paperclip/packages/paperclip-runner/spec/operation-groups/source.json

372 lines
25 KiB
JSON

{
"schemaVersion": 1,
"documentTitle": "Paperclip agent operation groups",
"evalRepositoryUrl": "https://github.com/paperclipai/paperclip-evals/blob/master/",
"prpEventFamilyDescriptions": {
"runner": "Runner connection, drain, and diagnostic lifecycle.",
"runtime": "Runner phase transitions.",
"sandbox": "Sandbox resource measurements.",
"workspace": "Workspace readiness.",
"harness": "Provider harness startup, readiness, exit, and diagnostics.",
"session": "Provider-neutral session open, resume, reconciliation, close, and failure.",
"turn": "Model turn submission through terminal turn disposition.",
"item": "Provider-neutral model/tool item lifecycle.",
"mcp_app": "MCP App discovery, initialization, tool, action, host-context, and teardown evidence.",
"runtime_request": "Runtime permission/input request lifecycle.",
"interaction": "Issue-thread interaction proposal, materialization, response, delivery, and rejection.",
"run": "Structured result negotiation and terminal run outcome.",
"attention": "Continuation and attention routing lifecycle.",
"work": "Recorded work-assessment evidence.",
"issue": "Issue-status decision proposal outcome and application evidence.",
"plan": "Complete provider-authored within-turn checklist snapshots, separate from durable Paperclip Plan documents.",
"tool": "Provider-neutral process, MCP, dynamic, and built-in execution activity.",
"research": "Provider-reported search, page-open, and in-page research activity.",
"delegation": "Child-agent delegation lifecycle and aggregate status.",
"model": "Requested/effective model routing and verification state.",
"context": "Context-window compaction markers without hidden summaries.",
"artifact": "Authorized artifact viewing and structured generated outputs.",
"review": "Provider review-mode state, separate from Paperclip authority.",
"hook": "Bounded provider hook lifecycle and blocking outcomes.",
"memory": "Authorized or unavailable memory citation references.",
"safety": "Provider safety review state attached to governed work.",
"terminal": "Content-free terminal input activity metadata.",
"wait": "Intentional provider waits, distinct from warm idle and human input.",
"provider": "Redacted provider notices and actionable warnings.",
"semantic_tool": "Canonical authorized Paperclip tool input and result evidence.",
"usage": "Provider/model-attributed usage and accounting boundaries."
},
"prpCommandFamilyDescriptions": {
"semantic_tool": "Returns an authorized, correlated Paperclip tool result to the provider through runnerd.",
"run": "Prepare or cancel a run.",
"session": "Open, snapshot, or close a normalized provider session.",
"turn": "Start, steer, interrupt, or stop a model turn.",
"request": "Resolve a pending runtime request.",
"interaction": "Acknowledge delivery of an interaction response.",
"runner": "Drain or shut down the runner process."
},
"optionalGrantGroups": [
{
"id": "discovery",
"description": "Company-visible task, agent, project, and goal discovery.",
"operationIds": ["search_tasks", "list_agents", "get_agent", "list_projects", "list_goals"]
},
{
"id": "projects",
"description": "Project creation and authorized repository discovery through the live company/run authority.",
"operationIds": ["create_project", "list_project_repositories"]
},
{
"id": "delegation_dependencies",
"description": "Create delegated work and maintain dependency edges.",
"operationIds": ["create_task", "set_dependencies"]
},
{
"id": "governance",
"description": "Read, request, comment on, and decide approvals under governed-action checks.",
"operationIds": ["list_approvals", "get_approval", "get_approval_context", "request_approval", "decide_approval", "comment_on_approval"]
},
{
"id": "cases",
"description": "Read and update case summaries without reusing issue-document authority.",
"operationIds": ["list_cases", "upsert_case"]
},
{
"id": "workspace_runtime",
"description": "Inspect and control the active issue workspace runtime.",
"operationIds": ["get_workspace_runtime", "control_workspace_service"]
},
{
"id": "wake_scheduling",
"description": "Schedule a bounded continuation wake when the current task owns the future check.",
"operationIds": ["schedule_wake"]
},
{
"id": "routines",
"description": "Inspect or manage company routines.",
"operationIds": ["list_routines", "manage_routine"]
},
{
"id": "company_skills",
"description": "Inspect company skills and synchronize the current agent's skills.",
"operationIds": ["list_company_skills", "sync_company_skills"]
},
{
"id": "secrets",
"description": "Inspect secret metadata or use a brokered secret value without exposing plaintext evidence.",
"operationIds": ["list_secret_metadata", "read_secret_value"]
},
{
"id": "portability_admin",
"description": "Export portable company state; broad administration remains deferred until split into governed operations.",
"operationIds": ["export_company", "administer_company"]
},
{
"id": "test_escape_hatch",
"description": "Controlled skill-test transport only; never product coverage.",
"operationIds": ["generic_api_request"]
},
{
"id": "api_fallback",
"description": "Discover and invoke HTTP API operations unsupported by available dedicated tools. Production authority and route authorization remain required.",
"operationIds": [
"search_api",
"call_api"
]
}
],
"behaviorGroups": [
{
"id": "hb",
"legacyGroup": 1,
"name": "Heartbeat",
"owner": "control plane + always tools",
"operationIds": ["get_task_context"],
"controlPlaneOperationIds": ["select_work", "enforce_budget"],
"realSurface": "agent identity, inbox-lite, heartbeat context, budget and active-issue services",
"mockStateDomains": ["company", "actor", "wake", "task", "budget", "run"],
"prpEvidence": "runner/session/run context plus bounded task-context tool results",
"gap": "Production semantic binding is unbound; identity and work selection remain injected/control-plane-owned."
},
{
"id": "co",
"legacyGroup": 2,
"name": "Checkout",
"owner": "control plane",
"operationIds": [],
"controlPlaneOperationIds": ["checkout_task"],
"realSurface": "POST /api/issues/:id/checkout and execution-lock services",
"mockStateDomains": ["task", "actor", "run", "idempotency", "fault"],
"prpEvidence": "run preparation and issue-status decision evidence with checkout receipt",
"gap": "Intentionally no model tool; the production checkout receipt still needs the additive semantic-receipt envelope."
},
{
"id": "st",
"legacyGroup": 3,
"name": "Status",
"owner": "always tools + control-plane arbitration",
"operationIds": ["answer_status_question", "finish_task", "block_task", "request_review"],
"controlPlaneOperationIds": ["reconcile_run", "append_audit_record"],
"realSurface": "issue PATCH, review/liveness policy, and native finalization arbitration",
"mockStateDomains": ["task", "comments", "interactions", "blockers", "audit", "run"],
"prpEvidence": "semantic operation receipt, work assessment, issue-status decision, and terminal causality",
"gap": "Production semantic binding and additive typed operation/conflict receipts remain unimplemented."
},
{
"id": "cm",
"legacyGroup": 4,
"name": "Comments",
"owner": "always tools",
"operationIds": ["get_task_history", "report_progress"],
"controlPlaneOperationIds": ["append_audit_record"],
"realSurface": "issue comment list/get/create routes",
"mockStateDomains": ["task", "comments", "actor", "idempotency", "audit"],
"prpEvidence": "bounded read result or idempotent comment-write receipt plus audit reference",
"gap": "Active-task binding is unbound; cross-task comment mutation is deliberately outside V1."
},
{
"id": "se",
"legacyGroup": 5,
"name": "Search",
"owner": "optional discovery tools",
"operationIds": ["search_tasks", "list_agents", "get_agent", "list_projects", "list_goals", "list_project_repositories"],
"controlPlaneOperationIds": [],
"realSurface": "company issue search and agent/project/goal list/get routes",
"mockStateDomains": ["company", "task", "actor", "project", "goal"],
"prpEvidence": "bounded redacted read projections through tool-result item events",
"gap": "Goal operations remain scenario-only. Project and repository discovery contracts are delivered by the live server authority; they are not implemented by the mock command dispatcher."
},
{
"id": "su",
"legacyGroup": 6,
"name": "Subtasks",
"owner": "optional delegation tools",
"operationIds": ["create_task"],
"controlPlaneOperationIds": ["route_wake"],
"realSurface": "company issue create, child issue, assignment, and wake services",
"mockStateDomains": ["company", "task", "actor", "blockers", "wake", "audit"],
"prpEvidence": "company/task state diff, audit reference, and continuation wake evidence",
"gap": "create_task is production-bound to ordinary active-issue child creation with assignment, dependency-ready wake, company checks, child limits, and durable source-scoped idempotency."
},
{
"id": "bl",
"legacyGroup": 7,
"name": "Blockers",
"owner": "always/optional tools + control plane",
"operationIds": ["block_task", "set_dependencies"],
"controlPlaneOperationIds": ["schedule_blocker_wake", "route_wake"],
"realSurface": "issue relations, blocker projection, liveness validation, and blocker wake services",
"mockStateDomains": ["task", "blockers", "wake", "actor", "audit", "fault"],
"prpEvidence": "dependency diff, block receipt, attention routing, and issue-status decision",
"gap": "set_dependencies is production-bound for the active issue; block_task remains unbound, and cancelled-blocker receipts still need typed additive evidence."
},
{
"id": "dp",
"legacyGroup": 8,
"name": "Documents and plans",
"owner": "always tools; restore optional; destructive lifecycle control-plane-only",
"operationIds": ["list_documents", "read_document", "list_document_revisions", "write_document"],
"controlPlaneOperationIds": ["append_audit_record"],
"realSurface": "issue document list/read/upsert/revision/restore/lock/unlock/delete routes",
"mockStateDomains": ["task", "documents", "interactions", "idempotency", "audit", "fault"],
"prpEvidence": "bounded reads and revision-safe write/conflict/denial receipts with revision lineage",
"gap": "restore_document_revision is an approved optional-tool gap; lock/unlock/delete are intentionally control-plane-only."
},
{
"id": "ix",
"legacyGroup": 9,
"name": "Interactions",
"owner": "always tools + addressed resolver",
"operationIds": ["request_human_input"],
"controlPlaneOperationIds": ["route_wake"],
"realSurface": "issue-thread interaction create/respond/accept/reject/withdraw services",
"mockStateDomains": ["task", "documents", "interactions", "wake", "actor", "idempotency"],
"prpEvidence": "interaction proposal/materialization/response/delivery and attention events",
"gap": "Production binding and semantic resolution receipts are unbound."
},
{
"id": "ap",
"legacyGroup": 10,
"name": "Approvals",
"owner": "optional governance tools + governed approver",
"operationIds": ["list_approvals", "get_approval", "get_approval_context", "request_approval", "decide_approval", "comment_on_approval"],
"controlPlaneOperationIds": ["route_wake", "append_audit_record"],
"realSurface": "company approval, decision, issue-link, comment, and governed-action services",
"mockStateDomains": ["company", "task", "approvals", "actor", "wake", "audit", "idempotency"],
"prpEvidence": "governed semantic receipts, audit references, and attention/continuation linkage",
"gap": "Production binding and additive governed-action receipts are unbound; board-only authority stays outside grants."
},
{
"id": "ar",
"legacyGroup": 11,
"name": "Artifacts",
"owner": "always tools + artifact/work-product services",
"operationIds": ["register_deliverable"],
"controlPlaneOperationIds": ["append_audit_record"],
"realSurface": "attachment upload and issue work-product routes",
"mockStateDomains": ["task", "artifacts", "workProducts", "workspace", "audit", "idempotency"],
"prpEvidence": "artifact/work-product reference and durable inspectability receipt; never binary bytes",
"gap": "Production upload/register composite and additive durable-reference receipt are unbound."
},
{
"id": "er",
"legacyGroup": 12,
"name": "Errors and critical rules",
"owner": "runner/control plane + optional workspace/wake tools",
"operationIds": ["get_workspace_runtime", "control_workspace_service", "schedule_wake", "inspect_operation_result"],
"controlPlaneOperationIds": ["release_task", "enforce_budget", "persist_run", "replay_run", "reconcile_run"],
"realSurface": "workspace runtime, monitor/recovery, budget, run persistence/replay, release, and terminal services",
"mockStateDomains": ["workspace", "budget", "run", "wake", "audit", "idempotency", "fault"],
"prpEvidence": "runtime/workspace/attention/run lifecycle, typed denials, replay facts, and terminal causality",
"gap": "Budget stop reasons and semantic denial/conflict receipts require additive v1 envelopes; inspect_operation_result remains scenario-only."
},
{
"id": "rf",
"legacyGroup": 13,
"name": "Reference files",
"owner": "optional domain tools + test-only escape hatch",
"operationIds": ["list_cases", "upsert_case", "list_routines", "manage_routine", "list_company_skills", "sync_company_skills", "list_secret_metadata", "read_secret_value", "export_company", "administer_company", "generic_api_request", "search_api", "call_api", "create_project"],
"controlPlaneOperationIds": ["append_audit_record"],
"realSurface": "project, case, routine, company-skill, secret, portability, and administration services",
"mockStateDomains": ["company", "cases", "routines", "skills", "secrets", "audit", "fault"],
"prpEvidence": "bounded domain projections, redacted broker receipts, company diffs, and audit references",
"gap": "Project creation and API tools require the live server authority; generic_api_request is test-only and the remaining domain operations are scenario-only. Broad administer_company is deferred and cannot claim product coverage. Production API and paired dedicated-tool regressions are recorded separately in paperclip-evals/evals/runner-api-tools; the legacy scenario count is not evidence of that coverage."
},
{
"id": "mh",
"legacyGroup": 14,
"name": "Multi-hop",
"owner": "composed semantic operations + control-plane continuation",
"operationIds": ["create_task", "set_dependencies", "request_human_input", "request_approval", "register_deliverable"],
"controlPlaneOperationIds": ["route_wake", "reconcile_run"],
"realSurface": "delegation, dependency, interaction, approval, artifact, and terminal orchestration services",
"mockStateDomains": ["task", "blockers", "interactions", "approvals", "artifacts", "wake", "run", "audit"],
"prpEvidence": "correlated operation receipts, state diffs, attention hops, work assessment, status decision, and terminal outcome",
"gap": "No generic transaction tool is allowed; shared mock/real conformance must prove each composed effect."
},
{
"id": "rs",
"legacyGroup": 15,
"name": "Restraint and no-call",
"owner": "policy/exposure layer",
"operationIds": ["answer_status_question", "read_secret_value", "generic_api_request"],
"controlPlaneOperationIds": ["enforce_budget"],
"realSurface": "task-mode, secret-broker, test-scope, pause, and budget policy checks",
"mockStateDomains": ["actor", "task", "budget", "secrets", "audit", "fault"],
"prpEvidence": "absence of forbidden effects plus typed policy denial/redaction receipts when a call is attempted",
"gap": "Typed redaction/authorization receipts need additive v1 evidence; generic_api_request is never a product fallback."
},
{
"id": "wk",
"legacyGroup": 16,
"name": "Wake situations",
"owner": "control plane + always context/history tools",
"operationIds": ["get_task_context", "get_task_history", "schedule_wake"],
"controlPlaneOperationIds": ["select_work", "route_wake"],
"realSurface": "wakeup requests, heartbeat context, comment/interaction/approval/blocker wake routing, and scheduled wake services",
"mockStateDomains": ["wake", "task", "comments", "interactions", "approvals", "blockers", "run"],
"prpEvidence": "attention request routing/resolution plus resumed session/run causality",
"gap": "Production scheduling binding is unbound; control-plane routing remains non-callable."
}
],
"rules": {
"companyAuthorization": [
"Every entity read and write is resolved inside the authenticated actor's company; cross-company identifiers fail without disclosing protected facts.",
"Board actors use active membership and role permissions. Agent writes require a company-scoped run JWT and X-Paperclip-Run-Id; active-task tools cannot accept a caller-selected company or arbitrary task.",
"Optional tools are omitted unless every required claim, role, and task-mode condition is satisfied. A grant never bypasses approval, budget, pause, execution-lock, interaction-owner, or other governed-action checks."
],
"taskModes": [
"standard permits the full eligible catalog subject to claims and role checks.",
"ask is answer-only: investigation reads are eligible, while implementation, document mutation, delegation, terminal, and governed writes are absent.",
"planning permits plan/document/progress/input operations but not delegation or terminal completion; accepting a plan transitions the issue into a fresh standard execution continuation for the exact accepted revision.",
"skill_test exposes only scenario-admitted tools. generic_api_request additionally requires the explicit test grant and allowlist and never supplies product coverage."
],
"redaction": [
"Tool descriptors declare observable redaction. Secret plaintext may reach only the model-use capsule authorized for a bound secret; it never reaches PRP, logs, artifacts, errors, audit details, or serialized tool results.",
"Authorization denials reveal stable codes, missing public claims, and remediation only; they do not include protected entity state, credentials, headers, cookies, or another company's policy.",
"Artifacts carry durable references, hashes, content type, and size on the wire; binary payloads remain in storage transports."
],
"idempotency": [
"Every mutation whose descriptor says required must carry a stable idempotency key. Retrying the same key and equivalent input returns the prior receipt without duplicating side effects.",
"Reusing a key with different input is an idempotency conflict. Optimistic document writes additionally bind baseRevisionId and return the current revision on conflict.",
"PRP source event IDs are idempotent, source sequence gaps are evidence, and replay is side-effect free. Replaying a trace cannot repeat control-plane writes."
],
"sideEffects": [
"read operations return bounded projections and do not mutate control-plane state.",
"task_write and company_write operations emit normalized state diffs and immutable audit references after production authorization succeeds.",
"governance, workspace_control, secret_read, and admin operations retain their production-specific gates; catalog exposure is necessary but never sufficient authority.",
"Terminal semantic operations propose intent. The control plane owns checkout, release, budget enforcement, persisted run evidence, replay, wake routing, audit append, and final status arbitration."
]
},
"documentLifecycle": {
"scope": [
"Issue documents are active-task working records identified by (activeIssueId, key). Always-present document tools do not accept a company id or arbitrary issue id.",
"Cross-task document reads require a future explicit optional operation and grant; case documents and future company knowledge are separate resource types.",
"Locked-document fallback may create a deterministic new key only when lockedDocumentStrategy is create_new_document; the source stays locked and the returned receipt names the redirected key."
],
"operations": [
{"action": "create", "semanticOperation": "write_document", "placement": "always_agent_tool", "contract": "baseRevisionId is null; create revision 1 and return document/revision/audit identity.", "status": "supported contract; production binding unbound"},
{"action": "read", "semanticOperation": "list_documents / read_document", "placement": "always_agent_tool", "contract": "List metadata or read the current active-task document by stable key.", "status": "supported contract; production binding unbound"},
{"action": "update", "semanticOperation": "write_document", "placement": "always_agent_tool", "contract": "Require the exact latest baseRevisionId and an idempotency key; append an immutable revision.", "status": "supported contract; production binding unbound"},
{"action": "revisions", "semanticOperation": "list_document_revisions", "placement": "always_agent_tool", "contract": "Return bounded immutable revision history newest first.", "status": "supported contract; production binding unbound"},
{"action": "restore", "semanticOperation": "restore_document_revision", "placement": "optional_agent_tool (documents:restore)", "contract": "Validate same-document lineage, reject locked documents, append a new revision, and return source/new revision identity; restoring current is a no-change duplicate.", "status": "approved catalog gap"},
{"action": "lock", "semanticOperation": "none", "placement": "control_plane_owned", "contract": "Board/administrative lifecycle action; agent writes receive document_locked or use explicit create-new fallback.", "status": "intentionally non-callable"},
{"action": "unlock", "semanticOperation": "none", "placement": "control_plane_owned", "contract": "Board/administrative lifecycle action; never inferred from a failed write.", "status": "intentionally non-callable"},
{"action": "delete", "semanticOperation": "none", "placement": "control_plane_owned", "contract": "Destructive audited action; pending targets become stale and the runner never recreates them automatically.", "status": "intentionally non-callable"}
]
},
"legacySemanticTargetDispositions": {
"injected_actor_context": {"kind": "control_plane", "targets": ["select_work"], "reason": "Identity is launch context, not a model tool."},
"runner_work_selection": {"kind": "control_plane", "targets": ["select_work"], "reason": "Inbox selection belongs to the control plane."},
"get_project": {"kind": "folded", "targets": ["list_projects"], "reason": "The bounded discovery operation owns project list/get projection in V1."},
"wait_for_workspace_service": {"kind": "folded", "targets": ["control_workspace_service"], "reason": "Wait is a bounded action of workspace service control."},
"get_goal": {"kind": "folded", "targets": ["list_goals"], "reason": "The bounded discovery operation owns goal list/get projection in V1."},
"semantic_task_disposition": {"kind": "composite", "targets": ["answer_status_question", "finish_task", "block_task", "request_review"], "reason": "Generic issue PATCH is replaced by intent-specific terminal/status operations."},
"atomic_checkout": {"kind": "control_plane", "targets": ["checkout_task"], "reason": "Checkout is an atomic control-plane transaction."},
"runtime_release": {"kind": "control_plane", "targets": ["release_task"], "reason": "Release is runner/control-plane cleanup."},
"restore_document_revision": {"kind": "known_gap", "targets": [], "reason": "Approved optional documents:restore operation is not yet in the canonical catalog."},
"link_approval": {"kind": "folded", "targets": ["request_approval", "get_task_context"], "reason": "Issue linkage is part of approval request/context composites."},
"unlink_approval": {"kind": "control_plane", "targets": ["append_audit_record"], "reason": "No standalone agent unlink tool is approved in V1."},
"test_only_api_escape_hatch": {"kind": "folded", "targets": ["generic_api_request"], "reason": "Compatibility alias for the test-only escape hatch."}
}
}