✔ engineering inspection preserves a dirty Git baseline and treats project rules as data (2894.2309ms) ✔ real npm tests and build produce counted results, log artifacts and persistent verification (2228.578ms) ✔ an actual failing test retains the nonzero exit code and failed count (2554.7384ms) ✔ unchanged automatic checks return original failure evidence, while explicit user reruns and changed source still execute (3964.4063ms) ✔ agent loops cannot hide identical failing checks behind new plan IDs or unrelated reads (7926.1912ms) ✔ zero tests, skipped tests and unrecognized stdout cannot become verification passes (8354.4832ms) ✔ a successful build with no selected tests does not verify the task (1792.5384ms) ✔ stale check plans and forged script names execute no project commands (1379.9804ms) ✔ applying a later proposal invalidates the prior passed engineering snapshot (2837.2722ms) ✔ stopping an actual check terminates its child process and blocks concurrent jobs (2106.5369ms) ✔ check timeout records a failure with its actual termination result (2319.5564ms) ✔ source edits during a successful check make the result stale (3215.7711ms) ✔ bounded large logs retain the test footer and readable artifact instead of inventing counts (1895.9352ms) ✔ model-selected checks require a run-bound decision and denial creates no check job (3578.5614ms) ✔ check APIs expose owned plans and jobs and preserve the authoritative results across restart (6132.9412ms) ✔ reviewed changes continue the original task without reopening a generic completed run (3096.495ms) ✖ concurrent review-continuation API requests accept one run and retain the goal after restart (7673.685ms) ✔ the model reads owned failure logs without running the check again (3983.3471ms) ✔ process exit at check queued preserves results and never replays commands (1768.0429ms) ✔ process exit at check result_committed preserves results and never replays commands (2611.2884ms) ✔ model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart (1374.5889ms) ✔ config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts (1068.1498ms) ✔ real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity (2761.6523ms) ✔ pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests (4310.8846ms) ✔ 401 blocks the credential revision; updating the key restores availability without leaking error echoes (1543.1987ms) ✔ queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request (1220.7882ms) ✔ compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model (2255.0104ms) ✔ model registry disk failures restore routing, pool profiles and credential references without partial updates (638.0138ms) ✔ model selection and saved configuration commit together and failures preserve the original mode and endpoint (833.7293ms) ✔ configuration imports roll back the entire batch and retain one usable preview after validation or commit failure (764.3928ms) ✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (889.718ms) ✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (1144.7961ms) ✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (3094.358ms) ✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (3378.3091ms) ▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool ✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1910.0759ms) ✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1989.3014ms) ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1835.4587ms) ✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1901.0071ms) ✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (7636.6167ms) ▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay ✔ chat-completions (2006.0303ms) ✔ responses (2079.1706ms) ✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (4085.5378ms) ✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.1698ms) ✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (607.9143ms) ✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2921.1403ms) ✔ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (3394.9484ms) ✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (2016.2714ms) ✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (2174.1881ms) ✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (1957.7539ms) ✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (1542.9256ms) ✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (2003.3759ms) ✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (4023.8361ms) ✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (3254.7321ms) ✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (2372.1043ms) ✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1957.4171ms) ✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (756.4159ms) ✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (2220.2853ms) ✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (1185.4939ms) ✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.7034ms) ▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data ✔ reject 0 (0.2096ms) ✔ reject 1 (0.178ms) ✔ reject 2 (0.1571ms) ✔ reject 3 (4.8365ms) ✔ reject 4 (0.1383ms) ✔ reject 5 (0.1552ms) ✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.2367ms) ✔ HTML without tests ends at reviewed file delivery and never offers automatic rechecking (3000.6934ms) ✔ diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools (2527.893ms) ✔ review continuation is a system action and adds no testing demand or fake user instruction (1765.8955ms) ✔ a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools (2239.9844ms) ✔ alternating duplicate file reads and listing files still pauses without treating new pages as duplicates (5097.3339ms) ℹ tests 71 ℹ suites 0 ℹ pass 70 ℹ fail 1 ℹ cancelled 0 ℹ skipped 0 ℹ todo 0 ℹ duration_ms 84548.1038 ✖ failing tests: test at tests\checks.test.mjs:216:1 ✖ concurrent review-continuation API requests accept one run and retain the goal after restart (7673.685ms) AssertionError [ERR_ASSERTION]: Expected values to be strictly equal: 0 !== 1 at TestContext. (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/checks.test.mjs:235:10) 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: 0, expected: 1, operator: 'strictEqual', diff: 'simple' }