opencode-swarm 7.109.4 → 7.110.0

package/.opencode/skills/swarm-pr-feedback/SKILL.md

@@ -6,7 +6,10 @@ description: >
   requested changes, CI/check failures, merge conflicts, stale PR branches, or
   PR follow-up work that must close all known issues without dropping findings.
   Supports multi-round bot reviews (the repository's bot posts a new review
-  after every push) via the iterative pattern documented in the body.
+  after every push) via the iterative pattern documented in the body. Stage A
+  (structural pre-checks) and Stage B (reviewer + test_engineer) gates and the
+  reviewer + critic closeout gate are MANDATORY for any change made as part of
+  this process.
 ---
 
 # Swarm PR Feedback
@@ -16,6 +19,12 @@ Use this skill to close known PR feedback. This is not a fresh broad PR review.
 feedback surfaces, verifies each claim, clusters related problems, fixes confirmed
 issues, validates the branch, and reports closure status for every item.
 
+**Mandatory gate contract.** Stage A (structural pre-checks) and Stage B
+(reviewer + test_engineer) gates and the reviewer + critic closeout gate are
+MANDATORY for any change made as part of this process. No fix lands, no closure
+ledger row is marked FIXED, and no PR is published until all three gates pass on
+the current diff. See "Mandatory Gates" below for the full protocol.
+
 When the work starts from a prior `swarm-pr-review` run, ingest the review's
 handoff artifact (for example
 `.swarm/pr-review/<run_id>/feedback-handoff.md` or `.json`) before triage.
@@ -188,11 +197,11 @@ tree:
   filesystem (`Read`/`Glob`/`Grep`), and fixes must land on the PR branch — without a
   checkout you would verify and patch the base branch's code instead. Record the
   `base_ref..head_ref` range for diff-scoped inspection.
-- Pass the `base_ref..head_ref` commit range in every read-only verification or
-  explorer/advisory-lane delegation so lane agents can inspect specific revisions
-  with `git show` when needed.
+ - Pass the `base_ref..head_ref` commit range in every read-only verification or
+   explorer/advisory-lane delegation so lane agents can inspect specific revisions
+   with `git show` when needed.
 - If no PR reference was provided (a pasted-feedback session on the current branch),
-  confirm the current branch is the intended PR branch before editing.
+   confirm the current branch is the intended PR branch before editing.
 
 When a verification lane result includes `output_ref`, treat `output` as a
 preview and call `retrieve_lane_output` before using it to classify, resolve,
@@ -481,25 +490,85 @@ or compatibility policy, mark the item `NEEDS_USER_DECISION` and ask.
   and let the merge queue perform final current-base validation. Still resolve real
   merge conflicts and SHA-dependent review threads before queuing.
 
-## Validation
+## Mandatory Gates
+
+**Stage A and Stage B gates and the reviewer + critic closeout gate are
+MANDATORY for any change made as part of the PR-feedback process.** No fix
+lands, no closure ledger row is marked FIXED, and no PR is published until all
+three gates pass on the current diff. This section uses the repository's
+established Stage A/B meaning: Stage A = `pre_check_batch`-equivalent structural
+pre-checks; Stage B = `reviewer` + `test_engineer` per-task gates (consistent
+with `execute`, `plan`, `specify`, `brainstorm`, `docs/swarm-briefing.md`, and
+`docs/council/README.md`).
+
+If a gate failure is suspected pre-existing, prove it on the base branch or
+label it `UNVERIFIED`. Do not call the branch green while required checks are
+non-green.
+
+### Stage A — structural pre-checks (mandatory before Stage B)
+
+Run for every changed surface. No "where relevant" — every PR-feedback change
+runs these; if a surface is genuinely untouched, state that explicitly rather
+than skipping silently.
+
+- `bun run build` (or the repository's build command) — must succeed.
+- typecheck — must pass.
+- lint/format (e.g. `biome ci .`) — must pass.
+- `git diff --check` — no whitespace or merge-marker errors.
+- exact failing CI/test command reproduced locally when a ledger item is rooted
+  in a CI/test failure — the reproduction must fail on the pre-fix tree and pass
+  after the fix.
+
+### Stage B — reviewer + test_engineer (mandatory after Stage A passes)
+
+Two independent agents on the Stage-A-green diff:
+
+- **reviewer** — independent (fresh context, not the implementer, not a continued
+  conversation). Validates each fix on the current diff against the feedback
+  item it closes. Verdict per item: APPROVE / NEEDS_REVISION / BLOCKED.
+- **test_engineer** — writes and runs the falsification probe or regression test
+  that proves each fix actually resolves its item (tests for changed behavior or
+  newly covered gaps). Verdict per item: PASS / FAIL / BLOCKED.
 
-Run targeted validation for every changed surface:
+Address every NEEDS_REVISION / BLOCKED / FAIL, then re-run the affected agent on
+the current diff.
 
-- exact failing CI/test command when reproducing a failure,
-- tests for changed behavior or newly covered gaps,
-- lint/format/typecheck/build where relevant,
-- `git diff --check`,
-- PR metadata checks after push: head SHA, check status, mergeability/conflicts,
-  and unresolved feedback state.
+### Closeout gate — reviewer + critic (mandatory after Stage B)
+
+A *separate* reviewer + critic pair on the Stage-B-approved diff. This is the
+swarm closeout contract (see `../swarm/SKILL.md` "Mandatory implementation
+closeout gate"); because this skill edits code, docs, release notes, or skill files it applies in full — Stage B
+alone does not satisfy it.
+
+- **independent reviewer** (fresh context, separate from the Stage B reviewer)
+  → APPROVE / NEEDS_REVISION / BLOCKED per item.
+- **final critic** (separate fresh context, not a continued conversation with
+  the reviewer, dispatched after the reviewer returns APPROVE) → APPROVE /
+  NEEDS_REVISION / BLOCKED per item. The critic challenges: is every original
+  feedback item actually resolved? Any requirement drift, weak evidence, missing
+  sibling-file checks, stale approvals, anything unwired or silently deferred?
+
+Address every NEEDS_REVISION / BLOCKED item, re-review with the reviewer if the
+critic surfaces correctness issues, then re-critic. **Any edit after the
+reviewer's or critic's approval invalidates that approval** — re-run the
+affected gate on the current diff before publishing.
+
+Record both closeout verdicts (reviewer + critic, with HEAD/diff) in
+`.claude/session/tasks/<slug>/gates.md` per the `durable-session-state` skill
+(`.swarm/` is the plugin's runtime state — never write task artifacts there).
+
+### Post-publish verification (mandatory after the PR is pushed)
+
+These checks run after the fix lands on the remote — they are NOT Stage A
+pre-checks and must not be folded into Stage A.
+
+- PR metadata checks after push: head SHA, check status,
+  mergeability/conflicts, and unresolved feedback state.
 - After conflict fixes, verify remote mergeability is clean (`MERGEABLE` /
   `CLEAN`), not only that local conflict markers disappeared.
 - For current-head CI, prefer run-level details when PR checks look stale:
   `gh run view <run-id> --json headSha,status,conclusion,jobs,url`.
 
-If a validation failure is suspected pre-existing, prove it on the base branch or
-label it `UNVERIFIED`. Do not call the branch green while required checks are
-non-green.
-
 ## Publishing And Communication
 
 After fixes, update the PR body or comment with a closure ledger:

package/dist/cli/{curator-zn1kmwmz.js → curator-4qqzpd85.js}

@@ -11,7 +11,7 @@ import {
   runCuratorInit,
   runCuratorPhase,
   writeCuratorSummary
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/cli/{curator-llm-factory-3hf9xpnd.js → curator-llm-factory-y4kvr1ph.js}

@@ -1,7 +1,7 @@
 // @bun
 import {
   createCuratorLLMDelegate
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/cli/{guardrail-explain-hjz1k6w0.js → guardrail-explain-10hh57cr.js}

@@ -1,8 +1,8 @@
 // @bun
 import {
   handleGuardrailExplain
-} from "./index-zh3qh6m7.js";
-import"./index-y3nx3ss0.js";
+} from "./index-xhsba2sn.js";
+import"./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/cli/{hive-promoter-j81yj97d.js → hive-promoter-wvxqyayt.js}

@@ -5,7 +5,7 @@ import {
   isHiveEligible,
   promoteFromSwarm,
   promoteToHive
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/cli/{index-y3nx3ss0.js → index-1mc2yfc2.js}

@@ -5008,8 +5008,10 @@ var BUNDLED_PROJECT_SKILLS = [
   "swarm-implement",
   "design-docs",
   "swarm-pr-review",
+  "swarm",
   "swarm-pr-feedback",
   "swarm-pr-subscribe",
+  "swarm-ci-monitor",
   "issue-ingest",
   "plan",
   "critic-gate",
@@ -7269,11 +7271,11 @@ var _internals7 = {
     return KnowledgeConfigSchema2.parse({});
   },
   applyCuratorKnowledgeUpdates: async (directory, recommendations, knowledgeConfig) => {
-    const { applyCuratorKnowledgeUpdates } = await import("./curator-zn1kmwmz.js");
+    const { applyCuratorKnowledgeUpdates } = await import("./curator-4qqzpd85.js");
     return applyCuratorKnowledgeUpdates(directory, recommendations, knowledgeConfig);
   },
   checkHivePromotions: async (entries, knowledgeConfig) => {
-    const { checkHivePromotions } = await import("./hive-promoter-j81yj97d.js");
+    const { checkHivePromotions } = await import("./hive-promoter-wvxqyayt.js");
     return checkHivePromotions(entries, knowledgeConfig);
   },
   applyProposalTriage: async (directory, triage) => {
@@ -16647,8 +16649,8 @@ var _internals21 = {
   loadCuratorDeps: async () => {
     const [{ CuratorConfigSchema }, curator, { createCuratorLLMDelegate: createCuratorLLMDelegate2 }] = await Promise.all([
       import("./schema-5vmb5dh8.js"),
-      import("./curator-zn1kmwmz.js"),
-      import("./curator-llm-factory-3hf9xpnd.js")
+      import("./curator-4qqzpd85.js"),
+      import("./curator-llm-factory-y4kvr1ph.js")
     ]);
     return { CuratorConfigSchema, curator, createCuratorLLMDelegate: createCuratorLLMDelegate2 };
   }
@@ -17144,7 +17146,7 @@ import { fileURLToPath } from "url";
 // package.json
 var package_default = {
   name: "opencode-swarm",
-  version: "7.109.4",
+  version: "7.110.0",
   description: "Architect-centric agentic swarm plugin for OpenCode - hub-and-spoke orchestration with SME consultation, code generation, and QA review",
   main: "dist/index.js",
   types: "dist/index.d.ts",
@@ -17199,8 +17201,10 @@ var package_default = {
     ".opencode/skills/swarm-implement",
     ".opencode/skills/design-docs",
     ".opencode/skills/swarm-pr-review",
+    ".opencode/skills/swarm",
     ".opencode/skills/swarm-pr-feedback",
     ".opencode/skills/swarm-pr-subscribe",
+    ".opencode/skills/swarm-ci-monitor",
     ".opencode/skills/issue-ingest",
     ".opencode/skills/plan",
     ".opencode/skills/critic-gate",
@@ -31867,7 +31871,7 @@ function buildDetailedHelp(commandName, entry) {
 async function handleHelpCommand(ctx) {
   const targetCommand = ctx.args.join(" ");
   if (!targetCommand) {
-    const { buildHelpText } = await import("./index-nvmy7xmj.js");
+    const { buildHelpText } = await import("./index-khj0knr0.js");
     return buildHelpText();
   }
   const tokens = targetCommand.split(/\s+/);
@@ -31876,7 +31880,7 @@ async function handleHelpCommand(ctx) {
     return _internals46.buildDetailedHelp(resolved.key, resolved.entry);
   }
   const similar = _internals46.findSimilarCommands(targetCommand);
-  const { buildHelpText: fullHelp } = await import("./index-nvmy7xmj.js");
+  const { buildHelpText: fullHelp } = await import("./index-khj0knr0.js");
   if (similar.length > 0) {
     return `Command '/swarm ${targetCommand}' not found.
 
@@ -32009,7 +32013,7 @@ var COMMAND_REGISTRY = {
   },
   "guardrail explain": {
     handler: async (ctx) => {
-      const { handleGuardrailExplain } = await import("./guardrail-explain-hjz1k6w0.js");
+      const { handleGuardrailExplain } = await import("./guardrail-explain-10hh57cr.js");
       return handleGuardrailExplain(ctx.directory, ctx.args);
     },
     description: "Dry-run: show what the guardrails would do to a command or write target (executes nothing)",

package/dist/cli/{index-nvmy7xmj.js → index-khj0knr0.js}

@@ -1,7 +1,7 @@
 // @bun
 import {
   handleGuardrailExplain
-} from "./index-zh3qh6m7.js";
+} from "./index-xhsba2sn.js";
 import {
   handleGuardrailLog
 } from "./index-p5vm9gy9.js";
@@ -80,7 +80,7 @@ import {
   handleWriteRetroCommand,
   normalizeSwarmCommandInput,
   resolveCommand
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/cli/{index-zh3qh6m7.js → index-xhsba2sn.js}

@@ -12,7 +12,7 @@ import {
   detectPosixWrites,
   detectWindowsWrites,
   resolveWriteTargets
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import {
   checkFileAuthority,
   classifyFile,

package/dist/cli/index.js

@@ -7,7 +7,7 @@ import {
   getPluginLockFilePaths,
   package_default,
   resolveCommand
-} from "./index-y3nx3ss0.js";
+} from "./index-1mc2yfc2.js";
 import"./index-d3txrx5q.js";
 import"./index-mtzjbaaa.js";
 import"./index-c8s9a3zh.js";

package/dist/config/bundled-skills.d.ts

@@ -1,4 +1,4 @@
-export declare const BUNDLED_PROJECT_SKILLS: readonly ["brainstorm", "specify", "clarify-spec", "resume", "clarify", "discover", "consult", "pre-phase-briefing", "council", "deep-dive", "deep-research", "codebase-review-swarm", "swarm-implement", "design-docs", "swarm-pr-review", "swarm-pr-feedback", "swarm-pr-subscribe", "issue-ingest", "plan", "critic-gate", "execute", "phase-wrap", "loop", "writing-tests", "running-tests", "engineering-conventions", "commit-pr", "worktree-retry-cleanup", "skill-edit-validation", "merge-queue-readiness", "gate-attribution", "ci-failure-batching"];
+export declare const BUNDLED_PROJECT_SKILLS: readonly ["brainstorm", "specify", "clarify-spec", "resume", "clarify", "discover", "consult", "pre-phase-briefing", "council", "deep-dive", "deep-research", "codebase-review-swarm", "swarm-implement", "design-docs", "swarm-pr-review", "swarm", "swarm-pr-feedback", "swarm-pr-subscribe", "swarm-ci-monitor", "issue-ingest", "plan", "critic-gate", "execute", "phase-wrap", "loop", "writing-tests", "running-tests", "engineering-conventions", "commit-pr", "worktree-retry-cleanup", "skill-edit-validation", "merge-queue-readiness", "gate-attribution", "ci-failure-batching"];
 interface CopyState {
     files: number;
     bytes: number;