story-kit: accept 233_story_auto_assign_backoff_for_failed_merge_items

.story_kit/work/6_archived/227_bug_thinking_traces_visible_in_agents_panel_in_release_builds_only.md

@@ -0,0 +1,28 @@
+---
+name: "Thinking traces visible in Agents panel in release builds only"
+---
+
+# Bug 227: Thinking traces visible in Agents panel in release builds only
+
+## Description
+
+Thinking traces from extended-thinking blocks are visible in the Agents panel in release builds but not in debug builds. The frontend code correctly ignores "thinking" events in the AgentPanel switch statement (they hit the default no-op case), so this may be a timing/buffering issue where release-mode speed causes events to be processed differently, or a stale frontend bundle issue.
+
+## How to Reproduce
+
+1. Build backend and frontend in release mode
+2. Start an agent on a story
+3. Observe the Agents panel in the web UI
+
+## Actual Result
+
+Thinking traces are visible in the Agents panel output in release builds.
+
+## Expected Result
+
+Thinking traces should be hidden from the Agents panel in all build modes. Only regular output, status changes, and errors should be displayed.
+
+## Acceptance Criteria
+
+- [ ] Thinking traces are not visible in the Agents panel in release builds
+- [ ] Thinking traces are not visible in the Agents panel in debug builds

.story_kit/work/6_archived/233_story_auto_assign_backoff_for_failed_merge_items.md

@@ -0,0 +1,22 @@
+---
+name: "Auto-assign backoff for failed merge items"
+---
+
+# Story 233: Auto-assign backoff for failed merge items
+
+## User Story
+
+As a supervisor, I want auto-assign to stop retrying stories in 4_merge/ that have repeatedly failed, so that one broken merge doesn't block the entire queue and burn API credits in an infinite loop.
+
+## Acceptance Criteria
+
+- [ ] When a mergemaster agent completes with gates_passed=false, the story_id is added to a persistent failure set (in-memory is fine, survives across agent completions but not server restarts)
+- [ ] auto_assign_available_work skips items in 4_merge/ that are in the failure set
+- [ ] The failure set is cleared for a story when: a) the story file is manually moved out of 4_merge/, or b) a human explicitly calls start_agent for it
+- [ ] Empty squash merges (merge succeeds but nothing staged) produce a clear, non-retryable error message explaining the feature branch has no unique changes vs master
+- [ ] Regression test: mergemaster fails on story X, auto-assign runs, story X is NOT re-assigned
+- [ ] Regression test: after manual start_agent clears the failure, auto-assign can pick it up again
+
+## Out of Scope
+
+- TBD