Skip to content
This repository was archived by the owner on Nov 14, 2026. It is now read-only.

Commit 595aa49

Browse files
authored
chore(release): prepare 0.57.0 (#197)
* chore(release): prepare 0.57.0 Bump version 0.56.0 -> 0.57.0 across pyproject.toml, uv.lock, README, docs, and installer references Consume Unreleased into a new 0.57.0 (2026-07-05) CHANGELOG section (ghost input-prompt/TUI stability fixes, native /benchmark command suite, benchmark and skill security hardening) and sync into docs/en/release-notes/changelog.md Add 0.57.0 entry to docs/en/release-notes/breaking-changes.md (no breaking changes) * docs: resolve release note review comments
1 parent 33ebf96 commit 595aa49

8 files changed

Lines changed: 94 additions & 118 deletions

File tree

‎CHANGELOG.md‎

Lines changed: 23 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -15,51 +15,31 @@ GitHub Releases page; `0.8.0` is the new starting line.
1515

1616
## Unreleased
1717

18-
- Show active subagent tool work in the pinned TUI status tail instead of
19-
leaving long foreground agent runs on the generic composing spinner.
20-
- Keep the TUI prompt bar visible while an agent turn is starting so the
21-
empty composer does not disappear during lazy-load frames.
22-
- Ported the running agent TUI toward Pi's stable diff-rendered scene model so streamed output keeps the input card visible without prompt jumps.
23-
- Added publishability-focused benchmark comparison planning for multi-model
24-
runs, activity metrics, exportable reports, and safe online source discovery.
25-
- Added an experimental Focus TUI mode for active agent turns, keeping the composer pinned, hiding file activity by default, and rendering live output without terminal scrollback jumps.
26-
- Stream file write/edit activity in a compact live shelf so changed files update in place during agent runs instead of adding noisy terminal rows.
27-
- Hardened `/benchmark` local fixture runs: task `max_steps` now caps the
28-
underlying agent turn, and `/benchmark:swe` requires `--trusted-dataset true`
29-
because trusted local fixture datasets execute verification commands.
30-
- Hardened benchmark and active-skill security edges: SWE verification commands
31-
are shape-validated before execution, benchmark discovery requires explicit
32-
network opt-in, benchmark run IDs avoid clock collisions, runtime overrides
33-
restore after setup failures, and active-skill deactivation persistence
34-
failures are surfaced instead of swallowed.
35-
- Strengthened the bundled `pythinker-core` benchmark suite with edge-case
36-
fixtures for atomic rollback, iterable de-duplication, explicit falsey
37-
metadata values, and safe path joins across absolute, sibling-prefix, parent,
38-
and symlink escapes.
39-
40-
- Keep the terminal input composer pinned to the bottom during agent runs with a fullscreen prompt mode to reduce TUI flicker.
41-
42-
- Explicitly invoked skills now remain active across later turns through a
43-
compact reminder, and can be cleared with a named stop request or "normal mode".
18+
## 0.57.0 (2026-07-05)
4419

4520
- **No more ghost/duplicate input prompt while the agent works.** After
46-
submitting a prompt, the editable input row is no longer fossilized above the
47-
stream as a second, ghostly prompt. The top border stays visible while the
48-
pre-attach race frame still collapses before the running-prompt delegate
49-
exists, preventing prompt chrome from fossilizing above the spinner. Once the
50-
running frame owns the prompt, the `❯` marker stays visible while only the
51-
editable buffer is hidden until the first scrollback commit, avoiding the
52-
collapsed one-line card under the lazy-load spinner; the full editable row
53-
remains below the live stream so you can still see where to steer.
54-
55-
- Added native `/benchmark` slash command for deterministic local Pythinker
56-
model evaluation with bundled smoke tasks, replayable artifacts, and branded
57-
markdown reports.
58-
- Expanded `/benchmark start` to use a richer default core suite, isolate file
59-
edits through the active toolset workspace override, and exclude generated
60-
verification caches from changed-file reports.
61-
- Added `/benchmark:swe` for native SWE-style JSONL benchmark tasks that run
62-
through Pythinker's existing model, tool, verification, and artifact path.
21+
submitting a prompt, the input card no longer fossilizes above the stream as
22+
a second, ghostly prompt. The prompt bar and top border now stay visible
23+
through turn-start and lazy-load frames, and running-agent output renders
24+
through a stable diff-rendered scene (ported from Pi) so the input card no
25+
longer jumps. An experimental Focus TUI mode (`tui.focus_mode`) pins the
26+
composer and hides file activity behind a compact live shelf for a cleaner
27+
fullscreen view, and active subagent tool work now surfaces in the pinned
28+
status tail instead of a generic composing spinner.
29+
- **Added a native `/benchmark` command suite.** Run deterministic local
30+
Pythinker model evaluations with bundled smoke tasks and SWE-style JSONL
31+
tasks (`/benchmark:swe`), plus `/benchmark compare`, `/benchmark export`,
32+
and `/benchmark discover` actions that produce replayable artifacts,
33+
activity metrics, and branded markdown reports.
34+
- **Hardened benchmark and skill security edges.** SWE verification commands
35+
are shape-validated before execution, benchmark discovery requires explicit
36+
network opt-in, run IDs avoid clock collisions, runtime overrides restore
37+
after setup failures, and active-skill deactivation failures now surface
38+
instead of being swallowed. Explicitly invoked skills stay active across
39+
later turns through a compact reminder until stopped by name or
40+
"normal mode".
41+
42+
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.57.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
6343

6444
## 0.56.0 (2026-07-02)
6545

‎README.md‎

Lines changed: 29 additions & 28 deletions
Original file line numberDiff line numberDiff line change
@@ -50,13 +50,13 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
5050
5151
---
5252

53-
## 🆕 What's New in 0.56.0
53+
## 🆕 What's New in 0.57.0
5454

55-
- **Windows shell UI recovers from mid-session console blanking.** Child processes spawned by the Shell tool, background tasks, and `!` commands no longer attach to the interactive console, and the prompt renderer forces an absolute repaint after terminal resizes and failed scrollback handoffs instead of diffing against a stale frame.
56-
- **Workflow progress rendering and lifecycle fixes.** Progress display no longer duplicates agents truncated by the per-phase display cap, leaked `agent()` coroutines are closed when `parallel()` rejects its arguments, and a 1000-agent lifetime backstop now guards against runaway workflow loops.
57-
- **Stale update-success notice cleared after downgrading.** Restarting into an older Homebrew install no longer leaves a permanent "Restart to apply" banner.
55+
- **No more ghost/duplicate input prompt while the agent works.** The input card no longer fossilizes above the stream as a second, ghostly prompt; the prompt bar and top border stay visible through turn-start and lazy-load frames; running-agent output renders through a stable diff-rendered scene (ported from Pi); and an experimental Focus TUI mode (`tui.focus_mode`) pins the composer and hides file activity behind a compact live shelf.
56+
- **Added a native `/benchmark` command suite.** Run deterministic local Pythinker model evaluations with bundled smoke tasks and SWE-style JSONL tasks (`/benchmark:swe`), plus `/benchmark compare`, `/benchmark export`, and `/benchmark discover` actions with replayable artifacts and branded markdown reports.
57+
- **Hardened benchmark and skill security edges.** SWE verification commands are shape-validated before execution, benchmark discovery requires explicit network opt-in, and active-skill deactivation failures now surface instead of being swallowed.
5858

59-
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.56.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
59+
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.57.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
6060

6161

6262
---
@@ -162,7 +162,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
162162

163163
| Platform | Recommended install | Artifact source |
164164
|---|---|---|
165-
| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.56.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
165+
| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.57.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
166166
| **<img src="https://img.shields.io/badge/-macOS-000000?style=flat-square&logo=apple&logoColor=white" alt="macOS"> / <img src="https://img.shields.io/badge/-Linux-FCC624?style=flat-square&logo=linux&logoColor=black" alt="Linux">** | `curl -fsSL https://pythinker.com/install.sh \| bash` | native tarball from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
167167
| **<img src="https://img.shields.io/badge/-macOS-000000?style=flat-square&logo=apple&logoColor=white" alt="macOS"> — Homebrew** | `brew install Pythoughts-labs/pythinker/pythinker-code` | auto-published Homebrew tap |
168168
| **🐳 Docker** | `docker run --rm -it ghcr.io/pythoughts-labs/pythinker-code` | GHCR multi-arch image |
@@ -190,35 +190,36 @@ pythinker # start the interactive TUI
190190

191191
### 🪟 Windows — native installer
192192

193-
`PythinkerSetup-0.56.0.exe` is a signed* Inno Setup wizard. Installs per-user
194-
into `%LOCALAPPDATA%\Programs\Pythinker`, registers `pythinker` on your user
195-
PATH (`HKCU\Environment`), broadcasts `WM_SETTINGCHANGE` so new shells see
196-
the change. **No UAC prompt.**
193+
`PythinkerSetup-0.57.0.exe` is an Inno Setup wizard. Release builds are signed
194+
when Authenticode secrets are configured in CI; otherwise the installer ships
195+
unsigned. Installs per-user into `%LOCALAPPDATA%\Programs\Pythinker`, registers
196+
`pythinker` on your user PATH (`HKCU\Environment`), broadcasts
197+
`WM_SETTINGCHANGE` so new shells see the change. **No UAC prompt.**
197198

198199
```powershell
199200
# One-line install (downloads the native .exe, verifies SHA-256, runs per-user)
200201
irm https://pythinker.com/install.ps1 | iex
201202
202203
# Or manually download the installer + checksum from the Releases page,
203204
# verify with Get-FileHash, then run:
204-
.\PythinkerSetup-0.56.0.exe
205+
.\PythinkerSetup-0.57.0.exe
205206
206207
# Open a fresh PowerShell
207208
pythinker --version
208209
```
209210

210-
**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.56.0.exe /ALLUSERS`
211+
**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.57.0.exe /ALLUSERS`
211212
installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
212213

213214
**Upgrade:** `pythinker update` from inside the running app — it downloads
214-
the newest installer, verifies SHA-256, and launches the signed Inno installer
215+
the newest installer, verifies SHA-256, and launches the Inno installer
215216
with visible progress (`/SILENT /NORESTART /CURRENTUSER /CLOSEAPPLICATIONS /NORESTARTAPPLICATIONS`).
216217

217218
**Uninstall:** Apps & Features → *Pythinker Code* → Uninstall reverts both
218219
the files and the PATH edit.
219220

220-
> 🛡 **First-launch SmartScreen warning** — \*until the Authenticode cert is
221-
> provisioned in CI, the installer ships unsigned and Windows shows
221+
> 🛡 **First-launch SmartScreen warning** — Until Authenticode secrets are
222+
> configured in CI for a release, the installer ships unsigned and Windows shows
222223
> *"Windows protected your PC."* Click **More info → Run anyway**. Use the
223224
> published `.sha256` as your integrity check until signing comes online.
224225
@@ -265,26 +266,26 @@ attached to every GitHub Release.
265266

266267
```sh
267268
# Debian / Ubuntu (x86_64)
268-
sudo dpkg -i pythinker-code_0.56.0_amd64.deb
269+
sudo dpkg -i pythinker-code_0.57.0_amd64.deb
269270
sudo apt-get install -f # only if dpkg reports missing deps
270271

271272
# Debian / Ubuntu (ARM64)
272-
sudo dpkg -i pythinker-code_0.56.0_arm64.deb
273+
sudo dpkg -i pythinker-code_0.57.0_arm64.deb
273274

274275
# Fedora / RHEL / openSUSE (x86_64)
275-
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm
276-
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm.sha256
277-
sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256
276+
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.57.0/pythinker-code-0.57.0.x86_64.rpm
277+
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.57.0/pythinker-code-0.57.0.x86_64.rpm.sha256
278+
sha256sum -c pythinker-code-0.57.0.x86_64.rpm.sha256
278279
# Fedora / RHEL:
279-
sudo dnf install ./pythinker-code-0.56.0.x86_64.rpm
280+
sudo dnf install ./pythinker-code-0.57.0.x86_64.rpm
280281
# openSUSE:
281-
sudo zypper install ./pythinker-code-0.56.0.x86_64.rpm
282+
sudo zypper install ./pythinker-code-0.57.0.x86_64.rpm
282283

283284
# Fedora / RHEL (aarch64)
284-
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm
285-
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm.sha256
286-
sha256sum -c pythinker-code-0.56.0.aarch64.rpm.sha256
287-
sudo dnf install ./pythinker-code-0.56.0.aarch64.rpm
285+
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.57.0/pythinker-code-0.57.0.aarch64.rpm
286+
curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.57.0/pythinker-code-0.57.0.aarch64.rpm.sha256
287+
sha256sum -c pythinker-code-0.57.0.aarch64.rpm.sha256
288+
sudo dnf install ./pythinker-code-0.57.0.aarch64.rpm
288289
```
289290

290291
Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -293,8 +294,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
293294
**Verify before install:**
294295

295296
```sh
296-
sha256sum -c pythinker-code_0.56.0_amd64.deb.sha256 # Debian/Ubuntu
297-
sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256 # Fedora/RHEL
297+
sha256sum -c pythinker-code_0.57.0_amd64.deb.sha256 # Debian/Ubuntu
298+
sha256sum -c pythinker-code-0.57.0.x86_64.rpm.sha256 # Fedora/RHEL
298299
```
299300

300301
**Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /

‎docs/en/guides/getting-started.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ On Windows, run the PowerShell bootstrap. It downloads the native installer, ver
4444
irm https://pythinker.com/install.ps1 | iex
4545
```
4646

47-
You can also download `PythinkerSetup-0.56.0.exe` manually from the [latest release](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
47+
You can also download `PythinkerSetup-0.57.0.exe` manually from the [latest release](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
4848

4949
Verify the installation:
5050

‎docs/en/release-notes/breaking-changes.md‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,10 @@ This page documents breaking changes in Pythinker Code releases and provides mig
44

55
## Unreleased
66

7+
## 0.57.0 (2026-07-05)
8+
9+
No breaking changes. This release is compatible with 0.56.0 user configuration, native installs, and session data.
10+
711
## 0.56.0 (2026-07-02)
812

913
No breaking changes. This release is compatible with 0.55.0 user configuration, native installs, and session data.

‎docs/en/release-notes/changelog.md‎

Lines changed: 23 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -17,40 +17,31 @@ GitHub Releases page; `0.8.0` is the new starting line.
1717

1818
## Unreleased
1919

20-
- Added publishability-focused benchmark comparison planning for multi-model
21-
runs, activity metrics, exportable reports, and safe online source discovery.
22-
- Stream file write/edit activity in a compact live shelf so changed files update in place during agent runs instead of adding noisy terminal rows.
23-
- Hardened `/benchmark` local fixture runs: task `max_steps` now caps the
24-
underlying agent turn, and `/benchmark:swe` requires `--trusted-dataset true`
25-
because trusted local fixture datasets execute verification commands.
26-
- Strengthened the bundled `pythinker-core` benchmark suite with edge-case
27-
fixtures for atomic rollback, iterable de-duplication, explicit falsey
28-
metadata values, and safe path joins across absolute, sibling-prefix, parent,
29-
and symlink escapes.
30-
31-
- Keep the terminal input composer pinned to the bottom during agent runs with a fullscreen prompt mode to reduce TUI flicker.
32-
33-
- Explicitly invoked skills now remain active across later turns through a
34-
compact reminder, and can be cleared with a named stop request or "normal mode".
20+
## 0.57.0 (2026-07-05)
3521

3622
- **No more ghost/duplicate input prompt while the agent works.** After
37-
submitting a prompt, the editable input row is no longer fossilized above the
38-
stream as a second, ghostly prompt. The top border stays visible while the
39-
pre-attach race frame still collapses before the running-prompt delegate
40-
exists, preventing prompt chrome from fossilizing above the spinner. Once the
41-
running frame owns the prompt, the `❯` marker stays visible while only the
42-
editable buffer is hidden until the first scrollback commit, avoiding the
43-
collapsed one-line card under the lazy-load spinner; the full editable row
44-
remains below the live stream so you can still see where to steer.
45-
46-
- Added native `/benchmark` slash command for deterministic local Pythinker
47-
model evaluation with bundled smoke tasks, replayable artifacts, and branded
48-
markdown reports.
49-
- Expanded `/benchmark start` to use a richer default core suite, isolate file
50-
edits through the active toolset workspace override, and exclude generated
51-
verification caches from changed-file reports.
52-
- Added `/benchmark:swe` for native SWE-style JSONL benchmark tasks that run
53-
through Pythinker's existing model, tool, verification, and artifact path.
23+
submitting a prompt, the input card no longer fossilizes above the stream as
24+
a second, ghostly prompt. The prompt bar and top border now stay visible
25+
through turn-start and lazy-load frames, and running-agent output renders
26+
through a stable diff-rendered scene (ported from Pi) so the input card no
27+
longer jumps. An experimental Focus TUI mode (`tui.focus_mode`) pins the
28+
composer and hides file activity behind a compact live shelf for a cleaner
29+
fullscreen view, and active subagent tool work now surfaces in the pinned
30+
status tail instead of a generic composing spinner.
31+
- **Added a native `/benchmark` command suite.** Run deterministic local
32+
Pythinker model evaluations with bundled smoke tasks and SWE-style JSONL
33+
tasks (`/benchmark:swe`), plus `/benchmark compare`, `/benchmark export`,
34+
and `/benchmark discover` actions that produce replayable artifacts,
35+
activity metrics, and branded markdown reports.
36+
- **Hardened benchmark and skill security edges.** SWE verification commands
37+
are shape-validated before execution, benchmark discovery requires explicit
38+
network opt-in, run IDs avoid clock collisions, runtime overrides restore
39+
after setup failures, and active-skill deactivation failures now surface
40+
instead of being swallowed. Explicitly invoked skills stay active across
41+
later turns through a compact reminder until stopped by name or
42+
"normal mode".
43+
44+
Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.57.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
5445

5546
## 0.56.0 (2026-07-02)
5647

0 commit comments

Comments
 (0)