ci: release packages

apps/pythinker-code/CHANGELOG.md

@@ -1,5 +1,23 @@
 # @pythoughts/pythinker-code
 
+## 0.13.0
+
+### Minor Changes
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Let permission rules gate the model a subagent runs on, so `Agent(model:some-model)` and `DynamicWorkflow(model:some-model)` now match instead of being silently ignored.
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Show the Dynamic Workflow plan before the run in `auto` permission mode, which previously approved the call without displaying it. The approval is asked once per distinct plan; `yolo` still approves without asking.
+
+### Patch Changes
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Fix Dynamic Workflow recent activity showing one growing line three times instead of the last three lines an agent wrote.
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Drop the preamble every Dynamic Workflow task repeats so each agent row shows the part that names it.
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Fix the Dynamic Workflow card clipping an agent's task down to one character once that agent returned a long summary.
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Fix `/workflow save` leaving the saved workflow uncallable until the session was reloaded, and add `Session.reloadSkills()` to re-discover skills written while a session is open.
+
 ## 0.12.0
 
 ### Minor Changes
@@ -22,7 +40,6 @@
 
 - [#38](https://github.com/Pythoughts-labs/pythinker-code/pull/38) [`44efbc7`](https://github.com/Pythoughts-labs/pythinker-code/commit/44efbc77360105de0efce185c86740fcf503944e) - Show update availability and live download progress in the status row under the prompt, replacing the startup banner chip that was computed once and never refreshed.
 
-
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Rename the ACP authentication method to reflect that login is multi-provider: it now reads "Log in with a provider" and explains that the provider is chosen in a terminal. Clients matching the previous wording will need updating.
 
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Let a Dynamic Workflow require structured output from its subagents. Passing `output_schema` makes each subagent return a validated object instead of free text, and a subagent that cannot satisfy the schema is reported separately from one that failed outright.
@@ -41,7 +58,6 @@
 
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Replace the Dynamic Workflow progress bar with the two things it can actually know: how many tool calls each agent has made, and how long it has been silent. The old bar pinned every tool-using agent at 75% until it finished, so an agent working hard and one wedged for ten minutes looked identical. A row that goes quiet now turns amber, then red.
 
-
 - [#30](https://github.com/Pythoughts-labs/pythinker-code/pull/30) [`463b176`](https://github.com/Pythoughts-labs/pythinker-code/commit/463b1766a80389fe44cd675bff29b83b3ce6c86b) - Let a Dynamic Workflow run its subagents on a different model than the agent orchestrating them. `DynamicWorkflow` accepts `model` and `effort` for every subagent in the call, and `/workflow model <alias>` sets that model for the session so an expensive orchestrator can hand mechanical work to a cheaper or faster one.
 
 ### Patch Changes
@@ -50,7 +66,6 @@
 
 - [#38](https://github.com/Pythoughts-labs/pythinker-code/pull/38) [`44efbc7`](https://github.com/Pythoughts-labs/pythinker-code/commit/44efbc77360105de0efce185c86740fcf503944e) - Stop offering an update with no build for the running platform, give every installer network call a timeout, expire a stale install lease instead of blocking updates forever, and say which version is installing and why a failed one stopped retrying.
 
-
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Survive two malformed inputs that used to end a run. A catalog entry that is not an object is now dropped when the catalog is read, instead of reaching the provider picker and throwing past the bundled-catalog fallback that was meant to save the login. A non-finite subagent concurrency limit now falls back to the default: `NaN` passed every clamp, and each free-slot test against it was false, so the batch launched nothing and never finished.
 
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Offer a model's declared thinking-effort levels when signing in to OpenAI Codex. The picker previously fell back to low / medium / high regardless of what the model supports, disagreeing with the effort list recorded in the config it then wrote.
@@ -77,14 +92,12 @@
 
 - [#32](https://github.com/Pythoughts-labs/pythinker-code/pull/32) [`a504a82`](https://github.com/Pythoughts-labs/pythinker-code/commit/a504a820c4d9db14e213f4a021c86b048c4b916d) - Show the whole large-workflow warning in the editor extension. The line was truncated to the panel width, so in a narrow side panel the reader saw the opening words and no reason.
 
-
 - [#28](https://github.com/Pythoughts-labs/pythinker-code/pull/28) [`cf5b6b1`](https://github.com/Pythoughts-labs/pythinker-code/commit/cf5b6b16e999431bd1a8f511c09883c330fc569d) - Keep a subagent on the model and effort its profile assigns when the subagent is resumed or retried, instead of reverting it to the main agent's model.
 
 - [#31](https://github.com/Pythoughts-labs/pythinker-code/pull/31) [`e5e9de4`](https://github.com/Pythoughts-labs/pythinker-code/commit/e5e9de46f0f51be6f3ab3d03d59a5841779c2215) - Brighten the periwinkle accent in the VS Code extension's dark theme so inline code in chat is easier to read.
 
 - [#31](https://github.com/Pythoughts-labs/pythinker-code/pull/31) [`e5e9de4`](https://github.com/Pythoughts-labs/pythinker-code/commit/e5e9de46f0f51be6f3ab3d03d59a5841779c2215) - Let `/yolo` and `/auto` be used in the VS Code extension before the first message is sent — the request now applies to the session that chat opens next instead of failing with "Could not change the permission mode."
 
-
 - [#24](https://github.com/Pythoughts-labs/pythinker-code/pull/24) [`ae01098`](https://github.com/Pythoughts-labs/pythinker-code/commit/ae01098b862a567552c7d49a6d5bd1808077a794) - Fix the Dynamic Workflow card showing `[object Object]`, phantom extra agent rows, and tool labels fused into streamed text when a workflow is called with object items.
 
 - [#24](https://github.com/Pythoughts-labs/pythinker-code/pull/24) [`ae01098`](https://github.com/Pythoughts-labs/pythinker-code/commit/ae01098b862a567552c7d49a6d5bd1808077a794) - Show Dynamic Workflow member progress from the observed stage only, so a running subagent no longer sits at 99% for the rest of its run.

apps/pythinker-code/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pythoughts/pythinker-code",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "description": "The Starting Point for Next-Gen Agents",
   "license": "MIT",
   "author": "Pythoughts",

apps/vscode/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 0.8.8
+
+### Patch Changes
+
+- Updated dependencies [[`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950)]:
+  - @pythoughts/pythinker-code-sdk@0.14.0
+
 ## 0.8.7
 
 ### Patch Changes

apps/vscode/package.json

@@ -3,7 +3,7 @@
   "publisher": "pythoughts",
   "displayName": "Pythinker Code",
   "description": "Pythinker Code extension for VS Code",
-  "version": "0.8.7",
+  "version": "0.8.8",
   "private": true,
   "license": "Apache-2.0",
   "type": "module",

packages/node-sdk/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @pythoughts/pythinker-code-sdk
 
+## 0.14.0
+
+### Minor Changes
+
+- [#41](https://github.com/Pythoughts-labs/pythinker-code/pull/41) [`e534040`](https://github.com/Pythoughts-labs/pythinker-code/commit/e534040c82d1e3b8c217e6e35ddcf248065ff950) - Fix `/workflow save` leaving the saved workflow uncallable until the session was reloaded, and add `Session.reloadSkills()` to re-discover skills written while a session is open.
+
 ## 0.13.0
 
 ### Minor Changes

packages/node-sdk/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pythoughts/pythinker-code-sdk",
-  "version": "0.13.0",
+  "version": "0.14.0",
   "private": true,
   "description": "TypeScript SDK for the Pythinker Code Agent",
   "license": "MIT",