ci: release packages

Author: github-actions[bot]

.changeset/dynamic-workflow-plan-approval.md

@@ -1,5 +1,27 @@
 # @pythoughts/pythinker-code
 
+## 0.12.0
+
+### Minor Changes
+
+- [#35](https://github.com/Pythoughts-labs/pythinker-code/pull/35) [`2ce6b5e`](https://github.com/Pythoughts-labs/pythinker-code/commit/2ce6b5e66935335567a6525413ad8e77b84d852f) - Show the plan before a Dynamic Workflow runs, and let a good one be saved as a command
+
+  Manual mode used to approve every `DynamicWorkflow` call outright. That approval
+  only ever fired in manual mode — auto and yolo approve earlier in the chain — so
+  the one mode whose purpose is to ask was the one mode that never saw what it was
+  agreeing to. A `DynamicWorkflow` call in manual mode now asks, and the approval
+  carries the fan-out: how many subagents, the task list, the prompt template, the
+  worker model, and the summed size of the prompts about to be sent. "Approve for
+  this session" is keyed to that workflow's description rather than granting every
+  future `DynamicWorkflow` call.
+
+  `/workflow save <name>` writes the last run back out as a skill under
+  `.pythinker-code/skills/`, so a fan-out that worked can be re-run by name.
+
+### Patch Changes
+
+- [#37](https://github.com/Pythoughts-labs/pythinker-code/pull/37) [`12069a8`](https://github.com/Pythoughts-labs/pythinker-code/commit/12069a890144380bff5d648ad51d7411ece94437) - Stop offering updates to versions that were never published: the update channel now advertises only the release that is actually available for download.
+
 ## 0.11.0
 
 ### Minor Changes

.changeset/update-channel-published-versions-only.md

@@ -1,6 +1,6 @@
 {
   "name": "@pythoughts/pythinker-code",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "description": "The Starting Point for Next-Gen Agents",
   "license": "MIT",
   "author": "Pythoughts",

apps/pythinker-code/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 0.8.6
+
+### Patch Changes
+
+- Updated dependencies [[`2ce6b5e`](https://github.com/Pythoughts-labs/pythinker-code/commit/2ce6b5e66935335567a6525413ad8e77b84d852f)]:
+  - @pythoughts/pythinker-code-sdk@0.13.0
+
 ## 0.8.5
 
 ### Patch Changes

apps/pythinker-code/package.json

@@ -3,7 +3,7 @@
   "publisher": "pythoughts",
   "displayName": "Pythinker Code",
   "description": "Pythinker Code extension for VS Code",
-  "version": "0.8.5",
+  "version": "0.8.6",
   "private": true,
   "license": "Apache-2.0",
   "type": "module",

apps/vscode/CHANGELOG.md

@@ -1,5 +1,23 @@
 # @pythoughts/pythinker-code-sdk
 
+## 0.13.0
+
+### Minor Changes
+
+- [#35](https://github.com/Pythoughts-labs/pythinker-code/pull/35) [`2ce6b5e`](https://github.com/Pythoughts-labs/pythinker-code/commit/2ce6b5e66935335567a6525413ad8e77b84d852f) - Show the plan before a Dynamic Workflow runs, and let a good one be saved as a command
+
+  Manual mode used to approve every `DynamicWorkflow` call outright. That approval
+  only ever fired in manual mode — auto and yolo approve earlier in the chain — so
+  the one mode whose purpose is to ask was the one mode that never saw what it was
+  agreeing to. A `DynamicWorkflow` call in manual mode now asks, and the approval
+  carries the fan-out: how many subagents, the task list, the prompt template, the
+  worker model, and the summed size of the prompts about to be sent. "Approve for
+  this session" is keyed to that workflow's description rather than granting every
+  future `DynamicWorkflow` call.
+
+  `/workflow save <name>` writes the last run back out as a skill under
+  `.pythinker-code/skills/`, so a fan-out that worked can be re-run by name.
+
 ## 0.12.0
 
 ### Minor Changes

apps/vscode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pythoughts/pythinker-code-sdk",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "private": true,
   "description": "TypeScript SDK for the Pythinker Code Agent",
   "license": "MIT",