From 8f6fc9d1afa6fea5230f5c637926cb8bfed8555d Mon Sep 17 00:00:00 2001 From: "m2 (AI Agent)" Date: Thu, 2 Jul 2026 05:19:56 +0200 Subject: [PATCH] wedge: verification gaps updated, run report addendum Co-Authored-By: Claude Fable 5 --- specs/001-market-first-wedge/VERIFICATION.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/specs/001-market-first-wedge/VERIFICATION.md b/specs/001-market-first-wedge/VERIFICATION.md index d24ffd3..760159c 100644 --- a/specs/001-market-first-wedge/VERIFICATION.md +++ b/specs/001-market-first-wedge/VERIFICATION.md @@ -29,8 +29,9 @@ Date: 2026-07-02 · Verifier: orchestrator (Claude Fable, factory loop) · State ## Known gaps / follow-ups 1. T031 third seed — operator decision (email-triage commercialization or alternative). -2. T040 Store canary deploy (chris-m2o, gunnar-m2o) + Scenario F. -3. T042–T044 Scout v0 as a Hermes plugin per scout/SPIKE.md + Scenario G. +2. chris-m2o's m2-gpt tenant key gets 401 "User not found" — blocks real LLM turns on that + desktop (fleet auth issue, surfaced by Scenario G; Scout hook dispatch itself verified). +3. Scout end-to-end through a REAL Hermes-dispatched turn — pending the 401 fix above. 4. Publish status flow (analyze I2): merge doesn't auto-flip `status: published` — manual step documented in runbook until automated. 5. memory-api partition CRUD (fedlearn T13 follow-up) unlocks true in-place reindex,