v0.1.5: standalone-readability pass — delink --strip provenance mode ([TT-NNNN]), Tier-2 dangling refs neutralized, verify/review-code giant skills split into reference/ on-demand files; guards now runtime-neutral (bun|node)

2026-09-25 00:09:37 +08:00
parent d6567b1842
commit 88204a90c8
74 changed files with 1417 additions and 1358 deletions
@@ -2,7 +2,7 @@
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://eightarms.net/octopus-workflow/schemas/review-status.schema.json",
  "title": "Review Status",
-  "description": "Schema for tracking the lifecycle state of a review session. This file lives at runs/{slug}/reviews/{stage}/status.json: initialized by the Orchestrator at Phase A (step 0.5) with the full required set, appended by the Synthesizer at Phase B (history[] + current_round), and finalized with `converged` by the Orchestrator at Phase E (see skills/_shared/review-pipeline-phases.md). Reader: the retrospective token-telemetry probe (retrospective/scripts/token-telemetry.ts) walks runs/**/reviews/*/status.json (canonical) and the legacy .artifacts/**/reviews/*/status.json, reading `history[]` (code-level legacy alias `rounds[]`, both handled) and `current_round`. For CLOSED runs (active workspace removed at archive-at-close), the probe reconstructs per-stage round counts from reviews/{stage}/round{N}/ artifact paths in the committed archive bundle runs/archive/{slug}.json ([org-internal #2591]). Since TD/TRC-F006 ([org-internal #2688]) the archive bundle can also embed an explicit digest of this history[] (top-level review_history: {stage, rounds, final_verdict, per_round[]}) so round counts and verdicts stay verifiable offline, without path reconstruction.",
+  "description": "Schema for tracking the lifecycle state of a review session. This file lives at runs/{slug}/reviews/{stage}/status.json: initialized by the Orchestrator at Phase A (step 0.5) with the full required set, appended by the Synthesizer at Phase B (history[] + current_round), and finalized with `converged` by the Orchestrator at Phase E (see skills/_shared/review-pipeline-phases.md). Reader: the retrospective token-telemetry probe (retrospective/scripts/token-telemetry.ts) walks runs/**/reviews/*/status.json (canonical) and the legacy .artifacts/**/reviews/*/status.json, reading `history[]` (code-level legacy alias `rounds[]`, both handled) and `current_round`. For CLOSED runs (active workspace removed at archive-at-close), the probe reconstructs per-stage round counts from reviews/{stage}/round{N}/ artifact paths in the committed archive bundle runs/archive/{slug}.json ([TT-2591]). Since TD/TRC-F006 ([TT-2688]) the archive bundle can also embed an explicit digest of this history[] (top-level review_history: {stage, rounds, final_verdict, per_round[]}) so round counts and verdicts stay verifiable offline, without path reconstruction.",
  "type": "object",
  "required": ["slug", "started_at", "current_round", "max_rounds", "converged", "history"],
  "properties": {
@@ -19,7 +19,7 @@
    "max_rounds": {
      "type": "integer",
      "default": 3,
-      "description": "Per-skill bound: `review-artifact` skill (process target) = 3 (the roadmap/design/plan targets were archived 2026-08-21, [org-internal #3072] phase 3); `review-code` = 2 default / 3 high-risk (`workflow-routing.yaml` `review.max_rounds`, [org-internal #3567]). `review-dag` (the review-artifact skill's DAG single-gate target) binds per depth from `dag_metrics.review_depth`: D1 ≤2, D2 ≤3, D3 ≤3, D4 ≤4 — D4 reaches round 4, exceeding the shared `review-artifact` default, so the DAG per-depth cap takes precedence (see review-artifact/SKILL.md review-dag Phase D MAX_ROUNDS). Set explicitly by the skill; default 3 is a fallback only."
+      "description": "Per-skill bound: `review-artifact` skill (process target) = 3 (the roadmap/design/plan targets were archived 2026-08-21, [TT-3072] phase 3); `review-code` = 2 default / 3 high-risk (`workflow-routing.yaml` `review.max_rounds`, [TT-3567]). `review-dag` (the review-artifact skill's DAG single-gate target) binds per depth from `dag_metrics.review_depth`: D1 ≤2, D2 ≤3, D3 ≤3, D4 ≤4 — D4 reaches round 4, exceeding the shared `review-artifact` default, so the DAG per-depth cap takes precedence (see review-artifact/SKILL.md review-dag Phase D MAX_ROUNDS). Set explicitly by the skill; default 3 is a fallback only."
    },
    "converged": {
      "type": "boolean"