Files
Agent-Workbench/docs/task-agreement-1.25-evidence/development/closure-related-first.tap
T

144 lines
14 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
✔ reviewed application invalidates old checks, names current SHA and advances through a new approved check to Git preview (7027.6062ms)
✔ skip-tests, foreign task, unknown operations, diagnostic and parent review retain their boundaries (3542.0117ms)
✔ before the first change, real baseline failures persist across later reads; passed baselines and changed sources cannot certify delivery (7925.077ms)
✔ actual process exit at Git queued never replays a commit and can reconcile the durable result (12228.2015ms)
✔ actual process exit at Git preparing never replays a commit and can reconcile the durable result (13472.9926ms)
✔ actual process exit at Git index_locked never replays a commit and can reconcile the durable result (12935.5605ms)
✔ actual process exit at Git prepared never replays a commit and can reconcile the durable result (13458.6752ms)
✔ actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result (14718.7159ms)
✔ actual process exit at Git publishing never replays a commit and can reconcile the durable result (13536.8903ms)
✔ actual process exit at Git committed never replays a commit and can reconcile the durable result (10170.8378ms)
✔ actual process exit at Git index_published never replays a commit and can reconcile the durable result (10511.0783ms)
✔ actual process exit at Git finished never replays a commit and can reconcile the durable result (10552.0196ms)
✔ an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock (9408.6244ms)
✔ known publication with a later source edit retains the commit and marks the delivery for inspection (10239.7669ms)
✔ CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership (12314.9979ms)
✔ adding new durable record kinds to an existing hot Store preserves all existing Maps and records (8707.2553ms)
✔ an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected (15946.4239ms)
✔ actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files (13927.9056ms)
✔ selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit (15163.0069ms)
Switched to a new branch 'owner-branch'
✔ source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD (20148.8753ms)
Switched to a new branch 'delivery-branch'
✔ a later Git metadata change keeps matching source evidence valid but a real source edit requires checks (11781.3294ms)
✔ a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence (5028.67ms)
HEAD is now at 086558c Sealed delivery fixture baseline
✔ Git filters, merge state, detached HEAD and old task ownership are explicitly rejected (22077.1016ms)
✔ local snapshot commits disable repository hooks and signing and isolate the Git child environment (8797.985ms)
✔ stopping before publication cancels safely; stopping after publication preserves the actual completed commit (16154.0249ms)
✔ delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart (12448.9014ms)
✔ the model can prepare an owned Git review and evidence report while publishing remains a separate user action (9575.5798ms)
✔ HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved (10121.8513ms)
✔ a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task (8700.51ms)
✔ diagnostic failures and repeated questions retain the original execution error, task, checks and read-only authority (1685.641ms)
✔ diagnostic binding survives reopen, rejects foreign Task references and detects original error or artifact tampering (1013.219ms)
✔ a new Task never adopts a previous Task error from session.lastFailure (875.8778ms)
✖ verified research and explicit no-test scopes do not demand an unrelated test job or claim engineering success (734.8099ms)
✖ unknown scope and unknown operations remain actionable even after a diagnostic answer or read proof (715.2239ms)
✖ delivery status HTTP is read-only, selection-bound and equal to the saved report after host restart (2465.8789ms)
✔ local draft preserves exact original ranges and duplicate source instances without inferring outputs or accepting facts (640.3857ms)
✔ review keeps unknown blocking, references distinct from output and boundaries distinct from compliance evidence (623.6808ms)
✔ draft adoption must account for every original range and does not fill paths from a reference (612.1128ms)
✔ source and requirement changes, other Tasks and tampered draft bytes are rejected without losing originals (1300.2355ms)
✔ partial explicit source review leaves the other source unreviewed while old file evidence remains valid (1141.153ms)
✔ bounded draft does not claim full source coverage and cannot acknowledge an omitted remainder (557.1067ms)
✔ draft HTTP preserves its original artifact across restart and rejects stale scope and source versions (4178.627ms)
✔ requirements HTTP binds selection, enforces optimistic revisions, restores original proofs and leaves provider history untouched (4527.9982ms)
✔ research evidence binds actual original bytes; model completion is not user acceptance (1156.0272ms)
✔ same text with distinct user source instances stays distinct; an appended requirement only invalidates its own revision (1509.7947ms)
✔ foreign project, old Task and fabricated evidence strings are rejected with preserved failed proofs (2230.9553ms)
✔ source changes invalidate prior proofs and cannot certify a read that was already stale at binding (1797.1727ms)
✔ missing or tampered artifacts never become evidence and original failures remain after recovery (1537.4072ms)
✔ checks omitted by explicit agreement are reported as not executed and never passed (671.1926ms)
✔ user confirmation stays separate from engineering evidence, is bounded to current inputs and cannot be silently converted (855.2691ms)
✔ existing multi-file results keep provenance and invalidate only evidence whose files changed (1171.4406ms)
✔ unrelated additions preserve the checked file facts but remain visible as unreviewed user sources (951.3432ms)
✔ actual Git preview and publication recheck changed requirement bindings without touching HEAD or the owner index (9342.2254ms)
✔ no-test file application and manual completion keep pending user requirements for explicit review (1338.5169ms)
✔ revision races, forged source ranges, evidence fields and deletion cannot overwrite sealed requirements (499.9262ms)
✔ requirement binding prevents completion and Git acceptance after a review changes; legacy tasks stay explicit (1540.5826ms)
✔ operational questions are diagnostic while explicit repair requests remain execution instructions (1.1236ms)
✔ file delivery requires a positive instruction, not saved evidence or a prohibited write (1.4723ms)
✔ an unsubstantiated text claim cannot complete a requested file delivery (674.0066ms)
✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (1868.9008ms)
✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (2493.7897ms)
✔ review continuation is a system action and adds no testing demand or fake user instruction (1791.6994ms)
✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (1337.9759ms)
✔ a budget pause becomes visible only after its input snapshot can be sealed with the original Run (1073.0452ms)
✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (10093.5932ms)
ℹ tests 65
ℹ suites 0
ℹ pass 62
ℹ fail 3
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 406884.4584
✖ failing tests:
test at tests\diagnostic-follow-up.test.mjs:72:1
✖ verified research and explicit no-test scopes do not demand an unrelated test job or claim engineering success (734.8099ms)
Error: 参考、禁止和待澄清内容只记录范围,不能携带证据或完成状态。
at planError (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/shared/contracts/task-plans.mjs:7:85)
at itemInput (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:29:13)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:114:87
at Array.map (<anonymous>)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:114:74
at async TaskPlanManager.mutate (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/task-plan-manager.mjs:27:70)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/diagnostic-follow-up.test.mjs:77:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
status: 400,
code: 'input'
}
test at tests\diagnostic-follow-up.test.mjs:87:1
✖ unknown scope and unknown operations remain actionable even after a diagnostic answer or read proof (715.2239ms)
Error: 参考、禁止和待澄清内容只记录范围,不能携带证据或完成状态。
at planError (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/shared/contracts/task-plans.mjs:7:85)
at itemInput (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:29:13)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:114:87
at Array.map (<anonymous>)
at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/requirement-review.mjs:114:74
at async TaskPlanManager.mutate (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/src/core/tasks/task-plan-manager.mjs:27:70)
at async TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/diagnostic-follow-up.test.mjs:89:3)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
status: 400,
code: 'input'
}
test at tests\diagnostic-follow-up.test.mjs:97:1
✖ delivery status HTTP is read-only, selection-bound and equal to the saved report after host restart (2465.8789ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:
+ actual - expected
... Skipped lines
{
execution: {
accountedTaskTokens: 0,
artifacts: [
{
...
executionSchemaVersion: 1,
+ exportedAt: '2026-11-04T05:48:30.667Z',
- exportedAt: '2026-11-04T05:48:30.582Z',
project: {
addedAt: '2026-11-04T05:48:28.692Z',
id: 'cf89bdee-4157-4cb1-bc93-d964404bb92b',
name: 'project',
root: 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\test-9GmYLr\\project'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/diagnostic-follow-up.test.mjs:104:10)
at process.processTicksAndRejections (node:internal/process/task_queues:104:5)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: { schemaVersion: 1, executionSchemaVersion: 1, exportedAt: '2026-11-04T05:48:30.667Z', project: { id: 'cf89bdee-4157-4cb1-bc93-d964404bb92b', root: 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\test-9GmYLr\\project', name: 'project', addedAt: '2026-11-04T05:48:28.692Z' }, session: { id: 'ca462e9a-2225-4483-a267-2cb352395ab9', projectId: 'cf89bdee-4157-4cb1-bc93-d964404bb92b', title: '新任务', status: 'failed', createdAt: '2026-11-04T05:48:28.708Z', updatedAt: '2026-11-04T05:48:28.868Z', messages: [], providerMessages: [], events: [Array], changes: [], approvals: [], failure: null, lastFailure: [Object], compactions: 0, estimatedTokens: 0, usage: null, archived: false, revision: 7, eventSeq: 7, taskId: '0a0e205d-7f6d-49bb-a3ce-dba5afae7a02', runId: '88cd26cf-d3eb-4706-b779-3a86c9f92815' }, execution: { schemaVersion: 1, task: [Object], run: [Object], workspaceIdentity: [Object], workspaces: [], runs: [Array], progress: [Object], artifacts: [Array], checks: [], browsingTabs: [], browsingActions: [], previewPlans: [], previewJobs: [], mcpJobs: [], taskPlans: [], taskProofs: [], researchTargets: [], researchJobs: [], engineJobs: [], browserPlans: [], browserJobs: [], contextPlans: [], changeSets: [], plans: [], deliveries: [], deliveryPlans: [], accountedTaskTokens: 0 } },
expected: { schemaVersion: 1, executionSchemaVersion: 1, exportedAt: '2026-11-04T05:48:30.582Z', project: { id: 'cf89bdee-4157-4cb1-bc93-d964404bb92b', root: 'D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\test-9GmYLr\\project', name: 'project', addedAt: '2026-11-04T05:48:28.692Z' }, session: { id: 'ca462e9a-2225-4483-a267-2cb352395ab9', projectId: 'cf89bdee-4157-4cb1-bc93-d964404bb92b', title: '新任务', status: 'failed', createdAt: '2026-11-04T05:48:28.708Z', updatedAt: '2026-11-04T05:48:28.868Z', messages: [], providerMessages: [], events: [Array], changes: [], approvals: [], failure: null, lastFailure: [Object], compactions: 0, estimatedTokens: 0, usage: null, archived: false, revision: 7, eventSeq: 7, taskId: '0a0e205d-7f6d-49bb-a3ce-dba5afae7a02', runId: '88cd26cf-d3eb-4706-b779-3a86c9f92815' }, execution: { schemaVersion: 1, task: [Object], run: [Object], workspaceIdentity: [Object], workspaces: [], runs: [Array], progress: [Object], artifacts: [Array], checks: [], browsingTabs: [], browsingActions: [], previewPlans: [], previewJobs: [], mcpJobs: [], taskPlans: [], taskProofs: [], researchTargets: [], researchJobs: [], engineJobs: [], browserPlans: [], browserJobs: [], contextPlans: [], changeSets: [], plans: [], deliveries: [], deliveryPlans: [], accountedTaskTokens: 0 } },
operator: 'deepStrictEqual',
diff: 'simple'
}