72 lines
7.5 KiB
Plaintext
72 lines
7.5 KiB
Plaintext
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (3062.3958ms)
|
||
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (2941.9099ms)
|
||
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (2015.6104ms)
|
||
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (1706.1138ms)
|
||
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (2584.501ms)
|
||
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (789.0881ms)
|
||
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5839ms)
|
||
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (5.3449ms)
|
||
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (662.3135ms)
|
||
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (579.6099ms)
|
||
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (598.4873ms)
|
||
✔ stopped and oversized bridge requests never reach a local model or tool callback (1577.1382ms)
|
||
✔ sealed r1-off failure fits its original 16K config with authentic latest status and readable source (12.6389ms)
|
||
✔ sealed r1-on failure fits its original 16K config with authentic latest status and readable source (9.6381ms)
|
||
✔ sealed r2-on failure fits its original 16K config with authentic latest status and readable source (7.4348ms)
|
||
✔ sealed r2-off failure fits its original 16K config with authentic latest status and readable source (7.4793ms)
|
||
✔ archived native call pairs require exact saved arguments/results rather than model-written summaries (8.2853ms)
|
||
✔ full system/user requirements and mandatory current failure can refuse rather than be trimmed (12.599ms)
|
||
✔ small native input is byte-preserving; developer instructions remain mandatory after compaction (0.2021ms)
|
||
✔ older failing checks and pending proposals remain visible after a later large file read (14.3281ms)
|
||
✔ bounded result keeps every check status and cuts Unicode only on whole characters (0.4779ms)
|
||
✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (1548.1472ms)
|
||
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (1524.7302ms)
|
||
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (3573.1765ms)
|
||
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (3010.9107ms)
|
||
▶ 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" (1635.9359ms)
|
||
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1647.7974ms)
|
||
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1415.6551ms)
|
||
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1100.0413ms)
|
||
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (5800.319ms)
|
||
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
|
||
✔ chat-completions (1341.171ms)
|
||
✔ responses (1825.7498ms)
|
||
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (3167.3185ms)
|
||
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.2009ms)
|
||
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (947.3069ms)
|
||
✔ continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause (1.9391ms)
|
||
✔ a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget (0.6105ms)
|
||
✔ budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters (9.6712ms)
|
||
✔ known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress (0.3926ms)
|
||
✔ actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools (3669.9089ms)
|
||
✔ a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly (4333.3035ms)
|
||
✔ actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay (4738.511ms)
|
||
✔ context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs (3259.9249ms)
|
||
✔ delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification (1963.5885ms)
|
||
✔ native seed framing reserves capacity before optional history without changing the selected window (894.1173ms)
|
||
✔ direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget (1664.4806ms)
|
||
✔ one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments (3021.8457ms)
|
||
✔ tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests (784.0557ms)
|
||
✔ oversized required user instructions pause intact and can be explicitly resumed after increasing the window (1196.5341ms)
|
||
✔ all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix (899.1541ms)
|
||
✔ a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived (865.0319ms)
|
||
✔ invalid orphan result is rejected before archive or network preparation (637.2555ms)
|
||
✔ invalid missing result is rejected before archive or network preparation (730.4606ms)
|
||
✔ invalid wrong result is rejected before archive or network preparation (676.8058ms)
|
||
✔ invalid duplicate call is rejected before archive or network preparation (646.4252ms)
|
||
✔ a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON (1420.7305ms)
|
||
✔ changed or missing archived evidence stops reuse and is never silently recreated (791.6619ms)
|
||
✔ transaction failure prevents publishing a plan and any corresponding model request (633.9934ms)
|
||
✔ the Provider rejects body mutation after a sealed plan before calling HTTP (560.1048ms)
|
||
✔ HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command (4914.6822ms)
|
||
✔ a real process exit after plan persistence marks interruption and never issues an automatic model request (1176.7657ms)
|
||
ℹ tests 61
|
||
ℹ suites 0
|
||
ℹ pass 61
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 76526.4353
|