Reconcile unified project guide compilation plans - #298
Merged
Conversation
📝 WalkthroughWalkthroughThe PR reconciles planning artifacts around WS-POL-003 unified compilation. It stages inactive compilation, authorization, approval, projection, checker, artifact, review, and contribution contracts with exact lineage, deterministic post-submit behavior, and POL-07 sole-port routing. ChangesUnified compilation and projection
Estimated code review effort: 3 (Moderate) | ~25 minutes Possibly related issues
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 10
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
@.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12-project-mutation-cutover.md:
- Around line 45-48: Update the inventory in
.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12-project-mutation-cutover.md:45-48
to move 12E, 12F3, and legacy 12G derivation into historical or explicitly
non-activatable entries gated by POL-04B/POL-08. Update
.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/STATUS.md:180-192
to identify 12E as transitional and include the same POL-04B/POL-08 removal
gate, keeping retired actions out of the active inventory.
- Around line 38-43: Complete the 12I action inventory for
project.guide_compilation.request and project.guide_compilation.execute by
adding PermissionId, ActionOwner, child ownership, resource/PREP scope, and
proof requirements, or link both rows to the existing complete 12I contract
defined by the inventory at Line 49-68. Ensure the activation contract is fully
specified without requiring AUTH implementation to infer missing fields.
In
@.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12F4-submission-policy-approval.md:
- Around line 25-38: Propagate the complete WS-POL-003 unified-lineage tuple
across all three sites: in
.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12F4-submission-policy-approval.md
lines 25-38, bind PREP and stale-generation checks to the current approval
hash/provenance; in
.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-04-post-submit-runtime-hardening.md
lines 3-6, replace generic stored-component wording with exact compilation,
result, component, catalogue, and compiled-plan lineage plus
sole-port/no-selection acceptance; in
.agent-loop/initiatives/WS-CON-001-contribution-compensation-boundary/PLAN.md
lines 3-7, replace the generic unified compilation/plan reference with the full
tuple, including post-submit component, catalogue hashes, and current approval
provenance/hash.
In
@.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-14-submission-checker-cutover.md:
- Around line 5-17: Clarify the ownership boundary in the chunk’s Goal and
related scope sections: AUTH must verify admission authority, including
authorization for submission.create, while feature owners retain submission
mutations and checker execution, findings, and routing. Explicitly exclude
product behavior and checker-port work from AUTH so the required AUTH action is
not omitted or moved into this service.
In
@.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-15-worker-authority-removal.md:
- Around line 108-111: Update the scanner rule described in the worker-authority
removal guidance to reject only legacy standalone or three-call derivation
paths, including the three transitional guide inference entry points. Exclude
unified compilation and its model-backed post-submit component, such as
WS-POL-003 provider compilation, from the rejection criteria.
In
@.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md:
- Around line 10-11: Update the goal statement in the post-submit checker
document to use the compound modifier “end-to-end” instead of “end to end,”
leaving the rest of the statement unchanged.
In
@.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/DECISIONS.md:
- Around line 3-9: Update
.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/DECISIONS.md
lines 3-9 so D1-D8 are explicitly historical or describe unified compilation
with zero post-submit model calls; update
.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/INTENT.md
lines 3-10 likewise, ensuring both documents consistently treat WS-POL-003 as
authoritative and no longer present setup-time post-submit derivation as active
guidance.
In
@.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03B-authorized-compilation-persistence.md:
- Around line 12-13: Replace stale human-worker terminology across both chunk
contracts: in
.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03B-authorized-compilation-persistence.md
lines 12-13, change “router/worker composition” to fixed-service execution
composition; lines 17-18, change “live unified worker cutover” to live
setup-service cutover; lines 22-25, describe authentication as
“workstream.project.setup”; and in
.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04A-hidden-unified-setup.md
lines 17-18, change “Live worker routing” to fixed-service routing.
In
@.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04B-live-unified-setup-cutover.md:
- Around line 22-24: Update the live orchestration contract around
compile_project_guide so each independent PREP projection binds immutable
compilation and exact result hashes, plus the matching sufficiency or
artifact-policy component hash. Replace the ambiguous shared
“compilation/component hash” wording and align both projection requirements with
WS-POL-003-05B and WS-AUTH-001-12G.
In
@.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06-post-submit-deterministic-cutover.md:
- Around line 5-8: Update the parent and acceptance language for post-submit
correction to state that correction requests consume existing provenance without
additional model calls, consistent with replay and recovery. Clarify that any
correction requiring new unified generation is a separate attempt and must use
its own idempotency key, including the corresponding references in
WS-POL-003-06A.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: a0647456-73a0-499a-b629-21167da4625c
📒 Files selected for processing (56)
.agent-loop/initiatives/WS-ART-001-immutable-artifact-storage/CHUNK_MAP.md.agent-loop/initiatives/WS-ART-001-immutable-artifact-storage/PLAN.md.agent-loop/initiatives/WS-ART-001-immutable-artifact-storage/chunks/WS-ART-001-06A-checker-input-materialization.md.agent-loop/initiatives/WS-ART-001-immutable-artifact-storage/chunks/WS-ART-001-06B-checker-output-routing.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/CHUNK_MAP.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/DECISIONS.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/PLAN.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/RISKS.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/STATUS.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12-project-mutation-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12B2-project-setup-service-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12F4-submission-policy-approval.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12G-post-submit-checker-policy-mutations.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12H-guide-activation.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12I-unified-compilation-activation.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-13-task-assignment-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-14-submission-checker-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-15-worker-authority-removal.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-16-evidence-live-proof.md.agent-loop/initiatives/WS-CON-001-contribution-compensation-boundary/PLAN.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/CHUNK_MAP.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/DECISIONS.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/INTENT.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/PLAN.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/STATUS.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-04-post-submit-runtime-hardening.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/CHUNK_MAP.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/DECISIONS.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/DISCOVERY.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/INTENT.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/PLAN.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/RISKS.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/STATUS.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03-compilation-persistence-validator.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03A-hidden-compilation-foundation.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03B-authorized-compilation-persistence.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04-initial-setup-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04A-hidden-unified-setup.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04B-live-unified-setup-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-05-approval-pre-submit-integration.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-05A-hidden-pre-submit-approval.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-05B-live-pre-submit-approval.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06-post-submit-deterministic-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06A-hidden-post-submit-projection.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06B-live-post-submit-projection.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-07-single-checker-service-port.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-08-visibility-correction-cleanup.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-PLAN-pr-trust-bundle.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-internal-review-evidence.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-pr-trust-bundle.md.agent-loop/initiatives/WS-REV-001-review-revision-lifecycle/CHUNK_MAP.md.agent-loop/initiatives/WS-REV-001-review-revision-lifecycle/PLAN.md.agent-loop/initiatives/WS-XINT-002-art-auth-end-to-end/CHUNK_MAP.md.agent-loop/initiatives/WS-XINT-002-art-auth-end-to-end/STATUS.md.agent-loop/initiatives/WS-XINT-002-art-auth-end-to-end/chunks/WS-XINT-002-06B-post-submit-checker-activation.md
abiorh-claw
self-requested a review
August 8, 2026 08:05
abiorh-claw
approved these changes
Aug 8, 2026
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md (2)
35-36: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winState the infrastructure-failure boundary explicitly.
“Without inventing product decision values” does not prohibit recording infrastructure failure as contributor blame or a review decision. Add that explicit acceptance criterion to protect the existing checker/review/revision lifecycle from misclassification.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md around lines 35 - 36, Update the acceptance criteria around the checker/review/revision lifecycle to explicitly define the infrastructure-failure boundary: infrastructure failures must not be recorded as contributor blame or review decisions, and must continue through the existing failure lifecycle without introducing product decision values.
28-34: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winRequire the complete lineage and retry contract.
The acceptance criteria omit required binding facts: project/task/assignment, guide/policy, artifact, manifest, generation, action, service identity, and transaction facts. They also do not state that replay returns the canonical result without rerunning completed members, or that a new evaluation requires a new attempt identity. Add these requirements before this chunk becomes executable. Otherwise stale, cross-resource, or replayed calls can bypass the required fail-closed behavior.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md around lines 28 - 34, Expand the acceptance criteria around the existing lineage and retry requirements to bind project/task/assignment, guide/policy, artifact, manifest, generation, action, service identity, and transaction facts. State that replay returns the canonical result without rerunning completed members, while any new evaluation requires a new attempt identity; preserve the existing same-run/plan and no-duplicate-effect constraints.
🧹 Nitpick comments (1)
.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-external-review-response.md (1)
8-24: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd traceable evidence to this review response.
The response lists cross-workstream claims and rerun commands, but it does not include exact artifact paths, line ranges, exit statuses, or relevant command output. Add those details for AUTH-12I custody, POL-04B projection binding, POL-002 cleanup, the no-decision conclusion, and the no-activation assertion. This will allow later reviewers to verify the response against the downstream WS-POL-003 contracts.
As per coding guidelines,
.agent-loop/**stores durable engineering memory, evidence, and review logs.Also applies to: 26-32, 34-42
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-external-review-response.md around lines 8 - 24, Add traceable evidence to the review response for AUTH-12I custody, POL-04B projection binding, POL-002 cleanup, the no-decision conclusion, and the no-activation assertion. For each claim, include exact artifact paths, line ranges, rerun commands, exit statuses, and relevant command output, while preserving the existing cross-workstream conclusions and documenting the evidence in the durable review record.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In
@.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md:
- Around line 35-36: Update the acceptance criteria around the
checker/review/revision lifecycle to explicitly define the
infrastructure-failure boundary: infrastructure failures must not be recorded as
contributor blame or review decisions, and must continue through the existing
failure lifecycle without introducing product decision values.
- Around line 28-34: Expand the acceptance criteria around the existing lineage
and retry requirements to bind project/task/assignment, guide/policy, artifact,
manifest, generation, action, service identity, and transaction facts. State
that replay returns the canonical result without rerunning completed members,
while any new evaluation requires a new attempt identity; preserve the existing
same-run/plan and no-duplicate-effect constraints.
---
Nitpick comments:
In
@.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-external-review-response.md:
- Around line 8-24: Add traceable evidence to the review response for AUTH-12I
custody, POL-04B projection binding, POL-002 cleanup, the no-decision
conclusion, and the no-activation assertion. For each claim, include exact
artifact paths, line ranges, rerun commands, exit statuses, and relevant command
output, while preserving the existing cross-workstream conclusions and
documenting the evidence in the durable review record.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: a1ca7462-2dca-485c-a4f3-d9e13d2e5e87
📒 Files selected for processing (25)
.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/STATUS.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12-project-mutation-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12B2-project-setup-service-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12F4-submission-policy-approval.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-14-submission-checker-cutover.md.agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-15-worker-authority-removal.md.agent-loop/initiatives/WS-CON-001-contribution-compensation-boundary/PLAN.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/DECISIONS.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/INTENT.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-04-post-submit-runtime-hardening.md.agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-05-post-submit-live-api-proof.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/CHUNK_MAP.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/DISCOVERY.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/STATUS.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03-compilation-persistence-validator.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03B-authorized-compilation-persistence.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04-initial-setup-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04A-hidden-unified-setup.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04B-live-unified-setup-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06-post-submit-deterministic-cutover.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06A-hidden-post-submit-projection.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-08-visibility-correction-cleanup.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-external-review-response.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-internal-review-evidence.md.agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-pr-trust-bundle.md
🚧 Files skipped from review as they are similar to previous changes (23)
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03B-authorized-compilation-persistence.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04A-hidden-unified-setup.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04B-live-unified-setup-cutover.md
- .agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/chunks/WS-POL-002-04-post-submit-runtime-hardening.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-internal-review-evidence.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-04-initial-setup-cutover.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06A-hidden-post-submit-projection.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-03-compilation-persistence-validator.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-08-visibility-correction-cleanup.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/chunks/WS-POL-003-06-post-submit-deterministic-cutover.md
- .agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/INTENT.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/STATUS.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-15-worker-authority-removal.md
- .agent-loop/initiatives/WS-CON-001-contribution-compensation-boundary/PLAN.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12B2-project-setup-service-cutover.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12-project-mutation-cutover.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/reviews/WS-POL-003-RECONCILIATION-pr-trust-bundle.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/STATUS.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/CHUNK_MAP.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-14-submission-checker-cutover.md
- .agent-loop/initiatives/WS-AUTH-001-workstream-authorization-service/chunks/WS-AUTH-001-12F4-submission-policy-approval.md
- .agent-loop/initiatives/WS-POL-002-post-submit-checker-foundation/DECISIONS.md
- .agent-loop/initiatives/WS-POL-003-unified-project-guide-compilation/DISCOVERY.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Chunk
WS-POL-003 planning reconciliation across remaining POL, AUTH, ART, XINT, REV, CON, and POL-002 work.
Goal
Make one unified Project Guide compilation attempt the sole future inference path and eliminate planning that could restore repeated model calls, mixed-generation policy lineage, or cross-boundary ownership.
Scope
No runtime code, migration, action availability, permission, CI threshold, or product data changes.
Design
One logical/provider attempt produces sufficiency, artifact, pre-submit, and post-submit proposals before approval. Approvals perform no inference. Post-submit projection is deterministic and performs zero additional model calls. No database transaction or prepared handle spans provider I/O.
POL owns compilation, projections, and checker orchestration. AUTH owns catalogue/evaluator/PREP activation and decision evidence. ART owns immutable materialization and bindings. REV and CON retain their lifecycle ownership.
Alternatives rejected
Acceptance proof
Test and documentation delta
Planning/docs only. No production or test code changed.
Commands passed:
python3 scripts/check_stale_authorization_docs.pypython3 scripts/check_stale_workstream_wording.pypython3 scripts/check_markdown_links.pypython3 scripts/test_agent_gates.pygit diff --checkReviewer results
Architecture, security, product/operations, QA, senior engineering, and documentation internal reviews passed. All ten CodeRabbit inline findings were addressed and architecture/security re-review passed on the repair diff.
CI integrity
No workflow, dependency, test, lint, coverage, or configuration gate was weakened. Hosted Agent Gates and Backend run on the exact pushed head.
Risks
Future planning skeletons require exact allowed paths, forbidden changes, runnable commands, and named reviewers before implementation. This PR activates nothing.
Ownership and next action
After human merge, WS-POL-003-01 is the first executable candidate and requires a separate explicit start.
Summary by CodeRabbit
Planning Updates
Reliability and Security
Documentation