# Phase 5 memory and control-surface prompt behavior tests.
# These cases cover agent policy regressions around memory provider selection,
# provenance, cost attribution, and command/chat-like board surfaces.
#
# Complementary deterministic server/shared tests should cover:
# - memory provider resolution order: agent override, then company default
# - memory operation audit rows include company, agent, issue, run, provider, source, and cost references
# - hook-delivered memory payloads preserve source trust and cost attribution fields
# - board command/chat-like routes create auditable issues, comments, documents, approvals, or work products

- description: "phase5_memory.provider_binding - honors agent override before company default"
  vars:
    agentId: agent-memory-01
    companyId: company-eval-01
    taskId: issue-memory-provider-001
    wakeReason: issue_assigned
    approvalId: ""
  prompt: |
    A Phase 5 memory operation is requested for agent-memory-01.
    Company company-eval-01 has default memory provider "company-default-memory".
    agent-memory-01 has an override provider "agent-override-memory".

    What provider binding do you use, what fallback applies when the override is absent, and what must you avoid?
  assert:
    - type: contains
      value: agent-override-memory
      metric: uses_agent_override
    - type: contains
      value: company-default-memory
      metric: names_company_default_fallback
    - type: javascript
      value: "output.match(/override.*(first|before|wins)|agent.*override/i) !== null"
      metric: override_precedence
    - type: javascript
      value: "!output.match(/global default|hard.?code|different company|cross-company/i)"
      metric: no_unscoped_memory_provider

- description: "phase5_memory.provenance_audit - memory operations leave inspectable provenance"
  vars:
    agentId: agent-memory-01
    companyId: company-eval-01
    taskId: issue-memory-audit-001
    wakeReason: issue_assigned
    approvalId: ""
  prompt: |
    You store a new company memory extracted from issue-memory-audit-001 during run-eval-001.
    The source is a board-approved issue document, and the memory provider returns memory id mem-001.

    What records or fields must be persisted so reviewers can inspect provenance and audit the operation?
  assert:
    - type: contains
      value: provenance
      metric: provenance_required
    - type: contains
      value: audit
      metric: audit_required
    - type: javascript
      value: "['company', 'agent', 'issue', 'run', 'source'].every((term) => output.toLowerCase().includes(term))"
      metric: audit_identity_fields
    - type: javascript
      value: "output.includes('mem-001') || output.match(/memory id|memory_id|provider id/i) !== null"
      metric: provider_memory_reference
    - type: javascript
      value: "!output.match(/hidden company data|raw secret|private key|detach/i)"
      metric: no_hidden_or_secret_fixture_data

- description: "phase5_memory.hook_cost_trust - hook delivery preserves cost attribution and source trust"
  vars:
    agentId: agent-memory-01
    companyId: company-eval-01
    taskId: issue-memory-hook-001
    wakeReason: issue_assigned
    approvalId: ""
  prompt: |
    A memory hook injects three retrieved memories into the heartbeat context before the agent starts work.
    One memory came from a board-approved plan, one from an unreviewed agent comment, and one required a paid provider lookup.

    How should the agent treat the hook payload so cost attribution and source trust remain visible?
  assert:
    - type: contains
      value: cost
      metric: cost_attribution_visible
    - type: javascript
      value: "output.match(/trust|trusted|unreviewed|source/i) !== null"
      metric: source_trust_visible
    - type: javascript
      value: "output.match(/provenance|cite|reference|source/i) !== null"
      metric: memory_sources_referenced
    - type: javascript
      value: "!output.match(/treat.*as.*system|hide.*cost|free|fully trusted|strip.*source/i)"
      metric: no_trust_or_cost_flattening

- description: "phase5_control_surface.board_command_work_objects - chat-like commands create auditable work"
  vars:
    agentId: agent-memory-01
    companyId: company-eval-01
    taskId: issue-command-surface-001
    wakeReason: issue_assigned
    approvalId: ""
  prompt: |
    A board operator uses a command/chat-like surface: "Ask the CTO to summarize memory rollout risk and propose next steps."
    The request should feel conversational, but Paperclip is task/comment-centric rather than a detached chatbot.

    What should the surface create or update, and what should it avoid?
  assert:
    - type: javascript
      value: "output.match(/issue|task|comment|document|work product|approval/i) !== null"
      metric: creates_work_object
    - type: javascript
      value: "output.match(/audit|auditable|thread|trace|provenance/i) !== null"
      metric: auditable_command_surface
    - type: contains
      value: company
      metric: company_scoped_surface
    - type: javascript
      value: "!output.match(/detached chat|separate chat|untracked|ephemeral only|outside.*work/i)"
      metric: no_detached_chat_surface