opencode-swarm 7.78.7 → 7.78.8

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

@@ -142,6 +142,42 @@ Build a complete feedback ledger before editing. Include every available source:
 If a source is unavailable, record that limitation. Do not treat missing access as
 evidence that no feedback exists.
 
+### CI matrix cascade check (do this before fixing)
+
+When the PR's `unit` job is a matrix across multiple OSes and downstream jobs
+(`integration`, `smoke`) have `needs: unit`, an OS leg failure blocks the
+entire pipeline. Before triaging, check:
+
+1. Are `integration` or `smoke` jobs in `skipped` or `cancelled` state rather
+   than `failed`? That signals a unit matrix cascade — the unit job failed
+   on one OS leg, blocking the downstream jobs from running on the current
+   HEAD.
+2. If a unit OS leg is the blocker, classify the failure:
+   - **Code issue** — the test itself fails. Reproduce locally; if the
+     test passes locally, the runner is the problem.
+   - **Runner performance** — the test step exceeds the configured timeout.
+     Run all files in the step locally with per-file timing; if cumulative
+     local runtime is <10 min and the runner can't complete in 60+ min, the
+     issue is runner performance. Bump the CI timeout as a stopgap and file
+     a follow-up issue for parallelization. Do not loop bumping the timeout
+     past 90 min without filing the follow-up.
+3. Surface cascade failures to the user explicitly. The downstream jobs'
+   results don't exist; the code's coverage of the current HEAD cannot be
+   confirmed by CI alone.
+
+### PR body claim verification
+
+PR body text like "PHASE 2 council APPROVED (5/5, round 2)" or "Final council
+APPROVED" must be backed by an evidence file in `.swarm/evidence/`
+(typically `phase-council.json` or `final-council.json`). Bot-generated PR
+bodies commonly auto-fill these claims without real review. Before accepting
+such a claim as part of triage:
+
+1. Check whether the corresponding evidence file exists with `verdict:APPROVED`.
+2. If the claim is unsupported, mark the closure ledger item as
+   `NEEDS_MORE_EVIDENCE` rather than `CONFIRMED`. Do not silently drop the
+   claim — it indicates the PR body was generated without a real review.
+
 ## Feedback Ledger
 
 Normalize each item before triage:
@@ -163,6 +199,59 @@ Rules:
   `CONFLICT-001` for merge/base drift and `CI-001` for check failures, so PR
   bodies can show exactly how operational blockers were closed.
 
+### Mandatory: integrate all PR comments with feedback or findings before validation
+
+**Before the Verification step begins, every PR comment that contains feedback
+or findings MUST be integrated into the total feedback ledger as a
+`FB-###` item.** This is a hard requirement, not a best-effort step.
+
+What counts as "feedback or findings":
+- A reviewer request for a code change ("please rename this", "add a test for
+  X", "this should call `_internals.foo`")
+- A reviewer claim about correctness, security, or style ("this is
+  incorrect", "X will leak")
+- A bot reviewer's findings table entries
+- A CI failure with a specific file:line root cause
+- A reviewer question that implies a code change is needed ("why is this
+  static?")
+- PR review summaries or aggregate comments
+
+What does NOT count (and is therefore not required to be a ledger item):
+- Pure acknowledgements ("LGTM", "looks good")
+- PR-level metadata changes (title, label, milestone)
+- Force-push acknowledgements
+
+Rules:
+- **No finding may be addressed outside the ledger.** If you fix something a
+  reviewer mentioned, the corresponding `FB-###` item MUST be in the ledger
+  before the fix. If you skip the fix, the `FB-###` item MUST be in the
+  ledger with a `DISPROVED`, `PRE_EXISTING`, `NEEDS_MORE_EVIDENCE`, or
+  `NEEDS_USER_DECISION` status before validation can begin.
+- **Status semantics for unaddressed items:**
+  - `CONFIRMED` and `PARTIAL` items must be addressed (fixed or
+    disproved) before validation can begin. A `CONFIRMED` item that is
+    left unaddressed is a regression against the review.
+  - `DISPROVED`, `PRE_EXISTING`, `NEEDS_MORE_EVIDENCE`, and
+    `NEEDS_USER_DECISION` items may remain open at validation time, but
+    each must be explicitly justified in the closure ledger.
+- **The closure ledger at the end of the run must account for every `FB-###`
+  item** with a final status (fixed / disproved / pre-existing / needs user
+  decision / needs more evidence).
+- **Comments from the latest bot round take precedence over earlier rounds**
+  for the same finding; the earlier-round `FB-###` item is updated with the
+  new evidence rather than a new item being created.
+- **Multi-round pattern continues to apply** (see "Multi-Round Bot Reviews"
+  section). A new bot round adds new `FB-###` items for findings that
+  weren't in the prior round; the prior round's items are carried forward
+  and updated with the new evidence.
+
+Rationale: silently addressing a review comment without a corresponding
+ledger item means the closure summary at the end of the run cannot
+demonstrate that every review comment was considered. The closure summary
+is the only artifact the user/maintainer reads to confirm the PR is ready
+to merge. Missing items in the ledger = missing items in the closure = a
+PR that ships with unreviewed feedback.
+
 ## Verification
 
 Classify every ledger item before fixing:
@@ -173,6 +262,7 @@ Classify every ledger item before fixing:
 | `PARTIAL` | The comment points at a real concern, but the framing, severity, or requested fix is incomplete. |
 | `DISPROVED` | Source, tests, or execution context prove the claim is false, unreachable, or already mitigated. |
 | `PRE_EXISTING` | The issue exists on the base branch and is not materially worsened by the PR. |
+| `NEEDS_MORE_EVIDENCE` | The claim (e.g., "council APPROVED") is unsupported by stored evidence (e.g., a missing or failed `.swarm/evidence/` artifact); more information is required before triage. |
 | `NEEDS_USER_DECISION` | The item requires a product, UX, compatibility, or scope choice that cannot be inferred. |
 
 Verification checklist:
@@ -184,6 +274,26 @@ Verification checklist:
 - Check related tests and whether a failing/proposed test would prove the item.
 - Check whether multiple feedback items share one root cause.
 
+### DI seam migration validation
+
+When a test file mutates a DI seam object (e.g., `_internals.foo = mock`),
+verify that the production source reads from the seam at call time. A common
+anti-pattern: the test mutates the seam object, but the production code
+imports the named function (`import { foo } from './module'`) which is bound
+at module load. The seam mutation has no effect on the named reference,
+so the test fails even though the seam object's `foo === mock`.
+
+Verification: open the source file and grep for call sites. If you see
+`import { foo } from '...'` followed by `foo(...)` in the production code,
+and the test does `_internals.foo = mock`, the test will fail. The fix is
+to change the production code to call `_internals.foo(...)` (or equivalent
+active-seam pattern) so the seam mutation is read at call time.
+
+If only a few call sites exist, fix them in the source. If many call sites
+exist, consider whether the migration should use `mock.module()` instead,
+which replaces the entire module object (including the named export
+reference).
+
 ## Fix Planning
 
 Cluster ledger items by root cause before coding. Fix in this order unless a user
@@ -251,6 +361,7 @@ FB-001 | fixed | commit/test evidence
 FB-002 | disproved | code evidence
 FB-003 | pre-existing | base-branch evidence
 FB-004 | needs user decision | decision required
+FB-005 | needs more evidence | .swarm/evidence/phase-council.json missing
 CONFLICT-001 | fixed | remote mergeability is MERGEABLE/CLEAN
 CI-001 | fixed | current-head check/run evidence
 ```

package/README.md

@@ -1107,7 +1107,7 @@ Control how tool outputs are summarized for LLM context.
 | `/swarm deep-dive <scope> [--profile <name>] [--max-explorers <n>]` | Read-only codebase audit with parallel explorers, dual reviewers, and critic challenge |
 | `/swarm design-docs <description> [--out <dir>] [--lang <name>] [--update]` | Generate or sync language-agnostic design docs (requires `design_docs.enabled`) |
 | `/swarm dark-matter` | Detect hidden file couplings from co-change history |
-| `/swarm finalize [--prune-branches] [--skill-review]` | Idempotent session close-out: retrospectives, lesson curation, evidence archive, context.md reset, config-backup cleanup, optional branch pruning, optional skill-improver proposal |
+| `/swarm finalize [--prune-branches] [--skill-review]` | Idempotent session close-out: retrospectives, lesson curation, evidence archive, git reset --hard + clean to align with remote branch (discards uncommitted changes), optional branch pruning, optional skill-improver proposal |
 | `/swarm close [--prune-branches] [--skill-review]` | Deprecated alias for `/swarm finalize [--prune-branches] [--skill-review]` |
 | `/swarm write-retro` | Write a phase retrospective manually |
 | `/swarm handoff` | Generate a handoff summary for context-budget-critical sessions |

package/dist/cli/index.js

@@ -52,7 +52,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "opencode-swarm",
-    version: "7.78.7",
+    version: "7.78.8",
     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",
@@ -37020,15 +37020,19 @@ function writeCheckpointLog(log2, directory) {
   fs9.writeFileSync(tempPath, JSON.stringify(log2, null, 2), "utf-8");
   fs9.renameSync(tempPath, logPath);
 }
-function gitExec(args) {
+function gitExec(args, cwd) {
   const result = child_process.spawnSync("git", args, {
+    cwd,
     encoding: "utf-8",
     timeout: GIT_TIMEOUT_MS,
-    stdio: ["pipe", "pipe", "pipe"]
+    stdio: ["ignore", "pipe", "pipe"],
+    windowsHide: true
   });
+  if (result.error) {
+    throw new Error(`git failed to start: ${result.error.code ?? "unknown"} \u2014 ${result.error.message}`);
+  }
   if (result.status !== 0) {
-    const err = new Error(result.stderr?.trim() || `git exited with code ${result.status}`);
-    throw err;
+    throw new Error(result.stderr?.trim() || `git exited with code ${result.status}`);
   }
   return result.stdout;
 }
@@ -37040,13 +37044,13 @@ function appendRetentionEvent(directory, event) {
     fs9.appendFileSync(eventsPath, line);
   } catch {}
 }
-function getCurrentSha() {
-  const output = gitExec(["rev-parse", "HEAD"]);
+function getCurrentSha(directory) {
+  const output = gitExec(["rev-parse", "HEAD"], directory);
   return output.trim();
 }
-function isGitRepo() {
+function isGitRepo(directory) {
   try {
-    gitExec(["rev-parse", "--git-dir"]);
+    gitExec(["rev-parse", "--git-dir"], directory);
     return true;
   } catch {
     return false;
@@ -37071,21 +37075,21 @@ function handleSave(label, directory) {
       }, null, 2);
     }
     const timestamp = new Date().toISOString();
-    gitExec(["add", "--all", "--", ":!.swarm/"]);
+    gitExec(["add", "--all", "--", ":!.swarm/"], directory);
     const hasStagedChanges = (() => {
       try {
-        gitExec(["diff", "--cached", "--quiet"]);
+        gitExec(["diff", "--cached", "--quiet"], directory);
         return false;
       } catch {
         return true;
       }
     })();
     if (hasStagedChanges) {
-      gitExec(["commit", "-m", `checkpoint: ${label}`]);
+      gitExec(["commit", "-m", `checkpoint: ${label}`], directory);
     } else if (allowEmptyCommits) {
-      gitExec(["commit", "--allow-empty", "-m", `checkpoint: ${label}`]);
+      gitExec(["commit", "--allow-empty", "-m", `checkpoint: ${label}`], directory);
     }
-    const newSha = getCurrentSha();
+    const newSha = getCurrentSha(directory);
     log2.checkpoints.push({
       label,
       sha: newSha,
@@ -37130,7 +37134,7 @@ function handleRestore(label, directory) {
         error: `checkpoint not found: "${label}"`
       }, null, 2);
     }
-    gitExec(["reset", "--soft", checkpoint.sha]);
+    gitExec(["reset", "--soft", checkpoint.sha], directory);
     return JSON.stringify({
       action: "restore",
       success: true,
@@ -37201,7 +37205,7 @@ var init_checkpoint = __esm(() => {
       label: exports_external.string().optional().describe("Checkpoint label (required for save, restore, delete)")
     },
     execute: async (args, directory) => {
-      if (!isGitRepo()) {
+      if (!isGitRepo(directory)) {
         return JSON.stringify({
           action: "unknown",
           success: false,
@@ -67722,7 +67726,7 @@ var init_registry = __esm(() => {
         sessionID: ctx.sessionID
       }),
       description: "Use /swarm finalize to finalize the swarm project and archive evidence",
-      details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs safe git ff-only to main. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.",
+      details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs aggressive git reset --hard to the default remote branch, discarding uncommitted changes and untracked files; falls back to a cautious reset that preserves uncommitted changes when the aggressive path cannot proceed. WARNING: alignment discards local changes and untracked files. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.",
       args: "--prune-branches, --skill-review",
       category: "core",
       toolPolicy: "none"

package/dist/commands/registry.d.ts

@@ -312,7 +312,7 @@ export declare const COMMAND_REGISTRY: {
     readonly finalize: {
         readonly handler: (ctx: CommandContext) => Promise<string>;
         readonly description: "Use /swarm finalize to finalize the swarm project and archive evidence";
-        readonly details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs safe git ff-only to main. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.";
+        readonly details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs aggressive git reset --hard to the default remote branch, discarding uncommitted changes and untracked files; falls back to a cautious reset that preserves uncommitted changes when the aggressive path cannot proceed. WARNING: alignment discards local changes and untracked files. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.";
         readonly args: "--prune-branches, --skill-review";
         readonly category: "core";
         readonly toolPolicy: "none";

package/dist/index.js

@@ -69,7 +69,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "opencode-swarm",
-    version: "7.78.7",
+    version: "7.78.8",
     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",
@@ -58440,15 +58440,19 @@ function writeCheckpointLog(log2, directory) {
   fs19.writeFileSync(tempPath, JSON.stringify(log2, null, 2), "utf-8");
   fs19.renameSync(tempPath, logPath);
 }
-function gitExec(args2) {
+function gitExec(args2, cwd) {
   const result = child_process.spawnSync("git", args2, {
+    cwd,
     encoding: "utf-8",
     timeout: GIT_TIMEOUT_MS,
-    stdio: ["pipe", "pipe", "pipe"]
+    stdio: ["ignore", "pipe", "pipe"],
+    windowsHide: true
   });
+  if (result.error) {
+    throw new Error(`git failed to start: ${result.error.code ?? "unknown"} — ${result.error.message}`);
+  }
   if (result.status !== 0) {
-    const err2 = new Error(result.stderr?.trim() || `git exited with code ${result.status}`);
-    throw err2;
+    throw new Error(result.stderr?.trim() || `git exited with code ${result.status}`);
   }
   return result.stdout;
 }
@@ -58460,13 +58464,13 @@ function appendRetentionEvent(directory, event) {
     fs19.appendFileSync(eventsPath, line);
   } catch {}
 }
-function getCurrentSha() {
-  const output = gitExec(["rev-parse", "HEAD"]);
+function getCurrentSha(directory) {
+  const output = gitExec(["rev-parse", "HEAD"], directory);
   return output.trim();
 }
-function isGitRepo() {
+function isGitRepo(directory) {
   try {
-    gitExec(["rev-parse", "--git-dir"]);
+    gitExec(["rev-parse", "--git-dir"], directory);
     return true;
   } catch {
     return false;
@@ -58491,21 +58495,21 @@ function handleSave(label, directory) {
       }, null, 2);
     }
     const timestamp = new Date().toISOString();
-    gitExec(["add", "--all", "--", ":!.swarm/"]);
+    gitExec(["add", "--all", "--", ":!.swarm/"], directory);
     const hasStagedChanges = (() => {
       try {
-        gitExec(["diff", "--cached", "--quiet"]);
+        gitExec(["diff", "--cached", "--quiet"], directory);
         return false;
       } catch {
         return true;
       }
     })();
     if (hasStagedChanges) {
-      gitExec(["commit", "-m", `checkpoint: ${label}`]);
+      gitExec(["commit", "-m", `checkpoint: ${label}`], directory);
     } else if (allowEmptyCommits) {
-      gitExec(["commit", "--allow-empty", "-m", `checkpoint: ${label}`]);
+      gitExec(["commit", "--allow-empty", "-m", `checkpoint: ${label}`], directory);
     }
-    const newSha = getCurrentSha();
+    const newSha = getCurrentSha(directory);
     log2.checkpoints.push({
       label,
       sha: newSha,
@@ -58550,9 +58554,9 @@ function saveCheckpointRecord(label, directory) {
       return { success: false, error: `duplicate label: "${label}"` };
     }
     let sha = "";
-    if (isGitRepo()) {
+    if (isGitRepo(directory)) {
       try {
-        sha = getCurrentSha();
+        sha = getCurrentSha(directory);
       } catch {
         sha = "";
       }
@@ -58582,7 +58586,7 @@ function handleRestore(label, directory) {
         error: `checkpoint not found: "${label}"`
       }, null, 2);
     }
-    gitExec(["reset", "--soft", checkpoint.sha]);
+    gitExec(["reset", "--soft", checkpoint.sha], directory);
     return JSON.stringify({
       action: "restore",
       success: true,
@@ -58653,7 +58657,7 @@ var init_checkpoint = __esm(() => {
       label: exports_external.string().optional().describe("Checkpoint label (required for save, restore, delete)")
     },
     execute: async (args2, directory) => {
-      if (!isGitRepo()) {
+      if (!isGitRepo(directory)) {
         return JSON.stringify({
           action: "unknown",
           success: false,
@@ -92941,7 +92945,7 @@ var init_registry = __esm(() => {
         sessionID: ctx.sessionID
       }),
       description: "Use /swarm finalize to finalize the swarm project and archive evidence",
-      details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs safe git ff-only to main. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.",
+      details: "Idempotent 4-stage terminal finalization: (1) finalize writes retrospectives for in-progress phases, (2) archive creates timestamped bundle of swarm artifacts and evidence, (3) clean removes active-state files for a clean slate, (4) align performs aggressive git reset --hard to the default remote branch, discarding uncommitted changes and untracked files; falls back to a cautious reset that preserves uncommitted changes when the aggressive path cannot proceed. WARNING: alignment discards local changes and untracked files. Resets agent sessions and delegation chains. Reads .swarm/close-lessons.md for explicit lessons and runs curation. Use --skill-review to run the quota-bounded skill_improver in proposal mode.",
       args: "--prune-branches, --skill-review",
       category: "core",
       toolPolicy: "none"

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "opencode-swarm",
-	"version": "7.78.7",
+	"version": "7.78.8",
 	"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",