Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Root cause behind #41-#44: the framework verifies agent actions continuously and its own declarations never

Aperta
  • Qualcosa non va?
#45 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
5/5
Tempo stimato
Più di una settimana
Idoneità per principianti
25/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
shell
Ambito
devtools

Direzione di ricerca

Start by reading the six proposed changes and their cited entry points: agents/audit/audit.sh:3724, .context/working/.gitignore, the fw init templates, fw termlink dispatch, and fw doctor. The issue describes a broad architectural problem and several possible fixes, not a bounded first change; agree on scope with maintainers before proceeding. Done would mean implementing an agreed change that derives declarations where possible and validates irreducible cases at runtime.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

This is the cause behind #41, #42, #43 and #44

Those four were filed as separate defects over one day. They are not four defects. They are
four instances of one, and filing instances instead of the class is itself the mistake this
issue exists to correct.

The asymmetry

AEF gates agent behaviour at runtime, and does it well. P-002 on commands, G-020 on edits,
P-010/P-011 on completion, Tier 0 on destruction. Every action an agent takes passes a hook.

The framework's own output passes nothing. A template's cross-reference, a gitignore rule,
a hardcoded filter regex, a behavioural rule in CLAUDE.md, a deliverable a dispatch asks for,
the Mitigation: line an audit prints — each is asserted once and believed forever.

The agent is presumed unreliable and checked constantly. The framework is presumed correct
and checked never.

Every instance below has the same shape: a statement the framework makes about itself, written
in one context and consumed in another, that nothing re-evaluates at the point of use.

# The declaration Where it was true
#41 template: "See CLAUDE.md §AC Classification Guidance" when someone intended to write that section
#42 .gitignore names watchtower.{pid,port,url} as intent — not as mechanism; all three were already tracked, and a gitignore rule never untracks
#43 CTL-013b's WARN text: stored verifications are decaying of the mechanism the author imagined; the real one is a rotating cursor
#44 CLAUDE.md: "ask the user before you continue" in an interactive session
G-002 handler prints fw fix-learned T-XXX if a task is focused — it just unfocused one
PL-033 audit Mitigation: fields for a reader holding human authority

The last row is independent evidence, not ours: it arrived on channel:learnings from project
100-Video-riper-and-translation-app at 2026-09-21T15:03:42Z, while we were diagnosing the
others. There, 18 of 26 audit findings prescribe actions an agent is structurally forbidden
to take (CTL-029 ×15 → task update --status work-completed, refused by the sovereignty
gate; D13 → fw inception sweep, which ticks a Human AC by design). That one is not a false
statement. It is a true statement addressed to somebody who is not reading it — same root,
different branch.

Why the audit cannot catch this

The audit measures compliance with declared rules. It cannot measure whether the declared
rules are true. It reported 14 WARNs, byte-identical across three orchestrated rounds, while
five real defects walked past it.

What actually caught them: an agent, incidentally, while doing something else. #41 because an
operator objected to a Human AC. #42 while tidying git status. #44 because a deliverable file
was absent. Zero were caught by fw doctor, fw audit or fw reviewer.

A stable audit is not evidence of health. It is evidence that the audit is measuring the things
that do not change.

The fix, and the trap in the fix

The obvious response is "add checks that the two artefacts agree". Please do not, or at
least not first — a check is itself a declaration, and it rots the same way. That is the same
defect one level up.

Derive, do not duplicate. Wherever a rule is stated twice, delete one and generate it from
the other. A check that two statements agree is strictly worse than having one statement.

Concretely, in rough order of leverage:

  1. _SESSION_STATE_FILTER (agents/audit/audit.sh:3724) should be generated from
    .context/working/.gitignore,     not asserted to agree with it. Today two lists of volatile
    paths exist in two languages in two files, must agree, and are never compared — which is why
    the audit filtered the noise while the ignore rule that should have prevented it sat inert.
  2. Ship the sections templates point at. fw init should emit
    §AC Classification Guidance into the generated CLAUDE.md, or generate the template's
    pointer from the section that exists. Failing both, one fw doctor line: every
    See CLAUDE.md §X in a shipped template resolves.
  3. Make execution context a fact, not an assumption. fw termlink dispatch knows its worker
    is headless; CLAUDE.md cannot know and never will, because one file serves both. Inject the
    context and let rules branch on it. This is #44, and it silently truncated a 3-cycle mandate
    to one cycle at exit_code 0.
  4. --expect-artifact <path> on dispatch. A run whose promised deliverable is missing should
    report incomplete, not status: done. This alone would have caught three separate instances
    in our sequence automatically instead of relying on somebody noticing an absent file.
  5. Audit mitigations should state the authority they require. Then an agent can tell which
    findings are addressed to it — PL-033's finding, and the cheapest of these to implement.
  6. One fw doctor line for the general case: no tracked path matches an ignore rule
    (git ls-files | git check-ignore --stdin --no-index must be empty). That is #42 generalised.

Where derivation is genuinely impossible, the check belongs in fw doctor — never in a
task's Verification block. A task closes and takes its check with it.

Environment

  • Framework 1.6.769, shared-tooling mode, project 1409-sprind
  • Registered locally as concern G-003 (high, watching) with all six instances
  • Instance issues: #41, #42, #43, #44
Lingua principale
Shell
Stelle
16
Fork
6
Merge medio
6h 24m
PR unite (30g)
5

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di DimitriGeelen/agentic-engineering-framework

Tutte le issue di DimitriGeelen/agentic-engineering-framework

Issue simili

Altre issue su Shell/Bash

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.