@mmerterden/multi-agent-pipeline 13.3.0 → 13.5.0

package/pipeline/scripts/phase0-exit-gate.mjs

@@ -14,6 +14,12 @@
  * and spacing guessed at 16 where the frame said `Spacing/12`. Half the commits on
  * that branch were rework.
  *
+ * A second run then showed the other half of the same failure: a Jira task was
+ * implemented without the repo or branch picker ever appearing, straight on whatever
+ * the local checkout was pointing at. Step 3 and Step 8 own those decisions, and
+ * `agent-state.json` is the only durable evidence they happened - so the gate asserts
+ * their output too, not just `taskType`.
+ *
  * A phase that reports success without its output is worse than one that fails:
  * every later phase then reasons from a field that is not there. So this is a
  * gate, not a lint  -  the spec already said what to write, and prose alone did
@@ -120,6 +126,52 @@ export function evaluate(state, extraInput = "") {
     );
   }
 
+  // Step 3 picks the base branch and Step 8 creates the worktree. A run that skipped
+  // both develops on whatever the checkout happened to have, which is how a Jira task
+  // got implemented on a stale local branch with no picker ever shown. The state file
+  // is the only durable evidence those steps ran, so it has to carry their output.
+  //
+  // `local` provider runs still choose a base branch; what they skip is push and PR.
+  // So this applies to every provider.
+  const baseBranch = typeof state.baseBranch === "string" ? state.baseBranch.trim() : "";
+  if (!baseBranch) {
+    failures.push(
+      "agent-state.json has no baseBranch. Step 3 asks for it (or takes it from the " +
+        "input); an unset value means the branch picker never ran and development " +
+        "happens on whatever the checkout was already pointing at.",
+    );
+  }
+
+  // Which ref the base actually came from. Without it, "built on a fresh origin ref"
+  // and "built on a month-old local branch" are indistinguishable after the fact -
+  // and the fetch-failure picker exists precisely to make that an explicit choice.
+  const fetchStatus = typeof state.baseFetchStatus === "string" ? state.baseFetchStatus.trim() : "";
+  const FETCH_STATES = ["fresh", "cached-stale", "local-branch", "aborted"];
+  if (baseBranch && !FETCH_STATES.includes(fetchStatus)) {
+    failures.push(
+      `agent-state.json has baseFetchStatus="${fetchStatus || "<unset>"}"; Step 3 must ` +
+        `record one of ${FETCH_STATES.join(" | ")}. An unset value means nothing ` +
+        `established whether the base ref was fetched or reused from a stale cache.`,
+    );
+  }
+
+  // Worktree isolation is a standing rule: never develop in the primary checkout.
+  const worktree = typeof state.worktreePath === "string" ? state.worktreePath.trim() : "";
+  const projectRoot = typeof state.projectRoot === "string" ? state.projectRoot.trim() : "";
+  if (!worktree && !projectRoot) {
+    failures.push(
+      "agent-state.json records neither worktreePath nor projectRoot. Step 8 creates " +
+        "the worktree; with no recorded path, later phases cannot tell which tree they " +
+        "are meant to edit and default to the current directory.",
+    );
+  }
+  if (worktree && projectRoot && worktree === projectRoot) {
+    failures.push(
+      `worktreePath equals projectRoot (${worktree}). Development must happen in a ` +
+        `separate worktree, never in the primary checkout.`,
+    );
+  }
+
   // The Figma access chain records which tier answered. A component task with no
   // recorded tier means nothing verified that the design was actually reachable,
   // which is how a run ends up guessing spacing.

package/pipeline/scripts/uninstall.mjs

@@ -38,6 +38,7 @@
 import { existsSync, readdirSync, readFileSync, rmSync, writeFileSync } from "fs";
 import { execFileSync } from "child_process";
 import { join } from "path";
+import { homedir } from "os";
 import { pathToFileURL } from "url";
 import { createInterface } from "readline";
 
@@ -157,21 +158,38 @@ function removeGeneratedCodexAgents(agentsDir) {
  * uninstall failure. Never edits `config.toml` directly - Codex keeps
  * marketplace and plugin state in the same file.
  */
-function deregisterCodexMcpServer() {
+function deregisterMcpServer(host, cliPath) {
+  const cli = cliPath || host;
   if (dryRun) {
-    report("would run", "codex mcp remove dev-toolkit");
+    report("would run", `${host} mcp remove dev-toolkit`);
     return;
   }
   try {
-    execFileSync("codex", ["mcp", "remove", "dev-toolkit"], { stdio: "pipe", timeout: 20_000 });
-    console.log("    removed: dev-toolkit MCP registration");
+    execFileSync(cli, ["mcp", "remove", "dev-toolkit"], { stdio: "pipe", timeout: 20_000 });
+    console.log(`    removed: dev-toolkit MCP registration (${host})`);
   } catch {
     console.log(
-      "    note: could not run `codex mcp remove dev-toolkit` (codex not on PATH, or not registered)",
+      `    note: could not run \`${host} mcp remove dev-toolkit\` (${host} not on PATH, or not registered)`,
     );
   }
 }
 
+function deregisterCodexMcpServer() {
+  deregisterMcpServer("codex");
+}
+
+/**
+ * Copilot registers the same server, so leaving it behind would keep a stale entry
+ * pointing at a package the user just removed.
+ *
+ * `copilot` is often a shell alias for `gh copilot`, invisible to execFileSync, so the
+ * real binary path is tried when the bare name is not resolvable.
+ */
+function deregisterCopilotMcpServer() {
+  const ghCopilot = join(homedir(), ".local", "share", "gh", "copilot", "copilot");
+  deregisterMcpServer("copilot", existsSync(ghCopilot) ? ghCopilot : undefined);
+}
+
 /**
  * Remove every directory under `parent` whose name matches a predicate.
  * @param {string} parent
@@ -475,6 +493,7 @@ export async function main() {
   if (forCopilot && HOME) {
     console.log("");
     console.log("  [Copilot CLI] Removing...");
+    deregisterCopilotMcpServer();
     const COP = join(HOME, ".copilot");
     rmIfExists(join(COP, "scripts"));
     // Pipeline-managed trees the installer lays down alongside scripts/.

package/pipeline/skills/shared/core/multi-agent/SKILL.md

@@ -336,6 +336,25 @@ Full contract: `refs/tracker-contract.md` section "TaskCreate ordering (strict)"
 > 6. **Branch name confirm**  -  `feature/PROJ-{id}-{kebab}` or `bugfix/...`  -  user confirms or edits. In multi-repo mode the branch name is shared across all selected repos (collision check runs per-repo; any collision applies the suffix to all). (Step 4)
 > 7. **Git identity  -  per repo**  -  route via `prefs.global.platformIdentityRouting`; ask if ambiguous. Multi-repo mode resolves identity **per repo independently** (phase-0-init.md L283). (Step 6)
 > 8. **Instruction files + workspace creation  -  serially per repo**  -  detect `.instructions/figma/` etc. In multi-repo mode, worktree creation loops per repo serially (phase-0-init.md L308); any failure rolls back previously-created worktrees. Write `agent-state.json` with `state.projects[]` array (scalar `project`/`projectRoot`/`branch` mirror `projects[0]` for back-compat). (Steps 7-8)
+>
+> **Exit gate (BLOCKING).** The contract above was prose only, and a run still took a
+> Jira ID and implemented straight onto the local checkout with no picker shown. Before
+> marking Phase 0 completed:
+>
+> ```bash
+> node "$HOME/.copilot/scripts/phase0-exit-gate.mjs" "$TASK_ID" --input "$USER_INPUT"
+> ```
+>
+> Non-zero means Phase 0 did not produce its own output - `taskType`, `baseBranch`,
+> `baseFetchStatus`, a worktree path distinct from the project root, and a recorded Figma
+> access tier when the input carries a Figma URL. Fix the missing step; do not proceed.
+>
+> **Credential inventory (Step 0).** Run
+> `bash "$HOME/.copilot/lib/credential-inventory.sh" --json` and store the result in
+> `agent-state.json.credentialInventory`. Per `refs/keychain.md` Rule 2, never ask the
+> user for data a mapped credential can fetch: a run asked for a hand-pasted Crashlytics
+> stack trace while a valid Firebase service account was mapped and resolving. Ask for
+> the pointer (the issue URL) instead, and say what you will do with it.
 
 **Step 1  -  Project detection + input parsing:**