@seldonframe/mcp 1.5.0 → 1.6.0

package/package.json

@@ -1,6 +1,8 @@
 {
   "name": "@seldonframe/mcp",
-  "version": "1.5.0",
+  "version": "1.6.0",
+  "description": "MCP server for SeldonFrame — AI-native Business OS platform. v1.6.0: BRAIN LAYER (the compounding moat). Two-layer file-tree of markdown notes implementing the Karpathy LLM-Wiki pattern: Layer 1 is per-workspace (notes about THIS workspace's customers, voice, pipeline patterns, learnings); Layer 2 is anonymized cross-workspace patterns the weekly cron promotes when 3+ workspaces independently observe the same thing with confidence ≥ 0.7. Each note carries a Bayesian-smoothed confidence score `(wins + 1) / (uses + 2)` so the system self-prunes bad entries (confidence drops, weekly cron archives) and self-promotes good ones (workspace pattern hits threshold, cron creates global note). The IDE agent reads relevant notes before generating blocks; the brain compounds across every workspace interaction. WHAT SHIPS: (1) brain_notes table (migration 0037, applied to prod) with org_id-NULL-for-global discriminator, scope text, path file-tree key, body markdown, metadata jsonb, confidence/uses/wins counters, and indexes for prefix listing + promotion + pruning. (2) lib/brain/store.ts CRUD: readBrainNote (ticks uses + last_used_at), listBrainDir (prefix-filtered, returns body previews), writeBrainNote (upsert, preserves confidence), appendToBrainNote (prepends dated paragraphs, 8KB cap), deleteBrainNote, computeConfidence, markBrainOutcome (win/loss feedback), findPromotionCandidates (uses ≥ 10, confidence ≥ 0.7, ≥ 3 workspaces), findPruneCandidates (confidence < 0.3, uses ≥ 10). (3) Single REST endpoint POST /api/v1/brain dispatching on `op` field (read|list|write|append|delete|list_patterns) with workspace bearer auth + path-traversal guards. (4) Four new MCP tools: read_brain_path, list_brain_dir, write_brain_note (with append flag), list_brain_patterns. Welcome message updated to teach the brain pattern. (5) Per-interaction triggers: submitPublicBookingAction appends to pipeline/booked-appointments.md when a booking confirms; the public intake POST appends a non-PII summary (answered/skipped field counts + low-risk values) to intake/recent-leads.md. Best-effort — failures don't block the user-facing response. (6) Weekly cron at /api/cron/brain-promote scheduled Sundays 05:00 UTC in vercel.json. Promotes high-confidence workspace notes to layer 2 (synthesized as bullet-list aggregations for v1.6; LLM-based synthesis lands in v1.7); prunes low-confidence workspace notes. Both ops idempotent. (7) create_workspace_v2 now pre-fetches up to 10 layer-2 patterns matching the resolved personality vertical and returns them inline as v2.brain_patterns so the IDE agent has cross-workspace context without a second round-trip. The brain compounds: each new workspace's interactions feed the brain, the cron promotes patterns weekly, the next workspace's IDE agent reads richer context, output quality improves over time WITHOUT code changes — the Karpathy compounding moat. ⚠️ BACKEND REDEPLOY REQUIRED. Migration 0037 already applied to prod. Set CRON_SECRET env var on Vercel if not already set.",
+  "description": "MCP server for SeldonFrame — AI-native Business OS platform. v1.5.1: HOTFIX — five fixes from the Coastline Music workspace test. (1) BLOCKING — apply-0031-prod.mjs applied the missing portal_documents migration that was crashing every contact-detail page load with `relation \"portal_documents\" does not exist`. Operators can now view lead records again. (2) Lucide icon allowlist now ENFORCED — pre-1.5.1 the LLM could pick icon names like \"piano\", \"microphone\", \"wood_oven\" that the renderer didn't have, so all those services-grid cards rendered with the same fallback icon (visible on Coastline Music + Cinder & Salt). New ICON_NAMES export from lucide-icons.ts (derived from ICON_PATHS so it stays in sync); new services validator rejects unknown icons and returns the full allowlist in the error so the LLM can self-correct on retry. (3) Smart pipeline-stage selection on booking — pre-1.5.1 every booking landed at the FIRST pipeline stage (\"Inquiry\" / \"Lead\"), forcing operators to manually move every deal up a stage. Now the deal-insert path matches stages whose names contain booked / scheduled / trial / appointment / consultation / reservation and uses that stage instead, falling back to first stage when no match exists. Personality-generated pipelines that declare \"Trial Lesson Booked\" / \"Estimate Scheduled\" automatically get the right behavior. New stage_match telemetry tag (\"smart\" vs \"first_stage_fallback\") + available_stages array in the public_booking_deal_created log. (4) FAQ headline centering bulletproofed with !important + max-width: none override on .sf-faq > .sf-faq__headline — the .sf-faq > * { max-width: 48rem } rule was constraining the H2 narrower than the page, making centered text appear left-anchored. (5) Hero subhead text-align: center pinned in base CSS (was inheriting parent text-align which varied by overlay), plus eyebrow pill background hardened to rgba(0,0,0,0.45) with white border + backdrop-filter blur on hero-with-image so the eyebrow text stays readable against any photo. ⚠️ BACKEND REDEPLOY REQUIRED. Migration 0031 already applied to prod by the same script that ships in this commit.",
   "description": "MCP server for SeldonFrame — AI-native Business OS platform. v1.5.0: BLOCK CODEGEN — kills the prop-schema-drift bug class structurally. Pre-1.5 every block's prop schema lived in TWO places: the SKILL.md frontmatter (LLM-readable YAML, the source of truth for the agent's generation prompt) AND lib/page-blocks/registry.ts (runtime Zod, the source of truth for server validation). Editing one without the other was undetectable until a runtime failure surfaced it; the Cinder & Salt booking-form bug (v1.4.2 hotfix) was one such failure. v1.5 makes drift structurally impossible: SKILL.md frontmatter is the single source of truth, and `pnpm blocks:emit` parses each block's frontmatter and generates packages/crm/src/blocks/<name>/__generated__/block.ts containing the Zod schema, the inferred TypeScript Props type, and the block metadata constants (name, version, surface, sectionType, description). The registry imports from these generated files; the toSection mapping + deterministic copy validators stay handwritten because they're logic, not schema. CI gate: `pnpm blocks:emit:check` re-runs the emitter and exits non-zero if any __generated__/block.ts is stale relative to its SKILL.md — a new unit test (tests/unit/blocks-codegen-staleness.spec.ts) makes every PR fail if anyone edits a SKILL.md without regenerating. Codegen handles all the types we use across 7 blocks: string/number/boolean with min/max bounds, enum, object with nested properties, array of objects with min_items/max_items, tuple (booking weekly_availability uses [openHour, closeHour] pairs), nullable, optional/required. Adds `yaml` devDependency for frontmatter parsing. Documented in packages/crm/src/blocks/README.md. ⚠️ BACKEND REDEPLOY REQUIRED.",
   "description": "MCP server for SeldonFrame — AI-native Business OS platform. v1.4.2: HOTFIX for the booking-form regression introduced by v1.4.1. The v2 booking persist path replaced Blueprint.booking.formFields wholesale with whatever the LLM generated — wiping out the standard `fullName` + `email` fields v1's bootstrap had set. Result: every v2 workspace shipped a booking form with NO name/email inputs, and submitPublicBookingAction rejected every submit with `missing_required_field fullName_present:false email_present:false`. Confirmed on Cinder & Salt (Hamilton wood-fired pizza) where the form had Party Size + Occasion + Allergies but no name/email. v1.4.2 fixes: (1) New mergeBookingFormFields helper in lib/page-blocks/persist.ts — server ALWAYS prepends fullName + email, dedupes against any LLM-provided field with the same id; LLM-provided extras (party_size, dog_name, service_address, etc.) keep working unchanged. (2) booking SKILL.md updated — voice rules now correctly say 'EXTRAS only, server adds standard name+email' instead of the wrong 'renderer adds them automatically'. (3) Backfill scripts shipped: backfill-booking-form-fields.mjs (47 prod workspaces had their blueprint.booking.formFields patched to include the standard fields) + scripts/rerender-all-bookings-v142.ts (re-renders bookings.content_html for 63 booking templates so the live booking pages actually show the form fields). Both scripts already executed against prod. ⚠️ BACKEND REDEPLOY REQUIRED.",
   "description": "MCP server for SeldonFrame — AI-native Business OS platform. v1.4.1: COMPLETE v2 BLOCK COVERAGE — v1.4 shipped 3 block primitives (hero, services, faq) and proved the architecture; v1.4.1 ships the remaining 4 (about, faq, cta, booking, intake) so v2 owns every operator-facing surface end-to-end. Validated against the Pawsh & Polish mobile-dog-grooming workspace test, where the v2 hero (\"One Dog at a Time, In Your Driveway. 4.9★, 280+ Reviews.\") and the niche-aware FAQ (\"Where does the van park?\", \"What if my dog is nervous?\") proved that LLM-in-IDE generation produces visibly better output than the v1 personality system ever did for a long-tail vertical. Now extending to about + cta (landing-section surface), booking (calendar surface — title, duration, location_kind, weekly availability hours, optional form fields, validators against the v1 'Free consultation / 30-minute conversation' template leak), and intake (form surface — title, questions with proper field types per vertical, completion message, validator against the 'Tell us about your project' template leak). New BlockSurface discriminator routes persistence — landing-section blocks mutate Blueprint.landing.sections + re-render via renderGeneralServiceV1; booking blocks mutate Blueprint.booking + bookings table metadata + re-render via renderCalcomMonthV1; intake blocks mutate Blueprint.intake + intakeForms table fields + re-render via renderFormbricksStackV1. Welcome message updated to teach Promise.all parallelism (sequential 7-block generation blows the 60s latency budget; parallel keeps it well under). Plus: FAQ + services + about section headlines reinforced with explicit centering CSS (display:block + margin:auto + width:100% + text-align:center) after operator feedback that the headline rendered left-aligned in some viewports. Reuses the same block_instances table (no migration needed). ⚠️ BACKEND REDEPLOY REQUIRED.",

package/src/tools.js

@@ -2660,6 +2660,149 @@ export const TOOLS = [
       return result;
     },
   },
+
+  // ─── v1.6.0 — brain layer (Karpathy LLM-Wiki) ───────────────────────────
+  //
+  // Two-layer brain stored as a file-tree of markdown notes:
+  //   - Layer 1 (workspace): notes about THIS workspace's customers, voice,
+  //     pipeline patterns, learnings. Reads cost 0 LLM tokens server-side
+  //     (the IDE agent's LLM consumes them as context).
+  //   - Layer 2 (global): cross-workspace patterns, anonymized. The weekly
+  //     cron promotes high-confidence workspace notes that appear in 3+
+  //     workspaces.
+  //
+  // Use these tools BEFORE generating a block to give the IDE agent's
+  // LLM workspace-specific + vertical-specific context. Use them AFTER
+  // a successful interaction to write back what worked.
+
+  {
+    name: "read_brain_path",
+    description:
+      "Read a single brain note from the workspace's layer-1 brain. Returns the body (markdown), confidence (0-1), uses (times read), wins (times the consuming interaction was successful), and metadata. Reading a note increments its `uses` counter — that's how the feedback loop knows the note has been consumed. Use BEFORE generating blocks: check for relevant entries (voice/copy-that-works.md, customers/recurring.md, learnings.md) so your generation reflects what's been observed about this workspace.",
+    inputSchema: obj(
+      {
+        workspace_id: str("Workspace id."),
+        path: str(
+          "Note path. Examples: voice/copy-that-works.md, customers/recurring.md, pipeline/closed-won-patterns.md, learnings.md.",
+        ),
+      },
+      ["workspace_id", "path"],
+    ),
+    handler: async (args) => {
+      const ws = args.workspace_id;
+      const result = await api("POST", "/brain", {
+        body: { op: "read", path: args.path },
+        workspace_id: ws,
+      });
+      return result;
+    },
+  },
+
+  {
+    name: "list_brain_dir",
+    description:
+      "List brain notes in the workspace's layer-1 brain. Returns metadata + a 120-char body preview per note (full body requires read_brain_path). Use to discover what the brain knows about this workspace before generating blocks. Pass `prefix` to filter by directory (e.g. 'voice/' returns voice-related notes only). Notes are returned sorted by confidence descending.",
+    inputSchema: obj(
+      {
+        workspace_id: str("Workspace id."),
+        prefix: str(
+          "Optional path prefix to filter (e.g. 'voice/', 'customers/'). Omit for all notes.",
+        ),
+      },
+      ["workspace_id"],
+    ),
+    handler: async (args) => {
+      const ws = args.workspace_id;
+      const result = await api("POST", "/brain", {
+        body: { op: "list", prefix: args.prefix ?? undefined },
+        workspace_id: ws,
+      });
+      return result;
+    },
+  },
+
+  {
+    name: "write_brain_note",
+    description:
+      "Write a brain note to the workspace's layer-1 brain. Use to capture insights the operator volunteers ('walk-ins on Saturday convert 3× better', 'don't ever say synergy in the copy', 'most leads come in via Instagram'). The note is REPLACED on subsequent writes to the same path; for append-style writes use `append: true`. Source field is recorded so the cron can attribute promotions correctly.",
+    inputSchema: obj(
+      {
+        workspace_id: str("Workspace id."),
+        path: str(
+          "Note path. Convention: <category>/<topic>.md. Examples: customers/recurring.md, voice/copy-that-works.md, learnings.md, ops/saturday-rush.md.",
+        ),
+        body: str(
+          "Markdown body of the note. Concrete, specific, observation-based. Avoid generalities.",
+        ),
+        append: {
+          type: "boolean",
+          description:
+            "When true, prepend the body as a new dated paragraph to the existing note (preserves history). When false (default), replaces the existing body.",
+        },
+        type: str(
+          "Optional note type for filtering: 'pattern' | 'fact' | 'preference' | 'warning' | 'playbook' | 'anti-pattern'.",
+        ),
+        tags: {
+          type: "array",
+          description: "Optional tags for filtering.",
+          items: { type: "string" },
+        },
+      },
+      ["workspace_id", "path", "body"],
+    ),
+    handler: async (args) => {
+      const ws = args.workspace_id;
+      const op = args.append ? "append" : "write";
+      const payload = {
+        op,
+        path: args.path,
+        metadata: {
+          source: "operator:claude-code",
+          type: args.type ?? undefined,
+          tags: args.tags ?? undefined,
+        },
+      };
+      if (op === "append") payload.paragraph = args.body;
+      else payload.body = args.body;
+      const result = await api("POST", "/brain", {
+        body: payload,
+        workspace_id: ws,
+      });
+      return result;
+    },
+  },
+
+  {
+    name: "list_brain_patterns",
+    description:
+      "List layer-2 cross-workspace patterns. These are anonymized insights the cron has promoted from workspaces that all observed the same thing (3+ workspaces, confidence >= 0.7). Use BEFORE generating blocks for a vertical-specific business — patterns/by-vertical/<vertical>.md gives you observations across every other workspace in that vertical. Compounding moat: each new workspace's interactions feed back into these patterns over time.",
+    inputSchema: obj(
+      {
+        workspace_id: str(
+          "Workspace id (used for auth; the patterns themselves are global).",
+        ),
+        vertical: str(
+          "Optional vertical filter: 'barbershop' | 'hvac' | 'legal' | 'restaurant' | etc. Returns patterns/by-vertical/<vertical>/* notes only.",
+        ),
+        block_type: str(
+          "Optional block-type filter: 'hero' | 'services' | 'faq' | etc. Returns patterns/by-block-type/<type>/* notes only.",
+        ),
+      },
+      ["workspace_id"],
+    ),
+    handler: async (args) => {
+      const ws = args.workspace_id;
+      const result = await api("POST", "/brain", {
+        body: {
+          op: "list_patterns",
+          vertical: args.vertical ?? undefined,
+          block_type: args.block_type ?? undefined,
+        },
+        workspace_id: ws,
+      });
+      return result;
+    },
+  },
 ];
 
 export const TOOL_MAP = Object.fromEntries(TOOLS.map((t) => [t.name, t]));

package/src/welcome.js

@@ -8,7 +8,7 @@
 // stripped. `create_full_workspace` is the only workspace-creation
 // path mentioned anywhere in this briefing.
 
-export const VERSION = "1.5.0";
+export const VERSION = "1.6.0";
 
 export const WELCOME_MARKDOWN = `# SeldonFrame — create a real Business OS in one conversation
 
@@ -167,6 +167,8 @@ further natural-language requests ("change the headline to …",
 - **\`create_workspace_v2\`** — PREFERRED workspace-creation tool (v1.4+).
   MCP-native: bootstraps the workspace + returns the list of blocks YOU
   generate using your own LLM. The first call for any new workspace.
+  v1.6+ also returns \`brain_patterns\` — anonymized cross-workspace
+  insights for this vertical that you should fold into your generation.
 - **\`list_blocks\`** — lists v2 page-block primitives available.
 - **\`get_block_skill\`** — fetches one block's SKILL.md (the generation
   prompt + prop schema you read before generating props).
@@ -174,6 +176,16 @@ further natural-language requests ("change the headline to …",
   + renders + replaces the matching section in the workspace's landing.
 - **\`complete_workspace_v2\`** — marks the v2 flow finished, reports which
   blocks landed.
+- **\`read_brain_path\`** / **\`list_brain_dir\`** — read the workspace's
+  layer-1 brain (notes about THIS workspace's customers, voice, pipeline
+  patterns). Use BEFORE generating blocks; reads tick the note's \`uses\`
+  counter so the system knows what's actually being consumed.
+- **\`write_brain_note\`** — capture insights the operator volunteers
+  ("walk-ins on Saturday convert 3× better"). Notes live in the
+  workspace's brain forever, contribute to layer-2 cross-workspace
+  patterns when 3+ workspaces independently observe them.
+- **\`list_brain_patterns\`** — read layer-2 cross-workspace patterns,
+  filtered by vertical or block_type.
 - **\`create_full_workspace\`** — v1 atomic creation (legacy). Server-side,
   deterministic. Use only when v2 is impossible.
 - **\`finalize_workspace\`** — MANDATORY closing call. Mints the