@remits/remits-cli 0.1.164 → 0.1.165

package/index.js

@@ -8,14 +8,14 @@
 - L631  Local State, Workspaces, And Verification Evidence
 - L2669  Account Repos, Guide Sync, And Platform Repo
 - L3509  Component Discovery And HTTP Logging
-- L4277  Skill Delivery And TOC Resolution
-- L4592  Auth And Component Staging
-- L5224  Component Summaries, Status, And Sync Gates
-- L7548  Branches, Promotion, Commit, And Test Runs
-- L9802  Tokens, Tools, Verification, And Config
-- L11319  Service Dashboard And WebSocket Listener
-- L13829  Agent And Ticket Workflows
-- L18090  Help, Auto Update, And Command Dispatch
+- L4279  Skill Delivery And TOC Resolution
+- L4594  Auth And Component Staging
+- L5226  Component Summaries, Status, And Sync Gates
+- L7550  Branches, Promotion, Commit, And Test Runs
+- L9813  Tokens, Tools, Verification, And Config
+- L11330  Service Dashboard And WebSocket Listener
+- L13840  Agent And Ticket Workflows
+- L18101  Help, Auto Update, And Command Dispatch
 */
 
 /*
@@ -899,7 +899,7 @@ function localStateWarnings(cwd, flags = {}) {
       .sort((a, b) => Date.parse(b.updatedAt || 0) - Date.parse(a.updatedAt || 0));
     const shown = recent.slice(0, 3).map((a) => a.actor);
     const stale = report.foreignActors.length - recent.length;
-    const setOne = 'Name this one with --actor <name> (or REMITS_AGENT_ID) if another agent shares this checkout.';
+    const setOne = 'Name this one with --local-agent <name> (or REMITS_LOCAL_AGENT_ID) if another agent shares this checkout; REMITS_AGENT_ID also declares agent identity to the platform.';
     const pruneHint = stale
       ? stale + ' spent actor dir(s) (idle, or left behind by finished processes) can be cleared with `remits-cli doctor local-state --prune-actors`.'
       : '';
@@ -3669,7 +3669,9 @@ function collectComponents(cwd) {
         component.html = content;
       } else if (type === 'htmltemplate' && ext === 'json') {
         component.previewData = content;
-      } else if (type === 'tool' && ext === 'json') {
+      } else if ((type === 'tool' || type === 'action') && ext === 'json') {
+        // An Action's .json sidecar is its input schema (manual-run form and x-remits-operations), exactly as
+        // repository sync maps it; staging used to drop it, so a staged declaration silently did not apply.
         component.inputSchema = content;
       } else if (type === 'i18n' && ext === 'json') {
         component.messages = content;
@@ -3850,7 +3852,7 @@ function componentPathInfo(cwd, filePath) {
   else if (type === 'embeddable' && ext === 'js') field = 'javascript';
   else if (type === 'htmltemplate' && ext === 'html') field = 'html';
   else if (type === 'htmltemplate' && ext === 'json') field = 'previewData';
-  else if (type === 'tool' && ext === 'json') field = 'inputSchema';
+  else if ((type === 'tool' || type === 'action') && ext === 'json') field = 'inputSchema';
   else if (type === 'i18n' && ext === 'json') field = 'messages';
   else if (type === 'schema' && ext === 'json') field = 'schema';
 
@@ -9130,10 +9132,18 @@ async function waitForToolStatus(api, cwd, options) {
 
 // One compact progress line for a streamed TestSuite frame: a finished case, or the suite roll-up.
 function testSuiteProgressLine(payload = {}) {
+  if (payload.event === 'case_started') {
+    return '[ws] running ' + (payload.activeCases || []).map((c) =>
+      c.name + (c.traceId ? ' [trace ' + c.traceId + ']' : '')).join(', ');
+  }
   if (payload.total != null || Array.isArray(payload.tests)) {
     const total = payload.total != null ? payload.total : (payload.tests || []).length;
     const passed = payload.passed != null ? payload.passed : (payload.tests || []).filter((t) => t && t.passed).length;
-    return '[ws] ' + (payload.testName || 'suite') + ': ' + passed + '/' + total + ' passed';
+    const active = (payload.activeCases || []).map((c) => c.name + (c.traceId ? ' [trace ' + c.traceId + ']' : ''));
+    const queued = (payload.shards || []).filter((s) => s.status === 'queued').length;
+    return '[ws] ' + (payload.testName || 'suite') + ': ' + passed + '/' + total + ' passed' +
+      (payload.status ? ' (' + payload.status + ')' : '') +
+      (active.length ? '; running: ' + active.join(', ') : '') + (queued ? '; ' + queued + ' workers queued' : '');
   }
   const mark = payload.passed === false ? 'FAIL' : 'pass';
   const detail = payload.outcome && payload.outcome !== 'passed' ? ' [' + payload.outcome + ']' : '';
@@ -9172,7 +9182,7 @@ function watchWebsocket(baseUrl, topicId, taskId, options = {}) {
           if (payload.taskId && followed.length && !followed.includes(payload.taskId)) {
             return;
           }
-          if (payload.tests || payload.name || payload.total != null) {
+          if (payload.tests || payload.name || payload.total != null || payload.event === 'case_started') {
             // Progress, not the payload. This used to print the whole suite result — every case, every
             // stacktrace — as one enormous line immediately before the readable summary said the same thing,
             // which buried the run world, the outcomes and the pivots an agent actually reads. --verbose still
@@ -9345,6 +9355,7 @@ async function testCommand(flags) {
     workspace,
     dataMode,
     dataModeSource,
+    caseConcurrency: flags.parallel !== undefined && runOptions.parallel === 1 ? 1 : undefined,
     testId: /^\d+$/.test(String(testRef)) ? Number(testRef) : undefined,
     testName: /^\d+$/.test(String(testRef)) ? undefined : String(testRef),
     tests: names

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remits/remits-cli",
-  "version": "0.1.164",
+  "version": "0.1.165",
   "description": "Local CLI for auth, component sync, and live test execution against Remits",
   "license": "MIT",
   "private": false,

package/skills/remits-cli/SKILL.md

@@ -181,10 +181,15 @@ reference named after it.
   from `./.remits-cli/actors/<local-agent>/tool-responses/<callId>.json` (or the legacy flat fallback
   if `doctor local-state` says the response is there) before reporting the work as done.
   (`tool-reference.md`)
-- **Workspace and local actor are different.** `workspace` is the server-side staging lane namespace;
-  `local actor` is the repo-local filesystem namespace for session logs, tool responses, and verification
-  mirrors. Use `REMITS_AGENT_ID=<name>` or `--local-agent <name>` when agents share a checkout, and run
-  `remits-cli doctor local-state` when inheriting one. (`cli-state.md`, `component-resolution.md`)
+- **Workspace, local actor and agent identity are three different things.** `workspace` is the
+  server-side staging lane. The **local actor** is only the repo-local folder for session logs, tool
+  responses and verification mirrors: name it with `--local-agent <name>` or `REMITS_LOCAL_AGENT_ID` when
+  agents share a checkout, and run `remits-cli doctor local-state` when inheriting one. **Agent identity**
+  (`--agent-id` / `REMITS_AGENT_ID`) is what the PLATFORM sees: it is sent on every call, it makes the
+  call an `agent` to the account's policy rules, and it decides ticket ownership. `REMITS_AGENT_ID` also
+  names the local folder when no local actor is set, which is why setting it "just for the folder" changes
+  how the platform treats you. If you are an AI agent, setting it is correct: say who you are, and let the
+  account's agent rules apply to you. (`cli-state.md`, `agent-sessions.md`)
 - **Writing the code is not finishing the job.** A change is complete when it is verified — a Test
   component (preferred, because it becomes regression protection) or a browser flow through
   `remits-cli token`. "Just do it" and "that's fine, commit it" are not evidence. If you genuinely
@@ -232,6 +237,11 @@ reference named after it.
 - **Reading and investigating are parallel-safe; editing one account's repository is exclusive**, via a
   lease. A refusal is not an error — carry on read-only and hand off with `ticket progress --next-step`.
   Never wait or poll for a lease. (`support-tickets.md`)
+- **`Refused by this account's '<rule>' rule` is a POLICY decision, not a missing capability.** The
+  sentence says who the call presented as (`[This call presents as agent (agentId=…)]`). Find the rule in
+  the account's `OPERATIONS.md` `remits-policy` block, report its id, its `when`/`forbid`, and why your call
+  matched, then ask a person. Never generalize it ("syncs are impossible here"), and never drop your agent
+  identity to get past it. (`support-tickets.md`)
 - **A brief's `## Rules you will be held to` section is ENFORCED, not requested.** The platform refuses
   the verb and the message says what to do instead — act on that sentence rather than retrying or
   looking for another door. A `[require]` rule needs a person; hand off. (`support-tickets.md`)

package/skills/remits-cli/references/cli-state.md

@@ -76,13 +76,19 @@ Think about remits-cli as two cooperating layers:
      - where a large tool response was written
      - which tool schemas were most recently cached here
 
-Per-repo state has two independent namespaces:
+Per-repo state has two independent namespaces, and one identity sits beside them:
 
 - **Workspace** (`--workspace`, `REMITS_WORKSPACE`, `.remits-cli/workspace`) chooses the server-side
   Redis staging lane. It changes what staged entries a run resolves.
-- **Local actor** (`--local-agent`, `REMITS_AGENT_ID`, generated fallback) chooses the local filesystem
-  namespace under `.remits-cli/actors/<local-agent>/`. It changes where session logs, tool responses,
-  verification mirrors, and diagnostics are written.
+- **Local actor** (`--local-agent` / `--actor`, then `REMITS_AGENT_ID`, then `REMITS_LOCAL_AGENT_ID`, then a
+  generated fallback) chooses the local filesystem namespace under `.remits-cli/actors/<local-agent>/`. It
+  changes where session logs, tool responses, verification mirrors, and diagnostics are written. To name
+  only the folder, use `--local-agent` or `REMITS_LOCAL_AGENT_ID`.
+- **Agent identity** (`--agent-id`, then `REMITS_AGENT_ID`) is not local state. The CLI sends it to the
+  platform on every call (`X-Remits-Agent-Id` and the payload `agentId`), so the call is an `agent` to the
+  account's `remits-policy` rules, owns the tickets it claims, and is attributed to that agent. Without it
+  the call is the signed-in person. `REMITS_AGENT_ID` therefore does two jobs, folder and identity; an AI
+  agent should set it deliberately, as identity.
 
 Run `remits-cli doctor local-state` to print the active actor, state directory, workspace source,
 foreign actors, git-tracked `.remits-cli` files, legacy flat state, and large/suspicious logs.

package/skills/remits-cli/references/command-reference.md

@@ -284,10 +284,12 @@ remits-cli corpus retire --corpus <name> --case <caseKey> [--case ...] [--restor
 `test run` starts a server-side task immediately. By default the CLI process polls until the task is
 terminal; `--watch false` disables websocket progress streaming but still waits. Pass `--wait false` to
 return after launch with the task id. A single run with `--names "a|b|c"` selects cases into one suite task,
-and those cases execute sequentially in declaration order. To overlap independent slow cases, launch
-separate `remits-cli test run --names "<case>" --wait false` commands from the same staged lane and keep the
-printed task ids; complete each proof with `test status --task-id <id>`. Avoid parallel runs for cases that
-share mutable fixtures, suite-level side effects, or undeclared live AI/provider calls.
+and those cases execute sequentially by default. Test metadata `caseConcurrency` (1–16, default 1)
+enables native server workers. Explicit `--parallel N` overrides it; `--parallel 1` forces serial.
+Parent/group IDs work with `test status` and corpus commands; case results retain child task and trace IDs.
+Scheduled batches additionally accept `suiteConcurrency` (1–16, default 1) and overlap only suites marked
+`parallelSafe: true`; other suites run as exclusive barriers. Avoid concurrency for shared mutable
+fixtures or order-dependent setup. See the Test component guide's Configuring Parallel Execution section.
 
 ### Reading a failing run
 

package/skills/remits-cli/references/development-loop.md

@@ -430,8 +430,9 @@ id + content hash, platform sync vs local HEAD. If it is not the world you meant
 about a different world.
 
 The platform launch is asynchronous. By default `remits-cli test run` waits for its task to finish, and any
-cases selected by `--names "a|b"` execute sequentially inside that suite task. If several slow cases are
-independent, use `--parallel N`. It splits the selected cases across N shards that run side by side, and the run
+cases selected by `--names "a|b"` execute sequentially by default. A Test sidecar can set
+`caseConcurrency: 2` for native server workers, including scheduled runs. Explicit `--parallel N`
+overrides that setting (`--parallel 1` forces serial). It splits the selected cases across N shards that run side by side, and the run
 keeps ONE id (`grp-…`) for `test status` and every corpus command. An instance runs only a few suites at once
 (two by default), so shards beyond that wait for a slot. Ask for 2–4. Starting separate
 `test run --names "<case>" --wait false` commands also works for one-off proofs, but every such run is a separate