create-snipara 1.3.53 → 1.3.55

package/README.md

@@ -195,6 +195,8 @@ snipara-companion workflow start --goal "ship auth hardening" --plan-file ./plan
 snipara-companion workflow phase-start context
 snipara-companion workflow run --mode full --include-session-context --query "load auth context"
 snipara-companion code impact --changed-files src/auth.ts tests/auth.test.ts --diff-summary "auth hardening"
+snipara-companion memory invalidate mem_old --reason "obsolete runbook"
+snipara-companion memory supersede mem_old mem_new --reason "corrected decision"
 snipara-companion workflow phase-commit context --summary "Loaded context and mapped impacted files" --files src/auth.ts
 snipara-companion timeline
 snipara-companion handoff --summary "auth context mapped" --next "implement auth hardening"
@@ -543,7 +545,7 @@ npx create-snipara print-config --json
 When testing a locally packed tarball, use `npm exec --package` instead of `npx`, for example:
 
 ```bash
-npm exec --package ./create-snipara-1.3.14.tgz create-snipara -- --help
+npm exec --package ./create-snipara-1.3.54.tgz create-snipara -- --help
 ```
 
 This avoids `npx` resolution issues with unpublished tarballs.

package/dist/index.js

@@ -13,7 +13,7 @@ import { homedir } from "os";
 // package.json
 var package_default = {
   name: "create-snipara",
-  version: "1.3.53",
+  version: "1.3.55",
   description: "Onboard Snipara Hosted MCP Context + Memory with auth, companion workflows, and optional Snipara Sandbox",
   main: "dist/index.js",
   type: "module",
@@ -1428,7 +1428,7 @@ Agent task lifecycle:
 6. Use whichever structural code graph tools are exposed in the current session
    for callers, imports, neighbors, and path questions. Tool exposure can vary.
 7. On paid Context plans, use \`snipara_code_symbol_card\` for agent-ready symbol
-   context and \`snipara_code_impact\` before risky multi-file changes, PR
+   context and \`snipara-companion code impact\` before risky multi-file changes, PR
    reviews, routes, services, jobs, auth, billing, deployment, schema, migrations,
    or explicit "what is missing" assessments.
 8. Use \`snipara_plan\` or \`snipara_decompose\` only for FULL-mode work and only
@@ -1458,7 +1458,12 @@ Agent task lifecycle:
     End the whole managed workflow with \`snipara-companion final-commit\`.
 16. Use \`snipara_remember_if_novel\` for one reusable memory while avoiding
     duplicates, and use \`snipara_remember\` for explicit direct memory writes.
-17. Do not store secrets, tokens, passwords, private keys, raw logs, transient
+17. When remembered knowledge is obsolete or replaced, use
+    \`snipara-companion memory invalidate <memory-id>\` or
+    \`snipara-companion memory supersede <old-memory-id> <new-memory-id>\`
+    when companion is installed; otherwise use hosted \`snipara_memory_invalidate\`
+    or \`snipara_memory_supersede\`.
+18. Do not store secrets, tokens, passwords, private keys, raw logs, transient
     command output, or unreviewed guesses in memory.
 `;
 }
@@ -1477,8 +1482,8 @@ Use Snipara Hosted MCP before answering project-specific questions.
 - Use \`snipara_context_query\` for source truth and \`snipara_get_chunk\` for exact cited sections.
 - When \`snipara_context_query\` returns \`answer_pack\`, use its facts, caveats, source map, and verification checklist before drafting claims.
 - Use \`snipara_code_callers\`, \`snipara_code_imports\`, \`snipara_code_neighbors\`, or \`snipara_code_shortest_path\` for canonical structural code questions.
-- When local commits or a dirty working tree matter and \`snipara-companion\` is installed, use \`snipara-companion code callers/imports/neighbors/shortest-path/impact\`; it auto-selects hosted MCP or the local overlay and reports \`sourceSelection\`.
-- On paid Context plans, use \`snipara_code_symbol_card\` before editing important symbols and \`snipara_code_impact\` before risky multi-file changes or PR reviews.
+- For code impact and structural code questions, use \`snipara-companion code callers/imports/neighbors/shortest-path/impact\` first when \`snipara-companion\` is installed; it auto-selects hosted MCP for clean indexed code or the local overlay for dirty/ahead worktrees and reports \`sourceSelection\`. Use hosted \`snipara_code_impact\` only when companion is unavailable or after push/reindex for canonical graph impact.
+- On paid Context plans, use \`snipara_code_symbol_card\` before editing important symbols.
 - Check every \`snipara_code_*\` response for indexed commit SHA, indexing time, included files, coverage, and freshness warnings.
 - Use local file reads, \`rg\`, \`git status --short\`, and tests for exact edits/current working tree; use Snipara for architecture and indexed code graph context.
 - When the plan is visible and \`snipara-companion\` is installed, keep the machine plan in JSON, use \`snipara-companion workflow start\`, \`phase-start\`, and \`phase-commit\` per phase, and after \`workflow resume\` rerun \`workflow phase-start\` before editing again.
@@ -1486,6 +1491,7 @@ Use Snipara Hosted MCP before answering project-specific questions.
 - Use Snipara Sandbox only when sandboxed execution or repeatable validation materially helps. For runtime-bound phases, capture compact rehydratable state with \`workflow runtime-checkpoint <phase_id> --summary "<state>" --rehydrate-file <state.json>\`. Then \`workflow resume\` restores workflow and memory continuity plus the recorded Sandbox binding and prints a reattach or rehydrate plan. It does not snapshot or exactly restore a live Snipara Sandbox or REPL process.
 - End substantial work with \`snipara_end_of_task_commit\` when available; for managed workflows, end every phase with \`snipara-companion workflow phase-commit\` and the task with \`snipara-companion final-commit\`.
 - Use \`snipara_remember_if_novel\` or \`snipara_remember\` only for narrow durable memories.
+- When remembered knowledge is obsolete or replaced and \`snipara-companion\` is installed, use \`snipara-companion memory invalidate <memory-id>\` or \`snipara-companion memory supersede <old-memory-id> <new-memory-id>\`; otherwise use hosted \`snipara_memory_invalidate\` or \`snipara_memory_supersede\`.
 - Do not store secrets, one-off command output, raw logs, or unreviewed guesses in memory.
 - Use the Snipara Claude Code plugin only when slash commands, skills, or hooks are helpful; Hosted MCP remains the normal agent path.
 `;
@@ -1508,15 +1514,15 @@ This workspace uses Snipara Hosted MCP for current project context, business/cli
 - When \`snipara_context_query\` returns \`answer_pack\`, use its facts, caveats, source map, and verification checklist before drafting claims.
 - Use \`snipara_get_chunk\` before relying on exact cited wording from reference-based results.
 - Use \`snipara_code_callers\`, \`snipara_code_imports\`, \`snipara_code_neighbors\`, or \`snipara_code_shortest_path\` for canonical structural code questions.
-- When local commits or a dirty working tree matter and \`snipara-companion\` is installed, use \`snipara-companion code callers/imports/neighbors/shortest-path/impact\`; it auto-selects hosted MCP or the local overlay and reports \`sourceSelection\`.
-- On paid Context plans, use \`snipara_code_symbol_card\` before editing important symbols and \`snipara_code_impact\` before risky multi-file changes or PR reviews.
+- For code impact and structural code questions, use \`snipara-companion code callers/imports/neighbors/shortest-path/impact\` first when \`snipara-companion\` is installed; it auto-selects hosted MCP for clean indexed code or the local overlay for dirty/ahead worktrees and reports \`sourceSelection\`. Use hosted \`snipara_code_impact\` only when companion is unavailable or after push/reindex for canonical graph impact.
+- On paid Context plans, use \`snipara_code_symbol_card\` before editing important symbols.
 - Check every \`snipara_code_*\` response for indexed commit SHA, indexing time, included files, coverage, and freshness warnings.
 - Use \`snipara_plan\` or \`snipara_decompose\` only for complex work and only when available.
 - Use local file reads, \`rg\`, \`git status --short\`, and tests for exact code edits and current working-tree state.
 - When \`snipara-companion\` is installed and the LLM has a visible multi-phase plan, keep the machine plan in JSON, use \`snipara-companion workflow start\`, \`phase-start\`, and \`phase-commit\` per phase, and after \`workflow resume\` rerun \`workflow phase-start\` before editing again.
 - Generated hooks can call \`snipara-companion pre-tool\`, \`post-tool\`, and \`stuck-guard status\` so Rescue Packs are runtime-triggered rather than relying only on instructions.
 - Use Snipara Sandbox only when sandboxed execution or repeatable validation materially helps. For runtime-bound phases, capture compact rehydratable state with \`workflow runtime-checkpoint <phase_id> --summary "<state>" --rehydrate-file <state.json>\`. Then \`workflow resume\` restores workflow and memory continuity plus the recorded Sandbox binding and prints a reattach or rehydrate plan. It does not snapshot or exactly restore a live Snipara Sandbox or REPL process.
-- End substantial work with \`snipara_end_of_task_commit\` when available; for managed workflows, end every phase with \`snipara-companion workflow phase-commit\` and the task with \`snipara-companion final-commit\`. Use \`snipara_remember_if_novel\` or \`snipara_remember\` only for narrow durable memories. Never store secrets.
+- End substantial work with \`snipara_end_of_task_commit\` when available; for managed workflows, end every phase with \`snipara-companion workflow phase-commit\` and the task with \`snipara-companion final-commit\`. Use \`snipara_remember_if_novel\` or \`snipara_remember\` only for narrow durable memories. When remembered knowledge is obsolete or replaced, use \`snipara-companion memory invalidate <memory-id>\` or \`snipara-companion memory supersede <old-memory-id> <new-memory-id>\` when companion is installed; otherwise use hosted \`snipara_memory_invalidate\` or \`snipara_memory_supersede\`. Never store secrets.
 `;
 }
 function buildCodexConfigTemplate(answers) {
@@ -2173,7 +2179,7 @@ function getClientGuidance(client) {
       "The generated .snipara/templates/codex-config.toml is a merge-ready snippet for ~/.codex/config.toml if your Codex app does not read project .codex/config.toml.",
       "Use SNIPARA_API_KEY as the only Codex bearer_token_env_var; restart Codex after changing MCP config.",
       "If Codex lazily exposes only a minimal tool set, force discovery for snipara_recall, snipara_context_query, snipara_settings, and the exact htask or swarm tool names you need; use snipara_help(list_all=true) to confirm the hosted catalog before concluding the MCP surface is incomplete.",
-      "When Codex still exposes only the minimal core tools, use snipara-orchestrator swarm-* and htask-* as the primary path for shared queues and multi-agent task work; keep snipara-companion swarm ... and htask ... as the direct hosted fallback when you only need one-off hosted calls."
+      "When Codex still exposes only the minimal core tools, use snipara-orchestrator swarm-* and htask-* as the primary path for shared queues and multi-agent task work."
     ];
   }
   if (client === "gemini") {
@@ -2460,9 +2466,10 @@ ${guidance.map((line) => `- ${line}`).join("\n")}
 
 - Start substantial work with \`snipara_recall\` and \`snipara_context_query\`.
 - Use \`answer_pack\` facts, caveats, source maps, and verification checks before making claims.
-- Use \`snipara_code_symbol_card\` and \`snipara_code_impact\` for important symbols or risky multi-file changes when available.
+- Use \`snipara_code_symbol_card\` for important symbols. For risky multi-file changes, use \`snipara-companion code impact\` first when companion is available; use hosted \`snipara_code_impact\` only when companion is unavailable or after push/reindex for canonical graph impact.
 - Use the installed \`snipara-companion\` binary for low-latency hooks; use \`${COMPANION_NPX_COMMAND}\` for one-off terminal commands when freshness matters.
 - Use a JSON machine plan plus \`snipara-companion workflow start\`, \`phase-start\`, \`phase-commit\`, \`workflow resume\`, and \`final-commit\` for multi-phase work. After \`workflow resume\`, rerun \`workflow phase-start <phase_id>\` before editing again.
+- When remembered knowledge is obsolete or replaced, use \`snipara-companion memory invalidate <memory-id>\` or \`snipara-companion memory supersede <old-memory-id> <new-memory-id>\` when companion is installed; otherwise use hosted \`snipara_memory_invalidate\` or \`snipara_memory_supersede\`.
 - Persist only durable decisions, learnings, preferences, workflows, and troubleshooting outcomes. Never persist secrets.
 `;
 }
@@ -3293,7 +3300,7 @@ function printSuccess(answers, report) {
       "If Codex shows only a minimal Snipara tool set, force discovery for snipara_recall, snipara_context_query, snipara_settings, and any exact htask or swarm tool names you need; confirm the hosted catalog with snipara_help(list_all=true)."
     );
     printNextStep(
-      "If Codex still does not expose the hosted task-routing tools, prefer snipara-orchestrator swarm-* and htask-* for shared queue or multi-agent task work, and keep snipara-companion swarm ... and htask ... as the direct hosted fallback for one-off calls."
+      "If Codex still does not expose the hosted task-routing tools, prefer snipara-orchestrator swarm-* and htask-* for shared queue or multi-agent task work."
     );
   }
   if (answers.aiClient === "mistral") {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-snipara",
-  "version": "1.3.53",
+  "version": "1.3.55",
   "description": "Onboard Snipara Hosted MCP Context + Memory with auth, companion workflows, and optional Snipara Sandbox",
   "main": "dist/index.js",
   "type": "module",