opencode-swarm 7.78.7 → 7.79.0

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/agents/architect.d.ts

@@ -70,4 +70,4 @@ export declare function buildCouncilWorkflow(council?: CouncilWorkflowConfig): s
  * BRAINSTORM, and PLAN inline paths stay in lockstep.
  */
 export declare function buildQaGateSelectionDialogue(modeLabel: 'BRAINSTORM' | 'SPECIFY' | 'PLAN'): string;
-export declare function createArchitectAgent(model: string, customPrompt?: string, customAppendPrompt?: string, adversarialTesting?: AdversarialTestingConfig, council?: CouncilWorkflowConfig, uiReview?: UIReviewConfig, memoryEnabled?: boolean, architecturalSupervision?: ArchitectureSupervisionWorkflowConfig, designDocsEnabled?: boolean, externalSkillsEnabled?: boolean): AgentDefinition;
+export declare function createArchitectAgent(model: string, customPrompt?: string, customAppendPrompt?: string, adversarialTesting?: AdversarialTestingConfig, council?: CouncilWorkflowConfig, uiReview?: UIReviewConfig, memoryEnabled?: boolean, architecturalSupervision?: ArchitectureSupervisionWorkflowConfig, designDocsEnabled?: boolean, externalSkillsEnabled?: boolean, turboEnabled?: boolean): AgentDefinition;

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: "7.79.0",
     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",
@@ -17406,15 +17406,15 @@ var init_tool_metadata = __esm(() => {
     },
     submit_council_verdicts: {
       description: "submit pre-collected council member verdicts for synthesis (architect MUST dispatch critic/reviewer/sme/test_engineer/explorer as Agent tasks first; this tool synthesizes only, it does not contact members)",
-      agents: ["architect"]
+      agents: []
     },
     submit_phase_council_verdicts: {
       description: "submit pre-collected phase-level council member verdicts for holistic phase synthesis (architect MUST dispatch all 5 council members with phase-scoped context first; this tool synthesizes only, it does not contact members)",
-      agents: ["architect"]
+      agents: []
     },
     declare_council_criteria: {
       description: "pre-declare acceptance criteria for a task before the coder starts work; criteria are read back during council evaluation",
-      agents: ["architect"]
+      agents: []
     },
     sbom_generate: {
       description: "SBOM generation for dependency inventory",
@@ -17676,19 +17676,19 @@ var init_tool_metadata = __esm(() => {
     },
     web_search: {
       description: "External web search (Tavily or Brave) for architect-driven council research, SME domain research, researcher auto-research, and skill-improver research. Returns titled results with snippets, URLs, normalized query metadata, temporal intent, freshness, and removed stale years. Config-gated on council.general.enabled in the resolved config: global ~/.config/opencode/opencode-swarm.json, then project .opencode/opencode-swarm.json overrides. Requires a search API key. Used by the architect in MODE: COUNCIL to gather a RESEARCH CONTEXT before dispatching council agents, by SME for opt-in external skill/source evaluation, and by the researcher agent for multi-source auto-research.",
-      agents: ["architect", "sme", "researcher", "skill_improver"]
+      agents: ["sme", "researcher", "skill_improver"]
     },
     web_fetch: {
       description: "Fetch the readable text of a single http(s) URL (architect-only). Returns decoded page text, document title, final URL after redirects, and an evidence reference. Reads primary sources that web_search only surfaces as snippets. Config-gated on council.general.enabled. Blocks private/loopback/link-local/metadata addresses (re-validated and re-pinned across redirects); enforces timeout and body size cap.",
-      agents: ["architect"]
+      agents: []
     },
     convene_general_council: {
       description: "Synthesize responses from a multi-model General Council. Accepts parallel member responses (Round 1, optionally Round 2), detects disagreements, and returns consensus points, persisting disagreements, and a structured synthesis. Architect-only. Config-gated on council.general.enabled in the resolved config: global ~/.config/opencode/opencode-swarm.json, then project .opencode/opencode-swarm.json overrides.",
-      agents: ["architect"]
+      agents: []
     },
     write_final_council_evidence: {
       description: "Persist project-scoped final council evidence to .swarm/evidence/final-council.json. PREREQUISITE: dispatch critic, reviewer, sme, test_engineer, and explorer as project-scoped Agent tasks and collect their CouncilMemberVerdict JSON \u2014 this tool synthesizes only. Rejects on insufficient quorum or CONCERNS with unresolved requiredFixes; normalizes verdicts to approved/concerns/rejected. Architect-only.",
-      agents: ["architect"]
+      agents: []
     },
     skill_generate: {
       description: "compile knowledge entries into a structured SKILL.md draft",
@@ -17722,10 +17722,6 @@ var init_tool_metadata = __esm(() => {
       description: "author or update .swarm/spec.md for the current project",
       agents: ["spec_writer"]
     },
-    knowledge_ack: {
-      description: "record an explicit KNOWLEDGE_APPLIED/IGNORED/VIOLATED acknowledgment",
-      agents: ["architect"]
-    },
     knowledge_receipt: {
       description: "file a receipt for retrieved knowledge (applied/ignored/contradicted + new lessons), recorded as immutable knowledge events",
       agents: ["architect", "coder"]
@@ -17782,27 +17778,27 @@ var init_tool_metadata = __esm(() => {
     },
     lean_turbo_plan_lanes: {
       description: "partition phase tasks into parallel lanes based on file-scope conflicts for Lean Turbo execution",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_acquire_locks: {
       description: "acquire file locks for all files in a lane (all-or-nothing) before lane execution",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_runner_status: {
       description: "read Lean Turbo run state from .swarm/turbo-state.json",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_review: {
       description: "dispatch a read-only reviewer agent to evaluate a completed Lean Turbo phase",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_run_phase: {
       description: "Execute a phase using Lean Turbo parallel lane execution. Plans lanes, acquires file locks, and dispatches coder agents concurrently. Use when Lean Turbo is active and you want to execute all tasks in a phase in parallel lanes.",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_status: {
       description: "returns Lean Turbo configuration and active status for the current session",
-      agents: ["architect"]
+      agents: []
     },
     apply_patch: {
       description: "Apply a unified diff patch to workspace files with exact context matching, atomic writes, and path validation",
@@ -17888,7 +17884,7 @@ function freezeSet(items) {
   });
   return proxy;
 }
-var OPENCODE_NATIVE_AGENTS, CLAUDE_CODE_NATIVE_COMMANDS, EXTERNAL_SKILL_TOOL_NAMES, EXTERNAL_SKILL_AGENT_TOOL_MAP, DEFAULT_AGENT_CONFIGS;
+var OPENCODE_NATIVE_AGENTS, CLAUDE_CODE_NATIVE_COMMANDS, EXTERNAL_SKILL_TOOL_NAMES, EXTERNAL_SKILL_AGENT_TOOL_MAP, COUNCIL_TOOL_NAMES, COUNCIL_AGENT_TOOL_MAP, GENERAL_COUNCIL_TOOL_NAMES, GENERAL_COUNCIL_AGENT_TOOL_MAP, TURBO_TOOL_NAMES, TURBO_AGENT_TOOL_MAP, DEFAULT_AGENT_CONFIGS;
 var init_constants = __esm(() => {
   init_agent_names();
   init_tool_metadata();
@@ -18021,6 +18017,34 @@ var init_constants = __esm(() => {
   EXTERNAL_SKILL_AGENT_TOOL_MAP = {
     architect: [...EXTERNAL_SKILL_TOOL_NAMES]
   };
+  COUNCIL_TOOL_NAMES = [
+    "submit_council_verdicts",
+    "submit_phase_council_verdicts",
+    "declare_council_criteria",
+    "write_final_council_evidence"
+  ];
+  COUNCIL_AGENT_TOOL_MAP = {
+    architect: [...COUNCIL_TOOL_NAMES]
+  };
+  GENERAL_COUNCIL_TOOL_NAMES = [
+    "convene_general_council",
+    "web_search",
+    "web_fetch"
+  ];
+  GENERAL_COUNCIL_AGENT_TOOL_MAP = {
+    architect: [...GENERAL_COUNCIL_TOOL_NAMES]
+  };
+  TURBO_TOOL_NAMES = [
+    "lean_turbo_plan_lanes",
+    "lean_turbo_acquire_locks",
+    "lean_turbo_runner_status",
+    "lean_turbo_review",
+    "lean_turbo_run_phase",
+    "lean_turbo_status"
+  ];
+  TURBO_AGENT_TOOL_MAP = {
+    architect: [...TURBO_TOOL_NAMES]
+  };
   DEFAULT_AGENT_CONFIGS = {
     coder: {
       model: "opencode/minimax-m2.5-free",
@@ -18434,7 +18458,7 @@ var init_schema = __esm(() => {
   });
   SummaryConfigSchema = exports_external.object({
     enabled: exports_external.boolean().default(true),
-    threshold_bytes: exports_external.number().min(1024).max(1048576).default(102400),
+    threshold_bytes: exports_external.number().min(1024).max(1048576).default(16384),
     max_summary_chars: exports_external.number().min(100).max(5000).default(1000),
     max_stored_bytes: exports_external.number().min(10240).max(104857600).default(10485760),
     retention_days: exports_external.number().min(1).max(365).default(7),
@@ -37020,15 +37044,19 @@ 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 +37068,13 @@ 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 +37099,21 @@ 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: ${label}`], directory);
     }
-    const newSha = getCurrentSha();
+    const newSha = getCurrentSha(directory);
     log2.checkpoints.push({
       label,
       sha: newSha,
@@ -37130,7 +37158,7 @@ function handleRestore(label, directory) {
         error: `checkpoint not found: "${label}"`
       }, null, 2);
     }
-    gitExec(["reset", "--soft", checkpoint.sha]);
+    gitExec(["reset", "--soft", checkpoint.sha], directory);
     return JSON.stringify({
       action: "restore",
       success: true,
@@ -37201,7 +37229,7 @@ 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 +67750,7 @@ 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/config/constants.d.ts

@@ -9,6 +9,12 @@ export declare const MEMORY_TOOL_NAMES: readonly ["swarm_memory_recall", "swarm_
 export declare const MEMORY_AGENT_TOOL_MAP: Partial<Record<AgentName, ToolName[]>>;
 export declare const EXTERNAL_SKILL_TOOL_NAMES: readonly ["external_skill_discover", "external_skill_list", "external_skill_inspect", "external_skill_promote", "external_skill_reject", "external_skill_delete", "external_skill_revoke"];
 export declare const EXTERNAL_SKILL_AGENT_TOOL_MAP: Partial<Record<AgentName, ToolName[]>>;
+export declare const COUNCIL_TOOL_NAMES: readonly ["submit_council_verdicts", "submit_phase_council_verdicts", "declare_council_criteria", "write_final_council_evidence"];
+export declare const COUNCIL_AGENT_TOOL_MAP: Partial<Record<AgentName, ToolName[]>>;
+export declare const GENERAL_COUNCIL_TOOL_NAMES: readonly ["convene_general_council", "web_search", "web_fetch"];
+export declare const GENERAL_COUNCIL_AGENT_TOOL_MAP: Partial<Record<AgentName, ToolName[]>>;
+export declare const TURBO_TOOL_NAMES: readonly ["lean_turbo_plan_lanes", "lean_turbo_acquire_locks", "lean_turbo_runner_status", "lean_turbo_review", "lean_turbo_run_phase", "lean_turbo_status"];
+export declare const TURBO_AGENT_TOOL_MAP: Partial<Record<AgentName, ToolName[]>>;
 /**
  * Human-readable descriptions for tools shown in the architect Available Tools block.
  * Used to generate the Available Tools section of the architect prompt at construction time.

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: "7.79.0",
     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",
@@ -330,15 +330,15 @@ var init_tool_metadata = __esm(() => {
     },
     submit_council_verdicts: {
       description: "submit pre-collected council member verdicts for synthesis (architect MUST dispatch critic/reviewer/sme/test_engineer/explorer as Agent tasks first; this tool synthesizes only, it does not contact members)",
-      agents: ["architect"]
+      agents: []
     },
     submit_phase_council_verdicts: {
       description: "submit pre-collected phase-level council member verdicts for holistic phase synthesis (architect MUST dispatch all 5 council members with phase-scoped context first; this tool synthesizes only, it does not contact members)",
-      agents: ["architect"]
+      agents: []
     },
     declare_council_criteria: {
       description: "pre-declare acceptance criteria for a task before the coder starts work; criteria are read back during council evaluation",
-      agents: ["architect"]
+      agents: []
     },
     sbom_generate: {
       description: "SBOM generation for dependency inventory",
@@ -600,19 +600,19 @@ var init_tool_metadata = __esm(() => {
     },
     web_search: {
       description: "External web search (Tavily or Brave) for architect-driven council research, SME domain research, researcher auto-research, and skill-improver research. Returns titled results with snippets, URLs, normalized query metadata, temporal intent, freshness, and removed stale years. Config-gated on council.general.enabled in the resolved config: global ~/.config/opencode/opencode-swarm.json, then project .opencode/opencode-swarm.json overrides. Requires a search API key. Used by the architect in MODE: COUNCIL to gather a RESEARCH CONTEXT before dispatching council agents, by SME for opt-in external skill/source evaluation, and by the researcher agent for multi-source auto-research.",
-      agents: ["architect", "sme", "researcher", "skill_improver"]
+      agents: ["sme", "researcher", "skill_improver"]
     },
     web_fetch: {
       description: "Fetch the readable text of a single http(s) URL (architect-only). Returns decoded page text, document title, final URL after redirects, and an evidence reference. Reads primary sources that web_search only surfaces as snippets. Config-gated on council.general.enabled. Blocks private/loopback/link-local/metadata addresses (re-validated and re-pinned across redirects); enforces timeout and body size cap.",
-      agents: ["architect"]
+      agents: []
     },
     convene_general_council: {
       description: "Synthesize responses from a multi-model General Council. Accepts parallel member responses (Round 1, optionally Round 2), detects disagreements, and returns consensus points, persisting disagreements, and a structured synthesis. Architect-only. Config-gated on council.general.enabled in the resolved config: global ~/.config/opencode/opencode-swarm.json, then project .opencode/opencode-swarm.json overrides.",
-      agents: ["architect"]
+      agents: []
     },
     write_final_council_evidence: {
       description: "Persist project-scoped final council evidence to .swarm/evidence/final-council.json. PREREQUISITE: dispatch critic, reviewer, sme, test_engineer, and explorer as project-scoped Agent tasks and collect their CouncilMemberVerdict JSON — this tool synthesizes only. Rejects on insufficient quorum or CONCERNS with unresolved requiredFixes; normalizes verdicts to approved/concerns/rejected. Architect-only.",
-      agents: ["architect"]
+      agents: []
     },
     skill_generate: {
       description: "compile knowledge entries into a structured SKILL.md draft",
@@ -646,10 +646,6 @@ var init_tool_metadata = __esm(() => {
       description: "author or update .swarm/spec.md for the current project",
       agents: ["spec_writer"]
     },
-    knowledge_ack: {
-      description: "record an explicit KNOWLEDGE_APPLIED/IGNORED/VIOLATED acknowledgment",
-      agents: ["architect"]
-    },
     knowledge_receipt: {
       description: "file a receipt for retrieved knowledge (applied/ignored/contradicted + new lessons), recorded as immutable knowledge events",
       agents: ["architect", "coder"]
@@ -706,27 +702,27 @@ var init_tool_metadata = __esm(() => {
     },
     lean_turbo_plan_lanes: {
       description: "partition phase tasks into parallel lanes based on file-scope conflicts for Lean Turbo execution",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_acquire_locks: {
       description: "acquire file locks for all files in a lane (all-or-nothing) before lane execution",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_runner_status: {
       description: "read Lean Turbo run state from .swarm/turbo-state.json",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_review: {
       description: "dispatch a read-only reviewer agent to evaluate a completed Lean Turbo phase",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_run_phase: {
       description: "Execute a phase using Lean Turbo parallel lane execution. Plans lanes, acquires file locks, and dispatches coder agents concurrently. Use when Lean Turbo is active and you want to execute all tasks in a phase in parallel lanes.",
-      agents: ["architect"]
+      agents: []
     },
     lean_turbo_status: {
       description: "returns Lean Turbo configuration and active status for the current session",
-      agents: ["architect"]
+      agents: []
     },
     apply_patch: {
       description: "Apply a unified diff patch to workspace files with exact context matching, atomic writes, and path validation",
@@ -848,7 +844,7 @@ function isLowCapabilityModel(modelId) {
   const lower = (modelId || "").toLowerCase();
   return LOW_CAPABILITY_MODELS.some((substr) => lower.includes(substr));
 }
-var OPENCODE_NATIVE_AGENTS, CLAUDE_CODE_NATIVE_COMMANDS, MEMORY_AGENT_TOOL_MAP, EXTERNAL_SKILL_TOOL_NAMES, EXTERNAL_SKILL_AGENT_TOOL_MAP, WRITE_TOOL_NAMES, DEFAULT_MODELS, DEFAULT_SCORING_CONFIG, LOW_CAPABILITY_MODELS, TURBO_MODE_BANNER = `## \uD83D\uDE80 TURBO MODE ACTIVE
+var OPENCODE_NATIVE_AGENTS, CLAUDE_CODE_NATIVE_COMMANDS, MEMORY_AGENT_TOOL_MAP, EXTERNAL_SKILL_TOOL_NAMES, EXTERNAL_SKILL_AGENT_TOOL_MAP, COUNCIL_TOOL_NAMES, COUNCIL_AGENT_TOOL_MAP, GENERAL_COUNCIL_TOOL_NAMES, GENERAL_COUNCIL_AGENT_TOOL_MAP, TURBO_TOOL_NAMES, TURBO_AGENT_TOOL_MAP, WRITE_TOOL_NAMES, DEFAULT_MODELS, DEFAULT_SCORING_CONFIG, LOW_CAPABILITY_MODELS, TURBO_MODE_BANNER = `## \uD83D\uDE80 TURBO MODE ACTIVE
 
 **Speed optimization enabled for this session.**
 
@@ -1054,6 +1050,34 @@ var init_constants = __esm(() => {
   EXTERNAL_SKILL_AGENT_TOOL_MAP = {
     architect: [...EXTERNAL_SKILL_TOOL_NAMES]
   };
+  COUNCIL_TOOL_NAMES = [
+    "submit_council_verdicts",
+    "submit_phase_council_verdicts",
+    "declare_council_criteria",
+    "write_final_council_evidence"
+  ];
+  COUNCIL_AGENT_TOOL_MAP = {
+    architect: [...COUNCIL_TOOL_NAMES]
+  };
+  GENERAL_COUNCIL_TOOL_NAMES = [
+    "convene_general_council",
+    "web_search",
+    "web_fetch"
+  ];
+  GENERAL_COUNCIL_AGENT_TOOL_MAP = {
+    architect: [...GENERAL_COUNCIL_TOOL_NAMES]
+  };
+  TURBO_TOOL_NAMES = [
+    "lean_turbo_plan_lanes",
+    "lean_turbo_acquire_locks",
+    "lean_turbo_runner_status",
+    "lean_turbo_review",
+    "lean_turbo_run_phase",
+    "lean_turbo_status"
+  ];
+  TURBO_AGENT_TOOL_MAP = {
+    architect: [...TURBO_TOOL_NAMES]
+  };
   WRITE_TOOL_NAMES = [
     "write",
     "edit",
@@ -15615,7 +15639,7 @@ var init_schema = __esm(() => {
   });
   SummaryConfigSchema = exports_external.object({
     enabled: exports_external.boolean().default(true),
-    threshold_bytes: exports_external.number().min(1024).max(1048576).default(102400),
+    threshold_bytes: exports_external.number().min(1024).max(1048576).default(16384),
     max_summary_chars: exports_external.number().min(100).max(5000).default(1000),
     max_stored_bytes: exports_external.number().min(10240).max(104857600).default(10485760),
     retention_days: exports_external.number().min(1).max(365).default(7),
@@ -58440,15 +58464,19 @@ 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 +58488,13 @@ 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 +58519,21 @@ 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: ${label}`], directory);
     }
-    const newSha = getCurrentSha();
+    const newSha = getCurrentSha(directory);
     log2.checkpoints.push({
       label,
       sha: newSha,
@@ -58550,9 +58578,9 @@ function saveCheckpointRecord(label, directory) {
       return { success: false, error: `duplicate label: "${label}"` };
     }
     let sha = "";
-    if (isGitRepo()) {
+    if (isGitRepo(directory)) {
       try {
-        sha = getCurrentSha();
+        sha = getCurrentSha(directory);
       } catch {
         sha = "";
       }
@@ -58582,7 +58610,7 @@ 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 +58681,7 @@ 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 +92969,7 @@ 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"
@@ -93640,25 +93668,19 @@ Members verify prior findings are resolved without re-reviewing unchanged code.
 The architect resolves any \`unresolvedConflicts\` in \`unifiedFeedbackMd\` BEFORE
 sending it to the coder — the coder never sees contradictory instructions.`;
 }
-function buildYourToolsList(council, memoryEnabled = false, externalSkillsEnabled = false) {
+function buildYourToolsList(council, memoryEnabled = false, externalSkillsEnabled = false, turboEnabled = false) {
+  const qaCouncilEnabled = council?.enabled === true;
+  const generalCouncilEnabled = council?.general?.enabled === true;
   const tools = [
     ...AGENT_TOOL_MAP.architect ?? [],
     ...memoryEnabled ? MEMORY_AGENT_TOOL_MAP.architect ?? [] : [],
-    ...externalSkillsEnabled ? EXTERNAL_SKILL_AGENT_TOOL_MAP.architect ?? [] : []
+    ...externalSkillsEnabled ? EXTERNAL_SKILL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...qaCouncilEnabled ? COUNCIL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...generalCouncilEnabled ? GENERAL_COUNCIL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...turboEnabled ? TURBO_AGENT_TOOL_MAP.architect ?? [] : []
   ];
   const sorted = [...tools].sort();
-  const qaCouncilEnabled = council?.enabled === true;
-  const generalCouncilEnabled = council?.general?.enabled === true;
-  const filtered = sorted.filter((t) => {
-    if (!qaCouncilEnabled && (t === "submit_council_verdicts" || t === "declare_council_criteria" || t === "submit_phase_council_verdicts")) {
-      return false;
-    }
-    if (!generalCouncilEnabled && t === "convene_general_council") {
-      return false;
-    }
-    return true;
-  });
-  return `Task (delegation), ${filtered.join(", ")}.`;
+  return `Task (delegation), ${sorted.join(", ")}.`;
 }
 function buildQaGateSelectionDialogue(modeLabel) {
   const leadIn = modeLabel === "BRAINSTORM" ? "Now ask the user which QA gates to enable for this plan — do not select on their behalf." : modeLabel === "SPECIFY" ? "Ask the user which QA gates to enable for this plan before suggesting the next step." : "No pending gate selection found in `.swarm/context.md`. Ask the user inline now.";
@@ -93707,25 +93729,19 @@ If the user accepts the default (1), skip writing this section entirely — seri
 \`\`\`
 If the user keeps the default phase-level behavior, do not write this section.`;
 }
-function buildAvailableToolsList(council, memoryEnabled = false, externalSkillsEnabled = false) {
+function buildAvailableToolsList(council, memoryEnabled = false, externalSkillsEnabled = false, turboEnabled = false) {
+  const qaCouncilEnabled = council?.enabled === true;
+  const generalCouncilEnabled = council?.general?.enabled === true;
   const tools = [
     ...AGENT_TOOL_MAP.architect ?? [],
     ...memoryEnabled ? MEMORY_AGENT_TOOL_MAP.architect ?? [] : [],
-    ...externalSkillsEnabled ? EXTERNAL_SKILL_AGENT_TOOL_MAP.architect ?? [] : []
+    ...externalSkillsEnabled ? EXTERNAL_SKILL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...qaCouncilEnabled ? COUNCIL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...generalCouncilEnabled ? GENERAL_COUNCIL_AGENT_TOOL_MAP.architect ?? [] : [],
+    ...turboEnabled ? TURBO_AGENT_TOOL_MAP.architect ?? [] : []
   ];
   const sorted = [...tools].sort();
-  const qaCouncilEnabled = council?.enabled === true;
-  const generalCouncilEnabled = council?.general?.enabled === true;
-  const filtered = sorted.filter((t) => {
-    if (!qaCouncilEnabled && (t === "submit_council_verdicts" || t === "declare_council_criteria" || t === "submit_phase_council_verdicts")) {
-      return false;
-    }
-    if (!generalCouncilEnabled && t === "convene_general_council") {
-      return false;
-    }
-    return true;
-  });
-  return filtered.map((t) => {
+  return sorted.map((t) => {
     const desc = TOOL_DESCRIPTIONS[t];
     return desc ? `${t} (${desc})` : t;
   }).join(", ");
@@ -93858,7 +93874,7 @@ function buildSlashCommandsList() {
   return lines.join(`
 `);
 }
-function createArchitectAgent(model, customPrompt, customAppendPrompt, adversarialTesting, council, uiReview, memoryEnabled = false, architecturalSupervision, designDocsEnabled = false, externalSkillsEnabled = false) {
+function createArchitectAgent(model, customPrompt, customAppendPrompt, adversarialTesting, council, uiReview, memoryEnabled = false, architecturalSupervision, designDocsEnabled = false, externalSkillsEnabled = false, turboEnabled = false) {
   let prompt = ARCHITECT_PROMPT;
   if (customPrompt) {
     prompt = customPrompt;
@@ -93867,7 +93883,7 @@ function createArchitectAgent(model, customPrompt, customAppendPrompt, adversari
 
 ${customAppendPrompt}`;
   }
-  prompt = prompt?.replace("{{YOUR_TOOLS}}", buildYourToolsList(council, memoryEnabled, externalSkillsEnabled))?.replace("{{AVAILABLE_TOOLS}}", buildAvailableToolsList(council, memoryEnabled, externalSkillsEnabled))?.replace("{{SLASH_COMMANDS}}", buildSlashCommandsList());
+  prompt = prompt?.replace("{{YOUR_TOOLS}}", buildYourToolsList(council, memoryEnabled, externalSkillsEnabled, turboEnabled))?.replace("{{AVAILABLE_TOOLS}}", buildAvailableToolsList(council, memoryEnabled, externalSkillsEnabled, turboEnabled))?.replace("{{SLASH_COMMANDS}}", buildSlashCommandsList());
   prompt = prompt?.replace(/\{\{QA_GATE_DIALOGUE_SPECIFY\}\}/g, buildQaGateSelectionDialogue("SPECIFY"))?.replace(/\{\{QA_GATE_DIALOGUE_BRAINSTORM\}\}/g, buildQaGateSelectionDialogue("BRAINSTORM"))?.replace(/\{\{QA_GATE_DIALOGUE_PLAN\}\}/g, buildQaGateSelectionDialogue("PLAN"));
   const councilBlock = buildCouncilWorkflow(council);
   const hasPlaceholder = prompt?.includes("{{COUNCIL_WORKFLOW}}") === true;
@@ -94168,6 +94184,7 @@ diff → syntax_check → placeholder_scan → imports → lint fix → build_ch
 Stage A tools return pass/fail. Fix failures by returning to coder.
 Stage A passing means: code compiles, parses, no secrets, no placeholders, no lint errors.
 Stage A passing does NOT mean: code is correct, secure, tested, or reviewed.
+PREFERRED AGGREGATOR: pre_check_batch runs lint:check + secretscan + sast_scan + quality_budget in PARALLEL (up to 4 concurrent). Prefer calling pre_check_batch over running those four tools individually — it produces the same verdicts faster and is the recommended approach for post-implementation verification. NOTE: pre_check_batch does NOT expose capture_baseline, changed_files scoping, or per-tool severity_threshold parameters. When you need SAST baseline capture or file-scoped scanning, call sast_scan or secretscan directly.
 
 VERIFICATION PROTOCOL: After the coder reports DONE, and before running Stage B gates:
 1. Read at least ONE of the modified files yourself to confirm the change exists
@@ -94350,7 +94367,7 @@ For every applicable directive in the block:
 - If runtime evidence shows a directive was violated (reviewer rejection, failing test, scope breach), record \`KNOWLEDGE_VIOLATED: <id> reason=<reason>\` and re-plan.
 - NEVER silently ignore a \`priority: critical\` directive. The knowledge_application gate may run in 'enforce' mode; in that mode an omitted ack on a critical directive blocks the action.
 
-You may also call the \`knowledge_ack\` tool to record an outcome explicitly when chat-text markers would be ambiguous (e.g. inside structured tool args).
+Chat-text markers (KNOWLEDGE_APPLIED/IGNORED/VIOLATED) are the sole mechanism that satisfies the knowledge-application enforcement gate. The \`knowledge_receipt\` tool records knowledge-usage receipts for audit but does NOT satisfy the gate.
 
 ## SKILL IMPROVER (low-frequency, expensive-model adviser)
 
@@ -97473,7 +97490,7 @@ function createSwarmAgents(swarmId, swarmConfig, isDefault, pluginConfig, projec
   const prefixName = (name2) => `${prefix}${name2}`;
   if (!isAgentDisabled("architect", swarmAgents, swarmPrefix)) {
     const architectPrompts = getPrompts("architect");
-    const architect = createArchitectAgent(getModel("architect"), architectPrompts.prompt, architectPrompts.appendPrompt, pluginConfig?.adversarial_testing, pluginConfig?.council, pluginConfig?.ui_review, pluginConfig?.memory?.enabled === true, pluginConfig?.architectural_supervision, pluginConfig?.design_docs?.enabled === true, pluginConfig?.external_skills?.curation_enabled === true);
+    const architect = createArchitectAgent(getModel("architect"), architectPrompts.prompt, architectPrompts.appendPrompt, pluginConfig?.adversarial_testing, pluginConfig?.council, pluginConfig?.ui_review, pluginConfig?.memory?.enabled === true, pluginConfig?.architectural_supervision, pluginConfig?.design_docs?.enabled === true, pluginConfig?.external_skills?.curation_enabled === true, pluginConfig?.turbo !== undefined);
     architect.name = prefixName("architect");
     const swarmName = swarmConfig.name || swarmId;
     const swarmIdentity = isDefault ? "default" : swarmId;
@@ -97790,20 +97807,30 @@ function getAgentConfigs(config3, directory, sessionId, projectContext) {
         allowedTools = Array.from(new Set([...allowedTools ?? [], ...externalSkillTools]));
       }
     }
-    if (baseAgentName === "architect" && config3?.council?.enabled === true && override !== undefined) {
-      const required3 = [
-        "declare_council_criteria",
-        "submit_council_verdicts"
-      ];
-      const missing = required3.filter((t) => !override.includes(t));
-      if (missing.length > 0) {
-        throw new Error(`[opencode-swarm] Conflicting config: council.enabled=true but tool_filter.overrides.architect omits ${missing.join(", ")}. ` + `Either set council.enabled=false, remove the architect override entirely to fall back on AGENT_TOOL_MAP, or add the missing council tools to the override. ` + `Refusing to silently override your explicit tool_filter.overrides.architect.`);
+    if (config3?.council?.enabled === true) {
+      const councilTools = COUNCIL_AGENT_TOOL_MAP[baseAgentName] ?? [];
+      if (councilTools.length > 0) {
+        allowedTools = Array.from(new Set([...allowedTools ?? [], ...councilTools]));
+      }
+    }
+    if (config3?.council?.general?.enabled === true) {
+      const generalCouncilTools = GENERAL_COUNCIL_AGENT_TOOL_MAP[baseAgentName] ?? [];
+      if (generalCouncilTools.length > 0) {
+        allowedTools = Array.from(new Set([...allowedTools ?? [], ...generalCouncilTools]));
+      }
+    }
+    if (config3?.turbo !== undefined) {
+      const turboTools = TURBO_AGENT_TOOL_MAP[baseAgentName] ?? [];
+      if (turboTools.length > 0) {
+        allowedTools = Array.from(new Set([...allowedTools ?? [], ...turboTools]));
       }
     }
     if (baseAgentName === "architect" && config3?.council?.enabled !== true && override !== undefined) {
       const councilTools = [
         "declare_council_criteria",
-        "submit_council_verdicts"
+        "submit_council_verdicts",
+        "submit_phase_council_verdicts",
+        "write_final_council_evidence"
       ];
       const present = councilTools.filter((t) => override.includes(t));
       if (present.length > 0 && !quiet) {
@@ -128992,65 +129019,6 @@ var imports = createSwarmTool({
   }
 });
 
-// src/tools/knowledge-ack.ts
-init_zod();
-import { randomUUID as randomUUID13 } from "node:crypto";
-init_state();
-init_logger();
-init_create_tool();
-var knowledge_ack = createSwarmTool({
-  description: "Record an acknowledgment outcome (applied/ignored/violated) for a previously-injected knowledge directive. Updates retrieval-outcome counters and appends a record to .swarm/knowledge-application.jsonl.",
-  args: {
-    id: exports_external.string().min(8).describe("Knowledge entry id from <swarm_knowledge_directives>."),
-    result: exports_external.enum(["applied", "ignored", "violated"]),
-    reason: exports_external.string().max(280).optional(),
-    phase: exports_external.string().optional(),
-    task_id: exports_external.string().optional(),
-    action: exports_external.string().optional(),
-    tool: exports_external.string().optional(),
-    target_agent: exports_external.string().optional(),
-    generated_skill_path: exports_external.string().optional()
-  },
-  execute: async (args2, directory, ctx) => {
-    const a = args2 ?? {};
-    if (!a.id || typeof a.id !== "string" || a.id.length < 8) {
-      return JSON.stringify({ recorded: false, error: "invalid id" });
-    }
-    if (a.result !== "applied" && a.result !== "ignored" && a.result !== "violated") {
-      return JSON.stringify({ recorded: false, error: "invalid result" });
-    }
-    const ack = {
-      id: a.id,
-      result: a.result,
-      reason: a.reason
-    };
-    let sessionId = ctx?.sessionID;
-    if (!sessionId) {
-      warn("[knowledge-ack] No sessionID in tool context — dedup disabled for this acknowledgment");
-      sessionId = randomUUID13();
-    }
-    const dedupKey = buildAckDedupKey(sessionId, a.id, a.result);
-    if (swarmState.knowledgeAckDedup.has(dedupKey)) {
-      return JSON.stringify({
-        recorded: false,
-        reason: "duplicate_ack",
-        id: a.id,
-        result: a.result
-      }, null, 2);
-    }
-    addKnowledgeAckDedup(dedupKey);
-    await recordAcknowledgment(directory, ack, {
-      phase: a.phase,
-      taskId: a.task_id,
-      action: a.action,
-      tool: a.tool,
-      targetAgent: a.target_agent,
-      sessionId
-    });
-    return JSON.stringify({ recorded: true, id: a.id, result: a.result }, null, 2);
-  }
-});
-
 // src/tools/knowledge-add.ts
 init_zod();
 init_config();
@@ -129059,7 +129027,7 @@ init_knowledge_store();
 init_knowledge_validator();
 init_manager();
 init_create_tool();
-import { randomUUID as randomUUID14 } from "node:crypto";
+import { randomUUID as randomUUID13 } from "node:crypto";
 var VALID_CATEGORIES2 = [
   "process",
   "architecture",
@@ -129158,7 +129126,7 @@ var knowledge_add = createSwarmTool({
       }
     } catch {}
     const entry = {
-      id: randomUUID14(),
+      id: randomUUID13(),
       tier: "swarm",
       lesson,
       category,
@@ -146695,7 +146663,6 @@ var TOOL_MANIFEST = defineHandlers({
   skill_retire: () => skill_retire,
   skill_improve: () => skill_improve,
   spec_write: () => spec_write,
-  knowledge_ack: () => knowledge_ack,
   knowledge_receipt: () => knowledge_receipt,
   knowledge_archive: () => knowledge_archive,
   swarm_memory_recall: () => swarm_memory_recall,
@@ -146729,7 +146696,6 @@ function buildPluginToolObject(agents, config3) {
     "knowledge_recall",
     "knowledge_remove",
     "knowledge_query",
-    "knowledge_ack",
     "knowledge_receipt",
     "knowledge_archive"
   ]);

package/dist/tools/index.d.ts

@@ -32,7 +32,6 @@ export { get_qa_gate_profile } from './get-qa-gate-profile';
 export { git_blame } from './git-blame';
 export { fetchGitingest, type GitingestArgs, gitingest } from './gitingest';
 export { imports } from './imports';
-export { knowledge_ack } from './knowledge-ack';
 export { knowledge_add } from './knowledge-add';
 export { knowledge_archive } from './knowledge-archive';
 export { knowledge_query } from './knowledge-query';

package/dist/tools/knowledge-receipt.d.ts

@@ -1,5 +1,5 @@
 /**
- * knowledge_receipt — the strong successor to knowledge_ack.
+ * knowledge_receipt — the knowledge acknowledgment tool (replaces the former knowledge_ack).
  *
  * An agent files a single receipt summarizing how it considered the knowledge
  * surfaced by a retrieval (referenced by `trace_id`): which entries were

package/dist/tools/manifest.d.ts

@@ -94,7 +94,6 @@ export declare const TOOL_MANIFEST: {
     skill_retire: () => ToolDefinition;
     skill_improve: () => ToolDefinition;
     spec_write: () => ToolDefinition;
-    knowledge_ack: () => ToolDefinition;
     knowledge_receipt: () => ToolDefinition;
     knowledge_archive: () => ToolDefinition;
     swarm_memory_recall: () => ToolDefinition;

package/dist/tools/tool-metadata.d.ts

@@ -101,15 +101,15 @@ export declare const TOOL_METADATA: {
     };
     submit_council_verdicts: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     submit_phase_council_verdicts: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     declare_council_criteria: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     sbom_generate: {
         description: string;
@@ -261,19 +261,19 @@ export declare const TOOL_METADATA: {
     };
     web_search: {
         description: string;
-        agents: ("sme" | "architect" | "researcher" | "skill_improver")[];
+        agents: ("sme" | "researcher" | "skill_improver")[];
     };
     web_fetch: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     convene_general_council: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     write_final_council_evidence: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     skill_generate: {
         description: string;
@@ -307,10 +307,6 @@ export declare const TOOL_METADATA: {
         description: string;
         agents: "spec_writer"[];
     };
-    knowledge_ack: {
-        description: string;
-        agents: "architect"[];
-    };
     knowledge_receipt: {
         description: string;
         agents: ("coder" | "architect")[];
@@ -345,27 +341,27 @@ export declare const TOOL_METADATA: {
     };
     lean_turbo_plan_lanes: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     lean_turbo_acquire_locks: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     lean_turbo_runner_status: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     lean_turbo_review: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     lean_turbo_run_phase: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     lean_turbo_status: {
         description: string;
-        agents: "architect"[];
+        agents: never[];
     };
     apply_patch: {
         description: string;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "opencode-swarm",
-	"version": "7.78.7",
+	"version": "7.79.0",
 	"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",