opencode-swarm-plugin 0.44.0 → 0.44.2

package/dist/swarm-review.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"swarm-review.d.ts","sourceRoot":"","sources":["../src/swarm-review.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAGH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AASxB;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,eAAO,MAAM,iBAAiB;;;;;iBAK5B,CAAC;AAEH;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,UAAU,GAAG,eAAe,CAAC;IACrC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,MAAM,CAAC,EAAE,WAAW,EAAE,CAAC;IACvB,kBAAkB,CAAC,EAAE,MAAM,CAAC;CAC7B;AAED,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;iBAkB5B,CAAC;AAEJ;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;CACf;AAED;;GAEG;AACH,MAAM,WAAW,mBAAmB;IAClC,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,IAAI,EAAE,MAAM,CAAC;IACb,sBAAsB,CAAC,EAAE,cAAc,EAAE,CAAC;IAC1C,gBAAgB,CAAC,EAAE,cAAc,EAAE,CAAC;CACrC;AAkDD;;;;;;;;;;GAUG;AACH,wBAAgB,oBAAoB,CAAC,OAAO,EAAE,mBAAmB,GAAG,MAAM,CAsGzE;AAmED;;;;;GAKG;AACH,eAAO,MAAM,YAAY;;;;;;;;;;;;;;CA+GvB,CAAC;AAEH;;;;GAIG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;CAkLhC,CAAC;AAMH;;GAEG;AACH,UAAU,gBAAgB;IACxB,QAAQ,EAAE,OAAO,CAAC;IAClB,QAAQ,EAAE,OAAO,CAAC;IAClB,aAAa,EAAE,MAAM,CAAC;IACtB,kBAAkB,EAAE,MAAM,CAAC;CAC5B;AAOD;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAGvD;AAED;;GAEG;AACH,wBAAgB,gBAAgB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAGxD;AAED;;GAEG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,MAAM,GAAG,gBAAgB,CAQhE;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAGtD;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAEvD;AAMD,eAAO,MAAM,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAGvB,CAAC"}
+{"version":3,"file":"swarm-review.d.ts","sourceRoot":"","sources":["../src/swarm-review.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAGH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AASxB;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,eAAO,MAAM,iBAAiB;;;;;iBAK5B,CAAC;AAEH;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,MAAM,EAAE,UAAU,GAAG,eAAe,CAAC;IACrC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,MAAM,CAAC,EAAE,WAAW,EAAE,CAAC;IACvB,kBAAkB,CAAC,EAAE,MAAM,CAAC;CAC7B;AAED,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;iBAkB5B,CAAC;AAEJ;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;CACf;AAED;;GAEG;AACH,MAAM,WAAW,mBAAmB;IAClC,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,EAAE,MAAM,CAAC;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,IAAI,EAAE,MAAM,CAAC;IACb,sBAAsB,CAAC,EAAE,cAAc,EAAE,CAAC;IAC1C,gBAAgB,CAAC,EAAE,cAAc,EAAE,CAAC;CACrC;AAkDD;;;;;;;;;;GAUG;AACH,wBAAgB,oBAAoB,CAAC,OAAO,EAAE,mBAAmB,GAAG,MAAM,CAsGzE;AAmED;;;;;GAKG;AACH,eAAO,MAAM,YAAY;;;;;;;;;;;;;;CA+HvB,CAAC;AAEH;;;;GAIG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;CAoNhC,CAAC;AAMH;;GAEG;AACH,UAAU,gBAAgB;IACxB,QAAQ,EAAE,OAAO,CAAC;IAClB,QAAQ,EAAE,OAAO,CAAC;IAClB,aAAa,EAAE,MAAM,CAAC;IACtB,kBAAkB,EAAE,MAAM,CAAC;CAC5B;AAOD;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAGvD;AAED;;GAEG;AACH,wBAAgB,gBAAgB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAGxD;AAED;;GAEG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,MAAM,GAAG,gBAAgB,CAQhE;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAGtD;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAEvD;AAMD,eAAO,MAAM,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAGvB,CAAC"}

package/dist/swarm-validation.d.ts

@@ -0,0 +1,127 @@
+/**
+ * Swarm Validation Hook Infrastructure
+ *
+ * Provides validation event types and hooks for post-swarm validation.
+ * Integrates with swarm-mail event sourcing to emit validation events.
+ *
+ * @module swarm-validation
+ */
+import { z } from "zod";
+/**
+ * Agent event type for validation events
+ *
+ * This is a minimal type that matches the swarm-mail AgentEvent interface
+ * for the validation events we emit.
+ */
+type AgentEvent = {
+    type: "validation_started";
+    project_key: string;
+    timestamp: number;
+    epic_id: string;
+    swarm_id: string;
+    started_at: number;
+} | {
+    type: "validation_issue";
+    project_key: string;
+    timestamp: string | number;
+    epic_id: string;
+    severity: "error" | "warning" | "info";
+    category: "schema_mismatch" | "missing_event" | "undefined_value" | "dashboard_render" | "websocket_delivery";
+    message: string;
+    location?: {
+        event_type?: string;
+        field?: string;
+        component?: string;
+    };
+} | {
+    type: "validation_completed";
+    project_key: string;
+    timestamp: number;
+    epic_id: string;
+    swarm_id: string;
+    passed: boolean;
+    issue_count: number;
+    duration_ms: number;
+};
+/**
+ * Severity levels for validation issues
+ */
+export declare const ValidationIssueSeverity: z.ZodEnum<{
+    error: "error";
+    info: "info";
+    warning: "warning";
+}>;
+/**
+ * Categories of validation issues
+ */
+export declare const ValidationIssueCategory: z.ZodEnum<{
+    schema_mismatch: "schema_mismatch";
+    missing_event: "missing_event";
+    undefined_value: "undefined_value";
+    dashboard_render: "dashboard_render";
+    websocket_delivery: "websocket_delivery";
+}>;
+/**
+ * Validation issue with location context
+ */
+export declare const ValidationIssueSchema: z.ZodObject<{
+    severity: z.ZodEnum<{
+        error: "error";
+        info: "info";
+        warning: "warning";
+    }>;
+    category: z.ZodEnum<{
+        schema_mismatch: "schema_mismatch";
+        missing_event: "missing_event";
+        undefined_value: "undefined_value";
+        dashboard_render: "dashboard_render";
+        websocket_delivery: "websocket_delivery";
+    }>;
+    message: z.ZodString;
+    location: z.ZodOptional<z.ZodObject<{
+        event_type: z.ZodOptional<z.ZodString>;
+        field: z.ZodOptional<z.ZodString>;
+        component: z.ZodOptional<z.ZodString>;
+    }, z.core.$strip>>;
+}, z.core.$strip>;
+export type ValidationIssue = z.infer<typeof ValidationIssueSchema>;
+/**
+ * Context for validation execution
+ */
+export interface ValidationContext {
+    /** Project key (path) */
+    project_key: string;
+    /** Epic ID being validated */
+    epic_id: string;
+    /** Swarm ID being validated */
+    swarm_id: string;
+    /** Validation start time */
+    started_at: Date;
+    /** Event emitter function */
+    emit: (event: AgentEvent) => Promise<void>;
+}
+/**
+ * Run post-swarm validation
+ *
+ * Emits validation_started, runs validators, emits validation_issue for each issue,
+ * and emits validation_completed with summary.
+ *
+ * @param ctx - Validation context
+ * @param events - Events to validate
+ * @returns Validation result with passed flag and issues
+ */
+export declare function runPostSwarmValidation(ctx: ValidationContext, events: unknown[]): Promise<{
+    passed: boolean;
+    issues: ValidationIssue[];
+}>;
+/**
+ * Report a validation issue
+ *
+ * Emits a validation_issue event with the provided issue details.
+ *
+ * @param ctx - Validation context
+ * @param issue - Validation issue to report
+ */
+export declare function reportIssue(ctx: ValidationContext, issue: ValidationIssue): Promise<void>;
+export {};
+//# sourceMappingURL=swarm-validation.d.ts.map

package/dist/swarm-validation.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"swarm-validation.d.ts","sourceRoot":"","sources":["../src/swarm-validation.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAExB;;;;;GAKG;AACH,KAAK,UAAU,GACX;IACE,IAAI,EAAE,oBAAoB,CAAC;IAC3B,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,MAAM,CAAC;IACjB,UAAU,EAAE,MAAM,CAAC;CACpB,GACD;IACE,IAAI,EAAE,kBAAkB,CAAC;IACzB,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE,MAAM,GAAG,MAAM,CAAC;IAC3B,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,OAAO,GAAG,SAAS,GAAG,MAAM,CAAC;IACvC,QAAQ,EACJ,iBAAiB,GACjB,eAAe,GACf,iBAAiB,GACjB,kBAAkB,GAClB,oBAAoB,CAAC;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,CAAC,EAAE;QACT,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,KAAK,CAAC,EAAE,MAAM,CAAC;QACf,SAAS,CAAC,EAAE,MAAM,CAAC;KACpB,CAAC;CACH,GACD;IACE,IAAI,EAAE,sBAAsB,CAAC;IAC7B,WAAW,EAAE,MAAM,CAAC;IACpB,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,MAAM,CAAC;IACjB,MAAM,EAAE,OAAO,CAAC;IAChB,WAAW,EAAE,MAAM,CAAC;IACpB,WAAW,EAAE,MAAM,CAAC;CACrB,CAAC;AAMN;;GAEG;AACH,eAAO,MAAM,uBAAuB;;;;EAAuC,CAAC;AAE5E;;GAEG;AACH,eAAO,MAAM,uBAAuB;;;;;;EAMlC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;iBAWhC,CAAC;AAEH,MAAM,MAAM,eAAe,GAAG,CAAC,CAAC,KAAK,CAAC,OAAO,qBAAqB,CAAC,CAAC;AAMpE;;GAEG;AACH,MAAM,WAAW,iBAAiB;IAChC,yBAAyB;IACzB,WAAW,EAAE,MAAM,CAAC;IACpB,8BAA8B;IAC9B,OAAO,EAAE,MAAM,CAAC;IAChB,+BAA+B;IAC/B,QAAQ,EAAE,MAAM,CAAC;IACjB,4BAA4B;IAC5B,UAAU,EAAE,IAAI,CAAC;IACjB,6BAA6B;IAC7B,IAAI,EAAE,CAAC,KAAK,EAAE,UAAU,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;CAC5C;AAMD;;;;;;;;;GASG;AACH,wBAAsB,sBAAsB,CAC1C,GAAG,EAAE,iBAAiB,EACtB,MAAM,EAAE,OAAO,EAAE,GAChB,OAAO,CAAC;IAAE,MAAM,EAAE,OAAO,CAAC;IAAC,MAAM,EAAE,eAAe,EAAE,CAAA;CAAE,CAAC,CA+BzD;AAED;;;;;;;GAOG;AACH,wBAAsB,WAAW,CAC/B,GAAG,EAAE,iBAAiB,EACtB,KAAK,EAAE,eAAe,GACrB,OAAO,CAAC,IAAI,CAAC,CAWf"}

package/dist/validators/index.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Validators - Event and schema validation utilities
+ *
+ * @module validators
+ */
+export * from "./schema-validator.js";
+//# sourceMappingURL=index.d.ts.map

package/dist/validators/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/validators/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAC"}

package/dist/validators/schema-validator.d.ts

@@ -0,0 +1,58 @@
+/**
+ * Event Schema Validator
+ *
+ * Validates emitted events against their Zod schemas.
+ * Catches:
+ * - Type mismatches
+ * - Missing required fields
+ * - Undefined values that could break UI rendering
+ * - Schema violations
+ *
+ * Used by:
+ * - Swarm event emission (validateEvent before emit)
+ * - Post-run validation (validateSwarmEvents for all events)
+ * - Debug tooling (identify schema drift)
+ */
+import type { ZodError } from "zod";
+export interface ValidationIssue {
+    severity: "error" | "warning";
+    category: "schema_mismatch" | "undefined_value" | "missing_field" | "type_error";
+    message: string;
+    location?: {
+        event_type?: string;
+        field?: string;
+    };
+    zodError?: ZodError;
+}
+export interface SchemaValidationResult {
+    valid: boolean;
+    issues: ValidationIssue[];
+}
+/**
+ * Validate a single event against its schema
+ *
+ * Usage:
+ * ```typescript
+ * const result = validateEvent(event);
+ * if (!result.valid) {
+ *   console.error("Schema validation failed:", result.issues);
+ * }
+ * ```
+ */
+export declare function validateEvent(event: unknown): SchemaValidationResult;
+/**
+ * Validate all events from a swarm run
+ *
+ * Usage:
+ * ```typescript
+ * const { passed, issueCount } = await validateSwarmEvents(events);
+ * if (!passed) {
+ *   console.error(`Found ${issueCount} validation issues`);
+ * }
+ * ```
+ */
+export declare function validateSwarmEvents(events: unknown[]): Promise<{
+    passed: boolean;
+    issueCount: number;
+}>;
+//# sourceMappingURL=schema-validator.d.ts.map

package/dist/validators/schema-validator.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"schema-validator.d.ts","sourceRoot":"","sources":["../../src/validators/schema-validator.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAGH,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,KAAK,CAAC;AAEpC,MAAM,WAAW,eAAe;IAC9B,QAAQ,EAAE,OAAO,GAAG,SAAS,CAAC;IAC9B,QAAQ,EACJ,iBAAiB,GACjB,iBAAiB,GACjB,eAAe,GACf,YAAY,CAAC;IACjB,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,CAAC,EAAE;QACT,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,KAAK,CAAC,EAAE,MAAM,CAAC;KAChB,CAAC;IACF,QAAQ,CAAC,EAAE,QAAQ,CAAC;CACrB;AAED,MAAM,WAAW,sBAAsB;IACrC,KAAK,EAAE,OAAO,CAAC;IACf,MAAM,EAAE,eAAe,EAAE,CAAC;CAC3B;AAED;;;;;;;;;;GAUG;AACH,wBAAgB,aAAa,CAAC,KAAK,EAAE,OAAO,GAAG,sBAAsB,CAkDpE;AAgCD;;;;;;;;;;GAUG;AACH,wBAAsB,mBAAmB,CACvC,MAAM,EAAE,OAAO,EAAE,GAChB,OAAO,CAAC;IAAE,MAAM,EAAE,OAAO,CAAC;IAAC,UAAU,EAAE,MAAM,CAAA;CAAE,CAAC,CAWlD"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-swarm-plugin",
-  "version": "0.44.0",
+  "version": "0.44.2",
   "description": "Multi-agent swarm coordination for OpenCode with learning capabilities, beads integration, and Agent Mail",
   "type": "module",
   "main": "./dist/index.js",
@@ -16,14 +16,27 @@
     "./plugin": {
       "import": "./dist/plugin.js",
       "types": "./dist/plugin.d.ts"
+    },
+    "./eval-capture": {
+      "import": "./dist/eval-capture.js",
+      "types": "./dist/eval-capture.d.ts"
+    },
+    "./compaction-prompt-scoring": {
+      "import": "./dist/compaction-prompt-scoring.js",
+      "types": "./dist/compaction-prompt-scoring.d.ts"
     }
   },
+  "files": [
+    "dist",
+    "bin",
+    "README.md"
+  ],
   "publishConfig": {
     "access": "public",
     "registry": "https://registry.npmjs.org/"
   },
   "scripts": {
-    "build": "bun build ./src/index.ts --outdir ./dist --target node --external @electric-sql/pglite --external swarm-mail --external vitest --external @vitest/ui --external lightningcss && bun build ./src/plugin.ts --outfile ./dist/plugin.js --target node --external @electric-sql/pglite --external swarm-mail --external vitest --external @vitest/ui --external lightningcss && tsc",
+    "build": "bun run scripts/build.ts",
     "dev": "bun --watch src/index.ts",
     "test": "bun test --timeout 10000 src/anti-patterns.test.ts src/mandate-promotion.test.ts src/mandate-storage.test.ts src/output-guardrails.test.ts src/pattern-maturity.test.ts src/skills.test.ts src/structured.test.ts src/schemas/",
     "test:integration": "bun test --timeout 60000 src/*.integration.test.ts",
@@ -56,11 +69,10 @@
     "@types/minimatch": "^6.0.0",
     "ai": "6.0.0-beta.150",
     "bun-types": "^1.3.4",
-    "evalite": "^1.0.0-beta.10",
+    "evalite": "^0.19.0",
     "pino-pretty": "^13.1.3",
     "turbo": "^2.6.3",
-    "typescript": "^5.7.0",
-    "vitest": "^4.0.15"
+    "typescript": "^5.7.0"
   },
   "peerDependencies": {
     "@opencode-ai/plugin": "^1.0.0"

package/.changeset/swarm-insights-data-layer.md

@@ -1,63 +0,0 @@
----
-"opencode-swarm-plugin": minor
----
-
-## 🧠 Swarm Insights: Data-Driven Decomposition
-
-> "It should allow the learner both to reflect on the quality of found solutions so that more effective cognitive schemata can be induced (including discriminations and generalizations) or further elaborated."
-> 
-> — *Training Complex Cognitive Skills: A Four-Component Instructional Design Model for Technical Training*
-
-**What changed:**
-
-New data layer (`swarm-insights.ts`) aggregates learnings from swarm coordination events to inform future decompositions. Coordinators and workers now get concise, context-efficient summaries injected into their prompts.
-
-**Key exports:**
-
-- `getStrategyInsights(swarmMail, task)` - Strategy success rates and recommendations
-  - Queries `subtask_outcome` events, calculates win/loss ratios
-  - Returns: `{ strategy, successRate, totalAttempts, recommendation }`
-  - Powers coordinator strategy selection with empirical data
-
-- `getFileInsights(swarmMail, files)` - File-specific gotchas from past failures
-  - Identifies files with high failure rates
-  - Returns: `{ file, failureCount, lastFailure, gotchas[] }`
-  - Workers see warnings about tricky files before touching them
-
-- `getPatternInsights(swarmMail)` - Common failure patterns and anti-patterns
-  - Detects recurring error types (type_error, timeout, conflict, test_failure)
-  - Returns: `{ pattern, frequency, recommendation }`
-  - Surfaces systemic issues for proactive prevention
-
-- `formatInsightsForPrompt(bundle, options)` - Context-aware formatting
-  - Token budget enforcement (default 500 tokens, ~2000 chars)
-  - Prioritizes top 3 strategies, 5 files, 3 patterns
-  - Clean markdown output for prompt injection
-
-- `getCachedInsights(swarmMail, cacheKey, computeFn)` - 5-minute TTL caching
-  - Prevents redundant queries during active swarms
-  - Transparent cache miss fallback
-
-**Why it matters:**
-
-Before this, coordinators decomposed tasks blind to past failures. "Split by file type" might have failed 8 times, but the coordinator would try it again. Workers would touch `auth/tokens.ts` without knowing it caused 3 prior failures.
-
-Now:
-- **Better decomposition**: Coordinator prompts show strategy success rates (e.g., "file-based: 85% success, feature-based: 40% - avoid")
-- **Fewer repeated mistakes**: Workers see file-specific warnings before editing
-- **Compounding learning**: Each swarm completion feeds the insights engine, improving future decompositions
-- **Context-efficient**: Hard token caps prevent insights from dominating prompt budgets
-
-The swarm now learns from its mistakes, not just records them.
-
-**Data sources:**
-- Event store: `subtask_outcome`, `eval_finalized` events
-- Semantic memory: File-specific learnings (TODO: full integration)
-- Anti-pattern registry: Detection and inversion rules
-
-**Integration points:**
-- Coordinator prompts: Inject strategy insights during decomposition
-- Worker prompts: Inject file insights when subtasks are spawned
-- Learning layer: Confidence decay, pattern maturity, implicit feedback scoring
-
-This is the foundation for adaptive swarm intelligence - decomposition that gets smarter with every task completed.

package/.hive/analysis/eval-failure-analysis-2025-12-25.md

@@ -1,331 +0,0 @@
-# Eval Failure Analysis Report
-**Date:** 2025-12-25
-**Analyst:** BrightStar
-**Cell:** opencode-swarm-plugin--ys7z8-mjlk7jsl4tt
-**Epic:** opencode-swarm-plugin--ys7z8-mjlk7js9bt1
-
-## Executive Summary
-
-Two eval failures analyzed:
-- **example.eval.ts**: 0% score - structural bug in eval setup
-- **compaction-prompt.eval.ts**: 53% score - case sensitivity + missing forbidden tools
-
-Both are fixable with code changes. No test data quality issues.
-
----
-
-## example.eval.ts - 0% Score
-
-### Status
-❌ **CRITICAL** - Complete failure (0%)
-
-### Root Cause
-**Eval structure mismatch** between data provider and task function.
-
-### Technical Details
-
-**File:** `evals/example.eval.ts`
-**Lines:** 14-30
-
-The eval has a fundamental flow error:
-
-```typescript
-// Line 14-26: data() provides BOTH input AND expected output
-data: async () => {
-  return [
-    {
-      input: "Test task",                    // ← String for task function
-      output: JSON.stringify({               // ← Expected output (ignored!)
-        epic: { title: "Test Epic", ... },
-        subtasks: [...]
-      }),
-    },
-  ];
-},
-
-// Line 28-30: task() does passthrough
-task: async (input) => {
-  return input;  // ← Returns "Test task" string, NOT the CellTree
-},
-
-// Line 31: Scorer expects CellTree JSON
-scorers: [subtaskIndependence],
-```
-
-**What happens:**
-1. Evalite passes `input` ("Test task") to task function
-2. Task returns "Test task" string unchanged
-3. Scorer `subtaskIndependence` receives "Test task"
-4. Scorer tries to parse as CellTree JSON → **FAILS**
-5. Score: 0%
-
-The `output` field in `data()` is ignored by Evalite - it's the `task()` return value that gets scored.
-
-### Impact
-- Example eval is useless for validation
-- False signal that scorer infrastructure is broken (it's not)
-- Wastes CI time
-
-### Proposed Fix
-
-**Option 1: Remove output from data (recommended)**
-```typescript
-data: async () => {
-  return [
-    {
-      input: {
-        epic: { title: "Test Epic", description: "Test" },
-        subtasks: [
-          { title: "Subtask 1", files: ["a.ts"], estimated_complexity: 1 },
-          { title: "Subtask 2", files: ["b.ts"], estimated_complexity: 1 },
-        ],
-      },
-    },
-  ];
-},
-
-task: async (input) => {
-  return JSON.stringify(input);  // Stringify the CellTree
-},
-```
-
-**Option 2: Fix task to use output**
-```typescript
-// Keep data() as-is, but fix task:
-task: async (input, context) => {
-  return context.expected.output;  // Use the output from data()
-},
-```
-
-Option 1 is cleaner - task functions should generate output, not just pass through.
-
----
-
-## compaction-prompt.eval.ts - 53% Score
-
-### Status
-⚠️ **DEGRADED** - Below target (53% vs 100% historical)
-
-### Root Causes
-
-#### RC1: Case-Sensitive Forbidden Tool Patterns (15% weight)
-
-**File:** `src/compaction-prompt-scoring.ts`
-**Lines:** 213-218
-
-```typescript
-const forbiddenTools = [
-  /\bEdit\b/,     // ← Requires capital E
-  /\bWrite\b/,    // ← Requires capital W
-  /swarmmail_reserve/,
-  /git commit/,
-];
-```
-
-**File:** `evals/fixtures/compaction-prompt-cases.ts`
-**Lines:** 76-83 (perfect fixture)
-
-```
-- edit      // ← lowercase e
-- write     // ← lowercase w
-- bash (for file modifications)
-```
-
-**Evidence:**
-```javascript
-/\bEdit\b/.test("- Edit")  // ✅ true
-/\bEdit\b/.test("- edit")  // ❌ false (word boundary + case)
-```
-
-**Impact:**
-- Perfect fixture: 0/4 forbidden tools matched
-- Forbidden tools scorer: 0% (should be 75-100%)
-- Overall impact: 15% of total score lost
-
-#### RC2: Missing Forbidden Tools (15% weight)
-
-Scorer expects **4 tools**:
-1. Edit (or edit)
-2. Write (or write)
-3. swarmmail_reserve
-4. git commit
-
-Perfect fixture has **3 tools** (and case mismatch):
-1. edit ❌ (lowercase)
-2. write ❌ (lowercase)
-3. bash ❌ (not in scorer's list)
-
-Missing: swarmmail_reserve, git commit
-
-**Impact:**
-- Even if case fixed, still only 2/4 tools = 50% on this scorer
-- Weighted: 50% × 15% = 7.5% contribution (should be 15%)
-
-#### RC3: "bash" Not in Scorer's List
-
-Fixtures mention "bash (for file modifications)" as forbidden, but scorer doesn't check for it.
-This creates a 3-way mismatch:
-- Fixture lists: edit, write, bash
-- Scorer checks: Edit, Write, swarmmail_reserve, git commit
-- Overlap: 0 tools (due to case)
-
-### Score Breakdown - Perfect Fixture
-
-Expected (if 100%):
-```
-epicIdSpecificity:        20% × 1.0 = 20%
-actionability:            20% × 1.0 = 20%
-coordinatorIdentity:      25% × 1.0 = 25%
-forbiddenToolsPresent:    15% × 1.0 = 15%
-postCompactionDiscipline: 20% × 1.0 = 20%
-                                 ─────
-TOTAL:                              100%
-```
-
-Actual (current):
-```
-epicIdSpecificity:        20% × 1.0 = 20% ✅
-actionability:            20% × 1.0 = 20% ✅
-coordinatorIdentity:      25% × 1.0 = 25% ✅
-forbiddenToolsPresent:    15% × 0.0 =  0% ❌ (0/4 matched)
-postCompactionDiscipline: 20% × 1.0 = 20% ✅
-                                 ─────
-TOTAL:                               85%
-```
-
-Perfect fixture alone should score 85%, but overall eval is 53%.
-This means the 5 "bad" fixtures are pulling average down further (expected behavior).
-
-### Historical Context
-
-Semantic memory claims 100% score previously. Likely scenarios:
-1. **Never actually ran** - aspiration documented before implementation
-2. **Ran with different fixtures** - fixtures were updated after scorer was written
-3. **Scorer was case-insensitive before** - regression in recent commit aa12943
-
-Commit aa12943 (2025-12-24) added the eval infrastructure. This is brand new code.
-
-### Proposed Fixes
-
-#### Fix 1: Make Scorer Case-Insensitive (Recommended)
-
-**File:** `src/compaction-prompt-scoring.ts`
-**Lines:** 213-218
-
-```typescript
-const forbiddenTools = [
-  /\bedit\b/i,              // Case insensitive with 'i' flag
-  /\bwrite\b/i,             // Case insensitive
-  /\bbash\b/i,              // Add bash (was missing)
-  /swarmmail_reserve/i,     // Keep, add 'i' for safety
-  /git commit/i,            // Keep, add 'i' for safety
-];
-```
-
-**Rationale:**
-- Coordinators might capitalize differently in prompts
-- Real prompts won't always match exact case
-- More robust matching
-
-#### Fix 2: Update Fixtures to Match Scorer (Alternative)
-
-**File:** `evals/fixtures/compaction-prompt-cases.ts`
-**Lines:** 76-83 (and all other fixtures)
-
-```
-- Edit                           // Capital E
-- Write                          // Capital W
-- bash (for file modifications)  // Keep or remove
-- swarmmail_reserve              // ADD
-- git commit                     // ADD
-```
-
-**Rationale:**
-- Keeps scorer strict (may catch real case issues)
-- Makes fixtures comprehensive (all 5 tools)
-- More explicit about what's forbidden
-
-#### Fix 3: Hybrid (Best of Both)
-
-1. Make scorer case-insensitive (Fix 1)
-2. Update fixtures to include all 5 tools (Fix 2)
-3. Remove "bash" from fixtures if not in coordinator forbidden list
-
-```typescript
-// Scorer (5 tools, case-insensitive):
-const forbiddenTools = [
-  /\bedit\b/i,
-  /\bwrite\b/i,
-  /swarmmail_reserve/i,
-  /git\s+commit/i,
-  /\bread\b/i,  // Consider adding - coordinators shouldn't read, should check status
-];
-```
-
-```
-// Fixture:
-- Edit
-- Write
-- swarmmail_reserve (only workers reserve files)
-- git commit (workers commit their changes)
-```
-
-### Risk Assessment
-
-**If we fix this, will scores jump to 100%?**
-
-**Perfect fixture:** 85% → 100% (if all 4 tools matched)
-**Other fixtures:** Depends on their issues
-
-Looking at fixture expected values:
-- Fixture 0 (perfect): Should be 100%
-- Fixture 1 (placeholder): Should fail (expected)
-- Fixture 2 (generic): Should fail (expected)
-- Fixture 3 (weak identity): Should partially fail (expected)
-- Fixture 4 (missing forbidden): Should fail on forbidden tools only
-- Fixture 5 (wrong first tool): Should fail on discipline only
-
-Average across 6 fixtures: ~66% expected (not 100%)
-
-**So 53% → ~70-80%** is realistic after fixes (not 100%).
-
-To get higher scores, need to fix issues in bad fixtures too, but those are SUPPOSED to fail.
-The scorer is working correctly on those.
-
----
-
-## Recommendations
-
-### Immediate Actions (P0)
-
-1. **Fix example.eval.ts structure** - 5 min fix, unblocks that eval
-2. **Make forbidden tools case-insensitive** - 5 min fix, +15-20% score boost
-3. **Add missing tools to fixtures** - 10 min, comprehensive coverage
-
-### Medium-term Actions (P1)
-
-4. **Verify 100% claim in semantic memory** - Check if historical data exists
-5. **Document scorer expectations** - Add comments to fixtures explaining weights
-6. **Add unit tests for scorers** - Test edge cases independently
-
-### Long-term Actions (P2)
-
-7. **Consider LLM-as-judge for semantic checks** - Case-insensitive by nature
-8. **Add visual diff in eval output** - Show what's missing from prompts
-9. **Create eval dashboard** - Track scores over time, detect regressions
-
----
-
-## Conclusion
-
-Both evals have **code bugs, not test data issues**:
-- example.eval.ts: Structural bug (task/data mismatch)
-- compaction-prompt.eval.ts: Case sensitivity + incomplete tool list
-
-Fixes are straightforward and low-risk. After fixes, expect:
-- example.eval.ts: 0% → 100%
-- compaction-prompt.eval.ts: 53% → 70-80%
-
-The 100% historical score in semantic memory is likely aspirational - these evals are brand new (commit aa12943, Dec 24).
-
-**Ready to implement fixes or escalate for review?**