dsh-fast-mode 1.5.28 → 1.5.29

package/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## 1.5.29（1.5.28 的补丁：把 `bench/turns.py` 真的放进包里）
+
+- `package.json` 的 `files` 是一份白名单，1.5.28 新增的 `bench/turns.py` 没进去：`npm pack dsh-fast-mode@1.5.28` 里没有这个脚本，而 `CHANGELOG` 和 `bench/README.md` 都在教读者运行它。1.5.29 只改白名单 + 版本号，**代码与 1.5.28 逐字相同**。
+- 复核方式：`npm pack dsh-fast-mode@1.5.29 --silent` 解包后应同时看到 `package/bench/turns.py` 与 `package/index.js` 里的 `VERSION = '1.5.29'`。
+
 ## 1.5.28（稳定性：压缩后同一轮里不再重复发同一条提醒）
 
 - **先量后改**：新增 `bench/turns.py`，把留存会话按 `turn/start` 切成轮，统计「够长却没收到提醒」「同一轮收到两次以上」「多轮会话里后续轮是否重新上膛」。72 小时窗口 68 个会话 / 1446 轮：647 个合格轮**646 个收到**提醒（99.8 %）、后续轮重新上膛 599/600；但**同一轮收到两次的有 114 轮**，其中 **105 轮（92 %）两次之间夹着一次上下文压缩**。

package/bench/turns.py

@@ -0,0 +1,210 @@
+#!/usr/bin/env python3
+"""Does the late-discipline reminder re-arm per turn, and only once per turn?
+
+The reminder is a once-per-turn lever: `disciplineSent` latches it so a long turn
+is told to stop narrating exactly once, and `noteTurn` clears the latch so the
+next request in the same session is told again. Both halves are invisible in the
+wall-clock numbers — a turn that never got the reminder looks like a turn that
+ignored it, and a turn that got it twice looks like a model that keeps forgetting.
+
+This reads retained transcripts, segments them on `turn/start`, and reports:
+
+- turns per session, steps per turn;
+- turns long enough to qualify (>= 4 steps) that got **no** reminder;
+- turns that got **two or more** reminders (the latch leaking);
+- re-arm rate: in multi-turn sessions, the share of later qualifying turns that
+  were reminded again.
+
+Usage:
+  python3 bench/turns.py                  # suite sessions
+  python3 bench/turns.py --limit 100      # first 100 transcripts
+  python3 bench/turns.py --min-steps 4 --json
+"""
+
+from __future__ import annotations
+
+import argparse
+import collections
+import glob
+import json
+import os
+import subprocess
+import time
+
+SESS = os.path.expanduser('~/.dsh/sessions')
+NEEDLE = 'this turn is long enough that prose'
+# A delivered directive is a message part; the model quoting it back inside its
+# own prose is an echo, so assistant-authored text never counts as delivery.
+PLUGIN_ROLES = {'user/message', 'agent/inbox/spliced', 'system/message'}
+
+
+def transcripts(pattern, limit, exclude_arm=('off',)):
+    """Session transcripts whose run directory (the slug) is not one of `exclude_arm`.
+
+    The slug mirrors the run directory, so `...-suite-D2G2-ledger-p1-def15--`
+    identifies the arm without re-reading the YAML.
+    """
+    out = []
+    for d in sorted(glob.glob(os.path.join(SESS, pattern))):
+        name = os.path.basename(d)
+        if any(name.endswith(f'-{arm}--') for arm in exclude_arm):
+            continue
+        out.extend(glob.glob(os.path.join(d, 'session-*', 'session.v4.jsonl.zstd')))
+    return out[:limit] if limit else out
+
+
+def text_of(data):
+    msg = data.get('message') or data
+    parts = msg.get('content') if isinstance(msg, dict) else None
+    if not isinstance(parts, list):
+        return ''
+    return ' '.join(p.get('text') or '' for p in parts
+                    if isinstance(p, dict) and p.get('type') == 'text')
+
+
+def scan(path):
+    """Return (started_ms, turns) for one transcript, or None if unreadable."""
+    p = subprocess.run(['zstd', '-dc', path], capture_output=True)
+    if p.returncode != 0:
+        return None
+    started = 0
+    turns = []
+    cur = {'steps': 0, 'reminders': 0, 'reminderSeqs': [], 'compactions': [],
+           'reminderSteps': []}
+    for line in p.stdout.decode('utf-8', 'replace').splitlines():
+        if ('turn/start' not in line and 'step/start' not in line
+                and 'Auto schedule' not in line and 'compaction/start' not in line):
+            continue
+        try:
+            o = json.loads(line)
+        except Exception:  # noqa: BLE001 - a torn line is not fatal
+            continue
+        kind = o.get('type')
+        data = o.get('data') or {}
+        if not started and isinstance(o.get('time'), int):
+            started = o['time']
+        if kind == 'turn/start':
+            if cur['steps'] or cur['reminders']:
+                turns.append(cur)
+            cur = {'steps': 0, 'reminders': 0, 'reminderSeqs': [], 'compactions': [],
+           'reminderSteps': []}
+        elif kind == 'step/start':
+            cur['steps'] += 1
+        elif kind == 'compaction/start':
+            cur['compactions'].append(o.get('seq'))
+        elif kind in PLUGIN_ROLES and NEEDLE in text_of(data):
+            cur['reminders'] += 1
+            cur['reminderSeqs'].append(o.get('seq'))
+            cur['reminderSteps'].append(cur['steps'])
+    if cur['steps'] or cur['reminders']:
+        turns.append(cur)
+    return started, turns
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--limit', type=int, default=0, help='transcripts; 0 = all')
+    ap.add_argument('--dir', default='--*dsh-runs-suite-*')
+    ap.add_argument('--min-steps', type=int, default=4)
+    ap.add_argument('--json', action='store_true')
+    ap.add_argument('--exclude-arm', action='append', default=[],
+                    help='skip sessions whose run directory ends in this arm (default: off)')
+    ap.add_argument('--explain-doubles', action='store_true',
+                    help='list every turn that got two reminders, with seqs and compactions')
+    ap.add_argument('--since-hours', type=float, default=0,
+                    help='only sessions started within this many hours')
+    a = ap.parse_args()
+
+    sessions = turns_total = multi = 0
+    qualifying = reminded = 0
+    misses = doubled = doubled_compacted = 0
+    later_qualifying = later_reminded = 0
+    per_session_turns = collections.Counter()
+    entry_steps = collections.Counter()
+    offenders = []
+    cutoff = (time.time() - a.since_hours * 3600) * 1000 if a.since_hours else 0
+    skipped_old = 0
+    for f in transcripts(a.dir, a.limit, tuple(a.exclude_arm or ['off'])):
+        r = scan(f)
+        if not r:
+            continue
+        started, turns = r
+        if cutoff and started and started < cutoff:
+            skipped_old += 1
+            continue
+        if not turns:
+            continue
+        sessions += 1
+        turns_total += len(turns)
+        per_session_turns[len(turns)] += 1
+        if len(turns) > 1:
+            multi += 1
+        for i, t in enumerate(turns):
+            if t['steps'] >= a.min_steps:
+                qualifying += 1
+                if t['reminders']:
+                    reminded += 1
+                else:
+                    misses += 1
+                if i > 0:
+                    later_qualifying += 1
+                    later_reminded += 1 if t['reminders'] else 0
+            if t['reminders']:
+                entry_steps[t['reminderSteps'][0]] += 1
+            if t['reminders'] > 1:
+                doubled += 1
+                seqs = t['reminderSeqs']
+                if any(c is not None and seqs and seqs[0] < c < seqs[-1] for c in t['compactions']):
+                    doubled_compacted += 1
+                if a.explain_doubles:
+                    offenders.append({
+                        'session': os.path.basename(os.path.dirname(os.path.dirname(f))),
+                        'turn': i + 1,
+                        'steps': t['steps'],
+                        'reminderSeqs': seqs,
+                        'reminderSteps': t['reminderSteps'],
+                        'compactions': t['compactions'],
+                    })
+
+    out = {
+        'sessions': sessions,
+        'turns': turns_total,
+        'multi_turn_sessions': multi,
+        'turns_per_session': dict(sorted(per_session_turns.items())),
+        'min_steps': a.min_steps,
+        'qualifying_turns': qualifying,
+        'reminded': reminded,
+        'missed': misses,
+        'doubled': doubled,
+        'doubled_with_compaction_between': doubled_compacted,
+        'entry_steps': dict(sorted(entry_steps.items())),
+        'later_qualifying_turns': later_qualifying,
+        'later_reminded': later_reminded,
+        'skipped_old': skipped_old,
+        'since_hours': a.since_hours,
+    }
+    if a.json:
+        print(json.dumps(out, ensure_ascii=False, indent=2))
+        return
+    print(f"sessions {sessions}  turns {turns_total}  multi-turn {multi} "
+          f"({100 * multi / max(sessions, 1):.0f} %)")
+    print(f"turns per session: {dict(sorted(per_session_turns.items()))}")
+    print(f"qualifying turns (>= {a.min_steps} steps) {qualifying}  "
+          f"reminded {reminded} ({100 * reminded / max(qualifying, 1):.0f} %)  "
+          f"missed {misses}  doubled {doubled} "
+          f"(with a compaction between: {doubled_compacted})")
+    if entry_steps:
+        print(f"first reminder landed at step: {dict(sorted(entry_steps.items()))}")
+    if a.explain_doubles and offenders:
+        print('doubled turns:')
+        for o in offenders[:20]:
+            print(f"  {o['session']} turn {o['turn']} steps {o['steps']} "
+                  f"reminders at steps {o['reminderSteps']} seqs {o['reminderSeqs']} "
+                  f"compactions {o['compactions']}")
+    print(f"later turns in multi-turn sessions: qualifying {later_qualifying}  "
+          f"reminded {later_reminded} "
+          f"({100 * later_reminded / max(later_qualifying, 1):.0f} %)")
+
+
+if __name__ == '__main__':
+    main()

package/index.js

@@ -97,7 +97,7 @@ const TAG = '[fast-mode]'
  * Shipped identity of this build. Traced into the debug log so a stale install is
  * visible at a glance, and pinned by a test against `package.json`.
  */
-export const VERSION = '1.5.28'
+export const VERSION = '1.5.29'
 const GLOBAL_AGENT = '__global__'
 
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-fast-mode",
-  "version": "1.5.28",
+  "version": "1.5.29",
   "description": "DeepSeek Harness fast mode: same thinking effort, fewer round trips. An adaptive parallel tool fan-out, output discipline that never trims the answer, and a cancellable stall guard. Never changes reasoning effort, the model, or the request body. Provider-agnostic, one dependency (@deepseek-ai/schemastery).",
   "repository": {
     "type": "git",
@@ -44,6 +44,7 @@
     "bench/reminders.py",
     "bench/patchshare.py",
     "bench/ablate.py",
+    "bench/turns.py",
     "docs/",
     "LICENSE"
   ],