71 lines
2.4 KiB
Plaintext
71 lines
2.4 KiB
Plaintext
TAP version 13
|
|
# Subtest: claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist
|
|
ok 1 - claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist
|
|
---
|
|
duration_ms: 740.530837
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: the hook alone blocks a path outside the workspace
|
|
ok 2 - claude: the hook alone blocks a path outside the workspace
|
|
---
|
|
duration_ms: 484.250736
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: a second turn resumes the first turn's session
|
|
ok 3 - claude: a second turn resumes the first turn's session
|
|
---
|
|
duration_ms: 857.991709
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude adapter: --restricted is always passed
|
|
ok 4 - claude adapter: --restricted is always passed
|
|
---
|
|
duration_ms: 5.19059
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable
|
|
ok 5 - claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable
|
|
---
|
|
duration_ms: 16.380045
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude adapter: a directory pin exits 2 before it runs; a pin with a space runs
|
|
ok 6 - claude adapter: a directory pin exits 2 before it runs; a pin with a space runs
|
|
---
|
|
duration_ms: 5.47195
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do
|
|
ok 7 - claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do
|
|
---
|
|
duration_ms: 869.204192
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: a missing hook or MCP file refuses before claude starts
|
|
ok 8 - claude: a missing hook or MCP file refuses before claude starts
|
|
---
|
|
duration_ms: 8.011154
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: row 66 a reply with a tell gets the correction notice on the next turn, a clean reply gets none, and the counts read after
|
|
ok 9 - claude: row 66 a reply with a tell gets the correction notice on the next turn, a clean reply gets none, and the counts read after
|
|
---
|
|
duration_ms: 1760.816087
|
|
type: 'test'
|
|
...
|
|
# Subtest: claude: row 66 a broken lists.json gives no clean verdict, the operator is told once, and the session still answers
|
|
ok 10 - claude: row 66 a broken lists.json gives no clean verdict, the operator is told once, and the session still answers
|
|
---
|
|
duration_ms: 951.447392
|
|
type: 'test'
|
|
...
|
|
1..10
|
|
# tests 10
|
|
# suites 0
|
|
# pass 10
|
|
# fail 0
|
|
# cancelled 0
|
|
# skipped 0
|
|
# todo 0
|
|
# duration_ms 5778.476849
|