feat: Implement well-known typed fields for verdicts in output models

feat(tests): add tests for handling first-person openers in clean_clue function

feat: implement streaming agent responses and enhance conversation flow with repeat guards

feat(core): add resilient loop and shared blackboard

feat: Instructor-validated structured output on the live path

feat: phase 2 architecture — manifest system, structured output, salience memory, SQLite ledger, observer