TAP version 13 # Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause ok 1 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause --- duration_ms: 2.1321 type: 'test' ... # Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget ok 2 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget --- duration_ms: 0.6068 type: 'test' ... # Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters ok 3 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters --- duration_ms: 9.3079 type: 'test' ... # Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress ok 4 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress --- duration_ms: 0.3558 type: 'test' ... # Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools ok 5 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools --- duration_ms: 4751.3131 type: 'test' ... # Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly ok 6 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly --- duration_ms: 4705.6661 type: 'test' ... # Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay ok 7 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay --- duration_ms: 5564.4875 type: 'test' ... # Subtest: an installed app outside the source drive resolves registered SDK and Purge through actual input verification ok 8 - an installed app outside the source drive resolves registered SDK and Purge through actual input verification --- duration_ms: 914.8235 type: 'test' ... # Subtest: standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source ok 9 - standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source --- duration_ms: 734.1177 type: 'test' ... # Subtest: registered hints keep explicit roots, environment and existing app-relative candidates in their original priority ok 10 - registered hints keep explicit roots, environment and existing app-relative candidates in their original priority --- duration_ms: 954.2754 type: 'test' ... # Subtest: unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates ok 11 - unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates --- duration_ms: 660.0479 type: 'test' ... # Subtest: oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source ok 12 - oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source --- duration_ms: 648.6414 type: 'test' ... # Subtest: a linked registry directory is rejected without reading or deleting its external source ok 13 - a linked registry directory is rejected without reading or deleting its external source --- duration_ms: 535.8272 type: 'test' ... # Subtest: matching research declarations do not replace actual installed version and critical-source checks ok 14 - matching research declarations do not replace actual installed version and critical-source checks --- duration_ms: 643.8511 type: 'test' ... # Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs ok 15 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs --- duration_ms: 3459.4364 type: 'test' ... # Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification ok 16 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification --- duration_ms: 2458.7904 type: 'test' ... # Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget ok 17 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget --- duration_ms: 1814.4073 type: 'test' ... # Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments ok 18 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments --- duration_ms: 4284.5983 type: 'test' ... # Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests ok 19 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests --- duration_ms: 1145.7315 type: 'test' ... # Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window ok 20 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window --- duration_ms: 1959.6419 type: 'test' ... # Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix ok 21 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix --- duration_ms: 1192.902 type: 'test' ... # Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived ok 22 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived --- duration_ms: 995.3467 type: 'test' ... # Subtest: invalid orphan result is rejected before archive or network preparation ok 23 - invalid orphan result is rejected before archive or network preparation --- duration_ms: 571.7397 type: 'test' ... # Subtest: invalid missing result is rejected before archive or network preparation ok 24 - invalid missing result is rejected before archive or network preparation --- duration_ms: 716.9611 type: 'test' ... # Subtest: invalid wrong result is rejected before archive or network preparation ok 25 - invalid wrong result is rejected before archive or network preparation --- duration_ms: 874.5525 type: 'test' ... # Subtest: invalid duplicate call is rejected before archive or network preparation ok 26 - invalid duplicate call is rejected before archive or network preparation --- duration_ms: 773.4805 type: 'test' ... # Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON ok 27 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON --- duration_ms: 2266.4706 type: 'test' ... # Subtest: changed or missing archived evidence stops reuse and is never silently recreated ok 28 - changed or missing archived evidence stops reuse and is never silently recreated --- duration_ms: 1024.9591 type: 'test' ... # Subtest: transaction failure prevents publishing a plan and any corresponding model request ok 29 - transaction failure prevents publishing a plan and any corresponding model request --- duration_ms: 888.5244 type: 'test' ... # Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP ok 30 - the Provider rejects body mutation after a sealed plan before calling HTTP --- duration_ms: 1040.6389 type: 'test' ... # Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command ok 31 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command --- duration_ms: 8457.7255 type: 'test' ... # Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request ok 32 - a real process exit after plan persistence marks interruption and never issues an automatic model request --- duration_ms: 1768.8931 type: 'test' ... # Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence ok 33 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence --- duration_ms: 2695.5234 type: 'test' ... # Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity ok 34 - user research registration creates an owned Task without model requests and seals the exact artifact identity --- duration_ms: 1303.2319 type: 'test' ... # Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload ok 35 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload --- duration_ms: 2110.7218 type: 'test' ... # Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses ok 36 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses --- duration_ms: 2873.1576 type: 'test' ... # Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history ok 37 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history --- duration_ms: 2315.4112 type: 'test' ... # Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID ok 38 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID --- duration_ms: 1741.1407 type: 'test' ... # Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed ok 39 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed --- duration_ms: 1698.7957 type: 'test' ... # Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts ok 40 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts --- duration_ms: 1266.0668 type: 'test' ... # Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay ok 41 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay --- duration_ms: 6165.4403 type: 'test' ... # Subtest: file identity rejects directory and invalid formats without running a target ok 42 - file identity rejects directory and invalid formats without running a target --- duration_ms: 553.1022 type: 'test' ... # Subtest: a stop from the event loop interrupts immediate model replies before later tools ok 43 - a stop from the event loop interrupts immediate model replies before later tools --- duration_ms: 1477.9181 type: 'test' ... # Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group ok 44 - a stop after the first tool preserves a complete interrupted multi-call protocol group --- duration_ms: 2530.3667 type: 'test' ... # Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands ok 45 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands --- duration_ms: 5577.5456 type: 'test' ... # Subtest: denial prevents command execution and produces a paired denied result ok 46 - denial prevents command execution and produces a paired denied result --- duration_ms: 2225.0045 type: 'test' ... # Subtest: stopping during approval interrupts pending calls without executing or replaying them ok 47 - stopping during approval interrupts pending calls without executing or replaying them --- duration_ms: 1912.8152 type: 'test' ... # Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state ok 48 - stopping a running fixture command terminates its own process tree and retains uncertain state --- duration_ms: 2420.613 type: 'test' ... # Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment ok 49 - command output decodes split UTF-8 and excludes the workbench key from child environment --- duration_ms: 1154.8194 type: 'test' ... # Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors ok 50 - model-list testing uses a tentative key without changing the saved connection and redacts service errors --- duration_ms: 6.2953 type: 'test' ... # Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities ok 51 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities --- duration_ms: 3238.6715 type: 'test' ... # Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history ok 52 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history --- duration_ms: 1746.2957 type: 'test' ... # Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project ok 53 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project --- duration_ms: 1193.6794 type: 'test' ... # Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code ok 54 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code --- duration_ms: 896.2749 type: 'test' ... # Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing ok 55 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing --- duration_ms: 2860.419 type: 'test' ... # Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay ok 56 - source edits after a catalog request prevent the read and appear as changed on the next request without replay --- duration_ms: 2821.4628 type: 'test' ... # Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project ok 57 - disabled and foreign skills cannot be read by guessing their IDs from another project --- duration_ms: 2917.0013 type: 'test' ... # Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code ok 58 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code --- duration_ms: 1433.2547 type: 'test' ... # Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact ok 59 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact --- duration_ms: 4065.4845 type: 'test' ... # Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network ok 60 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network --- duration_ms: 1257.671 type: 'test' ... # Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs ok 61 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs --- duration_ms: 2014.1819 type: 'test' ... # Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls ok 62 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls --- duration_ms: 2994.7415 type: 'test' ... # Subtest: JSON state keeps an atomic backup and preserves corrupt primary files ok 63 - JSON state keeps an atomic backup and preserves corrupt primary files --- duration_ms: 960.5337 type: 'test' ... # Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results ok 64 - tool-pair recovery fills missing results and drops orphan or duplicate results --- duration_ms: 0.4854 type: 'test' ... # Subtest: restart pauses unfinished work, retains proposals and never replays a command ok 65 - restart pauses unfinished work, retains proposals and never replays a command --- duration_ms: 721.8508 type: 'test' ... # Subtest: public snapshots carry increasing revisions without the private provider transcript or config key ok 66 - public snapshots carry increasing revisions without the private provider transcript or config key --- duration_ms: 723.9272 type: 'test' ... 1..66 # tests 66 # suites 0 # pass 66 # fail 0 # cancelled 0 # skipped 0 # todo 0 # duration_ms 63745.7711