@event4u/agent-config 9.8.0 → 9.9.0

package/docs/decisions/ADR-102-ticket-handoff-paste-and-mcp.md

@@ -1,72 +0,0 @@
----
-adr: 102
-status: accepted
-date: 2026-06-16
-decision: ticket-handoff-paste-and-mcp
-supersedes: —
-superseded_by: —
-phase: ticket-bundles (rework)
-type: structural
----
-
-# ADR-102 — Ticket handoff is paste/MCP, not an API export
-
-## Status
-
-**Accepted** · 2026-06-16. Supersedes the **transport decision** of
-[ADR-101](ADR-101-ticket-bundle-emission.md) (its R2/R4 GraphQL-export +
-idempotency, and the `linear_state` part of R3). The rest of ADR-101 — the
-bundle format, the buildability gate, `model_tier` per ticket, the traceability
-spine, v1-immutable — stands unchanged.
-
-## Context
-
-ADR-101 specified that a roadmap-materialised ticket bundle projects into Linear
-via a GraphQL exporter (`build_ticket_export.py`) with query/map-first
-idempotency tracked in a manifest `linear_state` map (CSV as a bootstrap).
-
-The maintainer's actual requirement is simpler: **be able to copy/paste an MD
-ticket into a Linear (or Jira) issue.** An automatic API export is unwanted —
-"the agent can do that via MCP anyway; we don't need to wire it through an API."
-The GraphQL client, the idempotency map, the transport spike, and the drift
-check were solving a problem that does not exist.
-
-## Decision
-
-1. **No bundled API client, no automatic export.** Remove
-   `build_ticket_export.py` and the planned `tickets:export` CLI.
-   The package ships zero Linear/Jira API wiring.
-2. **The MD ticket is the handoff artifact.** Its frontmatter `title` is the
-   issue title; its Markdown body is the issue description (renders in
-   Linear/Jira). A human pastes it; the body is authored render-ready.
-3. **MCP is the programmatic surface.** To create issues without pasting, the
-   agent uses a tracker **MCP server** (Linear/Jira) with the ticket as input.
-   Integration lives at the MCP layer, not in this package.
-4. **No tracker state in the bundle.** Drop `linear_state` from the manifest +
-   its schema. A tracker issue is a one-way copy; nothing is read back. The
-   bundle is the source of truth (ADR-101 D7, unchanged).
-
-## Consequences
-
-- **Positive.** Far less machinery to maintain (no API client, no idempotency
-  map, no transport spike, no drift check). No token dependency — the whole
-  thing works offline. Matches how the maintainer actually moves tickets.
-- **Negative / cost.** No one-command bulk import; bulk creation is paste-by-paste
-  or an MCP loop. Acceptable — bundles are small and the agent can drive MCP.
-- **Neutral.** Re-creating an edited ticket in the tracker is a re-paste / MCP
-  update; there is no automatic reconciliation (there was none worth keeping).
-
-## Alternatives considered
-
-1. **Keep the GraphQL exporter (ADR-101 R2).** Rejected by the maintainer —
-   unwanted API surface; MCP already covers programmatic creation.
-2. **CSV bootstrap.** Rejected — same "automatic export" we are removing.
-3. **A thin "render paste-ready" helper.** Not needed — the ticket body is
-   already paste-ready Markdown; a helper would be ceremony.
-
-## References
-
-- [ADR-101](ADR-101-ticket-bundle-emission.md) — the bundle format (transport
-  decision superseded here).
-- [`ticket-bundle-format`](../contracts/ticket-bundle-format.md) §8 — the
-  paste/MCP handoff (rewritten).

package/docs/decisions/ADR-103-global-knowledge-default-off-until-measured.md

@@ -1,92 +0,0 @@
----
-adr: 103
-status: superseded
-date: 2026-06-16
-decision: global-knowledge-default-off-until-measured
-supersedes: —
-superseded_by: 119
-phase: evidence-v2
-type: structural
----
-
-# ADR-103 — Global knowledge sharing defaults OFF until cross-project reuse is measured
-
-## Status
-
-Accepted (2026-06-16). Council-reviewed (claude-sonnet-4-5 + gpt-4o, design mode,
-2 rounds + peer-review) as part of Evidence v2 Phase 0. **Amends
-[ADR-100](ADR-100-global-knowledge-card-sharing.md) Decision-6/Consequences**
-(the `knowledge.global_sharing.enabled` default) only. The rest of ADR-100 — the
-file-first store, origin-tier scoping, redaction-on-write, hybrid promotion,
-kill-switch — stands unchanged.
-
-## Context
-
-[ADR-098](ADR-098-evidence-first-structure-discovery.md) Decision-10 killed the
-global/registry/promotion layer with an explicit gate: *measure cross-project
-reuse over the measurement window, then decide*. [ADR-100](ADR-100-global-knowledge-card-sharing.md)
-reversed that kill on the **same day** and shipped the layer **default-ON**,
-justified by "measured v1 reuse + the cross-project value case".
-
-An independent review of the shipped v1 (claude-sonnet-4-5 + gpt-4o) found that
-justification circular: v1 was ~1 day old, the measurement window was never
-waited out, so there is **no measured reuse** — "measured v1 reuse" is a
-rationale, not a data point. The global layer thus shipped having bypassed the
-very gate that was the point of the gating exercise. Default-ON cross-project
-data movement also sits poorly with the otherwise privacy-first posture of a tool
-**other people install**: the tier-classifier can misclassify, and redaction is
-regex-based (can miss novel formats) — both listed as accepted risks in ADR-100.
-
-## Decision
-
-1. **`knowledge.global_sharing.enabled` defaults to `false`.** The store is
-   opt-in, not opt-out, until cross-project reuse exists as a measured signal.
-   The kill-switch from ADR-100 is excellent; this ADR only inverts its default.
-
-2. **The measure-then-decide gate is restored, concretely.** The default flips
-   back to `true` only when reuse is instrumented across **≥ 2 real projects**
-   and shown positive — the `_lib/knowledge_global_promote.py record-seen`
-   sightings are the instrument that already exists. Until then, opt-in stands.
-
-3. **v1 is byte-for-byte unaffected.** Project-local discipline + cards do not
-   read or write the global store regardless of this default. Only the
-   cross-project layer is gated off.
-
-4. **No new mechanism.** Promotion stays suggest-then-confirm; tier scoping,
-   redaction-on-write, and the purge command are unchanged. This ADR changes one
-   default value and the obligation to measure before flipping it back.
-
-## Consequences
-
-- `knowledge.global_sharing.enabled` default flips `true → false` in
-  `src/config/agent-settings.template.yml`, `src/server/schemas/settings.ts`,
-  and the `src/agent-src/templates/agent-settings.md` settings table.
-- `evidence-discipline.md` § Global layer notes the default-off posture and the
-  reuse-gate condition for flipping it back on.
-- A consuming operator who wants cross-project sharing sets `enabled: true`
-  explicitly — a deliberate, informed opt-in.
-- The reuse measurement (Evidence v2 Phase 5 / global-promotion gate) is the
-  evidence that would justify flipping the default back; until that data exists,
-  the question is not re-litigated.
-
-## Alternatives
-
-- **Keep default-on (do nothing).** Rejected — restates the skipped-gate failure
-  the v1 review flagged; default cross-project data movement on an installed tool
-  is the wrong default before reuse is measured.
-- **`public`-only on, `vendor` off.** Considered; rejected as the default because
-  it still moves data cross-project by default. Off-until-measured is the cleaner
-  privacy-first default. An operator may set `allowed_tiers: [public]` after
-  opting in if they want the narrower surface.
-- **Delete the global layer.** Rejected — ADR-100's file-first design is sound;
-  the issue is the *default*, not the mechanism.
-
-## References
-
-- [ADR-100](ADR-100-global-knowledge-card-sharing.md) — the global layer; Decision-6
-  default amended here.
-- [ADR-098](ADR-098-evidence-first-structure-discovery.md) — the original
-  measure-then-decide gate this ADR restores.
-- `agents/roadmaps/archive/road-to-evidence-v2-project-intelligence.md` — Evidence v2
-  Phase 0 (council convergence inlined in its header; archived on completion).
-- `src/agent-src/contexts/execution/evidence-discipline.md` § Global layer.

package/docs/decisions/ADR-104-ai-council-config-global-only.md

@@ -1,119 +0,0 @@
----
-adr: 104
-status: accepted
-date: 2026-06-22
-decision: ai-council-config-global-only
-supersedes: 093
-superseded_by: —
-phase: ai-council-config-relocation
-type: structural
----
-
-# ADR-104 — The AI-council config is global-only (drop the project-local override)
-
-## Status
-
-**Accepted** · 2026-06-22. Maintainer directive (standing, restated and
-sharpened): the council is configured **once, globally** — and the agent
-must never search a project for council config, never infer "council not
-configured" from a project's missing files.
-
-Supersedes the project-local override that
-[ADR-093](ADR-093-ai-council-config-user-global.md) deliberately kept.
-
-## Context
-
-ADR-093 relocated the council config to the user-global namespace
-(`~/.event4u/agent-config/settings/.ai-council.yml`) but **kept** a
-project-local override as precedence rule 2:
-`<project_root>/agents/settings/.ai-council.yml` would win over the
-user-global file when present. ADR-093 also rejected the "global always
-wins" alternative, reasoning it would break a consumer team's
-deliberately-checked-in shared council config.
-
-In practice that hedge produced a recurring, infuriating failure mode that
-the loader's own correctness did *not* prevent — because the failure was
-in the **agent's mental model**, not the resolver:
-
-> *"Council war in diesem Projekt nicht konfiguriert (kein <!-- md-language-check: ignore -->
-> `.agent-settings.yml`/`scripts/ai_council`), daher habe ich die eine <!-- md-language-check: ignore -->
-> Architektur-Gabel selbst entschieden."* <!-- md-language-check: ignore -->
-
-An agent working in a consumer project, asked to consult the council on an
-architecture fork, looked **in the project** for council artefacts — the
-package-internal `scripts/ai_council` directory and the long-removed
-`.agent-settings.yml` `ai_council` block — found neither (they only exist
-inside the agent-config package), and concluded the council was
-unconfigured. It then decided a structural fork solo. The user's council
-*was* configured — globally — and would have answered from any project.
-
-The project-local override is the root of this confusion: as long as "the
-project might carry its own council config" is a documented truth, the
-agent treats the project tree as a place to look, and absence-in-project
-reads as not-configured. The override's intended beneficiary (a consumer
-team pinning a shared config in their repo) has never materialised and is
-not worth the recurring solo-decision failure on real work.
-
-## Decision
-
-**The council config is global-only.** `resolve_config_path` (in
-`scripts/ai_council/config.ts`) resolves with this precedence, first match
-wins:
-
-1. **`$AI_COUNCIL_CONFIG`** — an explicit absolute path (tests / power
-   users). Honoured even when absent. This is an explicit path, not a
-   project search.
-2. **User-global** `~/.event4u/agent-config/settings/.ai-council.yml`
-   (legacy `~/.config/agent-config/` read-fallback).
-
-The project-local branch is **removed**. The loader never builds or stats
-`<project_root>/agents/settings/.ai-council.yml`. `project_root` stays in
-the signature for caller stability but is not consulted for resolution.
-
-The corollary, binding on every agent-facing surface (the `ai-council`
-skill, the `/council` command family, the config contract): **the absence
-of a council file in a project says nothing about whether the council is
-configured.** An agent must never claim "council not configured" from
-missing project files (`.agent-settings.yml`, `scripts/ai_council`, a
-project `.ai-council.yml`). The CLI/resolver is the single authority — it
-reads the global file and works from every project, worktree, and CWD.
-
-## Consequences
-
-- A user-global `.ai-council.yml` with `enabled: true` works from **every**
-  project, including consumer repos and fresh worktrees, with zero
-  per-project setup — exactly the "configure once" intent of ADR-093, now
-  without the hedge that undermined it.
-- The "council not configured in this project" solo-decision failure mode
-  is structurally impossible: there is no project location to be absent.
-- `council_cli.ts` and `cmd_doctor.ts` (`doctor council-cli`) inherit the
-  change automatically — both already route through `resolve_config_path`.
-- A consumer team that genuinely wants a repo-pinned shared council config
-  uses `$AI_COUNCIL_CONFIG` (e.g. exported in their dev shell / CI) — an
-  explicit opt-in, never an implicit project-tree search.
-- `check_council_config_location.ts` keeps guarding against
-  `.agent-settings.yml` council references; its docstring is updated to
-  drop the "project-local first" description.
-
-## Alternatives
-
-- **Keep ADR-093 as-is (project-local override stays).** Rejected — this is
-  the exact configuration that produced the recurring failure; the loader
-  being correct did not save the agent's mental model.
-- **Fix only the agent-facing docs, leave the override in the loader.**
-  Rejected — as long as a project-local lookup exists, "look in the
-  project" remains a documented truth and the absence-reads-as-unconfigured
-  confusion recurs. Removing the lookup makes the instruction unambiguous.
-- **Add a project-local override behind an explicit opt-in flag.** Rejected
-  as unneeded complexity — `$AI_COUNCIL_CONFIG` already covers the rare
-  repo-pinned case explicitly.
-
-## References
-
-- [ADR-093](ADR-093-ai-council-config-user-global.md) — the user-global
-  relocation this ADR sharpens to global-only.
-- `docs/contracts/ai-council-config.md` § File location — precedence rules.
-- `src/scripts/ai_council/config.ts` — `resolve_config_path`.
-- `src/skills/ai-council/SKILL.md`, `src/domains/meta/council/default/command.md`
-  — agent-facing surfaces carrying the "never infer not-configured from
-  missing project files" corollary.

package/docs/decisions/ADR-105-automatic-subagent-orchestration.md

@@ -1,108 +0,0 @@
----
-adr: 105
-status: accepted
-date: 2026-06-23
-decision: automatic-subagent-orchestration
-supersedes: —
-superseded_by: — (Decision 2 amended by ADR-117: shipped default ask → on)
-phase: auto-subagent-orchestration
-type: structural
----
-
-# ADR-105 — Automatic subagent orchestration: activate-don't-fragment, prove before default-on
-
-## Status
-
-**Accepted** · 2026-06-23. Resolved by a deep AI-council round
-(claude-sonnet-4-5 + gpt-4o, design mode) plus host critical-evaluation, and
-implemented by `road-to-auto-subagent-orchestration.md`.
-
-> **Amended 2026-07-09 by ADR-117.** Decision 2 below ("conservative-until-proven
-> shipped default `ask`") is superseded: the shipped default is flipped to `on`
-> on subagent-capable hosts, on a bounded-downside re-evaluation (cost-routing
-> already ships, downside is small and reversible). Every other decision in this
-> ADR stands. See ADR-117 and `orchestration-default-flip-verdict § 2026-07-09`.
-
-## Context
-
-The package shipped three latent subagent surfaces — the
-`subagent-orchestration` skill (7 modes), `/orchestrate` (YAML pipelines), and
-the RDP `reasoning-orchestrator` ("dispatch by default") — all **opt-in**,
-none firing automatically. The goal: make subagent use automatic and
-settings-gated, so an orchestrating model delegates delegable sub-tasks to
-cheaper / faster / quota-separate subagents, each configured for its task,
-globally toggleable in `.agent-settings.yml`.
-
-The user's stated default was **on**. The council pushed back hard: a "default
-on" whose own design concedes it *may increase* token spend inverts risk in a
-package whose canon includes token-efficiency as an Iron Law, and whose
-multi-tool portability constraint means not every host even has a subagent
-primitive.
-
-## Decision
-
-1. **Activate, don't fragment.** Auto-dispatch is a settings + host-manifest
-   gate over the **existing** `subagent-orchestration` skill and RDP
-   "dispatch by default" — not a new parallel rule. Smallest surface.
-2. **Conservative-until-proven shipped default.** The full toggle ships now
-   (`subagents.enabled`, `subagents.auto: off|ask|on`), but the **shipped**
-   default is `ask` on hosts whose capability manifest reports
-   `subagent_spawn: true`, `off` elsewhere. The default flips toward `on`
-   (host-gated) **only** behind a real benchmark proving a net token-or-time
-   win at held quality (Phase 6). `on` is the destination, reached by
-   evidence — the reconciliation of the user's goal with the council's
-   prove-first.
-3. **Quota arbitrage is a runtime-detected bonus, never load-bearing.** The
-   "separate quota pool" (e.g. a subscription's distinct Sonnet allowance) is a
-   `host-capability-manifest` flag; routing is identical (minus the bonus)
-   where unsupported. No `.md` names a vendor's billing rule.
-4. **Deterministic classification v1.** Delegability is decided by enumerated
-   structural signals (frontmatter `parallelizable:`, ordered-plan,
-   independent-slices, a size floor); ambiguity defaults to ask/no-op, never
-   speculative spawn. No per-turn LLM meta-call in v1. LLM classification is
-   deferred to v2+, gated on the benchmark.
-5. **Verification budget preserves the floors.** Trivial/read-only sub-tasks
-   verify deterministically; non-trivial mutating sub-tasks get a full
-   cross-model judge (the `subagent-orchestration` Iron Law). A required
-   verification recorded as `none` is a surfaced safety gap.
-6. **Instrumentation first; kill-switch + surfaced guardrails.** Orchestration
-   telemetry rides additively on `audit-log-v1`. The kill-switch is a
-   single settings flip (`enabled: false` / `auto: off`). Rollback thresholds
-   (token blowup, spawn-failure, verify-skip, override rate) are surfaced from
-   the audit log — there is no automatic cohort-disable (a config package runs
-   no daemon).
-7. **Graceful host degradation.** Where the manifest reports
-   `subagent_spawn: false`, the whole layer is a clean no-op (single-agent),
-   surfaced explicitly. `.md` artefacts stay project-agnostic.
-
-## Consequences
-
-- Auto-dispatch is the default **where the host and settings allow it**, and a
-  no-op everywhere else. No safety floor is lifted.
-- The user's "default on" is an evidence-gated milestone, not assumed — the
-  one decision left for the user is to authorise/run the Phase-6 benchmark and
-  approve the default flip.
-- The implementation is mostly contexts + small pure helpers + a settings
-  block + two activated skills, keeping the diff minimal.
-
-## Alternatives considered
-
-- **Default `on` immediately** (the literal ask) — rejected: inverts risk
-  before measurement, against the frugality canon.
-- **New parallel auto-dispatch rule** — rejected: fragments a surface that
-  already exists; activation is the smaller change.
-- **Quota arbitrage as a core motivation** — rejected: vendor-specific,
-  fragile, violates portability; demoted to a runtime bonus.
-- **Council-strict default `off` forever** — rejected: forecloses the user's
-  goal; the benchmark gate is the middle path.
-
-## References
-
-- The auto-subagent-orchestration roadmap (now archived) + the
-  full council Convergence / Host verdict.
-- [`docs/contracts/auto-orchestration-v1.md`](../contracts/auto-orchestration-v1.md) — the manifest + spawn + telemetry contract.
-- Context docs under `src/agent-src/contexts/execution/`:
-  `host-capability-manifest`, `orchestration-telemetry`,
-  `auto-orchestration-activation`, `auto-dispatch-classification`,
-  `subagent-routing`, `subagent-spawn-contract`, `verify-budget`,
-  `subagent-steering`, `orchestration-benchmark-gate`.

package/docs/decisions/ADR-106-recursive-verification-benchmark-gate.md

@@ -1,126 +0,0 @@
----
-adr: 106
-status: accepted
-date: 2026-06-23
-decision: recursive-verification-benchmark-gate
-supersedes: —
-superseded_by: —
-phase: recursive-verification · Phase 0
-type: structural
----
-
-# ADR-106 — Recursive-verification benchmark gate: capability-OR-measured-novel-discipline, not capability-only
-
-## Status
-
-Accepted (2026-06-23). Locks the Phase 0 gate definition for
-[`road-to-recursive-verification.md`](../../agents/roadmaps/archive/road-to-recursive-verification.md)
-before any live `bench:ab` spend.
-
-## Context
-
-The `recursive-verification` skill (depth-bounded `attempt → critic verdict →
-re-attempt`, default `off`) needs a benchmark gate that decides whether its
-shipped default flips to `on`/`ask` for a given host. The roadmap's initial draft
-proposed **capability-axis-first**: ship only on a capability-axis lift; a
-discipline-axis-only lift does **not** pass, on the assumption that the package's
-existing always-on rules already deliver the discipline lift, so recursion would
-merely duplicate them at ~11× cost.
-
-This gate definition was put to the AI council (manual transport disabled; live
-`council run --depth deep`, 3 rounds; members **anthropic/claude-sonnet-4-5** +
-**openai/gpt-4o**, 2026-06-23, actual cost $0.0762). Both members independently
-converged that **capability-only is the wrong gate**, for a sound methodological
-reason; one member (anthropic) also raised a misreading that the host rejected.
-
-### What the council got right (accepted)
-
-- **The redundancy assumption is unmeasured.** The gate assumed recursion's
-  discipline lift is redundant with the existing rules *without measuring it*.
-  The fix is a **three-baseline** design and an explicit **marginal** lift:
-  - `D₀` = bare host (no rules, no recursion)
-  - `D₁` = rules only (always-on rules, no recursion)
-  - `D₂` = rules + recursion
-  - **novel discipline lift = `D₂ − D₁`** — recursion's contribution *over*
-    rules-only. Redundancy is now a measured fact, not an assumption.
-- **Cheap human-preference pre-test first.** Before any expensive benchmark, show
-  ~10 `(attempt₀, attempt_final)` pairs to humans and ask "which would you pay
-  for?". If preference < 60 %, the discipline lift is economically irrelevant →
-  capability-only gate stands and the expensive discipline arm is skipped (~$15
-  to settle the whole dispute). This mirrors the package's cheap-probe-first,
-  measure-first culture.
-- **Concrete cost ceiling, not "tolerable".** The original "at a tolerable cost"
-  is circular. Replace with a measurable ceiling (token multiplier / $-per-task).
-- **Per-(host, family) cell**, not host-global — recursion may pass for a weak
-  host on one family and fail for a strong host with no headroom.
-
-### What the council got wrong (rejected by the host)
-
-- anthropic framed the gate as a *"fatal flaw because the 0.333 → 1.000 lift is
-  already recursion."* This is a **misread** of `docs/benchmark.md`: that lift is
-  the *rules'* effect (vanilla → package), measured **without** recursion;
-  recursion's marginal lift is unmeasured (that is exactly what Phase 3 runs). The
-  valid extraction is the three-baseline design above, not "capability-first is
-  fatally wrong."
-- A weighted composite metric `w_cap·Δcap + w_disc·Δdisc` (openai) is **rejected**:
-  the weights are precisely the unknown the gate exists to discover (anthropic's
-  own counter, which the host endorses).
-
-## Decision
-
-The shipped default for `verification.recursive` flips to `on`/`ask` for a
-**(host, family) cell** if and only if:
-
-```
-capability_lift(host, family) significant       (McNemar on pass-rate, or scorer
-                                                  Wilcoxon p < 0.05, ≥6 discordant
-                                                  pairs, effect ≥ 0.5)
-OR
-( novel_discipline_lift = D₂ − D₁ > ε_disc       (recursion over rules-only —
-                                                  MEASURED, never assumed)
-  AND cost_per_task ≤ ceiling                     (concrete token-multiplier / $)
-  AND human_preference_rate > 0.6 )
-ELSE off.
-```
-
-**Cheap prerequisite (runs first, gates the rest):** the ~$15 human-preference
-test. Preference < 60 % ⇒ capability-only gate stands; skip the discipline arm.
-
-**The benchmark must report, per (host, family):** `pass_rate(D₀/D₂)`,
-`discipline_score(D₀ / D₁ / D₂)`, `cost(D₂)/cost(D₀)`, and
-`human_preference(recursion vs baseline)`. Without the `D₁` (rules-only) middle
-term, redundancy cannot be detected; without human-preference, a discipline lift
-cannot be validated as economically real.
-
-The first measured cell is `(claude-haiku-4-5, scope-discipline)`; multi-family
-expansion waits until data justifies it.
-
-## Consequences
-
-- Phase 3 of the roadmap gains a **rules-only (`D₁`) arm** and a **Phase 3a-pre
-  human-preference test**; the gate language changes from "capability-first;
-  discipline-only ⇒ STOP" to the two-branch rule above.
-- An honest-null is still first-class: capability flat **and** (human-preference
-  < 60 % OR `D₂ − D₁` ≤ ε OR cost over ceiling) ⇒ ship nothing, record the null.
-- The default stays `off` until a cell passes; no global flip without its own cell.
-- Slightly more measurement up front (three baselines + a human pre-test), bought
-  cheaply ($15 pre-test gates the expensive arm) — net a more honest gate.
-
-## Alternatives considered
-
-- **Capability-only (original draft).** Rejected: assumes, without measuring,
-  that recursion's discipline lift is redundant with the rules.
-- **Weighted composite metric.** Rejected: presupposes the weights the gate
-  exists to discover.
-- **Holistic / qualitative gate (openai round 1).** Rejected: too vague to
-  operationalise into a ship/no-ship decision.
-
-## References
-
-- [`road-to-recursive-verification.md`](../../agents/roadmaps/archive/road-to-recursive-verification.md)
-- [`docs/benchmark.md`](../benchmark.md) — the existing wrapper-lift A/B evidence.
-- Council round: anthropic/claude-sonnet-4-5 + openai/gpt-4o, 2026-06-23, deep
-  tier (3 rounds), $0.0762 actual.
-- [`subagent-orchestration`](../../src/skills/subagent-orchestration/SKILL.md),
-  [`verify-budget`](../../src/agent-src/contexts/execution/verify-budget.md),
-  `orchestration-benchmark-gate` (`gateVerdict` / `resolveShippedDefault`).

package/docs/decisions/ADR-107-legal-domain-pack-adoption.md

@@ -1,70 +0,0 @@
----
-adr: 107
-status: accepted
-date: 2026-06-24
-decision: legal-domain-pack-adoption
-supersedes: —
-superseded_by: —
-phase: road-to-legal-pack
-type: prospective
----
-
-# ADR-107 — Legal domain-pack adoption (EU/DE-scoped, procedure-only, evaluated honestly)
-
-## Status
-
-**Accepted** · 2026-06-24 · three AI-council rounds (anthropic/claude-sonnet-4-5 + openai/gpt-4o; the curl-timeout fix landed mid-series so rounds 2–3 ran two-voice). Implementing roadmap: road-to-legal-pack (archived on completion).
-
-## Context
-
-`event4u/agent-config` had legal-adjacent anchors (`contracts-cognition`, `privacy-review`, `data-handling-judgment`, `data-flow-mapper`, `domain-safety-disclaimer` legal sector) but no legal **domain pack**. Opening one is a `domain-adoption-policy` decision (three gates: demand signal, named maintenance owner, CI-tooling). External legal-plugin references (a first-party suite + community packs) showed reusable patterns but enforce everything via prompt instructions only (empty hooks).
-
-## Decision
-
-> **Amendment (2026-06-24, deep-council).** The pack id was renamed `legal` →
-> `legal-review-prep` after this ADR, to stop the name itself reading as "legal
-> advice" (deep AI-council + 7.1.0 reviewers; see `road-to-legal-review-prep`).
-> Read every `legal` pack-id reference below as `legal-review-prep`.
-
-Open a single, narrow `legal` pack — **not** a multi-plugin / multi-agent parity clone.
-
-1. **Scope: EU/DE-only, hard refusal.** Every selectable jurisdiction is an implicit currency promise; for a single maintainer the smallest correct cut is EU/DE with "consult local counsel" for everything else. Encoded in the `legal-safety-floor` rule + the pack description; surfaced via a machine-checkable `Jurisdiction:` tag.
-2. **Safety-floor first.** `rule:legal-safety-floor` + its deterministic linters land before any drafting skill (a drafting skill before its floor is the exact liability the floor prevents).
-3. **Skills ship procedure + output template only — no default legal positions.** Positions live in a practice profile (`legal-practice-profile`).
-4. **Deterministic hardening is the differentiator.** Disclaimer-presence, jurisdiction-tag, and freshness linters; privilege markers extend `domain-safety-pii` + `lethal-trifecta-guard` (no new hook unless the extension demonstrably fails).
-5. **Eval = regression/consistency harness, not a correctness oracle.** Self-labeled fixtures narrowed to the maintainer's genuine-competence domain (EU DPA / GDPR Art. 28) with spot-validation; a multi-attorney gold set (inter-annotator ≥0.7) is a **demand+funding-gated** track, NOT parity-gated (legal matching is classification, not the finding-count distributions the cross-model-parity keystone calibrates). The eval achieves *measurement* objectivity (reliable regression detection), never *ground-truth* objectivity — correctness stays attorney review.
-6. **No personas** — procedure-not-personality; role focus lives in skill tags + the practice profile.
-7. **Conditional product-liability gate** — commercial (Pro-tier) ship would require licensed-attorney review of the pack itself. **Resolved N/A 2026-06-24:** the suite is open-source forever, no commercial tier (ADR-108) — the gate never fires; the non-removable disclaimer + per-output attorney-review line cover end-user reliance.
-
-## Amendment (2026-06-24, deep-council) — attorney-framing-review promotion tripwire
-
-Promotion of `legal-review-prep` out of `surface_tier: lab` / `trust_level_default:
-experimental`, flipping `default_install` to anything but `false`, or any
-commercial / hosted surface, is **blocked** until a licensed German attorney has
-reviewed the *framing* (the `legal-safety-floor` rule, `LEGAL_NOTICE.md`, and the
-RDG individual-case wording — **not** skill correctness) and the review is recorded
-in `LEGAL_NOTICE.md` as `Framing reviewed by <name>, Rechtsanwalt/Rechtsanwältin,  <!-- md-language-check: ignore -->
-<date>`. The deep AI-council (2026-06-24) scoped this as a bounded (~€300–800,
-1–2h) one-time gate, **not** a blocker for the current lab release (lab is
-explicitly unvetted; users opt in knowingly via the consent gate). Enforced by
-`lint_legal_pack` (`promotion-gate` rule): a promoted tier without the recorded
-marker fails CI.
-
-## Rejections (recorded)
-
-matter-workspace (too heavy), scheduled watchers, community-skill installer hub, US-state employment tests, full litigation depth, bar-prep, Swiss cantonal depth, non-EU/DE jurisdictions, the cross-model-parity dependency for the eval (a false blocker, corrected in the full critique round).
-
-## Consequences
-
-- The pack ships `trust_level_default: experimental` / `surface_tier: lab` as the **conservative default for a high-risk legal domain**. Gate 2 was **resolved 2026-06-24 by maintainer decision: no named-owner / external-qualification gate** — the protection is the always-present, **test-enforced** not-legal-advice notice (every skill · chat output · README · dedicated legal-pack notice; `tests/scripts/legal-disclaimer-presence.test.ts`) plus the RDG individual-case guardrail. Tier promotion is a separate future decision.
-- A reusable domain-pack sequence (Safety-Floor → Enforcement → Evals → Skills → Practice-Profile) is **documented retrospectively**, validated against a second domain before promotion to a rule (per `domain-pack-extraction-when-triggered`, N=2) — it does not drive legal's design.
-
-## Alternatives considered
-
-Jurisdiction-neutral-with-EU-default (rejected — maximizes the maintenance surface the binding constraint exists to cut); objective eval pack at N=1 (rejected — manufactures false objectivity without a funded attorney gold set); ≤2 legal personas (rejected — decoration with maintenance cost, no incremental safety).
-
-## References
-
-- road-to-legal-pack — the implementing roadmap (archived on completion)
-- [ADR-013 — Discovery Frontmatter Contract](ADR-013-discovery-frontmatter-contract.md) (vocabulary amendment, same series)
-- `rule:legal-safety-floor`, `rule:domain-adoption-policy`, `rule:domain-safety-disclaimer`

package/docs/decisions/ADR-108-open-source-forever-no-commercial-tier.md

@@ -1,46 +0,0 @@
----
-adr: 108
-status: accepted
-date: 2026-06-24
-decision: open-source-forever-no-commercial-tier
-supersedes: —
-superseded_by: —
-phase: road-to-legal-pack
-type: standing
----
-
-# ADR-108 — The suite is open-source forever; no commercial / Pro tier
-
-## Status
-
-**Accepted** · 2026-06-24 · maintainer decision. Standing commitment for the whole `event4u/agent-config` suite, surfaced while resolving the legal pack's conditional product-liability gate (ADR-107 § 0.6).
-
-## Context
-
-The legal pack (ADR-107) carried a *conditional* product-liability gate: "if shipped commercially (Pro tier), a licensed attorney must review the pack itself before ship." That conditional only matters if a commercial/Pro tier is on the table. The maintainer's standing position is that it is not — and should be made durable so the question is not relitigated and so no future change silently introduces provider liability.
-
-## Decision
-
-**The entire `event4u/agent-config` suite is and remains open-source. There is no commercial tier, no Pro tier, no paid distribution — now or in the future.**
-
-Consequences for governance:
-
-1. **The legal pack's conditional product-liability gate (ADR-107 § 0.6) never fires.** There is no provider selling the pack; the only liability surface is end-user reliance, which is addressed by the non-removable disclaimer and the per-output attorney-review line in `legal-safety-floor`.
-2. **Liability disclaimer is permanent.** Every legal-pack output is a research-and-drafting aid, not legal advice, not a substitute for a licensed attorney, and not something anyone may rely on as definitive. This holds independent of distribution model.
-3. **Reopening requires a superseding ADR.** Introducing any paid/commercial tier would be a new, explicit decision that supersedes this ADR — and would re-activate the ADR-107 § 0.6 attorney-review-of-the-pack gate before any paid distribution.
-
-## Consequences
-
-- `legal-safety-floor` § Distribution states the open-source-forever stance and that the conditional gate is closed by decision.
-- ADR-107 § 0.6 is resolved as **N/A** (not applicable under this standing decision).
-
-## Alternatives considered
-
-- **Keep 0.6 purely conditional, no standing decision** (rejected — leaves the door open to silently introducing provider liability; the maintainer wanted it hardened for the future).
-- **A CI lint enforcing "no commercial tier"** (rejected — over-engineering; an ADR + the floor statement are the right durable surface, and there is no machine signal of "commercial intent" to lint).
-
-## References
-
-- [ADR-107 — Legal domain-pack adoption](ADR-107-legal-domain-pack-adoption.md) (§ 0.6 conditional gate, now resolved N/A)
-- `rule:legal-safety-floor` § Distribution + § What this pack is — and is not
-- road-to-legal-pack § 0.6 (archived on completion)