Commit Graph

4 Commits

Author SHA1 Message Date
f58ddba93e fix(routing): הוראת-יו"ר תעבוד בדרך הטבעית — הערה פותחת הרצת-CEO
All checks were successful
G12 Leak-Guard / leak-guard (pull_request) Successful in 37s
Lint — undefined names / undefined-names (pull_request) Successful in 10s
**התסמין:** היו"ר כותב הוראה על תיק והסוכן "מתעלם". ההרצה מדווחת succeeded/exit 0
ואפילו עולה כסף — ולכן זה שרד חודשים בלי שמישהו שם לב.

**שתי סיבות-שורש בלתי-תלויות, שתיהן מאומתות:**

1. ה-wakeup הישיר על ה-issue של התיק מבוטל תמיד: תיק שממתין ליו"ר הוא `in_review`
   ומשויך *לאדם*, ו-Paperclip עונה `issue_assignee_changed` → "אעיר את הבעלים החדש"
   → הבעלים אדם → אף סוכן לא מתעורר.
2. רשת-הביטחון בפלאגין מוסרת את ההוראה כ-`payload.prompt`, וה-runner קורא רק
   `payload.issueId` — הפרומפט נבלע. 18/18 מדידה ב-DB: 0% מסירה, אי-פעם.

**התיקון:** המסלול הטבעי (הערה בטאב-הסוכנים) מפרסם את ההערה בשרשור כרגיל **וגם**
פותח הרצת-CEO עם ההוראה, דרך `pc_open_ceo_run` — הפרימיטיב היחיד שאומת כמגיע
לסוכן (הוכח היום על 1043-02-26: 3,212→7,697 מילים). אותו תיקון ל-interaction-response,
שסובל מאותה תקלה (החצי השני של #228).

**G2 — הסרת מסלול מקביל:** ה-wakeup הנדון-לביטול הוסר מ-`post_comment`; הוא היה
המסלול השני, זה ששותק. כעת מסלול-מסירה קנוני אחד. `mark_comment_routed` מסמן את
ההערה כמנותבת כדי שה-sweep לא יירה הרצת-סרק על מה שכבר טופל.

**G12 — שער-הפלטפורמה:** המגע החדש (`mark_comment_routed`) נחשף דרך
`agent_platform_port.py` בלבד; leak-guard עובר.

התיקון יושב ב-backend (REST) ולא בפלאגין, ולכן אינו חשוף לבאג ה-invocation-scope
שמפיל את ה-sweep. תועד ב-docs/paperclip-quirks.md §7 עם המלכודות שנתקלנו בהן.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-16 12:32:20 +00:00
fe4694672e docs(paperclip-quirks): comment→CEO routing reads issue id from event.entityId (quirk #6)
All checks were successful
G12 Leak-Guard / leak-guard (pull_request) Successful in 4s
Lint — undefined names / undefined-names (pull_request) Successful in 11s
Document the Paperclip event-shape quirk that silently disabled user-comment→CEO
routing: `issue.comment.created` carries the issue id in `event.entityId`, not
`payload.issueId` (payload has commentId/bodySnippet/reopened). Includes the
empirical log from case 8124-09-24, the issue_assignee_changed cancellation
chain, the fix (plugin PR #2), and verification.

Invariants: upholds CLAUDE.md "ניתוב comments דרך CEO"; G12/X15 (fix lives in the
platform-port shell, not the decision skills). Docs-only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 04:59:36 +00:00
e239915fd3 docs(paperclip-quirks): §5 — pruned npx cache → 500/crash-loop + fix
Document the failure mode hit on 06/06/26: a pruned npx cache makes the
running paperclip serve GET / → 500 (deleted ui-dist) and, on restart,
crash-loop because the server's startup assertCloudDatabaseContract()
out-races the post-exec patch loop.

Records the synchronous pre-extract+patch gate now in start-paperclip.sh
(paperclip-config c824e0f), the `--help` clean-extract trick, the three
bugs found while building the fix (ui-dist vs dist marker, set -e on patch
failure, pkill -f self-match), the manual recovery runbook, and the e2e
verification.

Invariants: docs-only; touches no G*/INV-* code paths.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 21:24:12 +00:00
6a38789379 docs+heartbeat: paperclip quirks + temp-file pattern + self-recovery
All checks were successful
Build & Deploy / build-and-deploy (push) Successful in 7s
Two latent issues surfaced today while watching the case 8174-24
end-to-end run, both worth documenting and engineering around because
they will recur on every future case.

Bug 1 — issue.released flips done→todo
  After an agent successfully PATCHes its issue to "done", Paperclip's
  internal issue.released action reverts the status to "todo" within
  ~30 seconds. This triggers a fresh wakeup of the same agent on a
  task that is already complete.
  Reproduced on CMPA-18 (30/04/26):
      18:14:57  agent PATCH → status: done
      18:15:35  Paperclip   → issue.released → status: todo
      18:15:54  new researcher run started
  The fix at the right altitude (Paperclip itself) is outside our repo.
  Mitigation in HEARTBEAT.md §3 — when an agent boots and finds the
  issue in `todo` while expected outputs (file, DB rows) already exist,
  it must short-circuit: post a "no change" comment, PATCH back to done,
  and exit. Costs ~$0.20 per false wakeup but breaks the loop.

Bug 2 — Bash backtick trap on long comment bodies
  Researcher agent built a curl pipeline like:
      curl ... -d "$(python3 -c "body = '''...
        📁 קובץ מחקר: `/path/to/file.md`
        '''")"
  The backticks around the file path (markdown convention) get
  evaluated by the OUTER bash $(...) as command substitution. Bash
  then tries to exec /path/to/file.md, which is not executable, and
  prints "Permission denied" — a misleading error since the actual
  file ownership is fine. The curl itself succeeded; only the bash
  prelude noised up the log.
  Fix in HEARTBEAT.md §4א: long bodies must go via Write→tempfile
  then `curl -d @file`. Avoids every shell quoting edge case.

Files:
  • docs/paperclip-quirks.md — new. Full writeup of both bugs plus
    two prior known-quirks (CEO auto-block in_progress, INSERT vs
    API for wakeups). Each section: what happens, empirical evidence
    from logs, impact, workaround, status.
  • .claude/agents/HEARTBEAT.md — added the self-recovery section to
    §3 and the temp-file pattern to §4א. The temp-file pattern is the
    canonical answer for any agent posting markdown comments —
    applies to all 7 agents in this skill set.
  • CLAUDE.md — referenced the new doc from the docs index.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 18:23:32 +00:00