sawbuck 0.1.21 → 0.1.22

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sawbuck",
-  "version": "0.1.21",
+  "version": "0.1.22",
   "description": "Sign your agent to a contract so it does what you want: a deterministic, zero-LLM check that re-proves every win from the agent's source edits alone, so a green that came from editing the test is caught and reverted. A saddle for your coding harness.",
   "type": "module",
   "license": "MIT",
@@ -28,6 +28,7 @@
     "debt.mjs",
     "status.mjs",
     "memory.mjs",
+    "yank.mjs",
     "providers/obsidian.mjs",
     "providers/mem0.mjs",
     "providers/local.mjs",

package/sawbuck.mjs

@@ -19,6 +19,7 @@ import { fileURLToPath } from 'node:url';
 import { homedir } from 'node:os';
 import { createRequire } from 'node:module';
 import { recall as memRecall, conform as memConform } from './memory.mjs';
+import { tally, resolveSessionPath } from './yank.mjs';
 
 const SELF = fileURLToPath(import.meta.url);
 const HERE = dirname(SELF);
@@ -98,6 +99,10 @@ Usage:
                             shows only the debt a branch adds; --fail-on exits nonzero for a CI gate
   sawbuck run --attempt '<cmd>' [--loops N]
                             Thin harness: load context, run one attempt through the keep-if-verified gate
+  sawbuck yank [--session <path>] [--json]
+                            The steering meter: how much you had to steer (yank the reins) this session,
+                            read from your Claude Code transcript. The check guards the turns you did not
+                            steer — a miss there is the risk. Yank rate falling = the reins getting looser.
   sawbuck --help | --version
 
 Rides two engines: promptwheel (the check) + @promptwheel/logbook (memory).`;
@@ -264,11 +269,41 @@ switch (cmd) {
         const armed = existsSync(join(repo, 'promptwheel.config.json')) || existsSync(join(repo, 'package.json'));
         const mem = existsSync(join(repo, 'LOGBOOK.md')) || existsSync(join(repo, 'events.jsonl'));
         const seg = caught > 0 ? `🐴 sawbuck · ${caught} caught` : active ? `🐴 sawbuck · watching` : armed ? `🐴 sawbuck · ready` : mem ? `🐴 sawbuck · memory` : '';
-        if (seg) process.stdout.write(last ? `${seg} · ${last}` : seg);
+        const base = seg ? (last ? `${seg} · ${last}` : seg) : '';
+        // the live steering readout, when the wrapper forwards the session transcript path
+        let yk = '';
+        const ti = rest.findIndex((a) => a === '--transcript' || a === '--session');
+        if (ti > -1 && rest[ti + 1]) { try { const { yanks, turns } = tally(readFileSync(rest[ti + 1], 'utf8')); if (turns) yk = `🤠 ${yanks}/${turns} yanks`; } catch {} }
+        // live steering % from the reins engine's file (OFFLINE read; reins does the LLM work, never sawbuck)
+        let st = '';
+        try { const sj = JSON.parse(readFileSync(join(repo, '.sawbuck', 'steer.json'), 'utf8')); if (sj && sj.scored) st = `🤠 steer ${Math.round((sj.steeringRate || 0) * 100)}%`; } catch {}
+        const outp = [base, yk, st].filter(Boolean).join(' · ');
+        if (outp) process.stdout.write(outp);
       }
     } catch {}
     break;
   }
+  case 'yank': {
+    // the live steering meter (the reins hook): how much did you have to steer this session?
+    // A MIRROR read from the Claude Code transcript; the check guards the turns you did NOT steer.
+    const si = rest.findIndex((a) => a === '--session' || a === '--transcript');
+    const sess = resolveSessionPath(si > -1 ? rest[si + 1] : null, process.cwd());
+    if (!sess) { out('🐴 sawbuck: no session transcript found to read (pass --session <path.jsonl>).'); process.exit(2); }
+    let text = ''; try { text = readFileSync(sess, 'utf8'); } catch { out('🐴 sawbuck: could not read the session transcript.'); process.exit(2); }
+    const { turns, yanks, rate, recent } = tally(text);
+    if (flags.has('--json')) { out(JSON.stringify({ turns, yanks, rate, recent })); break; }
+    const pct = Math.round(rate * 100);
+    out('🐴 reins: steering this session');
+    if (yanks === 0) {
+      out(`   0 hard yanks across ${turns} turns — you did not have to pull the reins hard.`);
+    } else {
+      out(`   ${yanks} hard yank${yanks === 1 ? '' : 's'} across ${turns} turns (${pct}%) — times you pulled me back hard.`);
+      if (turns - yanks > 0) out(`   the check guards the other ${turns - yanks} turns you trusted me with — a miss there is the risk.`);
+      if (recent.length) out(`   recent: ${recent.map((r) => '"' + r + '"').join(' · ')}`);
+    }
+    out('   (terse course-corrections only; the full steer rate, incl. discursive redirects, is the harvest layer.)');
+    break;
+  }
   default: die(`unknown command '${cmd}'\n\n${help}`);
 }
 

package/yank.mjs

@@ -0,0 +1,87 @@
+#!/usr/bin/env node
+// yank.mjs — the live steering meter (the "reins" hook). Reads the current Claude
+// Code session transcript and counts YANKS: turns where you corrected or redirected
+// the agent. Deterministic, zero-dep, with a transparent definition shown in the
+// output. It is a MIRROR — a number about how much you had to steer this session —
+// and it pairs with the check: the check guards the turns you did NOT steer, where
+// a miss is the real risk. The yank rate falling over time is the reins getting
+// looser (the agent learning your cues).
+//
+// A yank is counted CONSERVATIVELY (precision over recall): a human turn, after the
+// agent has acted, that OPENS by correcting or redirecting ("no", "don't",
+// "actually", "stop", "undo", "instead", ...). Discursive steers buried mid-
+// paragraph are deliberately NOT counted here — that is the LLM-harvest layer's job;
+// this stays cheap, instant, and honest (an undercount with a clear definition beats
+// an inflated guess).
+
+import { readFileSync, readdirSync, statSync, existsSync } from 'node:fs';
+import { join } from 'node:path';
+import { homedir } from 'node:os';
+
+// leading correction/redirect markers at the START of the turn (case-insensitive)
+const LEAD = /^\s*["'(]?\s*(no\b|no,|nope\b|don'?t\b|do not\b|actually\b|wait\b|stop\b|undo\b|revert\b|instead\b|nah\b|hold on|rather\b|not (that|like|quite|what|really)|that'?s (not|wrong)|hmm,? ?no|why (did|are) you|you (shouldn'?t|weren'?t))/i;
+
+function humanText(o) {
+  if (!o || o.type !== 'user' || o.isMeta) return null;
+  if (o.userType && o.userType !== 'external') return null;
+  const c = o.message && o.message.content;
+  if (typeof c === 'string') return c;
+  if (Array.isArray(c)) {
+    if (c.some((b) => b && b.type === 'tool_result')) return null;      // tool output, not you
+    const t = c.filter((b) => b && b.type === 'text').map((b) => b.text || '').join(' ');
+    return t || null;
+  }
+  return null;
+}
+const isNoise = (t) => {
+  const s = t.trim();
+  if (s.includes('<task-notification>') || s.startsWith('<task-id>')) return true; // injected
+  if (s.replace(/\[Image #\d+\]/g, '').trim().length < 3) return true;             // image-only
+  return false;
+};
+
+// tally(transcriptText) -> { turns, yanks, rate, recent } over YOUR typed turns.
+export function tally(text) {
+  let turns = 0, yanks = 0, seenHuman = false, prevAssistantActed = false;
+  const recent = [];
+  for (const line of String(text).split('\n')) {
+    if (!line.trim()) continue;
+    let o; try { o = JSON.parse(line); } catch { continue; }
+    if (o.type === 'assistant') { prevAssistantActed = true; continue; }
+    const t = humanText(o);
+    if (t === null || isNoise(t)) continue;
+    const opener = !seenHuman; seenHuman = true;
+    turns++;
+    if (!opener && prevAssistantActed && LEAD.test(t)) {
+      yanks++;
+      recent.push(t.replace(/\s+/g, ' ').trim().slice(0, 48));
+    }
+    prevAssistantActed = false;
+  }
+  return { turns, yanks, rate: turns ? yanks / turns : 0, recent: recent.slice(-5) };
+}
+
+// Resolve the newest session transcript for a cwd. Claude Code stores transcripts
+// under ~/.claude/projects/<encoded-cwd>/<id>.jsonl (path separators -> dashes).
+// Best-effort: prefer the dir matching this cwd, else the newest across all. Never throws.
+export function resolveSessionPath(explicit, cwd = process.cwd()) {
+  if (explicit) return existsSync(explicit) ? explicit : null;
+  const root = join(homedir(), '.claude', 'projects');
+  if (!existsSync(root)) return null;
+  const key = cwd.replace(/[^A-Za-z0-9]/g, '-');
+  let dirs = [];
+  try { dirs = readdirSync(root).map((d) => join(root, d)).filter((p) => { try { return statSync(p).isDirectory(); } catch { return false; } }); }
+  catch { return null; }
+  const matched = dirs.filter((p) => p.endsWith('/' + key));
+  const pool = matched.length ? matched : dirs;
+  let best = null, bestT = 0;
+  for (const full of pool) {
+    let files = []; try { files = readdirSync(full); } catch { continue; }
+    for (const f of files) {
+      if (!f.endsWith('.jsonl')) continue;
+      const p = join(full, f);
+      try { const st = statSync(p); if (st.mtimeMs > bestT) { bestT = st.mtimeMs; best = p; } } catch {}
+    }
+  }
+  return best;
+}