@michelj/context-guard 0.4.3 → 0.6.1

package/references/register-template.md

@@ -1,85 +0,0 @@
-# Bad Case Register Template
-
-Use this format for `.codex/context/bad-cases.md`, task-local `.codex/context/tasks/<task-id>/bad-cases.md`, or the existing project context register.
-
-```md
-# Bad Case Register
-
-This register tracks bad cases found during development and the guards that prevent them from recurring.
-
-Record only bad cases that are user-visible, recurring, risky, fixed, deferred, or needed to explain a guard. Do not turn the register into a defect diary.
-
-## Active Cases
-
-### BC-YYYYMMDD-001: Short descriptive title
-
-- Status: open | resolved | recurred | deferred | superseded-by-route-change
-- First observed: YYYY-MM-DD
-- Last checked: YYYY-MM-DD
-- Scope: feature, files, tests, route, UI flow, API, or subsystem
-- Context task: `CTX-...` folder or shared
-- Roadmap nodes: `NODE-...`
-- Tags: #hot | #flaky | #ui | #data-loss | #route-risk | custom tags
-- Frequency: first-seen | repeated-N | high-frequency
-- Phenomenon: one-line user-visible behavior or failing output
-- Trigger / reproduction: shortest command, step, input, environment, or precondition
-- Root cause: confirmed cause, suspected cause, or unknown, one line
-- Fix method: code/test/config/documentation change that fixed it, one line
-- Guard type: script | native-test | manual | browser-screenshot | browser-dom | curl | cli | prompt | log-invariant | fixture | unit | integration | e2e | custom
-- Guard / verification: native test, command, reusable script, manual check, screenshot, log, invariant, or reproduction note, one line
-- Run policy: every-dev-completion | relevant-only | manual | release-only | goal-final | disabled-with-reason | user-defined cadence
-- Artifact policy: cleanup-on-pass | preserve-on-fail | manual-preserve | none
-- Blocker handling: credentials | external-service | permissions | resource-limits | network | destructive-confirmation | user-judgment | none
-- Red condition: exact output, visual state, assertion, or symptom that means this bad case has recurred
-- Green condition: exact evidence that means this bad case is absent
-- Expected failure reason: why the guard should fail for the old symptom, not for a broken test or unrelated environment issue
-- Reusable guard path: project test file, `.codex/context/task-cases/...#phase-name`, `.codex/context/bad-case-tests/...`, or none
-- Covered by task case: TC-YYYYMMDD-short-slug phase/checkpoint, or none
-- Test-chain issue: false-positive | false-negative | wrong-granularity | missing-phase | wrong-assertion | unrealistic-setup | missing-cleanup | unclear-localization | none
-- Guard reuse rule: reuse this recorded guard before creating any new test or script for this case
-- Test chain: ordered checks only when multiple checks are genuinely needed
-- High-frequency note: warning text to show Codex when this pattern repeats often
-- Recurrence analysis: why it came back, if it ever did
-- Route-change note: only when an approved technical route change intentionally changes expected behavior
-- Evidence: links to tests, commands run, PRs, commits, screenshots, or logs
-
-## Resolved History
-
-Move old resolved entries here only if the active section becomes noisy. Keep enough detail to replay the guard.
-```
-
-Use the `### BC-...` section form as the canonical editable source. If a session accidentally records loose bullet blocks such as `- ID: BC-...`, `- Title: ...`, `- Status: ...`, or `- Nodes: ...`, the renderer should still project them, but future edits should normalize them back into formal case sections.
-
-## Status Rules
-
-- `open`: bad case is known and not fixed.
-- `resolved`: fix is implemented and verification passed.
-- `recurred`: bad case came back after resolution; must be analyzed and fixed before completion.
-- `deferred`: intentionally not fixed in the current task; requires reason and owner/next step.
-- `superseded-by-route-change`: old behavior is no longer expected because an approved technical route changed it.
-
-## Context Guard Rules
-
-- Use `.codex/context/` as the project folder for bad-case memory. Do not introduce a separate bad-case folder for new projects.
-- Use the configured `.codex/context/preferences.json` `record_language` for bad-case titles, phenomenon, root cause, fix method, guard summaries, and test-chain notes.
-- Preserve exact commands, paths, code identifiers, logs, API names, and error messages in their original language.
-- Prefer existing recorded context, user-approved commands, native tests, screenshots, logs, or manual checks over newly invented tests.
-- When the user creates or approves a test, default its `Run policy` to `every-dev-completion`; Codex must run it at every development completion unless the user sets another cadence.
-- Only the user can demote an approved test to `relevant-only`, `manual`, `release-only`, `goal-final`, `disabled-with-reason`, or a custom cadence. Record why.
-- After user approval, automate the check when feasible; successful automated checks should clean temporary files, while failed checks should preserve concise diagnostic evidence for Codex to analyze and rerun after fixing.
-- Store reusable user-approved automated tests in `.codex/context/test-hub/registry.json` or approved task-case files; do not auto-register ordinary bad-case guards or roadmap `Test chain:` notes as always-run tests.
-- At development completion, prefer `context_guard.py dev-complete --root <project>` so Test Hub runs the approved always-run set and writes `.codex/context/test-hub/last-run.json`.
-- If an approved automated check is blocked by credentials, external services, permissions, resource limits, network, destructive confirmation, or user-only judgment, record the blocker and ask or warn the user instead of looping.
-- For resolved or recurred cases, `Guard / verification`, `Guard type`, `Red condition`, `Green condition`, and `Expected failure reason` are required.
-- The guard must be red-capable: it should fail if the same user-visible symptom returns.
-- When the bad case is part of a longer workflow, attach it to a human-approved task-case checkpoint instead of creating a separate isolated script. The bad-case entry should say which task case phase covers it.
-- If the test chain itself is wrong, record that as a bad case and classify the test-chain issue. Fix the test-chain design before trusting its result.
-- Do not script every bad case. Store bad-case-specific scripts under `.codex/context/bad-case-tests/` only when the user approved the test design, the script is genuinely reusable, and it does not belong in the native test suite.
-- Name any guard script with the bad case ID so it is easy to find and reuse.
-- Update existing context when expected behavior changes; do not create parallel guards for the same case unless the old one is explicitly obsolete.
-- If a guard is manual-only, list the exact manual check and why that is acceptable for now.
-- Link bad cases to roadmap nodes so Codex can quickly see which mainline decisions created or fixed them.
-- Keep record/display linkage explicit: use `Roadmap nodes:` or `Nodes:` on the bad case, or `Linked bad cases:` on the roadmap node.
-- Add tags and frequency notes when a bad case repeats often; high-frequency cases should stand out during quick scanning.
-- Promote high-frequency cases into fixed pressure checks and rerun them whenever related code, UI, context, or hooks change.
-- Keep entries compact. If the same information appears in a roadmap node, link to it instead of duplicating it.

package/references/task-case-template.md

@@ -1,63 +0,0 @@
-# Task Case Template
-
-Use task cases for realistic multi-step verification. A task case should simulate a full user or agent workflow and log phase-level checkpoints so failures identify the broken step. Test design is human-owned: Codex can draft a proposal, but a durable task case stays `proposed` until the user confirms it.
-
-```md
-# Task Case: short realistic workflow title
-
-- ID: TC-YYYYMMDD-short-slug
-- Status: proposed | approved | active | stable | deferred | obsolete
-- Route/task: `CTX-...` or branch name
-- Scope: feature, service, UI flow, agent workflow, or subsystem
-- Last checked: YYYY-MM-DD
-- Design confirmation: pending | user-approved YYYY-MM-DD
-- Run policy: every-dev-completion | relevant-only | manual | release-only | goal-final | disabled-with-reason | user-defined cadence
-- Automation entry: native command | script path | prompt/manual runner | none
-- Artifact policy: cleanup-on-pass | preserve-on-fail | manual-preserve
-- Linked roadmap nodes: NODE-...
-- Linked bad cases: BC-..., BC-...
-- Entry command/prompt: command, prompt, manual setup, or fixture
-- Not covered: explicit exclusions to avoid fake confidence
-- Stop condition: what means the workflow is complete
-- Cleanup: required cleanup or none
-- Blocker handling: credentials | external service | permissions | resource limits | network | destructive confirmation | user judgment | none
-
-## Phases
-
-### Phase 1: setup or trigger
-
-- Action: one realistic action
-- Expected checkpoint: invariant, log, UI state, file state, API result, or assertion
-- Covers bad cases: BC-...
-- Failure localization: what this phase failure usually means
-- Log note: what the script/agent should record
-
-### Phase 2: transition or recovery
-
-- Action: one realistic action
-- Expected checkpoint: invariant, log, UI state, file state, API result, or assertion
-- Covers bad cases: BC-...
-- Failure localization: what this phase failure usually means
-- Log note: what the script/agent should record
-
-## Result Log
-
-- YYYY-MM-DD: pass/fail, failed phase/checkpoint if any, evidence path or command output summary
-```
-
-Rules:
-
-- When the user explicitly asks to create, write, generate, design, or add a test/task case, begin the user-visible response with a compact intake line such as `测试创建识别：...` before proposing or implementing the case.
-- Prefer one task case with clear checkpoints over many disconnected bug-level scripts when the same workflow is being exercised.
-- Link bad cases to the checkpoint that catches them.
-- Keep the task case realistic enough to match actual product or agent usage.
-- Once a test is approved, automate it when it can be safely encapsulated. Future Codex turns should run the registered entry instead of reinterpreting the test design.
-- Automated approved tests should be registered in `.codex/context/test-hub/registry.json` or represented by this approved task-case file with `Run policy: every-dev-completion` and an executable `Entry command/prompt`.
-- At development completion, run the approved always-run set through `context_guard.py dev-complete --root <project>` instead of manually reconstructing each test.
-- Automated task cases should clean temporary files after full success and preserve the smallest useful evidence on failure.
-- If the automated case fails, Codex should analyze the failed phase/checkpoint, record or update the bad case, fix in scope, and rerun the same approved test until it passes or a non-actionable blocker is reached.
-- If blocked by credentials, unavailable services, permissions, hardware/resource limits, network, destructive-risk confirmation, or user-only judgment, stop and ask or warn the user with the blocker and evidence path.
-- Keep checkpoint logs concise and useful for localizing failure.
-- Keep the case in `proposed` state until the user confirms the design.
-- Once the user confirms the design, default `Run policy` to `every-dev-completion`; lower the cadence only when the user explicitly asks.
-- In goal mode, use human-approved task cases as phase gates and log phase progress; do not create broad new scripts or active task cases without confirmation unless the user explicitly asked for that exact test.

package/tests/BC-20260618-063.sh

@@ -1,116 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-
-python3 - "$SCRIPT" <<'PY'
-from __future__ import annotations
-
-import json
-import shutil
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-
-script = Path(sys.argv[1])
-root = Path(tempfile.mkdtemp(prefix="context-guard-branch-test-"))
-
-try:
-    subprocess.run(["python3", str(script), "init", "--root", str(root)], check=True, capture_output=True, text=True)
-    subprocess.run(["python3", str(script), "set-language", "--language", "zh", "--root", str(root)], check=True, capture_output=True, text=True)
-
-    ctx = root / ".codex" / "context"
-    (ctx / "index.md").write_text(
-        """# Context Index
-
-## Quick Scan
-
-- Current: CTX-20260618-main
-- Latest roadmap node: NODE-20260618-001
-- Hot bad-case tags: none
-- Resume candidate: none
-
-## Current
-
-- ID: CTX-20260618-main
-- Title: 主线任务
-- State: current
-- Folder: `.codex/context/tasks/CTX-20260618-main/`
-- Last updated: 2026-06-18
-- Summary: 正在推进主线任务。
-- Next step: 继续主线。
-
-## Parked / Resume Candidates
-
-None.
-
-## Archived
-
-None.
-""",
-        encoding="utf-8",
-    )
-    (ctx / "roadmap.md").write_text(
-        """# Context Roadmap
-
-## Nodes
-
-### NODE-20260618-001: 主线起点
-
-- Date: 2026-06-18
-- Status: done
-- Level: major
-- Branch: Main
-- Parent: none
-- Task: `CTX-20260618-main`
-- Outcome: 主线已经建立。
-- Decision / reason: 作为支线父节点。
-- Avoid going back: 不要把支线写回主线。
-- Next: 等待支线。
-- Linked bad cases: none
-- Test chain: none
-""",
-        encoding="utf-8",
-    )
-
-    result = subprocess.run(
-        [
-            "python3",
-            str(script),
-            "create-branch-task",
-            "--root",
-            str(root),
-            "--title",
-            "后端状态机设计",
-            "--branch",
-            "后端状态机",
-            "--parent-node",
-            "NODE-20260618-001",
-        ],
-        check=True,
-        capture_output=True,
-        text=True,
-    )
-
-    output = result.stdout + result.stderr
-    assert "CTX-" in output, output
-    assert "NODE-" in output, output
-
-    index = (ctx / "index.md").read_text(encoding="utf-8")
-    roadmap = (ctx / "roadmap.md").read_text(encoding="utf-8")
-    exports = json.loads((ctx / "roadmap" / "roadmap.json").read_text(encoding="utf-8"))
-
-    assert "- Current: CTX-20260618-main" not in index, index
-    assert "后端状态机设计" in index, index
-    assert "主线任务" in index and "resume-candidate" in index, index
-    assert "- Branch: 后端状态机" in roadmap, roadmap
-    assert "- Parent: NODE-20260618-001" in roadmap, roadmap
-    assert "- Task: `CTX-" in roadmap, roadmap
-    assert any(route["branch"] == "后端状态机" for route in exports["routes"]), exports
-
-    task_dirs = list((ctx / "tasks").glob("CTX-*"))
-    assert any((path / "context.md").exists() and "后端状态机设计" in (path / "context.md").read_text(encoding="utf-8") for path in task_dirs), task_dirs
-finally:
-    shutil.rmtree(root, ignore_errors=True)
-PY

package/tests/BC-20260618-065.sh

@@ -1,66 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-marker-test-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-cat > "$CTX/roadmap.md" <<'MD'
-# Context Roadmap
-
-## Nodes
-
-### NODE-20260618-001: 标记测试节点
-
-- Date: 2026-06-18
-- Status: done
-- Level: major
-- Branch: Main
-- Parent: none
-- Task: `CTX-20260618-marker`
-- Outcome: 检查问题案例标题行标记布局。
-- Decision / reason: 标记不能单独占一行。
-- Avoid going back: 不要把状态点放在标题前面。
-- Next: none
-- Linked bad cases: BC-20260618-999
-- Test chain: none
-MD
-
-cat > "$CTX/bad-cases.md" <<'MD'
-# Bad Case Register
-
-## Active Cases
-
-### BC-20260618-999: 这是一个很长的问题案例标题用于触发换行但标记不能单独成行
-
-- Status: resolved
-- First observed: 2026-06-18
-- Last checked: 2026-06-18
-- Scope: roadmap marker layout
-- Context task: `CTX-20260618-marker`
-- Roadmap nodes: NODE-20260618-001
-- Tags: #roadmap-ux
-- Frequency: repeated-2
-- Phenomenon: 状态点和频率点不应该单独一行。
-- Trigger / reproduction: 生成 roadmap 并检查 badcase-head。
-- Root cause: 标记位于标题前，窄列时容易变成单独一行。
-- Fix method: 将标记移到标题右侧的 inline marker 容器。
-- Guard / verification: 本脚本检查 HTML 结构。
-- Reusable guard path: none
-- Test chain: none
-MD
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-HTML="$CTX/roadmap/roadmap.html"
-
-grep -q 'class="badcase-markers"' "$HTML"
-grep -q '.badcase-head { display: grid; grid-template-columns: minmax(0, 1fr) auto;' "$HTML"
-if grep -q '<div class="badcase-head"><span class="status-dot' "$HTML"; then
-  echo "badcase marker still starts a separate title row" >&2
-  exit 1
-fi
-grep -q '<a class="detail-link" href="#case-1">' "$HTML"

package/tests/BC-20260626-080.sh

@@ -1,48 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-readable-map-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-cat > "$CTX/roadmap.md" <<'MD'
-# Context Roadmap
-
-## Nodes
-
-### NODE-20260626-001: 主线起点
-
-- Date: 2026-06-26
-- Status: done
-- Level: major
-- Branch: Main
-- Parent: none
-- Outcome: 这是一段很长的主线摘要，过去会直接显示在多路线概览卡片里，让路线图看起来像卡片墙而不是路线骨架。
-- Next: none
-- Linked bad cases: none
-
-### NODE-20260626-002: 支线入口
-
-- Date: 2026-06-26
-- Status: done
-- Level: major
-- Branch: 可读性支线
-- Parent: NODE-20260626-001
-- Outcome: 这是一段很长的支线摘要，应该留在详情里，而不是占据概览卡片的主要视觉空间。
-- Next: none
-- Linked bad cases: none
-MD
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-HTML="$CTX/roadmap/roadmap.html"
-
-grep -q 'class="route-stack branch-map"' "$HTML"
-grep -q '.track-grid.route-only {' "$HTML"
-grep -q 'grid-auto-columns: minmax(180px, 230px);' "$HTML"
-grep -q '.branch-map .summary {' "$HTML"
-grep -q 'display: none;' "$HTML"
-grep -q -- '-webkit-line-clamp: 3;' "$HTML"

package/tests/BC-20260626-081.sh

@@ -1,40 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-hidden-details-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-cat > "$CTX/roadmap.md" <<'MD'
-# Context Roadmap
-
-## Nodes
-
-### NODE-20260626-001: 可点击路线节点
-
-- Date: 2026-06-26
-- Status: done
-- Level: major
-- Branch: Main
-- Parent: none
-- Outcome: 这个节点的详细概括只能在点击节点后显示，不能默认铺在 roadmap 下方。
-- Next: none
-- Linked bad cases: none
-MD
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-HTML="$CTX/roadmap/roadmap.html"
-
-grep -q '<a class="lane-link" href="#node-1">' "$HTML"
-grep -q '<section class="inline-details" hidden data-inline-details' "$HTML"
-grep -q 'function setupInlineDetails()' "$HTML"
-grep -q 'class="detail-card" id="node-1"' "$HTML"
-
-if grep -q '<section class="inline-details" aria-label="Roadmap details">' "$HTML"; then
-  echo "inline details are visible by default" >&2
-  exit 1
-fi

package/tests/BC-20260626-082.sh

@@ -1,32 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SKILL_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
-SCRIPT="$SKILL_ROOT/scripts/context_guard.py"
-HOOK="$SKILL_ROOT/scripts/context_guard_hook.py"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-root-selection-XXXXXX")"
-ROOT="$(cd "$ROOT" && pwd -P)"
-trap 'rm -rf "$ROOT"' EXIT
-
-mkdir -p "$ROOT/project"
-git -C "$ROOT/project" init --quiet >/dev/null
-
-if (cd "$SKILL_ROOT" && python3 "$SCRIPT" show-roadmap >/tmp/context-guard-implicit-skill-root.out 2>&1); then
-  echo "show-roadmap unexpectedly accepted the skill directory as implicit project root" >&2
-  exit 1
-fi
-grep -q 'refusing to use the Context Guard skill directory' /tmp/context-guard-implicit-skill-root.out
-
-rm -rf "$SKILL_ROOT/.codex"
-printf '{"cwd":"%s/project","prompt":"show roadmap"}' "$ROOT" | (
-  cd "$SKILL_ROOT"
-  python3 "$HOOK" session-start
-) >/tmp/context-guard-hook-root.out
-
-test -f "$ROOT/project/.codex/context/index.md"
-test -f "$ROOT/project/.codex/context/roadmap.md"
-if test -e "$SKILL_ROOT/.codex/context/roadmap.md"; then
-  echo "hook wrote project context into the skill directory" >&2
-  exit 1
-fi
-grep -q "$ROOT/project/.codex/context" /tmp/context-guard-hook-root.out

package/tests/BC-20260626-083.sh

@@ -1,66 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-node-detail-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-cat > "$CTX/roadmap.md" <<'MD'
-# Context Roadmap
-
-## Nodes
-
-### NODE-20260626-001: 加入 Task Case 设计确认和 goal 阶段门控
-
-- Date: 2026-06-26
-- Status: done
-- Level: major
-- Branch: Main
-- Parent: none
-- Task: `CTX-20260626-test-chain`
-- Outcome: Context Guard 要求复杂 Task Case 先给用户确认测试设计；goal 模式下把 Task Case 作为阶段门控。
-- Decision / reason: 用户指出测试 case 应该是任务导向，而不是为每个 bug 造很多零散脚本。
-- Avoid going back: 不要让 agent 静默创建大批未经确认的测试 case。
-- Next: 继续观察 goal 模式下是否按阶段记录测试 checkpoint。
-- Linked bad cases: BC-20260626-999
-- Test chain: 节点详情页应显示用户问题、相关问题案例、采取方法和当前进度。
-MD
-
-cat > "$CTX/bad-cases.md" <<'MD'
-# Bad Case Register
-
-## Active Cases
-
-### BC-20260626-999: 测试链路变成碎片化脚本
-
-- Status: resolved
-- First observed: 2026-06-26
-- Last checked: 2026-06-26
-- Scope: test-chain design
-- Roadmap nodes: NODE-20260626-001
-- Tags: #test-chain #context-bloat
-- Phenomenon: agent 为每个 bug 创建零散脚本，真实任务流反而看不清。
-- Trigger / reproduction: 让 agent 为多个历史 bad case 设计测试。
-- Root cause: 测试链路没有以真实任务为单位组织。
-- Fix method: 引入 task case 草案确认和阶段 checkpoint。
-- Guard / verification: 检查节点详情页的相关问题案例和测试链路说明聚合在节点页面内。
-MD
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-DETAIL="$CTX/roadmap/roadmap-details.html"
-
-grep -q '用户提出的问题' "$DETAIL"
-grep -q '相关问题案例' "$DETAIL"
-grep -q '采取方法' "$DETAIL"
-grep -q '当前进度' "$DETAIL"
-grep -q '测试链路变成碎片化脚本' "$DETAIL"
-grep -q '引入 task case 草案确认和阶段 checkpoint' "$DETAIL"
-
-if grep -q '<h2 data-i18n="badCases">Bad Cases</h2>' "$DETAIL"; then
-  echo "detail page still renders a global bad-case list instead of node-scoped sections" >&2
-  exit 1
-fi

package/tests/BC-20260627-084.sh

@@ -1,74 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-readable-detail-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-cat > "$CTX/roadmap.md" <<'MD'
-# Context Roadmap
-
-### NODE-20260627-001: 重构节点详情阅读页
-- Date: 2026-06-27
-- Status: done
-- Level: major
-- Branch: Main
-- Outcome: Context Guard 现在承认用户截图、日志、复现和已定位根因可作为 red signal；证据足够时应停止补测试并进入实现。
-- Decision / reason: 用户反馈旧详情页像列表堆料，不利于浏览；详情页应该围绕当前节点，而不是全局展开 bad case 列表；按 `；`、`;` 拆成长字段短条目时不能切碎代码片段；采取方法需要短行展示，不能把多个决策塞进一个段落。用户反馈 skill 又陷入测试循环，说明验证预算还不够，需要明确 stop condition。
-- Avoid going back: 不要在节点详情里渲染全局 Bad Cases 长列表；不要把测试命令日志混入当前进度区；不要把采取方法渲染成一整段文字墙。
-- Next: 保持节点详情只呈现当前节点的关键内容。
-- Linked bad cases: BC-20260627-084
-MD
-
-cat > "$CTX/bad-cases.md" <<'MD'
-# Bad Case Register
-
-### BC-20260627-084: 节点详情采取方法像文字墙
-- Status: resolved
-- Roadmap nodes: NODE-20260627-001
-- Tags: #roadmap-ux #readability
-- Phenomenon: 节点详情的采取方法把多个长句拼成一段，用户很难扫读。
-- Fix method: 将采取方法拆成短列表；相关问题案例留在当前节点内；进度区不混入测试命令日志。
-- Guard / verification: 检查详情 HTML 中采取方法和当前进度使用 compact list。
-MD
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-HTML="$CTX/roadmap/roadmap.html"
-DETAIL="$CTX/roadmap/roadmap-details.html"
-
-python3 - "$SCRIPT" <<'PY'
-import importlib.util
-import sys
-
-script = sys.argv[1]
-spec = importlib.util.spec_from_file_location("context_guard_under_test", script)
-module = importlib.util.module_from_spec(spec)
-assert spec.loader
-spec.loader.exec_module(module)
-items = module.split_detail_items("第一条；按 `；`、`;` 拆成长字段短条目时不能切碎代码片段；第三条。")
-assert items == [
-    "第一条",
-    "按 `；`、`;` 拆成长字段短条目时不能切碎代码片段",
-    "第三条",
-], items
-assert module.polish_detail_zh(
-    "后续观察 stop hook 是否能让 Codex 在根因明确后先修复，再做一个最小 post-fix 检查。"
-) == "下一步观察结束钩子能否提醒 Codex：根因明确后先修复，再做一次最小检查。"
-PY
-
-grep -q 'class="detail-list"' "$HTML"
-grep -q 'class="detail-list"' "$DETAIL"
-grep -q '<li>.*不要在节点详情里渲染全局 Bad Cases 长列表' "$DETAIL"
-grep -q '<li>.*将采取方法拆成短列表' "$DETAIL"
-grep -q '用户发现 Context Guard 又把时间耗在反复补测试上，因此需要给验证流程设置明确的停止条件' "$DETAIL"
-grep -q '现在只要有截图、日志、复现步骤或明确根因，就可以确认问题已经成立' "$DETAIL"
-grep -q '证据足够时，先修复问题，再做最小验证' "$DETAIL"
-
-if grep -q '不要在节点详情里渲染全局 Bad Cases 长列表；不要把测试命令日志混入当前进度区；不要把采取方法渲染成一整段文字墙' "$DETAIL"; then
-  echo "method detail is still rendered as one paragraph wall" >&2
-  exit 1
-fi

package/tests/BC-20260630-086.sh

@@ -1,50 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT="${1:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts/context_guard.py}"
-ROOT="$(mktemp -d "${TMPDIR:-/tmp}/context-guard-user-request-XXXXXX")"
-trap 'rm -rf "$ROOT"' EXIT
-
-python3 "$SCRIPT" init --root "$ROOT" >/dev/null
-python3 "$SCRIPT" set-language --language zh --root "$ROOT" >/dev/null
-
-CTX="$ROOT/.codex/context"
-python3 "$SCRIPT" checkpoint-roadmap-node \
-  --root "$ROOT" \
-  --title "改善节点详情可读性" \
-  --branch "Main" \
-  --level major \
-  --user-request "用户希望节点详情里的问题摘要直接来自用户输入，不要由 Codex 自由发挥。" \
-  --outcome "节点详情页现在优先展示 User request 字段。" \
-  --decision "这是内部实现决策，不应该冒充用户提出的问题。" \
-  --next-step "继续保持用户问题摘要和实现复盘分离。" >/dev/null
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-DETAIL="$CTX/roadmap/roadmap-details.html"
-
-grep -q -- "- User request: 用户希望节点详情里的问题摘要直接来自用户输入" "$CTX/roadmap.md"
-grep -q "用户希望节点详情里的问题摘要直接来自用户输入，不要由 Codex 自由发挥" "$DETAIL"
-
-python3 - "$DETAIL" <<'PY'
-from pathlib import Path
-import re
-import sys
-
-html = Path(sys.argv[1]).read_text(encoding="utf-8")
-match = re.search(r'<h4>.*?用户提出的问题.*?</h4>\s*<div>(?P<body>.*?)</div>', html, re.S)
-assert match, "user-question section should render"
-body = match.group("body")
-assert "用户希望节点详情里的问题摘要直接来自用户输入" in body
-assert "内部实现决策" not in body
-assert "Outcome" not in body
-PY
-
-python3 "$SCRIPT" checkpoint-roadmap-node \
-  --root "$ROOT" \
-  --title "历史节点没有用户请求字段" \
-  --branch "Main" \
-  --level major \
-  --outcome "历史节点没有 User request 字段。" >/dev/null
-
-python3 "$SCRIPT" show-roadmap --root "$ROOT" >/dev/null
-grep -q "这个历史节点没有记录用户原始请求" "$DETAIL"