@sabaiway/agent-workflow-memory 8.0.0 → 8.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,23 @@ All notable changes to the memory substrate. Versions are this **package's** npm
|
|
|
4
4
|
they are distinct from the **deployment-lineage** stamp written into a project's
|
|
5
5
|
`docs/ai/.memory-version` (which tracks the shared `agent-workflow` lineage, head `3.0.0`).
|
|
6
6
|
|
|
7
|
+
## 8.0.2 — the rules template gains the Story sessions section (AD-152)
|
|
8
|
+
|
|
9
|
+
`references/templates/agent_rules.md`: the new section `### 2.7. Story sessions` is added after §2.6 and before the
|
|
10
|
+
`---` that closes §2, byte-identical to the kit's copy, which is the section's one source. It says a story runs as
|
|
11
|
+
five sessions — spec, plan, tests, code, and diff review + release + record — each ending at its own review
|
|
12
|
+
checkpoint, and that a split is one session. A deployment whose rules file lacks the section is offered the insert
|
|
13
|
+
by the kit's upgrade (`tools/rules-insert.mjs`); a file that already carries a Story sessions heading keeps its own
|
|
14
|
+
wording. No script changed.
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
## 8.0.1 — the orchestration seed's note names six activities (AD-147)
|
|
18
|
+
|
|
19
|
+
`references/templates/orchestration.json`: the `_README` is the kit's new canonical byte for byte. It names six
|
|
20
|
+
activities (`epic` with slots `author` and `review`, `task` with slots `author` and `execute`), the task slots'
|
|
21
|
+
values and the silent slots' defaults. The seed's slot shape is unchanged, so an older kit still accepts it. A
|
|
22
|
+
deployed file carrying the outgoing note refreshes on the next write. No script changed.
|
|
23
|
+
|
|
7
24
|
## 8.0.0 — the reader refuses an open-list clause: a guarantee is an invariant, never a list of cases (AD-133)
|
|
8
25
|
|
|
9
26
|
**BREAKING — the 35th rule id, `open-list`.** `references/scripts/spec-schema.mjs` refuses a Contract clause that
|
package/SKILL.md
CHANGED
|
@@ -3,7 +3,7 @@ name: agent-workflow-memory
|
|
|
3
3
|
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.
|
|
4
4
|
disable-model-invocation: true
|
|
5
5
|
metadata:
|
|
6
|
-
version: '8.0.
|
|
6
|
+
version: '8.0.2'
|
|
7
7
|
---
|
|
8
8
|
|
|
9
9
|
# agent-workflow-memory
|
package/capability.json
CHANGED
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@sabaiway/agent-workflow-memory",
|
|
3
|
-
"version": "8.0.
|
|
3
|
+
"version": "8.0.2",
|
|
4
4
|
"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.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"ai-agents",
|
|
@@ -94,6 +94,9 @@ Apply these when authoring a plan, reviewing, folding a finding, or editing code
|
|
|
94
94
|
- **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.
|
|
95
95
|
- **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 — evidence declarations ride consecutive plain invocations of ONE allow-listed tool, other stage writers combine via one launcher per stage; never an unbatched writer scatter (each gated write is its own prompt).
|
|
96
96
|
|
|
97
|
+
### 2.7. Story sessions
|
|
98
|
+
A story — one row of an epic's ledger, carried by one plan — runs as five sessions, each ending at its own review checkpoint: **spec** (the contract under `docs/ai/specs/`, drafted and reviewed on the `plan-authoring` recipe), **plan** (the ledger, same recipe), **tests** (one task per ledger row, red first), **code** (one task per row, to green), and **diff review, release and record** (the review of the staged tree on the `plan-execution` recipe, the release where the story ships one, then the changelog and handover entries and the plan's Phase: Cleanup). Tests and code never share a session, and a spec and its plan never share one either. A storyless plan runs the same five. **Exception — a split:** moving code and its existing cases into modules, with no new logic and no new case, is one session: a short spec (the Module list), the split, the diff review, the release, Cleanup.
|
|
99
|
+
|
|
97
100
|
---
|
|
98
101
|
|
|
99
102
|
## 3. Token & Session Optimization
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"_README": "Per-project orchestration config: the recipe used at each step (slot) of each named activity. Easiest: tell the agent in plain language and run the `set-recipe` writer — it interprets your intent, previews the change, and writes valid JSON for you. You can still hand-edit this file directly whenever you prefer; that option never goes away.
|
|
2
|
+
"_README": "Per-project orchestration config: the recipe used at each step (slot) of each named activity. Easiest: tell the agent in plain language and run the `set-recipe` writer — it interprets your intent, previews the change, and writes valid JSON for you. You can still hand-edit this file directly whenever you prefer; that option never goes away. Six activities are configured independently, and so is each slot within them: 'plan-authoring' (slots author, fold, review), 'plan-execution' (slots execute, review), 'routine' (slots carrier, parallel), 'feedback-triage' (slot review), 'epic' (slots author, review) and 'task' (slots author, execute). A slot's value is a recipe: a 'review' slot accepts solo | reviewed | council (you self-review / one backend reviews / both review and you synthesize), or an explicit roster array such as [\"codex-review\", \"agy-review\", \"review-lens\"] in hand-edit form; an 'execute' slot accepts solo | delegated | subagent (you implement / a backend runs a bounded sub-task / a full-tool frontier subagent carries a bounded slice you verify); the carrier slots 'plan-authoring.author', 'plan-authoring.fold', 'routine.carrier' and 'epic.author' accept solo | subagent, and the task slots 'task.author' and 'task.execute' take the execute values. 'routine.parallel' is a flag rather than a recipe: it accepts on | off and decides whether file-disjoint subagent slices dispatch concurrently. Every slot seeded below is 'solo' — no execution backend required. A slot the seed leaves silent takes the computed default stated further down: 'feedback-triage.review' is reviewed as soon as a review backend is ready (solo until then), and so is 'epic.review'; 'plan-authoring.author', 'plan-authoring.fold', 'routine.carrier', 'epic.author', 'task.author' and 'task.execute' stay 'solo', and 'routine.parallel' stays 'on'. Raise a slot to reviewed or council for a second opinion, or to delegated to hand off execution; those need an execution backend set up first. 'subagent' needs the executor vehicle placed in this project — the composition root's `agents` writer places it; without it the slot resolves to solo with the reason stated. Remove a slot's line, or a whole activity block (or run `set-recipe --unset <activity>.<slot>`), to fall back to the computed default: reviewed when a review backend is ready and otherwise solo for a review slot, solo for author, fold, execute and carrier, on for parallel. Run the read-only procedures advisor to see an activity's steps plus the recipe resolved for your environment. Strict JSON — no comments.",
|
|
3
3
|
"plan-authoring": {
|
|
4
4
|
"review": "solo"
|
|
5
5
|
},
|