lakehouse/bot/cycle.ts

// Single-cycle orchestrator. This is the manual entry point:
//   bun run bot/cycle.ts
//
// Steps (each step can short-circuit with a clear outcome):
//   1. Pause-file check         → skipped_pause
//   2. Cost budget check        → skipped_cost
//   3. Gather CycleContext      (dirty tree, last cycle, autotune status)
//   4. policy.shouldRunCycle    → skipped_policy
//   5. findGaps + policy.pickGap → skipped_no_gap
//   6. generateProposal         → model_failed
//   7. policy.scoreProposal     → proposal_rejected
//   8. git checkout new branch
//   9. applyProposal            → apply_failed
//  10. runTests                 → tests_failed
//  11. policy.shouldOpenPR      → pr_skipped_by_policy
//  12. git commit + push
//  13. openPr                   → pr_failed / ok
// 14. recordCost + postEvent (every outcome)
// 15. write cycle result to data/_bot/cycles/{cycle_id}.json

import { readFile, writeFile, mkdir, access } from "node:fs/promises";
import { createHash, randomUUID } from "node:crypto";
import { spawnSync } from "node:child_process";
import { join } from "node:path";

import type { CycleContext, CycleResult, CycleOutcome, Proposal } from "./types.ts";
import * as policy from "./policy.ts";
import { readCost, recordCost, budgetCheck, DAILY_CALLS_BUDGET, DAILY_TOKENS_BUDGET } from "./cost.ts";
import { findGaps, generateProposal } from "./propose.ts";
import { applyProposal } from "./apply.ts";
import { runTests } from "./test.ts";
import { openPr } from "./pr.ts";
import { postEvent } from "./observer.ts";
import { loadHistory, summarizeHistory, statsFor } from "./kb.ts";

const REPO_ROOT = "/home/profit/lakehouse";
const PAUSE_FILE = `${REPO_ROOT}/bot.paused`;
const CYCLES_DIR = `${REPO_ROOT}/data/_bot/cycles`;
const GATEWAY_URL = process.env.LH_GATEWAY_URL ?? "http://localhost:3100";

function log(msg: string) { console.log(`[bot] ${msg}`); }

async function fileExists(p: string): Promise<boolean> {
  try { await access(p); return true; } catch { return false; }
}

function git(args: string[]): { code: number; stdout: string; stderr: string } {
  const r = spawnSync("git", args, { cwd: REPO_ROOT, encoding: "utf8" });
  return { code: r.status ?? -1, stdout: r.stdout ?? "", stderr: r.stderr ?? "" };
}

async function gatherContext(cost: { calls: number; tokens: number }): Promise<CycleContext> {
  // Last cycle: newest file in CYCLES_DIR.
  let lastCycleAt: string | null = null;
  let lastCycleGapId: string | null = null;
  try {
    const { readdir, stat } = await import("node:fs/promises");
    const entries = await readdir(CYCLES_DIR).catch(() => [] as string[]);
    let newestTs = 0;
    let newestPath: string | null = null;
    for (const e of entries) {
      if (!e.endsWith(".json")) continue;
      const p = join(CYCLES_DIR, e);
      const s = await stat(p);
      if (s.mtimeMs > newestTs) { newestTs = s.mtimeMs; newestPath = p; }
    }
    if (newestPath) {
      const r = JSON.parse(await readFile(newestPath, "utf8")) as CycleResult;
      lastCycleAt = r.started_at;
      lastCycleGapId = r.gap?.id ?? null;
    }
  } catch {}

  // Autotune status — if the agent is busy, skip this cycle to avoid
  // contention on shared Ollama GPU memory.
  let autotuneBusy = false;
  try {
    const r = await fetch(`${GATEWAY_URL}/vectors/agent/status`, { signal: AbortSignal.timeout(2000) });
    if (r.ok) {
      const j = await r.json() as any;
      autotuneBusy = Boolean(j.running) && (j.queue_depth ?? 0) > 0;
    }
  } catch {}

  // Dirty tree check.
  const status = git(["status", "--porcelain"]);
  const workingTreeDirty = status.code === 0 && status.stdout.trim().length > 0;

  return {
    startedAt: new Date().toISOString(),
    dailyCallsUsed: cost.calls,
    dailyCallsBudget: DAILY_CALLS_BUDGET,
    dailyTokensUsed: cost.tokens,
    dailyTokensBudget: DAILY_TOKENS_BUDGET,
    lastCycleAt,
    lastCycleGapId,
    autotuneBusy,
    workingTreeDirty,
  };
}

async function persistResult(res: CycleResult): Promise<void> {
  await mkdir(CYCLES_DIR, { recursive: true });
  await writeFile(join(CYCLES_DIR, `${res.cycle_id}.json`), JSON.stringify(res, null, 2));
}

function sigHash(gap_id: string | null, proposalSummary: string): string {
  const h = createHash("sha256");
  h.update(gap_id ?? "no-gap");
  h.update("|");
  h.update(proposalSummary);
  return h.digest("hex").slice(0, 16);
}

function emit(res: CycleResult): Promise<void> {
  return postEvent({
    source: "bot",
    cycle_id: res.cycle_id,
    sig_hash: sigHash(res.gap?.id ?? null, res.proposal?.summary ?? ""),
    event_kind: res.outcome,
    ok: res.outcome === "ok",
    staffer_id: res.proposal?.model_used,
    turns: res.cloud_calls,
    duration_ms: new Date(res.ended_at).getTime() - new Date(res.started_at).getTime(),
    extra: {
      reason: res.reason,
      pr_url: res.prUrl,
      files_added: res.filesAdded,
      files_updated: res.filesUpdated,
      files_noop: res.filesNoop,
      tests_green: res.testsGreen,
    },
  });
}

async function main() {
  const cycle_id = `bot-${new Date().toISOString().replace(/[:.]/g, "-")}-${randomUUID().slice(0, 8)}`;
  const started_at = new Date().toISOString();
  log(`cycle ${cycle_id} starting`);

  const finish = async (outcome: CycleOutcome, reason: string, extra: Partial<CycleResult> = {}): Promise<CycleResult> => {
    const res: CycleResult = {
      cycle_id,
      started_at,
      ended_at: new Date().toISOString(),
      outcome,
      reason,
      gap: null,
      proposal: null,
      filesAdded: [],
      filesUpdated: [],
      filesNoop: [],
      testsGreen: null,
      testsOutput: "",
      prUrl: null,
      tokens_used: 0,
      cloud_calls: 0,
      ...extra,
    };
    await persistResult(res);
    await emit(res);
    log(`→ ${outcome}: ${reason}`);
    return res;
  };

  // 1. Pause.
  if (await fileExists(PAUSE_FILE)) {
    return finish("skipped_pause", `pause file at ${PAUSE_FILE}`);
  }

  // 2. Cost.
  const cost = await readCost();
  const bc = budgetCheck(cost);
  if (!bc.ok) return finish("skipped_cost", bc.reason);
  log(`cost: ${bc.reason}`);

  // 3+4. Context + policy.shouldRunCycle.
  const ctx = await gatherContext(cost);
  const srq = policy.shouldRunCycle(ctx);
  if (!srq.run) {
    return finish(ctx.workingTreeDirty ? "skipped_dirty_tree" : "skipped_policy", srq.reason);
  }

  // 5. Gaps + policy.pickGap.
  const gaps = await findGaps();
  log(`found ${gaps.length} [bot-eligible] gap(s) in PRD`);
  const gapPick = policy.pickGap(gaps);
  if (!gapPick.gap) return finish("skipped_no_gap", gapPick.reason);
  const gap = gapPick.gap;
  log(`picked gap ${gap.id}: "${gap.prd_line.slice(0, 80)}"`);

  // 6. KB lookup + Proposal.
  // Bot cycles compound: prior cycles on this gap inform the current
  // proposal. Summary is a compact block injected into the cloud prompt
  // so the model can build on past successes and steer around past
  // failures. Empty string when this is the first cycle on this gap.
  const history = await loadHistory(gap.id, 5);
  const stats = statsFor(history);
  if (history.length > 0) {
    log(`kb: ${stats.attempts} prior cycle(s) — ${stats.pr_opened} pr / ${stats.tests_failed} tests_failed / ${stats.proposal_rejected} rejected / ${stats.noop} noop`);
  } else {
    log(`kb: first cycle on this gap`);
  }
  const historySummary = summarizeHistory(history);

  let proposal: Proposal;
  try {
    proposal = await generateProposal(gap, historySummary);
    log(`proposal: ${proposal.summary} (${proposal.files.length} files, ~${proposal.estimated_loc} LOC, ${proposal.tokens_used} tokens)`);
  } catch (e) {
    await recordCost(1, 0);
    return finish("model_failed", (e as Error).message, { gap, cloud_calls: 1 });
  }
  await recordCost(1, proposal.tokens_used);

  // 7. Score.
  const score = policy.scoreProposal(proposal);
  if (!score.accept) {
    return finish("proposal_rejected", score.reason, { gap, proposal, tokens_used: proposal.tokens_used, cloud_calls: 1 });
  }
  log(`proposal accepted: ${score.reason}`);

  // 8. Branch.
  const dayStamp = new Date().toISOString().slice(0, 10).replace(/-/g, "");
  const branch = `bot/cycle-${dayStamp}-${gap.id}`;
  // Branch must be fresh. If one already exists from a prior failed cycle
  // for the same gap, bail — don't silently overwrite or reuse stale state.
  const check = git(["rev-parse", "--verify", `refs/heads/${branch}`]);
  if (check.code === 0) {
    return finish("apply_failed",
      `branch ${branch} already exists — delete it manually if you want a fresh cycle for this gap`,
      { gap, proposal, tokens_used: proposal.tokens_used, cloud_calls: 1 });
  }
  const co = git(["checkout", "-b", branch]);
  if (co.code !== 0) {
    return finish("apply_failed", `git checkout -b failed: ${co.stderr}`,
      { gap, proposal, tokens_used: proposal.tokens_used, cloud_calls: 1 });
  }
  log(`on branch ${branch}`);

  // 9. Apply — Mem0 ADD/UPDATE/NOOP semantics.
  const ap = await applyProposal(proposal);
  if (ap.errors.length > 0) {
    git(["checkout", "main"]);
    git(["branch", "-D", branch]);
    return finish("apply_failed", ap.errors.join("; "),
      { gap, proposal, tokens_used: proposal.tokens_used, cloud_calls: 1 });
  }
  const changed = [...ap.added, ...ap.updated];
  log(`apply: ${ap.added.length} add, ${ap.updated.length} update, ${ap.noop.length} noop`);

  // Short-circuit: if every proposed file was identical to what's on
  // disk, there's nothing to test or PR. Clean up the branch and exit.
  if (changed.length === 0) {
    git(["checkout", "main"]);
    git(["branch", "-D", branch]);
    return finish("cycle_noop",
      `all ${proposal.files.length} proposed file(s) were identical to current state`,
      { gap, proposal, filesNoop: ap.noop,
        tokens_used: proposal.tokens_used, cloud_calls: 1 });
  }

  // 10. Test.
  log(`running tests (this will take a while)...`);
  const testRes = await runTests();
  if (!testRes.green) {
    git(["checkout", "."]);
    git(["checkout", "main"]);
    git(["branch", "-D", branch]);
    return finish("tests_failed", "cargo or bun test failed", {
      gap, proposal,
      filesAdded: ap.added, filesUpdated: ap.updated, filesNoop: ap.noop,
      testsGreen: false, testsOutput: testRes.output,
      tokens_used: proposal.tokens_used, cloud_calls: 1,
    });
  }
  log(`tests green`);

  // 11. PR gate.
  const partial: CycleResult = {
    cycle_id, started_at,
    ended_at: new Date().toISOString(),
    outcome: "ok", reason: "",
    gap, proposal,
    filesAdded: ap.added, filesUpdated: ap.updated, filesNoop: ap.noop,
    testsGreen: true, testsOutput: testRes.output,
    prUrl: null, tokens_used: proposal.tokens_used, cloud_calls: 1,
  };
  const prGate = policy.shouldOpenPR(partial);
  if (!prGate.open) {
    git(["checkout", "main"]);
    git(["branch", "-D", branch]);
    return finish("pr_skipped_by_policy", prGate.reason, partial);
  }

  // 12. Commit + push.
  git(["add", ...changed]);
  const commitMsg = [
    `bot: ${proposal.summary}`,
    "",
    proposal.rationale,
    "",
    `PRD gap: ${gap.prd_line}`,
    `Cycle: ${cycle_id}`,
    "",
    `Co-Authored-By: ${proposal.model_used} (cloud) <bot@lakehouse.local>`,
  ].join("\n");
  const ci = git(["commit", "-m", commitMsg]);
  if (ci.code !== 0) {
    return finish("pr_failed", `git commit failed: ${ci.stderr}`, partial);
  }
  const ps = git(["push", "-u", "origin", branch]);
  if (ps.code !== 0) {
    return finish("pr_failed", `git push failed: ${ps.stderr}`, partial);
  }

  // 13. Open PR.
  try {
    const pr = await openPr({
      branch,
      title: `bot: ${proposal.summary}`,
      body: [
        `**Gap** (PRD line ${gap.line_number}): ${gap.prd_line}`,
        "",
        `**Rationale**`,
        proposal.rationale,
        "",
        `**Cycle**: \`${cycle_id}\``,
        `**Model**: \`${proposal.model_used}\``,
        `**Tokens**: ${proposal.tokens_used}`,
        `**Added**: ${ap.added.map(f => `\`${f}\``).join(", ") || "_none_"}`,
        `**Updated**: ${ap.updated.map(f => `\`${f}\``).join(", ") || "_none_"}`,
        ap.noop.length > 0 ? `**NOOP (identical to current)**: ${ap.noop.map(f => `\`${f}\``).join(", ")}` : "",
      ].join("\n"),
    });
    return finish("ok", `PR #${pr.number} opened`, { ...partial, prUrl: pr.html_url });
  } catch (e) {
    return finish("pr_failed", (e as Error).message, partial);
  }
}

main().catch(e => {
  console.error("[bot] fatal:", e);
  process.exit(1);
});