✔ sessionModel: agent vars win, then the system's execution settings (11.752989ms)
✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (5.483185ms)
✔ a chief-of-staff bundle lists launch among the bus tools and the manifest's typed tools (2.817745ms)
✔ a chief-of-staff bundle lists end_run and change_organization as typed and nothing untyped, for either harness (6.997344ms)
✔ the stop line names end_run for a role.end holder, and every other role keeps today's text (6.733162ms)
✔ a claude-code bundle adds the wrapped gate hook and the MCP config (2.504379ms)
✔ the prompt's built-in tools line is the harness's own names, as the manifest lists them (8.929666ms)
✔ the prompt names the project clones in the workspace, and none when there are none (7.863011ms)
✔ the prompt explains the review loop to a role with push_working, and reviews to one with fetch_review (7.102604ms)
✔ a bundle is written once: an existing file refuses (1.593274ms)
✔ a path with a single quote can't go into the hook command (1.744125ms)
✔ allow exits 0, a deny exits 2 with the reason on stderr (135.989054ms)
✔ a missing or wrong policy, or a bad event, exits 2 (83.882583ms)
✔ the bundle's wrapped command: a missing gate or node still blocks (1089.577446ms)
✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (761.835355ms)
✔ claude: the hook alone blocks a path outside the workspace (393.311801ms)
✔ claude: a second turn resumes the first turn's session (709.900207ms)
✔ claude adapter: --restricted is always passed (5.065902ms)
✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (15.022376ms)
✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (5.427828ms)
✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (674.034862ms)
✔ claude: a missing hook or MCP file refuses before claude starts (7.148952ms)
✔ pi: policy tools and typed tools pass, anything else is blocked (3.944789ms)
✔ claude: builtins map from pi names, typed tools need the mcp prefix (0.963247ms)
✔ file tool paths must resolve inside the workspace (2.351712ms)
✔ pi's own path normalisation can't be used to step out (1.538202ms)
✔ a symlink inside the workspace that points out is outside (1.163984ms)
✔ a dangling symlink is refused at any depth, in both harnesses (2.748085ms)
✔ read is checked under every spelling pi's read would open, in both harnesses (19.140207ms)
✔ other spellings cover directories, dangling links and pi's cwd (1.592041ms)
✔ a relative path climbs from the workspace's real path, in both harnesses (5.506639ms)
✔ claude path fields per tool (1.052403ms)
✔ glob patterns stay inside the workspace (0.628154ms)
✔ a path that can't be checked is blocked (0.355507ms)
✔ fetch_review's have lists the working refs before origin's, and no more than HAVE_MAX (214.106766ms)
✔ fetch_review's have orders the working refs newest first within each clone, one clone after another (129.142114ms)
✔ a runner git past its time: SIGTERM reaches its process group, and SIGKILL follows after the grace period (1807.679189ms)
✔ once a signalled runner git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (302.872663ms)
✔ initialize, ping and tools/list (48.06885ms)
✔ tools/call goes through the tool socket; a refusal is an isError result (40.250547ms)
✔ replies are compact JSON; over the cap a tool error names the size and the cap (33.254796ms)
✔ unknown tools and methods are JSON-RPC errors and never reach the socket (32.530671ms)
✔ a missing argument is a usage error (34.192519ms)
✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (368.07696ms)
✔ pi: a reply over the cap is a tool error naming the size and the cap; list_tasks asks for open tasks (343.068401ms)
✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (305.248219ms)
✔ pi: a read is refused when pi would open another spelling outside (313.715969ms)
✔ pi: a relative path climbs from the real path of a workspace behind a symlink (304.710864ms)
✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (293.969794ms)
✔ pi: a missing extension refuses before any model call (5.936834ms)
✔ pi: an extension without its configuration fails pi's start (256.217846ms)
✔ founderCheck: founder variables, then a needed service without a usable token (1.682213ms)
✔ turnRequest names the sender, class, reply and decision (0.239867ms)
✔ turnRequest says a tester's message is a test and never Jason's instruction (0.239708ms)
✔ turnRequest shows the message's own sent time, a day old as well as new (0.191935ms)
✔ stateBlock names the launch state with its time and event, and the open tasks with the cap (0.255558ms)
✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (191.215044ms)
✔ launches revoked and then restored: the turn's block reads allowed and gives the restore time (173.857456ms)
✔ a task closed on the tracker is missing from the next turn's open list (170.884141ms)
✔ a message read a day after it was sent shows the time it was sent (92.878244ms)
✔ a decision the human resolves becomes a turn citing the decision and the answer (148.017921ms)
✔ a failed state read fails the turn: no adapter runs, the sender hears why, the message is read (64.946542ms)
✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (51.092973ms)
✔ typed tools carry the runner's capability; launch goes to the host's launch socket (276.111751ms)
✔ end_run and change_organization reach the broker with the tool's arguments, and refusals keep their codes (284.109001ms)
✔ a RESULT gets no automatic reply; failed turns reply with the reason (1196.65156ms)
✔ SIGTERM during a turn kills the turn's process group and still exits 0 (94.594498ms)
✔ founder credentials stop before the claim (20) (90.472417ms)
✔ a refused claim exits 21; an ended run's capability exits 22 (92.93766ms)
✔ the launch ending under a running session exits 22 (102.381526ms)
✔ a broker that stays unreachable exits 23 after brokerRetries polls (199.927245ms)
✔ a broker that is down at the claim exits 23, not 21 (47.468955ms)
✔ no capability, or a malformed one, on stdin exits 2 (148.21306ms)
✔ a missing or malformed policy exits 2 before the claim (80.539326ms)
✔ the PM gets its task verbs and the reads, and no launch (10.445132ms)
✔ the chief of staff gets launch, send_message, end_run and change_organization, and no task verbs (2.203035ms)
✔ end_run sends role and reason, no decision; change_organization sends revision and the organization keys (2.916438ms)
✔ the organization keys change_organization takes are the broker's ORGANIZATION_KEYS (0.147141ms)
✔ a role without role.end or organization.change gets neither tool, and each tool follows its own grant (11.443134ms)
✔ the assistant gets send_message and the reads, no launch (2.212377ms)
✔ list_requirements reads the requirement ids, for a task.create holder with a tracker (2.941407ms)
✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (1.157381ms)
✔ a coder with a tracker gets its own task tools and no task_reassign (1.223648ms)
✔ launch only when the business's launch block names the instance as launcher (2.974238ms)
✔ an action outside the instance's authority has no tool (2.034293ms)
✔ the review loop: push_working and request_review for the coder, fetch_review and review_verdict for the reviewer, none for the PM (5.694429ms)
✔ callTool: one JSON line out, the result back, a refusal rejects (10.23694ms)
✔ list_tasks takes the broker's filters and pages; get_task takes a task_ref (2.582732ms)
✔ callTool sends list_tasks done false unless the session names done; other tools as given (2.473225ms)
✔ replyText: compact JSON up to the cap, an error naming the size and the cap over it (0.817834ms)
ℹ tests 90
ℹ suites 0
ℹ pass 90
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 10868.805917
