diff --git a/doc/evals.md b/doc/evals.md index 499d29278ce..6b9766920d5 100644 --- a/doc/evals.md +++ b/doc/evals.md @@ -257,3 +257,7 @@ named existing controls on legacy and native Codex. Discover it with results and follow-up coverage are recorded in that suite's guide. Continuation accounting has an explicit-only eight-cell Product E2E [baseline suite](../tests/runner-e2e/CONTINUATION-ACCOUNTING.md), complementing the deterministic lifecycle inventory. + +The explicit-only Product E2E `api-response-reading` suite verifies retrieval of +large saved API responses on local and Daytona native Codex runs. See the +[Runner E2E guide](../tests/runner-e2e/README.md#bounded-api-response-reading). diff --git a/doc/runner-api-tools.md b/doc/runner-api-tools.md index f095e14783c..2f72b0662be 100644 --- a/doc/runner-api-tools.md +++ b/doc/runner-api-tools.md @@ -54,6 +54,22 @@ can be supplied. Routes still validate payloads and enforce permissions. Requests have a 30-second HTTP timeout, 16 KiB URL limit and 10 MiB payload/response transfer limit. Responses above 24 KiB and binary responses become company-owned assets with retrievable references; text previews are limited to 2,000 bytes. +To inspect saved text without creating another artifact, call its authorized +content operation with `responseText`: + +```json +{"operationId":"GET /api/assets/{assetId}/content","pathParams":{"assetId":"RETURNED_ARTIFACT_ID"},"responseText":{"offsetBytes":0,"limitBytes":8192}} +``` + +The result contains `data` as text (including JSON), plus `responseText` with +`offsetBytes`, `nextOffsetBytes`, and `totalBytes`. Continue at `nextOffsetBytes` +until it is null. Windows end at UTF-8 boundaries. The limit defaults to 24 KiB +and accepts 4–24,576 bytes. The server rejects binary content, invalid UTF-8, +and offsets inside a code point or beyond the response. This option only works +with GET; never repeat a mutation to retrieve another part of its response. +Read the saved artifact for a stable snapshot instead of paging a changing live +response. The existing 10 MiB transfer limit and all route authorization remain. + Tool responses identify the HTTP route with `apiOperationId`. The native protocol reserves `operationId` and `callId` for semantic tool-call identity; API metadata must not masquerade as that envelope. Saved mutation receipts are normalized at diff --git a/packages/paperclip-runner/generated/capability/semantic-tool-contracts.json b/packages/paperclip-runner/generated/capability/semantic-tool-contracts.json index 1558a1ef65a..83b0294cb43 100644 --- a/packages/paperclip-runner/generated/capability/semantic-tool-contracts.json +++ b/packages/paperclip-runner/generated/capability/semantic-tool-contracts.json @@ -1 +1 @@ -[{"annotations":{"exposure":"always","operationId":"get_task_context","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read the active task and actor, including the exact approved Markdown revision when this issue has an accepted plan.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"get_task_context","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"get_task_history","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read bounded comments on the active task.","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"}},"required":[],"type":"object"},"name":"get_task_history","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"list_documents","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List revisioned documents on the active task.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_documents","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"read_document","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read the current revision of one active-task document.","inputSchema":{"additionalProperties":false,"properties":{"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"}},"required":["key"],"type":"object"},"name":"read_document","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"list_document_revisions","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read bounded revision history for one active-task document.","inputSchema":{"additionalProperties":false,"properties":{"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"},"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"}},"required":["key"],"type":"object"},"name":"list_document_revisions","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"report_progress","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Append a durable progress comment to the active task.","inputSchema":{"additionalProperties":false,"properties":{"body":{"description":"Multiline progress update.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","body"],"type":"object"},"name":"report_progress","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"answer_status_question","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Append the answer to a status-only wake without changing task disposition.","inputSchema":{"additionalProperties":false,"properties":{"body":{"description":"Concise status answer.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","body"],"type":"object"},"name":"answer_status_question","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"write_document","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create or update an active-task document with optimistic revision safety.","inputSchema":{"additionalProperties":false,"properties":{"baseRevisionId":{"description":"Current revision id, or null when creating.","maxLength":20000,"type":["string","null"]},"body":{"description":"Markdown document body.","maxLength":200000,"minLength":1,"type":"string"},"changeSummary":{"description":"Optional revision summary.","maxLength":20000,"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"},"title":{"description":"Document title.","maxLength":300,"minLength":1,"type":"string"}},"required":["idempotencyKey","key","title","body","baseRevisionId"],"type":"object"},"name":"write_document","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"request_human_input","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a durable human question or approval card on the current Paperclip task bound to this run; Paperclip renders it and authenticates the response. Use questions with continuationPolicy='wake_assignee' when an answer is needed, including otherwise tool-free chat turns. Supply a stable idempotencyKey and reuse it on retries. For one question at a time, ask only the next unanswered question and wait for its real answer. Never infer answers, answer your own card, or treat clarification as approval. Preserve existing review gates. Call this tool before claiming a question was asked; if creation fails, report the failure. Do not fabricate answer links or Markdown buttons, post duplicate cards, or substitute call_api. Use payload.questions for choices and payload.questionSet for text fields; see the payload schema for formats.","inputSchema":{"additionalProperties":false,"properties":{"continuationPolicy":{"enum":["none","wake_assignee","wake_assignee_on_accept"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"interactionKind":{"enum":["confirmation","checkbox","questions","suggest_tasks","item_verdicts"]},"payload":{"additionalProperties":true,"description":"Kind-specific interaction data. For interactionKind='questions', use version:1 and questions:[{id,prompt,selectionMode:'single'|'multi',required?,options:[{id,label,description?,freeText?}]}]. Choice questions need at least two distinct meaningful options. For an open-ended text answer, ALSO include questionSet:{schema:'paperclip.question_set.v1',questions:[{id,prompt,answerMode:'text',required?}]} with no options or customAnswer in its text questions. Keep matching IDs/prompts in both arrays; the required compatibility questions entry uses selectionMode:'single' and options:[{id:'describe',label:'Your answer',freeText:true}]. Without questionSet this incorrectly renders as a one-option choice. Never use a lone Other or describe option as the presentation. Option keys are id/label, not value. For confirmation, payload may be {}. Keep IDs stable across retries.","type":"object"},"prompt":{"description":"Question or decision prompt.","maxLength":10000,"minLength":1,"type":"string"},"targetRevisionId":{"description":"Optional bound document revision.","maxLength":20000,"type":["string","null"]},"title":{"description":"Interaction card title.","maxLength":300,"minLength":1,"type":"string"}},"required":["idempotencyKey","interactionKind","title","prompt","continuationPolicy"],"type":"object"},"name":"request_human_input","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"register_deliverable","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Register attachment metadata and its artifact work product without credentials or bytes in the tool result.","inputSchema":{"additionalProperties":false,"properties":{"byteSize":{"maximum":100000000,"minimum":0,"type":"integer"},"contentRef":{"description":"Opaque package-local content reference.","maxLength":2000,"minLength":1,"type":"string"},"contentType":{"description":"Media type.","maxLength":200,"minLength":1,"type":"string"},"filename":{"description":"Display filename.","maxLength":500,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"sha256":{"pattern":"^[a-fA-F0-9]{64}$","type":"string"},"title":{"description":"Work-product title.","maxLength":500,"minLength":1,"type":"string"}},"required":["idempotencyKey","filename","contentType","byteSize","sha256","contentRef","title"],"type":"object"},"name":"register_deliverable","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"finish_task","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Finish the active task with a durable summary.","inputSchema":{"additionalProperties":false,"properties":{"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"summary":{"description":"Completion summary.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","summary"],"type":"object"},"name":"finish_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"block_task","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Block the active task with a durable reason and optional first-class dependencies.","inputSchema":{"additionalProperties":false,"properties":{"blockedByTaskIds":{"description":"Internal task ids that block this task.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"reason":{"description":"Block reason.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","reason"],"type":"object"},"name":"block_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"request_review","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Move the active task to review with a durable summary.","inputSchema":{"additionalProperties":false,"properties":{"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"summary":{"description":"Review handoff summary.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","summary"],"type":"object"},"name":"request_review","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_agents","requiredClaims":["discovery:agents:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List redacted actor profiles.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_agents","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_agent","requiredClaims":["discovery:agents:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one redacted actor profile.","inputSchema":{"additionalProperties":false,"properties":{"actorId":{"description":"Actor id.","maxLength":200,"minLength":1,"type":"string"}},"required":["actorId"],"type":"object"},"name":"get_agent","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"hire_agent","requiredClaims":["delegation:agents:create"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a persistent native Runner teammate with an identity and persona. The teammate reports to the caller and inherits the caller's native runtime; provider, adapter, environment, and credential settings are selected by Paperclip and are never caller-supplied here. Reuse a suitable teammate from list_agents when possible.","inputSchema":{"additionalProperties":false,"properties":{"capabilities":{"maxLength":2000,"type":["string","null"]},"instructions":{"maxLength":20000,"type":["string","null"]},"name":{"maxLength":200,"minLength":1,"type":"string"},"role":{"enum":["ceo","cto","cmo","cfo","security","engineer","designer","pm","qa","devops","researcher","general"],"type":"string"},"title":{"maxLength":300,"type":["string","null"]}},"required":["name"],"type":"object"},"name":"hire_agent","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"search_tasks","requiredClaims":["discovery:tasks:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Search tasks by text and status within the run company.","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"},"query":{"maxLength":500,"type":"string"},"statuses":{"items":{"enum":["backlog","todo","in_progress","in_review","done","blocked","cancelled"]},"maxItems":7,"type":"array","uniqueItems":true}},"required":[],"type":"object"},"name":"search_tasks","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_approvals","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List approvals in the run company.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_approvals","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_approval","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one approval without protected data.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"}},"required":["approvalId"],"type":"object"},"name":"get_approval","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_approval_context","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one approval, its comments, and linked tasks.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"}},"required":["approvalId"],"type":"object"},"name":"get_approval_context","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_workspace_runtime","requiredClaims":["workspace:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read active-task workspace services.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"get_workspace_runtime","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"control_workspace_service","requiredClaims":["workspace:control"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Start, stop, or fault one active-task workspace service.","inputSchema":{"additionalProperties":false,"properties":{"action":{"enum":["start","stop","fail"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"serviceId":{"description":"Workspace service id.","maxLength":200,"minLength":1,"type":"string"},"url":{"description":"Optional service URL.","maxLength":20000,"type":["string","null"]}},"required":["idempotencyKey","serviceId","action"],"type":"object"},"name":"control_workspace_service","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"set_dependencies","requiredClaims":["dependencies:write"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Replace the active task's first-class blocker set.","inputSchema":{"additionalProperties":false,"properties":{"blockedByTaskIds":{"description":"Replacement blocker task ids.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","blockedByTaskIds"],"type":"object"},"name":"set_dependencies","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_task","requiredClaims":["delegation:tasks:create"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a project task from a conversation, or a child from an ordinary task. Persist initialPlan before execution. Set status to backlog when the user wants to save or plan work without starting it; backlog tasks never wake an agent. Omitted status means todo, subject to blockers.","inputSchema":{"additionalProperties":false,"properties":{"assigneeActorId":{"description":"Optional agent assignee. Omit to assign the current agent.","maxLength":20000,"type":["string","null"]},"blockedByTaskIds":{"description":"Initial blocker task ids.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"description":{"description":"Child task description.","maxLength":20000,"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"initialPlan":{"description":"Relevant markdown plan saved on the new task before execution starts.","maxLength":200000,"type":["string","null"]},"priority":{"enum":["critical","high","medium","low"]},"projectId":{"description":"Project ID for the task.","type":["string","null"]},"status":{"description":"Initial status. Use backlog to save work without executing it. Defaults to todo (blocked when dependencies are unresolved).","enum":["backlog","todo"]},"title":{"description":"Child task title.","maxLength":500,"minLength":1,"type":"string"}},"required":["idempotencyKey","title"],"type":"object"},"name":"create_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"},"task":{"additionalProperties":false,"properties":{"assigneeActorId":{"type":["string","null"]},"id":{"minLength":1,"type":"string"},"identifier":{"type":["string","null"]},"parentId":{"minLength":1,"type":["string","null"]},"projectId":{"minLength":1,"type":["string","null"]},"status":{"minLength":1,"type":"string"}},"required":["id","identifier","parentId","status","assigneeActorId"],"type":"object"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds","task"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"request_approval","requiredClaims":["governance:approvals:request"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a governed approval and waiting posture.","inputSchema":{"additionalProperties":false,"properties":{"approvalType":{"description":"Stable approval type.","maxLength":200,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"payload":{"additionalProperties":true,"type":"object"}},"required":["idempotencyKey","approvalType","payload"],"type":"object"},"name":"request_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"decide_approval","requiredClaims":["governance:approvals:decide"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Decide an approval as an explicitly authorized approver.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"},"decision":{"enum":["approved","rejected","cancelled"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"note":{"description":"Decision note.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","approvalId","decision","note"],"type":"object"},"name":"decide_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"comment_on_approval","requiredClaims":["governance:approvals:comment"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Add a durable comment to an approval.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"},"body":{"description":"Approval comment.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","approvalId","body"],"type":"object"},"name":"comment_on_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"schedule_wake","requiredClaims":["control_plane:wakes"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Schedule a deterministic continuation wake.","inputSchema":{"additionalProperties":false,"properties":{"delayTicks":{"maximum":10000,"minimum":1,"type":"integer"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"payload":{"additionalProperties":true,"type":"object"},"reason":{"enum":["manual","issue_commented","interaction_resolved","approval_resolved","blockers_resolved","scheduled_retry","resume"]}},"required":["idempotencyKey","reason","delayTicks"],"type":"object"},"name":"schedule_wake","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"generic_api_request","requiredClaims":["test:generic_api_request"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Test-only escape hatch. Disabled unless the scenario and explicit claim both enable it.","inputSchema":{"additionalProperties":false,"properties":{"body":{"additionalProperties":true,"type":"object"},"method":{"enum":["GET","POST","PATCH"]},"path":{"maxLength":500,"pattern":"^/mock/","type":"string"}},"required":["method","path"],"type":"object"},"name":"generic_api_request","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"search_api","requiredClaims":["api:discover"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Fallback only: discover Paperclip API operations when the available dedicated tools cannot express the task. Prefer dedicated tools for common operations; do not search before using them. For a persistent hire, first list_agents to reuse a suitable teammate. Search agent-hires for the hiring schema and agent-configurations for compatible adapter/runtime settings, then use call_api with the returned operationId. Supply role-specific instructionsBundle.files as a filename-to-content record. Use the returned agent.id for delegation and obey any pending approval. Provider helper threads are temporary workers, not Paperclip hires. If a hire response is uncertain, reconcile with list_agents before retrying.","inputSchema":{"additionalProperties":false,"properties":{"cursor":{"maxLength":200,"type":"string"},"limit":{"default":5,"maximum":10,"minimum":1,"type":"integer"},"query":{"maxLength":500,"minLength":1,"type":"string"}},"required":["query"],"type":"object"},"name":"search_api","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"call_api","requiredClaims":["api:call"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool.","inputSchema":{"additionalProperties":false,"properties":{"body":{"anyOf":[{"additionalProperties":true,"type":"object"},{"items":{},"type":"array"},{"type":"string"},{"type":"number"},{"type":"boolean"},{"type":"null"}],"description":"Request value matching the discovered schema. For JSON object or array requests, pass the object or array directly, never a JSON-encoded string. Strings are for text bodies or endpoints whose schema explicitly accepts a string."},"contentType":{"maxLength":120,"type":"string"},"files":{"items":{"additionalProperties":false,"oneOf":[{"properties":{"artifactId":{}},"required":["artifactId"]},{"properties":{"path":{}},"required":["path"]}],"properties":{"artifactId":{"type":"string"},"field":{"type":"string"},"path":{"description":"File relative to the active issue workspace. Remote files must first be uploaded as an artifact.","type":"string"}},"type":"object"},"maxItems":10,"type":"array"},"operationId":{"description":"Exact operationId returned by search_api, for example GET /api/projects/{id}. Do not guess identifiers.","maxLength":500,"minLength":1,"type":"string"},"pathParams":{"additionalProperties":{"type":"string"},"type":"object"},"query":{"additionalProperties":true,"type":"object"}},"required":["operationId"],"type":"object"},"name":"call_api","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_project","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a project after considering existing projects and available repositories. repositoryIds and repositoryUrls accept multiple existing repositories. Use HTTPS GitHub repositoryUrls when an accessible repo is not in the catalog; this registers project repositories, not remote GitHub repositories. Non-code projects may omit repositories. Cannot combine repositoryIds/repositoryUrls with workspace. Reuse the idempotency key on retries.","inputSchema":{"additionalProperties":false,"properties":{"archivedAt":{"description":"Archive timestamp.","maxLength":20000,"type":["string","null"]},"color":{"description":"Project color.","maxLength":20000,"type":["string","null"]},"description":{"description":"Project outcome and context.","maxLength":20000,"type":["string","null"]},"env":{"additionalProperties":true,"type":"object"},"executionWorkspacePolicy":{"additionalProperties":true,"type":"object"},"goalId":{"description":"Goal ID.","maxLength":20000,"type":["string","null"]},"goalIds":{"description":"Goal IDs.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"icon":{"description":"Project icon.","enum":["folder","rocket","code","terminal","database","globe","package","boxes","box","layers","briefcase","compass","target","flame","zap","star","bug","wrench","hammer","lightbulb","sparkles","shield","lock","search","cog","brain","cpu","git-branch","file-code","puzzle","gem","atom","heart","mail","message-square","crown","radar","telescope","hexagon",null],"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"leadAgentId":{"description":"Lead agent ID.","maxLength":20000,"type":["string","null"]},"name":{"description":"Project name.","maxLength":500,"minLength":1,"type":"string"},"repositoryIds":{"description":"Authorized repository IDs from list_project_repositories; may contain multiple repositories.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"repositoryUrls":{"description":"Existing HTTPS GitHub repository URLs, including repos absent from the catalog.","items":{"maxLength":2000,"pattern":"^https://github\\.com/(?!\\.{1,2}/)[A-Za-z0-9_.-]+/(?!\\.{1,2}/?$)[A-Za-z0-9_.-]+/?$","type":"string"},"maxItems":100,"type":"array"},"status":{"enum":["backlog","planned","in_progress","completed","cancelled"]},"targetDate":{"description":"Target date.","maxLength":20000,"type":["string","null"]},"workspace":{"additionalProperties":true,"type":"object"}},"required":["idempotencyKey","name"],"type":"object"},"name":"create_project","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_project_repositories","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List authorized repositories with stable IDs and names. Consider appropriate repositories before creating a project; never invent IDs.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_project_repositories","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_projects","requiredClaims":["discovery:projects:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Inspect available company projects before selecting a project for new work.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_projects","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_skill","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a reusable single-file skill in the company library. Supply a complete SKILL.md whose name and description match the inputs. This saves the skill and shows a card; it does not assign the skill to any agent. Reuse idempotencyKey on retries.","inputSchema":{"additionalProperties":false,"properties":{"description":{"maxLength":2000,"minLength":1,"type":"string"},"idempotencyKey":{"maxLength":240,"minLength":1,"type":"string"},"markdown":{"description":"Complete SKILL.md including name and description frontmatter and substantive instructions.","maxLength":200000,"minLength":1,"type":"string"},"name":{"description":"Lowercase skill name, matching SKILL.md frontmatter.","maxLength":120,"minLength":1,"pattern":"^[a-z0-9]+(?:-[a-z0-9]+)*$","type":"string"},"slug":{"description":"Optional; must equal name.","maxLength":120,"minLength":1,"pattern":"^[a-z0-9]+(?:-[a-z0-9]+)*$","type":"string"}},"required":["idempotencyKey","name","description","markdown"],"type":"object"},"name":"create_skill","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"reassign_task","requiredClaims":["delegation:tasks:assign"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Reassign an existing task to another company agent. Read search_tasks first and supply its current assignee and statusVersion to prevent overwriting a concurrent change. Preserve the task, documents, dependencies, and blocked/backlog status. Active work is stopped before handoff. Use a stable idempotency key for retries. Cannot reassign this run’s own task, conversations, completed tasks, or pending reviews; use create_task for delegation from the current task.","inputSchema":{"additionalProperties":false,"properties":{"assigneeActorId":{"description":"New company agent ID from list_agents.","minLength":1,"type":"string"},"expectedAssigneeActorId":{"description":"Current assigneeAgentId from search_tasks; null means unassigned.","type":["string","null"]},"expectedStatusVersion":{"description":"Current statusVersion from search_tasks.","minimum":0,"type":"integer"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"reason":{"description":"Why the task should move and context for the new owner.","maxLength":20000,"minLength":1,"type":"string"},"taskId":{"description":"Existing task ID from search_tasks.","minLength":1,"type":"string"}},"required":["idempotencyKey","taskId","assigneeActorId","expectedAssigneeActorId","expectedStatusVersion","reason"],"type":"object"},"name":"reassign_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}}] +[{"annotations":{"exposure":"always","operationId":"get_task_context","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read the active task and actor, including the exact approved Markdown revision when this issue has an accepted plan.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"get_task_context","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"get_task_history","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read bounded comments on the active task.","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"}},"required":[],"type":"object"},"name":"get_task_history","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"list_documents","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List revisioned documents on the active task.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_documents","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"read_document","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read the current revision of one active-task document.","inputSchema":{"additionalProperties":false,"properties":{"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"}},"required":["key"],"type":"object"},"name":"read_document","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"list_document_revisions","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read bounded revision history for one active-task document.","inputSchema":{"additionalProperties":false,"properties":{"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"},"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"}},"required":["key"],"type":"object"},"name":"list_document_revisions","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"always","operationId":"report_progress","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Append a durable progress comment to the active task.","inputSchema":{"additionalProperties":false,"properties":{"body":{"description":"Multiline progress update.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","body"],"type":"object"},"name":"report_progress","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"answer_status_question","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Append the answer to a status-only wake without changing task disposition.","inputSchema":{"additionalProperties":false,"properties":{"body":{"description":"Concise status answer.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","body"],"type":"object"},"name":"answer_status_question","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"write_document","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create or update an active-task document with optimistic revision safety.","inputSchema":{"additionalProperties":false,"properties":{"baseRevisionId":{"description":"Current revision id, or null when creating.","maxLength":20000,"type":["string","null"]},"body":{"description":"Markdown document body.","maxLength":200000,"minLength":1,"type":"string"},"changeSummary":{"description":"Optional revision summary.","maxLength":20000,"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"key":{"description":"Stable issue-document key.","maxLength":120,"minLength":1,"type":"string"},"title":{"description":"Document title.","maxLength":300,"minLength":1,"type":"string"}},"required":["idempotencyKey","key","title","body","baseRevisionId"],"type":"object"},"name":"write_document","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"request_human_input","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a durable human question or approval card on the current Paperclip task bound to this run; Paperclip renders it and authenticates the response. Use questions with continuationPolicy='wake_assignee' when an answer is needed, including otherwise tool-free chat turns. Supply a stable idempotencyKey and reuse it on retries. For one question at a time, ask only the next unanswered question and wait for its real answer. Never infer answers, answer your own card, or treat clarification as approval. Preserve existing review gates. Call this tool before claiming a question was asked; if creation fails, report the failure. Do not fabricate answer links or Markdown buttons, post duplicate cards, or substitute call_api. Use payload.questions for choices and payload.questionSet for text fields; see the payload schema for formats.","inputSchema":{"additionalProperties":false,"properties":{"continuationPolicy":{"enum":["none","wake_assignee","wake_assignee_on_accept"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"interactionKind":{"enum":["confirmation","checkbox","questions","suggest_tasks","item_verdicts"]},"payload":{"additionalProperties":true,"description":"Kind-specific interaction data. For interactionKind='questions', use version:1 and questions:[{id,prompt,selectionMode:'single'|'multi',required?,options:[{id,label,description?,freeText?}]}]. Choice questions need at least two distinct meaningful options. For an open-ended text answer, ALSO include questionSet:{schema:'paperclip.question_set.v1',questions:[{id,prompt,answerMode:'text',required?}]} with no options or customAnswer in its text questions. Keep matching IDs/prompts in both arrays; the required compatibility questions entry uses selectionMode:'single' and options:[{id:'describe',label:'Your answer',freeText:true}]. Without questionSet this incorrectly renders as a one-option choice. Never use a lone Other or describe option as the presentation. Option keys are id/label, not value. For confirmation, payload may be {}. Keep IDs stable across retries.","type":"object"},"prompt":{"description":"Question or decision prompt.","maxLength":10000,"minLength":1,"type":"string"},"targetRevisionId":{"description":"Optional bound document revision.","maxLength":20000,"type":["string","null"]},"title":{"description":"Interaction card title.","maxLength":300,"minLength":1,"type":"string"}},"required":["idempotencyKey","interactionKind","title","prompt","continuationPolicy"],"type":"object"},"name":"request_human_input","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"register_deliverable","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Register attachment metadata and its artifact work product without credentials or bytes in the tool result.","inputSchema":{"additionalProperties":false,"properties":{"byteSize":{"maximum":100000000,"minimum":0,"type":"integer"},"contentRef":{"description":"Opaque package-local content reference.","maxLength":2000,"minLength":1,"type":"string"},"contentType":{"description":"Media type.","maxLength":200,"minLength":1,"type":"string"},"filename":{"description":"Display filename.","maxLength":500,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"sha256":{"pattern":"^[a-fA-F0-9]{64}$","type":"string"},"title":{"description":"Work-product title.","maxLength":500,"minLength":1,"type":"string"}},"required":["idempotencyKey","filename","contentType","byteSize","sha256","contentRef","title"],"type":"object"},"name":"register_deliverable","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"finish_task","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Finish the active task with a durable summary.","inputSchema":{"additionalProperties":false,"properties":{"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"summary":{"description":"Completion summary.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","summary"],"type":"object"},"name":"finish_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"block_task","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Block the active task with a durable reason and optional first-class dependencies.","inputSchema":{"additionalProperties":false,"properties":{"blockedByTaskIds":{"description":"Internal task ids that block this task.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"reason":{"description":"Block reason.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","reason"],"type":"object"},"name":"block_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"always","operationId":"request_review","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Move the active task to review with a durable summary.","inputSchema":{"additionalProperties":false,"properties":{"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"summary":{"description":"Review handoff summary.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","summary"],"type":"object"},"name":"request_review","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_agents","requiredClaims":["discovery:agents:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List redacted actor profiles.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_agents","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_agent","requiredClaims":["discovery:agents:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one redacted actor profile.","inputSchema":{"additionalProperties":false,"properties":{"actorId":{"description":"Actor id.","maxLength":200,"minLength":1,"type":"string"}},"required":["actorId"],"type":"object"},"name":"get_agent","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"hire_agent","requiredClaims":["delegation:agents:create"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a persistent native Runner teammate with an identity and persona. The teammate reports to the caller and inherits the caller's native runtime; provider, adapter, environment, and credential settings are selected by Paperclip and are never caller-supplied here. Reuse a suitable teammate from list_agents when possible.","inputSchema":{"additionalProperties":false,"properties":{"capabilities":{"maxLength":2000,"type":["string","null"]},"instructions":{"maxLength":20000,"type":["string","null"]},"name":{"maxLength":200,"minLength":1,"type":"string"},"role":{"enum":["ceo","cto","cmo","cfo","security","engineer","designer","pm","qa","devops","researcher","general"],"type":"string"},"title":{"maxLength":300,"type":["string","null"]}},"required":["name"],"type":"object"},"name":"hire_agent","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"search_tasks","requiredClaims":["discovery:tasks:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Search tasks by text and status within the run company.","inputSchema":{"additionalProperties":false,"properties":{"limit":{"default":50,"maximum":200,"minimum":1,"type":"integer"},"query":{"maxLength":500,"type":"string"},"statuses":{"items":{"enum":["backlog","todo","in_progress","in_review","done","blocked","cancelled"]},"maxItems":7,"type":"array","uniqueItems":true}},"required":[],"type":"object"},"name":"search_tasks","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_approvals","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List approvals in the run company.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_approvals","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_approval","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one approval without protected data.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"}},"required":["approvalId"],"type":"object"},"name":"get_approval","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_approval_context","requiredClaims":["governance:approvals:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read one approval, its comments, and linked tasks.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"}},"required":["approvalId"],"type":"object"},"name":"get_approval_context","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"get_workspace_runtime","requiredClaims":["workspace:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Read active-task workspace services.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"get_workspace_runtime","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"control_workspace_service","requiredClaims":["workspace:control"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Start, stop, or fault one active-task workspace service.","inputSchema":{"additionalProperties":false,"properties":{"action":{"enum":["start","stop","fail"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"serviceId":{"description":"Workspace service id.","maxLength":200,"minLength":1,"type":"string"},"url":{"description":"Optional service URL.","maxLength":20000,"type":["string","null"]}},"required":["idempotencyKey","serviceId","action"],"type":"object"},"name":"control_workspace_service","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"set_dependencies","requiredClaims":["dependencies:write"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Replace the active task's first-class blocker set.","inputSchema":{"additionalProperties":false,"properties":{"blockedByTaskIds":{"description":"Replacement blocker task ids.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","blockedByTaskIds"],"type":"object"},"name":"set_dependencies","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_task","requiredClaims":["delegation:tasks:create"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a project task from a conversation, or a child from an ordinary task. Persist initialPlan before execution. Set status to backlog when the user wants to save or plan work without starting it; backlog tasks never wake an agent. Omitted status means todo, subject to blockers.","inputSchema":{"additionalProperties":false,"properties":{"assigneeActorId":{"description":"Optional agent assignee. Omit to assign the current agent.","maxLength":20000,"type":["string","null"]},"blockedByTaskIds":{"description":"Initial blocker task ids.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"description":{"description":"Child task description.","maxLength":20000,"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"initialPlan":{"description":"Relevant markdown plan saved on the new task before execution starts.","maxLength":200000,"type":["string","null"]},"priority":{"enum":["critical","high","medium","low"]},"projectId":{"description":"Project ID for the task.","type":["string","null"]},"status":{"description":"Initial status. Use backlog to save work without executing it. Defaults to todo (blocked when dependencies are unresolved).","enum":["backlog","todo"]},"title":{"description":"Child task title.","maxLength":500,"minLength":1,"type":"string"}},"required":["idempotencyKey","title"],"type":"object"},"name":"create_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"},"task":{"additionalProperties":false,"properties":{"assigneeActorId":{"type":["string","null"]},"id":{"minLength":1,"type":"string"},"identifier":{"type":["string","null"]},"parentId":{"minLength":1,"type":["string","null"]},"projectId":{"minLength":1,"type":["string","null"]},"status":{"minLength":1,"type":"string"}},"required":["id","identifier","parentId","status","assigneeActorId"],"type":"object"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds","task"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"request_approval","requiredClaims":["governance:approvals:request"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a governed approval and waiting posture.","inputSchema":{"additionalProperties":false,"properties":{"approvalType":{"description":"Stable approval type.","maxLength":200,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"payload":{"additionalProperties":true,"type":"object"}},"required":["idempotencyKey","approvalType","payload"],"type":"object"},"name":"request_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"decide_approval","requiredClaims":["governance:approvals:decide"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Decide an approval as an explicitly authorized approver.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"},"decision":{"enum":["approved","rejected","cancelled"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"note":{"description":"Decision note.","maxLength":20000,"minLength":1,"type":"string"}},"required":["idempotencyKey","approvalId","decision","note"],"type":"object"},"name":"decide_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"comment_on_approval","requiredClaims":["governance:approvals:comment"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Add a durable comment to an approval.","inputSchema":{"additionalProperties":false,"properties":{"approvalId":{"description":"Approval id.","maxLength":200,"minLength":1,"type":"string"},"body":{"description":"Approval comment.","maxLength":20000,"minLength":1,"type":"string"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"}},"required":["idempotencyKey","approvalId","body"],"type":"object"},"name":"comment_on_approval","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"schedule_wake","requiredClaims":["control_plane:wakes"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Schedule a deterministic continuation wake.","inputSchema":{"additionalProperties":false,"properties":{"delayTicks":{"maximum":10000,"minimum":1,"type":"integer"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"payload":{"additionalProperties":true,"type":"object"},"reason":{"enum":["manual","issue_commented","interaction_resolved","approval_resolved","blockers_resolved","scheduled_retry","resume"]}},"required":["idempotencyKey","reason","delayTicks"],"type":"object"},"name":"schedule_wake","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}},{"annotations":{"exposure":"optional","operationId":"generic_api_request","requiredClaims":["test:generic_api_request"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Test-only escape hatch. Disabled unless the scenario and explicit claim both enable it.","inputSchema":{"additionalProperties":false,"properties":{"body":{"additionalProperties":true,"type":"object"},"method":{"enum":["GET","POST","PATCH"]},"path":{"maxLength":500,"pattern":"^/mock/","type":"string"}},"required":["method","path"],"type":"object"},"name":"generic_api_request","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"search_api","requiredClaims":["api:discover"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Fallback only: discover Paperclip API operations when the available dedicated tools cannot express the task. Prefer dedicated tools for common operations; do not search before using them. For a persistent hire, first list_agents to reuse a suitable teammate. Search agent-hires for the hiring schema and agent-configurations for compatible adapter/runtime settings, then use call_api with the returned operationId. Supply role-specific instructionsBundle.files as a filename-to-content record. Use the returned agent.id for delegation and obey any pending approval. Provider helper threads are temporary workers, not Paperclip hires. If a hire response is uncertain, reconcile with list_agents before retrying.","inputSchema":{"additionalProperties":false,"properties":{"cursor":{"maxLength":200,"type":"string"},"limit":{"default":5,"maximum":10,"minimum":1,"type":"integer"},"query":{"maxLength":500,"minLength":1,"type":"string"}},"required":["query"],"type":"object"},"name":"search_api","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"call_api","requiredClaims":["api:call"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool. For large text responses, read the returned artifact with GET /api/assets/{assetId}/content and responseText; follow nextOffsetBytes until null.","inputSchema":{"additionalProperties":false,"properties":{"body":{"anyOf":[{"additionalProperties":true,"type":"object"},{"items":{},"type":"array"},{"type":"string"},{"type":"number"},{"type":"boolean"},{"type":"null"}],"description":"Request value matching the discovered schema. For JSON object or array requests, pass the object or array directly, never a JSON-encoded string. Strings are for text bodies or endpoints whose schema explicitly accepts a string."},"contentType":{"maxLength":120,"type":"string"},"files":{"items":{"additionalProperties":false,"oneOf":[{"properties":{"artifactId":{}},"required":["artifactId"]},{"properties":{"path":{}},"required":["path"]}],"properties":{"artifactId":{"type":"string"},"field":{"type":"string"},"path":{"description":"File relative to the active issue workspace. Remote files must first be uploaded as an artifact.","type":"string"}},"type":"object"},"maxItems":10,"type":"array"},"operationId":{"description":"Exact operationId returned by search_api, for example GET /api/projects/{id}. Do not guess identifiers.","maxLength":500,"minLength":1,"type":"string"},"pathParams":{"additionalProperties":{"type":"string"},"type":"object"},"query":{"additionalProperties":true,"type":"object"},"responseText":{"additionalProperties":false,"description":"GET only: return a bounded UTF-8 text window inline, including JSON as text, without saving another artifact. Offsets and limits are bytes. Use the returned nextOffsetBytes to continue; null means complete. Prefer reading a saved artifact for a stable snapshot. The 10 MiB transfer limit still applies.","properties":{"limitBytes":{"default":24576,"maximum":24576,"minimum":4,"type":"integer"},"offsetBytes":{"default":0,"maximum":10485760,"minimum":0,"type":"integer"}},"type":"object"}},"required":["operationId"],"type":"object"},"name":"call_api","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_project","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a project after considering existing projects and available repositories. repositoryIds and repositoryUrls accept multiple existing repositories. Use HTTPS GitHub repositoryUrls when an accessible repo is not in the catalog; this registers project repositories, not remote GitHub repositories. Non-code projects may omit repositories. Cannot combine repositoryIds/repositoryUrls with workspace. Reuse the idempotency key on retries.","inputSchema":{"additionalProperties":false,"properties":{"archivedAt":{"description":"Archive timestamp.","maxLength":20000,"type":["string","null"]},"color":{"description":"Project color.","maxLength":20000,"type":["string","null"]},"description":{"description":"Project outcome and context.","maxLength":20000,"type":["string","null"]},"env":{"additionalProperties":true,"type":"object"},"executionWorkspacePolicy":{"additionalProperties":true,"type":"object"},"goalId":{"description":"Goal ID.","maxLength":20000,"type":["string","null"]},"goalIds":{"description":"Goal IDs.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"icon":{"description":"Project icon.","enum":["folder","rocket","code","terminal","database","globe","package","boxes","box","layers","briefcase","compass","target","flame","zap","star","bug","wrench","hammer","lightbulb","sparkles","shield","lock","search","cog","brain","cpu","git-branch","file-code","puzzle","gem","atom","heart","mail","message-square","crown","radar","telescope","hexagon",null],"type":["string","null"]},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"leadAgentId":{"description":"Lead agent ID.","maxLength":20000,"type":["string","null"]},"name":{"description":"Project name.","maxLength":500,"minLength":1,"type":"string"},"repositoryIds":{"description":"Authorized repository IDs from list_project_repositories; may contain multiple repositories.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"repositoryUrls":{"description":"Existing HTTPS GitHub repository URLs, including repos absent from the catalog.","items":{"maxLength":2000,"pattern":"^https://github\\.com/(?!\\.{1,2}/)[A-Za-z0-9_.-]+/(?!\\.{1,2}/?$)[A-Za-z0-9_.-]+/?$","type":"string"},"maxItems":100,"type":"array"},"status":{"enum":["backlog","planned","in_progress","completed","cancelled"]},"targetDate":{"description":"Target date.","maxLength":20000,"type":["string","null"]},"workspace":{"additionalProperties":true,"type":"object"}},"required":["idempotencyKey","name"],"type":"object"},"name":"create_project","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_project_repositories","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"List authorized repositories with stable IDs and names. Consider appropriate repositories before creating a project; never invent IDs.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_project_repositories","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"list_projects","requiredClaims":["discovery:projects:read"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Inspect available company projects before selecting a project for new work.","inputSchema":{"additionalProperties":false,"properties":{},"required":[],"type":"object"},"name":"list_projects","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"create_skill","requiredClaims":[],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Create a reusable single-file skill in the company library. Supply a complete SKILL.md whose name and description match the inputs. This saves the skill and shows a card; it does not assign the skill to any agent. Reuse idempotencyKey on retries.","inputSchema":{"additionalProperties":false,"properties":{"description":{"maxLength":2000,"minLength":1,"type":"string"},"idempotencyKey":{"maxLength":240,"minLength":1,"type":"string"},"markdown":{"description":"Complete SKILL.md including name and description frontmatter and substantive instructions.","maxLength":200000,"minLength":1,"type":"string"},"name":{"description":"Lowercase skill name, matching SKILL.md frontmatter.","maxLength":120,"minLength":1,"pattern":"^[a-z0-9]+(?:-[a-z0-9]+)*$","type":"string"},"slug":{"description":"Optional; must equal name.","maxLength":120,"minLength":1,"pattern":"^[a-z0-9]+(?:-[a-z0-9]+)*$","type":"string"}},"required":["idempotencyKey","name","description","markdown"],"type":"object"},"name":"create_skill","outputSchema":{"additionalProperties":true,"type":"object"}},{"annotations":{"exposure":"optional","operationId":"reassign_task","requiredClaims":["delegation:tasks:assign"],"semanticContract":"paperclip.semantic-tool.v1","version":1},"description":"Reassign an existing task to another company agent. Read search_tasks first and supply its current assignee and statusVersion to prevent overwriting a concurrent change. Preserve the task, documents, dependencies, and blocked/backlog status. Active work is stopped before handoff. Use a stable idempotency key for retries. Cannot reassign this run’s own task, conversations, completed tasks, or pending reviews; use create_task for delegation from the current task.","inputSchema":{"additionalProperties":false,"properties":{"assigneeActorId":{"description":"New company agent ID from list_agents.","minLength":1,"type":"string"},"expectedAssigneeActorId":{"description":"Current assigneeAgentId from search_tasks; null means unassigned.","type":["string","null"]},"expectedStatusVersion":{"description":"Current statusVersion from search_tasks.","minimum":0,"type":"integer"},"idempotencyKey":{"description":"Caller-stable retry key.","maxLength":240,"minLength":1,"type":"string"},"reason":{"description":"Why the task should move and context for the new owner.","maxLength":20000,"minLength":1,"type":"string"},"taskId":{"description":"Existing task ID from search_tasks.","minLength":1,"type":"string"}},"required":["idempotencyKey","taskId","assigneeActorId","expectedAssigneeActorId","expectedStatusVersion","reason"],"type":"object"},"name":"reassign_task","outputSchema":{"additionalProperties":false,"properties":{"commandId":{"description":"Stable command identifier.","maxLength":200,"minLength":1,"type":"string"},"disposition":{"enum":["applied","duplicate"]},"entityRefs":{"description":"Entities affected by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"scheduledWakeIds":{"description":"Wake identifiers scheduled by the operation.","items":{"minLength":1,"type":"string"},"maxItems":200,"type":"array","uniqueItems":true},"stateRevision":{"minimum":0,"type":"integer"}},"required":["commandId","disposition","stateRevision","entityRefs","scheduledWakeIds"],"type":"object"}}] diff --git a/packages/paperclip-runner/generated/semantic-action-catalog.json b/packages/paperclip-runner/generated/semantic-action-catalog.json index 2df6b716fb4..020e3b3e9ed 100644 --- a/packages/paperclip-runner/generated/semantic-action-catalog.json +++ b/packages/paperclip-runner/generated/semantic-action-catalog.json @@ -112,7 +112,7 @@ "planning", "skill_test" ], - "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool.", + "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool. For large text responses, read the returned artifact with GET /api/assets/{assetId}/content and responseText; follow nextOffsetBytes until null.", "effect": "write", "inputSchema": { "additionalProperties": false, @@ -199,6 +199,25 @@ "query": { "additionalProperties": true, "type": "object" + }, + "responseText": { + "additionalProperties": false, + "description": "GET only: return a bounded UTF-8 text window inline, including JSON as text, without saving another artifact. Offsets and limits are bytes. Use the returned nextOffsetBytes to continue; null means complete. Prefer reading a saved artifact for a stable snapshot. The 10 MiB transfer limit still applies.", + "properties": { + "limitBytes": { + "default": 24576, + "maximum": 24576, + "minimum": 4, + "type": "integer" + }, + "offsetBytes": { + "default": 0, + "maximum": 10485760, + "minimum": 0, + "type": "integer" + } + }, + "type": "object" } }, "required": [ diff --git a/packages/paperclip-runner/protocol/fixtures/evals/native-execution-seeded.json b/packages/paperclip-runner/protocol/fixtures/evals/native-execution-seeded.json index 4ff19e56d72..527db909f33 100644 --- a/packages/paperclip-runner/protocol/fixtures/evals/native-execution-seeded.json +++ b/packages/paperclip-runner/protocol/fixtures/evals/native-execution-seeded.json @@ -24,7 +24,7 @@ "prpVersion": 1, "nativeExecutionVersion": 1, "catalogVersion": 1, - "catalogSha256": "sha256:1fa8ecf5d3c28e62a32e818de95633ff3efe5d4af1a100310516ff9b5ab2358d", + "catalogSha256": "sha256:c5e8a60c932b37ae017b1e27d2dbc92e1ffcca628b9797a87613cb4b5bb411b5", "driverContractVersion": 1, "driverKind": "paperclip-deterministic", "driverVersion": "1.0.0" diff --git a/packages/paperclip-runner/protocol/manifest.json b/packages/paperclip-runner/protocol/manifest.json index 83ac18ab79d..4f507e26601 100644 --- a/packages/paperclip-runner/protocol/manifest.json +++ b/packages/paperclip-runner/protocol/manifest.json @@ -160,7 +160,7 @@ }, { "path": "fixtures/evals/native-execution-seeded.json", - "sha256": "5f3144ea856ad27778f47de73eb542703b1d9df2abad2c427838fbaf69c3d59f", + "sha256": "2301e907b4a76d4e9f875259133a8aa20516368bb8b8380c831d20cd1aa10df3", "expectation": "accept", "compatibilityCase": "canonical" }, diff --git a/packages/paperclip-runner/src/protocol-actions/call-api.ts b/packages/paperclip-runner/src/protocol-actions/call-api.ts index ffbed93c8c9..02d23dde204 100644 --- a/packages/paperclip-runner/src/protocol-actions/call-api.ts +++ b/packages/paperclip-runner/src/protocol-actions/call-api.ts @@ -28,7 +28,7 @@ export const callApiAction = { }, "documentation": { "title": "Call the Paperclip API", - "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool.", + "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool. For large text responses, read the returned artifact with GET /api/assets/{assetId}/content and responseText; follow nextOffsetBytes until null.", "note": "Production HTTP fallback; does not grant privileges or replace dedicated tools." }, "examples": { @@ -51,7 +51,7 @@ export const callApiAction = { "operationId": "call_api", "version": 1, "title": "Call the Paperclip API", - "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool.", + "description": "Fallback only: call a discovered Paperclip API operation when dedicated tools lack the required operation or parameters. Uses your existing permissions. Prefer dedicated tools; never bypass a denial or runner lifecycle tool. For large text responses, read the returned artifact with GET /api/assets/{assetId}/content and responseText; follow nextOffsetBytes until null.", "exposure": "optional", "requiredClaims": [ "api:call" @@ -96,6 +96,15 @@ export const callApiAction = { "type": "string", "maxLength": 120 }, + "responseText": { + "description": "GET only: return a bounded UTF-8 text window inline, including JSON as text, without saving another artifact. Offsets and limits are bytes. Use the returned nextOffsetBytes to continue; null means complete. Prefer reading a saved artifact for a stable snapshot. The 10 MiB transfer limit still applies.", + "type": "object", + "properties": { + "offsetBytes": { "type": "integer", "minimum": 0, "maximum": 10485760, "default": 0 }, + "limitBytes": { "type": "integer", "minimum": 4, "maximum": 24576, "default": 24576 } + }, + "additionalProperties": false + }, "files": { "type": "array", "maxItems": 10, diff --git a/server/src/services/native-runtime/runner-api-client.ts b/server/src/services/native-runtime/runner-api-client.ts index dec7582012f..7fb6123e199 100644 --- a/server/src/services/native-runtime/runner-api-client.ts +++ b/server/src/services/native-runtime/runner-api-client.ts @@ -18,6 +18,10 @@ export const runnerApiCallSchema = z.object({ body: z.unknown().optional(), contentType: z.string().max(120).optional(), files: z.array(fileSchema).max(10).optional(), + responseText: z.object({ + offsetBytes: z.number().int().min(0).max(RUNNER_API_MAX_BYTES).optional(), + limitBytes: z.number().int().min(4).max(RUNNER_API_INLINE_BYTES).optional(), + }).strict().optional(), }).strict(); export type RunnerApiCall = z.infer; export type RunnerApiFile = z.infer; @@ -44,6 +48,7 @@ export function validateRunnerApiCall(value: unknown, context: RunnerApiContext) const input = parsed.data; const operation = runnerApiOperation(input.operationId); if (operation.transport !== "rest") throw unprocessable("This endpoint requires its existing protocol client; call_api supports REST only"); + if (input.responseText && operation.method !== "GET") throw badRequest("responseText requires a GET operation; read the saved artifact instead of repeating a mutation"); const restriction = runnerApiRestriction(operation.method, operation.path); if (restriction) throw forbidden(restriction); if (!operation.allowedModes.includes(context.workMode)) throw forbidden("call_api permits only reads in Ask and Plan modes; use the permitted dedicated tools"); @@ -139,7 +144,8 @@ export async function readBoundedResponse(response: Response, maxBytes = RUNNER_ } export async function executeRunnerApi(input: RunnerApiCall, context: RunnerApiContext, io: RunnerApiIo) { - const { operation } = validateRunnerApiCall(input, context); + const { operation, input: validated } = validateRunnerApiCall(input, context); + input = validated; const url = runnerApiUrl(operation, input, context, io.apiUrl); if (!io.token) throw new Error("Paperclip run authentication is unavailable"); const headers = new Headers({ Authorization: `Bearer ${io.token}`, "X-Paperclip-Run-Id": context.runId }); @@ -192,9 +198,27 @@ export async function executeRunnerApi(input: RunnerApiCall, context: RunnerApiC const uncertainty = { outcome: "unknown", guidance: "Inspect current state before retrying this mutation; it may already have succeeded." }; const base = { ok: response.ok, status: response.status, operationId: operation.operationId, contentType: type, retryAfter: response.headers.get("retry-after"), ...(uncertain ? uncertainty : {}) }; if (response.status >= 300 && response.status < 400) return { ...base, ok: false, error: "api_redirect_not_followed" }; + if (input.responseText) { + if (!/json|^text\//i.test(type)) return { ...base, ok: false, error: "response_text_requires_text_content" }; + const offsetBytes = input.responseText.offsetBytes ?? 0; + if (offsetBytes > bytes.length || (offsetBytes < bytes.length && (bytes[offsetBytes] & 0xc0) === 0x80)) { + return { ...base, ok: false, error: "response_text_invalid_offset", byteSize: bytes.length }; + } + let end = Math.min(bytes.length, offsetBytes + (input.responseText.limitBytes ?? RUNNER_API_INLINE_BYTES)); + // Do not cut a UTF-8 code point. The next offset always starts a whole one. + while (end < bytes.length && end > offsetBytes && (bytes[end] & 0xc0) === 0x80) end--; + if (end === offsetBytes && end < bytes.length) return { ...base, ok: false, error: "response_text_invalid_utf8" }; + try { + const data = new TextDecoder("utf-8", { fatal: true, ignoreBOM: true }).decode(bytes.subarray(offsetBytes, end)); + return { ...base, data, responseText: { offsetBytes, nextOffsetBytes: end < bytes.length ? end : null, totalBytes: bytes.length } }; + } catch { + return { ...base, ok: false, error: "response_text_invalid_utf8" }; + } + } if (!bytes.length) return { ...base, data: null }; if (bytes.length > RUNNER_API_INLINE_BYTES || !/json|^text\//i.test(type)) { - return { ...base, artifact: await io.saveResponse(bytes, type), byteSize: bytes.length, preview: /json|^text\//i.test(type) ? bytes.subarray(0, 2000).toString("utf8") : null }; + return { ...base, artifact: await io.saveResponse(bytes, type), byteSize: bytes.length, preview: /json|^text\//i.test(type) ? bytes.subarray(0, 2000).toString("utf8") : null, + ...(/json|^text\//i.test(type) ? { guidance: "Read the saved artifact with GET /api/assets/{assetId}/content and responseText: { offsetBytes: 0 }. Continue with responseText.nextOffsetBytes until null. Do not repeat a mutation to read its response." } : {}) }; } const text = bytes.toString("utf8"); if (/json/i.test(type)) { diff --git a/server/src/services/native-runtime/runner-api.integration.test.ts b/server/src/services/native-runtime/runner-api.integration.test.ts index 805a618c6b3..f04b2654c6e 100644 --- a/server/src/services/native-runtime/runner-api.integration.test.ts +++ b/server/src/services/native-runtime/runner-api.integration.test.ts @@ -3,7 +3,7 @@ import { randomUUID } from "node:crypto"; import { chmod, writeFile, symlink } from "node:fs/promises"; import { join } from "node:path"; import { eq } from "drizzle-orm"; -import { documents, heartbeatRuns, issues, routineDocuments, routines } from "@paperclipai/db"; +import { assets, documents, heartbeatRuns, issues, routineDocuments, routines } from "@paperclipai/db"; import { beforeAll, afterAll, beforeEach, afterEach, describe, expect, it, vi } from "vitest"; import { startRunnerApiTestServer } from "../../__tests__/helpers/runner-api-server.js"; import { createRunnerdCodexTransport, defaultCapabilityRunnerdBinary } from "../../vendor/paperclip-runner/index.js"; @@ -248,6 +248,29 @@ else if(m.id!==undefined) send({id:m.id,result:{}}); } finally { getObject.mockRestore(); } }); + it("retrieves every byte of a saved large response without creating an artifact loop", async () => { + const fixture = await server.fixture(); + const foreign = await server.fixture(); + const text = JSON.stringify({ padding: "🧭é".repeat(6000), evidence: "last-field-is-readable" }); + const stored = await server.storage.putFile({ companyId: fixture.companyId, namespace: "eval", originalFilename: "evidence.json", contentType: "application/json", body: Buffer.from(text) }); + const [asset] = await server.db.insert(assets).values({ ...stored, companyId: fixture.companyId, createdByAgentId: fixture.agentId }).returning(); + const call = (authority: typeof fixture.authority, assetId: string, responseText?: object) => authority.execute({ tool: "call_api", callId: randomUUID(), arguments: { operationId: "GET /api/assets/{assetId}/content", pathParams: { assetId }, ...(responseText ? { responseText } : {}) } }) as Promise; + const initial = await call(fixture.authority, asset.id); + expect(initial).toMatchObject({ status: 200, artifact: { byteSize: Buffer.byteLength(text) } }); + const before = (await fixture.snapshot()).assets.length; + let offsetBytes = 0; + let result = ""; + do { + const page = await call(fixture.authority, initial.artifact.artifactId, { offsetBytes, limitBytes: 4096 }); + expect(page).toMatchObject({ status: 200, responseText: { offsetBytes, totalBytes: Buffer.byteLength(text) } }); + result += page.data; + offsetBytes = page.responseText.nextOffsetBytes; + } while (offsetBytes !== null); + expect(JSON.parse(result)).toEqual(JSON.parse(text)); + expect((await fixture.snapshot()).assets).toHaveLength(before); + expect(await call(foreign.authority, initial.artifact.artifactId, { offsetBytes: 0 })).toMatchObject({ ok: false, status: 404 }); + }); + it("contains workspace files, checks artifact ownership, and persists downloads", async () => { const fixture = await server.fixture(); const foreign = await server.fixture(); diff --git a/server/src/services/native-runtime/runner-api.test.ts b/server/src/services/native-runtime/runner-api.test.ts index 047bf1a9248..3c164d60946 100644 --- a/server/src/services/native-runtime/runner-api.test.ts +++ b/server/src/services/native-runtime/runner-api.test.ts @@ -591,6 +591,51 @@ describe("runner API request boundary", () => { ).toThrow("inline JSON object"); } }); + it("reads complete large text without recursively saving response artifacts", async () => { + const text = "prefix\n" + "🧭é\n".repeat(6000) + "END-OF-EVIDENCE"; + const saveResponse = vi.fn(io(fetch).saveResponse); + const request = vi.fn(async () => new Response(text, { headers: { "content-type": "application/json" } })); + let offsetBytes = 0; + let received = ""; + do { + const result = await executeRunnerApi({ operationId: projects, responseText: { offsetBytes, limitBytes: 4096 } }, context, { ...io(request), saveResponse }) as any; + expect(result).toMatchObject({ ok: true, responseText: { offsetBytes, totalBytes: Buffer.byteLength(text) } }); + expect(Buffer.byteLength(result.data)).toBeLessThanOrEqual(4096); + received += result.data; + offsetBytes = result.responseText.nextOffsetBytes; + } while (offsetBytes !== null); + expect(received).toBe(text); + expect(saveResponse).not.toHaveBeenCalled(); + expect(request.mock.calls.every(([, options]) => new Headers(options?.headers).get("Authorization") === "Bearer private-agent-token")).toBe(true); + }); + it.each([{ offsetBytes: -1 }, { limitBytes: 0 }, { limitBytes: 3 }, { limitBytes: 24577 }, { offsetBytes: 0.5 }])("rejects invalid text windows before dispatch: %j", async responseText => { + const request = vi.fn(); + await expect(executeRunnerApi({ operationId: projects, responseText }, context, io(request))).rejects.toThrow("Invalid call_api arguments"); + expect(request).not.toHaveBeenCalled(); + }); + it("does not page mutation responses by repeating the mutation", async () => { + const request = vi.fn(); + await expect(executeRunnerApi({ operationId: createProject, body: { name: "Once" }, responseText: {} }, context, io(request))).rejects.toThrow("GET"); + expect(request).not.toHaveBeenCalled(); + }); + it("rejects binary, invalid UTF-8 and offsets that split text", async () => { + for (const [body, type, offsetBytes] of [ + [Buffer.from("binary"), "application/octet-stream", 0], + [Buffer.from([0xff]), "text/plain", 0], + [Buffer.concat([Buffer.from([0xc2]), Buffer.alloc(24576, 0x80)]), "text/plain", 0], + [Buffer.from("é"), "text/plain", 1], + [Buffer.from("short"), "text/plain", 6], + ] as const) { + const saveResponse = vi.fn(io(fetch).saveResponse); + const result = await executeRunnerApi({ operationId: projects, responseText: { offsetBytes } }, context, { ...io(async () => new Response(body, { headers: { "content-type": type } })), saveResponse }); + expect(result).toMatchObject({ ok: false, error: expect.stringContaining("response_text") }); + expect(saveResponse).not.toHaveBeenCalled(); + } + }); + it("preserves denials and the transfer limit for bounded text reads", async () => { + expect(await executeRunnerApi({ operationId: projects, responseText: {} }, context, io(async () => Response.json({ error: "denied" }, { status: 403 })))).toMatchObject({ ok: false, status: 403, data: '{"error":"denied"}' }); + expect(await executeRunnerApi({ operationId: projects, responseText: {} }, context, io(async () => new Response("small", { headers: { "content-type": "text/plain", "content-length": String(10 * 1024 * 1024 + 1) } })))).toMatchObject({ ok: false, status: null, outcome: "read_failed" }); + }); it("bounds streamed responses even without content-length", async () => { await expect( readBoundedResponse(new Response("too large"), 3), diff --git a/tests/runner-e2e/README.md b/tests/runner-e2e/README.md index 893e4b3a8a5..4ee26a4e118 100644 --- a/tests/runner-e2e/README.md +++ b/tests/runner-e2e/README.md @@ -1042,3 +1042,15 @@ keys with low request limits. It can only lower the configured campaign limit. Keep subscription qualification separate from API-key results. The explicit-only eight-cell [continuation accounting baseline](CONTINUATION-ACCOUNTING.md) tests productive work, bounded repair, restart and late gates with real providers. + +### Bounded API response reading + +`api-response-reading` is an explicit-only, two-cell native Codex suite (local +and Daytona). Each cell creates synthetic diagnostic evidence over 24 KiB via +the public API, outside the agent assignment. The browser starts one ordinary +task which must read the saved response in bounded text pages and persist the +exact hidden evidence code. The oracle also requires completed API tool events; +missing events or a narrative completion cannot pass. Existing run, copyback, +screenshot, billing and environment cleanup checks apply. Use +`--id api-response-reading.runner-codex.daytona.saved-text-pages` with an +immutable Daytona image; no private hooks or fixture database writes are used. diff --git a/tests/runner-e2e/api-response-reading.test.ts b/tests/runner-e2e/api-response-reading.test.ts new file mode 100644 index 00000000000..95a93cdbefc --- /dev/null +++ b/tests/runner-e2e/api-response-reading.test.ts @@ -0,0 +1,19 @@ +import { describe, expect, it } from "vitest"; +import { apiResponseReadingTask, responseEvidenceCode, responseEvidenceDescription, successfulApiReadCount } from "./api-response-reading.js"; + +describe("large API response evidence fixture", () => { + it("keeps evidence beyond both preview and inline limits and out of the assignment", () => { + const source = responseEvidenceDescription("fixture"); + const code = responseEvidenceCode("fixture"); + expect(Buffer.byteLength(source)).toBeGreaterThan(24 * 1024); + expect(source.indexOf(code)).toBeGreaterThan(24 * 1024); + expect(apiResponseReadingTask.buildPrompt("fixture")).not.toContain(code); + expect(apiResponseReadingTask.buildPrompt("fixture")).toContain("responseText.nextOffsetBytes"); + }); + it("counts only real completed API tool events, never narrative claims or missing evidence", () => { + const event = { eventType: "tool.execution.completed", payload: { prpEvent: { payload: { name: "call_api", status: "completed" } } } }; + expect(successfulApiReadCount([event])).toBe(1); + expect(successfulApiReadCount([])).toBe(0); + expect(successfulApiReadCount([{ ...event, eventType: "item.delta" }, { ...event, payload: null }, { ...event, payload: { prpEvent: { payload: { name: "call_api", status: "failed" } } } }])).toBe(0); + }); +}); diff --git a/tests/runner-e2e/api-response-reading.ts b/tests/runner-e2e/api-response-reading.ts new file mode 100644 index 00000000000..f737a4d32b5 --- /dev/null +++ b/tests/runner-e2e/api-response-reading.ts @@ -0,0 +1,43 @@ +import { createHash } from "node:crypto"; +import type { RunnerTaskFixture } from "./types.js"; + +export function responseEvidenceCode(nonce: string) { + return createHash("sha256").update(`bounded-response-evidence:${nonce}`).digest("hex"); +} +export function responseEvidenceDescription(nonce: string) { + return `${"Synthetic diagnostic padding.\n".repeat(1400)}\nEvidence code: ${responseEvidenceCode(nonce)}\n`; +} + +export function successfulApiReadCount(events: readonly { eventType?: string; payload?: unknown }[]) { + return events.filter(event => { + const outer = event.payload as { prpEvent?: { payload?: { name?: string; status?: string } } } | null; + const payload = outer?.prpEvent?.payload; + return event.eventType === "tool.execution.completed" && payload?.name === "call_api" && payload.status === "completed"; + }).length; +} + +export const apiResponseReadingTask: RunnerTaskFixture = { + id: "saved-text-pages", label: "Read saved large API evidence", groups: [], + workMode: "standard", flow: "single_turn", expectedRunCount: 1, + attemptTimeoutMs: { local: 10 * 60_000, daytona: 10 * 60_000 }, + expectedTerminalState: { issue: "done", run: "succeeded" }, + buildTitle: nonce => `Read large API evidence ${nonce}`, + buildVisibleMarker: nonce => `API_RESPONSE_READ_${nonce}`, + buildPrompt: nonce => [ + "Inspect diagnostic evidence task {{API_RESPONSE_SOURCE_ID}} using the Paperclip API tools.", + "Discover GET /api/issues/{id}, call it for that task, and retain the returned response artifact.", + "Read the saved artifact through GET /api/assets/{assetId}/content with responseText: {offsetBytes:0,limitBytes:8192}.", + "Continue using responseText.nextOffsetBytes until null. Extract the Evidence code at the end of its description.", + "The large response must be read with bounded responseText pages. Do not use other tools or API routes to obtain the evidence; if bounded reading fails, report the failure instead of substituting a different reader.", + "Write only that code followed by a newline to api-response-proof.txt in the current workspace. Do not edit the evidence task or create child tasks.", + `Verify the proof file and finish this task with paperclip_finish, reportedWorkDisposition done, and summary API_RESPONSE_READ_${nonce}.`, + ].join("\n"), + buildMatchers: (nonce, execution) => [ + { kind: "file_exact", path: "api-response-proof.txt", expected: `${responseEvidenceCode(nonce)}\n` }, + { kind: "message_contains", expected: `API_RESPONSE_READ_${nonce}` }, + { kind: "issue_status", expected: "done" }, + { kind: "run_status", expected: "succeeded" }, + { kind: "runtime_mode", expected: execution.profile.expectedRuntimeMode }, + { kind: "environment", expected: execution.environment.id }, + ], +}; diff --git a/tests/runner-e2e/catalog.test.ts b/tests/runner-e2e/catalog.test.ts index 6d3504082e8..a0f9fffe46e 100644 --- a/tests/runner-e2e/catalog.test.ts +++ b/tests/runner-e2e/catalog.test.ts @@ -71,10 +71,10 @@ describe("runner E2E catalog", () => { expect(localIntegrityTasks).toHaveLength(2); expect(openRouterBreadthTasks).toHaveLength(3); expect(runnerSuites.map((suite) => suite.expectedMatrixSize)).toEqual([ - 8, 46, 23, 47, 52, 28, 18, 6, 6, 42, 14, 10, 2, + 2, 8, 46, 23, 47, 52, 28, 18, 6, 6, 42, 14, 10, 2, ]); - expect(validateRunnerCatalog()).toHaveLength(302); - expect(new Set(runnerMatrix.map((entry) => entry.id)).size).toBe(302); + expect(validateRunnerCatalog()).toHaveLength(304); + expect(new Set(runnerMatrix.map((entry) => entry.id)).size).toBe(304); expect( runnerMatrix.filter((entry) => entry.suite.id === "core-compatibility"), ).toHaveLength(42); diff --git a/tests/runner-e2e/catalog.ts b/tests/runner-e2e/catalog.ts index f22fd9b8bf2..fe2844503c5 100644 --- a/tests/runner-e2e/catalog.ts +++ b/tests/runner-e2e/catalog.ts @@ -1,3 +1,4 @@ +import { apiResponseReadingTask } from "./api-response-reading.js"; import { accountingTasks } from "./accounting-cases.js"; import { continuationTasks } from "./continuation-cases.js"; import { lifecycleLiveTasks, lifecycleLiveDefinitionDigest } from "./lifecycle-live-cases.js"; @@ -911,6 +912,14 @@ const everydayProfiles = [ ].map(productionStoryProfile); export const runnerSuites: readonly RunnerSuiteFixture[] = [ + { + id: "api-response-reading", label: "Bounded API response reading", manualOnly: true, + description: "Retrieve evidence beyond a saved API preview through authorized bounded text windows.", + groups: [], environments: runnerEnvironments, + profiles: runnerProfiles.filter(profile => profile.id === "runner-codex"), + tasks: [apiResponseReadingTask], expectedMatrixSize: 2, + definitionMetadata: { version: 1, grading: "hidden-evidence-exact-copy-and-api-tool-events", scheduling: "explicit-only" }, + }, { id: "continuation-accounting", label: "Continuation accounting baseline", manualOnly: true, description: "Structured productive steps, bounded repair, restart and late gates; comments cannot buy more attempts.", diff --git a/tests/runner-e2e/runner.spec.ts b/tests/runner-e2e/runner.spec.ts index 19923ae6f3a..ec5e05116f7 100644 --- a/tests/runner-e2e/runner.spec.ts +++ b/tests/runner-e2e/runner.spec.ts @@ -1,3 +1,4 @@ +import { responseEvidenceDescription, successfulApiReadCount } from "./api-response-reading.js"; import { observeBrowserBootstrap } from "./browser-bootstrap-diagnostics.js"; import { runAccountingFlow } from "./accounting-flow.js"; import type { Issue } from "../../packages/shared/src/types/issue.js"; @@ -794,6 +795,14 @@ for (const execution of executions) { daytonaImage: process.env.PAPERCLIP_E2E_DAYTONA_IMAGE, }); + if (execution.suite.id === "api-response-reading") { + const source = await api.post<{ id: string }>(`/api/companies/${fixtures.company.id}/issues`, { + title: `Synthetic diagnostic evidence ${nonce}`, + description: responseEvidenceDescription(nonce), status: "backlog", + }); + prompt = prompt.replaceAll("{{API_RESPONSE_SOURCE_ID}}", source.id); + } + if (execution.suite.id === "lifecycle-baseline" && lifecycleLiveCase(execution.task.id)?.family === "blocker") { const prerequisite = await api.post<{ id: string }>(`/api/companies/${fixtures.company.id}/issues`, { title: `Supply dataset ${nonce}`, @@ -1885,6 +1894,11 @@ for (const execution of executions) { } } + if (execution.suite.id === "api-response-reading") { + const completedReads = successfulApiReadCount(runEventsByRun.flatMap(captured => captured.events)); + if (completedReads < 3) invariantFailures.push(`Expected source read and multiple bounded artifact reads; observed ${completedReads} completed API calls`); + } + const context = record(run.contextSnapshot); const environmentContext = record(context.paperclipEnvironment); const workspaceContext = record(context.paperclipWorkspace);