@event4u/agent-config 6.0.0 → 7.0.0

package/dist/agent-src/templates/scripts/work_engine/state_io.py

@@ -1,202 +0,0 @@
-"""State-file I/O helpers for the CLI entry point.
-
-Extracted from ``cli.py`` in P2.3 of
-``road-to-post-pr29-optimize.md``. Holds the format-preserving
-load/save pair, the v0 legacy serialiser, the JSON reader, the
-``DeliveryState`` projection helpers, and the legacy-file migration
-hint. Behaviour is byte-identical to the pre-split version — Goldens
-stay green.
-"""
-from __future__ import annotations
-
-import json
-from pathlib import Path
-from typing import Any
-
-from . import state as _state_module
-from .cli_args import DEFAULT_STATE_FILE, LEGACY_STATE_FILE, _FMT_V0, _FMT_V1
-from .delivery_state import DeliveryState
-from .errors import _CLIError
-from .migration.v0_to_v1 import migrate_payload
-from .state import SchemaError, WorkState
-
-
-def _maybe_raise_legacy_hint(state_file: Path) -> None:
-    """Surface a migration hint when only the pre-1.15.0 file is present.
-
-    The dispatcher renamed the default state file from
-    ``.implement-ticket-state.json`` to ``.work-state.json`` in 1.15.0
-    (alongside the ``implement_ticket → work_engine`` package move).
-    Existing checkouts that still carry the legacy file would otherwise
-    fail with a generic "no state file" message. This helper detects
-    the legacy file in the same directory and points the user at the
-    one-shot migration command instead.
-
-    Only fires when ``state_file`` has the canonical default name and
-    sits next to a legacy file — explicit ``--state-file`` overrides
-    bypass the hint so power users can carry their own naming scheme.
-    """
-    if state_file.name != DEFAULT_STATE_FILE.name:
-        return
-    legacy_candidate = state_file.with_name(LEGACY_STATE_FILE.name)
-    if not legacy_candidate.is_file():
-        return
-    raise _CLIError(
-        f"Found legacy state file {legacy_candidate} but no "
-        f"{state_file}. The default state file was renamed in 1.15.0. "
-        f"Run `python3 -m work_engine.migration.v0_to_v1 "
-        f"{legacy_candidate}` to migrate, or pass `--state-file "
-        f"{legacy_candidate}` to keep using the old name. See "
-        "docs/MIGRATION.md.",
-    )
-
-
-def _load(state_file: Path) -> tuple[WorkState, str]:
-    """Load ``state_file`` and tag it with the wire format detected."""
-    data = _read_json(state_file)
-    if not isinstance(data, dict):
-        raise _CLIError(
-            f"State file {state_file} must carry a JSON object; "
-            f"got {type(data).__name__}.",
-        )
-
-    # v1 declares ``version``; v0 has none. Anything else is invalid.
-    if data.get("version") == _state_module.SCHEMA_VERSION:
-        try:
-            return _state_module.from_dict(data), _FMT_V1
-        except SchemaError as exc:
-            raise _CLIError(f"State file shape is invalid: {exc}") from exc
-    if "version" in data:
-        raise _CLIError(
-            f"State file shape is invalid: unsupported version "
-            f"{data.get('version')!r}; expected {_state_module.SCHEMA_VERSION}",
-        )
-    if "ticket" not in data:
-        raise _CLIError(
-            "State file shape is invalid: missing 'ticket' (v0) or "
-            "'version' (v1) — file is neither shape.",
-        )
-    try:
-        migrated = migrate_payload(data)
-        return _state_module.from_dict(migrated), _FMT_V0
-    except SchemaError as exc:
-        raise _CLIError(f"State file shape is invalid: {exc}") from exc
-
-
-def _to_delivery(work: WorkState) -> DeliveryState:
-    """Project ``work`` into a ``DeliveryState`` for handler dispatch.
-
-    R1 P4 S1 (Option A2): handlers continue to consume ``DeliveryState``
-    with ``state.ticket``; the ``WorkState`` wrapper exists at the CLI
-    boundary so the dispatcher's directive-set selection has a v1
-    state object to read ``directive_set`` from. Mutable containers
-    (``memory``, ``changes``, ``outcomes``, ``questions``) are passed
-    by reference — in-place mutations land on both objects without an
-    explicit sync. Reassignments (``state.plan = …``, ``state.report
-    = …``) are mirrored back by :func:`_sync_back`.
-    """
-    return DeliveryState(
-        ticket=work.input.data,
-        persona=work.persona,
-        memory=work.memory,
-        plan=work.plan,
-        changes=work.changes,
-        tests=work.tests,
-        verify=work.verify,
-        outcomes=work.outcomes,
-        questions=work.questions,
-        report=work.report,
-        ui_audit=work.ui_audit,
-        ui_design=work.ui_design,
-        ui_review=work.ui_review,
-        ui_polish=work.ui_polish,
-        contract=work.contract,
-        stitch=work.stitch,
-        stack=work.stack,
-    )
-
-
-def _sync_back(work: WorkState, delivery: DeliveryState) -> None:
-    """Mirror handler mutations from ``delivery`` back into ``work``.
-
-    Container fields are shared by reference (see :func:`_to_delivery`)
-    so the assignment is a no-op for those — we still mirror them
-    defensively to cover the case where a handler reassigned the
-    attribute (``state.memory = [new_list]``) instead of mutating in
-    place.
-    """
-    work.input.data = delivery.ticket
-    work.persona = delivery.persona
-    work.memory = delivery.memory
-    work.plan = delivery.plan
-    work.changes = delivery.changes
-    work.tests = delivery.tests
-    work.verify = delivery.verify
-    work.outcomes = delivery.outcomes
-    work.questions = delivery.questions
-    work.report = delivery.report
-    work.ui_audit = delivery.ui_audit
-    work.ui_design = delivery.ui_design
-    work.ui_review = delivery.ui_review
-    work.ui_polish = delivery.ui_polish
-    work.contract = delivery.contract
-    work.stitch = delivery.stitch
-    work.stack = delivery.stack
-
-
-def _save(state_file: Path, work: WorkState, fmt: str) -> None:
-    """Persist ``work`` in the wire format it was loaded with.
-
-    v1 emits the canonical envelope via :func:`work_engine.state.to_dict`;
-    v0 emits the legacy flat shape that ``DeliveryState.asdict`` used
-    to produce, byte-identical to the pre-Phase-4 output so the
-    Golden Transcript replay stays green.
-    """
-    state_file.parent.mkdir(parents=True, exist_ok=True)
-    payload = _state_module.to_dict(work) if fmt == _FMT_V1 else _to_v0_dict(work)
-    state_file.write_text(
-        json.dumps(payload, indent=2, ensure_ascii=False) + "\n",
-        encoding="utf-8",
-    )
-
-
-def _to_v0_dict(work: WorkState) -> dict[str, Any]:
-    """Serialise ``work`` in the legacy v0 wire format.
-
-    Field order matches ``DeliveryState`` declaration order so
-    pre-Phase-4 state files round-trip byte-equal.
-    """
-    return {
-        "ticket": work.input.data,
-        "persona": work.persona,
-        "memory": work.memory,
-        "plan": work.plan,
-        "changes": work.changes,
-        "tests": work.tests,
-        "verify": work.verify,
-        "outcomes": work.outcomes,
-        "questions": work.questions,
-        "report": work.report,
-    }
-
-
-def _read_json(path: Path):
-    try:
-        raw = path.read_text(encoding="utf-8")
-    except OSError as exc:
-        raise _CLIError(f"Cannot read {path}: {exc}") from exc
-    try:
-        return json.loads(raw)
-    except json.JSONDecodeError as exc:
-        raise _CLIError(f"Invalid JSON in {path}: {exc}") from exc
-
-
-__all__ = [
-    "_load",
-    "_maybe_raise_legacy_hint",
-    "_read_json",
-    "_save",
-    "_sync_back",
-    "_to_delivery",
-    "_to_v0_dict",
-]

package/dist/cli/python/resolvePython.js

@@ -1,38 +0,0 @@
-/**
- * Python interpreter resolution.
- *
- * The Bash dispatcher's `require_python3` only checks PATH for
- * `python3`. We keep the same contract here: the first executable on
- * PATH named `python3` (or `python` on Windows) wins. No version
- * coercion, no venv hijacking — the engine's own scripts handle that.
- *
- * Exposed as a function so tests can stub it via dependency injection.
- */
-import { execaSync } from 'execa';
-export class PythonNotFoundError extends Error {
-    constructor() {
-        super('agent-config: python3 not found on PATH. Install Python 3.11+ and retry.');
-        this.name = 'PythonNotFoundError';
-    }
-}
-export function resolvePython() {
-    const candidates = process.platform === 'win32'
-        ? ['python3', 'python']
-        : ['python3'];
-    for (const bin of candidates) {
-        try {
-            const { stdout } = execaSync(bin, ['--version'], {
-                reject: false,
-                timeout: 5000,
-            });
-            const match = /Python\s+(\d+\.\d+\.\d+)/.exec(stdout);
-            if (match?.[1])
-                return { bin, version: match[1] };
-        }
-        catch {
-            // try next candidate
-        }
-    }
-    throw new PythonNotFoundError();
-}
-//# sourceMappingURL=resolvePython.js.map

package/dist/cli/python/resolvePython.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"resolvePython.js","sourceRoot":"","sources":["../../../src/cli/python/resolvePython.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,OAAO,CAAC;AASlC,MAAM,OAAO,mBAAoB,SAAQ,KAAK;IAC1C;QACI,KAAK,CACD,0EAA0E,CAC7E,CAAC;QACF,IAAI,CAAC,IAAI,GAAG,qBAAqB,CAAC;IACtC,CAAC;CACJ;AAED,MAAM,UAAU,aAAa;IACzB,MAAM,UAAU,GAAG,OAAO,CAAC,QAAQ,KAAK,OAAO;QAC3C,CAAC,CAAC,CAAC,SAAS,EAAE,QAAQ,CAAC;QACvB,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;IAElB,KAAK,MAAM,GAAG,IAAI,UAAU,EAAE,CAAC;QAC3B,IAAI,CAAC;YACD,MAAM,EAAE,MAAM,EAAE,GAAG,SAAS,CAAC,GAAG,EAAE,CAAC,WAAW,CAAC,EAAE;gBAC7C,MAAM,EAAE,KAAK;gBACb,OAAO,EAAE,IAAI;aAChB,CAAC,CAAC;YACH,MAAM,KAAK,GAAG,0BAA0B,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;YACtD,IAAI,KAAK,EAAE,CAAC,CAAC,CAAC;gBAAE,OAAO,EAAE,GAAG,EAAE,OAAO,EAAE,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;QACtD,CAAC;QAAC,MAAM,CAAC;YACL,qBAAqB;QACzB,CAAC;IACL,CAAC;IACD,MAAM,IAAI,mBAAmB,EAAE,CAAC;AACpC,CAAC"}

package/docs/case-studies/frontend-design-vs-ui-ux-pro-max.md

@@ -1,86 +0,0 @@
-# Competitive positioning — `frontend-design` pack vs. `ui-ux-pro-max`
-
-> Ours-vs-theirs verdict per the `competitive-positioning` skill,
-> closing `road-to-frontend-design-intelligence` Phase 8. Evidence:
-> full-tree deep-dive of `nextlevelbuilder/ui-ux-pro-max-skill`
-> @ `b7e3af80f6e331f6fb456667b82b12cade7c9d35` (2026-06-07) vs. this
-> repo post-adoption (ADR-061).
-
-## 1. Frame
-
-- **Theirs:** "Make any AI agent produce professional UI" — a
-  searchable design-knowledge corpus + BM25 engine + generative asset
-  add-ons, installed per-tool via an npm CLI. Segment: any developer
-  using an AI coding tool.
-- **Ours:** a governed skill/rule/command suite where frontend design is
-  one orchestrated capability among many — audit → design → apply →
-  review → polish with hard gates, now **grounded in the same corpus**.
-  Segment: teams standardizing AI-agent behavior across tools.
-
-## 2. Axes
-
-- **Design-knowledge grounding** — the differentiated capability that
-  triggered this adoption.
-- **Orchestration & gates** — who controls when knowledge is applied.
-- **Accessibility depth** — audit method, not just data.
-- **Stack coverage** — per-framework Do/Don't knowledge.
-- **Token authoring** — DTCG system + generators.
-- **Generative assets** — logo/CIP/banner generation.
-- **Governance & provenance** — licensing, refresh, safety surfaces.
-
-## 3. Verdict table
-
-| Axis | Ours (post-adoption) | Theirs | Verdict | Adopt? | Rationale |
-|---|---|---|---|---|---|
-| Design-knowledge grounding | Same corpus (11 CSVs + 16 stack CSVs + reasoning map) behind a **generalized manifest engine** with confidence + evidence-gap on every output | Origin of the corpus; frontend-hardcoded scripts | **Parity-plus** | done | ADR-061 adoption; our engine adds structured filters, named retrievers, schema-agnostic manifests |
-| Orchestration & gates | Directive set with audit gate, microcopy placeholder lock, a11y severity gate, polish ceiling | Skill prose + conventions; no enforced gates | **Ours** | — | Their corpus now feeds our gates — the combination argument inverts |
-| Accessibility depth | `accessibility-auditor` (WCAG 2.2 AA method) + corpus a11y data (contrast-adjusted palettes, chart grades, 44pt rules) | Checklist rows + a11y-graded data, no audit method | **Ours** | done | Their data enriched our gate; method stays ours |
-| Stack coverage | 16 stack corpora via `--stack` (Vue gap closed) + stack-dispatched executor skills | Same 16 CSVs | **Parity** | done | Verbatim adoption, one search mechanism |
-| Token authoring | `design-tokens` skill — DTCG 3-layer + Python generate/validate/embed (no Node dep) | `.cjs` generators (Node required) | **Ours (slight)** | done | Port removes the Node runtime requirement; brand→token sync deferred (watch note) |
-| Generative assets | **Not shipped** — gated by `domain-adoption-policy` (watch note); would adapt into `pack-ai-video` | Gemini logo/CIP/icon/banner/social suite | **Theirs** | gated | Heavy deps (`google-genai`, Chrome, API key) + no demand signal; revisit on trigger |
-| Governance & provenance | ADR-061, ATTRIBUTION with SHA pins, owner + cadence per corpus, runtime-safety review, Apache §4b markings | MIT/Apache files present; no refresh discipline documented | **Ours** | — | The axis their 86k-star repo does not compete on |
-
-## 4. Invariants (moats)
-
-- **Orchestration & gates** — inversion: "would a consumer drop our suite
-  for theirs?" Only if they wanted raw knowledge without enforcement;
-  the placeholder lock, audit gate, and a11y floor do not exist upstream.
-- **Governance & provenance** — refresh cadence + SHA pins + safety
-  reviews are structural in this package; a knowledge dump cannot match
-  them without becoming a governed suite itself.
-
-## 5. Adoption queue
-
-Empty — every `adopt? = done` row landed in
-`road-to-frontend-design-intelligence` Phases 1–6. The single open
-upstream capability (generative suite) is gated, not queued
-(`agents/settings/contexts/domain-watch/generative-brand-assets.md`).
-
-## 6. Unknowns
-
-- Their npm CLI's 18-tool projection breadth vs. our generator's
-  supported set: we verified parity for **our** targets
-  (`.claude` / `.cursor` / `.clinerules` / `.windsurf` / `.augment` via
-  `task generate-tools`); no claim about the 13 other tools they list —
-  we do not target them.
-- Real-session quality delta of grounded vs. ungrounded briefs — the
-  council's change-my-mind anchor (≥10 real sessions) applies to our own
-  Phase 9 expansion, and equally to claiming superiority here.
-
-## Net
-
-A consumer installing **our package alone** now gets the
-`ui-ux-pro-max` design knowledge **plus** orchestration, hard gates,
-a11y method, token authoring without Node, and provenance discipline.
-The combination is unnecessary; the gated generative suite is the one
-deliberate exception.
-
-## Upstream-contribute consideration (Step 8.3)
-
-Improvements worth proposing back (MIT obligations honored either way):
-the BM25 dedupe (`core.py` / `slide_search_core.py` byte-identical),
-the Python token toolchain (drops their Node dependency), and the
-manifest/filters layer. **Decision: defer the upstream PR** until the
-engine has soaked through one internal release cycle — proposing an
-interface we might still move is noise for the maintainer. Revisit at
-the first quarterly corpus refresh.

package/docs/contracts/agent-memory-contract.md

@@ -1,159 +0,0 @@
----
-stability: beta
-keep-beta-until: 2026-08-12
----
-
-# Agent-Memory Contract (as expected by `agent-config`)
-
-**Purpose.** Freeze the interface `agent-config` currently expects from
-the sibling package `@event4u/agent-memory`, so when that package
-actually ships we can diff its real surface against this document in
-one place — instead of chasing drift across skills, commands, and
-helpers.
-
-**Ownership.** `agent-memory` is ours; we decide release timing. This
-doc is internal, not a spec handed to an external team. The
-authoritative spec-side documents live under
-[`agents/roadmaps/agent-memory/`](../../agents/roadmaps/archive/agent-memory/); this context
-is the **consumer-side snapshot** — what our wired code assumes today.
-
-Last refreshed: 2026-04-22.
-
-## What this doc is *not*
-
-- Not a replacement for the agent-memory retrieval-contract spec —
-  that lives in the agent-memory package and is the spec we hand to
-  the implementer.
-- Not a commitment that consumer code looks exactly like this forever
-  — it is a point-in-time pin.
-- Not an agent-facing skill. Humans read this when the package lands.
-
-## Expected backend states
-
-Defined in [`memory-access.md`](../../docs/guidelines/agent-infra/memory-access.md)
-and `scripts/memory_status.py`:
-
-| Status | Meaning | Agent-config behaviour |
-|---|---|---|
-| `absent` | Package not installed or CLI not on PATH | File fallback only |
-| `misconfigured` | Installed but `health()` fails within 2s | Warn once / session, fall back to file |
-| `present` | Installed and healthy within 2s | Route retrieval through package |
-
-Detection must be **bounded** (≤ 2s cold probe), **cached** per
-process, **non-raising** on probe failure.
-
-## Expected CLI surface
-
-Probed in `scripts/memory_status.py` via `_CLI_CANDIDATES`:
-
-- Executable on `PATH` as **`memory`** (canonical, ships in
-  `@event4u/agent-memory` v1.1+ as `package.json#bin.memory`),
-  **`agent-memory`** (planned alias), or **`agentmem`** (legacy).
-- Supports `health` subcommand emitting a v1 health envelope on stdout
-  (`{contract_version, status, backend_version, features, latency_ms}`)
-  and exiting non-zero on unhealthy.
-- Supports `retrieve <query> [--type T …] [--limit N] [--layer 1|2|3]
-  [--budget N] [--low-trust] [--repository ID]` emitting a v1
-  retrieval envelope on stdout (always JSON).
-
-The retrieval invocation is **semantic, not key-based** — see the
-"⚠️ Known contract drift" section below for the consumer-side
-implication.
-
-If the released package diverges from these names, we update
-`_CLI_CANDIDATES` in `memory_status.py` — not the other way round.
-
-## Expected retrieval shape (present path)
-
-Source of truth: the retrieval-contract spec in the agent-memory
-package. Consumer skills call the shared abstraction, not the package
-directly.
-
-**Request** (Python):
-
-```python
-retrieve(types=[…], keys=[…] or {…}, limit: int = 20, timeout_ms: int = 2000)
-```
-
-**Response** (v1 envelope) — mandatory fields per entry: `id`, `type`,
-`source ∈ {repo, operational}`, `confidence`, `body`. Optional:
-`trust`, `last_validated`, `shadowed_by`.
-
-Envelope: `contract_version`, `status ∈ {ok, partial, error}`,
-`entries`, `slices`, `errors`.
-
-## ⚠️ Known contract drift (consumer vs. spec)
-
-**Status: resolved at the consumer boundary.** The CLI / JSON output of
-`scripts/memory_lookup.py` already emits the v1 envelope with
-`source ∈ {repo, operational}`, `confidence`, `slices`, `status`, and
-`contract_version` — see `memory_lookup.py:320-345` (envelope
-assembly).
-
-What remains is **internal-only**: the private `Hit` dataclass inside
-`memory_lookup.py` still uses `source ∈ {curated, intake}` and `score`.
-No skill, command, or external consumer imports `Hit` directly — they
-all go through the public JSON surface, which is already spec-aligned.
-
-| Internal `Hit` field | Public envelope field | Visible to consumers? |
-|---|---|---|
-| `id`, `type` | `id`, `type` | yes — match |
-| `source ∈ {curated, intake}` | `source ∈ {repo, operational}` | no — translated at boundary |
-| `score ∈ [0,1]` | `confidence` | no — translated at boundary |
-| `path` | — | no — internal scoring signal |
-
-**Trigger to revisit:** if a second module starts importing the `Hit`
-dataclass directly (e.g. `memory_lookup.py` is split into multiple
-files and `Hit` becomes a public type), rename `Hit.source`/`Hit.score`
-to match the envelope so the boundary translation can be deleted.
-Until then, the internal naming is an implementation detail.
-
-There is also a **calling-convention drift** between the contract's
-key-based `retrieve(types, keys, limit)` and the package's
-semantic-only `retrieve(query, …)`. This is tracked separately and
-is the subject of an ongoing design decision (hybrid contract — keys
-synthesise into a query for the package path; file-fallback stays
-key-match).
-
-## Expected `propose()` / signal emission
-
-Shape used by `scripts/memory_signal.py` and the `/propose-memory`
-command: JSONL append-only drop-ins under
-`agents/memory/intake/*.jsonl`, one signal per line. When the package
-is present, the same payload is accepted by a `propose()` CLI or MCP
-call. File-drop is the always-works path.
-
-**Required fields** (keep in sync with `/propose-memory` command):
-`ts`, `type`, `key` (path or logical id), `observation`, `source`
-(`agent` or `human`), `session_id`.
-
-**Optional fields:**
-
-- `tags: string[]` — zero or more schema-routing labels from the
-  controlled vocabulary `{convention, invariant, gotcha, pattern}`.
-  Default `[]`. Producers (`/memory propose`, `/memory mine-session`)
-  emit tags; consumers (`/memory promote`) read **tag intersection**
-  to pick the curated YAML target when a signal carries two tags
-  (e.g. `[gotcha, invariant]` → primary `gotcha` JSONL, promote target
-  resolved by the reviewer at promotion time). See
-  [`memory-consolidation`](../../.agent-src.uncondensed/skills/memory-consolidation/SKILL.md)
-  § Phase 3 for the schema-routing table.
-- `confidence: low | medium | high` — producer-supplied estimate; the
-  inline-review hook in `/memory load` ranks the top-3 by this field.
-
-## Revisit triggers
-
-Q29 is **parked open**, not a blocker. Revisit when **one** of these
-holds:
-
-- `@event4u/agent-memory` ships a tagged release (any v0.x)
-- A consumer project explicitly asks for the `present` path
-- The agent-memory repo opens an integration PR against `agent-config`
-- We change the file fallback's public shape (then rewrite this doc
-  *before* the change lands)
-
-## See also
-
-- [`memory-access guideline`](../../docs/guidelines/agent-infra/memory-access.md)
-- [`scripts/memory_status.py`](../../.agent-src.uncondensed/templates/scripts/memory_status.py)
-- [`scripts/memory_lookup.py`](../../.agent-src.uncondensed/templates/scripts/memory_lookup.py)

package/docs/parity/bench-ruflo.json

@@ -1,58 +0,0 @@
-{
-  "schema": "parity-bench-ruflo-v1",
-  "status": "infrastructure_ready_awaiting_corpus_run",
-  "owner_roadmap": "agents/roadmaps/step-11-ruflo-parity.md",
-  "parity_doc": "docs/parity/ruflo.md",
-  "parent_bench": "docs/parity/bench.json",
-  "claim_under_test": {
-    "source": "agents/evidence/audits/2026-05-14-north-star/external-findings.md § 2",
-    "headline": "Average dollar cost per 25-prompt corpus run, separated by model tier (Haiku / Sonnet / Opus) and by token class (input / output / cache-read / cache-write).",
-    "comparison_target": "ruflo cost-tracker README (claimed upstream, not yet pulled into this repo)",
-    "type": "claimed_upstream_not_verified_in_repo"
-  },
-  "measurement_protocol": {
-    "corpus": "internal/bench/corpus/* (25-prompt corpus owned by step-4-measurement-and-benchmark.md)",
-    "tracker": "scripts/cost/track.mjs",
-    "pricing": "internal/bench/pricing.yaml",
-    "session_source": "~/.claude/projects/*/sessions/*.jsonl (Claude Code-native, no manual tracking)",
-    "tokens_to_dollars": "track.mjs multiplies input/output/cache-read/cache-write tokens by per-1M pricing from internal/bench/pricing.yaml, separated by model id",
-    "headline_output": "average dollar cost per 25-prompt run, with min / max / p50 / p90 across N reports"
-  },
-  "current_window": {
-    "report_count": 0,
-    "verdict": "awaiting_first_corpus_run",
-    "notes": "Phase 1-5 of step-11 delivered the cost-tracking and bench infrastructure. Phase 6 Step 2 awaits the first end-to-end 25-prompt corpus run against the live tracker. Until then this file exists as a methodology contract, not a verdict surface."
-  },
-  "soak_inheritance": {
-    "follows": "docs/parity/bench.json",
-    "min_days": 60,
-    "min_reports": 30,
-    "earliest_flip": "2026-07-15",
-    "arbiter_command": "task bench:baseline-ready",
-    "notes": "bench-ruflo.json flips status to 'baseline_ready' only after the parent bench.json flips. No independent soak window — same corpus, same arbiter."
-  },
-  "redundancy_verdict": {
-    "status": "pending",
-    "criterion": "Once bench.json soak completes, this verdict is set by comparing the dollar cost in current_window vs ruflo's published table.",
-    "outcome_branches": {
-      "redundant": "Our cost-per-25-prompt-run sits within Ruflo's published range (or beats it). G5 redundancy gate row for cost surface flips green.",
-      "behind": "Our cost-per-run > Ruflo's. Follow-up issue filed; G5 stays open."
-    }
-  },
-  "fields_pending_first_run": [
-    "current_window.avg_cost_per_run_usd",
-    "current_window.cost_by_model.haiku_usd",
-    "current_window.cost_by_model.sonnet_usd",
-    "current_window.cost_by_model.opus_usd",
-    "current_window.cost_by_class.input_usd",
-    "current_window.cost_by_class.output_usd",
-    "current_window.cost_by_class.cache_read_usd",
-    "current_window.cost_by_class.cache_write_usd"
-  ],
-  "decisions_pending": {},
-  "_meta": {
-    "created": "2026-05-16",
-    "created_by": "step-11-ruflo-parity.md Phase 6 Step 2",
-    "spec": "scripts/cost/track.mjs --bench-ruflo (planned wiring); for now the file is a methodology contract"
-  }
-}

package/docs/parity/ruflo.md

@@ -1,46 +0,0 @@
-# Parity verdict — Ruflo
-
-> Per-row verdict against the eight Ruflo measurement-governance patterns
-> catalogued in
-> [`external-findings.md § 2`](../../agents/evidence/audits/2026-05-14-north-star/external-findings.md).
-> Owner roadmap: [`step-11-ruflo-parity.md`](../../agents/roadmaps/step-11-ruflo-parity.md)
-> (Phase 6 Step 1). Cross-index lives at
-> [`step-99-north-star-restructure.md`](../../agents/roadmaps/step-99-north-star-restructure.md)
-> Phase 5 Step 2.
->
-> **Verdict legend:** `[x] covered by <file:line>` · `[~] superseded by <approach>` · `[!] gap`.
-> **Acceptance:** zero `[!]` rows. Closure flips the corresponding cell in the
-> [composite scorecard](../../agents/evidence/audits/2026-05-14-north-star/external-findings.md#5-composite-scorecard--agent-config-vs-the-field)
-> `vs Ruflo` column from `–` to `=` or `+`.
-
-**Measured-vs-claimed disclaimer:** Each row cites the **mechanism** that
-covers Ruflo's pattern. Numbers attached to those mechanisms (cost figures,
-smoke baselines, ADR count) are claimed until the 25-prompt bench corpus
-soak in [`bench.json`](bench.json) flips from `warmup` to `baseline_ready`
-(min 60 days, ≥ 30 reports — earliest 2026-07-15).
-
-## Verdict table
-
-| # | Ruflo pattern | Verdict | Evidence |
-|---|---|---|---|
-| 1 | **Cost-tracker plugin** — real model pricing, per-1M, separated input/output/cache | `[x] covered by` | [`scripts/cost/track.mjs`](../../src/scripts/cost/track.mjs) + [`internal/bench/pricing.yaml`](../../bench/pricing.yaml) (Haiku/Sonnet/Opus per-1M, input/output/cache-read/cache-write split). Step-11 Phase 1. |
-| 2 | **Auto-capture from session jsonl** — reads Claude Code log, no manual tracking | `[x] covered by` | [`scripts/cost/track.mjs`](../../src/scripts/cost/track.mjs) reads `~/.claude/projects/*/sessions/*.jsonl` automatically. Step-11 Phase 1 Step 1. |
-| 3 | **50/75/90/100 % budget ladder with hard stop** | `[x] covered by` | [`scripts/cost/budget.mjs`](../../src/scripts/cost/budget.mjs) — exit codes 0/1/2/3 per tier; opt-in fail-closed via `cost.enforcement` setting. Fixtures: `tests/fixtures/cost/budget/{under-50,at-100,over-100}/`. Step-11 Phase 2. |
-| 4 | **Measured-vs-claimed disclaimer** — every percentage tagged "claimed upstream" | `[x] covered by` | One-line `**Measured-vs-claimed disclaimer:**` header block on all 9 active roadmaps in `agents/roadmaps/`. Verified 2026-05-16. Step-11 Phase 5 Step 4. |
-| 5 | **Smoke test as contract** — `bash scripts/smoke.sh` with declared baseline | `[x] covered by` | Four per-tier smoke scripts: [`scripts/smoke/kernel.sh`](../../src/scripts/smoke/kernel.sh), [`router.sh`](../../src/scripts/smoke/router.sh), [`schema.sh`](../../src/scripts/smoke/schema.sh), [`skills.sh`](../../src/scripts/smoke/skills.sh). Declared baselines in [`docs/contracts/smoke-contracts.md`](../contracts/smoke-contracts.md). CI gate: [`.github/workflows/smoke.yml`](../../.github/workflows/smoke.yml). Step-11 Phase 3. |
-| 6 | **Per-plugin ADR directory** — `docs/adrs/0001-*.md` co-located with subsystem | `[x] covered by` | Six bootstrap ADRs under [`docs/adrs/{cost,memory,router,schema,smoke,telegraph}/`](../adrs/). Coverage gate: [`scripts/audit_adr_coverage.py`](../../src/scripts/audit_adr_coverage.py) (`task lint-adr-coverage`). Contract: [`docs/contracts/adr-layout.md`](../contracts/adr-layout.md). Step-11 Phase 4. |
-| 7 | **Namespace contract** — `<stem>-<intent>` kebab-case, reserved-names list | `[x] covered by` | [`scripts/lint_namespace.py`](../../src/scripts/lint_namespace.py) enforces shape + length floors + reserved-names + skill-dir-matches-name across 430 names · 0 issues. Contract: [`docs/contracts/namespace.md`](../contracts/namespace.md). CI gate: `task lint-namespace`. Step-11 Phase 5 Step 1. |
-| 8 | **Topology choices in swarm** — `hierarchical / mesh / star / adaptive` with anti-drift defaults | `[x] covered by` | [`.agent-src.uncondensed/skills/subagent-orchestration/SKILL.md`](../../.agent-src.uncondensed/skills/subagent-orchestration/SKILL.md) `Topology hints` subsection — 7-row table mapping each mode to topology + Ruflo anti-drift default (`hierarchical, 6–8 agents, raft consensus`). Step-11 Phase 5 Step 2. |
-| 9 | **MCP-tool count + source-line refs** — every tool with `<file>:<line>` citation | `[x] covered by` | [`docs/contracts/mcp-tool-inventory.md`](../contracts/mcp-tool-inventory.md) — 20 tools (9 stdio-implemented · 11 discovery stubs) each with catalog `<file>:<line>` + handler `<file>:<line>`. Generator: [`scripts/audit_mcp_tools.py`](../../src/scripts/audit_mcp_tools.py). CI drift gate: `task lint-mcp-inventory`. Step-11 Phase 5 Step 3. |
-
-## Open `[!]` rows
-
-**Zero.** Every Ruflo pattern is mechanism-covered. Numbers behind those
-mechanisms remain claimed until [`bench.json`](bench.json) soak completes
-(see disclaimer above).
-
-## Cross-references
-
-- Composite scorecard refresh: owned by [`step-99-north-star-restructure.md`](../../agents/roadmaps/step-99-north-star-restructure.md) Phase 5 Step 4 (replaces [`external-findings.md § 5`](../../agents/evidence/audits/2026-05-14-north-star/external-findings.md)).
-- Bench-ruflo redundancy verdict: [`bench-ruflo.json`](bench-ruflo.json) (step-11 Phase 6 Step 2).
-- G5 redundancy gate cite: step-99 Acceptance Criteria row "G5 — external redundancy (Domination Mandate)".