pythinker-code 0.50.0__tar.gz → 0.52.0__tar.gz

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythinker-code
-Version: 0.50.0
+Version: 0.52.0
 Summary: Pythinker — an agentic CLI developed by Pythoughts-labs.
 Keywords: cli,agent,ai,coding-assistant,llm,claude,openai,terminal
 Author: Pythoughts-labs
@@ -115,12 +115,16 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.50.0
+## 🆕 What's New in 0.52.0
 
-- **Safer silent updates.** The downloaded build is now staged beside the running executable and promoted at exit, instead of overwriting the live onefile bundle in place — eliminating mid-session `zlib: incorrect header check` crashes after a background update.
-- **Cleaner update notice.** The "Updated → vX. Restart to apply." line renders below the prompt's bottom border, not inside the input area.
+- **Model-aware thinking levels.** The thinking selector and Shift+Tab cycle now scope reasoning effort to what the active GPT-5-family model accepts; unsupported persisted levels are clamped before the API call.
+- **Cleaner diff cards.** Diff syntax highlighting no longer paints an opaque code-theme background over green/red row tints — tints show through on every terminal.
+- **Truecolor in VS Code terminals.** Integrated terminals reporting `TERM_PROGRAM=vscode` (and forks) are promoted to truecolor so diff tints don't fall back to 16-color mode.
+- **No duplicate welcome banner on reload.** Same-session reloads (`/model`, `/theme`, `/thinking`, …) keep the existing banner instead of stacking a second splash.
+- **Update notice moved to footer.** The persistent "Restart to apply" / "Update available" line renders below the status/clock row, clear of the input box.
+- **Safer Homebrew self-upgrades.** Silent `brew upgrade` runs with cleanup/auto-update disabled so the in-use Cellar version isn't deleted mid-session.
 
-Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.50.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.52.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -210,7 +214,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.50.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.52.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
 | **<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) |
 | **<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 |
 | **🐳 Docker** | `docker run --rm -it ghcr.io/pythoughts-labs/pythinker-code` | GHCR multi-arch image |
@@ -238,7 +242,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.50.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.52.0.exe` is a signed* Inno Setup wizard. Installs per-user
 into `%LOCALAPPDATA%\Programs\Pythinker`, registers `pythinker` on your user
 PATH (`HKCU\Environment`), broadcasts `WM_SETTINGCHANGE` so new shells see
 the change. **No UAC prompt.**
@@ -249,13 +253,13 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.50.0.exe
+.\PythinkerSetup-0.52.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.50.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.52.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -313,26 +317,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.50.0_amd64.deb
+sudo dpkg -i pythinker-code_0.52.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.50.0_arm64.deb
+sudo dpkg -i pythinker-code_0.52.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.50.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.52.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.50.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.52.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.50.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.52.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.50.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.50.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.52.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.52.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -341,8 +345,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.50.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.50.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.52.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.52.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/README.md

@@ -50,12 +50,16 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.50.0
+## 🆕 What's New in 0.52.0
 
-- **Safer silent updates.** The downloaded build is now staged beside the running executable and promoted at exit, instead of overwriting the live onefile bundle in place — eliminating mid-session `zlib: incorrect header check` crashes after a background update.
-- **Cleaner update notice.** The "Updated → vX. Restart to apply." line renders below the prompt's bottom border, not inside the input area.
+- **Model-aware thinking levels.** The thinking selector and Shift+Tab cycle now scope reasoning effort to what the active GPT-5-family model accepts; unsupported persisted levels are clamped before the API call.
+- **Cleaner diff cards.** Diff syntax highlighting no longer paints an opaque code-theme background over green/red row tints — tints show through on every terminal.
+- **Truecolor in VS Code terminals.** Integrated terminals reporting `TERM_PROGRAM=vscode` (and forks) are promoted to truecolor so diff tints don't fall back to 16-color mode.
+- **No duplicate welcome banner on reload.** Same-session reloads (`/model`, `/theme`, `/thinking`, …) keep the existing banner instead of stacking a second splash.
+- **Update notice moved to footer.** The persistent "Restart to apply" / "Update available" line renders below the status/clock row, clear of the input box.
+- **Safer Homebrew self-upgrades.** Silent `brew upgrade` runs with cleanup/auto-update disabled so the in-use Cellar version isn't deleted mid-session.
 
-Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.50.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.52.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -145,7 +149,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.50.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.52.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
 | **<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) |
 | **<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 |
 | **🐳 Docker** | `docker run --rm -it ghcr.io/pythoughts-labs/pythinker-code` | GHCR multi-arch image |
@@ -173,7 +177,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.50.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.52.0.exe` is a signed* Inno Setup wizard. Installs per-user
 into `%LOCALAPPDATA%\Programs\Pythinker`, registers `pythinker` on your user
 PATH (`HKCU\Environment`), broadcasts `WM_SETTINGCHANGE` so new shells see
 the change. **No UAC prompt.**
@@ -184,13 +188,13 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.50.0.exe
+.\PythinkerSetup-0.52.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.50.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.52.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -248,26 +252,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.50.0_amd64.deb
+sudo dpkg -i pythinker-code_0.52.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.50.0_arm64.deb
+sudo dpkg -i pythinker-code_0.52.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.50.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.52.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.50.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.52.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.50.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.52.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.50.0/pythinker-code-0.50.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.50.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.50.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.52.0/pythinker-code-0.52.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.52.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.52.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -276,8 +280,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.50.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.50.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.52.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.52.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythinker-code"
-version = "0.50.0"
+version = "0.52.0"
 description = "Pythinker — an agentic CLI developed by Pythoughts-labs."
 readme = "README.md"
 requires-python = ">=3.12"

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/CHANGELOG.md

@@ -15,6 +15,100 @@ GitHub Releases page; `0.8.0` is the new starting line.
 
 ## Unreleased
 
+## 0.52.0 (2026-06-23)
+
+- **`InvalidToolError` now names the failing tool and the reason.** A bad
+  tool path in `agent.yaml` (typo, missing class, or — most commonly — a
+  `pythinker` binary built before the tool was added) used to surface as a
+  bare `Invalid tools: ['pythinker_code.tools.agent:ImplementAndJudge']`
+  with the actual reason buried in the log file. The aggregated error now
+  lists each bad tool with the per-tool reason, and a class-name miss logs
+  a `Did you mean '<Closest>'?` hint. A constructor exception on one tool
+  is caught per-tool so the user gets one clear error instead of a
+  traceback. Rebuild the binary (`make build-bin`) if the new error names
+  a tool that exists in the working tree.
+- **Auto-chain `implementer` → `judge` for non-trivial scoped edits.** The new
+  `ImplementAndJudge` tool runs `implementer` once, hands the artifact to
+  `judge`, and on `NEEDS_WORK` re-invokes `implementer` once with the
+  judge's `REQUIRED FIXES` under a `## Revision brief` section before
+  re-judging. Two implementer invocations is the hard cap — a
+  still-`NEEDS_WORK` after revision surfaces the contradiction and stops.
+  Parent agents should call `ImplementAndJudge` instead of `Agent:
+  implementer` + `Agent: judge`; bare `judge` calls remain the right shape
+  for non-implementation reviews (reports, audits, severity-scored
+  findings).
+- **Judge adopts the minimum-diff rubric dimension.** Every non-trivial diff
+  the judge reviews is now checked against the reduction ladder
+  (skip-need → reuse-stdlib → use-native → use-installed-dep → one-line →
+  minimum) and the minimum-diff rubric (no abstractions, no new deps
+  without justification, no new config keys without a consumer, no
+  reformatting churn outside the changed lines). The judge applies the full
+  ladder uniformly — there is no mode switch on the judge.
+- **Bundled judge-branded skills.** `judge-minimum-diff` (the rubric
+  applied as a judge dimension) and `judge-overengineering-review` (the
+  parent-facing review checklist) ship as static default skills, replacing
+  ad-hoc prose in the system prompt with explicit, versionable content.
+- **Fix OpenAI Responses requests that could still send `role="system"` after
+  switching to a newer Pythinker catalog model (gpt-5.5, gpt-5.3-codex,
+  gpt-5.3-codex-spark, or any user-defined fine-tune).** Pythinker observed
+  OpenAI returning `System messages are not allowed` on this path, but the
+  `system→developer` conversion was previously gated on the openai SDK's
+  `ResponsesModel` literal, which lags Pythinker's own model catalog. The
+  conversion now runs unconditionally in `OpenAIResponses`, so all local
+  system messages are normalized before sending. Also fixes the model-switch
+  carry-over path (`_carry_context_to_session`) whose seeded `role="system"`
+  summary message was sent verbatim on the first request after a switch.
+- **Background bash tasks (npm dev, docker run) no longer show the agent
+  verb spinner.** Pure-bash background work now shows a fixed "Running in
+  background…" label instead of "Composing…/Brewing…" verbs, which read as
+  agent activity. Mixed bash+agent background work keeps the verb spinner
+  while the agent is actively producing tokens.
+- **Quiet background tasks no longer force a 0.1s prompt repaint.** When a
+  background task has produced no output for 2 seconds, the refresh loop
+  drops to the idle 1.0s interval instead of spinning the braille marker at
+  12.5 fps — fixing the "stuck spinner" look for long-running dev servers
+  on Windows VS Code.
+- **Welcome banner no longer shows a stale "Update available" chip after a
+  successful /update.** The banner chip now mirrors the under-input notice:
+  when the update has landed this session (state=UPDATED, smoke check passed),
+  it shows "Updated X → vY. Restart to apply." instead of telling the user
+  to re-run an update that already completed.
+
+## 0.51.0 (2026-06-22)
+
+- **Reasoning levels now match each GPT model.** The thinking selector and
+  Shift+Tab cycle scope reasoning effort to what the active OpenAI GPT-5-family
+  model actually accepts — e.g. gpt-5.4/gpt-5.5 no longer offer `minimal`
+  (which they reject) and keep `xhigh`, while gpt-5.0 keeps `minimal`. A
+  persisted unsupported level is clamped to the nearest supported one before
+  it is sent, so the API never rejects it.
+- **Diff cards no longer show a "blue overlay".** The syntax highlighter no
+  longer paints the code theme's opaque background (e.g. catppuccin `#1E1E2E`)
+  onto diff lines, so the green/red row tints — and the terminal background on
+  context lines — show through on every terminal. Previously that code-theme
+  block masked the row tints and only blended where the terminal background
+  happened to match it.
+- **VS Code-family terminals are detected as truecolor.** `color_depth()` now
+  promotes integrated terminals reporting `TERM_PROGRAM=vscode` (including forks
+  built on it) to truecolor — like the existing Windows Terminal promotion — so
+  diff tints don't fall back to the colorless 16-color path when the terminal
+  doesn't advertise `COLORTERM`.
+- **Model/theme switches no longer reprint the welcome banner.** A same-session
+  reload (`/model`, `/theme`, `/thinking`, `/new`, fork, …) now keeps the
+  existing banner and shows only its own "Switched to… / Reloading…"
+  confirmation, instead of stacking a redundant second welcome splash below it.
+  `/clear` and `/reload` still wipe the screen and reprint the banner.
+- **Update notice no longer crowds the prompt.** The persistent "Restart to apply"
+  / "Update available" line now renders as the last footer row — below the
+  status/clock line — instead of directly under the input box, keeping the input
+  area clear.
+- **Homebrew self-upgrades no longer risk the live session.** The updater now runs
+  `brew upgrade` with `HOMEBREW_NO_INSTALL_CLEANUP` and `HOMEBREW_NO_AUTO_UPDATE`,
+  so brew can't delete the in-use Cellar version mid-session; the new build is
+  staged side-by-side and goes live on restart.
+
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.51.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
+
 ## 0.50.0 (2026-06-20)
 
 - **Silent native updates no longer crash a running session.** The downloaded

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/agents/default/agent.yaml

@@ -7,6 +7,7 @@ agent:
   tools:
     - "pythinker_code.tools.agent:Agent"
     - "pythinker_code.tools.agent:RunAgents"
+    - "pythinker_code.tools.agent:ImplementAndJudge"
     - "pythinker_code.tools.skill:ReadSkill"
     # - "pythinker_code.tools.dmail:SendDMail"
     # - "pythinker_code.tools.think:Think"

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/agents/default/judge.yaml

@@ -18,6 +18,7 @@ agent:
 
       ## Context Gate
       - Require the parent's packet: the original request, the diff or changed files, the commands actually run with their results, residual risks, and the draft final answer. If a load-bearing piece is missing, verdict BLOCKED and name it.
+      - When judging a code-change summary produced by `implementer`, require the implementer's `<coding_artifact>` block in the packet; if it is missing for a non-trivial code change, verdict BLOCKED and name it.
 
       ## External Claims (offline gate)
       You run offline by design — the verify profile blocks network and doc-lookup tools, so you never go online. External claims are judged by the parent's evidence, never by your own research or training-cutoff memory:
@@ -39,6 +40,7 @@ agent:
       - Safety and scope: no unsafe or destructive action, no secret or PII exposure, no scope creep beyond the request.
       - Production guardrails: changed code that touches caches, resources, trust boundaries, shared state, outbound requests, long-lived listeners, or authorization context has explicit defenses for stampedes, cleanup, schemas, races, retry storms, leaks, and IDOR risks.
       - Findings quality: for reports, each finding is actionable, anchored to evidence, and severity-ranked consistently with the base prompt's severity rubric (critical/high/medium/low/info).
+      - Minimum-diff: the diff takes the smallest rung of the reduction ladder (skip-need → reuse-stdlib → use-native → use-installed-dep → one-line → minimum) before adding new code; no abstractions, dependencies, config keys, files, or error paths that the brief did not ask for. New dependencies require a one-line justification; new config keys require a one-line consumer. The ladder applies uniformly — judge once, not per-mode.
 
       ## Role Exit Checklist
       - PASS: sound; at most minor wording nits remain.

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/agents/default/system.md

@@ -97,6 +97,8 @@ Build only after requirements are understood (ask if unclear) and evidence is ga
 
 For refactors, update every call site the interface change touches, and do not alter existing logic — especially in tests — beyond what the change requires. For features, add tests if the project already has tests. Migrations go additive before destructive, reversible where the framework allows; never edit a migration that already shipped. Identify the synchronization model in use and conform to it; explicitly flag any new lock, atomic, or async-boundary change. Update comments, docstrings, and README snippets your change makes false — stale documentation is a bug you just wrote.
 
+**Default to `ImplementAndJudge` for non-trivial scoped edits** instead of calling `implementer` and `judge` separately. The chain runs `implementer` first, hands the artifact to `judge`, and on `NEEDS_WORK` re-invokes `implementer` once with the judge's `REQUIRED FIXES` under a `## Revision brief` section before re-judging. The implementer cap is two invocations total — a still-`NEEDS_WORK` after revision surfaces the contradiction to you and stops. Pass `scope` so the judge can `git diff` only the allowed paths; pass `acceptance` to give the judge concrete pass conditions beyond the rubric.
+
 ### 4.5 Research & file generation
 
 For research or multimedia tasks (images, video, PDFs, docs, spreadsheets, presentations): clarify requirements first, plan before deep or wide research, design search queries deliberately. Detect tools already in the environment before installing anything; third-party installs go in an isolated/virtual environment. After generating or editing any media file, read it back to confirm the content. Never install to or delete from outside the working directory without confirmation.
@@ -121,6 +123,8 @@ For research or multimedia tasks (images, video, PDFs, docs, spreadsheets, prese
 
 **Judge gate.** Before delivering high-stakes or hard-to-reverse work, run an independent `judge` subagent as the last step when available. Triggers — any one suffices: a change spanning multiple files or touching production guardrail surfaces (§6); a deliverable the user will merge, deploy, publish, or act on; a security audit or any severity-scored findings report; a release or destructive action. When unsure whether work is high-stakes, treat it as high-stakes; skip it for low-stakes, reversible, or trivial work. Hand the judge a tight packet: original request, the diff or changed files, the commands actually run with their results, residual risks, and your draft answer. It is one cheap spot-checking pass that gates your evidence — it does not redo work or replace deterministic tests and lint, so run those first. Treat `NEEDS_WORK` or `BLOCKED` as a stop: fix or revise, re-judge only if the change was material. When the judge is unavailable, walk the same checklist yourself, lead with the same `PASS`/`NEEDS_WORK`/`BLOCKED` verdict, state what verification actually ran, and put any missing packet element under **BLOCKERS**.
 
+Default to `ImplementAndJudge` for non-trivial scoped edits (see §4.4); reserve a bare `judge` call for non-implementation reviews — reports, audits, severity-scored findings, or answers that don't ship code.
+
 **Background shell** (root agent only). Launch long-running commands via `Shell` with `run_in_background=true` and a short `description`; the system notifies you at terminal states. `TaskList` re-enumerates active tasks (especially after context compaction); `TaskOutput` gives non-blocking snapshots (`block=true` only to intentionally wait); `TaskStop` cancels. After starting a background task, default to returning control to the user. The only task-management slash command for users is `/task` — never invent subcommands like `/task list` or `/tasks`. Subagents and sessions without these tools must not assume background-task control.
 
 **Skills (`ReadSkill`).** Load a skill's exact instructions before applying its workflow — mandatory for `review-pr`, `diagnose-ci-failures`, `fix-errors`, `implement-specs`, `spec-driven-implementation`, `check-impl-against-spec`, `resolve-merge-conflicts`, and `create-pr`. Read skill details only when needed, to conserve context. Catalog and scope precedence in §12.

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/app.py

@@ -832,7 +832,11 @@ class PythinkerCLI:
                         await external_cancel_task
 
     async def run_shell(
-        self, command: str | None = None, *, prefill_text: str | None = None
+        self,
+        command: str | None = None,
+        *,
+        prefill_text: str | None = None,
+        suppress_banner: bool = False,
     ) -> bool:
         """Run the Pythinker CLI instance with shell UI."""
         from pythinker_code.ui.shell import Shell, WelcomeInfoItem
@@ -953,7 +957,12 @@ class PythinkerCLI:
             )
         )
         async with self._env():
-            shell = Shell(self._soul, welcome_info=welcome_info, prefill_text=prefill_text)
+            shell = Shell(
+                self._soul,
+                welcome_info=welcome_info,
+                prefill_text=prefill_text,
+                suppress_banner=suppress_banner,
+            )
             return await shell.run(command)
 
     async def run_print(

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/cli/__init__.py

@@ -862,7 +862,12 @@ def pythinker(
     # exception handler can clean it up even when _run() fails before returning.
     _latest_created_session: Session | None = None
 
-    async def _run(session_id: str | None, prefill_text: str | None = None) -> tuple[Session, int]:
+    async def _run(
+        session_id: str | None,
+        prefill_text: str | None = None,
+        *,
+        suppress_banner: bool = False,
+    ) -> tuple[Session, int]:
         """
         Create/load session and run the CLI instance.
 
@@ -1056,7 +1061,11 @@ def pythinker(
             try:
                 match ui:
                     case "shell":
-                        shell_ok = await instance.run_shell(prompt, prefill_text=prefill_text)
+                        shell_ok = await instance.run_shell(
+                            prompt,
+                            prefill_text=prefill_text,
+                            suppress_banner=suppress_banner,
+                        )
                         exit_code = ExitCode.SUCCESS if shell_ok else ExitCode.FAILURE
                     case "print":
                         exit_code = await instance.run_print(
@@ -1190,10 +1199,15 @@ def pythinker(
         """
         last_session: Session | None = None
         prefill_text: str | None = None
+        suppress_banner = False
         try:
             while True:
                 try:
-                    last_session, exit_code = await _run(session_id, prefill_text=prefill_text)
+                    last_session, exit_code = await _run(
+                        session_id,
+                        prefill_text=prefill_text,
+                        suppress_banner=suppress_banner,
+                    )
                     break
                 except Reload as e:
                     if e.clear_screen:
@@ -1220,6 +1234,10 @@ def pythinker(
                             _print_resume_hint(old)
                     session_id = e.session_id
                     prefill_text = e.prefill_text
+                    # A non-clearing reload (/model, /theme, /new, fork, …) leaves
+                    # the previous banner on screen, so skip reprinting the splash.
+                    # /clear and /reload wiped the screen above and want it back.
+                    suppress_banner = not e.clear_screen
                     continue
                 except SwitchToWeb as e:
                     # The web worker subprocess becomes the session's writer.

{pythinker_code-0.50.0 → pythinker_code-0.52.0}/src/pythinker_code/llm.py

@@ -3,6 +3,8 @@ from __future__ import annotations
 import contextlib
 import json
 import os
+import re
+from collections.abc import Collection
 from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Literal, cast, get_args
@@ -12,7 +14,9 @@ from pythinker_core.chat_provider import ChatProvider, ThinkingEffort
 from pythinker_code.constant import USER_AGENT
 from pythinker_code.thinking import (
     DEFAULT_THINKING_EFFORT,
+    available_thinking_levels,
     bool_to_thinking_effort,
+    clamp_thinking_effort,
     normalize_thinking_effort,
     thinking_effort_enabled,
 )
@@ -457,7 +461,15 @@ def create_llm(
             else DEFAULT_THINKING_EFFORT
         )
     elif supports_thinking:
-        effective_effort = requested_effort
+        # Clamp to the model's actually-supported levels so a persisted effort
+        # the model rejects (e.g. ``minimal`` on gpt-5.4/5.5) is never sent.
+        effective_effort = (
+            clamp_thinking_effort(
+                requested_effort, available_model_thinking_levels(model, capabilities)
+            )
+            if requested_effort is not None
+            else None
+        )
     else:
         # Clamp to the model's supported levels: non-reasoning models have
         # only the off level, so explicit non-off requests become off instead of
@@ -594,6 +606,55 @@ def derive_model_capabilities(model: LLMModel) -> set[ModelCapability]:
     return capabilities
 
 
+_GPT5_REASONING_RE = re.compile(r"gpt-5(?:\.(\d+))?", re.IGNORECASE)
+
+
+def openai_gpt_reasoning_levels(model_id: str) -> tuple[ThinkingEffort, ...] | None:
+    """Reasoning-effort levels an OpenAI GPT-5-family model actually accepts.
+
+    OpenAI's ``reasoning_effort`` set is model-dependent and has drifted across
+    the GPT-5 line, so the provider-neutral ladder over-offers levels a given
+    model rejects (e.g. ``minimal`` on gpt-5.4/5.5). Returns the supported
+    levels low->high including ``off`` (OpenAI ``none``), or ``None`` when
+    *model_id* is not a recognized GPT-5 reasoning model.
+
+    Matrix (OpenAI docs):
+
+    * ``5.0``                  -> minimal, low, medium, high
+    * ``5.1`` / ``5.2`` / ``5.3`` -> low, medium, high (``minimal`` replaced by ``none``)
+    * ``5.1-codex-max``, ``5.4+`` -> low, medium, high, xhigh (``minimal`` dropped)
+    """
+    match = _GPT5_REASONING_RE.search(model_id)
+    if match is None:
+        return None
+    minor = int(match.group(1)) if match.group(1) else 0
+    if minor == 0:
+        return ("off", "minimal", "low", "medium", "high")
+    if minor >= 4 or "codex-max" in model_id.lower():
+        return ("off", "low", "medium", "high", "xhigh")
+    return ("off", "low", "medium", "high")
+
+
+def available_model_thinking_levels(
+    model: LLMModel, capabilities: Collection[str] | None
+) -> tuple[ThinkingEffort, ...]:
+    """Selectable thinking levels for *model*, scoped to provider-specific support.
+
+    Starts from the capability-derived ladder, then narrows to a provider's
+    actually-accepted set when known (currently the OpenAI GPT-5 family) so the
+    selector never offers — and :func:`create_llm` never sends — a level the
+    model rejects. Falls back to the full ladder for models without a known
+    per-model rule.
+    """
+    base = available_thinking_levels(capabilities)
+    gpt_levels = openai_gpt_reasoning_levels(model.model)
+    if gpt_levels is None:
+        return base
+    allowed = set(gpt_levels)
+    scoped: tuple[ThinkingEffort, ...] = tuple(level for level in base if level in allowed)
+    return scoped or base
+
+
 def _is_kimi_k2_model(model_name: str) -> bool:
     return "kimi-k2" in model_name.lower().replace("_", "-")