64 lines
5.0 KiB
Plaintext
64 lines
5.0 KiB
Plaintext
✔ unchanged proposals cannot hide repeated original-log reads or identical session inspections (7840.4099ms)
|
||
✔ reusing a verified proof never resets identical-state detection or creates a new proof (7554.8239ms)
|
||
✔ coverage merges adjacent pages, separates changed sources and never claims old Run coverage in a continuation (0.7609ms)
|
||
✔ a mixed turn with new bytes and three repeated modules advances, while repeat-only and independent no-op guards still pause (1.0676ms)
|
||
✖ runtime sends the next real HTTP request after a W-shaped mixed-progress turn instead of stopping on its trailing repeats (6689.1491ms)
|
||
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.4238ms)
|
||
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.416ms)
|
||
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (8.4159ms)
|
||
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3823ms)
|
||
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (6404.2281ms)
|
||
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (8093.5606ms)
|
||
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (8668.529ms)
|
||
✔ continuations distinguish unread source, later original line ranges and already returned result wrappers (842.2536ms)
|
||
✔ pure-file batch returns unused small-page space while mixed and historical allocation stays conservative (0.3518ms)
|
||
✔ observed upstream high input pauses before a new request, preserves reported usage and distinguishes the limiting ledger (741.5577ms)
|
||
✔ chat-completions: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (4509.482ms)
|
||
✔ responses: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (4572.2051ms)
|
||
✔ anthropic-messages: complete actual Unicode/CRLF pages and small source survive the next bounded wire request (4518.5769ms)
|
||
✔ fixed normal exploration, pagination, SHA changes and repeated ranges are external observations, not a score (1.338ms)
|
||
✔ read-only research is valid work; model summaries and unchanged timestamped listings do not become engineering evidence (0.3832ms)
|
||
✔ new permissions, network and broken tools are failure evidence; repeated invalid inputs remain candidates (0.374ms)
|
||
✔ waiting for original long checks, review and approvals stays waiting across repeated observations (0.4987ms)
|
||
✔ baseline facts, real repairs, current-source check results and requirement evidence have distinct growth (0.2121ms)
|
||
✔ bounded memory keeps unknown instead of claiming an unretained range is repeated; Task/Run instances cannot mix (11.7104ms)
|
||
✔ actual runtime records growing pages then a repeated page without changing model rounds, stop rules or original tool pairs (4199.5811ms)
|
||
✔ actual invalid tool calls repeat under the original step budget; observation never adds an early stop (3716.7296ms)
|
||
✔ actual command approval is observed as waiting and denial stays a permission failure (2248.9794ms)
|
||
✔ network errors remain model failures with shadow failure evidence, never a fabricated no-progress cause (3853.8006ms)
|
||
✔ observer receipt failure cannot change tool results, model budget or completion (1850.6486ms)
|
||
✔ a later receipt recovers after an observation write failure without misaligning retained source receipts (2842.5174ms)
|
||
✔ real applied files, counted checks and current requirement proofs grow after an existing-facts baseline (3780.7322ms)
|
||
✔ receipt retention stays aligned at the cap and a foreign step cannot enter the Run (1954.7431ms)
|
||
✔ an actual approved long check records its owned running job as waiting before the original counted result (5270.8712ms)
|
||
ℹ tests 33
|
||
ℹ suites 0
|
||
ℹ pass 32
|
||
ℹ fail 1
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 59994.7735
|
||
|
||
✖ failing tests:
|
||
|
||
test at tests\read-budget.test.mjs:36:1
|
||
✖ runtime sends the next real HTTP request after a W-shaped mixed-progress turn instead of stopping on its trailing repeats (6689.1491ms)
|
||
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
|
||
+ actual - expected
|
||
|
||
+ 'paused'
|
||
- 'completed'
|
||
|
||
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/read-budget.test.mjs:56:72)
|
||
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: 'paused',
|
||
expected: 'completed',
|
||
operator: 'strictEqual',
|
||
diff: 'simple'
|
||
}
|