Implement Meeting Context V1 and extraction improvements

Introduce Meeting Context V1 with YAML schema, validation and template. Support optional --meeting-context during chunk extraction. Inject authoritative Meeting Context into extraction prompts. Record Meeting Context provenance in extraction output. Activate todos.md in shared prompt assembly. Strengthen responsibility attribution and decision/todo boundaries. Add focused Gold scenarios and validation tests. Update architecture and pipeline documentation.
2026-08-01 16:49:48 +02:00
parent 63075eaca9
commit 06f0e7e651
25 changed files with 1453 additions and 22 deletions
@@ -0,0 +1,74 @@
+# Meeting Context V1 template.
+# This file is manually maintained. Enter only objective context that is known
+# before or independently of model output.
+schema_version: "1"
+
+meeting:
+  # Human-readable title for the meeting.
+  title: ""
+  # Dominant meeting language, for example "de" or "en".
+  language: "de"
+  # Optional ISO date. Leave null if unknown.
+  date: null
+  # Optional meeting objective. Do not infer it from generated summaries.
+  objective: ""
+  # Optional neutral notes about context, scope or source material.
+  notes: ""
+
+participants:
+  # participant_id must remain stable across corrections and later runs.
+  # Use aliases for alternative spellings, short names or Whisper variants.
+  # attendance_status distinguishes actual participants from mentioned persons.
+  # role and department may remain null; uncertain values must not be guessed.
+  - participant_id: ""
+    display_name: ""
+    aliases: []
+    role: null
+    department: null
+    attendance_status: "present"
+    notes: null
+
+mentioned_people:
+  # People discussed or referenced but not present in the meeting.
+  # Mentioned people are not speakers and must not become responsible persons
+  # unless the meeting evidence explicitly assigns or confirms responsibility.
+  - person_id: ""
+    display_name: ""
+    aliases: []
+    role: null
+    department: null
+    attendance_status: "not_present"
+    notes: null
+
+organization:
+  name: null
+
+  departments:
+    # Department ids should be stable. aliases capture spelling variants.
+    - id: ""
+      name: ""
+      aliases: []
+
+  abbreviations:
+    # Fill in only abbreviations that are known for this meeting context.
+    # Leave values empty when expansion is unknown.
+    PM: ""
+    BD: ""
+    MK: ""
+    GF: ""
+
+known_entities:
+  # Relevant projects, products, systems, locations and technical terms.
+  # These lists provide vocabulary only; they must not imply responsibility.
+  projects: []
+  products: []
+  systems: []
+  locations: []
+  technical_terms: []
+
+context_rules:
+  participant_list_is_authoritative: true
+  do_not_infer_roles: true
+  do_not_infer_departments: true
+  do_not_infer_responsibilities: true
+  mentioned_people_are_not_participants: true