create-agdf 0.30.0 → 0.32.0

package/generated/.agdf/control/README.md

@@ -11,6 +11,7 @@ Explicit initialization creates `control_layout: "run-folders-v1"`. This is the
   SOT_REGISTRY.md
   CONTEXT_GRAPH.md
   AGENT_QUALITY_CONTRACTS.json
+  BRAND.md
   templates/
   planned/<plan_id>/UR.md
   runs/<run_id>/
@@ -28,6 +29,10 @@ Explicit initialization creates `control_layout: "run-folders-v1"`. This is the
 
 Configuration, templates and curated project context stay project-wide. A multi-Run closure preview is a target-wide decision proposal under `closure-previews/`; it changes no Run until deliberately applied. Run-owned outputs never use a separate top-level artefacts directory.
 
+`BRAND.md` starts as a neutral English worksheet. Complete it with the project's
+own design intent and declare the finished source in `SOT_REGISTRY.md` when it is
+authoritative for design work.
+
 `RUN_STATE.md` keeps identity, objective, mode and typed decisions, source bindings and operations. Approval status, current gate, current document references, relationship chains, evidence summaries and inventory are derived when read. They are not separately writable tables or a second state file. A binding embeds its reviewer attestation; no separate RECORD/REVIEW JSON repeats its mapping. A planned handoff records its source in the creation receipt and immutable planning snapshot, without an origin JSON copy.
 
 Create a fresh scaffold in an explicitly confirmed existing Git repository:

package/generated/.agdf/control/templates/BRAND.md

@@ -0,0 +1,28 @@
+# Brand and Design Intent
+
+Complete this worksheet with confirmed project decisions. Declare the completed
+profile in `SOT_REGISTRY.md` when it is the project's authoritative design source.
+
+## Owner and scope
+
+Name the accountable owner, the product, and the surfaces and audiences covered.
+
+## Design intent
+
+Describe what people should understand, feel, or be able to do when using the
+product. Tie each priority to a concrete user task or situation.
+
+## Information and visual priorities
+
+Explain what deserves emphasis in relevant states and how the project balances
+competing priorities. Record any confirmed constraints and their sources.
+
+## Observable checks
+
+For each applicable priority, name the scenario, the expected observable outcome,
+and the evidence that would verify it. Record open decisions with their owners.
+
+## Related sources
+
+Link the project's design system, implementation values, and brand usage policy
+where applicable.

package/generated/.agdf/control/templates/artefacts/PRD.md

@@ -69,6 +69,17 @@ visible feedback, blocker/failure behavior, recovery/next action, observable suc
 evidence. Specify observable behavior, not implementation. Do not leave the section empty or retain
 placeholders when requesting approval.
 
+Use separate field names; never combine them (for example,
+`observable_success_required_evidence` is not `observable_success`). For same-language approval,
+each criterion needs at least one nonempty `observable_success`, `visible_feedback` or
+`expected_effective_state`. Keep applicable UX fields separate as well. Example:
+
+```markdown
+- criterion_id: AC-001
+  - observable_success: A later list command shows the saved task unchanged.
+  - required_evidence: A real CLI test across separate processes.
+```
+
 ## 6. Non-Goals
 
 What remains out of scope?

package/generated/.agdf/control/templates/artefacts/SD.md

@@ -25,6 +25,10 @@ Use stable IDs. If no binding design decision is needed, record one reasoned bul
 When a decision selects or changes external technology (framework, library, API, protocol,
 service or major version), name the checked authoritative source, version and check date in its
 rationale.
+Quoted CLI arguments such as `done <id>` are literal syntax. In a decision clause, a labelled
+inline JSON schema/example may use quoted type metavariables such as `"<uuid>"` and
+`"<non-empty string>"`; keep actual choices, rationale and consequence concrete. The complete
+notation and unresolved-prompt boundary are defined in `meta/contracts/sd-definition.md`.
 
 ## 4. Integration Points
 

package/generated/.agdf/control/templates/artefacts/UX_INTENT_DEFINITION.md

@@ -1,7 +1,7 @@
 # UX Intent Definition: <Title>
 
 Status: draft | ready | blocked | not_applicable
-Decision: ready | blocked | not_applicable
+- decision: ready | blocked | not_applicable
 Based on: approved UR and post-UR routing evidence
 Date:
 Owner:

package/generated/.opencode/agdf-interaction-locales.json

@@ -746,7 +746,12 @@
         "currentRunRecordEvidence": "Record actual evidence through the current Run evidence owner.",
         "currentRunSelectNoConversion": "Select a valid current Run; unsupported control is never converted automatically.",
         "currentRunCreateWithUuid": "create a current Run with an operation UUID",
-        "currentUrPersistBeforeApproval": "Create or select the current Run, then persist its UR revision before requesting approval."
+        "currentUrPersistBeforeApproval": "Create or select the current Run, then persist its UR revision before requesting approval.",
+        "blockedPrdReadiness": "PRD criteria or required sources are incomplete",
+        "blockedApprovalSummary": "The required approval summary is incomplete",
+        "completeApprovalSummary": "complete the current artefact approval summary and record a new run revision",
+        "forbidApprovalBeforeSummaryReady": "present or approve the current artefact before its required approval summary is ready",
+        "nextApprovalSummary": "complete the current artefact approval summary, then record the revision through the inspected current recording operation"
       },
       "scopeClassification": {
         "title": "AGDF scope classification",
@@ -1333,6 +1338,8 @@
           "stop": "Stop and inspect supported diagnostics. Do not invent a repair, target or replacement operation."
         },
         "causes": {
+          "prepared_call_unknown": "Reference unavailable, not proven expired. Nothing dispatched. Observe/recover the saved original UUID and request; retain its target, revision and inputs.",
+          "prepared_call_store_unavailable": "Private call store unavailable; nothing dispatched. Retain the original request and UUID. Repair storage or use explicit original-request recovery.",
           "operation_source_invalid": "Check the referenced path, UTF-8 content and current canonical digest. Re-read the source reference; do not invent a path or hash.",
           "presentation_missing": "Read the current binding and prepare its presentation. Obtain the required bound human reply before approval; do not substitute an old presentation.",
           "closeout_not_ready": "Read the current gate and missing prerequisites. Complete required evidence and human decisions before closeout; this attempt cannot complete the Run.",
@@ -1345,6 +1352,216 @@
       },
       "doctorEmptyInventory": {
         "policyDescription": "No active Runs. Status follows allow_no_active_runs={policy}; zero findings. This is delivery policy, not a project-health verdict."
+      },
+      "companion": {
+        "title": "AGDF Companion",
+        "notices": {
+          "waitingApproval": "Waiting for approval: {gate}",
+          "waitingDecision": "Waiting for a decision: {gate}",
+          "blocked": "Blocked: {gate} – {decision}"
+        },
+        "decisions": {
+          "revise": "revision needed",
+          "block": "blocked",
+          "blocked": "blocked",
+          "decline": "declined"
+        },
+        "origin": {
+          "session": "Changed in this session",
+          "selected": "Selected by you",
+          "named": "Named in the chat"
+        },
+        "fields": {
+          "nextStep": "Next step",
+          "objective": "Objective",
+          "lastRead": "As of {time}",
+          "openRuns": "{count} open runs",
+          "moreRuns": "+ {count} more",
+          "position": "{position} of {count} open runs",
+          "events": "Events",
+          "material": "Material",
+          "newRun": "New run",
+          "gatePurpose": "What this gate decides",
+          "checkedFolder": "Checked project folder",
+          "finding": "Finding",
+          "step": "Step {position} of {count}"
+        },
+        "actions": {
+          "retry": "Read again",
+          "stillOn": "Stop motion",
+          "stillOff": "Start motion",
+          "noticeOff": "Notices off",
+          "noticeOn": "Notices on",
+          "soundOn": "Sound on",
+          "soundOff": "Sound off",
+          "expand": "More",
+          "collapse": "Less",
+          "infoShow": "ⓘ Details",
+          "infoHide": "ⓘ Hide details",
+          "previous": "Previous run",
+          "next": "Next run",
+          "about": "About",
+          "closeAbout": "Close",
+          "backToChat": "Back to chat run"
+        },
+        "about": {
+          "text": "Shows the state of your AGDF runs beside the chat. Read-only: approvals stay in the chat.",
+          "version": "AGDF plugin {version}"
+        },
+        "command": {
+          "description": "Switch the AGDF Companion on or off",
+          "enabled": "AGDF Companion switched on.",
+          "disabled": "AGDF Companion switched off.",
+          "waiting": "AGDF Companion is switched on and waits for space: {reason}"
+        },
+        "languageNames": {
+          "en": "English",
+          "de": "Englisch"
+        },
+        "states": {
+          "laeuft": "working",
+          "baut": "building",
+          "wartet": "waiting for approval",
+          "blockiert": "blocked",
+          "fertig": "done",
+          "bereit": "idle"
+        },
+        "statusStates": {
+          "laeuft": "working",
+          "baut": "building",
+          "wartet": "waiting",
+          "blockiert": "blocked",
+          "fertig": "done",
+          "bereit": "idle",
+          "notSetUp": "not set up",
+          "unreadable": "unreadable"
+        },
+        "reasons": {
+          "turnActive": "Claude is working on this turn",
+          "done": "Run completed",
+          "blocked": "{gate}: {decision}",
+          "waitingApproval": "Approval pending: {gate}",
+          "waitingDecision": "Decision pending: {gate}",
+          "working": "Next: {gate}",
+          "building": "In progress: {gate}",
+          "ended": "Run ended",
+          "idle": "No run shown",
+          "completionUnconfirmed": "Completion not confirmed",
+          "unreadable": "Run not readable: {reason}"
+        },
+        "routes": {
+          "quick_task": "Compact Delivery",
+          "verified_change": "Verified Change",
+          "structured": "Structured delivery",
+          "undecided": "Delivery path open"
+        },
+        "activity": {
+          "draft": {
+            "working": "drafting the {gate}",
+            "idle": "{gate} draft is next"
+          },
+          "analysis": {
+            "working": "analysing the existing system",
+            "idle": "System analysis is next"
+          },
+          "route": {
+            "working": "choosing the delivery path",
+            "idle": "Delivery path is next"
+          },
+          "build": {
+            "working": "building and testing",
+            "idle": "Implementation is next"
+          },
+          "review": {
+            "working": "reviewing the code",
+            "idle": "Code review is next"
+          },
+          "quality": {
+            "working": "checking the quality",
+            "idle": "Quality check is next"
+          },
+          "acceptance": {
+            "working": "preparing the acceptance",
+            "idle": "Acceptance is next"
+          },
+          "closeout": {
+            "working": "closing out",
+            "idle": "Closeout is next"
+          },
+          "other": {
+            "working": "working on: {step}",
+            "idle": "{step} is next"
+          }
+        },
+        "turn": {
+          "you": "Your turn",
+          "claude": "Claude is working",
+          "blocked": "Blocked",
+          "approve": "Approve {gate}",
+          "decide": "Decide: {gate}",
+          "inChat": "In the chat with “{approval}”",
+          "moment": "One moment",
+          "next": "Up next",
+          "drafting": "I'm preparing a draft for you: {step}",
+          "workingOn": "I'm working on it: {step}",
+          "draft": "Draft: {step}",
+          "resume": "Tell me in the chat when I should carry on."
+        },
+        "unreadable": {
+          "missing": "run state file missing or not readable",
+          "too_large": "run state file too large",
+          "run_version_unsupported": "run recorded in an older format",
+          "run_state_invalid": "run state invalid",
+          "control_layout_unsupported": "control folder layout not supported",
+          "control_invalid": "control folder configuration invalid",
+          "read_failed": "control folder could not be read",
+          "unavailable": "run view could not be obtained",
+          "exit": "run view command ended with an error",
+          "malformed": "run view returned an unexpected result",
+          "resource_denied": "access to the control folder was denied",
+          "source_changed": "control folder changed while reading",
+          "timeout": "reading the control folder took too long",
+          "resource_limit": "control folder exceeds a read limit"
+        },
+        "messages": {
+          "reading": "Reading run state …",
+          "noControl": "No AGDF control folder in “{folder}”.",
+          "notSetUp": "AGDF isn't set up in this project yet.",
+          "notSetUpHint": "Tell me in the chat if you'd like to use AGDF here – I'll set it up with you.",
+          "noOpenRuns": "No open runs in this project.",
+          "allRunsDone": "All runs across the line. 🏁",
+          "allRunsDoneHint": "What's next? Just tell me in the chat.",
+          "noRunsYet": "Starting grid empty.",
+          "noRunsYetHint": "Tell me in the chat what you have in mind – I'll get the first run ready.",
+          "noRunAssigned": "No run assigned",
+          "noRunAssignedHint": "No run changed in this session. Choose an open run to show it here.",
+          "unreadable": "Run state not readable: {reason}",
+          "stale": "Read failed at {time}; showing the state from {readAt}.",
+          "unreadableRuns": "{count} runs not readable: {reasons}",
+          "runViewUnavailable": "Run view unavailable: {reason}",
+          "eventsUnavailable": "Events unavailable; the run state is still read.",
+          "drift": "{document} changed after recording (recorded {recorded}, now {current}). Re-record it from the current file or restore the file."
+        },
+        "events": {
+          "approval_requested": "Approval requested for {gate}",
+          "approval_recorded": "Approval recorded for {gate}",
+          "write_rejected": "Call rejected ({reason})",
+          "effect_unknown": "Effect unknown – check the operation status",
+          "recovery_required": "Recovery required",
+          "run_completed": "Run completed",
+          "material_staged": "Material staged ({gate})",
+          "document_recorded": "{gate} recorded",
+          "drift": "{document} changed after recording",
+          "ofRun": "{text} · {run}"
+        },
+        "review": {
+          "summary": "{slot}: {bytes} bytes, {digest}",
+          "match": "matches its source file",
+          "mismatch": "differs from its source file",
+          "not_determinable": "source not determinable – please check the preview",
+          "unavailable": "facts unavailable",
+          "truncated": "preview truncated"
+        }
       }
     },
     "de": {
@@ -2080,7 +2297,12 @@
         "currentRunRecordEvidence": "Tatsächliche Nachweise über die dafür vorgesehene Funktion des aktuellen Runs erfassen.",
         "currentRunSelectNoConversion": "Einen gültigen aktuellen Run auswählen; nicht unterstützte Steuerungsdaten werden niemals automatisch konvertiert.",
         "currentRunCreateWithUuid": "einen aktuellen Run mit einer Operations-UUID anlegen",
-        "currentUrPersistBeforeApproval": "Den aktuellen Run anlegen oder auswählen und seine UR-Revision vor der Freigabeanfrage dauerhaft speichern."
+        "currentUrPersistBeforeApproval": "Den aktuellen Run anlegen oder auswählen und seine UR-Revision vor der Freigabeanfrage dauerhaft speichern.",
+        "blockedPrdReadiness": "Die PRD-Kriterien oder erforderlichen Quellen sind noch unvollständig",
+        "blockedApprovalSummary": "Die erforderliche Freigabezusammenfassung ist unvollständig",
+        "completeApprovalSummary": "die Freigabezusammenfassung des aktuellen Artefakts vervollständigen und eine neue Run-Revision erfassen",
+        "forbidApprovalBeforeSummaryReady": "das aktuelle Artefakt präsentieren oder freigeben, bevor seine erforderliche Freigabezusammenfassung vollständig ist",
+        "nextApprovalSummary": "die Freigabezusammenfassung des aktuellen Artefakts vervollständigen und die Revision dann über den geprüften aktuellen Erfassungsvorgang erfassen"
       },
       "scopeClassification": {
         "title": "AGDF-Scope-Klassifizierung",
@@ -2667,6 +2889,8 @@
           "stop": "Stoppen und unterstützte Diagnosen prüfen. Keine Reparatur, kein Ziel und keine Ersatzoperation erfinden."
         },
         "causes": {
+          "prepared_call_unknown": "Verweis nicht verfügbar, Ablauf unbelegt. Nichts ausgeführt. Originalanfrage und UUID prüfen/wiederaufnehmen; Ziel, Revision und Eingaben erhalten.",
+          "prepared_call_store_unavailable": "Privater Aufrufspeicher nicht verfügbar; nichts ausgeführt. Originalanfrage und UUID erhalten. Speicher reparieren oder Originalanfrage-Wiederaufnahme nutzen.",
           "operation_source_invalid": "Referenzierten path, UTF-8-Inhalt und aktuellen digest prüfen. Quellreferenz erneut lesen; keinen Pfad oder Hash erfinden.",
           "presentation_missing": "Aktuelle Bindung und Präsentation vorbereiten. Gebundene menschliche Antwort vor der Freigabe einholen; keine alte Präsentation einsetzen.",
           "closeout_not_ready": "Aktuelles Gate und fehlende Voraussetzungen lesen. Erforderliche Nachweise und menschliche Entscheidungen vor dem Abschluss erfüllen; jetzt kein Abschluss.",
@@ -2679,6 +2903,216 @@
       },
       "doctorEmptyInventory": {
         "policyDescription": "Keine aktiven Runs. Status folgt allow_no_active_runs={policy}; null Befunde. Dies ist Lieferrichtlinie, kein Urteil über den Projektzustand."
+      },
+      "companion": {
+        "title": "AGDF Companion",
+        "notices": {
+          "waitingApproval": "Wartet auf Freigabe: {gate}",
+          "waitingDecision": "Wartet auf Entscheidung: {gate}",
+          "blocked": "Blockiert: {gate} – {decision}"
+        },
+        "decisions": {
+          "revise": "Überarbeitung nötig",
+          "block": "blockiert",
+          "blocked": "blockiert",
+          "decline": "abgelehnt"
+        },
+        "origin": {
+          "session": "In dieser Sitzung geändert",
+          "selected": "Von dir ausgewählt",
+          "named": "Im Chat genannt"
+        },
+        "fields": {
+          "nextStep": "Nächster Schritt",
+          "objective": "Ziel",
+          "lastRead": "Stand {time}",
+          "openRuns": "{count} offene Runs",
+          "moreRuns": "+ {count} weitere",
+          "position": "{position} von {count} offenen Runs",
+          "events": "Ereignisse",
+          "material": "Material",
+          "newRun": "Neues Vorhaben",
+          "gatePurpose": "Wozu dieses Gate da ist",
+          "checkedFolder": "Geprüfter Projektordner",
+          "finding": "Befund",
+          "step": "Schritt {position} von {count}"
+        },
+        "actions": {
+          "retry": "Neu lesen",
+          "stillOn": "Bewegung aus",
+          "stillOff": "Bewegung an",
+          "noticeOff": "Meldung aus",
+          "noticeOn": "Meldung an",
+          "soundOn": "Ton an",
+          "soundOff": "Ton aus",
+          "expand": "Mehr",
+          "collapse": "Weniger",
+          "infoShow": "ⓘ Details",
+          "infoHide": "ⓘ Details ausblenden",
+          "previous": "Vorheriger Run",
+          "next": "Nächster Run",
+          "about": "About",
+          "closeAbout": "Schließen",
+          "backToChat": "Zurück zum Chat-Run"
+        },
+        "about": {
+          "text": "Zeigt den Zustand deiner AGDF-Runs neben dem Chat. Nur lesend: Freigaben bleiben im Chat.",
+          "version": "AGDF-Plugin {version}"
+        },
+        "command": {
+          "description": "AGDF Companion ein- oder ausschalten",
+          "enabled": "AGDF Companion eingeschaltet.",
+          "disabled": "AGDF Companion ausgeschaltet.",
+          "waiting": "AGDF Companion ist eingeschaltet und wartet auf Platz: {reason}"
+        },
+        "languageNames": {
+          "en": "German",
+          "de": "Deutsch"
+        },
+        "states": {
+          "laeuft": "läuft",
+          "baut": "baut",
+          "wartet": "wartet auf Freigabe",
+          "blockiert": "blockiert",
+          "fertig": "fertig",
+          "bereit": "bereit"
+        },
+        "statusStates": {
+          "laeuft": "läuft",
+          "baut": "baut",
+          "wartet": "wartet",
+          "blockiert": "blockiert",
+          "fertig": "fertig",
+          "bereit": "bereit",
+          "notSetUp": "nicht eingerichtet",
+          "unreadable": "nicht lesbar"
+        },
+        "reasons": {
+          "turnActive": "Claude arbeitet gerade an diesem Turn",
+          "done": "Run abgeschlossen",
+          "blocked": "{gate}: {decision}",
+          "waitingApproval": "Freigabe ausstehend: {gate}",
+          "waitingDecision": "Entscheidung ausstehend: {gate}",
+          "working": "Als Nächstes: {gate}",
+          "building": "In Arbeit: {gate}",
+          "ended": "Run beendet",
+          "idle": "Kein Run angezeigt",
+          "completionUnconfirmed": "Abschluss nicht bestätigt",
+          "unreadable": "Run nicht lesbar: {reason}"
+        },
+        "routes": {
+          "quick_task": "Compact Delivery",
+          "verified_change": "Verified Change",
+          "structured": "Strukturierte Lieferung",
+          "undecided": "Lieferweg noch offen"
+        },
+        "activity": {
+          "draft": {
+            "working": "schreibt am {gate}-Entwurf",
+            "idle": "{gate}-Entwurf steht an"
+          },
+          "analysis": {
+            "working": "analysiert den Bestand",
+            "idle": "Bestandsanalyse steht an"
+          },
+          "route": {
+            "working": "wählt den Lieferweg",
+            "idle": "Lieferweg steht an"
+          },
+          "build": {
+            "working": "baut und testet",
+            "idle": "Umsetzung steht an"
+          },
+          "review": {
+            "working": "prüft den Code",
+            "idle": "Code-Prüfung steht an"
+          },
+          "quality": {
+            "working": "prüft die Qualität",
+            "idle": "Qualitätsprüfung steht an"
+          },
+          "acceptance": {
+            "working": "bereitet die Abnahme vor",
+            "idle": "Abnahme steht an"
+          },
+          "closeout": {
+            "working": "schließt ab",
+            "idle": "Abschluss steht an"
+          },
+          "other": {
+            "working": "arbeitet an: {step}",
+            "idle": "{step} steht an"
+          }
+        },
+        "turn": {
+          "you": "Du bist dran",
+          "claude": "Claude arbeitet",
+          "blocked": "Blockiert",
+          "approve": "{gate} freigeben",
+          "decide": "Entscheidung treffen: {gate}",
+          "inChat": "Im Chat mit „{approval}“",
+          "moment": "Einen Augenblick",
+          "next": "Als Nächstes",
+          "drafting": "Ich bereite einen Entwurf für dich vor: {step}",
+          "workingOn": "Ich arbeite gerade daran: {step}",
+          "draft": "Entwurf: {step}",
+          "resume": "Sag mir im Chat, wenn ich weitermachen soll."
+        },
+        "unreadable": {
+          "missing": "Run-Datei fehlt oder ist nicht lesbar",
+          "too_large": "Run-Datei ist zu groß",
+          "run_version_unsupported": "Run in einem älteren Format erfasst",
+          "run_state_invalid": "Run-Zustand ungültig",
+          "control_layout_unsupported": "Aufbau des Kontrollordners nicht unterstützt",
+          "control_invalid": "Konfiguration des Kontrollordners ungültig",
+          "read_failed": "Kontrollordner konnte nicht gelesen werden",
+          "unavailable": "Run-Ansicht konnte nicht abgerufen werden",
+          "exit": "Run-Ansicht-Befehl endete mit einem Fehler",
+          "malformed": "Run-Ansicht lieferte ein unerwartetes Ergebnis",
+          "resource_denied": "Zugriff auf den Kontrollordner verweigert",
+          "source_changed": "Kontrollordner hat sich beim Lesen geändert",
+          "timeout": "Lesen des Kontrollordners dauerte zu lange",
+          "resource_limit": "Kontrollordner überschreitet eine Lesegrenze"
+        },
+        "messages": {
+          "reading": "Run-Status wird gelesen …",
+          "noControl": "Kein AGDF-Kontrollordner in „{folder}“.",
+          "notSetUp": "AGDF ist in diesem Projekt noch nicht eingerichtet.",
+          "notSetUpHint": "Sag mir im Chat, wenn du AGDF hier nutzen möchtest – ich richte es mit dir ein.",
+          "noOpenRuns": "Keine offenen Runs in diesem Projekt.",
+          "allRunsDone": "Alle Runs im Ziel. 🏁",
+          "allRunsDoneHint": "Was steht als Nächstes an? Sag's mir im Chat.",
+          "noRunsYet": "Startaufstellung leer.",
+          "noRunsYetHint": "Erzähl mir im Chat, was du vorhast – ich mach den ersten Run startklar.",
+          "noRunAssigned": "Kein Run zugeordnet",
+          "noRunAssignedHint": "In dieser Sitzung hat sich kein Run geändert. Wähle einen offenen Run, um ihn hier zu zeigen.",
+          "unreadable": "Run-Status nicht lesbar: {reason}",
+          "stale": "Lesen um {time} fehlgeschlagen; angezeigt wird der Stand von {readAt}.",
+          "unreadableRuns": "{count} Runs nicht lesbar: {reasons}",
+          "runViewUnavailable": "Run-Ansicht nicht verfügbar: {reason}",
+          "eventsUnavailable": "Ereignisse nicht verfügbar; der Run-Status wird weiter gelesen.",
+          "drift": "{document} wurde nach der Erfassung geändert (erfasst {recorded}, jetzt {current}). Aus der aktuellen Datei neu erfassen oder die Datei wiederherstellen."
+        },
+        "events": {
+          "approval_requested": "Freigabe angefragt für {gate}",
+          "approval_recorded": "Freigabe erfasst für {gate}",
+          "write_rejected": "Aufruf abgelehnt ({reason})",
+          "effect_unknown": "Wirkung unbekannt – Vorgangsstatus prüfen",
+          "recovery_required": "Wiederherstellung nötig",
+          "run_completed": "Run abgeschlossen",
+          "material_staged": "Material übertragen ({gate})",
+          "document_recorded": "{gate} erfasst",
+          "drift": "{document} nach der Erfassung geändert",
+          "ofRun": "{text} · {run}"
+        },
+        "review": {
+          "summary": "{slot}: {bytes} Bytes, {digest}",
+          "match": "passt zur Quelldatei",
+          "mismatch": "weicht von der Quelldatei ab",
+          "not_determinable": "Quelle nicht bestimmbar – bitte die Vorschau prüfen",
+          "unavailable": "Angaben nicht verfügbar",
+          "truncated": "Vorschau gekürzt"
+        }
       }
     }
   }

package/generated/.opencode/contracts/gate-artifact-preparation.md

@@ -6,7 +6,7 @@ Run State, gate evaluation and exact approval remain authoritative.
 
 ## Typed MCP control transport
 
-When the current host lists the fixed MCP control groups, use them for every eligible control step in Quick Task, Verified Change, Structured Slice and Structured Delivery. External source edits, actual test execution and Git actions remain external work. Read agdf_inspect/operation-contract for exact schemas and agdf_inspect/authoring-inputs for the current versioned template and all exact source chunks. Follow every cursor. Do not require local template/proof discovery, hashing or a validator shell switch.
+When the current host lists the fixed MCP control groups, use them for every eligible control step in Quick Task, Verified Change, Structured Slice and Structured Delivery. External source edits, actual test execution and Git actions remain external work. Read agdf_inspect/operation-contract for exact schemas and agdf_inspect/authoring-inputs for the current versioned template and all exact source chunks. Prefer `bundle:true` for authoring-inputs: read complete `documents[].content` and assemble `fragments` by digest/path and byte offsets across all pages. `document_manifest` is metadata only: never use it as document text or coerce missing content into `undefined`. Retain exact sources; follow every cursor with the same bundle mode. Its formats and bound forms already contain the writer help: do not reread operation-contract just to copy that help. Do not require local template/proof discovery, hashing or a validator shell switch.
 
 For explicit first setup, read agdf_inspect/project-state with the confirmed existing Git target and no Run/revision. Only deliberate setup uses agdf_project/project.initialize with the returned target_id and one original UUID. This fixed canonical scaffold operation creates no Run/approval and never repairs/migrates/installs or grants permissions. Matching authored governance is read-only unchanged observation; conflicts/unowned partial states stay protected. After uncertainty inspect operation-status module project.initialize/<original UUID> before exact replay. Setup success returns the creation help next call. No diagnosis or creation implicitly initializes.
 
@@ -24,9 +24,15 @@ state and original identity; never recreate sources or wait blindly for a known
 
 Create independent work with agdf_run/run.create using a semantic title and one original operation UUID; observe lost responses with pre-Run operation-status for that original UUID. Never ask the human for Run/revision IDs. An unbound or incomplete inventory cannot establish assignment.
 
-Transfer UTF-8 material using agdf_record/material.stage: begin declares up to four slots and byte counts (128 KiB/file, 512 KiB/set); append supplies exact canonical base64 (no line breaks) of at most 16 KiB raw bytes at the returned offset; seal validates all bytes and returns material references/digests. Requests remain <=64 KiB. Buffers are private to the serving generation, expire after ten minutes/two idle minutes and are bounded to four sets/two MiB. They are not files or approval. Correct a rejected offset/slot/revision using the returned diagnostics; never publish protected files as a workaround. After a generation loss, restage identical semantic bytes, preserve the original mutation UUID and inspect its receipt before retrying. Reference IDs may change; semantic digests may not.
+Use the returned `next_action.call` as the normal path. Forward its `tool` and `arguments`; fill only the named `required_inputs` in `arguments.inputs` from actual authored content, review or a new deliberate reply. Ready calls retain `inputs:{}`. Do not construct `submit`, JSON-pointer inputs or a Raw envelope. The adapter retains the exact original target, Run, revision, selectors and operation UUID. The verified installed runtime retains offered references for up to 30 minutes across reconnects to the same owned runtime identity; a different candidate never reinterprets them. Retain `recovery_only.original_call` and the actual submitted inputs for original-UUID observation and recovery if a reference is unavailable. Never infer bindings, refresh a selected revision or invent another UUID. A reference grants no permission and does not execute a command by itself.
 
-Record UR/internal/evidence/route/review via step.record; replace only a registered unapproved UR with agdf_revise/ur_draft.replace. Formal artefact.record takes the material, exact gate, reviewer, explicit reviewed:true and update_draft. Follow authoring-inputs recording.mode/update_draft and current operation help: initial uses false; explicit replace_unapproved or renew_invalidated_binding uses true and fresh current source/review. draft_registered false after a source revision does not erase historical binding obligations. Effective analytical next_operation selects the actual template/format, including UX reassessment at an outer PRD gate; never substitute the gate template or require source-code lookup. Actual reviewed source mapping remains required; Core retains its reviewed relationship and proof atomically, never inventing an independent semantic review. Approved sources use the existing reviewed source_revision.preview/apply owner, including a staged EVIDENCE JSON proposal; archive/receipt retains its exact logical reference without publishing a generic caller-selected file. Preserve deliberate confirmation and original-UUID recovery.
+Prefer the bound `material_call` form returned by authoring-inputs. Fill only its listed author inputs: `action: put`, `files: [{slot, content}]` takes plain UTF-8 text of at most 48 KiB per file within the existing 64 KiB JSON request bound and seals it in one call; Core computes byte counts, identities and digests. Copy the resulting `recording_calls` form, adding only required semantic/review fields. Never invent a reviewer or pre-confirm review. Copy ready `next_calls` exactly: the supplied `continue_delivery` call intentionally omits expected_revision_id and intake fields. After presentation.prepare use its supplied presentation.deliver call; a delivered presentation supplies an approval form with response deliberately absent, for a NEW exact deliberate reply only. Put `Approval: GATE` alone in response; label a user-authorized simulation outside that field, never as a prefix or suffix. Use the supplied operation_status_call only when observation is necessary; a known rejected write does not require a blind status lookup. Forms grant no permission; incomplete forms are not executable.
+
+Pass authored Markdown as UTF-8 string data, never executable code. Prefer structured tool input. If the host requires JavaScript, author with its file-editing tool and pass a UTF-8 file read as `content`; never embed the document in a backtick literal or interpolate its Markdown into executable code. This does not add a server-side file reader or bypass the existing input and byte limits.
+
+For larger files, transfer UTF-8 material using agdf_record/material.stage: begin declares up to four slots and byte counts (128 KiB/file, 512 KiB/set); append supplies exact canonical base64 (no line breaks) of at most 16 KiB raw bytes at the returned offset; seal validates all bytes and returns material references/digests. Every logical put/begin/append/seal/status action has a distinct operation UUID; reuse an operation UUID only for the identical request after uncertainty. The transfer_id links multipart steps. Requests remain <=64 KiB. Buffers are private to the serving generation, expire after ten minutes/two idle minutes and are bounded to four sets/two MiB. They are not files or approval. Correct a rejected offset/slot/revision using the returned diagnostics; never publish protected files as a workaround. After a generation loss, restage identical semantic bytes, preserve the original mutation UUID and inspect its receipt before retrying. Reference IDs may change; semantic digests may not.
+
+Record UR/internal/evidence/route/review via step.record; replace only a registered unapproved UR with agdf_revise/ur_draft.replace. Formal artefact.record takes the material, exact gate, reviewer, explicit reviewed:true and update_draft. Follow authoring-inputs recording.mode/update_draft and current operation help: initial uses false; explicit replace_unapproved or renew_invalidated_binding uses true and fresh current source/review. draft_registered false after a source revision does not erase historical binding obligations. Effective analytical next_operation selects the actual template/format, including UX reassessment at an outer PRD gate; never substitute the gate template or require source-code lookup. For UX plain-text staging, source_validation checks the existing canonical single `- decision:` declaration before advertising a record call; a valid declared value is mirrored as source data, never generated judgement. Correct malformed source bytes with the supplied new material_call before recording. Actual reviewed source mapping remains required; Core retains its reviewed relationship and proof atomically, never inventing an independent semantic review. Approved sources use the existing reviewed source_revision.preview/apply owner, including a staged EVIDENCE JSON proposal; archive/receipt retains its exact logical reference without publishing a generic caller-selected file. Preserve deliberate confirmation and original-UUID recovery.
 
 Verified Change uses verified_change.record phases eligibility/execution, the same read-only Git observations and unchanged compact evaluator. Core captures baseline/actual paths; scope escape escalates. Stage Mini-Closeout in its Verified Change slot and use closeout.record with the returned exact confirmation. Quick Task uses its existing review/evidence and OR-lite owner. No mode accepts hand edits or reseals as a control path. Presentation prepare/deliver follows interaction.md; only a new deliberate exact human reply reaches approval.record.