jason.woltje
158205c5cc
Unclaimed files left in the canonical checkout. Inventory: canonical-cleanup-inventory.md (commit-as-evidence groups). detect-secrets scan clean on 2026-11-02: hits are sha256 pins, git object ids, test sentinels already in tracked tests and unit-file lines.
117 lines
10 KiB
Plaintext
117 lines
10 KiB
Plaintext
✔ sessionModel: agent vars win, then the system's execution settings (15.205218ms)
|
||
✔ a pi bundle: prompt, policy, tools and manifest, 0600 in a 0700 directory (4.330159ms)
|
||
✔ a chief-of-staff bundle lists launch among the bus tools and the manifest's typed tools (2.674919ms)
|
||
✔ a chief-of-staff bundle lists end_run and change_organization as typed and only instance.name untyped, for either harness (4.601613ms)
|
||
✔ the stop line names end_run for a role.end holder, and every other role keeps today's text (8.138976ms)
|
||
✔ a claude-code bundle adds the wrapped gate hook and the MCP config (2.406239ms)
|
||
✔ the prompt's built-in tools line is the harness's own names, as the manifest lists them (11.233552ms)
|
||
✔ the prompt names the project clones in the workspace, and none when there are none (6.760356ms)
|
||
✔ the prompt explains the review loop to a role with push_working, and reviews to one with fetch_review (7.506539ms)
|
||
✔ the prompt explains landing to a role with land_work, and to no other (3.785122ms)
|
||
✔ the prompt tells the pm to ask the chief of staff for sessions, and no other role (6.636362ms)
|
||
✔ a bundle is written once: an existing file refuses (1.575704ms)
|
||
✔ a path with a single quote can't go into the hook command (1.974894ms)
|
||
✔ web grant on pi: the bundle has web_search and web_fetch, and no built-in web tool (1.998684ms)
|
||
✔ no web grant on pi: no web tool in the bundle, and the gate blocks a web call (1.939982ms)
|
||
✔ web grant on claude-code: the bundle has web_search and web_fetch, and no built-in web tool (1.598153ms)
|
||
✔ no web grant on claude-code: no web tool in the bundle, and the gate blocks a web call (1.528175ms)
|
||
✔ a granted session's gate lets the typed web tools through and still blocks the built-ins (1.598158ms)
|
||
✔ search-source searxng-url: a granted role gets the typed broker tools and no harness web tool; an ungranted role gets nothing (4.068292ms)
|
||
✔ search-source searxng-bundled: a granted role gets the typed broker tools and no harness web tool; an ungranted role gets nothing (4.357731ms)
|
||
✔ search-source harness-builtin: claude-code gets WebSearch and WebFetch and no typed web tool, only when granted (6.002962ms)
|
||
✔ search-source harness-builtin is refused for a granted pi role, which has no built-in web tool (1.702969ms)
|
||
✔ allow exits 0, a deny exits 2 with the reason on stderr (130.273385ms)
|
||
✔ a missing or wrong policy, or a bad event, exits 2 (90.161754ms)
|
||
✔ the bundle's wrapped command: a missing gate or node still blocks (1093.904547ms)
|
||
✔ claude: typed tools through MCP, the hook blocks, builtins outside --tools don't exist (787.424143ms)
|
||
✔ claude: the hook alone blocks a path outside the workspace (460.648227ms)
|
||
✔ claude: a second turn resumes the first turn's session (770.205559ms)
|
||
✔ claude adapter: --restricted is always passed (5.029092ms)
|
||
✔ claude adapter: MOSAIC_CLAUDE_BIN wins over PATH and must be an absolute executable (16.171912ms)
|
||
✔ claude adapter: a directory pin exits 2 before it runs; a pin with a space runs (6.590643ms)
|
||
✔ claude: CLAUDE.md files and auto-memory don't reach the model; without --restricted they do (743.557176ms)
|
||
✔ claude: a missing hook or MCP file refuses before claude starts (7.294392ms)
|
||
✔ pi: policy tools and typed tools pass, anything else is blocked (3.113165ms)
|
||
✔ claude: builtins map from pi names, typed tools need the mcp prefix (0.728313ms)
|
||
✔ file tool paths must resolve inside the workspace (1.628715ms)
|
||
✔ pi's own path normalisation can't be used to step out (1.023215ms)
|
||
✔ a symlink inside the workspace that points out is outside (0.922306ms)
|
||
✔ a dangling symlink is refused at any depth, in both harnesses (4.804508ms)
|
||
✔ read is checked under every spelling pi's read would open, in both harnesses (21.583947ms)
|
||
✔ other spellings cover directories, dangling links and pi's cwd (1.446145ms)
|
||
✔ a relative path climbs from the workspace's real path, in both harnesses (4.256783ms)
|
||
✔ claude path fields per tool (0.878247ms)
|
||
✔ glob patterns stay inside the workspace (0.894311ms)
|
||
✔ a path that can't be checked is blocked (0.380469ms)
|
||
✔ fetch_review's have lists the working refs before origin's, and no more than HAVE_MAX (236.930429ms)
|
||
✔ fetch_review's have orders the working refs newest first within each clone, one clone after another (146.484031ms)
|
||
✔ a runner git past its time: SIGTERM reaches its process group, and SIGKILL follows after the grace period (1808.944836ms)
|
||
✔ once a signalled runner git has closed, its group gets SIGKILL, so a process that ignored SIGTERM dies too (304.00457ms)
|
||
✔ land_work sends one land line and resolves the host's started answer (3.395962ms)
|
||
✔ initialize, ping and tools/list (54.805746ms)
|
||
✔ tools/call goes through the tool socket; a refusal is an isError result (36.54933ms)
|
||
✔ replies are compact JSON; over the cap a tool error names the size and the cap (40.171693ms)
|
||
✔ unknown tools and methods are JSON-RPC errors and never reach the socket (30.843147ms)
|
||
✔ a missing argument is a usage error (31.978071ms)
|
||
✔ pi: typed tools reach the socket, the gate blocks, agent_end writes the marker (389.218429ms)
|
||
✔ pi: a reply over the cap is a tool error naming the size and the cap; list_tasks asks for open tasks (307.002672ms)
|
||
✔ pi: a write through a dangling symlink is blocked, and nothing appears outside (303.076715ms)
|
||
✔ pi: a read is refused when pi would open another spelling outside (320.453084ms)
|
||
✔ pi: a relative path climbs from the real path of a workspace behind a symlink (316.794027ms)
|
||
✔ pi: a relative path climbs from the real path of a dataRoot behind a symlink (319.552897ms)
|
||
✔ pi: a missing extension refuses before any model call (5.891957ms)
|
||
✔ pi: an extension without its configuration fails pi's start (253.018808ms)
|
||
✔ founderCheck: founder variables, then a needed service without a usable token (1.690157ms)
|
||
✔ turnRequest names the sender, class, reply and decision (0.290377ms)
|
||
✔ turnRequest says a tester's message is a test and never Jason's instruction (0.328756ms)
|
||
✔ turnRequest shows the message's own sent time, a day old as well as new (0.221959ms)
|
||
✔ stateBlock names the launch state with its time and event, and the open tasks with the cap (0.330594ms)
|
||
✔ a message becomes a turn, the answer goes back as a RESULT, SIGTERM releases and exits 0 (278.63092ms)
|
||
✔ launches revoked and then restored: the turn's block reads allowed and gives the restore time (233.814357ms)
|
||
✔ a task closed on the tracker is missing from the next turn's open list (220.185138ms)
|
||
✔ a message read a day after it was sent shows the time it was sent (154.306368ms)
|
||
✔ a decision the human resolves becomes a turn citing the decision and the answer (213.550176ms)
|
||
✔ a failed state read fails the turn: no adapter runs, the sender hears why, the message is read (122.96812ms)
|
||
✔ a SIGTERM before the claim stops the runner with exit 0 and no claim (99.826629ms)
|
||
✔ typed tools carry the runner's capability; launch goes to the host's launch socket (420.464622ms)
|
||
✔ end_run and change_organization reach the broker with the tool's arguments, and refusals keep their codes (427.455392ms)
|
||
✔ a RESULT gets no automatic reply; failed turns reply with the reason (1288.670852ms)
|
||
✔ the bus's launch notice is one turn with no reply, and is not taken again (282.190477ms)
|
||
✔ SIGTERM during a turn kills the turn's process group and still exits 0 (150.694303ms)
|
||
✔ founder credentials stop before the claim (20) (172.234623ms)
|
||
✔ a refused claim exits 21; an ended run's capability exits 22 (199.395717ms)
|
||
✔ the launch ending under a running session exits 22 (147.512404ms)
|
||
✔ a broker that stays unreachable exits 23 after brokerRetries polls (243.32205ms)
|
||
✔ a broker that is down at the claim exits 23, not 21 (94.552282ms)
|
||
✔ no capability, or a malformed one, on stdin exits 2 (194.02496ms)
|
||
✔ a missing or malformed policy exits 2 before the claim (130.124822ms)
|
||
✔ every role sees read_spec, record writer follows its grant, citation schemas stay strict (13.492178ms)
|
||
✔ typed socket forwards read content/history and agent record writes, and cannot write a spec (192.10641ms)
|
||
✔ the PM gets its task verbs and the reads, and no launch (8.137366ms)
|
||
✔ the chief of staff gets launch, send_message, end_run and change_organization, and no task verbs (3.375838ms)
|
||
✔ request_staff is the pm's alone: staff.request over message.send, roles and counts bounded (11.036365ms)
|
||
✔ end_run sends role and reason, no decision; change_organization sends revision and the organization keys (4.069431ms)
|
||
✔ the organization keys change_organization takes are the broker's ORGANIZATION_KEYS (0.104233ms)
|
||
✔ a role without role.end or organization.change gets neither tool, and each tool follows its own grant (6.524791ms)
|
||
✔ the assistant gets send_message, the reads and the web tools (it holds the web grant), no launch (1.287016ms)
|
||
✔ list_requirements reads the requirement ids, for a task.create holder with a tracker (2.666299ms)
|
||
✔ a coder gets no launch, no resolve_decision, and no task tools without a tracker (1.290844ms)
|
||
✔ a coder with a tracker gets its own task tools and no task_reassign (1.337456ms)
|
||
✔ launch only when the business's launch block names the instance as launcher (1.976096ms)
|
||
✔ an action outside the instance's authority has no tool (1.109284ms)
|
||
✔ the review loop: push_working and request_review for the coder, fetch_review and review_verdict for the reviewer, none for the PM (4.19586ms)
|
||
✔ land_work is there only with land, after push_working, with the task and the decision (2.441687ms)
|
||
✔ callTool: one JSON line out, the result back, a refusal rejects (10.270807ms)
|
||
✔ list_tasks takes the broker's filters and pages; get_task takes a task_ref (2.263277ms)
|
||
✔ callTool sends list_tasks done false unless the session names done; other tools as given (2.484567ms)
|
||
✔ replyText: compact JSON up to the cap, an error naming the size and the cap over it (0.60034ms)
|
||
✔ web_search's query maxLength is the web layer's SEARCH_MAX_QUERY_CHARS (2.324396ms)
|
||
ℹ tests 108
|
||
ℹ suites 0
|
||
ℹ pass 108
|
||
ℹ fail 0
|
||
ℹ cancelled 0
|
||
ℹ skipped 0
|
||
ℹ todo 0
|
||
ℹ duration_ms 12049.56719
|