docs(refactor): split open-questions.md into open + closed-questions archive - #46
Merged
Conversation
…archive Frees 97 LOC from open-questions.md (499 → 402) by archiving 8 closed §13.N entries into new closed-questions.md. Removes 500-LOC hook pressure so Wave 9 R-phase findings + Phase 10 decision register can land without destructive trim of historical content. Changes: - docs/meta-factory/closed-questions.md (NEW) — archive of 8 closed entries (§13.3, §13.21, §13.23, §13.25, §13.26, §13.27, §13.28, §13.29) with TOC and Authoritative-for header. - docs/meta-factory/open-questions.md — header authority statement updated; TOC added; closed entries removed; 21 open/armed entries retained. - Cross-reference sweep across docs/ packages/ .claude/ agents/ — 12 refs updated to closed-questions.md; research-patches/retros preserved (append-only/read-only per Artifact Ownership Contract). - .claude/rules/doc-authority-hierarchy.md §2 — §13.21 refs + See also updated; closed-questions.md listed in canonical docs. - packages/core/principles/09-doc-authority-hierarchy.ts — closed-questions.md added to REQUIRED_HEADER_DOCS. - docs/meta-factory/EXECUTION-PLAN.md — fix pre-existing MD040 violations at lines 72 and 168 (add text lang specifier to unlabelled fenced blocks). §1.7 Bootstrap: this is the introducing commit of closed-questions.md as a new canonical artefact. The append-only discipline in its authority header applies prospectively to future closures; this introducing migration moves 8 historical entries atomically and pre-dates the prospective enforcement. Prior-art: skipped — doc-only refactor split, no new capability; structural split of open-questions.md into open + closed archive, no new code capability.
This was referenced May 12, 2026
6 tasks
This was referenced May 26, 2026
artyhoo
added a commit
that referenced
this pull request
May 29, 2026
…eep evaluation (#268) Variant scored: MCP-consumer bridge (handoff_create_task + accept_existing_plan + WebSocket tail + handoff_sync_status). 7 DeepWiki probes + 2 WebSearch queries + SSOT #27/#28/#30/#43/#44/#46/#67/#80 consult + SKILL.md:404/429 disambiguation. Verdict: REFERENCE (not ADOPT). Body-format falsifier PASSES — description field accepts arbitrary markdown (z.string().optional(), no .max()). Minimum call = {projectId, title}. BUT full pipeline bridge blocked by three structural issues: (1) accept_existing_plan requires physical PLAN.md on disk in .ai-factory/ — filesystem coupling beyond MCP boundary; (2) WebSocket broadcast channel has no topic filter — client must filter by taskId; (3) aif-handoff Reviewer (autoMode) conflicts with reviewer-discipline.md §2 strategy-fork-surface gate. Admission gate §2.4: PR #127/#128 touch packages/runtime/ only — no packages/mcp/ or apps/coordinator/ changes. Gate CLEAR. SKILL.md:404 vs :429 inconsistency resolved analytically (both consistent — BFR verdict = REFERENCE for SP skill; operational action = ADOPT SP dispatch template). Prior-art: prior-art-evaluations.md#44 (DEFER, body-format now confirmed compatible); prior-art-evaluations.md#30 (DEFER, accept_existing_plan bypass documented); prior-art-evaluations.md#67 (REJECT unchanged — Variant A is optional layer, not replacement). Sub-wave D proposes new SSOT row for Variant A bridge vocabulary.
artyhoo
added a commit
that referenced
this pull request
May 29, 2026
…k + aif-handoff MCP) REFERENCE (#275) Verdict per BFR-default §1: REFERENCE — design-vocabulary for dispatch-trigger optimisation of Variant A; not actionable standalone. Key findings (2026-05-29 evidence): - CC PostToolUse hooks expose a purpose-built `mcp_tool` hook type for already-connected MCP servers (code.claude.com/docs/en/hooks.md fetched 2026-05-29) — T-AIF-BRIDGE-B'-1 evades via different shape than originally framed. - aif-handoff MCP server runs standalone without coordinator daemon for task creation (DeepWiki ×2 phrasings: «MCP server can be invoked statelessly from an arbitrary process» + «MCP HTTP daemon runs independently») — T-AIF-BRIDGE-B'-3 evades. - 4 sub-options each fit <100 LOC bridge target: Option (a') = 0 LOC bash (mcp_tool hook config), Option (a) = ~25 LOC bash (command hook + curl), Option (b) = ~15 LOC chokidar Node, Option (c) = ~10 LOC fswatch bash. BUT: B' inherits all 3 of SW-A's ADOPT-blockers verbatim (PLAN.md disk coupling, WebSocket-broadcast no-topic-filter, autoMode Reviewer vs reviewer-discipline.md §2 conflict — DN-1=B-constrained applies). B' optimises only the dispatch trigger; the load-bearing blockers persist. Comparison table vs A and B in §6. §4 5-criteria: PASS-PASS-PARTIAL-PASS-INHERITED. Match ~35%. Atomicity INCONCLUSIVE/MITIGABLE (chokidar awaitWriteFinish for Option b; empirical for hooks). Falsifier: B' upgrades to ADOPT VOCABULARY iff Sub-wave D greenlights A AND DN-1=B-constrained adopted. T-discipline applied per kickoff §6 SW-B2: T1 / T3 / T7 / T11 / T12 / T13 / T15 / T16 / T17 / T19 (own cold-QA before push) / T20 + T-AIF-BRIDGE-B'-1..5. Prior-art: SSOT #20 (CC hooks API, ADOPT) + SSOT #27/#28/#30/#43/#44/#46/#67/#80 (aif-handoff rows). Additive note to SSOT #44 proposed (no verdict change). Proposed new SSOT row at next-available slot #85.
artyhoo
added a commit
that referenced
this pull request
May 29, 2026
… Implementer-equivalent only) value-add audit (#276) R-phase patch for Sub-wave C of the aif-handoff-as-runtime-bridge umbrella. Evaluates Variant C (kickoff §3 lines 124-145): aif-handoff as Implementer- equivalent only, bypass Planner+Reviewer cycle, thin CLI wrapper for kickoff dispatch + kanban status tracking. Verdict: REJECT (BFR-default §1 ladder). Rationale: - The kickoff-framed "aif-handoff exec --kickoff <path>" CLI does not exist in lee-to/aif-handoff (DeepWiki probes 1+5, 2026-05-29). - No first-class Implementer-only mode; skipReview:true bypasses Reviewer but Planner is mandatory unless accept_existing_plan with on-disk PLAN.md (same disk coupling SW-A flagged for Variant A). - BEFORE/AFTER maintainer-action count: 25% literal / 0% cognitive reduction (T-AIF-BRIDGE-C table §4) — below kickoff §8 STOP 30% threshold → verdict "Variant C value-add insufficient". - Pure-tracker pattern (paused:true + autoMode:false + manual state-machine transitions) IS shipped but adds zero automation beyond UI tracking; Docker+SQLite infra unjustified. Cites: - SW-A merged PR #268 (Variant A REFERENCE, 28% match, 3 ADOPT-blockers) - SW-B merged PR #267 (Variant B REJECT, ~5% match, no dir-watch capability) - PR #269 follow-up (mechanical corrections, no verdict changes) - DN-1=B-constrained input consumed in criterion 5 (mooted for Variant C which bypasses aif-handoff Reviewer entirely) - Gate-4 admission re-sweep: PR #127+#128 touch packages/runtime/ only (no MCP/coordinator drift in 30-day window) 5 distinct DeepWiki probes + 2 WebSearches + cross-ref to SW-A/SW-B/PR #269 = 19+ evidence channels (T1 floor exceeded 3.8x). §1.7 forward+backward + §self-application + T-trap walk per ai-laziness-traps.md §3. Single output file under docs/meta-factory/research-patches/. No code, skill, agent, install.sh, or .claude/rules/ modifications. ### §1.7 Forward-check applied build-first-reuse-default.md §1 verdict ladder applied; BFR §3 6-layer search performed (SSOT rows #27/#28/#29/#30/#43/#44/#46/#67/#80 reviewed at prior-art-evaluations.md:95-148; DeepWiki >=5 probes; WebSearch >=2 phrasings; own-stack sweep at .claude/skills/meta-orchestrator/SKILL.md:441 anti-scope + :404+:429 SP requesting-code-review). no-paid-llm-in-ci.md §1 enforced (all evidence via subscription-bundled DeepWiki/WebSearch + free gh CLI + bash). reviewer-discipline.md §2 respected (DN-1=B-constrained consumed as fact, not re-litigated; verdict is research finding against §8 STOP, not strategy choice). ai-laziness-traps.md §3 active T-traps applied (T1, T3, T7, T11, T12, T13, T15, T16, T17, T19, T20, T-AIF-BRIDGE-C MANDATORY BEFORE/AFTER table at patch §4). Evidence: see patch §8 file:line citations. ### §1.7 Backward-check applied SSOT #27/#28/#67 receive additive notes (additive-only; no verdict changes). Original DEFER/DEFER/REJECT rationales reviewed at prior-art-evaluations.md: 95, 96, 135 — consistent with Sub-wave C findings (reinforce existing classifications, do not re-litigate). No .claude/rules/* modified; no .claude/skills/* modified; no agents/* modified; no packages/* modified; no install.sh modified; no kickoff.md modified. Single output file in docs/meta-factory/research-patches/. Scope strictly bounded to Variant C; SW-A/SW-B/SW-B2/SW-D out of scope. T15 self-application confirmed in patch §10. Memory not written (Sub-wave D synthesis is the natural codification surface). Evidence: see patch §9 file:line citations.
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
1 participant
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.
Summary
Splits the 499-LOC monolithic
docs/meta-factory/open-questions.mdinto two scoped files:open-questions.md(402 LOC, 21 armed/open entries)closed-questions.md(167 LOC, 8 terminal-status entries — append-only archive)Original §13.N anchor numbers preserved across both files for backward-link stability.
What moved to
closed-questions.mdPartial-closure entries (§13.7 sub-items, §13.16 v1-shipped, §13.22 v1-shipped) stay in open-questions per classification rules — terminal status not reached.
Cross-references updated (non-historical only)
12 files redirected from
open-questions.md §13.Ntoclosed-questions.md §13.Nfor moved entries. Historical archives (research-patches/,retros/,PHASE-*-PROMPT.md) intentionally not edited — append-only per Artifact Ownership Contract; backward-link stability preserved via anchor-number retention.package-lock.jsonchurn (+1087/-2) is npm install side-effect from fresh worktree, not a functional change.Test plan
npm test— 291/291 + preset 38/38 greenmake self-audit— 56/56 (principle 09 includes new file in REQUIRED_HEADER_DOCS atpackages/core/principles/09-doc-authority-hierarchy.ts:48)open-questions.md §13.{closed}refs across 8 closed IDs in non-historical files (.claude/,agents/,packages/,docs/meta-factory/)closed-questions.md:6with append-only declaration atclosed-questions.md:11§1.7 Skipped: doc-maintenance refactor — file split + cross-ref redirects; no new rule, no semantic change to existing disciplines. principle 09 REQUIRED_HEADER_DOCS extended by exactly one path (
packages/core/principles/09-doc-authority-hierarchy.ts:48); rule-consistency verified mechanically viamake self-audit56/56 green + 0-leak per-entry grep across 8 closed IDs in non-historical surface. §1.7's protected scope = rule-introduction/extension drift (#recommendation-skips-own-discipline); this PR is mechanical maintenance, not a recommendation introducing or extending a discipline.