feat: audio upload + AI-assisted tempo map generation

Users can now upload any audio file to generate a CTP tempo map:

BPM detection (lib/analysis/bpm-detect.ts):
- Runs entirely client-side via Web Audio API — audio is never uploaded
- Decodes any browser-supported format (MP3, WAV, AAC, OGG, FLAC, M4A)
- Energy envelope → onset strength → autocorrelation over 55–210 BPM range
- Returns BPM, normalised confidence score, duration, and optional half-time BPM
  for songs where a double-time pulse is detected

AI CTP generation (lib/analysis/ai-ctp.ts):
- Calls Claude (claude-opus-4-6) with adaptive thinking + structured JSON output
- System prompt explains CTP rules and section layout conventions
- Claude uses knowledge of well-known songs to produce accurate section maps;
  falls back to a sensible generic structure for unknown tracks
- Only BPM + duration + optional metadata is sent to the server (no audio data)

API route (app/api/analyze/route.ts):
- POST /api/analyze accepts { bpm, duration, title?, artist?, mbid?, contributed_by? }
- Validates input, calls generateCTPWithAI, runs CTP schema validation
- Returns { ctp, warnings } — warnings are surfaced in the UI rather than 500-ing

UI (components/TempoAnalyzer.tsx, app/(web)/analyze/page.tsx):
- Drag-and-drop or browse file upload
- Shows BPM, confidence, duration after detection
- Half-time toggle when double-time is detected
- Metadata form: title, artist, MusicBrainz ID, contributor name
  (filename parsed into artist/title as a convenience default)
- AI generation with streaming-style progress states
- Sections review via TempoMapEditor
- Download .ctp.json or submit directly to the database

Also: added @anthropic-ai/sdk to package.json, ANTHROPIC_API_KEY to .env.example,
updated next.config.mjs serverComponentsExternalPackages, added Analyze nav link.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

lib/analysis/ai-ctp.ts

@@ -0,0 +1,179 @@
+/**
+ * AI-assisted CTP document generation
+ *
+ * Takes the results of BPM detection (and optional song metadata) and uses
+ * Claude to produce a plausible, well-structured CTP document.
+ *
+ * Claude is asked to:
+ *   - Divide the song into typical sections (Intro, Verse, Chorus, Bridge…)
+ *   - Assign realistic start bars for each section
+ *   - Note any tempo changes it would expect for the song/genre
+ *   - Return a fully valid CTP 1.0 JSON document
+ *
+ * The caller should treat the result as a *draft* — the generated sections
+ * are educated guesses and should be verified against the recording.
+ */
+
+import Anthropic from "@anthropic-ai/sdk";
+import type { CTPDocument } from "@/lib/ctp/schema";
+
+const client = new Anthropic();
+
+// ─── Input / output types ─────────────────────────────────────────────────────
+
+export interface AnalysisInput {
+  bpm: number;
+  duration: number;      // seconds
+  title?: string;
+  artist?: string;
+  mbid?: string | null;
+  contributedBy?: string;
+}
+
+// ─── JSON Schema for structured output ───────────────────────────────────────
+// Must be strict (no additionalProperties, all required fields present).
+
+const CTP_SCHEMA = {
+  type: "object",
+  additionalProperties: false,
+  required: ["version", "metadata", "count_in", "sections"],
+  properties: {
+    version: { type: "string", enum: ["1.0"] },
+    metadata: {
+      type: "object",
+      additionalProperties: false,
+      required: [
+        "title", "artist", "mbid", "duration_seconds",
+        "contributed_by", "verified", "created_at",
+      ],
+      properties: {
+        title:            { type: "string" },
+        artist:           { type: "string" },
+        mbid:             { type: ["string", "null"] },
+        duration_seconds: { type: "number" },
+        contributed_by:   { type: "string" },
+        verified:         { type: "boolean" },
+        created_at:       { type: "string" },
+      },
+    },
+    count_in: {
+      type: "object",
+      additionalProperties: false,
+      required: ["enabled", "bars", "use_first_section_tempo"],
+      properties: {
+        enabled:                 { type: "boolean" },
+        bars:                    { type: "integer", minimum: 1, maximum: 8 },
+        use_first_section_tempo: { type: "boolean" },
+      },
+    },
+    sections: {
+      type: "array",
+      minItems: 1,
+      items: {
+        type: "object",
+        additionalProperties: false,
+        required: ["label", "start_bar", "time_signature", "transition"],
+        // bpm is required for step, bpm_start/bpm_end for ramp — handled via oneOf
+        // but we keep this schema simple (strict mode) and validate downstream with Zod.
+        properties: {
+          label:      { type: "string" },
+          start_bar:  { type: "integer", minimum: 1 },
+          bpm:        { type: "number" },
+          bpm_start:  { type: "number" },
+          bpm_end:    { type: "number" },
+          transition: { type: "string", enum: ["step", "ramp"] },
+          time_signature: {
+            type: "object",
+            additionalProperties: false,
+            required: ["numerator", "denominator"],
+            properties: {
+              numerator:   { type: "integer", minimum: 1, maximum: 32 },
+              denominator: { type: "integer", enum: [1, 2, 4, 8, 16, 32] },
+            },
+          },
+        },
+      },
+    },
+  },
+};
+
+// ─── System prompt ────────────────────────────────────────────────────────────
+
+const SYSTEM_PROMPT = `\
+You are an expert music producer and session musician assisting cover bands with click tracks.
+
+You will receive automated BPM detection results for a song and must generate a CTP (Click Track Protocol) document describing the song's full tempo map.
+
+CTP rules:
+- "version" must be "1.0"
+- sections[0].start_bar must be 1
+- sections must be sorted by start_bar ascending, with no gaps
+- Step sections have a single "bpm" field; ramp sections have "bpm_start" and "bpm_end" (no "bpm" field)
+- All BPM values must be between 20 and 400
+- time_signature.denominator must be a power of 2 (1, 2, 4, 8, 16, or 32)
+- metadata.verified must be false (this is AI-generated, not human-verified)
+- metadata.created_at must be an ISO 8601 datetime string
+
+Guidelines for section layout:
+- Use typical pop/rock section names: Intro, Verse, Pre-Chorus, Chorus, Bridge, Outro
+- Estimate bar counts based on song duration and BPM (bars = duration_seconds × BPM / 60 / beats_per_bar)
+- Most songs are 4/4; note any unusual meters if you know the song
+- If you know the song has a tempo change (ritardando, double-time feel, key change with tempo shift), model it with a ramp or step section
+- If unsure about sections, use a single constant-tempo section covering the whole song
+- Use the detected BPM as the primary tempo — do not invent a different BPM unless the song is well-known to have a different tempo
+
+The output is a draft for human review. Add reasonable section structure based on the song's typical arrangement.`;
+
+// ─── Main function ────────────────────────────────────────────────────────────
+
+export async function generateCTPWithAI(input: AnalysisInput): Promise<CTPDocument> {
+  const { bpm, duration, title, artist, mbid, contributedBy } = input;
+
+  const approxBars = Math.round((duration * bpm) / 60 / 4); // assuming 4/4
+
+  const userMessage = `\
+Generate a CTP document for the following song:
+
+Title: ${title ?? "Unknown Title"}
+Artist: ${artist ?? "Unknown Artist"}
+MusicBrainz ID: ${mbid ?? "unknown"}
+Detected BPM: ${bpm}
+Duration: ${duration.toFixed(1)} seconds (~${approxBars} bars at 4/4)
+Contributed by: ${contributedBy ?? "anonymous"}
+
+Create a plausible section layout for this song. If this is a well-known song, use your knowledge of its actual arrangement. If not, use a sensible generic structure.`;
+
+  const response = await client.messages.create({
+    model: "claude-opus-4-6",
+    max_tokens: 2048,
+    thinking: { type: "adaptive" },
+    system: SYSTEM_PROMPT,
+    messages: [{ role: "user", content: userMessage }],
+    output_config: {
+      format: {
+        type: "json_schema",
+        schema: CTP_SCHEMA,
+      },
+    },
+  });
+
+  const textBlock = response.content.find((b) => b.type === "text");
+  if (!textBlock || textBlock.type !== "text") {
+    throw new Error("Claude did not return a text block");
+  }
+
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(textBlock.text);
+  } catch {
+    throw new Error(`Claude returned invalid JSON: ${textBlock.text.slice(0, 200)}`);
+  }
+
+  // Stamp the current timestamp if Claude left a placeholder
+  const doc = parsed as CTPDocument;
+  if (!doc.metadata.created_at || doc.metadata.created_at.includes("placeholder")) {
+    doc.metadata.created_at = new Date().toISOString();
+  }
+
+  return doc;
+}