90 lines
7.1 KiB
Plaintext
90 lines
7.1 KiB
Plaintext
✔ sessionModel: agent vars win, then the system's execution settings (7.818791ms)
|
||
✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (3.958461ms)
|
||
✔ a claude-code bundle adds the wrapped gate hook and the MCP config (2.006285ms)
|
||
✔ the prompt's built-in tools line is the harness's own names, as the manifest lists them (6.767726ms)
|
||
✔ the prompt names the project clones in the workspace, and none when there are none (4.321076ms)
|
||
✔ the prompt explains the review loop to a role with push_working, and reviews to one with fetch_review (5.229878ms)
|
||
✔ a bundle is written once: an existing file refuses (1.138055ms)
|
||
✔ a path with a single quote can't go into the hook command (1.178722ms)
|
||
✔ allow exits 0, a deny exits 2 with the reason on stderr (105.209197ms)
|
||
✔ a missing or wrong policy, or a bad event, exits 2 (75.667182ms)
|
||
✔ the bundle's wrapped command: a missing gate or node still blocks (1086.870053ms)
|
||
✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (747.639312ms)
|
||
✔ claude: the hook alone blocks a path outside the workspace (437.905122ms)
|
||
✔ claude: a second turn resumes the first turn's session (712.601477ms)
|
||
✔ claude adapter: --restricted is always passed (5.580292ms)
|
||
✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (18.712325ms)
|
||
✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (6.03325ms)
|
||
✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (717.696021ms)
|
||
✔ claude: a missing hook or MCP file refuses before claude starts (8.027014ms)
|
||
✔ pi: policy tools and typed tools pass, anything else is blocked (2.436629ms)
|
||
✔ claude: builtins map from pi names, typed tools need the mcp prefix (0.545655ms)
|
||
✔ file tool paths must resolve inside the workspace (0.907059ms)
|
||
✔ pi's own path normalisation can't be used to step out (0.797671ms)
|
||
✔ a symlink inside the workspace that points out is outside (0.728073ms)
|
||
✔ a dangling symlink is refused at any depth, in both harnesses (2.222052ms)
|
||
✔ read is checked under every spelling pi's read would open, in both harnesses (10.70842ms)
|
||
✔ other spellings cover directories, dangling links and pi's cwd (1.051642ms)
|
||
✔ a relative path climbs from the workspace's real path, in both harnesses (3.527694ms)
|
||
✔ claude path fields per tool (0.560541ms)
|
||
✔ glob patterns stay inside the workspace (0.485835ms)
|
||
✔ a path that can't be checked is blocked (0.294007ms)
|
||
✔ fetch_review's have lists the working refs before origin's, and no more than HAVE_MAX (175.213151ms)
|
||
✔ fetch_review's have orders the working refs newest first within each clone, one clone after another (125.803885ms)
|
||
✔ a runner git past its time: SIGTERM reaches its process group, and SIGKILL follows after the grace period (1810.345907ms)
|
||
✔ once a signalled runner git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (306.760621ms)
|
||
✔ initialize, ping and tools/list (35.641176ms)
|
||
✔ tools/call goes through the tool socket; a refusal is an isError result (28.433447ms)
|
||
✔ replies are compact JSON; over the cap a tool error names the size and the cap (36.25454ms)
|
||
✔ unknown tools and methods are JSON-RPC errors and never reach the socket (27.383742ms)
|
||
✔ a missing argument is a usage error (25.253669ms)
|
||
✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (337.882943ms)
|
||
✔ pi: a reply over the cap is a tool error naming the size and the cap; list_tasks asks for open tasks (314.761128ms)
|
||
✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (321.01008ms)
|
||
✔ pi: a read is refused when pi would open another spelling outside (318.063812ms)
|
||
✔ pi: a relative path climbs from the real path of a workspace behind a symlink (313.87451ms)
|
||
✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (315.529524ms)
|
||
✔ pi: a missing extension refuses before any model call (6.587803ms)
|
||
✔ pi: an extension without its configuration fails pi's start (280.495828ms)
|
||
✔ founderCheck: founder variables, then a needed service without a usable token (0.977707ms)
|
||
✔ turnRequest names the sender, class, reply and decision (0.165136ms)
|
||
✔ turnRequest says a tester's message is a test and never Jason's instruction (0.194422ms)
|
||
✔ turnRequest shows the message's own sent time, a day old as well as new (0.118702ms)
|
||
✔ stateBlock names the launch state with its time and event, and the open tasks with the cap (0.191277ms)
|
||
✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (151.877608ms)
|
||
✔ launches revoked and then restored: the turn's block reads allowed and gives the restore time (170.374365ms)
|
||
✔ a task closed on the tracker is missing from the next turn's open list (167.916173ms)
|
||
✔ a message read a day after it was sent shows the time it was sent (89.418575ms)
|
||
✔ a decision the human resolves becomes a turn citing the decision and the answer (141.776777ms)
|
||
✔ a failed state read fails the turn: no adapter runs, the sender hears why, the message is read (64.117418ms)
|
||
✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (49.325445ms)
|
||
✔ typed tools carry the runner's capability; launch goes to the host's launch socket (272.981431ms)
|
||
✔ a RESULT gets no automatic reply; failed turns reply with the reason (1191.823731ms)
|
||
✔ SIGTERM during a turn kills the turn's process group and still exits 0 (94.329678ms)
|
||
✔ founder credentials stop before the claim (20) (93.650679ms)
|
||
✔ a refused claim exits 21; an ended run's capability exits 22 (99.618949ms)
|
||
✔ the launch ending under a running session exits 22 (105.158034ms)
|
||
✔ a broker that stays unreachable exits 23 after brokerRetries polls (207.676602ms)
|
||
✔ a broker that is down at the claim exits 23, not 21 (46.942533ms)
|
||
✔ no capability, or a malformed one, on stdin exits 2 (156.480452ms)
|
||
✔ a missing or malformed policy exits 2 before the claim (87.86403ms)
|
||
✔ the PM gets launch, its task verbs and the reads (6.088115ms)
|
||
✔ list_requirements reads the requirement ids, for a task.create holder with a tracker (3.626245ms)
|
||
✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (1.182533ms)
|
||
✔ a coder with a tracker gets its own task tools and no task_reassign (1.040036ms)
|
||
✔ launch only when the business's launch block names the instance as launcher (0.983847ms)
|
||
✔ an action outside the instance's authority has no tool (0.975084ms)
|
||
✔ the review loop: push_working and request_review for the coder, fetch_review and review_verdict for the reviewer, none for the PM (3.958918ms)
|
||
✔ callTool: one JSON line out, the result back, a refusal rejects (6.993845ms)
|
||
✔ list_tasks takes the broker's filters and pages; get_task takes a task_ref (1.928614ms)
|
||
✔ callTool sends list_tasks done false unless the session names done; other tools as given (1.906119ms)
|
||
✔ replyText: compact JSON up to the cap, an error naming the size and the cap over it (0.611221ms)
|
||
ℹ tests 81
|
||
ℹ suites 0
|
||
ℹ pass 81
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 19769.962427
|