moflo 4.8.16 → 4.8.17

package/src/@claude-flow/guidance/dist/conformance-kit.js

@@ -0,0 +1,629 @@
+/**
+ * Agent Cell Conformance Kit
+ *
+ * Canonical acceptance test proving the entire guidance control plane works
+ * end-to-end. Implements the "Memory Clerk" agent cell pattern:
+ *
+ * 1. Read 20 memory entries (knowledge retrieval)
+ * 2. Run 1 model inference (reasoning)
+ * 3. Propose 5 memory writes based on inference
+ * 4. Inject a coherence drop at write #3
+ * 5. Verify the system switches to read-only and blocks remaining writes
+ * 6. Emit a signed proof envelope
+ * 7. Return a complete, replayable trace
+ *
+ * @module @claude-flow/guidance/conformance-kit
+ */
+import { createHash, randomUUID } from 'node:crypto';
+import { createMemoryWriteGate, createMemoryEntry, } from './memory-gate.js';
+import { createProofChain } from './proof.js';
+import { createLedger } from './ledger.js';
+import { createCoherenceScheduler, createEconomicGovernor, } from './coherence.js';
+import { createToolGateway } from './gateway.js';
+// ============================================================================
+// Simulated Runtime
+// ============================================================================
+/**
+ * A test runtime that wires together all guidance control plane components
+ * and records every operation as a TraceEvent.
+ */
+export class SimulatedRuntime {
+    memoryGate;
+    proofChain;
+    ledger;
+    coherenceScheduler;
+    economicGovernor;
+    toolGateway;
+    authority;
+    coherenceScore;
+    memoryStore = new Map();
+    memoryEntries = [];
+    traceEvents = [];
+    coherenceHistory = [];
+    seq = 0;
+    memoryReadCount = 0;
+    memoryWritesAttemptedCount = 0;
+    memoryWritesCommittedCount = 0;
+    memoryWritesBlockedCount = 0;
+    memoryOps = [];
+    constructor(config) {
+        this.memoryGate = config.memoryGate;
+        this.proofChain = config.proofChain;
+        this.ledger = config.ledger;
+        this.coherenceScheduler = config.coherenceScheduler;
+        this.economicGovernor = config.economicGovernor;
+        this.toolGateway = config.toolGateway ?? createToolGateway();
+        this.authority = config.authority;
+        this.coherenceScore = config.initialCoherenceScore ?? 0.9;
+        if (config.initialMemory) {
+            for (const [key, entry] of config.initialMemory) {
+                this.memoryStore.set(`${entry.namespace}:${key}`, entry);
+            }
+        }
+    }
+    // =========================================================================
+    // CellRuntime implementation
+    // =========================================================================
+    readMemory(key, namespace) {
+        this.memoryReadCount++;
+        const storeKey = `${namespace}:${key}`;
+        const entry = this.memoryStore.get(storeKey);
+        const value = entry?.value ?? null;
+        const valueHash = createHash('sha256')
+            .update(JSON.stringify(value))
+            .digest('hex');
+        this.memoryOps.push({
+            key,
+            namespace,
+            operation: 'read',
+            valueHash,
+            timestamp: Date.now(),
+        });
+        this.emitTrace('memory_read', { key, namespace, found: entry !== undefined }, 'read_allowed');
+        this.economicGovernor.recordToolCall('memory_read', 1);
+        return value;
+    }
+    writeMemory(key, namespace, value, evidence) {
+        this.memoryWritesAttemptedCount++;
+        // Emit proposal trace
+        this.emitTrace('memory_write_proposed', {
+            key,
+            namespace,
+            valuePreview: typeof value === 'string' ? value.slice(0, 100) : typeof value,
+            evidence: evidence ?? {},
+        }, 'proposed');
+        // Check coherence before allowing the write
+        const privilegeLevel = this.resolvePrivilegeLevel(this.coherenceScore);
+        this.emitTrace('coherence_check', { score: this.coherenceScore, privilegeLevel }, privilegeLevel);
+        if (privilegeLevel === 'read-only' || privilegeLevel === 'suspended') {
+            this.memoryWritesBlockedCount++;
+            const reason = `Write blocked: privilege level is "${privilegeLevel}" (coherence: ${this.coherenceScore.toFixed(3)})`;
+            this.emitTrace('memory_write_blocked', {
+                key,
+                namespace,
+                privilegeLevel,
+                coherenceScore: this.coherenceScore,
+            }, 'blocked_coherence');
+            return { allowed: false, reason };
+        }
+        // Evaluate through the MemoryWriteGate
+        const decision = this.memoryGate.evaluateWrite(this.authority, key, namespace, value, this.memoryEntries);
+        if (!decision.allowed) {
+            this.memoryWritesBlockedCount++;
+            this.emitTrace('memory_write_blocked', { key, namespace, gateReason: decision.reason }, 'blocked_gate');
+            return { allowed: false, reason: decision.reason };
+        }
+        // Commit the write
+        this.memoryWritesCommittedCount++;
+        const storeKey = `${namespace}:${key}`;
+        this.memoryStore.set(storeKey, { namespace, value });
+        const entry = createMemoryEntry(key, namespace, value, this.authority);
+        this.memoryEntries.push(entry);
+        const valueHash = createHash('sha256')
+            .update(JSON.stringify(value))
+            .digest('hex');
+        this.memoryOps.push({
+            key,
+            namespace,
+            operation: 'write',
+            valueHash,
+            timestamp: Date.now(),
+        });
+        this.emitTrace('memory_write_committed', { key, namespace, valueHash }, 'committed');
+        this.economicGovernor.recordToolCall('memory_write', 2);
+        this.economicGovernor.recordStorageUsage(Buffer.byteLength(JSON.stringify(value), 'utf-8'));
+        return { allowed: true, reason: 'Write committed' };
+    }
+    invokeModel(prompt) {
+        const tokens = Math.ceil(prompt.length / 4) + 50;
+        this.economicGovernor.recordTokenUsage(tokens);
+        const response = `[Simulated inference for: ${prompt.slice(0, 50)}...]`;
+        this.emitTrace('model_infer', {
+            promptLength: prompt.length,
+            responseLength: response.length,
+            tokensEstimated: tokens,
+        }, 'inference_complete');
+        return response;
+    }
+    invokeTool(name, params) {
+        const decision = this.toolGateway.evaluate(name, params);
+        this.emitTrace('tool_invoke', {
+            toolName: name,
+            params,
+            allowed: decision.allowed,
+            gate: decision.gate,
+        }, decision.allowed ? 'allowed' : 'blocked');
+        if (!decision.allowed) {
+            return { result: null, allowed: false };
+        }
+        const result = { status: 'ok', tool: name };
+        this.toolGateway.recordCall(name, params, result, 10);
+        this.economicGovernor.recordToolCall(name, 10);
+        return { result, allowed: true };
+    }
+    getCoherenceScore() {
+        return this.coherenceScore;
+    }
+    setCoherenceScore(score) {
+        const previousScore = this.coherenceScore;
+        this.coherenceScore = score;
+        this.coherenceHistory.push(score);
+        const previousLevel = this.resolvePrivilegeLevel(previousScore);
+        const newLevel = this.resolvePrivilegeLevel(score);
+        if (previousLevel !== newLevel) {
+            this.emitTrace('privilege_change', { previousScore, newScore: score, previousLevel, newLevel }, `${previousLevel}->${newLevel}`);
+        }
+    }
+    getProofChain() {
+        return this.proofChain;
+    }
+    getLedger() {
+        return this.ledger;
+    }
+    // =========================================================================
+    // Public trace emission (used by cells for run_start / run_end)
+    // =========================================================================
+    /**
+     * Emit a custom trace event. Exposed so agent cells can record
+     * lifecycle events (run_start, run_end) through the same trace stream.
+     */
+    emitCustomTrace(type, payload, decision) {
+        this.emitTrace(type, payload, decision);
+    }
+    // =========================================================================
+    // Accessors for test inspection
+    // =========================================================================
+    getTraceEvents() {
+        return [...this.traceEvents];
+    }
+    getCoherenceHistory() {
+        return [...this.coherenceHistory];
+    }
+    getMemoryReads() {
+        return this.memoryReadCount;
+    }
+    getMemoryWritesAttempted() {
+        return this.memoryWritesAttemptedCount;
+    }
+    getMemoryWritesCommitted() {
+        return this.memoryWritesCommittedCount;
+    }
+    getMemoryWritesBlocked() {
+        return this.memoryWritesBlockedCount;
+    }
+    getMemoryOps() {
+        return [...this.memoryOps];
+    }
+    getBudgetUsage() {
+        const usage = this.economicGovernor.getUsageSummary();
+        return {
+            tokens: usage.tokens.used,
+            toolCalls: usage.toolCalls.used,
+            storageBytes: usage.storage.usedBytes,
+            timeMs: usage.time.usedMs,
+            costUsd: usage.cost.totalUsd,
+        };
+    }
+    // =========================================================================
+    // Private helpers
+    // =========================================================================
+    resolvePrivilegeLevel(score) {
+        const thresholds = this.coherenceScheduler.getThresholds();
+        if (score >= thresholds.healthyThreshold)
+            return 'full';
+        if (score >= thresholds.warningThreshold)
+            return 'restricted';
+        if (score >= thresholds.readOnlyThreshold)
+            return 'read-only';
+        return 'suspended';
+    }
+    emitTrace(type, payload, decision) {
+        const usage = this.economicGovernor.getUsageSummary();
+        const event = {
+            seq: this.seq++,
+            ts: Date.now(),
+            type,
+            payload,
+            decision,
+            budgetSnapshot: {
+                tokens: usage.tokens.used,
+                toolCalls: usage.toolCalls.used,
+                storageBytes: usage.storage.usedBytes,
+            },
+        };
+        this.traceEvents.push(event);
+    }
+}
+// ============================================================================
+// Memory Clerk Cell
+// ============================================================================
+/**
+ * The canonical test agent cell. Exercises every layer of the guidance
+ * control plane by performing reads, inference, and gated writes with
+ * a deliberate coherence drop mid-run.
+ */
+export class MemoryClerkCell {
+    cellId;
+    name = 'MemoryClerk';
+    readCount;
+    inferenceCount;
+    writeCount;
+    coherenceDropAtWrite;
+    droppedCoherenceScore;
+    constructor(cellId, options) {
+        this.cellId = cellId ?? `cell-${randomUUID()}`;
+        this.readCount = options?.readCount ?? 20;
+        this.inferenceCount = options?.inferenceCount ?? 1;
+        this.writeCount = options?.writeCount ?? 5;
+        this.coherenceDropAtWrite = options?.coherenceDropAtWrite ?? 3;
+        this.droppedCoherenceScore = options?.droppedCoherenceScore ?? 0.2;
+    }
+    run(runtime) {
+        const runId = `run-${randomUUID()}`;
+        const startTime = Date.now();
+        const sim = runtime;
+        // ----- Step 1: run_start -----
+        sim.emitCustomTrace('run_start', { cellId: this.cellId, runId, name: this.name }, 'started');
+        const coherenceHistory = [runtime.getCoherenceScore()];
+        // ----- Step 2: 20 memory reads -----
+        for (let i = 0; i < this.readCount; i++) {
+            runtime.readMemory(`knowledge-${i}`, 'clerk-workspace');
+        }
+        coherenceHistory.push(runtime.getCoherenceScore());
+        // ----- Step 3: Model inference -----
+        let inferenceResult = '';
+        for (let i = 0; i < this.inferenceCount; i++) {
+            inferenceResult = runtime.invokeModel(`Analyze the ${this.readCount} knowledge entries and determine ` +
+                `which ${this.writeCount} insights to persist.`);
+        }
+        coherenceHistory.push(runtime.getCoherenceScore());
+        // ----- Steps 4-7: Propose writes with coherence drop -----
+        let writesCommitted = 0;
+        let writesBlocked = 0;
+        for (let i = 1; i <= this.writeCount; i++) {
+            // Inject coherence drop just before the target write
+            if (i === this.coherenceDropAtWrite) {
+                runtime.setCoherenceScore(this.droppedCoherenceScore);
+            }
+            coherenceHistory.push(runtime.getCoherenceScore());
+            const result = runtime.writeMemory(`insight-${i}`, 'clerk-workspace', {
+                insightId: i,
+                content: `Insight #${i} derived from model inference`,
+                inferenceRef: inferenceResult.slice(0, 20),
+                timestamp: Date.now(),
+            }, { source: 'model_inference', writeIndex: i });
+            if (result.allowed) {
+                writesCommitted++;
+            }
+            else {
+                writesBlocked++;
+            }
+        }
+        // ----- Step 8: Emit proof envelope -----
+        const event = runtime.getLedger().createEvent(`task-${this.cellId}`, 'general', 'conformance-test');
+        event.toolsUsed = ['memory_read', 'memory_write', 'model_infer'];
+        event.filesTouched = [];
+        runtime.getLedger().finalizeEvent(event);
+        const proofEnvelope = runtime.getProofChain().append(event, [], sim.getMemoryOps(), { agentId: this.cellId, sessionId: runId });
+        const proofEnvelopeHash = proofEnvelope.contentHash;
+        // Determine final outcome
+        let outcome = 'completed';
+        if (writesBlocked > 0 && writesCommitted > 0) {
+            outcome = 'restricted';
+        }
+        else if (writesBlocked > 0 && writesCommitted === 0) {
+            outcome = 'suspended';
+        }
+        // ----- Step 9: run_end -----
+        sim.emitCustomTrace('run_end', {
+            cellId: this.cellId,
+            runId,
+            outcome,
+            duration: Date.now() - startTime,
+            writesCommitted,
+            writesBlocked,
+        }, outcome);
+        return {
+            cellId: this.cellId,
+            runId,
+            traceEvents: sim.getTraceEvents(),
+            memoryReads: sim.getMemoryReads(),
+            memoryWritesAttempted: sim.getMemoryWritesAttempted(),
+            memoryWritesCommitted: sim.getMemoryWritesCommitted(),
+            memoryWritesBlocked: sim.getMemoryWritesBlocked(),
+            proofEnvelopeHash,
+            coherenceHistory,
+            budgetUsage: sim.getBudgetUsage(),
+            outcome,
+        };
+    }
+}
+// ============================================================================
+// Conformance Runner
+// ============================================================================
+/**
+ * Orchestrates conformance tests by creating all control plane components,
+ * running the MemoryClerkCell, and verifying every invariant.
+ */
+export class ConformanceRunner {
+    authority;
+    signingKey;
+    constructor(authority, signingKey) {
+        if (!signingKey) {
+            throw new Error('ConformanceRunner requires an explicit signingKey');
+        }
+        this.signingKey = signingKey;
+        this.authority = authority ?? {
+            agentId: 'memory-clerk-agent',
+            role: 'worker',
+            namespaces: ['clerk-workspace'],
+            maxWritesPerMinute: 100,
+            canDelete: false,
+            canOverwrite: true,
+            trustLevel: 0.8,
+        };
+    }
+    /**
+     * Run the full conformance test suite and return a structured result
+     * with individual pass/fail checks.
+     */
+    runConformanceTest() {
+        const startTime = Date.now();
+        const checks = [];
+        // Assemble the control plane
+        const memoryGate = createMemoryWriteGate({
+            authorities: [this.authority],
+            enableContradictionTracking: false,
+        });
+        const proofChain = createProofChain({ signingKey: this.signingKey });
+        const ledger = createLedger();
+        const coherenceScheduler = createCoherenceScheduler();
+        const economicGovernor = createEconomicGovernor({
+            tokenLimit: 100_000,
+            toolCallLimit: 1_000,
+        });
+        const runtime = new SimulatedRuntime({
+            memoryGate,
+            proofChain,
+            ledger,
+            coherenceScheduler,
+            economicGovernor,
+            authority: this.authority,
+            initialCoherenceScore: 0.9,
+        });
+        const cell = new MemoryClerkCell();
+        const result = cell.run(runtime);
+        // ----- Check 1: Exactly 20 memory reads -----
+        checks.push({
+            name: 'memory_reads_count',
+            passed: result.memoryReads === 20,
+            expected: 20,
+            actual: result.memoryReads,
+            details: `Expected 20 memory reads, got ${result.memoryReads}`,
+        });
+        // ----- Check 2: 5 memory writes attempted -----
+        checks.push({
+            name: 'memory_writes_attempted',
+            passed: result.memoryWritesAttempted === 5,
+            expected: 5,
+            actual: result.memoryWritesAttempted,
+            details: `Expected 5 write attempts, got ${result.memoryWritesAttempted}`,
+        });
+        // ----- Check 3: First 2 writes committed -----
+        checks.push({
+            name: 'memory_writes_committed',
+            passed: result.memoryWritesCommitted === 2,
+            expected: 2,
+            actual: result.memoryWritesCommitted,
+            details: `Expected 2 committed writes (writes 1-2 before coherence drop), got ${result.memoryWritesCommitted}`,
+        });
+        // ----- Check 4: Last 3 writes blocked -----
+        checks.push({
+            name: 'memory_writes_blocked',
+            passed: result.memoryWritesBlocked === 3,
+            expected: 3,
+            actual: result.memoryWritesBlocked,
+            details: `Expected 3 blocked writes (writes 3-5 after coherence drop), got ${result.memoryWritesBlocked}`,
+        });
+        // ----- Check 5: Proof envelope hash is valid SHA-256 hex -----
+        const isValidHash = typeof result.proofEnvelopeHash === 'string' &&
+            /^[0-9a-f]{64}$/.test(result.proofEnvelopeHash);
+        checks.push({
+            name: 'proof_envelope_hash',
+            passed: isValidHash,
+            expected: 'SHA-256 hex string (64 chars)',
+            actual: result.proofEnvelopeHash,
+            details: `Hash length: ${result.proofEnvelopeHash.length}, valid hex: ${isValidHash}`,
+        });
+        // ----- Check 6: Sequential seq numbers -----
+        let seqValid = true;
+        let seqErrorAt = -1;
+        for (let i = 0; i < result.traceEvents.length; i++) {
+            if (result.traceEvents[i].seq !== i) {
+                seqValid = false;
+                seqErrorAt = i;
+                break;
+            }
+        }
+        checks.push({
+            name: 'sequential_seq_numbers',
+            passed: seqValid,
+            expected: 'Sequential 0..N',
+            actual: seqValid
+                ? `0..${result.traceEvents.length - 1}`
+                : `Gap at index ${seqErrorAt} (seq=${result.traceEvents[seqErrorAt]?.seq})`,
+            details: seqValid
+                ? `All ${result.traceEvents.length} events have sequential seq numbers`
+                : `Sequence breaks at index ${seqErrorAt}`,
+        });
+        // ----- Check 7: Budget tracking is consistent -----
+        const budgetValid = result.budgetUsage.tokens > 0 && result.budgetUsage.toolCalls > 0;
+        checks.push({
+            name: 'budget_tracking_consistent',
+            passed: budgetValid,
+            expected: 'Non-zero token and tool call usage',
+            actual: result.budgetUsage,
+            details: `tokens=${result.budgetUsage.tokens}, toolCalls=${result.budgetUsage.toolCalls}, storageBytes=${result.budgetUsage.storageBytes}`,
+        });
+        // ----- Check 8: Outcome is "restricted" -----
+        checks.push({
+            name: 'outcome_restricted',
+            passed: result.outcome === 'restricted',
+            expected: 'restricted',
+            actual: result.outcome,
+            details: 'Expected "restricted" when some writes committed and some blocked',
+        });
+        // ----- Check 9: Proof chain integrity -----
+        const chainValid = proofChain.verifyChain();
+        checks.push({
+            name: 'proof_chain_valid',
+            passed: chainValid,
+            expected: true,
+            actual: chainValid,
+            details: 'Full proof chain HMAC and hash-chain verification',
+        });
+        // ----- Check 10: Trace has run_start and run_end bookends -----
+        const hasRunStart = result.traceEvents.some((e) => e.type === 'run_start');
+        const hasRunEnd = result.traceEvents.some((e) => e.type === 'run_end');
+        checks.push({
+            name: 'trace_bookends',
+            passed: hasRunStart && hasRunEnd,
+            expected: 'run_start and run_end present',
+            actual: { hasRunStart, hasRunEnd },
+            details: `run_start=${hasRunStart}, run_end=${hasRunEnd}`,
+        });
+        // ----- Check 11: Coherence history records the drop -----
+        const hasCoherenceDrop = result.coherenceHistory.some((s) => s < 0.3);
+        checks.push({
+            name: 'coherence_drop_recorded',
+            passed: hasCoherenceDrop,
+            expected: 'At least one coherence score below 0.3',
+            actual: result.coherenceHistory,
+            details: `Min coherence: ${Math.min(...result.coherenceHistory).toFixed(3)}`,
+        });
+        const allPassed = checks.every((c) => c.passed);
+        return {
+            passed: allPassed,
+            checks,
+            trace: result.traceEvents,
+            proofHash: result.proofEnvelopeHash,
+            duration: Date.now() - startTime,
+        };
+    }
+    /**
+     * Replay a previously captured trace and verify that every decision
+     * is reproduced identically by the control plane logic.
+     */
+    runReplayTest(originalTrace) {
+        const coherenceScheduler = createCoherenceScheduler();
+        const thresholds = coherenceScheduler.getThresholds();
+        const divergences = [];
+        for (const event of originalTrace) {
+            let replayDecision;
+            switch (event.type) {
+                case 'memory_read':
+                    replayDecision = 'read_allowed';
+                    break;
+                case 'memory_write_proposed':
+                    replayDecision = 'proposed';
+                    break;
+                case 'coherence_check': {
+                    const score = event.payload.score;
+                    if (score >= thresholds.healthyThreshold) {
+                        replayDecision = 'full';
+                    }
+                    else if (score >= thresholds.warningThreshold) {
+                        replayDecision = 'restricted';
+                    }
+                    else if (score >= thresholds.readOnlyThreshold) {
+                        replayDecision = 'read-only';
+                    }
+                    else {
+                        replayDecision = 'suspended';
+                    }
+                    break;
+                }
+                case 'memory_write_committed':
+                    replayDecision = 'committed';
+                    break;
+                case 'memory_write_blocked': {
+                    const hasPrivilegeLevel = event.payload.privilegeLevel !== undefined;
+                    replayDecision = hasPrivilegeLevel
+                        ? 'blocked_coherence'
+                        : 'blocked_gate';
+                    break;
+                }
+                case 'model_infer':
+                    replayDecision = 'inference_complete';
+                    break;
+                case 'tool_invoke':
+                    replayDecision = event.payload.allowed
+                        ? 'allowed'
+                        : 'blocked';
+                    break;
+                case 'privilege_change': {
+                    const prev = event.payload.previousLevel;
+                    const next = event.payload.newLevel;
+                    replayDecision = `${prev}->${next}`;
+                    break;
+                }
+                case 'run_start':
+                    replayDecision = 'started';
+                    break;
+                case 'run_end':
+                    replayDecision = event.payload.outcome;
+                    break;
+                default:
+                    replayDecision = 'unknown';
+            }
+            if (replayDecision !== event.decision) {
+                divergences.push({
+                    seq: event.seq,
+                    originalDecision: event.decision,
+                    replayDecision,
+                });
+            }
+        }
+        return {
+            identical: divergences.length === 0,
+            totalEvents: originalTrace.length,
+            divergences,
+        };
+    }
+}
+// ============================================================================
+// Factory Functions
+// ============================================================================
+/**
+ * Create a MemoryClerkCell with an optional cellId override.
+ */
+export function createMemoryClerkCell(cellId) {
+    return new MemoryClerkCell(cellId);
+}
+/**
+ * Create a ConformanceRunner with optional authority override.
+ */
+export function createConformanceRunner(authority, signingKey) {
+    return new ConformanceRunner(authority, signingKey ?? 'conformance-test-key');
+}
+//# sourceMappingURL=conformance-kit.js.map