create-snipara 1.3.56 → 2.0.1

package/README.md

@@ -15,12 +15,17 @@ creates or reuses auth, writes Hosted MCP config, and prepares the local project
 so an LLM client can use Snipara context and reviewed memory. Install once with
 `create-snipara`; continue every session with `snipara-companion`.
 
+Use it when the goal is outcome-first agent work: the user asks for judgment,
+implementation, release, or verification, and the agent handles Snipara context,
+workflow state, package checks, Git operations, deployment, and smoke checks
+behind the scenes.
+
 Use it for:
 
-- Hosted MCP onboarding for Claude Code, Cursor, Windsurf, Codex, Gemini, Mistral, VS Code/Copilot, Continue, ChatGPT Desktop, and similar clients
+- Hosted MCP onboarding for Claude Code, Cursor, Windsurf, Codex, Gemini, Mistral, VS Code/Copilot, Continue, ChatGPT Desktop, Orca-style MCP clients, LM Studio-backed local stacks, and similar clients
 - free account signup with reviewed Context + Memory
 - local project wiring, `doctor`, `repair`, and `upgrade`
-- GitHub repository sync and PR Answer Packs approval when the current folder is a GitHub repo
+- local source activation without GitHub, plus optional GitHub repository sync and PR Answer Packs approval when the current folder is a GitHub repo
 
 ## Why It Exists
 
@@ -34,7 +39,7 @@ flowchart LR
     CLI --> Auth["Snipara auth and project key"]
     CLI --> MCP["Hosted MCP config"]
     CLI --> Templates["AGENTS.md, CLAUDE.md, Cursor, Codex, MCP references"]
-    MCP --> Agents["Claude Code, Cursor, Codex, Gemini, Mistral, VS Code, ChatGPT"]
+    MCP --> Agents["Claude Code, Cursor, Codex, Gemini, Mistral, VS Code, ChatGPT, Orca, LM Studio stacks"]
     Templates --> Agents
     Agents --> Context["Snipara context and memory"]
 ```
@@ -77,7 +82,7 @@ Free onboarding is now **Context + Memory**, not Context-only:
 
 - Context Free: three projects and 1,000 context queries/month
 - Memory Free: reviewed hosted memories for continuity across sessions
-- Hosted MCP: direct connection for Claude Code, Cursor, Windsurf, Codex, Gemini, Mistral, VS Code/Copilot, Continue, ChatGPT Desktop, and other MCP clients
+- Hosted MCP: direct connection for Claude Code, Cursor, Windsurf, Codex, Gemini, Mistral, VS Code/Copilot, Continue, ChatGPT Desktop, Orca-style MCP clients, LM Studio-backed local stacks, and other MCP clients
 
 The CLI opens a browser device-flow login when the user does not already have a key, auto-provisions the free Context + Memory account when needed, then writes the returned API key into the local MCP config.
 
@@ -102,6 +107,7 @@ That distinction matters:
 - opens the browser device-flow free Context + Memory account flow when needed
 - writes Hosted MCP configuration
 - detects a GitHub remote and can open the Snipara GitHub App automation path
+- activates the current folder locally through `snipara-companion source init` so docs and code overlay context are available before GitHub approval
 - explains the GitHub PR Answer Packs path for AI-assisted pull request workflows
 - installs `snipara-companion` by default for local status, briefs, timelines,
   phase commits, handoffs, resume, and managed workflows
@@ -129,6 +135,7 @@ That distinction matters:
 Keep the package roles simple:
 
 - `create-snipara` = connect the user to Hosted MCP Context + Memory
+- `snipara-companion source init` = automatic local source snapshot, document dry-run, and local code overlay without GitHub
 - `create-snipara --github` = connect the current GitHub repository through the browser approval flow for repository sync and PR Answer Packs
 - `snipara-openclaw-install` = OpenClaw-only wrapper for Hosted MCP config plus OpenClaw env and hook setup
 - `snipara-business` = prepare business context from local or mounted folders
@@ -190,6 +197,8 @@ the human-facing contract.
 
 ```bash
 snipara-companion status
+snipara-companion source init .
+snipara-companion source sync --json
 snipara-companion brief --task "ship auth hardening" --changed-files src/auth.ts
 snipara-companion workflow start --goal "ship auth hardening" --plan-file ./plan.json
 snipara-companion workflow phase-start context
@@ -206,6 +215,20 @@ snipara-companion workflow run --mode full --include-session-context --query "im
 snipara-companion final-commit --summary "Shipped auth hardening and tests" --files src/auth.ts tests/auth.test.ts
 ```
 
+### Local source first
+
+For free users, the first useful source step does not need GitHub approval:
+
+```bash
+snipara-companion source init .
+snipara-companion source status --json
+```
+
+That creates `.snipara/source/latest.json`, previews supported document sync,
+and refreshes `.snipara/code-overlay/latest.json` from local files. GitHub
+automation is still the canonical hosted repository path for teams, PR Answer
+Packs, and shared CODE indexing after the user approves the provider.
+
 ## Main Commands
 
 ### Install or initialize

package/dist/index.js

@@ -13,7 +13,7 @@ import { homedir } from "os";
 // package.json
 var package_default = {
   name: "create-snipara",
-  version: "1.3.56",
+  version: "2.0.1",
   description: "Onboard Snipara Hosted MCP Context + Memory with auth, companion workflows, and optional Snipara Sandbox",
   main: "dist/index.js",
   type: "module",
@@ -48,6 +48,8 @@ var package_default = {
     "windsurf",
     "gemini",
     "mistral",
+    "orca",
+    "lm-studio",
     "vscode",
     "continue",
     "claude-desktop"
@@ -90,7 +92,7 @@ var API_URL = "https://api.snipara.com";
 var COMPANION_PACKAGE_NAME = "snipara-companion";
 var COMPANION_COMMAND_NAME = "snipara-companion";
 var COMPANION_NPX_COMMAND = "npx -y snipara-companion@latest";
-var MIN_COMPANION_VERSION = "1.3.0";
+var MIN_COMPANION_VERSION = "3.0.0";
 var GITHUB_ANSWER_PACKS_LABEL = "GitHub PR Answer Packs";
 var MCP_PACKAGE_NAME = "snipara-mcp";
 var SANDBOX_PACKAGE_NAME = "snipara-sandbox[all]";
@@ -101,6 +103,17 @@ var SANDBOX_COMMAND_NAME = "snipara-sandbox";
 var LEGACY_SANDBOX_COMMAND_NAME = "rlm";
 var ORCHESTRATOR_COMMAND_NAME = "snipara-orchestrator";
 var DEVICE_CLIENT_ID = "create-snipara";
+var EXPERIENCE_GOAL_SECTION = `## Experience Goal
+
+The target experience is outcome-first agent work across supported clients:
+Codex, Claude Code, Cursor, Orca, LM Studio-backed local stacks, or another
+MCP-capable environment. The user should be able to state an outcome, ask for
+engineering judgment, or request a release while the agent handles Snipara
+context retrieval, workflow state, verification, package checks, Git operations,
+deployment, and production smoke checks behind the scenes. Surface important
+decisions, blockers, and evidence, but do not make the user manually orchestrate
+routine Snipara or release mechanics.`;
+var UNIVERSAL_CLIENT_GUIDANCE = "The target experience is outcome-first: the user can ask for engineering judgment or a release, and the agent should use Snipara context, workflow state, verification, package checks, Git, deploy, and smoke checks without making the user orchestrate routine mechanics.";
 var DeviceAuthorizationAborted = class extends Error {
 };
 var AI_CLIENT_CHOICES = [
@@ -529,6 +542,7 @@ function printBanner() {
 \u2551                                                                       \u2551
 \u2551   \u2022 Hosted MCP for LLM agents                                         \u2551
 \u2551   \u2022 Free account path with hosted context and reviewed memory         \u2551
+\u2551   \u2022 Local source activation before GitHub approval                    \u2551
 \u2551   \u2022 API / SDK for product integrations                                \u2551
 \u2551   \u2022 Optional local companion and Snipara Sandbox helpers              \u2551
 \u2551   \u2022 One CLI for auth, config, doctor, repair, and upgrade             \u2551
@@ -1413,6 +1427,8 @@ This project uses Snipara Hosted MCP for project context and reviewed memory.
   \`snipara-companion task-commit\` as the reliable local fallback, then restart
   or reload Codex after MCP config changes.
 
+${EXPERIENCE_GOAL_SECTION}
+
 Agent task lifecycle:
 
 1. Start every new thread by validating hosted MCP availability, then use
@@ -1478,6 +1494,9 @@ Use Snipara Hosted MCP before answering project-specific questions.
 
 - Endpoint: \`${buildHostedMcpEndpoint(answers)}\`
 - If a session exposes only a subset of expected Snipara tools, call \`snipara_help(list_all=true)\` before concluding a tool is unavailable.
+
+${EXPERIENCE_GOAL_SECTION}
+
 - Start substantial work with \`snipara_recall\` and a targeted \`snipara_context_query\`.
 - 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.
@@ -1509,6 +1528,9 @@ This workspace uses Snipara Hosted MCP for current project context, business/cli
 - Check the configured Snipara MCP server before answering project-specific questions.
 - If a session exposes only a subset of expected Snipara tools, call \`snipara_help(list_all=true)\` before concluding a tool is unavailable.
 - Endpoint: \`${buildHostedMcpEndpoint(answers)}\`
+
+${EXPERIENCE_GOAL_SECTION}
+
 - Use \`snipara_recall\` for durable decisions, preferences, and validated learnings.
 - Use \`snipara_context_query\` for docs, business context, current client/project truth, and narrative source material.
 - When \`snipara_context_query\` returns \`answer_pack\`, use its facts, caveats, source map, and verification checklist before drafting claims.
@@ -2228,6 +2250,24 @@ function getClientGuidance(client) {
 function getCompanionCommands(answers) {
   const projectFlag = answers.projectSlug ? ` --project ${answers.projectSlug}` : "";
   const clientFlag = getCompanionInitClientFlag(answers.aiClient);
+  const localSourceCommands = answers.installCompanion ? [
+    {
+      title: "Activate this folder locally",
+      command: `${COMPANION_NPX_COMMAND} source init .`,
+      purpose: "Create a local source snapshot, preview supported document sync, and build a local code overlay without GitHub."
+    },
+    {
+      title: "Refresh local source context",
+      command: `${COMPANION_NPX_COMMAND} source sync --json`,
+      purpose: "Refresh the local snapshot, document dry-run, and code overlay cache after files change."
+    }
+  ] : [
+    {
+      title: "Enable local source activation",
+      command: "npx create-snipara repair --with-companion",
+      purpose: `Install ${COMPANION_PACKAGE_NAME} so this project can run ${COMPANION_NPX_COMMAND} source init without GitHub.`
+    }
+  ];
   const businessOnboardingCommands = answers.installCompanion ? [
     {
       title: "Preview a business folder import",
@@ -2271,6 +2311,7 @@ function getCompanionCommands(answers) {
       command: "create-snipara repair",
       purpose: "Rebuild config files, hooks, and the companion pack."
     },
+    ...localSourceCommands,
     {
       title: "Run a focused hosted query",
       command: `${COMPANION_NPX_COMMAND} query --query "how does auth middleware work?" --max-tokens 4000`,
@@ -2477,7 +2518,7 @@ async function createCompanionPack(answers) {
   console.log(chalk.bold("\n\u{1F5C2}\uFE0F  Generating Companion Pack\n"));
   const packDir = path.join(process.cwd(), ".snipara", "companion");
   const commands = getCompanionCommands(answers);
-  const guidance = getClientGuidance(answers.aiClient);
+  const guidance = [UNIVERSAL_CLIENT_GUIDANCE, ...getClientGuidance(answers.aiClient)];
   const detection = detectEnvironment();
   const clientPackFilename = getClientPackFilename(answers.aiClient);
   fs.mkdirSync(packDir, { recursive: true });
@@ -2527,7 +2568,29 @@ Apply only after reviewing the manifest:
 
 \`npx create-snipara repair --with-companion\``}
 
-For source-code repositories, use the GitHub OAuth/code onboarding path instead of \`onboard-folder\`.
+## Local Source Activation
+
+Use this first when the user has not connected GitHub yet, or when the folder has no Git metadata.
+It creates a local source snapshot, previews supported document sync, and refreshes the local code
+overlay cache that agents can query immediately.
+
+${answers.installCompanion ? `Activate the current folder:
+
+\`${COMPANION_NPX_COMMAND} source init .\`
+
+Refresh after file changes:
+
+\`${COMPANION_NPX_COMMAND} source sync --json\`
+
+Inspect local drift:
+
+\`${COMPANION_NPX_COMMAND} source status --json\`` : `This setup did not install snipara-companion. Enable it before local source activation:
+
+\`npx create-snipara repair --with-companion\``}
+
+GitHub automation remains useful after first value: it gives Snipara a canonical hosted repository
+sync and PR Answer Packs. Local source activation is the fallback, not a replacement for explicit
+provider approval when a team wants shared hosted code context.
 
 ## GitHub PR Answer Packs
 
@@ -3320,6 +3383,7 @@ function printSuccess(answers, report) {
     printNextStep(
       `${COMPANION_COMMAND_NAME} ${MIN_COMPANION_VERSION}+ is installed for low-latency local hooks.`
     );
+    printNextStep(`Activate local source context now with: ${COMPANION_NPX_COMMAND} source init .`);
     printNextStep(
       `Use ${COMPANION_NPX_COMMAND} recall / query / plan / upload / task-commit for explicit local workflows and as a fallback when an AI client exposes only a partial MCP surface.`
     );

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-snipara",
-  "version": "1.3.56",
+  "version": "2.0.1",
   "description": "Onboard Snipara Hosted MCP Context + Memory with auth, companion workflows, and optional Snipara Sandbox",
   "main": "dist/index.js",
   "type": "module",
@@ -35,6 +35,8 @@
     "windsurf",
     "gemini",
     "mistral",
+    "orca",
+    "lm-studio",
     "vscode",
     "continue",
     "claude-desktop"