Files
Agent-Workbench/docs/reliability-1.25.2-evidence/development/reservation-related.tap
T

33 lines
3.1 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.
✔ a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request (4483.0667ms)
✔ explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model (5840.5527ms)
✔ insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget (4140.1776ms)
✔ changed session, changed registry, expiry and altered frozen preview all require a new explicit preview (4818.6121ms)
✔ preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run (3887.2131ms)
✔ controlled installation pins the native kernel and bridge independently of the existing connection-probe identity (1098.6733ms)
✔ controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract (0.5582ms)
✔ owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations (5.2247ms)
✔ bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch (1258.0513ms)
✔ bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect (1038.2197ms)
✔ bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity (981.6166ms)
✔ stopped and oversized bridge requests never reach a local model or tool callback (970.7125ms)
✔ sealed r1-off failure fits its original 16K config with authentic latest status and readable source (12.806ms)
✔ sealed r1-on failure fits its original 16K config with authentic latest status and readable source (9.9597ms)
✔ sealed r2-on failure fits its original 16K config with authentic latest status and readable source (8.4737ms)
✔ sealed r2-off failure fits its original 16K config with authentic latest status and readable source (7.6596ms)
✔ archived native call pairs require exact saved arguments/results rather than model-written summaries (8.2988ms)
✔ full system/user requirements and mandatory current failure can refuse rather than be trimmed (12.297ms)
✔ small native input is byte-preserving; developer instructions remain mandatory after compaction (0.1682ms)
✔ older failing checks and pending proposals remain visible after a later large file read (14.6659ms)
✔ bounded result keeps every check status and cuts Unicode only on whole characters (0.4505ms)
✔ a real two-reply failure replay reaches request three at 16K with complete goal, original sources and sealed tool evidence (11758.0826ms)
✔ request deduplication retains long original intent, extra requirements, constraints and acceptance without changing the stored contract (3002.1571ms)
✔ only the routine context avoids plan echoes; diagnostic API and requests without an included plan keep original observations (808.1222ms)
ℹ tests 24
ℹ suites 0
ℹ pass 24
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 23364.9313