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.

samples/real_live/project_process_meeting/README.md

@@ -31,6 +31,9 @@ Original input files:
 
 Reference material:
 
+- `meeting_context.yaml`: manually maintained Meeting Context V1 scaffold for
+  reliable metadata. It can be validated and injected into chunk extraction
+  with `--meeting-context`; later pipeline stages are not connected yet.
 - `reference/human_reference_protocol.md`: not currently included. No exact
   existing human-written protocol file was found in the repository workspace.
 

samples/real_live/project_process_meeting/meeting_context.yaml

@@ -0,0 +1,135 @@
+schema_version: "1"
+
+meeting:
+  meeting_id: "2026-07-27-projektprozess"
+  title: "Projektprozess für neue Projektideen in F&E, Marketing und Business Development"
+  language: "de"
+  date: 2026-07-27
+  objective: ""
+  notes: "Manuell gepflegter Kontext; noch nicht an die Pipeline angeschlossen."
+
+participants:
+
+  - participant_id: "martin"
+    display_name: "Martin"
+    aliases:
+      - "Martin Tazl"
+      - "Herr Tazl"
+    role: "Leiter F&E und Technik"
+    department_id: "fe"
+    attendance_status: "present"
+    notes: null
+
+  - participant_id: "lars"
+    display_name: "Lars"
+    aliases:
+      - "Lars Vollmert"
+      - "Herr Vollmert"
+    roles:
+      - "Leiter EDD"
+      - "Leiter Product Management"
+    department_id: "pm"
+    attendance_status: "present"
+    notes: null
+
+  - participant_id: "malte"
+    display_name: "Malte"
+    aliases:
+      - "Jan-Malte"
+      - "Herr Schnau"
+    role: "Product Manager GreenLine"
+    department_id: "pm"
+    attendance_status: "present"
+    notes: null
+
+  - participant_id: "bjoern"
+    display_name: "Björn"
+    aliases:
+      - "Björn-Erik"
+      - "Herr Falkenau"
+    role: "Leiter Marketing"
+    department_id: "mk"
+    attendance_status: "present"
+    notes: null
+
+mentioned_people:
+
+  - person_id: "jovana"
+    display_name: "Jovana"
+    aliases:
+      - "Jovana Husemann"
+      - "Frau Husemann"
+      - "Giovanna"
+      - "Jovanna"
+      - "Giovana"
+    role: "Leiterin Business Development"
+    department_id: "bd"
+    attendance_status: "not_present"
+    notes: null
+
+organization:
+
+  name: "Naue GmbH & Co. KG"
+
+  departments:
+
+    - id: "fe"
+      name: "F&E"
+      aliases:
+        - "Forschung und Entwicklung"
+        - "Research and Development"
+
+    - id: "pm"
+      name: "Product Management"
+      aliases: []
+
+    - id: "mk"
+      name: "Marketing"
+      aliases: []
+
+    - id: "bd"
+      name: "Business Development"
+      aliases: []
+
+  abbreviations:
+
+    PM: "Product Management"
+    BD: "Business Development"
+    MK: "Marketing"
+    GF: "Geschäftsführung"
+
+known_entities:
+
+  projects: []
+
+  products:
+    - "Bentofix"
+    - "Carbofol"
+    - "Combigrid"
+    - "Secugrid"
+    - "Secutex"
+    - "SoftRock"
+
+  systems: []
+
+  locations:
+    - "Adorf"
+    - "Bückeburg"
+    - "Espelkamp"
+    - "Malaysia"
+
+  technical_terms: []
+
+context_rules:
+
+  participant_list_is_authoritative: true
+
+  do_not_infer_roles: true
+
+  do_not_infer_departments: true
+
+  do_not_infer_responsibilities: true
+
+  do_not_infer_attendance: true
+
+  mentioned_people_are_not_participants: true

samples/templates/meeting_context.template.yaml

@@ -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