create-snipara 2.1.0 → 2.1.1

package/README.md

@@ -6,6 +6,10 @@
 with project-owned context, reviewed memory, shared guidance, and optional code
 impact tooling instead of starting cold every session.
 
+The shortest path is three moments: connect the folder your agent already uses,
+let Snipara index its project context, then ask one question that only the
+project can answer.
+
 ```bash
 npx create-snipara
 ```

package/dist/index.js

@@ -14,7 +14,7 @@ import { homedir } from "os";
 // package.json
 var package_default = {
   name: "create-snipara",
-  version: "2.1.0",
+  version: "2.1.1",
   description: "Onboard Snipara Cloud or self-hosted MCP with an automatic project-grounded proof of value",
   main: "dist/index.js",
   type: "module",
@@ -98,7 +98,7 @@ var COMPANION_PACKAGE_NAME = "snipara-companion";
 var COMPANION_COMMAND_NAME = "snipara-companion";
 var COMPANION_NPX_COMMAND = "npx -y snipara-companion@latest";
 var CREATE_SNIPARA_NPX_COMMAND = "npx -y create-snipara@latest";
-var MIN_COMPANION_VERSION = "3.0.0";
+var MIN_COMPANION_VERSION = "3.8.0";
 var GITHUB_ANSWER_PACKS_LABEL = "GitHub PR Answer Packs";
 var MCP_PACKAGE_NAME = "snipara-mcp";
 var SANDBOX_PACKAGE_NAME = "snipara-sandbox[all]";
@@ -3510,8 +3510,7 @@ Agent task lifecycle:
     commit SHA, indexing time, included file sample, coverage, freshness warnings,
     and sync guidance before relying on it. If \`git status --short\` is dirty,
     warn that the indexed graph may not include local edits.
-12. Use Snipara Sandbox only when sandboxed execution, repeatable validation, or
-    isolated transformations materially help.
+12. Before executable repository tests, probe the required Snipara Sandbox capabilities using \`validation gate\` with an explicit request and workflow/lot scope. If absent, inaccessible or incompatible, ask the user to choose another test environment, install/configure Sandbox, or continue without Sandbox (local tests versus no tests). Never fall back silently or treat no response as approval; preserve the scoped choice and proof limits across resume. Static reads and documentation do not require a container.
 13. If a broad query is slow, retry once with a narrow keyword query before
     falling back to local search.
 14. When generated hooks are enabled, \`snipara-companion pre-tool\`, \`post-tool\`,
@@ -3562,7 +3561,7 @@ ${EXPERIENCE_GOAL_SECTION}
 - If a broad query is slow, retry once with a narrow keyword query before falling back to local search.
 - 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.
 - If generated hooks are enabled, \`snipara-companion pre-tool\`, \`post-tool\`, and \`stuck-guard status\` provide runtime Rescue Pack checks when the agent loops on failures or empty searches.
-- 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.
+- Before executable repository tests, run \`validation gate\` with an explicit request and workflow/lot scope. If unavailable or incompatible, ask the user to choose another environment, install/configure Sandbox, or continue without Sandbox (local tests versus no tests). Never fall back silently or infer approval. Preserve the scoped choice and proof requirements across resume. 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\`.
@@ -3603,7 +3602,7 @@ ${EXPERIENCE_GOAL_SECTION}
 - If a broad query is slow, retry once with a narrow keyword query before falling back to local search.
 - 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.
+- Before executable repository tests, run \`validation gate\` with an explicit request and workflow/lot scope. If unavailable or incompatible, ask the user to choose another environment, install/configure Sandbox, or continue without Sandbox (local tests versus no tests). Never fall back silently or infer approval. Preserve the scoped choice and proof requirements across resume. 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, 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.
 `;
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-snipara",
-  "version": "2.1.0",
+  "version": "2.1.1",
   "description": "Onboard Snipara Cloud or self-hosted MCP with an automatic project-grounded proof of value",
   "main": "dist/index.js",
   "type": "module",