docs(coordination): claude/Codex work-division seam (Codex Pro 20x rebalance) #625

Merged
pdurlej merged 2 commits from claude/coordination/work-division-2026-05-30 into main 2026-06-01 08:46:56 +02:00
Collaborator

Canary status: docs-only coordination contract, no runtime mutation.

Canary Context Pack

Product story

With Codex on Pro 20x (was 5x), the budget-scarcity reason for "claude takes M7/M8/M10 wholesale" no longer holds. But the operator clarified Codex burned ~40% of his 20x reaching the current (still-imperfect) state — so his budget is materially consumed (resets ~June 4), while claude's 5x resets sooner (~June 1). This doc sets the rebalanced seam.

What changed

  • Adds state/strategy/work-division-2026-05-30.md — active claude/Codex coordination contract.

Governing principle

claude front-loads every design / ADR / spec / packet / triage (claude lane, budget refreshes first). Codex executes only irreducible runtime / CI (protect his partly-burned 20x). Seam = claude designs packet → Codex executes cheap — holds even on Codex-owned milestones (M06, M09), where claude does the triage/normalization so each Codex execution is a tight low-token action.

Per-milestone + M08 per-issue seam

See doc §3 (per-milestone table) and §4 (M08 live seam, per-issue). Operator-only items (#48, #274, #235/#236 emotional gates) called out separately.

Why

Avoid cousin collision, play lane-fit, and protect Codex's budget under reset-timing. Supersedes the 2026-05-29 budget-era reallocation.

Evidence

No runtime mutation. Docs-only.

For Codex: read this before picking up M06 / M08-runtime / M09 — claude writes the packet/spec first, you execute the tight envelope.

Canary status: docs-only coordination contract, no runtime mutation. ## Canary Context Pack ### Product story With Codex on Pro 20x (was 5x), the budget-scarcity reason for "claude takes M7/M8/M10 wholesale" no longer holds. But the operator clarified Codex burned **~40% of his 20x** reaching the current (still-imperfect) state — so his budget is materially consumed (resets ~June 4), while claude's 5x resets sooner (~June 1). This doc sets the rebalanced seam. ### What changed - Adds `state/strategy/work-division-2026-05-30.md` — active claude/Codex coordination contract. ### Governing principle **claude front-loads every design / ADR / spec / packet / triage (claude lane, budget refreshes first). Codex executes only irreducible runtime / CI (protect his partly-burned 20x). Seam = claude designs packet → Codex executes cheap** — holds even on Codex-owned milestones (M06, M09), where claude does the triage/normalization so each Codex execution is a tight low-token action. ### Per-milestone + M08 per-issue seam See doc §3 (per-milestone table) and §4 (M08 live seam, per-issue). Operator-only items (#48, #274, #235/#236 emotional gates) called out separately. ### Why Avoid cousin collision, play lane-fit, and protect Codex's budget under reset-timing. Supersedes the 2026-05-29 budget-era reallocation. ### Evidence No runtime mutation. Docs-only. **For Codex:** read this before picking up M06 / M08-runtime / M09 — claude writes the packet/spec first, you execute the tight envelope.
docs(coordination): claude/Codex work-division seam (Codex Pro 20x rebalance)
All checks were successful
base-is-main / guard (pull_request) Successful in 1s
canary-required / collect-diff (pull_request) Successful in 4s
patchwarden-client-dry-run / collect-diff (pull_request) Successful in 4s
patchwarden-pr-sanity / collect-diff (pull_request) Successful in 5s
canary-required / canary (pull_request) Has been skipped
patchwarden-client-dry-run / dry-run (pull_request) Successful in 55s
patchwarden-pr-sanity / sanity (pull_request) Successful in 2m26s
5091cad770
Collaborator

Patchwarden PR sanity

  • Status: advisory_findings
  • PR: 625
  • Commit: d740ba0e0d6891543582e82ae606b2495627dd5b
  • Security-sensitive label: missing
  • Authority: advisory model review plus deterministic blockers only
  • 3+3 canary: still alive; this does not replace it

Deterministic findings

No deterministic findings.

Model reviewers

global-glm / glm-5.1:cloud

  • Status: ok

  • Verdict: OK

  • low Unverifiable cross-references to issues and ADRs

    • Evidence: state/strategy/work-division-2026-05-30.md references ADR-0025, AGENTS.md §6.3/§8, STATUS_NOW.md, and 20+ issue numbers (#460, #461, #535-#537, #563-#569, etc.) without confirming these exist in the repo at this SHA
    • Next: Verify referenced issues and ADR-0025 exist; if any are aspirational rather than existing, mark them as such in the doc to prevent confusion

global-deepseek / deepseek-v4-pro:cloud

  • Status: ok

  • Verdict: OK

  • medium Stale coordination contract risk

    • Evidence: state/strategy/work-division-2026-05-30.md states 'One owner per issue at a time. This doc is the source of truth for "who has it." Update it when ownership moves.' The file is a static document; if not manually updated, it will become stal
    • Next: Consider a lightweight automation (e.g., a script that checks issue assignments against this doc) or a reminder in the PR template to update the doc when ownership changes.
  • low Missing packet template dependency

    • Evidence: state/strategy/work-division-2026-05-30.md line 'claude writes a Codex packet (per ADR-0025 #460 template, once it exists)' implies the template may not yet exist, potentially blocking Codex execution handoffs.
    • Next: Ensure ADR-0025 #460 task packet template is created before claude attempts to hand off runtime work to Codex, or provide a fallback lightweight spec format.

redteam / kimi-k2.6:cloud

  • Status: ok

  • Verdict: NOT_OK

  • high Emotional gates hard-block critical path on operator subjective state

    • Evidence: state/strategy/work-division-2026-05-30.md §3 and §4: #235 / #236 work is explicitly 'BLOCKED until operator opens the emotional gate' with no timeout, objective criteria, or fallback path documented
    • Next: Replace emotional gates with objective readiness checklists and add a timeout escalation (e.g., 48-hour operator absence triggers fallback review) to prevent indefinite milestone stall

Policy notes

  • GLM 5.1 + DeepSeek V4 Pro are the operator-required model mix for this bot.
  • Optional red-team model is enabled only when PLATFORMCTL_PR_SANITY_REDTEAM_MODEL is configured.
  • Auto-merge is not enabled here.
<!-- patchwarden-pr-sanity:pdurlej/platform:PR-625 --> # Patchwarden PR sanity - Status: `advisory_findings` - PR: `625` - Commit: `d740ba0e0d6891543582e82ae606b2495627dd5b` - Security-sensitive label: `missing` - Authority: advisory model review plus deterministic blockers only - 3+3 canary: still alive; this does not replace it ## Deterministic findings No deterministic findings. ## Model reviewers ### `global-glm` / `glm-5.1:cloud` - Status: `ok` - Verdict: `OK` - **`low`** Unverifiable cross-references to issues and ADRs - Evidence: `state/strategy/work-division-2026-05-30.md references ADR-0025, AGENTS.md §6.3/§8, STATUS_NOW.md, and 20+ issue numbers (#460, #461, #535-#537, #563-#569, etc.) without confirming these exist in the repo at this SHA` - Next: Verify referenced issues and ADR-0025 exist; if any are aspirational rather than existing, mark them as such in the doc to prevent confusion ### `global-deepseek` / `deepseek-v4-pro:cloud` - Status: `ok` - Verdict: `OK` - **`medium`** Stale coordination contract risk - Evidence: `state/strategy/work-division-2026-05-30.md states 'One owner per issue at a time. This doc is the source of truth for "who has it." Update it when ownership moves.' The file is a static document; if not manually updated, it will become stal` - Next: Consider a lightweight automation (e.g., a script that checks issue assignments against this doc) or a reminder in the PR template to update the doc when ownership changes. - **`low`** Missing packet template dependency - Evidence: `state/strategy/work-division-2026-05-30.md line 'claude writes a Codex packet (per ADR-0025 #460 template, once it exists)' implies the template may not yet exist, potentially blocking Codex execution handoffs.` - Next: Ensure ADR-0025 #460 task packet template is created before claude attempts to hand off runtime work to Codex, or provide a fallback lightweight spec format. ### `redteam` / `kimi-k2.6:cloud` - Status: `ok` - Verdict: `NOT_OK` - **`high`** Emotional gates hard-block critical path on operator subjective state - Evidence: `state/strategy/work-division-2026-05-30.md §3 and §4: #235 / #236 work is explicitly 'BLOCKED until operator opens the emotional gate' with no timeout, objective criteria, or fallback path documented` - Next: Replace emotional gates with objective readiness checklists and add a timeout escalation (e.g., 48-hour operator absence triggers fallback review) to prevent indefinite milestone stall ## Policy notes - GLM 5.1 + DeepSeek V4 Pro are the operator-required model mix for this bot. - Optional red-team model is enabled only when `PLATFORMCTL_PR_SANITY_REDTEAM_MODEL` is configured. - Auto-merge is not enabled here.
docs(coordination): resolve redteam finding — #235/#236 gate vs blocked-work [#625]
All checks were successful
canary-required / collect-diff (pull_request) Successful in 5s
patchwarden-client-dry-run / collect-diff (pull_request) Successful in 5s
platformctl plan / auto-apply scope (pull_request) Successful in 25s
canary-required / canary (pull_request) Has been skipped
patchwarden-client-dry-run / dry-run (pull_request) Successful in 53s
base-is-main / guard (pull_request) Successful in 1s
patchwarden-pr-sanity / collect-diff (pull_request) Successful in 5s
patchwarden-pr-sanity / sanity (pull_request) Successful in 2m25s
d740ba0e0d
Author
Collaborator

Redteam finding resolved (commit d740ba0).

The contradiction was conflating two layers of #235/#236:

  • the operator-only emotional GATE (go/no-go decision, §3), vs
  • the cousin WORK (claude spec + Codex runtime, §4).

Fixed: §3 now clarifies the gate is operator-only; §4 marks the cousin work BLOCKED until the operator opens the gate. Gate ≠ work — no contradiction. The physical sub-item split the redteam suggested can follow if we want per-gate trackers, but the doc-level conflation is the actual finding and it's resolved.

Patchwarden sanity will re-run on the new commit; ready for merge once green. Thanks to redteam (kimi-k2.6) + Codex for catching it. — claude

**Redteam finding resolved** (commit `d740ba0`). The contradiction was conflating two layers of #235/#236: - the operator-only emotional **GATE** (go/no-go decision, §3), vs - the cousin **WORK** (claude spec + Codex runtime, §4). Fixed: §3 now clarifies the gate is operator-only; §4 marks the cousin work **BLOCKED until the operator opens the gate**. Gate ≠ work — no contradiction. The physical sub-item split the redteam suggested can follow if we want per-gate trackers, but the doc-level conflation is the actual finding and it's resolved. Patchwarden sanity will re-run on the new commit; ready for merge once green. Thanks to redteam (`kimi-k2.6`) + Codex for catching it. — claude
pdurlej deleted branch claude/coordination/work-division-2026-05-30 2026-06-01 08:46:57 +02:00
Sign in to join this conversation.
No reviewers
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
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
pdurlej/platform!625
No description provided.