pythinker-code 0.51.0__tar.gz → 0.53.0__tar.gz

{pythinker_code-0.51.0 → pythinker_code-0.53.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythinker-code
-Version: 0.51.0
+Version: 0.53.0
 Summary: Pythinker — an agentic CLI developed by Pythoughts-labs.
 Keywords: cli,agent,ai,coding-assistant,llm,claude,openai,terminal
 Author: Pythoughts-labs
@@ -115,16 +115,12 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.51.0
+## 🆕 What's New in 0.53.0
 
-- **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.
+- **GPT/ChatGPT re-auth crash fixed.** A "Could not resolve authentication method" crash when a session token is invalidated mid-session (OAuth refresh rotated on another machine) now routes into the standard `/login` re-authentication path instead of dumping a traceback.
+- **Cleaner `ImplementAndJudge` label in the TUI.** The chain now shows `Implement & Judge — <brief>` instead of the raw `ImplementAndJudge(4 args: …)` argument dump.
 
-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).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.53.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -214,7 +210,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.51.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.53.0.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 |
@@ -242,7 +238,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.51.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.53.0.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.**
@@ -253,13 +249,13 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.51.0.exe
+.\PythinkerSetup-0.53.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.51.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.53.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -317,26 +313,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.51.0_amd64.deb
+sudo dpkg -i pythinker-code_0.53.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.51.0_arm64.deb
+sudo dpkg -i pythinker-code_0.53.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.51.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.53.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.51.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.53.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.51.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.53.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.51.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.51.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.53.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.53.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -345,8 +341,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.51.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.51.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.53.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.53.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /

{pythinker_code-0.51.0 → pythinker_code-0.53.0}/README.md

@@ -50,16 +50,12 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.51.0
+## 🆕 What's New in 0.53.0
 
-- **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.
+- **GPT/ChatGPT re-auth crash fixed.** A "Could not resolve authentication method" crash when a session token is invalidated mid-session (OAuth refresh rotated on another machine) now routes into the standard `/login` re-authentication path instead of dumping a traceback.
+- **Cleaner `ImplementAndJudge` label in the TUI.** The chain now shows `Implement & Judge — <brief>` instead of the raw `ImplementAndJudge(4 args: …)` argument dump.
 
-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).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.53.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -149,7 +145,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.51.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.53.0.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 |
@@ -177,7 +173,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.51.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.53.0.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.**
@@ -188,13 +184,13 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.51.0.exe
+.\PythinkerSetup-0.53.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.51.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.53.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -252,26 +248,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.51.0_amd64.deb
+sudo dpkg -i pythinker-code_0.53.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.51.0_arm64.deb
+sudo dpkg -i pythinker-code_0.53.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.51.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.53.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.51.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.53.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.51.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.53.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.51.0/pythinker-code-0.51.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.51.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.51.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.53.0/pythinker-code-0.53.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.53.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.53.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -280,8 +276,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.51.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.51.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.53.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.53.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /

{pythinker_code-0.51.0 → pythinker_code-0.53.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythinker-code"
-version = "0.51.0"
+version = "0.53.0"
 description = "Pythinker — an agentic CLI developed by Pythoughts-labs."
 readme = "README.md"
 requires-python = ">=3.12"

{pythinker_code-0.51.0 → pythinker_code-0.53.0}/src/pythinker_code/CHANGELOG.md

@@ -15,6 +15,77 @@ GitHub Releases page; `0.8.0` is the new starting line.
 
 ## Unreleased
 
+## 0.53.0 (2026-06-23)
+
+- **GPT/ChatGPT session re-authentication crash fixed.** A fatal "Could not
+  resolve authentication method" error when a session token is invalidated
+  mid-session (e.g. the OAuth refresh token was rotated by signing in on
+  another machine) now surfaces as a typed 401 that routes into the standard
+  re-authentication path — prompting `/login` rather than dumping a traceback.
+- **`ImplementAndJudge` renders as `Implement & Judge — <brief>` in the TUI.**
+  The chain no longer shows the raw `ImplementAndJudge(4 args: …)` argument
+  dump; it now displays a clean `Implement & Judge — <brief>` label matching
+  the style of other named subagent invocations.
+
+## 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

{pythinker_code-0.51.0 → pythinker_code-0.53.0}/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-0.51.0 → pythinker_code-0.53.0}/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-0.51.0 → pythinker_code-0.53.0}/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-0.53.0/src/pythinker_code/skills/judge-minimum-diff/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: judge-minimum-diff
+description: Reduction-ladder and minimum-diff checks the Pythinker judge subagent applies to every non-trivial diff.
+---
+
+# Judge Minimum-Diff Lens
+
+Use when judging a code change, diff, or implementation report. This is the
+rubric dimension the Pythinker judge subagent applies to every non-trivial
+diff — the same ladder that lives in the base system prompt's §6 (Code
+Standards), surfaced here as an explicit rubric so the judge, an
+implementer doing pre-flight, or a reviewer running the over-engineering
+skill apply it uniformly.
+
+The judge applies the full ladder. There is no mode switch on the judge
+(`lite` / `full` / `ultra`); the implementer is the role that would carry a
+mode toggle if one is ever introduced.
+
+## The ladder — walk it before writing code; stop at the first rung that holds
+
+1. **Does this need to exist at all?** A speculative need is skipped, said so
+   in one line. YAGNI is the highest rung.
+2. **Does the standard library do it?** Use it.
+3. **Does a native platform or framework feature cover it?** A database
+   constraint over an app-level check, a built-in form control over a picker
+   library, the language's own construct over a hand-rolled one — use it.
+4. **Does a dependency already in the manifest solve it?** Use it; never add
+   a new dependency for what a few lines cover.
+5. **Can it be one line?** Make it one line.
+6. **Only then** write the minimum code that works.
+
+When two rungs both hold, take the higher one and move on. The ladder is a
+reflex, not a research project. None of this overrides the guards below:
+trust-boundary validation, error handling that prevents data loss, security,
+and accessibility stay in even at rung 5.
+
+## Minimum-diff rubric
+
+A diff passes the minimum-diff check when **all** of these hold:
+
+- The change takes the smallest rung of the ladder above before adding new
+  code.
+- There are **no abstractions** (no interface with one implementation, no
+  factory for one product, no config layer for a value that never changes)
+  that the brief did not ask for.
+- There are **no new dependencies** unless the brief asked for one; when one
+  is added, a one-line justification names why an already-installed
+  dependency or the standard library couldn't cover it.
+- There are **no new config keys** unless a consumer is named in the same
+  diff (a value with no consumer is over-engineering).
+- There are **no new files** unless the brief asked for them; reuse the
+  nearest neighbor's module.
+- There are **no error paths for impossible scenarios**; validate at
+  boundaries, not deep in business logic.
+- There is **no reformatting, renaming, or wrapping churn** outside the
+  changed lines. Formatting churn is scope creep.
+- **Comments only where they earn their keep**: non-obvious algorithms,
+  deliberate simplifications whose ceiling matters, business rules, or
+  genuine `TODO:` technical debt. No self-evident comments.
+
+When a deliberate simplification has a known ceiling (a coarse lock, an
+O(n²) scan, a naive heuristic), mark it with a `judge:` comment naming the
+ceiling and the upgrade path. The judge reads these comments as evidence,
+not as license.
+
+## When NOT to be lazy
+
+Never simplify away:
+
+- Input validation at trust boundaries.
+- Error handling that prevents data loss (rollback, idempotency, atomic
+  state, listener cleanup).
+- Security measures (parameterized SQL, canonicalized paths, encoded output,
+  hand-off-crypto, secret hygiene).
+- Accessibility basics (semantic HTML, alt text, focus order, keyboard
+  reachability, contrast).
+- Anything the user explicitly requested.
+
+A junior-friendly check: would a senior engineer call this over-engineered?
+If yes, simplify. If no, the diff is at the right rung.
+
+## How the judge applies this rubric
+
+When the judge receives an `implementer` packet:
+
+- **Evidence**: the implementer's `<coding_artifact>` block is the
+  implementer's claim; the judge verifies it against the diff.
+- **Currency / Fidelity / Verification / Safety / Scope / Production
+  guardrails / Findings quality**: per the standard judge rubric in the base
+  prompt.
+- **Minimum-diff** (this rubric): the judge checks every bullet under
+  *Minimum-diff rubric* above. A NEEDS_WORK verdict is required when the
+  diff adds any of the over-engineering shapes, even if the change works.
+
+The verdict contract is unchanged: `PASS` / `NEEDS_WORK` / `BLOCKED` as the
+first word of SUMMARY. The chain tool parses the verdict verbatim and
+optionally re-invokes the implementer once on `NEEDS_WORK`.
+
+## Hardware and physical-world caveat
+
+Hardware is never the ideal on paper: a real clock drifts, a real sensor
+reads off, a PCA9685 runs a few percent fast. Leave the calibration knob,
+not just less code. The physical world needs tuning a minimal model can't
+see.

pythinker_code-0.53.0/src/pythinker_code/skills/judge-overengineering-review/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: judge-overengineering-review
+description: Over-engineering review checklist the parent runs before declaring non-trivial code changes done.
+---
+
+# Judge Over-Engineering Review
+
+Use when reviewing a non-trivial diff for over-engineering before declaring
+the work done. This skill is the parent-facing companion to the
+`judge-minimum-diff` rubric — the parent runs it as a pre-flight pass, and
+the `judge` subagent applies the same rubric as a quality-gate dimension.
+
+## When to run
+
+- Before declaring any non-trivial code change complete.
+- During code review of a pull request that touches more than one file or
+  introduces new abstractions.
+- When a previous implementer or coder's diff feels heavier than the
+  brief required.
+
+For trivial one-line fixes or pure typo corrections, skip this skill —
+YAGNI applies to review overhead too.
+
+## Workflow
+
+1. **Read the brief** the implementer was given. Note the explicit asks and
+   the explicit non-goals.
+2. **Read the diff** scoped to the allowed paths. Note every new file, new
+   abstraction, new dependency, and new config key.
+3. **Walk the reduction ladder** from `judge-minimum-diff`:
+
+   - Did the diff take the highest rung that holds?
+   - Is there stdlib / native / installed-dep reuse the diff missed?
+   - Could the change be one line and isn't?
+
+4. **Score each finding** under the rubric below.
+5. **Report** in the parent-facing review block format: `path:line` for
+   every finding, severity per §4.1 of the base prompt, the suggested
+   smallest fix.
+
+## Review checklist
+
+A diff fails the over-engineering review when it has **any** of:
+
+- **Speculative abstraction.** Interface with one implementation, factory
+  for one product, abstract base class with one subclass, config layer for
+  a value that never varies.
+- **New dependency without justification.** The standard library, a
+  native platform feature, or an already-installed dependency could have
+  covered it. A new dep needs a one-line justification in the diff or PR
+  body.
+- **New config key without a consumer in the same diff.** A new key with no
+  reader is dead configuration.
+- **New file without brief backing.** A new module/folder the brief did not
+  ask for, even if "tidier". Reuse the nearest neighbor first.
+- **Error handling for impossible scenarios.** Validating deep in business
+  logic for inputs the boundary already filtered; re-validating after a
+  function the caller controls.
+- **Boilerplate scaffolding "for later".** TODOs that fill a stub, fixtures
+  the test doesn't use, helper modules with no callers yet.
+- **Formatting churn outside the changed lines.** Reformat, rename, or
+  rewrap on lines the brief did not ask to change.
+- **Self-evident comments.** Restating what the next line of code already
+  says. Comments only earn their keep when they document non-obvious
+  algorithms, deliberate simplifications with a known ceiling, business
+  rules, or genuine `TODO:` debt.
+- **Clever over boring.** Clever is what someone decodes at 3am. Boring is
+  the default; clever needs justification.
+- **Length-as-quality.** A 500-line diff to replace a 50-line problem is a
+  finding, not an accomplishment.
+
+A diff **passes** when none of the above apply, every non-trivial design
+choice has a one-line reason in the diff or PR body, and the deliberate
+simplifications (if any) carry a `judge:` comment naming the ceiling.
+
+## When NOT to flag
+
+- **Trust-boundary validation.** Always keep — never call this
+  over-engineering.
+- **Error handling that prevents data loss** (rollback, idempotency,
+  atomic state, listener cleanup). Always keep.
+- **Security measures** (parameterized SQL, canonicalized paths, encoded
+  output, secret hygiene). Always keep.
+- **Accessibility basics**. Always keep.
+- **User-explicit asks.** If the brief says "add a factory", add the
+  factory. Don't second-guess explicit requirements.
+
+## Output
+
+A parent-facing review block:
+
+```text
+SUMMARY
+OVER-ENGINEERING FINDINGS
+- severity: path:line — what + why + smallest fix
+NOT OVER-ENGINEERED (deliberate)
+- path:line — why this is at the right rung
+VERDICT
+PASS | NEEDS_WORK | BLOCKED
+```
+
+`PASS` = diff is at the right rung; ship it. `NEEDS_WORK` = at least one
+finding above applies; revise and re-review. `BLOCKED` = the brief and the
+diff disagree about scope; clarify with the user before continuing.