@moreih29/nexus-core 0.12.0 → 0.14.0

package/agents/engineer/meta.yml

@@ -1,11 +0,0 @@
-name: engineer
-description: Implementation — writes code, debugs issues, follows specifications
-  from Lead and architect
-task: Code implementation, edits, debugging
-alias_ko: 엔지니어
-category: do
-resume_tier: bounded
-model_tier: standard
-capabilities:
-  - no_task_create
-id: engineer

package/agents/postdoc/meta.yml

@@ -1,13 +0,0 @@
-name: postdoc
-description: Research methodology and synthesis — designs investigation
-  approach, evaluates evidence quality, writes synthesis documents
-task: Research methodology, evidence synthesis
-alias_ko: 포닥
-category: how
-resume_tier: persistent
-model_tier: high
-capabilities:
-  - no_file_edit
-  - no_task_create
-  - no_task_update
-id: postdoc

package/agents/researcher/meta.yml

@@ -1,12 +0,0 @@
-name: researcher
-description: Independent investigation — conducts web searches, gathers
-  evidence, and reports findings with citations
-task: Web search, independent investigation
-alias_ko: 리서처
-category: do
-resume_tier: persistent
-model_tier: standard
-capabilities:
-  - no_file_edit
-  - no_task_create
-id: researcher

package/agents/reviewer/meta.yml

@@ -1,12 +0,0 @@
-name: reviewer
-description: Content verification — validates accuracy, checks facts, confirms
-  grammar and format of non-code deliverables
-task: Content verification, fact-checking, grammar review
-alias_ko: 리뷰어
-category: check
-resume_tier: ephemeral
-model_tier: standard
-capabilities:
-  - no_file_edit
-  - no_task_create
-id: reviewer

package/agents/strategist/meta.yml

@@ -1,13 +0,0 @@
-name: strategist
-description: Business strategy — evaluates market positioning, competitive
-  landscape, and business viability of decisions
-task: Business strategy, market analysis, competitive positioning
-alias_ko: 전략가
-category: how
-resume_tier: persistent
-model_tier: high
-capabilities:
-  - no_file_edit
-  - no_task_create
-  - no_task_update
-id: strategist

package/agents/tester/meta.yml

@@ -1,12 +0,0 @@
-name: tester
-description: Testing and verification — tests, verifies, validates stability and
-  security of implementations
-task: Testing, verification, security review
-alias_ko: 테스터
-category: check
-resume_tier: ephemeral
-model_tier: standard
-capabilities:
-  - no_file_edit
-  - no_task_create
-id: tester

package/agents/writer/meta.yml

@@ -1,11 +0,0 @@
-name: writer
-description: Technical writing — transforms research findings, code, and
-  analysis into clear documents and presentations for the intended audience
-task: Technical writing, documentation, presentations
-alias_ko: 라이터
-category: do
-resume_tier: bounded
-model_tier: standard
-capabilities:
-  - no_task_create
-id: writer

package/conformance/README.md

@@ -1,311 +0,0 @@
-# Nexus Conformance Fixtures
-
-Declarative behavioral tests for Nexus MCP tools. Each fixture describes a tool invocation (or sequence of invocations) and the state assertions that must hold afterwards. Fixtures are harness-neutral: they use abstract tool names and JSONPath assertions, so any consumer can write a runner against their own harness implementation.
-
-## What conformance fixtures are
-
-A conformance fixture is a JSON document that specifies:
-
-1. **Precondition** — the state files that must exist (or must not exist) before the test runs.
-2. **Action** (or **Steps** or **Event**) — one or more tool invocations, or a single lifecycle event, with concrete parameters.
-3. **Postcondition** — assertions on the tool return value and on state files after the invocation.
-4. **Covers** — a declaration of which state-schema fields and return-value paths this fixture verifies.
-
-Fixtures do not contain any test runner code. Consumers load the JSON, reconstruct precondition state, call their own tool implementation, and verify the postconditions.
-
-## Fixture format
-
-All fixtures must validate against [`schema/fixture.schema.json`](schema/fixture.schema.json).
-
-Every fixture must include a top-level `covers` field (required). An optional `uncovered_params` field may also appear.
-
-### `covers` field
-
-`covers` declares which schema fields and return-value paths this fixture's postcondition actually verifies. The coverage validator uses this declaration to track completeness across the fixture suite.
-
-```json
-"covers": {
-  "state_schemas": {
-    "plan.schema.json": ["id", "topic", "issues[].status"]
-  },
-  "return_value": {
-    "plan_start": ["created", "plan_id", "issueCount"]
-  },
-  "description": "Verifies plan creation fields and initial issue status."
-}
-```
-
-**Constraint**: at least one of `state_schemas` or `return_value` must be non-empty. Both may be present.
-
-- `state_schemas` — map of state-schema filename (e.g. `plan.schema.json`) to an array of field paths verified by this fixture's postcondition. Field paths use dot-notation with array index notation (e.g. `issues[].status`).
-- `return_value` — map of abstract tool name (e.g. `plan_start`) to an array of return-value field paths verified by this fixture's postcondition.
-- `description` — optional human-readable explanation of coverage rationale or known gaps.
-
-### `uncovered_params` field
-
-`uncovered_params` is an optional array of `action.params` keys that are intentionally not asserted in the postcondition. Entries listed here are treated as explicit exceptions by the coverage validator, preventing false anti-pattern warnings.
-
-Use this field for routing or contextual input params whose effect is not directly observable via state-file or return-value assertions:
-
-```json
-"uncovered_params": ["research_summary"]
-```
-
-### Schema `oneOf` constraint
-
-Each fixture must contain exactly one of: `action` (single tool invocation), `event` (single lifecycle event), or `steps` (multi-step sequence). These three branches are mutually exclusive.
-
-### Single-action fixture
-
-```json
-{
-  "test_id": "plan_start_happy_path",
-  "description": "...",
-  "covers": {
-    "state_schemas": { "plan.schema.json": ["id", "topic", "issues[].status"] },
-    "return_value": { "plan_start": ["created", "plan_id", "issueCount"] }
-  },
-  "precondition": {
-    "state_files": {
-      ".nexus/state/plan.json": null
-    }
-  },
-  "action": {
-    "tool": "plan_start",
-    "params": { "topic": "...", "issues": ["..."], "research_summary": "..." }
-  },
-  "postcondition": {
-    "return_value": { "$.created": true },
-    "state_files": {
-      ".nexus/state/plan.json": { "$.topic": "..." }
-    }
-  }
-}
-```
-
-### Multi-step scenario
-
-```json
-{
-  "test_id": "full_plan_cycle",
-  "description": "...",
-  "covers": {
-    "state_schemas": { "plan.schema.json": ["id", "topic", "issues[].status"] }
-  },
-  "steps": [
-    {
-      "description": "...",
-      "action": { "tool": "plan_start", "params": { ... } },
-      "assert_return": { "$.created": true },
-      "assert_state": { ".nexus/state/plan.json": { "$.issues.length": 2 } }
-    }
-  ]
-}
-```
-
-## Event-based (Lifecycle) Fixtures
-
-`agent-tracker.json`은 MCP tool이 아니라 harness의 session hook이 관리한다. 이 파일의 구조적 정확성을 검증하기 위해 `action` 대신 `event` 필드를 사용하는 lifecycle fixture를 사용한다.
-
-Event fixture는 "harness가 특정 event를 실행한 후 state 파일의 구조가 올바른가"를 선언적으로 명세한다. Tool invocation 없이 event 트리거만으로 postcondition을 검증한다.
-
-### Event types
-
-`event.type`은 다음 3종 중 하나여야 한다:
-
-| Event type | 책임 범위 |
-|---|---|
-| `agent_spawn` | `agent-tracker.json`에 신규 항목 생성 (running 상태) |
-| `agent_complete` | `agent-tracker.json` 항목을 완료 상태로 전환 |
-| `agent_resume` | `agent-tracker.json` 재개 카운터 증가 및 상태 복귀 |
-
-### Lifecycle fixture 구조 예시
-
-```json
-{
-  "test_id": "agent_spawn_creates_entry",
-  "description": "...",
-  "covers": {
-    "state_schemas": {
-      "agent-tracker.schema.json": ["harness_id", "agent_name", "agent_id", "status"]
-    }
-  },
-  "event": {
-    "type": "agent_spawn",
-    "params": { ... }
-  },
-  "postcondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": { "$[0].status": "running" }
-    }
-  }
-}
-```
-
-### Lifecycle fixture 목록
-
-`conformance/lifecycle/` 디렉토리에 3개 파일이 존재한다:
-
-| 파일 | Event type | 검증 대상 |
-|---|---|---|
-| `agent-spawn.json` | `agent_spawn` | `agent-tracker.json` 첫 항목 생성 (running 상태) |
-| `agent-complete.json` | `agent_complete` | `agent-tracker.json` 항목 완료 상태 전환 |
-| `agent-resume.json` | `agent_resume` | `agent-tracker.json` 재개 카운터 및 상태 복귀 |
-
-## Assertion conventions
-
-Assertions are key/value objects where keys are JSONPath expressions and values are expected results or matchers.
-
-| Pattern | Meaning |
-|---|---|
-| `"$.field": "expected"` | Exact string match |
-| `"$.field": 42` | Exact number match |
-| `"$.field": true` | Boolean match |
-| `"$.array.length": 3` | Array length check |
-| `"$.field": { "type": "iso8601" }` | Value is a valid ISO 8601 timestamp |
-| `"$.field": { "type": "number", "min": 1 }` | Numeric value >= 1 |
-| `"$.field": { "type": "string", "minLength": 5 }` | String with minimum length |
-| `".nexus/state/plan.json": null` | File must not exist |
-| `".nexus/state/artifacts/findings.md": {}` | File must exist; content not inspected (use for non-JSON artifacts like .md, .txt, binary files) |
-| `"{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json"` | State file path with substitutable tokens. Test runner MUST substitute `{STATE_ROOT}` with `.nexus/state` and `{HARNESS_ID}` with the harness identifier (from `event.params.harness_id` or runner configuration) before applying assertions. Only `{STATE_ROOT}` and `{HARNESS_ID}` are recognized; arbitrary tokens are forbidden. |
-
-For `state_files`, a `null` value at the file path key means the file must be absent. A `null` value at a JSONPath key within a file assertion means that field must be `null`.
-
-## Authoring Rules
-
-Fixtures must satisfy the following rules. The coverage validator enforces Rules 1–3 at CI time.
-
-**Rule 1 — Coverage**: 모든 state-schema 필드(required + optional)는 최소 1개 fixture의 `covers.state_schemas`에 등장해야 한다. 단 한 필드라도 누락되면 validator가 실패한다.
-
-**Rule 2 — No Silent Drop**: `action.params`의 모든 key는 `postcondition`(state_files 또는 return_value)에서 assert되거나 `uncovered_params`에 명시되어야 한다. 두 조건 모두 충족하지 않는 param key는 anti-pattern으로 보고된다.
-
-**Rule 3 — CI Gate**: fixture 추가 또는 수정 시 `validate:conformance` validator 통과가 release block이다. 실패 상태로 merge할 수 없다.
-
-**Rule 4 — Truthful Covers**: `covers`는 실제로 postcondition에서 assert하는 필드만 나열해야 한다. 허위 claim 금지. validator는 covers 선언과 실제 assertion 간 교차 검증을 수행하지 않지만, review 시 수동 검증 대상이다.
-
-## Running the Coverage Validator
-
-`conformance-coverage.ts`는 두 가지를 검증한다:
-
-1. **Schema field coverage** — `conformance/state-schemas/`의 모든 schema 파일에서 추출한 필드가 전체 fixture의 `covers.state_schemas` union에 포함되는지 확인한다.
-2. **Params anti-pattern** — single-action fixture의 `action.params` key가 `postcondition` assertion 또는 `uncovered_params`에 트레이스 가능한지 확인한다.
-
-### 실행 명령
-
-```
-bun run validate:conformance
-```
-
-또는 직접 실행:
-
-```
-bun run scripts/conformance-coverage.ts
-```
-
-### 출력 해석
-
-**PASS** (exit code 0):
-
-```
-✓ All state-schema fields covered: 5 schemas, 54 fields across 48 fixtures
-```
-
-**FAIL — schema field coverage 미달** (exit code 1):
-
-```
-✗ Schema field coverage incomplete:
-  plan.schema.json: missing fields [issues[].how_agents]
-```
-
-**FAIL — params anti-pattern 감지** (exit code 1):
-
-```
-✗ Params anti-pattern detected (params not verified in postcondition):
-  conformance/tools/plan-start.json (plan_start_happy_path): uncovered params [research_summary]
-```
-
-exit code 2는 파일 파싱 등 fatal error를 의미한다.
-
-## Writing a test runner
-
-A conformance test runner does the following for each fixture:
-
-1. **Load** the fixture JSON file.
-2. **Establish precondition**: for each entry in `precondition.state_files`, write the content object as JSON to the specified path, or delete the file if the value is `null`. Before resolving any path, substitute placeholder tokens: replace `{STATE_ROOT}` with `.nexus/state` and `{HARNESS_ID}` with the harness identifier found in `event.params.harness_id` (for lifecycle fixtures) or runner configuration (for general fixtures). Only `{STATE_ROOT}` and `{HARNESS_ID}` are recognized tokens; treat any other `{…}` token in a path as an authoring error.
-3. **Execute**:
-   - For single-action fixtures: call the tool named by `action.tool` with `action.params`.
-   - For event fixtures: trigger the harness session hook for the event type specified by `event.type`, passing `event.params`.
-   - For multi-step scenarios: iterate `steps` in order, calling each `action` (or triggering each `event`) and evaluating `assert_return` and `assert_state` after each step before proceeding.
-4. **Evaluate postconditions**:
-   - Check `postcondition.return_value` assertions against the tool's return value.
-   - Check `postcondition.state_files` assertions against the actual file system state. Apply the same `{STATE_ROOT}` / `{HARNESS_ID}` substitution to path keys before resolving (same rule as precondition). For each entry in `state_files`:
-     - Value is `null` → assert the file does NOT exist.
-     - Value is an empty object `{}` → assert the file EXISTS; do NOT parse content (use for non-JSON artifacts: .md, .txt, binary).
-     - Value is a non-empty object `{...}` → parse file as JSON and evaluate each JSONPath assertion against the parsed content.
-   - If `postcondition.error` is `true`, the tool call must have produced an error.
-   - If `postcondition.error_contains` is set, the error message must contain that substring.
-5. **Report** pass/fail per `test_id`.
-
-Example runner sketch (TypeScript):
-
-```typescript
-import fixtures from "./tools/plan-start.json";
-
-for (const fixture of fixtures) {
-  applyPrecondition(fixture.precondition);
-  const result = await callTool(fixture.action.tool, fixture.action.params);
-  assertPostcondition(fixture.postcondition, result);
-}
-```
-
-## Coverage
-
-### Abstract tools (11/11 커버됨)
-
-11개 abstract tool 모두 전용 fixture 파일을 갖는다. 각 fixture는 tool의 happy path, error path, optional 파라미터 경로를 포함한다.
-
-| Abstract name | Description | Fixture file |
-|---|---|---|
-| `plan_start` | Start a new plan session | `tools/plan-start.json` |
-| `plan_decide` | Record a decision on a plan issue | `tools/plan-decide.json` |
-| `plan_status` | Query the current plan state | `tools/plan-status.json` |
-| `plan_update` | Add, remove, edit, or reopen plan issues | `tools/plan-update.json` |
-| `task_add` | Add a task to the task list | `tools/task-add.json` |
-| `task_update` | Update a task's status | `tools/task-update.json` |
-| `task_list` | List tasks with dependency-aware ready set | `tools/task-list.json` |
-| `task_close` | Archive cycle into history and delete source files | `tools/task-close.json` |
-| `history_search` | Search past cycles in history.json | `tools/history-search.json` |
-| `context` | Read or write .nexus/context/ knowledge files | `tools/context.json` |
-| `artifact_write` | Write an artifact output file | `tools/artifact-write.json` |
-
-### Lifecycle events (3/3 커버됨)
-
-| Event type | Fixture file |
-|---|---|
-| `agent_spawn` | `lifecycle/agent-spawn.json` |
-| `agent_complete` | `lifecycle/agent-complete.json` |
-| `agent_resume` | `lifecycle/agent-resume.json` |
-
-### State-schema field coverage
-
-4개 state-schema의 모든 필드가 100% 커버된다:
-
-| Schema | 검증 도구 |
-|---|---|
-| `plan.schema.json` | `tools/plan-*.json` fixtures |
-| `tasks.schema.json` | `tools/task-*.json` fixtures |
-| `history.schema.json` | `tools/history-search.json`, `tools/task-close.json` |
-| `agent-tracker.schema.json` | `lifecycle/agent-*.json` fixtures |
-
-Validator 통과 결과 예시: `✓ All state-schema fields covered: 4 schemas across fixture suite`
-
-## Excluded tools
-
-AST and LSP tools (`ast_search`, `ast_replace`, `lsp_diagnostics`, `lsp_goto_definition`, etc.) are harness utilities that depend on language server infrastructure. They are not ecosystem contracts and are excluded from conformance coverage.
-
-## 관련 문서
-
-- `docs/nexus-outputs-contract.md` — harness 산출물 계약 (artifact 경로, 파일 형식)
-- `docs/nexus-state-overview.md` — state file 기술 스펙 (schema 정의, 파일 위치)
-- `docs/nexus-tools-contract.md` — 11개 abstract tool 계약 (params, return value)
-- `CONSUMING.md §Conformance Obligation` — consumer가 준수해야 하는 conformance 의무

package/conformance/examples/plan.extension.schema.example.json

@@ -1,25 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "conformance/examples/plan.extension.schema.example.json",
-  "title": "Example: Harness-local plan state extension",
-  "description": "Non-normative reference example of a harness-local extension schema for plan.json. Harnesses MAY add supplemental fields via {base}.extension.json files in .nexus/state/{harness-id}/. Consumers replace harness_specific_field_example with their own fields. See docs/nexus-outputs-contract.md §Harness-local State Extension for the pattern definition.",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["extends"],
-  "properties": {
-    "extends": {
-      "type": "string",
-      "const": "conformance/state-schemas/plan.schema.json",
-      "description": "Reference to the parent common-schema this extension supplements"
-    },
-    "harness_id": {
-      "type": "string",
-      "pattern": "^[a-z][a-z0-9-]*$",
-      "description": "Identifier of the harness that produced this extension file"
-    },
-    "harness_specific_field_example": {
-      "type": "string",
-      "description": "Placeholder — replace with your harness's actual extension fields as needed"
-    }
-  }
-}

package/conformance/lifecycle/README.md

@@ -1,48 +0,0 @@
-# Lifecycle Fixtures
-
-이 fixture들은 harness의 session hook이 event를 재현한 후의 state 파일을 검증한다.
-
-## Event Types
-
-| Fixture | Event Type | 검증 대상 |
-|---|---|---|
-| `agent-spawn.json` | `agent_spawn` | `agent-tracker.json` 첫 항목 생성 (running 상태) |
-| `agent-complete.json` | `agent_complete` | `agent-tracker.json` 항목 완료 상태 전환 |
-| `agent-resume.json` | `agent_resume` | `agent-tracker.json` 재개 카운터 및 상태 복귀 |
-| `session-end.json` | `session_end` | `agent-tracker.json` 삭제, `history.json` · `memory/` · `context/` · `rules/` 보존 |
-
-## Why session-end was re-added at v0.11.0
-
-v0.6.0에서 session-start/session-end fixture를 제거한 이유는 당시 구현이 `runtime.schema.json`에 의존했기 때문이다. `runtime.schema.json`은 execution semantics를 포함하므로 nexus-core의 prompt-only 원칙과 충돌했다. v0.11.0 재도입은 `runtime.schema.json`을 완전히 배제하고 `agent-tracker.schema.json`과 `history.schema.json`만 참조한다. session_end fixture가 검증하는 핵심 invariant는 두 가지다: (1) agent-tracker.json은 세션 종료 시 삭제된다(session-scoped), (2) history.json · memory/ · context/ · rules/는 삭제되어서는 안 된다(Negative MUST — cross-session knowledge 보존).
-
-## Tool-action 대신 Event 트리거 사용
-
-각 fixture는 `action` (tool invocation) 대신 `event` 필드를 사용한다. `agent-tracker.json`은 harness의 session hook이 관리하며, MCP tool이 직접 쓰지 않는다. Event fixture는 "harness가 event를 실행한 후 state 파일의 구조가 올바른가"를 선언적으로 명세한다.
-
-## Placeholder token 경로
-
-이 lifecycle fixture 3종의 `precondition.state_files` 및 `postcondition.state_files` 키는 모두 placeholder token 형식을 사용한다:
-
-```
-{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json
-```
-
-Test runner는 이 키를 파일 시스템 경로로 해석하기 전에 다음 치환을 수행해야 한다:
-
-| Token | 치환 값 | 출처 |
-|---|---|---|
-| `{STATE_ROOT}` | `.nexus/state` | 고정 상수 |
-| `{HARNESS_ID}` | harness 식별자 (예: `claude-nexus`) | 해당 fixture의 `event.params.harness_id` |
-
-치환 규약:
-- `{STATE_ROOT}`와 `{HARNESS_ID}` 두 token만 인식된다. 그 외 `{…}` 형태의 token이 경로에 등장하면 authoring 오류로 처리한다.
-- 공통 파일 fixture (`plan-*`, `task-*`, `history-*`, `artifact-write`)는 하드코딩된 경로를 사용하며 이 token 규약이 적용되지 않는다. Token 경로는 lifecycle fixture 4종(`agent-spawn`, `agent-complete`, `agent-resume`, `session-end`)의 `agent-tracker.json` 경로에만 적용된다.
-
-### Fixture별 경로 요약
-
-| Fixture | `event.params.harness_id` 예시 | 해석된 경로 |
-|---|---|---|
-| `agent-spawn.json` | `claude-nexus` | `.nexus/state/claude-nexus/agent-tracker.json` |
-| `agent-complete.json` | `claude-nexus` | `.nexus/state/claude-nexus/agent-tracker.json` |
-| `agent-resume.json` | `claude-nexus` | `.nexus/state/claude-nexus/agent-tracker.json` |
-| `session-end.json` | `claude-nexus` | `.nexus/state/claude-nexus/agent-tracker.json` (null assertion — file must not exist after session end) |

package/conformance/lifecycle/agent-complete.json

@@ -1,44 +0,0 @@
-{
-  "test_id": "agent_complete",
-  "description": "Verifies that agent_complete transitions an agent to completed status and records stopped_at, last_message, and files_touched in agent-tracker.json",
-  "precondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": [
-        {
-          "harness_id": "claude-nexus",
-          "agent_name": "architect",
-          "agent_id": "uuid-eng01",
-          "started_at": "2026-04-13T00:00:00.000Z",
-          "resume_count": 0,
-          "status": "running"
-        }
-      ]
-    }
-  },
-  "event": {
-    "type": "agent_complete",
-    "params": {
-      "agent_id": "uuid-eng01",
-      "last_message": "Implementation complete",
-      "files_touched": ["src/foo.ts", "src/bar.ts"]
-    },
-    "description": "Harness records agent completion with output summary and list of modified files"
-  },
-  "postcondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": {
-        "$.length": 1,
-        "$[0].status": "completed",
-        "$[0].stopped_at": { "type": "iso8601" },
-        "$[0].last_message": "Implementation complete",
-        "$[0].files_touched.length": 2,
-        "$[0].files_touched[0]": "src/foo.ts"
-      }
-    }
-  },
-  "covers": {
-    "state_schemas": {
-      "agent-tracker.schema.json": ["status", "stopped_at", "last_message", "files_touched", "files_touched[]"]
-    }
-  }
-}

package/conformance/lifecycle/agent-resume.json

@@ -1,43 +0,0 @@
-{
-  "test_id": "agent_resume",
-  "description": "Verifies that agent_resume transitions a completed agent back to running status and increments resume_count and sets last_resumed_at",
-  "precondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": [
-        {
-          "harness_id": "claude-nexus",
-          "agent_name": "architect",
-          "agent_id": "uuid-eng01",
-          "started_at": "2026-04-13T00:00:00.000Z",
-          "resume_count": 0,
-          "status": "completed",
-          "stopped_at": "2026-04-13T01:00:00.000Z",
-          "last_message": "Implementation complete",
-          "files_touched": ["src/foo.ts", "src/bar.ts"]
-        }
-      ]
-    }
-  },
-  "event": {
-    "type": "agent_resume",
-    "params": {
-      "agent_id": "uuid-eng01"
-    },
-    "description": "Harness resumes a previously completed agent, incrementing the resume counter and updating lifecycle timestamps"
-  },
-  "postcondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": {
-        "$.length": 1,
-        "$[0].status": "running",
-        "$[0].resume_count": 1,
-        "$[0].last_resumed_at": { "type": "iso8601" }
-      }
-    }
-  },
-  "covers": {
-    "state_schemas": {
-      "agent-tracker.schema.json": ["last_resumed_at", "resume_count", "status"]
-    }
-  }
-}

package/conformance/lifecycle/agent-spawn.json

@@ -1,36 +0,0 @@
-{
-  "test_id": "agent_spawn",
-  "description": "Verifies that agent_spawn appends a new running agent entry to agent-tracker.json with required fields initialized correctly",
-  "precondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": []
-    }
-  },
-  "event": {
-    "type": "agent_spawn",
-    "params": {
-      "harness_id": "claude-nexus",
-      "agent_name": "architect",
-      "agent_id": "uuid-eng01"
-    },
-    "description": "Harness spawns an agent instance and records its initial state in the agent registry"
-  },
-  "postcondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/agent-tracker.json": {
-        "$.length": 1,
-        "$[0].harness_id": "claude-nexus",
-        "$[0].agent_name": "architect",
-        "$[0].agent_id": "uuid-eng01",
-        "$[0].started_at": { "type": "iso8601" },
-        "$[0].resume_count": 0,
-        "$[0].status": "running"
-      }
-    }
-  },
-  "covers": {
-    "state_schemas": {
-      "agent-tracker.schema.json": ["harness_id", "agent_name", "agent_id", "started_at", "resume_count", "status"]
-    }
-  }
-}

package/conformance/lifecycle/memory-access-record.json

@@ -1,27 +0,0 @@
-{
-  "test_id": "memory_access_record",
-  "description": "Verifies that a memory-access.jsonl record is written with the required fields when an agent reads a memory file during a session",
-  "precondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/memory-access.jsonl": null
-    }
-  },
-  "event": {
-    "type": "session_end",
-    "params": {
-      "harness_id": "claude-nexus"
-    },
-    "description": "Harness reads memory file and appends an access record to memory-access.jsonl. This fixture validates the structure of the resulting JSONL record against memory-access.schema.json."
-  },
-  "postcondition": {
-    "state_files": {
-      "{STATE_ROOT}/{HARNESS_ID}/memory-access.jsonl": {}
-    }
-  },
-  "covers": {
-    "state_schemas": {
-      "memory-access.schema.json": ["path", "last_accessed_ts", "access_count", "last_agent", "schema_version"]
-    },
-    "description": "memory-access.jsonl is a JSONL file where each line is a memory-access.schema.json record. This fixture asserts the file exists after a session where memory was read. Content is not inspected via JSONPath because JSONL is not parseable as a single JSON object; field coverage is declared here to satisfy the schema coverage gate."
-  }
-}