@vheins/local-memory-mcp 0.9.17 → 0.10.1

package/dist/prompts/project-briefing.md

@@ -11,7 +11,7 @@ Briefing Steps:
 2. **Tasks**: Call `task-list` for `in_progress,pending` tasks.
 3. **Handoffs**: Call `handoff-list` with `status=pending` to surface transfer context. Treat only handoffs with unfinished work, blockers, next owner, or linked task as active.
 4. **Memory**: Call `memory-search` or `memory-recap` for recent decisions, patterns, and mistakes; hydrate important entries with `memory-detail`.
-5. **Standards**: Call `standard-search` with current repo/stack when implementation guidance is needed.
+5. **Standards**: Call `standard-search` with current repo/stack as the mandatory pre-implementation standards check. If no relevant standards are returned, say no applicable standards were found.
 6. **Core Context**: Summarize active task, pending handoffs, applicable standards, and top architectural decisions.
 7. **Priority Reminder**: Treat task priority with MCP semantics: `1=Low`, `2=Normal`, `3=Medium`, `4=High`, `5=Critical`.
 8. **Action**: Propose next steps based on the active queue.

package/dist/prompts/review-and-audit.md

@@ -24,7 +24,7 @@ ONLY call MCP tools. No prose, code, or external plans.
 
 ## 2. PRE-TASK ANALYSIS
 1. **Search**: Call `memory-search` (Hybrid Search). 0.55 similarity threshold.
-2. **Standards**: Call `standard-search` when implementation conventions are relevant.
+2. **Standards**: Call `standard-search` before creating implementation tasks so task scope reflects applicable coding standards. If no relevant standards are returned, note that no applicable standards were found.
 3. **Handoffs**: Call `handoff-list` for pending transfer context related to the target. Treat handoffs as active only when they contain unfinished work, blockers, a next owner, or a linked task.
 4. **De-duplicate**: Call `task-list`. Skip existing/redundant tasks. Link via `parent_id`/`depends_on`.
 

package/dist/prompts/session-planner.md

@@ -11,7 +11,7 @@ Plan execution for: '{{objective}}'.
 
 Steps:
 1. **Orient**: Call `task-list` to avoid duplicate active/backlog work.
-2. **Standards**: Call `standard-search` if the objective touches implementation conventions.
+2. **Standards**: Call `standard-search` for objectives that may lead to code edits, test edits, refactors, migrations, or implementation decisions. If no relevant standards are returned, state that no applicable standards were found.
 3. **Handoffs**: Call `handoff-list` for pending context that may affect sequencing. Stale pending handoffs that only summarize completed work should be closed with `handoff-update`, not planned as queue work.
 4. **Analyze**: Break into 3-7 atomic, verifiable tasks.
 5. **Phase**: Group into `research`, `implementation`, and `validation`.

package/dist/prompts/task-management-guidelines.md

@@ -16,7 +16,7 @@ agent: Project Manager
 ## 2. DETAIL TOOLS
 -   **Tasks**: Call `task-detail` for history/comments (ID or `task_code`).
 -   **Memory**: Call `memory-detail` for full entry content.
--   **Standards**: Call `standard-search` before implementation when coding standards may apply.
+-   **Standards**: Call `standard-search` before any code edit, test edit, refactor, migration, or implementation decision. If no relevant standards are returned, continue and state that no applicable standards were found.
 -   **Handoffs**: Call `handoff-list` to discover pending context transfers before starting a task. Close stale handoffs with `handoff-update` when no concrete next owner, unfinished task, or blocker remains.
 
 ## 3. WORKFLOW

package/dist/prompts/task-memory-executor.md

@@ -27,7 +27,7 @@ agent: Task Executor
 3. **Claim**: Use `task-claim` with `task_code` or `task_id` before implementation.
 4. **Start**: `task-update` status to `in_progress` (MUST transition: `pending` → `in_progress`). Add agent/role metadata.
 5. **Research**: Call `memory-search` (Hybrid Search) and hydrate relevant results with `memory-detail`.
-6. **Standards (MANDATORY PER TASK)**: Call `standard-search` for every task inside the execution loop before implementation, using the task intent plus inferred language/stack/repo as filters. This is required even for decomposed tasks and sub-agent assignments, so each task execution remains aligned with current standards. Apply only relevant standards and hydrate details when needed.
+6. **Standards (MANDATORY PER TASK)**: Call `standard-search` for every task inside the execution loop before any code edit, test edit, refactor, migration, or implementation decision, using the task intent, affected files, inferred language, stack, and repo as filters. This is required even for small tasks, decomposed tasks, and sub-agent assignments. Apply only relevant standards, hydrate details when needed, and if no relevant standards are returned, continue and state that no applicable standards were found.
 7. **Execute**:
    - **Trace**: Inspect logic, call sites, and docs. DO NOT infer from file presence.
    - **Logic**: Implement per description/intent.

package/dist/prompts/tool-usage-guidelines.md

@@ -24,7 +24,7 @@ Use the tools in the same flow exposed by the dashboard: navigate with compact l
 - **Automatic cleanup**: Moving a task to `completed` or `canceled` automatically releases active claims and expires pending handoffs linked to that task.
 
 ## 3. Standards Flow
-- **Search first**: Use `standard-search` to find coding standards by `query`, `language`, `stack`, `repo`, and `is_global`.
+- **Search first**: `standard-search` is mandatory before any code edit, test edit, refactor, migration, or implementation decision. Search by `query`, `language`, `stack`, `repo`, and `is_global`; if no relevant standards are returned, continue and state that no applicable standards were found.
 - **Apply precisely**: Treat standards as implementation rules, not generic documentation summaries.
 - **Store atomically**: Use `standard-store` for one rule per entry with `name`, `content`, `context`, `version`, `language`, `stack`, `tags`, and correct repo/global scope.
 - **Scope**: Prefer repo-specific standards for local conventions; use global standards only for cross-repo rules.

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@vheins/local-memory-mcp",
-	"version": "0.9.17",
+	"version": "0.10.1",
 	"description": "MCP Local Memory Service for coding copilot agents",
 	"mcpName": "io.github.vheins/local-memory-mcp",
 	"type": "module",