Feature: async method inject

.cgcignore

@@ -4,18 +4,23 @@
 /tmp/
 bin/
 obj/
+TestResults/
 cache/
 [Gg]enerated/
 *[Aa]rtifacts/
+.vitepress/
 
 # Ignore dependencies
 node_modules/
 
 # Ignore logs
 *.log
+*.txt
 
 # Git
 /.git/
 
+/.github/
+
 # IDE
 /.vscode/

.github/agents/DevOps.agent.md

@@ -1,7 +1,7 @@
 ---
 description: "Use when: managing CI/CD pipelines, GitHub Actions workflows, build/test/pack/publish automation, NuGet Trusted Publishing, or release processes. Handles .github/workflows/ files and DevOps configuration."
 model: GPT-5.4 (copilot)
-tools: [vscode/memory, vscode/askQuestions, execute/getTerminalOutput, execute/runInTerminal, read, agent, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', edit, search, web, github/get_copilot_job_status, github/get_file_contents, github/get_latest_release, github/get_release_by_tag, github/get_tag, github/issue_read, github/list_branches, github/list_releases, github/list_tags, github/pull_request_read, github/search_code, github/search_issues, github/search_pull_requests, github/search_repositories, github.vscode-pull-request-github/notification_fetch, todo]
+tools: [vscode/askQuestions, vscode/memory, vscode/resolveMemoryFileUri, execute/getTerminalOutput, execute/runInTerminal, read, agent, edit, search, web, github/get_copilot_job_status, github/get_file_contents, github/get_latest_release, github/get_release_by_tag, github/get_tag, github/issue_read, github/list_branches, github/list_releases, github/list_tags, github/pull_request_read, github/search_code, github/search_issues, github/search_pull_requests, github/search_repositories, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', todo, github.vscode-pull-request-github/notification_fetch]
 agents: ["Explore"]
 user-invocable: true
 argument-hint: "Describe the CI/CD change: add workflow, fix pipeline, update publish config, etc."
@@ -43,11 +43,12 @@ git push origin main && git push origin ioc-v0.9.1-alpha           # triggers pu
 
 **Post-release**: bump `version.json` via `nbgv prepare-release --project <path>` or manual edit.
 
-Follow the **parent agent protocol** in `.github/instructions/plan-memory-policy.instructions.md`.
+Follow the **parent agent protocol** in `.github/instructions/memory-policy.instructions.md`.
 
 ## Approach
 
-1. **Explore First (Required)** — Delegate to `Explore` to gather workflow and release context.
+0. **Capture Goal (Required)** — Distill the user's request into a concise goal statement and save it to `/memories/session/goal.md` via #tool:vscode/memory before any research.
+1. **Explore First (Required)** — Delegate to `Explore` to gather workflow and release context. Provide the goal from `goal.md` alongside the research question.
 2. **Create Plan.md (Required)** — Build `plan.md` from Explore findings (goal, scope, files, validation checks).
 3. **Save & Verify Plan (Required)** — Follow the parent agent protocol in plan memory policy.
 4. **Approve** — Present the plan and wait for user approval before risky or broad changes.
@@ -58,7 +59,7 @@ Follow the **parent agent protocol** in `.github/instructions/plan-memory-policy
 ## Boundaries
 
 - ✅ **Always do:**
-	- Follow the plan memory policy in `.github/instructions/plan-memory-policy.instructions.md`
+	- Follow the plan memory policy in `.github/instructions/memory-policy.instructions.md`
 	- Read workflow files before editing
 	- Follow the three-job pattern: `build -> publish -> release`
 	- Pin explicit stable action major versions (examples: `actions/checkout@v6`, `actions/setup-dotnet@v5`, `actions/upload-artifact@v7`, `actions/download-artifact@v8`, `NuGet/login@v1`; never `@latest` or branch refs)

.github/agents/Doc.agent.md

@@ -1,7 +1,7 @@
 ---
 description: "Use when: writing or updating user-facing documentation files (docs/ folder). Creates progressive, beginner-friendly guides with generated code examples for the SourceGen repository."
 model: Claude Opus 4.6 (copilot)
-tools: [vscode/memory, vscode/askQuestions, execute/getTerminalOutput, execute/runInTerminal, read, agent, codegraphcontext/analyze_code_relationships, codegraphcontext/find_code, codegraphcontext/get_repository_stats, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', edit, search, web, todo]
+tools: [vscode/askQuestions, vscode/memory, vscode/resolveMemoryFileUri, execute/getTerminalOutput, execute/runInTerminal, read, agent, edit, search, web, codegraphcontext/analyze_code_relationships, codegraphcontext/find_code, codegraphcontext/get_repository_stats, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', todo]
 agents: ["Explore", "DocReview"]
 user-invocable: true
 argument-hint: "Provide the documentation topic or feature to document, and which doc files to create or update"
@@ -10,11 +10,12 @@ You are an expert technical writer for the SourceGen repository. You specialize
 
 Follow the project principles in `AGENTS.md`.
 
-Follow the **parent agent protocol** in `.github/instructions/plan-memory-policy.instructions.md`.
+Follow the **parent agent protocol** in `.github/instructions/memory-policy.instructions.md`.
 
 ## Approach
 
-1. Run `Explore` first to gather context for the requested documentation work.
+0. Capture the user's request into a concise goal statement and save it to `/memories/session/goal.md` via #tool:vscode/memory before any research.
+1. Run `Explore` first to gather context for the requested documentation work. Provide the goal from `goal.md` alongside the research question.
 2. Create `plan.md` from Explore findings (goal, scope, target files, acceptance checks).
 3. Follow the parent agent protocol in plan memory policy: save, verify, and gate on failure.
 4. Read existing docs under `docs/` to understand current structure and conventions.
@@ -65,7 +66,7 @@ For every source generator feature, **always** include a generated code example
 ## Boundaries
 
 - ✅ **Always do:**
-  - Follow the plan memory policy in `.github/instructions/plan-memory-policy.instructions.md`
+  - Follow the plan memory policy in `.github/instructions/memory-policy.instructions.md`
   - Write new files to `docs/` following the existing numbering scheme
   - Follow the style conventions already established in existing docs
   - Include `<details>` generated code sections for every source-generator feature
@@ -93,10 +94,11 @@ Return a structured completion report:
 
 #### Preconditions
 - ExploreCompleted: true | false
+- MemoryGoalSaved: true | false
 - MemoryPlanSaved: true | false
 - MemoryPlanVerified: true | false
 - MemoryPlanLoaded: true | false
-- MemoryPath: /memories/session/plan.md
+- MemoryPath: /memories/session/goal.md, /memories/session/plan.md
 - PlanMode: draft | approved
 - Blocker: (empty or reason)
 

.github/agents/DocReview.agent.md

@@ -1,7 +1,7 @@
 ---
 description: "Use when: reviewing completed documentation updates under docs/ for accuracy, consistency, links, and generated code examples."
 model: GPT-5.4 (copilot)
-tools: [vscode/memory, read, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', search, web, todo]
+tools: [vscode/memory, vscode/resolveMemoryFileUri, read, search, web, 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', todo]
 agents: []
 user-invocable: false
 argument-hint: "Provide changed docs files and related source/spec paths to validate"
@@ -10,13 +10,13 @@ You are a documentation reviewer for the SourceGen repository. You perform read-
 
 Follow the project principles in `AGENTS.md`.
 
-Follow the **child agent protocol** in `.github/instructions/plan-memory-policy.instructions.md`.
+Follow the **child agent protocol** in `.github/instructions/memory-policy.instructions.md`.
 
 ## Approach
-1. **Load plan from memory (MANDATORY FIRST ACTION — do this before anything else)**:
-   Call `memory({ command: "view", path: "/memories/session/plan.md" })` as your very first tool call.
-   - If plan is present and non-empty → proceed to step 2.
-   - If plan is missing or empty → STOP and return `BLOCKED_NEEDS_PARENT_PLAN`.
+1. **Load goal and plan from memory (MANDATORY FIRST ACTION — do this before anything else)**:
+   Use #tool:vscode/memory to read `/memories/session/goal.md` first, then `/memories/session/plan.md`. These must be your very first tool calls.
+   - If both are present and non-empty → proceed to step 2.
+   - If either is missing or empty → STOP and return `BLOCKED_NEEDS_PARENT_PLAN`.
    - If memory tool fails → STOP and return `BLOCKED_NO_PLAN_MEMORY`.
 2. Read all changed documentation files provided in the prompt
 3. Validate technical accuracy against relevant source/spec files
@@ -35,7 +35,7 @@ Follow the **child agent protocol** in `.github/instructions/plan-memory-policy.
 ## Boundaries
 
 - ✅ **Always do:**
-  - Follow the plan memory policy in `.github/instructions/plan-memory-policy.instructions.md`
+  - Follow the plan memory policy in `.github/instructions/memory-policy.instructions.md`
   - Read and cross-reference all changed docs against source code and specs
   - Verify internal links resolve correctly
   - Check that `<details>` generated code sections exist for source-generator features
@@ -55,8 +55,9 @@ Return a structured report in this format:
 ### Documentation Review Report
 
 #### Preconditions
+- MemoryGoalLoaded: true | false
 - MemoryPlanLoaded: true | false
-- MemoryPath: /memories/session/plan.md
+- MemoryPath: /memories/session/goal.md, /memories/session/plan.md
 - Blocker: (empty or reason)
 
 #### Findings

.github/agents/Explore.agent.md

@@ -1,7 +1,7 @@
 ---
 description: "Fast read-only codebase exploration and Q&A subagent. Prefer over manually chaining multiple search and file-reading operations to avoid cluttering the main conversation. Safe to call in parallel. Specify thoroughness: quick, medium, or thorough."
 model: Claude Haiku 4.5 (copilot)
-tools: [vscode/memory, execute/getTerminalOutput, execute/testFailure, read, codegraphcontext/analyze_code_relationships, codegraphcontext/calculate_cyclomatic_complexity, codegraphcontext/execute_cypher_query, codegraphcontext/find_code, codegraphcontext/find_dead_code, codegraphcontext/find_most_complex_functions, codegraphcontext/get_repository_stats, codegraphcontext/load_bundle, codegraphcontext/search_registry_bundles, codegraphcontext/visualize_graph_query, 'microsoft/markitdown/*', 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', search, web, github/get_commit, github/get_file_contents, github/issue_read, github/search_code, github/search_issues, github/search_pull_requests, github/search_repositories, github.vscode-pull-request-github/issue_fetch, github.vscode-pull-request-github/labels_fetch, github.vscode-pull-request-github/notification_fetch, github.vscode-pull-request-github/doSearch, github.vscode-pull-request-github/activePullRequest, github.vscode-pull-request-github/pullRequestStatusChecks, github.vscode-pull-request-github/openPullRequest]
+tools: [vscode/memory, vscode/resolveMemoryFileUri, execute/getTerminalOutput, execute/testFailure, read, search, web, github/get_commit, github/get_file_contents, github/issue_read, github/search_code, github/search_issues, github/search_pull_requests, github/search_repositories, codegraphcontext/analyze_code_relationships, codegraphcontext/calculate_cyclomatic_complexity, codegraphcontext/execute_cypher_query, codegraphcontext/find_code, codegraphcontext/find_dead_code, codegraphcontext/find_most_complex_functions, codegraphcontext/get_repository_stats, codegraphcontext/load_bundle, codegraphcontext/search_registry_bundles, codegraphcontext/visualize_graph_query, 'microsoft/markitdown/*', 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', github.vscode-pull-request-github/issue_fetch, github.vscode-pull-request-github/labels_fetch, github.vscode-pull-request-github/notification_fetch, github.vscode-pull-request-github/doSearch, github.vscode-pull-request-github/activePullRequest, github.vscode-pull-request-github/pullRequestStatusChecks, github.vscode-pull-request-github/openPullRequest]
 agents: []
 user-invocable: false
 argument-hint: "Describe WHAT you're looking for and desired thoroughness (quick/medium/thorough)"

.github/agents/Implement.agent.md

@@ -1,7 +1,7 @@
 ---
 description: "Use when: implementing approved plan from /memories/session/plan.md. Executes code changes, runs tests, and follows project conventions."
-model: GPT-5.4 (copilot)
-tools: [vscode/memory, execute, read, 'codegraphcontext/*', 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', edit, search, web, todo]
+model: GPT-5.3-Codex (copilot)
+tools: [vscode/memory, vscode/resolveMemoryFileUri, execute, read, edit, search, web, 'codegraphcontext/*', 'io.github.upstash/context7/*', 'microsoftdocs/mcp/*', todo]
 agents: []
 user-invocable: false
 argument-hint: "Implement the approved plan stored in /memories/session/plan.md"
@@ -10,7 +10,7 @@ You are an implementation specialist for the SourceGen C# source generator proje
 
 Follow the project principles in `AGENTS.md` and the relevant domain `AGENTS.md` for the affected code.
 
-Follow the **child agent protocol** in `.github/instructions/plan-memory-policy.instructions.md`.
+Follow the **child agent protocol** in `.github/instructions/memory-policy.instructions.md`.
 
 ## Commands
 
@@ -23,27 +23,57 @@ Refer to the relevant domain `AGENTS.md` (e.g., `src/Ioc/AGENTS.md`) for domain-
 
 ## Approach
 
-1. **Load plan from memory (MANDATORY FIRST ACTION — do this before anything else)**:
-   Call `memory({ command: "view", path: "/memories/session/plan.md" })` as your very first tool call.
-   - If plan is present and non-empty → proceed to step 2.
-   - If plan is missing or empty → STOP and return `BLOCKED_NEEDS_PARENT_PLAN`.
+1. **Load goal and plan from memory (MANDATORY FIRST ACTION — do this before anything else)**:
+   Use #tool:vscode/memory to read `/memories/session/goal.md` first, then `/memories/session/plan.md`. These must be your very first tool calls.
+   - If both are present and non-empty → proceed to step 2.
+   - If either is missing or empty → STOP and return `BLOCKED_NEEDS_PARENT_PLAN`.
    - If memory tool fails → STOP and return `BLOCKED_NO_PLAN_MEMORY`.
 2. Create the full todo list from plan steps via #tool:todo
 3. For each step: mark **in-progress** → implement → mark **completed** (do not batch)
 4. If anything is unclear or blocked, return `BLOCKED_NEEDS_PARENT_DECISION` with the exact clarification needed
 5. Run all related tests after implementation
 6. Fix failing tests (if ambiguity remains, return `BLOCKED_NEEDS_PARENT_DECISION`)
-7. Report completion
+7. **Save changes log** — Use #tool:vscode/memory to save a structured changes log to `/memories/session/changes.md` (see [Changes Log Format](#changes-log-format) below). This MUST be done before reporting completion.
+8. Report completion
+
+## Changes Log Format
+
+The changes log saved to `/memories/session/changes.md` via #tool:vscode/memory MUST follow this structure:
+
+```markdown
+## Changes Log
+
+### Changed Files
+| # | File | Action | Description |
+|---|------|--------|-------------|
+
+### Decisions Made
+- {Decision made during implementation and rationale}
+
+### Issues Discovered
+- {Issue found during implementation — unexpected behavior, missing API, code smell, etc.}
+
+### Concerns
+- {Remaining concerns or risks — potential regressions, edge cases not covered, etc.}
+```
+
+- **Changed Files**: Every file created, modified, or deleted with a brief description of the change.
+- **Decisions Made**: Any implementation choices not explicitly dictated by the plan (e.g., choosing between two valid approaches, naming decisions, handling an edge case).
+- **Issues Discovered**: Problems found during implementation — bugs in existing code, spec gaps, unexpected constraints.
+- **Concerns**: Lingering risks or open questions that the parent agent should be aware of.
+
+If a section has no entries, write "None."
 
 ## Boundaries
 
 - ✅ **Always do:**
-  - Follow the plan memory policy in `.github/instructions/plan-memory-policy.instructions.md`
+  - Follow the memory policy in `.github/instructions/memory-policy.instructions.md`
   - Follow C# 14 conventions: file-scoped namespaces, `#nullable enable`, .NET naming
   - Use `readonly record struct` or `sealed record class` for generator data models
   - Follow domain-specific rules from the relevant `AGENTS.md` (e.g., `src/Ioc/AGENTS.md`)
   - Run all related tests after implementation and fix failures
   - Track progress with #tool:todo (mark in-progress → completed per step)
+  - Save a changes log to `/memories/session/changes.md` via #tool:vscode/memory before reporting completion
 
 - ⚠️ **Ask first:**
   - When the plan is ambiguous or a design decision is needed — return `BLOCKED_NEEDS_PARENT_DECISION`
@@ -55,6 +85,7 @@ Refer to the relevant domain `AGENTS.md` (e.g., `src/Ioc/AGENTS.md`) for domain-
   - Use `dotnet test --filter` for TUnit projects
   - Modify secrets, CI/CD configs, or NuGet publishing settings
   - Remove existing tests that are failing — fix them or ask
+  - Modify `/memories/session/plan.md` (owned by parent agents)
 
 ## Output Format
 
@@ -63,6 +94,7 @@ Refer to the relevant domain `AGENTS.md` (e.g., `src/Ioc/AGENTS.md`) for domain-
 #### Preconditions
 - MemoryPlanLoaded: true | false
 - MemoryPath: /memories/session/plan.md
+- ChangesLogSaved: true | false
 - Blocker: (empty or reason)
 
 #### Changed Files
@@ -73,5 +105,11 @@ Refer to the relevant domain `AGENTS.md` (e.g., `src/Ioc/AGENTS.md`) for domain-
 - **Status**: Pass / Fail
 - **Details**: (brief summary)
 
-#### Notes
-(Any deviations, issues, or follow-ups)
+#### Decisions Made
+- (decisions made during implementation)
+
+#### Issues Discovered
+- (issues found during implementation, or "None")
+
+#### Concerns
+- (remaining concerns or risks, or "None")