68 lines
4.8 KiB
Plaintext
68 lines
4.8 KiB
Plaintext
✔ sessionModel: agent vars win, then the system's execution settings (15.710134ms)
|
||
✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (7.19641ms)
|
||
✔ a claude-code bundle adds the wrapped gate hook and the MCP config (4.370385ms)
|
||
✔ a bundle is written once: an existing file refuses (3.60041ms)
|
||
✔ a path with a single quote can't go into the hook command (5.870182ms)
|
||
✔ allow exits 0, a deny exits 2 with the reason on stderr (184.820086ms)
|
||
✔ a missing or wrong policy, or a bad event, exits 2 (154.073013ms)
|
||
✔ the bundle's wrapped command: a missing gate or node still blocks (1184.92167ms)
|
||
✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (1314.353822ms)
|
||
✔ claude: the hook alone blocks a path outside the workspace (801.328646ms)
|
||
✔ claude: a second turn resumes the first turn's session (4378.050797ms)
|
||
✔ claude adapter: --restricted is always passed (36.882982ms)
|
||
✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (60.393798ms)
|
||
✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (25.352839ms)
|
||
✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (2421.168836ms)
|
||
✔ claude: a missing hook or MCP file refuses before claude starts (14.062127ms)
|
||
✔ pi: policy tools and typed tools pass, anything else is blocked (4.174644ms)
|
||
✔ claude: builtins map from pi names, typed tools need the mcp prefix (1.111094ms)
|
||
✔ file tool paths must resolve inside the workspace (1.770023ms)
|
||
✔ pi's own path normalisation can't be used to step out (1.56933ms)
|
||
✔ a symlink inside the workspace that points out is outside (1.171302ms)
|
||
✔ a dangling symlink is refused at any depth, in both harnesses (5.858297ms)
|
||
✔ read is checked under every spelling pi's read would open, in both harnesses (30.962487ms)
|
||
✔ other spellings cover directories, dangling links and pi's cwd (3.07546ms)
|
||
✔ a relative path climbs from the workspace's real path, in both harnesses (9.236145ms)
|
||
✔ claude path fields per tool (1.242068ms)
|
||
✔ glob patterns stay inside the workspace (1.096918ms)
|
||
✔ a path that can't be checked is blocked (0.616827ms)
|
||
✔ initialize, ping and tools/list (67.951354ms)
|
||
✔ tools/call goes through the tool socket; a refusal is an isError result (59.919842ms)
|
||
✔ unknown tools and methods are JSON-RPC errors and never reach the socket (43.456935ms)
|
||
✔ a missing argument is a usage error (53.330459ms)
|
||
✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (632.868257ms)
|
||
✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (614.380615ms)
|
||
✔ pi: a read is refused when pi would open another spelling outside (651.479884ms)
|
||
✔ pi: a relative path climbs from the real path of a workspace behind a symlink (723.032154ms)
|
||
✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (2554.662054ms)
|
||
✔ pi: a missing extension refuses before any model call (232.765756ms)
|
||
✔ pi: an extension without its configuration fails pi's start (1618.744704ms)
|
||
✔ founderCheck: founder variables, then a needed service without a usable token (1.976567ms)
|
||
✔ turnRequest names the sender, class, reply and decision (0.299389ms)
|
||
✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (210.482414ms)
|
||
✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (86.085773ms)
|
||
✔ typed tools carry the runner's capability; launch goes to the host's launch socket (446.628147ms)
|
||
✔ a RESULT gets no automatic reply; failed turns reply with the reason (1327.24301ms)
|
||
✔ SIGTERM during a turn kills the turn's process group and still exits 0 (181.784623ms)
|
||
✔ founder credentials stop before the claim (20) (166.651097ms)
|
||
✔ a refused claim exits 21; an ended run's capability exits 22 (289.938182ms)
|
||
✔ the launch ending under a running session exits 22 (240.827767ms)
|
||
✔ a broker that stays unreachable exits 23 after brokerRetries polls (271.861137ms)
|
||
✔ a broker that is down at the claim exits 23, not 21 (347.033181ms)
|
||
✔ no capability, or a malformed one, on stdin exits 2 (2809.24595ms)
|
||
✔ a missing or malformed policy exits 2 before the claim (302.59668ms)
|
||
✔ the PM gets launch, its task verbs and the reads (9.768128ms)
|
||
✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (2.988792ms)
|
||
✔ a coder with a tracker gets its own task tools and no task_reassign (3.179117ms)
|
||
✔ launch only when the business's launch block names the instance as launcher (2.450704ms)
|
||
✔ an action outside the instance's authority has no tool (5.732816ms)
|
||
✔ callTool: one JSON line out, the result back, a refusal rejects (16.198564ms)
|
||
ℹ tests 59
|
||
ℹ suites 0
|
||
ℹ pass 59
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 10553.327487
|