pythinker-code 0.56.0__tar.gz → 0.58.0__tar.gz

{pythinker_code-0.56.0 → pythinker_code-0.58.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythinker-code
-Version: 0.56.0
+Version: 0.58.0
 Summary: Pythinker — an agentic CLI developed by Pythoughts-labs.
 Keywords: cli,agent,ai,coding-assistant,llm,claude,openai,terminal
 Author: Pythoughts-labs
@@ -115,13 +115,13 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.56.0
+## 🆕 What's New in 0.58.0
 
-- **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.
-- **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.
-- **Stale update-success notice cleared after downgrading.** Restarting into an older Homebrew install no longer leaves a permanent "Restart to apply" banner.
+- **Agent core deepened with an observable request-assembly path.** Provider handoff, prompt ordering, and context persistence now run through explicit compatibility contracts, conversation history updates are transactional (atomic replacement with cancellation and rollback), and agent/skill definitions resolve through one source-aware catalogue instead of scattered lookups.
+- **Agent-spec loading is more defensive and truthful.** Subagent `path`, `extend`, and `system_prompt_path` references that resolve outside their spec's directory are now rejected instead of loaded, and malformed frontmatter parsing errors are no longer misreported as harmless skips.
+- **Thinking and subagent activity render cleanly in the terminal.** Live reasoning previews render complete Markdown without exposing stray HTML comments, and activity-tree rows stay visually stable during long-running turns.
 
-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).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.58.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -191,6 +191,22 @@ Optional web frontend and visualization frontend ship alongside the CLI for rich
 
 Swap providers and models per-session: `--model openai/gpt-5.5`, hosted Pythinker models, or your own keys.
 
+</td>
+</tr>
+<tr>
+<td width="50%" valign="top">
+
+### 📊 Local Benchmarks
+
+Run `/benchmark` to execute deterministic local coding tasks through the active Pythinker session, with replayable artifacts and verification reports.
+
+</td>
+<td width="50%" valign="top">
+
+### 🧪 SWE-Style Fixtures
+
+Run trusted local JSONL fixtures with `/benchmark:swe --dataset <path> --trusted-dataset true` when you want SWE-style task inputs without a hosted evaluator.
+
 </td>
 </tr>
 </table>
@@ -211,7 +227,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.56.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.58.0.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 |
@@ -239,10 +255,11 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.56.0.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.**
+`PythinkerSetup-0.58.0.exe` is an Inno Setup wizard. Release builds are signed
+when Authenticode secrets are configured in CI; otherwise the installer ships
+unsigned. 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.**
 
 ```powershell
 # One-line install (downloads the native .exe, verifies SHA-256, runs per-user)
@@ -250,24 +267,24 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.56.0.exe
+.\PythinkerSetup-0.58.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.56.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.58.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
-the newest installer, verifies SHA-256, and launches the signed Inno installer
+the newest installer, verifies SHA-256, and launches the Inno installer
 with visible progress (`/SILENT /NORESTART /CURRENTUSER /CLOSEAPPLICATIONS /NORESTARTAPPLICATIONS`).
 
 **Uninstall:** Apps & Features → *Pythinker Code* → Uninstall reverts both
 the files and the PATH edit.
 
-> 🛡 **First-launch SmartScreen warning** — \*until the Authenticode cert is
-> provisioned in CI, the installer ships unsigned and Windows shows
+> 🛡 **First-launch SmartScreen warning** — Until Authenticode secrets are
+> configured in CI for a release, the installer ships unsigned and Windows shows
 > *"Windows protected your PC."* Click **More info → Run anyway**. Use the
 > published `.sha256` as your integrity check until signing comes online.
 
@@ -314,26 +331,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.56.0_amd64.deb
+sudo dpkg -i pythinker-code_0.58.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.56.0_arm64.deb
+sudo dpkg -i pythinker-code_0.58.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.58.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.56.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.58.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.56.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.58.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.56.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.56.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.58.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.58.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -342,8 +359,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.56.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.58.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.58.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /
@@ -683,6 +700,7 @@ Pythinker is a small, extensible runtime — not a monolith. Build on it.
 | 🌊 **Flows** | `/flow:<name>` executes bundled prompt flows | bundled & user-defined |
 | 🪝 **Hooks** | Observe or block tool execution; integrate policy or automation | hook events API |
 | 🧩 **Plugins** | Installable extension packages | `pythinker plugin` |
+| 📊 **Benchmarks** | Deterministic local coding tasks with verification reports | `/benchmark`, `src/pythinker_code/benchmark/` |
 
 ---
 

{pythinker_code-0.56.0 → pythinker_code-0.58.0}/README.md

@@ -50,13 +50,13 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.56.0
+## 🆕 What's New in 0.58.0
 
-- **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.
-- **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.
-- **Stale update-success notice cleared after downgrading.** Restarting into an older Homebrew install no longer leaves a permanent "Restart to apply" banner.
+- **Agent core deepened with an observable request-assembly path.** Provider handoff, prompt ordering, and context persistence now run through explicit compatibility contracts, conversation history updates are transactional (atomic replacement with cancellation and rollback), and agent/skill definitions resolve through one source-aware catalogue instead of scattered lookups.
+- **Agent-spec loading is more defensive and truthful.** Subagent `path`, `extend`, and `system_prompt_path` references that resolve outside their spec's directory are now rejected instead of loaded, and malformed frontmatter parsing errors are no longer misreported as harmless skips.
+- **Thinking and subagent activity render cleanly in the terminal.** Live reasoning previews render complete Markdown without exposing stray HTML comments, and activity-tree rows stay visually stable during long-running turns.
 
-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).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.58.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
 
 
 ---
@@ -126,6 +126,22 @@ Optional web frontend and visualization frontend ship alongside the CLI for rich
 
 Swap providers and models per-session: `--model openai/gpt-5.5`, hosted Pythinker models, or your own keys.
 
+</td>
+</tr>
+<tr>
+<td width="50%" valign="top">
+
+### 📊 Local Benchmarks
+
+Run `/benchmark` to execute deterministic local coding tasks through the active Pythinker session, with replayable artifacts and verification reports.
+
+</td>
+<td width="50%" valign="top">
+
+### 🧪 SWE-Style Fixtures
+
+Run trusted local JSONL fixtures with `/benchmark:swe --dataset <path> --trusted-dataset true` when you want SWE-style task inputs without a hosted evaluator.
+
 </td>
 </tr>
 </table>
@@ -146,7 +162,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.56.0.exe` from [Releases](https://github.com/Pythoughts-labs/pythinker-code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.58.0.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 |
@@ -174,10 +190,11 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.56.0.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.**
+`PythinkerSetup-0.58.0.exe` is an Inno Setup wizard. Release builds are signed
+when Authenticode secrets are configured in CI; otherwise the installer ships
+unsigned. 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.**
 
 ```powershell
 # One-line install (downloads the native .exe, verifies SHA-256, runs per-user)
@@ -185,24 +202,24 @@ irm https://pythinker.com/install.ps1 | iex
 
 # Or manually download the installer + checksum from the Releases page,
 # verify with Get-FileHash, then run:
-.\PythinkerSetup-0.56.0.exe
+.\PythinkerSetup-0.58.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.56.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.58.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
-the newest installer, verifies SHA-256, and launches the signed Inno installer
+the newest installer, verifies SHA-256, and launches the Inno installer
 with visible progress (`/SILENT /NORESTART /CURRENTUSER /CLOSEAPPLICATIONS /NORESTARTAPPLICATIONS`).
 
 **Uninstall:** Apps & Features → *Pythinker Code* → Uninstall reverts both
 the files and the PATH edit.
 
-> 🛡 **First-launch SmartScreen warning** — \*until the Authenticode cert is
-> provisioned in CI, the installer ships unsigned and Windows shows
+> 🛡 **First-launch SmartScreen warning** — Until Authenticode secrets are
+> configured in CI for a release, the installer ships unsigned and Windows shows
 > *"Windows protected your PC."* Click **More info → Run anyway**. Use the
 > published `.sha256` as your integrity check until signing comes online.
 
@@ -249,26 +266,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.56.0_amd64.deb
+sudo dpkg -i pythinker-code_0.58.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.56.0_arm64.deb
+sudo dpkg -i pythinker-code_0.58.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.x86_64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.58.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.56.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.58.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.56.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.58.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm
-curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.56.0/pythinker-code-0.56.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.56.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.56.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.aarch64.rpm
+curl -LO https://github.com/Pythoughts-labs/pythinker-code/releases/download/v0.58.0/pythinker-code-0.58.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.58.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.58.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -277,8 +294,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.56.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.56.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.58.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.58.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /
@@ -618,6 +635,7 @@ Pythinker is a small, extensible runtime — not a monolith. Build on it.
 | 🌊 **Flows** | `/flow:<name>` executes bundled prompt flows | bundled & user-defined |
 | 🪝 **Hooks** | Observe or block tool execution; integrate policy or automation | hook events API |
 | 🧩 **Plugins** | Installable extension packages | `pythinker plugin` |
+| 📊 **Benchmarks** | Deterministic local coding tasks with verification reports | `/benchmark`, `src/pythinker_code/benchmark/` |
 
 ---
 

{pythinker_code-0.56.0 → pythinker_code-0.58.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythinker-code"
-version = "0.56.0"
+version = "0.58.0"
 description = "Pythinker — an agentic CLI developed by Pythoughts-labs."
 readme = "README.md"
 requires-python = ">=3.12"
@@ -76,6 +76,10 @@ dev = [
     "pytest>=9.0.3",
     "pytest-asyncio>=1.3.0",
     "pytest-cov>=6.0",
+    # Pure-Python VT100/xterm emulator: PTY UI tests feed raw terminal bytes to
+    # a virtual screen so they can assert on the *rendered* frame (catching
+    # incomplete-erase "ghost" rows), not just the byte stream.
+    "pyte>=0.8.2",
     # Pinned: ruff 0.15's formatter reflow fails `make check`. Unpin once the
     # formatting churn is resolved. Mirrored as a Dependabot ignore in
     # .github/dependabot.yml.

{pythinker_code-0.56.0 → pythinker_code-0.58.0}/src/pythinker_code/CHANGELOG.md

@@ -15,6 +15,79 @@ GitHub Releases page; `0.8.0` is the new starting line.
 
 ## Unreleased
 
+## 0.58.0 (2026-07-11)
+
+- **Agent-spec loading is more defensive and truthful.** Subagent `path`, `extend`, and
+  `system_prompt_path` references that resolve outside their spec's directory (or the built-in
+  agents directory) are now rejected instead of loaded, and the markdown agent catalogue no longer
+  reclassifies an unexpected parser error as a harmless "invalid field" skip — only genuinely
+  malformed frontmatter is skipped.
+- **Thinking and subagent activity now render cleanly in the terminal.** Live reasoning previews
+  render complete Markdown without exposing top-level HTML comments, activity-tree rows remain
+  visually stable, and the coral shimmer is reserved for the active verb spinner.
+- **Agent request compatibility is now executable and reviewable.** Provider handoff,
+  prompt ordering, persisted-versus-effective history, context JSONL restoration,
+  agent projections, and Toolset lifecycle behavior now have explicit compatibility
+  contracts guarding future agent-core changes.
+- **Skill discovery is bounded without making skills unreachable.** Pythinker now
+  searches one deterministic `SkillCatalog`, keeps exhaustive exact-name resolution,
+  and sends only task-relevant candidates to the model within an 8,000-character
+  request budget. The exhaustive `Runtime.skills` mapping remains available during
+  the compatibility window.
+- **Agent requests now have one observable assembly path.** Required guidance fails
+  closed, optional guidance reports sanitized degradation outcomes, and the new
+  `/prompt-manifest` command explains the latest request composition without storing
+  raw prompts, user text, or provenance paths.
+- **Conversation history updates are transactional.** Normal appends persist before
+  changing memory, while compaction, pruning, revert, and clear flows use atomic
+  replacement with coherent cancellation and rollback behavior. Concurrent revert
+  conflicts now stop after a bounded retry budget instead of starving indefinitely.
+  Existing JSONL records and restoration behavior remain compatible.
+- **Agent definitions now resolve through one source-aware catalogue.** YAML and
+  Markdown definitions share deterministic precedence, collision diagnostics, and
+  safe provenance handling. Unknown fields warn in this release, become errors in
+  the following minor release, and the `LaborMarket`, `AgentTypeDefinition`, and
+  generated-wrapper adapters remain through that strict-default release.
+- **Tool execution and MCP lifecycle behavior now have deterministic fault coverage.**
+  Publication rebuilds preserve the previous MCP tool registry if registration
+  fails. Characterization crossed the execution-overhead threshold, but a controlled
+  private extraction measured slightly worse and was reverted, so
+  `PythinkerToolset` remains the implementation boundary.
+- **Agent-core seams hardened from review.** Persisted usage/checkpoint records reject
+  boolean and negative token counts, `update_token_count` validates at the boundary, a
+  temporary system-prompt descriptor is closed if `fdopen` fails, request finalization
+  surfaces every provider acknowledgement failure, a failed skill projection is always
+  recorded as failed (never blurred to not-applicable), and request-assembly telemetry no
+  longer emits unbounded per-request token values as metric attributes.
+
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.58.0`, or use the native installer for your platform from the [Releases page](https://github.com/Pythoughts-labs/pythinker-code/releases/latest).
+
+## 0.57.0 (2026-07-05)
+
+- **No more ghost/duplicate input prompt while the agent works.** After
+  submitting a prompt, the input card no longer fossilizes above the stream as
+  a second, ghostly prompt. The prompt bar and top border now stay visible
+  through turn-start and lazy-load frames, and running-agent output renders
+  through a stable diff-rendered scene (ported from Pi) so the input card no
+  longer jumps. An experimental Focus TUI mode (`tui.focus_mode`) pins the
+  composer and hides file activity behind a compact live shelf for a cleaner
+  fullscreen view, and active subagent tool work now surfaces in the pinned
+  status tail instead of a generic composing spinner.
+- **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 that produce replayable artifacts,
+  activity metrics, and branded markdown reports.
+- **Hardened benchmark and skill security edges.** SWE verification commands
+  are shape-validated before execution, benchmark discovery requires explicit
+  network opt-in, run IDs avoid clock collisions, runtime overrides restore
+  after setup failures, and active-skill deactivation failures now surface
+  instead of being swallowed. Explicitly invoked skills stay active across
+  later turns through a compact reminder until stopped by name or
+  "normal mode".
+
+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).
+
 ## 0.56.0 (2026-07-02)
 
 - **Windows shell UI recovers from mid-session console blanking.** The TUI's

{pythinker_code-0.56.0 → pythinker_code-0.58.0}/src/pythinker_code/agents/default/system.md

@@ -127,7 +127,7 @@ Default to `ImplementAndJudge` for non-trivial scoped edits (see §4.4); reserve
 
 **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.
+**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`. If the user explicitly invokes or names a skill as an active mode, keep applying that loaded skill until they ask to stop it or return to normal mode. Read skill details only when needed, to conserve context. Catalog and scope precedence in §12.
 
 **Inline `/command` references.** Slash commands execute only as their own message starting with `/`. A `/command` or `/skill:<name>` mentioned mid-message did not auto-run, but it still expresses intent — act on it rather than leading your reply by reporting it as failed. For `/plan`, call `EnterPlanMode` (a real tool in your toolset, not just prose); for `/goal`, pursue the described objective until it is verifiably done; for `/skill:<name>`, load it via `ReadSkill` and apply it; for other guidance commands, apply the equivalent guidance yourself. Mention invoking the real command only when genuinely needed. Never silently drop such a reference.
 
@@ -255,8 +255,8 @@ Precedence per §2. `README`/`README.md` files are optional supplementary contex
 
 ## 12. Skills
 
-Skills are reusable, self-contained capability directories, each with a `SKILL.md` of instructions, examples, scripts, and reference material — specialized domain knowledge, workflow patterns, pre-configured tool chains, and templates. They are grouped by scope (`Project`, `User`, `Extra`, `Built-in`); when scopes define the same name, the more specific wins: **Project › User › Extra › Built-in.**
+Skills are reusable, self-contained capability directories, each with a `SKILL.md` of instructions, examples, scripts, and reference material — specialized domain knowledge, workflow patterns, pre-configured tool chains, and templates. When scopes define the same name, the more specific wins: **Project › User › Extra › Built-in.**
 
 ${PYTHINKER_SKILLS}
 
-Identify the skills relevant to the current task and read their `SKILL.md` before applying the workflow (§5). If a skill `<name>` has a companion `<name>-local`, treat it as local project specialization applied after the core skill. Read skill details only when needed, to conserve the context window.
+Identify the skills relevant to the current task and read their `SKILL.md` before applying the workflow (§5). If a skill `<name>` has a companion `<name>-local`, treat it as local project specialization applied after the core skill. Read skill details only when needed, to conserve the context window.