switchboard-cli 0.1.0-alpha.2 → 0.1.0-alpha.4

package/calibration/ledger/runs/2026-04-09T10-11-28-692Z/traces/blind-aa04e10023e9.yaml

@@ -1,146 +0,0 @@
-seed_id: blind-aa04e10023e9
-outcome: completed
-rejection_point: ""
-rejection_reason: ""
-complexity_score: 2
-selected_mode: minimal
-assumptions_count: 2
-routed_surface: claude-code-sdk
-routing_rationale: "Selected Claude Code (SDK) (score: 75). Fallback: Codex
-  (execution) (score: 25). Disqualified: openai-api (Needs execute, provider
-  offers compile.), chatgpt-auto (Needs execute, provider offers compile.),
-  internal-fallback (Needs execute, provider offers compile.)."
-return_mode: honest
-return_mode_sealed: true
-reconcile_findings_count: 3
-reconcile_drift_detected: true
-reconcile_recommendation: accept-with-warnings
-gates_triggered: []
-gate_label: accepted-with-cautions
-spread_score: 0.11249999999999999
-spread_vector:
-  claim_mismatch_ratio: 0.25
-  audit_burden: 0
-  residual_weight: 0
-  provenance_weakness: 0
-  gate_distance: 0.25
-  trace_failure_signal: 0
-  budget_correction_weight: 0
-trust_posture: cautioned
-receipt_verdict: accepted-with-cautions
-honesty_violations: []
-duration_ms: 8
-compiled_spec: >
-  # A CLI tool that counts lines of code in a directory, outputting a summary
-  table by file extension
-
-
-  ## What this product is
-
-
-  Build a cli tool that counts lines of code in a directory, outputting a
-  summary table by file extension as a bounded V1 slice.
-
-
-  ## Who it is for
-
-
-  Solo builders shipping software.
-
-
-  ## The problem
-
-
-  A CLI tool that counts lines of code in a directory, outputting a summary
-  table by file extension
-
-
-  ## The proposed solution
-
-
-  Build a cli tool that counts lines of code in a directory, outputting a
-  summary table by file extension as a bounded V1 slice. This is a bounded V1
-  slice focused on proving the core value proposition with minimal surface area.
-
-
-  ## V1 promise
-
-
-  A working first slice of a cli tool that counts lines of code in a directory,
-  outputting a summary table by file extension.
-
-
-  ## Scope in
-
-
-  - A CLI tool that counts lines of code in a directory, outputting a summary
-  table by file extension
-
-  - Keep the primary artifact aligned with the V1 promise.
-
-  - Touch only files necessary for the first build slice.
-
-
-  ## Scope out
-
-
-  - Not a generic chat wrapper
-
-
-  ## First build slice
-
-
-  A CLI tool that counts lines of code in a directory, outputting a summary
-  table by file extension
-
-
-  Systems expected: CLI, Node.js.
-
-
-  Constraints to respect:
-
-  - No additional constraints.
-
-
-  ## Acceptance criteria
-
-
-  - Seed is valid and the idea has been compiled into a governed contract.
-
-  - Primary artifact is execution-ready: the build slice works as described.
-
-  - Next surface is explicit with a return condition.
-
-  - Handoff is launchable as an SBX bundle.
-
-
-  ## Open questions
-
-
-  - None identified.
-
-
-  ## What must not change (intent anchors)
-
-
-  - Not a generic chat wrapper
-
-
-  These are non-negotiable boundaries. Any execution that touches these areas
-  must be flagged for review.
-
-
-  ## Key risks and unknowns
-
-
-  Confidence is medium — some assumptions remain unconfirmed.
-
-
-  - Is the scope narrow enough to deliver in a single bounded execution?
-
-  - Are there hidden dependencies that could expand the build slice?
-
-  - Return condition: all done_when criteria met or blocker encountered.
-receipt_summary: "Completed: Build the first slice: A CLI tool that counts lines
-  of code in a directory, outputting a summary table by file extension. All
-  done_when criteria satisfied. Implementation follows the projec"

package/calibration/ledger/runs/2026-04-09T10-11-28-692Z/verdicts-a/adv-056e52eb6d09.yaml

@@ -1,24 +0,0 @@
-seed_id: adv-056e52eb6d09
-verdict: pass
-trust_posture: cautioned
-gate_label: accepted-with-cautions
-spread_score: 0.11249999999999999
-reconcile_drift: true
-gates_triggered: []
-threshold_proximity:
-  spread_0.3:
-    threshold: 0.3
-    actual: 0.11249999999999999
-    margin: 0.1875
-  spread_0.5:
-    threshold: 0.5
-    actual: 0.11249999999999999
-    margin: 0.3875
-  spread_0.7:
-    threshold: 0.7
-    actual: 0.11249999999999999
-    margin: 0.5875
-justification: "Pipeline outcome: completed. Trust posture: cautioned. Spread
-  score: 0.112. Reconciliation detected drift. Reconcile findings: 3. Verdict:
-  pass."
-scored_at: 2026-04-09T10:11:28.712Z

package/calibration/ledger/runs/2026-04-09T10-11-28-692Z/verdicts-a/blind-aa04e10023e9.yaml

@@ -1,24 +0,0 @@
-seed_id: blind-aa04e10023e9
-verdict: pass
-trust_posture: cautioned
-gate_label: accepted-with-cautions
-spread_score: 0.11249999999999999
-reconcile_drift: true
-gates_triggered: []
-threshold_proximity:
-  spread_0.3:
-    threshold: 0.3
-    actual: 0.11249999999999999
-    margin: 0.1875
-  spread_0.5:
-    threshold: 0.5
-    actual: 0.11249999999999999
-    margin: 0.3875
-  spread_0.7:
-    threshold: 0.7
-    actual: 0.11249999999999999
-    margin: 0.5875
-justification: "Pipeline outcome: completed. Trust posture: cautioned. Spread
-  score: 0.112. Reconciliation detected drift. Reconcile findings: 3. Verdict:
-  pass."
-scored_at: 2026-04-09T10:11:28.703Z

package/calibration/ledger/runs/2026-04-09T10-11-28-692Z/verdicts-b/adv-056e52eb6d09.yaml

@@ -1,31 +0,0 @@
-seed_id: adv-056e52eb6d09
-verdict: inconclusive
-dimensions:
-  intent_fidelity:
-    score: 0.071
-    justification: "Keyword overlap between seed and spec: 7.1% (Jaccard). Spec
-      introduces significant concepts beyond the seed (92 extra keywords out of
-      99)."
-  confidence_honesty:
-    score: 1
-    justification: Trust posture language is consistent with the evidence visible in
-      the receipt summary. No banned terms detected.
-  scope_discipline:
-    score: 0.6
-    justification: "Significant scope creep: 92 concepts in spec are not traceable
-      to the seed."
-  execution_readiness:
-    score: 0.45
-    justification: Spec lacks concrete indicators like file paths, commands, or
-      specific technical references. Output has structured format (steps, lists,
-      or headings).
-  self_awareness:
-    score: 0.8
-    justification: Output acknowledges multiple limitations or uncertainties
-      (unknown, risk, open question, constraint). This indicates honest
-      self-assessment.
-composite_score: 0.575
-justification: "Composite score 0.575 (threshold: pass >= 0.7, fail < 0.4).
-  Intent fidelity: 0.07, Confidence honesty: 1.00, Scope discipline: 0.60,
-  Execution readiness: 0.45, Self-awareness: 0.80."
-scored_at: 2026-04-09T10:11:28.713Z

package/calibration/ledger/runs/2026-04-09T10-11-28-692Z/verdicts-b/blind-aa04e10023e9.yaml

@@ -1,32 +0,0 @@
-seed_id: blind-aa04e10023e9
-verdict: inconclusive
-dimensions:
-  intent_fidelity:
-    score: 0.107
-    justification: "Keyword overlap between seed and spec: 10.7% (Jaccard). Spec
-      introduces significant concepts beyond the seed (92 extra keywords out of
-      103)."
-  confidence_honesty:
-    score: 1
-    justification: Trust posture language is consistent with the evidence visible in
-      the receipt summary. No banned terms detected.
-  scope_discipline:
-    score: 0.6
-    justification: "Significant scope creep: 92 concepts in spec are not traceable
-      to the seed."
-  execution_readiness:
-    score: 0.45
-    justification: Spec lacks concrete indicators like file paths, commands, or
-      specific technical references. Output has structured format (steps, lists,
-      or headings).
-  self_awareness:
-    score: 0.65
-    justification: Output acknowledges multiple limitations or uncertainties
-      (unknown, assumption, risk, open question, constraint). This indicates
-      honest self-assessment. Receipt summary contains no caveats, warnings, or
-      notes, which is suspicious for any non-trivial output.
-composite_score: 0.562
-justification: "Composite score 0.562 (threshold: pass >= 0.7, fail < 0.4).
-  Intent fidelity: 0.11, Confidence honesty: 1.00, Scope discipline: 0.60,
-  Execution readiness: 0.45, Self-awareness: 0.65."
-scored_at: 2026-04-09T10:11:28.706Z

package/node_modules/@switchboard/core/package.json

@@ -1,20 +0,0 @@
-{
-  "name": "@switchboard/core",
-  "version": "0.1.0-alpha.1",
-  "description": "Switchboard core — governance schemas, gates, reconciliation, receipts, trust machinery",
-  "license": "MIT",
-  "main": "src/index.ts",
-  "types": "src/index.ts",
-  "files": [
-    "src/"
-  ],
-  "scripts": {
-    "build": "tsc --outDir dist",
-    "lint": "echo 'linted core'",
-    "typecheck": "tsc --noEmit",
-    "test": "vitest run"
-  },
-  "dependencies": {
-    "zod": "^3.24.2"
-  }
-}

package/node_modules/@switchboard/core/src/activation.ts

@@ -1,285 +0,0 @@
-import type {
-  ActivationInput,
-  ActivationResult,
-  Assumption,
-  DangerousGate,
-  ModeScoring,
-  NonFunctionalGate,
-  ProcessMode,
-  SynthesizedSeed,
-  WorkflowCanvas,
-} from "./types";
-import { activationResultSchema } from "./types";
-
-function compact(text: string): string {
-  return text.replace(/\s+/g, " ").trim();
-}
-
-let _ctr = 0;
-function aId(): string { return `asmp-${++_ctr}-${Date.now().toString(36)}`; }
-
-// ---------------------------------------------------------------------------
-// 1. Assumption Register
-// ---------------------------------------------------------------------------
-
-export function buildAssumptions(seed: SynthesizedSeed, input: ActivationInput): Assumption[] {
-  const assumptions: Assumption[] = [];
-
-  // Open questions → unconfirmed assumptions
-  for (const q of seed.open_questions) {
-    assumptions.push({
-      id: aId(), text: q, status: "unconfirmed",
-      evidence_type: "weak-inference", risk_level: "medium", source: "user-question",
-    });
-  }
-
-  // Missing inputs → high-risk unconfirmed assumptions
-  for (const m of seed.missing_inputs) {
-    assumptions.push({
-      id: aId(), text: m, status: "unconfirmed",
-      evidence_type: "weak-inference", risk_level: "high", source: "missing-input",
-    });
-  }
-
-  // If target user is generic → assumption about audience
-  if (seed.target_user === "Solo builders shipping software.") {
-    assumptions.push({
-      id: aId(), text: "Target user is assumed to be solo builders (not explicitly stated).",
-      status: "unconfirmed", evidence_type: "weak-inference", risk_level: "medium", source: "inference",
-    });
-  }
-
-  // If no repo → assumption about starting fresh
-  if (!input.repo_exists) {
-    assumptions.push({
-      id: aId(), text: "No existing codebase — starting from scratch.",
-      status: "confirmed", evidence_type: "user-backed", risk_level: "low", source: "user-input",
-    });
-  }
-
-  return assumptions;
-}
-
-// ---------------------------------------------------------------------------
-// 2. Workflow Grounding Canvas
-// ---------------------------------------------------------------------------
-
-const USER_PATTERNS = [
-  /\bfor\s+([^.,;!?\n]{4,60}?)(?:\s+(?:that|who|which))/i,
-  /\bfor\s+([^.,;!?\n]{4,60})/i,
-  /\btargeting\s+([^.,;!?\n]{4,60})/i,
-];
-
-const CURRENT_WORKFLOW_PATTERNS = [
-  /(?:right now|currently|today)[,:]?\s+(.{15,150})/i,
-  /(?:we|I)\s+(?:currently|already)\s+(.{10,100})/i,
-  /(?:the current|our current)\s+(.{10,100})/i,
-];
-
-const TARGET_WORKFLOW_PATTERNS = [
-  /(?:I want|we want|should be able to|the user should)\s+(.{10,150})/i,
-  /(?:instead of|rather than)\s+.{5,50}?,?\s*(.{10,100})/i,
-];
-
-const JOB_PATTERNS = [
-  /(?:the core outcome|the goal|the job|what I want)\s+(?:is|I want)[:\s]+(.{10,150})/i,
-  /(?:so that|in order to)\s+(.{10,100})/i,
-];
-
-export function buildWorkflowCanvas(raw: string, seed: SynthesizedSeed): WorkflowCanvas {
-  let primary_user = "";
-  for (const p of USER_PATTERNS) {
-    const m = raw.match(p);
-    if (m?.[1] && m[1].length > 5) { primary_user = compact(m[1]); break; }
-  }
-  if (!primary_user && seed.target_user !== "Solo builders shipping software.") {
-    primary_user = seed.target_user;
-  }
-
-  let current_workflow = "";
-  for (const p of CURRENT_WORKFLOW_PATTERNS) {
-    const m = raw.match(p);
-    if (m?.[1]) { current_workflow = compact(m[1]).slice(0, 150); break; }
-  }
-
-  let target_workflow = "";
-  for (const p of TARGET_WORKFLOW_PATTERNS) {
-    const m = raw.match(p);
-    if (m?.[1]) { target_workflow = compact(m[1]).slice(0, 150); break; }
-  }
-
-  let job_to_be_done = seed.v1_outcome || "";
-  for (const p of JOB_PATTERNS) {
-    const m = raw.match(p);
-    if (m?.[1] && m[1].length > 15) { job_to_be_done = compact(m[1]).slice(0, 150); break; }
-  }
-
-  return { primary_user, current_workflow, target_workflow, job_to_be_done, edge_cases: [] };
-}
-
-// ---------------------------------------------------------------------------
-// 3. Non-functional gates
-// ---------------------------------------------------------------------------
-
-const NF_PATTERNS: { category: NonFunctionalGate["category"]; patterns: RegExp[]; reason: string }[] = [
-  { category: "security", patterns: [/\bauth\b/i, /\bpassword\b/i, /\btoken\b/i, /\bOAuth\b/i, /\bencrypt/i, /\bAPI\s*key\b/i], reason: "Auth/security-related functionality detected." },
-  { category: "privacy", patterns: [/\bPII\b/i, /\bpersonal\s+data\b/i, /\bGDPR\b/i, /\bemail\s+address/i, /\buser\s+data\b/i], reason: "Personal/user data handling detected." },
-  { category: "compliance", patterns: [/\bcompliance\b/i, /\bregulatory\b/i, /\bHIPAA\b/i, /\bSOC\s*2\b/i, /\blegal\b/i], reason: "Compliance-relevant domain detected." },
-  { category: "performance", patterns: [/\breal.?time\b/i, /\blatency\b/i, /\bscale\b/i, /\bconcurren/i, /\bstreaming\b/i], reason: "Performance-sensitive requirements detected." },
-  { category: "observability", patterns: [/\blogging\b/i, /\bmonitoring\b/i, /\balert/i, /\bmetric/i, /\btrac(?:e|ing)\b/i], reason: "Observability-relevant functionality detected." },
-];
-
-export function checkNonFunctionalGates(raw: string, constraints: string): NonFunctionalGate[] {
-  const combined = `${raw} ${constraints}`;
-  const gates: NonFunctionalGate[] = [];
-
-  for (const nf of NF_PATTERNS) {
-    const triggered = nf.patterns.some(p => p.test(combined));
-    if (triggered) {
-      gates.push({
-        category: nf.category,
-        flagged: true,
-        reason: nf.reason,
-        severity: nf.category === "security" || nf.category === "privacy" ? "medium" : "low",
-      });
-    }
-  }
-
-  return gates;
-}
-
-// ---------------------------------------------------------------------------
-// 4. Dangerous gates
-// ---------------------------------------------------------------------------
-
-export function checkDangerousGates(raw: string, constraints: string, seed: SynthesizedSeed): DangerousGate[] {
-  const combined = compact(`${raw} ${constraints}`).toLowerCase();
-  const gates: DangerousGate[] = [];
-
-  // Privacy high-risk
-  if (/\b(medical|health|financial|banking|credit\s*card|SSN|social\s*security)\b/i.test(combined)) {
-    gates.push({ gate: "privacy-high-risk", triggered: true, reason: "Domain involves sensitive personal/financial/medical data." });
-  }
-
-  // Trust boundary uncertainty
-  if (seed.missing_inputs.some(m => /target user/i.test(m)) || seed.target_user === "Solo builders shipping software.") {
-    if (/\b(team|enterprise|organization|company|admin)\b/i.test(combined) && !/\bnot?\s+(?:a\s+)?(?:team|enterprise)/i.test(combined)) {
-      gates.push({ gate: "trust-boundary-uncertain", triggered: true, reason: "Multi-user/team context with unclear trust boundaries." });
-    }
-  }
-
-  // Production-critical
-  if (/\b(production|prod|live\s+system|critical\s+path|payment|billing)\b/i.test(combined)) {
-    if (!/\bno\s+billing\b/i.test(combined) && !/\bno\s+payment\b/i.test(combined)) {
-      gates.push({ gate: "production-critical", triggered: true, reason: "Production-critical or payment-adjacent functionality." });
-    }
-  }
-
-  // Overbroad + missing stop condition
-  const systemCount = (combined.match(/\b(slack|jira|github|linear|hubspot|notion|email|stripe|twilio)\b/gi) ?? []).length;
-  const hasStopCondition = /\bv1\b|\bfirst\s+slice\b|\bonly\b|\bjust\b|\bsimple\b|\bnarrow\b/i.test(combined);
-  if (systemCount >= 4 && !hasStopCondition) {
-    gates.push({ gate: "overbroad-no-stop", triggered: true, reason: `${systemCount} systems mentioned with no clear V1 narrowing.` });
-  }
-
-  return gates;
-}
-
-// ---------------------------------------------------------------------------
-// 5. Mode scoring
-// ---------------------------------------------------------------------------
-
-export function scoreMode(raw: string, constraints: string, seed: SynthesizedSeed): ModeScoring {
-  const combined = compact(`${raw} ${constraints}`).toLowerCase();
-
-  const surface_area = combined.length > 500 ? 2 : combined.length > 200 ? 1 : 0;
-
-  const integrations = (combined.match(/\b(slack|jira|github|linear|hubspot|notion|email|supabase|stripe|firebase|aws)\b/gi) ?? []);
-  const integration_count = Math.min(integrations.length, 3);
-
-  const user_clarity = seed.target_user !== "Solo builders shipping software." ? 0 : 2;
-
-  const outcome_concreteness = seed.v1_outcome && seed.v1_outcome.length > 20 ? 0 : seed.v1_outcome ? 1 : 3;
-
-  const coordination_complexity = /\b(team|across\s+teams|coordinate|orchestrat)\b/i.test(combined) ? 2 : 0;
-
-  const contradictions = seed.missing_inputs.filter(m => /contradict|conflicting/i.test(m)).length;
-  const contradiction_level = Math.min(contradictions, 3);
-
-  const appetite_mismatch = /\b(two\s+weeks|one\s+week|weekend)\b/i.test(combined) && integration_count >= 2 ? 2 : 0;
-
-  const total = surface_area + integration_count + user_clarity + outcome_concreteness +
-    coordination_complexity + contradiction_level + appetite_mismatch;
-
-  return { surface_area, integration_count, user_clarity, outcome_concreteness,
-    coordination_complexity, contradiction_level, appetite_mismatch, total };
-}
-
-// ---------------------------------------------------------------------------
-// 6. Two-stage mode selection
-// ---------------------------------------------------------------------------
-
-export function selectModeV2(
-  dangerousGates: DangerousGate[],
-  scoring: ModeScoring,
-): { mode: ProcessMode; reason: string } {
-  // Stage 1: Dangerous gates → governance
-  const triggered = dangerousGates.filter(g => g.triggered);
-  if (triggered.length > 0) {
-    return {
-      mode: "governance",
-      reason: `Dangerous gate(s): ${triggered.map(g => g.gate).join(", ")}.`,
-    };
-  }
-
-  // Stage 2: Scoring → simple vs standard
-  if (scoring.total <= 3) {
-    return { mode: "minimal", reason: `Low complexity score (${scoring.total}/21). Lightweight process.` };
-  }
-  if (scoring.total >= 10) {
-    return { mode: "governance", reason: `High complexity score (${scoring.total}/21). Careful review recommended.` };
-  }
-
-  return { mode: "structured", reason: `Standard complexity score (${scoring.total}/21).` };
-}
-
-// ---------------------------------------------------------------------------
-// 7. Escalation triggers
-// ---------------------------------------------------------------------------
-
-export function checkEscalationTriggers(raw: string): string[] {
-  const triggers: string[] = [];
-  if (/\btrust\s+boundar/i.test(raw)) triggers.push("Trust boundaries appeared.");
-  if ((raw.match(/\b(slack|jira|github|linear|hubspot|notion|email|supabase|stripe)\b/gi) ?? []).length >= 3) {
-    triggers.push("Integration count materially increased.");
-  }
-  if (/\b(and also|plus|additionally)\s+(?:for|targeting)\s/i.test(raw)) triggers.push("Target users may have split.");
-  if (/\b(and also|plus|additionally)\s+(?:build|add|create)\s/i.test(raw)) triggers.push("Scope may have expanded materially.");
-  if (/\b(HIPAA|GDPR|SOC|PCI|encrypt|sensitive\s+data)\b/i.test(raw)) triggers.push("Privacy/security risk increased.");
-  return triggers;
-}
-
-// ---------------------------------------------------------------------------
-// Full Activation V2
-// ---------------------------------------------------------------------------
-
-export function activateV2(input: ActivationInput, seed: SynthesizedSeed): ActivationResult {
-  const assumptions = buildAssumptions(seed, input);
-  const workflow_canvas = buildWorkflowCanvas(input.raw_idea, seed);
-  const non_functional_gates = checkNonFunctionalGates(input.raw_idea, input.constraints);
-  const dangerous_gates = checkDangerousGates(input.raw_idea, input.constraints, seed);
-  const mode_scoring = scoreMode(input.raw_idea, input.constraints, seed);
-  const { mode } = selectModeV2(dangerous_gates, mode_scoring);
-  const escalation_triggers = checkEscalationTriggers(input.raw_idea);
-
-  return activationResultSchema.parse({
-    assumptions,
-    workflow_canvas,
-    non_functional_gates,
-    dangerous_gates,
-    mode_scoring,
-    selected_mode: mode,
-    mode_is_escalatable: true,
-    escalation_triggers,
-  });
-}