@sabaiway/agent-workflow-memory 2.2.0 → 2.3.0

package/CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to the memory substrate. Versions are this **package's** npm
 they are distinct from the **deployment-lineage** stamp written into a project's
 `docs/ai/.memory-version` (which tracks the shared `agent-workflow` lineage, head `2.0.0`).
 
+## 2.3.0 — agent_rules template: a report-facts Communication bullet + the writer-batch lens re-render (REPORT-FACTS train, AD-054)
+
+A **feature** release (ships with kit 1.47.0 / engine 1.17.0 / bridges 2.7.0+2.6.0; the deployment
+lineage head stays `2.0.0` — no deployed-`docs/ai` structure change). The bundled `agent_rules.md`
+template gains:
+- **§2.5 Communication — a report-facts bullet.** Any claim about the current host or session state
+  (prompts fired, sandbox scope, whether a bypass was needed, network reachability, approval counts)
+  must trace to **live tool output** from **this session**; a memory/handover snapshot is **context,
+  never report facts**, and an unbacked claim is **omitted or explicitly marked unverified**. The
+  report-facts twin lands in the memory template only (the kit template carries no §2.5 Communication).
+- **§2.6 lens re-render.** The planning/review lens gains the writer-economy clause, kept in parity
+  with the engine lens fragment by the lens-mirror guard.
+
 ## 2.2.0 — agent_rules template re-render: the lens gains the prompt-economy clause (REC-UX-REWORK D7, AD-053)
 
 A **feature** release (ships with kit 1.46.0 / engine 1.16.0; the deployment lineage head stays

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-memory
 description: Deploy or upgrade a portable AI-agent memory substrate in any project — an entry-point `AGENTS.md` (+ `CLAUDE.md` alias) and a structured `docs/ai/` context store with cap/archive/index enforcement. Use when the user wants to bootstrap `docs/ai/`, set up the Memory Map and session protocols, install the docs-rotation pre-commit hook, or run `/agent-workflow-memory` / `/agent-workflow-memory upgrade`. Triggers on "set up the memory system", "deploy the AI memory here", "bootstrap docs/ai", "upgrade the memory substrate". This is the substrate only — the workflow methodology (plan→execute→review, queue, Cleanup) is owned elsewhere and injected into AGENTS.md by the family composition root.
 disable-model-invocation: true
 metadata:
-  version: '2.2.0'
+  version: '2.3.0'
 ---
 
 # agent-workflow-memory

package/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "agent-workflow-memory",
   "kind": "memory-substrate",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "provides": ["context"],
   "roles": {},
   "detect": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sabaiway/agent-workflow-memory",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "description": "Portable, cross-agent memory substrate for AI coding agents — an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement, deployable standalone or as part of the agent-workflow family. The memory layer of the agent-workflow family.",
   "keywords": [
     "ai-agents",

package/references/templates/agent_rules.md

@@ -71,6 +71,7 @@ Apply this as part of §2 before any user-facing summary:
 - **Lead with the result**, then the details; show exactly what was asked — no deflection, no "almost done" when the ask was the finished thing.
 - **No condescension, no filler.** Own a miss plainly and fix it in the same message.
 - **Large artifact (≈>100 lines):** deliver a real summary or the key excerpt inline **and** link the file — never flood the reader with a 2000-line paste, never hide the answer behind a bare pointer.
+- **Live host/session facts are tool-composed only.** Any claim about the current host or session state (prompts fired, sandbox scope, whether a bypass was needed, network reachability, approval counts) must trace to **live tool output** from **this session**; a memory/handover snapshot is **context, never report facts**, and a claim with no live signal is **omitted or explicitly marked unverified** — never asserted from recollection.
 
 ### 2.6. Planning, review & process-fidelity invariants
 Apply these when authoring a plan, reviewing, folding a finding, or editing code — the layer read **before any code change**. (Full canon: the project's planning / workflow-methodology + orchestration canon. This section is rendered from that canon and refreshed on upgrade; a custom edit is preserved verbatim, but flagged.)
@@ -85,7 +86,7 @@ Apply these when authoring a plan, reviewing, folding a finding, or editing code
 - **Per-round emission.** Every review round emits **{round N · finding-origin tally · per-backend verdict}** so the crossover is a computed, visible signal, not a remembered rule.
 - **Recipe fidelity.** Council runs every backend the recipe names, **every round**; silently dropping a ready backend for quota/convenience is a forbidden downgrade — an unavailable backend is a LOUD, stated degrade, never a quiet drop.
 - **ExitPlanMode ≠ execute.** A harness "approved — start coding" prompt authorizes the PLAN only; this methodology overrides it. Continue into execution only as a DELIBERATE transition after the plan + cold-start prompt exist, never an implicit slide.
-- **Cost lanes.** Route every step to the **cheapest adequate executor** — L0 deterministic script (the batched gate matrix over `gates.json`, the rotation `--check`s) · L1 cheap subagent (extraction/drafting only; the orchestrator verifies) · L2 subscription bridge · L3 frontier judgment. A step with **no named guardrail does not move down** a lane, and the **red lines never move down** (council review models · real code · ADR/handover/changelog-entry wording · persuasive copy · go/no-go · the approval asks). Own-error repair: salvage recorded state first (L0/L1, batched), never frontier re-derivation. **Prompt economy:** read-only fan-out (research/sweeps/extraction) runs ONLY on restricted-tool vehicles — a full-tool subagent for read-only work is a forbidden lane downgrade (invisible prompt-flood + blast radius), and a subagent is never told to shell out for facts obtainable read-only; the orchestrator's own shell form is ONE plain pipeline per call (a `;`/`&&` chain or env-prefixed invocation never matches a prefix allow rule); a fan-out launcher that gates per call yields to the agent-spawn lane — capability-gated: without restricted-tool vehicles (generic full-tool spawning does not count), read-only research stays in the orchestrator's own context, never a vehicle mandate a host cannot satisfy. Judgment, code, synthesis stay at the frontier lane (a task that genuinely runs/writes keeps a full-tool subagent); honest limit: no deterministic gate classifies a dispatch — canon at the point of use + placed vehicles + the retro loop.
+- **Cost lanes.** Route every step to the **cheapest adequate executor** — L0 deterministic script (the batched gate matrix over `gates.json`, the rotation `--check`s) · L1 cheap subagent (extraction/drafting only; the orchestrator verifies) · L2 subscription bridge · L3 frontier judgment. A step with **no named guardrail does not move down** a lane, and the **red lines never move down** (council review models · real code · ADR/handover/changelog-entry wording · persuasive copy · go/no-go · the approval asks). Own-error repair: salvage recorded state first (L0/L1, batched), never frontier re-derivation. **Prompt economy:** read-only fan-out (research/sweeps/extraction) runs ONLY on restricted-tool vehicles — a full-tool subagent for read-only work is a forbidden lane downgrade (invisible prompt-flood + blast radius), and a subagent is never told to shell out for facts obtainable read-only; the orchestrator's own shell form is ONE plain pipeline per call (a `;`/`&&` chain or env-prefixed invocation never matches a prefix allow rule); a fan-out launcher that gates per call yields to the agent-spawn lane — capability-gated: without restricted-tool vehicles (generic full-tool spawning does not count), read-only research stays in the orchestrator's own context, never a vehicle mandate a host cannot satisfy. Judgment, code, synthesis stay at the frontier lane (a task that genuinely runs/writes keeps a full-tool subagent); honest limit: no deterministic gate classifies a dispatch — canon at the point of use + placed vehicles + the retro loop. **Writer economy:** a stage's repeated WRITER commands batch into ONE invocation — the review-ledger triad rides one batched write, other stage writers combine via one launcher per stage; never one writer call at a time (each write is its own prompt).
 
 ---