release: v1.5.0

CHANGELOG.md

@@ -7,24 +7,43 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.5.0] - 2026-08-08
+
 ### Added
 
-- **ClawCodex Desktop — a native desktop app** (`ui-desktop/`). The full
-  agent in a polished Electron window: streaming chat with live tool
-  activity, approval prompts, session sidebar with resume, side-by-side
-  previews, and settings — no terminal required.
+- **ClawCodex Desktop — a native desktop app** (`ui-desktop/`, #802–#805).
+  The full agent in a polished Electron window: streaming chat with live
+  tool activity and reasoning, permission approvals with
+  once/session/always grants, a session sidebar with resume (same durable
+  store as the TUI), side-by-side previews, settings, and the official
+  pixel-art crab as the app icon and in-app brand mark.
 
   ```
   clawcodex desktop
   ```
 
-  launches it from a checkout (installs UI deps on first run). Under the
-  hood the app spawns `clawcodex serve` — a new loopback HTTP + WebSocket
-  gateway (`/api/*` REST + JSON-RPC `/api/ws`) that runs sessions on the
-  same in-process agent core as the TUI, so both surfaces share one config,
-  one session store, and one set of skills. Ported from the reference
-  desktop implementation and fully rebranded, with a claw-mark icon set,
-  staged in PRs #802/#803/#804.
+  launches it from a checkout (installs UI deps on first run; `--no-dev`
+  builds once and launches Electron directly). Under the hood the app
+  spawns **`clawcodex serve`** — a new loopback HTTP + WebSocket gateway
+  (`/api/*` REST + JSON-RPC `/api/ws`) that runs sessions on the same
+  in-process agent core as the TUI, so both surfaces share one config, one
+  session store, and one set of skills. Ported from the reference desktop
+  implementation (~310K lines of TypeScript across ~1,500 files) and fully
+  rebranded, verified live end-to-end (boot → real chat turn → streamed
+  reply rendered), with macOS packaging producing a DMG/zip via
+  electron-builder.
+
+### Fixed
+
+- The desktop app's `lib/` source directories are tracked again — the root
+  `.gitignore`'s Python-oriented `lib/` pattern had silently excluded 180
+  renderer source files from the initial import; fresh clones failed at
+  boot (#806).
+- Desktop default UI scale is 100% (Chromium actual size) instead of the
+  reference's dense 90% preset, which read too small on typical displays;
+  per-install zoom choices persist (#807).
+- A second `clawcodex desktop` now explains the app is already running
+  (dev port probe) instead of dying on a vite stack trace (#808).
 
 ## [1.4.0] - 2026-08-02
 

README.md

@@ -135,6 +135,7 @@ The `session`, `settings`, and `env` blocks are optional — sensible defaults a
 
 ## 📰 News
 
+- **2026-08-08 (v1.5.0):** **ClawCodex Desktop — the whole agent in a native app (#802–#808)** — ClawCodex now ships a real desktop application (`ui-desktop/`): streaming chat with a live tool trail and reasoning, permission approvals with once/session/always grants, a session sidebar that lists and resumes the **same durable sessions as the TUI**, side-by-side previews, settings, and the official pixel-art crab as the dock icon and in-app brand mark. `clawcodex desktop` launches it from a checkout (first run installs the UI deps; `--no-dev` builds once and launches Electron directly). The architecture is the interesting part: the app spawns **`clawcodex serve`** — one loopback port serving `/api/*` REST plus a JSON-RPC WebSocket gateway at `/api/ws` — and sessions run on the **same in-process agent core the TUI uses**, so both surfaces share one config, one session store, one skills set, and one permission system; the wire contract is the TUI's own gateway vocabulary, adapted server-side. The port itself is one of the largest single features ClawCodex has landed: ~310K lines of TypeScript across ~1,500 files brought over from the reference desktop implementation, rebranded end to end, with every quality gate held to the reference's own baseline (typecheck green, lint identical, unit-test failure set byte-identical) and the whole loop verified live — boot → real chat turn → streamed reply rendered in the window. macOS packaging works today (`npm run dist:mac` → DMG/zip via electron-builder, hardened-runtime config in place). Ship-week fixes landed the same day: the root `.gitignore`'s Python-oriented `lib/` pattern had silently kept 180 renderer source files out of the initial import — fresh clones failed at boot until #806; the default UI scale moved from the reference's dense 90% preset to Chromium's 100% actual size (#807); and a second `clawcodex desktop` now gets a friendly "already running" message instead of a vite stack trace (#808).
 - **2026-08-02 (v1.4.0):** **Fusion models — give a text-only model vision (#771, #787)** — several strong reasoning models cannot see images at all: `deepseek-v4-pro` rejects an image content block outright (`400 unknown variant \`image_url\``), so pasting a screenshot, `@`-mentioning one, or letting `Read` return one ended the turn. A **fusion model** pairs that base model with a second, vision-capable one — every image is described by the vision model first, and the base model reads the description. `/fusion create <name> <base> <vision>` saves one; it then behaves like a normal model in the `/model` picker, as `--model <name>`, in `-p`, and across restarts. Ported from [claude-code-router](https://ccrdesk.top/en/configuration/fusion-models/)'s Fusion Model concept, with one deliberate difference: CCR is a proxy, so it can only offer vision as a *tool* the model may choose to call — which cannot help a pasted image, already on the wire before the model gets a turn. ClawCodex owns the agent loop, so it substitutes images in place, covering paste, `@file.png`, `Read`, and Bash image output at once. Verified end to end on Terminal-Bench 2.1's `code-from-image` task — transcribing handwritten pseudocode from a PNG and reproducing its output — with `deepseek-v4-flash` + `openai:gpt-5.6-luna` (#787); the base model alone returns a 400 on the same image. **Also in v1.4.0:** GPT-5.6 Sol/Terra/Luna (#773); four more OpenAI-compatible providers — groq, cerebras, baseten, xai — taking the registry to 30 (#784); `/mode` becomes `/permissions` with a three-level picker and Full Access by default (#768); `AskUserQuestion` finally renders a real picker instead of returning JSON to the model (#774); the OpenAI provider now picks its wire protocol from the model rather than the auth mode, which is what makes `gpt-5.6-luna` usable on an API key (#783); cached prompt tokens are billed at the cache rate instead of the full input rate, and OpenRouter's streamed reasoning is no longer discarded (#785, #786); and headless runs stop reporting a cut-short run as a success (#777–#782).
 - **2026-07-29 (v1.3.0):** **ClawCodex scores 80.9% on Terminal-Bench 2.1 — a top-tier open-source result on Opus 5 (#720–#725, #747–#754)** — running headless on `claude-opus-5` at `effort=xhigh`, ClawCodex solved **72 of 89** Terminal-Bench 2.1 tasks: **80.9% pass@1** on a single run. On the [public 2.1 leaderboard](https://www.tbench.ai/leaderboard/terminal-bench/2.1) (k=5 averages) that would slot **around third** — behind Claude Code / Fable 5 (83.8%) and Codex / GPT-5.5 (83.1%), statistically level with the 79–80% cluster, and **ahead of Claude Code on Opus 4.8 (78.9%) and Sonnet 5 (74.6%)**. Getting there was open, unglamorous parity work: a Harbor eval adapter (`eval/harbor/`) for three-way ClawCodex-vs-openclaude-vs-Claude-Code runs (#720, #724, #725), then a run of prompt- and reliability-parity fixes — restored task-tool skip conditions and parallel-tool guidance, deferred nonessential initial tools, and recovery of trials lost to empty turns and transport drops (#747–#754). **Also in v1.3.0:** `claude-opus-5` support with an interactive `/effort` fix (#746), bounded persistent memory with a background self-improvement review (#731), a VS Code extension driving the agent-server over stdio (#727), image-paste input with an `[Image #N]` un-attach chip (#761, #762), the `CLAUDE.md → CLAWCODEX.md` context-file rebrand (#732), and transport-retry hardening (#757, #760). Stated plainly: this is a single k=1 pass (binomial 1σ ±4.2pp) against the board's k=5 ± ~1.2pp averages, benchmarked on `main` at #756 (before the v1.3.0 tag), so read it as directional rather than a ranked submission.
 - **2026-07-13:** **`/eco` token compression — -80% Bash-output tokens, measured, now a headline (#708, #712)** — a new session toggle compresses the model-bound rendering of every Bash result with deterministic filters ported from [RTK](https://github.com/rtk-ai/rtk)'s method set: failure-focused test summaries (kept error lines are never rewritten), `git`/`pip`/`npm` ceremony stripping, log dedup with `[×N]` counts, and a recoverable head-cap — all behind a **never-worse** guard, with every lossy compression teeing the full output to disk behind a runnable recovery hint (#708). A reproducible benchmark (`eval/eco/`) replays 27 real command outputs through the exact production pipeline and counts real tokenizer tokens: **92,989 → 17,767 (-80%)** corpus-wide, -88% on filter hits, plus an honestly conservative recompute of RTK's own 30-minute-session model (-19% under their averaged assumptions — real sessions are fat-tailed) (#712). Full tables: the [`/eco` section](#eco-benchmark) and [`eval/eco/results/`](eval/eco/results/results.md).
@@ -143,7 +144,6 @@ The `session`, `settings`, and `env` blocks are optional — sensible defaults a
 - **2026-07-07:** **Bounded the ESC-cancel chunk queue in OpenAI-compatible streaming (#278)** — `OpenAICompatibleProvider.chat_stream_response`'s worker-thread queue (added in #148) was an unbounded `queue.Queue`. A non-graceful disconnect from a proxy that keeps sending bytes after ESC (and never closes the SDK iterator) let the orphaned worker thread accumulate chunks in memory indefinitely. The queue is now capped at 64 chunks, so `put()` blocks the worker once full instead of growing without bound.
 - **2026-07-06 (v1.0.0):** **ClawCodex v1.0.0 — the 1.0 release: goal-directed autonomy, hooks & MCP wired for production, and a hardened permission system** — 86 commits since v0.7.0 (#580–#668) finish wiring the big subsystems end-to-end and graduate ClawCodex to 1.0. **Goal-directed autonomy:** the `/goal` + `/subgoal` completion-condition loop keeps the agent working until an LLM judge confirms the goal is actually met (#664), the new Monitor tool streams long-running shell output with backpressure (#665), background-bash completion notifications (#663), coordinator mode wired end-to-end on the live paths (#634), and `/advisor` token-efficient worker/reviewer pairing restored on the Ink TUI (#668). **Hooks live in production:** configured hooks now actually fire — bootstrap Hooks abstraction (#583), UserPromptSubmit (#597), multi-scope + lifecycle hooks (#595), `if` pre-filters (#643), PreToolUse `permissionDecision` (#655), PermissionRequest hooks at the ask seam (#637), MCP elicitation hooks (#659), and teammate TaskCompleted / TeammateIdle stop hooks (#642). **MCP completion:** OAuth server auth via the `/mcp` flow (#662), live `tools/list_changed` refresh (#598, #604), server instructions injected into the system prompt (#654), and `clawcodex mcp serve` re-exposes ClawCodex tools as an MCP stdio server (#635). **Permission hardening:** readable approval boxes with broadenable, persistent session grants (#608–#611), compound-command permission parity (#622), Bash normalization hardening (#626), `disableBypassPermissionsMode` lockdown (#660), an honest refuse-to-start unsandboxed guard (#658), subprocess secret-scrubbing (#650), and a flag-gated LLM security-classifier lane for auto mode (#589). **TUI maturity:** faithful Claude Code look & feel — diff rendering, tool-call transcript, task list, composer + permission-mode badge, busy line (#612–#616) — plus a minimal vim editing engine (#667), Esc-interrupt with a defanged Ctrl+C (#625), fully editable multi-line input (#621), slash-command argument hints (#631), a persistent session-stats line (#657), and restored `/cost`, `/skills`, and `/model` (#627, #629, #630). **Reliability:** the production compaction pipeline is wired and auto-compact actually applies its result (#587, #607), full retry lane + model fallback + message-history caching (#586), parallel Agent fan-out with the concurrency-cap deadlock fixed (#590), killing a background agent really stops the run (#606), and output styles work end-to-end (#640). Codebase stats: 1,170 Python files, **256,909 lines** (up from 233,520 lines on 2026-06-11).
 - **2026-06-30 (v0.7.0):** **ClawCodex v0.7.0 — TUI auto-theming, faithful inline rendering & a Claude-Code-style tool trail** — the Ink TUI now detects your terminal's background color (OSC 11) on startup and selects the light/dark theme to match, so text stays readable on any terminal with no env var needed (#577). Inline mode renders *truly* inline like Claude Code: no screen wipe on launch, and no overlap with prior terminal output on startup or with the returning shell prompt on exit (#573, #575). The tool trail reads Claude-style — workspace-relative paths (`Read(src/foo.ts)`), `Grep(pattern)` labels, and a `Read N lines` result collapse (#574) — and the banner gains a 🦞 mascot with brighter secondary text on dark themes (#576).
-- **2026-06-24 (v0.6.0):** **ClawCodex v0.6.0 — interactive TUI REPL parity** — a batch of input ports brings the Python REPL to parity with the ink reference: a working slash-command menu (execute / complete / filter like the ink REPL), the sparkle spinner with a live token + elapsed busy row, context-aware prompt footer hints (interrupt / bash / grammar), the `?` shortcuts help panel, an `@` file-mention dropdown with in-place splice, double-press Ctrl+C / Ctrl+D to exit, Ctrl+R history search + double-Esc clear-draft, a `[Pasted text #N +K lines]` large-paste placeholder, and the completed command queue (drain queued prompts + dim preview). Login docs now list all 25 providers (#383).
 - **2026-06-23:** **One-click installer** — `curl -fsSL https://clawcodex.app/install.sh | bash` installs uv (no sudo), provisions Python 3.10+, clones to `~/.clawcodex`, creates a lock-pinned venv, and registers `clawcodex` on PATH; ships status / doctor / verify / update / uninstall subcommands, is safe to re-run, and works on macOS / Linux / WSL.
 📚 Older items have moved to the full **[News archive](docs/NEWS.md)**.