deslop(governance): reconcile cousin roster to canonical 9 (+ 3 operator calls) #732
Labels
No labels
W6d-automerge-calibration
agent/claude-code
agent/codex
agent/hermes
agent/iskra
agent/ollama
agent/patchwarden
automerge-candidate
class/security-sensitive
cutover-gate
dependency/blocked
dependency/blocks-others
dependency/cross-repo
dependency/needs-confirmation
domain:agents
domain:ci
domain:docs
domain:forgejo
domain:infra
domain:memory
domain:runtime
domain:signal
domain:ux
flow/architecture
flow/blocked
flow/deployed
flow/done
flow/implementation
flow/intake
flow/maintained
flow/observed
flow/ready
flow/refining
flow/retired
flow/review
iterating
judge/codex-candidate
judge/hermes-candidate
judge/low-confidence
judge/needs-refinement
judge/operator-needed
judge/p0
judge/p1
judge/p2
judge/p3
judge/park
judge/patchwarden-candidate
judge/stale-priority
kind/adr
kind/bug
kind/chore
kind/feature
kind/infra
kind/ops
kind/refactor
kind/research
large-impact
merge/auto
merge/manual
merge/manual-dependency-conflict
merge/manual-failing-tests
merge/manual-merge-conflict
merge/manual-missing-review
merge/manual-operator-preference
merge/manual-red-zone
merge/manual-security-sensitive
merge/manual-unclear-scope
merge/manual-unknown
meta
mode:operator-only
mode:patchwarden-iskra-approved
mode:safe-auto
needs-operator-decision
needs-triage
not-ready
observed/erroring
observed/needs-followup
observed/pending
observed/retire-candidate
observed/unused
observed/used
operator-emotional
owner-attention
phase/02
phase/03
priority:p0
priority:p1
priority:p2
priority:p3
proposed
ready-for-agent
ready-for-operator
recovery
review:claude-reviewed
review:codex-reviewed
review:dziadek-reviewed
review:needs-human
risk/exposure
risk/process
risk/product
risk/runtime
safety:external-write
safety:no-prod-mutation
safety:prod-impact
safety:secret-touch
size/large
size/medium
size/small
size/tiny
size/unknown
source/adr
source/agent-generated
source/manual
source/operator-chat
source/voice-note
status:blocked
status:codex-ready
status:merged:pending-evidence
status:needs-evidence
status:operator-needed
status:parked
tier/full
tier/lite
tier/stacked
tier:0-platform-substrate
tier:1-iskra-value-layer
tier:2-tools-products-modules
type:bug
type:chore
type:docs
type:feat
type:policy
type:research
No milestone
No project
No assignees
2 participants
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
pdurlej/platform#732
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
From the 2026-06-05 deslop audit — the highest-leverage governance drift (roster identity drives Forgejo write-identity boundaries).
Problem
The cousin roster is described 5+ mutually inconsistent ways across "canonical" sources: AGENTS.md §0 lists 8 names; AGENTS.md §Cousins (self-branded "canonical per ADR-0010") says "seven" with a DIFFERENT set incl. antigravity; ADR-0010 lists 7;
docs/agents/cousin-roles.md(the cited glossary) says "seven"; ADR-0016 says 7→8; ADR-0023 says "8 cousins" then adds gemini as "9th". The glossary's own amendment rule was violated for both deepseek AND gemini. MAP.md self-contradicts (line 349 vs 104-105).Canonical source-of-truth (verified:
agent-souls/AGENTS.md§1, which explicitly declares itself the source-of-truth)9 cousins:
3 OPERATOR decisions needed before the sync is mechanical
(antigravity = confirmed NOT a cousin — Gemini is "via Antigravity" = the harness. No decision needed.)
Fix (after operator answers the 3)
Pick ONE canonical roster (count + membership), then sync ALL of:
AGENTS.md(§0 + §Cousins),docs/agents/cousin-roles.md,decisions/0010,decisions/0016,MAP.md,policies/agent-capabilities.yaml. Resolve gemini-vs-antigravity conflation. Update cousin-roles.md amendment log; honor the amendment rule going forward.Acceptance
Design + the 3 operator calls; the cross-file sync is then mechanical (Codex).
Role: advisor · Intent: research packet (decyzja NIE podjęta — to brama operatora)
🫖 Pan Herbatka — zinwentaryzowałem cały roster-drift na żywo na
main(plik:linia), żeby 3 bity operatora od razu odpaliły mechaniczny sync. Nie rozstrzygam — mapuję + rekomenduję.Kanon (per ADR-0023 →
agent-souls/AGENTS.md §1): 9 kuzynów (bez operatora)Iskra · Codex · Prof Opus · Pan Herbatka · Pyfallow · Oracle · Hermes · Dziadek (deepseek) · Gemini
Mapa driftu — 10 „kanonicznych" źródeł, 5+ różnych odpowiedzi
AGENTS.md:13§0AGENTS.md:75§Cousinsdecisions/0010:16docs/agents/cousin-roles.md:10decisions/0016:1,21decisions/0023-gemini:11,42MAP.md:104-105vs:349MAP.md §By cousin (91-102)policies/agent-capabilities.yaml:29,42agent-souls/AGENTS.md §13 bity tylko-operator (rekomendacje advisor — decyzja Piotra)
Mechaniczne (bez decyzji — codex-ready od razu)
AGENTS.md:82,docs/agents/cousin-roles.md:38.ADR-0023(gemini vs wloczykij) — to issue #730 (renumber wloczykij → 0026).cousin-roles.md; honoruj amendment-rule dalej.Pliki do sync po decyzji
AGENTS.md(§0 + §Cousins) ·docs/agents/cousin-roles.md·decisions/0010·decisions/0016·MAP.md(104-105, 349, 91-102) ·policies/agent-capabilities.yaml— zweryfikowane na
main2026-06-08 (Pan Herbatka, advisor)Iskra judgment
pdurlej/platform#issue#732judge/p2,judge/operator-needediskraviaopenclawRationale: This is P2 operator-needed governance cleanup because inconsistent cousin identity sources can confuse agent authority, write boundaries, and future audits.
Caveat: Do not rewrite identity doctrine mechanically; first resolve the three owner calls and then patch all canonical references consistently.
Structured openclaw.judge.v0 payload