@aibyzero/byz 0.0.0 → 0.1.1

package/workflows/cm/assets/readme/test-evidence.svg

@@ -0,0 +1,64 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="380" viewBox="0 0 1200 380" role="img" aria-labelledby="title desc">
+  <title id="title">CM Workflow test evidence receipts</title>
+  <desc id="desc">Three editorial evidence receipts distinguish code logic review, actual project command execution, and browser-based user path testing.</desc>
+
+  <rect width="1200" height="380" fill="#F4F0E8"/>
+  <path d="M48 38H1152M48 336H1152" stroke="#151515" stroke-width="1.5"/>
+
+  <text x="48" y="70" fill="#C44B32" font-size="18" font-weight="800"
+        font-family="ui-monospace, SFMono-Regular, Menlo, monospace" letter-spacing="2">TEST EVIDENCE RECEIPTS</text>
+  <text x="48" y="108" fill="#151515" font-size="30" font-weight="700"
+        font-family="Georgia, Songti SC, serif">三种测试，三类凭证，不互相冒充</text>
+  <text x="1152" y="70" fill="#777168" font-size="17" text-anchor="end"
+        font-family="ui-monospace, SFMono-Regular, Menlo, monospace">READONLY BY DEFAULT</text>
+
+  <g transform="translate(48 136)">
+    <rect width="344" height="164" fill="#FAF8F2" stroke="#AAA399"/>
+    <text x="18" y="31" fill="#777168" font-size="15" font-weight="800"
+          font-family="ui-monospace, SFMono-Regular, Menlo, monospace">RECEIPT 01</text>
+    <text x="18" y="70" fill="#151515" font-size="29" font-weight="700"
+          font-family="Georgia, Songti SC, serif">Logic</text>
+    <path d="M18 84H326" stroke="#AAA399"/>
+    <text x="18" y="111" fill="#151515" font-size="17"
+          font-family="-apple-system, BlinkMacSystemFont, Segoe UI, sans-serif">入口 · 分支 · 状态 · 输出</text>
+    <text x="18" y="143" fill="#C44B32" font-size="15" font-weight="800"
+          font-family="ui-monospace, SFMono-Regular, Menlo, monospace">SUPPORTED ≠ EXECUTED</text>
+  </g>
+
+  <g transform="translate(428 136)">
+    <rect width="344" height="164" fill="#FAF8F2" stroke="#AAA399"/>
+    <text x="18" y="31" fill="#777168" font-size="15" font-weight="800"
+          font-family="ui-monospace, SFMono-Regular, Menlo, monospace">RECEIPT 02</text>
+    <text x="18" y="70" fill="#151515" font-size="29" font-weight="700"
+          font-family="Georgia, Songti SC, serif">Commands</text>
+    <path d="M18 84H326" stroke="#AAA399"/>
+    <text x="18" y="111" fill="#151515" font-size="17"
+          font-family="-apple-system, BlinkMacSystemFont, Segoe UI, sans-serif">正式脚本 · 退出码 · 测试日志</text>
+    <g transform="translate(18 126)">
+      <rect width="118" height="24" fill="#2E6655"/>
+      <text x="59" y="17" fill="#F4F0E8" font-size="13" font-weight="800" text-anchor="middle"
+            font-family="ui-monospace, SFMono-Regular, Menlo, monospace">ACTUAL RUN</text>
+    </g>
+  </g>
+
+  <g transform="translate(808 136)">
+    <rect width="344" height="164" fill="#FAF8F2" stroke="#AAA399"/>
+    <text x="18" y="31" fill="#777168" font-size="15" font-weight="800"
+          font-family="ui-monospace, SFMono-Regular, Menlo, monospace">RECEIPT 03</text>
+    <text x="18" y="70" fill="#151515" font-size="29" font-weight="700"
+          font-family="Georgia, Songti SC, serif">Browser</text>
+    <path d="M18 84H326" stroke="#AAA399"/>
+    <text x="18" y="111" fill="#151515" font-size="17"
+          font-family="-apple-system, BlinkMacSystemFont, Segoe UI, sans-serif">操作 · URL · 可观察结果 · 截图</text>
+    <g transform="translate(18 126)">
+      <rect width="104" height="24" fill="#151515"/>
+      <text x="52" y="17" fill="#F4F0E8" font-size="13" font-weight="800" text-anchor="middle"
+            font-family="ui-monospace, SFMono-Regular, Menlo, monospace">USER PATH</text>
+    </g>
+  </g>
+
+  <text x="48" y="326" fill="#C44B32" font-size="16" font-weight="800"
+        font-family="ui-monospace, SFMono-Regular, Menlo, monospace">NO SOURCE EDIT · NO DEPENDENCY INSTALL · NO WEAKENED ASSERTION</text>
+  <text x="1152" y="326" fill="#2E6655" font-size="16" font-weight="800" text-anchor="end"
+        font-family="ui-monospace, SFMono-Regular, Menlo, monospace">EVIDENCE ATTACHED ✓</text>
+</svg>

package/workflows/cm/compat/claude-commands/cm-ai.md

@@ -0,0 +1,3 @@
+# /cm:ai — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-ai/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill 及其 `references/` 节点。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-check.md

@@ -0,0 +1,3 @@
+# /cm:check — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-check/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-fix.md

@@ -0,0 +1,3 @@
+# /cm:fix — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-fix/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-idea.md

@@ -0,0 +1,3 @@
+# /cm:idea — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-idea/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-init.md

@@ -0,0 +1,3 @@
+# /cm:init — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-init/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-prd.md

@@ -0,0 +1,3 @@
+# /cm:prd — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-prd/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-refactor.md

@@ -0,0 +1,3 @@
+# /cm:refactor — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-refactor/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/compat/claude-commands/cm-test.md

@@ -0,0 +1,3 @@
+# /cm:test — Claude Code macOS/Linux 兼容入口
+
+读取 `~/.claude/skills/cm-test/SKILL.md`，将 `$ARGUMENTS` 原样作为用户输入，严格执行该 Skill。Skill 是唯一规则源；本文件不定义业务流程。如 Skill 不存在，提示重新安装 CM Workflow。

package/workflows/cm/docs/architecture.md

@@ -0,0 +1,130 @@
+# Architecture
+
+CM Workflow has one workflow implementation and two runtime entry surfaces.
+
+```mermaid
+flowchart LR
+    Codex["Codex $cm-*"] --> Skills["skills/cm-*/SKILL.md"]
+    Claude["Claude Code /cm-*"] --> Skills
+    Legacy["macOS/Linux /cm:* alias"] --> Wrappers["compat/claude-commands/"]
+    Wrappers --> Skills
+    Skills --> Context["runtime/project-context.md"]
+    Skills --> Orchestration["runtime/orchestration.md"]
+    Skills --> Review["runtime/review.md"]
+    Skills --> TaskGates["runtime/task-gates.md"]
+    Skills --> Logging["runtime/logging.md"]
+    Skills --> External["runtime/external-expert.md"]
+    Skills --> References["flow references: N1-N8 / PRD modes"]
+    Skills --> Templates["templates/"]
+    Skills --> Specs["requirements / design / tasks / optional test-cases"]
+    Specs --> Target["target code repository"]
+    External --> Provider["optional external browser / manual handoff"]
+    Provider --> ExternalEvidence["specs .external/"]
+    Logging --> Writer["scripts/cm-log-event.py"]
+    Writer --> ProjectLog["specs 运行日志.jsonl + .cm-run.json/.lock"]
+    Writer --> GlobalLog["~/.cm-workflow/logs private mirror"]
+    Config["optional .cm-workflow.yml/.json"] --> ConfigCheck["scripts/cm_workflow_config.py"]
+    ConfigCheck --> Routing["runtime/workflow-routing.md"]
+    Routing --> Skills
+    TaskGates --> GateCheck["scripts/cm-task-gate.py"]
+    GateCheck --> Reviews["specs .reviews handoff + verdict evidence"]
+    Check["scripts/cm-check-runtime.sh"] -. validates .-> Skills
+    Check -. validates .-> Wrappers
+```
+
+## Sources of truth
+
+- Each numbered feature's `tasks.md` is the authoritative business-task state.
+- An optional project `.cm-workflow.yml`/`.yaml`/`.json` selects finite workflow
+  profiles, role adapters, model aliases, and test/delivery policies. It is
+  configuration, not permission or task state; missing configuration means the
+  built-in defaults remain active. The contract lives in
+  `runtime/workflow-config.md`; node projection and route-state semantics live in
+  `runtime/workflow-routing.md`.
+- `.cm-specs-status` binds approval to a full requirements/design/tasks/test semantic manifest;
+  only N5/N6 task and AC completion markers are normalized so an interrupted run can resume;
+  `.cm-status.json`, `.cm-run.json`, `运行日志.jsonl`, `.reviews/`,
+  `METRICS.md`, and `LESSONS.md` are the durable audit and recovery artifacts.
+- The user-global `~/.cm-workflow/logs/` tree is a reconstructable local mirror,
+  not an authoritative state store or telemetry endpoint.
+- Codex plans, OMX state, subagent threads, and Claude task panels are
+  reconstructable mirrors.
+- Per-feature `test-cases.json` is the optional AI-readable test intent.
+  Execution results stay in `.reviews/`; no competing result database is added.
+- N3 implementation handoffs and N4 verdicts also stay in `.reviews/` as
+  content-bound evidence. `runtime/task-gates.md` validates their transition; they
+  never replace the checkbox state in `tasks.md`.
+
+## Runtime compatibility
+
+Codex discovers the plugin through `.codex-plugin/plugin.json` and calls Skills
+directly. Claude Code invokes the same Skills as `/cm-*` on every platform.
+The macOS/Linux installer also maps the three-line compatibility wrappers to
+the historic `/cm:*` aliases. Windows uses `/cm-*` because `:` is not legal in
+native filenames. Workflow assets resolve relative to the active Skill; no flow
+may hardcode a Codex cache path or treat `~/.claude` as the universal source
+root.
+
+## Review model
+
+Implementation cannot be marked complete without task-scoped review evidence.
+The preferred channel is a fresh Codex subagent or independent thread, followed
+by an isolated read-only Codex CLI review. `self-degraded` is allowed only when
+independent channels are unavailable and must be recorded in the evidence.
+N3 must first produce a schema-valid `ready_for_review` handoff. N4 owns the
+`approved | changes_requested | blocked` verdict, and N5 runs the shared gate
+instead of treating any matching filename as approval. At most two attempts are
+allowed. Parallel writers also pass the same gate tool with distinct registered
+worktrees and branches; failure downgrades execution to serial.
+
+## External reasoning model
+
+`external-expert` is an independent utility Skill for product deliberation,
+problem or academic research, diagnosis, test design, and critique. CM defaults
+to EXPLICIT activation. A user can opt only the current invocation into AUTO,
+which routes to LOCAL, CONSULT, or VERIFY; HANDOFF is explicit-only. A global
+router cannot silently enable CM AUTO. The local main agent chooses outbound
+context, applies accepted changes, and runs verification.
+
+Requests and raw responses live under `.external/`; they cannot satisfy N4.
+If an external conversation contributed to a plan, diagnosis, tests, or patch,
+it is an authoring channel and is ineligible to review the same work.
+
+Before browser dispatch, the runtime routes visible modes through
+`Pro → Extra High → High → SKIPPED`. Fallback inside this chain is automatic;
+Medium and Instant are excluded. `SKIPPED` sends nothing and returns control to
+the local workflow. An explicit strict-Pro request blocks when Pro is missing.
+Task routing is a separate earlier gate; AUTO never authorizes local-file
+transmission and mixed-task implementation remains local.
+
+## Logging model
+
+`runtime/logging.md` defines one event envelope for Codex and Claude Code.
+`scripts/cm-log-event.py` writes the specs-local `运行日志.jsonl` first, mirrors
+the same event into a per-run global JSONL file, and maintains an append-only
+`index.jsonl`. `.cm-run.json` lets a new session reuse an active `run_id`; a
+completed run causes the next invocation to rotate to a new id. Project and
+global standard-library file locks serialize concurrent writers, while a
+deterministic event id deduplicates an otherwise identical retry.
+
+The project log is authoritative. If the global mirror fails, a specs-backed
+workflow records a `degrade` event locally and continues. A global-only utility
+has no safe fallback and fails explicitly. Global directories and files use
+private owner-only permissions where the operating system supports POSIX modes.
+The envelope contains operational metadata only; prompts, responses, source
+content, external conversation links, and credentials stay out of it.
+
+Long-running desktop and browser work emits event-based progress checkpoints,
+not a timer-driven heartbeat. Temporary profiles, processes, aliases, worktrees,
+and fixtures use paired resource events; an unmatched acquisition blocks the
+next task or run completion. Each acquisition has a unique run-local resource
+id, so a delayed cleanup cannot close a later resource.
+
+## Testing model
+
+`cm-prd` can generate one `test-cases.json` per behavior-bearing feature.
+`cm-ai` consumes logic cases during task review and browser cases during QA.
+`cm-test` is a separate, default-read-only entry for already implemented
+features. Its `--generate-cases` mode reads existing code and writes a validated
+inferred draft, then stops before execution. Test failures can be handed to
+`cm-fix` only by an explicit user decision.

package/workflows/cm/docs/fixes/.reviews/fix-manifest-runtime-checkbox-drift-r1.md

@@ -0,0 +1,33 @@
+---
+at: 2026-08-04T20:10:00-07:00
+reviewer: codex-subagent
+independent: true
+task: fix-manifest-runtime-checkbox-drift
+round: 1
+scope:
+  - scripts/cm-spec-manifest.py
+  - scripts/test-spec-manifest.py
+  - runtime/test-contract.md
+  - skills/cm-ai/references/N1-init.md
+  - skills/cm-prd/SKILL.md
+  - docs/architecture.md
+  - docs/user-guide.md
+---
+
+Verdict: changes_requested (1 blocking finding).
+
+The runtime task/AC checkbox normalization is correct for ordinary specification
+lines, but the regular expressions also match Markdown examples inside fenced or
+four-space-indented code blocks. Changing an example from unchecked to checked
+could therefore evade the approved-spec manifest.
+
+Review comment:
+
+- [P1] Do not normalize task/AC-shaped text inside Markdown code examples —
+  `scripts/cm-spec-manifest.py`
+
+  Normalize only semantic list items in the document body. Preserve fenced and
+  indented code bytes exactly, and add regression fixtures for both forms.
+
+Disposition: accepted. The implementation will remain schema-compatible, but
+the canonicalization pass will become Markdown-context-aware before round 2.

package/workflows/cm/docs/fixes/.reviews/fix-manifest-runtime-checkbox-drift-r2.md

@@ -0,0 +1,31 @@
+---
+at: 2026-08-04T20:22:00-07:00
+reviewer: codex-subagent
+independent: true
+task: fix-manifest-runtime-checkbox-drift
+round: 2
+scope:
+  - scripts/cm-spec-manifest.py
+  - scripts/test-spec-manifest.py
+  - runtime/test-contract.md
+  - skills/cm-ai/references/N1-init.md
+  - skills/cm-prd/SKILL.md
+  - docs/architecture.md
+  - docs/user-guide.md
+---
+
+Verdict: approved (0 blocking findings).
+
+The first-round Markdown context issue is resolved. Independent verification
+confirmed:
+
+- initial unchecked files retain their raw SHA-256 for backward compatibility;
+- ordinary `T-*` and `AC-*` completion markers remain manifest-matched;
+- fenced and indented code examples, ordinary checklists, and task/AC text
+  changes still produce a manifest mismatch;
+- backtick/tilde fences, tab indentation, CRLF, and non-UTF-8 bytes remain safe;
+- the completed isolated dogfood specs fixture returns `status: matched`;
+- the focused fixture, runtime check, plugin validation, and `git diff --check`
+  pass.
+
+The reviewer made no file changes.

package/workflows/cm/docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a1-handoff.json

@@ -0,0 +1,56 @@
+{
+  "schema_version": 1,
+  "task_id": "T-FIX-model-call-boundary-identity",
+  "attempt": 1,
+  "status": "ready_for_review",
+  "changed_files": [
+    ".claude/rules/security.md",
+    ".claude/rules/testing.md",
+    ".omx/logs/execution-ledger.md",
+    ".omx/plans/model-usage-adapter.md",
+    "README.md",
+    "docs/fixes/20260806-model-call-boundary-identity.md",
+    "runtime/logging.md",
+    "runtime/model-efficiency.md",
+    "scripts/cm-log-event.py",
+    "scripts/cm-openai-compatible-call.py",
+    "scripts/cm-usage-report.py",
+    "scripts/test-cm-openai-compatible-call.py",
+    "scripts/test-cm-usage-report.py"
+  ],
+  "verification": [
+    {
+      "command": "python3 scripts/test-cm-openai-compatible-call.py",
+      "status": "passed",
+      "evidence": "Strict JSON/URL/Unicode/depth, response error logging, exit 3/4, duplicate and completed call-id fixtures passed."
+    },
+    {
+      "command": "python3 scripts/test-cm-usage-report.py",
+      "status": "passed",
+      "evidence": "Writer identity matching plus reporter mismatch, conflicting-claim and usage-before-claim fixtures passed."
+    },
+    {
+      "command": "./scripts/cm-check-runtime.sh",
+      "status": "passed",
+      "evidence": "Runtime, logging, timing, routing, adapter, config, task-gate and manifest fixtures passed for plugin v0.10.4."
+    },
+    {
+      "command": "python3 scripts/validate-public-repo.py && python3 scripts/scan-public-safety.py",
+      "status": "passed",
+      "evidence": "Public repository validation and safety scan passed."
+    },
+    {
+      "command": "/bin/bash scripts/test-shell-compat.sh && plugin validator && git diff --check",
+      "status": "passed",
+      "evidence": "Shell compatibility, Codex plugin validation and whitespace validation passed."
+    }
+  ],
+  "evidence": [
+    "docs/fixes/20260806-model-call-boundary-identity.md",
+    "red: deep packet exited 1 with RecursionError before repair",
+    "red: mismatched usage counted success and resolved an unrelated claim before repair",
+    "green: mismatched writer event exits 2 and reporter keeps the claim unresolved"
+  ],
+  "blockers": [],
+  "scope_deviation": []
+}

package/workflows/cm/docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a2-handoff.json

@@ -0,0 +1,85 @@
+{
+  "schema_version": 1,
+  "task_id": "T-FIX-model-call-boundary-identity",
+  "attempt": 2,
+  "status": "ready_for_review",
+  "changed_files": [
+    ".claude/CLAUDE.md",
+    ".claude/rules/security.md",
+    ".claude/rules/testing.md",
+    "README.md",
+    "docs/fixes/.reviews/fix-manifest-runtime-checkbox-drift-r2.md",
+    "docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a1-handoff.json",
+    "docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-r1.md",
+    "docs/fixes/20260804-manifest-runtime-checkbox-drift.md",
+    "docs/fixes/20260806-model-call-boundary-identity.md",
+    "docs/fixes/20260807-prelanding-integrity.md",
+    "docs/user-guide.md",
+    "runtime/logging.md",
+    "runtime/model-efficiency.md",
+    "runtime/orchestration.md",
+    "runtime/review.md",
+    "runtime/task-gates.md",
+    "runtime/task-handoff.schema.json",
+    "runtime/workflow-config.md",
+    "runtime/workflow-routing.md",
+    "scripts/cm-check-runtime.sh",
+    "scripts/cm-log-event.py",
+    "scripts/cm-openai-compatible-call.py",
+    "scripts/cm-task-gate.py",
+    "scripts/cm-usage-report.py",
+    "scripts/cm_workflow_config.py",
+    "scripts/scan-public-safety.py",
+    "scripts/test-cm-openai-compatible-call.py",
+    "scripts/test-cm-usage-report.py",
+    "scripts/test-task-gate.py",
+    "scripts/test-workflow-config.py",
+    "scripts/validate-public-repo.py",
+    "skills/cm-ai/SKILL.md",
+    "skills/cm-ai/references/N3-execute-task.md",
+    "skills/cm-ai/references/N4-review.md",
+    "skills/cm-ai/references/N5-mark-done.md",
+    "skills/cm-fix/SKILL.md",
+    "skills/cm-prd/SKILL.md",
+    "skills/cm-refactor/SKILL.md",
+    "skills/cm-test/SKILL.md",
+    "templates/cm-workflow.yml"
+  ],
+  "implementation_sha256": "b7e6fcf18221012f08ba9d46c657d7c40831ccb49fe2903fbababa7d65ae356d",
+  "verification": [
+    {
+      "command": "python3 scripts/test-cm-usage-report.py && python3 scripts/test-cm-openai-compatible-call.py && python3 scripts/test-workflow-config.py && python3 scripts/test-task-gate.py",
+      "status": "passed",
+      "evidence": "Managed usage requires a claim, stdout delivery is outcome-safe, unsupported managed reviewer config is rejected, and implementation mutations invalidate content-bound review evidence."
+    },
+    {
+      "command": "python3 -m py_compile scripts/cm-log-event.py scripts/cm-usage-report.py scripts/cm-openai-compatible-call.py scripts/cm-task-gate.py scripts/cm_workflow_config.py scripts/test-cm-usage-report.py scripts/test-cm-openai-compatible-call.py scripts/test-workflow-config.py scripts/test-task-gate.py",
+      "status": "passed",
+      "evidence": "All modified Python runtime and fixture files compiled successfully."
+    },
+    {
+      "command": "./scripts/cm-check-runtime.sh",
+      "status": "passed",
+      "evidence": "Runtime, log, timing, usage, adapter, config, task-gate, manifest and review recovery fixtures passed for plugin v0.10.4."
+    },
+    {
+      "command": "python3 scripts/validate-public-repo.py && python3 scripts/scan-public-safety.py",
+      "status": "passed",
+      "evidence": "Public repository validation and safety scan passed after the optional handoff digest contract was added."
+    },
+    {
+      "command": "/bin/bash scripts/test-shell-compat.sh && plugin validator && git diff --check",
+      "status": "passed",
+      "evidence": "Shell compatibility, Codex plugin validation and whitespace validation passed."
+    }
+  ],
+  "evidence": [
+    "docs/fixes/20260806-model-call-boundary-identity.md",
+    "docs/fixes/20260807-prelanding-integrity.md",
+    "round 1 recorded four blocking findings and verdict changes_requested",
+    "attempt 2 covers every currently modified or untracked landing path",
+    "implementation digest was generated by cm-task-gate.py hash-implementation"
+  ],
+  "blockers": [],
+  "scope_deviation": []
+}

package/workflows/cm/docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-r1.md

@@ -0,0 +1,53 @@
+---
+at: 2026-08-07T00:02:49-07:00
+reviewer: self-degraded
+independent: false
+degraded_reason: fresh codex-cli review started in an isolated repository but the account weekly limit was 100 percent; subagent delegation was not authorized for this task
+task: T-FIX-model-call-boundary-identity
+attempt: 1
+round: 1
+verdict: changes_requested
+blocking_findings: 4
+handoff: fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a1-handoff.json
+handoff_sha256: 27dd0d380030d27dda39dc4754b1199283c7872693dfd57b2fccf124f448ea3a
+scope:
+  - .claude/rules/security.md
+  - .claude/rules/testing.md
+  - .omx/logs/execution-ledger.md
+  - .omx/plans/model-usage-adapter.md
+  - README.md
+  - docs/fixes/20260806-model-call-boundary-identity.md
+  - runtime/logging.md
+  - runtime/model-efficiency.md
+  - scripts/cm-log-event.py
+  - scripts/cm-openai-compatible-call.py
+  - scripts/cm-usage-report.py
+  - scripts/test-cm-openai-compatible-call.py
+  - scripts/test-cm-usage-report.py
+---
+
+Verdict: changes requested. This is a self-degraded review, not an independent
+review.
+
+Blocking findings:
+
+1. The handoff listed only 13 paths and bound the review to the handoff JSON SHA,
+   not to the implementation bytes. Additional current changes were outside the
+   review scope, and an implementation file could change after review without
+   invalidating N5. Red fixture: `cm-task-gate.py hash-implementation` was an
+   unknown command and an unbound handoff remained eligible for N4/N5.
+2. A bundled `openai-compatible` `model_usage` event could be written without a
+   preceding claim, then counted as verified usage. Red fixture observed one call
+   and 999 input tokens from a claimless managed completion.
+3. The provider could return successfully and log `outcome: success`, after which
+   writing the model result to stdout raised an unhandled `BrokenPipeError`. The
+   process traceback and success usage contradicted each other.
+4. Configuration accepted `reviewer.adapter: openai-compatible`, but N4 recognizes
+   only `codex-subagent`, `codex-cli`, or `self-degraded` review evidence. The API
+   call therefore spent tokens without being able to satisfy the review gate.
+
+Required correction: bind each new handoff to the exact changed-file contents,
+reject claimless managed usage in both writer and reporter, make stdout delivery
+part of the adapter outcome boundary, and reject the unsupported managed reviewer
+route before any call. A complete attempt-2 handoff must cover the entire landing
+scope and rerun all focused and repository gates.

package/workflows/cm/docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-r2.md

@@ -0,0 +1,80 @@
+---
+at: 2026-08-07T01:08:00-07:00
+reviewer: codex-subagent
+independent: true
+task: T-FIX-model-call-boundary-identity
+attempt: 2
+round: 2
+verdict: blocked
+blocking_findings: 1
+handoff: fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a2-handoff.json
+handoff_sha256: 11ca8a55a4f0fd17d2cefbd98281c0f5cfac437709b4ba23c15e35d98c785145
+scope:
+  - .claude/CLAUDE.md
+  - .claude/rules/security.md
+  - .claude/rules/testing.md
+  - README.md
+  - docs/fixes/.reviews/fix-manifest-runtime-checkbox-drift-r2.md
+  - docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-a1-handoff.json
+  - docs/fixes/.reviews/fix-model-call-boundary-identity-T-FIX-model-call-boundary-identity-r1.md
+  - docs/fixes/20260804-manifest-runtime-checkbox-drift.md
+  - docs/fixes/20260806-model-call-boundary-identity.md
+  - docs/fixes/20260807-prelanding-integrity.md
+  - docs/user-guide.md
+  - runtime/logging.md
+  - runtime/model-efficiency.md
+  - runtime/orchestration.md
+  - runtime/review.md
+  - runtime/task-gates.md
+  - runtime/task-handoff.schema.json
+  - runtime/workflow-config.md
+  - runtime/workflow-routing.md
+  - scripts/cm-check-runtime.sh
+  - scripts/cm-log-event.py
+  - scripts/cm-openai-compatible-call.py
+  - scripts/cm-task-gate.py
+  - scripts/cm-usage-report.py
+  - scripts/cm_workflow_config.py
+  - scripts/scan-public-safety.py
+  - scripts/test-cm-openai-compatible-call.py
+  - scripts/test-cm-usage-report.py
+  - scripts/test-task-gate.py
+  - scripts/test-workflow-config.py
+  - scripts/validate-public-repo.py
+  - skills/cm-ai/SKILL.md
+  - skills/cm-ai/references/N3-execute-task.md
+  - skills/cm-ai/references/N4-review.md
+  - skills/cm-ai/references/N5-mark-done.md
+  - skills/cm-fix/SKILL.md
+  - skills/cm-prd/SKILL.md
+  - skills/cm-refactor/SKILL.md
+  - skills/cm-test/SKILL.md
+  - templates/cm-workflow.yml
+---
+
+Verdict: blocked with one blocking finding.
+
+The four round-1 functional defects are fixed: implementation content binding passes,
+claimless managed usage is rejected and not counted, stdout write/flush failures record
+only error outcomes without traceback, and managed reviewer configuration is rejected
+before API dispatch. All focused and repository-level gates passed.
+
+Blocking finding:
+
+- `docs/fixes/20260806-model-call-boundary-identity.md` still names the round-1
+  `changes_requested` file as the authoritative review conclusion instead of identifying
+  it as historical and pointing to this final disposition. In addition, the attempt-2
+  handoff and prior review prose call the 40 content-bound paths “all currently modified
+  or untracked landing paths”, while the a2 handoff and r2 review files themselves are
+  intentionally outside that digest to avoid self-reference. The implementation scope is
+  complete, but the evidence wording is not honest about that boundary.
+
+Required disposition: correct the archive to distinguish historical r1 from final r2,
+describe the 40 paths as the pre-handoff implementation/landing scope, and explicitly
+state that a2/r2 evidence files are excluded from their own content digest. Because the
+archive is content-bound, that correction invalidates this attempt-2 implementation hash.
+The two-round contract forbids silently creating attempt 3; this requires human disposition
+or a separately scoped follow-up fix.
+
+Residual risk: no live third-party provider call was made; full task-diff completeness
+still depends on N3's explicit working-tree comparison.

package/workflows/cm/docs/fixes/.reviews/fix-review-evidence-scope-honesty-T-FIX-review-evidence-scope-honesty-a1-handoff.json

@@ -0,0 +1,35 @@
+{
+  "schema_version": 1,
+  "task_id": "T-FIX-review-evidence-scope-honesty",
+  "attempt": 1,
+  "status": "ready_for_review",
+  "changed_files": [
+    "docs/fixes/20260806-model-call-boundary-identity.md",
+    "docs/fixes/20260807-prelanding-integrity.md"
+  ],
+  "implementation_sha256": "37072fa0aec0fd4faa33724199ccfab845209f3d7d02102a3b59f52c3ec06007",
+  "verification": [
+    {
+      "command": "rg final-disposition and digest-boundary assertions in both archives",
+      "status": "passed",
+      "evidence": "The archives now identify r1 as historical, r2 as final blocked, the 40 pre-handoff paths as content-bound, and a2/r2 evidence as excluded to avoid self-reference."
+    },
+    {
+      "command": "./scripts/cm-check-runtime.sh",
+      "status": "passed",
+      "evidence": "All CM runtime and fixture groups passed for plugin v0.10.4."
+    },
+    {
+      "command": "python3 scripts/validate-public-repo.py && python3 scripts/scan-public-safety.py && git diff --check",
+      "status": "passed",
+      "evidence": "Public repository validation, safety scan and whitespace validation passed."
+    }
+  ],
+  "evidence": [
+    "independent round-2 finding: final disposition and self-referential digest boundary were described inaccurately",
+    "human disposition: open a separately scoped small fix rather than create attempt 3",
+    "the historical a2 handoff and blocked r2 review were not rewritten or disguised"
+  ],
+  "blockers": [],
+  "scope_deviation": []
+}

package/workflows/cm/docs/fixes/.reviews/fix-review-evidence-scope-honesty-T-FIX-review-evidence-scope-honesty-r1.md

@@ -0,0 +1,33 @@
+---
+at: 2026-08-07T01:21:09-07:00
+reviewer: codex-subagent
+independent: true
+task: T-FIX-review-evidence-scope-honesty
+attempt: 1
+round: 1
+verdict: approved
+blocking_findings: 0
+handoff: fix-review-evidence-scope-honesty-T-FIX-review-evidence-scope-honesty-a1-handoff.json
+handoff_sha256: c4eb262bb26c1231c389018b41cbdd5b0a241ab55959b3d9cc2dcdfe6ff2abfc
+scope:
+  - docs/fixes/20260806-model-call-boundary-identity.md
+  - docs/fixes/20260807-prelanding-integrity.md
+---
+
+Zero findings. Verdict: approved.
+
+The independent review confirmed that r1 is identified as historical
+`changes_requested`, r2 remains the original task's final `blocked` disposition,
+and the 40 content-bound paths are accurately limited to the pre-a2-handoff
+implementation and landing scope. The archives explicitly explain that a2/r2
+evidence files cannot participate in their own implementation digest without
+self-reference.
+
+The historical a2 handoff was not rewritten, its SHA-256 still matches the digest
+recorded by the blocked r2 review, and the new follow-up handoff covers exactly the
+two authorized archive files. Its recomputed implementation digest matches the
+handoff. Runtime consistency, public repository validation, safety scan, handoff
+validation and `git diff --check` passed.
+
+Residual non-blocking risk: the historical evidence is currently untracked and has
+no immutable Git baseline; internal handoff/review digest consistency is intact.