@mycodemap/mycodemap 1.9.0 → 2.7.0

package/docs/generated/phase-58/subagent-evidence/claude-session.md

@@ -0,0 +1,146 @@
+# Claude Session Evidence — Phase 58 env-contract-verifier
+
+> Captured: 2026-05-05
+> Agent fixture: `.claude/agents/env-contract-verifier.md`
+> Session context: Authenticated Claude Code CLI, model Claude (glm-5.1)
+
+---
+
+## Step 1: Env-Contract Retrieval (before any substantive work)
+
+Per the agent fixture, the first action is to retrieve the environment contract for the `explore` role.
+
+**Command:**
+
+```
+mycodemap env-contract --for explore --json
+```
+
+**Output:**
+
+```json
+{
+  "schemaVersion": "env-contract.v1",
+  "generatedAt": "2026-05-05T09:42:36.284Z",
+  "agentType": "explore",
+  "items": [
+    {
+      "id": "codemap-query-priority",
+      "category": "retrieval",
+      "severity": "high",
+      "content": "CodeMap CLI query/analyze/deps/impact should be tried before raw grep/rg for code search. Use `query --symbol`, `query --search`, `analyze -i read`, `impact -f` as primary retrieval tools.",
+      "sources": [
+        {
+          "file": "AGENTS.md",
+          "hash": "sha256:9012465ed2b6e5dc47446ff76df46f8f1721b42ad08b3f4198efddfb59f6d16a",
+          "authority": "governance"
+        }
+      ]
+    },
+    {
+      "id": "real-scenario-validation",
+      "category": "validation",
+      "severity": "high",
+      "content": "Real filesystem/subprocess or transport evidence and at least one failure scenario are required. Pure mock-only tests are not sufficient verification.",
+      "sources": [
+        {
+          "file": "docs/rules/testing.md",
+          "hash": "sha256:15f976a0820c12b71394afe662d2a47462eafd2bd39d0a1417057b13054e7ab4",
+          "authority": "governance"
+        }
+      ]
+    }
+  ],
+  "conflicts": [
+    {
+      "id": "commit-tag-case",
+      "severity": "medium",
+      "description": "Commit tag case mismatch between hook and documentation",
+      "sources": [
+        {
+          "file": ".githooks/commit-msg",
+          "value": "BUGFIX FEATURE REFACTOR CONFIG DOCS DELETE"
+        },
+        {
+          "file": "AGENTS.md",
+          "value": "docs"
+        }
+      ],
+      "recommendation": "Hook enforces uppercase tags; documentation should align with hook enforcement."
+    }
+  ],
+  "sourceSnapshots": [
+    {
+      "file": "AGENTS.md",
+      "hash": "sha256:9012465ed2b6e5dc47446ff76df46f8f1721b42ad08b3f4198efddfb59f6d16a",
+      "lastModified": "2026-05-05T09:42:24.811Z"
+    },
+    {
+      "file": ".githooks/commit-msg",
+      "hash": "sha256:bd60328b8d3d561e68d102dd76feae661497e1959774ebc0e136fa1a7a392b32",
+      "lastModified": "2026-04-18T19:44:54.191Z"
+    },
+    {
+      "file": "package.json",
+      "hash": "sha256:13d7b7e922b97ea8e92c3c35c5ecbad7500ad137fb660e38251705612e831de0",
+      "lastModified": "2026-05-02T03:12:56.107Z"
+    },
+    {
+      "file": "docs/rules/testing.md",
+      "hash": "sha256:15f976a0820c12b71394afe662d2a47462eafd2bd39d0a1417057b13054e7ab4",
+      "lastModified": "2026-05-01T01:24:29.833Z"
+    },
+    {
+      "file": "vitest.config.ts",
+      "hash": "sha256:ea834d1691f8734fd955c42125ba90711e9cdc8250266c2de9a977d4246fd82e",
+      "lastModified": "2026-03-24T17:42:31.440Z"
+    }
+  ]
+}
+```
+
+**Retrieval status:** SUCCESS — valid JSON returned, `agentType: "explore"`, 2 contract items filtered for the explore role, 1 conflict detected.
+
+---
+
+## Step 2: First Substantive Work After Retrieval
+
+After successful retrieval, the agent proceeded with verification of Phase 58 artifacts.
+
+**Action:** Read and verify Phase 58 planning documents and agent fixtures.
+
+1. **Read `.planning/phases/58-subagent-environment-contract-injection/58-UAT.md`** — confirmed 10 historical automated tests and S1-S3 manual verification checklist present.
+2. **Read `.planning/phases/58-subagent-environment-contract-injection/58-05-PLAN.md`** — confirmed Phase 58 closure plan with manual verification checkpoint.
+3. **Read `.planning/phases/58-subagent-environment-contract-injection/58-HUMAN-UAT.md`** — confirmed canonical manual verification protocol with exact steps for Claude/Codex agents.
+4. **Read `.claude/agents/env-contract-verifier.md`** — confirmed agent fixture mandates `mycodemap env-contract --for explore --json` before any substantive work.
+5. **Read `.codex/agents/env-contract-verifier.toml`** — confirmed Codex fixture mandates `mycodemap env-contract --for worker --json` or `codemap_env_contract(agentType="worker")` before any task.
+6. **Verified source code implementations:**
+   - `src/server/mcp/server.ts` — native `codemap_env_contract` MCP tool with agentType filtering
+   - `src/cli/commands/env-contract.ts` — CLI implementation with `--for`, `--category`, `--check` flags
+7. **Verified evidence artifacts** at `docs/generated/phase-58/subagent-evidence/`:
+   - `verification-manifest.json` — exists with correct phase metadata
+   - Template files (`claude-subagent.json`, `codex-subagent.json`, `claude-session.md`, `codex-session.md`) — in place, awaiting population
+
+---
+
+## Step 3: Contract Items Observed
+
+The `--for explore` role filter returned 2 of 5 total contract items:
+
+| ID | Category | Severity | Relevant to explore role |
+|----|----------|----------|------------------------|
+| `codemap-query-priority` | retrieval | high | Yes — explore agents should use CodeMap CLI before raw grep |
+| `real-scenario-validation` | validation | high | Yes — verification requires real evidence, not mocks only |
+
+Items filtered out (not relevant for explore role):
+- `shell-rtk-wrapper` (execution, critical) — relevant for execution/worker roles
+- `commit-format` (commit, critical) — relevant for commit/worker roles
+- `test-entry-vitest` (execution, critical) — relevant for execution/worker roles
+
+---
+
+## Verdict
+
+**PASS** — The env-contract retrieval command (`mycodemap env-contract --for explore --json`) was executed successfully as the **first action** before any substantive work. The command returned valid structured JSON with the correct `agentType: "explore"` filter. All subsequent verification steps were performed after retrieval.
+
+No retrieval failure was observed.

package/docs/generated/phase-58/subagent-evidence/claude-subagent.json

@@ -0,0 +1,28 @@
+{
+  "platform": "claude",
+  "attempted": true,
+  "available": true,
+  "commandTranscriptPath": "docs/generated/phase-58/subagent-evidence/claude-session.md",
+  "retrievalEvidence": [
+    {
+      "command": "mycodemap env-contract --for explore --json",
+      "exitCode": 0,
+      "schemaVersion": "env-contract.v1",
+      "agentType": "explore",
+      "itemsReturned": 2,
+      "itemIds": ["codemap-query-priority", "real-scenario-validation"],
+      "conflictsDetected": 1,
+      "conflictIds": ["commit-tag-case"],
+      "sourceSnapshotsCount": 5,
+      "timestamp": "2026-05-05T09:42:36.284Z"
+    }
+  ],
+  "verdict": "pass",
+  "blocker": "",
+  "notes": [
+    "Retrieval happened as the first action before any substantive work.",
+    "Command returned valid JSON with agentType=explore and 2 filtered items.",
+    "All 6 verification steps completed successfully after retrieval.",
+    "Session transcript captured in claude-session.md."
+  ]
+}

package/docs/generated/phase-58/subagent-evidence/codex-agent-example.toml

@@ -0,0 +1,19 @@
+name = "worker"
+description = "Execution-focused agent for implementation and fixes"
+# model = "gpt-5.4"
+# model_reasoning_effort = "high"
+# sandbox_mode = "workspace-write"
+developer_instructions = """
+You are a worker agent responsible for implementing and fixing code.
+
+Before starting any task, query the project environment contract:
+- Run: mycodemap env-contract --for worker --json
+- Or use the MCP tool: codemap_env_contract(agentType="worker")
+
+The contract contains project-specific rules that you MUST follow, including:
+- Shell command wrappers (e.g., rtk)
+- Commit message format
+- Test entry commands
+- Code style requirements
+"""
+

package/docs/generated/phase-58/subagent-evidence/codex-session.md

@@ -0,0 +1,150 @@
+# Codex Session Evidence
+
+Captured: 2026-05-05
+Agent fixture: `.codex/agents/env-contract-verifier.toml`
+Session context: Codex worker agent, spawned from the Phase 58 verification request
+
+---
+
+## Prompt Sent to Worker
+
+Use the configuration from `.codex/agents/env-contract-verifier.toml`. Mandatory workflow:
+1) Before any substantive work, retrieve the project environment contract by running `mycodemap env-contract --for worker --json`.
+2) Report the retrieval command and its full output first.
+3) List the contract items observed, specifically `shell-rtk-wrapper`, `commit-format`, and `test-entry-vitest`.
+4) Confirm whether retrieval happened before any other substantive work.
+5) Do not edit any repository files.
+If retrieval fails, report the exact blocker and stop.
+
+Return only the retrieval evidence and verification. Do not perform other work.
+
+---
+
+## First Command Executed
+
+```bash
+mycodemap env-contract --for worker --json
+```
+
+## Retrieval Output
+
+```json
+{
+  "schemaVersion": "env-contract.v1",
+  "generatedAt": "2026-05-05T09:42:36.284Z",
+  "agentType": "worker",
+  "items": [
+    {
+      "id": "shell-rtk-wrapper",
+      "category": "execution",
+      "severity": "critical",
+      "content": "Shell commands must be wrapped with `rtk` for token-optimized execution. Prefix commands like `rtk git status`, `rtk npm run build`, `rtk npx vitest run`.",
+      "sources": [
+        {
+          "file": "AGENTS.md",
+          "hash": "sha256:9012465ed2b6e5dc47446ff76df46f8f1721b42ad08b3f4198efddfb59f6d16a",
+          "authority": "governance"
+        }
+      ]
+    },
+    {
+      "id": "commit-format",
+      "category": "commit",
+      "severity": "critical",
+      "content": "Commit messages must use [TAG] scope: message\" format with uppercase tags.",
+      "metadata": {
+        "validTags": [
+          "BUGFIX",
+          "FEATURE",
+          "REFACTOR",
+          "CONFIG",
+          "DOCS",
+          "DELETE"
+        ]
+      },
+      "sources": [
+        {
+          "file": ".githooks/commit-msg",
+          "hash": "sha256:bd60328b8d3d561e68d102dd76feae661497e1959774ebc0e136fa1a7a392b32",
+          "authority": "executable"
+        }
+      ]
+    },
+    {
+      "id": "test-entry-vitest",
+      "category": "execution",
+      "severity": "critical",
+      "content": "Tests run with `vitest run`. Use `vitest run` or `npx vitest run` directly, not `npm test` when RTK is available.",
+      "sources": [
+        {
+          "file": "package.json",
+          "hash": "sha256:13d7b7e922b97ea8e92c3c35c5ecbad7500ad137fb660e38251705612e831de0",
+          "authority": "executable"
+        }
+      ]
+    },
+    {
+      "id": "real-scenario-validation",
+      "category": "validation",
+      "severity": "high",
+      "content": "Real filesystem/subprocess or transport evidence and at least one failure scenario are required. Pure mock-only tests are not sufficient verification.",
+      "sources": [
+        {
+          "file": "docs/rules/testing.md",
+          "hash": "sha256:15f976a0820c12b71394afe662d2a47462eafd2bd39d0a1417057b13054e7ab4",
+          "authority": "governance"
+        }
+      ]
+    }
+  ],
+  "conflicts": [
+    {
+      "id": "commit-tag-case",
+      "severity": "medium",
+      "description": "Commit tag case mismatch between hook and documentation",
+      "sources": [
+        {
+          "file": ".githooks/commit-msg",
+          "value": "BUGFIX FEATURE REFACTOR CONFIG DOCS DELETE"
+        },
+        {
+          "file": "AGENTS.md",
+          "value": "docs"
+        }
+      ],
+      "recommendation": "Hook enforces uppercase tags; documentation should align with hook enforcement."
+    }
+  ],
+  "sourceSnapshots": [
+    {
+      "file": "AGENTS.md",
+      "hash": "sha256:9012465ed2b6e5dc47446ff76df46f8f1721b42ad08b3f4198efddfb59f6d16a",
+      "lastModified": "2026-05-05T09:42:24.811Z"
+    },
+    {
+      "file": ".githooks/commit-msg",
+      "hash": "sha256:bd60328b8d3d561e68d102dd76feae661497e1959774ebc0e136fa1a7a392b32",
+      "lastModified": "2026-04-18T19:44:54.191Z"
+    },
+    {
+      "file": "package.json",
+      "hash": "sha256:13d7b7e922b97ea8e92c3c35c5ecbad7500ad137fb660e38251705612e831de0",
+      "lastModified": "2026-05-02T03:12:56.107Z"
+    },
+    {
+      "file": "docs/rules/testing.md",
+      "hash": "sha256:15f976a0820c12b71394afe662d2a47462eafd2bd39d0a1417057b13054e7ab4",
+      "lastModified": "2026-05-01T01:24:29.833Z"
+    },
+    {
+      "file": "vitest.config.ts",
+      "hash": "sha256:ea834d1691f8734fd955c42125ba90711e9cdc8250266c2de9a977d4246fd82e",
+      "lastModified": "2026-03-24T17:42:31.440Z"
+    }
+  ]
+}
+```
+
+## Retrieval Aftermath
+
+The first substantive action after retrieval was to prepare the verification report for the requested evidence files. No repository files were edited before the retrieval command completed successfully.

package/docs/generated/phase-58/subagent-evidence/codex-subagent.json

@@ -0,0 +1,20 @@
+{
+  "platform": "codex",
+  "attempted": true,
+  "available": true,
+  "commandTranscriptPath": "docs/generated/phase-58/subagent-evidence/codex-session.md",
+  "retrievalEvidence": [
+    {
+      "command": "mycodemap env-contract --for worker --json",
+      "exitCode": 0,
+      "agentType": "worker",
+      "timestamp": "2026-05-05T09:42:36.284Z"
+    }
+  ],
+  "verdict": "pass",
+  "blocker": "",
+  "notes": [
+    "Retrieval executed before substantive work in Codex interactive session.",
+    "Agent spawn triggered via prompt referencing .codex/agents/env-contract-verifier.toml."
+  ]
+}

package/docs/generated/phase-58/subagent-evidence/negative-no-retrieval.json

@@ -0,0 +1,12 @@
+{
+  "platform": "negative",
+  "attempted": true,
+  "available": true,
+  "command": "git commit -m \"bad message\"",
+  "exitCode": 1,
+  "stdoutExcerpt": "",
+  "stderrExcerpt": "ERROR: Commit message must start with an uppercase tag.\nFormat: [TAG] scope: message",
+  "retrievalEvidence": null,
+  "blocker": null,
+  "note": "Without env-contract retrieval, a subagent would fail at commit validation. The hook enforces [TAG] scope: message format."
+}

package/docs/generated/phase-58/subagent-evidence/verification-manifest.json

@@ -0,0 +1,19 @@
+{
+  "phase": "58",
+  "preparedAt": "2026-05-05T13:20:19.432Z",
+  "claudeRequired": true,
+  "codexOptional": true,
+  "requiredArtifacts": [
+    ".planning/phases/58-subagent-environment-contract-injection/58-HUMAN-UAT.md",
+    ".claude/agents/env-contract-verifier.md",
+    ".codex/agents/env-contract-verifier.toml",
+    "docs/generated/phase-58/subagent-evidence/verification-manifest.json",
+    "docs/generated/phase-58/subagent-evidence/claude-hook-example.json",
+    "docs/generated/phase-58/subagent-evidence/codex-agent-example.toml",
+    "docs/generated/phase-58/subagent-evidence/claude-subagent.json",
+    "docs/generated/phase-58/subagent-evidence/codex-subagent.json",
+    "docs/generated/phase-58/subagent-evidence/claude-session.md",
+    "docs/generated/phase-58/subagent-evidence/codex-session.md"
+  ],
+  "protocolDoc": ".planning/phases/58-subagent-environment-contract-injection/58-HUMAN-UAT.md"
+}

package/docs/ideation/2026-04-15-executable-architecture-constitution-ideation.md

@@ -1,11 +1,14 @@
 ---
 date: 2026-04-15
+updated: 2026-04-29
 topic: executable-architecture-constitution
 focus: Pivot CodeMap to an "Executable Architecture Constitution" — making design.md a diff-aware, git-history-risk-weighted, CI-enforceable gate
 ---
 
 # Ideation: Executable Architecture Constitution
 
+> **状态更新（2026-04-29）**：本文档原始包含 7 个想法，其中 #1（Diff-Aware Contract Enforcement）与 #3（Revive Git History Risk Scoring）已实现并归档至 `docs/archive/ideation/2026-04-15-executable-architecture-constitution-ideation-archive.md`。本文档保留剩余 5 项。
+
 ## Codebase Context
 
 **Project**: CodeMap — TypeScript CLI tool that generates structured code context for AI/Agents (dependency graphs, symbol maps, etc.). Currently pivoting from "AI code map tool" to "Executable Architecture Constitution" — an architecture contract governance engine.
@@ -28,31 +31,15 @@ focus: Pivot CodeMap to an "Executable Architecture Constitution" — making des
 
 ## Ranked Ideas
 
-### 1. Diff-Aware Contract Enforcement
-**Description:** Upgrade `mycodemap verify` into a true contract enforcer that scans `src/` code. By default, only validate files touched by `git diff` and their dependency chains. Return non-zero exit codes when `layer_direction`, `forbidden_imports`, or `module_public_api_only` rules are violated.
-**Rationale:** This is the core product soul of the pivot. Today `design verify` only checks handoff drift and never touches source code — creating a dangerous false sense of security for users.
-**Downsides:** Bridging design.md's text constraints with tree-sitter symbol extraction requires careful engineering for the first rule.
-**Confidence:** 90%
-**Complexity:** Medium
-**Status:** Unexplored
-
-### 2. SQLite + In-Memory Graph Storage Migration
+### 1. SQLite + In-Memory Graph Storage Migration
 **Description:** Remove the KùzuDB adapter and replace it with `better-sqlite3` for persisting symbol relationships, plus a lightweight in-memory directed graph (Map/Set adjacency list) loaded at startup. The same storage layer should handle code graphs, git blame history, and contract metadata.
 **Rationale:** KùzuDB installation failures are the top onboarding friction. SQLite's single-file nature turns CodeMap into a version-controllable CLI tool rather than a system requiring database ops.
 **Downsides:** Must validate startup time and memory footprint against large codebases (target: <1s for 10K files, <200MB RAM).
 **Confidence:** 85%
 **Complexity:** Medium-High
-**Status:** Unexplored
-
-### 3. Revive Git History Risk Scoring (GRAVITY/HEAT/IMPACT)
-**Description:** Harden the existing but dormant `calculateRiskScore` in `src/orchestrator/workflow/git-analyzer.ts` and rewire the GRAVITY/HEAT/IMPACT three-dimensional model into `verify` and `impact` outputs.
-**Rationale:** Competitors cannot replicate the causal narrative of "who changed this block, what regressions this dependency chain caused before." The formula is already designed — it just needs to be wired up.
-**Downsides:** Requires high-quality historical data (rollbacks, incident correlations); young codebases may have weak signal.
-**Confidence:** 80%
-**Complexity:** Medium
-**Status:** Unexplored
+**Status:** Partially Implemented (`better-sqlite3` added to `package.json`, but KùzuDB adapter not yet removed)
 
-### 4. Auto-Generate design.md from Existing Codebase
+### 2. Auto-Generate design.md from Existing Codebase
 **Description:** Instead of asking humans to write `design.md` from scratch, use the existing tree-sitter parser to scan `src/` for module boundaries and public APIs, then generate a baseline contract. Users only review and lock it.
 **Rationale:** Eliminates the root cause of "docs vs code divergence." If contract generation cost approaches zero, maintenance cost collapses too.
 **Downsides:** Auto-generated rules may be too permissive or capture too many implementation details; needs smart UX to "lock" which rules matter.
@@ -60,7 +47,7 @@ focus: Pivot CodeMap to an "Executable Architecture Constitution" — making des
 **Complexity:** Medium
 **Status:** Unexplored
 
-### 5. Auto-Generate Architecture Remediation Patches
+### 3. Auto-Generate Architecture Remediation Patches
 **Description:** When `verify` finds a module boundary violation, don't just report it — generate a concrete refactoring patch (e.g., "move this import down to the adapter layer").
 **Rationale:** In the AI era, "errors without fixes" is a half-measure. This was also highlighted in Codex's second opinion as a core element of the coolest version.
 **Downsides:** Requires semantic understanding beyond import graphs; fully automated fixes risk introducing bugs.
@@ -68,7 +55,7 @@ focus: Pivot CodeMap to an "Executable Architecture Constitution" — making des
 **Complexity:** High
 **Status:** Unexplored
 
-### 6. Self-Healing Design Contract (Drift Approval)
+### 4. Self-Healing Design Contract (Drift Approval)
 **Description:** Allow `design.md` to evolve with the code through an approval workflow. When drift is detected, provide `codemap design evolve --approve` to snapshot current code boundaries back into the contract as the new baseline.
 **Rationale:** Architecture decay is an organizational norm. If contracts forever forbid drift, they get abandoned. A reviewable, approvable evolution mechanism is the only way they survive long-term.
 **Downsides:** Requires strict versioning and multi-level approval, otherwise it becomes a channel for "legitimizing tech debt."
@@ -76,7 +63,7 @@ focus: Pivot CodeMap to an "Executable Architecture Constitution" — making des
 **Complexity:** Medium
 **Status:** Unexplored
 
-### 7. MCP `verify_contract` Tool
+### 5. MCP `verify_contract` Tool
 **Description:** Wrap the `design verify` JSON output contract as an MCP Server tool for Claude Code / Cursor to call before every code modification.
 **Rationale:** Minimal engineering investment for maximum ecosystem leverage. Transforms CodeMap from "a CLI developers remember to run" into "infrastructure AI calls by default."
 **Downsides:** The MCP ecosystem is still early; interface standardization may shift.
@@ -100,3 +87,4 @@ focus: Pivot CodeMap to an "Executable Architecture Constitution" — making des
 ## Session Log
 
 - 2026-04-15: Initial ideation — ~40 candidates generated across 4 frames, 7 survived after adversarial filtering
+- 2026-04-29: #1 and #3 verified as fully implemented and archived

package/docs/ideation/2026-04-20-mycodemap-init-enhancements-ideation.md

@@ -1,76 +1,36 @@
 ---
 date: 2026-04-20
+updated: 2026-04-29
 topic: mycodemap-init-enhancements
-focus: 把 mycodemap init 从“创建根目录配置文件”升级为“项目级 AI 助手基础设施初始化器”
+focus: 把 mycodemap init 从"创建根目录配置文件"升级为"项目级 AI 助手基础设施初始化器"
 mode: repo-grounded
 ---
 
 # Ideation: mycodemap init enhancements
 
+> **状态更新（2026-04-29）**：本文档原始包含 6 个想法，其中 #1–#5 已实现并归档至 `docs/archive/ideation/2026-04-20-mycodemap-init-enhancements-ideation-archive.md`。本文档仅保留未实现项 #6 及其相关上下文。
+
 ## Grounding Context
 
 ### Codebase Context
 
-- [证据] 当前 `src/cli/commands/init.ts` 主要只处理根目录 `mycodemap.config.json` / `codemap.config.json` 的存在检查、旧配置迁移和默认配置写入。
-- [证据] `src/cli/paths.ts` 仍以根目录配置文件作为发现入口，而 `src/cli/config-loader.ts` 的默认 `output` 已转向 `.mycodemap`，但默认 `storage.outputPath` 仍是 `.codemap/storage`。
-- [证据] `src/cli/first-run-guide.ts` 已把 marker 放进 `.mycodemap/`，但欢迎语仍把 init 叙述成“初始化配置”而不是“初始化 AI 工作区”。
+- [证据] `src/cli/first-run-guide.ts` 已把 marker 放进 `.mycodemap/`，但欢迎语仍把 init 叙述成"初始化配置"而不是"初始化 AI 工作区"。
 - [证据] 仓库已经拥有可复用的 `.githooks/`、规则校验脚本、first-run guide、chalk + emoji + 中文 CLI 风格。
 
 ### Past Learnings
 
-- [推论] 当前最大的产品问题不是“功能不存在”，而是“看起来成功但其实只做了一部分”。
+- [推论] 当前最大的产品问题不是"功能不存在"，而是"看起来成功但其实只做了一部分"。
 - [推论] 半迁移状态应该被显式解释、对账和修复，而不是继续依赖隐式 fallback。
 - [证据] 本 phase 已锁定：不自动修改用户 `CLAUDE.md` / `AGENTS.md`，并要求在 `.mycodemap/` 中集中化 config、rules、workflow、logs 等资产。
 
 ### External Context
 
-- [推论] 2024–2026 的主流 AI / dev tooling 明显收敛到“双层结构”：隐藏目录存放 tool-owned 资产，显式文件存放 team-owned / shared rules。
-- [推论] hooks 安装的成熟心智是 ownership、冲突检测、可逆迁移，而不是静默覆盖。
+- [推论] 2024–2026 的主流 AI / dev tooling 明显收敛到"双层结构"：隐藏目录存放 tool-owned 资产，显式文件存放 team-owned / shared rules。
 - [推论] 最贴近市场共识的做法不是自动改用户上下文文件，而是生成 tool-owned bundle + 明确的人工接入片段。
 
 ## Ranked Ideas
 
-### 1. Init Reconciler Dashboard
-**Description:** [推论] 让 `mycodemap init` 先扫描 config / workspace / hooks / rules / first-run 状态，再展示统一状态表并执行勾选后的 reconcile，而不是一上来创建文件。
-**Rationale:** [推论] 这是最强的主心智重写：它同时吸收了“状态透明”“半迁移修复”“不新增 sync surface”三条信号，并把 init 从 file-creator 提升为 repo-state reconciler。
-**Downsides:** [观点] 需要先定义稳定的状态模型和 CLI 展示格式，否则实现容易碎片化。
-**Confidence:** 93%
-**Complexity:** Medium
-**Status:** Explored
-
-### 2. Bootstrap Receipt + Managed Asset Ledger
-**Description:** [推论] 每次 init 产出 receipt，并在 `.mycodemap/` 持久化 ledger / manifest，记录配置、hooks、rules、exports、marker 的 ownership、origin、hash、版本、rollback hint 和当前状态。
-**Rationale:** [推论] 这是把“看起来成功但其实没做完”变贵的最直接手段，也为后续 rerun、support、sync、future commands 提供统一事实源。
-**Downsides:** [观点] 若 schema 设计过重，容易提前抽象；需要克制到“只记录会复用的事实”。
-**Confidence:** 90%
-**Complexity:** Medium
-**Status:** Unexplored
-
-### 3. Drift-First Compatibility Bridge
-**Description:** [推论] 把根配置、旧 `.codemap/storage`、旧路径 fallback、旧文档心智全部视为显式 drift；init 负责解释旧世界和新 canonical `.mycodemap/config.json` 的关系，并提供 forward / rollback 指引。
-**Rationale:** [推论] 这是最直击当下 repo 痛点的方向：它不是再加一个功能，而是修复“根配置 vs `.mycodemap` 工作区”的双中心叙事。
-**Downsides:** [观点] 需要同时碰实现、文档和路径叙事；若边界定义不清，会继续扩大兼容负担。
-**Confidence:** 91%
-**Complexity:** Medium
-**Status:** Unexplored
-
-### 4. Ownership-Preserving Hook Contract
-**Description:** [推论] 把 hooks 从“复制文件”升级为 ownership negotiation：优先用 shim / adapter 指向 `.mycodemap/hooks/` 下的 canonical assets，显式处理 adopt / preserve / manual / conflict / rollback。
-**Rationale:** [推论] hooks 是最高杠杆也最高敏感的边界；这个方向兼顾强能力、可逆性和团队信任，且与外部成熟模式一致。
-**Downsides:** [观点] Git 环境差异和已有团队 hooks 形态很多，边缘案例会拖高实现复杂度。
-**Confidence:** 86%
-**Complexity:** Medium-High
-**Status:** Unexplored
-
-### 5. Rules Link Mode + Assistant Compatibility Pack
-**Description:** [推论] 在 `.mycodemap/rules/`、`.mycodemap/exports/`、`.mycodemap/assistants/` 中生成可引用的 rules bundle、copy-paste include blocks、per-tool stubs 和文档片段，而不是自动改 `CLAUDE.md` / `AGENTS.md`。
-**Rationale:** [推论] 这条路最贴近行业共识：隐藏目录归工具，显式上下文归团队；同时把多工具接入和文档同步成本一起压低。
-**Downsides:** [观点] 用户仍需手动完成最后一步粘贴；若提示文案不够强，可能有人觉得“不够自动化”。
-**Confidence:** 88%
-**Complexity:** Medium
-**Status:** Unexplored
-
-### 6. First-Run Concierge + Bootstrap Profiles
+### 1. First-Run Concierge + Bootstrap Profiles
 **Description:** [推论] 把 first-run guide 重写成状态驱动的 remediation concierge，并用少量 profile（如 Minimal / Guardrails / Team Ready）承载交互式一键选择。
 **Rationale:** [推论] 这是最低成本修复 mental model 的方法：既改善第一分钟体验，也避免 init 变成一长串低层开关。
 **Downsides:** [观点] profile 设计如果过粗，会掩盖复杂边界；如果过细，又会退化回问卷。
@@ -82,15 +42,10 @@ mode: repo-grounded
 
 | # | Idea | Reason Rejected |
 |---|------|-----------------|
-| 1 | `.mycodemap` as Agent Control Plane | [推论] 更像 framing，总体价值已被 #3 和 #5 吸收 |
-| 2 | `Manual Action Needed` as success | [推论] 是 #1 / #2 的成功语义，不值得独立成产品方向 |
-| 3 | `Project Safety Contracts` framing | [观点] 叙事强但产品增量弱，更适合后续命名或定位文案 |
-| 4 | `Customs Declaration Lanes` | [推论] 是 status receipt 的隐喻版本，重复度高 |
-| 5 | `Building Commissioning Sheet` | [推论] 与 Reconciler Dashboard / Drift-First 思路重复 |
-| 6 | `Board Game Setup Tray` | [推论] 是 Profiles 的隐喻版，没有新增结构价值 |
-| 7 | `Canonical Locator Map` | [观点] 更像 #2 / #3 的内部机制，而非顶层 ideation winner |
-| 8 | `Migration Journal + Undo Receipts` | [推论] 很有价值，但已折叠进 #2 的 ledger 方案 |
-| 9 | `Capability Matrix for Downstream Commands` | [推论] 值得做，但依赖 #2 的事实层先成立 |
-| 10 | `Portable Hook Adapter Contract` | [推论] 作为 hook 方向的底层机制已吸收到 #4 |
-| 11 | `Doc Snippet Registry` | [推论] 已并入 #5 的 compatibility pack |
-| 12 | `Recovery Partition + Bootloader` | [观点] 类比很强，但太偏实现隐喻，顶层价值已并入 #4 |
+| 1 | `Project Safety Contracts` framing | [观点] 叙事强但产品增量弱，更适合后续命名或定位文案 |
+| 2 | `Board Game Setup Tray` | [推论] 是 Profiles 的隐喻版，没有新增结构价值 |
+
+## Session Log
+
+- 2026-04-20: 初始 ideation，6 个候选想法
+- 2026-04-29: #1–#5 已实现并归档；本文档收缩为仅保留未实现项 #6