Prevent sampleless speaker identities

openspec/specs/meeting-session/spec.md

@@ -208,9 +208,9 @@ The rules editor `write_rules` tool SHALL replace the whole configured workflow
 
 The rules editor `write_rules` tool SHALL refuse invalid YAML without changing the configured workflow rules file.
 
-The rules and identities editor agent SHALL receive speaker identity tools to search/list, read, create, update, delete, and merge identities in the local speaker identity database.
+The rules and identities editor agent SHALL receive speaker identity tools to search/list, read, update, delete, and merge identities in the local speaker identity database, and a create tool that refuses sampleless identity creation with an actionable response.
 
-The rules and identities editor agent SHALL receive speaker sample tools to list, read, delete, and queue playback of samples linked to identities.
+The rules and identities editor agent SHALL receive speaker sample tools to list, read, delete, and queue playback of samples linked to identities. The delete sample tool SHALL refuse to delete the last remaining sample for an identity.
 
 The first model request caused by each user-submitted chat turn SHALL send the `X-Initiator: user` header, while follow-up model requests within that same turn, such as tool-call continuations, SHALL send `X-Initiator: agent`.
 
@@ -259,8 +259,10 @@ Meeting Assistant SHALL provide a diagnostic endpoint that opens the workflow ru
 #### Scenario: Rules editor can manage speaker identities
 - **GIVEN** the speaker identity database contains speaker identities and samples
 - **WHEN** the rules editor agent runs
-- **THEN** it can search, read, create, update, delete, and merge speaker identities
+- **THEN** it can search, read, update, delete, and merge speaker identities
+- **AND** sampleless identity creation is refused with an actionable response
 - **AND** it can list, read, delete, and queue playback of identity samples
+- **AND** deleting the last sample for an identity is refused
 
 #### Scenario: User sends a rules-editing chat turn
 - **GIVEN** the rules editor chat window is open

openspec/specs/meeting-transcription/spec.md

@@ -215,7 +215,7 @@ The configured maximum snippet count per identity SHALL prevent unbounded growth
 
 Live speaker matching SHALL be read-only with respect to the speaker identity database. Candidate elimination, canonical promotion, transcription counters, stored snippet updates, and new unmatched identity creation SHALL happen only after transcription is finished and after automatic summary generation has completed, using the latest meeting note frontmatter.
 
-When the summary agent records a speaker override from a diarized transcript label to a named speaker, final speaker identity processing SHALL attach the current run speaker sample to an existing identity with that name when one exists, or create a new canonical speaker identity with that name when none exists.
+When the summary agent records a speaker override from a diarized transcript label to a named speaker, final speaker identity processing SHALL attach the current run speaker sample to an existing identity with that name when one exists, or create a new canonical speaker identity with that name when none exists. Meeting Assistant SHALL NOT create a new speaker identity for an override when no current run sample or current run candidate can be resolved for the source speaker label.
 
 When a speaker override maps a current-run unnamed candidate to an existing named identity, Meeting Assistant SHALL merge the candidate's meeting reference and useful snippets into the named identity instead of leaving a duplicate candidate.
 
@@ -253,6 +253,13 @@ When the summary agent records that a speaker identity was wrongfully matched, f
 - **THEN** Meeting Assistant creates a canonical speaker identity named `Sabrina`
 - **AND** stores the meeting reference and current speaker sample on that identity
 
+#### Scenario: Speaker override with missing source sample is skipped
+- **GIVEN** the speaker identity database has no accepted name `Sabrina`
+- **AND** the summary agent records that transcript speaker `Guest-5` is `Sabrina`
+- **AND** final speaker identity processing has no sample or segment for `Guest-5`
+- **WHEN** final speaker identity processing runs
+- **THEN** Meeting Assistant does not create a speaker identity for `Sabrina`
+
 #### Scenario: Speaker identity deletion removes a wrong match
 - **GIVEN** the speaker identity database contains canonical speaker `Sabrina`
 - **AND** the summary agent records that `Sabrina` was wrongfully matched