refactor(messaging): project inter-agent messages into pi session transcript
Inter-agent messages previously entered the recipient's context as a separate prompt block (recentMessages), rebuilt every turn. This double- charged tokens and kept messages outside pi's native AgentMessage stream. Now at prepareRun: pull the recipient's unread inbox, project each AgentMessageRecord into a pi user-role AgentMessage, persist to SqliteSessionStore, and mark delivered. The recipient reads messages as natural conversation turns in the transcript. - db: listAgentInboxUnread + markAgentInboxDelivered (transactional) - agent-runtime/inbox-projection.ts: AgentMessageRecord -> pi AgentMessage - runtime-bridge.prepareRun: inject + deliver before loadMessages - prompt-builder: delete recentMessages context block + buildMessagesSection - message-normalize: drop unused normalizeMessagesForPrompt - delete prompt-builder/attachment-resolver.ts (orphan after section removal) Send path (api-server/routes-messages, ipc, UI) unchanged — inbox table remains the UI source. Transactional delivery marking prevents duplicate injection across runs. Failed append -> no mark -> retry on next run.
This commit is contained in:
1 parent
5547c29491
commit
b50716d4e8
11 files changed
+254
-175
No files matched your search
@@ -120,6 +120,7 @@ export class AppDatabaseBase {
|
||||
this.messages = buildMessageMethods(getDb, ra, {
|
||||
getAgent: (id) => this.getAgent(id),
|
||||
addActivity: (input) => this.addActivity(input),
|
||||
transaction: tx,
|
||||
});
|
||||
this.runs = buildRunMethods(getDb, ra, tx, { logsDir: this.logsDir });
|
||||
this.workspacesMod = buildWorkspaceMethods(getDb, ra, tx);
|
||||
|
||||
Reference in new issue
Block a user