93 lines
7.3 KiB
Plaintext
93 lines
7.3 KiB
Plaintext
✔ sessionModel: agent vars win, then the system's execution settings (8.336262ms)
|
||
✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (3.73651ms)
|
||
✔ a chief-of-staff bundle lists launch among the bus tools and the manifest's typed tools (1.83352ms)
|
||
✔ a claude-code bundle adds the wrapped gate hook and the MCP config (1.960877ms)
|
||
✔ the prompt's built-in tools line is the harness's own names, as the manifest lists them (6.365162ms)
|
||
✔ the prompt names the project clones in the workspace, and none when there are none (4.178899ms)
|
||
✔ the prompt explains the review loop to a role with push_working, and reviews to one with fetch_review (5.321894ms)
|
||
✔ a bundle is written once: an existing file refuses (1.195191ms)
|
||
✔ a path with a single quote can't go into the hook command (1.627967ms)
|
||
✔ allow exits 0, a deny exits 2 with the reason on stderr (91.785693ms)
|
||
✔ a missing or wrong policy, or a bad event, exits 2 (70.197842ms)
|
||
✔ the bundle's wrapped command: a missing gate or node still blocks (1081.759522ms)
|
||
✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (630.039285ms)
|
||
✔ claude: the hook alone blocks a path outside the workspace (372.91978ms)
|
||
✔ claude: a second turn resumes the first turn's session (629.321399ms)
|
||
✔ claude adapter: --restricted is always passed (5.60668ms)
|
||
✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (15.415489ms)
|
||
✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (5.654092ms)
|
||
✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (655.381315ms)
|
||
✔ claude: a missing hook or MCP file refuses before claude starts (7.387197ms)
|
||
✔ pi: policy tools and typed tools pass, anything else is blocked (2.307652ms)
|
||
✔ claude: builtins map from pi names, typed tools need the mcp prefix (0.50058ms)
|
||
✔ file tool paths must resolve inside the workspace (0.864654ms)
|
||
✔ pi's own path normalisation can't be used to step out (0.707123ms)
|
||
✔ a symlink inside the workspace that points out is outside (0.619251ms)
|
||
✔ a dangling symlink is refused at any depth, in both harnesses (1.997468ms)
|
||
✔ read is checked under every spelling pi's read would open, in both harnesses (10.015755ms)
|
||
✔ other spellings cover directories, dangling links and pi's cwd (0.953892ms)
|
||
✔ a relative path climbs from the workspace's real path, in both harnesses (3.099227ms)
|
||
✔ claude path fields per tool (0.432944ms)
|
||
✔ glob patterns stay inside the workspace (0.440722ms)
|
||
✔ a path that can't be checked is blocked (0.248403ms)
|
||
✔ fetch_review's have lists the working refs before origin's, and no more than HAVE_MAX (158.003536ms)
|
||
✔ fetch_review's have orders the working refs newest first within each clone, one clone after another (113.915448ms)
|
||
✔ a runner git past its time: SIGTERM reaches its process group, and SIGKILL follows after the grace period (1809.588064ms)
|
||
✔ once a signalled runner git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (303.912453ms)
|
||
✔ initialize, ping and tools/list (32.054718ms)
|
||
✔ tools/call goes through the tool socket; a refusal is an isError result (28.373541ms)
|
||
✔ replies are compact JSON; over the cap a tool error names the size and the cap (31.650781ms)
|
||
✔ unknown tools and methods are JSON-RPC errors and never reach the socket (24.213877ms)
|
||
✔ a missing argument is a usage error (23.282202ms)
|
||
✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (304.751435ms)
|
||
✔ pi: a reply over the cap is a tool error naming the size and the cap; list_tasks asks for open tasks (311.459536ms)
|
||
✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (297.277741ms)
|
||
✔ pi: a read is refused when pi would open another spelling outside (307.711166ms)
|
||
✔ pi: a relative path climbs from the real path of a workspace behind a symlink (316.537035ms)
|
||
✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (289.241357ms)
|
||
✔ pi: a missing extension refuses before any model call (6.119421ms)
|
||
✔ pi: an extension without its configuration fails pi's start (240.388238ms)
|
||
✔ founderCheck: founder variables, then a needed service without a usable token (0.885229ms)
|
||
✔ turnRequest names the sender, class, reply and decision (0.151317ms)
|
||
✔ turnRequest says a tester's message is a test and never Jason's instruction (0.168317ms)
|
||
✔ turnRequest shows the message's own sent time, a day old as well as new (0.112311ms)
|
||
✔ stateBlock names the launch state with its time and event, and the open tasks with the cap (0.200779ms)
|
||
✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (149.506174ms)
|
||
✔ launches revoked and then restored: the turn's block reads allowed and gives the restore time (165.502176ms)
|
||
✔ a task closed on the tracker is missing from the next turn's open list (167.53618ms)
|
||
✔ a message read a day after it was sent shows the time it was sent (86.091424ms)
|
||
✔ a decision the human resolves becomes a turn citing the decision and the answer (138.823674ms)
|
||
✔ a failed state read fails the turn: no adapter runs, the sender hears why, the message is read (61.373189ms)
|
||
✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (42.595564ms)
|
||
✔ typed tools carry the runner's capability; launch goes to the host's launch socket (271.992761ms)
|
||
✔ a RESULT gets no automatic reply; failed turns reply with the reason (1164.476662ms)
|
||
✔ SIGTERM during a turn kills the turn's process group and still exits 0 (92.1364ms)
|
||
✔ founder credentials stop before the claim (20) (87.106671ms)
|
||
✔ a refused claim exits 21; an ended run's capability exits 22 (84.848762ms)
|
||
✔ the launch ending under a running session exits 22 (96.356717ms)
|
||
✔ a broker that stays unreachable exits 23 after brokerRetries polls (198.700381ms)
|
||
✔ a broker that is down at the claim exits 23, not 21 (46.62532ms)
|
||
✔ no capability, or a malformed one, on stdin exits 2 (151.119305ms)
|
||
✔ a missing or malformed policy exits 2 before the claim (81.296412ms)
|
||
✔ the PM gets its task verbs and the reads, and no launch (5.103995ms)
|
||
✔ the chief of staff gets launch and send_message, and no task verbs (1.403783ms)
|
||
✔ the assistant gets send_message and the reads, no launch (1.628825ms)
|
||
✔ list_requirements reads the requirement ids, for a task.create holder with a tracker (2.257009ms)
|
||
✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (1.108602ms)
|
||
✔ a coder with a tracker gets its own task tools and no task_reassign (0.920281ms)
|
||
✔ launch only when the business's launch block names the instance as launcher (1.638031ms)
|
||
✔ an action outside the instance's authority has no tool (1.260173ms)
|
||
✔ the review loop: push_working and request_review for the coder, fetch_review and review_verdict for the reviewer, none for the PM (2.801425ms)
|
||
✔ callTool: one JSON line out, the result back, a refusal rejects (6.532995ms)
|
||
✔ list_tasks takes the broker's filters and pages; get_task takes a task_ref (1.889571ms)
|
||
✔ callTool sends list_tasks done false unless the session names done; other tools as given (2.027402ms)
|
||
✔ replyText: compact JSON up to the cap, an error naming the size and the cap over it (0.64468ms)
|
||
ℹ tests 84
|
||
ℹ suites 0
|
||
ℹ pass 84
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 19149.464181
|