#!/usr/bin/env node
// Hook: pre-agent-cap.mjs
// Event: PreToolUse (WebSearch | WebFetch | Task)
// Purpose: Enforce the /trekresearch Phase 5 loop bound at the harness level,
//   so the cap is a reader that fells rather than prose the model obeys.
//
// Why this exists: the Phase 5 budget gate (lib/util/research-loop-cap.mjs) is
// invoked BY the loop. A gate the caller chooses to consult is advice. The
// spike in docs/spike-pretooluse-subagent-reach.md (RESULT: FIRES) established
// that a plugin PreToolUse hook does observe tool calls made INSIDE sub-agents
// on CC 2.1.226, which is what makes a second, non-optional gate possible.
//
// Two limits carried over from that spike, neither of which changes the design:
//   - Reach was measured on one CC version and regressed once before (#34692),
//     so this hook is defence in depth, never the only gate. research-loop-cap
//     must stay correct if this hook silently stops firing.
//   - Whether a blocking (exit 2) decision from inside a sub-agent propagates
//     usefully was NOT measured — the probe always exited 0 by design.
//
// Scope key — the property that makes this safe to wire globally:
//   session_id + a scope marker file that only the Phase 5 loop writes, at
//   <data root>/trekresearch-loop-scope/<session_id>.json, where the data root
//   comes from research-loop-cap.mjs's resolveDataRoot() — the same function
//   the writer resolves through, because a writer and a reader that resolve
//   the root separately are a hook that enforces nothing while reporting that
//   it does:
//       { "runId": "<run id>", "startedAt": "<ISO-8601>" }
//   No marker for this session => out of scope => allow, unconditionally. An
//   unrelated session must never be denied because some other run spent its
//   budget; a PreToolUse hook that over-blocks breaks every session on the box.
//
//   Stated limit, because the guarantee above is about OTHER sessions and reads
//   as broader than it is: `claude --resume` keeps the same session_id, so a
//   resumed session is the same session by this key. If a run reached its cap
//   and then died before removing the marker, the resume inherits the remainder
//   of the TTL, for any WebSearch/WebFetch/Task — research or not. Three things
//   bound it rather than close it: only an EXHAUSTED run denies at all (a
//   part-spent crash leaves no tombstone and is allowed), the TTL is 2h rather
//   than a working day, and every denial prints the marker path to delete. A
//   liveness check would close it properly, but a PreToolUse hook has nothing
//   trustworthy to check liveness against — the marker's writer is a shell
//   snippet whose $$ is a subshell, not the session.
//
// Fail-open vs fail-closed, deliberately split:
//   - Out of scope (no marker, no session_id, unparsable stdin, stale marker,
//     kill switch, STORM off) => exit 0. Fail OPEN.
//   - In scope and over budget => exit 2. Fail CLOSED, mirroring
//     research-loop-cap.mjs's own stance: a budget control that cannot count
//     must not grant. (The former "CLAUDE_PLUGIN_DATA absent" deny is gone —
//     the root now always resolves, so that branch could no longer fire.)
//   - In scope and the ledger cannot be counted (EISDIR, EACCES, EIO — anything
//     but ENOENT) => exit 2, same reason. This branch used to ALLOW: the hook
//     carried a private countTurns() whose catch returned 0, so an unreadable
//     ledger read as "no turns spent". Counting now goes through the
//     primitive's exported readLedger(), so reader and writer cannot hold
//     different rules about what an unreadable ledger means.
//
// Counting is read-only. The ledger is append-only and written solely by
// research-loop-cap.mjs's allowTurn(); if this hook appended, the cap would
// count its own enforcement.
//
// Kill switch: VOYAGE_DISABLE_CAP_HOOK=1 disables enforcement entirely.

import { readFileSync, existsSync, rmSync } from 'node:fs';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';

const HERE = dirname(fileURLToPath(import.meta.url));
const { resolveLedgerPath, resolveDataRoot, resolveMaxConvTurns, isStormEnabled, readLedger, MAX_TOTAL_DIMENSIONS } =
  await import(join(HERE, '..', '..', 'lib', 'util', 'research-loop-cap.mjs'));

const SCOPE_DIRNAME = 'trekresearch-loop-scope';
// 2h — comfortably longer than any real research run (a 24-turn loop at a couple
// of minutes a turn is under an hour), and short enough that debris does not own
// the rest of the working day. The TTL is measured from marker.startedAt rather
// than from last activity, and `claude --resume` keeps the same session_id, so
// this window is what a resumed session can inherit from a run that died holding
// the marker. It was 6h; nothing needed six.
const DEFAULT_TTL_MS = 2 * 60 * 60 * 1000;

const env = process.env;

function allow() {
  process.exit(0);
}

function deny(message) {
  process.stderr.write(`[voyage] BLOCKED: trekresearch loop cap\n${message}\n`);
  process.exit(2);
}

// 1. Kill switch.
if (env.VOYAGE_DISABLE_CAP_HOOK === '1') allow();

// 2. Default-off: no loop runs unless STORM is enabled, so nothing to enforce.
if (!isStormEnabled(env)) allow();

// 3. Parse stdin. Unparsable input is not evidence of a loop turn.
let input;
try {
  input = JSON.parse(readFileSync(0, 'utf-8'));
} catch {
  allow();
}

const sessionId = input?.session_id;
if (!sessionId || typeof sessionId !== 'string') allow();

// 4. Resolve the scope marker through the writer's own root resolution.
//    VOYAGE_CAP_SCOPE_DIR stays as a test/override seam; unset, this lands on
//    exactly the directory the Phase 5 snippet writes into.
const scopeDir = env.VOYAGE_CAP_SCOPE_DIR || resolveDataRoot(env);

const markerPath = join(scopeDir, SCOPE_DIRNAME, `${sessionId}.json`);
if (!existsSync(markerPath)) allow();

let marker;
try {
  marker = JSON.parse(readFileSync(markerPath, 'utf-8'));
} catch {
  allow(); // A marker we cannot read cannot tell us which run we are in.
}

if (!marker?.runId) allow();

// 5. TTL / auto-reset. A marker left behind by a crashed run must not deny
//    tool calls for the rest of the machine's life.
const ttlRaw = Number(env.VOYAGE_CAP_SCOPE_TTL_MS);
const ttlMs = Number.isFinite(ttlRaw) && ttlRaw > 0 ? ttlRaw : DEFAULT_TTL_MS;
const startedAt = Date.parse(marker.startedAt ?? '');
if (!Number.isFinite(startedAt) || Date.now() - startedAt > ttlMs) {
  try { rmSync(markerPath, { force: true }); } catch { /* best effort */ }
  allow();
}

// --- In scope from here on. ---

// 6. The ledger is the only source of truth for turns spent, and it is counted
//    through the primitive's OWN readLedger(). This hook used to carry a
//    private copy of the counting rule whose read error returned 0 — so an
//    unreadable ledger read as "no turns spent" and ALLOWED, in the one branch
//    where this hook is supposed to fail closed.
const ledgerPath = resolveLedgerPath(env);

// 7. Same bound the primitive uses: turns-per-dimension × the whole dimension
//    list under settings.json:16's maxDimensions ceiling.
const budget = resolveMaxConvTurns(env) * MAX_TOTAL_DIMENSIONS;

let ledger;
try {
  ledger = readLedger(ledgerPath, marker.runId);
} catch (e) {
  deny(
    `  Run ${marker.runId} is in scope, but its turn ledger could not be read:\n` +
    `    ${e.message}\n` +
    `  A budget control that cannot count must not grant. Fix or remove the\n` +
    `  ledger, or set VOYAGE_DISABLE_CAP_HOOK=1 to disable enforcement.`,
  );
}

const toolLine =
  `  Tool: ${input?.tool_name ?? 'unknown'}${input?.agent_type ? ` (agent: ${input.agent_type})` : ''}\n`;

// Every denial names the marker. If this run is over and the marker outlived it
// — the loop's own cleanup covers its three exits, but a crash between the
// exhaustion record and the removal runs no cleanup at all — deleting this file
// is the remedy, and a resumed session (same session_id) would otherwise sit out
// the remaining TTL for work that has nothing to do with research.
const remedyLines =
  `  If this loop is not running, the marker is debris — delete it:\n` +
  `    ${markerPath}\n` +
  `  It also auto-resets ${Math.round(ttlMs / 3600000)}h after the run started (VOYAGE_CAP_SCOPE_TTL_MS).\n`;

// 8. The boundary is the TOMBSTONE, not the count.
//
// allowTurn() appends before the turn runs, so during the final granted turn the
// ledger already holds `budget` records. Denying at `granted >= budget` blocked
// that turn's own tool calls — the primitive granted B turns and this hook
// permitted B-1 — and it forced every exhausted run out through an exit-2 tool
// denial rather than the graceful "cap exhausted" exit, the only exit the prose
// at commands/trekresearch.md teaches the model to handle.
//
// Moving the boundary to `granted > budget` alone would have made this hook
// unable to fire at all once the claim mechanism made a breached ledger
// impossible — a deny branch that cannot be reached is a dead security claim,
// not a backstop. So the primitive records its own denials, and the case this
// hook exists for is the one it now catches: the gate said no and a tool call
// arrived anyway.
if (ledger.exhausted > 0) {
  deny(
    `  Run ${marker.runId} was already denied a turn by the budget gate\n` +
    `  (${ledger.granted}/${budget} loop turns spent), and this call came after it.\n` +
    toolLine +
    `  Remaining gaps belong in the brief as open questions, not in another turn.\n` +
    remedyLines +
    `  Raise TREKRESEARCH_MAX_CONV_TURNS deliberately, or set VOYAGE_DISABLE_CAP_HOOK=1.`,
  );
}

// 9. Backstop for a ledger that exceeded the bound however it managed to.
if (ledger.granted > budget) {
  deny(
    `  Run ${marker.runId} shows ${ledger.granted} granted turns against a budget of ${budget}.\n` +
    toolLine +
    `  The ledger has been breached; the loop is over regardless of cause.\n` +
    remedyLines +
    `  Raise TREKRESEARCH_MAX_CONV_TURNS deliberately, or set VOYAGE_DISABLE_CAP_HOOK=1.`,
  );
}

allow();