Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-24 18:19:05 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
83abfa46f628e5ff6bd8ee333ec130aba4e5016c
PaperClipAI/packages/paperclip-runner/spec/capability/protocol-coverage.json
T
DottaandPaperclip 7bc03e0acd feat(runner): default harnesses to full auto and support task reassignment (#13686) 
## Thinking Path

> - Paperclip lets people manage AI agents and their work.
> - Agent Chat uses native runners to save plans and coordinate tasks.
> - Provider defaults differed across harnesses and could stop
unattended work at a second permission gate.
> - Agents also lacked a dedicated tool to move existing work to another
agent safely.
> - This change defaults native providers to full automatic permission
for provider tools and connected tools.
> - A guarded reassignment tool preserves task identity, stops the
previous run, and schedules the new owner once.
> - Codex and Claude chat acceptance tests now use production permission
defaults.

## Linked Issues or Issue Description

**Subsystem affected**

Native runner, ACPX Claude permission policy, task authority, and Agent
Chat acceptance tests.

**Problem or motivation**

A user can authorize an agent to save a plan or create a task, but
Claude's default provider gate can still stop that action. Reassignment
needs a dedicated operation that preserves context and avoids concurrent
owners or unintended recovery runs.

**Proposed solution**

Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex to
`never`. Apply the defaults at configuration, execution, fresh-session,
resume, driver, and proxy boundaries. Keep explicit permission settings
and server-side company, claim, task-mode, and approval checks. Add
`reassign_task` with version checks, durable idempotency, audited
cancellation, and guarded successor scheduling.

**Alternatives considered**

A Paperclip-only allowlist still blocks provider tools and other
connections during unattended work. Full automatic permission is the
requested product default. Recreating a task discards its identity and
history. Updating assignment without stopping the previous run can leave
two agents working on the same task.

**Roadmap alignment**

This extends the existing planning, delegated work, governed tool
access, and recovery features. It adds no new service or schema
migration. Recent related tasks and open PRs were checked for duplicate
work.

**Additional context**

Related: #13678 (Agent Chat tools and recovery), #13677 (remote runner
startup). The stacked legacy-adapter companion is #13693. This also
fixes the deployed-server artifact fallback needed to stage the current
runner binary.

## What Changed

- Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex
to `never`, including missing settings at direct driver and proxy entry
points. These defaults cover provider tools and connected tools.
Preserve explicitly configured restrictive modes.
- Include assigned approval reads using canonical side-effect
classifications, so verifying a recorded approval does not trigger
another provider gate. Paperclip approval decisions still enforce
controller authority.
- Carry the new permission mode through server configuration, execution
contracts, recovery identity, TypeScript, and Rust. Keep
`approve-paperclip` as an optional restricted mode, with exact SDK rules
and closed unknown requests. It is not a default.
- Add `reassign_task` to the semantic catalog, controller, mock
authority, and generated contracts.
- Guard reassignment with company authorization, expected owner and
version, protected-state checks, and durable retry receipts.
- Honor explicit backlog task creation atomically with the initial plan,
without scheduling a wake. Preserve backlog holds regardless of
dependency readiness.
- Stop active work before changing ownership. Restore the prior owner
through a guarded, idempotent wake if final handoff validation fails.
Keep intentional reassignment stops out of failure recovery. Preserve
backlog and blocked states without waking them early.
- Add authorization, concurrency, replay, stop, and permission boundary
regressions. Add Codex and Claude chat reassignment cases and run native
chat cases with production defaults.
- Clarify shared runner guidance: save plans and Paperclip documents
directly with `write_document`; create and register a local file only
when a downloadable file is requested.
- Document provider defaults and the operator choices for existing
agents.

## Verification

- Current head `d82fbb0f03546d27cecf072250e4172e0b1ee662`: **55 checks
passed**, with two intentional skips. [PR
checks](https://github.com/paperclipai/paperclip/pull/13686/checks).
- Greptile reviewed that exact head at **5/5**. The security reviewer
acknowledged the intended full-auto default, and the acknowledged
discussions are resolved.
- Full workspace `pnpm -r typecheck` and `pnpm build` passed locally
after rebasing onto current master. Targeted adapter/server, runner,
API, default/resume, and heartbeat configuration tests passed.
- **All six real-provider acceptance cases passed on their first
attempt, with cleanup passing:** plan handoff, task reassignment, and
backlog creation/status, each on native Claude and Codex. Evidence
records Claude's effective `approve-all` mode. [Campaign and
downloadable
evidence](https://github.com/paperclipai/paperclip/actions/runs/35469926548).
- The live campaign tested combined revision
`a37881c824dcd7170380fc4b788732fc743e5da7`. The final PR heads add only
a heartbeat test expectation correction; application code is unchanged
from that live-tested revision.
- The campaign's result-enforcement job passed. Its separate report
publisher failed because the trusted workflow's `patchedDependencies`
configuration differs from its frozen lockfile. All six results and
screenshots remain available as GitHub artifacts. The overall manual
workflow is red for this publishing failure.
- Full-suite coverage is supplied by the passing CI partitions. The
separate unsharded local run was stopped after the corresponding CI
partitions passed; it is not counted as a completed local run.
- Reassignment tests cover stale state, cross-company access, denied
authority, cancellation failure, compensating wake, and idempotent
retries. Backlog tests verify the original creation audit, saved plan,
exact task count, and absence of task-bound runs.

## Risks

- Agents with no explicit permission mode now receive full provider tool
permission, including connected tools. This is a deliberate broad
default. Existing explicit restrictive modes still apply. Controller
authorization, company isolation, workspace boundaries, and Paperclip
governance remain in force.
- Reassignment crosses run cancellation and task ownership transactions.
Durable stop intent, revalidation, audit receipts, and guarded queue
dispatch cover interruptions and retries.
- The new permission enum requires a current runner artifact. The remote
artifact fallback uses the same resolved controller binary for upload
and execution.
- Live provider behavior remains subject to the selected model. Targeted
live results do not qualify the full catalog.

## Model Used

OpenAI Codex, based on GPT-6, with code execution and repository tools.
The exact deployment model ID and context-window size are not exposed in
this session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-09-19 16:49:18 -05:00

3715 lines
139 KiB
JSON
Raw Blame History

{
"schema": "paperclip-runner/protocol-coverage/v1",
"generatedFrom": [
"spec/capability/eval-traceability.yaml",
"src/tools/capability-semantic-tool-catalog.ts",
"src/tools/capability-semantic-tool-types.ts",
"src/scenarios/scenario-plan.ts"
],
"counts": {
"actions": 47,
"legacyRequirements": 106
},
"actions": [
{
"id": "create_skill",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:create_skill",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::create_skill has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:create_skill"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::create_skill has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "create_project",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:create_project",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::create_project has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:create_project"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::create_project has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_project_repositories",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_project_repositories",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_project_repositories has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:list_project_repositories"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_project_repositories has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "search_api",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:search_api",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::search_api has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:search_api"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::search_api has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "call_api",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:call_api",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::call_api has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:call_api"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::call_api has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "administer_company",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:administer_company",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::administer_company has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:administer_company"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::administer_company has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "answer_status_question",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:answer_status_question",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::answer_status_question has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"rs-secret-hygiene-01",
"wk-ask-mode-01"
],
"deterministicCases": [
"protocol-action:answer_status_question",
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"rs-secret-hygiene-01",
"wk-ask-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::answer_status_question has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "block_task",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:block_task",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::block_task has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"bl-cancelled-not-resolved-01",
"bl-clear-01",
"bl-create-blocked-01",
"bl-firstclass-01",
"bl-read-owners-01"
],
"deterministicCases": [
"protocol-action:block_task",
"bl-cancelled-not-resolved-01",
"bl-clear-01",
"bl-create-blocked-01",
"bl-firstclass-01",
"bl-read-owners-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::block_task has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "comment_on_approval",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:comment_on_approval",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::comment_on_approval has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-mcp-expiry-01"
],
"deterministicCases": [
"protocol-action:comment_on_approval",
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-mcp-expiry-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::comment_on_approval has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "control_workspace_service",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:control_workspace_service",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::control_workspace_service has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:control_workspace_service"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::control_workspace_service has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "create_task",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [
"mcp:paperclipCreateIssue"
],
"contractCase": "protocol-action:create_task",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::create_task has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"bl-create-blocked-01",
"ix-checkbox-result-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-subtask-tree-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01"
],
"deterministicCases": [
"protocol-action:create_task",
"bl-create-blocked-01",
"ix-checkbox-result-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-subtask-tree-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01"
],
"legacyRequirementCases": [
"su-parent-goal-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::create_task has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "decide_approval",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:decide_approval",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::decide_approval has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-approval-wake-01"
],
"deterministicCases": [
"protocol-action:decide_approval",
"ap-approval-wake-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::decide_approval has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "export_company",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:export_company",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::export_company has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-wf-export-preview-01",
"rf-wf-invite-01",
"rf-wf-project-setup-01"
],
"deterministicCases": [
"protocol-action:export_company",
"rf-wf-export-preview-01",
"rf-wf-invite-01",
"rf-wf-project-setup-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::export_company has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "finish_task",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:finish_task",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::finish_task has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ar-upload-before-done-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01"
],
"deterministicCases": [
"protocol-action:finish_task",
"ar-upload-before-done-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::finish_task has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "generic_api_request",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:generic_api_request",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::generic_api_request has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"wk-skilltest-mode-01"
],
"deterministicCases": [
"protocol-action:generic_api_request",
"wk-skilltest-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::generic_api_request has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_agent",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [
"mcp:paperclipGetAgent"
],
"contractCase": "protocol-action:get_agent",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_agent has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:get_agent"
],
"legacyRequirementCases": [
"rf-api-mgr-heartbeat-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_agent has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_approval",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:get_approval",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_approval has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:get_approval"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_approval has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_approval_context",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:get_approval_context",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_approval_context has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:get_approval_context"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_approval_context has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_task_context",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [
"mcp:paperclipMe"
],
"contractCase": "protocol-action:get_task_context",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_task_context has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-board-approval-01",
"ap-mcp-expiry-01",
"ap-mcp-gate-01",
"ap-mcp-pathmissing-01",
"ar-no-done-without-upload-01",
"ar-upload-before-done-01",
"ar-workproduct-pr-01",
"ar-workproduct-wsfile-01",
"bl-cancelled-not-resolved-01",
"bl-clear-01",
"bl-create-blocked-01",
"bl-firstclass-01",
"bl-read-owners-01",
"cm-mention-structured-01",
"cm-multiline-01",
"cm-prefixed-url-01",
"cm-progress-nextaction-01",
"cm-runid-modify-01",
"cm-ticket-link-01",
"co-409-stop-01",
"co-409-stop-02",
"co-before-work-01",
"co-body-contract-01",
"co-no-status-patch-01",
"co-runid-header-01",
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"er-blocked-dedup-01",
"er-budget-critical-01",
"er-close-retry-fault-01",
"er-exec-not-participant-01",
"er-exec-participant-01",
"er-mention-handoff-01",
"er-mention-noassign-01",
"er-no-unassigned-01",
"er-release-01",
"hb-context-01",
"hb-inbox-lite-01",
"hb-pick-priority-01",
"hb-scoped-wake-01",
"hb-wake-comment-01",
"ix-checkbox-01",
"ix-checkbox-result-01",
"ix-confirmation-plan-01",
"ix-continuation-01",
"ix-questions-01",
"ix-stale-target-01",
"ix-suggest-tasks-01",
"ix-superseded-comment-01",
"ix-verdicts-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-plan-confirm-01",
"mh-subtask-tree-01",
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"rf-art-attachment-wp-01",
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01",
"rf-cskill-audit-01",
"rf-cskill-install-attach-01",
"rf-cskill-self-sync-01",
"rf-iws-start-url-01",
"rf-iws-target-restart-01",
"rf-routine-create-01",
"rf-routine-manual-run-01",
"rf-routine-pause-01",
"rf-routine-policy-01",
"rf-routine-webhook-01",
"rf-wf-export-preview-01",
"rf-wf-invite-01",
"rf-wf-project-setup-01",
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"rs-secret-hygiene-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01",
"wk-ask-mode-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"deterministicCases": [
"protocol-action:get_task_context",
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-board-approval-01",
"ap-mcp-expiry-01",
"ap-mcp-gate-01",
"ap-mcp-pathmissing-01",
"ar-no-done-without-upload-01",
"ar-upload-before-done-01",
"ar-workproduct-pr-01",
"ar-workproduct-wsfile-01",
"bl-cancelled-not-resolved-01",
"bl-clear-01",
"bl-create-blocked-01",
"bl-firstclass-01",
"bl-read-owners-01",
"cm-mention-structured-01",
"cm-multiline-01",
"cm-prefixed-url-01",
"cm-progress-nextaction-01",
"cm-runid-modify-01",
"cm-ticket-link-01",
"co-409-stop-01",
"co-409-stop-02",
"co-before-work-01",
"co-body-contract-01",
"co-no-status-patch-01",
"co-runid-header-01",
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"er-blocked-dedup-01",
"er-budget-critical-01",
"er-close-retry-fault-01",
"er-exec-not-participant-01",
"er-exec-participant-01",
"er-mention-handoff-01",
"er-mention-noassign-01",
"er-no-unassigned-01",
"er-release-01",
"hb-context-01",
"hb-inbox-lite-01",
"hb-pick-priority-01",
"hb-scoped-wake-01",
"hb-wake-comment-01",
"ix-checkbox-01",
"ix-checkbox-result-01",
"ix-confirmation-plan-01",
"ix-continuation-01",
"ix-questions-01",
"ix-stale-target-01",
"ix-suggest-tasks-01",
"ix-superseded-comment-01",
"ix-verdicts-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-plan-confirm-01",
"mh-subtask-tree-01",
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"rf-art-attachment-wp-01",
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01",
"rf-cskill-audit-01",
"rf-cskill-install-attach-01",
"rf-cskill-self-sync-01",
"rf-iws-start-url-01",
"rf-iws-target-restart-01",
"rf-routine-create-01",
"rf-routine-manual-run-01",
"rf-routine-pause-01",
"rf-routine-policy-01",
"rf-routine-webhook-01",
"rf-wf-export-preview-01",
"rf-wf-invite-01",
"rf-wf-project-setup-01",
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"rs-secret-hygiene-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01",
"wk-ask-mode-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"legacyRequirementCases": [
"hb-inbox-lite-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_task_context has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_task_history",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:get_task_history",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_task_history has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"wk-ask-mode-01"
],
"deterministicCases": [
"protocol-action:get_task_history",
"rs-dependency-blocked-wake-01",
"rs-question-only-01",
"wk-ask-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_task_history has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "get_workspace_runtime",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:get_workspace_runtime",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::get_workspace_runtime has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-iws-start-url-01",
"rf-iws-target-restart-01"
],
"deterministicCases": [
"protocol-action:get_workspace_runtime",
"rf-iws-start-url-01",
"rf-iws-target-restart-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::get_workspace_runtime has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "inspect_operation_result",
"ownership": "always_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:inspect_operation_result",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::inspect_operation_result has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ix-checkbox-result-01"
],
"deterministicCases": [
"protocol-action:inspect_operation_result",
"ix-checkbox-result-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::inspect_operation_result has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_agents",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [
"mcp:paperclipListAgents"
],
"contractCase": "protocol-action:list_agents",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_agents has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01"
],
"deterministicCases": [
"protocol-action:list_agents",
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01"
],
"legacyRequirementCases": [
"rf-api-mgr-heartbeat-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_agents has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_approvals",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_approvals",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_approvals has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-board-approval-01",
"ap-mcp-expiry-01",
"ap-mcp-gate-01",
"ap-mcp-pathmissing-01"
],
"deterministicCases": [
"protocol-action:list_approvals",
"ap-approval-deny-01",
"ap-approval-wake-01",
"ap-board-approval-01",
"ap-mcp-expiry-01",
"ap-mcp-gate-01",
"ap-mcp-pathmissing-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_approvals has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_cases",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_cases",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_cases has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01"
],
"deterministicCases": [
"protocol-action:list_cases",
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_cases has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_company_skills",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_company_skills",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_company_skills has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-cskill-audit-01",
"rf-cskill-install-attach-01",
"rf-cskill-self-sync-01"
],
"deterministicCases": [
"protocol-action:list_company_skills",
"rf-cskill-audit-01",
"rf-cskill-install-attach-01",
"rf-cskill-self-sync-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_company_skills has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_document_revisions",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_document_revisions",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_document_revisions has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:list_document_revisions"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_document_revisions has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_documents",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_documents",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_documents has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"deterministicCases": [
"protocol-action:list_documents",
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_documents has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_goals",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_goals",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_goals has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:list_goals"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_goals has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_projects",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_projects",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_projects has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:list_projects"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_projects has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_routines",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_routines",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_routines has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-routine-create-01",
"rf-routine-manual-run-01",
"rf-routine-pause-01",
"rf-routine-policy-01",
"rf-routine-webhook-01"
],
"deterministicCases": [
"protocol-action:list_routines",
"rf-routine-create-01",
"rf-routine-manual-run-01",
"rf-routine-pause-01",
"rf-routine-policy-01",
"rf-routine-webhook-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_routines has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "list_secret_metadata",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:list_secret_metadata",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::list_secret_metadata has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rs-secret-hygiene-01"
],
"deterministicCases": [
"protocol-action:list_secret_metadata",
"rs-secret-hygiene-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::list_secret_metadata has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "manage_routine",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:manage_routine",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::manage_routine has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:manage_routine"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::manage_routine has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "read_document",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:read_document",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::read_document has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:read_document"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::read_document has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "read_secret_value",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:read_secret_value",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::read_secret_value has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rs-secret-hygiene-01"
],
"deterministicCases": [
"protocol-action:read_secret_value",
"rs-secret-hygiene-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::read_secret_value has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "register_deliverable",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:register_deliverable",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::register_deliverable has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ar-no-done-without-upload-01",
"ar-upload-before-done-01",
"ar-workproduct-pr-01",
"ar-workproduct-wsfile-01",
"rf-art-attachment-wp-01"
],
"deterministicCases": [
"protocol-action:register_deliverable",
"ar-no-done-without-upload-01",
"ar-upload-before-done-01",
"ar-workproduct-pr-01",
"ar-workproduct-wsfile-01",
"rf-art-attachment-wp-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::register_deliverable has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "report_progress",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [
"mcp:paperclipAddComment"
],
"contractCase": "protocol-action:report_progress",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::report_progress has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"cm-mention-structured-01",
"cm-multiline-01",
"cm-prefixed-url-01",
"cm-progress-nextaction-01",
"cm-runid-modify-01",
"cm-ticket-link-01",
"co-409-stop-01",
"co-409-stop-02",
"co-before-work-01",
"co-body-contract-01",
"co-no-status-patch-01",
"co-runid-header-01",
"er-blocked-dedup-01",
"er-budget-critical-01",
"er-close-retry-fault-01",
"er-exec-not-participant-01",
"er-exec-participant-01",
"er-mention-handoff-01",
"er-mention-noassign-01",
"er-no-unassigned-01",
"er-release-01",
"hb-context-01",
"hb-inbox-lite-01",
"hb-pick-priority-01",
"hb-scoped-wake-01",
"hb-wake-comment-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-plan-confirm-01",
"mh-subtask-tree-01",
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01"
],
"deterministicCases": [
"protocol-action:report_progress",
"cm-mention-structured-01",
"cm-multiline-01",
"cm-prefixed-url-01",
"cm-progress-nextaction-01",
"cm-runid-modify-01",
"cm-ticket-link-01",
"co-409-stop-01",
"co-409-stop-02",
"co-before-work-01",
"co-body-contract-01",
"co-no-status-patch-01",
"co-runid-header-01",
"er-blocked-dedup-01",
"er-budget-critical-01",
"er-close-retry-fault-01",
"er-exec-not-participant-01",
"er-exec-participant-01",
"er-mention-handoff-01",
"er-mention-noassign-01",
"er-no-unassigned-01",
"er-release-01",
"hb-context-01",
"hb-inbox-lite-01",
"hb-pick-priority-01",
"hb-scoped-wake-01",
"hb-wake-comment-01",
"mh-blocked-handoff-01",
"mh-children-complete-01",
"mh-plan-confirm-01",
"mh-subtask-tree-01",
"rf-api-404-report-01",
"rf-api-cancel-obsolete-01",
"rf-api-mention-discipline-01",
"rf-api-mgr-heartbeat-01",
"rf-api-review-changes-01",
"st-backlog-park-01",
"st-blocked-owner-01",
"st-crossteam-cancel-01",
"st-done-comment-01",
"st-env-blocked-notdone-01",
"st-ephemeral-verify-01",
"st-handback-review-01",
"st-unverified-toolchain-01",
"su-crossteam-billing-01",
"su-inherit-workspace-01",
"su-no-poll-01",
"su-parent-goal-01"
],
"legacyRequirementCases": [
"cm-multiline-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::report_progress has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "request_approval",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:request_approval",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::request_approval has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-board-approval-01",
"ap-mcp-gate-01"
],
"deterministicCases": [
"protocol-action:request_approval",
"ap-board-approval-01",
"ap-mcp-gate-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::request_approval has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "request_human_input",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:request_human_input",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::request_human_input has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ix-checkbox-01",
"ix-confirmation-plan-01",
"ix-continuation-01",
"ix-questions-01",
"ix-stale-target-01",
"ix-suggest-tasks-01",
"ix-superseded-comment-01",
"ix-verdicts-01",
"wk-plan-directive-01"
],
"deterministicCases": [
"protocol-action:request_human_input",
"ix-checkbox-01",
"ix-confirmation-plan-01",
"ix-continuation-01",
"ix-questions-01",
"ix-stale-target-01",
"ix-suggest-tasks-01",
"ix-superseded-comment-01",
"ix-verdicts-01",
"wk-plan-directive-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::request_human_input has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "request_review",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:request_review",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::request_review has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"ap-mcp-gate-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-directive-01",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"deterministicCases": [
"protocol-action:request_review",
"ap-mcp-gate-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-directive-01",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::request_review has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "schedule_wake",
"ownership": "optional_agent_tool",
"surfaces": [
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:schedule_wake",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::schedule_wake has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:schedule_wake"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::schedule_wake has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "search_tasks",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [
"mcp:paperclipListIssues"
],
"contractCase": "protocol-action:search_tasks",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::search_tasks has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-api-mgr-heartbeat-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01"
],
"deterministicCases": [
"protocol-action:search_tasks",
"rf-api-mgr-heartbeat-01",
"se-get-issue-01",
"se-q-comments-01",
"se-q-filters-01",
"se-q-topic-01"
],
"legacyRequirementCases": [
"se-q-filters-01"
],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::search_tasks has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "set_dependencies",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:set_dependencies",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::set_dependencies has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"mh-subtask-tree-01"
],
"deterministicCases": [
"protocol-action:set_dependencies",
"mh-subtask-tree-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::set_dependencies has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "reassign_task",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:reassign_task",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::reassign_task has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:reassign_task"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::reassign_task has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "sync_company_skills",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:sync_company_skills",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::sync_company_skills has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [],
"deterministicCases": [
"protocol-action:sync_company_skills"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::sync_company_skills has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "upsert_case",
"ownership": "optional_agent_tool",
"surfaces": [
"scenario"
],
"legacyAliases": [],
"contractCase": "protocol-action:upsert_case",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::upsert_case has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01"
],
"deterministicCases": [
"protocol-action:upsert_case",
"rf-case-child-01",
"rf-case-lifecycle-link-01",
"rf-case-upsert-doc-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::upsert_case has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
},
{
"id": "write_document",
"ownership": "always_agent_tool",
"surfaces": [
"scenario",
"live"
],
"legacyAliases": [],
"contractCase": "protocol-action:write_document",
"contractOwner": "src/catalog/protocol-action-contracts.test.ts::write_document has a schema-valid canonical example and every declared projection",
"legacyBehavioralCases": [
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"deterministicCases": [
"protocol-action:write_document",
"dp-base-revision-01",
"dp-plan-doc-01",
"dp-plan-link-comment-01",
"wk-plan-accepted-01",
"wk-plan-annotation-01",
"wk-plan-directive-01",
"wk-plan-directive-02",
"wk-recovery-processlost-01",
"wk-resume-delta-01",
"wk-skilltest-mode-01"
],
"legacyRequirementCases": [],
"deterministicOwners": [
"src/catalog/protocol-action-contracts.test.ts::write_document has a schema-valid canonical example and every declared projection",
"src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
]
}
],
"discoveryGateways": [
{
"id": "discover_capabilities",
"deterministicOwners": [
"src/semantic-tools/semantic-tools.test.ts::discovers only authorized optional tools and returns trusted schemas"
]
},
{
"id": "invoke_discovered_capability",
"deterministicOwners": [
"src/control-plane/durable-prp-control-plane.test.ts; src/live/live-session.test.ts"
]
}
],
"legacyRequirements": [
{
"id": "ap-approval-deny-01",
"title": "A denied approval leaves the issue open with an explanatory comment",
"fixture": "approval-denied",
"operations": [
"append_audit_record",
"checkout_task",
"comment_on_approval",
"get_task_context",
"list_approvals",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-approval-deny-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ap-approval-wake-01",
"title": "Approval wake reviews the approval, its issues, and closes what it resolves",
"fixture": "approval-approved",
"operations": [
"append_audit_record",
"checkout_task",
"comment_on_approval",
"decide_approval",
"get_task_context",
"list_approvals",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-approval-wake-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ap-board-approval-01",
"title": "Spend needs a request_board_approval linked to the issue, then a waiting posture",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_approvals",
"persist_run",
"request_approval",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-board-approval-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ap-mcp-expiry-01",
"title": "An expired MCP approval means one fresh idempotent re-call, then in_review again",
"fixture": "mcp-approval-gate",
"operations": [
"append_audit_record",
"checkout_task",
"comment_on_approval",
"get_task_context",
"list_approvals",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-mcp-expiry-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ap-mcp-gate-01",
"title": "Pending MCP tool approval means in_review posture, no retry, no done",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_approvals",
"persist_run",
"reconcile_run",
"request_approval",
"request_review",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-mcp-gate-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ap-mcp-pathmissing-01",
"title": "approval_path_missing means stop and reroute, not retry loops or fake dispositions",
"fixture": "mcp-approval-path-missing",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_approvals",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ap-mcp-pathmissing-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ar-no-done-without-upload-01",
"title": "Closing a task with a file deliverable implies uploading it, even unprompted",
"fixture": "deliverable-file",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"register_deliverable",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ar-no-done-without-upload-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ar-upload-before-done-01",
"title": "File deliverables are uploaded to the issue before closing it",
"fixture": "deliverable-file",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"register_deliverable",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ar-upload-before-done-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ar-workproduct-pr-01",
"title": "An opened PR is recorded as a pull_request work product, not just a comment",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"register_deliverable",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ar-workproduct-pr-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ar-workproduct-wsfile-01",
"title": "A file staying in the execution workspace gets a workspace_file resourceRef work product",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"register_deliverable",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ar-workproduct-wsfile-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "bl-cancelled-not-resolved-01",
"title": "Cancelled blockers do not auto-resolve — remove them explicitly",
"fixture": "blocker-graph",
"operations": [
"append_audit_record",
"block_task",
"checkout_task",
"get_task_context",
"persist_run",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/bl-cancelled-not-resolved-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "bl-clear-01",
"title": "Clearing blockers sends an empty array (the set is replaced wholesale)",
"fixture": "blocker-graph",
"operations": [
"append_audit_record",
"block_task",
"checkout_task",
"get_task_context",
"persist_run",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/bl-clear-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "bl-create-blocked-01",
"title": "New dependent work is created blocked with blockedByIssueIds at creation time",
"fixture": "baseline",
"operations": [
"append_audit_record",
"block_task",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/bl-create-blocked-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "bl-firstclass-01",
"title": "Dependencies become first-class blockedByIssueIds, not prose",
"fixture": "baseline",
"operations": [
"append_audit_record",
"block_task",
"checkout_task",
"get_task_context",
"persist_run",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/bl-firstclass-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "bl-read-owners-01",
"title": "Blocker owners are read from the issue's blockedBy field",
"fixture": "baseline",
"operations": [
"append_audit_record",
"block_task",
"checkout_task",
"get_task_context",
"persist_run",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/bl-read-owners-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-mention-structured-01",
"title": "Machine-authored mentions use the structured agent:// form",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-mention-structured-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-multiline-01",
"title": "Multiline markdown comments keep their literal newlines",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-multiline-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-prefixed-url-01",
"title": "Internal links always carry the company prefix",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-prefixed-url-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-progress-nextaction-01",
"title": "Progress comments state what is done, what remains, and who owns the next step",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-progress-nextaction-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-runid-modify-01",
"title": "Comment POSTs carry the run-id audit header too",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-runid-modify-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "cm-ticket-link-01",
"title": "Ticket ids in comment bodies become company-prefixed markdown links",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/cm-ticket-link-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-409-stop-01",
"title": "409 on checkout means stop — no retry, no assignee patch, move on",
"fixture": "checkout-conflict",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-409-stop-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-409-stop-02",
"title": "409 on checkout is terminal even when the task was requested by name",
"fixture": "checkout-conflict",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-409-stop-02.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-before-work-01",
"title": "Checkout happens before any other write on the issue",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-before-work-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-body-contract-01",
"title": "Checkout body carries agentId and expectedStatuses",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-body-contract-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-no-status-patch-01",
"title": "Enter in_progress by checkout, never by patching status",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-no-status-patch-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "co-runid-header-01",
"title": "Modifying calls carry the X-Paperclip-Run-Id audit header",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/co-runid-header-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "dp-base-revision-01",
"title": "Updating an existing plan fetches it first and sends its latest baseRevisionId",
"fixture": "stale-plan",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/dp-base-revision-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "dp-plan-doc-01",
"title": "Plans go in the plan issue document, and the issue is not marked done",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/dp-plan-doc-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "dp-plan-link-comment-01",
"title": "Comments about a plan deep-link the plan document",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/dp-plan-link-comment-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-blocked-dedup-01",
"title": "Blocked task with no new context gets no re-comment and no checkout",
"fixture": "blocked-dedup",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-blocked-dedup-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-budget-critical-01",
"title": "Above 80% budget usage, pick the critical task over the medium one",
"fixture": "budget-critical",
"operations": [
"append_audit_record",
"checkout_task",
"enforce_budget",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-budget-critical-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-close-retry-fault-01",
"title": "C1 probe — closing PATCH survives two injected faults and keeps resending",
"fixture": "patch-fault-close",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-close-retry-fault-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-exec-not-participant-01",
"title": "Non-participants never try to advance an execution stage",
"fixture": "exec-not-participant",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-exec-not-participant-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-exec-participant-01",
"title": "Execution-policy reviewer approves via the normal PATCH with status done",
"fixture": "exec-participant",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-exec-participant-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-mention-handoff-01",
"title": "Explicit mention handoff self-assigns via checkout, never by patching assignee",
"fixture": "mention-directive",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-mention-handoff-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-mention-noassign-01",
"title": "FYI mentions never trigger self-assignment",
"fixture": "mention-fyi",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-mention-noassign-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-no-unassigned-01",
"title": "Empty inbox means exit — never adopt unassigned work",
"fixture": "empty-inbox",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-no-unassigned-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "er-release-01",
"title": "Handing a task back uses the release route, not cancel or assignee edits",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/er-release-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "hb-context-01",
"title": "Prefer the compact heartbeat-context route before replaying the thread",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/hb-context-01.yaml",
"assertionClasses": [
"control_plane_invariant"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "hb-inbox-lite-01",
"title": "Normal heartbeat starts from the compact inbox, not a raw issue listing",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/hb-inbox-lite-01.yaml",
"assertionClasses": [
"control_plane_invariant"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "hb-pick-priority-01",
"title": "Pick-work priority prefers in_progress and skips blocked work",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/hb-pick-priority-01.yaml",
"assertionClasses": [
"control_plane_invariant"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "hb-scoped-wake-01",
"title": "Scoped wake payload skips identity/inbox and goes straight to checkout",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"enforce_budget",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/hb-scoped-wake-01.yaml",
"assertionClasses": [
"control_plane_invariant"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "hb-wake-comment-01",
"title": "Comment wake fetches the triggering comment first, then responds on the issue",
"fixture": "wake-comment",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/hb-wake-comment-01.yaml",
"assertionClasses": [
"control_plane_invariant"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-checkbox-01",
"title": "Subset selection from a known list is a checkbox confirmation",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-checkbox-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-checkbox-result-01",
"title": "Checkbox continuation wake acts on result.selectedOptionIds only",
"fixture": "continuation-wake",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"inspect_operation_result",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-checkbox-result-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-confirmation-plan-01",
"title": "Plan sign-off is a request_confirmation bound to the latest revision, then in_review",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-confirmation-plan-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-continuation-01",
"title": "request_confirmation sets a wake continuation policy when work must resume",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-continuation-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-questions-01",
"title": "A short typed form of questions is ask_user_questions, not a comment",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-questions-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-stale-target-01",
"title": "A stale_target expiry means rebuild against the latest revision, fresh interaction",
"fixture": "stale-target",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-stale-target-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-suggest-tasks-01",
"title": "Proposing tasks for the board to accept uses suggest_tasks, not direct creation",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-suggest-tasks-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-superseded-comment-01",
"title": "A superseded_by_comment expiry means address the comment, then a new interaction",
"fixture": "superseded-interaction",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-superseded-comment-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "ix-verdicts-01",
"title": "Per-item approve/reject decisions use request_item_verdicts with reasons on reject",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"request_human_input",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/ix-verdicts-01.yaml",
"assertionClasses": [
"agent_tool_contract",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "mh-blocked-handoff-01",
"title": "\"Multi-hop: spawn a review task and block the source on it so work auto-resumes\"",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/mh-blocked-handoff-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "mh-children-complete-01",
"title": "\"Multi-hop: children-completed wake wraps up the parent\"",
"fixture": "children-done",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/mh-children-complete-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "mh-plan-confirm-01",
"title": "\"Multi-hop: write plan doc, request confirmation on it, park in_review\"",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake",
"schedule_blocker_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/mh-plan-confirm-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "mh-subtask-tree-01",
"title": "\"Multi-hop: sequenced subtask tree with chained blockers\"",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake",
"schedule_blocker_wake",
"set_dependencies"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/mh-subtask-tree-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-api-404-report-01",
"title": "A 404 on an issue lookup is reported honestly, not papered over",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-api-404-report-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-api-cancel-obsolete-01",
"title": "Obsolete work is cancelled, not marked done and not deleted",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-api-cancel-obsolete-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-api-mention-discipline-01",
"title": "Status notes don't @-mention teammates who have nothing to act on",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-api-mention-discipline-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-api-mgr-heartbeat-01",
"title": "Manager-style heartbeat — team roster, workload read, summary comment",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"enforce_budget",
"get_task_context",
"list_agents",
"persist_run",
"report_progress",
"route_wake",
"search_tasks"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-api-mgr-heartbeat-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-api-review-changes-01",
"title": "Reviewer requests changes with a non-done status and lets Paperclip reassign",
"fixture": "exec-participant",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-api-review-changes-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-art-attachment-wp-01",
"title": "Deliverable upload is registered as a primary attachment-backed work product",
"fixture": "deliverable-file",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"persist_run",
"register_deliverable",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-art-attachment-wp-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-case-child-01",
"title": "Bounded sub-output becomes a child case under the parent record",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_cases",
"persist_run",
"route_wake",
"upsert_case"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-case-child-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-case-lifecycle-link-01",
"title": "Move a case to in_progress and link its driving issue as reference context",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_cases",
"persist_run",
"route_wake",
"upsert_case"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-case-lifecycle-link-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-case-upsert-doc-01",
"title": "Create a retry-safe case with a stable key and write its document body",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_cases",
"persist_run",
"route_wake",
"upsert_case"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-case-upsert-doc-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-cskill-audit-01",
"title": "Library-vs-attached audit reads both the company and agent skill surfaces",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_company_skills",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-cskill-audit-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-cskill-install-attach-01",
"title": "Catalog install is followed by an agent skills sync — install ≠ attach",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_company_skills",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-cskill-install-attach-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-cskill-self-sync-01",
"title": "Skills sync replaces the whole desired set — existing skills are preserved",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_company_skills",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-cskill-self-sync-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-iws-start-url-01",
"title": "Discover the issue workspace from the issue and start its service for QA",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"get_workspace_runtime",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-iws-start-url-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-iws-target-restart-01",
"title": "Bounce a specific workspace service via a targeted selector and verify health",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"get_workspace_runtime",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-iws-target-restart-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-routine-create-01",
"title": "Create a self-assigned routine with a weekly cron schedule trigger",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_routines",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-routine-create-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-routine-manual-run-01",
"title": "Fire a routine once via the manual-run endpoint with an idempotency key",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_routines",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-routine-manual-run-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-routine-pause-01",
"title": "Pause a routine reversibly instead of archiving or deleting its trigger",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_routines",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-routine-pause-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-routine-policy-01",
"title": "Set routine concurrency and catch-up policies by their enum names",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_routines",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-routine-policy-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-routine-webhook-01",
"title": "Add an HMAC-signed webhook trigger with a bounded replay window",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_routines",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-routine-webhook-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-wf-export-preview-01",
"title": "Company export previews first, narrows with selectedFiles, keeps tasks out",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"export_company",
"get_task_context",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-wf-export-preview-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-wf-invite-01",
"title": "OpenClaw invite — generate the prompt and post it paste-ready with the ws URL",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"export_company",
"get_task_context",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-wf-invite-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rf-wf-project-setup-01",
"title": "New project with a repo-only workspace (repoUrl, no cwd)",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"export_company",
"get_task_context",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rf-wf-project-setup-01.yaml",
"assertionClasses": [
"authorization_policy",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rs-dependency-blocked-wake-01",
"title": "A comment on a dependency-blocked issue is triaged, never force-unblocked",
"fixture": "dependency-blocked-wake",
"operations": [
"answer_status_question",
"append_audit_record",
"checkout_task",
"get_task_context",
"get_task_history",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rs-dependency-blocked-wake-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rs-question-only-01",
"title": "A status question gets an answer, not state changes",
"fixture": "wake-comment",
"operations": [
"answer_status_question",
"append_audit_record",
"checkout_task",
"get_task_context",
"get_task_history",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rs-question-only-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "rs-secret-hygiene-01",
"title": "The API key never appears in comment bodies, even when asked to document auth",
"fixture": "baseline",
"operations": [
"answer_status_question",
"append_audit_record",
"checkout_task",
"get_task_context",
"list_secret_metadata",
"persist_run",
"read_secret_value",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/rs-secret-hygiene-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"restraint_no_call"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "se-get-issue-01",
"title": "Direct issue fetch plus thread read to answer a history question",
"fixture": "issue-detail",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"route_wake",
"search_tasks"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/se-get-issue-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "se-q-comments-01",
"title": "Search reaches comment bodies, not just titles",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"route_wake",
"search_tasks"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/se-q-comments-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "se-q-filters-01",
"title": "Combine q with status/assignee filters",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"route_wake",
"search_tasks"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/se-q-filters-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "se-q-topic-01",
"title": "Find an issue by topic using the q search param",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_agents",
"persist_run",
"route_wake",
"search_tasks"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/se-q-topic-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-backlog-park-01",
"title": "Postponed work is parked in backlog, not cancelled or closed",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-backlog-park-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-blocked-owner-01",
"title": "Blocking on another issue sets status blocked plus first-class blockedByIssueIds",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-blocked-owner-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-crossteam-cancel-01",
"title": "Cross-team tasks are never cancelled — reassign to the manager instead",
"fixture": "crossteam",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-crossteam-cancel-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-done-comment-01",
"title": "Closing a task is checkout, then PATCH done with an explanatory comment",
"fixture": "done-evidence",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-done-comment-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-env-blocked-notdone-01",
"title": "Impossible deliverable (absent mount, read-only prefix, no route) ends blocked with a named owner — never done or in_review",
"fixture": "env-blocked-task",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-env-blocked-notdone-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-ephemeral-verify-01",
"title": "Artifacts produced outside the synced workspace — the disposition PATCH must carry a persistence caveat (or relocation), never a bare done",
"fixture": "ephemeral-artifacts-task",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-ephemeral-verify-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-handback-review-01",
"title": "Board user asking for the task back gets reassigned + in_review, not done",
"fixture": "handback-comment",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-handback-review-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "st-unverified-toolchain-01",
"title": "Unrunnable mandated verification (certified toolchain unobtainable) ends blocked stating what could not be verified — no unqualified completion claim",
"fixture": "toolchain-verify-task",
"operations": [
"append_audit_record",
"checkout_task",
"finish_task",
"get_task_context",
"persist_run",
"reconcile_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/st-unverified-toolchain-01.yaml",
"assertionClasses": [
"agent_tool_contract"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "su-crossteam-billing-01",
"title": "Cross-team delegation sets billingCode",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/su-crossteam-billing-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "su-inherit-workspace-01",
"title": "Non-child follow-up on the same code change inherits the execution workspace",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/su-inherit-workspace-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "su-no-poll-01",
"title": "Delegate long work as a child issue and rely on wakes, not polling",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/su-no-poll-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "su-parent-goal-01",
"title": "Subtasks are created with parentId and goalId set",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"create_task",
"get_task_context",
"persist_run",
"report_progress",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/su-parent-goal-01.yaml",
"assertionClasses": [
"authorization_policy"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-ask-mode-01",
"title": "Ask-mode wake is answer-only — comment, no state or document writes",
"fixture": "baseline",
"operations": [
"answer_status_question",
"append_audit_record",
"checkout_task",
"get_task_context",
"get_task_history",
"persist_run",
"route_wake"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-ask-mode-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-plan-accepted-01",
"title": "Accepted-plan continuation creates subtasks, never re-plans or re-asks",
"fixture": "continuation-wake",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-plan-accepted-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-plan-annotation-01",
"title": "Plan-annotation wake revises the document and answers annotations via nested routes",
"fixture": "plan-annotations",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-plan-annotation-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-plan-directive-01",
"title": "Planning-mode wake produces plan PUT, revision-bound confirmation, then in_review",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"reconcile_run",
"request_human_input",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-plan-directive-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-plan-directive-02",
"title": "Layer probe — planning directive via wake prose only (no task-context markdown)",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-plan-directive-02.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-recovery-processlost-01",
"title": "Process-lost recovery verifies durable progress first and never redoes posted work",
"fixture": "recovery-processlost",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-recovery-processlost-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-resume-delta-01",
"title": "Layer probe — resume delta with condensed contract only preserves close discipline",
"fixture": "baseline",
"operations": [
"append_audit_record",
"checkout_task",
"get_task_context",
"list_documents",
"persist_run",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-resume-delta-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
},
{
"id": "wk-skilltest-mode-01",
"title": "Skill-test mode writes the structured result to the output document, scoped to this issue",
"fixture": "skill-test-task",
"operations": [
"append_audit_record",
"checkout_task",
"generic_api_request",
"get_task_context",
"list_documents",
"persist_run",
"request_review",
"route_wake",
"write_document"
],
"sourceAnchor": "paperclip-evals/paperclip-skill-optimization/skills/paperclip/tests/cases/wk-skilltest-mode-01.yaml",
"assertionClasses": [
"control_plane_invariant",
"combined_multi_hop"
],
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts::renders every scenario with exposure, control plane, authorization, diff, and parity"
}
],
"lifecycleRequirements": [
{
"id": "provider-round-trip",
"requirement": "provider -> runnerd -> control plane -> runnerd -> provider",
"deterministicOwner": "src/live/runnerd-codex-transport.test.ts"
},
{
"id": "single-daemon",
"requirement": "one Paperclip-owned sandbox daemon and no TypeScript sandbox dispatcher",
"deterministicOwner": "src/live/runnerd-codex-transport.test.ts"
},
{
"id": "catalog-drift",
"requirement": "canonical catalog consistency and drift rejection",
"deterministicOwner": "runner/crates/runner-core/src/provider_bridge.rs::durable_session_refuses_catalog_drift"
},
{
"id": "authorization",
"requirement": "authorization denial and unknown-tool rejection",
"deterministicOwner": "runner/crates/runner-core/src/provider_bridge.rs::forwards_only_authorized_calls_and_correlates_results"
},
{
"id": "duplicates",
"requirement": "correlated duplicate and conflicting-result handling",
"deterministicOwner": "runner/crates/runner-core/src/provider_bridge.rs::rejects_unknown_tools_and_conflicting_duplicate_results"
},
{
"id": "recovery",
"requirement": "lost ACK, reconnect, runner restart, and provider-thread recovery",
"deterministicOwner": "src/control-plane/durable-prp-control-plane.test.ts; src/live/live-session.test.ts"
},
{
"id": "interrupt",
"requirement": "interruption while waiting for a tool result",
"deterministicOwner": "src/live/live-session.test.ts; src/live/clean-room-server.test.ts"
},
{
"id": "bounds",
"requirement": "bounded queues, logs, frames, and retries",
"deterministicOwner": "src/live/turn-stream.test.ts; runner/crates/runner-core/src/durable/runner.rs"
},
{
"id": "cleanup",
"requirement": "process-group cleanup with no abandoned provider",
"deterministicOwner": "runner/crates/runner-core/tests/process_supervisor.rs"
},
{
"id": "secrets",
"requirement": "secret isolation and network restrictions",
"deterministicOwner": "src/live/clean-room-server.test.ts; runner/crates/runner-core/src/durable/runner.rs"
},
{
"id": "transcript-accounting",
"requirement": "assistant transcript capture, token usage, and cost inputs",
"deterministicOwner": "src/live/live-session.test.ts; src/cli/eval-session.ts"
},
{
"id": "state-reconstruction",
"requirement": "fixture and post-run state reconstruction",
"deterministicOwner": "src/scenarios/scenario-explorer.test.ts; src/live/live-session.test.ts"
},
{
"id": "paperclip-adapter-selection",
"requirement": "paperclip_runner is selectable without changing legacy adapter behavior",
"deterministicOwner": "server/src/services/native-runtime/runtime-mode.test.ts; server/src/__tests__/heartbeat-native-runner-selection.test.ts"
},
{
"id": "real-control-plane-binding",
"requirement": "advertised runner tools re-authorize the live company, issue, agent, and run before using real Paperclip services",
"deterministicOwner": "server/src/services/native-runtime/paperclip-runner-tool-authority.test.ts; server/src/services/native-runtime/paperclip-runner-real-server.integration.test.ts"
},
{
"id": "shared-paperclip-prp-route",
"requirement": "Rust runnerd authenticates to the shared Paperclip server route and completes a real bound semantic tool call",
"deterministicOwner": "server/src/realtime/runner-prp-ws.test.ts; server/src/services/native-runtime/paperclip-runner-real-server.integration.test.ts"
},
{
"id": "real-control-plane-idempotency",
"requirement": "real service mutations are replay-safe and reject conflicting idempotency-key reuse",
"deterministicOwner": "server/src/services/native-runtime/paperclip-runner-tool-authority.test.ts"
},
{
"id": "paperclip-thread-projection",
"requirement": "committed PRP reasoning and semantic tool items render in the existing Paperclip task chat",
"deterministicOwner": "ui/src/adapters/paperclip-runner/index.test.ts; server/src/services/native-runtime/paperclip-control-plane-port.test.ts"
}
]
}
Reference in new issue View Git Blame Copy Permalink