pythinker-code 0.17.0__tar.gz → 0.18.0__tar.gz

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythinker-code
-Version: 0.17.0
+Version: 0.18.0
 Summary: Pythinker Code is your next CLI agent.
 Keywords: cli,agent,ai,coding-assistant,llm,claude,openai,terminal
 Author: Mohamed Elkholy
@@ -115,15 +115,15 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.17.0
+## 🆕 What's New in 0.18.0
 
-- **Sharper compaction continuity.** PreCompact now carries custom instructions, restores skill and hook context after compaction, triggers SessionStart after restore, and preserves the `Conversation compacted.` handoff so long sessions resume cleanly.
-- **Better subagent orchestration.** Subagent specs merge inherited subagent maps, launches preserve parent-agent IDs for spawn-tree tracking, RunAgents fingerprints include agent names, and markdown agent discovery warns on unknown models instead of silently falling back.
-- **Polished terminal workflow.** The shell adopts the robot-brand palette, compact transcript/agent/file-mention menus, pinned live todo activity, calmer tool output, and safer auto-backgrounding for long shell commands.
-- **Release and installer hardening.** Interactive sessions show a blocking pre-start update prompt, update exits wait for acknowledgement, Homebrew publish retries package installs, and native installers gain a friendlier animated path with Windows User PATH automation.
-- **Provider compatibility refresh.** Anthropic SDK support is updated for 0.101 tool-result block types so direct Anthropic sessions continue to stream tool output correctly.
+- **Live subagent activity streaming.** Subagent tool calls now stream live into the transcript, with safe pending headers for in-flight tool calls, new transcript progress events, and a unified shimmer animation across active-work labels so long-running exploration stays legible.
+- **Smarter delegation and orchestration.** A Context-First Orchestration Protocol guides the default agent, specialist subagents receive prompt packets for single-objective delegation plus evidence and verification gates, and overflow RunAgents children are deferred instead of hard-failing.
+- **Calmer, more resilient TUI.** In-flight and singular Ask payloads no longer flash an invalid badge, MCP startup status is cleaner, and shell rendering and MCP guidance are refined.
+- **Sturdier configuration handling.** Incompatible legacy JSON config is now preserved instead of being silently reset to defaults.
+- **Security and shell hardening.** The security scan and shell execution paths were hardened against unexpected input.
 
-Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.17.0`, or use the native installer for your platform from the [Releases page](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.18.0`, or use the native installer for your platform from the [Releases page](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest).
 
 
 ---
@@ -213,7 +213,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.17.0.exe` from [Releases](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.18.0.exe` from [Releases](https://github.com/mohamed-elkholy95/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/mohamed-elkholy95/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 mohamed-elkholy95/pythinker/pythinker-code` | auto-published Homebrew tap |
 | **<img src="https://img.shields.io/badge/-Linux-FCC624?style=flat-square&logo=linux&logoColor=black" alt="Linux"> — system package** | Download the `.deb` or `.rpm` for your distro below | [Releases](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest) |
@@ -238,7 +238,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.17.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.18.0.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 +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-0.17.0.exe
+.\PythinkerSetup-0.18.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.17.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.18.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -305,26 +305,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.17.0_amd64.deb
+sudo dpkg -i pythinker-code_0.18.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.17.0_arm64.deb
+sudo dpkg -i pythinker-code_0.18.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.x86_64.rpm
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.17.0.x86_64.rpm.sha256
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.x86_64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.18.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.17.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.18.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.17.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.18.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.aarch64.rpm
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.17.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.17.0.aarch64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.aarch64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.18.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.18.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -333,8 +333,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.17.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.17.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.18.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.18.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /
@@ -364,7 +364,7 @@ at `~/.local/bin/pythinker`.
 curl -fsSL https://pythinker.com/install.sh | bash
 
 # Pin a specific version
-curl -fsSL https://pythinker.com/install.sh | bash -s -- --version 0.17.0
+curl -fsSL https://pythinker.com/install.sh | bash -s -- --version 0.18.0
 
 # Custom prefix (defaults to $HOME/.local)
 curl -fsSL https://pythinker.com/install.sh | bash -s -- --prefix /opt/pythinker
@@ -385,9 +385,9 @@ Supported targets:
 
 | `uname -s / -m`             | Tarball asset                                            |
 |---|---|
-| Linux / x86_64              | `pythinker-0.17.0-x86_64-unknown-linux-gnu.tar.gz`        |
-| Linux / aarch64             | `pythinker-0.17.0-aarch64-unknown-linux-gnu.tar.gz`       |
-| Darwin / arm64              | `pythinker-0.17.0-aarch64-apple-darwin.tar.gz`            |
+| Linux / x86_64              | `pythinker-0.18.0-x86_64-unknown-linux-gnu.tar.gz`        |
+| Linux / aarch64             | `pythinker-0.18.0-aarch64-unknown-linux-gnu.tar.gz`       |
+| Darwin / arm64              | `pythinker-0.18.0-aarch64-apple-darwin.tar.gz`            |
 
 The script prints PATH guidance if `~/.local/bin` isn't already on your
 `$PATH`. Intel macOS users — use Homebrew or `pip install pythinker-code`;
@@ -617,14 +617,18 @@ Pythinker loads [Model Context Protocol](https://modelcontextprotocol.io/) tools
 ### 🛠️ Manage persistent MCP servers
 
 ```sh
+# 📚 Context7 stdio server (Codex-style: NAME -- COMMAND)
+pythinker mcp add context7 -- npx -y @upstash/context7-mcp --api-key YOUR-API-KEY
+# Added MCP server 'context7' to ~/.pythinker/mcp.json
+
 # 🌐 Streamable HTTP server with API key
-pythinker mcp add --transport http context7 https://mcp.context7.com/mcp \
-  --header "CONTEXT7_API_KEY: ctx7sk-your-key"
+pythinker mcp add --transport http docs https://example.com/mcp \
+  --header "API_KEY: your-key"
 
 # 🔐 Streamable HTTP server with OAuth
 pythinker mcp add --transport http --auth oauth linear https://mcp.linear.app/mcp
 
-# 💻 stdio server
+# 💻 stdio server with explicit transport
 pythinker mcp add --transport stdio chrome-devtools -- npx chrome-devtools-mcp@latest
 
 # 📋 List, authorize, test, and remove
@@ -714,16 +718,9 @@ file paths, or any user-identifying data. Two channels:
 - Your real name, email, IP address, hostname (host name field is dropped at the edge collector)
 - Tool arguments (e.g. what file you read, what command you ran)
 
-### Opting in or forcing off
-
-Telemetry is off by default. To enable it for a process:
-
-```sh
-export PYTHINKER_ENABLE_TELEMETRY=1
-pythinker
-```
+### Turning it off
 
-To force telemetry off even if another setting enabled it:
+Telemetry is on by default. To turn it off:
 
 ```sh
 # 1. Per-invocation CLI flag
@@ -753,8 +750,8 @@ export PYTHINKER_OTEL_ENDPOINT="https://your-otel-collector.example.com"
 export PYTHINKER_OTEL_TOKEN="<your bearer token>"
 ```
 
-The defaults point at infrastructure operated by the pythinker maintainers;
-set `PYTHINKER_ENABLE_TELEMETRY=1` to use them.
+The defaults point at infrastructure operated by the pythinker maintainers and
+are used automatically unless you turn telemetry off.
 
 ---
 

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/README.md

@@ -50,15 +50,15 @@ It speaks the [**Agent Client Protocol (ACP)**](https://github.com/agentclientpr
 
 ---
 
-## 🆕 What's New in 0.17.0
+## 🆕 What's New in 0.18.0
 
-- **Sharper compaction continuity.** PreCompact now carries custom instructions, restores skill and hook context after compaction, triggers SessionStart after restore, and preserves the `Conversation compacted.` handoff so long sessions resume cleanly.
-- **Better subagent orchestration.** Subagent specs merge inherited subagent maps, launches preserve parent-agent IDs for spawn-tree tracking, RunAgents fingerprints include agent names, and markdown agent discovery warns on unknown models instead of silently falling back.
-- **Polished terminal workflow.** The shell adopts the robot-brand palette, compact transcript/agent/file-mention menus, pinned live todo activity, calmer tool output, and safer auto-backgrounding for long shell commands.
-- **Release and installer hardening.** Interactive sessions show a blocking pre-start update prompt, update exits wait for acknowledgement, Homebrew publish retries package installs, and native installers gain a friendlier animated path with Windows User PATH automation.
-- **Provider compatibility refresh.** Anthropic SDK support is updated for 0.101 tool-result block types so direct Anthropic sessions continue to stream tool output correctly.
+- **Live subagent activity streaming.** Subagent tool calls now stream live into the transcript, with safe pending headers for in-flight tool calls, new transcript progress events, and a unified shimmer animation across active-work labels so long-running exploration stays legible.
+- **Smarter delegation and orchestration.** A Context-First Orchestration Protocol guides the default agent, specialist subagents receive prompt packets for single-objective delegation plus evidence and verification gates, and overflow RunAgents children are deferred instead of hard-failing.
+- **Calmer, more resilient TUI.** In-flight and singular Ask payloads no longer flash an invalid badge, MCP startup status is cleaner, and shell rendering and MCP guidance are refined.
+- **Sturdier configuration handling.** Incompatible legacy JSON config is now preserved instead of being silently reset to defaults.
+- **Security and shell hardening.** The security scan and shell execution paths were hardened against unexpected input.
 
-Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.17.0`, or use the native installer for your platform from the [Releases page](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest).
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.18.0`, or use the native installer for your platform from the [Releases page](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest).
 
 
 ---
@@ -148,7 +148,7 @@ matches your OS — no Python, Node, or `uv` prerequisite.
 
 | Platform | Recommended install | Artifact source |
 |---|---|---|
-| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.17.0.exe` from [Releases](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest) |
+| **🪟 Windows** | `irm https://pythinker.com/install.ps1 \| iex` | `PythinkerSetup-0.18.0.exe` from [Releases](https://github.com/mohamed-elkholy95/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/mohamed-elkholy95/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 mohamed-elkholy95/pythinker/pythinker-code` | auto-published Homebrew tap |
 | **<img src="https://img.shields.io/badge/-Linux-FCC624?style=flat-square&logo=linux&logoColor=black" alt="Linux"> — system package** | Download the `.deb` or `.rpm` for your distro below | [Releases](https://github.com/mohamed-elkholy95/Pythinker-Code/releases/latest) |
@@ -173,7 +173,7 @@ pythinker                      # start the interactive TUI
 
 ### 🪟 Windows — native installer
 
-`PythinkerSetup-0.17.0.exe` is a signed* Inno Setup wizard. Installs per-user
+`PythinkerSetup-0.18.0.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 +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-0.17.0.exe
+.\PythinkerSetup-0.18.0.exe
 
 # Open a fresh PowerShell
 pythinker --version
 ```
 
-**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.17.0.exe /ALLUSERS`
+**Per-machine install** (IT-managed boxes): `.\PythinkerSetup-0.18.0.exe /ALLUSERS`
 installs to `%ProgramFiles%\Pythinker` and writes PATH to HKLM (requires admin).
 
 **Upgrade:** `pythinker update` from inside the running app — it downloads
@@ -240,26 +240,26 @@ attached to every GitHub Release.
 
 ```sh
 # Debian / Ubuntu (x86_64)
-sudo dpkg -i pythinker-code_0.17.0_amd64.deb
+sudo dpkg -i pythinker-code_0.18.0_amd64.deb
 sudo apt-get install -f       # only if dpkg reports missing deps
 
 # Debian / Ubuntu (ARM64)
-sudo dpkg -i pythinker-code_0.17.0_arm64.deb
+sudo dpkg -i pythinker-code_0.18.0_arm64.deb
 
 # Fedora / RHEL / openSUSE (x86_64)
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.x86_64.rpm
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.x86_64.rpm.sha256
-sha256sum -c pythinker-code-0.17.0.x86_64.rpm.sha256
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.x86_64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.x86_64.rpm.sha256
+sha256sum -c pythinker-code-0.18.0.x86_64.rpm.sha256
 # Fedora / RHEL:
-sudo dnf install ./pythinker-code-0.17.0.x86_64.rpm
+sudo dnf install ./pythinker-code-0.18.0.x86_64.rpm
 # openSUSE:
-sudo zypper install ./pythinker-code-0.17.0.x86_64.rpm
+sudo zypper install ./pythinker-code-0.18.0.x86_64.rpm
 
 # Fedora / RHEL (aarch64)
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.aarch64.rpm
-curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.17.0/pythinker-code-0.17.0.aarch64.rpm.sha256
-sha256sum -c pythinker-code-0.17.0.aarch64.rpm.sha256
-sudo dnf install ./pythinker-code-0.17.0.aarch64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.aarch64.rpm
+curl -LO https://github.com/mohamed-elkholy95/Pythinker-Code/releases/download/v0.18.0/pythinker-code-0.18.0.aarch64.rpm.sha256
+sha256sum -c pythinker-code-0.18.0.aarch64.rpm.sha256
+sudo dnf install ./pythinker-code-0.18.0.aarch64.rpm
 ```
 
 Both packages drop a small `/usr/bin/pythinker` launcher that execs the real
@@ -268,8 +268,8 @@ binary under `/usr/lib/pythinker/`, so your `$PATH` stays tidy.
 **Verify before install:**
 
 ```sh
-sha256sum -c pythinker-code_0.17.0_amd64.deb.sha256        # Debian/Ubuntu
-sha256sum -c pythinker-code-0.17.0.x86_64.rpm.sha256       # Fedora/RHEL
+sha256sum -c pythinker-code_0.18.0_amd64.deb.sha256        # Debian/Ubuntu
+sha256sum -c pythinker-code-0.18.0.x86_64.rpm.sha256       # Fedora/RHEL
 ```
 
 **Upgrade:** download the new `.deb`/`.rpm` from Releases and `dpkg -i` /
@@ -299,7 +299,7 @@ at `~/.local/bin/pythinker`.
 curl -fsSL https://pythinker.com/install.sh | bash
 
 # Pin a specific version
-curl -fsSL https://pythinker.com/install.sh | bash -s -- --version 0.17.0
+curl -fsSL https://pythinker.com/install.sh | bash -s -- --version 0.18.0
 
 # Custom prefix (defaults to $HOME/.local)
 curl -fsSL https://pythinker.com/install.sh | bash -s -- --prefix /opt/pythinker
@@ -320,9 +320,9 @@ Supported targets:
 
 | `uname -s / -m`             | Tarball asset                                            |
 |---|---|
-| Linux / x86_64              | `pythinker-0.17.0-x86_64-unknown-linux-gnu.tar.gz`        |
-| Linux / aarch64             | `pythinker-0.17.0-aarch64-unknown-linux-gnu.tar.gz`       |
-| Darwin / arm64              | `pythinker-0.17.0-aarch64-apple-darwin.tar.gz`            |
+| Linux / x86_64              | `pythinker-0.18.0-x86_64-unknown-linux-gnu.tar.gz`        |
+| Linux / aarch64             | `pythinker-0.18.0-aarch64-unknown-linux-gnu.tar.gz`       |
+| Darwin / arm64              | `pythinker-0.18.0-aarch64-apple-darwin.tar.gz`            |
 
 The script prints PATH guidance if `~/.local/bin` isn't already on your
 `$PATH`. Intel macOS users — use Homebrew or `pip install pythinker-code`;
@@ -552,14 +552,18 @@ Pythinker loads [Model Context Protocol](https://modelcontextprotocol.io/) tools
 ### 🛠️ Manage persistent MCP servers
 
 ```sh
+# 📚 Context7 stdio server (Codex-style: NAME -- COMMAND)
+pythinker mcp add context7 -- npx -y @upstash/context7-mcp --api-key YOUR-API-KEY
+# Added MCP server 'context7' to ~/.pythinker/mcp.json
+
 # 🌐 Streamable HTTP server with API key
-pythinker mcp add --transport http context7 https://mcp.context7.com/mcp \
-  --header "CONTEXT7_API_KEY: ctx7sk-your-key"
+pythinker mcp add --transport http docs https://example.com/mcp \
+  --header "API_KEY: your-key"
 
 # 🔐 Streamable HTTP server with OAuth
 pythinker mcp add --transport http --auth oauth linear https://mcp.linear.app/mcp
 
-# 💻 stdio server
+# 💻 stdio server with explicit transport
 pythinker mcp add --transport stdio chrome-devtools -- npx chrome-devtools-mcp@latest
 
 # 📋 List, authorize, test, and remove
@@ -649,16 +653,9 @@ file paths, or any user-identifying data. Two channels:
 - Your real name, email, IP address, hostname (host name field is dropped at the edge collector)
 - Tool arguments (e.g. what file you read, what command you ran)
 
-### Opting in or forcing off
-
-Telemetry is off by default. To enable it for a process:
-
-```sh
-export PYTHINKER_ENABLE_TELEMETRY=1
-pythinker
-```
+### Turning it off
 
-To force telemetry off even if another setting enabled it:
+Telemetry is on by default. To turn it off:
 
 ```sh
 # 1. Per-invocation CLI flag
@@ -688,8 +685,8 @@ export PYTHINKER_OTEL_ENDPOINT="https://your-otel-collector.example.com"
 export PYTHINKER_OTEL_TOKEN="<your bearer token>"
 ```
 
-The defaults point at infrastructure operated by the pythinker maintainers;
-set `PYTHINKER_ENABLE_TELEMETRY=1` to use them.
+The defaults point at infrastructure operated by the pythinker maintainers and
+are used automatically unless you turn telemetry off.
 
 ---
 

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythinker-code"
-version = "0.17.0"
+version = "0.18.0"
 description = "Pythinker Code is your next CLI agent."
 readme = "README.md"
 requires-python = ">=3.12"

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/CHANGELOG.md

@@ -15,6 +15,18 @@ GitHub Releases page; `0.8.0` is the new starting line.
 
 ## Unreleased
 
+## 0.18.0 (2026-05-27)
+
+### What changed in this release
+
+- **Live subagent activity streaming.** Subagent tool calls now stream live into the transcript, with safe pending headers for in-flight tool calls, new transcript progress events, and a unified shimmer animation across active-work labels so long-running exploration stays legible.
+- **Smarter delegation and orchestration.** A Context-First Orchestration Protocol guides the default agent, specialist subagents receive prompt packets for single-objective delegation plus evidence and verification gates, and overflow RunAgents children are deferred instead of hard-failing.
+- **Calmer, more resilient TUI.** In-flight and singular Ask payloads no longer flash an invalid badge, MCP startup status is cleaner, and shell rendering and MCP guidance are refined.
+- **Sturdier configuration handling.** Incompatible legacy JSON config is now preserved instead of being silently reset to defaults.
+- **Security and shell hardening.** The security scan and shell execution paths were hardened against unexpected input.
+
+Upgrade with `pythinker update`, `pip install --upgrade pythinker-code==0.18.0`, or use the native installer for your OS (see the README install table).
+
 ## 0.17.0 (2026-05-25)
 
 ### What changed in this release

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/code_reviewer.yaml

@@ -20,8 +20,9 @@ agent:
 
       Review discipline:
       - If `.pythinker/review-guidelines.md` exists, read it before scoring findings.
+      - Build a review context packet: base ref/diff scope, changed behavior, likely tests, user-visible impact, and validation evidence.
       - Flag only issues introduced or made reachable by the diff.
-      - Prefer no finding over vague speculation.
+      - Prefer no finding over vague speculation. Every finding must cite concrete evidence and a failure mode.
       - Do not request tests unless they cover a distinct behavior or risk introduced by the change.
       - Treat V0 robustness suggestions as future work unless they risk correctness, security, data loss, or persistent hangs.
       - For user-visible UI/behavior changes, check whether screenshots, GIFs, videos, or equivalent visual evidence are present; if absent, request that evidence as a blocking review concern.

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/coder.yaml

@@ -7,13 +7,23 @@ agent:
 
       Stay tightly scoped to exactly what the parent assigned. Do not expand into adjacent cleanup or refactors. If you discover related work, surface it under RISKS or BLOCKERS rather than doing it.
 
-      Before editing, read the target files and confirm the line ranges/patterns you will change. Prefer the minimum edit that satisfies the brief. After edits, run the smallest relevant verification command available and report the result.
+      Context gate before editing:
+      - Confirm the parent provided a clear goal, scope, constraints, and acceptance criteria. If not, inspect the code enough to infer them or report BLOCKERS.
+      - Read target files, nearby patterns, and relevant tests before writing. Do not edit code you cannot explain.
+      - Prefer the minimum implementation that satisfies the brief; no speculative abstractions or broad formatting churn.
+
+      Implementation method:
+      - Before editing, read the target files and confirm the line ranges/patterns you will change.
+      - Prefer StrReplaceFile for narrow changes; use WriteFile only for new files or intentional full rewrites.
+      - Add or update tests when the brief requires behavior changes and the project has relevant tests.
+      - After edits, inspect the diff/changed files for scope creep, TODOs/placeholders, import mistakes, and logic mismatches.
+      - Run the smallest relevant verification command available and report the result. If verification cannot run, explain the blocker.
 
       Final response contract:
       ### SUMMARY
       One paragraph with what you did and the outcome.
       ### EVIDENCE
-      Bullet list of concrete file paths, command results, or observed errors that support the outcome.
+      Bullet list of concrete file paths, command results, diff inspection, or observed errors that support the outcome.
       ### CHANGES
       Bullet list of every file you modified, or `None.` if read-only.
       ### RISKS

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/debugger.yaml

@@ -5,24 +5,31 @@ agent:
     ROLE_ADDITIONAL: |
       You are now running as a subagent. All `user` messages are sent by the main agent. The main agent cannot see your context, only your last message. Treat the parent agent as your caller. Do not ask the end user questions; surface ambiguity in your final summary.
 
-      You are a root-cause debugger. Your job is to run `pythinker debug failure <log-file>` when a failure log is available, or request the parent provide the log path/command evidence.
+      You are a root-cause debugger. Your job is to establish reproduction evidence, isolate the likely cause, and recommend the smallest next action before anyone edits code.
+
+      Reproduction protocol:
+      - If a failure log is available, run `pythinker debug failure <log-file> --format json` and translate the result for the parent.
+      - If no log file is available but a failing command is provided, run the command only when it is safe and bounded; capture stdout/stderr and exit code.
+      - If neither log nor command evidence is available, do not guess. Request the parent provide the missing log path, failing command, environment, or reproduction steps under BLOCKERS.
 
       Operating rules:
       - If `.pythinker/review-guidelines.md` exists, read it before judging failure severity or fix priority.
       - Read-only by convention. Do not edit source files.
-      - Focus on reproduction evidence, changed-file correlation, likely root cause, and minimal next action.
+      - Observe first: stack traces, assertions, recent diffs, environment, and reproduction steps.
+      - Correlate failures with changed files, callers/callees, config, tests, and recent assumptions.
+      - State confidence. Separate confirmed root cause from plausible hypotheses.
       - Check graceful degradation, observability/logging, recovery behavior, structured result/status correctness, approval/policy mismatches, and user-facing string regressions when they explain or worsen the failure.
-      - Default to `--format json` and translate the result into the structured response block below.
+      - Recommend the minimal next action and the verification that should prove the fix.
 
       Final response contract:
       ### SUMMARY
       One paragraph: likely root cause, confidence, and first recommended action.
       ### EVIDENCE
-      Bullet list of log/stack/diff evidence with file:line when available.
+      Bullet list of log/stack/diff/reproduction evidence with file:line when available.
       ### CHANGES
       None.
       ### RISKS
-      Ambiguities, missing reproduction context, or `None observed.`.
+      Ambiguities, alternate hypotheses, missing reproduction context, or `None observed.`.
       ### BLOCKERS
       Missing log path, command, environment, or `None.`.
   when_to_use: |

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/explore.yaml

@@ -7,6 +7,12 @@ agent:
 
       You are a codebase exploration specialist. Your role is EXCLUSIVELY to search, read, and analyze existing code and resources. You do NOT have access to file editing tools. If the task appears to require a write, stop and put the gap under BLOCKERS.
 
+      Context packet requirements:
+      - Collect the smallest evidence set that can support the parent's decision: relevant files, symbols, callers/callees, tests, docs, commands, config, and existing patterns.
+      - Do not provide architecture judgment, root-cause claims, implementation recommendations, or risk assessment unless the evidence is cited.
+      - Distinguish CONFIRMED facts from LIKELY inferences. Put unknowns and missing evidence under RISKS or BLOCKERS.
+      - Prefer path:line-range citations for load-bearing findings. Search broadly enough to avoid a false map, then stop when the parent has enough context.
+
       Your strengths:
       - Rapidly finding files using glob patterns
       - Searching code and text with powerful regex patterns
@@ -21,6 +27,7 @@ agent:
       - NEVER use Shell for any file creation or modification commands
       - Adapt your search depth based on the thoroughness level specified by the caller
       - Wherever possible, spawn multiple parallel tool calls for grepping and reading files to maximize speed
+      - When running lint or complexity checks (e.g. ruff, flake8), always run with the project's configured rule set first (no extra `--select` flags). If you run supplemental checks that add rules not in the project config (e.g. `--select C901` when C901 is absent from pyproject.toml), you MUST label those findings explicitly as "outside project lint policy — not an enforced violation" so the caller can distinguish real project violations from advisory findings.
 
       If the prompt includes a <git-context> block, use it to orient yourself about the repository state before starting your investigation.
 
@@ -29,6 +36,8 @@ agent:
       Final response contract:
       ### SUMMARY
       One paragraph with the headline answer.
+      ### CONTEXT PACKET
+      Bullets for goal, relevant files/symbols, existing patterns, tests/docs, and unknowns.
       ### EVIDENCE
       Bullet list of concrete file paths, line ranges, search hits, and command results.
       ### CHANGES

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/implementer.yaml

@@ -7,17 +7,23 @@ agent:
 
       You are an implementation specialist. Land exactly the change the parent assigned with the minimum surrounding edit. Do not refactor adjacent code, rename unrelated variables, tidy files, or expand scope. Put related follow-up work under RISKS or BLOCKERS instead.
 
+      Context gate before editing:
+      - Confirm the parent provided a clear goal, scope, constraints, and acceptance criteria. If not, inspect the code enough to infer them or report BLOCKERS.
+      - Read target files, nearby patterns, and relevant tests before writing. Do not edit code you cannot explain.
+      - Prefer the minimum implementation that satisfies the brief; no speculative abstractions or broad formatting churn.
+
       Method:
-      - Read target files before editing.
+      - Read target files before editing and confirm the line ranges/patterns you will change.
       - Prefer StrReplaceFile for narrow changes; use WriteFile only for new files or intentional full rewrites.
       - Add or update tests when the brief requires behavior changes and the project has relevant tests.
-      - After edits, run the smallest relevant verification command and report pass/fail evidence.
+      - After edits, inspect the diff/changed files for scope creep, TODOs/placeholders, import mistakes, and logic mismatches.
+      - Run the smallest relevant verification command and report pass/fail evidence. If verification cannot run, explain the blocker.
 
       Final response contract:
       ### SUMMARY
       One paragraph with what changed and the verification outcome.
       ### EVIDENCE
-      Bullet list of file reads, command results, and test/lint evidence.
+      Bullet list of file reads, command results, diff inspection, and test/lint evidence.
       ### CHANGES
       Bullet list of every modified path with a one-line reason.
       ### RISKS

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/plan.yaml

@@ -5,13 +5,35 @@ agent:
     ROLE_ADDITIONAL: |
       You are now running as a subagent. All the `user` messages are sent by the main agent. The main agent cannot see your context, it can only see your last message when you finish the task. You must treat the parent agent as your caller. Do not directly ask the end user questions. If something is unclear, explain the ambiguity in your final summary to the parent agent.
 
-      Before designing your implementation plan, consider whether you fully understand the codebase areas relevant to the task. If not, recommend the parent agent to use the explore agent (subagent_type="explore") to investigate key questions first.
+      You are a read-only planning and architecture specialist. Your output must be an evidence-backed execution plan, not a guess.
+
+      Context gate:
+      - Before designing a plan, build a context packet from repository evidence, docs, tests, existing patterns, and the user's stated goal.
+      - If the relevant codebase area is not understood, do not invent a plan. Recommend concrete `explore` questions for the parent agent to run first.
+      - State assumptions explicitly and separate them from confirmed evidence.
+      - Before proposing a fix for any lint or complexity violation, verify the rule is in the project's active rule set (e.g. `select` in pyproject.toml or .ruff.toml). Findings that only appear via an explicit `--select <rule>` flag not present in the project config are NOT project violations; do not include them in the plan unless the user explicitly asked to enforce that rule.
+
+      Plan requirements:
+      - Include a User Request Summary and the success criteria you optimized for.
+      - Identify likely files/modules and why they are in scope.
+      - Provide a Task Dependency Graph: each task, what it depends on, and the reason.
+      - Provide a Parallel Execution Graph: which tasks can run together, which must be sequential, and the critical path.
+      - For every task, include artifacts to change, acceptance criteria, suggested specialist (`explore`, `implementer`, `review`, `security-reviewer`, `debugger`, `verifier`), and the smallest verification command/check.
+      - Call out risks, blockers, migration/backward-compatibility concerns, and test gaps.
 
       Ground the plan in evidence. Read enough files to avoid guessing, name the trade-offs, and choose one path with a reason. Each step should name the artifact it changes and the verification that proves it worked. Order steps by dependency first, then by risk reduced per effort.
 
       Final response contract:
       ### SUMMARY
       One paragraph with the recommended plan and why.
+      ### CONTEXT
+      User request summary, confirmed context, assumptions, and unknowns.
+      ### TASK DEPENDENCY GRAPH
+      Table or bullets showing task dependencies and reasons.
+      ### PARALLEL EXECUTION GRAPH
+      Execution waves, critical path, and what can/cannot run concurrently.
+      ### PLAN
+      Numbered tasks with artifacts, acceptance criteria, specialist recommendation, and verification.
       ### EVIDENCE
       Bullet list of concrete file paths, line ranges, docs, or search hits that shaped the plan.
       ### CHANGES

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/review.yaml

@@ -7,6 +7,11 @@ agent:
 
       You are a code review specialist. Your job is to read the requested diff/files and emit severity-scored findings. You are read-only by convention: do not patch code even if the fix is obvious. Describe the fix so the parent can dispatch an implementer.
 
+      Evidence gate:
+      - Do not score or report a finding until you have read the relevant diff/file and at least one supporting caller, test, config, or sibling pattern when applicable.
+      - Flag only issues introduced or made reachable by the requested diff/files.
+      - Prefer no finding over vague speculation. Label residual uncertainty under RISKS.
+
       Method:
       - If `.pythinker/review-guidelines.md` exists, read it before scoring findings.
       - Read the diff or target files before scoring.

{pythinker_code-0.17.0 → pythinker_code-0.18.0}/src/pythinker_code/agents/default/security_reviewer.yaml

@@ -7,6 +7,12 @@ agent:
 
       You are a security reviewer. For diff-focused review, run `pythinker secscan diff` and reformat the result for the parent. For repo-wide vulnerability discovery, run the Python-native `pythinker security-scan` pipeline.
 
+      Security review discipline:
+      - Build a threat context before judging: changed trust boundaries, inputs/outputs, authz/authn, filesystem/network access, secrets, serialization, command execution, and persistence.
+      - Report only reachable or plausibly reachable vulnerabilities backed by evidence. Prefer no finding over speculative risk.
+      - For each finding, include exploit preconditions, impact, severity rationale, and the smallest safe mitigation.
+      - Treat secrets/PII carefully: never print raw secret values; redact if needed.
+
       Operating rules:
       - If `.pythinker/review-guidelines.md` exists, read it before scoring findings.
       - Read-only by convention. You may run secscan/security-scan CLI commands and read outputs, but do not edit source files.