story-kit: remove 266_story_matrix_bot_structured_conversation_history

.story_kit/work/1_upcoming/266_story_matrix_bot_structured_conversation_history.md

@@ -1,35 +0,0 @@
----
-name: "Matrix bot structured conversation history"
----
-
-# Story 266: Matrix bot structured conversation history
-
-## User Story
-
-As a user chatting with the Matrix bot, I want it to remember and own its prior responses naturally, so that conversations feel like talking to one continuous entity rather than a new instance each message.
-
-## Problem
-
-The bot currently flattens per-room conversation history into a text prefix (`build_context_prefix`) prepended to each new message. Claude sees this as third-party context rather than its own prior responses, causing it to feel disconnected and not take ownership of things it previously said.
-
-Additionally, history is in-memory only (`HashMap` initialized on startup) — any server restart wipes all conversation state.
-
-## Acceptance Criteria
-
-- [ ] Conversation history is passed as structured API messages (user/assistant turns) rather than a flattened text prefix
-- [ ] Claude recognises its prior responses as its own, maintaining consistent personality across a conversation
-- [ ] Per-room history survives server restarts (persisted to disk or database)
-- [ ] Rolling window trimming still applies to keep context bounded
-- [ ] Multi-user rooms still attribute messages to the correct sender
-
-## Technical Notes
-
-- `build_context_prefix()` in `bot.rs` is the current flattening logic
-- The Claude API accepts a `messages` array with `role: "user"` / `role: "assistant"` — use this instead of text serialization
-- `ConversationHistory` type at line 58 of `bot.rs` already has the right structure, it just needs to be passed through properly
-- For persistence, consider SQLite (already a dependency via matrix-sdk) or simple JSON files per room
-
-## Out of Scope
-
-- Infinite history / summarization of old context
-- Cross-room memory