⚖MikeWatch Forks of the Mike legal-AI codebase, distilled for legal-tech readers
Home · dropthejase/louis · this thread

dropthejase rips out the off-the-shelf chat memory

After wiring up the framework's built-in session manager, the fork tore it out and rebuilt conversation history by hand.

chat-uiinfrastructure

dropthejase first took the obvious path: plug in the session manager that ships with Strands (the agent framework Mike is built on) and let it stash chat transcripts in S3, Amazon's cloud file store. That got conversations surviving a page refresh and reloading from a stored snapshot.

Then the fork reversed course. The built-in manager didn't give the team enough control over what gets replayed when a user reopens a chat - specifically, the tool activity and reasoning steps that make an AI conversation legible after the fact. So they replaced it with their own persistence layer and quietly stopped writing to the database table they'd originally set up for chat messages. History now lives in S3, full stop.

So what Anyone building a legal chat product on Strands should treat the bundled session manager as a starting demo, not a foundation - if you want a usable transcript, you're writing the storage yourself.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

10 commits from dropthejase/louis, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
6905873f refactor(frontend): merge streamChat functions, wire runtimeSessionId, write messages to Supabase, hydrate on load Jason Lee 2026-05-07 ↗ GitHub
commit body 
Merges streamChat/streamProjectChat into a single streamChat taking prompt
directly. Generates runtimeSessionId per chat (handleNewChat) and loads it
from chats.agentcore_session_id for existing chats. Writes user and
assistant messages to Supabase chat_messages (removed from the agent).
Hydrates message history from Supabase when opening an existing chat.
619f3d1f feat(agent): wire S3SessionManager for conversation persistence Jason Lee 2026-05-07 ↗ GitHub 
Add SessionManager with S3Storage to createAgent; when a sessionId is
provided the agent auto-persists and restores full message history to
the sessions bucket after each invocation.
702b9381 feat(backend,frontend,infra): chat history from S3 snapshot; sessions bucket Jason Lee 2026-05-07 ↗ GitHub
commit body 
Add GET /chat/:chatId/messages backend route that reads the Strands
snapshot_latest.json from S3 and transforms it into MikeMessage[].
Replace Supabase chat_messages hydration in useAssistantChat with a
call to this endpoint; remove frontend chat_messages writes. Add
sessionsBucket to StorageStack and wire SESSIONS_BUCKET_NAME env var
into ApiStack Lambda.
e63a501b feat: AgentCore user ID header, session ID format, Cognito-compatible schema Jason Lee 2026-05-08 ↗ GitHub
40c1e3ad feat: persist AgentCore session ID for multi-turn continuity across refreshes Jason Lee 2026-05-08 ↗ GitHub
commit body 
- Add agentcore_session_id + agentcore_session_created_at columns to chats schema
- Add PUT /chat/:chatId/session-id endpoint - writes on first turn, no-ops if already set
- Frontend saves runtimeSessionId to DB after each turn (fire-and-forget)
- On chat load, GET /chat/:chatId/session-id restores the session ID so
  AgentCore can resume the correct S3 snapshot after page refresh
af04dc99 fix: persist AgentCore session ID on chat_id SSE event, not post-stream Jason Lee 2026-05-08 ↗ GitHub 
Previously saved after stream completed - tab-close mid-stream lost the
session ID. Now fires immediately when the chat_id event arrives (first
SSE event, before AgentCore runs) so any interruption still persists it.
ae70567f fix(chat): load messages from S3 snapshot instead of empty chat_messages table Jason Lee 2026-05-12 ↗ GitHub
commit body 
- getChat() now calls GET /chat/:chatId and GET /chat/:chatId/messages in parallel; messages come from S3 AgentCore session snapshot
- Fix snapshotMessagesToMikeMessages to accept content blocks with no type field (Strands snapshot omits type on text blocks)
- Update FEATURE-PARITY.md with pending items: tier display, account settings parity, credit enforcement
efdae23d feat(agents,api): replace SessionManager with manual S3 conversation persistence Jason Lee 2026-05-13 ↗ GitHub
commit body 
Drop Strands SessionManager/S3Storage (baked stale system prompt into every
turn). Own S3 read/write via AfterInvocationEvent hook on conversations/{chatId}/messages.json.
System prompt always fresh from code. API chat history reads same key directly.
838d29ba Merge feature/session-persistence-without-s3sessionamanger into development Jason Lee 2026-05-13 ↗ GitHub
febe83f5 fix(api): restore tool activity + reasoning blocks on chat history reload Jason Lee 2026-05-13 ↗ GitHub
commit body 
snapshotMessagesToMikeMessages now handles nested Strands snapshot format:
- toolUse/toolResult blocks use nested objects (no type field) not flat Bedrock format
- reasoning blocks parsed and emitted as reasoning events
- text block filters exclude nested blocks to avoid false matches
- read_document filename extracted from document_metadata block in result text

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-334.md from inside the repo you want the changes in.

⬇ Download capture-thread-334.md