Files
Agent-Workbench/docs/working-memory-u-evidence/receipts/related-first.tap
T
2026-11-04 08:39:17 +08:00

153 lines
15 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 (8116.9218ms)
✔ skip-tests, foreign task, unknown operations, diagnostic and parent review retain their boundaries (2965.204ms)
✔ a question about the previous workbench error receives local error context and current change states (1341.4906ms)
✔ an unknown model request stops, and explicit resume never replays the approved command (2131.6929ms)
✔ exhausted refused connections preserve tool results, and explicit resume adds no new user turn or replay (2227.0125ms)
✔ stopping during model backoff cancels further requests and clears the running request state (914.8183ms)
✔ HTTP authentication errors are classified, redacted and never automatically retried (17.4279ms)
✔ temporary HTTP service errors retry and recover with recorded attempt counts (7.4365ms)
✔ invalid and oversized protocol responses fail once with a useful response-format diagnosis (5.2664ms)
✔ HTTP rate limits expose their source and obey the service retry interval before recovery (1015.9125ms)
✔ Windows commands preserve Chinese through a PowerShell pipeline into Node (983.9238ms)
✔ Windows shell syntax errors stay readable and native command exit codes are retained (1032.8241ms)
✔ review and completed states do not turn a generic continue click into a new model request (422.9744ms)
✔ old session data receives a truthful historical connection diagnosis without rewriting history (551.5989ms)
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (2.2003ms)
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.5209ms)
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.1926ms)
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3538ms)
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (4618.3986ms)
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (5999.1068ms)
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (5915.4917ms)
✔ continuations distinguish unread source, later original line ranges and already returned result wrappers (590.0577ms)
✔ pure-file batch returns unused small-page space while mixed and historical allocation stays conservative (0.3084ms)
✔ observed upstream high input pauses before a new request, preserves reported usage and distinguishes the limiting ledger (558.7255ms)
✔ chat-completions: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (3265.8259ms)
✔ responses: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (3413.1852ms)
✔ anthropic-messages: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (3396.7732ms)
✔ native seed framing reserves capacity before optional history without changing the selected window (826.4653ms)
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1753.7547ms)
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3765.4129ms)
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (711.6512ms)
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1533.4787ms)
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (1312.9184ms)
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (923.5828ms)
✔ invalid orphan result is rejected before archive or network preparation (571.7966ms)
✔ invalid missing result is rejected before archive or network preparation (645.4569ms)
✔ invalid wrong result is rejected before archive or network preparation (549.2025ms)
✔ invalid duplicate call is rejected before archive or network preparation (603.0141ms)
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1638.1392ms)
✔ changed or missing archived evidence stops reuse and is never silently recreated (751.1586ms)
✔ transaction failure prevents publishing a plan and any corresponding model request (683.0362ms)
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (552.2518ms)
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (8666.2995ms)
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1482.3823ms)
✔ small code and actual failed command stay visible when their original multi-tool group cannot fit (1703.9666ms)
✔ mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes (2338.1549ms)
✔ working observations are bound to the current Task and stop treating a pre-application file revision as current evidence (2292.7081ms)
✔ a sealed observation rejects changed or missing original result artifacts instead of recreating evidence (1395.0718ms)
✔ a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid (5573.5312ms)
✔ budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries (4.5082ms)
✔ actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening (10048.7649ms)
✖ actual HTTP file pagination advances over a long file with each returned page visible in the next request (4146.3631ms)
✔ later mixed history pages cannot displace the actual module sources and complete requirements (4580.2189ms)
✖ a later narrow page of the same file revision cannot evict the wider actual observation (2651.8243ms)
✔ six small source files stay complete across metadata turns even when mandatory evidence exceeds the soft target (2968.2269ms)
✔ historical read-artifact navigation points to the original artifact and next page, never its result wrapper (989.7483ms)
✔ a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view (1145.1304ms)
✔ actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes (8159.6506ms)
ℹ tests 58
ℹ suites 0
ℹ pass 56
ℹ fail 2
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 76114.4173
✖ failing tests:
test at tests\working-set.test.mjs:167:1
✖ actual HTTP file pagination advances over a long file with each returned page visible in the next request (4146.3631ms)
AssertionError [ERR_ASSERTION]: {"id":"4fee52eb-0c33-4554-8ae8-c6399a0270bf","source":"model_connection","origin":"upstream","stage":"model_request","kind":"service","httpStatus":500,"endpoint":"http://127.0.0.1:62975/v1","model":"file-page-fixture","route":"/chat/completions","attempts":3,"occurredAt":"2026-11-03T23:31:54.583Z","retryable":true,"title":"模型服务暂时无法处理请求","upstream":{"schema":1,"scope":"http-body","httpStatus":500,"code":null,"type":null,"message":"The newest actual budgeted page must be sent","param":null,"reason":null,"requestId":null,"responseId":null,"eventType":null,"headers":{"content-type":"application/json","date":"Tue, 03 Nov 2026 23:31:54 GMT"},"retryAfter":null,"retryAfterMs":null,"rawPreview":"{\"error\":{\"message\":\"The newest actual budgeted page must be sent\"}}","previewTruncated":false,"capture":{"scope":"http-body","receivedBytes":68,"capturedBytes":68,"storedBytes":68,"retention":"artifact","complete":true,"truncated":false,"interrupted":false,"capturedRange":[0,68],"redacted":false,"sha256":"5a2c893c215663a6b01fd3d9a8a17d6746589c9b3d5fee24ec78c4c699e01ed7"},"artifactId":"6d27c170-f9eb-45e9-9d52-fe214a87b143","artifactSha256":"5a2c893c215663a6b01fd3d9a8a17d6746589c9b3d5fee24ec78c4c699e01ed7","artifactScope":"http-body","sessionId":"4906d316-54fe-4084-a02d-4253bc683800"},"upstreamRequestId":null,"code":null,"type":null,"limitReason":null,"wireAttemptId":"45bd8afb-3fc4-413e-b679-df99edc9cb12","message":"模型服务暂时无法处理请求(HTTP 500)。 The newest actual budgeted page must be sent","detail":"The newest actual budgeted page must be sent","suggestion":"稍后重试,或检查模型服务状态。","requestUrl":"http://127.0.0.1:62975/v1/chat/completions","responseUrl":"http://127.0.0.1:62975/v1/chat/completions","redirected":false,"redirectMode":"manual","retryDecision":"attempt_limit","remainingWaitBudgetMs":297493,"runId":"3de3e8e3-5e9c-49b7-9407-71ef2e857685","messageId":"bda902da-4848-4b52-980f-b476b5aed982"}
+ actual - expected
+ 'failed'
- 'completed'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/working-set.test.mjs:185:10)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: false,
code: 'ERR_ASSERTION',
actual: 'failed',
expected: 'completed',
operator: 'strictEqual',
diff: 'simple'
}
test at tests\working-set.test.mjs:217:1
✖ a later narrow page of the same file revision cannot evict the wider actual observation (2651.8243ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+ actual - expected
+ 'usly read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
'An actual previously read complete source line.\n' +
'An actual previously read complete source line.\n' +
'An actual previously read complete source line.\n' +
+ 'An a'
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n' +
- 'An actual previously read complete source line.\n'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/working-set.test.mjs:227:10)
at Test.runInAsyncScope (node:async_hooks:227:14)
at Test.run (node:internal/test_runner/test:1402:25)
at Test.processPendingSubtests (node:internal/test_runner/test:974:18)
at Test.postRun (node:internal/test_runner/test:1542:19)
at Test.run (node:internal/test_runner/test:1467:12)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: 'usly read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn a',
expected: 'An actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\nAn actual previously read complete source line.\n',
operator: 'strictEqual',
diff: 'simple'
}