Why: P2 A01 rerun failed on route contract C8; determine cause before any fix.
Evidence: docs/superpowers/specs/2026-10-21-fast-slow-o2-c8-review.md
Impact: docs and task card only; no code or paid runs.
Refs: feature/fast-slow-o2-c8-review
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Review found the design steered analysis findings to direct_relation,
which the host always downgrades, and the plan's eval/live command fails
without the live build tag.
Evidence: Verified against material_evidence.go and go list ./eval/live/;
the live-tag test runs offline (SELF).
Impact: Docs and task card only.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/662
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: O2 P1 proved the route contract on the real route, but A01 stopped at
the first work checkpoint because the model mixed evidence modes and the
evaluation stops on any rejection. The user chose a zero-paid design that
tightens the tool guidance and lets the evaluation allow one correction.
Evidence: Offline replay of the A01 checkpoint against agent-system-core
reproduces "direct relation cannot have result" (SELF); design-only change.
Impact: Adds a design doc, an implementation plan and the task card; no
product code, paid request, instance config or deployment.
Refs: .task/feature-fast-slow-o2-a01-evidence-design.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: include the current integration baseline before verification.
Evidence: fetched origin/main=adbef2f49c6c252a09449496afbdb6685201993b.
Impact: integrate upstream changes without rewriting task history.
Refs: task-sync
Why: independent re-review of the receipt pass-through fix passed with no blockers.
Evidence: reviewer replay of live eval and runtime tests on 16f98b8
Impact: task card and review package only.
Refs: docs/superpowers/specs/2026-10-20-fast-slow-o2-i2-review.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The user approved O2 I1 at stage 6 on 2026-10-20, accepted the C2 numbering, and asked to start I2.
Evidence: Agent-Native #48 merged at 2fc66be after head 899fd70 status success; merged tree 720ec93 matches the pre-merge merge-tree.
Impact: Task card and review package only.
Refs: Agent-Native#48, Agent-System-Dev#647
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: O2 I1 is implemented in Agent-Native #48 and needs user stage 6 review before merge.
Evidence: Worker attempt 2 success at 899fd70; host vet and tests (with -race) pass; PR #48 CI success; independent review PASS with no blocking issues.
Impact: Task card and review package only; Agent-Native #48 stays draft until stage 6 approval.
Refs: Agent-Native#48, Agent-System-Dev#639
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: user chose O2 in the completion signal evaluation; stage 4/5 docs precede any code.
Evidence: read-only code location in Agent-Native runtime/llm and Backend runtime (SELF).
Impact: docs only; no product code, no paid requests.
Refs: docs/superpowers/specs/2026-10-19-fast-slow-completion-signal-evaluation.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: RDM and Frontend units must implement one citation interface.
Evidence: Derived from the merged U6 evidence batch model (RDM 703e41d) and current cockpit/inspect read models.
Impact: Spec only.
Refs: docs/superpowers/plans/2026-10-18-regulations-knowledge-base-plan.md U7
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: U1 of the regulations KB plan requires a verified import inventory before any schema or ingestion work.
Evidence: dump sha256 matches manifest; 2878/2907 originals hash-verified in a disposable pgvector container (SELF).
Impact: Spec only; no corpus data or product code changed.
Refs: docs/superpowers/plans/2026-10-18-regulations-knowledge-base-plan.md U1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why:
Provide phased rollout roadmap (Phases 1-5) for stock repositories and mandatory defaults for new projects under governance v2.
Evidence:
Specification documented in docs/superpowers/specs/2026-10-16-stock-repos-adoption-matrix.md.
Impact:
Clarifies U6 and U7 governance deliverables for multi-repo rollout without ambiguity.
Refs:
feature/development-governance-v2
Why:
Audit differences between Agent-System-Dev agent_exec.py and Development-Manager runner.go to clarify layer responsibilities for governance v2.
Evidence:
Architecture specification document created in docs/superpowers/specs/.
Impact:
Provides guidance for U3 shared executor convergence without duplicating logic across repositories.
Refs:
feature/development-governance-v2
Why: user approved the four design documents and authorized implementation
(/goal); the plan's section-7 tradeoffs gate the I1 public DTO and had to be
frozen before any implementation unit starts. A read-only audit of the RDM
backend (Agent-System-RDM main 5df66106) supplied the source facts.
Evidence: audit findings recorded in rollout section 7 (tree is doc->section
only, no confidence field, no persisted conflict entity, per-project event seq
complete); review fixes folded into the read-model contract (statReasons,
structuralGap, AssertionSummary); precheck receipt READY imported via
task-resume.
Impact: unlocks I1 implementation in the RDM repo; design deliverable ready
for PR/CI/merge; no business code, pins, database or deployment touched.
Refs: .task/feature-document-visualization-plan.md
Why: Let each project route expensive implementation work across available Agent CLIs while the host model retains planning and delivery control.
Evidence: The specification passed placeholder, consistency, scope, path, and whitespace self-checks; implementation and runtime validation remain NOT_RUN.
Impact: Defines a review-only R1-R10 design for Markdown configuration, adapters, run-everything execution, receipts, recovery, and host fallback without enabling the new route.
Refs: .task/feature-goal-first-delivery.md
weichenandCursor