                if ft.is_file() && p != path && matches(&p, e.metadata().map(|m| m.len()).unwrap_or(0)) {
+                    return Some(p);
+                }
+                let hidden = p.file_name().and_then(|n| n.to_str()).is_some_and(|n| n.starts_with('.') || n == "node_modules");
+                if ft.is_dir() && depth < 3 && !hidden {
+                    stack.push((p, depth + 1));
+                }
+            }
+        }
+    }
+    None
+}
+
+/// Where the file of a generated image is now: by name, then (with a copy in the image
+/// store) by content. Corrects the stored path when found.
+pub fn relocate(app: &App, rec: &ImageRecord) -> Option<PathBuf> {
+    let path = Path::new(&rec.path);
+    let roots = app.user_roots(rec.user_id.as_deref());
+    let found = find_moved(path, &roots).or_else(|| {
+        let hash = rec.blob.as_deref()?;
+        let (_, bytes) = app.store.blob(hash).ok()??;
+        find_by_content(path, &roots, hash, bytes.len() as u64)
+    })?;
+    let _ = app.store.set_image_path(&rec.id, &found.display().to_string());
+    Some(found)
+}
+
+/// After an agent moved or renamed files: find the generated images of `owner` from the
+/// last two weeks whose files are gone and correct their paths. Returns how many.
+pub fn relocate_missing(app: &App, owner: Option<&str>) -> usize {
+    let since = now_ms() - 14 * 86_400_000;
+    let Ok(list) = app.store.images(owner, 500) else { return 0 };
+    list.iter().filter(|r| r.created_at >= since && !Path::new(&r.path).exists()).filter(|r| relocate(app, r).is_some()).count()
+}
+
+/// Copies in the image store for generated images from before they were kept (once per
+/// image, files up to 25 MB): later moves and renames are then found by content.
+pub fn backfill_copies(app: &App) -> Result<usize> {
+    let mut n = 0;
+    for (id, path) in app.store.images_without_copy()? {
+        let Ok(meta) = std::fs::metadata(&path) else { continue };
+        if !meta.is_file() || meta.len() > 25 * 1024 * 1024 {
+            continue;
+        }
+        let Ok(bytes) = std::fs::read(&path) else { continue };
+        let mime = match Path::new(&path).extension().and_then(|e| e.to_str()).map(|e| e.to_ascii_lowercase()).as_deref() {
+            Some("jpg" | "jpeg") => "image/jpeg",
+            Some("webp") => "image/webp",
+            _ => "image/png",
+        };
+        let hash = app.store.put_blob(mime, &bytes)?;
+        app.store.set_image_blob(&id, &hash)?;
+        n += 1;
+    }
+    Ok(n)
+}
+
 /// Downscaled copy for the model's context.
 fn preview_for_model(path: &Path) -> Option<ImageData> {
     let img = image::open(path).ok()?;
@@ -363,6 +458,37 @@ impl Tool for GenerateImage {
 mod tests {
     use super::*;
 
+    #[test]
+    fn finds_moved_files_and_keeps_their_copies() {
+        let dir = std::env::temp_dir().join(format!("cc-img-moved-{}", std::process::id()));
+        let art = dir.join("art");
+        std::fs::create_dir_all(art.join("older")).unwrap();
+        std::fs::write(art.join("older/20261110-a.png"), b"x").unwrap();
+        // Moved into a subfolder: found; renamed or outside the roots: not.
+        assert_eq!(find_moved(&art.join("20261110-a.png"), std::slice::from_ref(&dir)), Some(art.join("older/20261110-a.png")));
+        assert_eq!(find_moved(&art.join("20261110-b.png"), std::slice::from_ref(&dir)), None);
+        assert_eq!(find_moved(&art.join("20261110-a.png"), &[dir.join("elsewhere")]), None);
+        // Renamed: found by content.
+        std::fs::write(art.join("older/level-5.png"), b"renamed bytes").unwrap();
+        let h = crate::blobs::hash(b"renamed bytes");
+        assert_eq!(find_by_content(&art.join("20261110-c.png"), std::slice::from_ref(&dir), &h, 13), Some(art.join("older/level-5.png")));
+        assert_eq!(find_by_content(&art.join("20261110-c.png"), std::slice::from_ref(&dir), &crate::blobs::hash(b"other"), 13), None);
+        // The image store keeps the copy of a generated image.
+        let store = crate::store::Store::open(&dir.join("t.db")).unwrap();
+        let hash = store.put_blob("image/png", b"png bytes").unwrap();
+        store
+            .add_image(&ImageRecord { id: "i".into(), user_id: None, session_id: None, prompt: "p".into(), model: "m".into(), path: "/gone.png".into(), width: 1, height: 1, created_at: 0, blob: Some(hash.clone()) })
+            .unwrap();
+        assert_eq!(store.gc_blobs().unwrap(), 0);
+        // Moved with the file manager: the entry follows (file or folder, not look-alikes).
+        assert_eq!(store.move_image_paths("/gone.png", "/art/new.png").unwrap(), 1);
+        assert_eq!(store.move_image_paths("/art", "/bilder/").unwrap(), 1);
+        assert_eq!(store.move_image_paths("/bild", "/x").unwrap(), 0);
+        assert_eq!(store.image("i").unwrap().unwrap().path, "/bilder/new.png");
+        assert_eq!(store.blob(&hash).unwrap().unwrap().1, b"png bytes");
+        std::fs::remove_dir_all(&dir).unwrap();
+    }
+
     fn m(id: &str) -> ImageModel {
         with_defaults(ImageModel { id: id.into(), ..Default::default() })
     }

server/src/main.rs

@@ -22,6 +22,7 @@ mod lsp;
 mod mentions;
 mod metrics;
 mod mcp;
+mod media;
 mod permission;
 mod prompts;
 mod push;

server/src/media.rs

@@ -0,0 +1,200 @@
+//! Media overview of a chat: every image, video and audio file that was shown in it –
+//! generated images, images in tool results (screenshots), media files the agent wrote,
+//! media referenced in answers, and the user's own attachments. Includes subagents.
+
+use crate::app::App;
+use crate::types::{Message, Part, Role};
+use serde::Serialize;
+use serde_json::Value;
+use std::collections::HashSet;
+use std::path::{Path, PathBuf};
+
+#[derive(Debug, Serialize, PartialEq)]
+pub struct MediaItem {
+    /// "image", "video" or "audio".
+    pub kind: &'static str,
+    pub url: String,
+    pub name: String,
+    /// "generated", "tool", "written", "answer" or "upload".
+    pub source: &'static str,
+    pub created_at: i64,
+    /// Message to jump to (only for messages of the chat itself, not of subagents).
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub message_id: Option<String>,
+}
+
+const IMAGE: &[&str] = &["png", "jpg", "jpeg", "gif", "webp", "svg", "bmp", "avif"];
+const VIDEO: &[&str] = &["mp4", "webm", "mov", "m4v", "ogv"];
+const AUDIO: &[&str] = &["mp3", "wav", "ogg", "oga", "m4a", "flac", "opus", "aac"];
+
+/// Kind of a media file by its extension.
+pub fn kind_of(path: &str) -> Option<&'static str> {
+    let ext = Path::new(path.split(['?', '#']).next().unwrap_or(path)).extension()?.to_str()?.to_ascii_lowercase();
+    if IMAGE.contains(&ext.as_str()) {
+        Some("image")
+    } else if VIDEO.contains(&ext.as_str()) {
+        Some("video")
+    } else if AUDIO.contains(&ext.as_str()) {
+        Some("audio")
+    } else {
+        None
+    }
+}
+
+fn kind_of_mime(mime: &str) -> &'static str {
+    if mime.starts_with("video/") {
+        "video"
+    } else if mime.starts_with("audio/") {
+        "audio"
+    } else {
+        "image"
+    }
+}
+
+/// Like JavaScript's encodeURIComponent.
+fn encode(s: &str) -> String {
+    let mut out = String::with_capacity(s.len());
+    for b in s.bytes() {
+        if b.is_ascii_alphanumeric() || b"-_.!~*'()".contains(&b) {
+            out.push(b as char);
+        } else {
+            out.push_str(&format!("%{b:02X}"));
+        }
+    }
+    out
+}
+
+/// Absolute, normalised path of `p` (relative to `cwd`).
+fn resolve(p: &str, cwd: &Path) -> PathBuf {
+    let joined = if p.starts_with('/') { PathBuf::from(p) } else { cwd.join(p) };
+    crate::tools::normalize(&joined)
+}
+
+/// Media file paths in a text: Markdown images/links and plain paths with a media extension.
+fn paths_in(text: &str) -> Vec<String> {
+    let mut out = Vec::new();
+    for token in text.split(|c: char| c.is_whitespace() || "()[]<>\"'`,;".contains(c)) {
+        let t = token.trim_end_matches(['.', ':', '!', '?']);
+        if t.is_empty() || t.contains("://") || t.starts_with("data:") {
+            continue;
+        }
+        if kind_of(t).is_some() && t.chars().any(|c| c == '/' || c == '.') {
+            out.push(t.to_string());
+        }
+    }
+    out
+}
+
+/// All media of a chat and its subagents, newest first.
+pub fn collect(app: &App, session_id: &str) -> anyhow::Result<Vec<MediaItem>> {
+    let mut sessions = vec![session_id.to_string()];
+    // Subagents (and theirs).
+    let mut i = 0;
+    while i < sessions.len() && sessions.len() < 500 {
+        let children = app.store.child_sessions(&sessions[i])?;
+        sessions.extend(children);
+        i += 1;
+    }
+    let mut out: Vec<MediaItem> = Vec::new();
+    let mut seen: HashSet<String> = HashSet::new();
+    let mut push = |item: MediaItem, out: &mut Vec<MediaItem>| {
+        if seen.insert(item.url.clone()) {
+            out.push(item);
+        }
+    };
+    for sid in &sessions {
+        let Some(session) = app.store.get_session(sid)? else { continue };
+        let cwd = PathBuf::from(&session.cwd);
+        let own = sid == session_id;
+        // Tool results are shown in the card of the call: jump to that message.
+        let mut call_msg: Option<String> = None;
+        for m in app.store.messages(sid)? {
+            collect_message(&m, &cwd, own, call_msg.as_deref(), &mut |item| push(item, &mut out));
+            if m.role == Role::Assistant {
+                call_msg = Some(m.id.clone());
+            }
+        }
+    }
+    // Generated images whose tool result was not found (e.g. removed by a rewind).
+    for img in app.store.images_of_sessions(&sessions)? {
+        push(
+            MediaItem { kind: "image", url: format!("/api/images/{}/file", img.id), name: file_name(&img.path), source: "generated", created_at: img.created_at, message_id: None },
+            &mut out,
+        );
+    }
+    // Names of generated images (their files).
+    let names: std::collections::HashMap<String, String> = app.store.images_of_sessions(&sessions)?.into_iter().map(|i| (format!("/api/images/{}/file", i.id), file_name(&i.path))).collect();
+    for item in &mut out {
+        if let Some(n) = names.get(&item.url) {
+            item.name = n.clone();
+        }
+    }
+    out.sort_by(|a, b| b.created_at.cmp(&a.created_at));
+    Ok(out)
+}
+
+fn file_name(p: &str) -> String {
+    Path::new(p).file_name().and_then(|n| n.to_str()).unwrap_or(p).to_string()
+}
+
+fn collect_message(m: &Message, cwd: &Path, own: bool, call_msg: Option<&str>, add: &mut dyn FnMut(MediaItem)) {
+    let mid = own.then(|| m.id.clone());
+    let result_mid = own.then(|| call_msg.unwrap_or(&m.id).to_string());
+    let at = m.created_at;
+    let file = |p: &str, source: &'static str| -> Option<MediaItem> {
+        let kind = kind_of(p)?;
+        let abs = resolve(p, cwd);
+        abs.is_file().then(|| MediaItem { kind, url: format!("/api/files/raw?path={}", encode(&abs.display().to_string())), name: file_name(p), source, created_at: at, message_id: mid.clone() })
+    };
+    for p in &m.parts {
+        match p {
+            Part::Image { image } if m.role == Role::User => {
+                if let Some(h) = &image.blob {
+                    add(MediaItem { kind: kind_of_mime(&image.media_type), url: format!("/api/blobs/{h}"), name: "image".into(), source: "upload", created_at: at, message_id: mid.clone() });
+                }
+            }
+            Part::ToolResult { images, meta, .. } => {
+                let ids: Vec<&str> = meta.as_ref().and_then(|v| v["image_ids"].as_array()).map(|a| a.iter().filter_map(Value::as_str).collect()).unwrap_or_default();
+                if !ids.is_empty() {
+                    for id in ids {
+                        add(MediaItem { kind: "image", url: format!("/api/images/{id}/file"), name: "image".into(), source: "generated", created_at: at, message_id: result_mid.clone() });
+                    }
+                } else {
+                    for img in images {
+                        if let Some(h) = &img.blob {
+                            add(MediaItem { kind: kind_of_mime(&img.media_type), url: format!("/api/blobs/{h}"), name: "screenshot".into(), source: "tool", created_at: at, message_id: result_mid.clone() });
+                        }
+                    }
+                }
+            }
+            Part::ToolCall { name, input, .. } if matches!(name.as_str(), "write" | "edit") => {
+                if let Some(item) = input["path"].as_str().and_then(|p| file(p, "written")) {
+                    add(item);
+                }
+            }
+            Part::Text { text } if m.role == Role::Assistant => {
+                for p in paths_in(text) {
+                    if let Some(item) = file(&p, "answer") {
+                        add(item);
+                    }
+                }
+            }
+            _ => {}
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn kinds_paths_and_encoding() {
+        assert_eq!(kind_of("a/b.PNG"), Some("image"));
+        assert_eq!(kind_of("clip.mp4?v=1"), Some("video"));
+        assert_eq!(kind_of("song.flac"), Some("audio"));
+        assert_eq!(kind_of("main.rs"), None);
+        assert_eq!(paths_in("Saved to `art/final/hero.png` and ![x](shots/a.webp). See https://x.org/y.png"), vec!["art/final/hero.png", "shots/a.webp"]);
+        assert_eq!(encode("/w/ä b.png"), "%2Fw%2F%C3%A4%20b.png");
+    }
+}

server/src/prompts.rs

@@ -32,6 +32,8 @@ pub struct Agent {
     pub max_parallel: Option<usize>,
     /// Review loop after each turn (None/0 rounds = off).
     pub refine: Option<crate::config::RefineConfig>,
+    /// binary_info and decompile available (besides craft).
+    pub reverse: bool,
     /// Source file of Markdown agents.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub path: Option<String>,
@@ -43,12 +45,12 @@ pub use codecraft_core::prompts::*;
 pub fn builtin_agents(clean_room: bool) -> Vec<Agent> {
     let craft = craft_prompt(clean_room);
     vec![
-        Agent { name: "build".into(), description: "Full access: implement, edit, run".into(), mode: "primary".into(), prompt: BUILD_PROMPT.into(), tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
-        Agent { name: "plan".into(), description: "Read-only: analyse and propose a plan".into(), mode: "primary".into(), prompt: PLAN_PROMPT.into(), tools: None, read_only: true, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
-        Agent { name: "chat".into(), description: "Just talk: answers, explanations, web search – no files or shell".into(), mode: "primary".into(), prompt: CHAT_PROMPT.into(), tools: Some(vec!["web_search".into(), "web_fetch".into()]), read_only: true, style: "chat".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
-        Agent { name: "craft".into(), description: "Study a target, build your own version, check and refine".into(), mode: "primary".into(), prompt: craft, tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
-        Agent { name: "general".into(), description: "General-purpose subagent for multi-step tasks".into(), mode: "subagent".into(), prompt: GENERAL_PROMPT.into(), tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
-        Agent { name: "explore".into(), description: "Read-only subagent for fast codebase searches".into(), mode: "subagent".into(), prompt: EXPLORE_PROMPT.into(), tools: None, read_only: true, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, path: None },
+        Agent { name: "build".into(), description: "Full access: implement, edit, run".into(), mode: "primary".into(), prompt: BUILD_PROMPT.into(), tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
+        Agent { name: "plan".into(), description: "Read-only: analyse and propose a plan".into(), mode: "primary".into(), prompt: PLAN_PROMPT.into(), tools: None, read_only: true, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
+        Agent { name: "chat".into(), description: "Just talk: answers, explanations, web search – no files or shell".into(), mode: "primary".into(), prompt: CHAT_PROMPT.into(), tools: Some(vec!["web_search".into(), "web_fetch".into()]), read_only: true, style: "chat".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
+        Agent { name: "craft".into(), description: "Study a target, build your own version, check and refine".into(), mode: "primary".into(), prompt: craft, tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
+        Agent { name: "general".into(), description: "General-purpose subagent for multi-step tasks".into(), mode: "subagent".into(), prompt: GENERAL_PROMPT.into(), tools: None, read_only: false, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
+        Agent { name: "explore".into(), description: "Read-only subagent for fast codebase searches".into(), mode: "subagent".into(), prompt: EXPLORE_PROMPT.into(), tools: None, read_only: true, style: "coding".into(), model: None, source: "builtin".into(), max_parallel: None, refine: None, reverse: false, path: None },
     ]
 }
 
@@ -121,7 +123,8 @@ pub fn agents(app: &App, root: &Path, cwd: &Path) -> Vec<Agent> {
                 model: meta.get("model").filter(|m| m.contains('/')).cloned(),
                 source: "file".into(),
                 max_parallel: meta.get("max_parallel").and_then(|v| v.parse().ok()),
-                refine: meta.get("refine_rounds").and_then(|v| v.parse().ok()).map(|rounds| crate::config::RefineConfig { rounds, model: meta.get("refine_model").cloned(), criteria: None }),
+                refine: meta.get("refine_rounds").and_then(|v| v.parse().ok()).map(|rounds| crate::config::RefineConfig { rounds, model: meta.get("refine_model").cloned(), criteria: None, after_todos: meta.get("refine_after_todos").is_none_or(|v| v != "false") }),
+                reverse: meta.get("reverse_tools").is_some_and(|v| v == "true"),
                 path: Some(p.display().to_string()),
             });
         }
@@ -141,6 +144,7 @@ pub fn agents(app: &App, root: &Path, cwd: &Path) -> Vec<Agent> {
             source: "config".into(),
             max_parallel: a.max_parallel.or(base.as_ref().and_then(|b| b.max_parallel)),
             refine: a.refine.clone().or(base.as_ref().and_then(|b| b.refine.clone())),
+            reverse: a.reverse_tools.unwrap_or_else(|| base.as_ref().is_some_and(|b| b.reverse)),
             path: None,
         });
     }
@@ -173,6 +177,7 @@ pub fn agents_for(app: &App, root: &Path, cwd: &Path, user_id: Option<&str>) ->
             source: "personal".into(),
             max_parallel: None,
             refine: a.refine,
+            reverse: a.reverse_tools.unwrap_or(false),
             path: None,
         });
     }

server/src/reverse.rs

@@ -142,7 +142,10 @@ impl Tool for Decompile {
         "Decompile an executable or library with Ghidra (x86/x64/ARM/MIPS/PowerPC/68k …, PE, ELF, \
          Mach-O, raw DOS). Writes pseudo-C for every function plus strings, imports and exports \
          into .codecraft/decompiled/<name>/ and returns an overview. Can take several minutes for \
-         large programs; results are cached per file."
+         large programs; results are cached per file. Raw firmware images (.bin without a file \
+         format) need `processor` (Ghidra language id, e.g. \"ARM:LE:32:Cortex\" for Cortex-M, \
+         \"ARM:LE:32:v8\", \"AVR8:LE:16:atmega256\", \"Xtensa:LE:32:default\" for ESP32) and usually \
+         `base_address` (load address, e.g. \"0x08000000\" for STM32 flash)."
             .into()
     }
     fn schema(&self) -> Value {
@@ -151,7 +154,9 @@ impl Tool for Decompile {
             "properties": {
                 "path": {"type": "string"},
                 "max_functions": {"type": "integer", "description": "Limit for very large binaries (default: all)"},
-                "force": {"type": "boolean", "description": "Re-run even if cached"}
+                "force": {"type": "boolean", "description": "Re-run even if cached"},
+                "processor": {"type": "string", "description": "Ghidra language id for raw images, e.g. ARM:LE:32:Cortex (default: detected from the file format)"},
+                "base_address": {"type": "string", "description": "Load address of a raw image, e.g. 0x08000000"}
             },
             "required": ["path"]
         })
@@ -171,7 +176,20 @@ impl Tool for Decompile {
             bail!("{} is not a file", path.display());
         }
         let name = path.file_name().and_then(|n| n.to_str()).unwrap_or("binary").replace(|c: char| !c.is_ascii_alphanumeric() && c != '.' && c != '-', "_");
-        let out_dir = ctx.cwd.join(".codecraft/decompiled").join(format!("{name}-{}", file_hash(&path)?));
+        let processor = input["processor"].as_str().map(str::trim).filter(|s| !s.is_empty()).map(String::from);
+        let base = input["base_address"].as_str().map(str::trim).filter(|s| !s.is_empty()).map(String::from);
+        if processor.as_deref().is_some_and(|p| !p.chars().all(|c| c.is_ascii_alphanumeric() || ":_-.".contains(c))) {
+            bail!("invalid processor id (expected e.g. ARM:LE:32:Cortex)");
+        }
+        if base.as_deref().is_some_and(|b| !b.trim_start_matches("0x").chars().all(|c| c.is_ascii_hexdigit())) {
+            bail!("invalid base_address (expected e.g. 0x08000000)");
+        }
+        // Another processor or load address is another analysis.
+        let variant = match (&processor, &base) {
+            (None, None) => String::new(),
+            (p, b) => format!("-{}", crate::blobs::hash(format!("{p:?}{b:?}").as_bytes()).get(..8).unwrap_or("")),
+        };
+        let out_dir = ctx.cwd.join(".codecraft/decompiled").join(format!("{name}-{}{variant}", file_hash(&path)?));
         if out_dir.join(".done").exists() && !input["force"].as_bool().unwrap_or(false) {
             return Ok(ToolOutput::text(format!("(cached)\n{}", summarize(&out_dir, &ctx.cwd)?)));
         }
@@ -183,7 +201,15 @@ impl Tool for Decompile {
         let scripts = scripts_dir().display().to_string();
         let max = input["max_functions"].as_u64().map(|n| n.to_string()).unwrap_or_else(|| "2147483647".into());
         let (p, proj, out) = (path.display().to_string(), project.display().to_string(), out_dir.display().to_string());
-        let args = vec![proj.as_str(), "cc", "-import", p.as_str(), "-scriptPath", scripts.as_str(), "-postScript", "CodeCraftExport.java", out.as_str(), max.as_str(), "-deleteProject", "-max-cpu", "2"];
+        let mut args = vec![proj.as_str(), "cc", "-import", p.as_str()];
+        // Raw firmware: the binary loader with the given processor and load address.
+        if let Some(proc_id) = processor.as_deref() {
+            args.extend(["-processor", proc_id]);
+        }
+        if let Some(addr) = base.as_deref() {
+            args.extend(["-loader", "BinaryLoader", "-loader-baseAddr", addr]);
+        }
+        args.extend(["-scriptPath", scripts.as_str(), "-postScript", "CodeCraftExport.java", out.as_str(), max.as_str(), "-deleteProject", "-max-cpu", "2"]);
         let java = tools.join("jdk").display().to_string();
         let mut cmd = match &ctx.sandbox {
             Some(spec) => {

server/src/runner.rs

@@ -18,6 +18,8 @@ use tokio::sync::mpsc;
 use tokio_util::sync::CancellationToken;
 
 const MAX_STEPS: usize = 250;
+/// Modes with enforced reviews work through their todo list (e.g. overnight).
+const MAX_STEPS_ENFORCED: usize = 2_000;
 const MAX_SUBAGENT_DEPTH: usize = 3;
 
 /// What happened to a prompt.
@@ -224,7 +226,12 @@ pub fn available_tools(app: &App, agent: &Agent, owner: Option<&crate::store::Us
     all.into_iter()
         .filter(|t| !agent.read_only || t.read_only())
         // Craft tools only where they are useful.
-        .filter(|t| agent.name == "craft" || !matches!(t.name(), "browser_snapshot" | "image_compare" | "binary_info" | "decompile" | "craft_phase") || agent.tools.is_some())
+        .filter(|t| {
+            agent.name == "craft"
+                || agent.tools.is_some()
+                || (agent.reverse && matches!(t.name(), "binary_info" | "decompile"))
+                || !matches!(t.name(), "browser_snapshot" | "image_compare" | "binary_info" | "decompile" | "craft_phase")
+        })
         .filter(|t| match &agent.tools {
             None => true,
             Some(list) => {
@@ -260,7 +267,15 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
     let mut stop_hooks = 0;
     let mut refine_done = 0u32;
     let turn_start = now_ms();
-    for _ in 0..MAX_STEPS {
+    // Compacted for the current step (no second compaction before a request went through).
+    let mut compacted_now = false;
+    // Mandatory reviews of completed todos: rounds per todo, and where the last one ended.
+    let mut todo_reviews: std::collections::HashMap<String, u32> = std::collections::HashMap::new();
+    let mut review_since = turn_start;
+    // Reminders about open todos at the end of a turn (see MAX_IDLE_CONTINUES).
+    let mut last_reminder: Option<Value> = None;
+    let mut idle_continues = 0u32;
+    for step_no in 0..=MAX_STEPS_ENFORCED {
         if cancel.is_cancelled() {
             break;
         }
@@ -275,40 +290,65 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
             agent.prompt = prompts::craft_prompt(clean_room);
         }
         let model_spec = agent.model.clone().unwrap_or_else(|| session.model.clone());
+        let step_limit = if enforced_review(&agent) > 0 { MAX_STEPS_ENFORCED } else { MAX_STEPS };
+        if step_no >= step_limit {
+            app.emit(Event::Error { session_id: session_id.into(), message: format!("Stopped after {step_limit} steps (limit of a turn) – send a message to continue.") });
+            break;
+        }
         let (provider, mut model) = app.registry().resolve(&model_spec)?;
         if let Some(effort) = app.with_runtime(session_id, |r| r.effort.clone()) {
             model.effort = Some(effort);
         }
 
-        // Auto-compaction when the last request used most of the context window.
-        if let (Some(u), Some(ctx_len)) = (&session.last_usage, model.context) {
+        let history = active_history(app.store.messages_for_model(session_id)?);
+        // Providers count input + max_tokens against the context window: the answer needs
+        // room too. Estimated input = last request (input + its answer) + what came since.
+        let est_input = estimate_input(session.last_usage.as_ref(), &history);
+        let want_output = model.max_output.unwrap_or(16_000);
+        if let Some(ctx_len) = model.context {
             let threshold = app.config().server.auto_compact_threshold;
-            if threshold > 0.0 && u.context_tokens() as f64 > ctx_len as f64 * threshold {
-                compact(app.clone(), session_id, cancel.clone(), Some((u.context_tokens(), ctx_len))).await?;
+            // Input limit: the context window, or the provider's lower input limit.
+            let input_limit = model.max_input.map_or(ctx_len, |m| m.min(ctx_len));
+            let room = ctx_len.saturating_sub(est_input);
+            // Most of the input limit used, or no room left for a reasonable answer.
+            if threshold > 0.0 && (est_input as f64 > input_limit as f64 * threshold || room < want_output.min(MIN_ANSWER_ROOM)) && !compacted_now {
+                compacted_now = true;
+                compact(app.clone(), session_id, cancel.clone(), Some((est_input, input_limit))).await?;
                 continue;
             }
         }
+        let max_tokens = answer_budget(want_output, model.context, est_input);
 
         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_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,
             tools: tools.iter().map(|t| t.def()).collect(),
-            max_tokens: model.max_output.unwrap_or(16_000),
+            max_tokens,
             reasoning: true,
             session_id: Some(session_id.to_string()),
             model: model.clone(),
         };
         let step = match stream_step(&app, &session, &agent.name, &model_spec, provider, req.clone(), &cancel).await {
-            Ok(step) => step,
+            Ok(step) => {
+                compacted_now = false;
+                step
+            }
+            // The estimate was off and the provider says the input is too long: compact
+            // once and try again instead of stopping.
+            Err(e) if is_context_overflow(&e) && !compacted_now && !cancel.is_cancelled() => {
+                compacted_now = true;
+                app.emit(Event::Error { session_id: session_id.into(), message: format!("context window full ({}) – compacting the conversation and continuing", short_error(&e)) });
+                compact(app.clone(), session_id, cancel.clone(), Some((est_input, model.context.unwrap_or(0)))).await?;
+                continue;
+            }
             // Host down or budget used up: switch to the model's fallback for this step.
             Err(e) if model.fallback.is_some() && !cancel.is_cancelled() && needs_fallback(&e) => {
                 let fb = model.fallback.clone().unwrap_or_default();
                 let (fb_provider, fb_model) = app.registry().resolve(&fb)?;
                 app.emit(Event::Error { session_id: session_id.into(), message: format!("{model_spec} is not available ({}) – using the fallback model {fb}", short_error(&e)) });
-                let req = ChatRequest { model: fb_model.clone(), max_tokens: fb_model.max_output.unwrap_or(16_000), ..req };
+                let req = ChatRequest { model: fb_model.clone(), max_tokens: answer_budget(fb_model.max_output.unwrap_or(16_000), fb_model.context, est_input), ..req };
                 stream_step(&app, &session, &agent.name, &fb, fb_provider, req, &cancel).await?
             }
             Err(e) => return Err(e),
@@ -353,12 +393,37 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
             }
         }
         let normal_end = matches!(step.stop_reason.as_str(), "stop" | "end_turn" | "");
+        // Enforced reviews also mean: work until the todo list is done. Ending the turn with
+        // open todos sends the agent back (as long as it makes progress).
+        if calls.is_empty() && depth == 0 && normal_end && !cancel.is_cancelled() && enforced_review(&agent) > 0 {
+            let todos_now = app.session(session_id)?.todos;
+            let open = open_todos(&todos_now);
+            if !open.is_empty() {
+                let progressed = last_reminder.as_ref() != Some(&todos_now);
+                idle_continues = if progressed { 0 } else { idle_continues + 1 };
+                if idle_continues < MAX_IDLE_CONTINUES {
+                    last_reminder = Some(todos_now);
+                    save_user_parts(
+                        &app,
+                        session_id,
+                        vec![Part::Text {
+                            text: format!(
+                                "<todo-reminder open=\"{}\">\n{}\n</todo-reminder>\nThese todos are still open. Continue working until all of them are completed (each completed todo is reviewed). Only if you are truly blocked and need the user, say clearly what you need and stop.",
+                                open.len(),
+                                open.iter().map(|t| format!("- {t}")).collect::<Vec<_>>().join("\n")
+                            ),
+                        }],
+                    )?;
+                    continue;
+                }
+            }
+        }
         if calls.is_empty() && depth == 0 && normal_end && !cancel.is_cancelled() {
             // Refinement loop: a reviewer checks the turn; findings send the agent back to work.
             let rounds = agent.refine.as_ref().map(|r| r.rounds).unwrap_or(0);
             if refine_done < rounds {
                 refine_done += 1;
-                match review_turn(&app, &session, &agent, &model_spec, turn_start, refine_done, rounds, &cancel).await {
+                match review_turn(&app, &session, &agent, &model_spec, turn_start, None, refine_done, rounds, &cancel).await {
                     Ok(Some(feedback)) => {
                         save_user_parts(&app, session_id, vec![Part::Text { text: feedback }])?;
                         continue;
@@ -396,7 +461,8 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
             agent: agent.name.clone(),
             roots: roots.clone(),
             sandbox: crate::sandbox::spec_for(&app, session.owner_id.as_deref()),
-            clean_room,
+            // Clean room is a craft rule; other modes with reverse tools may analyse binaries.
+            clean_room: clean_room && agent.name == "craft",
             owner_id: None,
         };
         let by_name = |n: &str| tools.iter().find(|t| t.name() == n).cloned();
@@ -412,6 +478,40 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
                 results.push(execute_call(&app, &session, &base, by_name(name), id, name, input.clone(), depth).await);
             }
         }
+        // Mode with a review: every todo marked completed is reviewed; with findings it is
+        // reopened and the agent has to fix them and complete it again (max. `rounds` per todo).
+        // The verdict goes into the same message as the tool results.
+        let rounds = enforced_review(&agent);
+        if rounds > 0 && depth == 0 && !cancel.is_cancelled() && calls.iter().any(|(_, n, _)| n == "todo_write") {
+            let todos_now = app.session(session_id)?.todos;
+            let due: Vec<String> = newly_completed(&session.todos, &todos_now)
+                .into_iter()
+                .filter(|t| todo_reviews.get(t).copied().unwrap_or(0) < rounds)
+                .collect();
+            if !due.is_empty() {
+                for t in &due {
+                    *todo_reviews.entry(t.clone()).or_default() += 1;
+                }
+                let round = due.iter().filter_map(|t| todo_reviews.get(t)).copied().max().unwrap_or(1);
+                let fresh = app.session(session_id)?;
+                let reviewed = review_turn(&app, &fresh, &agent, &model_spec, review_since, Some(&due), round, rounds, &cancel).await;
+                review_since = now_ms();
+                match reviewed {
+                    Ok(Some(feedback)) => {
+                        app.set_todos(session_id, reopen_todos(&todos_now, &due))?;
+                        results.push(Part::Text { text: feedback });
+                    }
+                    Ok(None) => {
+                        let open = open_todos(&todos_now);
+                        let next = if open.is_empty() { "All todos are done – check the whole request once more, then finish." } else { "Continue with the next open todo." };
+                        results.push(Part::Text {
+                            text: format!("<refine-approved reviewer=\"{}\">\n{}\n</refine-approved>\nReview passed. {next}", review_model(&agent, &model_spec), due.iter().map(|t| format!("- {t}")).collect::<Vec<_>>().join("\n")),
+                        });
+                    }
+                    Err(e) => tracing::warn!("todo review of {session_id} failed: {e:#}"),
+                }
+            }
+        }
         // Deliver messages the user queued while we were working (with attachments).
         results.extend(take_queue(&app, session_id));
         save_user_parts(&app, session_id, results)?;
@@ -419,6 +519,55 @@ pub async fn run_session(app: Arc<App>, session_id: &str, cancel: CancellationTo
     Ok(final_text)
 }
 
+/// Review rounds when the mode enforces reviews of completed todos (0 = not enforced).
+fn enforced_review(agent: &prompts::Agent) -> u32 {
+    agent.refine.as_ref().filter(|r| r.after_todos).map(|r| r.rounds).unwrap_or(0)
+}
+
+/// The model that reviews for this mode.
+fn review_model(agent: &prompts::Agent, model_spec: &str) -> String {
+    agent.refine.as_ref().and_then(|r| r.model.clone()).filter(|m| !m.is_empty()).unwrap_or_else(|| model_spec.to_string())
+}
+
+/// Contents of the todos that are not completed yet.
+fn open_todos(todos: &Value) -> Vec<String> {
+    todos.as_array().into_iter().flatten().filter(|t| t["status"] != "completed").filter_map(|t| t["content"].as_str()).map(String::from).collect()
+}
+
+/// Times in a row the agent may end its turn with open todos without making progress.
+const MAX_IDLE_CONTINUES: u32 = 10;
+
+/// Contents of the todos that are completed in `after` but were not in `before`.
+fn newly_completed(before: &Value, after: &Value) -> Vec<String> {
+    let done_before: std::collections::HashSet<&str> = before
+        .as_array()
+        .into_iter()
+        .flatten()
+        .filter(|t| t["status"] == "completed")
+        .filter_map(|t| t["content"].as_str())
+        .collect();
+    after
+        .as_array()
+        .into_iter()
+        .flatten()
+        .filter(|t| t["status"] == "completed")
+        .filter_map(|t| t["content"].as_str())
+        .filter(|c| !done_before.contains(c))
+        .map(String::from)
+        .collect()
+}
+
+/// The todo list with the given items open again (in progress).
+fn reopen_todos(todos: &Value, items: &[String]) -> Value {
+    let mut out = todos.clone();
+    for t in out.as_array_mut().into_iter().flatten() {
+        if t["content"].as_str().is_some_and(|c| items.iter().any(|i| i == c)) {
+            t["status"] = Value::from("in_progress");
+        }
+    }
+    out
+}
+
 fn tool_result(call_id: &str, name: &str, content: String, is_error: bool, meta: Option<Value>) -> Part {
     Part::ToolResult { call_id: call_id.into(), name: name.into(), content, images: vec![], is_error, meta }
 }
@@ -563,7 +712,15 @@ async fn execute_call(
         // Pass depth through the agent name channel: subagents run with depth+1.
         run_task(app, &ctx, input, depth).await
     } else {
-        tool.run(input, &ctx).await
+        let moves = name == "bash" && input["command"].as_str().is_some_and(moves_files);
+        let out = tool.run(input, &ctx).await;
+        if moves {
+            // Generated images the command moved or renamed keep their entries.
+            let a = app.clone();
+            let owner = session.owner_id.clone();
+            tokio::task::spawn_blocking(move || crate::images::relocate_missing(&a, owner.as_deref()));
+        }
+        out
     };
     // Diagnostics: report new errors of the changed file right away.
     let res = match res {
@@ -609,6 +766,11 @@ async fn execute_call(
     }
 }
 
+/// A shell command that may move or rename files (`mv`, `git mv`, `rename`).
+fn moves_files(cmd: &str) -> bool {
+    cmd.split(|c: char| c.is_whitespace() || ";&|()`$".contains(c)).any(|w| w == "mv" || w == "rename")
+}
+
 async fn run_task(app: &Arc<App>, ctx: &ToolCtx, input: Value, depth: usize) -> Result<tools::ToolOutput> {
     let prompt = tools::arg_str(&input, "prompt")?.to_string();
     let description = input["description"].as_str().unwrap_or("subagent").to_string();
@@ -766,6 +928,47 @@ fn estimate_prompt_tokens(req: &ChatRequest) -> u64 {
 
 /// Errors after which the fallback model takes over: the host is unreachable
 /// (connection, timeout, gateway errors) or the provider's budget is used up.
+/// Room an answer gets at least before the conversation is compacted.
+const MIN_ANSWER_ROOM: u64 = 32_000;
+
+/// Estimated input tokens of the next request: the last request (its input and answer)
+/// plus the messages that came after that answer (tool results, user messages), at about
+/// 3 characters per token; without usage (fresh or just compacted) the whole history.
+fn estimate_input(last: Option<&crate::types::Usage>, history: &[Message]) -> u64 {
+    let chars_of = |m: &Message| -> u64 {
+        m.parts
+            .iter()
+            .map(|p| match p {
+                Part::Text { text } | Part::Reasoning { text, .. } | Part::Summary { text, .. } => text.len() as u64,
+                Part::ToolCall { input, .. } => input.to_string().len() as u64,
+                Part::ToolResult { content, images, .. } => content.len() as u64 + images.len() as u64 * 4_500,
+                Part::Image { .. } => 4_500,
+            })
+            .sum()
+    };
+    match last {
+        Some(u) => {
+            let after = history.iter().rposition(|m| m.role == Role::Assistant).map(|i| &history[i + 1..]).unwrap_or(&[]);
+            u.context_tokens() + after.iter().map(chars_of).sum::<u64>() / 3
+        }
+        None => history.iter().map(chars_of).sum::<u64>() / 3 + 8_000,
+    }
+}
+
+/// max_tokens for a request: the model's maximum, but no more than the window leaves
+/// (with a margin for the estimate), and never below a small floor.
+fn answer_budget(max_output: u64, context: Option<u64>, est_input: u64) -> u64 {
+    let Some(ctx) = context else { return max_output };
+    let room = ctx.saturating_sub(est_input + est_input / 50 + 2_000);
+    max_output.min(room).max(4_096.min(max_output))
+}
+
+/// The provider rejected the request because input + output exceed the context window.
+fn is_context_overflow(e: &anyhow::Error) -> bool {
+    let s = format!("{e:#}").to_lowercase();
+    ["input too long", "context length", "context_length", "maximum context", "context window", "prompt is too long", "too many tokens", "reduce the length"].iter().any(|k| s.contains(k))
+}
+
 fn needs_fallback(e: &anyhow::Error) -> bool {
     let s = format!("{e:#}").to_lowercase();
     ["connect", "timed out", "timeout", "http 502", "http 503", "http 504", "dns", "budget"].iter().any(|k| s.contains(k))
@@ -1120,7 +1323,7 @@ fn advance_phase(app: &App, session_id: &str, phase: &str, only_from: Option<&st
 /// Review the last turn against the user's request. Returns feedback for the
 /// agent, or None when the reviewer approves.
 #[allow(clippy::too_many_arguments)]
-async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent, model_spec: &str, turn_start: i64, round: u32, rounds: u32, cancel: &CancellationToken) -> Result<Option<String>> {
+async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent, model_spec: &str, since: i64, todos: Option<&[String]>, round: u32, rounds: u32, cancel: &CancellationToken) -> Result<Option<String>> {
     let refine = agent.refine.clone().unwrap_or_default();
     let spec = refine.model.clone().filter(|m| !m.is_empty()).unwrap_or_else(|| model_spec.to_string());
     let (provider, mut model) = app.registry().resolve(&spec)?;
@@ -1134,7 +1337,12 @@ async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent,
             .rposition(|m| matches!(m.role, Role::User) && m.parts.iter().any(|p| matches!(p, Part::Text { text } if !text.starts_with("<refine-feedback") && !text.starts_with("<hook-"))))
             .unwrap_or(0);
         let request: String = history.get(req_idx).map(|m| m.parts.iter().filter_map(|p| if let Part::Text { text } = p { Some(text.as_str()) } else { None }).collect::<Vec<_>>().join("\n")).unwrap_or_default();
-        let mut work = transcript_of(&history[(req_idx + 1).min(history.len())..]);
+        // A todo review looks at the work since the last review, the end-of-turn review at the whole turn.
+        let from = match todos {
+            Some(_) => history.iter().position(|m| m.created_at >= since).unwrap_or(history.len()).max(req_idx + 1),
+            None => req_idx + 1,
+        };
+        let mut work = transcript_of(&history[from.min(history.len())..]);
         if work.len() > 30_000 {
             let mut start = work.len() - 30_000;
             while !work.is_char_boundary(start) {
@@ -1145,7 +1353,7 @@ async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent,
         // Actual file changes of this turn (checkpoint vs. current content).
         let mut changes = String::new();
         let mut seen = std::collections::HashSet::new();
-        for (path, before) in app.store.checkpoints_since(&session.id, turn_start)? {
+        for (path, before) in app.store.checkpoints_since(&session.id, since)? {
             if !seen.insert(path.clone()) || changes.len() > 30_000 {
                 continue;
             }
@@ -1159,10 +1367,17 @@ async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent,
         let system = "You review the work of an AI coding agent for the user. Be strict about what matters for the user's request and ignore style nitpicks. \
             Reply in exactly this format: the first line is APPROVED or CHANGES_NEEDED. For CHANGES_NEEDED, follow with at most 8 concrete, actionable findings as a bullet list \
             (with file:line where possible). If the important work is done and correct, reply APPROVED.";
+        let focus = match todos {
+            Some(items) => format!(
+                "<completed-todos>\n{}\n</completed-todos>\nThe agent just marked these todo items as completed. Review only whether they are really done and correct; other parts of the request may still be in progress.\n\n",
+                items.iter().map(|t| format!("- {t}")).collect::<Vec<_>>().join("\n")
+            ),
+            None => String::new(),
+        };
         let body = format!(
-            "<request>\n{request}\n</request>\n\n<criteria>\n{criteria}\n</criteria>\n\n<agent-work mode=\"{}\">\n{work}\n</agent-work>\n\n<file-changes>\n{}\n</file-changes>",
+            "<request>\n{request}\n</request>\n\n{focus}<criteria>\n{criteria}\n</criteria>\n\n<agent-work mode=\"{}\">\n{work}\n</agent-work>\n\n<file-changes>\n{}\n</file-changes>",
             agent.name,
-            if changes.is_empty() { "(no files changed in this turn)" } else { changes.as_str() }
+            if changes.is_empty() { "(no files changed since the last review)" } else { changes.as_str() }
         );
         let req = ChatRequest { system: system.into(), messages: vec![Message::new(Role::User, vec![Part::Text { text: body }])], tools: vec![], max_tokens: 4000, reasoning: false, model: model.clone(), session_id: Some(session.id.clone()) };
         let (text, usage) = complete_text(app, &spec, provider, req, cancel.clone()).await?;
@@ -1175,10 +1390,17 @@ async fn review_turn(app: &Arc<App>, session: &Session, agent: &prompts::Agent,
         }
         let findings: String = lines.collect::<Vec<_>>().join("\n");
         let findings = if findings.trim().is_empty() { text.clone() } else { findings };
-        Ok(Some(format!(
+        Ok(Some(match todos {
+            Some(items) => format!(
+                "<refine-feedback round=\"{round}/{rounds}\" reviewer=\"{spec}\" todos=\"{}\">\n{}\n</refine-feedback>\nThe review of the todo(s) you just completed found problems, so they are open again. Fix these findings (or explain briefly why one does not apply), verify, then mark the todo(s) completed again – that triggers the next review.",
+                items.len(),
+                findings.trim()
+            ),
+            None => format!(
                 "<refine-feedback round=\"{round}/{rounds}\" reviewer=\"{spec}\">\n{}\n</refine-feedback>\nAddress these review findings (or explain briefly why one does not apply), verify, then finish.",
                 findings.trim()
-        )))
+            ),
+        }))
     }
     .await;
     app.emit(Event::Waiting { session_id: session.id.clone(), reason: None });
@@ -1301,6 +1523,47 @@ async fn compact_inner(app: Arc<App>, session_id: &str, cancel: CancellationToke
 mod tests {
     use super::*;
 
+    #[test]
+    fn todo_completion_and_reopening() {
+        let before = serde_json::json!([{"content": "A", "status": "in_progress"}, {"content": "B", "status": "completed"}, {"content": "C", "status": "pending"}]);
+        let after = serde_json::json!([{"content": "A", "status": "completed"}, {"content": "B", "status": "completed"}, {"content": "C", "status": "pending"}]);
+        assert_eq!(newly_completed(&before, &after), vec!["A".to_string()]);
+        assert_eq!(newly_completed(&Value::Null, &after), vec!["A".to_string(), "B".to_string()]);
+        assert_eq!(open_todos(&after), vec!["C".to_string()]);
+        let reopened = reopen_todos(&after, &["A".to_string()]);
+        assert_eq!(reopened[0]["status"], "in_progress");
+        assert_eq!(reopened[1]["status"], "completed");
+    }
+
+    #[test]
+    fn answer_room_and_overflow() {
+        // The case from production: DeepSeek V4.1 Flash, 1M window, 384K output, 720K input.
+        let (ctx, out) = (1_048_576u64, 393_216u64);
+        let b = answer_budget(out, Some(ctx), 720_000);
+        assert!(720_000 + b <= ctx && b > 300_000, "{b}");
+        assert_eq!(answer_budget(out, Some(ctx), 100_000), out);
+        assert_eq!(answer_budget(16_000, None, 5_000_000), 16_000);
+        assert_eq!(answer_budget(out, Some(ctx), 1_040_000), 4_096);
+        assert!(is_context_overflow(&anyhow!("HTTP 400: [invalid_request_error] Input too long: model limit 1048576 tokens, requested 1108739 tokens")));
+        assert!(is_context_overflow(&anyhow!("This model's maximum context length is 128000 tokens")));
+        assert!(!is_context_overflow(&anyhow!("HTTP 429 rate limited")));
+        // Estimate: last request + what came after its answer (about 3 chars per token).
+        let u = crate::types::Usage { input_tokens: 1_000, cache_read_tokens: 9_000, output_tokens: 500, ..Default::default() };
+        let mut call = Message::new(Role::Assistant, vec![call("c1")]);
+        call.id = "a".into();
+        let result = Message::new(Role::User, vec![Part::ToolResult { call_id: "c1".into(), name: "bash".into(), content: "x".repeat(3_000), images: vec![], is_error: false, meta: None }]);
+        assert_eq!(estimate_input(Some(&u), &[call.clone(), result.clone()]), 10_500 + 1_000);
+        assert!(estimate_input(None, &[call, result]) >= 1_000 + 8_000);
+    }
+
+    #[test]
+    fn detects_commands_that_move_files() {
+        assert!(moves_files("mkdir -p art/old && mv art/*.png art/old/"));
+        assert!(moves_files("git mv a.png b.png"));
+        assert!(moves_files("cd art;mv x y"));
+        assert!(!moves_files("ls -la movies && cat remove.txt"));
+    }
+
     fn call(id: &str) -> Part {
         Part::ToolCall { id: id.into(), name: "bash".into(), input: serde_json::json!({}), extra: None }
     }

server/src/store.rs

@@ -1,6 +1,6 @@
 //! SQLite persistence for sessions and messages.
 
-use crate::types::{ImageData, Message, Part, Session, now_ms};
+use crate::types::{ImageData, Message, Part, Role, Session, now_ms};
 use serde::Serialize;
 use serde_json::{Value, json};
 use anyhow::Result;
@@ -170,6 +170,7 @@ impl Store {
             ("users", "monthly_quota", "ALTER TABLE users ADD COLUMN monthly_quota REAL"),
             ("jobs", "webhook_secret", "ALTER TABLE jobs ADD COLUMN webhook_secret TEXT"),
             ("jobs", "settings", "ALTER TABLE jobs ADD COLUMN settings TEXT"),
+            ("images", "blob", "ALTER TABLE images ADD COLUMN blob TEXT"),
             ("usage", "allowance", "ALTER TABLE usage ADD COLUMN allowance REAL"),
         ] {
             let exists: bool = conn
@@ -243,28 +244,7 @@ impl Store {
             let (sdata, mdata) = row?;
             let session: Session = serde_json::from_str(&sdata)?;
             // Snippet from the visible text of the matching message (not JSON keys).
-            let mut snippet = String::new();
-            if let Some(m) = mdata.and_then(|d| serde_json::from_str::<Message>(&d).ok()) {
-                for p in &m.parts {
-                    let text = match p {
-                        Part::Text { text } | Part::Summary { text, .. } | Part::Reasoning { text, .. } => text.as_str(),
-                        Part::ToolResult { content, .. } => content.as_str(),
-                        _ => continue,
-                    };
-                    if let Some(i) = text.to_lowercase().find(&needle) {
-                        let mut a = i.saturating_sub(60);
-                        while !text.is_char_boundary(a) {
-                            a -= 1;
-                        }
-                        let mut b = (i + needle.len() + 100).min(text.len());
-                        while !text.is_char_boundary(b) {
-                            b += 1;
-                        }
-                        snippet = format!("{}{}{}", if a > 0 { "…" } else { "" }, text[a..b].replace('\n', " "), if b < text.len() { "…" } else { "" });
-                        break;
-                    }
-                }
-            }
+            let snippet = mdata.and_then(|d| serde_json::from_str::<Message>(&d).ok()).and_then(|m| snippet_in(&m, &needle)).unwrap_or_default();
             if snippet.is_empty() && !session.title.to_lowercase().contains(&needle) {
                 continue; // matched only JSON structure (keys, ids)
             }
@@ -273,6 +253,121 @@ impl Store {
         Ok(out)
     }
 
+    /// A part of a session's messages for the chat view (long chats are not loaded at
+    /// once). Returns the messages (oldest first) and whether older / newer ones exist.
+    pub fn messages_window(&self, session_id: &str, w: &MessageWindow) -> Result<(Vec<Message>, bool, bool)> {
+        let conn = self.conn.lock().unwrap();
+        let seq_of = |id: &str| -> Result<i64> {
+            conn.query_row("SELECT seq FROM messages WHERE session_id = ?1 AND id = ?2", params![session_id, id], |r| r.get(0))
+                .optional()?
+                .ok_or_else(|| anyhow::anyhow!("message {id} not found"))
+        };
+        let (sql, a, limit): (&str, i64, i64) = match w {
+            // From the last summary (compaction) on, at most `limit`.
+            MessageWindow::Tail { limit } => {
+                let from: i64 = conn
+                    .query_row(
+                        "SELECT seq FROM messages WHERE session_id = ?1 AND data LIKE '%\"type\":\"summary\"%' ORDER BY seq DESC LIMIT 1",
+                        [session_id],
+                        |r| r.get(0),
+                    )
+                    .optional()?
+                    .unwrap_or(i64::MIN);
+                ("SELECT data FROM messages WHERE session_id = ?1 AND seq >= ?2 ORDER BY seq DESC LIMIT ?3", from, *limit)
+            }
+            // Scrolling up stops at a summary (compaction); the history before it on request.
+            MessageWindow::Before { id, limit, stop_at_summary } => {
+                let before = seq_of(id)?;
+                let summary: Option<i64> = if *stop_at_summary {
+                    conn.query_row(
+                        "SELECT seq FROM messages WHERE session_id = ?1 AND seq < ?2 AND data LIKE '%\"type\":\"summary\"%' ORDER BY seq DESC LIMIT 1",
+                        params![session_id, before],
+                        |r| r.get(0),
+                    )
+                    .optional()?
+                } else {
+                    None
+                };
+                match summary {
+                    Some(from) => {
+                        let mut stmt = conn.prepare("SELECT seq, data FROM messages WHERE session_id = ?1 AND seq >= ?2 AND seq < ?3 ORDER BY seq DESC LIMIT ?4")?;
+                        let mut rows: Vec<(i64, Message)> = Vec::new();
+                        for r in stmt.query_map(params![session_id, from, before, limit], |r| Ok((r.get::<_, i64>(0)?, r.get::<_, String>(1)?)))? {
+                            let (seq, data) = r?;
+                            rows.push((seq, serde_json::from_str(&data)?));
+                        }
+                        drop(stmt);
+                        return Self::finish_window(&conn, session_id, rows, false);
+                    }
+                    None => ("SELECT data FROM messages WHERE session_id = ?1 AND seq < ?2 ORDER BY seq DESC LIMIT ?3", before, *limit),
+                }
+            }
+            MessageWindow::After { id, limit } => ("SELECT data FROM messages WHERE session_id = ?1 AND seq > ?2 ORDER BY seq ASC LIMIT ?3", seq_of(id)?, *limit),
+            // The message and about half the limit before it.
+            MessageWindow::Around { id, limit } => {
+                let seq = seq_of(id)?;
+                let before: i64 = conn.query_row(
+                    "SELECT COALESCE(MIN(seq), ?2) FROM (SELECT seq FROM messages WHERE session_id = ?1 AND seq < ?2 ORDER BY seq DESC LIMIT ?3)",
+                    params![session_id, seq, limit / 2],
+                    |r| r.get(0),
+                )?;
+                ("SELECT data FROM messages WHERE session_id = ?1 AND seq >= ?2 ORDER BY seq ASC LIMIT ?3", before, *limit)
+            }
+        };
+        let mut rows: Vec<(i64, Message)> = Vec::new();
+        let mut stmt = conn.prepare(&sql.replace("SELECT data", "SELECT seq, data"))?;
+        for r in stmt.query_map(params![session_id, a, limit], |r| Ok((r.get::<_, i64>(0)?, r.get::<_, String>(1)?)))? {
+            let (seq, data) = r?;
+            rows.push((seq, serde_json::from_str(&data)?));
+        }
+        drop(stmt);
+        Self::finish_window(&conn, session_id, rows, matches!(w, MessageWindow::Tail { .. }))
+    }
+
+    /// Sort a window and tell whether older / newer messages exist around it.
+    fn finish_window(conn: &Connection, session_id: &str, mut rows: Vec<(i64, Message)>, tail: bool) -> Result<(Vec<Message>, bool, bool)> {
+        rows.sort_by_key(|(seq, _)| *seq);
+        let exists = |q: &str, seq: i64| -> Result<bool> { Ok(conn.prepare(q)?.exists(params![session_id, seq])?) };
+        let older = match rows.first() {
+            Some((first, _)) => exists("SELECT 1 FROM messages WHERE session_id = ?1 AND seq < ?2", *first)?,
+            None => tail && exists("SELECT 1 FROM messages WHERE session_id = ?1 AND seq > ?2", i64::MIN)?,
+        };
+        let newer = match rows.last() {
+            Some((last, _)) => exists("SELECT 1 FROM messages WHERE session_id = ?1 AND seq > ?2", *last)?,
+            None => false,
+        };
+        Ok((rows.into_iter().map(|(_, m)| m).collect(), older, newer))
+    }
+
+    /// Messages of one session containing `q` (case-insensitive), newest first:
+    /// (message id, role, created_at, snippet).
+    pub fn search_messages(&self, session_id: &str, q: &str, limit: usize) -> Result<Vec<(String, Role, i64, String)>> {
+        let needle = q.to_lowercase();
+        let like = format!("%{}%", q.replace('\\', "\\\\").replace('%', "\\%").replace('_', "\\_"));
+        let conn = self.conn.lock().unwrap();
+        let mut stmt = conn.prepare("SELECT data FROM messages WHERE session_id = ?1 AND data LIKE ?2 ESCAPE '\\' ORDER BY seq DESC")?;
+        let mut out = Vec::new();
+        for r in stmt.query_map(params![session_id, like], |r| r.get::<_, String>(0))? {
+            let Ok(m) = serde_json::from_str::<Message>(&r?) else { continue };
+            // Only visible text counts (not JSON keys or ids).
+            if let Some(snippet) = snippet_in(&m, &needle) {
+                out.push((m.id.clone(), m.role, m.created_at, snippet));
+                if out.len() >= limit {
+                    break;
+                }
+            }
+        }
+        Ok(out)
+    }
+
+    /// Ids of the subagent sessions started by a session.
+    pub fn child_sessions(&self, id: &str) -> Result<Vec<String>> {
+        let conn = self.conn.lock().unwrap();
+        let mut stmt = conn.prepare("SELECT id FROM sessions WHERE parent_id = ?1")?;
+        let rows = stmt.query_map([id], |r| r.get(0))?.collect::<rusqlite::Result<Vec<String>>>()?;
+        Ok(rows)
+    }
+
     pub fn delete_session(&self, id: &str) -> Result<()> {
         let conn = self.conn.lock().unwrap();
         // Child sessions (subagents) go with their parent.
@@ -394,6 +489,10 @@ impl Store {
         }
         drop(rows);
         drop(stmt);
+        // Copies of generated images (see ImageRecord::blob).
+        for h in conn.prepare("SELECT blob FROM images WHERE blob IS NOT NULL")?.query_map([], |r| r.get::<_, String>(0))? {
+            used.insert(h?);
+        }
         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)) {
@@ -966,6 +1065,10 @@ pub struct ImageRecord {
     pub width: i64,
     pub height: i64,
     pub created_at: i64,
+    /// Copy of the bytes in the image store: the file may be moved or deleted later
+    /// (agents tidy up folders), the image stays viewable.
+    #[serde(skip)]
+    pub blob: Option<String>,
 }
 
 fn image_row(r: &rusqlite::Row) -> rusqlite::Result<ImageRecord> {
@@ -979,22 +1082,74 @@ fn image_row(r: &rusqlite::Row) -> rusqlite::Result<ImageRecord> {
         width: r.get(6)?,
         height: r.get(7)?,
         created_at: r.get(8)?,
+        blob: r.get(9)?,
     })
 }
 
-const IMAGE_COLS: &str = "id, user_id, session_id, prompt, model, path, width, height, created_at";
+const IMAGE_COLS: &str = "id, user_id, session_id, prompt, model, path, width, height, created_at, blob";
 
 impl Store {
     pub fn add_image(&self, img: &ImageRecord) -> Result<()> {
         let conn = self.conn.lock().unwrap();
         conn.execute(
-            &format!("INSERT INTO images ({IMAGE_COLS}) VALUES (?1,?2,?3,?4,?5,?6,?7,?8,?9)"),
-            params![img.id, img.user_id, img.session_id, img.prompt, img.model, img.path, img.width, img.height, img.created_at],
+            &format!("INSERT INTO images ({IMAGE_COLS}) VALUES (?1,?2,?3,?4,?5,?6,?7,?8,?9,?10)"),
+            params![img.id, img.user_id, img.session_id, img.prompt, img.model, img.path, img.width, img.height, img.created_at, img.blob],
         )?;
         Ok(())
     }
 
+    /// Store bytes in the image store; returns their hash.
+    pub fn put_blob(&self, media_type: &str, bytes: &[u8]) -> Result<String> {
+        let hash = crate::blobs::hash(bytes);
+        self.conn.lock().unwrap().execute(
+            "INSERT OR IGNORE INTO blobs (hash, media_type, data, created_at) VALUES (?1, ?2, ?3, ?4)",
+            params![hash, media_type, bytes, now_ms()],
+        )?;
+        Ok(hash)
+    }
+
+    /// Generated images from before the copies in the image store (id, path).
+    pub fn images_without_copy(&self) -> Result<Vec<(String, String)>> {
+        let conn = self.conn.lock().unwrap();
+        let mut stmt = conn.prepare("SELECT id, path FROM images WHERE blob IS NULL")?;
+        let rows = stmt.query_map([], |r| Ok((r.get(0)?, r.get(1)?)))?.collect::<rusqlite::Result<Vec<_>>>()?;
+        Ok(rows)
+    }
+
+    pub fn set_image_blob(&self, id: &str, hash: &str) -> Result<()> {
+        self.conn.lock().unwrap().execute("UPDATE images SET blob = ?2 WHERE id = ?1", params![id, hash])?;
+        Ok(())
+    }
+
+    /// A file or folder was moved: generated images in it follow.
+    pub fn move_image_paths(&self, from: &str, to: &str) -> Result<usize> {
+        let from = from.trim_end_matches('/');
+        let to = to.trim_end_matches('/');
+        Ok(self.conn.lock().unwrap().execute(
+            "UPDATE images SET path = ?2 || substr(path, length(?1) + 1)
+             WHERE path = ?1 OR substr(path, 1, length(?1) + 1) = ?1 || '/'",
+            params![from, to],
+        )?)
+    }
+
+    /// The file of a generated image was found somewhere else.
+    pub fn set_image_path(&self, id: &str, path: &str) -> Result<()> {
+        self.conn.lock().unwrap().execute("UPDATE images SET path = ?2 WHERE id = ?1", params![id, path])?;
+        Ok(())
+    }
+
     /// Latest images; `user = None` lists everybody's (admins).
+    /// Generated images of these sessions.
+    pub fn images_of_sessions(&self, sessions: &[String]) -> Result<Vec<ImageRecord>> {
+        let conn = self.conn.lock().unwrap();
+        let mut stmt = conn.prepare(&format!("SELECT {IMAGE_COLS} FROM images WHERE session_id = ?1"))?;
+        let mut out = Vec::new();
+        for s in sessions {
+            out.extend(stmt.query_map([s], image_row)?.collect::<rusqlite::Result<Vec<_>>>()?);
+        }
+        Ok(out)
+    }
+
     pub fn images(&self, user: Option<&str>, limit: i64) -> Result<Vec<ImageRecord>> {
         let conn = self.conn.lock().unwrap();
         let mut stmt = conn.prepare(&format!(
@@ -1342,3 +1497,45 @@ pub struct PushSub {
     pub p256dh: String,
     pub auth: String,
 }
+
+/// Which messages of a session the chat view loads (see Store::messages_window).
+pub enum MessageWindow {
+    Tail { limit: i64 },
+    Before { id: String, limit: i64, stop_at_summary: bool },
+    After { id: String, limit: i64 },
+    Around { id: String, limit: i64 },
+}
+
+/// Text around the first occurrence of `needle` (lowercase) in the visible text of a
+/// message: its text, reasoning, summaries, tool calls and tool output.
+fn snippet_in(m: &Message, needle: &str) -> Option<String> {
+    for p in &m.parts {
+        let owned;
+        let text = match p {
+            Part::Text { text } | Part::Summary { text, .. } | Part::Reasoning { text, .. } => text.as_str(),
+            Part::ToolResult { content, .. } => content.as_str(),
+            Part::ToolCall { input, .. } => {
+                owned = input.to_string();
+                owned.as_str()
+            }
+            _ => continue,
+        };
+        let lower = text.to_lowercase();
+        // Lowercasing can change byte lengths (rare): then cut the lowercase text.
+        let (src, i) = match lower.find(needle) {
+            Some(i) if lower.len() == text.len() => (text, i),
+            Some(i) => (lower.as_str(), i),
+            None => continue,
+        };
+        let mut a = i.saturating_sub(60);
+        while !src.is_char_boundary(a) {
+            a -= 1;
+        }
+        let mut b = (i + needle.len() + 100).min(src.len());
+        while !src.is_char_boundary(b) {
+            b += 1;
+        }
+        return Some(format!("{}{}{}", if a > 0 { "…" } else { "" }, src[a..b].replace('\n', " "), if b < src.len() { "…" } else { "" }));
+    }
+    None
+}

server/src/tools/bash.rs

@@ -135,7 +135,7 @@ impl Tool for Bash {
 /// The bash command for a script, sandboxed for non-admin users.
 pub fn shell_command(ctx: &ToolCtx, command: &str) -> std::result::Result<Command, ToolOutput> {
     // stderr of every command (not just the last one) goes into the output.
-    let script = format!("exec 2>&1\n{command}");
+    let script = format!("exec 2>&1\n{}{command}", commit_attribution(ctx));
     Ok(match &ctx.sandbox {
         Some(spec) => {
             if !crate::sandbox::available() {
@@ -161,6 +161,36 @@ pub fn shell_command(ctx: &ToolCtx, command: &str) -> std::result::Result<Comman
     })
 }
 
+/// Directory with the git wrapper that adds the co-author trailer to commits.
+fn git_wrapper_dir() -> String {
+    std::env::var("CODECRAFT_GIT_WRAPPER").unwrap_or_else(|_| "/usr/local/lib/codecraft/bin".into())
+}
+
+/// Shell lines that make `git commit` in this command carry the co-author trailer of
+/// the session's model (see docker/git-coauthor). Set in the script itself, so it
+/// works inside the sandbox (which clears the environment) too.
+fn commit_attribution(ctx: &ToolCtx) -> String {
+    let template = ctx.app.config().server.commit_trailer.clone();
+    let dir = git_wrapper_dir();
+    if template.trim().is_empty() || !std::path::Path::new(&dir).join("git").exists() {
+        return String::new();
+    }
+    let Ok(session) = ctx.app.session(&ctx.session_id) else { return String::new() };
+    let (provider, model_id) = session.model.split_once('/').unwrap_or(("", session.model.as_str()));
+    let name = ctx.app.registry().resolve(&session.model).ok().and_then(|(_, m)| m.name).filter(|n| !n.trim().is_empty()).unwrap_or_else(|| model_id.to_string());
+    let trailer = commit_trailer(&template, &name, provider, model_id);
+    format!("export PATH={}:\"$PATH\" CODECRAFT_COMMIT_TRAILER={}\n", shell_quote(&dir), shell_quote(&trailer))
+}
+
+/// The trailer text for a model ("Co-Authored-By: DeepSeek V4.1 Flash (opencode-go) via CodeCraft").
+pub fn commit_trailer(template: &str, model: &str, provider: &str, model_id: &str) -> String {
+    template.replace("{model}", model).replace("{provider}", provider).replace("{model_id}", model_id).replace(['\n', '\r'], " ").trim().to_string()
+}
+
+fn shell_quote(s: &str) -> String {
+    format!("'{}'", s.replace('\'', "'\\''"))
+}
+
 fn tail(s: &str, max: usize) -> String {
     if s.len() <= max {
         return s.to_string();
@@ -171,3 +201,18 @@ fn tail(s: &str, max: usize) -> String {
     }
     s[start..].to_string()
 }
+
+#[cfg(test)]
+mod commit_tests {
+    use super::*;
+
+    #[test]
+    fn commit_trailer_text() {
+        assert_eq!(
+            commit_trailer(crate::config::DEFAULT_COMMIT_TRAILER, "DeepSeek V4.1 Flash", "opencode-go", "deepseek-v4.1-flash"),
+            "Co-Authored-By: DeepSeek V4.1 Flash (opencode-go) via CodeCraft"
+        );
+        assert_eq!(commit_trailer("By {model_id}\nx", "M", "p", "m-1"), "By m-1 x");
+        assert_eq!(shell_quote("it's"), "'it'\\''s'");
+    }
+}

web/index.html

@@ -2,7 +2,9 @@
 <html lang="en">
   <head>
     <meta charset="UTF-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover" />
+    <!-- interactive-widget: the on-screen keyboard shrinks the page (Android) instead of
+         shifting it up – the top bar stays in place. -->
+    <meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover, interactive-widget=resizes-content" />
     <meta name="theme-color" content="#282828" />
     <link rel="icon" href="/icon.svg" type="image/svg+xml" />
     <link rel="apple-touch-icon" href="/apple-touch-icon.png" />

web/src/components/ChatView.tsx

@@ -1,12 +1,12 @@
 import { takePrefill } from "../share";
 import { Icon } from "./Icon";
 import { FileChip, FileFigure, fileType, imageSize, imageSrc } from "./FileFigure";
-import { useEffect, useLayoutEffect, useMemo, useRef, useState } from "react";
+import { memo, useCallback, useEffect, useLayoutEffect, useMemo, useRef, useState, type ReactNode, type RefObject } from "react";
 import { del, get, patch, post } from "../api";
 import { useFetch, useModels } from "../hooks";
 import { fmtCompact, fmtCost, fmtNumber, fmtPercent, useT, type Key } from "../i18n";
 import { navigate } from "../router";
-import { dismissError, loadSession, loadSessions, useStore } from "../store";
+import { dismissError, getState, loadAround, loadOlder, loadSession, loadSessions, useStore } from "../store";
 import type { Aggregate, ImageData, Message, Part, Session, Todo } from "../types";
 import { ActivityLine, Dots, Spinner, ThinkIcon, WorkBar } from "./Activity";
 import { useReasoningMode, useTodosCollapsed } from "../prefs";
@@ -26,8 +26,10 @@ import { ShellsChip } from "./ShellsPanel";
 import { TodoList, ToolCard } from "./ToolCard";
 import { confirmDialog, promptDialog, toast } from "../dialogs";
 import { ChatTabBar, ChatTabPanes, useChatTabs } from "./ChatTabs";
+import { MediaGallery } from "./MediaGallery";
 
 type ToolResult = Extract<Part, { type: "tool_result" }>;
+type ToolCall = Extract<Part, { type: "tool_call" }>;
 
 const EMPTY: Message[] = [];
 
@@ -115,7 +117,36 @@ function BackgroundResult({ text }: { text: string }) {
   );
 }
 
-const REFINE_RE = /^<refine-feedback round="([^"]*)" reviewer="([^"]*)">\n?([\s\S]*?)\n?<\/refine-feedback>/;
+const REFINE_RE = /^<refine-feedback round="([^"]*)" reviewer="([^"]*)"(?: todos="\d+")?>\n?([\s\S]*?)\n?<\/refine-feedback>/;
+/** Enforced reviews: a completed todo passed, or a reminder about open todos. */
+const NOTE_RE = /^<(refine-approved|todo-reminder)(?: reviewer="([^"]*)")?(?: open="\d+")?>\n?([\s\S]*?)\n?<\/(?:refine-approved|todo-reminder)>/;
+/** Messages from the harness shown as cards instead of user bubbles. */
+const isHarnessNote = (text: string) => BG_RE.test(text) || REFINE_RE.test(text) || NOTE_RE.test(text);
+
+/** A todo passed its review, or the agent was sent back to its open todos. */
+function HarnessNote({ text }: { text: string }) {
+  const t = useT();
+  const m = text.match(NOTE_RE);
+  if (!m) return null;
+  const [, kind, reviewer, body] = m;
+  const items = body.split("\n").map((l) => l.replace(/^- /, "").trim()).filter(Boolean);
+  const approved = kind === "refine-approved";
+  return (
+    <div className={`harness-note ${approved ? "ok" : ""}`}>
+      <Icon name={approved ? "check" : "refresh"} />
+      <span className="grow">
+        <b>{t(approved ? "chat.reviewPassed" : "chat.todoReminder", { n: items.length })}</b> {items.join(" · ")}
+      </span>
+      {reviewer && <span className="chip">{reviewer}</span>}
+    </div>
+  );
+}
+
+function HarnessMessage({ text }: { text: string }) {
+  if (REFINE_RE.test(text)) return <RefineFeedback text={text} />;
+  if (NOTE_RE.test(text)) return <HarnessNote text={text} />;
+  return <BackgroundResult text={text} />;
+}
 
 /** Findings of the review loop, sent back to the agent. */
 function RefineFeedback({ text }: { text: string }) {
@@ -137,10 +168,299 @@ function RefineFeedback({ text }: { text: string }) {
   );
 }
 
+/** Search the whole chat on the server; a hit loads its part of the chat. */
+function ChatSearch({ sessionId, onPick, onClose }: { sessionId: string; onPick: (messageId: string) => void; onClose: () => void }) {
+  const t = useT();
+  const [q, setQ] = useState("");
+  const [hits, setHits] = useState<{ id: string; role: string; created_at: number; snippet: string }[]>();
+  useEffect(() => {
+    const query = q.trim();
+    if (query.length < 2) return setHits(undefined);
+    let alive = true;
+    const h = setTimeout(() => {
+      get<typeof hits>(`/sessions/${sessionId}/search?q=${encodeURIComponent(query)}`)
+        .then((r) => alive && setHits(r ?? []))
+        .catch(() => alive && setHits([]));
+    }, 250);
+    return () => {
+      alive = false;
+      clearTimeout(h);
+    };
+  }, [q, sessionId]);
+  return (
+    <div className="chat-search" role="search">
+      <div className="row">
+        <Icon name="search" />
+        <input autoFocus value={q} placeholder={t("chat.searchPlaceholder")} onChange={(e) => setQ(e.target.value)} onKeyDown={(e) => e.key === "Escape" && onClose()} aria-label={t("chat.search")} />
+        <button className="small ghost" onClick={onClose} aria-label={t("common.close")}>
+          <Icon name="close" />
+        </button>
+      </div>
+      {hits && (
+        <div className="chat-search-hits">
+          <div className="hint">{hits.length ? t("chat.searchHits", { n: hits.length }) : t("chat.searchNone")}</div>
+          {hits.map((h) => (
+            <button key={h.id} onClick={() => onPick(h.id)}>
+              <span className="who">
+                {t(h.role === "assistant" ? "chat.agent" : "chat.you")} · {new Date(h.created_at).toLocaleString(undefined, { dateStyle: "short", timeStyle: "short" })}
+              </span>
+              <span className="snippet">{h.snippet}</span>
+            </button>
+          ))}
+        </div>
+      )}
+    </div>
+  );
+}
+
+/** A part of the chat: a user message, a summary, or the work of the agent after it. */
+type Block = { kind: "user" | "summary" | "work"; messages: Message[] };
+
+const hasUserText = (m: Message) => m.role === "user" && m.parts.some((p) => (p.type === "text" && !isHarnessNote(p.text)) || p.type === "image");
+
+/** Group the messages into user messages and the agent's work between them. */
+function blocksOf(messages: Message[]): Block[] {
+  const out: Block[] = [];
+  for (const m of messages) {
+    const kind = m.parts.some((p) => p.type === "summary") ? "summary" : hasUserText(m) ? "user" : "work";
+    const last = out[out.length - 1];
+    if (kind === "work" && last?.kind === "work") last.messages.push(m);
+    else out.push({ kind, messages: [m] });
+  }
+  return out;
+}
+
+/**
+ * The messages of a chat. Memoised: typing, streaming and status changes of the
+ * chat view do not touch it – only new messages, tool results or the busy state.
+ */
+const MessageList = memo(function MessageList({
+  messages,
+  results,
+  busy,
+  canEdit,
+  canRegenerate,
+  sessionId,
+  model,
+  baseDir,
+  onRewind,
+  highlight,
+}: {
+  messages: Message[];
+  results: Map<string, ToolResult>;
+  busy: boolean;
+  canEdit: boolean;
+  canRegenerate: boolean;
+  sessionId: string;
+  model: string;
+  baseDir: string;
+  onRewind: (m: Message) => void;
+  highlight?: string;
+}) {
+  const blocks = useMemo(() => blocksOf(messages), [messages]);
+  const lastWork = blocks.map((b) => b.kind).lastIndexOf("work");
+  const lastAssistant = [...messages].reverse().find((m) => m.role === "assistant")?.id;
+  return (
+    <>
+      {blocks.map((b, i) => {
+        // Stable while older messages are loaded above (they may join the first block):
+        // the last message; the block still growing at the end keeps its first one.
+        const key = b.kind === "work" && i !== lastWork ? b.messages[b.messages.length - 1].id : b.messages[0].id;
+        if (b.kind !== "work") return <MessageItem key={key} m={b.messages[0]} canEdit={canEdit} onRewind={onRewind} highlight={highlight} />;
+        const items = b.messages.map((m) => (
+          <AssistantOrNote
+            key={m.id}
+            m={m}
+            results={results}
+            busy={busy}
+            baseDir={baseDir}
+            highlight={highlight}
+            regenerate={canRegenerate && m.id === lastAssistant ? { sessionId, model } : undefined}
+          />
+        ));
+        // Finished turns with tool steps fold into one line (the answer stays visible).
+        const steps = b.messages.flatMap((m) => m.parts.filter((p) => p.type === "tool_call")) as ToolCall[];
+        if (i === lastWork || steps.length < 2) return <div key={key}>{items}</div>;
+        return <WorkBlock key={key} messages={b.messages} steps={steps} open={!!highlight && b.messages.some((m) => m.id === highlight)} baseDir={baseDir}>{items}</WorkBlock>;
+      })}
+    </>
+  );
+});
+
+/** A finished turn: "42 steps · 3 files" and the answer; the steps on click. */
+function WorkBlock({ messages, steps, open: forced, baseDir, children }: { messages: Message[]; steps: ToolCall[]; open: boolean; baseDir: string; children: ReactNode }) {
+  const t = useT();
+  const [open, setOpen] = useState(false);
+  const files = new Set(steps.filter((c) => ["write", "edit"].includes(c.name) && typeof c.input?.path === "string").map((c) => c.input.path as string));
+  // The answer: text of the last assistant message of the turn.
+  const answer = [...messages].reverse().find((m) => m.role === "assistant" && m.parts.some((p) => p.type === "text" && p.text.trim()));
+  const answerText = answer ? (answer.parts.filter((p) => p.type === "text") as { text: string }[]).map((p) => p.text).join("\n\n") : "";
+  if (open || forced) {
+    return (
+      <div className="work-block open">
+        <button className="work-head" onClick={() => setOpen(false)} aria-expanded>
+          <Icon name="chevron-down" className="tiny" /> {t("chat.workSteps", { n: steps.length })}
+          {files.size > 0 && <span> · {t("chat.workFiles", { n: files.size })}</span>}
+        </button>
+        {children}
+      </div>
+    );
+  }
+  return (
+    <div className="msg work-block" data-mid={answer?.id}>
+      <button className="work-head" onClick={() => setOpen(true)} aria-expanded={false}>
+        <Icon name="chevron-right" className="tiny" /> {t("chat.workSteps", { n: steps.length })}
+        {files.size > 0 && <span> · {t("chat.workFiles", { n: files.size })}</span>}
+      </button>
+      {answerText && (
+        <>
+          <Markdown text={answerText} baseDir={baseDir} />
+          <ImageRefs text={answerText} baseDir={baseDir} />
+        </>
+      )}
+    </div>
+  );
+}
+
+/** An assistant message, or a user message that only carries tool results / harness notes. */
+const AssistantOrNote = memo(function AssistantOrNote({
+  m,
+  results,
+  busy,
+  baseDir,
+  highlight,
+  regenerate,
+}: {
+  m: Message;
+  results: Map<string, ToolResult>;
+  busy: boolean;
+  baseDir: string;
+  highlight?: string;
+  regenerate?: { sessionId: string; model: string };
+}) {
+  const cls = `msg ${highlight === m.id ? "highlight" : ""}`;
+  if (m.role === "assistant") {
+    return (
+      <div className={cls} data-mid={m.id}>
+        <AssistantParts parts={m.parts} results={results} running={busy} live={false} baseDir={baseDir} />
+        {regenerate && <RegenerateButton sessionId={regenerate.sessionId} messageId={m.id} model={regenerate.model} />}
+      </div>
+    );
+  }
+  const notes = (m.parts.filter((p) => p.type === "text") as { text: string }[]).filter((p) => isHarnessNote(p.text));
+  if (!notes.length) return null;
+  return (
+    <div className={cls} data-mid={m.id}>
+      {notes.map((p, i) => (
+        <HarnessMessage key={i} text={p.text} />
+      ))}
+    </div>
+  );
+});
+
+/** A user message or a summary of the history before it. */
+const MessageItem = memo(function MessageItem({ m, canEdit, onRewind, highlight }: { m: Message; canEdit: boolean; onRewind: (m: Message) => void; highlight?: string }) {
+  const t = useT();
+  const [summaryOpen, setSummaryOpen] = useState(false);
+  const summary = m.parts.find((p) => p.type === "summary");
+  if (summary && summary.type === "summary") {
+    return (
+      <details className="summary-divider" data-mid={m.id} onToggle={(e) => setSummaryOpen((e.currentTarget as HTMLDetailsElement).open)}>
+        <summary>
+          {summary.auto
+            ? t("chat.compactedAuto", { tokens: summary.tokens ? fmtCompact(summary.tokens) : "?" })
+            : summary.tokens
+              ? t("chat.compactedManual", { tokens: fmtCompact(summary.tokens) })
+              : t("chat.compacted")}
+        </summary>
+        {summaryOpen && <Markdown text={summary.text} />}
+      </details>
+    );
+  }
+  const allTexts = m.parts.filter((p) => p.type === "text") as { text: string }[];
+  const background = allTexts.filter((p) => isHarnessNote(p.text));
+  const texts = allTexts.filter((p) => !isHarnessNote(p.text));
+  const imgs = m.parts.filter((p) => p.type === "image") as { image: ImageData }[];
+  return (
+    <div className={`msg ${highlight === m.id ? "highlight" : ""}`} data-mid={m.id}>
+      {background.map((p, i) => (
+        <HarnessMessage key={i} text={p.text} />
+      ))}
+      <div className="msg-user">
+        {canEdit && (
+          <div className="msg-actions">
+            <button className="small ghost" onClick={() => onRewind(m)} title={t("chat.rewind")}>
+              <Icon name="edit" />
+            </button>
+          </div>
+        )}
+        <UserText text={texts.map((p) => p.text).join("\n\n")} />
+        {imgs.length > 0 && (
+          <div className="user-files">
+            {imgs.map((p, i) => (
+              <FileFigure key={i} name={`image-${i + 1}.${fileType(undefined, p.image.media_type).toLowerCase()}`} mime={p.image.media_type} size={imageSize(p.image)}>
+                <img src={imageSrc(p.image)} alt="" loading="lazy" decoding="async" />
+              </FileFigure>
+            ))}
+          </div>
+        )}
+      </div>
+    </div>
+  );
+});
+
+/**
+ * Older messages: loaded automatically when scrolled to the top; the history before a
+ * summary only on request. Keeps the scroll position while the list grows upwards.
+ */
+function OlderLoader({ sessionId, afterSummary, scrollRef }: { sessionId: string; afterSummary?: boolean; scrollRef: RefObject<HTMLDivElement | null> }) {
+  const t = useT();
+  const [loading, setLoading] = useState(false);
+  const sentinel = useRef<HTMLDivElement>(null);
+  const load = useCallback(async () => {
+    const el = scrollRef.current;
+    if (loading || !el) return;
+    setLoading(true);
+    const before = { height: el.scrollHeight, top: el.scrollTop };
+    try {
+      // Scrolling stops at a summary; its button loads the history before it.
+      await loadOlder(sessionId, !afterSummary);
+      requestAnimationFrame(() => {
+        el.scrollTop = before.top + (el.scrollHeight - before.height);
+      });
+    } finally {
+      setLoading(false);
+    }
+  }, [loading, sessionId, scrollRef, afterSummary]);
+  useEffect(() => {
+    const node = sentinel.current;
+    if (!node || afterSummary || typeof IntersectionObserver === "undefined") return;
+    const io = new IntersectionObserver((e) => e[0]?.isIntersecting && void load(), { root: scrollRef.current, rootMargin: "300px 0px 0px 0px" });
+    io.observe(node);
+    return () => io.disconnect();
+  }, [afterSummary, load, scrollRef]);
+  return (
+    <div ref={sentinel} className="older-loader">
+      {loading ? (
+        <Spinner small />
+      ) : (
+        <button className="small ghost" onClick={() => void load()}>
+          <Icon name="arrow-up" /> {t(afterSummary ? "chat.showBeforeSummary" : "chat.loadOlder")}
+        </button>
+      )}
+    </div>
+  );
+}
+
 export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string; onMenu: () => void; onClosePane?: () => void }) {
   const t = useT();
   const session = useStore((s) => s.sessionById[sessionId]);
   const messages = useStore((s) => s.messages[sessionId] ?? EMPTY);
+  const win = useStore((s) => s.windows[sessionId]);
+  // Message to show (search hit, media): scrolled into view and marked.
+  const [highlight, setHighlight] = useState<string>();
+  const [searching, setSearching] = useState(false);
+  const [gallery, setGallery] = useState(false);
   const draft = useStore((s) => s.drafts[sessionId]);
   const busy = useStore((s) => !!s.busy[sessionId]);
   const errors = useStore((s) => s.errors[sessionId]);
@@ -197,11 +517,47 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
     return m;
   }, [messages]);
 
-  // Keep scrolled to the bottom while the user hasn't scrolled up.
+  // Keep scrolled to the bottom while the user hasn't scrolled up (only when the
+  // content changes – reading the height forces a layout).
+  const permCount = permissions.length + questions.length;
   useLayoutEffect(() => {
     const el = scrollRef.current;
     if (el && stick.current) el.scrollTop = el.scrollHeight;
+  }, [messages, draft, busy, waiting, compacting, permCount, errors]);
+
+  // Stable callbacks for the (memoised) message list.
+  const rewindRef = useRef<(m: Message) => void>(() => undefined);
+  const onRewind = useCallback((m: Message) => rewindRef.current(m), []);
+  const showLatest = useCallback(async () => {
+    setHighlight(undefined);
+    await loadSession(sessionId);
+    follow(true);
+  }, [sessionId]);
+  /** Load the part of the chat around a message and scroll to it. */
+  const jumpTo = useCallback(
+    async (messageId: string) => {
+      follow(false);
+      if (!getState().messages[sessionId]?.some((m) => m.id === messageId)) await loadAround(sessionId, messageId);
+      setHighlight(messageId);
+    },
+    [sessionId],
+  );
+  useEffect(() => {
+    if (!highlight) return;
+    const h = setTimeout(() => document.querySelector(`[data-mid="${highlight}"]`)?.scrollIntoView({ block: "center" }), 50);
+    return () => clearTimeout(h);
+  }, [highlight, messages]);
+  // … also when the pane gets smaller (on-screen keyboard opens) without a render.
+  const hasSession = !!session;
+  useEffect(() => {
+    const el = scrollRef.current;
+    if (!el || typeof ResizeObserver === "undefined") return;
+    const ro = new ResizeObserver(() => {
+      if (stick.current) el.scrollTop = el.scrollHeight;
     });
+    ro.observe(el);
+    return () => ro.disconnect();
+  }, [hasSession, sessionId]);
 
   if (loadError) return <div className="empty">{loadError}</div>;
   if (!session) return <div className="empty">{t("common.loading")}</div>;
@@ -240,9 +596,10 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
     }
   };
 
-  const lastAssistantIdx = messages.reduce((acc, m, i) => (m.role === "assistant" ? i : acc), -1);
+
   const [rewinding, setRewinding] = useState<Message>();
   const rewind = (m: Message) => setRewinding(m);
+  rewindRef.current = rewind;
   const rewindDone = async () => {
     const m = rewinding!;
     setRewinding(undefined);
@@ -331,6 +688,9 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
             >
               <Icon name="terminal" />
             </button>
+            <button className={`small ghost ${searching ? "active" : ""}`} onClick={() => setSearching(!searching)} title={t("chat.search")} aria-label={t("chat.search")}>
+              <Icon name="search" />
+            </button>
             <button className="small ghost" onClick={tabs.openFiles} title={t("files.newTab")}>
               <Icon name="folder" />
             </button>
@@ -354,6 +714,16 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
                 >
                   <Icon name="edit" /> {t("instructions.title")}
                 </a>
+                <a
+                  href="#"
+                  onClick={(e) => {
+                    e.preventDefault();
+                    (e.currentTarget.closest("details") as HTMLDetailsElement).open = false;
+                    setGallery(true);
+                  }}
+                >
+                  <Icon name="image" /> {t("media.title")}
+                </a>
                 {telegramPaired && !session.parent_id && (
                   <a
                     href="#"
@@ -407,6 +777,17 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
           </button>
         )}
       </div>
+      {gallery && (
+        <MediaGallery
+          sessionId={sessionId}
+          onClose={() => setGallery(false)}
+          onJump={(id) => {
+            setGallery(false);
+            void jumpTo(id);
+          }}
+        />
+      )}
+      {searching && <ChatSearch sessionId={sessionId} onPick={(id) => void jumpTo(id)} onClose={() => setSearching(false)} />}
       <ChatTabBar state={tabs} />
       <ChatTabPanes state={tabs} />
       <div className="chat-pane" hidden={tabs.tab !== "chat"}>
@@ -432,71 +813,24 @@ export function ChatView({ sessionId, onMenu, onClosePane }: { sessionId: string
         <div className="chat">
           {showStats && <UsageOverlay session={session} onClose={() => setShowStats(false)} />}
           {messages.length === 0 && !draft && <div className="empty">{t("chat.empty")}</div>}
-          {messages.map((m, idx) => {
-            if (m.role === "assistant") {
-              const lastAnswer = idx === lastAssistantIdx && !busy && !readOnly && !session.parent_id;
-              return (
-                <div key={m.id} className="msg">
-                  <AssistantParts parts={m.parts} results={results} running={busy} live={false} baseDir={session.cwd} />
-                  {lastAnswer && <RegenerateButton sessionId={sessionId} messageId={m.id} model={session.model} />}
-                </div>
-              );
-            }
-            const summary = m.parts.find((p) => p.type === "summary");
-            if (summary && summary.type === "summary") {
-              return (
-                <details key={m.id} className="summary-divider">
-                  <summary>
-                    {summary.auto
-                      ? t("chat.compactedAuto", { tokens: summary.tokens ? fmtCompact(summary.tokens) : "?" })
-                      : summary.tokens
-                        ? t("chat.compactedManual", { tokens: fmtCompact(summary.tokens) })
-                        : t("chat.compacted")}
-                  </summary>
-                  <Markdown text={summary.text} />
-                </details>
-              );
-            }
-            const allTexts = m.parts.filter((p) => p.type === "text") as { text: string }[];
-            const background = allTexts.filter((p) => BG_RE.test(p.text) || REFINE_RE.test(p.text));
-            const texts = allTexts.filter((p) => !BG_RE.test(p.text) && !REFINE_RE.test(p.text));
-            const imgs = m.parts.filter((p) => p.type === "image") as { image: ImageData }[];
-            if (texts.length === 0 && imgs.length === 0) {
-              return background.length ? (
-                <div key={m.id} className="msg">
-                  {background.map((p, i) => (
-                    REFINE_RE.test(p.text) ? <RefineFeedback key={i} text={p.text} /> : <BackgroundResult key={i} text={p.text} />
-                  ))}
-                </div>
-              ) : null;
-            }
-            return (
-              <div key={m.id} className="msg">
-                {background.map((p, i) => (
-                  REFINE_RE.test(p.text) ? <RefineFeedback key={i} text={p.text} /> : <BackgroundResult key={i} text={p.text} />
-                ))}
-                <div className="msg-user">
-                  {!busy && !readOnly && (
-                    <div className="msg-actions">
-                      <button className="small ghost" onClick={() => rewind(m)} title={t("chat.rewind")}>
-                        <Icon name="edit" />
+          {win?.older && <OlderLoader sessionId={sessionId} afterSummary={messages[0]?.parts.some((p) => p.type === "summary")} scrollRef={scrollRef} />}
+          <MessageList
+            messages={messages}
+            results={results}
+            busy={busy}
+            canEdit={!busy && !readOnly}
+            canRegenerate={!busy && !readOnly && !session.parent_id && !win?.newer}
+            sessionId={sessionId}
+            model={session.model}
+            baseDir={session.cwd}
+            onRewind={onRewind}
+            highlight={highlight}
+          />
+          {win?.newer && (
+            <button className="back-to-latest" onClick={() => void showLatest()}>
+              <Icon name="arrow-down" /> {t("chat.backToLatest")}
             </button>
-                    </div>
           )}
-                  <UserText text={texts.map((p) => p.text).join("\n\n")} />
-                  {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={imageSize(p.image)}>
-                          <img src={imageSrc(p.image)} alt="" loading="lazy" decoding="async" />
-                        </FileFigure>
-                      ))}
-                    </div>
-                  )}
-                </div>
-              </div>
-            );
-          })}
           {draft && (
             <div className="msg">
               <AssistantParts parts={draft.parts} results={results} running={busy} live baseDir={session.cwd} />
@@ -597,9 +931,10 @@ function UserText({ text }: { text: string }) {
     const last = rest.pop()!;
     if (last.trim().endsWith(":")) break;
   }
+  const body = rest.join("\n").trim();
   return (
     <>
-      {rest.join("\n").trimEnd()}
+      {body && <Markdown text={body} breaks />}
       {files.length > 0 && (
         <div className="user-files">
           {files.map((f) => (

web/src/components/Composer.tsx

@@ -9,6 +9,7 @@ import type { ImageData, Session } from "../types";
 import { ModelSelect } from "./ModelSelect";
 import { EffortSelect } from "./Regenerate";
 import { VoiceButton } from "./Voice";
+import { Markdown } from "./Markdown";
 import { confirmDialog, promptDialog, toast } from "../dialogs";
 
 interface Suggestion {
@@ -67,6 +68,8 @@ export function Composer({
   const [effort, setEffort] = useState("");
   const [interim, setInterim] = useState("");
   const [picker, setPicker] = useState(false);
+  // Rendered Markdown instead of the text field (to check formatting before sending).
+  const [preview, setPreview] = useState(false);
   const models = useModels();
   const [prov, ...mid] = session.model.split("/");
   const reasoning = !!models.find((p) => p.provider === prov)?.models.find((m) => m.id === mid.join("/"))?.reasoning;
@@ -265,7 +268,20 @@ export function Composer({
             ))}
           </div>
         )}
+        {preview && (
+          <div
+            className="composer-preview"
+            role="button"
+            tabIndex={0}
+            title={t("composer.previewEdit")}
+            onClick={() => (setPreview(false), setTimeout(() => ref.current?.focus(), 0))}
+            onKeyDown={(e) => e.key === "Enter" && (setPreview(false), setTimeout(() => ref.current?.focus(), 0))}
+          >
+            {text.trim() ? <Markdown text={text} breaks /> : <span className="hint">{t("composer.previewEmpty")}</span>}
+          </div>
+        )}
         <textarea
+          style={preview ? { display: "none" } : undefined}
           ref={ref}
           rows={1}
           value={text}
@@ -337,6 +353,15 @@ export function Composer({
               }}
             />
           )}
+          <button
+            className={`ghost ${preview ? "active" : ""}`}
+            style={{ padding: "3px 6px" }}
+            onClick={() => setPreview(!preview)}
+            aria-pressed={preview}
+            title={t(preview ? "composer.previewEdit" : "composer.preview")}
+          >
+            <Icon name={preview ? "edit" : "eye"} />
+          </button>
           <VoiceButton onText={(d) => setText(text ? `${text.replace(/\s+$/, "")} ${d}` : d)} onInterim={setInterim} />
           <label className="ghost" style={{ cursor: "pointer", padding: "3px 6px" }} title={t("composer.attach")}>
             <Icon name="clip" />

web/src/components/Icon.tsx

@@ -125,6 +125,12 @@ const P: Record<string, ReactNode> = {
       <path d="M15 4a3 3 0 0 1 3 3 3 3 0 0 1 2 5 3 3 0 0 1-2 5 3 3 0 0 1-6 1" />
     </>
   ),
+  search: (
+    <>
+      <circle cx="11" cy="11" r="6.5" />
+      <path d="m16 16 4.5 4.5" />
+    </>
+  ),
   eye: (
     <>
       <path d="M2 12s3.5-7 10-7 10 7 10 7-3.5 7-10 7S2 12 2 12Z" />

web/src/components/Markdown.tsx

@@ -44,7 +44,30 @@ export function SvgBlock({ code, children }: { code: string; children?: ReactNod
   );
 }
 
-export const Markdown = memo(function Markdown({ text, baseDir }: { text: string; baseDir?: string }) {
+/**
+ * Keep single line breaks as typed (Markdown would join the lines into one paragraph):
+ * a hard break at the end of every line that continues a paragraph. Code blocks stay as
+ * they are.
+ */
+export function keepLineBreaks(text: string) {
+  let fence: string | null = null;
+  const lines = text.split("\n");
+  return lines
+    .map((line, i) => {
+      const f = line.match(/^\s*(`{3,}|~{3,})/);
+      if (f) {
+        if (!fence) fence = f[1][0];
+        else if (f[1][0] === fence) fence = null;
+        return line;
+      }
+      const next = lines[i + 1];
+      if (fence || next === undefined || !line.trim() || !next.trim() || / {2}$|\\$/.test(line)) return line;
+      return `${line}  `;
+    })
+    .join("\n");
+}
+
+export const Markdown = memo(function Markdown({ text, baseDir, breaks }: { text: string; baseDir?: string; breaks?: boolean }) {
   return (
     <div className="markdown">
       <ReactMarkdown
@@ -81,7 +104,7 @@ export const Markdown = memo(function Markdown({ text, baseDir }: { text: string
           },
         }}
       >
-        {text}
+        {breaks ? keepLineBreaks(text) : text}
       </ReactMarkdown>
     </div>
   );

web/src/components/MediaGallery.tsx

@@ -0,0 +1,125 @@
+import { useEffect, useState } from "react";
+import { get } from "../api";
+import { useT, type Key } from "../i18n";
+import { Spinner } from "./Activity";
+import { Icon } from "./Icon";
+
+interface MediaItem {
+  kind: "image" | "video" | "audio";
+  url: string;
+  name: string;
+  source: "generated" | "tool" | "written" | "answer" | "upload";
+  created_at: number;
+  message_id?: string;
+}
+
+type Filter = "all" | MediaItem["kind"];
+
+/**
+ * All images, videos and audio files of a chat (with its subagents), newest first.
+ * An item opens large; "show in chat" jumps to the message it came with.
+ */
+export function MediaGallery({ sessionId, onClose, onJump }: { sessionId: string; onClose: () => void; onJump: (messageId: string) => void }) {
+  const t = useT();
+  const [items, setItems] = useState<MediaItem[]>();
+  const [error, setError] = useState<string>();
+  const [filter, setFilter] = useState<Filter>("all");
+  const [open, setOpen] = useState<number>();
+
+  useEffect(() => {
+    get<MediaItem[]>(`/sessions/${sessionId}/media`)
+      .then(setItems)
+      .catch((e) => setError(e.message));
+  }, [sessionId]);
+
+  const shown = (items ?? []).filter((i) => filter === "all" || i.kind === filter);
+  const count = (k: Filter) => (items ?? []).filter((i) => k === "all" || i.kind === k).length;
+  const current = open !== undefined ? shown[open] : undefined;
+
+  // Keyboard: Esc closes, arrows step through the open item.
+  useEffect(() => {
+    const onKey = (e: KeyboardEvent) => {
+      if (e.key === "Escape") return current ? setOpen(undefined) : onClose();
+      if (current && e.key === "ArrowRight") setOpen((o) => Math.min((o ?? 0) + 1, shown.length - 1));
+      if (current && e.key === "ArrowLeft") setOpen((o) => Math.max((o ?? 0) - 1, 0));
+    };
+    window.addEventListener("keydown", onKey);
+    return () => window.removeEventListener("keydown", onKey);
+  }, [current, shown.length, onClose]);
+
+  return (
+    <div className="modal-backdrop" onClick={onClose}>
+      <div className="modal media-gallery" role="dialog" aria-label={t("media.title")} onClick={(e) => e.stopPropagation()}>
+        <div className="media-head">
+          <h3>
+            <Icon name="image" /> {t("media.title")}
+          </h3>
+          <div className="media-filters" role="radiogroup">
+            {(["all", "image", "video", "audio"] as Filter[]).map((k) => (
+              <button key={k} role="radio" aria-checked={filter === k} className={`chip-btn ${filter === k ? "active" : ""}`} onClick={() => (setFilter(k), setOpen(undefined))} disabled={!!items && count(k) === 0 && k !== "all"}>
+                {t(`media.filter.${k}` as Key)} {items && <small>{count(k)}</small>}
+              </button>
+            ))}
+          </div>
+          <button className="small ghost" onClick={onClose} aria-label={t("common.close")}>
+            <Icon name="close" />
+          </button>
+        </div>
+        {error && <div className="notice err">{error}</div>}
+        {!items && !error && (
+          <div className="empty">
+            <Spinner />
+          </div>
+        )}
+        {items && shown.length === 0 && <div className="empty">{t("media.none")}</div>}
+        {current ? (
+          <div className="media-viewer">
+            <div className="media-stage">
+              {current.kind === "image" && <img src={current.url} alt={current.name} />}
+              {current.kind === "video" && <video src={current.url} controls autoPlay />}
+              {current.kind === "audio" && <audio src={current.url} controls autoPlay />}
+            </div>
+            <div className="media-bar">
+              <button className="small ghost" disabled={open === 0} onClick={() => setOpen((o) => (o ?? 1) - 1)} aria-label={t("media.prev")}>
+                <Icon name="arrow-left" />
+              </button>
+              <span className="grow">
+                {current.name} · {t(`media.source.${current.source}` as Key)} · {new Date(current.created_at).toLocaleString(undefined, { dateStyle: "short", timeStyle: "short" })}
+              </span>
+              {current.message_id && (
+                <button className="small" onClick={() => onJump(current.message_id!)}>
+                  {t("media.showInChat")}
+                </button>
+              )}
+              <a className="small button" href={current.url} target="_blank" rel="noreferrer">
+                <Icon name="external" /> {t("media.open")}
+              </a>
+              <button className="small ghost" disabled={open === shown.length - 1} onClick={() => setOpen((o) => (o ?? 0) + 1)} aria-label={t("media.next")}>
+                <Icon name="arrow-right" />
+              </button>
+              <button className="small ghost" onClick={() => setOpen(undefined)} aria-label={t("media.back")}>
+                <Icon name="close" />
+              </button>
+            </div>
+          </div>
+        ) : (
+          <div className="media-grid">
+            {shown.map((m, i) => (
+              <button key={m.url} className={`media-tile ${m.kind}`} onClick={() => setOpen(i)} title={`${m.name} · ${t(`media.source.${m.source}` as Key)}`}>
+                {m.kind === "image" && <img src={m.url} alt="" loading="lazy" decoding="async" />}
+                {m.kind === "video" && <video src={`${m.url}#t=0.1`} preload="metadata" muted />}
+                {m.kind === "audio" && (
+                  <span className="media-audio">
+                    <Icon name="music" />
+                    <span>{m.name}</span>
+                  </span>
+                )}
+                {m.kind === "video" && <Icon name="play" className="media-play" />}
+              </button>
+            ))}
+          </div>
+        )}
+      </div>
+    </div>
+  );
+}

web/src/components/NewSession.tsx

@@ -1,6 +1,7 @@
 import { Icon } from "./Icon";
 import { useEffect, useMemo, useRef, useState, type ReactNode } from "react";
 import { post, uploadFile } from "../api";
+import { promptDialog, toast } from "../dialogs";
 import { useAgents, useFetch } from "../hooks";
 import { useT, type Key } from "../i18n";
 import type { ImageData } from "../types";
@@ -602,6 +603,20 @@ export function FolderPicker({ path, onPick }: { path: string; onPick: (p: strin
     // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [listing?.path]);
   const rel = listing ? listing.path.slice(listing.workspace.length) || "/" : "";
+  /** Create a subfolder of the shown folder and select it. */
+  const newFolder = async () => {
+    if (!listing) return;
+    const name = (await promptDialog({ title: t("files.newFolder"), message: t("files.newFolderName") }))?.trim();
+    if (!name) return;
+    if (name.includes("/") || name === "." || name === "..") return toast(t("new.invalidFolderName"));
+    const target = `${listing.path.replace(/\/$/, "")}/${name}`;
+    try {
+      await post("/files/create", { path: target, dir: true });
+      setBrowse(target);
+    } catch (e: any) {
+      toast(e.message);
+    }
+  };
   return (
     <div className="wiz-picker">
       {roots.length > 1 && (
@@ -622,6 +637,11 @@ export function FolderPicker({ path, onPick }: { path: string; onPick: (p: strin
             <Icon name="arrow-up" /> {t("new.up")}
           </button>
         )}
+        {listing && (
+          <button className="small" onClick={() => void newFolder()}>
+            <Icon name="plus" /> {t("files.newFolder")}
+          </button>
+        )}
       </div>
       <div className="dir-list">
         {listing?.dirs.length === 0 && <div className="empty" style={{ padding: 16 }}>{t("new.noSubdirs")}</div>}

web/src/components/Settings.tsx

@@ -248,6 +248,7 @@ function General({ cfg, reload }: { cfg: ConfigResponse; reload: () => void }) {
     small_model: s.small_model ?? "",
     currency: s.currency ?? "USD",
     auto_compact_threshold: s.auto_compact_threshold ?? 0.85,
+    commit_trailer: ((s as any).commit_trailer ?? "Co-Authored-By: {model} ({provider}) via CodeCraft") as string,
     max_parallel_subagents: s.max_parallel_subagents ?? 4,
     monthly_budget: s.monthly_budget ?? 0,
     budget_warning: s.budget_warning ?? 0.8,
@@ -271,6 +272,7 @@ function General({ cfg, reload }: { cfg: ConfigResponse; reload: () => void }) {
         { path: ["server", "small_model"], value: form.small_model },
         { path: ["server", "currency"], value: form.currency },
         { path: ["server", "auto_compact_threshold"], value: Number(form.auto_compact_threshold) },
+        { path: ["server", "commit_trailer"], value: form.commit_trailer.trim() },
         { path: ["server", "max_parallel_subagents"], value: Number(form.max_parallel_subagents) },
         { path: ["server", "monthly_budget"], value: Number(form.monthly_budget) || 0 },
         { path: ["server", "budget_warning"], value: Number(form.budget_warning) || 0.8 },
@@ -305,6 +307,9 @@ function General({ cfg, reload }: { cfg: ConfigResponse; reload: () => void }) {
           <label>{t("settings.autoCompact")}</label>
           <input type="number" min={0} max={1} step={0.05} value={form.auto_compact_threshold} onChange={(e) => setForm({ ...form, auto_compact_threshold: e.target.value })} />
           <div className="hint">{t("settings.autoCompactHint")}</div>
+          <label>{t("settings.commitTrailer")}</label>
+          <input className="mono" value={form.commit_trailer} placeholder={t("settings.commitTrailerOff")} onChange={(e) => setForm({ ...form, commit_trailer: e.target.value })} />
+          <div className="hint">{t("settings.commitTrailerHint")}</div>
           <label>{t("settings.monthlyBudgetTotal")}</label>
           <input type="number" min={0} value={form.monthly_budget} onChange={(e) => setForm({ ...form, monthly_budget: e.target.value })} />
           <div className="hint">{t("settings.monthlyBudgetHint")}</div>
@@ -376,6 +381,7 @@ interface ModelRow {
   name?: string;
   context?: number;
   max_output?: number;
+  max_input?: number;
   reasoning?: boolean;
   vision?: boolean;
   effort?: string;
@@ -454,6 +460,7 @@ function ProviderEditor({ name, p, reload, status }: { name: string; p: Json; re
             price_multipliers: f.price_multipliers ?? m.price_multipliers,
             context: m.context ?? f.context,
             max_output: m.max_output ?? f.max_output,
+            max_input: m.max_input ?? f.max_input ?? undefined,
             vision: m.vision || !!f.vision,
             reasoning: m.reasoning || !!f.reasoning,
           };
@@ -616,6 +623,7 @@ function ProviderEditor({ name, p, reload, status }: { name: string; p: Json; re
                   <th>ID</th>
                   <th>{t("settings.context")}</th>
                   <th>{t("settings.maxOutput")}</th>
+                  <th title={t("settings.maxInputHint")}>{t("settings.maxInput")}</th>
                   <th title={t("settings.reasoning")}><Icon name="brain" /></th>
                   <th title={t("settings.vision")}><Icon name="eye" /></th>
                   <th>{t("settings.effort")}</th>
@@ -640,6 +648,9 @@ function ProviderEditor({ name, p, reload, status }: { name: string; p: Json; re
                     <td>
                       <input type="number" value={m.max_output ?? ""} onChange={(e) => setModel(i, { max_output: num(e.target.value) })} />
                     </td>
+                    <td>
+                      <input type="number" value={m.max_input ?? ""} placeholder="–" onChange={(e) => setModel(i, { max_input: num(e.target.value) })} />
+                    </td>
                     <td>
                       <input type="checkbox" checked={!!m.reasoning} onChange={(e) => setModel(i, { reasoning: e.target.checked })} />
                     </td>

web/src/components/ToolCard.tsx

@@ -1,5 +1,6 @@
 import { Icon } from "./Icon";
 import { FileFigure, imageSize, imageSrc } from "./FileFigure";
+import { useState } from "react";
 import { useT } from "../i18n";
 import { navigate } from "../router";
 import { useStore } from "../store";
@@ -68,6 +69,8 @@ export function TodoList({ todos }: { todos: Todo[] }) {
 
 export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; result?: ToolResult; running: boolean; baseDir?: string }) {
   const t = useT();
+  // The body (diff, output) is only built while the card is open – long chats have thousands.
+  const [toggled, setToggled] = useState<boolean | null>(null);
   const progress = useStore((s) => s.progress[call.id]);
   const status = result ? (result.is_error ? "err" : "ok") : running ? "run" : "err";
   const statusText = result ? <Icon name={result.is_error ? "x-mark" : "check"} /> : running ? "…" : "–";
@@ -119,9 +122,13 @@ export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; r
   const openByDefault =
     (status === "err" && !!result) ||
     (!!result && !result.is_error && ((diffLines > 0 && diffLines <= 40) || call.name === "generate_image"));
+  const open = toggled ?? openByDefault;
 
   return (
-    <details className={`tool ${status === "run" ? "running" : ""}`} open={openByDefault}>
+    <details className={`tool ${status === "run" ? "running" : ""}`} open={open} onToggle={(e) => {
+      const now = (e.currentTarget as HTMLDetailsElement).open;
+      if (now !== open) setToggled(now);
+    }}>
       <summary>
         <span className="tool-name">{call.name}</span>
         <span className="tool-title">{toolTitle(call.name, call.input)}</span>
@@ -130,6 +137,7 @@ export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; r
         {call.name === "task" && call.input?.background && <span className="chip">{t("tool.background")}</span>}
         {status === "run" ? <Spinner small /> : <span className={`status ${status}`}>{statusText}</span>}
       </summary>
+      {open && (
       <div className="tool-body">
         {call.name === "bash" && <pre className="mono">$ {call.input?.command}</pre>}
         {(call.name === "edit" || call.name === "write") && meta?.diff && <Diff diff={meta.diff} />}
@@ -158,11 +166,25 @@ export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; r
         )}
         {Array.isArray(meta?.image_ids) ? (
           <div className="gallery small">
-            {meta.image_ids.map((id: string) => (
+            {meta.image_ids.map((id: string, i: number) => {
+              // The file may be gone (moved or deleted later): fall back to the preview the model saw.
+              const preview = result?.images?.[i];
+              return (
                 <FileFigure key={id} url={`/api/images/${id}/file`} className="gallery-item">
-                <img src={`/api/images/${id}/file`} alt="" />
+                  <img
+                    src={`/api/images/${id}/file`}
+                    alt=""
+                    onError={(e) => {
+                      const img = e.currentTarget;
+                      if (preview && !img.dataset.fallback) {
+                        img.dataset.fallback = "1";
+                        img.src = imageSrc(preview);
+                      }
+                    }}
+                  />
                 </FileFigure>
-            ))}
+              );
+            })}
           </div>
         ) : (
           result?.images?.map((img, i) => (
@@ -172,6 +194,7 @@ export function ToolCard({ call, result, running, baseDir }: { call: ToolCall; r
           ))
         )}
       </div>
+      )}
     </details>
   );
 }

web/src/components/settings/AgentsEditor.tsx

@@ -61,6 +61,8 @@ function AgentRow({ a, raw, tools, onSaved }: { a: AgentInfo; raw: any; tools: T
     refine_rounds: String(raw?.refine?.rounds ?? a.refine?.rounds ?? 0),
     refine_model: raw?.refine?.model ?? "",
     refine_criteria: raw?.refine?.criteria ?? "",
+    refine_after_todos: (raw?.refine?.after_todos ?? a.refine?.after_todos ?? true) as boolean,
+    reverse_tools: !!(raw?.reverse_tools ?? a.reverse),
   });
   const builtin = a.source === "builtin" || (a.source === "config" && !raw?.prompt && ["build", "plan", "craft", "chat", "general", "explore"].includes(a.name));
 
@@ -74,9 +76,10 @@ function AgentRow({ a, raw, tools, onSaved }: { a: AgentInfo; raw: any; tools: T
       const rounds = Math.max(0, Math.min(10, Number(form.refine_rounds) || 0));
       patches.push({
         path: [...base, "refine"],
-        value: rounds || form.refine_model || form.refine_criteria ? { rounds, model: form.refine_model || null, criteria: form.refine_criteria || null } : null,
+        value: rounds || form.refine_model || form.refine_criteria ? { rounds, model: form.refine_model || null, criteria: form.refine_criteria || null, after_todos: form.refine_after_todos } : null,
       });
     }
+    if (a.name !== "craft") patches.push({ path: [...base, "reverse_tools"], value: form.reverse_tools || null });
     if (!builtin || form.description) patches.push({ path: [...base, "description"], value: form.description || null });
     if (!builtin) {
       patches.push({ path: [...base, "mode"], value: form.mode });
@@ -158,6 +161,20 @@ function AgentRow({ a, raw, tools, onSaved }: { a: AgentInfo; raw: any; tools: T
                 <label>{t("agents.refineCriteria")}</label>
                 <textarea rows={3} value={form.refine_criteria} onChange={(e) => setForm({ ...form, refine_criteria: e.target.value })} />
                 <div className="hint">{t("agents.refineCriteriaHint")}</div>
+                <label className="check">
+                  <input type="checkbox" checked={form.refine_after_todos} onChange={(e) => setForm({ ...form, refine_after_todos: e.target.checked })} />
+                  {t("agents.refineAfterTodos")}
+                </label>
+                <div className="hint">{t("agents.refineAfterTodosHint")}</div>
+              </>
+            )}
+            {a.name !== "craft" && (
+              <>
+                <label className="check">
+                  <input type="checkbox" checked={form.reverse_tools} onChange={(e) => setForm({ ...form, reverse_tools: e.target.checked })} />
+                  {t("agents.reverseTools")}
+                </label>
+                <div className="hint">{t("agents.reverseToolsHint")}</div>
               </>
             )}
             <label>{t("agents.description")}</label>

web/src/i18n/de.ts

@@ -189,7 +189,7 @@ export const de: Messages = {
   "tools.install": "Ghidra installieren",
   "tools.reinstall": "Installation prüfen / reparieren",
   "tools.installing": "Installiere (Download ca. 800 MB, auf ARM wird der Dekompiler kompiliert – das dauert einige Minuten)…",
-  "tools.ghidraHint": "Mit Ghidra können Agenten im Craft-Deep-Modus Programme dekompilieren (Windows .exe/.dll, Linux, DOS …), um zu verstehen, wie sie funktionieren. Wird samt eigenem JDK ins Daten-Volume installiert.",
+  "tools.ghidraHint": "Mit Ghidra können Agenten Programme und Firmware dekompilieren (Windows .exe/.dll, Linux, DOS …), um zu verstehen, wie sie funktionieren – im Craft-Deep-Modus und in Modi mit Reverse-Engineering-Werkzeugen (Einstellungen → Agenten & Befehle). Wird samt eigenem JDK ins Daten-Volume installiert.",
   "rewind.intro": "Die Unterhaltung wird auf den Stand vor dieser Nachricht zurückgesetzt; du kannst sie bearbeiten und neu senden.",
   "rewind.noFiles": "Der Agent hat seitdem keine Dateien geändert.",
   "rewind.restore": "Auch die {n} vom Agenten geänderte(n) Datei(en) zurücksetzen",
@@ -334,6 +334,39 @@ export const de: Messages = {
   "wizard.idea.cadBox": "Eine Box mit Schnappdeckel, Innenmaß 80 × 50 × 30 mm",
   "wizard.idea.cadBracket": "Eine Wandhalterung für ein 25-mm-Rohr mit zwei M4-Schraublöchern",
   "activity.reviewing": "Ergebnis wird geprüft (Runde {round})…",
+  "chat.reviewPassed": "Review bestanden:",
+  "chat.todoReminder": "Weiterarbeiten – {n} offene Todos:",
+  "agents.reverseTools": "Reverse-Engineering-Werkzeuge (binary_info, decompile mit Ghidra)",
+  "agents.reverseToolsHint": "Der Agent kann in diesem Modus Programme und Firmware untersuchen und dekompilieren (Ghidra muss unter Einstellungen → Werkzeuge installiert sein). Craft hat sie im Deep-Modus ohnehin.",
+  "agents.refineAfterTodos": "Jedes erledigte Todo prüfen und bis zum Ende der Liste arbeiten",
+  "agents.refineAfterTodosHint": "Jedes Todo, das der Agent als erledigt markiert, wird geprüft; bei Befunden wird es wieder geöffnet. Beendet er den Turn mit offenen Todos, arbeitet er weiter (für unbeaufsichtigte Läufe, z. B. über Nacht). Aus: nur ein Review am Ende des Turns.",
+  "chat.workSteps": "{n} Schritte",
+  "chat.workFiles": "{n} Dateien",
+  "chat.loadOlder": "Ältere Nachrichten laden",
+  "chat.showBeforeSummary": "Verlauf vor der Zusammenfassung anzeigen",
+  "chat.backToLatest": "Zu den neuesten Nachrichten",
+  "chat.search": "Im Chat suchen",
+  "chat.searchPlaceholder": "Nachrichten, Tool-Ausgaben … durchsuchen",
+  "chat.searchNone": "Keine Treffer",
+  "chat.searchHits": "{n} Treffer",
+  "chat.you": "Du",
+  "chat.agent": "Agent",
+  "media.title": "Medien",
+  "media.none": "Noch keine Bilder, Videos oder Audiodateien in diesem Chat.",
+  "media.filter.all": "Alle",
+  "media.filter.image": "Bilder",
+  "media.filter.video": "Videos",
+  "media.filter.audio": "Audio",
+  "media.source.generated": "generiert",
+  "media.source.tool": "Tool-Ausgabe",
+  "media.source.written": "vom Agenten geschrieben",
+  "media.source.answer": "in einer Antwort",
+  "media.source.upload": "dein Anhang",
+  "media.showInChat": "Im Chat zeigen",
+  "media.open": "Öffnen",
+  "media.prev": "Vorheriges",
+  "media.next": "Nächstes",
+  "media.back": "Zurück zur Übersicht",
   "chat.reviewRound": "Review {round}: Änderungen nötig",
   "agents.refine": "Review-Schleife",
   "agents.refineRounds": "Review-Runden pro Aufgabe",
@@ -554,6 +587,7 @@ export const de: Messages = {
   "jobs.tplMode": "Modus",
   "new.title": "Neue Session",
   "new.directory": "Projektverzeichnis",
+  "new.invalidFolderName": "Ordnernamen dürfen kein „/“ enthalten.",
   "new.up": "Hoch",
   "new.noSubdirs": "Keine Unterverzeichnisse",
   "new.model": "Modell",
@@ -662,6 +696,9 @@ export const de: Messages = {
   "composer.mode": "Modus",
   "composer.model": "Modell",
   "composer.permissionMode": "Berechtigungsmodus",
+  "composer.preview": "Vorschau (Markdown)",
+  "composer.previewEdit": "Zurück zum Bearbeiten",
+  "composer.previewEmpty": "Noch nichts zum Anzeigen.",
   "composer.attach": "Dateien anhängen",
 
   "command.compact": "Unterhaltung zusammenfassen, um Kontext freizugeben",
@@ -733,6 +770,9 @@ export const de: Messages = {
   "settings.smallModelHint": "Für Session-Titel. Die Komprimierung nutzt das Session-Modell.",
   "settings.currency": "Währung",
   "settings.autoCompact": "Auto-Komprimierung bei",
+  "settings.commitTrailer": "Commit-Vermerk der Agenten",
+  "settings.commitTrailerOff": "aus",
+  "settings.commitTrailerHint": "Wird als Trailer an jeden Git-Commit eines Agenten angehängt. {model} = Modellname, {provider} = Anbieter, {model_id} = Modell-ID. Leer = aus. Deine eigenen Commits bleiben unverändert.",
   "settings.autoCompactHint": "Anteil des Kontextfensters (0 = aus).",
   "settings.craft": "Craft-Modus",
   "settings.cleanRoom": "Clean Room",
@@ -753,6 +793,8 @@ export const de: Messages = {
   "settings.pricesHint": "Preise pro 1 Mio. Tokens in der eingestellten Währung. Cache-Preise fallen auf den Input-Preis zurück.",
   "settings.modelsEmptyHint": "Keine Modelle eingetragen: Sie werden automatisch beim Provider abgefragt.",
   "settings.context": "Kontext",
+  "settings.maxInput": "Max. Eingabe",
+  "settings.maxInputHint": "Eingabe-Limit, falls der Anbieter eines unterhalb des Kontextfensters setzt (leer: das Kontextfenster). Der Chat wird zusammengefasst, bevor die Eingabe es erreicht.",
   "settings.maxOutput": "Max. Ausgabe",
   "settings.reasoning": "Reasoning",
   "settings.vision": "Bilder",

web/src/i18n/en.ts

@@ -188,7 +188,7 @@ export const en = {
   "tools.install": "Install Ghidra",
   "tools.reinstall": "Check / repair installation",
   "tools.installing": "Installing (download ~800 MB, on ARM the decompiler is compiled – this takes several minutes)…",
-  "tools.ghidraHint": "Ghidra lets agents in craft Deep mode decompile programs (Windows .exe/.dll, Linux, DOS, …) to study how they work. Installed into the data volume together with its own JDK.",
+  "tools.ghidraHint": "Ghidra lets agents decompile programs and firmware (Windows .exe/.dll, Linux, DOS, …) to study how they work – in craft Deep mode and in modes with reverse engineering tools (Settings → Agents & commands). Installed into the data volume together with its own JDK.",
   "rewind.intro": "The conversation is reset to before this message; you can edit and resend it.",
   "rewind.noFiles": "The agent did not change files since then.",
   "rewind.restore": "Also restore the {n} file(s) the agent changed",
@@ -333,6 +333,39 @@ export const en = {
   "wizard.idea.cadBox": "A box with a snap-on lid, inner size 80 × 50 × 30 mm",
   "wizard.idea.cadBracket": "A wall bracket for a 25 mm pipe with two M4 screw holes",
   "activity.reviewing": "Reviewing the result (round {round})…",
+  "chat.reviewPassed": "Review passed:",
+  "chat.todoReminder": "Back to work – {n} open todos:",
+  "agents.reverseTools": "Reverse engineering tools (binary_info, decompile with Ghidra)",
+  "agents.reverseToolsHint": "The agent can inspect and decompile programs and firmware in this mode (Ghidra must be installed under Settings → Tools). Craft has them anyway in deep mode.",
+  "agents.refineAfterTodos": "Review every completed todo and work until the list is done",
+  "agents.refineAfterTodosHint": "Each todo the agent marks completed is reviewed; with findings it is reopened. Ending the turn with open todos sends the agent back to work (for unattended runs, e.g. overnight). Off: only one review at the end of the turn.",
+  "chat.workSteps": "{n} steps",
+  "chat.workFiles": "{n} files",
+  "chat.loadOlder": "Load older messages",
+  "chat.showBeforeSummary": "Show the history before the summary",
+  "chat.backToLatest": "Back to the latest messages",
+  "chat.search": "Search in this chat",
+  "chat.searchPlaceholder": "Search messages, tool output …",
+  "chat.searchNone": "No matches",
+  "chat.searchHits": "{n} matches",
+  "chat.you": "You",
+  "chat.agent": "Agent",
+  "media.title": "Media",
+  "media.none": "No images, videos or audio in this chat yet.",
+  "media.filter.all": "All",
+  "media.filter.image": "Images",
+  "media.filter.video": "Videos",
+  "media.filter.audio": "Audio",
+  "media.source.generated": "generated",
+  "media.source.tool": "tool output",
+  "media.source.written": "written by the agent",
+  "media.source.answer": "in an answer",
+  "media.source.upload": "your attachment",
+  "media.showInChat": "Show in chat",
+  "media.open": "Open",
+  "media.prev": "Previous",
+  "media.next": "Next",
+  "media.back": "Back to the overview",
   "chat.reviewRound": "Review {round}: changes requested",
   "agents.refine": "Review loop",
   "agents.refineRounds": "Review rounds per task",
@@ -553,6 +586,7 @@ export const en = {
   "jobs.tplMode": "Mode",
   "new.title": "New session",
   "new.directory": "Project directory",
+  "new.invalidFolderName": "Folder names cannot contain “/”.",
   "new.up": "Up",
   "new.noSubdirs": "No subdirectories",
   "new.model": "Model",
@@ -661,6 +695,9 @@ export const en = {
   "composer.mode": "Mode",
   "composer.model": "Model",
   "composer.permissionMode": "Permission mode",
+  "composer.preview": "Preview (Markdown)",
+  "composer.previewEdit": "Back to editing",
+  "composer.previewEmpty": "Nothing to preview yet.",
   "composer.attach": "Attach files",
 
   "command.compact": "Summarize the conversation to free up context",
@@ -732,6 +769,9 @@ export const en = {
   "settings.smallModelHint": "Used for session titles. Compaction uses the session model.",
   "settings.currency": "Currency",
   "settings.autoCompact": "Auto-compact at",
+  "settings.commitTrailer": "Commit note of agents",
+  "settings.commitTrailerOff": "off",
+  "settings.commitTrailerHint": "Added as a trailer to every git commit an agent makes. {model} = model name, {provider} = provider, {model_id} = model id. Empty = off. Your own commits stay unchanged.",
   "settings.autoCompactHint": "Fraction of the context window (0 = off).",
   "settings.craft": "Craft mode",
   "settings.cleanRoom": "Clean room",
@@ -752,6 +792,8 @@ export const en = {
   "settings.pricesHint": "Prices per 1M tokens in the configured currency. Cache prices default to the input price.",
   "settings.modelsEmptyHint": "No models listed: they are discovered automatically from the provider.",
   "settings.context": "Context",
+  "settings.maxInput": "Max input",
+  "settings.maxInputHint": "Input limit, if the provider sets one below the context window (empty: the context window). The chat is compacted before the input reaches it.",
   "settings.maxOutput": "Max output",
   "settings.reasoning": "Reasoning",
   "settings.vision": "Vision",

web/src/main.tsx

@@ -10,6 +10,43 @@ import { captureShare } from "./share";
 applyTheme();
 captureShare();
 registerSW({ immediate: true });
+undoKeyboardShift();
+
+/**
+ * Browsers that do not resize the page for the on-screen keyboard (iOS Safari, older
+ * Android) scroll the whole page up to show the input – and do not always scroll it back
+ * when the keyboard closes, leaving the top bar (menu) out of reach. The app never
+ * scrolls the page itself (only its panes), so any page offset is undone once the
+ * visible area grows again.
+ */
+function undoKeyboardShift() {
+  const vv = window.visualViewport;
+  if (!vv) return;
+  let last = vv.height;
+  const reset = () => {
+    const el = document.scrollingElement ?? document.documentElement;
+    if (window.scrollY !== 0 || el.scrollTop !== 0 || document.body.scrollTop !== 0) {
+      window.scrollTo(0, 0);
+      el.scrollTop = 0;
+      document.body.scrollTop = 0;
+    }
+  };
+  vv.addEventListener("resize", () => {
+    // Grown back (keyboard closed or closing): after the browser's own adjustment.
+    if (vv.height > last + 1) {
+      requestAnimationFrame(reset);
+      setTimeout(reset, 350);
+    }
+    last = vv.height;
+  });
+  // Keyboard closed by leaving the input (no resize on some browsers).
+  document.addEventListener("focusout", () =>
+    setTimeout(() => {
+      const a = document.activeElement;
+      if (!a || !(a instanceof HTMLInputElement || a instanceof HTMLTextAreaElement || (a as HTMLElement).isContentEditable)) reset();
+    }, 300),
+  );
+}
 
 createRoot(document.getElementById("root")!).render(
   <StrictMode>

web/src/store.ts

@@ -32,6 +32,8 @@ export interface State {
   /** Includes subagent sessions loaded on demand. */
   sessionById: Record<string, Session>;
   messages: Record<string, Message[]>;
+  /** Long chats are loaded in parts: are there older / newer messages than the loaded ones? */
+  windows: Record<string, { older: boolean; newer: boolean } | undefined>;
   /** Sessions the current user may only read (shared with them). */
   readOnly: Record<string, boolean>;
   drafts: Record<string, Draft | undefined>;
@@ -58,6 +60,7 @@ let state: State = {
   sessions: [],
   sessionById: {},
   messages: {},
+  windows: {},
   readOnly: {},
   drafts: {},
   busy: {},
@@ -130,7 +133,8 @@ export function applyEvent(ev: ServerEvent) {
       setState((s) => {
         const list = s.messages[ev.session_id];
         const drafts = s.drafts[ev.session_id]?.id === ev.message.id ? { ...s.drafts, [ev.session_id]: undefined } : s.drafts;
-        if (!list) return { drafts };
+        // Viewing an older part of the chat: the new message comes with "back to the end".
+        if (!list || s.windows[ev.session_id]?.newer) return { drafts };
         if (list.some((m) => m.id === ev.message.id)) return { drafts };
         return { messages: { ...s.messages, [ev.session_id]: [...list, ev.message] }, drafts };
       });
@@ -231,9 +235,17 @@ export async function loadSessions() {
   }));
 }
 
+/** Messages loaded when a chat opens (from the last summary on, at most this many). */
+export const PAGE = 200;
+
+type Page = { messages: Message[]; has_older: boolean; has_newer: boolean };
+
 export async function loadSession(id: string) {
-  const data = await get<{ session: Session; messages: Message[]; busy: boolean; can_write: boolean; queue: QueueItem[]; step?: any }>(`/sessions/${id}`);
+  const data = await get<{ session: Session; messages: Message[]; busy: boolean; can_write: boolean; queue: QueueItem[]; step?: any; has_older?: boolean; has_newer?: boolean }>(
+    `/sessions/${id}?limit=${PAGE}`,
+  );
   setState((s) => ({
+    windows: { ...s.windows, [id]: { older: !!data.has_older, newer: !!data.has_newer } },
     ...upsertSession(s, data.session),
     sessionById: { ...s.sessionById, [id]: data.session },
     messages: { ...s.messages, [id]: data.messages },
@@ -247,6 +259,31 @@ export async function loadSession(id: string) {
   }));
 }
 
+/** Older messages before the loaded ones (scrolling up). Returns how many came. */
+export async function loadOlder(id: string, stopAtSummary = true): Promise<number> {
+  const first = getState().messages[id]?.[0];
+  if (!first) return 0;
+  const page = await get<Page>(`/sessions/${id}/messages?before=${encodeURIComponent(first.id)}&limit=${PAGE}${stopAtSummary ? "&stop_at_summary=true" : ""}`);
+  setState((s) => {
+    const cur = s.messages[id] ?? [];
+    if (cur[0]?.id !== first.id) return {}; // changed meanwhile
+    return {
+      messages: { ...s.messages, [id]: [...page.messages, ...cur] },
+      windows: { ...s.windows, [id]: { older: page.has_older, newer: s.windows[id]?.newer ?? false } },
+    };
+  });
+  return page.messages.length;
+}
+
+/** Show the part of the chat around a message (search hit, media). */
+export async function loadAround(id: string, messageId: string) {
+  const page = await get<Page>(`/sessions/${id}/messages?around=${encodeURIComponent(messageId)}&limit=${PAGE}`);
+  setState((s) => ({
+    messages: { ...s.messages, [id]: page.messages },
+    windows: { ...s.windows, [id]: { older: page.has_older, newer: page.has_newer } },
+  }));
+}
+
 /** After reconnects: reload everything that could have changed. */
 export async function resync() {
   const isAdmin = getState().me?.role === "admin";

web/src/styles.css

@@ -527,6 +527,20 @@ button.session-group:hover {
   word-break: break-word;
   position: relative;
 }
+/* User messages are Markdown too; the line breaks come from keepLineBreaks. */
+.msg-user .markdown {
+  white-space: normal;
+}
+.composer-preview {
+  min-height: 44px;
+  max-height: 40vh;
+  overflow-y: auto;
+  padding: 10px 12px;
+  border-radius: var(--radius);
+  border: 1px dashed var(--bg3);
+  background: var(--bg1);
+  cursor: text;
+}
 .msg-user .msg-actions {
   position: absolute;
   top: 4px;
@@ -1054,6 +1068,13 @@ button.session-group:hover {
 .form label {
   color: var(--fg2);
 }
+.form label.check {
+  grid-column: 2;
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  color: var(--fg1);
+}
 .form .hint {
   grid-column: 2;
   font-size: 12px;
@@ -3150,6 +3171,28 @@ button.danger-solid {
 .refine-card summary .icon {
   color: var(--purple);
 }
+.harness-note {
+  display: flex;
+  align-items: baseline;
+  gap: 8px;
+  margin: 6px 0;
+  padding: 6px 10px;
+  border-left: 3px solid var(--blue);
+  border-radius: 4px;
+  background: var(--bg1);
+  font-size: 12.5px;
+  color: var(--fg2);
+}
+.harness-note .icon {
+  color: var(--blue);
+  flex-shrink: 0;
+}
+.harness-note.ok {
+  border-left-color: var(--green);
+}
+.harness-note.ok .icon {
+  color: var(--green);
+}
 
 /* --- automations ---------------------------------------------------------------- */
 .job.off {
@@ -4142,3 +4185,216 @@ span.chat-tab > button {
     font-size: 12px;
   }
 }
+
+/* --- long chats ------------------------------------------------------------------
+ * Finished turns fold into one line, older messages load on demand, search hits. */
+.work-block > .work-head {
+  display: inline-flex;
+  align-items: center;
+  gap: 5px;
+  border: none;
+  background: none;
+  padding: 2px 0;
+  margin-bottom: 4px;
+  font-size: 12.5px;
+  color: var(--muted);
+  cursor: pointer;
+}
+.work-block > .work-head:hover {
+  color: var(--fg1);
+}
+.work-block.open {
+  border-left: 2px solid var(--bg2);
+  padding-left: 10px;
+  margin-bottom: 14px;
+}
+.older-loader {
+  display: flex;
+  justify-content: center;
+  padding: 6px 0 12px;
+}
+.back-to-latest {
+  position: sticky;
+  bottom: 8px;
+  display: flex;
+  align-items: center;
+  gap: 6px;
+  margin: 10px auto 0;
+  box-shadow: var(--shadow);
+}
+.msg.highlight,
+.summary-divider[data-mid].highlight {
+  outline: 2px solid var(--accent);
+  outline-offset: 4px;
+  border-radius: var(--radius);
+}
+.chat-search {
+  border-bottom: 1px solid var(--bg2);
+  padding: 6px 12px;
+  background: var(--bg0);
+}
+.chat-search > .row {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+}
+.chat-search > .row input {
+  flex: 1;
+  min-width: 0;
+}
+.chat-search-hits {
+  max-height: 40vh;
+  overflow-y: auto;
+  margin-top: 6px;
+  display: flex;
+  flex-direction: column;
+  gap: 2px;
+}
+.chat-search-hits button {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 2px;
+  text-align: left;
+  border: none;
+  background: transparent;
+  padding: 6px 8px;
+  border-radius: 6px;
+}
+.chat-search-hits button:hover {
+  background: var(--bg1);
+}
+.chat-search-hits .who {
+  font-size: 11.5px;
+  color: var(--muted);
+}
+.chat-search-hits .snippet {
+  font-size: 13px;
+  color: var(--fg1);
+  overflow: hidden;
+  display: -webkit-box;
+  -webkit-line-clamp: 2;
+  -webkit-box-orient: vertical;
+}
+
+/* --- media overview of a chat --------------------------------------------------- */
+.media-gallery {
+  width: min(1100px, calc(100vw - 24px));
+  height: min(820px, calc(100dvh - 24px));
+  display: flex;
+  flex-direction: column;
+  gap: 10px;
+}
+.media-head {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+  flex-wrap: wrap;
+}
+.media-head h3 {
+  margin: 0;
+  display: flex;
+  align-items: center;
+  gap: 6px;
+}
+.media-filters {
+  display: flex;
+  gap: 6px;
+  flex-wrap: wrap;
+  flex: 1;
+}
+.media-filters .chip-btn {
+  padding: 3px 10px;
+  font-size: 13px;
+}
+.media-filters small {
+  color: var(--muted);
+  margin-left: 2px;
+}
+.media-grid {
+  flex: 1;
+  min-height: 0;
+  overflow-y: auto;
+  display: grid;
+  grid-template-columns: repeat(auto-fill, minmax(150px, 1fr));
+  grid-auto-rows: 150px;
+  gap: 8px;
+}
+.media-tile {
+  position: relative;
+  padding: 0;
+  overflow: hidden;
+  border-radius: 8px;
+  background: var(--bg2);
+  border: 1px solid var(--bg3);
+}
+.media-tile img,
+.media-tile video {
+  width: 100%;
+  height: 100%;
+  object-fit: cover;
+  display: block;
+}
+.media-tile .media-play {
+  position: absolute;
+  inset: 0;
+  margin: auto;
+  width: 34px;
+  height: 34px;
+  color: #fff;
+  filter: drop-shadow(0 1px 3px rgba(0, 0, 0, 0.6));
+}
+.media-audio {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  gap: 8px;
+  height: 100%;
+  padding: 8px;
+  font-size: 12px;
+  color: var(--fg2);
+  word-break: break-all;
+}
+.media-audio .icon {
+  width: 28px;
+  height: 28px;
+  color: var(--accent);
+}
+.media-viewer {
+  flex: 1;
+  min-height: 0;
+  display: flex;
+  flex-direction: column;
+  gap: 8px;
+}
+.media-stage {
+  flex: 1;
+  min-height: 0;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  background: var(--bg1);
+  border-radius: 8px;
+}
+.media-stage img,
+.media-stage video {
+  max-width: 100%;
+  max-height: 100%;
+  object-fit: contain;
+}
+.media-bar {
+  display: flex;
+  align-items: center;
+  gap: 6px;
+  flex-wrap: wrap;
+  font-size: 12.5px;
+  color: var(--fg2);
+}
+.media-bar .grow {
+  flex: 1;
+  min-width: 0;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}

web/src/theme.ts

@@ -23,6 +23,7 @@ export const THEMES = [
   { id: "rosepine", name: "Rosé Pine", source: "rose-pine/rose-pine-theme", license: "MIT" },
   { id: "everforest", name: "Everforest", source: "sainnhe/everforest", license: "MIT" },
   { id: "kanagawa", name: "Kanagawa", source: "rebelot/kanagawa.nvim", license: "MIT" },
+  { id: "tintenblau", name: "Tintenblau", source: "zink/tintenblau", license: "private" },
 ] as const;
 
 export type Theme = (typeof THEMES)[number]["id"];

web/src/themes/index.ts

@@ -30,3 +30,5 @@ import "./everforest-dark.css";
 import "./everforest-light.css";
 import "./kanagawa-dark.css";
 import "./kanagawa-light.css";
+import "./tintenblau-dark.css";
+import "./tintenblau-light.css";

web/src/themes/tintenblau-dark.css

@@ -0,0 +1,40 @@
+/*
+ * Tintenblau Dark
+ * Palette: zink/tintenblau (colors.toml, neovim.lua, zed.json of the desktop theme).
+ */
+:root[data-theme="tintenblau-dark"] {
+  color-scheme: dark;
+  --theme-color: #232a44;
+
+  --bg0: #232a44;
+  --bg1: #2b3352;
+  --bg2: #353e60;
+  --bg3: #4a5478;
+  --fg0: #f5efe3;
+  --fg1: #eae4d6;
+  --fg2: #d6d0c2;
+  --fg3: #bdcfd4;
+  --muted: #8e96b4;
+
+  --accent: #7aa0cc;
+  --accent2: #d4b46a;
+  --on-accent: #232a44;
+  --red: #d47a6a;
+  --green: #96b4bc;
+  --aqua: #96b4bc;
+  --blue: #7aa0cc;
+  --purple: #c896b2;
+
+  --diff-add: rgba(150, 180, 188, 0.16);
+  --diff-del: rgba(212, 122, 106, 0.16);
+  --shadow: 0 6px 24px rgba(10, 14, 30, 0.45);
+
+  --syntax-keyword: #c896b2;
+  --syntax-string: #d47a6a;
+  --syntax-number: #96b4bc;
+  --syntax-comment: #8e96b4;
+  --syntax-function: #7aa0cc;
+  --syntax-type: #d4b46a;
+  --syntax-variable: #eae4d6;
+  --syntax-meta: #baa0c4;
+}

web/src/themes/tintenblau-light.css

@@ -0,0 +1,40 @@
+/*
+ * Tintenblau (light)
+ * Palette: zink/tintenblau (colors.toml, neovim.lua, zed.json of the desktop theme).
+ */
+:root[data-theme="tintenblau-light"] {
+  color-scheme: light;
+  --theme-color: #f0ead9;
+
+  --bg0: #f0ead9;
+  --bg1: #e6dfd0;
+  --bg2: #dbd3c1;
+  --bg3: #c9c0ac;
+  --fg0: #0f1628;
+  --fg1: #1e2a4a;
+  --fg2: #3a3f5a;
+  --fg3: #5e5a6a;
+  --muted: #8a8694;
+
+  --accent: #2a3f6f;
+  --accent2: #6a4a2c;
+  --on-accent: #f0ead9;
+  --red: #8a3028;
+  --green: #4a5a3a;
+  --aqua: #3a5a6a;
+  --blue: #3a5a8a;
+  --purple: #5a4a72;
+
+  --diff-add: rgba(74, 90, 58, 0.14);
+  --diff-del: rgba(138, 48, 40, 0.12);
+  --shadow: 0 6px 24px rgba(30, 42, 74, 0.16);
+
+  --syntax-keyword: #2a3f6f;
+  --syntax-string: #8a3028;
+  --syntax-number: #5a4a72;
+  --syntax-comment: #8a8694;
+  --syntax-function: #3a5a6a;
+  --syntax-type: #6a4a2c;
+  --syntax-variable: #1e2a4a;
+  --syntax-meta: #4a5a3a;
+}

web/src/types.ts

@@ -141,6 +141,7 @@ export interface ModelInfo {
   name: string;
   context?: number;
   max_output?: number | null;
+  max_input?: number | null;
   reasoning: boolean;
   vision: boolean;
   effort?: string | null;
@@ -166,7 +167,9 @@ export interface AgentInfo {
   tools?: string[] | null;
   source: "builtin" | "config" | "file" | "personal";
   max_parallel?: number | null;
-  refine?: { rounds: number; model?: string | null; criteria?: string | null } | null;
+  refine?: { rounds: number; model?: string | null; criteria?: string | null; after_todos?: boolean } | null;
+  /** binary_info and decompile (Ghidra) available in this mode. */
+  reverse?: boolean;
   /** Source file of Markdown agents. */
   path?: string | null;
 }

web/src/whatsnew.ts

@@ -3,6 +3,40 @@
  * under "unreleased"; scripts/release.sh renames the key to the release version.
  */
 export const WHATS_NEW: Record<string, { en: string[]; de: string[] }> = {
+  "202611-00022": {
+    en: ["New theme “Tintenblau” (Settings → General → Theme)"],
+    de: ["Neues Theme „Tintenblau“ (Einstellungen → Allgemein → Theme)"],
+  },
+  "202611-00021": {
+    en: ["Git commits of agents name the model: “Co-Authored-By: <model> (<provider>) via CodeCraft” (Settings → General)"],
+    de: ["Git-Commits von Agenten nennen das Modell: „Co-Authored-By: <Modell> (<Anbieter>) via CodeCraft“ (Einstellungen → Allgemein)"],
+  },
+  "202611-00020": {
+    en: ["Reverse engineering: decompile with Ghidra can be enabled for any mode (Settings → Agents & commands), now also for raw firmware"],
+    de: ["Reverse Engineering: Dekompilieren mit Ghidra lässt sich für jeden Modus einschalten (Einstellungen → Agenten & Befehle), jetzt auch für rohe Firmware"],
+  },
+  "202611-00019": {
+    en: ["Long chats open and react much faster: older messages load when you scroll up, finished turns fold into one line", "Search in a chat (magnifier in the top bar) and ⋯ → Media: all images, videos and audio of a chat"],
+    de: ["Lange Chats öffnen und reagieren viel schneller: ältere Nachrichten laden beim Hochscrollen, abgeschlossene Turns sind eingeklappt", "Suche im Chat (Lupe oben) und ⋯ → Medien: alle Bilder, Videos und Audiodateien eines Chats"],
+  },
+  "202611-00018": {
+    en: [
+      "Modes with a review: every completed todo is reviewed, and the agent keeps working until the todo list is done – for overnight runs",
+      "Long chats are compacted in time instead of failing with “input too long”",
+    ],
+    de: [
+      "Modi mit Review: jedes erledigte Todo wird geprüft, und der Agent arbeitet weiter, bis die Liste abgehakt ist – für Läufe über Nacht",
+      "Lange Chats werden rechtzeitig zusammengefasst, statt mit „Eingabe zu lang“ abzubrechen",
+    ],
+  },
+  "202611-00017": {
+    en: ["Your messages are shown as Markdown; the eye button next to the text field previews it before sending"],
+    de: ["Deine Nachrichten werden als Markdown dargestellt; das Augen-Symbol neben dem Textfeld zeigt vor dem Senden eine Vorschau"],
+  },
+  "202611-00014": {
+    en: ["Folder picker (new automation, new chat): create a new folder right there"],
+    de: ["Ordnerauswahl (neue Automatisierung, neuer Chat): direkt einen neuen Ordner anlegen"],
+  },
   "202611-00013": {
     en: [
       "New automation editor: instructions, a graphical schedule and an assistant chat that writes the instructions with you",