From 439419debb4f9100a883680c9afa2a4437da0fa7 Mon Sep 17 00:00:00 2001 From: Dotta Date: Thu, 3 Sep 2026 02:32:37 -0500 Subject: [PATCH] test(runner): emit terminal text before finish --- tests/runner-e2e/catalog.test.ts | 26 +++++++++++++++++++++++++- tests/runner-e2e/catalog.ts | 8 ++++---- 2 files changed, 29 insertions(+), 5 deletions(-) diff --git a/tests/runner-e2e/catalog.test.ts b/tests/runner-e2e/catalog.test.ts index 4060ea010e..cf032cc808 100644 --- a/tests/runner-e2e/catalog.test.ts +++ b/tests/runner-e2e/catalog.test.ts @@ -111,6 +111,30 @@ describe("runner E2E catalog", () => { expect(plan?.buildPrompt("nonce")).toContain("exactly two numbered steps"); }); + it("emits native terminal text before invoking the terminal tool", () => { + const message = runnerTasks.find((task) => task.id === "message-marker"); + const ask = runnerTasks.find((task) => task.id === "ask-question"); + const plan = runnerTasks.find((task) => task.id === "plan-revise-accept"); + const question = localIntegrityTasks.find( + (task) => task.id === "structured-question-resume", + ); + + for (const prompt of [ + message?.buildPrompt("nonce"), + ask?.buildPrompt("nonce"), + plan?.buildPrompt("nonce"), + question?.buildPrompt("nonce"), + ]) { + expect(prompt).toContain("first emit"); + expect(prompt!.indexOf("first emit")).toBeLessThan( + prompt!.indexOf("paperclip_finish exactly once"), + ); + expect(prompt).toContain( + "Do not wait for the terminal tool result before emitting the response", + ); + } + }); + it("uses only declared secret references in generated payloads", () => { expect( runnerMatrix.every((entry) => @@ -213,7 +237,7 @@ describe("runner E2E catalog", () => { "do not spell, quote, repeat, announce, or include PAPERCLIP_E2E_PLAN_DONE_nonce", ); expect(task!.buildPrompt("nonce")).toContain( - "paperclip_finish with PAPERCLIP_E2E_PLAN_DONE_nonce as its complete summary", + 'summary:"PAPERCLIP_E2E_PLAN_DONE_nonce"', ); expect(task!.buildPrompt("nonce")).toContain( "one atomic issue PATCH with status `done` and that exact comment", diff --git a/tests/runner-e2e/catalog.ts b/tests/runner-e2e/catalog.ts index a8e0a9b11c..cfbc40dae5 100644 --- a/tests/runner-e2e/catalog.ts +++ b/tests/runner-e2e/catalog.ts @@ -381,7 +381,7 @@ export const runnerTasks: readonly RunnerTaskFixture[] = [ "Complete this task in a single run.", `The exact marker also appears unescaped in the task title: PAPERCLIP_E2E_OK_${nonce}`, `Your final visible task-thread response must be exactly this marker: PAPERCLIP_E2E_OK_${nonce}`, - `In a native runner, call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_OK_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. After it succeeds, emit that exact marker once as the complete user-facing final response and do not call another tool.`, + `In a native runner, in the same provider turn first emit that exact marker once as the complete user-facing final response, then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_OK_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Do not wait for the terminal tool result before emitting the response, and do not call another tool.`, `In a legacy runner, make exactly one public-API write containing the marker: PATCH /api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"PAPERCLIP_E2E_OK_${nonce}"}. Do not POST to /comments, and do not include the marker in any other write.`, "The visible task-thread response is asserted; hidden reasoning or provider terminal output alone does not count.", "Use underscore characters exactly as shown and do not insert backslashes.", @@ -448,7 +448,7 @@ export const runnerTasks: readonly RunnerTaskFixture[] = [ "Only after the revised plan is accepted, implement it by posting one final visible task-thread response containing exactly " + `PAPERCLIP_E2E_PLAN_DONE_${nonce}` + " and mark the task Done.", - `For a native runner, remain in the requested planning collaboration mode. Call write_document for key \`plan\`, then call request_human_input exactly once with interactionKind \`confirmation\`, targetRevisionId set to the returned latest Plan revision, and continuationPolicy \`wake_assignee\`. Do not call paperclip_finish while waiting for either Plan confirmation. After the revised Plan is accepted, call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_PLAN_DONE_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}, then emit exactly that marker as the complete final response and do not call another tool.`, + `For a native runner, remain in the requested planning collaboration mode. Call write_document for key \`plan\`, then call request_human_input exactly once with interactionKind \`confirmation\`, targetRevisionId set to the returned latest Plan revision, and continuationPolicy \`wake_assignee\`. Do not call paperclip_finish while waiting for either Plan confirmation. After the revised Plan is accepted, in the same provider turn first emit exactly PAPERCLIP_E2E_PLAN_DONE_${nonce} as the complete final response, then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_PLAN_DONE_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Do not wait for the terminal tool result before emitting the response, and do not call another tool.`, `For a legacy runner, use the public Paperclip API. The first PUT of the \`plan\` issue document creates it. For every later PUT, first GET the current document and set \`baseRevisionId\` to its \`latestRevisionId\`; a 409 means you must GET again and retry with the new latest revision. Create a \`request_confirmation\` targeting the successful PUT response's \`latestRevisionId\` with \`continuationPolicy: wake_assignee\`, and move the issue to \`in_review\` while waiting. After the revised Plan is accepted, write PAPERCLIP_E2E_PLAN_DONE_${nonce} exactly once through one atomic issue PATCH with status \`done\` and that exact comment; do not POST a separate comment or perform a second write.`, "Do not create files, child tasks, or unrelated work, and do not expose credentials.", ].join("\n"), @@ -499,7 +499,7 @@ export const runnerTasks: readonly RunnerTaskFixture[] = [ `Your final visible task-thread answer must be exactly this complete marker, including its final suffix: E2E_ASK_12_${nonce}.`, "Do not create or modify files, do not create a plan or additional work, and do not expose credentials.", "After posting the direct answer, mark this task Done.", - `In a native runner, call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"E2E_ASK_12_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. After it succeeds, emit exactly E2E_ASK_12_${nonce} as the complete final response and do not call another tool.`, + `In a native runner, in the same provider turn first emit exactly E2E_ASK_12_${nonce} as the complete final response, then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"E2E_ASK_12_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Do not wait for the terminal tool result before emitting the response, and do not call another tool.`, `In a legacy runner, post exactly E2E_ASK_12_${nonce} as the task comment body and mark the task Done through the public API.`, ].join("\n"), buildMatchers(nonce, execution) { @@ -577,7 +577,7 @@ const structuredQuestionResumeTask = { `In a native runner, call request_human_input exactly once with idempotencyKey \`question-${nonce}\`, interactionKind \`questions\`, title \`Verification word\`, prompt \`Choose the verification word\`, continuationPolicy \`wake_assignee\`, and payload {version:1,questions:[{id:\`verification-word\`,prompt:\`Choose the verification word.\`,selectionMode:\`single\`,required:true,options:[{id:\`cobalt\`,label:\`Cobalt\`},{id:\`amber\`,label:\`Amber\`}]}]}.`, "In a legacy runner, POST /api/issues/$PAPERCLIP_TASK_ID/interactions with {kind:`ask_user_questions`,continuationPolicy:`wake_assignee`,payload:{version:1,questions:[{id:`verification-word`,prompt:`Choose the verification word.`,selectionMode:`single`,required:true,options:[{id:`cobalt`,label:`Cobalt`},{id:`amber`,label:`Amber`}]}]}} using Authorization and X-Paperclip-Run-Id, then move the issue to `in_review`.", `After the answer arrives, if it is Cobalt, publish exactly PAPERCLIP_E2E_QUESTION_DONE_${nonce} once as the complete visible response and mark the task Done.`, - `In a native runner, after the answer arrives call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_QUESTION_DONE_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}, then emit that exact final response and do not call another tool.`, + `In a native runner, after the answer arrives, in the same provider turn first emit exactly PAPERCLIP_E2E_QUESTION_DONE_${nonce} as the complete final response, then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_QUESTION_DONE_${nonce}",completionClaim:{contractRevision:"1",objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Do not wait for the terminal tool result before emitting the response, and do not call another tool.`, `In a legacy runner, post exactly PAPERCLIP_E2E_QUESTION_DONE_${nonce} as the task comment body and mark the task Done through the public API.`, "Do not create files, plans, child tasks, or unrelated work, and do not expose credentials.", ].join("\n"),