Synchronize recording lifecycle regression tests

openspec/changes/archive/2026-05-19-define-meeting-assistant-v1/specs/meeting-summary/spec.md

@@ -58,6 +58,12 @@ The summary agent SHALL be able to read and write the assistant context body as
 - **WHEN** transcription, final speaker recognition, and summary generation progress
 - **THEN** Meeting Assistant updates assistant context frontmatter state to `transcribing`, `speaker recognition`, `summarizing`, `finished`, or `error` as appropriate
 
+#### Scenario: Summary failure follows initialized transcription
+- **GIVEN** a meeting has completed its initial metadata collection and reached `transcribing`
+- **WHEN** recording stops and automatic summary generation fails
+- **THEN** assistant context transitions from `transcribing` to `summarizing` and then `error`
+- **AND** observing captured audio alone does not establish that metadata collection has finished
+
 #### Scenario: Summary pipeline is invoked
 - **WHEN** transcript processing finishes for the current meeting
 - **THEN** the agent can read the transcript, assistant context, user notes, glossary, and bound project knowledge, can write the finished markdown summary to the configured summary note, and can update existing project files